Moved example configuration from docs/examples/ to top-level examples/

.gitignore

@@ -2,6 +2,8 @@
 .codex
 AGENTS.md
 
+.DS_Store
+
 # ---> Go
 # If you prefer the allow list template instead of the deny list, see community template:
 # https://github.com/github/gitignore/blob/main/community/Golang/Go.AllowList.gitignore
@@ -22,6 +24,9 @@ AGENTS.md
 # Dependency directories (remove the comment below to include it)
 # vendor/
 
+# Go cache
+.gocache
+
 # Go workspace file
 go.work
 go.work.sum

README.md

@@ -1,279 +1,22 @@
 # narratio
 
-`narratio` is a Go orchestration application for processing D&D session audio into transcripts and generated artifacts.
+Narratio is a Go orchestration application that turns D&D session audio into polished transcripts and generated session artifacts.
 
-## Current Implementation
-
-Implemented now:
-
-- strict config loading/validation (`pipeline.yml` and `session.yml`)
-- local workspace/session layout, locking, and manifest persistence
-- resumable stage control (`run`, `plan`, `resume`, `run-stage`, `status`)
-- real `prepare`, `transcribe`, `merge`, `polish`, `normalize`, `trim`, and `analyze` stages
-- real WhisperX, Seriatim, and Audita adapters
-- real Scriptorium subprocess adapter
-- optional Scriptorium render diagnostics (`render_debug`)
-
-Not implemented yet:
-
-- `archive` stage behavior
-- `notify` stage behavior
-- additional analyze artifacts beyond `session_recap`
-- generic DAG orchestration
-
-## Config Files
-
-Narratio expects two YAML files:
-
-- `pipeline.yml`: pipeline/workspace settings
-- `session.yml`: per-session settings
-
-YAML decoding is strict (`KnownFields(true)`), so unknown fields fail fast.
-
-## Canonical Stage Order
-
-1. `prepare`
-2. `transcribe`
-3. `merge`
-4. `polish`
-5. `normalize`
-6. `trim`
-7. `analyze`
-8. `archive`
-9. `notify`
-
-## Transcript Tiers
-
-- `transcripts/merged.json`: canonical deterministic merged transcript from Seriatim merge
-- `transcripts/processed.json`: full raw Audita-polished transcript output
-- `transcripts/normalized.json`: Seriatim-normalized transcript from the normalize stage
-- `transcripts/trimmed.json`: gameplay-only normalized polished transcript from trim stage
-
-## Normalize Configuration
-
-`pipeline.normalize` is optional. When omitted, Narratio defaults to:
-
-- `output_path: transcripts/normalized.json`
-- `output_schema: seriatim-intermediate`
-- `report: true`
-
-Allowed `normalize.output_schema` values:
-
-- `seriatim-minimal`
-- `seriatim-intermediate`
-- `seriatim-full`
-
-`normalize.output_path` is treated as session-workdir-relative when not absolute.
-
-Normalize stage behavior summary:
-
-- normalize runs after `polish` and before `trim`
-- normalize resolves `transcripts/processed.json`
-- normalize runs Seriatim `normalize` to produce `transcripts/normalized.json`
-- normalize diagnostics are written to:
-  - `artifacts/seriatim.normalize.report.json` (when enabled)
-  - `logs/seriatim.normalize.stdout.log`
-  - `logs/seriatim.normalize.stderr.log`
-  - `config/seriatim.normalize.generated.yml`
-
-## Trim Configuration
-
-`pipeline.trim` is optional. If omitted, no trim config is loaded. If `trim.enabled` is omitted, it defaults to `false`.
-
-When `trim.enabled: true`:
-
-- `trim.output_path` is required
-- `trim.bounds.prompt_id` is required
-- `trim.bounds.transcript_input_name` is required
-- `trim.bounds.output_path` is required
-- `trim.bounds.timeout` must be a valid Go duration when provided
-- `trim.bounds.render_debug: true` requires `trim.bounds.render_output_path`
-- `trim.bounds.profile_id` may be empty to use the prompt default profile
-
-Trim paths are treated as session-workdir-relative when not absolute.
-
-Example trim config:
-
-```yaml
-trim:
-  enabled: true
-  output_path: "transcripts/trimmed.json"
-  bounds:
-    prompt_id: "dnd_session.bounds"
-    profile_id: ""
-    transcript_input_name: "transcript"
-    output_path: "artifacts/session_bounds.json"
-    timeout: "10m"
-    render_debug: false
-    render_output_path: "artifacts/session_bounds.render.json"
-  seriatim:
-    report: false
-```
-
-Trim behavior summary:
-
-- trim discovers and validates `transcripts/normalized.json`
-- trim uses Scriptorium bounds (`dnd_session.bounds` by example config) to produce `artifacts/session_bounds.json`
-- bounds IDs are validated against the same normalized transcript ID space that Seriatim trim will consume
-- trim converts bounds to Seriatim keep selector (for example `10-868`) and runs Seriatim trim
-- if trim is disabled, Narratio copies normalized transcript to trimmed transcript and records `trim_action=copy_disabled`
-
-Trim outputs and diagnostics:
-
-- `artifacts/session_bounds.json`
-- `transcripts/trimmed.json`
-- `logs/scriptorium.bounds.stdout.log`
-- `logs/scriptorium.bounds.stderr.log`
-- `config/scriptorium.bounds.generated.yml`
-- `logs/seriatim.trim.stdout.log`
-- `logs/seriatim.trim.stderr.log`
-- `config/seriatim.trim.generated.yml`
-- optional bounds render-debug outputs:
-  - `artifacts/session_bounds.render.json`
-  - `logs/scriptorium.bounds.render.stdout.log`
-  - `logs/scriptorium.bounds.render.stderr.log`
-  - `config/scriptorium.bounds.render.generated.yml`
-
-Render-debug files are diagnostics and are not treated as canonical stage output artifact refs.
-
-## Scriptorium Configuration
-
-`pipeline.scriptorium` is optional. When present, Narratio validates and uses it for analyze-stage artifact generation.
-
-Key points:
-
-- `scriptorium.binary` is required when section is present
-- `scriptorium.config_path` is optional
-- `scriptorium.timeout` defaults to `10m` when omitted
-- `scriptorium.render_debug` enables render diagnostics globally
-- artifacts are configured under `scriptorium.artifacts` (map shape supports multiple artifacts)
-- enabled artifacts require `prompt_id` and `output_path`
-- artifact `render_debug` may override global render setting
-- `vars` currently support boolean and string values
-
-Example `session_recap` artifact definition:
-
-```yaml
-scriptorium:
-  binary: "scriptorium"
-  config_path: "/etc/scriptorium/config.yml"
-  timeout: "10m"
-  render_debug: false
-
-  artifacts:
-    session_recap:
-      enabled: true
-      prompt_id: "dnd.session_recap"
-      profile_id: "local-quality" # optional
-      output_path: "artifacts/session_recap.md"
-      timeout: "10m"
-      # render_debug: true # optional per-artifact override
-
-      inputs:
-        transcript:
-          source: "trimmed_transcript"
-          required: true
-
-        previous_recap:
-          source: "previous_session_artifact"
-          artifact: "session_recap"
-          path: "" # optional; set when available
-          required: false
-
-      vars:
-        session_id: true
-        session_date: true
-        campaign_name: true
-        previous_session_id: true
-        output_kind: "session_recap"
-```
-
-Prompt IDs and profile IDs are configuration values. They are not hardcoded in analyze-stage logic.
-
-Do not put secrets in `pipeline.yml`. If API-key behavior is configured, use env var names only.
-
-## Scriptorium Runtime Behavior
-
-Narratio integrates with Scriptorium through the public CLI subprocess contract:
-
-- generation: `scriptorium run`
-- diagnostics/testing: `scriptorium render --format json` when `render_debug` is enabled
-
-For the initial implementation, only `session_recap` generation is supported.
-
-Analyze-stage session recap behavior:
-
-- available transcript input sources for configured artifacts: `processed_transcript`, `normalized_transcript`, `trimmed_transcript`
-- session recap should use gameplay-only transcript input (`source: trimmed_transcript`)
-- Narratio resolves `trimmed_transcript` from trim manifest output (`transcript_trimmed`) or fallback `transcripts/trimmed.json`
-- Narratio resolves `normalized_transcript` from normalize manifest output (`transcript_normalized`) or fallback `transcripts/normalized.json`
-- missing trimmed transcript fails clearly and advises running trim stage first
-- `normalized_transcript` is the preferred full-transcript source for future table/meta-analysis artifacts
-- `processed_transcript` remains supported for advanced/debug use cases
-- optionally includes `previous_recap` when configured and resolvable
-- omits optional previous recap when unavailable
-- fails if required inputs are missing
-- validates output file exists and is non-empty
-
-Expected session output paths:
-
-- `artifacts/session_recap.md`
-- `logs/scriptorium.session_recap.stdout.log`
-- `logs/scriptorium.session_recap.stderr.log`
-- `config/scriptorium.session_recap.generated.yml`
-- `artifacts/session_recap.render.json` when render diagnostics are enabled
-
-## Examples
-
-Starter files:
-
-- `examples/pipeline.minimal.yml`
-- `examples/session.minimal.yml`
-- `examples/speakers.yml`
-
-## Commands
-
-Run tests:
+It coordinates transcription, merge/polish/normalize/trim processing, artifact generation, archive publishing, and resumable run state in one operator workflow.
 
 ```bash
-go test ./...
+narratio run --session-id 2026-04-04
 ```
 
-Plan a run:
+This command requires discoverable `pipeline.yml` and `session.yml` files (or explicit `--config` and `--session` flags).
 
-```bash
-go run ./cmd/narratio plan --config examples/pipeline.minimal.yml --session examples/session.minimal.yml
-```
+## Documentation
 
-Run full pipeline:
-
-```bash
-go run ./cmd/narratio run --config examples/pipeline.minimal.yml --session examples/session.minimal.yml
-```
-
-Run analyze only:
-
-```bash
-go run ./cmd/narratio run-stage --config examples/pipeline.minimal.yml --session examples/session.minimal.yml analyze
-```
-
-## Operational Note
-
-Checksum-based stale detection is not implemented yet.
-
-If prepared inputs or prompt/runtime config change, rerun the appropriate upstream stages before relying on downstream artifacts.
-
-Examples:
-
-- glossary/autocorrect/speaker-context changes: rerun at least `merge`, `polish`, `normalize`, `trim`, and `analyze`
-- trim bounds prompt/profile/config changes: rerun at least `normalize`, `trim`, and `analyze`
-- session recap prompt/profile/input-source changes: rerun `analyze`
-
-## Roadmap
-
-Near-term roadmap:
-
-- extend analyze to additional configured artifacts
-- support workflows where later artifacts consume earlier generated artifacts
-- keep orchestration explicit without a generic DAG engine
-- implement archive and notify backends
+- [Configuration](docs/config.md)
+- [CLI Reference](docs/cli.md)
+- [Operations and Recovery](docs/operations.md)
+- [Troubleshooting](docs/troubleshooting.md)
+- [Development Guide](docs/development.md)
+- [Architecture Principles](docs/architecture.md)
+- [Internal Component Contracts](docs/internal/README.md)
+- [Config Examples](examples/)

architecture.md

@@ -1,316 +0,0 @@
-# Narratio Architecture
-
-## 1. Purpose
-
-`narratio` is a Go orchestrator for D&D session processing. It runs a stage-based local pipeline from audio input through transcript processing and artifact generation, with manifest-based skip/force/resume behavior.
-
-Narratio integrates with Scriptorium through the **public CLI** (`scriptorium run` and `scriptorium render`) via synchronous subprocess execution.
-
-## 2. Current Status
-
-Implemented:
-
-- strict `pipeline.yml` + `session.yml` loading with strict YAML field checking (`KnownFields(true)`)
-- local workspace/session layout, lock file handling, artifact path helpers, checksums, and atomic writes
-- manifest store and stage status transitions for resumable runs
-- real `prepare`, `transcribe`, `merge`, and `polish` stages
-- real WhisperX HTTP adapter
-- real Seriatim subprocess adapter
-- real Audita subprocess adapter
-- real Scriptorium subprocess adapter
-- real `normalize` stage producing `transcripts/normalized.json`
-- real `trim` stage producing `transcripts/trimmed.json`
-- real `analyze` stage for initial `session_recap` generation
-- optional Scriptorium render diagnostics (`render_debug`) before production run
-
-Still placeholder/future:
-
-- `archive` stage behavior
-- `notify` stage behavior
-- additional Scriptorium artifact types beyond `session_recap`
-- artifact-to-artifact workflows beyond the initial single-artifact implementation
-- generic stale detection based on input/config checksums
-
-## 3. Pipeline and Stage Boundaries
-
-Canonical stage order:
-
-1. `prepare`
-2. `transcribe`
-3. `merge`
-4. `polish`
-5. `normalize`
-6. `trim`
-7. `analyze`
-8. `archive`
-9. `notify`
-
-Boundary rules:
-
-- orchestration logic lives in `internal/app`
-- stage business logic lives in `internal/stage`
-- external-tool CLI construction lives in adapter packages
-- Scriptorium CLI details stay in `internal/adapters/scriptorium`
-
-## 4. Scriptorium Integration Model
-
-Integration mode:
-
-- public CLI subprocesses only (no Scriptorium internal Go packages, no HTTP API)
-- production generation uses `scriptorium run`
-- diagnostics/testing render uses `scriptorium render --format json`
-
-Run invocation shape used by adapter:
-
-```bash
-scriptorium run --prompt <prompt_id> --input name=path --out <output_path>
-```
-
-Optional flags passed when configured:
-
-- `--config <path>`
-- `--profile <profile_id>`
-- repeated `--var name=value`
-- repeated `--input name=path`
-- `--timeout <duration>`
-- `--api-key-env <ENV_NAME>` when configured
-
-Render invocation shape used by adapter:
-
-```bash
-scriptorium render --prompt <prompt_id> --input name=path --format json --out <render_output_path>
-```
-
-Adapter behavior:
-
-- always passes `--out`
-- captures stdout/stderr separately
-- writes generated invocation metadata YAML (redacted, no secrets)
-- treats exit code `0` as success
-- treats exit code `1` as failure
-- treats exit code `2` as failure with `validation_failed=true` and preserves output metadata when available
-- validates successful output files exist and are non-empty
-- does not treat non-empty stderr as failure by itself
-
-## 5. Configuration Contract
-
-`pipeline.scriptorium` is optional. Existing pipelines without Scriptorium continue to work.
-
-`pipeline.trim` is optional. Existing pipelines without trim config continue to work.
-
-`pipeline.normalize` is optional. Existing pipelines without normalize config continue to work.
-
-When `pipeline.normalize` is omitted, defaults are applied:
-
-- `output_path: transcripts/normalized.json`
-- `output_schema: seriatim-intermediate`
-- `report: true`
-
-When `pipeline.normalize` is present:
-
-- `output_path` must be non-empty
-- `output_schema` must be one of `seriatim-minimal`, `seriatim-intermediate`, or `seriatim-full`
-- relative `output_path` values are session-workdir-relative paths
-- Seriatim binary settings still come from `pipeline.seriatim`
-
-When `pipeline.trim` is present:
-
-- `enabled` is optional and defaults to `false` when omitted
-- relative `output_path`, `bounds.output_path`, and `bounds.render_output_path` values are session-workdir-relative paths
-- do not store secrets in trim config values
-
-When `pipeline.trim.enabled: true`:
-
-- `output_path` is required and non-empty
-- `bounds.prompt_id` is required and non-empty
-- `bounds.transcript_input_name` is required and non-empty
-- `bounds.output_path` is required and non-empty
-- `bounds.timeout` must parse as a Go duration when provided
-- `bounds.render_debug: true` requires non-empty `bounds.render_output_path`
-- `bounds.profile_id` may be empty to use the prompt default profile
-- prompt IDs are config values, not hardcoded stage logic
-
-When `pipeline.scriptorium` is present:
-
-- `binary` is required and non-empty
-- `config_path` is optional; when provided it must be non-empty
-- `timeout` is optional; when provided it must parse as a Go duration
-- default `timeout` is `10m`
-- unknown YAML fields fail strict decode
-
-Artifacts are configured as a map under `pipeline.scriptorium.artifacts` so multiple artifacts are possible in the config shape.
-
-For each artifact definition:
-
-- `enabled: true` requires non-empty `prompt_id`
-- `enabled: true` requires non-empty `output_path`
-- `timeout` must parse as Go duration when present
-- optional per-artifact `render_debug` may override global `scriptorium.render_debug`
-- `inputs` are named and each input requires non-empty `source`
-- inputs may be optional (`required: false`)
-- `vars` values currently support `string` and `bool`
-
-Prompt IDs and profile IDs are configuration values, not hardcoded stage logic.
-
-Trim config shape:
-
-```yaml
-trim:
-  enabled: true
-  output_path: "transcripts/trimmed.json"
-  bounds:
-    prompt_id: "dnd_session.bounds"
-    profile_id: ""
-    transcript_input_name: "transcript"
-    output_path: "artifacts/session_bounds.json"
-    timeout: "10m"
-    render_debug: false
-    render_output_path: "artifacts/session_bounds.render.json"
-  seriatim:
-    report: false
-```
-
-## 6. Transcript Tiers
-
-Narratio currently produces and uses four transcript tiers:
-
-- `transcripts/merged.json`: canonical deterministic merged transcript from Seriatim merge
-- `transcripts/processed.json`: full raw Audita-polished transcript output (includes pre/post-game content)
-- `transcripts/normalized.json`: normalized transcript generated by Seriatim normalize
-- `transcripts/trimmed.json`: gameplay-only normalized polished transcript from trim stage
-
-Trim reads `transcripts/normalized.json`, validates bounds IDs against that same transcript ID space, and writes `transcripts/trimmed.json`.
-
-## 7. Normalize Stage (Current Implementation)
-
-Normalize stage behavior:
-
-- stage order position: after `polish` and before `trim`
-- discovers processed transcript from manifest polish outputs (`transcript_processed`) when present, else `work/<session_id>/transcripts/processed.json`
-- validates processed transcript JSON shape (`segments` array required)
-- runs Seriatim `normalize` to produce normalized transcript
-- validates normalized transcript JSON shape (`segments` array required)
-- validates normalize report JSON when enabled
-
-Expected normalize outputs and diagnostics:
-
-- `transcripts/normalized.json`
-- `artifacts/seriatim.normalize.report.json` (when normalize report is enabled)
-- `logs/seriatim.normalize.stdout.log`
-- `logs/seriatim.normalize.stderr.log`
-- `config/seriatim.normalize.generated.yml`
-
-## 8. Trim Stage (Current Implementation)
-
-Trim stage behavior:
-
-- stage order position: after `normalize` and before `analyze`
-- discovers normalized transcript from manifest normalize outputs (`transcript_normalized`) when present, else `work/<session_id>/transcripts/normalized.json`
-- validates normalized transcript JSON shape (`segments` array required)
-- when `trim.enabled: false` (or trim config omitted), deterministically copies normalized transcript to `transcripts/trimmed.json` and records `trim_action=copy_disabled`
-- when `trim.enabled: true`:
-  - runs Scriptorium bounds prompt using configured `trim.bounds.prompt_id`
-  - writes bounds output to configured path (typically `artifacts/session_bounds.json`)
-  - parses and validates bounds output against the same normalized transcript being trimmed
-  - converts bounds range to Seriatim keep selector (for example `10-868`)
-  - runs Seriatim `trim` to produce `transcripts/trimmed.json`
-  - supports no-trim bounds actions (`none`/`copy`) by copying normalized transcript unchanged
-- validates trimmed transcript JSON shape (`segments` array required)
-
-Expected trim outputs and diagnostics:
-
-- `artifacts/session_bounds.json`
-- `transcripts/trimmed.json`
-- `logs/scriptorium.bounds.stdout.log`
-- `logs/scriptorium.bounds.stderr.log`
-- `config/scriptorium.bounds.generated.yml`
-- `logs/seriatim.trim.stdout.log`
-- `logs/seriatim.trim.stderr.log`
-- `config/seriatim.trim.generated.yml`
-- optional bounds render-debug outputs when enabled:
-  - `artifacts/session_bounds.render.json`
-  - `logs/scriptorium.bounds.render.stdout.log`
-  - `logs/scriptorium.bounds.render.stderr.log`
-  - `config/scriptorium.bounds.render.generated.yml`
-
-Render-debug files are diagnostics. They are recorded in stage metadata/log/config refs and are not treated as canonical stage output artifact refs.
-
-## 9. Analyze Stage (Current Implementation)
-
-The current real analyze implementation supports only `scriptorium.artifacts.session_recap`.
-
-Behavior:
-
-- if `pipeline.scriptorium` is missing, analyze returns a skipped result with metadata
-- if no Scriptorium artifacts are enabled, analyze returns a skipped result with metadata
-- if enabled artifacts exist but `session_recap` is not enabled, analyze fails clearly
-- available transcript input sources for configured artifacts: `processed_transcript`, `normalized_transcript`, `trimmed_transcript`
-- `session_recap` should use `trimmed_transcript` input (`transcripts/trimmed.json`) for in-universe recap generation
-- `trimmed_transcript` input is resolved from manifest (`trim` output kind `transcript_trimmed`) when available, otherwise fallback path `work/<session_id>/transcripts/trimmed.json`
-- `normalized_transcript` input is resolved from manifest (`normalize` output kind `transcript_normalized`) when available, otherwise fallback path `work/<session_id>/transcripts/normalized.json`
-- `processed_transcript` input is resolved from manifest (`polish` output kind `transcript_processed`) when available, otherwise fallback path `work/<session_id>/transcripts/processed.json`
-- `normalized_transcript` is the preferred full-transcript source for future table/meta-analysis artifacts
-- `processed_transcript` remains available for advanced/debug use cases
-- transcript inputs are validated as JSON with top-level `segments` array
-- configured inputs are resolved by source
-- optional `previous_recap` is omitted when unavailable
-- required `previous_recap` fails before invocation when unavailable
-- vars are built from config + session metadata
-- `render_debug` controls pre-run `scriptorium render` diagnostics
-- render failure stops stage before production run
-- render output is validated as JSON
-- production call uses Scriptorium adapter `RunArtifact`
-- successful run output must exist and be non-empty
-- missing `trimmed_transcript` input for configured `trimmed_transcript` source fails clearly with guidance to run trim stage first
-- manifest records output refs, logs, generated config paths, and non-secret provenance metadata
-
-## 10. Session Recap Paths
-
-Current expected paths for `session_recap`:
-
-- artifact output: `artifacts/session_recap.md`
-- run stdout log: `logs/scriptorium.session_recap.stdout.log`
-- run stderr log: `logs/scriptorium.session_recap.stderr.log`
-- run generated invocation/config: `config/scriptorium.session_recap.generated.yml`
-- render output (when enabled): `artifacts/session_recap.render.json`
-- render stdout log: `logs/scriptorium.session_recap.render.stdout.log`
-- render stderr log: `logs/scriptorium.session_recap.render.stderr.log`
-- render generated invocation/config: `config/scriptorium.session_recap.render.generated.yml`
-
-## 11. Security and Privacy
-
-- do not store secrets in pipeline YAML, generated invocation YAML, logs, or manifest metadata
-- if API-key integration is configured, pass env var names only (never raw key values)
-- avoid logging transcript content or rendered prompt content by default
-- treat generated artifacts and logs as potentially sensitive session material
-
-## 12. Operational Caveat (Pre-Stale-Detection)
-
-Checksum-based stale detection is not implemented yet.
-
-If prepared inputs or prompt/runtime configuration change (for example glossary files, prompt IDs, profile IDs, or relevant pipeline settings), rerun the appropriate prior stages to refresh downstream artifacts.
-
-Examples:
-
-- glossary or autocorrect changes usually require rerunning at least `merge`, `polish`, `normalize`, `trim`, and `analyze`
-- trim prompt/profile changes require rerunning at least `normalize`, `trim`, and `analyze`
-- session recap prompt/profile/input-source changes require rerunning `analyze`
-
-## 13. Roadmap
-
-Planned next steps:
-
-- extend analyze beyond `session_recap` to additional configured artifacts
-- support artifact inputs that consume prior generated artifacts
-- keep this composable without adding a generic DAG engine in the near term
-- implement real `archive` backend behavior
-- implement real `notify` backend behavior
-- add checksum-based stale detection and stale transitions
-
-Architectural invariants remain:
-
-- strict config decoding/validation
-- manifest-driven run control
-- clear stage/adapter separation
-- configuration-driven prompt/profile/input/vars/output mapping
-- Scriptorium integration through public CLI subprocess contract

docs/architecture.md

@@ -0,0 +1,202 @@
+# Narratio Architecture
+
+## Purpose
+
+`narratio` is a Go orchestration application for processing D&D session audio into polished transcripts and generated session artifacts.
+
+This document defines the development principles for the project. It is inward-facing: its audience is developers and LLM coding agents. It should guide future changes, not serve as a complete implementation reference.
+
+Implemented component details belong under `docs/internal/`.
+
+## Project Shape
+
+Narratio is a modular, stage-driven orchestrator.
+
+It coordinates specialized downstream systems rather than reimplementing their domains:
+
+- WhisperX handles transcription.
+- Seriatim handles deterministic transcript merge/normalization/trim behavior.
+- Audita handles transcript correction and polishing.
+- Scriptorium handles prompt execution and generated artifacts.
+
+Narratio owns orchestration, configuration loading, session/run state, local and remote path modeling, manifest persistence, stage sequencing, resume behavior, and archive semantics.
+
+Narratio should remain explicit and comprehensible. It is not intended to become a generic workflow engine.
+
+## Core Principles
+
+### Modular and composable
+
+Code should be organized around clear responsibilities. Stages, adapters, config loading, manifest persistence, path construction, and storage behavior should remain separable and independently testable.
+
+### Hexagonal boundaries
+
+External systems should be isolated behind narrow adapters. Stage logic should depend on Narratio-level interfaces and data structures, not on external SDK types, subprocess argument construction, or transport-specific details.
+
+### Standard library preference
+
+Prefer the Go standard library. Add dependencies only when they provide substantial value, are necessary for an external integration, or are a widely used de facto standard.
+
+Accepted examples include a YAML library for configuration and the AWS SDK for S3-compatible storage.
+
+### Explicit orchestration
+
+The pipeline should remain stage-driven and explicit. New behavior should be added through clear stage, adapter, config, or manifest contracts rather than implicit side effects or generic workflow abstraction.
+
+## Stage Design
+
+Each stage should have a clear scope of responsibility.
+
+A stage should define:
+
+- its purpose;
+- required input state;
+- produced output state;
+- config fields it consumes;
+- external adapters it uses;
+- manifest refs it reads or writes;
+- skip, force, and resume behavior;
+- failure behavior;
+- tests that protect its contract.
+
+Stages should avoid reaching across boundaries. If shared behavior is needed, prefer a helper or service with a narrow interface over duplicating ad hoc logic between stages.
+
+## Transactionality and Resume
+
+A stage should behave transactionally.
+
+A stage is complete only when its outputs have been written, validated, and recorded in the manifest. If a stage fails, Narratio should preserve enough local state for inspection, recovery, and resume.
+
+A failed or incomplete run must not be treated as successful. Later stages should depend on manifest-recorded success, not merely on incidental files existing on disk.
+
+## Manifest Model
+
+The manifest is the durable local ledger for a run.
+
+It should record:
+
+- run identity;
+- stage status;
+- input and output refs;
+- logs and generated config refs;
+- checksums or provenance where useful;
+- non-secret adapter and archive metadata.
+
+Resume behavior should be manifest-driven. Filesystem state may be inspected and validated, but it should not replace manifest stage state as the source of run progress.
+
+## Adapter Boundaries
+
+Adapters own external integration details.
+
+Expected boundaries:
+
+- WhisperX HTTP details stay in the WhisperX adapter.
+- Seriatim CLI construction stays in the Seriatim adapter.
+- Audita CLI construction stays in the Audita adapter.
+- Scriptorium CLI construction stays in the Scriptorium adapter.
+- Object-storage details stay behind the storage adapter interface.
+- AWS SDK types stay inside the S3 storage implementation.
+
+Stage code should express intent in Narratio terms and call adapters through narrow contracts.
+
+## Configuration Philosophy
+
+Configuration should be strict, explicit, and operator-friendly.
+
+Principles:
+
+- YAML decoding should reject unknown fields.
+- Defaults should be centralized and testable.
+- Empty configured values should not silently override meaningful defaults.
+- Session templating should remain narrow and deterministic.
+- Template support should serve operator convenience, not become a general configuration language.
+
+Narratio should not become a secondary configuration system for downstream tools. Seriatim, Audita, and Scriptorium should own their runtime defaults wherever practical. Narratio should pass required stage-contract paths and explicit operator overrides.
+
+## Path and Storage Discipline
+
+Local and remote paths are part of Narratio’s application contract.
+
+Code should use centralized path helpers for workspace, spool, session, run, artifact, log, config, and archive paths. Stages should avoid reconstructing canonical paths through scattered string concatenation.
+
+Storage backends should receive explicit bucket-relative keys. Storage implementations should not infer campaign, session, run, or root-prefix semantics.
+
+## Archive Invariants
+
+Archive behavior must preserve a clear commit boundary.
+
+A remote run is current only after the archive stage has successfully uploaded the run record, required promoted outputs, `current/manifest.json`, and finally `current/run_id.txt`.
+
+`current/run_id.txt` is the final remote commit marker and must be written last.
+
+Failed, incomplete, skipped, or uncommitted archive attempts must not be presented as current remote state. Local cleanup is permitted only after successful archive commit and only when explicitly configured.
+
+## Security and Privacy
+
+Narratio handles private campaign material.
+
+Rules:
+
+- Do not store raw secrets in pipeline or session YAML.
+- Use environment variable names or secret-file references for secret handling.
+- Do not write raw secret values to manifests, logs, generated configs, or archive metadata.
+- Treat transcripts, generated artifacts, prompts, reports, and logs as potentially sensitive.
+- Avoid logging transcript or prompt content unless there is a deliberate diagnostic reason.
+
+## Diagnostics
+
+Diagnostics should be durable and discoverable, but distinct from canonical outputs.
+
+Logs, reports, generated invocation/config files, and render-debug files support debugging. Transcript tiers and configured artifacts are pipeline products.
+
+Manifest refs should preserve that distinction.
+
+## Determinism
+
+Where practical, Narratio should prefer deterministic behavior:
+
+- stable local path layout;
+- stable remote key layout;
+- sorted upload order;
+- predictable generated config files;
+- repeatable command construction;
+- tests that do not depend on live external services.
+
+Run IDs and timestamps may be intentionally variable, but surrounding behavior should remain testable.
+
+## Testing Expectations
+
+Core behavior should be testable without live external services.
+
+Tests should cover:
+
+- config loading, defaults, and validation;
+- CLI parsing and command construction;
+- path helpers;
+- manifest transitions;
+- stage success, failure, skip, and resume behavior;
+- adapter command construction;
+- fake storage behavior;
+- archive commit ordering;
+- example config validity where practical.
+
+Live S3, WhisperX, LLM, or subprocess integration tests should be explicit integration tests, not required for ordinary unit test runs.
+
+## Documentation Expectations
+
+Documentation must follow `docs/documentation/policy.md`.
+
+Current behavior belongs in user-facing docs and `docs/internal/`. Future, planned, aspirational, experimental, or unimplemented work belongs only under `docs/roadmap/`.
+
+`docs/architecture.md` should remain concise and principle-focused. It should not duplicate the full config reference, CLI reference, operations guide, or internal stage documentation.
+
+## Non-Goals
+
+Narratio is not:
+
+- a generic DAG or workflow engine;
+- a replacement configuration layer for Seriatim, Audita, or Scriptorium;
+- a storage backend abstraction beyond the needs of this pipeline;
+- a place to embed raw secrets;
+- a place for stage logic to depend directly on AWS SDK types or downstream tool internals;
+- a prompt-authoring system.

docs/cli.md

@@ -0,0 +1,222 @@
+# CLI
+
+## Shortest Useful Command
+
+```bash
+narratio run --session-id 2026-04-04
+```
+
+This command uses default config discovery for `pipeline.yml` and `session.yml`; both files must be discoverable unless you pass explicit `--config` and `--session` paths.
+
+## Command Overview
+
+Implemented commands:
+
+- `run`: execute pipeline stages and persist manifest state.
+- `plan`: validate config, prepare workspace layout, and print stage run/skip decisions.
+- `resume`: continue from first non-succeeded stage unless forced.
+- `status`: read and print stage statuses from an existing manifest.
+- `run-stage`: execute exactly one stage.
+
+Unknown commands print usage and exit non-zero.
+
+For config semantics, see [docs/config.md](./config.md). For operator lifecycle and recovery, see [docs/operations.md](./operations.md).
+
+## Complete Flag Reference
+
+### `run`
+
+- `--config <path>`: optional explicit `pipeline.yml` path.
+- `--session <path>`: optional explicit `session.yml` path.
+- `--session-id <value>`: session template variable value.
+- `--force`: force stage execution.
+- `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated).
+
+### `plan`
+
+- `--config <path>`
+- `--session <path>`
+- `--session-id <value>`
+- `--force`
+
+### `resume`
+
+- `--config <path>`
+- `--session <path>`
+- `--session-id <value>`
+- `--force`
+- `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated).
+
+### `run-stage`
+
+- `--config <path>`
+- `--session <path>`
+- `--session-id <value>`
+- `--force`
+- `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated).
+- positional `<stage>`: required stage name.
+
+Valid stage names:
+
+- `prepare`
+- `transcribe`
+- `merge`
+- `polish`
+- `normalize`
+- `trim`
+- `analyze`
+- `archive`
+- `notify`
+
+### `status`
+
+- `--manifest <path>`: required manifest path.
+
+## Command Reference
+
+### `run`
+
+Purpose:
+- Execute configured stages in canonical order.
+
+Syntax:
+
+```bash
+narratio run [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] [--artifacts <name[,name...]>]
+```
+
+Success output:
+- `narratio run: session <session_id>; executed=<n> skipped=<n>; manifest=<path>`
+
+Common failure cases:
+- missing default config/session paths when flags omitted.
+- invalid template/rendered session mismatch.
+- unknown/invalid `--artifacts` value.
+- `--artifacts` with unknown configured artifact key.
+
+### `plan`
+
+Purpose:
+- Validate config, load secrets (if configured), prepare workdir, and print stage run/skip decisions.
+
+Syntax:
+
+```bash
+narratio plan [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force]
+```
+
+Success output includes:
+- `narratio plan: workdir prepared at <path>`
+- one line per stage (`<stage>: run|skip`)
+- `totals: run=<n> skip=<n>`
+
+Common failure cases:
+- same config/session discovery and validation failures as `run`.
+- secrets directory read failures when `pipeline.secrets.env_dir` is configured.
+
+### `resume`
+
+Purpose:
+- Continue from session-manifest stage status.
+
+Syntax:
+
+```bash
+narratio resume [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] [--artifacts <name[,name...]>]
+```
+
+Success output:
+- `narratio resume: session <session_id> has no remaining stages`
+- or `narratio resume: session <session_id>; executed=<n> skipped=<n>; manifest=<path>`
+
+Common failure cases:
+- same discovery/template/validation failures as `run`.
+- manifest load errors when existing manifest is unreadable.
+- invalid or unknown artifact selections.
+
+### `status`
+
+Purpose:
+- Inspect one manifest file without executing stages.
+
+Syntax:
+
+```bash
+narratio status --manifest <manifest.json>
+```
+
+Success output includes:
+- `session_id: <id>`
+- `updated_at: <timestamp>`
+- `stages:` entries (`- <stage>: <status>`)
+
+Common failure cases:
+- missing `--manifest`.
+- unreadable or invalid manifest path.
+
+### `run-stage`
+
+Purpose:
+- Execute exactly one stage.
+
+Syntax:
+
+```bash
+narratio run-stage [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] [--artifacts <name[,name...]>] <stage>
+```
+
+Success output:
+- `narratio run-stage: stage=<name> executed=<n> skipped=<n> force=<true|false>; manifest=<path>`
+
+`--artifacts` behavior:
+- accepted only when `<stage>` is `analyze`.
+- names are normalized (trimmed, deduplicated, sorted).
+- unknown configured artifact keys fail.
+
+Common failure cases:
+- missing stage positional arg.
+- unknown stage name.
+- using `--artifacts` with any non-`analyze` stage.
+
+## Common Workflows
+
+Default-discovery run:
+
+```bash
+narratio run --session-id 2026-04-04
+```
+
+Run only selected analyze artifacts:
+
+```bash
+narratio run --session-id 2026-04-04 --artifacts session_recap,player_handout
+```
+
+Resume with selected analyze artifacts:
+
+```bash
+narratio resume --session-id 2026-04-04 --artifacts player_handout
+```
+
+Run only analyze stage with selected artifacts:
+
+```bash
+narratio run-stage --session-id 2026-04-04 --artifacts player_handout analyze
+```
+
+## Diagnostic / Recovery Commands
+
+Inspect stage status:
+
+```bash
+narratio status --manifest <manifest.json>
+```
+
+Get manifest path from previous output:
+- `run`, `resume`, and `run-stage` print `manifest=<path>` on success.
+
+## `--artifacts` and `--force`
+
+- `--artifacts` filters which configured artifacts are executable when analyze runs.
+- `--artifacts` does not imply `--force`.
+- If analyze is already `succeeded` and `--force` is not set, runner-level skip still applies.

docs/config.md

@@ -0,0 +1,304 @@
+# Configuration
+
+## 1. Overview
+
+Narratio loads two YAML files:
+
+- `pipeline.yml`: pipeline-level runtime configuration.
+- `session.yml`: per-session metadata and input selection.
+
+These commands load and validate both files before running:
+
+- `narratio run`
+- `narratio plan`
+- `narratio resume`
+- `narratio run-stage`
+
+Behavior:
+
+- strict YAML decode is enabled (`KnownFields(true)`): unknown fields fail.
+- session templates render before session YAML decode.
+- defaults are applied for optional pipeline fields.
+- validation enforces required fields, value formats, and cross-field constraints.
+
+## 2. Config file discovery
+
+Pipeline config lookup for `run`, `plan`, `resume`, and `run-stage`:
+
+- If `--config <path>` is provided, that path is used.
+- If omitted, Narratio searches in order:
+  1. `/usr/local/etc/narratio/pipeline.yml`
+  2. `/etc/narratio/pipeline.yml`
+- First existing file wins.
+
+## 3. Session file discovery and templating
+
+Session config lookup for `run`, `plan`, `resume`, and `run-stage`:
+
+- If `--session <path>` is provided, that path is used.
+- If omitted, Narratio searches in order:
+  1. `./session.yml`
+  2. `/usr/local/etc/narratio/session.yml`
+  3. `/etc/narratio/session.yml`
+- First existing file wins.
+
+Template behavior:
+
+- Supported placeholders:
+  - `{{session_id}}`
+  - `{{ session_id }}`
+- `--session-id <value>` supplies the placeholder value.
+- unresolved placeholders fail load.
+- if rendered `session_id` mismatches `--session-id`, load fails.
+
+## 4. Minimal pipeline config
+
+```yaml
+whisperx:
+  transcribe_url: "https://transcription.example.com/transcribe"
+```
+
+Why this is sufficient:
+
+- `whisperx.transcribe_url` is required.
+- `workspace.root` defaults to `/var/lib/narratio`.
+- optional sections (`seriatim`, `audita`, `archive`, `scriptorium`, `trim`, `normalize`, etc.) receive defaults or stay inactive.
+
+## 5. Minimal session template
+
+```yaml
+session_id: "{{ session_id }}"
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./examples/speakers.yml
+  autocorrect_file: ./examples/autocorrect.yml
+  glossary_file: ./examples/glossary.yml
+```
+
+Usage:
+
+```bash
+narratio run --config /path/to/pipeline.yml --session ./session.yml --session-id 2026-05-03
+```
+
+## 6. Production-oriented config
+
+```yaml
+workspace:
+  root: /var/lib/narratio/workspace
+  cleanup_after_archive: true
+
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+    root_prefix: dnd
+    region: us-east-1
+    access_key_id_env: OBJECT_STORAGE_KEY_ID
+    secret_access_key_env: OBJECT_STORAGE_KEY
+
+spool:
+  root: /var/spool/narratio
+  delete_audio_after_archive: true
+
+archive:
+  enabled: true
+  upload_run: true
+  promote_artifacts:
+    - from: transcripts/trimmed.json
+      to: transcripts/trimmed.json
+      required: true
+    - from: artifacts/session_recap.md
+      to: artifacts/session_recap.md
+      required: true
+
+whisperx:
+  transcribe_url: "https://transcription.example.com/transcribe"
+
+scriptorium:
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+```
+
+Operational notes:
+
+- archive promotion is explicit and path-based via `archive.promote_artifacts`.
+- Narratio does not auto-promote all generated analyze artifacts.
+
+## 7. Full pipeline reference
+
+| Path | Type | Required | Default |
+| --- | --- | --- | --- |
+| `pipeline.workspace.root` | string | No | `/var/lib/narratio` |
+| `pipeline.workspace.cleanup_after_archive` | bool | No | `false` |
+| `pipeline.secrets.env_dir` | string | Conditional | none |
+| `pipeline.storage.backend` | string | No | empty |
+| `pipeline.storage.bucket` | string | No | empty |
+| `pipeline.storage.prefix` | string | No | empty |
+| `pipeline.storage.s3.bucket` | string | Conditional | empty |
+| `pipeline.storage.s3.root_prefix` | string | No | `dnd` |
+| `pipeline.storage.s3.region` | string | No | empty |
+| `pipeline.storage.s3.endpoint` | string | No | empty |
+| `pipeline.storage.s3.force_path_style` | bool | No | `false` |
+| `pipeline.storage.s3.access_key_id_env` | string | No | `OBJECT_STORAGE_KEY_ID` |
+| `pipeline.storage.s3.secret_access_key_env` | string | No | `OBJECT_STORAGE_KEY` |
+| `pipeline.spool.root` | string | No | `/var/spool/narratio` |
+| `pipeline.spool.delete_audio_after_archive` | bool | No | `false` |
+| `pipeline.archive.enabled` | bool | No | `true` |
+| `pipeline.archive.upload_run` | bool | No | `true` |
+| `pipeline.archive.promote_artifacts[]` | list | No | trimmed + session_recap rules |
+| `pipeline.archive.promote_artifacts[].from` | string | Yes (per rule) | none |
+| `pipeline.archive.promote_artifacts[].to` | string | Yes (per rule) | none |
+| `pipeline.archive.promote_artifacts[].required` | bool | No | `true` |
+| `pipeline.whisperx.transcribe_url` | string | Yes | none |
+| `pipeline.whisperx.language` | string | No | `en` |
+| `pipeline.whisperx.timeout` | duration string | No | `30m` |
+| `pipeline.whisperx.retries` | int | No | `3` |
+| `pipeline.whisperx.retry_delay` | duration string | No | `2s` |
+| `pipeline.whisperx.concurrency` | int | No | `2` |
+| `pipeline.seriatim.binary` | string | No | `seriatim` |
+| `pipeline.seriatim.timeout` | duration string | No | `10m` |
+| `pipeline.seriatim.output_schema` | string | No | `seriatim-intermediate` |
+| `pipeline.seriatim.coalesce_gap` | float | No | `3.0` |
+| `pipeline.seriatim.report` | bool | No | `true` |
+| `pipeline.seriatim.env.overlap_word_run_gap` | float | No | unset |
+| `pipeline.seriatim.env.overlap_word_run_reorder_window` | float | No | unset |
+| `pipeline.seriatim.env.backchannel_max_duration` | float | No | unset |
+| `pipeline.seriatim.env.filler_max_duration` | float | No | unset |
+| `pipeline.audita.binary` | string | No | `audita` |
+| `pipeline.audita.timeout` | duration string | No | `3h` |
+| `pipeline.audita.llm_api_key_env` | string | No | empty |
+| `pipeline.audita.modules[]` | list[string] | No | empty |
+| `pipeline.audita.base_url` | string | No | empty |
+| `pipeline.audita.model` | string | No | empty |
+| `pipeline.audita.total_llm_concurrency` | int | No | unset |
+| `pipeline.audita.proposal_llm_concurrency` | int | No | unset |
+| `pipeline.audita.validation_model` | string | No | empty |
+| `pipeline.audita.validation_llm_concurrency` | int | No | unset |
+| `pipeline.audita.transcript_description` | string | No | empty |
+| `pipeline.audita.config_path` | string | No | empty |
+| `pipeline.audita.output_schema` | string | No | empty |
+| `pipeline.audita.work_dir_retention` | string | No | empty |
+| `pipeline.audita.report` | bool | No | `true` |
+| `pipeline.normalize.output_path` | string | No | `transcripts/normalized.json` |
+| `pipeline.normalize.output_schema` | string | No | `seriatim-intermediate` |
+| `pipeline.normalize.report` | bool | No | `true` |
+| `pipeline.trim.enabled` | bool | No | `false` |
+| `pipeline.trim.output_path` | string | Conditional | none |
+| `pipeline.trim.bounds.prompt_id` | string | Conditional | none |
+| `pipeline.trim.bounds.profile_id` | string | No | empty |
+| `pipeline.trim.bounds.transcript_input_name` | string | Conditional | none |
+| `pipeline.trim.bounds.output_path` | string | Conditional | none |
+| `pipeline.trim.bounds.timeout` | duration string | No | `10m` |
+| `pipeline.trim.bounds.render_debug` | bool | No | `false` |
+| `pipeline.trim.bounds.render_output_path` | string | Conditional | none |
+| `pipeline.trim.seriatim.report` | bool | No | `false` |
+| `pipeline.scriptorium.binary` | string | No | `scriptorium` |
+| `pipeline.scriptorium.config_path` | string | No | empty |
+| `pipeline.scriptorium.timeout` | duration string | No | `10m` |
+| `pipeline.scriptorium.render_debug` | bool | No | `false` |
+| `pipeline.scriptorium.artifacts` | map | No | empty |
+| `pipeline.scriptorium.artifacts.<name>.enabled` | bool | No | `false` |
+| `pipeline.scriptorium.artifacts.<name>.depends_on[]` | list[string] | No | empty |
+| `pipeline.scriptorium.artifacts.<name>.render_debug` | bool | No | unset |
+| `pipeline.scriptorium.artifacts.<name>.prompt_id` | string | Conditional | none |
+| `pipeline.scriptorium.artifacts.<name>.profile_id` | string | No | empty |
+| `pipeline.scriptorium.artifacts.<name>.output_path` | string | Conditional | none |
+| `pipeline.scriptorium.artifacts.<name>.timeout` | duration string | No | empty |
+| `pipeline.scriptorium.artifacts.<name>.inputs.<key>.source` | string | Conditional | none |
+| `pipeline.scriptorium.artifacts.<name>.inputs.<key>.artifact` | string | No | empty |
+| `pipeline.scriptorium.artifacts.<name>.inputs.<key>.path` | string | No | empty |
+| `pipeline.scriptorium.artifacts.<name>.inputs.<key>.required` | bool | No | `false` |
+| `pipeline.scriptorium.artifacts.<name>.vars.<key>` | map value | No | empty |
+| `pipeline.analyzer.binary_path` | string | No | empty |
+| `pipeline.analyzer.timeout` | duration string | No | empty |
+| `pipeline.analyzer.artifacts.output_dir` | string | No | empty |
+| `pipeline.analyzer.artifacts.types[]` | list[string] | No | empty |
+| `pipeline.notification.backend` | string | No | empty |
+| `pipeline.notification.recipient` | string | No | empty |
+| `pipeline.notification.timeout` | duration string | No | empty |
+
+Scriptorium artifact-key and dependency rules:
+
+- artifact keys must match `^[a-z][a-z0-9_]*$`.
+- enabled artifacts require `prompt_id` and `output_path`.
+- `output_path` must be relative, traversal-safe, and under `artifacts/`.
+- configured artifact input sources use `narratio.artifact.<name>`.
+- if input source references `narratio.artifact.<name>`, artifact `<name>` must exist and must be listed in `depends_on`.
+- every `depends_on` entry must be a configured artifact key.
+- self-dependency is rejected.
+- enabled dependency cycles are rejected.
+- any artifact referenced by `depends_on` or `narratio.artifact.<name>` source must define `output_path` (even if not enabled).
+
+Allowed `pipeline.scriptorium.artifacts.<name>.inputs.<key>.source` values:
+
+- `previous_session_artifact`
+- `narratio.transcript.merged`
+- `narratio.transcript.polished`
+- `narratio.transcript.full`
+- `narratio.transcript.trimmed`
+- `narratio.bounds.session`
+- `narratio.artifact.<configured_artifact_key>`
+
+## 8. Full session reference
+
+| Path | Type | Required | Default |
+| --- | --- | --- | --- |
+| `session.session_id` | string | Yes | none |
+| `session.campaign` | string | Yes | none |
+| `session.date` | string | No | empty |
+| `session.title` | string | No | empty |
+| `session.inputs.audio_dir` | string | Conditional | empty |
+| `session.inputs.audio_files[]` | list[string] | Conditional | empty |
+| `session.inputs.audio_s3.prefix` | string | Conditional | none |
+| `session.inputs.speakers_file` | string | Yes | none |
+| `session.inputs.autocorrect_file` | string | Yes | none |
+| `session.inputs.glossary_file` | string | Yes | none |
+
+Audio-source rule:
+
+- configure exactly one mode:
+  - `audio_dir`, or
+  - `audio_files` (at least one), or
+  - `audio_s3.prefix`
+- `audio_s3` cannot be combined with local audio fields.
+
+## 9. Secrets
+
+Narratio supports filesystem-based secret injection via `pipeline.secrets.env_dir`.
+
+Behavior:
+
+- `env_dir` may be absolute or relative.
+- relative `env_dir` resolves from current working directory.
+- files with valid env-var names (`[A-Za-z_][A-Za-z0-9_]*`) are loaded.
+- values are loaded from file contents with trailing newline trimming.
+- existing process env vars are preserved.
+- invalid names and subdirectories are skipped.
+- missing/unreadable `env_dir` fails command execution.
+
+Guidance:
+
+- do not put secret values directly in YAML.
+- configure env var names in config and provide values via env/secrets files.
+
+## 10. Examples
+
+Maintained examples:
+
+- `examples/pipeline.minimal.yml`
+- `examples/pipeline.production.yml`
+- `examples/pipeline.full.annotated.yml`
+- `examples/session.template.yml`
+- `examples/session.local-audio.yml`
+- `examples/session.s3-audio.yml`
+
+These examples are validated by `internal/config` tests.

docs/development.md

@@ -0,0 +1,92 @@
+# Development Guide
+
+## Purpose
+Canonical contributor workflow and engineering conventions for implemented Narratio behavior.
+
+## Repository layout
+
+- `cmd/narratio/`: CLI entrypoint.
+- `internal/app/`: command handlers, plan/run/resume orchestration, cleanup gates, secrets loading.
+- `internal/config/`: strict YAML loading, defaults, and validation.
+- `internal/stage/`: stage implementations and stage registry/order.
+- `internal/adapters/`: external boundary adapters (WhisperX, Seriatim, Audita, Scriptorium, storage, notify).
+- `internal/manifest/`: session/run manifest types and persistence.
+- `internal/artifacts/`: canonical local/remote path helpers and local artifact store.
+- `docs/`: canonical documentation set.
+- `examples/`: maintained config examples used by tests.
+
+## Build and test commands
+
+- Run focused CLI behavior checks:
+
+```bash
+go test ./internal/app -run TestExecute -v
+```
+
+- Run config example load/validate checks:
+
+```bash
+go test ./internal/config -run TestExamplesLoadAndValidate -v
+```
+
+- Run full test suite:
+
+```bash
+go test ./...
+```
+
+## Coding conventions
+
+- Keep orchestration explicit and stage-driven; do not introduce generic workflow/DAG abstractions.
+- Keep external-system details inside adapter packages; stages should consume Narratio-level contracts only.
+- Use centralized path helpers from `internal/artifacts` rather than ad hoc path concatenation.
+- Preserve manifest-driven state transitions (`running`, `succeeded`, `failed`, `skipped`, `stale`) as the source of run progress.
+- Keep user/operator docs implementation-accurate; planned work belongs only under `docs/roadmap/`.
+
+For design principles and invariants, see [docs/architecture.md](./architecture.md). For stage/adapter contracts, see [docs/internal/README.md](./internal/README.md).
+
+## Dependency policy
+
+- Prefer Go standard library where practical.
+- Add third-party dependencies only when they provide clear value for required behavior.
+- Keep dependency additions narrow to the boundary package that needs them.
+
+## Change playbooks
+
+### Add config fields
+
+1. Add fields to config structs in `internal/config`.
+2. Set defaults in `internal/config/defaults.go` when appropriate.
+3. Add validation rules in `internal/config/validate.go`.
+4. Add or update load/validate tests in `internal/config/*_test.go`.
+5. Update canonical config docs and examples:
+   - [docs/config.md](./config.md)
+   - relevant files under `examples/`
+
+### Add CLI flags or commands
+
+1. Update command parsing and behavior in `internal/app`.
+2. Add or update command tests (`TestExecute` and command-specific tests).
+3. Update [docs/cli.md](./cli.md) and, if operator workflow changes, [docs/operations.md](./operations.md).
+
+### Add or modify stages/adapters
+
+1. Implement stage behavior in `internal/stage` with clear input/output boundaries.
+2. Keep external transport/subprocess details in `internal/adapters`.
+3. Preserve manifest and promotion semantics expected by runner and archive logic.
+4. Add/update stage and adapter tests.
+5. Update internal component contracts in `docs/internal/`.
+
+### Update examples
+
+1. Keep canonical examples only in `examples/`.
+2. Ensure examples load and validate through runtime config paths.
+3. Update `internal/config/load_validate_test.go` as needed.
+4. Update links in `docs/config.md` if example filenames change.
+
+### Update docs and roadmap
+
+1. Keep implemented behavior in canonical docs (`README`, `docs/*.md`, `docs/internal/`).
+2. Keep planned/unimplemented behavior only in `docs/roadmap/`.
+3. After completing roadmap items, remove or mark them complete in `docs/roadmap/documentation.md`.
+4. Run a link/path sweep before finalizing changes.

docs/documentation/policy.md

@@ -0,0 +1,356 @@
+# Go Project Documentation Policy
+
+## Purpose
+
+Project documentation must help four audiences:
+
+1. users who need to run the application;
+2. administrators/operators who need to configure and operate it;
+3. developers who need to understand and change it safely;
+4. LLM coding agents that need clear scope, boundaries, and invariants.
+
+Docs should be accurate, concise, task-oriented, and organized by audience. Prefer links to canonical docs over repetition.
+
+## Core Rules
+
+### 1. Keep docs concise
+
+Each document should cover a defined scope and only the essentials for that scope.
+
+Avoid:
+- long background explanations;
+- repeated reference material;
+- implementation detail in user-facing docs;
+- aspirational language outside roadmap docs;
+- verbose examples where one minimal example is clearer.
+
+### 2. Document only implemented behavior outside roadmap files
+
+Unimplemented, planned, aspirational, experimental, or future work may be described only under:
+
+- `docs/roadmap/`
+
+No other documentation file, including `README.md`, should describe code, features, modules, stages, commands, config fields, or behaviors that do not currently exist.
+
+If a feature is partial, non-roadmap docs may describe only the implemented portion and its current boundary.
+
+### 3. Use canonical homes
+
+Each type of information should have one canonical location.
+
+Canonical homes:
+
+- project purpose and quickstart: `README.md`
+- development principles: `docs/architecture.md`
+- configuration reference: `docs/config.md`
+- CLI reference: `docs/cli.md`
+- operations and recovery: `docs/operations.md`
+- troubleshooting: `docs/troubleshooting.md`
+- implemented internals: `docs/internal/`
+- future work: `docs/roadmap/`
+- contributor workflow: `docs/development.md`
+- copyable examples: `examples/`
+
+Other files should summarize briefly and link to the canonical source.
+
+### 4. Keep examples real
+
+Examples should be valid, maintained, and free of secrets.
+
+Where practical:
+- example configs should load successfully;
+- example commands should match real CLI syntax;
+- important examples should be covered by tests.
+
+## Documentation Profiles
+
+All projects require:
+
+- `README.md`
+- `docs/architecture.md`
+
+Additional docs depend on the project.
+
+### Small library
+
+Recommended:
+- `docs/development.md`, if contributor conventions are non-obvious
+
+### Simple CLI
+
+Required:
+- `docs/cli.md`
+
+Recommended:
+- `docs/development.md`
+
+### Config-driven CLI
+
+Required:
+- `docs/cli.md`
+- `docs/config.md`
+
+Recommended:
+- `examples/`
+- `docs/development.md`
+
+### Stateful or operator-facing application
+
+Required:
+- `docs/cli.md`, if CLI-based
+- `docs/config.md`, if config-driven
+- `docs/operations.md`
+
+Recommended:
+- `docs/troubleshooting.md`
+- `examples/`
+- `docs/development.md`
+
+### Modular, staged, service-oriented, or orchestration application
+
+Required:
+- `docs/cli.md`, if CLI-based
+- `docs/config.md`, if config-driven
+- `docs/operations.md`
+- `docs/internal/`
+- `docs/development.md`
+
+Recommended:
+- `docs/troubleshooting.md`
+- validated examples under `examples/`
+
+## Required Documents
+
+### README.md
+
+**Audience:** users, administrators, operators
+
+The README is the outward-facing project orientation page.
+
+It should include, in order:
+
+1. concise description;
+2. elevator pitch;
+3. shortest useful command or usage example;
+4. links to targeted docs.
+
+The README should be short. It is not a manual.
+
+The “shortest useful command” means the simplest command that performs the project’s core use case. (It does not mean `app --help`.)
+
+### docs/architecture.md
+
+**Audience:** developers, LLM coding agents
+
+`docs/architecture.md` is required for every project.
+
+It is an inward-facing development policy document. It should describe how the project is intended to be built and changed.
+
+It should include:
+
+- project shape;
+- core design principles;
+- package and boundary philosophy;
+- state/persistence philosophy, if applicable;
+- external integration philosophy, if applicable;
+- error-handling and logging principles;
+- testing expectations;
+- documentation expectations;
+- architectural invariants;
+- explicit non-goals, if useful.
+
+For small projects, this file may be brief. It may simply state that the project is intentionally narrow, monolithic, and dependency-light.
+
+### docs/config.md
+
+**Audience:** administrators, operators, advanced users
+
+Required for applications with configuration files.
+
+It should include, in order:
+
+1. config file locations and discovery precedence;
+2. minimal working config;
+3. production-oriented config;
+4. full configuration reference;
+5. secrets handling, if applicable;
+6. links to maintained examples.
+
+The full configuration reference should be canonical.
+
+### docs/cli.md
+
+**Audience:** users, administrators, operators
+
+Required for CLI applications.
+
+It should include, in order:
+
+1. shortest useful command;
+2. command overview;
+3. complete flag reference;
+4. common workflows;
+5. diagnostic or recovery commands, if applicable.
+
+Explain when commands are useful, not just their syntax.
+
+### docs/operations.md
+
+**Audience:** administrators, operators
+
+Required for applications that maintain state, support resume behavior, run multiple stages, write durable artifacts, use remote storage, or require recovery procedures.
+
+It should cover:
+
+- normal workflow;
+- filesystem layout;
+- remote storage layout, if applicable;
+- logs and manifests;
+- resume/retry behavior;
+- cleanup behavior;
+- archive/backup behavior;
+- safe recovery procedures;
+- operational caveats.
+
+### docs/troubleshooting.md
+
+**Audience:** administrators, operators
+
+Recommended once recurring failure modes exist.
+
+Each entry should include:
+
+- symptom;
+- likely cause;
+- diagnostic command or inspection step;
+- safe fix;
+- relevant links.
+
+### docs/development.md
+
+**Audience:** developers, LLM coding agents
+
+Required for projects maintained by humans and LLM coding agents.
+
+It should include:
+
+- repository layout;
+- build/test commands;
+- coding conventions;
+- dependency policy;
+- how to add config fields;
+- how to add CLI flags;
+- how to add stages/modules/adapters, if applicable;
+- how to update examples;
+- documentation update expectations.
+
+### docs/internal/
+
+**Audience:** developers, LLM coding agents
+
+Required for modular, staged, service-oriented, or orchestration projects.
+
+This directory describes implemented internal components. It is not the roadmap.
+
+Use one file per major component where useful.
+
+Each component doc should include:
+
+1. purpose;
+2. inputs and outputs;
+3. boundaries;
+4. config fields used;
+5. external adapters used;
+6. state or manifest behavior, if applicable;
+7. skip/resume behavior, if applicable;
+8. failure behavior;
+9. tests to inspect before changing;
+10. architectural invariants.
+
+### docs/roadmap/
+
+**Audience:** maintainers, developers, LLM coding agents
+
+This is the only place for planned, future, aspirational, experimental, or unimplemented work.
+
+Roadmap docs should clearly distinguish:
+
+- proposed work;
+- accepted plans;
+- deferred ideas;
+- rejected ideas;
+- implementation prompts or task breakdowns, if useful.
+
+Roadmap docs should not be confused with current behavior.
+
+### docs/integrations/
+
+**Audience:** developers, LLM coding agents
+
+Required for projects that depend on external CLIs, APIs, services, protocols, or file formats where the integration contract is important to maintain.
+
+This directory contains concise, versioned reference notes for external integration contracts. It should document only the parts of the external system that this project actually uses.
+
+Use one file per integration where useful.
+
+## Examples Directory
+
+Projects with non-trivial configuration or workflows should include `examples/`.
+
+Useful examples include:
+
+- minimal working config;
+- production-oriented config;
+- full annotated config;
+- local development config;
+- remote/object-storage config;
+- minimal session/input file.
+
+Examples should be valid, maintained, tested when practical, and linked from relevant docs.
+
+## Security and Privacy
+
+Docs and examples must not include:
+
+- real API keys;
+- tokens;
+- passwords;
+- private keys;
+- private environment dumps;
+- sensitive user data;
+- raw private transcripts;
+- private infrastructure details unless intentionally public.
+
+Document secret-handling mechanisms, not actual secret values.
+
+## Maintenance Rules
+
+When docs change, verify the affected behavior.
+
+Where practical:
+
+- load example config files in tests;
+- test CLI examples or command parser behavior;
+- validate documented flags against real flags;
+- remove stale references;
+- update links after renames;
+- keep roadmap content out of non-roadmap docs.
+
+If documentation and code disagree, fix the documentation and/or open a roadmap item; do not leave aspirational behavior in current-behavior docs.
+
+Documentation is complete only when it matches the current code.
+
+## Documentation Change Checklist
+
+Before merging documentation changes, verify:
+
+- README is concise and orientation-focused.
+- `docs/architecture.md` describes development principles.
+- Future work appears only under `docs/roadmap/`.
+- User-facing docs avoid unnecessary internals.
+- Developer-facing docs preserve boundaries and invariants.
+- Config examples match the schema.
+- CLI examples match real commands and flags.
+- Defaults appear in the canonical config reference.
+- No secrets or private data are included.
+- Links are accurate.

docs/integrations/README.md

@@ -0,0 +1,15 @@
+# Integration Documentation Index
+
+## Audience
+Developers and LLM coding agents changing Narratio's external integration contracts.
+
+## Scope
+Implemented-only reference notes for the external systems Narratio currently integrates with.
+
+## Integration Docs
+- `audita.md`: Audita adapter invocation and validation contract.
+- `seriatim.md`: Seriatim normalize/merge/trim adapter contract.
+- `scriptorium.md`: Scriptorium run/render adapter contract.
+
+## Canonical Owner
+`docs/integrations/` is the canonical home for external integration reference notes per `docs/documentation/policy.md`.

docs/integrations/audita.md

@@ -1,147 +1,66 @@
-# Audita
+# Integration: audita
 
-Audita is a framework-first transcript correction application. The public `audita` package provides:
+## Purpose
+Define Narratio's adapter contract for transcript polishing via Audita CLI subprocess execution.
 
-- deterministic transcript normalization
-- token-batched module orchestration
-- concrete `glossary`, `homophones`, `spoken_word`, and `grammar` modules built on reusable proposal / validator contracts
-- structured run reporting and work-dir diagnostics
+## Inputs and Outputs
+Inputs (`audita.PolishRequest`):
+- merged transcript path
+- glossary path
+- output processed transcript path
+- optional report path (required when report enabled)
+- work dir
+- generated config path
+- stdout/stderr log paths
+- optional module/model/base URL and concurrency knobs
 
-The previous working implementation has been preserved as `audita_prototype` inside this repository. Its full regression suite lives under `tests/audita_prototype`.
+Outputs (`audita.PolishResult`):
+- processed transcript path
+- optional report path
+- generated config path
+- stdout/stderr log paths
+- exit code, duration, invoked binary
+- adapter metadata
 
-## Development
+## Boundaries
+Owns:
+- Deterministic CLI argument construction for `audita process`
+- Environment bridging for API credentials
+- Invocation config emission
+- Output validation for processed transcript and report
 
-This project is set up for `uv`.
+Does not own:
+- Upstream/downstream stage orchestration
+- Credential sourcing policy beyond required env-var presence check
 
-```sh
-uv sync --extra dev
-uv run pytest
-```
+## Config Fields Used
+Via `pipeline.audita.*` mapped in app/stage wiring:
+- `binary`, `timeout`, `llm_api_key_env`, `modules`, `base_url`, `model`
+- `transcript_description`, `config_path`, `output_schema`, `work_dir_retention`
+- `total_llm_concurrency`, `proposal_llm_concurrency`, `validation_model`, `validation_llm_concurrency`, `report`
 
-## Usage
+## External Adapters Used
+- Shared subprocess helper (`internal/adapters/subprocess`) to run CLI and capture logs.
 
-Process a transcript with the current framework implementation:
+## State and Manifest Behavior
+- No direct manifest writes.
+- Stage-level metadata records adapter provenance and credential-present signal.
+- Generated invocation YAML is written when `GeneratedConfigPath` is provided.
 
-```sh
-uv run audita process transcript.json --glossary glossary.yaml --output corrected.json
-```
+## Skip and Resume Behavior
+- Adapter has no skip/resume logic. Stage/runner controls this.
 
-The framework currently runs this default module sequence:
+## Failure Behavior
+- Constructor validation fails on invalid binary/timeout/schema/concurrency/URL values.
+- Run fails on missing required paths, missing required credential env var, subprocess errors, invalid processed JSON shape, or invalid report JSON.
+- Failures preserve stdout/stderr paths in returned result metadata.
 
-1. `glossary`
-2. `homophones`
-3. `glossary`
-4. `spoken_word`
-5. `grammar`
+## Tests to Inspect Before Changing
+- `internal/adapters/audita/subprocess_test.go`
+- `internal/adapters/audita/fake_test.go`
+- `internal/stage/polish_test.go`
 
-Resolved run instance names are auto-numbered for repeats, so the default report pipeline is:
-
-1. `glossary_1`
-2. `homophones`
-3. `glossary_2`
-4. `spoken_word`
-5. `grammar`
-
-The default module sequence is fully implemented today:
-
-- `glossary` proposes glossary-supported acoustic corrections
-- `homophones` proposes conservative homophone and mistranscription corrections
-- `spoken_word` proposes conservative dysfluency cleanup
-- `grammar` proposes punctuation, capitalization, and spacing cleanup only
-
-To run a custom module sequence, pass `--modules`:
-
-```sh
-uv run audita process transcript.json --glossary glossary.yaml --modules grammar --output corrected.json
-```
-
-To also write a structured JSON report:
-
-```sh
-uv run audita process transcript.json --glossary glossary.yaml --output corrected.json --report-json report.json
-```
-
-From a checked-out repository, you can also use the root launcher:
-
-```sh
-./audita process transcript.json --glossary glossary.yaml --output corrected.json
-```
-
-For a system-wide command, install the source tree under `/usr/local/src/audita`, sync dependencies there, and symlink the root launcher into your `PATH`:
-
-```sh
-cd /usr/local/src/audita
-uv sync --extra dev
-ln -s /usr/local/src/audita/audita /usr/local/bin/audita
-audita process transcript.json --glossary glossary.yaml --output corrected.json
-```
-
-Without `--output`, Audita writes the corrected transcript JSON to stdout and progress logs to stderr.
-`--report-json` writes a separate machine-readable run report and never mixes report data into stdout.
-
-Useful configuration can be supplied by CLI flag or environment variable. CLI flags take precedence over environment variables. Normal runs now require LLM API credentials, because the `glossary`, `homophones`, `spoken_word`, and `grammar` modules make real LLM calls. `AUDITA_LLM_API_KEY` and `--llm-api-key` are the preferred provider-neutral credential surfaces, while `OPENROUTER_API_KEY` remains supported as a backward-compatible fallback.
-
-| Environment variable | CLI flag | Default | Purpose |
-| --- | --- | --- | --- |
-| `AUDITA_MODULES` | `--modules` | `glossary,homophones,glossary,spoken_word,grammar` | Comma-separated logical module keys to run; CLI overrides the environment value |
-| `AUDITA_LLM_API_KEY` | `--llm-api-key` | unset | Preferred provider-neutral LLM API credential; CLI overrides both environment-key variants |
-| `AUDITA_VALIDATION_LLM_API_KEY` | `--validation-llm-api-key` | unset | Validation-phase LLM API credential; defaults to the primary LLM API key |
-| `AUDITA_MODEL` | `--model` | `openrouter/google/gemma-4-31b-it` | LLM model name sent to the configured OpenAI-compatible endpoint |
-| `AUDITA_VALIDATION_MODEL` | `--validation-model` | unset | Validation-phase LLM model; defaults to `AUDITA_MODEL` |
-| `AUDITA_BASE_URL` | `--base-url` | `https://openrouter.ai/api/v1` | OpenAI-compatible API base URL |
-| `AUDITA_VALIDATION_BASE_URL` | `--validation-base-url` | unset | Validation-phase OpenAI-compatible API base URL; defaults to `AUDITA_BASE_URL` |
-| `AUDITA_LLM_TIMEOUT_SECONDS` | `--llm-timeout-seconds` | `600` | Per-request timeout in seconds for LLM calls to the configured OpenAI-compatible endpoint |
-| `AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS` | `--validation-llm-timeout-seconds` | unset | Validation-phase per-request timeout in seconds; defaults to `AUDITA_LLM_TIMEOUT_SECONDS` |
-| `AUDITA_VALIDATION_MAX_PROMPT_TOKENS` | `--validation-max-prompt-tokens` | `2048` | Maximum estimated tokens per validation-phase LLM prompt batch |
-| `AUDITA_TARGET_SECTIONS` | `--target-sections` | unset | Exact number of contiguous proposal-stage transcript sections; errors if min/max token bounds cannot be satisfied |
-| `AUDITA_MAX_RETRIES` | `--max-retries` | `3` | Maximum Instructor retries for structured responses |
-| `AUDITA_VALIDATION_MAX_RETRIES` | `--validation-max-retries` | unset | Validation-phase structured-output retries; defaults to `AUDITA_MAX_RETRIES` |
-| `AUDITA_VALIDATION_LLM_CONCURRENCY` | `--validation-llm-concurrency` | unset | Validation-phase LLM concurrency; defaults to `AUDITA_LLM_CONCURRENCY` |
-| `AUDITA_MAX_SECTION_TOKENS` | `--max-section-tokens` | `8192` | Maximum estimated tokens per proposal-stage transcript section |
-| `AUDITA_MIN_SECTION_TOKENS` | `--min-section-tokens` | `2048` | Minimum estimated tokens per proposal-stage transcript section when balancing for concurrency |
-| `AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD` | `--glossary-confidence-threshold` | `0.8` | Minimum confidence required for glossary proposals to survive validation |
-| `AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD` | `--grammar-confidence-threshold` | `0.8` | Minimum confidence required for grammar proposals to survive validation |
-| `AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD` | `--homophones-confidence-threshold` | `0.8` | Minimum confidence required for homophone proposals to survive validation |
-| `AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD` | `--spoken-word-confidence-threshold` | `0.8` | Minimum confidence required for spoken-word proposals to survive validation |
-| `AUDITA_NORMALIZE_MAX_SEGMENT_GAP` | `--normalize-max-segment-gap` | `4.0` | Same-speaker gaps eligible for deterministic merging |
-| `AUDITA_NORMALIZE_ELLIPSIS_GAP` | `--normalize-ellipsis-gap` | `3.5` | Same-speaker gaps above this value are joined with ` ... ` |
-| `AUDITA_NORMALIZE_MAX_SEGMENT_DURATION` | `--normalize-max-segment-duration` | `60.0` | Maximum merged segment duration |
-| `AUDITA_NORMALIZE_MAX_SEGMENT_TOKENS` | `--normalize-max-segment-tokens` | `2048` | Maximum merged segment prompt payload size |
-| `AUDITA_WORK_DIR` | `--work-dir` | `/tmp/audita` | Per-run scratch diagnostics directory |
-| `AUDITA_WORK_DIR_RETENTION` | `--work-dir-retention` | `auto` | Whether to retain the per-run work directory: `auto`, `always`, or `never` |
-
-Set `AUDITA_MODULES=grammar` to run only the grammar module by default, or override it per command with `--modules`.
-
-Validation-phase LLM settings inherit from the primary `AUDITA_*` LLM settings by default. Set any of the `AUDITA_VALIDATION_*` values only when you want LLM-backed validators to use a different model, endpoint, credential, timeout, retry budget, or concurrency level.
-
-OpenRouter remains the default out of the box:
-
-```sh
-export AUDITA_LLM_API_KEY=your-openrouter-key
-audita process transcript.json --glossary glossary.yaml --output corrected.json
-```
-
-You can point Audita at any OpenAI-compatible endpoint by changing `AUDITA_BASE_URL` and, if needed, `AUDITA_MODEL`. For example, a local vLLM server:
-
-```sh
-export AUDITA_LLM_API_KEY=local-dev-key
-export AUDITA_BASE_URL=http://localhost:8000/v1
-export AUDITA_MODEL=meta-llama/Llama-3.1-8B-Instruct
-audita process transcript.json --glossary glossary.yaml --output corrected.json
-```
-
-Or the actual OpenAI API:
-
-```sh
-export AUDITA_LLM_API_KEY=your-openai-key
-export AUDITA_BASE_URL=https://api.openai.com/v1
-export AUDITA_MODEL=gpt-4.1-mini
-audita process transcript.json --glossary glossary.yaml --output corrected.json
-```
-
-`AUDITA_WORK_DIR` stores per-run diagnostics while processing. Under the default `AUDITA_WORK_DIR_RETENTION=auto`, clean successful runs are removed, while failed runs and successful runs with final skipped corrections are preserved. Use `always` to keep every run directory and `never` to remove successful run directories even when skips remain.
-Failed runs always preserve the run directory and include an authoritative `report.json` alongside normalization and prompt/response diagnostics.
-
-## Prototype Archive
-
-The archived prototype remains importable as `audita_prototype` and is still covered by its original regression suite. This is intentional: the new `audita` package is a framework-oriented rewrite, not a thin wrapper around the old code.
+## Architectural Invariants
+- Processed output must be valid JSON with top-level `segments` array.
+- When report is enabled, report output must be valid JSON.
+- If `llm_api_key_env` is configured, credential must be present in environment.

docs/integrations/scriptorium.md

@@ -1,339 +1,64 @@
-# Narratio -> Scriptorium CLI Integration
-
-## 1. Purpose
-
-This document defines how Narratio should invoke Scriptorium through the **public CLI**.
-
-This is a **subprocess integration contract**, not an internal Go API contract.
-
-## 2. Assumptions
-
-- `scriptorium` is installed and available on `PATH`.
-- Scriptorium is configured with `config.yml`.
-- `config.yml` provides `prompt_dir`, `profile_dir`, and `schema_dir` as needed.
-- Prompt and profile libraries are already deployed for the environment.
-- Narratio provides prepared artifact files (for example polished transcript, glossary, previous recap, campaign notes).
-- Initial integration is synchronous subprocess execution.
-- Narratio remains the orchestrator.
-
-In normal operation, Narratio does not need to pass `--prompt-dir` and `--profile-dir` if they are supplied by Scriptorium config.
-
-Narratio may pass `--config <PATH>` when it must use a non-default Scriptorium config file.
-
-## 3. Core Commands Narratio May Call
-
-Primary commands for subprocess integration:
-
-- `scriptorium run`
-- `scriptorium render`
-
-For production generation, use `scriptorium run`.
-
-`scriptorium render` is for debugging, dry-runs, test assertions, and validating command construction without LLM execution.
-
-Note: `scriptorium serve` and HTTP API exist, but they are not the initial integration path.
-
-## 4. Command Selection Guidance
-
-- Use `run` to generate an output artifact.
-- Use `render` to inspect the prepared prompt and effective settings without calling the LLM.
-- Use `render --format json` when Narratio/tests need structured prepare output.
-
-## 5. Recommended `run` Invocation Shape
-
-Production shape:
-
-```bash
-scriptorium run \
-  --prompt <prompt_id> \
-  --input transcript=<processed-transcript-path> \
-  --out <output-artifact-path>
-```
-
-Common optional additions:
-
-- `--config <path>`: use a specific Scriptorium config file.
-- `--profile <profile_id>`: override prompt default profile.
-- `--var name=value` (repeatable): small metadata values.
-- `--input name=path` (repeatable): additional named artifacts.
-- `--timeout <duration>`: per-run timeout override.
-- Runtime model override flags (`--llm-base-url`, `--model`, etc.) only for exceptional/operator-directed cases.
-
-## 6. Recommended `render` Invocation Shape
-
-Human-readable debug shape:
-
-```bash
-scriptorium render \
-  --prompt <prompt_id> \
-  --input transcript=<processed-transcript-path> \
-  --format text
-```
-
-Structured debug/test shape:
-
-```bash
-scriptorium render \
-  --prompt <prompt_id> \
-  --input transcript=<processed-transcript-path> \
-  --format json \
-  --out <render-debug-path>
-```
-
-`render` does **not** call the LLM, does **not** validate model output, and does **not** perform repair.
-
-## 7. Inputs
-
-- Pass inputs as repeated `--input name=path` flags.
-- `name` must match the Prompt Definition input name.
-- Prefer absolute paths, or paths relative to a working directory controlled by Narratio.
-- Pass Audita output as the primary transcript input.
-- Additional inputs may include glossary, previous recap, campaign notes, event logs, final state maps, or other prompt-specific artifacts.
-- Scriptorium reads input files directly; Narratio does not need to inline file content for CLI use.
-
-## 8. Variables
-
-Use repeated `--var name=value` for small metadata values.
-
-Typical examples:
-
-- `session_date`
-- `session_id`
-- `campaign_name`
-- `previous_session_id`
-- `output_kind`
-
-Large content belongs in input files, not `--var` values.
-
-## 9. Prompt IDs and Output Artifact Types
-
-Narratio should treat prompt IDs as configuration, not hardcoded business logic.
-
-Narratio config may map stage/output names to prompt IDs, for example:
-
-- session recap prompt
-- structured event extraction prompt
-- glossary suggestion prompt
-- player-facing summary prompt
-
-Prompt IDs used by Narratio should come from the deployed Scriptorium prompt library.
-
-## 10. Profiles
-
-- Prompts may declare `default_profile`.
-- Narratio may omit `--profile` to use prompt default profile.
-- Narratio may pass `--profile` to force profile selection.
-- This enables environment/profile selection like `local-fast`, `local-quality`, `frontier`, `batch`, or test profiles.
-- Profile names should generally be Narratio configuration values.
-
-## 11. Runtime Overrides
-
-Supported runtime override flags:
-
-- `--llm-base-url`
-- `--model`
-- `--api-key-env`
-- `--temperature`
-- `--max-tokens`
-- `--top-p`
-- `--timeout`
-
-Guidance:
-
-- Keep normal model/runtime settings in Execution Profiles.
-- Use runtime overrides only for explicit per-run exceptions, tests, or operator overrides.
-- Never pass raw API keys on the command line.
-- `--api-key-env` names an environment variable; Narratio must ensure that variable is set in subprocess environment.
-
-## 12. Config Behavior
-
-- Default config path: `/etc/scriptorium/config.yml`.
-- `--config <PATH>` overrides default path.
-- Missing default config is allowed by Scriptorium.
-- If `--config` is provided explicitly, the file must exist and be valid.
-- CLI flags override `config.yml`.
-- `config.yml` overrides built-in application defaults.
-
-Narratio can either:
-
-- rely on system default config path, or
-- carry an explicit config path and pass `--config`.
-
-## 13. Environment Handling
-
-Subprocess environment recommendations:
-
-- Pass through required API-key environment variables referenced by `api_key_env`.
-- Do not pass raw API keys as CLI arguments.
-- Avoid logging full environment dumps.
-- Capture stdout and stderr separately.
-- Use a controlled working directory.
-- Prefer absolute artifact paths.
-
-## 14. Output Handling
-
-For `scriptorium run`:
-
-- Use `--out` when Narratio needs durable artifact files.
-- Without `--out`, artifact content is written to stdout.
-- Preferred orchestration pattern: always use `--out`, then treat the file as stage output artifact.
-- Capture stderr for diagnostics.
-
-For `scriptorium render`:
-
-- Use `--out` to store render diagnostics.
-- Use `--format json` when tests need to inspect selected profile, effective runtime settings, input hashes, prompt hash, and rendered messages.
-
-## 15. Exit Status and Errors
-
-Current CLI behavior (verified from implementation/tests):
-
-- `0`: success.
-- `1`: runtime/parse/config/load/render/generation/IO error.
-- `2`: run completed but output validation failed (`ValidationFailed`).
-
-Additional details:
-
-- On `run`, output artifact write happens before exit code selection. If validation fails, artifact may still be written and exit code is `2`.
-- `stderr` carries both errors and normal run summary output; non-empty stderr alone does not imply failure.
-- `render` returns `0` on success and `1` on failures.
-
-Narratio should treat non-zero exit codes as failed stage execution, but may record generated artifact paths if a run exited `2` and output file exists.
-
-## 16. Recommended Narratio Integration Pattern
-
-1. Build CLI args from Narratio stage configuration.
-2. Use subprocess context cancellation/timeout.
-3. Pass absolute input paths.
-4. Pass `--out` to a session-scoped artifact path.
-5. Add `--var` metadata values.
-6. Optionally add `--config`.
-7. Optionally add `--profile`.
-8. Ensure required API-key env vars are present.
-9. Run subprocess synchronously.
-10. Capture stdout/stderr separately.
-11. On success, store output artifact path and invocation metadata in stage artifacts.
-12. On failure, store exit code and stderr diagnostics in stage status.
-
-## 17. Suggested Narratio Configuration Shape
-
-Illustrative `pipeline.yml` shape:
-
-```yaml
-scriptorium:
-  binary: scriptorium
-  config_path: /etc/scriptorium/config.yml
-  timeout: 10m
-  render_debug: false
-  artifacts:
-    session_recap:
-      enabled: true
-      prompt_id: dnd.session_recap
-      profile_id: local-quality   # optional
-      output_path: artifacts/session_recap.md
-      timeout: 10m
-      render_debug: false          # optional artifact override
-      inputs:
-        transcript:
-          source: trimmed_transcript
-          required: true
-        previous_recap:
-          source: previous_session_artifact
-          artifact: session_recap
-          path: ""                 # optional
-          required: false
-      vars:
-        session_id: true
-        session_date: true
-        campaign_name: true
-        previous_session_id: true
-        output_kind: session_recap
-```
-
-The key idea: map Narratio artifact names to prompt ID, optional profile, expected inputs, vars, and output destination.
-
-## 18. Testing Strategy for Narratio Integration
-
-- Use `scriptorium render --format json` to verify command construction without LLM calls.
-- Use dedicated test prompt/profile libraries for integration tests.
-- Use small fixture transcripts.
-- Verify missing-input failure behavior.
-- Verify prompt `default_profile` behavior.
-- Verify explicit `--profile` override behavior.
-- Verify `--config` behavior (default and explicit).
-- Verify output file creation when `--out` is used.
-- Verify stderr capture on failures.
-- Avoid real API keys in tests.
-
-## 19. Security and Privacy Notes
-
-- Never pass raw API keys on command line.
-- Do not log full rendered prompts by default; transcripts may contain sensitive content.
-- Avoid logging prompt content unless explicit debug mode is enabled.
-- Treat generated artifacts as potentially sensitive.
-- Use session-scoped, access-controlled output paths.
-- `api_key_env` names should come from environment management, not embedded secrets.
-
-## 20. Initial D&D Artifact Generation Examples
-
-These are examples only. Use prompt IDs from the deployed prompt library.
-
-Session recap:
-
-```bash
-scriptorium run \
-  --prompt dnd.session_recap \
-  --input transcript=/work/session-42/transcript.polished.md \
-  --input glossary=/work/session-42/glossary.yml \
-  --out /work/session-42/artifacts/session_recap.md
-```
-
-Structured events:
-
-```bash
-scriptorium run \
-  --prompt dnd.structured_events \
-  --input transcript=/work/session-42/transcript.polished.md \
-  --out /work/session-42/artifacts/structured_events.json
-```
-
-Glossary suggestions:
-
-```bash
-scriptorium run \
-  --prompt dnd.glossary_suggestions \
-  --input transcript=/work/session-42/transcript.polished.md \
-  --input previous_recap=/work/session-41/artifacts/session_recap.md \
-  --out /work/session-42/artifacts/glossary_suggestions.md
-```
-
-Player-facing summary:
-
-```bash
-scriptorium run \
-  --prompt dnd.player_summary \
-  --input transcript=/work/session-42/transcript.polished.md \
-  --input structured_events=/work/session-42/artifacts/structured_events.json \
-  --out /work/session-42/artifacts/player_summary.md
-```
-
-## 21. Non-Goals
-
-Initial Narratio integration should not:
-
-- call Scriptorium internal Go packages
-- use HTTP API as the primary path
-- expect Scriptorium to read S3 refs directly
-- make Scriptorium responsible for Narratio stage state
-- make Scriptorium responsible for notification
-- require Scriptorium to understand D&D workflow semantics beyond prompt definitions
-
-## 22. Future Extension Notes
-
-Possible later extensions:
-
-- HTTP API integration
-- S3 artifact references if Scriptorium adds S3 reader support
-- richer render diagnostics and policy controls
-- token budgeting/prompt-size checks
-- batch execution if Scriptorium later adds batch support
+# Integration: scriptorium
+
+## Purpose
+Define Narratio's adapter contract for Scriptorium artifact generation and render-debug subprocess invocations.
+
+## Inputs and Outputs
+Inputs:
+- `RunArtifactRequest`: binary, config path, prompt/profile IDs, input map, vars map, timeout, output path, logs/config paths, optional API env and working dir
+- `RenderArtifactRequest`: same core fields for render mode
+
+Outputs (`ArtifactResult`):
+- output path
+- stdout/stderr log paths
+- generated config path
+- exit code and duration
+- command mode (`run` or `render`)
+- prompt/profile provenance
+- validation failure signal
+- adapter metadata
+
+## Boundaries
+Owns:
+- Deterministic CLI arg construction for `scriptorium run` and `scriptorium render`
+- Common request validation
+- Invocation config emission
+- Output existence/non-empty checks
+- Validation-failure mapping for run exit code 2
+
+Does not own:
+- Artifact selection policy (`analyze` stage)
+- Bounds semantic validation (`trim` stage)
+
+## Config Fields Used
+Via `pipeline.scriptorium.*` and stage-level artifact config:
+- `binary`, `config_path`, `timeout`, `render_debug`
+- artifact-level `prompt_id`, `profile_id`, `timeout`, `inputs`, `vars`, `output_path`
+
+## External Adapters Used
+- Shared subprocess helper (`internal/adapters/subprocess`).
+
+## State and Manifest Behavior
+- No direct manifest writes.
+- Stage metadata records adapter outputs and command mode.
+- Generated invocation YAML is written when requested.
+
+## Skip and Resume Behavior
+- Adapter has no skip/resume logic. Stage/runner controls execution.
+
+## Failure Behavior
+- Request validation fails for missing binary/prompt/output, invalid timeout, invalid input/var names, or missing required API env var.
+- Subprocess errors bubble with command context.
+- `run` exit code 2 is treated as `ValidationFailed=true` and surfaced as error by calling stage.
+- Successful subprocess still fails if output file is missing/empty.
+
+## Tests to Inspect Before Changing
+- `internal/adapters/scriptorium/subprocess_test.go`
+- `internal/adapters/scriptorium/fake_test.go`
+- `internal/stage/analyze_test.go`
+- `internal/stage/trim_test.go`
+
+## Architectural Invariants
+- Both modes require explicit timeout > 0.
+- Input/var maps are sorted into deterministic CLI argument order.
+- Run-mode validation failures are represented explicitly, not silently skipped.

docs/integrations/seriatim.md

@@ -1,403 +1,60 @@
-# seriatim
-
-`seriatim` merges per-speaker WhisperX-style JSON transcripts into a single JSON transcript that preserves speaker identity and chronological order.
-
-The current implementation supports the `merge` command. It reads one or more input JSON files, optionally maps each input file to a canonical speaker using `speakers.yml`, sorts all segments by timestamp, detects and resolves overlaps when word-level timing is available, assigns consecutive numeric `id` values, and writes a merged JSON artifact.
-
-## Usage
-
-Run from source:
-
-```sh
-go run ./cmd/seriatim merge \
-  --input-file samples/raw/2026-04-19-Eric_Rakestraw.json \
-  --input-file samples/raw/2026-04-19-Mike_Brown.json \
-  --output-file merged.json
-```
-
-Optional report output:
-
-```sh
-go run ./cmd/seriatim merge \
-  --input-file eric.json \
-  --input-file mike.json \
-  --output-file merged.json \
-  --report-file report.json
-```
-
-## CLI
-
-```text
-seriatim merge [flags]
-```
-
-Global flags:
-
-| Flag | Description |
-| --- | --- |
-| `--help` | Show command help. |
-| `--version` | Show application version. Local builds default to `dev`; release builds inject the release version. |
-
-`merge` flags:
-
-| Flag | Required | Default | Description |
-| --- | --- | --- | --- |
-| `--input-file` | Yes | none | Input transcript JSON file. Repeat once per speaker/input file. |
-| `--output-file` | Yes | none | Merged transcript JSON output path. |
-| `--report-file` | No | none | Optional report JSON output path. |
-| `--speakers` | No | none | Speaker map YAML file. When omitted, input file basenames are used as speaker labels. |
-| `--autocorrect` | No | none | Autocorrect rules YAML file. When omitted, the default `autocorrect` module leaves text unchanged. |
-| `--input-reader` | No | `json-files` | Input reader module. |
-| `--output-modules` | No | `json` | Comma-separated output modules. |
-| `--output-schema` | No | `seriatim-intermediate` | JSON output contract. Allowed values are `seriatim-minimal`, `seriatim-intermediate`, and `seriatim-full`. If omitted, the runtime default is used; consumers that depend on a specific shape should set this explicitly. |
-| `--preprocessing-modules` | No | `validate-raw,normalize-speakers,trim-text` | Comma-separated preprocessing modules, evaluated in order. |
-| `--postprocessing-modules` | No | `detect-overlaps,resolve-overlaps,backchannel,filler,resolve-danglers,coalesce,detect-overlaps,autocorrect,assign-ids,validate-output` | Comma-separated postprocessing modules, evaluated in order. |
-| `--coalesce-gap` | No | `3.0` | Maximum same-speaker gap in seconds for `coalesce`; also used as the `resolve-overlaps` context window. Must be a non-negative float. |
-
-Environment variables:
-
-| Environment Variable | Default | Description |
-| --- | --- | --- |
-| `SERIATIM_OUTPUT_SCHEMA` | `seriatim-intermediate` | Output schema used when `--output-schema` is not explicitly provided. Allowed values are `seriatim-minimal`, `seriatim-intermediate`, and `seriatim-full`. The CLI flag takes precedence. |
-| `SERIATIM_OVERLAP_WORD_RUN_GAP` | `1.0` | Maximum gap in seconds between adjacent timed words when `resolve-overlaps` builds word-run replacement segments. Must be a positive float. |
-| `SERIATIM_OVERLAP_WORD_RUN_REORDER_WINDOW` | `1.0` | Near-start window in seconds for ordering replacement word runs shortest-first. Must be a positive float. |
-| `SERIATIM_BACKCHANNEL_MAX_DURATION` | `2.0` | Maximum duration in seconds for `backchannel` classification. Must be a positive float. |
-| `SERIATIM_FILLER_MAX_DURATION` | `1.25` | Maximum duration in seconds for `filler` classification. Must be a positive float. |
-
-## Input JSON Format
-
-Each input file must be valid JSON with a top-level `segments` array. The current parser accepts the WhisperX segment subset needed for merging:
-
-```json
-{
-  "segments": [
-    {
-      "start": 1.25,
-      "end": 3.5,
-      "text": "Hello there.",
-      "words": [
-        {"word": "Hello", "start": 1.25, "end": 1.55, "score": 0.98},
-        {"word": "there.", "start": 1.7, "end": 2.0}
-      ]
-    }
-  ]
-}
-```
-
-Required segment fields:
-
-- `start`: number, must be `>= 0`.
-- `end`: number, must be `>= start`.
-- `text`: string.
-
-Optional word fields:
-
-- `words`: array of word timing objects.
-- `words[].word`: string.
-- `words[].start`: optional number, must be `>= 0` when present.
-- `words[].end`: optional number, must be `>= start` when present with `start`.
-- `words[].score`: optional number.
-- `words[].speaker`: optional raw speaker label string.
-
-Word-level timing is preserved internally for overlap resolution. If a word is missing `start` or `end`, seriatim keeps the word text, emits a warning in the optional report, and does not use that word as a timing anchor. Word timing is not emitted in the final JSON artifact.
-
-## Speaker Map Format
-
-`speakers.yml` maps input files to canonical speaker names using ordered substring rules:
-
-This file is optional. If `--speakers` is omitted, `seriatim` uses each input file basename as the segment speaker label.
-
-```yaml
-match:
-  - speaker: "Eric Rakestraw"
-    match:
-      - "Eric_Rakestraw"
-      - "Eric"
-
-  - speaker: "Mike Brown"
-    match:
-      - "Mike_Brown"
-      - "mb"
-```
-
-For each `--input-file`, `seriatim` takes the file basename and evaluates the rules in order. The first rule with a matching substring wins, and no later rules are evaluated.
-
-For example, this input:
-
-```text
-samples/raw/2026-04-19-Eric_Rakestraw.json
-```
-
-matches this rule because the basename contains `Eric_Rakestraw`:
-
-```yaml
-- speaker: "Eric Rakestraw"
-  match:
-    - "Eric_Rakestraw"
-```
-
-Important details:
-
-- Matching is against the input file basename, not the full path.
-- Matching is case-insensitive.
-- Rules are evaluated from first to last.
-- Each rule must have a non-empty `speaker`.
-- Each rule must have at least one non-empty `match` string.
-- Duplicate speaker names are invalid.
-- Every input file must match at least one rule or the command fails.
-
-Deprecated old format:
-
-```yaml
-inputs:
-  eric.json:
-    speaker: "Eric Rakestraw"
-```
-
-The old `inputs:` direct mapping format is no longer supported.
-
-## Output JSON Format
-
-`--output-modules json` controls the writer. `--output-schema` controls the JSON contract that writer serializes.
-
-The named schemas are stable public contracts. If a consumer depends on a specific shape, it should request that schema explicitly at runtime. The runtime default selection may change in a future release.
-
-The `seriatim-intermediate` schema is the current default selection when neither `--output-schema` nor `SERIATIM_OUTPUT_SCHEMA` is set. It stays close to the minimal schema, but adds optional `categories` on each segment:
-
-```json
-{
-  "metadata": {
-    "application": "seriatim",
-    "version": "dev",
-    "output_schema": "seriatim-intermediate"
-  },
-  "segments": [
-    {
-      "id": 1,
-      "start": 1.25,
-      "end": 3.5,
-      "speaker": "Eric Rakestraw",
-      "text": "Hello there.",
-      "categories": ["backchannel"]
-    }
-  ]
-}
-```
-
-The `seriatim-full` schema uses the full seriatim envelope:
-
-```json
-{
-  "metadata": {
-    "application": "seriatim",
-    "version": "dev",
-    "input_reader": "json-files",
-    "input_files": ["eric.json", "mike.json"],
-    "preprocessing_modules": ["validate-raw", "normalize-speakers", "trim-text"],
-    "postprocessing_modules": ["detect-overlaps", "resolve-overlaps", "backchannel", "filler", "resolve-danglers", "coalesce", "detect-overlaps", "autocorrect", "assign-ids", "validate-output"],
-    "output_modules": ["json"]
-  },
-  "segments": [
-    {
-      "id": 1,
-      "source": "eric.json",
-      "source_segment_index": 0,
-      "speaker": "Eric Rakestraw",
-      "start": 1.25,
-      "end": 3.5,
-      "text": "Hello there.",
-      "overlap_group_id": 1
-    },
-    {
-      "id": 2,
-      "source": "eric.json",
-      "source_ref": "word-run:1:1:1",
-      "derived_from": ["eric.json#0"],
-      "speaker": "Eric Rakestraw",
-      "start": 2.0,
-      "end": 2.5,
-      "text": "Resolved word run",
-      "categories": ["backchannel"]
-    }
-  ],
-  "overlap_groups": [
-    {
-      "id": 1,
-      "start": 1.25,
-      "end": 4.0,
-      "segments": ["eric.json#0", "mike.json#0"],
-      "speakers": ["Eric Rakestraw", "Mike Brown"],
-      "class": "unknown",
-      "resolution": "unresolved"
-    }
-  ]
-}
-```
-
-The `seriatim-minimal` schema emits minimal metadata and compact ordered segments:
-
-```json
-{
-  "metadata": {
-    "application": "seriatim",
-    "version": "dev",
-    "output_schema": "seriatim-minimal"
-  },
-  "segments": [
-    {
-      "id": 1,
-      "start": 1.25,
-      "end": 3.5,
-      "speaker": "Eric Rakestraw",
-      "text": "Hello there."
-    }
-  ]
-}
-```
-
-Minimal output intentionally omits categories, overlap groups, source/provenance fields, and pipeline configuration metadata.
-
-Intermediate output intentionally omits overlap groups and source/provenance fields, but keeps optional `categories` and minimal metadata.
-
-Segments are sorted deterministically by:
-
-```text
-(start, end, source, source_segment_index/source_ref, speaker)
-```
-
-Final segment IDs are assigned after sorting and start at `1`.
-
-The public Go output contract is available from:
-
-```go
-import "gitea.maximumdirect.net/eric/seriatim/schema"
-```
-
-The same package embeds machine-readable JSON Schemas in `schema/full-output.schema.json`, `schema/intermediate-output.schema.json`, and `schema/minimal-output.schema.json`. The default `validate-output` postprocessor validates the selected output shape and verifies final segment IDs are present, sequential, and start at `1`.
-
-## Overlap Detection
-
-The default postprocessing pipeline detects overlapping segment groups.
-
-Overlap behavior:
-
-- A strict timing overlap is required: `next.start < current_group_end`.
-- Segments that only touch at a boundary are not grouped.
-- Groups require at least two distinct speakers.
-- Transitive overlaps are grouped together.
-- Segments in detected groups receive `overlap_group_id`.
-- `overlap_groups[].segments` contains stable references in `source#source_segment_index` format.
-- `class` is currently `unknown`.
-- `resolution` is `unresolved` until `resolve-overlaps` replaces the group.
-
-## Overlap Resolution
-
-The default postprocessing pipeline runs `detect-overlaps`, then `resolve-overlaps`, then `backchannel`, then `filler`, then `resolve-danglers`, then `coalesce`, then a second `detect-overlaps` pass.
-
-For each detected overlap group, `resolve-overlaps` uses preserved WhisperX word timing to build smaller word-run replacement segments:
-
-- The resolution window expands the detected overlap group by `--coalesce-gap` seconds on both sides.
-- Nearby same-speaker context segments are included when they intersect the expanded window and their start or end is within `--coalesce-gap` of the original overlap boundary.
-- Once a segment is selected for replacement, all timed words from that segment participate in word-run construction; the window controls segment selection, not per-word clipping.
-- Context segments that are part of another detected overlap group are not pulled into the current group.
-- Untimed words are included in replacement text in original word order when nearby timed words create a replacement run.
-- Untimed words do not affect replacement segment start/end times or word-run gap splitting.
-- Words for the same speaker are merged into one run when the gap between adjacent words is no greater than `SERIATIM_OVERLAP_WORD_RUN_GAP`.
-- The default word-run gap is `1.0` seconds.
-- Set `SERIATIM_OVERLAP_WORD_RUN_GAP` to a positive number of seconds to override the default.
-- Near-start replacement word runs are reordered so shorter segments come first when adjacent starts are within `SERIATIM_OVERLAP_WORD_RUN_REORDER_WINDOW`.
-- The default word-run reorder window is `1.0` seconds.
-- Set `SERIATIM_OVERLAP_WORD_RUN_REORDER_WINDOW` to a positive number of seconds to override the default.
-- Replacement segment text is built by joining word text with single spaces.
-- Replacement segments include `source_ref` and `derived_from`.
-- Replacement segments omit `source_segment_index` because they are derived from one or more original segments.
-- Resolved overlap groups are removed before the second detection pass.
-- Replacement segments are left without `overlap_group_id` until the second detection pass annotates any remaining overlap.
-- If a speaker has no usable word timing in a group, that speaker's original segment is kept.
-- If no speakers in a group have usable word timing, the original group and annotations remain unchanged.
-
-## Backchannels
-
-The default pipeline runs `backchannel` before `coalesce`. It tags short acknowledgement segments with:
-
-```json
-"categories": ["backchannel"]
-```
-
-Backchannel matching is case-insensitive, ignores punctuation for matching and word-count purposes, trims surrounding whitespace, and requires a matching acknowledgement phrase, no more than three whitespace-delimited words, and duration no greater than `SERIATIM_BACKCHANNEL_MAX_DURATION` seconds. The default maximum duration is `2.0` seconds.
-
-## Fillers
-
-The default pipeline runs `filler` after `backchannel` and before `coalesce`. It tags short filler utterances with:
-
-```json
-"categories": ["filler"]
-```
-
-Filler matching is case-insensitive, ignores punctuation for matching and word-count purposes, trims surrounding whitespace, and requires only filler tokens such as `um`, `uh`, `er`, `erm`, `ah`, `eh`, `hmm`, `mm`, or repeated combinations of those tokens. Matching segments must contain no more than three whitespace-delimited words and have duration no greater than `SERIATIM_FILLER_MAX_DURATION` seconds. The default maximum duration is `1.25` seconds.
-
-## Dangler Resolution
-
-The default pipeline runs `resolve-danglers` before `coalesce` and before the second overlap detection pass. It repairs short derived fragments when they share provenance with a nearby segment:
-
-- Dangling-end fragments have no more than two words and end in punctuation.
-- Dangling-start fragments have no more than two words.
-- Matching uses same-speaker segments with any shared `derived_from` value.
-- Merged segments use `source_ref` values such as `resolve-danglers:1`, keep the target segment's transcript position, and union `derived_from`.
-
-## Coalescing
-
-The default pipeline runs `coalesce` after `resolve-danglers` and before the second overlap detection pass. It merges adjacent same-speaker segments in the transcript's current order when `next.start - current.end <= --coalesce-gap`.
-
-Coalesced segments use `source_ref` values such as `coalesce:1`, include `derived_from`, and omit `source_segment_index`.
-
-Different-speaker backchannel and filler segments do not block coalescing of surrounding same-speaker segments. Same-speaker backchannel and filler segments are merged normally when they are within `--coalesce-gap`. When same-speaker segments are coalesced, any `backchannel` or `filler` category from the merged inputs is dropped from the coalesced segment.
-
-## Autocorrect
-
-Autocorrect is included in the default postprocessing pipeline. If `--autocorrect` is omitted, the module leaves transcript text unchanged and records a skip event in the optional report.
-
-Enable corrections by passing `--autocorrect`:
-
-```sh
-go run ./cmd/seriatim merge \
-  --input-file input.json \
-  --autocorrect autocorrect.yml \
-  --output-file merged.json
-```
-
-`autocorrect.yml` format:
-
-```yaml
-autocorrect:
-  - target: "Hrank"
-    match:
-      - "hrank"
-      - "Frank"
-
-  - target: "Mike Brown"
-    match:
-      - "Mike Pat"
-```
-
-Matching behavior:
-
-- Matching is case-sensitive.
-- Matches apply only to whole tokens, not substrings inside larger words.
-- Punctuation and whitespace can surround a match.
-- Multi-word and hyphenated matches are supported.
-- Duplicate match strings are invalid, including duplicates across separate rules.
-
-## Current Limitations
-
-- Only JSON input is supported.
-- Overlap resolution depends on WhisperX word timing; groups without usable word timing remain unresolved.
-- Alternate output formats are not implemented yet.
-
-## Release Builds
-
-Local builds record version metadata as `dev`. Release builds should inject the release version with `ldflags`:
-
-```sh
-go build -ldflags "-X gitea.maximumdirect.net/eric/seriatim/internal/buildinfo.Version=v1.0.0" ./cmd/seriatim
-```
+# Integration: seriatim
+
+## Purpose
+Define Narratio's adapter contract for merge, normalize, and trim subprocess invocations of Seriatim.
+
+## Inputs and Outputs
+Inputs:
+- `MergeRequest`: raw/normalized transcript inputs, output path, optional report, speaker/autocorrect paths, logs/config
+- `NormalizeRequest`: input transcript, output path, schema, optional report, timeout/log/config
+- `TrimRequest`: input transcript, output path, keep selector, timeout/log/config
+
+Outputs:
+- `MergeResult`, `NormalizeResult`, `TrimResult` with output paths, logs/config paths, exit code, duration, binary provenance, and metadata.
+
+## Boundaries
+Owns:
+- Validated deterministic CLI invocation construction
+- Optional env tuning propagation for merge
+- Invocation config file emission
+- JSON output validation
+
+Does not own:
+- Transcript input selection/promotion logic (stage-owned)
+- Bounds computation (scriptorium/trim-stage-owned)
+
+## Config Fields Used
+Via `pipeline.seriatim.*` mapped in app/stage wiring:
+- `binary`, `timeout`, `output_schema`, `coalesce_gap`, `report`
+- `env.overlap_word_run_gap`
+- `env.overlap_word_run_reorder_window`
+- `env.backchannel_max_duration`
+- `env.filler_max_duration`
+
+## External Adapters Used
+- Shared subprocess helper (`internal/adapters/subprocess`).
+
+## State and Manifest Behavior
+- No direct manifest writes.
+- Stage metadata consumes adapter result fields and preserves generated config/log references.
+
+## Skip and Resume Behavior
+- Adapter has no skip/resume logic. Runner controls stage execution.
+
+## Failure Behavior
+- Constructor fails for invalid binary/timeout/output-schema/coalesce-gap.
+- Merge fails on missing output path/inputs/report path (if enabled), subprocess errors, invalid merged output JSON, invalid report JSON.
+- Normalize fails on missing input/output, invalid schema, subprocess errors, invalid normalized output JSON shape, invalid report JSON.
+- Trim fails on missing input/output/keep selector, subprocess errors, invalid trimmed output JSON shape.
+
+## Tests to Inspect Before Changing
+- `internal/adapters/seriatim/subprocess_test.go`
+- `internal/adapters/seriatim/fake_test.go`
+- `internal/stage/merge_test.go`
+- `internal/stage/normalize_test.go`
+- `internal/stage/trim_test.go`
+
+## Architectural Invariants
+- Supported output schemas are limited to `seriatim-minimal`, `seriatim-intermediate`, `seriatim-full`.
+- Normalize/trim outputs must include `segments` arrays.
+- Merge/normalize/trim all route through deterministic subprocess invocation.

docs/internal/README.md

@@ -0,0 +1,28 @@
+# Internal Documentation Index
+
+## Audience
+Developers and LLM coding agents changing Narratio internals.
+
+## Scope
+Implementation-accurate contracts for workspace/state, manifests, stages, artifact resolution, and adapter boundaries.
+
+## Component Docs
+- `adapters.md`: external adapter map, runtime wiring, and boundary ownership.
+- `storage.md`: remote storage backend contracts and object-store invariants.
+- `manifest.md`: session/run manifest schemas, lifecycle transitions, and persistence semantics.
+- `artifacts.md`: built-in artifact registry, runtime artifact catalog, and source-resolution behavior.
+- `workspace.md`: local state model, manifests, run-local layout, promotion, and cleanup invariants.
+- `stage-prepare.md`: input materialization and provenance capture.
+- `stage-transcribe.md`: WhisperX transcript generation.
+- `stage-merge.md`: Seriatim normalization + merge.
+- `stage-polish.md`: Audita transcript polishing.
+- `stage-normalize.md`: post-polish normalization.
+- `stage-trim.md`: bounds-driven transcript trimming.
+- `stage-analyze.md`: dependency-ordered Scriptorium artifact generation for selected configured artifacts.
+- `stage-archive.md`: archive upload and current-pointer publish contract.
+
+## External Integration Notes
+- `../integrations/README.md`: canonical location for external integration contracts (`audita.md`, `seriatim.md`, `scriptorium.md`).
+
+## Canonical Owner
+`docs/internal/` is the canonical home for implemented internals per `docs/documentation/policy.md`.

docs/internal/adapters.md

@@ -0,0 +1,79 @@
+# Internal: Adapters
+
+## Purpose
+Describe the external adapter boundaries used by Narratio stages and app orchestration, including default runtime wiring.
+
+## Inputs and outputs
+Inputs:
+- Stage requests passed through adapter interfaces (for example transcription, merge/normalize/trim, polish, artifact generation, object-store operations, notifications).
+- Resolved config values used to construct default adapters.
+
+Outputs:
+- Adapter-specific result structs (paths, metadata, status/attempt info, duration/exit details).
+- Adapter errors returned to stage/app orchestration.
+
+## Boundaries
+Owns:
+- Transport/process/SDK details at system boundaries (`HTTP`, subprocess CLI invocation, AWS SDK calls).
+- Request/response contracts in `internal/adapters/*` packages.
+
+Does not own:
+- Stage sequencing, skip/force/resume decisions.
+- Manifest transition logic.
+- Canonical workspace path policy.
+
+## Config fields used
+Default wiring and adapter calls consume:
+- `pipeline.whisperx.*`
+- `pipeline.seriatim.*`
+- `pipeline.audita.*`
+- `pipeline.scriptorium.*`
+- `pipeline.storage.*` and `pipeline.archive.*` (object-store construction/gating)
+- `pipeline.notification.*` (sender boundary exists; placeholder behavior today)
+
+## External adapters used
+Runtime env boundary fields (`internal/stage.Env`):
+- `whisperx.Client`
+- `seriatim.Runner`
+- `audita.Runner`
+- `scriptorium.Runner`
+- `storage.ObjectStore`
+- `notify.Sender`
+- `analyzer.Runner`
+
+Current execution usage:
+- Actively used by implemented stages: `WhisperX`, `Seriatim`, `Audita`, `Scriptorium`, `ObjectStore`, `Notifier`.
+- Present but not used by implemented stage set: `Analyzer`, legacy `storage.Backend`.
+
+Default construction in app runner:
+- Auto-constructed when not injected: WhisperX HTTP client, Seriatim subprocess runner, Audita subprocess runner, Scriptorium subprocess runner, object store (only when needed), and `notify.NoopSender`.
+- Callers can inject test/fake implementations through `app.RunOptions.Env`.
+
+## State and manifest behavior
+- Adapters do not directly mutate session/run manifests.
+- Stages and runner own manifest writes and stage status transitions.
+- Adapter outputs are persisted indirectly through stage result mapping (outputs/logs/generated configs/metadata).
+
+## Skip and resume behavior
+- No adapter-level skip/resume semantics.
+- Skip/resume/force behavior is decided by app runner using manifest stage state.
+
+## Failure behavior
+- Adapter constructors validate config-derived values and fail early on invalid required inputs.
+- Adapter run-time failures are returned to stage code with boundary context and are recorded as stage failures by runner logic.
+- Subprocess adapters preserve stdout/stderr and generated-config paths to aid diagnosis.
+
+## Tests to inspect before changing
+- `internal/adapters/whisperx/http_test.go`
+- `internal/adapters/seriatim/subprocess_test.go`
+- `internal/adapters/audita/subprocess_test.go`
+- `internal/adapters/scriptorium/subprocess_test.go`
+- `internal/adapters/storage/*_test.go`
+- `internal/adapters/notify/fake_test.go`
+- `internal/adapters/analyzer/fake_test.go`
+- `internal/app/runner_test.go`
+
+## Architectural invariants
+- Stage code depends on adapter interfaces, not transport-specific implementation types.
+- External SDK-specific types remain inside adapter implementations.
+- Default app wiring must remain deterministic and overrideable via injected env dependencies.

docs/internal/artifacts.md

@@ -0,0 +1,87 @@
+# Internal: Artifacts
+
+## Purpose
+Define Narratio's artifact identity and resolution model for built-in transcript/bounds artifacts and runtime-configured analyze artifacts.
+
+## Inputs and outputs
+Inputs:
+- artifact sources from config/runtime (`pipeline.scriptorium.artifacts.*.inputs.*.source`)
+- session paths and optional session manifest stage outputs
+- runtime artifact catalog state for configured artifact sources
+
+Outputs:
+- resolved local artifact path and provenance (`ResolvedSessionArtifact`)
+- runtime catalog entries for planned/executable/available artifacts
+- validation errors for unsupported, missing, or invalid artifact sources
+
+## Boundaries
+Owns:
+- built-in artifact registry and content validation rules
+- runtime artifact catalog for configured artifact source IDs
+- source resolution behavior for built-in and configured artifact sources
+
+Does not own:
+- artifact generation (stages produce files)
+- manifest transition policy
+- archive promotion behavior
+
+## Config fields used
+- `pipeline.scriptorium.artifacts.<name>.enabled`
+- `pipeline.scriptorium.artifacts.<name>.output_path`
+- `pipeline.scriptorium.artifacts.<name>.inputs.<key>.source`
+
+## External adapters used
+- none
+
+## State and manifest behavior
+Built-in registry entries:
+
+| Artifact ID | Canonical file | Producer stage | Output kind |
+| --- | --- | --- | --- |
+| `narratio.transcript.merged` | `transcripts/merged.json` | `merge` | `transcript_merged` |
+| `narratio.transcript.polished` | `transcripts/processed.json` | `polish` | `transcript_processed` |
+| `narratio.transcript.full` | `transcripts/normalized.json` | `normalize` | `transcript_normalized` |
+| `narratio.transcript.trimmed` | `transcripts/trimmed.json` | `trim` | `transcript_trimmed` |
+| `narratio.bounds.session` | `artifacts/session_bounds.json` | `trim` | `session_bounds` |
+
+Runtime catalog entries include built-ins and configured `narratio.artifact.<name>` sources.
+
+Catalog states:
+- `planned`: source is registered and known for this run
+- `executable`: configured artifact is selected for analyze execution
+- `available`: artifact has a usable file path (generated this run or reused from disk)
+
+Resolution behavior:
+- built-in sources resolve via manifest producer outputs first, then canonical fallback path
+- configured `narratio.artifact.<name>` sources resolve through runtime catalog availability
+- configured source lookup requires catalog context
+
+Configured artifact provenance values:
+- `generated.current_analyze_run`
+- `filesystem.disabled_artifact_output`
+
+Content validation:
+- transcript built-ins: JSON with top-level `segments` array
+- bounds built-in: valid JSON
+- configured artifacts: non-empty text file
+
+## Skip and resume behavior
+- resolver and catalog have no direct skip/resume decisions
+- stage/runner skip-resume behavior consumes catalog/resolver results
+
+## Failure behavior
+- unsupported source -> source validation error
+- known source unavailable -> `ErrSessionArtifactNotFound`
+- configured source without catalog -> resolution error
+- resolved file with invalid content -> validation error
+
+## Tests to inspect before changing
+- `internal/artifacts/artifact_resolver_test.go`
+- `internal/artifacts/catalog_test.go`
+- `internal/stage/analyze_test.go`
+- `internal/config/scriptorium_test.go`
+
+## Architectural invariants
+- built-in IDs are static and registry-backed
+- configured artifact IDs are runtime-derived (`narratio.artifact.<name>`) and catalog-backed
+- built-in/source resolution remains deterministic and validation-gated

docs/internal/manifest.md

@@ -0,0 +1,81 @@
+# Internal: Manifest
+
+## Purpose
+Describe Narratio's durable execution state model for session-level and run-level manifests, including lifecycle transitions and persistence behavior.
+
+## Inputs and outputs
+Inputs:
+- Session identity and run identity from app orchestration.
+- Stage transition events and stage result payloads.
+
+Outputs:
+- Session manifest at `{workspace.root}/work/{campaign}/{session_id}/manifest.json`.
+- Run manifest at `{workspace.root}/work/{campaign}/{session_id}/runs/{run_id}/manifest.json`.
+
+## Boundaries
+Owns:
+- Manifest schemas (`Manifest`, `RunManifest`, stage records, error records, input/artifact records).
+- Stage status/action transition methods.
+- Persistent store contract (`manifest.Store`) and local JSON store implementation.
+
+Does not own:
+- Stage implementation details.
+- Path construction policy outside manifest file persistence calls.
+- CLI command behavior.
+
+## Config fields used
+Manifest package itself does not read config directly.
+
+Manifest identity fields are populated by app/stage orchestration from:
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.storage.s3.*` (when archive/S3 identity is set)
+
+## External adapters used
+- No external service adapters.
+- Uses local filesystem for persistence via `manifest.LocalStore`.
+
+## State and manifest behavior
+Session manifest model:
+- Tracks durable per-session stage state and provenance (`pending`, `running`, `succeeded`, `failed`, `skipped`, `stale`, `interrupted`).
+- Stores resolved inputs, durable artifacts, stage logs/config refs, and stage metadata.
+
+Run manifest model:
+- Tracks one invocation (`run_id`) with requested stages and force mode.
+- Tracks per-stage action (`run` or `skip`) and per-stage status.
+- Tracks overall run status (`running`, `succeeded`, `failed`).
+
+Persistence behavior:
+- Load validates required identity/timestamp fields and normalizes maps/records.
+- Save updates `updated_at` and writes JSON atomically (temp file + rename).
+- Session and run manifests are saved incrementally before/after stage transitions.
+
+Relationship during execution:
+- Runner updates both manifests for every stage transition.
+- Session manifest is the durable pipeline-progress ledger.
+- Run manifest is invocation history and audit record.
+- Analyze stage outputs are persisted as `kind=scriptorium_artifact` with `source_id=narratio.artifact.<name>` for configured artifact identity.
+
+## Skip and resume behavior
+- Resume and skip decisions are based on session-manifest stage statuses.
+- `--force` reruns selected stages and marks downstream succeeded stages as `stale` in session manifest.
+- Run manifest records whether each stage was executed or skipped in that invocation.
+
+## Failure behavior
+- Stage failure marks both manifests failed for that stage and records error messages/timestamps.
+- Save failures are returned immediately and fail the command.
+- Invalid/malformed manifest files fail load with explicit validation/decode errors.
+
+## Tests to inspect before changing
+- `internal/manifest/manifest_test.go`
+- `internal/manifest/run_manifest_test.go`
+- `internal/manifest/store_test.go`
+- `internal/app/runner_test.go`
+- `internal/app/run_control_test.go`
+- `internal/app/resume_run_stage_test.go`
+
+## Architectural invariants
+- Session manifest is authoritative for stage progression across invocations.
+- Run manifest is invocation-scoped and never replaces session manifest as progress authority.
+- Manifest writes are atomic and deterministic (JSON + newline, temp rename pattern).

docs/internal/stage-analyze.md

@@ -0,0 +1,84 @@
+# Stage: analyze
+
+## Purpose
+Execute selected configured Scriptorium artifacts in deterministic dependency order and promote successful outputs to canonical session artifact paths.
+
+## Inputs and Outputs
+Inputs:
+- configured artifact definitions from `pipeline.scriptorium.artifacts`
+- selected artifact filter from runtime (`--artifacts`) when provided
+- resolved artifact input sources declared per artifact (`inputs.*.source`)
+- optional previous-session file inputs (`previous_session_artifact`)
+
+Outputs:
+- one promoted output file per executed configured artifact at that artifact's configured `output_path`
+- stage metadata containing generated artifact entries and reused disabled-artifact entries
+
+## Boundaries
+Owns:
+- runtime artifact catalog construction for analyze execution
+- selected-artifact planning and dependency ordering
+- per-artifact input resolution, var resolution, timeout/render-debug resolution
+- Scriptorium run/render invocation for each selected artifact
+- run-local output generation and canonical promotion
+
+Does not own:
+- transcript generation/processing stages
+- archive promotion policy
+- per-artifact resume semantics
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.scriptorium.binary`
+- `pipeline.scriptorium.config_path`
+- `pipeline.scriptorium.timeout`
+- `pipeline.scriptorium.render_debug`
+- `pipeline.scriptorium.artifacts.<name>.*`
+  - `enabled`
+  - `depends_on`
+  - `prompt_id`
+  - `profile_id`
+  - `timeout`
+  - `output_path`
+  - `render_debug`
+  - `inputs`
+  - `vars`
+
+## External Adapters Used
+- Scriptorium adapter:
+  - optional `RenderArtifact` (render debug)
+  - `RunArtifact` (artifact generation)
+
+## State and Manifest Behavior
+- If `pipeline.scriptorium` is absent, stage returns success metadata with `skipped=true`.
+- If no artifacts are configured, stage returns success metadata with `skipped=true`.
+- If zero artifacts are executable after `enabled` + `--artifacts` filtering, stage returns success metadata with `skipped=true`.
+- Builds runtime catalog with built-ins and configured artifacts.
+- Non-executable configured artifacts are marked available only when their configured output file exists and is valid on disk.
+- Executes selected configured artifacts in topological order with deterministic tie-breaking.
+- For each generated artifact, records metadata fields including `name`, `source_id`, `output_kind`, `path`, `prompt_id`, `profile_id`, and `provenance`.
+- Reused disabled artifacts are recorded separately in `reused_artifacts` with provenance `filesystem.disabled_artifact_output`.
+
+## Skip and Resume Behavior
+- Runner-level skip applies when analyze is already `succeeded` and `--force` is not set.
+- Analyze remains stage-scoped for resume/skip; there is no per-artifact resume state.
+- `--artifacts` filters which configured artifacts are executable when analyze runs; it does not imply `--force`.
+
+## Failure Behavior
+- Fails on invalid dependency ordering, unavailable required configured inputs, invalid built-in input prerequisites, render/run adapter failures, validation-failed adapter results, or missing/empty outputs.
+- Required configured dependency missing from catalog availability fails clearly before invocation.
+- Optional missing inputs are omitted.
+
+## Tests to Inspect Before Changing
+- `internal/stage/analyze_test.go`
+- `internal/artifacts/catalog_test.go`
+- `internal/artifacts/artifact_resolver_test.go`
+- `internal/adapters/scriptorium/subprocess_test.go`
+
+## Architectural Invariants
+- Configured artifacts are identified by `narratio.artifact.<name>` source IDs.
+- Artifact-to-artifact references rely on explicit `depends_on` declarations validated in config.
+- Generated analyze outputs are treated uniformly as Scriptorium artifacts.
+- Successful outputs must exist and be non-empty before promotion.

docs/internal/stage-archive.md

@@ -0,0 +1,68 @@
+# Stage: archive
+
+## Purpose
+Publish run records and promoted session artifacts to object storage, then atomically advance the remote current pointer.
+
+## Inputs and Outputs
+Inputs:
+- session manifest and prerequisite stage records
+- run root contents under `runs/{run_id}/`
+- promotion sources from session root (`archive.promote_artifacts`)
+
+Outputs:
+- uploaded run files under `{session_prefix}/runs/{run_id}/...`
+- uploaded promoted artifacts under `{session_prefix}/...`
+- `{session_prefix}/current/manifest.json`
+- `{session_prefix}/current/run_id.txt` written last
+
+## Boundaries
+Owns:
+- Archive enable/disable gate behavior
+- Prerequisite stage success enforcement
+- Run file collection and upload (excluding `audio/`)
+- Promotion rule resolution and upload
+- Commit pointer publish order
+
+Does not own:
+- Stage execution before archive
+- Post-archive local cleanup policy execution (handled by app cleanup logic)
+
+## Config Fields Used
+- `pipeline.archive.enabled`
+- `pipeline.archive.upload_run`
+- `pipeline.archive.promote_artifacts`
+- `pipeline.storage.s3.bucket`
+- `pipeline.storage.s3.root_prefix`
+- `pipeline.workspace.root`
+- `session.campaign`
+- `session.session_id`
+
+## External Adapters Used
+- Object storage backend (`env.ObjectStore`) for upload/list primitives.
+
+## State and Manifest Behavior
+- Requires `prepare`, `transcribe`, `merge`, `polish`, `normalize`, `trim`, and `analyze` status `succeeded`.
+- Resolves bucket/prefix from manifest identity first, then config fallback.
+- Writes metadata including:
+  - upload counts/paths
+  - `current_manifest_key`
+  - `current_run_id_key`
+  - `current_pointer_written`
+- On skipped archive path, returns metadata with `skipped=true` and pointer not written.
+
+## Skip and Resume Behavior
+- Stage may self-skip (metadata skip) when archive disabled or run upload disabled.
+- Runner-level skip also applies for previously succeeded stage unless forced.
+
+## Failure Behavior
+- Fails on missing prerequisite success, missing object store when required, missing run root, missing required promotion source, upload failures, or pointer write failures.
+- Pointer semantics are fail-safe: `current/run_id.txt` is not written if prior required uploads fail.
+
+## Tests to Inspect Before Changing
+- `internal/stage/archive_test.go`
+- `internal/app/post_archive_cleanup_test.go`
+
+## Architectural Invariants
+- Run upload excludes `audio/` subtree.
+- `current/manifest.json` uploads before `current/run_id.txt`.
+- `current/run_id.txt` is the remote publish commit marker.

docs/internal/stage-merge.md

@@ -0,0 +1,63 @@
+# Stage: merge
+
+## Purpose
+Normalize per-speaker raw transcripts and merge them into one merged transcript via Seriatim.
+
+## Inputs and Outputs
+Inputs:
+- `transcripts/raw/*.json`
+- `inputs/speakers.yml`
+- `inputs/autocorrect.yml`
+
+Outputs:
+- `transcripts/merged.json`
+- optional `artifacts/seriatim.report.json` (when report enabled)
+
+## Boundaries
+Owns:
+- Raw transcript discovery/validation
+- Per-input normalize calls to Seriatim
+- Final merge call to Seriatim
+- Run-local log/config/report path wiring
+- Promotion of merged/report outputs to canonical paths
+
+Does not own:
+- Transcript polishing or downstream artifact generation
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.seriatim.binary`
+- `pipeline.seriatim.timeout`
+- `pipeline.seriatim.output_schema`
+- `pipeline.seriatim.coalesce_gap`
+- `pipeline.seriatim.report`
+- `pipeline.seriatim.env.*`
+
+## External Adapters Used
+- Seriatim adapter:
+  - `Normalize` for each raw input
+  - `Run` for final merge
+
+## State and Manifest Behavior
+- Reads transcript inputs from transcribe stage outputs in manifest when present; falls back to canonical raw directory.
+- Writes run-local outputs/logs/config under `runs/{run_id}/merge/...` when enabled.
+- Promotes canonical merged transcript and optional report.
+- Records normalized-input provenance and adapter metadata in stage metadata.
+
+## Skip and Resume Behavior
+- Runner-level skip applies when already succeeded and not forced.
+- Forced rerun of this or upstream stages can stale downstream succeeded stages via runner invalidation.
+
+## Failure Behavior
+- Fails on missing/invalid raw transcripts, missing speakers/autocorrect files, normalize failure, merge failure, invalid merged output JSON, or invalid report JSON when enabled.
+
+## Tests to Inspect Before Changing
+- `internal/stage/merge_test.go`
+- `internal/adapters/seriatim/subprocess_test.go`
+
+## Architectural Invariants
+- Merge consumes normalized forms of each raw transcript.
+- Merged transcript must validate before promotion.
+- Report output is optional and gated by config.

docs/internal/stage-normalize.md

@@ -0,0 +1,56 @@
+# Stage: normalize
+
+## Purpose
+Normalize the processed transcript into a deterministic intermediate schema for trim and optionally emit a normalize report.
+
+## Inputs and Outputs
+Inputs:
+- `transcripts/processed.json`
+
+Outputs:
+- `transcripts/normalized.json` (or configured normalize output path)
+- optional `artifacts/seriatim.normalize.report.json`
+
+## Boundaries
+Owns:
+- Processed transcript discovery/validation
+- Normalize request construction and invocation
+- Optional normalize report wiring
+- Promotion of normalized transcript and optional report
+
+Does not own:
+- Bounds detection or segment trimming
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.normalize.output_path`
+- `pipeline.normalize.output_schema`
+- `pipeline.normalize.report`
+- `pipeline.seriatim.binary`
+- `pipeline.seriatim.timeout`
+
+## External Adapters Used
+- Seriatim adapter (`Normalize`).
+
+## State and Manifest Behavior
+- Reads processed transcript from polish outputs in manifest when present; falls back to canonical path.
+- Uses run-local output/report/log/config paths when run layout is enabled.
+- Promotes canonical normalized transcript and optional normalize report.
+- Records adapter/result metadata including source path selection.
+
+## Skip and Resume Behavior
+- Runner-level skip applies when already succeeded and not forced.
+- Forced reruns can stale downstream succeeded stages.
+
+## Failure Behavior
+- Fails on missing/invalid processed transcript, adapter error, invalid normalized output, or invalid report output when report enabled.
+
+## Tests to Inspect Before Changing
+- `internal/stage/normalize_test.go`
+- `internal/adapters/seriatim/subprocess_test.go`
+
+## Architectural Invariants
+- Normalized output must validate as processed-transcript-compatible JSON (`segments` array required).
+- Default normalize config is applied when `pipeline.normalize` is unset.

docs/internal/stage-polish.md

@@ -0,0 +1,69 @@
+# Stage: polish
+
+## Purpose
+Polish merged transcript with Audita and produce a processed transcript for downstream normalization/analyze.
+
+## Inputs and Outputs
+Inputs:
+- `transcripts/merged.json`
+- `inputs/glossary.yml`
+
+Outputs:
+- `transcripts/processed.json`
+- optional `artifacts/audita.report.json` (when report enabled)
+
+## Boundaries
+Owns:
+- Merged transcript discovery/validation
+- Audita invocation request construction
+- Run-local logs/config/work-dir/report wiring
+- Promotion of processed transcript and optional report
+
+Does not own:
+- Upstream merge normalization
+- Downstream normalize/trim/analyze logic
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.audita.binary`
+- `pipeline.audita.timeout`
+- `pipeline.audita.llm_api_key_env`
+- `pipeline.audita.modules`
+- `pipeline.audita.base_url`
+- `pipeline.audita.model`
+- `pipeline.audita.transcript_description`
+- `pipeline.audita.config_path`
+- `pipeline.audita.output_schema`
+- `pipeline.audita.work_dir_retention`
+- `pipeline.audita.total_llm_concurrency`
+- `pipeline.audita.proposal_llm_concurrency`
+- `pipeline.audita.validation_model`
+- `pipeline.audita.validation_llm_concurrency`
+- `pipeline.audita.report`
+
+## External Adapters Used
+- Audita adapter (`env.Audita.Run`).
+
+## State and Manifest Behavior
+- Reads merged transcript from merge manifest outputs when available; falls back to canonical merged path.
+- Uses run-local output/report/log/config/scratch paths when run layout is enabled.
+- Promotes canonical `transcripts/processed.json` and optional report.
+- Records adapter invocation metadata, credential presence signal, and output provenance in stage metadata.
+
+## Skip and Resume Behavior
+- Runner-level skip applies when already succeeded and not forced.
+- Forced rerun can stale downstream succeeded stages via runner invalidation.
+
+## Failure Behavior
+- Fails on missing/invalid merged transcript, missing glossary, adapter error, invalid processed output shape (`segments` array required), or invalid report JSON when enabled.
+
+## Tests to Inspect Before Changing
+- `internal/stage/polish_test.go`
+- `internal/adapters/audita/subprocess_test.go`
+
+## Architectural Invariants
+- Processed transcript must contain a top-level `segments` array.
+- Report behavior is strictly config-gated.
+- Stage output canonicalization always ends at `transcripts/processed.json`.

docs/internal/stage-prepare.md

@@ -0,0 +1,74 @@
+# Stage: prepare
+
+## Purpose
+Materialize all required session inputs into canonical local workspace paths and record input provenance in the session manifest.
+
+## Inputs and Outputs
+Inputs:
+- `session.yml` (resolved session config)
+- `pipeline.resolved.yml` (materialized from resolved pipeline config)
+- `speakers.yml`
+- `autocorrect.yml`
+- `glossary.yml`
+- audio source:
+  - local (`session.inputs.audio_dir` or `session.inputs.audio_files`), or
+  - S3 (`session.inputs.audio_s3.prefix`)
+
+Outputs:
+- `inputs/session.yml`
+- `inputs/pipeline.resolved.yml`
+- `inputs/speakers.yml`
+- `inputs/autocorrect.yml`
+- `inputs/glossary.yml`
+- `audio/*.flac` in session workdir
+- `manifest.Inputs` records with checksums and source metadata
+
+## Boundaries
+Owns:
+- Input path resolution and validation
+- Local copy/materialization of configs and audio files
+- S3 audio download to run-scoped spool, then copy into work audio dir
+
+Does not own:
+- Transcript generation/processing
+- Archive publish behavior
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `session.inputs.speakers_file`
+- `session.inputs.autocorrect_file`
+- `session.inputs.glossary_file`
+- `session.inputs.audio_dir`
+- `session.inputs.audio_files`
+- `session.inputs.audio_s3.prefix`
+- `pipeline.workspace.root`
+- `pipeline.spool.root`
+- `pipeline.storage.s3.bucket`
+- `pipeline.storage.s3.root_prefix`
+
+## External Adapters Used
+- Object storage backend (`env.ObjectStore`) for S3 audio list/download when `audio_s3` is configured.
+
+## State and Manifest Behavior
+- Ensures workspace layout exists.
+- Writes resolved config and input files to canonical `inputs/` paths.
+- Records all prepared inputs into `manifest.Inputs` (sorted deterministically by kind/path).
+- For S3 audio, records `S3Bucket`, `S3Key`, `S3Size`, `S3ETag`, and `SpoolPath` in each audio input record.
+
+## Skip and Resume Behavior
+- Runner-level skip applies when stage already `succeeded` and `--force` is not set.
+- Stage itself is deterministic/idempotent for unchanged inputs (`copyFileIfChanged`, `writeBytesIfChanged`).
+
+## Failure Behavior
+- Fails on missing required files, invalid audio source combinations, no discoverable `.flac` files, duplicate audio basenames, missing object store for S3 mode, or S3 list/download failures.
+
+## Tests to Inspect Before Changing
+- `internal/stage/prepare_test.go`
+- `internal/app/session_cli_test.go`
+- `internal/config/load_validate_test.go`
+
+## Architectural Invariants
+- `audio_dir`/`audio_files` and `audio_s3` are mutually exclusive.
+- Audio files must be `.flac`.
+- Canonical `inputs/*` and `audio/*` paths are the durable source for downstream stages.

docs/internal/stage-transcribe.md

@@ -0,0 +1,58 @@
+# Stage: transcribe
+
+## Purpose
+Generate per-speaker raw transcripts from prepared audio using WhisperX.
+
+## Inputs and Outputs
+Inputs:
+- `audio/*.flac` prepared by `prepare`
+
+Outputs:
+- `transcripts/raw/<speaker>.json` for each input audio file
+
+## Boundaries
+Owns:
+- Discovering prepared audio inputs
+- Deriving speaker ids from audio basenames
+- Parallel WhisperX invocation with bounded concurrency
+- Validating produced JSON and promoting run-local outputs
+
+Does not own:
+- Transcript merge/polish/normalize/trim/analyze
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.whisperx.transcribe_url`
+- `pipeline.whisperx.language`
+- `pipeline.whisperx.timeout`
+- `pipeline.whisperx.retries`
+- `pipeline.whisperx.retry_delay`
+- `pipeline.whisperx.concurrency`
+
+## External Adapters Used
+- WhisperX adapter (`env.WhisperX.Transcribe`).
+
+## State and Manifest Behavior
+- Uses run-local output paths under `runs/{run_id}/transcribe/outputs/...` when run layout is enabled.
+- Validates each generated transcript JSON before promotion.
+- Promotes canonical outputs to `transcripts/raw/*.json`.
+- Records per-file metadata (attempts/status/duration/output path) in stage metadata.
+
+## Skip and Resume Behavior
+- Runner-level skip applies for previously succeeded stage unless forced.
+- On forced upstream reruns, downstream succeeded stages can be marked `stale` by runner logic.
+
+## Failure Behavior
+- Fails if no prepared audio exists, duplicate speaker basenames are detected, adapter output path mismatches expected path, any output JSON is invalid, or one worker fails.
+- Cancels in-flight workers after first terminal error.
+
+## Tests to Inspect Before Changing
+- `internal/stage/transcribe_test.go`
+- `internal/app/whisperx_wiring_test.go`
+
+## Architectural Invariants
+- Speaker identity is derived from `.flac` basename and must be unique.
+- Every successful speaker output must be valid JSON before promotion.
+- Canonical raw transcript set is the only supported merge input surface.

docs/internal/stage-trim.md

@@ -0,0 +1,75 @@
+# Stage: trim
+
+## Purpose
+Optionally trim the normalized transcript to session bounds; always produce a durable trimmed transcript.
+
+## Inputs and Outputs
+Inputs:
+- `transcripts/normalized.json`
+
+Outputs:
+- `transcripts/trimmed.json` (or configured trim output path)
+- when trim enabled: `artifacts/session_bounds.json`
+
+## Boundaries
+Owns:
+- Trim-enabled switch behavior
+- Bounds generation via Scriptorium artifact run
+- Bounds validation against normalized transcript
+- Keep-selector derivation and Seriatim trim invocation
+- Copy-through behavior when disabled or bounds indicate unchanged transcript
+
+Does not own:
+- Upstream normalization
+- Downstream artifact analysis
+
+## Config Fields Used
+- `session.session_id`
+- `session.campaign`
+- `pipeline.workspace.root`
+- `pipeline.trim.enabled`
+- `pipeline.trim.output_path`
+- `pipeline.trim.bounds.prompt_id`
+- `pipeline.trim.bounds.profile_id`
+- `pipeline.trim.bounds.timeout`
+- `pipeline.trim.bounds.output_path`
+- `pipeline.trim.bounds.transcript_input_name`
+- `pipeline.trim.bounds.render_debug`
+- `pipeline.trim.bounds.render_output_path`
+- `pipeline.seriatim.binary`
+- `pipeline.seriatim.timeout`
+- `pipeline.scriptorium.binary`
+- `pipeline.scriptorium.config_path`
+- `pipeline.scriptorium.timeout`
+
+## External Adapters Used
+- Scriptorium adapter:
+  - optional `RenderArtifact` for bounds debug render
+  - `RunArtifact` for bounds output
+- Seriatim adapter:
+  - `Trim` when bounds indicate trimming is required
+
+## State and Manifest Behavior
+- Reads normalized transcript from normalize manifest outputs when available; falls back to canonical path.
+- Uses run-local outputs/logs/reports/config/scratch paths when run layout is enabled.
+- Promotes canonical trimmed transcript; promotes session bounds when trim enabled.
+- Records bounds diagnostics, trim action, keep selector, and adapter metadata.
+
+## Skip and Resume Behavior
+- Runner-level skip applies when already succeeded and not forced.
+- Forced reruns can stale downstream succeeded stages.
+- When `trim.enabled=false`, stage still succeeds by copying normalized to trimmed output.
+
+## Failure Behavior
+- Fails on missing/invalid normalized transcript.
+- With trim enabled, fails on missing adapters/config, bounds generation/validation errors, invalid bounds JSON, invalid range/segment ids, trim adapter failures, or invalid trimmed output.
+
+## Tests to Inspect Before Changing
+- `internal/stage/trim_test.go`
+- `internal/adapters/scriptorium/subprocess_test.go`
+- `internal/adapters/seriatim/subprocess_test.go`
+
+## Architectural Invariants
+- Trim never falls back to processed transcript; normalized transcript is required input.
+- `session_bounds` output exists only for enabled trim path.
+- Render-debug artifacts are diagnostics and not declared stage outputs.

docs/internal/storage.md

@@ -0,0 +1,71 @@
+# Internal: Storage
+
+## Purpose
+Document Narratio's remote storage backend contracts and implementations under `internal/adapters/storage`.
+
+## Inputs and outputs
+Inputs:
+- Resolved storage config (`pipeline.storage.*`).
+- Bucket-relative object keys and local file paths from stage/app orchestration.
+
+Outputs:
+- Listed/downloaded/uploaded object metadata (`ObjectInfo`).
+- Existence checks and storage-layer errors.
+
+## Boundaries
+Owns:
+- Remote object-store interface and implementation details.
+- S3 client wiring and API calls.
+- Object key normalization and upload/download/list primitives.
+
+Does not own:
+- Session/run prefix semantics.
+- Archive commit order semantics.
+- Manifest updates.
+
+## Config fields used
+- `pipeline.storage.backend`
+- `pipeline.storage.s3.bucket`
+- `pipeline.storage.s3.region`
+- `pipeline.storage.s3.endpoint`
+- `pipeline.storage.s3.force_path_style`
+- `pipeline.storage.s3.access_key_id_env`
+- `pipeline.storage.s3.secret_access_key_env`
+
+## External adapters used
+Storage package contracts:
+- `ObjectStore` (active remote object-store boundary): `List`, `Download`, `Upload`, `Exists`.
+- `Backend` (archive request boundary): currently implemented with `NoopBackend` only.
+
+Implementations:
+- `S3Backend`: AWS SDK-backed `ObjectStore` implementation.
+- `FakeBackend`: deterministic test `ObjectStore` and archive backend.
+- `NoopBackend`: deterministic no-op archive backend for compatibility wiring.
+
+## State and manifest behavior
+- Storage implementations are stateless with respect to manifest/session lifecycle.
+- Caller supplies fully-qualified bucket-relative keys.
+- Storage layer does not infer campaign/session/run/root-prefix semantics.
+- Caller controls publish ordering; storage layer executes individual operations in the order invoked.
+
+## Skip and resume behavior
+- No storage-level skip/resume behavior.
+- Skip/resume decisions are made by stage/app logic before storage calls occur.
+
+## Failure behavior
+- `NewObjectStoreFromConfig` fails when no remote backend is configured or required S3 config is missing.
+- `S3Backend` constructor fails when required bucket is missing or AWS client setup fails.
+- CRUD operations return contextual errors (including not-found behavior via `Exists`).
+- Key normalization is applied before operations (`\\` to `/`, leading slash trimmed).
+
+## Tests to inspect before changing
+- `internal/adapters/storage/factory_test.go`
+- `internal/adapters/storage/s3_backend_test.go`
+- `internal/adapters/storage/fake_test.go`
+- `internal/adapters/storage/keys_test.go`
+- `internal/adapters/storage/archive.go` + consumers in stage tests (`prepare`, `archive`)
+
+## Architectural invariants
+- Callers pass full bucket-relative keys.
+- Storage backends must not prepend or infer narratio prefixes.
+- Remote transport details remain isolated to storage adapter implementations.

docs/internal/workspace.md

@@ -0,0 +1,68 @@
+# Workspace internals
+
+## Purpose
+Define the local durable and run-local workspace model used by stages, manifests, resume, and archive.
+
+## Inputs and Outputs
+Inputs:
+- `pipeline.workspace.root`
+- `session.campaign`
+- `session.session_id`
+- generated `run_id`
+
+Outputs:
+- Session manifest at `{workspace.root}/work/{campaign}/{session_id}/manifest.json`
+- Run manifest at `{workspace.root}/work/{campaign}/{session_id}/runs/{run_id}/manifest.json`
+- Canonical durable session directories and run-local stage trees
+
+## Boundaries
+Owns:
+- Session-level path layout (`inputs/`, `audio/`, `transcripts/`, `artifacts/`, `reports/`, `logs/`, `config/`, `current/`, `runs/`)
+- Run-local stage sandbox layout under `runs/{run_id}/{stage}/`
+- Session lock acquisition/release (`.lock`)
+
+Does not own:
+- Stage business logic
+- Remote archive semantics (documented in `stage-archive.md`)
+- CLI argument parsing
+
+## Config Fields Used
+- `pipeline.workspace.root`
+- `pipeline.workspace.cleanup_after_archive`
+- `pipeline.spool.root`
+- `pipeline.spool.delete_audio_after_archive`
+- `session.campaign`
+- `session.session_id`
+
+## External Adapters Used
+None directly in this subsystem. Stages may use object storage adapters and then write local outputs into this layout.
+
+## State and Manifest Behavior
+- Session state is persisted in the session manifest (`manifest.Manifest`).
+- Invocation history is persisted per run in run manifests under `runs/{run_id}/manifest.json`.
+- During each run, stage outputs are often written run-local first (`runs/{run_id}/{stage}/outputs/...`) and promoted to canonical session paths after stage success.
+- `manifest.Artifacts` entries record `ProducerRunID` for durable outputs.
+- For S3 audio sessions, `prepare` records spool/work paths and S3 provenance in `manifest.Inputs`.
+
+## Skip and Resume Behavior
+- Skip/resume decisions are made in `internal/app` (`run_control.go`, `resume.go`) using stage status in the session manifest.
+- `--force` reruns selected stages and marks downstream previously-succeeded stages as `stale`.
+- Workspace layout is idempotent (`EnsureLayoutFor`) and reused across runs.
+
+## Failure Behavior
+- Failures preserve manifests and run-local files for inspection.
+- Lock conflicts fail fast via `ErrLockConflict`.
+- Cleanup can fail post-archive; failure is recorded in archive stage metadata and returned by the run.
+
+## Tests to Inspect Before Changing
+- `internal/artifacts/local_test.go`
+- `internal/stage/run_local_test.go`
+- `internal/app/run_control_test.go`
+- `internal/app/resume_run_stage_test.go`
+- `internal/app/post_archive_cleanup_test.go`
+
+## Architectural Invariants
+- Session root is campaign-aware: `{workspace.root}/work/{campaign}/{session_id}`.
+- Run roots are always nested: `runs/{run_id}` under the session root.
+- Run-local output promotion must end in canonical session paths.
+- Cleanup only targets run-scoped directories and must never delete configured root directories.

docs/operations.md

@@ -0,0 +1,149 @@
+# Operations
+
+This guide describes the implemented operator lifecycle for Narratio.
+
+For field-level configuration, see [docs/config.md](./config.md). For full command/flag reference, see [docs/cli.md](./cli.md).
+
+## Normal workflow (S3-first path)
+
+1. Upload session `.flac` files to object storage under the session audio prefix.
+2. Run Narratio:
+
+```bash
+narratio run --session-id 2026-04-04
+```
+
+3. Read success output:
+- `narratio run: session <session_id>; executed=<n> skipped=<n>; manifest=<path>`
+- use `manifest=<path>` with `status` for inspection.
+
+Notes:
+- default config/session discovery applies unless `--config` and `--session` are passed.
+- S3 audio mode requires `session.inputs.audio_s3.prefix` and valid object-store access.
+
+## Local filesystem layout and state artifacts
+
+Session root:
+- `{workspace.root}/work/{campaign}/{session_id}/`
+
+Primary state:
+- `manifest.json`: session-level stage state.
+- `runs/{run_id}/manifest.json`: invocation-level state.
+- `.lock`: session lock while a run is active.
+
+Canonical session directories:
+- `inputs/`
+- `audio/`
+- `transcripts/`
+- `artifacts/`
+- `reports/`
+- `logs/`
+- `config/`
+- `current/`
+- `runs/`
+
+Run-local stage directories:
+- `runs/{run_id}/{stage}/` with stage-local `outputs/`, `logs/`, `reports/`, `config/`, `scratch/`.
+
+Behavior:
+- directory creation is idempotent.
+- stage outputs are generally generated run-local first, then promoted to canonical paths on success.
+
+## Analyze artifact execution lifecycle
+
+Analyze executes configured artifacts from `pipeline.scriptorium.artifacts`.
+
+Execution model:
+- executable set = enabled artifacts, filtered by `--artifacts` when provided.
+- artifact-to-artifact dependencies are declared via `depends_on`.
+- selected artifacts run in deterministic dependency order.
+- after each successful artifact run, output is promoted to configured canonical `output_path`.
+
+Configured artifact source reuse:
+- a non-executable configured artifact can satisfy inputs if its configured output file already exists and is valid.
+- reused configured artifact provenance is `filesystem.disabled_artifact_output`.
+
+`--artifacts` behavior:
+- accepted on `run`, `resume`, and `run-stage analyze`.
+- filters analyze execution only; does not force stage rerun.
+
+## Remote archive layout and publish contract
+
+When archive is enabled and run upload is enabled, archive publishes under:
+
+- session prefix: `{root_prefix}/campaigns/{campaign}/sessions/{session_id}/`
+- run prefix: `{session_prefix}/runs/{run_id}/`
+
+Archive uploads:
+- run record files from run root (excluding `audio/`).
+- promoted files from explicit `archive.promote_artifacts` rules.
+
+Publish order:
+1. upload `current/manifest.json`
+2. upload `current/run_id.txt` last
+
+`current/run_id.txt` is the remote commit marker.
+
+Archive promotion is explicit and path-based:
+- Narratio does not auto-promote all generated analyze artifacts.
+- missing required promotion sources fail archive stage.
+- missing optional promotion sources are skipped.
+
+## Resume, retry, and safe rerun behavior
+
+Default skip:
+- `run` and `run-stage` skip already-succeeded stages unless `--force` is set.
+
+Resume:
+- `resume` starts at first non-succeeded stage.
+- `resume --force` runs full stage order.
+
+Forced reruns:
+- force-rerunning an upstream succeeded stage marks downstream succeeded stages as `stale`.
+
+Safe rerun pattern:
+1. rerun the changed stage with `--force`.
+2. run `resume` to rebuild downstream stages.
+
+## Cleanup behavior
+
+Cleanup is considered only when archive stage executed and succeeded.
+
+Cleanup toggles:
+- `pipeline.spool.delete_audio_after_archive=true` deletes run-scoped spool audio.
+- `pipeline.workspace.cleanup_after_archive=true` deletes run-scoped local run directory.
+
+Cleanup eligibility gates:
+- archive enabled
+- archive run upload enabled
+- run record upload completed
+- current pointer write completed (`current/run_id.txt` written)
+
+No cleanup for failed/incomplete/unarchived/archive-skipped runs.
+
+## Failure and recovery playbooks
+
+After failure, Narratio keeps:
+- session manifest
+- run manifest
+- run-local artifacts/logs/config/reports
+
+Failed or incomplete runs remain local-only.
+
+Recommended recovery:
+
+1. inspect state:
+
+```bash
+narratio status --manifest <manifest-path>
+```
+
+2. fix root cause (config/input/credentials/service availability).
+3. continue with `resume`, or targeted `run-stage --force` followed by `resume`.
+
+## Operational caveats
+
+- `status` requires explicit `--manifest`; there is no session-id lookup command.
+- local and S3 audio input modes are mutually exclusive.
+- archive publish requires upstream stages through `analyze` to be `succeeded`.
+- required promotion rules can fail when selected analyze artifacts did not generate a required file path.

docs/roadmap/runtime-artifacts.md

@@ -0,0 +1,762 @@
+# Roadmap: Runtime-Defined Scriptorium Artifacts
+
+## Status
+
+Implementation roadmap for a pre-release hard cutover.
+
+## Purpose
+
+Narratio currently treats artifact generation as a narrow `analyze` stage that supports a hard-coded `session_recap` artifact. This roadmap describes how to generalize artifact generation so operators can define Scriptorium-backed output artifacts at runtime through `pipeline.yml`.
+
+The goal is to keep Narratio as a fixed pipeline orchestrator while making the artifact generation step configurable, composable, deterministic, and easy to regenerate selectively.
+
+## Desired Outcome
+
+Operators should be able to define artifacts such as session recaps, player handouts, NPC summaries, quest logs, entity maps, or other campaign-specific outputs without changing Narratio code.
+
+A configured artifact is declared under:
+
+```text
+pipeline.scriptorium.artifacts.<name>
+```
+
+Each configured artifact becomes a canonical runtime artifact source ID:
+
+```text
+narratio.artifact.<name>
+```
+
+For example:
+
+```yaml
+scriptorium:
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd_session.session_recap
+      output_path: artifacts/session_recap.md
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+```
+
+This artifact is addressable by later artifacts as:
+
+```text
+narratio.artifact.session_recap
+```
+
+A dependent artifact can then consume it explicitly:
+
+```yaml
+scriptorium:
+  artifacts:
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd_session.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+```
+
+## Resolved Design Decisions
+
+The following decisions are settled for the initial implementation:
+
+1. Configured artifact outputs must live under Narratio's internal artifact output directory, initially `artifacts/`.
+2. The artifact output directory should be defined as an internal default in `internal/config/defaults.go`, but no public configuration knob should be exposed yet.
+3. Artifact `output_path` should remain explicit in the initial implementation to avoid guessing file extensions or output formats.
+4. A disabled artifact may still be referenced as an input if its declared output already exists on disk and passes basic validation.
+5. A disabled artifact is not executable during the current analyze run.
+6. Artifact-to-artifact references require an explicit `depends_on` entry. Narratio should fail fast if the dependency declaration is missing.
+7. The manifest remains stage-oriented: `analyze` succeeds or fails as a full stage.
+8. Analyze-stage metadata may record per-artifact output details for provenance and later resolution, but not for intra-stage resume semantics.
+9. `--artifacts` should be added as a CLI filter for selective artifact generation.
+10. `--artifacts` does not imply `--force`; it only changes which configured artifacts are treated as executable when `analyze` actually runs.
+11. Because Narratio is still pre-release, the hard-coded `session_recap` behavior should be removed immediately rather than deprecated gradually.
+
+## Scope
+
+This roadmap covers:
+
+- introducing a runtime artifact catalog;
+- generalizing configured Scriptorium artifact execution;
+- supporting `narratio.artifact.<name>` source IDs;
+- adding explicit artifact dependencies;
+- supporting disabled-but-resolvable artifact inputs;
+- adding selective artifact execution via `--artifacts`;
+- recording generated artifacts in analyze-stage metadata and/or manifest outputs;
+- removing hard-coded `session_recap` behavior;
+- updating tests and documentation.
+
+## Non-Goals
+
+This feature should not turn Narratio into a general workflow engine.
+
+The initial implementation should not add:
+
+- arbitrary shell-command artifacts;
+- arbitrary user-defined stages;
+- loops or conditional branching;
+- automatic archive promotion of generated artifacts;
+- semantic knowledge of particular artifact types;
+- per-artifact resume semantics within a successful or failed analyze stage;
+- automatic dependency inference without `depends_on`.
+
+Narratio should continue to orchestrate a fixed pipeline. The configurable part is the set of Scriptorium artifact invocations performed during the `analyze` stage.
+
+## Current State
+
+Narratio already has several relevant pieces in place:
+
+- `pipeline.scriptorium.artifacts` is modeled as a map of artifact definitions.
+- The Scriptorium adapter already accepts generic run/render requests.
+- The artifact resolver already understands canonical artifact source IDs.
+- The `analyze` stage already resolves inputs, optionally runs render-debug, invokes Scriptorium, verifies output, and records metadata.
+
+The main limitation is that `analyze` currently treats `session_recap` as the only executable artifact and rejects other enabled artifact definitions.
+
+## Target Architecture
+
+### Runtime Artifact Catalog
+
+Introduce a per-run artifact catalog that tracks built-in artifacts and configured artifacts.
+
+Conceptually:
+
+```text
+ArtifactCatalog
+├── built-in artifacts
+│   ├── narratio.transcript.merged
+│   ├── narratio.transcript.polished
+│   ├── narratio.transcript.full
+│   ├── narratio.transcript.trimmed
+│   └── narratio.bounds.session
+│
+└── configured artifacts
+    ├── narratio.artifact.session_recap
+    ├── narratio.artifact.player_handout
+    └── narratio.artifact.npc_summary
+```
+
+The catalog should distinguish between three states:
+
+```text
+planned       valid configured or built-in artifact known to Narratio
+available     artifact has been produced or otherwise resolved
+executable    configured artifact selected for execution in this analyze run
+```
+
+Configured artifacts can be planned without being executable. This distinction is important for disabled artifacts and for `--artifacts` filtering.
+
+### Configured Artifact Source IDs
+
+Configured artifact keys map directly to source IDs:
+
+```text
+pipeline.scriptorium.artifacts.<name>
+→ narratio.artifact.<name>
+```
+
+`session_recap` should no longer be a special built-in analyze artifact. Instead, it is just a conventional configured artifact key:
+
+```yaml
+scriptorium:
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd_session.session_recap
+      output_path: artifacts/session_recap.md
+```
+
+`narratio.artifact.session_recap` remains valid only because `session_recap` is configured.
+
+### Artifact Output Directory
+
+Add an internal default artifact output directory, initially:
+
+```text
+artifacts
+```
+
+This default should live in `internal/config/defaults.go` or the existing equivalent defaults location.
+
+For the initial implementation:
+
+- expose no public config knob for the artifact output directory;
+- require each configured artifact to provide an explicit `output_path`;
+- validate that each configured artifact `output_path` is run-relative;
+- validate that each configured artifact `output_path` is under the internal artifact output directory;
+- reject output paths that escape the run workspace or use path traversal.
+
+This preserves future configurability without forcing Narratio to guess output extensions or formats now.
+
+### Enabled, Disabled, and Selected Artifacts
+
+Configured artifacts should have three distinct execution states:
+
+```text
+enabled by config       artifact has enabled: true
+selected for execution  artifact remains executable after --artifacts filtering
+disabled for execution  artifact is not executable, but may be resolvable from disk
+```
+
+Without `--artifacts`, all configured artifacts with `enabled: true` are selected for execution.
+
+With `--artifacts`, only the named artifacts are selected for execution. All other configured artifacts are treated as disabled for the current analyze invocation, regardless of their configured `enabled` value.
+
+Disabled artifacts may still be resolved as inputs if their configured `output_path` exists on disk and passes validation.
+
+### Disabled Artifact Resolution
+
+If artifact `B` references artifact `A`, and `A` is disabled for execution, Narratio should attempt to resolve `A` from disk.
+
+This should succeed only when:
+
+1. `A` is defined in `pipeline.scriptorium.artifacts`;
+2. `A` has a valid `output_path`;
+3. the output path exists in the current run workspace;
+4. the output is non-empty, or otherwise passes any available artifact-specific validation.
+
+The resolved provenance should make the source clear, for example:
+
+```text
+filesystem.disabled_artifact_output
+```
+
+If the file does not exist or fails validation, the dependent artifact should fail before invoking Scriptorium.
+
+Example error wording:
+
+```text
+artifact player_handout requires narratio.artifact.session_recap, but session_recap is disabled for execution and artifacts/session_recap.md does not exist
+```
+
+### Explicit Dependencies
+
+Artifact-to-artifact references require explicit `depends_on` entries.
+
+If artifact `B` has an input source of `narratio.artifact.A`, then `B.depends_on` must include `A`.
+
+This should fail:
+
+```yaml
+scriptorium:
+  artifacts:
+    player_handout:
+      enabled: true
+      prompt_id: dnd_session.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+```
+
+This should pass:
+
+```yaml
+scriptorium:
+  artifacts:
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd_session.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+```
+
+`depends_on` values refer to configured artifact keys, not full source IDs.
+
+Dependency validation should fail on:
+
+- references to unknown artifact keys;
+- missing `depends_on` entries for artifact-to-artifact input references;
+- self-dependencies;
+- dependency cycles among executable artifacts.
+
+Dependencies on disabled artifacts are permitted, but the disabled dependency must resolve from disk before the dependent artifact runs.
+
+### Execution Order
+
+The analyze stage should execute selected artifacts in dependency order.
+
+Rules:
+
+- selected artifacts are executable;
+- disabled artifacts are never executed;
+- selected artifacts may depend on other selected artifacts;
+- selected artifacts may depend on disabled artifacts if those disabled artifacts resolve from disk;
+- independent selected artifacts run in deterministic sorted-name order.
+
+Use topological sorting over selected artifacts, while validating dependency references across the full configured artifact set.
+
+### Input Resolution
+
+Input resolution should use the artifact catalog and existing artifact resolver behavior.
+
+For each configured artifact input:
+
+- built-in sources resolve through existing resolver behavior;
+- `previous_session_artifact` preserves existing behavior;
+- `narratio.artifact.<name>` resolves through the runtime artifact catalog;
+- selected dependencies resolve after being produced earlier in the same analyze execution;
+- disabled dependencies resolve from their configured output path on disk;
+- optional missing inputs are omitted;
+- required missing inputs fail before Scriptorium is invoked.
+
+### Analyze Stage Generalization
+
+The `analyze` stage should become the generic Scriptorium artifact stage.
+
+High-level flow:
+
+1. Load configured Scriptorium artifacts.
+2. Apply the `--artifacts` filter, if present.
+3. If no artifacts are selected for execution, return success metadata with `skipped=true`.
+4. Build the runtime artifact catalog.
+5. Validate artifact names, output paths, source IDs, dependencies, selected artifacts, and required fields.
+6. Resolve any disabled dependencies that are required by selected artifacts.
+7. Sort selected artifacts by dependency order.
+8. For each selected artifact:
+   - resolve configured inputs;
+   - build the Scriptorium run request;
+   - optionally run Scriptorium render-debug;
+   - run Scriptorium;
+   - fail on validation-failed result;
+   - verify the output exists and is non-empty;
+   - record artifact output metadata;
+   - register `narratio.artifact.<name>` as available in the catalog.
+9. Return aggregate analyze-stage metadata containing all generated and reused artifacts relevant to the run.
+
+The Scriptorium adapter should remain generic. It should not decide which artifacts run, how dependencies work, or how artifacts are registered.
+
+### Manifest and Metadata
+
+The manifest should remain stage-oriented.
+
+This means:
+
+- `analyze` succeeds or fails as a full stage;
+- if `analyze` has already succeeded and the user does not force it, the runner skips it as a full stage;
+- Narratio should not implement per-artifact resume in the first version.
+
+However, analyze-stage metadata should still record artifact outputs for provenance and future resolution.
+
+Recommended metadata shape:
+
+```json
+{
+  "skipped": false,
+  "artifacts": [
+    {
+      "name": "session_recap",
+      "source_id": "narratio.artifact.session_recap",
+      "output_kind": "scriptorium_artifact",
+      "path": "artifacts/session_recap.md",
+      "prompt_id": "dnd_session.session_recap",
+      "profile_id": "local-gemma-31b",
+      "provenance": "generated.current_analyze_run"
+    },
+    {
+      "name": "player_handout",
+      "source_id": "narratio.artifact.player_handout",
+      "output_kind": "scriptorium_artifact",
+      "path": "artifacts/player_handout.md",
+      "prompt_id": "dnd_session.player_handout",
+      "profile_id": "local-gemma-31b",
+      "provenance": "generated.current_analyze_run"
+    }
+  ],
+  "reused_artifacts": [
+    {
+      "name": "session_recap",
+      "source_id": "narratio.artifact.session_recap",
+      "path": "artifacts/session_recap.md",
+      "provenance": "filesystem.disabled_artifact_output"
+    }
+  ]
+}
+```
+
+The exact struct can differ from this example, but it should preserve:
+
+- artifact name;
+- canonical source ID;
+- output path;
+- prompt/profile provenance for generated artifacts;
+- reused-vs-generated provenance.
+
+### Resume and Force Behavior
+
+Keep resume behavior stage-level.
+
+Recommended semantics:
+
+```text
+No --force, analyze already succeeded:
+  runner skips analyze, regardless of --artifacts.
+
+--force, no --artifacts:
+  analyze regenerates all configured artifacts with enabled: true.
+
+--force --artifacts player_handout:
+  analyze treats only player_handout as executable.
+  all other configured artifacts are disabled for execution.
+  disabled dependencies may be reused from disk.
+
+--artifacts player_handout on a not-yet-completed analyze stage:
+  analyze runs only player_handout.
+  disabled dependencies may be reused from disk.
+```
+
+`--artifacts` should not imply `--force`. It is an execution filter, not a resume override.
+
+### `--artifacts` CLI Flag
+
+Add an `--artifacts` flag to commands that can execute or resume the analyze stage.
+
+The flag should accept one or more configured artifact names. Internally, normalize values to a set of artifact keys.
+
+Recommended behavior:
+
+- validate all requested artifact names against `pipeline.scriptorium.artifacts`;
+- reject unknown artifact names before running stages;
+- treat requested artifacts as the only executable artifacts for the analyze stage;
+- treat all other configured artifacts as disabled for execution;
+- allow disabled artifacts to satisfy dependencies from disk as described above;
+- if `--artifacts` is used while executing a stage other than `analyze`, either reject it or ignore it with a clear validation error. Prefer rejection.
+
+The exact CLI parsing style can follow Narratio's existing conventions. Both comma-separated and repeatable values are acceptable if the CLI package supports them cleanly, but the internal representation should be a set of artifact keys.
+
+### Archive Behavior
+
+Do not automatically archive every generated artifact.
+
+Artifact generation and archive promotion should remain separate concerns. Operators should continue to use `archive.promote_artifacts` to decide which generated files should be promoted or uploaded.
+
+Example:
+
+```yaml
+archive:
+  promote_artifacts:
+    - from: artifacts/session_recap.md
+      to: artifacts/session_recap.md
+      required: true
+    - from: artifacts/player_handout.md
+      to: artifacts/player_handout.md
+      required: false
+```
+
+A later enhancement may add opt-in automatic promotion of configured artifacts, but explicit promotion should remain the default.
+
+## Implementation Plan
+
+### Phase 1: Config Model and Defaults
+
+Add or update the configured artifact model to include:
+
+- `enabled`;
+- `depends_on`;
+- `prompt_id`;
+- `profile_id`;
+- `output_path`;
+- `timeout`;
+- `render_debug`;
+- `inputs`;
+- `vars`.
+
+Add an internal default artifact output directory in `internal/config/defaults.go`, initially set to `artifacts`.
+
+Validation rules:
+
+- artifact names must match a conservative identifier pattern such as `^[a-z][a-z0-9_]*$`;
+- selected/executable artifacts require `prompt_id` and `output_path`;
+- configured artifacts that may be referenced while disabled require `output_path`;
+- configured artifact output paths must be run-relative;
+- configured artifact output paths must live under the internal artifact output directory;
+- configured artifact output paths must not escape the run workspace;
+- `narratio.artifact.<name>` input sources must refer to configured artifact keys;
+- any `narratio.artifact.<name>` input source must have a matching `depends_on` entry;
+- `depends_on` entries must refer to configured artifact keys;
+- dependencies must not contain self-references or executable cycles;
+- input names and var names must remain compatible with the Scriptorium adapter's validation rules;
+- unknown YAML fields must continue to fail strict decode.
+
+Tests:
+
+- valid single configured artifact;
+- valid multiple independent artifacts;
+- valid artifact-to-artifact dependency;
+- valid dependency on disabled artifact with output path;
+- invalid artifact name;
+- missing required fields;
+- output path outside `artifacts/`;
+- dependency on missing artifact;
+- missing `depends_on` for artifact input source;
+- self-dependency;
+- cycle detection;
+- typo in `narratio.artifact.<name>` source;
+- unknown YAML fields still fail strict decode.
+
+### Phase 2: CLI Filtering
+
+Add the `--artifacts` flag and carry the selected artifact set into the run execution options.
+
+Implementation notes:
+
+- parse values according to existing CLI conventions;
+- normalize to artifact key strings;
+- validate against configured artifact definitions after config load;
+- make the selected set available to the analyze stage;
+- reject use with commands or stages where analyze cannot run.
+
+Tests:
+
+- no `--artifacts` means all enabled artifacts are selected;
+- one requested artifact is selected;
+- multiple requested artifacts are selected;
+- unknown requested artifact fails;
+- `--artifacts` does not imply `--force`;
+- `--artifacts` with already-succeeded analyze stage is skipped unless forced;
+- `--artifacts` on unsupported stage command fails clearly.
+
+### Phase 3: Runtime Artifact Catalog
+
+Introduce an internal artifact catalog abstraction.
+
+Responsibilities:
+
+- register built-in artifact definitions;
+- register configured artifact definitions;
+- map configured artifact keys to `narratio.artifact.<name>` IDs;
+- track planned, available, and executable artifact states;
+- expose lookup by canonical source ID;
+- record generated provenance;
+- record disabled-from-disk provenance.
+
+Keep the catalog narrow. It should not execute Scriptorium and should not understand prompt semantics.
+
+Tests:
+
+- built-in source lookup;
+- configured source registration;
+- duplicate/conflicting source handling;
+- planned but unavailable artifact lookup;
+- selected artifact state;
+- disabled artifact state;
+- registering an artifact as available after generation;
+- registering a disabled artifact as available from disk;
+- resolving a configured artifact from analyze metadata if that behavior is implemented.
+
+### Phase 4: Resolver Integration
+
+Update artifact resolution so configured artifact IDs are resolved through the runtime catalog.
+
+Resolution behavior:
+
+- built-in sources continue using existing resolver behavior;
+- configured artifact sources resolve from catalog availability/provenance;
+- selected configured artifacts become available after generation;
+- disabled configured artifacts may become available from disk;
+- missing optional configured artifact inputs are omitted;
+- missing required configured artifact inputs fail clearly.
+
+Tests:
+
+- configured artifact consumes a built-in transcript source;
+- configured artifact consumes another configured artifact produced earlier in the same analyze run;
+- configured artifact consumes a disabled artifact resolved from disk;
+- required disabled artifact missing on disk fails;
+- required configured artifact missing fails;
+- optional missing configured artifact is omitted;
+- reused artifact provenance is recorded distinctly from generated artifact provenance.
+
+### Phase 5: Analyze Stage Generalization
+
+Refactor `analyze` to execute selected configured artifacts.
+
+Implementation notes:
+
+- remove the hard-coded `session_recap` selection path;
+- remove the hard-coded rejection of non-`session_recap` artifacts;
+- preserve skip behavior when Scriptorium config is absent or no artifacts are selected;
+- build the runtime artifact catalog;
+- apply `--artifacts` filtering;
+- validate selected artifacts and their dependencies;
+- pre-resolve disabled dependencies from disk where required;
+- compute deterministic dependency order;
+- execute selected artifacts one at a time in dependency order;
+- keep render-debug behavior at global and artifact levels;
+- keep Scriptorium adapter invocation generic;
+- after each successful run, register the artifact as available in the catalog;
+- aggregate generated and reused artifact metadata.
+
+Tests:
+
+- no Scriptorium config skips;
+- empty artifact map skips;
+- no selected artifacts skips;
+- disabled artifacts do not run;
+- one selected artifact runs;
+- multiple independent artifacts run in deterministic order;
+- dependent selected artifact receives prior selected artifact as input;
+- dependent selected artifact receives disabled-from-disk artifact as input;
+- render-debug works for configured artifacts;
+- Scriptorium validation failure fails the stage;
+- missing required input fails the stage;
+- successful outputs are non-empty and recorded;
+- artifact filter executes only requested artifacts.
+
+### Phase 6: Manifest and Stage Metadata
+
+Update analyze-stage metadata and manifest output recording to support dynamic configured artifacts.
+
+Recommended behavior:
+
+- every generated configured artifact gets `source_id: narratio.artifact.<name>`;
+- every generated configured artifact gets a generic output kind such as `scriptorium_artifact`;
+- reused disabled artifacts are recorded separately from generated artifacts;
+- metadata is sufficient for debugging, provenance, and future resolver support;
+- metadata does not create per-artifact resume semantics.
+
+Because this is a pre-release hard cutover, do not preserve a special legacy `session_recap` output kind unless a current internal test or archive path still requires it temporarily. Prefer updating tests and examples to treat `session_recap` as an ordinary configured artifact.
+
+Tests:
+
+- metadata records one generated configured artifact;
+- metadata records multiple generated configured artifacts;
+- metadata records reused disabled artifact provenance;
+- `session_recap` is recorded as a normal configured artifact;
+- manifest still treats `analyze` as a single succeeded or failed stage;
+- runner skip behavior remains stage-level.
+
+### Phase 7: Archive and Promotion Review
+
+Review archive behavior after dynamic artifacts are recorded.
+
+Implementation notes:
+
+- do not automatically promote every configured artifact;
+- keep `archive.promote_artifacts` explicit;
+- update default or example promotion rules to use configured `session_recap` output path;
+- ensure required promotion rules fail clearly when selected artifact generation did not produce a required file.
+
+Tests:
+
+- generated artifact can be promoted by explicit archive rule;
+- required archive promotion fails if selected artifact was not generated and no file exists;
+- optional archive promotion skips cleanly if file is absent;
+- hard cutover does not rely on hard-coded `session_recap` generation.
+
+### Phase 8: Documentation and Examples
+
+Status: complete.
+
+Update documentation after the implementation is complete.
+
+Recommended documentation changes:
+
+- update `docs/config.md` with the generalized artifact configuration model;
+- update `docs/internal/artifacts.md` to describe the runtime artifact catalog;
+- update `docs/stages/analyze.md` to describe generic Scriptorium artifact generation;
+- update Scriptorium integration docs only if the adapter contract changes;
+- update full annotated pipeline examples;
+- add at least one example with multiple artifacts and one dependency;
+- document `--artifacts` behavior and its relationship to `--force`;
+- remove documentation stating that only `session_recap` is supported.
+
+Documentation should make clear that:
+
+- configured artifact source IDs use `narratio.artifact.<name>`;
+- `depends_on` uses artifact keys, not full source IDs;
+- artifact-to-artifact source references require explicit `depends_on`;
+- disabled artifacts can be reused from disk when required by selected artifacts;
+- `--artifacts` filters execution but does not imply `--force`;
+- archive promotion remains explicit;
+- per-artifact resume is not part of the initial implementation.
+
+## Migration Strategy
+
+Because Narratio is pre-release, perform a hard cutover.
+
+Required changes:
+
+1. Remove the hard-coded `session_recap` analyze behavior.
+2. Require `session_recap` to be declared under `pipeline.scriptorium.artifacts.session_recap` if the operator wants a session recap.
+3. Treat `narratio.artifact.session_recap` as valid only when `session_recap` is a configured artifact key.
+4. Update config examples to show `session_recap` as a normal configured artifact.
+5. Update tests to stop assuming that `session_recap` is a built-in analyze artifact.
+6. Keep archive promotion explicit and path-based.
+
+Example replacement config:
+
+```yaml
+scriptorium:
+  binary: scriptorium
+  config_path: /etc/scriptorium/config.yml
+  timeout: 10m
+  render_debug: false
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd_session.session_recap
+      profile_id: local-gemma-31b
+      output_path: artifacts/session_recap.md
+      timeout: 20m
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+        prior_recap:
+          source: previous_session_artifact
+          artifact: artifacts/session_recap.md
+          required: false
+      vars:
+        artifact_title: Session Recap
+```
+
+## Acceptance Criteria
+
+The feature is complete when:
+
+- operators can define more than one enabled Scriptorium artifact in `pipeline.yml`;
+- Narratio runs selected artifacts in deterministic dependency order;
+- configured artifacts are addressable as `narratio.artifact.<name>`;
+- one configured artifact can consume another configured artifact as an input;
+- artifact-to-artifact input references require explicit `depends_on`;
+- disabled artifacts can satisfy dependencies from existing on-disk outputs;
+- missing required disabled artifacts fail clearly;
+- optional missing inputs are omitted;
+- `--artifacts` can selectively execute valid configured artifact names;
+- `--artifacts` does not imply `--force`;
+- render-debug behavior works for all configured artifacts;
+- generated and reused artifacts are recorded in analyze-stage metadata;
+- `session_recap` is no longer hard-coded and works as a normal configured artifact;
+- archive promotion remains explicit;
+- tests cover config validation, dependency sorting, disabled artifact resolution, resolver behavior, CLI filtering, analyze execution, archive interactions, and metadata.
+
+## Suggested Implementation Order
+
+1. Config model, defaults, and validation.
+2. CLI parsing and propagation of `--artifacts` selection.
+3. Runtime artifact catalog.
+4. Resolver integration for configured artifacts.
+5. Analyze stage generalization.
+6. Stage metadata and manifest output recording.
+7. Archive behavior review.
+8. Documentation and examples.
+
+This order keeps the most static pieces first, then moves into execution behavior once the configuration contract is explicit and well tested.

docs/troubleshooting.md

@@ -0,0 +1,289 @@
+# Troubleshooting
+
+## Purpose
+Canonical operator troubleshooting guide for recurring implemented Narratio failures.
+
+## Config file discovery failure
+
+Symptom:
+- `run`, `plan`, `resume`, or `run-stage` fails with config/session not found.
+
+Likely Cause:
+- `pipeline.yml` or `session.yml` is missing from discovery paths.
+- wrong working directory when relying on `./session.yml`.
+
+Diagnostics:
+
+```bash
+pwd
+ls -l ./session.yml
+ls -l /usr/local/etc/narratio/pipeline.yml /etc/narratio/pipeline.yml
+```
+
+Safe Fix:
+- pass explicit `--config` and `--session`.
+- or place files in documented discovery paths.
+
+Links:
+- [docs/config.md](./config.md)
+- [docs/cli.md](./cli.md)
+
+## Session template rendering failure
+
+Symptom:
+- load fails with unresolved placeholder or `session_id` mismatch.
+
+Likely Cause:
+- templated `session.yml` used without `--session-id`.
+- rendered `session_id` differs from passed `--session-id`.
+
+Diagnostics:
+
+```bash
+narratio plan --session ./session.yml --session-id 2026-04-04
+```
+
+Safe Fix:
+- pass `--session-id` when template placeholders are present.
+- ensure rendered `session_id` matches intended run session id.
+
+Links:
+- [docs/config.md](./config.md)
+
+## Strict YAML decode or validation failure
+
+Symptom:
+- config load fails with unknown field or validation error.
+
+Likely Cause:
+- typo/stale field name.
+- missing required fields or invalid constraints.
+
+Diagnostics:
+
+```bash
+narratio plan --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04
+```
+
+Safe Fix:
+- align fields/values to canonical config reference and examples.
+
+Links:
+- [docs/config.md](./config.md)
+- [examples/](../examples/)
+
+## `--artifacts` selection failure
+
+Symptom:
+- `run`/`resume`/`run-stage` fails with invalid or unknown artifact selection.
+
+Likely Cause:
+- `--artifacts` contains blank names or unknown artifact keys.
+- `pipeline.scriptorium.artifacts` missing while using `--artifacts`.
+
+Diagnostics:
+
+```bash
+narratio run --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04 --artifacts player_handout
+```
+
+Safe Fix:
+- use configured artifact keys only.
+- ensure `pipeline.scriptorium.artifacts` is defined.
+
+Links:
+- [docs/cli.md](./cli.md)
+- [docs/config.md](./config.md)
+
+## `run-stage --artifacts` on non-analyze stage
+
+Symptom:
+- `run-stage` fails with `--artifacts is only supported for stage "analyze"`.
+
+Likely Cause:
+- `--artifacts` was used with a non-`analyze` stage.
+
+Diagnostics:
+
+```bash
+narratio run-stage --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04 --artifacts session_recap polish
+```
+
+Safe Fix:
+- use `--artifacts` only with `run-stage ... analyze`.
+
+Links:
+- [docs/cli.md](./cli.md)
+
+## Configured artifact dependency/input validation failure
+
+Symptom:
+- config validation fails for `depends_on`, `narratio.artifact.<name>` source, or artifact output path.
+
+Likely Cause:
+- `narratio.artifact.<name>` source missing matching `depends_on` key.
+- dependency references unknown artifact key.
+- dependency self-reference or enabled dependency cycle.
+- artifact output path missing/invalid/outside `artifacts/` root.
+
+Diagnostics:
+
+```bash
+narratio plan --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04
+```
+
+Safe Fix:
+- ensure artifact-to-artifact inputs have explicit `depends_on` entries using artifact keys.
+- ensure referenced artifacts exist and define valid `output_path` values.
+- keep output paths relative and under `artifacts/`.
+
+Links:
+- [docs/config.md](./config.md)
+- [docs/internal/stage-analyze.md](./internal/stage-analyze.md)
+
+## Required configured artifact input unavailable at analyze time
+
+Symptom:
+- analyze fails because configured input source is unavailable.
+
+Likely Cause:
+- required upstream configured artifact was not selected/executed this run.
+- non-executable dependency output file is missing or invalid on disk.
+
+Diagnostics:
+
+```bash
+narratio status --manifest /path/to/manifest.json
+narratio run-stage --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04 --artifacts player_handout analyze
+```
+
+Safe Fix:
+- run analyze with needed artifacts selected.
+- or ensure dependency output file exists at configured path and is valid.
+
+Links:
+- [docs/operations.md](./operations.md)
+- [docs/config.md](./config.md)
+
+## Manifest/status path failure
+
+Symptom:
+- `status` fails because manifest path is missing, unreadable, or invalid.
+
+Likely Cause:
+- wrong manifest path.
+- manifest removed after cleanup.
+- `--manifest` omitted.
+
+Diagnostics:
+
+```bash
+narratio status --manifest /path/to/manifest.json
+ls -l /path/to/manifest.json
+```
+
+Safe Fix:
+- use manifest path printed by `run`, `resume`, or `run-stage`.
+
+Links:
+- [docs/cli.md](./cli.md)
+- [docs/operations.md](./operations.md)
+
+## Session lock conflict (`.lock`)
+
+Symptom:
+- run fails with lock conflict for session workdir.
+
+Likely Cause:
+- another Narratio process is running same session.
+- stale lock from interrupted prior run.
+
+Diagnostics:
+
+```bash
+ls -l {workspace.root}/work/{campaign}/{session_id}/.lock
+cat {workspace.root}/work/{campaign}/{session_id}/.lock
+ps aux | grep narratio
+```
+
+Safe Fix:
+- wait for active run to finish.
+- if no process is active, remove only stale session `.lock` file.
+
+Links:
+- [docs/operations.md](./operations.md)
+- [docs/internal/workspace.md](./internal/workspace.md)
+
+## Secrets env-dir or credential-env failure
+
+Symptom:
+- startup fails loading secrets directory, or stage fails due to missing credential env vars.
+
+Likely Cause:
+- invalid `pipeline.secrets.env_dir` path/permissions.
+- required credential env var unset/empty.
+
+Diagnostics:
+
+```bash
+ls -la /path/to/secrets_dir
+env | grep -E 'AUDITA|OBJECT_STORAGE|AWS|SCRIPTORIUM'
+```
+
+Safe Fix:
+- fix secrets directory and credential env vars.
+- keep secret values out of YAML.
+
+Links:
+- [docs/config.md](./config.md)
+
+## S3-audio prepare failure
+
+Symptom:
+- `prepare` fails in S3 mode (listing/downloading/no audio/backend error).
+
+Likely Cause:
+- wrong `session.inputs.audio_s3.prefix`.
+- no `.flac` files at resolved prefix.
+- invalid/missing object-store credentials or backend config.
+- mixed local+S3 audio input config.
+
+Diagnostics:
+
+```bash
+narratio run-stage --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04 prepare
+```
+
+Safe Fix:
+- configure exactly one audio source mode.
+- verify `.flac` files and storage access.
+
+Links:
+- [docs/config.md](./config.md)
+- [docs/operations.md](./operations.md)
+
+## Archive promotion/current-pointer failure
+
+Symptom:
+- archive fails on required promotion source missing or pointer write failure.
+
+Likely Cause:
+- required promoted file absent (including analyze outputs not generated for this run).
+- storage upload failed before `current/run_id.txt` commit marker write.
+
+Diagnostics:
+
+```bash
+narratio status --manifest /path/to/manifest.json
+narratio run-stage --config /path/to/pipeline.yml --session /path/to/session.yml --session-id 2026-04-04 archive
+```
+
+Safe Fix:
+- rerun or resume upstream stages to generate required files.
+- adjust promotion rules to match files that must exist.
+- retry after storage issue is resolved.
+
+Links:
+- [docs/operations.md](./operations.md)
+- [docs/config.md](./config.md)
+- [docs/internal/stage-archive.md](./internal/stage-archive.md)

examples/pipeline.full.annotated.yml

@@ -0,0 +1,182 @@
+# Full annotated pipeline example for implemented Narratio config fields.
+# Values are safe placeholders and must be adapted per environment.
+
+workspace:
+  # Optional: defaults to /var/lib/narratio.
+  root: /var/lib/narratio/workspace
+  # Optional: remove run-scoped workdir after successful archive commit.
+  cleanup_after_archive: false
+
+# Optional: local secret file loader (directory of ENV_VAR_NAME files).
+# secrets:
+#   env_dir: ./secrets
+
+storage:
+  # Optional storage backend selector; use "s3" for archive + S3 audio workflows.
+  backend: s3
+  # Compatibility fields retained in schema.
+  bucket: ""
+  prefix: ""
+  s3:
+    # Required when using S3 audio or S3 archive uploads.
+    bucket: my-dnd-archive
+    # Optional; defaults to "dnd".
+    root_prefix: dnd
+    # Optional region/endpoint settings.
+    region: us-east-1
+    endpoint: ""
+    force_path_style: false
+    # Optional; defaults shown explicitly.
+    access_key_id_env: OBJECT_STORAGE_KEY_ID
+    secret_access_key_env: OBJECT_STORAGE_KEY
+
+spool:
+  # Optional; defaults to /var/spool/narratio.
+  root: /var/spool/narratio
+  # Optional cleanup of run-scoped spool audio after successful archive commit.
+  delete_audio_after_archive: false
+
+archive:
+  # Optional booleans; defaults are true.
+  enabled: true
+  upload_run: true
+  # Optional promotion rules; required files fail archive if missing.
+  promote_artifacts:
+    - from: transcripts/trimmed.json
+      to: transcripts/trimmed.json
+      required: true
+    - from: artifacts/session_recap.md
+      to: artifacts/session_recap.md
+      required: true
+    - from: artifacts/player_handout.md
+      to: artifacts/player_handout.md
+      required: false
+
+whisperx:
+  # Required.
+  transcribe_url: "https://transcription.example.com/transcribe"
+  # Optional overrides; defaults shown explicitly.
+  language: en
+  timeout: 30m
+  retries: 3
+  retry_delay: 2s
+  concurrency: 2
+
+seriatim:
+  # Optional overrides; defaults shown explicitly.
+  binary: seriatim
+  timeout: 10m
+  output_schema: seriatim-intermediate
+  coalesce_gap: 3.0
+  report: true
+  env:
+    # Optional advanced tuning; set only when needed.
+    overlap_word_run_gap: 1.0
+    overlap_word_run_reorder_window: 1.0
+    backchannel_max_duration: 2.0
+    filler_max_duration: 1.25
+
+audita:
+  # Optional overrides; defaults shown explicitly where applicable.
+  binary: audita
+  timeout: 3h
+  llm_api_key_env: AUDITA_LLM_API_KEY
+  modules: [glossary, homophones, spoken_word, grammar]
+  base_url: ""
+  model: ""
+  total_llm_concurrency: 2
+  proposal_llm_concurrency: 1
+  validation_model: ""
+  validation_llm_concurrency: 1
+  transcript_description: ""
+  config_path: /usr/local/etc/audita/config.yml
+  output_schema: audita-v1
+  work_dir_retention: auto
+  report: true
+
+normalize:
+  # Optional; defaults shown explicitly.
+  output_path: transcripts/normalized.json
+  output_schema: seriatim-intermediate
+  report: true
+
+trim:
+  # Keep disabled unless bounds prompt integration is configured.
+  enabled: false
+  output_path: transcripts/trimmed.json
+  bounds:
+    prompt_id: dnd.session_bounds
+    profile_id: local-fast
+    transcript_input_name: transcript
+    output_path: reports/session_bounds.json
+    timeout: 10m
+    render_debug: false
+    render_output_path: reports/session_bounds.render.json
+  seriatim:
+    report: false
+
+scriptorium:
+  binary: scriptorium
+  config_path: /usr/local/etc/scriptorium/config.yml
+  timeout: 10m
+  render_debug: false
+  artifacts:
+    # Configured artifact keys map to source IDs narratio.artifact.<key>.
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      profile_id: local-fast
+      output_path: artifacts/session_recap.md
+      timeout: 10m
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+        previous_recap:
+          source: previous_session_artifact
+          artifact: session_recap
+          path: ""
+          required: false
+      vars:
+        session_id: true
+        session_date: true
+        campaign_name: true
+        previous_session_id: true
+        output_kind: session_recap
+
+    # Example dependent artifact:
+    # - depends_on entries use artifact keys.
+    # - narratio.artifact.<key> sources require matching depends_on membership.
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.player_handout
+      profile_id: local-fast
+      output_path: artifacts/player_handout.md
+      timeout: 10m
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+      vars:
+        session_id: true
+        campaign_name: true
+        output_kind: player_handout
+
+analyzer:
+  # Optional adapter settings.
+  binary_path: ""
+  timeout: 2m
+  artifacts:
+    output_dir: ""
+    types: []
+
+notification:
+  # Optional notification settings.
+  backend: ""
+  recipient: ""
+  timeout: 30s

examples/pipeline.minimal.yml

@@ -1,109 +1,2 @@
-workspace:
-  root: ./tmp/narratio-workspace
-
-storage:
-  backend: local
-
 whisperx:
   transcribe_url: "https://transcription.example.com/transcribe"
-  language: "en"
-  timeout: "30m"
-  retries: 3
-  retry_delay: "2s"
-  concurrency: 2
-
-seriatim:
-  binary: "seriatim"
-  timeout: "10m"
-  output_schema: "seriatim-intermediate"
-  coalesce_gap: 3.0
-  report: true
-  env:
-    overlap_word_run_gap: 1.0
-    overlap_word_run_reorder_window: 1.0
-    backchannel_max_duration: 2.0
-    filler_max_duration: 1.25
-
-audita:
-  binary: "audita"
-  timeout: "3h"
-  llm_api_key_env: "AUDITA_LLM_API_KEY"
-  modules:
-    - glossary
-    - homophones
-    - glossary
-    - spoken_word
-    - grammar
-    - homophones
-    - glossary
-  base_url: "https://openrouter.ai/api/v1"
-  model: "openrouter/google/gemma-4-31b-it"
-  llm_concurrency: 1
-  validation_model: ""
-  validation_llm_concurrency: 1
-  report: true
-
-normalize:
-  # Session-workdir-relative when not absolute.
-  output_path: "transcripts/normalized.json"
-  output_schema: "seriatim-intermediate"
-  report: true
-
-trim:
-  enabled: true
-  # Session-workdir-relative when not absolute.
-  output_path: "transcripts/trimmed.json"
-  bounds:
-    prompt_id: "dnd_session.bounds"
-    # Empty means use prompt default profile.
-    profile_id: ""
-    transcript_input_name: "transcript"
-    output_path: "artifacts/session_bounds.json"
-    timeout: "10m"
-    render_debug: false
-    render_output_path: "artifacts/session_bounds.render.json"
-  seriatim:
-    report: false
-
-scriptorium:
-  binary: "scriptorium"
-  config_path: "/etc/scriptorium/config.yml"
-  timeout: "10m"
-  render_debug: false
-  artifacts:
-    session_recap:
-      enabled: true
-      prompt_id: "dnd.session_recap"
-      profile_id: "local-quality"
-      output_path: "artifacts/session_recap.md"
-      timeout: "10m"
-      # Optional per-artifact override of global scriptorium.render_debug.
-      # render_debug: true
-      inputs:
-        transcript:
-          # Available transcript sources:
-          # - trimmed_transcript (recommended for session_recap)
-          # - normalized_transcript (recommended for future full-session analysis)
-          # - processed_transcript (raw Audita-polished output)
-          source: "trimmed_transcript"
-          required: true
-        previous_recap:
-          source: "previous_session_artifact"
-          artifact: "session_recap"
-          # Optional: set when previous recap is available.
-          path: ""
-          required: false
-      vars:
-        session_id: true
-        session_date: true
-        campaign_name: true
-        previous_session_id: true
-        output_kind: "session_recap"
-
-analyzer:
-  timeout: 20m
-  artifacts:
-    output_dir: artifacts
-
-notification:
-  timeout: 10s

examples/pipeline.production.yml

@@ -0,0 +1,116 @@
+workspace:
+  root: /var/lib/narratio/workspace
+  cleanup_after_archive: true
+
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+    root_prefix: dnd
+    region: us-east-1
+    access_key_id_env: OBJECT_STORAGE_KEY_ID
+    secret_access_key_env: OBJECT_STORAGE_KEY
+
+spool:
+  root: /var/spool/narratio
+  delete_audio_after_archive: true
+
+archive:
+  enabled: true
+  upload_run: true
+  promote_artifacts:
+    - from: transcripts/trimmed.json
+      to: transcripts/trimmed.json
+      required: true
+    - from: artifacts/session_recap.md
+      to: artifacts/session_recap.md
+      required: true
+    - from: artifacts/player_handout.md
+      to: artifacts/player_handout.md
+      required: false
+
+whisperx:
+  transcribe_url: "https://transcription.example.com/transcribe"
+  language: en
+  timeout: 45m
+  retries: 3
+  retry_delay: 3s
+  concurrency: 2
+
+seriatim:
+  binary: seriatim
+  timeout: 10m
+  output_schema: seriatim-intermediate
+  coalesce_gap: 3.0
+  report: true
+
+audita:
+  binary: audita
+  timeout: 3h
+  llm_api_key_env: AUDITA_LLM_API_KEY
+  modules: [glossary, homophones, spoken_word, grammar]
+  output_schema: audita-v1
+  work_dir_retention: auto
+  total_llm_concurrency: 2
+  proposal_llm_concurrency: 1
+  validation_llm_concurrency: 1
+  report: true
+
+normalize:
+  output_path: transcripts/normalized.json
+  output_schema: seriatim-intermediate
+  report: true
+
+trim:
+  enabled: false
+
+scriptorium:
+  binary: scriptorium
+  config_path: /usr/local/etc/scriptorium/config.yml
+  timeout: 10m
+  render_debug: false
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      profile_id: local-fast
+      output_path: artifacts/session_recap.md
+      timeout: 10m
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+        previous_recap:
+          source: previous_session_artifact
+          artifact: session_recap
+          required: false
+      vars:
+        session_id: true
+        session_date: true
+        campaign_name: true
+        previous_session_id: true
+        output_kind: session_recap
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.player_handout
+      profile_id: local-fast
+      output_path: artifacts/player_handout.md
+      timeout: 10m
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+      vars:
+        session_id: true
+        output_kind: player_handout
+
+analyzer:
+  timeout: 2m
+
+notification:
+  timeout: 30s

examples/session.local-audio.yml

@@ -0,0 +1,9 @@
+session_id: 2026-05-03
+campaign: sample-campaign
+date: 2026-05-03
+title: Sample Session
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./examples/speakers.yml
+  autocorrect_file: ./examples/autocorrect.yml
+  glossary_file: ./examples/glossary.yml

examples/session.minimal.yml

@@ -1,10 +0,0 @@
-session_id: 2026-05-03
-campaign: sample-campaign
-date: 2026-05-03
-title: Sample Session
-inputs:
-  audio_dir: ./audio
-  speakers_file: ./speakers.yml
-  autocorrect_file: ./autocorrect.yml
-  glossary_file: ./glossary.yml
-

examples/session.s3-audio.yml

@@ -0,0 +1,10 @@
+session_id: 2026-05-03
+campaign: sample-campaign
+date: 2026-05-03
+title: Sample Session
+inputs:
+  audio_s3:
+    prefix: audio/
+  speakers_file: ./examples/speakers.yml
+  autocorrect_file: ./examples/autocorrect.yml
+  glossary_file: ./examples/glossary.yml

examples/session.template.yml

@@ -0,0 +1,7 @@
+session_id: "{{ session_id }}"
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./examples/speakers.yml
+  autocorrect_file: ./examples/autocorrect.yml
+  glossary_file: ./examples/glossary.yml

go.mod

@@ -2,4 +2,27 @@ module gitea.maximumdirect.net/eric/narratio
 
 go 1.25.0
 
-require gopkg.in/yaml.v3 v3.0.1
+require (
+	github.com/aws/aws-sdk-go-v2/config v1.32.17
+	github.com/aws/aws-sdk-go-v2/credentials v1.19.16
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.101.0
+	github.com/aws/smithy-go v1.25.1
+	gopkg.in/yaml.v3 v3.0.1
+)
+
+require (
+	github.com/aws/aws-sdk-go-v2 v1.41.7 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.10 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.23 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.23 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.23 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.24 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.9 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.15 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.23 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.23 // indirect
+	github.com/aws/aws-sdk-go-v2/service/signin v1.0.11 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.17 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.21 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.42.1 // indirect
+)

go.sum

@@ -1,3 +1,39 @@
+github.com/aws/aws-sdk-go-v2 v1.41.7 h1:DWpAJt66FmnnaRIOT/8ASTucrvuDPZASqhhLey6tLY8=
+github.com/aws/aws-sdk-go-v2 v1.41.7/go.mod h1:4LAfZOPHNVNQEckOACQx60Y8pSRjIkNZQz1w92xpMJc=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.10 h1:gx1AwW1Iyk9Z9dD9F4akX5gnN3QZwUB20GGKH/I+Rho=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.10/go.mod h1:qqY157uZoqm5OXq/amuaBJyC9hgBCBQnsaWnPe905GY=
+github.com/aws/aws-sdk-go-v2/config v1.32.17 h1:FpL4/758/diKwqbytU0prpuiu60fgXKUWCpDJtApclU=
+github.com/aws/aws-sdk-go-v2/config v1.32.17/go.mod h1:OXqUMzgXytfoF9JaKkhrOYsyh72t9G+MJH8mMRaexOE=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.16 h1:r3RJBuU7X9ibt8RHbMjWE6y60QbKBiII6wSrXnapxSU=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.16/go.mod h1:6cx7zqDENJDbBIIWX6P8s0h6hqHC8Avbjh9Dseo27ug=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.23 h1:UuSfcORqNSz/ey3VPRS8TcVH2Ikf0/sC+Hdj400QI6U=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.23/go.mod h1:+G/OSGiOFnSOkYloKj/9M35s74LgVAdJBSD5lsFfqKg=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.23 h1:GpT/TrnBYuE5gan2cZbTtvP+JlHsutdmlV2YfEyNde0=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.23/go.mod h1:xYWD6BS9ywC5bS3sz9Xh04whO/hzK2plt2Zkyrp4JuA=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.23 h1:bpd8vxhlQi2r1hiueOw02f/duEPTMK59Q4QMAoTTtTo=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.23/go.mod h1:15DfR2nw+CRHIk0tqNyifu3G1YdAOy68RftkhMDDwYk=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.24 h1:OQqn11BtaYv1WLUowvcA30MpzIu8Ti4pcLPIIyoKZrA=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.24/go.mod h1:X5ZJyfwVrWA96GzPmUCWFQaEARPR7gCrpq2E92PJwAE=
+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.9 h1:FLudkZLt5ci0ozzgkVo8BJGwvqNaZbTWb3UcucAateA=
+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.9/go.mod h1:w7wZ/s9qK7c8g4al+UyoF1Sp/Z45UwMGcqIzLWVQHWk=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.15 h1:ieLCO1JxUWuxTZ1cRd0GAaeX7O6cIxnwk7tc1LsQhC4=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.15/go.mod h1:e3IzZvQ3kAWNykvE0Tr0RDZCMFInMvhku3qNpcIQXhM=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.23 h1:pbrxO/kuIwgEsOPLkaHu0O+m4fNgLU8B3vxQ+72jTPw=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.23/go.mod h1:/CMNUqoj46HpS3MNRDEDIwcgEnrtZlKRaHNaHxIFpNA=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.23 h1:03xatSQO4+AM1lTAbnRg5OK528EUg744nW7F73U8DKw=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.23/go.mod h1:M8l3mwgx5ToK7wot2sBBce/ojzgnPzZXUV445gTSyE8=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.101.0 h1:etqBTKY581iwLL/H/S2sVgk3C9lAsTJFeXWFDsDcWOU=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.101.0/go.mod h1:L2dcoOgS2VSgbPLvpak2NyUPsO1TBN7M45Z4H7DlRc4=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.11 h1:TdJ+HdzOBhU8+iVAOGUTU63VXopcumCOF1paFulHWZc=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.11/go.mod h1:R82ZRExE/nheo0N+T8zHPcLRTcH8MGsnR3BiVGX0TwI=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.17 h1:7byT8HUWrgoRp6sXjxtZwgOKfhss5fW6SkLBtqzgRoE=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.17/go.mod h1:xNWknVi4Ezm1vg1QsB/5EWpAJURq22uqd38U8qKvOJc=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.21 h1:+1Kl1zx6bWi4X7cKi3VYh29h8BvsCoHQEQ6ST9X8w7w=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.21/go.mod h1:4vIRDq+CJB2xFAXZ+YgGUTiEft7oAQlhIs71xcSeuVg=
+github.com/aws/aws-sdk-go-v2/service/sts v1.42.1 h1:F/M5Y9I3nwr2IEpshZgh1GeHpOItExNM9L1euNuh/fk=
+github.com/aws/aws-sdk-go-v2/service/sts v1.42.1/go.mod h1:mTNxImtovCOEEuD65mKW7DCsL+2gjEH+RPEAexAzAio=
+github.com/aws/smithy-go v1.25.1 h1:J8ERsGSU7d+aCmdQur5Txg6bVoYelvQJgtZehD12GkI=
+github.com/aws/smithy-go v1.25.1/go.mod h1:YE2RhdIuDbA5E5bTdciG9KrW3+TiEONeUWCqxX9i1Fc=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

internal/adapters/audita/runner.go

@@ -24,6 +24,12 @@ type PolishRequest struct {
 	Modules                  []string
 	BaseURL                  string
 	Model                    string
+	TranscriptDescription    string
+	ConfigPath               string
+	OutputSchema             string
+	WorkDirRetention         string
+	TotalLLMConcurrency      *int
+	ProposalLLMConcurrency   *int
 	ValidationModel          string
 	ValidationLLMConcurrency *int
 	StdoutLogPath            string

internal/adapters/audita/subprocess.go

@@ -21,7 +21,12 @@ type SubprocessRunnerConfig struct {
 	Modules                  []string
 	BaseURL                  string
 	Model                    string
-	LLMConcurrency           *int
+	TranscriptDescription    string
+	ConfigPath               string
+	OutputSchema             string
+	WorkDirRetention         string
+	TotalLLMConcurrency      *int
+	ProposalLLMConcurrency   *int
 	ValidationModel          string
 	ValidationLLMConcurrency *int
 	Report                   bool
@@ -35,7 +40,12 @@ type SubprocessRunner struct {
 	modules                  []string
 	baseURL                  string
 	model                    string
-	llmConcurrency           *int
+	transcriptDescription    string
+	configPath               string
+	outputSchema             string
+	workDirRetention         string
+	totalLLMConcurrency      *int
+	proposalLLMConcurrency   *int
 	validationModel          string
 	validationLLMConcurrency *int
 	report                   bool
@@ -49,7 +59,12 @@ func NewSubprocessRunnerFromConfigValues(
 	modules []string,
 	baseURL string,
 	model string,
-	llmConcurrency *int,
+	transcriptDescription string,
+	configPath string,
+	outputSchema string,
+	workDirRetention string,
+	totalLLMConcurrency *int,
+	proposalLLMConcurrency *int,
 	validationModel string,
 	validationLLMConcurrency *int,
 	report bool,
@@ -68,7 +83,12 @@ func NewSubprocessRunnerFromConfigValues(
 		Modules:                  modules,
 		BaseURL:                  baseURL,
 		Model:                    model,
-		LLMConcurrency:           llmConcurrency,
+		TranscriptDescription:    transcriptDescription,
+		ConfigPath:               configPath,
+		OutputSchema:             outputSchema,
+		WorkDirRetention:         workDirRetention,
+		TotalLLMConcurrency:      totalLLMConcurrency,
+		ProposalLLMConcurrency:   proposalLLMConcurrency,
 		ValidationModel:          validationModel,
 		ValidationLLMConcurrency: validationLLMConcurrency,
 		Report:                   report,
@@ -83,33 +103,39 @@ func NewSubprocessRunner(cfg SubprocessRunnerConfig) (*SubprocessRunner, error)
 	if cfg.Timeout <= 0 {
 		return nil, fmt.Errorf("audita timeout must be > 0")
 	}
-	if len(cfg.Modules) == 0 {
-		return nil, fmt.Errorf("audita modules must include at least one module")
-	}
 	for i, module := range cfg.Modules {
 		if strings.TrimSpace(module) == "" {
 			return nil, fmt.Errorf("audita module at index %d is empty", i)
 		}
 	}
-	if strings.TrimSpace(cfg.BaseURL) == "" {
-		return nil, fmt.Errorf("audita base url is required")
-	}
-	u, err := url.Parse(cfg.BaseURL)
-	if err != nil || u.Scheme == "" || u.Host == "" {
-		if err != nil {
-			return nil, fmt.Errorf("audita base url %q is invalid: %w", cfg.BaseURL, err)
+	if strings.TrimSpace(cfg.BaseURL) != "" {
+		u, err := url.Parse(cfg.BaseURL)
+		if err != nil || u.Scheme == "" || u.Host == "" {
+			if err != nil {
+				return nil, fmt.Errorf("audita base url %q is invalid: %w", cfg.BaseURL, err)
+			}
+			return nil, fmt.Errorf("audita base url %q is invalid", cfg.BaseURL)
 		}
-		return nil, fmt.Errorf("audita base url %q is invalid", cfg.BaseURL)
 	}
-	if strings.TrimSpace(cfg.Model) == "" {
-		return nil, fmt.Errorf("audita model is required")
+	if cfg.TotalLLMConcurrency != nil && *cfg.TotalLLMConcurrency <= 0 {
+		return nil, fmt.Errorf("audita total llm concurrency must be > 0 when provided")
 	}
-	if cfg.LLMConcurrency != nil && *cfg.LLMConcurrency <= 0 {
-		return nil, fmt.Errorf("audita llm concurrency must be > 0 when provided")
+	if cfg.ProposalLLMConcurrency != nil && *cfg.ProposalLLMConcurrency <= 0 {
+		return nil, fmt.Errorf("audita proposal llm concurrency must be > 0 when provided")
 	}
 	if cfg.ValidationLLMConcurrency != nil && *cfg.ValidationLLMConcurrency <= 0 {
 		return nil, fmt.Errorf("audita validation llm concurrency must be > 0 when provided")
 	}
+	switch strings.TrimSpace(cfg.OutputSchema) {
+	case "", "bare-segments", "audita-v1":
+	default:
+		return nil, fmt.Errorf("audita output schema must be one of: bare-segments, audita-v1")
+	}
+	switch strings.TrimSpace(cfg.WorkDirRetention) {
+	case "", "always", "auto", "never":
+	default:
+		return nil, fmt.Errorf("audita work dir retention must be one of: always, auto, never")
+	}
 
 	modules := make([]string, len(cfg.Modules))
 	for i, m := range cfg.Modules {
@@ -123,7 +149,12 @@ func NewSubprocessRunner(cfg SubprocessRunnerConfig) (*SubprocessRunner, error)
 		modules:                  modules,
 		baseURL:                  strings.TrimSpace(cfg.BaseURL),
 		model:                    strings.TrimSpace(cfg.Model),
-		llmConcurrency:           cfg.LLMConcurrency,
+		transcriptDescription:    strings.TrimSpace(cfg.TranscriptDescription),
+		configPath:               strings.TrimSpace(cfg.ConfigPath),
+		outputSchema:             strings.TrimSpace(cfg.OutputSchema),
+		workDirRetention:         strings.TrimSpace(cfg.WorkDirRetention),
+		totalLLMConcurrency:      cfg.TotalLLMConcurrency,
+		proposalLLMConcurrency:   cfg.ProposalLLMConcurrency,
 		validationModel:          strings.TrimSpace(cfg.ValidationModel),
 		validationLLMConcurrency: cfg.ValidationLLMConcurrency,
 		report:                   cfg.Report,
@@ -152,7 +183,7 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
 	}
 
 	reqModules := req.Modules
-	if len(reqModules) == 0 {
+	if reqModules == nil {
 		reqModules = append([]string(nil), r.modules...)
 	}
 	args := r.buildArgs(req, reqModules)
@@ -168,14 +199,9 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
 		env["AUDITA_LLM_API_KEY"] = credential
 		credentialPresent = true
 	}
-	primaryConcurrencyViaEnv := false
-	if r.llmConcurrency != nil {
-		env["AUDITA_LLM_CONCURRENCY"] = strconv.Itoa(*r.llmConcurrency)
-		primaryConcurrencyViaEnv = true
-	}
 
 	if req.GeneratedConfigPath != "" {
-		if err := r.writeInvocationConfig(req, args, reqModules, credentialPresent, primaryConcurrencyViaEnv); err != nil {
+		if err := r.writeInvocationConfig(req, args, reqModules, credentialPresent); err != nil {
 			return PolishResult{}, fmt.Errorf("write audita invocation config %q: %w", req.GeneratedConfigPath, err)
 		}
 	}
@@ -196,7 +222,7 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
 			req.StderrLogPath,
 		)
 		wrappedMessage = addSubprocessStreamHint(wrappedMessage, err)
-		return r.failureResult(req, reqModules, runRes, credentialPresent, primaryConcurrencyViaEnv), fmt.Errorf(
+		return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf(
 			"%s: %w",
 			wrappedMessage,
 			err,
@@ -204,11 +230,11 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
 	}
 
 	if err := validateProcessedOutput(req.OutputProcessedPath); err != nil {
-		return r.failureResult(req, reqModules, runRes, credentialPresent, primaryConcurrencyViaEnv), fmt.Errorf("validate audita processed output %q: %w", req.OutputProcessedPath, err)
+		return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf("validate audita processed output %q: %w", req.OutputProcessedPath, err)
 	}
 	if r.report {
 		if err := validateJSONFile(req.ReportPath); err != nil {
-			return r.failureResult(req, reqModules, runRes, credentialPresent, primaryConcurrencyViaEnv), fmt.Errorf("validate audita report output %q: %w", req.ReportPath, err)
+			return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf("validate audita report output %q: %w", req.ReportPath, err)
 		}
 	}
 
@@ -223,21 +249,25 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
 		Duration:                runRes.Duration,
 		InvokedBinary:           r.binary,
 		Metadata: map[string]any{
-			"adapter":                          "audita_subprocess",
-			"modules":                          reqModules,
-			"base_url":                         r.baseURL,
-			"model":                            r.model,
-			"validation_model":                 r.validationModel,
-			"validation_llm_concurrency":       r.validationLLMConcurrency,
-			"credential_env_var":               r.llmAPIKeyEnv,
-			"credential_present":               credentialPresent,
-			"primary_llm_concurrency_via_env":  primaryConcurrencyViaEnv,
-			"primary_llm_concurrency_env_name": "AUDITA_LLM_CONCURRENCY",
+			"adapter":                    "audita_subprocess",
+			"modules":                    reqModules,
+			"base_url":                   r.baseURL,
+			"model":                      r.model,
+			"transcript_description":     r.transcriptDescription,
+			"config_path":                r.configPath,
+			"output_schema":              r.outputSchema,
+			"work_dir_retention":         r.workDirRetention,
+			"validation_model":           r.validationModel,
+			"total_llm_concurrency":      r.totalLLMConcurrency,
+			"proposal_llm_concurrency":   r.proposalLLMConcurrency,
+			"validation_llm_concurrency": r.validationLLMConcurrency,
+			"credential_env_var":         r.llmAPIKeyEnv,
+			"credential_present":         credentialPresent,
 		},
 	}, nil
 }
 
-func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, runRes subprocess.RunResult, credentialPresent bool, primaryConcurrencyViaEnv bool) PolishResult {
+func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, runRes subprocess.RunResult, credentialPresent bool) PolishResult {
 	return PolishResult{
 		ProcessedTranscriptPath: req.OutputProcessedPath,
 		ReportPath:              req.ReportPath,
@@ -249,16 +279,20 @@ func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, ru
 		Duration:                runRes.Duration,
 		InvokedBinary:           r.binary,
 		Metadata: map[string]any{
-			"adapter":                          "audita_subprocess",
-			"modules":                          modules,
-			"base_url":                         r.baseURL,
-			"model":                            r.model,
-			"validation_model":                 r.validationModel,
-			"validation_llm_concurrency":       r.validationLLMConcurrency,
-			"credential_env_var":               r.llmAPIKeyEnv,
-			"credential_present":               credentialPresent,
-			"primary_llm_concurrency_via_env":  primaryConcurrencyViaEnv,
-			"primary_llm_concurrency_env_name": "AUDITA_LLM_CONCURRENCY",
+			"adapter":                    "audita_subprocess",
+			"modules":                    modules,
+			"base_url":                   r.baseURL,
+			"model":                      r.model,
+			"transcript_description":     r.transcriptDescription,
+			"config_path":                r.configPath,
+			"output_schema":              r.outputSchema,
+			"work_dir_retention":         r.workDirRetention,
+			"validation_model":           r.validationModel,
+			"total_llm_concurrency":      r.totalLLMConcurrency,
+			"proposal_llm_concurrency":   r.proposalLLMConcurrency,
+			"validation_llm_concurrency": r.validationLLMConcurrency,
+			"credential_env_var":         r.llmAPIKeyEnv,
+			"credential_present":         credentialPresent,
 		},
 	}
 }
@@ -269,14 +303,38 @@ func (r *SubprocessRunner) buildArgs(req PolishRequest, modules []string) []stri
 		req.MergedTranscriptPath,
 		"--glossary", req.GlossaryPath,
 		"--output", req.OutputProcessedPath,
-		"--modules", strings.Join(modules, ","),
-		"--base-url", r.baseURL,
-		"--model", r.model,
 		"--work-dir", req.WorkDir,
 	}
+	if r.baseURL != "" {
+		args = append(args, "--base-url", r.baseURL)
+	}
+	if r.model != "" {
+		args = append(args, "--model", r.model)
+	}
+	if len(modules) > 0 {
+		args = append(args, "--modules", strings.Join(modules, ","))
+	}
 	if r.report {
 		args = append(args, "--report-json", req.ReportPath)
 	}
+	if r.transcriptDescription != "" {
+		args = append(args, "--transcript-description", r.transcriptDescription)
+	}
+	if r.configPath != "" {
+		args = append(args, "--config", r.configPath)
+	}
+	if r.outputSchema != "" {
+		args = append(args, "--output-schema", r.outputSchema)
+	}
+	if r.workDirRetention != "" {
+		args = append(args, "--work-dir-retention", r.workDirRetention)
+	}
+	if r.totalLLMConcurrency != nil {
+		args = append(args, "--total-llm-concurrency", strconv.Itoa(*r.totalLLMConcurrency))
+	}
+	if r.proposalLLMConcurrency != nil {
+		args = append(args, "--proposal-llm-concurrency", strconv.Itoa(*r.proposalLLMConcurrency))
+	}
 	if r.validationModel != "" {
 		args = append(args, "--validation-model", r.validationModel)
 	}
@@ -286,29 +344,31 @@ func (r *SubprocessRunner) buildArgs(req PolishRequest, modules []string) []stri
 	return args
 }
 
-func (r *SubprocessRunner) writeInvocationConfig(req PolishRequest, args []string, modules []string, credentialPresent bool, primaryConcurrencyViaEnv bool) error {
+func (r *SubprocessRunner) writeInvocationConfig(req PolishRequest, args []string, modules []string, credentialPresent bool) error {
 	payload := map[string]any{
-		"schema":                          "audita.generated.v1",
-		"binary":                          r.binary,
-		"args":                            args,
-		"timeout":                         r.timeout.String(),
-		"modules":                         modules,
-		"base_url":                        r.baseURL,
-		"model":                           r.model,
-		"validation_model":                r.validationModel,
-		"validation_llm_concurrency":      r.validationLLMConcurrency,
-		"report_enabled":                  r.report,
-		"merged_transcript_path":          req.MergedTranscriptPath,
-		"glossary_path":                   req.GlossaryPath,
-		"output_path":                     req.OutputProcessedPath,
-		"report_path":                     req.ReportPath,
-		"work_dir":                        req.WorkDir,
-		"credential_env_var":              r.llmAPIKeyEnv,
-		"credential_present":              credentialPresent,
-		"primary_llm_concurrency_via_env": primaryConcurrencyViaEnv,
-	}
-	if r.llmConcurrency != nil {
-		payload["llm_concurrency"] = *r.llmConcurrency
+		"schema":                     "audita.generated.v1",
+		"binary":                     r.binary,
+		"args":                       args,
+		"timeout":                    r.timeout.String(),
+		"modules":                    modules,
+		"base_url":                   r.baseURL,
+		"model":                      r.model,
+		"transcript_description":     r.transcriptDescription,
+		"config_path":                r.configPath,
+		"output_schema":              r.outputSchema,
+		"work_dir_retention":         r.workDirRetention,
+		"validation_model":           r.validationModel,
+		"total_llm_concurrency":      r.totalLLMConcurrency,
+		"proposal_llm_concurrency":   r.proposalLLMConcurrency,
+		"validation_llm_concurrency": r.validationLLMConcurrency,
+		"report_enabled":             r.report,
+		"merged_transcript_path":     req.MergedTranscriptPath,
+		"glossary_path":              req.GlossaryPath,
+		"output_path":                req.OutputProcessedPath,
+		"report_path":                req.ReportPath,
+		"work_dir":                   req.WorkDir,
+		"credential_env_var":         r.llmAPIKeyEnv,
+		"credential_present":         credentialPresent,
 	}
 	return subprocess.WriteYAMLAtomic(req.GeneratedConfigPath, payload, 0o644)
 }

internal/adapters/audita/subprocess_test.go

@@ -25,7 +25,8 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
 
 	wrapper := writeAuditaHelperWrapper(t)
-	llmConcurrency := 1
+	totalLLMConcurrency := 3
+	proposalLLMConcurrency := 2
 	validationLLMConcurrency := 2
 	runner, err := NewSubprocessRunner(SubprocessRunnerConfig{
 		Binary:                   wrapper,
@@ -34,7 +35,12 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
 		Modules:                  []string{"glossary", "homophones", "glossary"},
 		BaseURL:                  "https://openrouter.ai/api/v1",
 		Model:                    "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency:           &llmConcurrency,
+		TranscriptDescription:    "Campaign Session 42",
+		ConfigPath:               "/etc/audita/config.yml",
+		OutputSchema:             "audita-v1",
+		WorkDirRetention:         "auto",
+		TotalLLMConcurrency:      &totalLLMConcurrency,
+		ProposalLLMConcurrency:   &proposalLLMConcurrency,
 		ValidationModel:          "openrouter/google/gemma-4-31b-it",
 		ValidationLLMConcurrency: &validationLLMConcurrency,
 		Report:                   true,
@@ -93,11 +99,17 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
 		"process", req.MergedTranscriptPath,
 		"--glossary", req.GlossaryPath,
 		"--output", req.OutputProcessedPath,
-		"--modules", "glossary,homophones,glossary",
+		"--work-dir", req.WorkDir,
 		"--base-url", "https://openrouter.ai/api/v1",
 		"--model", "openrouter/google/gemma-4-31b-it",
-		"--work-dir", req.WorkDir,
+		"--modules", "glossary,homophones,glossary",
 		"--report-json", req.ReportPath,
+		"--transcript-description", "Campaign Session 42",
+		"--config", "/etc/audita/config.yml",
+		"--output-schema", "audita-v1",
+		"--work-dir-retention", "auto",
+		"--total-llm-concurrency", "3",
+		"--proposal-llm-concurrency", "2",
 		"--validation-model", "openrouter/google/gemma-4-31b-it",
 		"--validation-llm-concurrency", "2",
 	}
@@ -107,8 +119,8 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
 	if rec.Env["AUDITA_LLM_API_KEY"] != "super-secret" {
 		t.Fatalf("AUDITA_LLM_API_KEY = %q, want propagated secret", rec.Env["AUDITA_LLM_API_KEY"])
 	}
-	if rec.Env["AUDITA_LLM_CONCURRENCY"] != "1" {
-		t.Fatalf("AUDITA_LLM_CONCURRENCY = %q, want 1", rec.Env["AUDITA_LLM_CONCURRENCY"])
+	if rec.Env["AUDITA_LLM_CONCURRENCY"] != "" {
+		t.Fatalf("AUDITA_LLM_CONCURRENCY = %q, want empty/omitted", rec.Env["AUDITA_LLM_CONCURRENCY"])
 	}
 
 	cfgData, err := os.ReadFile(req.GeneratedConfigPath)
@@ -124,16 +136,14 @@ func TestSubprocessRunnerMissingConfiguredCredentialFails(t *testing.T) {
 	if runtime.GOOS == "windows" {
 		t.Skip("helper wrapper script uses /bin/sh")
 	}
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "MISSING_AUDITA_KEY",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         false,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "MISSING_AUDITA_KEY",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       false,
 	})
 	req := auditaReqForTest(t, false)
 
@@ -155,16 +165,14 @@ func TestSubprocessRunnerUnconfiguredCredentialEnvOmitsCredential(t *testing.T)
 	recordPath := filepath.Join(t.TempDir(), "record.json")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         false,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       false,
 	})
 	req := auditaReqForTest(t, false)
 
@@ -211,6 +219,65 @@ func TestSubprocessRunnerInheritsParentEnvironment(t *testing.T) {
 	}
 }
 
+func TestSubprocessRunnerOmitsModulesFlagWhenNotConfigured(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("helper wrapper script uses /bin/sh")
+	}
+	t.Setenv("GO_WANT_AUDITA_HELPER", "1")
+	t.Setenv("AUDITA_HELPER_MODE", "success")
+	recordPath := filepath.Join(t.TempDir(), "record.json")
+	t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
+
+	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "",
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       false,
+	})
+	req := auditaReqForTest(t, false)
+	if _, err := runner.Run(context.Background(), req); err != nil {
+		t.Fatalf("Run() error = %v", err)
+	}
+	rec := readAuditaHelperRecord(t, recordPath)
+	for i := 0; i < len(rec.Args); i++ {
+		if rec.Args[i] == "--modules" {
+			t.Fatalf("args contained --modules unexpectedly: %#v", rec.Args)
+		}
+	}
+}
+
+func TestSubprocessRunnerOmitsBaseURLAndModelFlagsWhenNotConfigured(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("helper wrapper script uses /bin/sh")
+	}
+	t.Setenv("GO_WANT_AUDITA_HELPER", "1")
+	t.Setenv("AUDITA_HELPER_MODE", "success")
+	recordPath := filepath.Join(t.TempDir(), "record.json")
+	t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
+
+	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "",
+		Report:       false,
+	})
+	req := auditaReqForTest(t, false)
+	if _, err := runner.Run(context.Background(), req); err != nil {
+		t.Fatalf("Run() error = %v", err)
+	}
+	rec := readAuditaHelperRecord(t, recordPath)
+	for i := 0; i < len(rec.Args); i++ {
+		if rec.Args[i] == "--base-url" {
+			t.Fatalf("args contained --base-url unexpectedly: %#v", rec.Args)
+		}
+		if rec.Args[i] == "--model" {
+			t.Fatalf("args contained --model unexpectedly: %#v", rec.Args)
+		}
+	}
+}
+
 func TestSubprocessRunnerSubprocessFailure(t *testing.T) {
 	if runtime.GOOS == "windows" {
 		t.Skip("helper wrapper script uses /bin/sh")
@@ -220,16 +287,14 @@ func TestSubprocessRunnerSubprocessFailure(t *testing.T) {
 	t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "OPENAI_KEY_SOURCE",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         true,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       true,
 	})
 	req := auditaReqForTest(t, true)
 	_, err := runner.Run(context.Background(), req)
@@ -256,16 +321,14 @@ func TestSubprocessRunnerSubprocessFailureAddsStderrDescriptorHint(t *testing.T)
 	t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "OPENAI_KEY_SOURCE",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         true,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       true,
 	})
 	req := auditaReqForTest(t, true)
 	_, err := runner.Run(context.Background(), req)
@@ -286,16 +349,14 @@ func TestSubprocessRunnerMissingOutputFails(t *testing.T) {
 	t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "OPENAI_KEY_SOURCE",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         false,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       false,
 	})
 	req := auditaReqForTest(t, false)
 	_, err := runner.Run(context.Background(), req)
@@ -316,16 +377,14 @@ func TestSubprocessRunnerInvalidOutputJSONFails(t *testing.T) {
 	t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "OPENAI_KEY_SOURCE",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         false,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       false,
 	})
 	req := auditaReqForTest(t, false)
 	_, err := runner.Run(context.Background(), req)
@@ -346,16 +405,14 @@ func TestSubprocessRunnerSegmentsMissingFails(t *testing.T) {
 	t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "OPENAI_KEY_SOURCE",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         false,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       false,
 	})
 	req := auditaReqForTest(t, false)
 	_, err := runner.Run(context.Background(), req)
@@ -376,16 +433,14 @@ func TestSubprocessRunnerInvalidReportJSONFails(t *testing.T) {
 	t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
 	t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
 
-	llmConcurrency := 1
 	runner := mustAuditaRunner(t, SubprocessRunnerConfig{
-		Binary:         writeAuditaHelperWrapper(t),
-		Timeout:        mustParseAuditaDuration(t, "2s"),
-		LLMAPIKeyEnv:   "OPENAI_KEY_SOURCE",
-		Modules:        []string{"glossary"},
-		BaseURL:        "https://openrouter.ai/api/v1",
-		Model:          "openrouter/google/gemma-4-31b-it",
-		LLMConcurrency: &llmConcurrency,
-		Report:         true,
+		Binary:       writeAuditaHelperWrapper(t),
+		Timeout:      mustParseAuditaDuration(t, "2s"),
+		LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
+		Modules:      []string{"glossary"},
+		BaseURL:      "https://openrouter.ai/api/v1",
+		Model:        "openrouter/google/gemma-4-31b-it",
+		Report:       true,
 	})
 	req := auditaReqForTest(t, true)
 	_, err := runner.Run(context.Background(), req)
@@ -398,11 +453,11 @@ func TestSubprocessRunnerInvalidReportJSONFails(t *testing.T) {
 }
 
 func TestSubprocessRunnerConstructorValidation(t *testing.T) {
-	_, err := NewSubprocessRunnerFromConfigValues("", "3h", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", nil, "", nil, true)
+	_, err := NewSubprocessRunnerFromConfigValues("", "3h", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", "", "", "", "", nil, nil, "", nil, true)
 	if err == nil {
 		t.Fatal("expected binary validation error")
 	}
-	_, err = NewSubprocessRunnerFromConfigValues("audita", "bad", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", nil, "", nil, true)
+	_, err = NewSubprocessRunnerFromConfigValues("audita", "bad", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", "", "", "", "", nil, nil, "", nil, true)
 	if err == nil {
 		t.Fatal("expected timeout parse error")
 	}

internal/adapters/storage/factory.go

@@ -0,0 +1,29 @@
+package storage
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+// NewObjectStoreFromConfig constructs a remote object store from resolved config.
+func NewObjectStoreFromConfig(ctx context.Context, cfg *config.Config) (ObjectStore, error) {
+	if cfg == nil || cfg.Pipeline == nil {
+		return nil, fmt.Errorf("pipeline config is required")
+	}
+
+	if strings.EqualFold(strings.TrimSpace(cfg.Pipeline.Storage.Backend), "s3") {
+		if cfg.Pipeline.Storage.S3 == nil {
+			return nil, fmt.Errorf("pipeline.storage.s3 is required when pipeline.storage.backend is s3")
+		}
+		return NewS3BackendFromConfig(ctx, *cfg.Pipeline.Storage.S3)
+	}
+
+	if cfg.Pipeline.Storage.S3 != nil && strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket) != "" {
+		return NewS3BackendFromConfig(ctx, *cfg.Pipeline.Storage.S3)
+	}
+
+	return nil, fmt.Errorf("no remote object store backend is configured")
+}

internal/adapters/storage/factory_test.go

@@ -0,0 +1,56 @@
+package storage
+
+import (
+	"context"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+func TestNewObjectStoreFromConfigBuildsS3WhenBackendIsS3(t *testing.T) {
+	original := newS3Client
+	t.Cleanup(func() { newS3Client = original })
+	newS3Client = func(_ context.Context, _ s3ClientOptions) (s3API, error) {
+		return &fakeS3API{}, nil
+	}
+
+	store, err := NewObjectStoreFromConfig(context.Background(), &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Storage: config.StorageConfig{
+				Backend: "s3",
+				S3: &config.StorageS3Config{
+					Bucket: "my-archive",
+				},
+			},
+		},
+	})
+	if err != nil {
+		t.Fatalf("NewObjectStoreFromConfig() error = %v", err)
+	}
+	if _, ok := store.(*S3Backend); !ok {
+		t.Fatalf("store type = %T, want *S3Backend", store)
+	}
+}
+
+func TestNewObjectStoreFromConfigRequiresS3ConfigWhenBackendIsS3(t *testing.T) {
+	_, err := NewObjectStoreFromConfig(context.Background(), &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Storage: config.StorageConfig{Backend: "s3"},
+		},
+	})
+	if err == nil || !strings.Contains(err.Error(), "pipeline.storage.s3 is required") {
+		t.Fatalf("NewObjectStoreFromConfig() error = %v, want missing storage.s3 error", err)
+	}
+}
+
+func TestNewObjectStoreFromConfigNoRemoteBackendConfigured(t *testing.T) {
+	_, err := NewObjectStoreFromConfig(context.Background(), &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Storage: config.StorageConfig{Backend: "local"},
+		},
+	})
+	if err == nil || !strings.Contains(err.Error(), "no remote object store backend is configured") {
+		t.Fatalf("NewObjectStoreFromConfig() error = %v, want no-backend error", err)
+	}
+}

internal/adapters/storage/fake.go

@@ -1,6 +1,14 @@
 package storage
 
-import "context"
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+	"time"
+)
 
 // NoopBackend is a deterministic no-op archive/storage adapter.
 type NoopBackend struct{}
@@ -18,6 +26,21 @@ type FakeBackend struct {
 	Requests []ArchiveRequest
 	Err      error
 	Result   ArchiveResult
+
+	Objects map[string]FakeObject
+	Uploads []FakeUploadCall
+
+	ListErr     error
+	DownloadErr error
+	UploadErr   error
+	ExistsErr   error
+}
+
+// FakeUploadCall captures one upload invocation in call order.
+type FakeUploadCall struct {
+	LocalPath string
+	Key       string
+	Options   UploadOptions
 }
 
 // Archive records request and returns configured response.
@@ -38,3 +61,148 @@ func (f *FakeBackend) Archive(ctx context.Context, req ArchiveRequest) (ArchiveR
 	}
 	return res, nil
 }
+
+// FakeObject is a deterministic fake object-store record.
+type FakeObject struct {
+	Key          string
+	Data         []byte
+	Metadata     map[string]string
+	ETag         string
+	LastModified *time.Time
+}
+
+// SeedObject inserts or replaces an object in the fake object store.
+func (f *FakeBackend) SeedObject(obj FakeObject) {
+	if f.Objects == nil {
+		f.Objects = map[string]FakeObject{}
+	}
+	key := normalizeObjectKey(obj.Key)
+	obj.Key = key
+	obj.Data = append([]byte(nil), obj.Data...)
+	obj.Metadata = copyMetadata(obj.Metadata)
+	f.Objects[key] = obj
+}
+
+// List returns deterministic prefix-filtered objects.
+func (f *FakeBackend) List(ctx context.Context, prefix string) ([]ObjectInfo, error) {
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+	if f.ListErr != nil {
+		return nil, f.ListErr
+	}
+
+	normalizedPrefix := normalizeObjectKey(prefix)
+	keys := make([]string, 0, len(f.Objects))
+	for key := range f.Objects {
+		if strings.HasPrefix(key, normalizedPrefix) {
+			keys = append(keys, key)
+		}
+	}
+	sort.Strings(keys)
+
+	out := make([]ObjectInfo, 0, len(keys))
+	for _, key := range keys {
+		obj := f.Objects[key]
+		out = append(out, ObjectInfo{
+			Key:          obj.Key,
+			Size:         int64(len(obj.Data)),
+			ETag:         obj.ETag,
+			LastModified: obj.LastModified,
+		})
+	}
+	return out, nil
+}
+
+// Download writes one object to a local path.
+func (f *FakeBackend) Download(ctx context.Context, key, localPath string) error {
+	if err := ctx.Err(); err != nil {
+		return err
+	}
+	if f.DownloadErr != nil {
+		return f.DownloadErr
+	}
+	if strings.TrimSpace(localPath) == "" {
+		return fmt.Errorf("download object: local path is required")
+	}
+
+	obj, ok := f.Objects[normalizeObjectKey(key)]
+	if !ok {
+		return fmt.Errorf("download object %q: %w", key, os.ErrNotExist)
+	}
+
+	if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
+		return fmt.Errorf("download object %q: create parent directory: %w", key, err)
+	}
+	if err := os.WriteFile(localPath, obj.Data, 0o644); err != nil {
+		return fmt.Errorf("download object %q: write local file: %w", key, err)
+	}
+	return nil
+}
+
+// Upload reads a local file and stores it under key.
+func (f *FakeBackend) Upload(ctx context.Context, localPath, key string, opts UploadOptions) (ObjectInfo, error) {
+	if err := ctx.Err(); err != nil {
+		return ObjectInfo{}, err
+	}
+	if f.UploadErr != nil {
+		return ObjectInfo{}, f.UploadErr
+	}
+	if strings.TrimSpace(localPath) == "" {
+		return ObjectInfo{}, fmt.Errorf("upload object: local path is required")
+	}
+	if strings.TrimSpace(key) == "" {
+		return ObjectInfo{}, fmt.Errorf("upload object: key is required")
+	}
+
+	data, err := os.ReadFile(localPath)
+	if err != nil {
+		return ObjectInfo{}, fmt.Errorf("upload object %q from %q: %w", key, localPath, err)
+	}
+
+	normalizedKey := normalizeObjectKey(key)
+	f.Uploads = append(f.Uploads, FakeUploadCall{
+		LocalPath: localPath,
+		Key:       normalizedKey,
+		Options: UploadOptions{
+			Metadata:    copyMetadata(opts.Metadata),
+			ContentType: opts.ContentType,
+		},
+	})
+	now := time.Now().UTC()
+	obj := FakeObject{
+		Key:          normalizedKey,
+		Data:         data,
+		Metadata:     copyMetadata(opts.Metadata),
+		LastModified: &now,
+	}
+	f.SeedObject(obj)
+	return ObjectInfo{
+		Key:          normalizedKey,
+		Size:         int64(len(data)),
+		LastModified: &now,
+	}, nil
+}
+
+// Exists checks object presence.
+func (f *FakeBackend) Exists(ctx context.Context, key string) (bool, error) {
+	if err := ctx.Err(); err != nil {
+		return false, err
+	}
+	if f.ExistsErr != nil {
+		return false, f.ExistsErr
+	}
+	_, ok := f.Objects[normalizeObjectKey(key)]
+	return ok, nil
+}
+
+func copyMetadata(in map[string]string) map[string]string {
+	if len(in) == 0 {
+		return nil
+	}
+	out := make(map[string]string, len(in))
+	for k, v := range in {
+		out[k] = v
+	}
+	return out
+}

internal/adapters/storage/fake_test.go

@@ -3,6 +3,9 @@ package storage
 import (
 	"context"
 	"errors"
+	"os"
+	"path/filepath"
+	"strings"
 	"testing"
 )
 
@@ -29,3 +32,84 @@ func TestFakeBackendError(t *testing.T) {
 		t.Fatal("expected error, got nil")
 	}
 }
+
+func TestFakeBackendListPrefixFiltering(t *testing.T) {
+	fake := &FakeBackend{}
+	fake.SeedObject(FakeObject{Key: "dnd/campaigns/forsaken/audio/a.flac", Data: []byte("a")})
+	fake.SeedObject(FakeObject{Key: "dnd/campaigns/forsaken/audio/b.flac", Data: []byte("b")})
+	fake.SeedObject(FakeObject{Key: "dnd/campaigns/other/audio/c.flac", Data: []byte("c")})
+
+	items, err := fake.List(context.Background(), "dnd/campaigns/forsaken/audio/")
+	if err != nil {
+		t.Fatalf("List() error = %v", err)
+	}
+	if len(items) != 2 {
+		t.Fatalf("List() len = %d, want 2", len(items))
+	}
+	if items[0].Key != "dnd/campaigns/forsaken/audio/a.flac" || items[1].Key != "dnd/campaigns/forsaken/audio/b.flac" {
+		t.Fatalf("List() keys = %#v", items)
+	}
+}
+
+func TestFakeBackendDownload(t *testing.T) {
+	fake := &FakeBackend{}
+	fake.SeedObject(FakeObject{Key: "audio/a.flac", Data: []byte("audio-a")})
+
+	dst := filepath.Join(t.TempDir(), "nested", "a.flac")
+	if err := fake.Download(context.Background(), "audio/a.flac", dst); err != nil {
+		t.Fatalf("Download() error = %v", err)
+	}
+	data, err := os.ReadFile(dst)
+	if err != nil {
+		t.Fatalf("ReadFile() error = %v", err)
+	}
+	if string(data) != "audio-a" {
+		t.Fatalf("downloaded content = %q, want %q", string(data), "audio-a")
+	}
+}
+
+func TestFakeBackendUploadAndExists(t *testing.T) {
+	fake := &FakeBackend{}
+
+	local := filepath.Join(t.TempDir(), "upload.txt")
+	if err := os.WriteFile(local, []byte("payload"), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	info, err := fake.Upload(context.Background(), local, `runs\id\artifact.txt`, UploadOptions{
+		Metadata: map[string]string{"kind": "artifact"},
+	})
+	if err != nil {
+		t.Fatalf("Upload() error = %v", err)
+	}
+	if info.Key != "runs/id/artifact.txt" {
+		t.Fatalf("Upload() key = %q, want normalized key", info.Key)
+	}
+
+	ok, err := fake.Exists(context.Background(), "runs/id/artifact.txt")
+	if err != nil {
+		t.Fatalf("Exists() error = %v", err)
+	}
+	if !ok {
+		t.Fatal("Exists() = false, want true")
+	}
+}
+
+func TestFakeBackendObjectErrors(t *testing.T) {
+	fake := &FakeBackend{DownloadErr: errors.New("download fail"), UploadErr: errors.New("upload fail"), ListErr: errors.New("list fail"), ExistsErr: errors.New("exists fail")}
+
+	if _, err := fake.List(context.Background(), "x"); err == nil || !strings.Contains(err.Error(), "list fail") {
+		t.Fatalf("List() error = %v, want list fail", err)
+	}
+	if err := fake.Download(context.Background(), "x", filepath.Join(t.TempDir(), "x")); err == nil || !strings.Contains(err.Error(), "download fail") {
+		t.Fatalf("Download() error = %v, want download fail", err)
+	}
+	local := filepath.Join(t.TempDir(), "x.txt")
+	_ = os.WriteFile(local, []byte("x"), 0o644)
+	if _, err := fake.Upload(context.Background(), local, "x", UploadOptions{}); err == nil || !strings.Contains(err.Error(), "upload fail") {
+		t.Fatalf("Upload() error = %v, want upload fail", err)
+	}
+	if _, err := fake.Exists(context.Background(), "x"); err == nil || !strings.Contains(err.Error(), "exists fail") {
+		t.Fatalf("Exists() error = %v, want exists fail", err)
+	}
+}

internal/adapters/storage/keys.go

@@ -0,0 +1,8 @@
+package storage
+
+import "strings"
+
+func normalizeObjectKey(key string) string {
+	normalized := strings.ReplaceAll(strings.TrimSpace(key), "\\", "/")
+	return strings.TrimLeft(normalized, "/")
+}

internal/adapters/storage/keys_test.go

@@ -0,0 +1,21 @@
+package storage
+
+import "testing"
+
+func TestNormalizeObjectKey(t *testing.T) {
+	tests := []struct {
+		in   string
+		want string
+	}{
+		{in: `dnd\campaigns\forsaken\a.flac`, want: "dnd/campaigns/forsaken/a.flac"},
+		{in: " /dnd/campaigns/forsaken/a.flac ", want: "dnd/campaigns/forsaken/a.flac"},
+		{in: "//dnd/campaigns/forsaken/a.flac", want: "dnd/campaigns/forsaken/a.flac"},
+		{in: "", want: ""},
+	}
+
+	for _, tt := range tests {
+		if got := normalizeObjectKey(tt.in); got != tt.want {
+			t.Fatalf("normalizeObjectKey(%q) = %q, want %q", tt.in, got, tt.want)
+		}
+	}
+}

internal/adapters/storage/object_store.go

@@ -0,0 +1,32 @@
+package storage
+
+import (
+	"context"
+	"time"
+)
+
+// ObjectStore is a remote object storage boundary used by future prepare/archive work.
+//
+// Key invariant:
+// callers pass full bucket-relative object keys. Backend implementations do not
+// infer Narratio session semantics and do not prepend root prefixes.
+type ObjectStore interface {
+	List(ctx context.Context, prefix string) ([]ObjectInfo, error)
+	Download(ctx context.Context, key, localPath string) error
+	Upload(ctx context.Context, localPath, key string, opts UploadOptions) (ObjectInfo, error)
+	Exists(ctx context.Context, key string) (bool, error)
+}
+
+// ObjectInfo describes one object in remote storage.
+type ObjectInfo struct {
+	Key          string
+	Size         int64
+	ETag         string
+	LastModified *time.Time
+}
+
+// UploadOptions configures optional object upload metadata.
+type UploadOptions struct {
+	Metadata    map[string]string
+	ContentType string
+}

internal/adapters/storage/s3_backend.go

@@ -0,0 +1,275 @@
+package storage
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	awsconfig "github.com/aws/aws-sdk-go-v2/config"
+	"github.com/aws/aws-sdk-go-v2/credentials"
+	"github.com/aws/aws-sdk-go-v2/service/s3"
+	"github.com/aws/aws-sdk-go-v2/service/s3/types"
+	"github.com/aws/smithy-go"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+type s3API interface {
+	ListObjectsV2(ctx context.Context, params *s3.ListObjectsV2Input, optFns ...func(*s3.Options)) (*s3.ListObjectsV2Output, error)
+	GetObject(ctx context.Context, params *s3.GetObjectInput, optFns ...func(*s3.Options)) (*s3.GetObjectOutput, error)
+	PutObject(ctx context.Context, params *s3.PutObjectInput, optFns ...func(*s3.Options)) (*s3.PutObjectOutput, error)
+	HeadObject(ctx context.Context, params *s3.HeadObjectInput, optFns ...func(*s3.Options)) (*s3.HeadObjectOutput, error)
+}
+
+// S3Backend is an ObjectStore implementation backed by S3-compatible APIs.
+type S3Backend struct {
+	bucket string
+	client s3API
+}
+
+type s3ClientOptions struct {
+	Region         string
+	Endpoint       string
+	ForcePathStyle bool
+	AccessKeyID    string
+	SecretKey      string
+}
+
+var newS3Client = func(ctx context.Context, opts s3ClientOptions) (s3API, error) {
+	loadOpts := make([]func(*awsconfig.LoadOptions) error, 0, 1)
+	if strings.TrimSpace(opts.Region) != "" {
+		loadOpts = append(loadOpts, awsconfig.WithRegion(strings.TrimSpace(opts.Region)))
+	}
+	if strings.TrimSpace(opts.AccessKeyID) != "" && strings.TrimSpace(opts.SecretKey) != "" {
+		loadOpts = append(loadOpts, awsconfig.WithCredentialsProvider(
+			credentials.NewStaticCredentialsProvider(
+				strings.TrimSpace(opts.AccessKeyID),
+				strings.TrimSpace(opts.SecretKey),
+				"",
+			),
+		))
+	}
+	awsCfg, err := awsconfig.LoadDefaultConfig(ctx, loadOpts...)
+	if err != nil {
+		return nil, fmt.Errorf("load aws config: %w", err)
+	}
+
+	return s3.NewFromConfig(awsCfg, func(o *s3.Options) {
+		if strings.TrimSpace(opts.Endpoint) != "" {
+			endpoint := strings.TrimSpace(opts.Endpoint)
+			o.BaseEndpoint = &endpoint
+		}
+		o.UsePathStyle = opts.ForcePathStyle
+	}), nil
+}
+
+// NewS3BackendFromConfig builds an S3 backend from resolved config.
+func NewS3BackendFromConfig(ctx context.Context, cfg config.StorageS3Config) (*S3Backend, error) {
+	bucket := strings.TrimSpace(cfg.Bucket)
+	if bucket == "" {
+		return nil, fmt.Errorf("storage.s3.bucket is required")
+	}
+
+	client, err := newS3Client(ctx, s3ClientOptions{
+		Region:         cfg.Region,
+		Endpoint:       cfg.Endpoint,
+		ForcePathStyle: cfg.ForcePathStyle,
+		AccessKeyID:    s3CredentialFromEnv(orDefaultEnvName(cfg.AccessKeyIDEnv, config.DefaultS3AccessKeyIDEnv)),
+		SecretKey:      s3CredentialFromEnv(orDefaultEnvName(cfg.SecretKeyEnv, config.DefaultS3SecretAccessKeyEnv)),
+	})
+	if err != nil {
+		return nil, fmt.Errorf("build s3 client: %w", err)
+	}
+
+	return &S3Backend{
+		bucket: bucket,
+		client: client,
+	}, nil
+}
+
+func s3CredentialFromEnv(envVarName string) string {
+	name := strings.TrimSpace(envVarName)
+	if name == "" {
+		return ""
+	}
+	value, ok := os.LookupEnv(name)
+	if !ok {
+		return ""
+	}
+	return strings.TrimSpace(value)
+}
+
+func orDefaultEnvName(name, fallback string) string {
+	trimmed := strings.TrimSpace(name)
+	if trimmed == "" {
+		return fallback
+	}
+	return trimmed
+}
+
+// List returns objects under prefix.
+func (b *S3Backend) List(ctx context.Context, prefix string) ([]ObjectInfo, error) {
+	normalizedPrefix := normalizeObjectKey(prefix)
+	out := make([]ObjectInfo, 0)
+	var token *string
+
+	for {
+		resp, err := b.client.ListObjectsV2(ctx, &s3.ListObjectsV2Input{
+			Bucket:            &b.bucket,
+			Prefix:            &normalizedPrefix,
+			ContinuationToken: token,
+		})
+		if err != nil {
+			return nil, fmt.Errorf("list objects under %q: %w", normalizedPrefix, err)
+		}
+
+		for _, item := range resp.Contents {
+			var lastModified *time.Time
+			if item.LastModified != nil {
+				t := *item.LastModified
+				lastModified = &t
+			}
+			out = append(out, ObjectInfo{
+				Key:          normalizeObjectKey(valueOrEmpty(item.Key)),
+				Size:         valueOrZeroInt64(item.Size),
+				ETag:         strings.Trim(valueOrEmpty(item.ETag), "\""),
+				LastModified: lastModified,
+			})
+		}
+
+		if !valueOrFalseBool(resp.IsTruncated) || resp.NextContinuationToken == nil {
+			break
+		}
+		token = resp.NextContinuationToken
+	}
+	return out, nil
+}
+
+// Download retrieves one object to localPath, creating parent directories as needed.
+func (b *S3Backend) Download(ctx context.Context, key, localPath string) error {
+	normalizedKey := normalizeObjectKey(key)
+	if strings.TrimSpace(localPath) == "" {
+		return fmt.Errorf("download object: local path is required")
+	}
+
+	resp, err := b.client.GetObject(ctx, &s3.GetObjectInput{
+		Bucket: &b.bucket,
+		Key:    &normalizedKey,
+	})
+	if err != nil {
+		return fmt.Errorf("download object %q: %w", normalizedKey, err)
+	}
+	defer resp.Body.Close()
+
+	if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
+		return fmt.Errorf("download object %q: create parent directory: %w", normalizedKey, err)
+	}
+	dst, err := os.Create(localPath)
+	if err != nil {
+		return fmt.Errorf("download object %q: create local file: %w", normalizedKey, err)
+	}
+	defer dst.Close()
+
+	if _, err := io.Copy(dst, resp.Body); err != nil {
+		return fmt.Errorf("download object %q: copy body: %w", normalizedKey, err)
+	}
+	if err := dst.Sync(); err != nil {
+		return fmt.Errorf("download object %q: sync local file: %w", normalizedKey, err)
+	}
+	return nil
+}
+
+// Upload sends a local file to key.
+func (b *S3Backend) Upload(ctx context.Context, localPath, key string, opts UploadOptions) (ObjectInfo, error) {
+	normalizedKey := normalizeObjectKey(key)
+	if strings.TrimSpace(localPath) == "" {
+		return ObjectInfo{}, fmt.Errorf("upload object: local path is required")
+	}
+	if normalizedKey == "" {
+		return ObjectInfo{}, fmt.Errorf("upload object: key is required")
+	}
+
+	file, err := os.Open(localPath)
+	if err != nil {
+		return ObjectInfo{}, fmt.Errorf("upload object %q from %q: %w", normalizedKey, localPath, err)
+	}
+	defer file.Close()
+
+	stat, err := file.Stat()
+	if err != nil {
+		return ObjectInfo{}, fmt.Errorf("upload object %q from %q: stat local file: %w", normalizedKey, localPath, err)
+	}
+
+	input := &s3.PutObjectInput{
+		Bucket:   &b.bucket,
+		Key:      &normalizedKey,
+		Body:     file,
+		Metadata: copyMetadata(opts.Metadata),
+	}
+	if strings.TrimSpace(opts.ContentType) != "" {
+		ct := strings.TrimSpace(opts.ContentType)
+		input.ContentType = &ct
+	}
+
+	resp, err := b.client.PutObject(ctx, input)
+	if err != nil {
+		return ObjectInfo{}, fmt.Errorf("upload object %q from %q: %w", normalizedKey, localPath, err)
+	}
+
+	return ObjectInfo{
+		Key:  normalizedKey,
+		Size: stat.Size(),
+		ETag: strings.Trim(valueOrEmpty(resp.ETag), "\""),
+	}, nil
+}
+
+// Exists checks whether one object key exists.
+func (b *S3Backend) Exists(ctx context.Context, key string) (bool, error) {
+	normalizedKey := normalizeObjectKey(key)
+	_, err := b.client.HeadObject(ctx, &s3.HeadObjectInput{
+		Bucket: &b.bucket,
+		Key:    &normalizedKey,
+	})
+	if err == nil {
+		return true, nil
+	}
+
+	var notFound *types.NotFound
+	if errors.As(err, &notFound) {
+		return false, nil
+	}
+	var apiErr smithy.APIError
+	if errors.As(err, &apiErr) {
+		switch apiErr.ErrorCode() {
+		case "NotFound", "NoSuchKey", "404":
+			return false, nil
+		}
+	}
+	return false, fmt.Errorf("head object %q: %w", normalizedKey, err)
+}
+
+func valueOrEmpty(v *string) string {
+	if v == nil {
+		return ""
+	}
+	return *v
+}
+
+func valueOrZeroInt64(v *int64) int64 {
+	if v == nil {
+		return 0
+	}
+	return *v
+}
+
+func valueOrFalseBool(v *bool) bool {
+	if v == nil {
+		return false
+	}
+	return *v
+}

internal/adapters/storage/s3_backend_test.go

@@ -0,0 +1,253 @@
+package storage
+
+import (
+	"context"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/aws/aws-sdk-go-v2/service/s3"
+	"github.com/aws/aws-sdk-go-v2/service/s3/types"
+	"github.com/aws/smithy-go"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+type fakeS3API struct {
+	listOut *s3.ListObjectsV2Output
+	listErr error
+
+	getBody io.ReadCloser
+	getErr  error
+
+	putOut *s3.PutObjectOutput
+	putErr error
+
+	headErr error
+
+	lastList *s3.ListObjectsV2Input
+	lastGet  *s3.GetObjectInput
+	lastPut  *s3.PutObjectInput
+	lastHead *s3.HeadObjectInput
+}
+
+func (f *fakeS3API) ListObjectsV2(_ context.Context, params *s3.ListObjectsV2Input, _ ...func(*s3.Options)) (*s3.ListObjectsV2Output, error) {
+	f.lastList = params
+	if f.listErr != nil {
+		return nil, f.listErr
+	}
+	if f.listOut == nil {
+		return &s3.ListObjectsV2Output{}, nil
+	}
+	return f.listOut, nil
+}
+
+func (f *fakeS3API) GetObject(_ context.Context, params *s3.GetObjectInput, _ ...func(*s3.Options)) (*s3.GetObjectOutput, error) {
+	f.lastGet = params
+	if f.getErr != nil {
+		return nil, f.getErr
+	}
+	body := f.getBody
+	if body == nil {
+		body = io.NopCloser(strings.NewReader(""))
+	}
+	return &s3.GetObjectOutput{Body: body}, nil
+}
+
+func (f *fakeS3API) PutObject(_ context.Context, params *s3.PutObjectInput, _ ...func(*s3.Options)) (*s3.PutObjectOutput, error) {
+	f.lastPut = params
+	if f.putErr != nil {
+		return nil, f.putErr
+	}
+	if f.putOut == nil {
+		return &s3.PutObjectOutput{}, nil
+	}
+	return f.putOut, nil
+}
+
+func (f *fakeS3API) HeadObject(_ context.Context, params *s3.HeadObjectInput, _ ...func(*s3.Options)) (*s3.HeadObjectOutput, error) {
+	f.lastHead = params
+	if f.headErr != nil {
+		return nil, f.headErr
+	}
+	return &s3.HeadObjectOutput{}, nil
+}
+
+func TestS3BackendListAndKeyNormalization(t *testing.T) {
+	lastModified := time.Date(2026, 5, 16, 12, 0, 0, 0, time.UTC)
+	client := &fakeS3API{
+		listOut: &s3.ListObjectsV2Output{
+			Contents: []types.Object{
+				{Key: strPtr(`dnd\campaigns\forsaken\a.flac`), Size: int64Ptr(7), ETag: strPtr(`"abc"`), LastModified: &lastModified},
+			},
+		},
+	}
+	backend := &S3Backend{bucket: "bucket-1", client: client}
+
+	items, err := backend.List(context.Background(), `dnd\campaigns\`)
+	if err != nil {
+		t.Fatalf("List() error = %v", err)
+	}
+	if len(items) != 1 {
+		t.Fatalf("List() len = %d, want 1", len(items))
+	}
+	if items[0].Key != "dnd/campaigns/forsaken/a.flac" {
+		t.Fatalf("List() key = %q, want normalized slash key", items[0].Key)
+	}
+	if items[0].ETag != "abc" {
+		t.Fatalf("List() ETag = %q, want %q", items[0].ETag, "abc")
+	}
+	if client.lastList == nil || *client.lastList.Prefix != "dnd/campaigns/" {
+		t.Fatalf("List() prefix = %#v, want normalized prefix", client.lastList)
+	}
+}
+
+func TestS3BackendDownloadCreatesParentDirectory(t *testing.T) {
+	client := &fakeS3API{getBody: io.NopCloser(strings.NewReader("audio"))}
+	backend := &S3Backend{bucket: "bucket-1", client: client}
+
+	dst := filepath.Join(t.TempDir(), "nested", "clip.flac")
+	if err := backend.Download(context.Background(), `audio\clip.flac`, dst); err != nil {
+		t.Fatalf("Download() error = %v", err)
+	}
+
+	data, err := os.ReadFile(dst)
+	if err != nil {
+		t.Fatalf("ReadFile() error = %v", err)
+	}
+	if string(data) != "audio" {
+		t.Fatalf("downloaded content = %q, want %q", string(data), "audio")
+	}
+	if client.lastGet == nil || *client.lastGet.Key != "audio/clip.flac" {
+		t.Fatalf("GetObject key = %#v, want normalized key", client.lastGet)
+	}
+}
+
+func TestS3BackendUploadAndExists(t *testing.T) {
+	client := &fakeS3API{putOut: &s3.PutObjectOutput{ETag: strPtr(`"etag123"`)}}
+	backend := &S3Backend{bucket: "bucket-1", client: client}
+
+	local := filepath.Join(t.TempDir(), "artifact.txt")
+	if err := os.WriteFile(local, []byte("artifact"), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	info, err := backend.Upload(context.Background(), local, `runs\id\artifact.txt`, UploadOptions{
+		Metadata: map[string]string{"kind": "artifact"},
+	})
+	if err != nil {
+		t.Fatalf("Upload() error = %v", err)
+	}
+	if info.Key != "runs/id/artifact.txt" {
+		t.Fatalf("Upload key = %q, want normalized key", info.Key)
+	}
+	if info.ETag != "etag123" {
+		t.Fatalf("Upload ETag = %q, want %q", info.ETag, "etag123")
+	}
+	if client.lastPut == nil || *client.lastPut.Key != "runs/id/artifact.txt" {
+		t.Fatalf("PutObject key = %#v, want normalized key", client.lastPut)
+	}
+
+	ok, err := backend.Exists(context.Background(), "runs/id/artifact.txt")
+	if err != nil {
+		t.Fatalf("Exists() error = %v", err)
+	}
+	if !ok {
+		t.Fatal("Exists() = false, want true")
+	}
+}
+
+func TestS3BackendUploadMissingLocalFile(t *testing.T) {
+	backend := &S3Backend{bucket: "bucket-1", client: &fakeS3API{}}
+	_, err := backend.Upload(context.Background(), filepath.Join(t.TempDir(), "missing.txt"), "key.txt", UploadOptions{})
+	if err == nil || !strings.Contains(err.Error(), "no such file") {
+		t.Fatalf("Upload() error = %v, want missing local file error", err)
+	}
+}
+
+func TestS3BackendExistsNotFound(t *testing.T) {
+	backend := &S3Backend{
+		bucket: "bucket-1",
+		client: &fakeS3API{
+			headErr: &smithy.GenericAPIError{Code: "NotFound", Message: "missing"},
+		},
+	}
+	ok, err := backend.Exists(context.Background(), "missing-key")
+	if err != nil {
+		t.Fatalf("Exists() error = %v", err)
+	}
+	if ok {
+		t.Fatal("Exists() = true, want false")
+	}
+}
+
+func TestNewS3BackendFromConfigUsesClientOptions(t *testing.T) {
+	original := newS3Client
+	t.Cleanup(func() { newS3Client = original })
+	t.Setenv("OBJECT_STORAGE_KEY_ID", "id-123")
+	t.Setenv("OBJECT_STORAGE_KEY", "secret-abc")
+
+	var got s3ClientOptions
+	newS3Client = func(_ context.Context, opts s3ClientOptions) (s3API, error) {
+		got = opts
+		return &fakeS3API{}, nil
+	}
+
+	backend, err := NewS3BackendFromConfig(context.Background(), config.StorageS3Config{
+		Bucket:         "my-archive",
+		Region:         "us-east-1",
+		Endpoint:       "http://localhost:9000",
+		ForcePathStyle: true,
+	})
+	if err != nil {
+		t.Fatalf("NewS3BackendFromConfig() error = %v", err)
+	}
+	if backend.bucket != "my-archive" {
+		t.Fatalf("backend.bucket = %q, want %q", backend.bucket, "my-archive")
+	}
+	if got.Region != "us-east-1" || got.Endpoint != "http://localhost:9000" || !got.ForcePathStyle {
+		t.Fatalf("client options = %#v, want region/endpoint/path-style values", got)
+	}
+	if got.AccessKeyID != "id-123" || got.SecretKey != "secret-abc" {
+		t.Fatalf("client options credentials = %#v, want env-resolved static credentials", got)
+	}
+}
+
+func TestNewS3BackendFromConfigRequiresBucket(t *testing.T) {
+	_, err := NewS3BackendFromConfig(context.Background(), config.StorageS3Config{})
+	if err == nil || !strings.Contains(err.Error(), "bucket is required") {
+		t.Fatalf("NewS3BackendFromConfig() error = %v, want bucket validation", err)
+	}
+}
+
+func TestNewS3BackendFromConfigFallsBackWhenCredentialEnvMissing(t *testing.T) {
+	original := newS3Client
+	t.Cleanup(func() { newS3Client = original })
+
+	var got s3ClientOptions
+	newS3Client = func(_ context.Context, opts s3ClientOptions) (s3API, error) {
+		got = opts
+		return &fakeS3API{}, nil
+	}
+
+	_, err := NewS3BackendFromConfig(context.Background(), config.StorageS3Config{
+		Bucket:         "my-archive",
+		Region:         "us-east-1",
+		AccessKeyIDEnv: "MISSING_ACCESS_KEY_ID",
+		SecretKeyEnv:   "MISSING_SECRET_KEY",
+	})
+	if err != nil {
+		t.Fatalf("NewS3BackendFromConfig() error = %v", err)
+	}
+	if got.AccessKeyID != "" || got.SecretKey != "" {
+		t.Fatalf("client options credentials = %#v, want empty fallback values", got)
+	}
+}
+
+func strPtr(v string) *string { return &v }
+func int64Ptr(v int64) *int64 { return &v }
+
+var _ s3API = (*fakeS3API)(nil)

internal/app/analyze_artifacts.go

@@ -0,0 +1,66 @@
+package app
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+type artifactSelectionFlag struct {
+	values []string
+}
+
+func (f *artifactSelectionFlag) String() string {
+	return strings.Join(f.values, ",")
+}
+
+func (f *artifactSelectionFlag) Set(value string) error {
+	f.values = append(f.values, value)
+	return nil
+}
+
+func (f *artifactSelectionFlag) Normalize() ([]string, error) {
+	if len(f.values) == 0 {
+		return nil, nil
+	}
+
+	seen := map[string]struct{}{}
+	out := make([]string, 0, len(f.values))
+	for _, raw := range f.values {
+		for _, part := range strings.Split(raw, ",") {
+			name := strings.TrimSpace(part)
+			if name == "" {
+				return nil, fmt.Errorf("artifact names must be non-empty")
+			}
+			if _, ok := seen[name]; ok {
+				continue
+			}
+			seen[name] = struct{}{}
+			out = append(out, name)
+		}
+	}
+
+	sort.Strings(out)
+	return out, nil
+}
+
+func validateSelectedAnalyzeArtifacts(cfg *config.Config, selected []string) error {
+	if len(selected) == 0 {
+		return nil
+	}
+	if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Scriptorium == nil {
+		return fmt.Errorf("--artifacts requires pipeline.scriptorium.artifacts to be configured")
+	}
+	configured := cfg.Pipeline.Scriptorium.Artifacts
+	if len(configured) == 0 {
+		return fmt.Errorf("--artifacts requires at least one configured artifact in pipeline.scriptorium.artifacts")
+	}
+	for _, name := range selected {
+		if _, ok := configured[name]; !ok {
+			return fmt.Errorf("--artifacts includes unknown artifact %q", name)
+		}
+	}
+	return nil
+}

internal/app/analyze_artifacts_commands_test.go

@@ -0,0 +1,140 @@
+package app
+
+import (
+	"bytes"
+	"context"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
+)
+
+func TestExecuteRunStageArtifactsNonAnalyzeFails(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFilesWithScriptoriumArtifacts(t, workspaceRoot)
+
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+	code := Execute(
+		[]string{"run-stage", "--config", pipelinePath, "--session", sessionPath, "--artifacts", "session_recap", "polish"},
+		&stdout,
+		&stderr,
+	)
+	if code == 0 {
+		t.Fatal("exit code = 0, want non-zero")
+	}
+	if !strings.Contains(stderr.String(), `run-stage: --artifacts is only supported for stage "analyze"`) {
+		t.Fatalf("stderr = %q, want stage-gating error", stderr.String())
+	}
+}
+
+func TestExecuteUnknownArtifactsFailValidation(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFilesWithScriptoriumArtifacts(t, workspaceRoot)
+
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+	code := Execute(
+		[]string{"run", "--config", pipelinePath, "--session", sessionPath, "--artifacts", "unknown_artifact"},
+		&stdout,
+		&stderr,
+	)
+	if code == 0 {
+		t.Fatal("exit code = 0, want non-zero")
+	}
+	if !strings.Contains(stderr.String(), `run: --artifacts includes unknown artifact "unknown_artifact"`) {
+		t.Fatalf("stderr = %q, want unknown-artifact validation error", stderr.String())
+	}
+}
+
+func TestRunStageArtifactsDoesNotImplyForce(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFilesWithScriptoriumArtifacts(t, workspaceRoot)
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+
+	store := &manifest.LocalStore{}
+	seed := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
+	seed.MarkStageSucceeded("analyze", time.Date(2026, 5, 3, 10, 1, 0, 0, time.UTC), nil)
+	if err := store.Save(context.Background(), manifestPath, seed); err != nil {
+		t.Fatalf("save manifest: %v", err)
+	}
+
+	var out bytes.Buffer
+	err := RunStage(
+		context.Background(),
+		[]string{"--config", pipelinePath, "--session", sessionPath, "--artifacts", "session_recap,session_recap", "analyze"},
+		&out,
+	)
+	if err != nil {
+		t.Fatalf("RunStage() error = %v", err)
+	}
+	if !strings.Contains(out.String(), "stage=analyze executed=0 skipped=1 force=false") {
+		t.Fatalf("output = %q, want analyze skip without force", out.String())
+	}
+}
+
+func TestResumeArtifactsWithSucceededAnalyzeSkipsUnlessForced(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFilesWithScriptoriumArtifacts(t, workspaceRoot)
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+
+	store := &manifest.LocalStore{}
+	seed := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
+	for _, stageName := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze", "archive", "notify"} {
+		seed.MarkStageSucceeded(stageName, time.Date(2026, 5, 3, 10, 1, 0, 0, time.UTC), nil)
+	}
+	if err := store.Save(context.Background(), manifestPath, seed); err != nil {
+		t.Fatalf("save manifest: %v", err)
+	}
+
+	var out bytes.Buffer
+	err := Resume(
+		context.Background(),
+		[]string{"--config", pipelinePath, "--session", sessionPath, "--artifacts", "session_recap"},
+		&out,
+	)
+	if err != nil {
+		t.Fatalf("Resume() error = %v", err)
+	}
+	if !strings.Contains(out.String(), "has no remaining stages") {
+		t.Fatalf("output = %q, want no remaining stages", out.String())
+	}
+}
+
+func writeValidConfigFilesWithScriptoriumArtifacts(t *testing.T, workspaceRoot string) (string, string) {
+	t.Helper()
+
+	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
+	f, err := os.OpenFile(pipelinePath, os.O_APPEND|os.O_WRONLY, 0)
+	if err != nil {
+		t.Fatalf("open pipeline config for append: %v", err)
+	}
+	defer f.Close()
+
+	extra := `
+scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+    player_handout:
+      enabled: true
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      depends_on:
+        - session_recap
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+`
+	if _, err := f.WriteString(extra); err != nil {
+		t.Fatalf("append scriptorium config: %v", err)
+	}
+	return pipelinePath, sessionPath
+}

internal/app/analyze_artifacts_test.go

@@ -0,0 +1,132 @@
+package app
+
+import (
+	"testing"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+func TestArtifactSelectionFlagNormalize(t *testing.T) {
+	tests := []struct {
+		name    string
+		inputs  []string
+		want    []string
+		wantErr string
+	}{
+		{
+			name:   "single value",
+			inputs: []string{"session_recap"},
+			want:   []string{"session_recap"},
+		},
+		{
+			name:   "repeatable and comma separated values are deduped and sorted",
+			inputs: []string{"session_recap,player_handout", "session_recap"},
+			want:   []string{"player_handout", "session_recap"},
+		},
+		{
+			name:    "empty token fails",
+			inputs:  []string{"session_recap,"},
+			wantErr: "artifact names must be non-empty",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			var flag artifactSelectionFlag
+			for _, in := range tt.inputs {
+				if err := flag.Set(in); err != nil {
+					t.Fatalf("Set(%q) error = %v", in, err)
+				}
+			}
+
+			got, err := flag.Normalize()
+			if tt.wantErr != "" {
+				if err == nil {
+					t.Fatalf("Normalize() error = nil, want %q", tt.wantErr)
+				}
+				if err.Error() != tt.wantErr {
+					t.Fatalf("Normalize() error = %q, want %q", err.Error(), tt.wantErr)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("Normalize() error = %v", err)
+			}
+			if len(got) != len(tt.want) {
+				t.Fatalf("Normalize() len = %d, want %d; got=%v", len(got), len(tt.want), got)
+			}
+			for i := range got {
+				if got[i] != tt.want[i] {
+					t.Fatalf("Normalize()[%d] = %q, want %q", i, got[i], tt.want[i])
+				}
+			}
+		})
+	}
+}
+
+func TestValidateSelectedAnalyzeArtifacts(t *testing.T) {
+	tests := []struct {
+		name     string
+		cfg      *config.Config
+		selected []string
+		wantErr  string
+	}{
+		{
+			name:     "empty selection is accepted",
+			cfg:      &config.Config{},
+			selected: nil,
+		},
+		{
+			name:     "scriptorium required when selected artifacts present",
+			cfg:      &config.Config{Pipeline: &config.PipelineConfig{}},
+			selected: []string{"session_recap"},
+			wantErr:  "--artifacts requires pipeline.scriptorium.artifacts to be configured",
+		},
+		{
+			name: "unknown selected artifact fails",
+			cfg: &config.Config{
+				Pipeline: &config.PipelineConfig{
+					Scriptorium: &config.ScriptoriumConfig{
+						Artifacts: map[string]config.ScriptoriumArtifactConfig{
+							"session_recap": {Enabled: true, PromptID: "dnd.session_recap", OutputPath: "artifacts/session_recap.md"},
+						},
+					},
+				},
+			},
+			selected: []string{"player_handout"},
+			wantErr:  `--artifacts includes unknown artifact "player_handout"`,
+		},
+		{
+			name: "known selected artifacts are accepted",
+			cfg: &config.Config{
+				Pipeline: &config.PipelineConfig{
+					Scriptorium: &config.ScriptoriumConfig{
+						Artifacts: map[string]config.ScriptoriumArtifactConfig{
+							"session_recap":  {Enabled: true, PromptID: "dnd.session_recap", OutputPath: "artifacts/session_recap.md"},
+							"player_handout": {Enabled: true, PromptID: "dnd.player_handout", OutputPath: "artifacts/player_handout.md"},
+						},
+					},
+				},
+			},
+			selected: []string{"player_handout", "session_recap"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := validateSelectedAnalyzeArtifacts(tt.cfg, tt.selected)
+			if tt.wantErr != "" {
+				if err == nil {
+					t.Fatalf("error = nil, want %q", tt.wantErr)
+				}
+				if err.Error() != tt.wantErr {
+					t.Fatalf("error = %q, want %q", err.Error(), tt.wantErr)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("error = %v, want nil", err)
+			}
+		})
+	}
+}

internal/app/commands_test.go

@@ -12,6 +12,7 @@ import (
 	"testing"
 	"time"
 
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
 	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
 )
 
@@ -63,12 +64,13 @@ func TestExecuteMissingRequiredFlags(t *testing.T) {
 		args []string
 		want string
 	}{
-		{name: "run missing flags", args: []string{"run"}, want: "run: --config and --session are required"},
-		{name: "plan missing flags", args: []string{"plan"}, want: "plan: --config and --session are required"},
+		{name: "run missing flags", args: []string{"run"}, want: "run: no pipeline config path provided and no default pipeline config found; searched:"},
+		{name: "plan missing flags", args: []string{"plan"}, want: "plan: no pipeline config path provided and no default pipeline config found; searched:"},
 		{name: "status missing flags", args: []string{"status"}, want: "status: --manifest is required"},
-		{name: "resume missing flags", args: []string{"resume"}, want: "resume: --config and --session are required"},
+		{name: "resume missing flags", args: []string{"resume"}, want: "resume: no pipeline config path provided and no default pipeline config found; searched:"},
 		{name: "run-stage missing name", args: []string{"run-stage", "--config", "a", "--session", "b"}, want: "run-stage: expected exactly one stage name"},
-		{name: "run-stage missing config flags", args: []string{"run-stage", "polish"}, want: "run-stage: --config and --session are required"},
+		{name: "run-stage missing config flags", args: []string{"run-stage", "polish"}, want: "run-stage: no pipeline config path provided and no default pipeline config found; searched:"},
+		{name: "run missing config uses defaults", args: []string{"run", "--session", "session.yml"}, want: "run: no pipeline config path provided and no default pipeline config found; searched:"},
 	}
 
 	for _, tc := range cases {
@@ -109,7 +111,7 @@ func TestExecuteRunStageUnknownFails(t *testing.T) {
 func TestExecuteRunStageNormalizeIsAccepted(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot, "https://example.com/transcribe")
-	workRoot := filepath.Join(workspaceRoot, "work", "2026-05-03")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
 	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "processed.json"), `{"segments":[{"id":1}]}`)
 
 	var stdout bytes.Buffer
@@ -154,7 +156,7 @@ func TestExecuteRunStageTranscribeUsesConfiguredWhisperXServer(t *testing.T) {
 		t.Fatal("expected whisperx server to be called at least once")
 	}
 
-	outPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "transcripts", "raw", "alice.json")
+	outPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "transcripts", "raw", "alice.json")
 	data, err := os.ReadFile(outPath)
 	if err != nil {
 		t.Fatalf("ReadFile(%q): %v", outPath, err)
@@ -168,6 +170,159 @@ func TestExecuteRunStageTranscribeUsesConfiguredWhisperXServer(t *testing.T) {
 	}
 }
 
+func TestExecuteRunStagePolishLoadsCredentialFromSecretsDir(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	configDir := t.TempDir()
+	sessionID := "2026-05-03"
+	secretsDir := filepath.Join(configDir, "secrets")
+	if err := os.MkdirAll(secretsDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll(%q): %v", secretsDir, err)
+	}
+	if err := os.WriteFile(filepath.Join(secretsDir, "OPENROUTER_API_KEY"), []byte("from-secret-file\n"), 0o600); err != nil {
+		t.Fatalf("write OPENROUTER_API_KEY secret file: %v", err)
+	}
+
+	seriatimBinary := writeSeriatimAppTestWrapper(t)
+	auditaBinary := writeAuditaAppTestWrapper(t)
+	t.Setenv("GO_WANT_APP_SERIATIM_HELPER", "1")
+	t.Setenv("GO_WANT_APP_AUDITA_HELPER", "1")
+
+	pipelinePath := filepath.Join(configDir, "pipeline.yml")
+	sessionPath := filepath.Join(configDir, "session.yml")
+	pipelineYAML := `workspace:
+  root: ` + workspaceRoot + `
+storage:
+  backend: local
+secrets:
+  env_dir: ./secrets
+whisperx:
+  transcribe_url: https://example.com/transcribe
+seriatim:
+  binary: ` + seriatimBinary + `
+audita:
+  binary: ` + auditaBinary + `
+  llm_api_key_env: OPENROUTER_API_KEY
+analyzer:
+  timeout: 20m
+notification:
+  timeout: 10s
+`
+	sessionYAML := `session_id: ` + sessionID + `
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
+		t.Fatalf("write pipeline.yml: %v", err)
+	}
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	originalWD, err := os.Getwd()
+	if err != nil {
+		t.Fatalf("Getwd(): %v", err)
+	}
+	if err := os.Chdir(configDir); err != nil {
+		t.Fatalf("Chdir(%q): %v", configDir, err)
+	}
+	t.Cleanup(func() {
+		_ = os.Chdir(originalWD)
+	})
+
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", sessionID)
+	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "merged.json"), `{"schema":"seriatim-intermediate","segments":[]}`)
+	mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "glossary.yml"), "[]\n")
+
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+	code := Execute([]string{"run-stage", "--config", pipelinePath, "--session", sessionPath, "--force", "polish"}, &stdout, &stderr)
+	if code != 0 {
+		t.Fatalf("exit code = %d, want 0; stderr=%q", code, stderr.String())
+	}
+	if !strings.Contains(stdout.String(), "stage=polish executed=1 skipped=0") {
+		t.Fatalf("stdout = %q, want polish execution", stdout.String())
+	}
+}
+
+func TestExecuteRunFailsWhenConfiguredSecretsDirMissing(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	configDir := t.TempDir()
+	pipelinePath := filepath.Join(configDir, "pipeline.yml")
+	sessionPath := filepath.Join(configDir, "session.yml")
+
+	pipelineYAML := `workspace:
+  root: ` + workspaceRoot + `
+storage:
+  backend: local
+secrets:
+  env_dir: ./missing-secrets
+whisperx:
+  transcribe_url: https://example.com/transcribe
+seriatim:
+  binary: seriatim
+audita:
+  binary: audita
+analyzer:
+  timeout: 20m
+notification:
+  timeout: 10s
+`
+	sessionYAML := `session_id: 2026-05-03
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
+		t.Fatalf("write pipeline.yml: %v", err)
+	}
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+	code := Execute([]string{"run", "--config", pipelinePath, "--session", sessionPath}, &stdout, &stderr)
+	if code == 0 {
+		t.Fatal("exit code = 0, want non-zero")
+	}
+	if !strings.Contains(stderr.String(), "read secrets env_dir") {
+		t.Fatalf("stderr = %q, want secrets read-dir error context", stderr.String())
+	}
+}
+
+func TestExecuteUsesDefaultPipelineConfigPathWhenConfigFlagOmitted(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"source":"default-config-test","segments":[{"speaker":"alice"}]}`))
+	}))
+	defer srv.Close()
+
+	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot, srv.URL)
+	originalDefaults := append([]string(nil), config.DefaultPipelineConfigSearchPaths...)
+	config.DefaultPipelineConfigSearchPaths = []string{pipelinePath}
+	defer func() {
+		config.DefaultPipelineConfigSearchPaths = originalDefaults
+	}()
+
+	var stdout bytes.Buffer
+	var stderr bytes.Buffer
+	code := Execute([]string{"run", "--session", sessionPath}, &stdout, &stderr)
+	if code != 0 {
+		t.Fatalf("exit code = %d, want 0; stderr=%q", code, stderr.String())
+	}
+	if !strings.Contains(stdout.String(), "narratio run: session 2026-05-03; executed=9 skipped=0; manifest=") {
+		t.Fatalf("stdout = %q, want successful run output", stdout.String())
+	}
+}
+
 func TestExecuteInvalidCommand(t *testing.T) {
 	var stdout bytes.Buffer
 	var stderr bytes.Buffer
@@ -224,6 +379,11 @@ func writeValidConfigFiles(t *testing.T, workspaceRoot string, transcribeURL ...
   root: ` + workspaceRoot + `
 storage:
   backend: s3
+  s3:
+    bucket: test-bucket
+archive:
+  enabled: true
+  upload_run: false
 whisperx:
   transcribe_url: ` + url + `
   timeout: 2s
@@ -247,6 +407,7 @@ notification:
 `
 
 	sessionYAML := `session_id: 2026-05-03
+campaign: sample-campaign
 inputs:
   audio_dir: ./audio
   speakers_file: ./speakers.yml

internal/app/pipeline_config_path.go

@@ -0,0 +1,49 @@
+package app
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+func resolvePipelineConfigPath(flagValue string) (string, error) {
+	return resolvePipelineConfigPathWithCandidates(flagValue, config.DefaultPipelineConfigSearchPaths)
+}
+
+func resolvePipelineConfigPathWithCandidates(flagValue string, candidates []string) (string, error) {
+	if explicit := strings.TrimSpace(flagValue); explicit != "" {
+		return explicit, nil
+	}
+
+	ordered := make([]string, 0, len(candidates))
+	for _, raw := range candidates {
+		path := strings.TrimSpace(raw)
+		if path == "" {
+			continue
+		}
+		ordered = append(ordered, path)
+		info, err := os.Stat(path)
+		if err == nil {
+			if info.IsDir() {
+				continue
+			}
+			return filepath.Clean(path), nil
+		}
+		if errors.Is(err, os.ErrNotExist) {
+			continue
+		}
+		return "", fmt.Errorf("check default pipeline config %q: %w", path, err)
+	}
+
+	if len(ordered) == 0 {
+		return "", fmt.Errorf("no pipeline config path provided and no default locations configured")
+	}
+	return "", fmt.Errorf(
+		"no pipeline config path provided and no default pipeline config found; searched: %s",
+		strings.Join(ordered, ", "),
+	)
+}

internal/app/pipeline_config_path_test.go

@@ -0,0 +1,65 @@
+package app
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestResolvePipelineConfigPathWithCandidatesExplicitWins(t *testing.T) {
+	got, err := resolvePipelineConfigPathWithCandidates("  ./custom/pipeline.yml  ", []string{"/a", "/b"})
+	if err != nil {
+		t.Fatalf("resolvePipelineConfigPathWithCandidates() error = %v", err)
+	}
+	if got != "./custom/pipeline.yml" {
+		t.Fatalf("resolved path = %q, want explicit path", got)
+	}
+}
+
+func TestResolvePipelineConfigPathWithCandidatesUsesFirstExisting(t *testing.T) {
+	dir := t.TempDir()
+	first := filepath.Join(dir, "first.yml")
+	second := filepath.Join(dir, "second.yml")
+	if err := os.WriteFile(second, []byte("workspace:\n  root: ./tmp\n"), 0o644); err != nil {
+		t.Fatalf("write second default: %v", err)
+	}
+
+	got, err := resolvePipelineConfigPathWithCandidates("", []string{first, second})
+	if err != nil {
+		t.Fatalf("resolvePipelineConfigPathWithCandidates() error = %v", err)
+	}
+	if got != filepath.Clean(second) {
+		t.Fatalf("resolved path = %q, want %q", got, filepath.Clean(second))
+	}
+}
+
+func TestResolvePipelineConfigPathWithCandidatesPrecedence(t *testing.T) {
+	dir := t.TempDir()
+	first := filepath.Join(dir, "first.yml")
+	second := filepath.Join(dir, "second.yml")
+	if err := os.WriteFile(first, []byte("workspace:\n  root: ./tmp\n"), 0o644); err != nil {
+		t.Fatalf("write first default: %v", err)
+	}
+	if err := os.WriteFile(second, []byte("workspace:\n  root: ./tmp\n"), 0o644); err != nil {
+		t.Fatalf("write second default: %v", err)
+	}
+
+	got, err := resolvePipelineConfigPathWithCandidates("", []string{first, second})
+	if err != nil {
+		t.Fatalf("resolvePipelineConfigPathWithCandidates() error = %v", err)
+	}
+	if got != filepath.Clean(first) {
+		t.Fatalf("resolved path = %q, want first candidate %q", got, filepath.Clean(first))
+	}
+}
+
+func TestResolvePipelineConfigPathWithCandidatesMissing(t *testing.T) {
+	_, err := resolvePipelineConfigPathWithCandidates("", []string{"/does/not/exist/one.yml", "/does/not/exist/two.yml"})
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "no default pipeline config found") {
+		t.Fatalf("error = %q, want missing-defaults context", err.Error())
+	}
+}

internal/app/plan.go

@@ -5,9 +5,12 @@ import (
 	"flag"
 	"fmt"
 	"io"
+	"log/slog"
+	"os"
 
 	"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
 	"gitea.maximumdirect.net/eric/narratio/internal/config"
+	"gitea.maximumdirect.net/eric/narratio/internal/logging"
 	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
 )
 
@@ -18,9 +21,11 @@ func Plan(ctx context.Context, args []string, out io.Writer) error {
 
 	var pipelinePath string
 	var sessionPath string
+	var sessionID string
 	var force bool
-	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml")
+	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
 	fs.StringVar(&sessionPath, "session", "", "path to session.yml")
+	fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
 	fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
 
 	if err := fs.Parse(args); err != nil {
@@ -29,20 +34,30 @@ func Plan(ctx context.Context, args []string, out io.Writer) error {
 	if fs.NArg() != 0 {
 		return fmt.Errorf("plan: unexpected positional arguments")
 	}
-	if pipelinePath == "" || sessionPath == "" {
-		return fmt.Errorf("plan: --config and --session are required")
+	resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
+	if err != nil {
+		return fmt.Errorf("plan: %w", err)
+	}
+	resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
+	if err != nil {
+		return fmt.Errorf("plan: %w", err)
 	}
 
-	cfg, err := config.Load(pipelinePath, sessionPath)
+	cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
+		SessionID: sessionID,
+	})
 	if err != nil {
 		return fmt.Errorf("plan: %w", err)
 	}
 	if err := config.Validate(cfg); err != nil {
 		return fmt.Errorf("plan: %w", err)
 	}
+	if _, err := loadSecretsFromConfig(cfg, logging.NewLogger(os.Stderr, slog.LevelInfo)); err != nil {
+		return fmt.Errorf("plan: %w", err)
+	}
 
 	store := artifacts.NewLocalStore(cfg.Pipeline.Workspace.Root)
-	paths, err := store.EnsureLayout(cfg.Session.SessionID)
+	paths, err := store.EnsureLayoutFor(cfg.Session.Campaign, cfg.Session.SessionID)
 	if err != nil {
 		return fmt.Errorf("plan: prepare workdir: %w", err)
 	}

internal/app/plan_test.go

@@ -36,7 +36,7 @@ func TestPlanCreatesAndReusesWorkdir(t *testing.T) {
 		t.Fatalf("first output = %q, want totals", got)
 	}
 
-	sessionWorkdir := artifacts.SessionWorkDir(workspaceRoot, "2026-05-03")
+	sessionWorkdir := artifacts.SessionWorkDirForCampaign(workspaceRoot, "sample-campaign", "2026-05-03")
 	expectedDirs := []string{
 		sessionWorkdir,
 		filepath.Join(sessionWorkdir, "inputs"),
@@ -63,7 +63,7 @@ func TestPlanCreatesAndReusesWorkdir(t *testing.T) {
 func TestPlanShowsRunAndSkipFromManifest(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
 
 	store := &manifest.LocalStore{}
 	m := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
@@ -89,6 +89,54 @@ func TestPlanShowsRunAndSkipFromManifest(t *testing.T) {
 	}
 }
 
+func TestPlanFailsWhenConfiguredSecretsDirMissing(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	configDir := t.TempDir()
+	pipelinePath := filepath.Join(configDir, "pipeline.yml")
+	sessionPath := filepath.Join(configDir, "session.yml")
+
+	pipelineYAML := `workspace:
+  root: ` + workspaceRoot + `
+storage:
+  backend: local
+secrets:
+  env_dir: ./missing-secrets
+whisperx:
+  transcribe_url: https://example.com/transcribe
+seriatim:
+  binary: seriatim
+audita:
+  binary: audita
+analyzer:
+  timeout: 20m
+notification:
+  timeout: 10s
+`
+	sessionYAML := `session_id: 2026-05-03
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
+		t.Fatalf("write pipeline.yml: %v", err)
+	}
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	var out bytes.Buffer
+	err := Plan(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath}, &out)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "read secrets env_dir") {
+		t.Fatalf("error = %q, want secrets read error context", err.Error())
+	}
+}
+
 func assertDir(t *testing.T, path string) {
 	t.Helper()
 	info, err := os.Stat(path)

internal/app/post_archive_cleanup.go

@@ -0,0 +1,208 @@
+package app
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
+)
+
+func runPostArchiveCleanup(ctx context.Context, env *Env, manifestPath string, m *manifest.Manifest, executed []string) error {
+	if env == nil || env.Config == nil || env.Config.Pipeline == nil || m == nil {
+		return nil
+	}
+
+	spoolRequested := env.Config.Pipeline.Spool.DeleteAudioAfterArchive
+	workRequested := env.Config.Pipeline.Workspace.CleanupAfterArchive
+	if !spoolRequested && !workRequested {
+		return nil
+	}
+
+	sr := archiveStageRecordForCleanup(m, executed)
+	if sr == nil {
+		return nil
+	}
+	if sr.Metadata == nil {
+		sr.Metadata = map[string]any{}
+	}
+	sr.Metadata["spool_cleanup_requested"] = spoolRequested
+	sr.Metadata["workdir_cleanup_requested"] = workRequested
+
+	eligible, reason := archiveCleanupEligible(env.Config, sr)
+	if !eligible {
+		sr.Metadata["cleanup_skipped"] = true
+		sr.Metadata["cleanup_skipped_reason"] = reason
+		if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
+			return fmt.Errorf("save manifest cleanup skip metadata %q: %w", manifestPath, err)
+		}
+		return nil
+	}
+
+	spoolDir := strings.TrimSpace(m.LocalSpoolDir)
+	if spoolDir == "" {
+		spoolDir = artifacts.SessionSpoolAudioDir(
+			env.Config.Pipeline.Spool.Root,
+			strings.TrimSpace(env.Config.Session.Campaign),
+			strings.TrimSpace(env.Config.Session.SessionID),
+			strings.TrimSpace(m.RunID),
+		)
+	}
+	workDir := strings.TrimSpace(m.LocalWorkDir)
+	if workDir == "" {
+		workDir = artifacts.SessionRunRootForCampaign(
+			env.Config.Pipeline.Workspace.Root,
+			strings.TrimSpace(env.Config.Session.Campaign),
+			strings.TrimSpace(env.Config.Session.SessionID),
+			strings.TrimSpace(m.RunID),
+		)
+	}
+
+	if spoolRequested {
+		if err := removeRunScopedDir(strings.TrimSpace(env.Config.Pipeline.Spool.Root), spoolDir, "pipeline.spool.delete_audio_after_archive"); err != nil {
+			sr.Metadata["cleanup_failed"] = true
+			sr.Metadata["cleanup_failed_policy"] = "pipeline.spool.delete_audio_after_archive"
+			sr.Metadata["cleanup_failed_path"] = spoolDir
+			_ = env.ManifestStore.Save(ctx, manifestPath, m)
+			return err
+		}
+		sr.Metadata["spool_cleanup_deleted"] = filepath.Clean(spoolDir)
+	}
+
+	if !workRequested {
+		sr.Metadata["cleanup_completed"] = true
+		sr.Metadata["cleanup_skipped"] = false
+		if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
+			return fmt.Errorf("save manifest cleanup metadata %q: %w", manifestPath, err)
+		}
+		return nil
+	}
+
+	if err := removeRunScopedDir(strings.TrimSpace(env.Config.Pipeline.Workspace.Root), workDir, "pipeline.workspace.cleanup_after_archive"); err != nil {
+		sr.Metadata["cleanup_failed"] = true
+		sr.Metadata["cleanup_failed_policy"] = "pipeline.workspace.cleanup_after_archive"
+		sr.Metadata["cleanup_failed_path"] = workDir
+		_ = env.ManifestStore.Save(ctx, manifestPath, m)
+		return err
+	}
+
+	sr.Metadata["workdir_cleanup_deleted"] = filepath.Clean(workDir)
+	sr.Metadata["cleanup_completed"] = true
+	sr.Metadata["cleanup_skipped"] = false
+	return nil
+}
+
+func archiveStageRecordForCleanup(m *manifest.Manifest, executed []string) *manifest.StageRecord {
+	if m == nil {
+		return nil
+	}
+	archiveRan := false
+	for _, name := range executed {
+		if name == "archive" {
+			archiveRan = true
+			break
+		}
+	}
+	if !archiveRan {
+		return nil
+	}
+	sr := m.Stages["archive"]
+	if sr == nil || sr.Status != manifest.StatusSucceeded {
+		return nil
+	}
+	return sr
+}
+
+func archiveCleanupEligible(cfg *config.Config, sr *manifest.StageRecord) (bool, string) {
+	if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Archive == nil {
+		return false, "archive configuration is missing"
+	}
+	enabled := true
+	if cfg.Pipeline.Archive.Enabled != nil {
+		enabled = *cfg.Pipeline.Archive.Enabled
+	}
+	if !enabled {
+		return false, "archive.enabled is false"
+	}
+	uploadRun := true
+	if cfg.Pipeline.Archive.UploadRun != nil {
+		uploadRun = *cfg.Pipeline.Archive.UploadRun
+	}
+	if !uploadRun {
+		return false, "archive.upload_run is false"
+	}
+	if sr == nil || sr.Metadata == nil {
+		return false, "archive metadata is missing"
+	}
+	if skipped, _ := sr.Metadata["skipped"].(bool); skipped {
+		return false, "archive stage was skipped"
+	}
+	if uploaded, _ := sr.Metadata["uploaded"].(bool); !uploaded {
+		return false, "archive did not upload run record"
+	}
+	if pointer, _ := sr.Metadata["current_pointer_written"].(bool); !pointer {
+		return false, "archive did not write current pointer"
+	}
+	if strings.TrimSpace(asString(sr.Metadata["current_run_id_key"])) == "" {
+		return false, "archive current run pointer key is missing"
+	}
+	return true, ""
+}
+
+func removeRunScopedDir(root, target, policy string) error {
+	cleanRoot := strings.TrimSpace(root)
+	cleanTarget := strings.TrimSpace(target)
+	if cleanRoot == "" {
+		return fmt.Errorf("cleanup policy %s: root path is required", policy)
+	}
+	if cleanTarget == "" {
+		return fmt.Errorf("cleanup policy %s: target path is required", policy)
+	}
+
+	rootAbs, err := filepath.Abs(cleanRoot)
+	if err != nil {
+		return fmt.Errorf("cleanup policy %s: resolve root %q: %w", policy, cleanRoot, err)
+	}
+	targetAbs, err := filepath.Abs(cleanTarget)
+	if err != nil {
+		return fmt.Errorf("cleanup policy %s: resolve target %q: %w", policy, cleanTarget, err)
+	}
+
+	rel, err := filepath.Rel(rootAbs, targetAbs)
+	if err != nil {
+		return fmt.Errorf("cleanup policy %s: relative path from %q to %q: %w", policy, rootAbs, targetAbs, err)
+	}
+	if rel == "." {
+		return fmt.Errorf("cleanup policy %s: refusing to delete root directory %q", policy, rootAbs)
+	}
+	if rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
+		return fmt.Errorf("cleanup policy %s: refusing to delete path outside root: root=%q target=%q", policy, rootAbs, targetAbs)
+	}
+
+	info, err := os.Lstat(targetAbs)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return nil
+		}
+		return fmt.Errorf("cleanup policy %s: stat target %q: %w", policy, targetAbs, err)
+	}
+	if info.Mode()&os.ModeSymlink != 0 {
+		return fmt.Errorf("cleanup policy %s: refusing to delete symlink path %q", policy, targetAbs)
+	}
+	if !info.IsDir() {
+		return fmt.Errorf("cleanup policy %s: target %q is not a directory", policy, targetAbs)
+	}
+	if err := os.RemoveAll(targetAbs); err != nil {
+		return fmt.Errorf("cleanup policy %s: remove %q: %w", policy, targetAbs, err)
+	}
+	return nil
+}
+
+func asString(v any) string {
+	s, _ := v.(string)
+	return s
+}

internal/app/post_archive_cleanup_test.go

@@ -0,0 +1,403 @@
+package app
+
+import (
+	"context"
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
+	"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
+	"gitea.maximumdirect.net/eric/narratio/internal/stage"
+)
+
+type archiveSuccessStage struct {
+	metadata map[string]any
+}
+
+func (archiveSuccessStage) Name() string           { return "archive" }
+func (archiveSuccessStage) Declares() stage.IODecl { return stage.IODecl{} }
+func (s archiveSuccessStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
+	md := map[string]any{
+		"stage":                   "archive",
+		"uploaded":                true,
+		"current_pointer_written": true,
+		"current_run_id_key":      "dnd/campaigns/sample-campaign/sessions/2026-05-03/current/run_id.txt",
+	}
+	for k, v := range s.metadata {
+		md[k] = v
+	}
+	return &stage.StageResult{Metadata: md}, nil
+}
+
+type notifyFailStage struct{}
+
+func (notifyFailStage) Name() string           { return "notify" }
+func (notifyFailStage) Declares() stage.IODecl { return stage.IODecl{} }
+func (notifyFailStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
+	return nil, errors.New("notify failed")
+}
+
+func TestPostArchiveCleanupDisabledKeepsLocalDirs(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = false
+	cfg.Pipeline.Workspace.CleanupAfterArchive = false
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+	assertExists(t, seed.localSourceAudio)
+}
+
+func TestPostArchiveCleanupSpoolOnly(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = false
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertMissing(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+	assertExists(t, seed.localSourceAudio)
+}
+
+func TestPostArchiveCleanupWorkdirOnly(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = false
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertExists(t, cfg.Pipeline.Workspace.Root)
+	assertExists(t, seed.otherRunDir)
+	assertMissing(t, seed.runWorkDir)
+	assertExists(t, seed.spoolAudioDir)
+}
+
+func TestPostArchiveCleanupBothPolicies(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertMissing(t, seed.spoolAudioDir)
+	assertMissing(t, seed.runWorkDir)
+	assertExists(t, seed.otherRunDir)
+}
+
+func TestPostArchiveCleanupNotRunWhenArchiveFails(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+
+	_, err := executeStages(context.Background(), cfg, []stage.Stage{failingStage{name: "archive", err: errors.New("archive failed")}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
+	if err == nil || !strings.Contains(err.Error(), "stage \"archive\" failed") {
+		t.Fatalf("executeStages() error = %v, want archive failure", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+func TestPostArchiveCleanupNotRunWhenArchiveSkipped(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{metadata: map[string]any{"skipped": true}}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+func TestPostArchiveCleanupNotRunWhenCurrentPointerMissing(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{metadata: map[string]any{"current_pointer_written": false}}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+func TestPostArchiveCleanupNotRunWhenArchiveUploadDisabled(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+	cfg.Pipeline.Archive.UploadRun = boolPtr(false)
+
+	if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+func TestPostArchiveCleanupWaitsUntilAllStagesSucceed(t *testing.T) {
+	cfg, seed := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+
+	_, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}, notifyFailStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
+	if err == nil || !strings.Contains(err.Error(), "stage \"notify\" failed") {
+		t.Fatalf("executeStages() error = %v, want notify failure", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+func TestPostArchiveCleanupFailsOnUnsafePath(t *testing.T) {
+	cfg, _ := cleanupFixtureConfig(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = false
+
+	manifestPath := manifestPathFor(cfg)
+	store := &manifest.LocalStore{}
+	m, err := store.Load(context.Background(), manifestPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+	m.LocalSpoolDir = filepath.Join(filepath.Dir(cfg.Pipeline.Spool.Root), "outside-spool")
+	if err := store.Save(context.Background(), manifestPath, m); err != nil {
+		t.Fatalf("Save() error = %v", err)
+	}
+
+	_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
+	if err == nil || !strings.Contains(err.Error(), "refusing to delete path outside root") {
+		t.Fatalf("executeStages() error = %v, want safe-path failure", err)
+	}
+}
+
+func TestPostArchiveCleanupNotRunWhenPromotionIsMissing(t *testing.T) {
+	cfg, seed, runID := archiveStageCleanupFixture(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+	cfg.Pipeline.Archive.PromoteArtifacts = []config.ArchivePromotionRule{
+		{From: "artifacts/missing.md", To: "artifacts/missing.md", Required: boolPtr(true)},
+	}
+
+	archiveStageImpl, err := stage.Select("archive")
+	if err != nil {
+		t.Fatalf("Select(archive) error = %v", err)
+	}
+	_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
+	if err == nil || !strings.Contains(err.Error(), "required promotion source missing") {
+		t.Fatalf("executeStages() error = %v, want promotion-missing failure", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+	assertExists(t, filepath.Join(seed.runWorkDir, "manifest.json"))
+	assertExists(t, artifacts.SessionRunRootForCampaign(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID))
+}
+
+func TestPostArchiveCleanupNotRunWhenCurrentManifestUploadFails(t *testing.T) {
+	cfg, seed, _ := archiveStageCleanupFixture(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+	failKey := seed.sessionPrefix + "current/manifest.json"
+
+	archiveStageImpl, err := stage.Select("archive")
+	if err != nil {
+		t.Fatalf("Select(archive) error = %v", err)
+	}
+	_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{
+		Env: &Env{ObjectStore: &failKeyStore{delegate: &storage.FakeBackend{}, failKey: failKey}},
+	})
+	if err == nil || !strings.Contains(err.Error(), "current manifest") {
+		t.Fatalf("executeStages() error = %v, want current-manifest failure", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+func TestPostArchiveCleanupNotRunWhenCurrentPointerUploadFails(t *testing.T) {
+	cfg, seed, _ := archiveStageCleanupFixture(t)
+	cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
+	cfg.Pipeline.Workspace.CleanupAfterArchive = true
+	failKey := seed.sessionPrefix + "current/run_id.txt"
+
+	archiveStageImpl, err := stage.Select("archive")
+	if err != nil {
+		t.Fatalf("Select(archive) error = %v", err)
+	}
+	_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{
+		Env: &Env{ObjectStore: &failKeyStore{delegate: &storage.FakeBackend{}, failKey: failKey}},
+	})
+	if err == nil || !strings.Contains(err.Error(), "current run pointer") {
+		t.Fatalf("executeStages() error = %v, want current-run-pointer failure", err)
+	}
+
+	assertExists(t, seed.spoolAudioDir)
+	assertExists(t, seed.runWorkDir)
+}
+
+type cleanupSeed struct {
+	runWorkDir       string
+	otherRunDir      string
+	spoolAudioDir    string
+	localSourceAudio string
+	sessionPrefix    string
+}
+
+func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) {
+	t.Helper()
+
+	cfg := testConfig(t)
+	cfg.Pipeline.Archive = &config.ArchiveConfig{Enabled: boolPtr(true), UploadRun: boolPtr(true)}
+	cfg.Pipeline.Spool.Root = filepath.Join(t.TempDir(), "spool")
+
+	runID := "20260516T010203Z-1a2b3c4d"
+	runWorkDir := artifacts.SessionRunRootForCampaign(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
+	otherRunDir := artifacts.SessionRunRootForCampaign(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, "20260516T010204Z-5e6f7a8b")
+	spoolAudioDir := artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
+
+	mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "logs", "stage.log"), "log\n")
+	mustWriteFile(t, filepath.Join(otherRunDir, "logs", "stage.log"), "other\n")
+	mustWriteFile(t, filepath.Join(spoolAudioDir, "speaker.flac"), "flac\n")
+
+	localSourceAudio := filepath.Join(filepath.Dir(cfg.SessionPath), "audio", "alice.flac")
+	mustWriteFile(t, localSourceAudio, "source\n")
+
+	seed := manifest.New(cfg.Session.SessionID, time.Now().UTC())
+	seed.Campaign = cfg.Session.Campaign
+	seed.RunID = runID
+	seed.LocalWorkDir = runWorkDir
+	seed.LocalSpoolDir = spoolAudioDir
+	seed.S3Bucket = "my-dnd-archive"
+	seed.S3SessionPrefix = "dnd/campaigns/sample-campaign/sessions/2026-05-03/"
+	seed.S3RunPrefix = seed.S3SessionPrefix + "runs/" + runID + "/"
+
+	store := &manifest.LocalStore{}
+	if err := os.MkdirAll(filepath.Dir(manifestPathFor(cfg)), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := store.Save(context.Background(), manifestPathFor(cfg), seed); err != nil {
+		t.Fatalf("seed manifest save error = %v", err)
+	}
+
+	return cfg, cleanupSeed{
+		runWorkDir:       runWorkDir,
+		otherRunDir:      otherRunDir,
+		spoolAudioDir:    spoolAudioDir,
+		localSourceAudio: localSourceAudio,
+		sessionPrefix:    seed.S3SessionPrefix,
+	}
+}
+
+func archiveStageCleanupFixture(t *testing.T) (*config.Config, cleanupSeed, string) {
+	t.Helper()
+
+	cfg, seed := cleanupFixtureConfig(t)
+	runID := "20260516T010203Z-1a2b3c4d"
+	cfg.Pipeline.Storage.S3 = &config.StorageS3Config{
+		Bucket:     "my-dnd-archive",
+		RootPrefix: "dnd",
+	}
+	cfg.Pipeline.Archive = &config.ArchiveConfig{
+		Enabled:   boolPtr(true),
+		UploadRun: boolPtr(true),
+		PromoteArtifacts: []config.ArchivePromotionRule{
+			{From: "transcripts/trimmed.json", To: "transcripts/trimmed.json", Required: boolPtr(true)},
+			{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md", Required: boolPtr(true)},
+		},
+	}
+	writeArchiveFixtureRunFiles(
+		t,
+		seed.runWorkDir,
+		artifacts.SessionWorkDirForCampaign(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID),
+	)
+
+	store := &manifest.LocalStore{}
+	seedManifest, err := store.Load(context.Background(), manifestPathFor(cfg))
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+	for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze"} {
+		seedManifest.MarkStageSucceeded(name, time.Now().UTC(), nil)
+	}
+	seedManifest.S3SessionPrefix = artifacts.S3SessionPrefix("dnd", cfg.Session.Campaign, cfg.Session.SessionID)
+	seedManifest.S3RunPrefix = artifacts.S3RunPrefix(seedManifest.S3SessionPrefix, runID)
+	if err := store.Save(context.Background(), manifestPathFor(cfg), seedManifest); err != nil {
+		t.Fatalf("Save() error = %v", err)
+	}
+	seed.sessionPrefix = seedManifest.S3SessionPrefix
+	return cfg, seed, runID
+}
+
+func writeArchiveFixtureRunFiles(t *testing.T, runWorkDir, sessionRoot string) {
+	t.Helper()
+	mustWriteFile(t, filepath.Join(runWorkDir, "prepare", "inputs", "session.yml"), "session_id: 2026-05-03\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "transcribe", "outputs", "transcripts", "raw", "speaker.json"), "{}\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "trim", "outputs", "transcripts", "trimmed.json"), "{}\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "analyze", "outputs", "artifacts", "session_recap.md"), "# recap\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "polish", "reports", "audita.report.json"), "{}\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "merge", "config", "seriatim.generated.yml"), "key: value\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "logs", "audita.stderr.log"), "stderr\n")
+	mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
+
+	mustWriteFile(t, filepath.Join(sessionRoot, "transcripts", "trimmed.json"), "{}\n")
+	mustWriteFile(t, filepath.Join(sessionRoot, "artifacts", "session_recap.md"), "# recap\n")
+}
+
+type failKeyStore struct {
+	delegate *storage.FakeBackend
+	failKey  string
+}
+
+func (s *failKeyStore) List(ctx context.Context, prefix string) ([]storage.ObjectInfo, error) {
+	return s.delegate.List(ctx, prefix)
+}
+
+func (s *failKeyStore) Download(ctx context.Context, key, localPath string) error {
+	return s.delegate.Download(ctx, key, localPath)
+}
+
+func (s *failKeyStore) Upload(ctx context.Context, localPath, key string, opts storage.UploadOptions) (storage.ObjectInfo, error) {
+	if strings.TrimSpace(key) == strings.TrimSpace(s.failKey) {
+		return storage.ObjectInfo{}, errors.New("forced upload failure")
+	}
+	return s.delegate.Upload(ctx, localPath, key, opts)
+}
+
+func (s *failKeyStore) Exists(ctx context.Context, key string) (bool, error) {
+	return s.delegate.Exists(ctx, key)
+}
+
+func assertExists(t *testing.T, path string) {
+	t.Helper()
+	if _, err := os.Stat(path); err != nil {
+		t.Fatalf("expected path to exist %q: %v", path, err)
+	}
+}
+
+func assertMissing(t *testing.T, path string) {
+	t.Helper()
+	if _, err := os.Stat(path); !os.IsNotExist(err) {
+		t.Fatalf("expected path to be removed %q, stat err=%v", path, err)
+	}
+}

internal/app/resume.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 
+	"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
 	"gitea.maximumdirect.net/eric/narratio/internal/config"
 	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
 )
@@ -17,10 +18,14 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
 
 	var pipelinePath string
 	var sessionPath string
+	var sessionID string
 	var force bool
-	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml")
+	var selectedArtifacts artifactSelectionFlag
+	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
 	fs.StringVar(&sessionPath, "session", "", "path to session.yml")
+	fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
 	fs.BoolVar(&force, "force", false, "force stage execution")
+	fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)")
 
 	if err := fs.Parse(args); err != nil {
 		return fmt.Errorf("resume: invalid flags: %w", err)
@@ -28,17 +33,31 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
 	if fs.NArg() != 0 {
 		return fmt.Errorf("resume: unexpected positional arguments")
 	}
-	if pipelinePath == "" || sessionPath == "" {
-		return fmt.Errorf("resume: --config and --session are required")
+	resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
+	if err != nil {
+		return fmt.Errorf("resume: %w", err)
+	}
+	resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
+	if err != nil {
+		return fmt.Errorf("resume: %w", err)
 	}
 
-	cfg, err := config.Load(pipelinePath, sessionPath)
+	cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
+		SessionID: sessionID,
+	})
 	if err != nil {
 		return fmt.Errorf("resume: %w", err)
 	}
 	if err := config.Validate(cfg); err != nil {
 		return fmt.Errorf("resume: %w", err)
 	}
+	normalizedArtifacts, err := selectedArtifacts.Normalize()
+	if err != nil {
+		return fmt.Errorf("resume: invalid --artifacts: %w", err)
+	}
+	if err := validateSelectedAnalyzeArtifacts(cfg, normalizedArtifacts); err != nil {
+		return fmt.Errorf("resume: %w", err)
+	}
 
 	full := BuildFullPlan()
 	selected := full
@@ -57,7 +76,10 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
 		}
 	}
 
-	summary, err := executeStages(ctx, cfg, selected, RunOptions{Force: force})
+	summary, err := executeStages(ctx, cfg, selected, RunOptions{
+		Force:             force,
+		SelectedArtifacts: normalizedArtifacts,
+	})
 	if err != nil {
 		return fmt.Errorf("resume: %w", err)
 	}
@@ -74,7 +96,11 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
 }
 
 func loadManifestIfPresent(ctx context.Context, cfg *config.Config) (*manifest.Manifest, error) {
-	path := manifestPathFor(cfg)
+	path := artifacts.SessionManifestPathForCampaign(
+		cfg.Pipeline.Workspace.Root,
+		cfg.Session.Campaign,
+		cfg.Session.SessionID,
+	)
 	exists, err := fileExists(path)
 	if err != nil {
 		return nil, fmt.Errorf("check manifest %q: %w", path, err)

internal/app/resume_run_stage_test.go

@@ -16,7 +16,7 @@ import (
 func TestResumeStartsAfterCompletedStages(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
 
 	store := &manifest.LocalStore{}
 	m := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
@@ -25,7 +25,7 @@ func TestResumeStartsAfterCompletedStages(t *testing.T) {
 	if err := store.Save(context.Background(), manifestPath, m); err != nil {
 		t.Fatalf("save manifest: %v", err)
 	}
-	workRoot := filepath.Join(workspaceRoot, "work", "2026-05-03")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
 	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "raw", "alice.json"), `{"segments":[]}`)
 	mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "speakers.yml"), "match:\n  - speaker: Alice\n    match: [\"alice\"]\n")
 	mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "autocorrect.yml"), "[]\n")
@@ -52,7 +52,7 @@ func TestResumeStartsAfterCompletedStages(t *testing.T) {
 func TestResumeNoRemainingStages(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
 
 	store := &manifest.LocalStore{}
 	m := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
@@ -81,7 +81,7 @@ func TestResumeForceRerunsSucceeded(t *testing.T) {
 	}))
 	defer srv.Close()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot, srv.URL)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
 
 	store := &manifest.LocalStore{}
 	m := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
@@ -105,8 +105,8 @@ func TestResumeForceRerunsSucceeded(t *testing.T) {
 func TestRunStageExecutesOnlySelectedStage(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
-	workRoot := filepath.Join(workspaceRoot, "work", "2026-05-03")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
 	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "merged.json"), `{"segments":[]}`)
 	mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "glossary.yml"), "terms: []\n")
 
@@ -135,8 +135,8 @@ func TestRunStageExecutesOnlySelectedStage(t *testing.T) {
 func TestRunStageSkipAndForce(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
-	workRoot := filepath.Join(workspaceRoot, "work", "2026-05-03")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
 	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "merged.json"), `{"segments":[]}`)
 	mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "glossary.yml"), "terms: []\n")
 
@@ -166,11 +166,57 @@ func TestRunStageSkipAndForce(t *testing.T) {
 	}
 }
 
+func TestRunStageForceMarksDownstreamStaleAndResumeContinuesFromStale(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
+	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "merged.json"), `{"segments":[]}`)
+	mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "glossary.yml"), "terms: []\n")
+
+	store := &manifest.LocalStore{}
+	seed := manifest.New("2026-05-03", time.Date(2026, 5, 3, 10, 0, 0, 0, time.UTC))
+	for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze", "archive", "notify"} {
+		seed.MarkStageSucceeded(name, time.Date(2026, 5, 3, 10, 1, 0, 0, time.UTC), nil)
+	}
+	if err := store.Save(context.Background(), manifestPath, seed); err != nil {
+		t.Fatalf("save manifest: %v", err)
+	}
+
+	var out bytes.Buffer
+	err := RunStage(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath, "--force", "polish"}, &out)
+	if err != nil {
+		t.Fatalf("RunStage(force) error = %v", err)
+	}
+	if !strings.Contains(out.String(), "stage=polish executed=1 skipped=0 force=true") {
+		t.Fatalf("output = %q, want forced polish rerun", out.String())
+	}
+
+	afterForce, err := store.Load(context.Background(), manifestPath)
+	if err != nil {
+		t.Fatalf("load manifest after force: %v", err)
+	}
+	for _, name := range []string{"normalize", "trim", "analyze", "archive", "notify"} {
+		if afterForce.Stages[name] == nil || afterForce.Stages[name].Status != manifest.StatusStale {
+			t.Fatalf("stage %q = %#v, want stale", name, afterForce.Stages[name])
+		}
+	}
+
+	out.Reset()
+	err = Resume(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath}, &out)
+	if err != nil {
+		t.Fatalf("Resume() error = %v", err)
+	}
+	if !strings.Contains(out.String(), "executed=5 skipped=0") {
+		t.Fatalf("output = %q, want resume to execute normalize..notify", out.String())
+	}
+}
+
 func TestRunStageTrimExecutes(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
-	workRoot := filepath.Join(workspaceRoot, "work", "2026-05-03")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
 	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "normalized.json"), `{"segments":[{"id":1},{"id":2}]}`)
 
 	var out bytes.Buffer
@@ -198,8 +244,8 @@ func TestRunStageTrimExecutes(t *testing.T) {
 func TestRunStageNormalizeExecutes(t *testing.T) {
 	workspaceRoot := t.TempDir()
 	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
-	manifestPath := filepath.Join(workspaceRoot, "work", "2026-05-03", "manifest.json")
-	workRoot := filepath.Join(workspaceRoot, "work", "2026-05-03")
+	manifestPath := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03", "manifest.json")
+	workRoot := filepath.Join(workspaceRoot, "work", "sample-campaign", "2026-05-03")
 	mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "processed.json"), `{"segments":[{"id":1},{"id":2}]}`)
 
 	var out bytes.Buffer

internal/app/run.go

@@ -16,10 +16,14 @@ func Run(ctx context.Context, args []string, out io.Writer) error {
 
 	var pipelinePath string
 	var sessionPath string
+	var sessionID string
 	var force bool
-	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml")
+	var selectedArtifacts artifactSelectionFlag
+	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
 	fs.StringVar(&sessionPath, "session", "", "path to session.yml")
+	fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
 	fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
+	fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)")
 
 	if err := fs.Parse(args); err != nil {
 		return fmt.Errorf("run: invalid flags: %w", err)
@@ -27,20 +31,37 @@ func Run(ctx context.Context, args []string, out io.Writer) error {
 	if fs.NArg() != 0 {
 		return fmt.Errorf("run: unexpected positional arguments")
 	}
-	if pipelinePath == "" || sessionPath == "" {
-		return fmt.Errorf("run: --config and --session are required")
+	resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
+	if err != nil {
+		return fmt.Errorf("run: %w", err)
+	}
+	resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
+	if err != nil {
+		return fmt.Errorf("run: %w", err)
 	}
 
-	cfg, err := config.Load(pipelinePath, sessionPath)
+	cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
+		SessionID: sessionID,
+	})
 	if err != nil {
 		return fmt.Errorf("run: %w", err)
 	}
 	if err := config.Validate(cfg); err != nil {
 		return fmt.Errorf("run: %w", err)
 	}
+	normalizedArtifacts, err := selectedArtifacts.Normalize()
+	if err != nil {
+		return fmt.Errorf("run: invalid --artifacts: %w", err)
+	}
+	if err := validateSelectedAnalyzeArtifacts(cfg, normalizedArtifacts); err != nil {
+		return fmt.Errorf("run: %w", err)
+	}
 
 	stages := BuildFullPlan()
-	summary, err := executeStages(ctx, cfg, stages, RunOptions{Force: force})
+	summary, err := executeStages(ctx, cfg, stages, RunOptions{
+		Force:             force,
+		SelectedArtifacts: normalizedArtifacts,
+	})
 	if err != nil {
 		return fmt.Errorf("run: %w", err)
 	}

internal/app/run_control.go

@@ -1,6 +1,8 @@
 package app
 
 import (
+	"time"
+
 	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
 	"gitea.maximumdirect.net/eric/narratio/internal/stage"
 )
@@ -49,3 +51,43 @@ func firstNonSucceededIndex(stages []stage.Stage, m *manifest.Manifest) int {
 	}
 	return len(stages)
 }
+
+func canonicalStageNames() []string {
+	all := stage.All()
+	out := make([]string, 0, len(all))
+	for _, s := range all {
+		if s == nil {
+			continue
+		}
+		out = append(out, s.Name())
+	}
+	return out
+}
+
+func downstreamStageNames(stageName string) []string {
+	names := canonicalStageNames()
+	for i, name := range names {
+		if name != stageName {
+			continue
+		}
+		return append([]string(nil), names[i+1:]...)
+	}
+	return nil
+}
+
+func invalidateDownstreamSucceededStages(m *manifest.Manifest, upstreamStage string, at time.Time) []string {
+	if m == nil || m.Stages == nil {
+		return nil
+	}
+
+	invalidated := make([]string, 0)
+	for _, downstream := range downstreamStageNames(upstreamStage) {
+		sr := m.Stages[downstream]
+		if sr == nil || sr.Status != manifest.StatusSucceeded {
+			continue
+		}
+		m.MarkStageStale(downstream, at, "upstream stage rerun with force")
+		invalidated = append(invalidated, downstream)
+	}
+	return invalidated
+}

internal/app/run_control_test.go

@@ -1,6 +1,7 @@
 package app
 
 import (
+	"reflect"
 	"testing"
 	"time"
 
@@ -40,3 +41,48 @@ func TestDecideStageActions(t *testing.T) {
 		t.Fatalf("forced prepare action = %q, want %q", forced[0].Action, stageActionRun)
 	}
 }
+
+func TestDownstreamStageNames(t *testing.T) {
+	got := downstreamStageNames("polish")
+	want := []string{"normalize", "trim", "analyze", "archive", "notify"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("downstreamStageNames(polish) = %#v, want %#v", got, want)
+	}
+
+	missing := downstreamStageNames("unknown")
+	if len(missing) != 0 {
+		t.Fatalf("downstreamStageNames(unknown) = %#v, want empty", missing)
+	}
+}
+
+func TestInvalidateDownstreamSucceededStages(t *testing.T) {
+	now := time.Now().UTC()
+	m := manifest.New("2026-05-03", now)
+	m.MarkStageSucceeded("prepare", now, nil)
+	m.MarkStageSucceeded("transcribe", now, nil)
+	m.MarkStageSucceeded("merge", now, nil)
+	m.MarkStageSucceeded("polish", now, nil)
+	m.MarkStageSucceeded("normalize", now, nil)
+	m.MarkStageSucceeded("trim", now, nil)
+	m.MarkStageFailed("analyze", now, "analysis failed")
+	m.MarkStageSucceeded("archive", now, nil)
+	m.MarkStageSucceeded("notify", now, nil)
+
+	got := invalidateDownstreamSucceededStages(m, "polish", now.Add(1*time.Second))
+	want := []string{"normalize", "trim", "archive", "notify"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("invalidateDownstreamSucceededStages() = %#v, want %#v", got, want)
+	}
+
+	for _, stageName := range want {
+		if m.Stages[stageName].Status != manifest.StatusStale {
+			t.Fatalf("%s status = %q, want stale", stageName, m.Stages[stageName].Status)
+		}
+	}
+	if m.Stages["analyze"].Status != manifest.StatusFailed {
+		t.Fatalf("analyze status = %q, want failed", m.Stages["analyze"].Status)
+	}
+	if m.Stages["prepare"].Status != manifest.StatusSucceeded {
+		t.Fatalf("prepare status = %q, want succeeded", m.Stages["prepare"].Status)
+	}
+}

internal/app/run_stage.go

@@ -16,10 +16,14 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
 
 	var pipelinePath string
 	var sessionPath string
+	var sessionID string
 	var force bool
-	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml")
+	var selectedArtifacts artifactSelectionFlag
+	fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
 	fs.StringVar(&sessionPath, "session", "", "path to session.yml")
+	fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
 	fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
+	fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)")
 
 	if err := fs.Parse(args); err != nil {
 		return fmt.Errorf("run-stage: invalid flags: %w", err)
@@ -27,25 +31,45 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
 	if fs.NArg() != 1 {
 		return fmt.Errorf("run-stage: expected exactly one stage name")
 	}
-	if pipelinePath == "" || sessionPath == "" {
-		return fmt.Errorf("run-stage: --config and --session are required")
-	}
-
 	stageName := fs.Arg(0)
+	normalizedArtifacts, err := selectedArtifacts.Normalize()
+	if err != nil {
+		return fmt.Errorf("run-stage: invalid --artifacts: %w", err)
+	}
+	if len(normalizedArtifacts) > 0 && stageName != "analyze" {
+		return fmt.Errorf("run-stage: --artifacts is only supported for stage \"analyze\"")
+	}
 	stages, err := BuildSingleStagePlan(stageName)
 	if err != nil {
 		return fmt.Errorf("run-stage: %w", err)
 	}
 
-	cfg, err := config.Load(pipelinePath, sessionPath)
+	resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
+	if err != nil {
+		return fmt.Errorf("run-stage: %w", err)
+	}
+	resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
+	if err != nil {
+		return fmt.Errorf("run-stage: %w", err)
+	}
+
+	cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
+		SessionID: sessionID,
+	})
 	if err != nil {
 		return fmt.Errorf("run-stage: %w", err)
 	}
 	if err := config.Validate(cfg); err != nil {
 		return fmt.Errorf("run-stage: %w", err)
 	}
+	if err := validateSelectedAnalyzeArtifacts(cfg, normalizedArtifacts); err != nil {
+		return fmt.Errorf("run-stage: %w", err)
+	}
 
-	summary, err := executeStages(ctx, cfg, stages, RunOptions{Force: force})
+	summary, err := executeStages(ctx, cfg, stages, RunOptions{
+		Force:             force,
+		SelectedArtifacts: normalizedArtifacts,
+	})
 	if err != nil {
 		return fmt.Errorf("run-stage: %w", err)
 	}

internal/app/runner.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"log/slog"
 	"os"
-	"path/filepath"
 	"strings"
 
 	"gitea.maximumdirect.net/eric/narratio/internal/adapters/audita"
@@ -22,16 +21,19 @@ import (
 )
 
 type RunOptions struct {
-	Force bool
-	Env   *Env
+	Force             bool
+	SelectedArtifacts []string
+	Env               *Env
 }
 
 type RunSummary struct {
-	SessionID    string
-	ManifestPath string
-	StageNames   []string
-	Executed     []string
-	Skipped      []string
+	SessionID       string
+	RunID           string
+	ManifestPath    string
+	RunManifestPath string
+	StageNames      []string
+	Executed        []string
+	Skipped         []string
 }
 
 func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage, opts RunOptions) (*RunSummary, error) {
@@ -42,6 +44,7 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
 	if env.Config == nil {
 		env.Config = cfg
 	}
+	env.SelectedAnalyzeArtifacts = append([]string(nil), opts.SelectedArtifacts...)
 	if env.ArtifactStore == nil {
 		env.ArtifactStore = artifacts.NewLocalStore(cfg.Pipeline.Workspace.Root)
 	}
@@ -51,6 +54,9 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
 	if env.Logger == nil {
 		env.Logger = logging.NewLogger(os.Stderr, slog.LevelInfo)
 	}
+	if _, err := loadSecretsFromConfig(env.Config, env.Logger); err != nil {
+		return nil, fmt.Errorf("load secrets from files: %w", err)
+	}
 	if env.WhisperX == nil {
 		client, err := buildDefaultWhisperXClient(env.Config)
 		if err != nil {
@@ -78,17 +84,24 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
 	if env.Storage == nil {
 		env.Storage = &storage.NoopBackend{}
 	}
+	if env.ObjectStore == nil && needsObjectStoreForRun(env.Config, stages) {
+		objectStore, err := storage.NewObjectStoreFromConfig(ctx, env.Config)
+		if err != nil {
+			return nil, fmt.Errorf("initialize object store backend: %w", err)
+		}
+		env.ObjectStore = objectStore
+	}
 	if env.Notifier == nil {
 		env.Notifier = &notify.NoopSender{}
 	}
 
 	artifactStore := env.ArtifactStore
-	paths, err := artifactStore.EnsureLayout(cfg.Session.SessionID)
+	paths, err := artifactStore.EnsureLayoutFor(cfg.Session.Campaign, cfg.Session.SessionID)
 	if err != nil {
 		return nil, fmt.Errorf("prepare workdir: %w", err)
 	}
 
-	lock, err := artifactStore.AcquireSessionLock(cfg.Session.SessionID)
+	lock, err := artifactStore.AcquireSessionLockFor(cfg.Session.Campaign, cfg.Session.SessionID)
 	if err != nil {
 		return nil, fmt.Errorf("acquire session lock: %w", err)
 	}
@@ -101,6 +114,42 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
 	if err != nil {
 		return nil, err
 	}
+	runID, err := artifacts.NewRunID()
+	if err != nil {
+		return nil, fmt.Errorf("generate run id: %w", err)
+	}
+	identityChanged, err := ensureManifestIdentity(cfg, m, runID)
+	if err != nil {
+		return nil, fmt.Errorf("initialize manifest identity: %w", err)
+	}
+	if identityChanged {
+		if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
+			return nil, fmt.Errorf("save manifest identity %q: %w", manifestPath, err)
+		}
+	}
+	runManifestPath := artifacts.SessionRunManifestPathForCampaign(
+		cfg.Pipeline.Workspace.Root,
+		cfg.Session.Campaign,
+		cfg.Session.SessionID,
+		runID,
+	)
+	runManifestStore := &manifest.LocalStore{}
+	runManifest, err := runManifestStore.CreateRun(
+		ctx,
+		cfg.Session.SessionID,
+		cfg.Session.Campaign,
+		runID,
+		opts.Force,
+		requestedStageNames(stages),
+	)
+	if err != nil {
+		return nil, fmt.Errorf("create run manifest: %w", err)
+	}
+	runManifest.SessionManifestPath = manifestPath
+	syncRunManifestIdentityFromSession(m, runManifest)
+	if err := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); err != nil {
+		return nil, fmt.Errorf("save initial run manifest %q: %w", runManifestPath, err)
+	}
 
 	stageEnv := env
 
@@ -115,12 +164,23 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
 
 		if d.Action == stageActionSkip {
 			skipped = append(skipped, s.Name())
+			skipAt := nowUTC()
+			runManifest.SetStageAction(s.Name(), manifest.RunStageActionSkip, skipAt)
+			runManifest.MarkStageSkipped(s.Name(), skipAt, "already_succeeded")
+			if err := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); err != nil {
+				return nil, fmt.Errorf("save run manifest after skip %q: %w", s.Name(), err)
+			}
 			env.Logger.Info("skipping stage", "stage", s.Name(), "reason", "already_succeeded", "force", opts.Force)
 			continue
 		}
 		executed = append(executed, s.Name())
 
 		now := nowUTC()
+		runManifest.SetStageAction(s.Name(), manifest.RunStageActionRun, now)
+		runManifest.MarkStageRunning(s.Name(), now)
+		if err := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); err != nil {
+			return nil, fmt.Errorf("save run manifest before stage %q: %w", s.Name(), err)
+		}
 		m.MarkStageRunning(s.Name(), now)
 		env.Logger.Info("starting stage", "stage", s.Name())
 		if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
@@ -130,31 +190,65 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
 
 		result, err := s.Run(ctx, stageEnv, m)
 		if err != nil {
-			m.MarkStageFailed(s.Name(), nowUTC(), err.Error())
+			failedAt := nowUTC()
+			m.MarkStageFailed(s.Name(), failedAt, err.Error())
 			if saveErr := env.ManifestStore.Save(ctx, manifestPath, m); saveErr != nil {
 				return nil, fmt.Errorf("stage %q failed (%v) and manifest save failed (%v)", s.Name(), err, saveErr)
 			}
+			runManifest.MarkStageFailed(s.Name(), failedAt, err.Error())
+			syncRunManifestIdentityFromSession(m, runManifest)
+			if saveErr := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); saveErr != nil {
+				return nil, fmt.Errorf("stage %q failed (%v) and run-manifest save failed (%v)", s.Name(), err, saveErr)
+			}
 			env.Logger.Info("stage failed", "stage", s.Name(), "error", err)
 			return nil, fmt.Errorf("stage %q failed: %w", s.Name(), err)
 		}
 
-		outputs := mapResultOutputs(result)
-		m.MarkStageSucceeded(s.Name(), nowUTC(), outputs)
+		outputs := mapResultOutputs(s.Name(), result, runID)
+		succeededAt := nowUTC()
+		m.MarkStageSucceeded(s.Name(), succeededAt, outputs)
 		applyStageResultToManifest(m, s.Name(), result)
+		if opts.Force {
+			invalidateDownstreamSucceededStages(m, s.Name(), succeededAt)
+		}
 
 		if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
 			return nil, fmt.Errorf("save manifest after stage %q: %w", s.Name(), err)
 		}
+		runManifest.MarkStageSucceeded(s.Name(), succeededAt, outputs)
+		applyStageResultToRunManifest(runManifest, s.Name(), result)
+		syncRunManifestIdentityFromSession(m, runManifest)
+		if err := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); err != nil {
+			return nil, fmt.Errorf("save run manifest after stage %q: %w", s.Name(), err)
+		}
 		env.Logger.Debug("manifest saved", "stage", s.Name(), "transition", "succeeded", "path", manifestPath)
 		env.Logger.Info("stage succeeded", "stage", s.Name())
 	}
 
+	if err := runPostArchiveCleanup(ctx, env, manifestPath, m, executed); err != nil {
+		failedAt := nowUTC()
+		runManifest.MarkFailed(failedAt, err.Error())
+		syncRunManifestIdentityFromSession(m, runManifest)
+		if saveErr := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); saveErr != nil {
+			return nil, fmt.Errorf("post-archive cleanup failed (%v) and run-manifest save failed (%v)", err, saveErr)
+		}
+		return nil, fmt.Errorf("post-archive cleanup: %w", err)
+	}
+	completedAt := nowUTC()
+	runManifest.MarkSucceeded(completedAt)
+	syncRunManifestIdentityFromSession(m, runManifest)
+	if err := runManifestStore.SaveRun(ctx, runManifestPath, runManifest); err != nil {
+		return nil, fmt.Errorf("save final run manifest %q: %w", runManifestPath, err)
+	}
+
 	return &RunSummary{
-		SessionID:    cfg.Session.SessionID,
-		ManifestPath: manifestPath,
-		StageNames:   runNames,
-		Executed:     executed,
-		Skipped:      skipped,
+		SessionID:       cfg.Session.SessionID,
+		RunID:           runID,
+		ManifestPath:    manifestPath,
+		RunManifestPath: runManifestPath,
+		StageNames:      runNames,
+		Executed:        executed,
+		Skipped:         skipped,
 	}, nil
 }
 
@@ -227,7 +321,7 @@ func buildDefaultAuditaRunner(cfg *config.Config) (audita.Runner, error) {
 	}
 
 	a := cfg.Pipeline.Audita
-	if strings.TrimSpace(a.Binary) == "" || strings.TrimSpace(a.Timeout) == "" || len(a.Modules) == 0 || strings.TrimSpace(a.BaseURL) == "" || strings.TrimSpace(a.Model) == "" {
+	if strings.TrimSpace(a.Binary) == "" || strings.TrimSpace(a.Timeout) == "" {
 		// Compatibility fallback for tests or internal call paths that bypass config validation/defaults.
 		return &audita.NoopRunner{}, nil
 	}
@@ -244,7 +338,12 @@ func buildDefaultAuditaRunner(cfg *config.Config) (audita.Runner, error) {
 		append([]string(nil), a.Modules...),
 		a.BaseURL,
 		a.Model,
-		a.LLMConcurrency,
+		a.TranscriptDescription,
+		a.ConfigPath,
+		a.OutputSchema,
+		a.WorkDirRetention,
+		a.TotalLLMConcurrency,
+		a.ProposalLLMConcurrency,
 		a.ValidationModel,
 		a.ValidationLLMConcurrency,
 		report,
@@ -289,22 +388,31 @@ func fileExists(path string) (bool, error) {
 	return false, err
 }
 
-func mapResultOutputs(result *stage.StageResult) []manifest.ArtifactRecord {
+func mapResultOutputs(stageName string, result *stage.StageResult, runID string) []manifest.ArtifactRecord {
 	if result == nil || len(result.Outputs) == 0 {
 		return nil
 	}
 
+	runID = strings.TrimSpace(runID)
 	out := make([]manifest.ArtifactRecord, 0, len(result.Outputs))
 	for _, ref := range result.Outputs {
 		localPath := ref.AbsolutePath
 		if localPath == "" {
 			localPath = ref.RelativePath
 		}
+		kind := ref.Kind
+		sourceID := ""
+		if stageName == "analyze" {
+			sourceID = artifacts.ConfiguredArtifactSourceID(ref.Kind)
+			kind = "scriptorium_artifact"
+		}
 		out = append(out, manifest.ArtifactRecord{
-			Kind:      ref.Kind,
-			LocalPath: localPath,
-			RemoteKey: ref.RemoteKey,
-			Checksum:  ref.Checksum,
+			Kind:          kind,
+			SourceID:      sourceID,
+			LocalPath:     localPath,
+			ProducerRunID: runID,
+			RemoteKey:     ref.RemoteKey,
+			Checksum:      ref.Checksum,
 		})
 	}
 
@@ -330,6 +438,132 @@ func applyStageResultToManifest(m *manifest.Manifest, stageName string, result *
 	}
 }
 
-func manifestPathFor(cfg *config.Config) string {
-	return filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.SessionID, "manifest.json")
+func ensureManifestIdentity(cfg *config.Config, m *manifest.Manifest, runID string) (bool, error) {
+	if cfg == nil || cfg.Pipeline == nil || cfg.Session == nil || m == nil {
+		return false, nil
+	}
+
+	changed := false
+	campaign := strings.TrimSpace(cfg.Session.Campaign)
+	sessionID := strings.TrimSpace(cfg.Session.SessionID)
+	if sessionID == "" {
+		sessionID = strings.TrimSpace(m.SessionID)
+	}
+
+	if m.Campaign == "" && campaign != "" {
+		m.Campaign = campaign
+		changed = true
+	}
+	runID = strings.TrimSpace(runID)
+	if runID != "" && m.RunID != runID {
+		m.RunID = runID
+		changed = true
+	}
+	if m.LocalWorkDir == "" && campaign != "" && sessionID != "" && m.RunID != "" {
+		m.LocalWorkDir = artifacts.SessionRunRootForCampaign(cfg.Pipeline.Workspace.Root, campaign, sessionID, m.RunID)
+		changed = true
+	}
+	if m.LocalSpoolDir == "" && campaign != "" && sessionID != "" && m.RunID != "" && strings.TrimSpace(cfg.Pipeline.Spool.Root) != "" {
+		m.LocalSpoolDir = artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, campaign, sessionID, m.RunID)
+		changed = true
+	}
+	if cfg.Pipeline.Storage.S3 != nil {
+		if m.S3Bucket == "" && strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket) != "" {
+			m.S3Bucket = strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket)
+			changed = true
+		}
+		sessionPrefix := artifacts.S3SessionPrefix(cfg.Pipeline.Storage.S3.RootPrefix, campaign, sessionID)
+		if m.S3SessionPrefix == "" && sessionPrefix != "" {
+			m.S3SessionPrefix = sessionPrefix
+			changed = true
+		}
+		runPrefix := artifacts.S3RunPrefix(sessionPrefix, m.RunID)
+		if m.S3RunPrefix == "" && runPrefix != "" {
+			m.S3RunPrefix = runPrefix
+			changed = true
+		}
+	}
+
+	return changed, nil
+}
+
+func requestedStageNames(stages []stage.Stage) []string {
+	out := make([]string, 0, len(stages))
+	for _, s := range stages {
+		if s == nil {
+			continue
+		}
+		out = append(out, s.Name())
+	}
+	return out
+}
+
+func applyStageResultToRunManifest(m *manifest.RunManifest, stageName string, result *stage.StageResult) {
+	if m == nil || result == nil {
+		return
+	}
+	sr := m.Stages[stageName]
+	if sr == nil {
+		return
+	}
+	if len(result.Logs) > 0 {
+		sr.Logs = append([]string(nil), result.Logs...)
+	}
+	if len(result.GeneratedConfigs) > 0 {
+		sr.GeneratedConfigs = append([]string(nil), result.GeneratedConfigs...)
+	}
+	if len(result.Metadata) > 0 {
+		sr.Metadata = result.Metadata
+	}
+}
+
+func syncRunManifestIdentityFromSession(session *manifest.Manifest, run *manifest.RunManifest) {
+	if session == nil || run == nil {
+		return
+	}
+	run.Campaign = session.Campaign
+	run.LocalWorkDir = session.LocalWorkDir
+	run.LocalSpoolDir = session.LocalSpoolDir
+	run.S3Bucket = session.S3Bucket
+	run.S3SessionPrefix = session.S3SessionPrefix
+	run.S3RunPrefix = session.S3RunPrefix
+}
+
+func manifestPathFor(cfg *config.Config) string {
+	return artifacts.SessionManifestPathForCampaign(
+		cfg.Pipeline.Workspace.Root,
+		cfg.Session.Campaign,
+		cfg.Session.SessionID,
+	)
+}
+
+func needsObjectStoreForRun(cfg *config.Config, stages []stage.Stage) bool {
+	if cfg == nil || cfg.Pipeline == nil || cfg.Session == nil {
+		return false
+	}
+	stageRequested := func(name string) bool {
+		for _, s := range stages {
+			if s != nil && s.Name() == name {
+				return true
+			}
+		}
+		return false
+	}
+
+	if cfg.Session.Inputs.AudioS3 != nil && stageRequested("prepare") {
+		return true
+	}
+	if !stageRequested("archive") {
+		return false
+	}
+	if cfg.Pipeline.Archive == nil {
+		return false
+	}
+	if cfg.Pipeline.Archive.Enabled != nil && !*cfg.Pipeline.Archive.Enabled {
+		return false
+	}
+	if cfg.Pipeline.Archive.UploadRun != nil && !*cfg.Pipeline.Archive.UploadRun {
+		return false
+	}
+	return true
 }

internal/app/runner_test.go

@@ -3,6 +3,7 @@ package app
 import (
 	"context"
 	"errors"
+	"fmt"
 	"os"
 	"path/filepath"
 	"strings"
@@ -44,6 +45,213 @@ func (s countingStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest
 	return &stage.StageResult{Metadata: map[string]any{"counting": true}}, nil
 }
 
+type captureSelectedArtifactsStage struct {
+	name     string
+	captured *[]string
+}
+
+func (s captureSelectedArtifactsStage) Name() string           { return s.name }
+func (s captureSelectedArtifactsStage) Declares() stage.IODecl { return stage.IODecl{} }
+func (s captureSelectedArtifactsStage) Run(_ context.Context, env *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
+	if s.captured != nil {
+		*s.captured = append((*s.captured)[:0], env.SelectedAnalyzeArtifacts...)
+	}
+	return &stage.StageResult{Metadata: map[string]any{"captured": true}}, nil
+}
+
+type analyzeOutputStage struct {
+	output artifacts.Ref
+}
+
+func (s analyzeOutputStage) Name() string           { return "analyze" }
+func (s analyzeOutputStage) Declares() stage.IODecl { return stage.IODecl{} }
+func (s analyzeOutputStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
+	return &stage.StageResult{
+		Outputs: []artifacts.Ref{s.output},
+	}, nil
+}
+
+type selectedAnalyzeArtifactStage struct {
+	expected []string
+}
+
+func (s selectedAnalyzeArtifactStage) Name() string           { return "analyze" }
+func (s selectedAnalyzeArtifactStage) Declares() stage.IODecl { return stage.IODecl{} }
+func (s selectedAnalyzeArtifactStage) Run(_ context.Context, env *stage.Env, m *manifest.Manifest) (*stage.StageResult, error) {
+	if len(env.SelectedAnalyzeArtifacts) != len(s.expected) {
+		return nil, fmt.Errorf("selected artifacts len = %d, want %d", len(env.SelectedAnalyzeArtifacts), len(s.expected))
+	}
+	for i := range s.expected {
+		if env.SelectedAnalyzeArtifacts[i] != s.expected[i] {
+			return nil, fmt.Errorf("selected artifacts[%d] = %q, want %q", i, env.SelectedAnalyzeArtifacts[i], s.expected[i])
+		}
+	}
+
+	outputPath := filepath.Join(
+		artifacts.SessionWorkDirForCampaign(env.Config.Pipeline.Workspace.Root, env.Config.Session.Campaign, m.SessionID),
+		"artifacts",
+		"player_handout.md",
+	)
+	if err := os.MkdirAll(filepath.Dir(outputPath), 0o755); err != nil {
+		return nil, fmt.Errorf("mkdir artifact dir: %w", err)
+	}
+	if err := os.WriteFile(outputPath, []byte("player handout\n"), 0o644); err != nil {
+		return nil, fmt.Errorf("write player handout: %w", err)
+	}
+
+	return &stage.StageResult{
+		Outputs: []artifacts.Ref{
+			{
+				Kind:         "player_handout",
+				Category:     "artifacts",
+				RelativePath: "artifacts/player_handout.md",
+				AbsolutePath: outputPath,
+			},
+		},
+		Metadata: map[string]any{
+			"stage": "analyze",
+		},
+	}, nil
+}
+
+func TestExecuteStagesPropagatesSelectedArtifactsToEnv(t *testing.T) {
+	cfg := testConfig(t)
+
+	captured := []string{}
+	stageToRun := captureSelectedArtifactsStage{name: "analyze", captured: &captured}
+	_, err := executeStages(context.Background(), cfg, []stage.Stage{stageToRun}, RunOptions{
+		SelectedArtifacts: []string{"player_handout", "session_recap"},
+	})
+	if err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	if len(captured) != 2 {
+		t.Fatalf("captured len = %d, want 2 (%v)", len(captured), captured)
+	}
+	if captured[0] != "player_handout" || captured[1] != "session_recap" {
+		t.Fatalf("captured = %v, want [player_handout session_recap]", captured)
+	}
+}
+
+func TestExecuteStagesAnalyzeOutputsPersistAsScriptoriumArtifacts(t *testing.T) {
+	cfg := testConfig(t)
+	storeForPaths := artifacts.NewLocalStore(cfg.Pipeline.Workspace.Root)
+	sessionPaths := storeForPaths.SessionPathsFor(cfg.Session.Campaign, cfg.Session.SessionID)
+	outputPath := filepath.Join(sessionPaths.ArtifactsDir, "session_recap.md")
+
+	stageToRun := analyzeOutputStage{
+		output: artifacts.Ref{
+			Kind:         "session_recap",
+			Category:     "artifacts",
+			RelativePath: "artifacts/session_recap.md",
+			AbsolutePath: outputPath,
+		},
+	}
+	summary, err := executeStages(context.Background(), cfg, []stage.Stage{stageToRun}, RunOptions{})
+	if err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+
+	store := &manifest.LocalStore{}
+	sessionManifest, err := store.Load(context.Background(), summary.ManifestPath)
+	if err != nil {
+		t.Fatalf("load session manifest: %v", err)
+	}
+	sessionStage := sessionManifest.Stages["analyze"]
+	if sessionStage == nil {
+		t.Fatal("session manifest analyze stage missing")
+	}
+	if len(sessionStage.Outputs) != 1 {
+		t.Fatalf("session analyze outputs len = %d, want 1", len(sessionStage.Outputs))
+	}
+	sessionOutput := sessionStage.Outputs[0]
+	if sessionOutput.Kind != "scriptorium_artifact" {
+		t.Fatalf("session output kind = %q, want scriptorium_artifact", sessionOutput.Kind)
+	}
+	if sessionOutput.SourceID != "narratio.artifact.session_recap" {
+		t.Fatalf("session output source_id = %q, want narratio.artifact.session_recap", sessionOutput.SourceID)
+	}
+	if sessionOutput.LocalPath != outputPath {
+		t.Fatalf("session output local_path = %q, want %q", sessionOutput.LocalPath, outputPath)
+	}
+
+	runManifest, err := store.LoadRun(context.Background(), summary.RunManifestPath)
+	if err != nil {
+		t.Fatalf("load run manifest: %v", err)
+	}
+	runStage := runManifest.Stages["analyze"]
+	if runStage == nil {
+		t.Fatal("run manifest analyze stage missing")
+	}
+	if len(runStage.Outputs) != 1 {
+		t.Fatalf("run analyze outputs len = %d, want 1", len(runStage.Outputs))
+	}
+	runOutput := runStage.Outputs[0]
+	if runOutput.Kind != "scriptorium_artifact" {
+		t.Fatalf("run output kind = %q, want scriptorium_artifact", runOutput.Kind)
+	}
+	if runOutput.SourceID != "narratio.artifact.session_recap" {
+		t.Fatalf("run output source_id = %q, want narratio.artifact.session_recap", runOutput.SourceID)
+	}
+	if runOutput.LocalPath != outputPath {
+		t.Fatalf("run output local_path = %q, want %q", runOutput.LocalPath, outputPath)
+	}
+}
+
+func TestExecuteStagesArchiveFailsWhenRequiredRecapPromotionMissingForSelectedArtifacts(t *testing.T) {
+	cfg := testConfig(t)
+	cfg.Pipeline.Storage.S3 = &config.StorageS3Config{
+		Bucket:     "my-dnd-archive",
+		RootPrefix: "dnd",
+	}
+	cfg.Pipeline.Archive = &config.ArchiveConfig{
+		Enabled:   boolPtr(true),
+		UploadRun: boolPtr(true),
+		PromoteArtifacts: []config.ArchivePromotionRule{
+			{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md", Required: boolPtr(true)},
+		},
+	}
+
+	store := &manifest.LocalStore{}
+	manifestPath := manifestPathFor(cfg)
+	seed := manifest.New(cfg.Session.SessionID, time.Now().UTC())
+	seed.Campaign = cfg.Session.Campaign
+	for _, stageName := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim"} {
+		seed.MarkStageSucceeded(stageName, time.Now().UTC(), nil)
+	}
+	if err := os.MkdirAll(filepath.Dir(manifestPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := store.Save(context.Background(), manifestPath, seed); err != nil {
+		t.Fatalf("Save manifest error = %v", err)
+	}
+
+	archiveStageImpl, err := stage.Select("archive")
+	if err != nil {
+		t.Fatalf("Select(archive) error = %v", err)
+	}
+
+	_, err = executeStages(
+		context.Background(),
+		cfg,
+		[]stage.Stage{
+			selectedAnalyzeArtifactStage{expected: []string{"player_handout"}},
+			archiveStageImpl,
+		},
+		RunOptions{
+			SelectedArtifacts: []string{"player_handout"},
+			Env:               &Env{ObjectStore: &storage.FakeBackend{}},
+		},
+	)
+	if err == nil {
+		t.Fatal("expected archive promotion failure, got nil")
+	}
+	if !strings.Contains(err.Error(), "required promotion source missing") {
+		t.Fatalf("error = %q, want required promotion source missing", err.Error())
+	}
+}
+
 func TestExecuteStagesPlaceholderSuccessUpdatesManifest(t *testing.T) {
 	cfg := testConfig(t)
 
@@ -144,6 +352,15 @@ func TestExecuteStagesPlaceholderSuccessUpdatesManifest(t *testing.T) {
 			}
 			continue
 		}
+		if name == "archive" {
+			if sr.Metadata == nil || sr.Metadata["stage"] != "archive" {
+				t.Fatalf("archive metadata missing stage=archive: %#v", sr.Metadata)
+			}
+			if sr.Metadata["skipped"] != true {
+				t.Fatalf("archive metadata missing skipped=true for test config without archive section: %#v", sr.Metadata)
+			}
+			continue
+		}
 		if sr.Metadata == nil || sr.Metadata["placeholder"] != true {
 			t.Fatalf("stage %q missing placeholder metadata", name)
 		}
@@ -226,6 +443,56 @@ func TestExecuteStagesForceRerunsSucceeded(t *testing.T) {
 	}
 }
 
+func TestExecuteStagesForceSuccessInvalidatesDownstreamSucceededStages(t *testing.T) {
+	cfg := testConfig(t)
+	manifestPath := manifestPathFor(cfg)
+	store := &manifest.LocalStore{}
+
+	existing := manifest.New(cfg.Session.SessionID, time.Date(2026, 5, 3, 1, 0, 0, 0, time.UTC))
+	for _, stageName := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "archive", "notify"} {
+		existing.MarkStageSucceeded(stageName, time.Date(2026, 5, 3, 1, 1, 0, 0, time.UTC), nil)
+	}
+	existing.MarkStageFailed("analyze", time.Date(2026, 5, 3, 1, 1, 0, 0, time.UTC), "previous analyze failure")
+	if err := os.MkdirAll(filepath.Dir(manifestPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := store.Save(context.Background(), manifestPath, existing); err != nil {
+		t.Fatalf("Save manifest error = %v", err)
+	}
+
+	runs := 0
+	stageToRun := countingStage{name: "polish", runs: &runs}
+	summary, err := executeStages(context.Background(), cfg, []stage.Stage{stageToRun}, RunOptions{Force: true})
+	if err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+	if runs != 1 {
+		t.Fatalf("runs = %d, want 1 with force", runs)
+	}
+	if len(summary.Executed) != 1 || summary.Executed[0] != "polish" || len(summary.Skipped) != 0 {
+		t.Fatalf("summary = %#v, want executed polish", summary)
+	}
+
+	loaded, err := store.Load(context.Background(), manifestPath)
+	if err != nil {
+		t.Fatalf("Load manifest error = %v", err)
+	}
+	if loaded.Stages["polish"] == nil || loaded.Stages["polish"].Status != manifest.StatusSucceeded {
+		t.Fatalf("polish status = %#v, want succeeded", loaded.Stages["polish"])
+	}
+	for _, stageName := range []string{"normalize", "trim", "archive", "notify"} {
+		if loaded.Stages[stageName] == nil || loaded.Stages[stageName].Status != manifest.StatusStale {
+			t.Fatalf("%s status = %#v, want stale", stageName, loaded.Stages[stageName])
+		}
+	}
+	if loaded.Stages["analyze"] == nil || loaded.Stages["analyze"].Status != manifest.StatusFailed {
+		t.Fatalf("analyze status = %#v, want preserved failed", loaded.Stages["analyze"])
+	}
+	if loaded.Stages["transcribe"] == nil || loaded.Stages["transcribe"].Status != manifest.StatusSucceeded {
+		t.Fatalf("transcribe status = %#v, want preserved succeeded", loaded.Stages["transcribe"])
+	}
+}
+
 func TestExecuteStagesFailureUpdatesManifest(t *testing.T) {
 	cfg := testConfig(t)
 
@@ -271,7 +538,14 @@ func TestExecuteStagesLoadsExistingManifest(t *testing.T) {
 
 	existing := manifest.New(cfg.Session.SessionID, time.Date(2026, 5, 3, 1, 0, 0, 0, time.UTC))
 	existing.MarkStageSucceeded("prepare", time.Date(2026, 5, 3, 1, 1, 0, 0, time.UTC), nil)
-	audioPath := filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.SessionID, "audio", "alice.flac")
+	audioPath := filepath.Join(
+		cfg.Pipeline.Workspace.Root,
+		"work",
+		cfg.Session.Campaign,
+		cfg.Session.SessionID,
+		"audio",
+		"alice.flac",
+	)
 	if err := os.MkdirAll(filepath.Dir(audioPath), 0o755); err != nil {
 		t.Fatalf("MkdirAll() error = %v", err)
 	}
@@ -306,6 +580,208 @@ func TestExecuteStagesLoadsExistingManifest(t *testing.T) {
 	}
 }
 
+func TestExecuteStagesCreatesRunManifestPerInvocation(t *testing.T) {
+	cfg := testConfig(t)
+	run1, err := executeStages(context.Background(), cfg, []stage.Stage{BuildFullPlan()[0]}, RunOptions{})
+	if err != nil {
+		t.Fatalf("first executeStages() error = %v", err)
+	}
+	run2, err := executeStages(context.Background(), cfg, []stage.Stage{BuildFullPlan()[0]}, RunOptions{Force: true})
+	if err != nil {
+		t.Fatalf("second executeStages() error = %v", err)
+	}
+
+	if run1.RunID == "" || run2.RunID == "" {
+		t.Fatalf("run ids must be set, got %q and %q", run1.RunID, run2.RunID)
+	}
+	if run1.RunID == run2.RunID {
+		t.Fatalf("expected distinct run ids, got %q", run1.RunID)
+	}
+	if run1.RunManifestPath == "" || run2.RunManifestPath == "" {
+		t.Fatalf("run manifest paths must be set, got %q and %q", run1.RunManifestPath, run2.RunManifestPath)
+	}
+	if run1.RunManifestPath == run2.RunManifestPath {
+		t.Fatalf("expected distinct run manifest paths, got %q", run1.RunManifestPath)
+	}
+	for _, path := range []string{run1.RunManifestPath, run2.RunManifestPath} {
+		if _, statErr := os.Stat(path); statErr != nil {
+			t.Fatalf("run manifest missing at %q: %v", path, statErr)
+		}
+	}
+
+	store := &manifest.LocalStore{}
+	sessionManifest, err := store.Load(context.Background(), run2.ManifestPath)
+	if err != nil {
+		t.Fatalf("Load session manifest error = %v", err)
+	}
+	if sessionManifest.RunID != run2.RunID {
+		t.Fatalf("session manifest run_id = %q, want latest run id %q", sessionManifest.RunID, run2.RunID)
+	}
+}
+
+func TestExecuteStagesRunManifestRecordsSkippedStage(t *testing.T) {
+	cfg := testConfig(t)
+	store := &manifest.LocalStore{}
+	manifestPath := manifestPathFor(cfg)
+	existing := manifest.New(cfg.Session.SessionID, time.Date(2026, 5, 3, 1, 0, 0, 0, time.UTC))
+	existing.MarkStageSucceeded("transcribe", time.Date(2026, 5, 3, 1, 1, 0, 0, time.UTC), nil)
+	if err := os.MkdirAll(filepath.Dir(manifestPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := store.Save(context.Background(), manifestPath, existing); err != nil {
+		t.Fatalf("Save manifest error = %v", err)
+	}
+
+	summary, err := executeStages(context.Background(), cfg, []stage.Stage{BuildFullPlan()[1]}, RunOptions{})
+	if err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+	if len(summary.Skipped) != 1 || summary.Skipped[0] != "transcribe" {
+		t.Fatalf("summary = %#v, want skipped transcribe", summary)
+	}
+
+	runManifest, err := store.LoadRun(context.Background(), summary.RunManifestPath)
+	if err != nil {
+		t.Fatalf("LoadRun() error = %v", err)
+	}
+	sr := runManifest.Stages["transcribe"]
+	if sr == nil {
+		t.Fatal("run manifest transcribe stage missing")
+	}
+	if sr.Action != manifest.RunStageActionSkip {
+		t.Fatalf("action = %q, want %q", sr.Action, manifest.RunStageActionSkip)
+	}
+	if sr.Status != manifest.StatusSkipped {
+		t.Fatalf("status = %q, want %q", sr.Status, manifest.StatusSkipped)
+	}
+}
+
+func TestExecuteStagesRunLocalArtifactsAndCanonicalPromotion(t *testing.T) {
+	cfg := testConfig(t)
+	stages := []stage.Stage{
+		BuildFullPlan()[0], // prepare
+		BuildFullPlan()[1], // transcribe
+		BuildFullPlan()[2], // merge
+		BuildFullPlan()[3], // polish
+		BuildFullPlan()[4], // normalize
+		BuildFullPlan()[5], // trim
+	}
+
+	summary, err := executeStages(context.Background(), cfg, stages, RunOptions{})
+	if err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+	if summary.RunID == "" {
+		t.Fatal("run id must be set")
+	}
+
+	runRoot := artifacts.SessionRunRootForCampaign(
+		cfg.Pipeline.Workspace.Root,
+		cfg.Session.Campaign,
+		cfg.Session.SessionID,
+		summary.RunID,
+	)
+	paths := artifacts.NewLocalStore(cfg.Pipeline.Workspace.Root).SessionPathsFor(cfg.Session.Campaign, cfg.Session.SessionID)
+
+	runLocalChecks := []string{
+		filepath.Join(runRoot, "transcribe", "outputs", "transcripts", "raw", "alice.json"),
+		filepath.Join(runRoot, "merge", "logs", "seriatim.stdout.log"),
+		filepath.Join(runRoot, "polish", "config", "audita.generated.yml"),
+		filepath.Join(runRoot, "normalize", "logs", "seriatim.normalize.stdout.log"),
+		filepath.Join(runRoot, "trim", "outputs", "transcripts", "trimmed.json"),
+	}
+	for _, p := range runLocalChecks {
+		if _, statErr := os.Stat(p); statErr != nil {
+			t.Fatalf("run-local artifact missing at %q: %v", p, statErr)
+		}
+	}
+
+	canonicalChecks := []string{
+		filepath.Join(paths.TranscriptsRawDir, "alice.json"),
+		filepath.Join(paths.TranscriptsDir, "merged.json"),
+		filepath.Join(paths.TranscriptsDir, "processed.json"),
+		filepath.Join(paths.TranscriptsDir, "normalized.json"),
+		filepath.Join(paths.TranscriptsDir, "trimmed.json"),
+	}
+	for _, p := range canonicalChecks {
+		if _, statErr := os.Stat(p); statErr != nil {
+			t.Fatalf("canonical promoted artifact missing at %q: %v", p, statErr)
+		}
+	}
+
+	store := &manifest.LocalStore{}
+	sessionManifest, err := store.Load(context.Background(), summary.ManifestPath)
+	if err != nil {
+		t.Fatalf("Load manifest error = %v", err)
+	}
+	if got := sessionManifest.Stages["trim"]; got == nil || len(got.Outputs) == 0 {
+		t.Fatalf("trim stage outputs missing in session manifest: %#v", got)
+	}
+	for _, out := range sessionManifest.Stages["trim"].Outputs {
+		if strings.Contains(out.LocalPath, string(filepath.Separator)+"runs"+string(filepath.Separator)) {
+			t.Fatalf("session manifest output should be canonical, got run-local path %q", out.LocalPath)
+		}
+		if out.ProducerRunID != summary.RunID {
+			t.Fatalf("producer_run_id = %q, want %q", out.ProducerRunID, summary.RunID)
+		}
+	}
+
+	runManifest, err := store.LoadRun(context.Background(), summary.RunManifestPath)
+	if err != nil {
+		t.Fatalf("LoadRun() error = %v", err)
+	}
+	mergeStage := runManifest.Stages["merge"]
+	if mergeStage == nil || len(mergeStage.Logs) == 0 {
+		t.Fatalf("merge logs missing in run manifest: %#v", mergeStage)
+	}
+	for _, logPath := range mergeStage.Logs {
+		if !strings.Contains(logPath, filepath.Join("runs", summary.RunID, "merge", "logs")) {
+			t.Fatalf("run manifest merge log path = %q, want run-local merge logs path", logPath)
+		}
+	}
+}
+
+func TestExecuteStagesSkippedStagePreservesExistingOutputsProvenance(t *testing.T) {
+	cfg := testConfig(t)
+	store := &manifest.LocalStore{}
+	manifestPath := manifestPathFor(cfg)
+
+	existing := manifest.New(cfg.Session.SessionID, time.Date(2026, 5, 3, 1, 0, 0, 0, time.UTC))
+	existing.MarkStageSucceeded("transcribe", time.Date(2026, 5, 3, 1, 1, 0, 0, time.UTC), []manifest.ArtifactRecord{
+		{
+			Kind:          "transcript_raw",
+			LocalPath:     "transcripts/raw/alice.json",
+			ProducerRunID: "20260501T000000Z-deadbeef",
+		},
+	})
+	if err := os.MkdirAll(filepath.Dir(manifestPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := store.Save(context.Background(), manifestPath, existing); err != nil {
+		t.Fatalf("Save manifest error = %v", err)
+	}
+
+	summary, err := executeStages(context.Background(), cfg, []stage.Stage{BuildFullPlan()[1]}, RunOptions{})
+	if err != nil {
+		t.Fatalf("executeStages() error = %v", err)
+	}
+	if len(summary.Skipped) != 1 || summary.Skipped[0] != "transcribe" {
+		t.Fatalf("summary = %#v, want skipped transcribe", summary)
+	}
+
+	loaded, err := store.Load(context.Background(), manifestPath)
+	if err != nil {
+		t.Fatalf("Load manifest error = %v", err)
+	}
+	got := loaded.Stages["transcribe"]
+	if got == nil || len(got.Outputs) != 1 {
+		t.Fatalf("transcribe outputs = %#v, want one preserved output", got)
+	}
+	if got.Outputs[0].ProducerRunID != "20260501T000000Z-deadbeef" {
+		t.Fatalf("producer_run_id = %q, want preserved value", got.Outputs[0].ProducerRunID)
+	}
+}
+
 func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 	cases := []struct {
 		name string
@@ -315,7 +791,7 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 		{name: "merge", env: &Env{Seriatim: &seriatim.FakeRunner{Err: errors.New("merge fail")}}},
 		{name: "polish", env: &Env{Audita: &audita.FakeRunner{Err: errors.New("polish fail")}}},
 		{name: "analyze", env: &Env{Scriptorium: &scriptorium.FakeRunner{RunErr: errors.New("analyze fail")}}},
-		{name: "archive", env: &Env{Storage: &storage.FakeBackend{Err: errors.New("archive fail")}}},
+		{name: "archive", env: &Env{ObjectStore: &storage.FakeBackend{UploadErr: errors.New("archive fail")}}},
 		{name: "notify", env: &Env{Notifier: &notify.FakeSender{Err: errors.New("notify fail")}}},
 	}
 
@@ -332,7 +808,7 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 			tc.env.ArtifactStore = artifactStore
 			tc.env.ManifestStore = &manifest.LocalStore{}
 			if tc.name == "transcribe" {
-				paths, ensureErr := artifactStore.EnsureLayout(cfg.Session.SessionID)
+				paths, ensureErr := artifactStore.EnsureLayoutFor(cfg.Session.Campaign, cfg.Session.SessionID)
 				if ensureErr != nil {
 					t.Fatalf("EnsureLayout() error = %v", ensureErr)
 				}
@@ -347,7 +823,7 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 				}
 			}
 			if tc.name == "merge" {
-				paths, ensureErr := artifactStore.EnsureLayout(cfg.Session.SessionID)
+				paths, ensureErr := artifactStore.EnsureLayoutFor(cfg.Session.Campaign, cfg.Session.SessionID)
 				if ensureErr != nil {
 					t.Fatalf("EnsureLayout() error = %v", ensureErr)
 				}
@@ -366,7 +842,7 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 				}
 			}
 			if tc.name == "polish" {
-				paths, ensureErr := artifactStore.EnsureLayout(cfg.Session.SessionID)
+				paths, ensureErr := artifactStore.EnsureLayoutFor(cfg.Session.Campaign, cfg.Session.SessionID)
 				if ensureErr != nil {
 					t.Fatalf("EnsureLayout() error = %v", ensureErr)
 				}
@@ -378,7 +854,7 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 				}
 			}
 			if tc.name == "analyze" {
-				paths, ensureErr := artifactStore.EnsureLayout(cfg.Session.SessionID)
+				paths, ensureErr := artifactStore.EnsureLayoutFor(cfg.Session.Campaign, cfg.Session.SessionID)
 				if ensureErr != nil {
 					t.Fatalf("EnsureLayout() error = %v", ensureErr)
 				}
@@ -394,12 +870,47 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
 							PromptID:   "dnd.session_recap",
 							OutputPath: "artifacts/session_recap.md",
 							Inputs: map[string]config.ScriptoriumInputConfig{
-								"transcript": {Source: "processed_transcript", Required: true},
+								"transcript": {Source: "narratio.transcript.polished", Required: true},
 							},
 						},
 					},
 				}
 			}
+			if tc.name == "archive" {
+				cfg.Pipeline.Archive = &config.ArchiveConfig{
+					Enabled:   boolPtr(true),
+					UploadRun: boolPtr(true),
+				}
+				cfg.Pipeline.Storage.S3 = &config.StorageS3Config{
+					Bucket:     "my-dnd-archive",
+					RootPrefix: "dnd",
+				}
+				runID := "20260516T010203Z-0a1b2c3d"
+				runWorkDir := filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.Campaign, cfg.Session.SessionID, runID)
+				if err := os.MkdirAll(filepath.Join(runWorkDir, "inputs"), 0o755); err != nil {
+					t.Fatalf("mkdir archive inputs dir: %v", err)
+				}
+				if err := os.WriteFile(filepath.Join(runWorkDir, "inputs", "session.yml"), []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
+					t.Fatalf("write archive fixture session.yml: %v", err)
+				}
+				if err := os.WriteFile(filepath.Join(runWorkDir, "manifest.json"), []byte("{}\n"), 0o644); err != nil {
+					t.Fatalf("write archive fixture manifest.json: %v", err)
+				}
+
+				seed := manifest.New(cfg.Session.SessionID, time.Now().UTC())
+				seed.Campaign = cfg.Session.Campaign
+				seed.RunID = runID
+				seed.LocalWorkDir = runWorkDir
+				seed.S3Bucket = "my-dnd-archive"
+				seed.S3SessionPrefix = "dnd/campaigns/" + cfg.Session.Campaign + "/sessions/" + cfg.Session.SessionID + "/"
+				seed.S3RunPrefix = seed.S3SessionPrefix + "runs/" + runID + "/"
+				for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze"} {
+					seed.MarkStageSucceeded(name, time.Now().UTC(), nil)
+				}
+				if err := tc.env.ManifestStore.Save(context.Background(), manifestPathFor(cfg), seed); err != nil {
+					t.Fatalf("seed archive manifest: %v", err)
+				}
+			}
 
 			_, runErr := executeStages(context.Background(), cfg, []stage.Stage{selected}, RunOptions{Env: tc.env})
 			if runErr == nil {
@@ -430,7 +941,7 @@ func testConfig(t *testing.T) *config.Config {
 	pipelinePath := filepath.Join(cfgDir, "pipeline.yml")
 
 	mustWriteFile(t, pipelinePath, "workspace:\n  root: "+workspace+"\n")
-	mustWriteFile(t, sessionPath, "session_id: 2026-05-03\n")
+	mustWriteFile(t, sessionPath, "session_id: 2026-05-03\ncampaign: sample-campaign\n")
 	mustWriteFile(t, filepath.Join(cfgDir, "speakers.yml"), "alice: alice.flac\n")
 	mustWriteFile(t, filepath.Join(cfgDir, "autocorrect.yml"), "[]\n")
 	mustWriteFile(t, filepath.Join(cfgDir, "glossary.yml"), "[]\n")
@@ -442,6 +953,7 @@ func testConfig(t *testing.T) *config.Config {
 		SessionPath:  sessionPath,
 		Session: &config.SessionConfig{
 			SessionID: "2026-05-03",
+			Campaign:  "sample-campaign",
 			Inputs: config.SessionInputsConfig{
 				AudioDir:        "./audio",
 				SpeakersFile:    "./speakers.yml",
@@ -452,6 +964,55 @@ func testConfig(t *testing.T) *config.Config {
 	}
 }
 
+func TestBuildDefaultRunnersWithOmittedToolSections(t *testing.T) {
+	dir := t.TempDir()
+	pipelinePath := filepath.Join(dir, "pipeline.yml")
+	sessionPath := filepath.Join(dir, "session.yml")
+	pipelineYAML := `workspace:
+  root: ` + t.TempDir() + `
+whisperx:
+  transcribe_url: https://example.com/transcribe
+analyzer:
+  timeout: 20m
+notification:
+  timeout: 10s
+`
+	sessionYAML := `session_id: 2026-05-03
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	mustWriteFile(t, pipelinePath, pipelineYAML)
+	mustWriteFile(t, sessionPath, sessionYAML)
+
+	cfg, err := config.Load(pipelinePath, sessionPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+	if err := config.Validate(cfg); err != nil {
+		t.Fatalf("Validate() error = %v", err)
+	}
+
+	serRunner, err := buildDefaultSeriatimRunner(cfg)
+	if err != nil {
+		t.Fatalf("buildDefaultSeriatimRunner() error = %v", err)
+	}
+	if _, ok := serRunner.(*seriatim.SubprocessRunner); !ok {
+		t.Fatalf("seriatim runner type = %T, want *seriatim.SubprocessRunner", serRunner)
+	}
+
+	audRunner, err := buildDefaultAuditaRunner(cfg)
+	if err != nil {
+		t.Fatalf("buildDefaultAuditaRunner() error = %v", err)
+	}
+	if _, ok := audRunner.(*audita.SubprocessRunner); !ok {
+		t.Fatalf("audita runner type = %T, want *audita.SubprocessRunner", audRunner)
+	}
+}
+
 func mustWriteFile(t *testing.T, path, contents string) {
 	t.Helper()
 	if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
@@ -461,3 +1022,8 @@ func mustWriteFile(t *testing.T, path, contents string) {
 		t.Fatalf("WriteFile(%q): %v", path, err)
 	}
 }
+
+func boolPtr(v bool) *bool {
+	p := v
+	return &p
+}

internal/app/secrets_env.go

@@ -0,0 +1,88 @@
+package app
+
+import (
+	"fmt"
+	"log/slog"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+var envVarNamePattern = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
+
+type secretsLoadStats struct {
+	Dir               string
+	Loaded            int
+	PreservedExisting int
+	Skipped           int
+}
+
+func loadSecretsFromConfig(cfg *config.Config, logger *slog.Logger) (*secretsLoadStats, error) {
+	if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Secrets == nil {
+		return nil, nil
+	}
+
+	rawDir := strings.TrimSpace(cfg.Pipeline.Secrets.EnvDir)
+	if rawDir == "" {
+		return nil, nil
+	}
+
+	resolvedDir := rawDir
+	if !filepath.IsAbs(resolvedDir) {
+		cwd, err := os.Getwd()
+		if err != nil {
+			return nil, fmt.Errorf("resolve secrets env_dir %q from current working directory: %w", rawDir, err)
+		}
+		resolvedDir = filepath.Join(cwd, resolvedDir)
+	}
+	resolvedDir = filepath.Clean(resolvedDir)
+
+	entries, err := os.ReadDir(resolvedDir)
+	if err != nil {
+		return nil, fmt.Errorf("read secrets env_dir %q: %w", resolvedDir, err)
+	}
+
+	stats := &secretsLoadStats{Dir: resolvedDir}
+	for _, entry := range entries {
+		name := entry.Name()
+		if !envVarNamePattern.MatchString(name) {
+			stats.Skipped++
+			continue
+		}
+		if entry.IsDir() {
+			stats.Skipped++
+			continue
+		}
+
+		secretPath := filepath.Join(resolvedDir, name)
+		bytes, err := os.ReadFile(secretPath)
+		if err != nil {
+			return nil, fmt.Errorf("read secret file %q: %w", secretPath, err)
+		}
+		value := strings.TrimRight(string(bytes), "\r\n")
+
+		if _, exists := os.LookupEnv(name); exists {
+			stats.PreservedExisting++
+			continue
+		}
+		if err := os.Setenv(name, value); err != nil {
+			return nil, fmt.Errorf("set environment variable %q from %q: %w", name, secretPath, err)
+		}
+		stats.Loaded++
+	}
+
+	if logger != nil {
+		logger.Info(
+			"loaded secret environment variables from filesystem",
+			"secrets_env_dir", stats.Dir,
+			"loaded", stats.Loaded,
+			"preserved_existing", stats.PreservedExisting,
+			"skipped", stats.Skipped,
+		)
+	}
+
+	return stats, nil
+}

internal/app/secrets_env_test.go

@@ -0,0 +1,155 @@
+package app
+
+import (
+	"os"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+func TestLoadSecretsFromConfigLoadsValidFiles(t *testing.T) {
+	dir := t.TempDir()
+	mustWriteSecretFile(t, filepath.Join(dir, "NARRATIO_TEST_SECRET_A"), "value-1\n")
+	mustWriteSecretFile(t, filepath.Join(dir, "NARRATIO_TEST_SECRET_B"), "value-2\r\n")
+	mustWriteSecretFile(t, filepath.Join(dir, "not-valid-name.txt"), "ignored")
+
+	cfg := &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Secrets: &config.SecretsConfig{EnvDir: dir},
+		},
+	}
+
+	stats, err := loadSecretsFromConfig(cfg, nil)
+	if err != nil {
+		t.Fatalf("loadSecretsFromConfig() error = %v", err)
+	}
+	if stats == nil {
+		t.Fatal("stats = nil, want non-nil")
+	}
+	if stats.Loaded != 2 {
+		t.Fatalf("Loaded = %d, want 2", stats.Loaded)
+	}
+	if stats.PreservedExisting != 0 {
+		t.Fatalf("PreservedExisting = %d, want 0", stats.PreservedExisting)
+	}
+	if stats.Skipped == 0 {
+		t.Fatalf("Skipped = %d, want > 0 for invalid filename", stats.Skipped)
+	}
+	if got := os.Getenv("NARRATIO_TEST_SECRET_A"); got != "value-1" {
+		t.Fatalf("NARRATIO_TEST_SECRET_A = %q, want value-1", got)
+	}
+	if got := os.Getenv("NARRATIO_TEST_SECRET_B"); got != "value-2" {
+		t.Fatalf("NARRATIO_TEST_SECRET_B = %q, want value-2", got)
+	}
+}
+
+func TestLoadSecretsFromConfigPreservesExistingEnv(t *testing.T) {
+	t.Setenv("OBJECT_STORAGE_KEY", "existing")
+
+	dir := t.TempDir()
+	mustWriteSecretFile(t, filepath.Join(dir, "OBJECT_STORAGE_KEY"), "from-file\n")
+
+	cfg := &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Secrets: &config.SecretsConfig{EnvDir: dir},
+		},
+	}
+
+	stats, err := loadSecretsFromConfig(cfg, nil)
+	if err != nil {
+		t.Fatalf("loadSecretsFromConfig() error = %v", err)
+	}
+	if stats.PreservedExisting != 1 {
+		t.Fatalf("PreservedExisting = %d, want 1", stats.PreservedExisting)
+	}
+	if got := os.Getenv("OBJECT_STORAGE_KEY"); got != "existing" {
+		t.Fatalf("OBJECT_STORAGE_KEY = %q, want existing", got)
+	}
+}
+
+func TestLoadSecretsFromConfigRelativeDirUsesCWD(t *testing.T) {
+	cwd := t.TempDir()
+	secretsDir := filepath.Join(cwd, "secrets")
+	if err := os.MkdirAll(secretsDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll(%q): %v", secretsDir, err)
+	}
+	mustWriteSecretFile(t, filepath.Join(secretsDir, "OBJECT_STORAGE_KEY_ID"), "id-123\n")
+
+	originalWD, err := os.Getwd()
+	if err != nil {
+		t.Fatalf("Getwd(): %v", err)
+	}
+	if err := os.Chdir(cwd); err != nil {
+		t.Fatalf("Chdir(%q): %v", cwd, err)
+	}
+	t.Cleanup(func() {
+		_ = os.Chdir(originalWD)
+	})
+
+	cfg := &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Secrets: &config.SecretsConfig{EnvDir: "./secrets"},
+		},
+	}
+	if _, err := loadSecretsFromConfig(cfg, nil); err != nil {
+		t.Fatalf("loadSecretsFromConfig() error = %v", err)
+	}
+	if got := os.Getenv("OBJECT_STORAGE_KEY_ID"); got != "id-123" {
+		t.Fatalf("OBJECT_STORAGE_KEY_ID = %q, want id-123", got)
+	}
+}
+
+func TestLoadSecretsFromConfigMissingDirFails(t *testing.T) {
+	cfg := &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Secrets: &config.SecretsConfig{EnvDir: filepath.Join(t.TempDir(), "missing")},
+		},
+	}
+
+	_, err := loadSecretsFromConfig(cfg, nil)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "read secrets env_dir") {
+		t.Fatalf("error = %q, want read-dir context", err.Error())
+	}
+}
+
+func TestLoadSecretsFromConfigUnreadableValidEntryFails(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("symlink behavior differs on windows")
+	}
+
+	dir := t.TempDir()
+	broken := filepath.Join(dir, "OPENROUTER_API_KEY")
+	if err := os.Symlink(filepath.Join(dir, "does-not-exist"), broken); err != nil {
+		t.Fatalf("Symlink(%q): %v", broken, err)
+	}
+
+	cfg := &config.Config{
+		Pipeline: &config.PipelineConfig{
+			Secrets: &config.SecretsConfig{EnvDir: dir},
+		},
+	}
+
+	_, err := loadSecretsFromConfig(cfg, nil)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "read secret file") {
+		t.Fatalf("error = %q, want read secret file context", err.Error())
+	}
+}
+
+func mustWriteSecretFile(t *testing.T, path, contents string) {
+	t.Helper()
+	if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
+		t.Fatalf("MkdirAll(%q): %v", path, err)
+	}
+	if err := os.WriteFile(path, []byte(contents), 0o600); err != nil {
+		t.Fatalf("WriteFile(%q): %v", path, err)
+	}
+}

internal/app/session_cli_test.go

@@ -0,0 +1,86 @@
+package app
+
+import (
+	"bytes"
+	"context"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestPlanUsesDiscoveredSessionTemplateWithSessionID(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
+
+	sessionTemplate := `session_id: "{{ session_id }}"
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionTemplate), 0o644); err != nil {
+		t.Fatalf("write session template: %v", err)
+	}
+
+	cwd := filepath.Dir(sessionPath)
+	originalWD, err := os.Getwd()
+	if err != nil {
+		t.Fatalf("Getwd(): %v", err)
+	}
+	if err := os.Chdir(cwd); err != nil {
+		t.Fatalf("Chdir(%q): %v", cwd, err)
+	}
+	t.Cleanup(func() { _ = os.Chdir(originalWD) })
+
+	var out bytes.Buffer
+	if err := Plan(context.Background(), []string{"--config", pipelinePath, "--session-id", "2026-04-04"}, &out); err != nil {
+		t.Fatalf("Plan() error = %v", err)
+	}
+	if !strings.Contains(out.String(), "narratio plan: workdir prepared") {
+		t.Fatalf("output = %q, want plan output", out.String())
+	}
+}
+
+func TestPlanFailsWhenSessionIDMismatchesConcreteSession(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
+
+	var out bytes.Buffer
+	err := Plan(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath, "--session-id", "2026-04-04"}, &out)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "session_id mismatch") {
+		t.Fatalf("error = %q, want mismatch context", err.Error())
+	}
+}
+
+func TestRunStageAcceptsSessionIDFlagAndParsesStageName(t *testing.T) {
+	workspaceRoot := t.TempDir()
+	pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
+
+	var out bytes.Buffer
+	err := RunStage(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath, "--session-id", "2026-05-03", "prepare"}, &out)
+	if err != nil {
+		t.Fatalf("RunStage() error = %v", err)
+	}
+	if !strings.Contains(out.String(), "stage=prepare") {
+		t.Fatalf("output = %q, want stage output", out.String())
+	}
+}
+
+func TestResolveSessionConfigPathErrorIncludesSearchedPaths(t *testing.T) {
+	_, err := resolveSessionConfigPathWithCandidates("", []string{"./session.yml", "/usr/local/etc/narratio/session.yml", "/etc/narratio/session.yml"})
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "searched") {
+		t.Fatalf("error = %q, want searched paths", err.Error())
+	}
+	if !strings.Contains(err.Error(), "pass --session") {
+		t.Fatalf("error = %q, want explicit-session guidance", err.Error())
+	}
+}

internal/app/session_config_path.go

@@ -0,0 +1,49 @@
+package app
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+func resolveSessionConfigPath(flagValue string) (string, error) {
+	return resolveSessionConfigPathWithCandidates(flagValue, config.DefaultSessionConfigSearchPaths)
+}
+
+func resolveSessionConfigPathWithCandidates(flagValue string, candidates []string) (string, error) {
+	if explicit := strings.TrimSpace(flagValue); explicit != "" {
+		return explicit, nil
+	}
+
+	ordered := make([]string, 0, len(candidates))
+	for _, raw := range candidates {
+		path := strings.TrimSpace(raw)
+		if path == "" {
+			continue
+		}
+		ordered = append(ordered, path)
+		info, err := os.Stat(path)
+		if err == nil {
+			if info.IsDir() {
+				continue
+			}
+			return filepath.Clean(path), nil
+		}
+		if errors.Is(err, os.ErrNotExist) {
+			continue
+		}
+		return "", fmt.Errorf("check default session config %q: %w", path, err)
+	}
+
+	if len(ordered) == 0 {
+		return "", fmt.Errorf("no session config path provided and no default locations configured")
+	}
+	return "", fmt.Errorf(
+		"no session config path provided and no default session config found; searched: %s; pass --session to use an explicit path",
+		strings.Join(ordered, ", "),
+	)
+}

internal/app/session_config_path_test.go

@@ -0,0 +1,68 @@
+package app
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestResolveSessionConfigPathWithCandidatesExplicitWins(t *testing.T) {
+	got, err := resolveSessionConfigPathWithCandidates("  ./custom/session.yml  ", []string{"./session.yml", "/a", "/b"})
+	if err != nil {
+		t.Fatalf("resolveSessionConfigPathWithCandidates() error = %v", err)
+	}
+	if got != "./custom/session.yml" {
+		t.Fatalf("resolved path = %q, want explicit path", got)
+	}
+}
+
+func TestResolveSessionConfigPathWithCandidatesUsesFirstExisting(t *testing.T) {
+	dir := t.TempDir()
+	first := filepath.Join(dir, "first.yml")
+	second := filepath.Join(dir, "second.yml")
+	if err := os.WriteFile(second, []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
+		t.Fatalf("write second default: %v", err)
+	}
+
+	got, err := resolveSessionConfigPathWithCandidates("", []string{first, second})
+	if err != nil {
+		t.Fatalf("resolveSessionConfigPathWithCandidates() error = %v", err)
+	}
+	if got != filepath.Clean(second) {
+		t.Fatalf("resolved path = %q, want %q", got, filepath.Clean(second))
+	}
+}
+
+func TestResolveSessionConfigPathWithCandidatesPrecedence(t *testing.T) {
+	dir := t.TempDir()
+	first := filepath.Join(dir, "first.yml")
+	second := filepath.Join(dir, "second.yml")
+	if err := os.WriteFile(first, []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
+		t.Fatalf("write first default: %v", err)
+	}
+	if err := os.WriteFile(second, []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
+		t.Fatalf("write second default: %v", err)
+	}
+
+	got, err := resolveSessionConfigPathWithCandidates("", []string{first, second})
+	if err != nil {
+		t.Fatalf("resolveSessionConfigPathWithCandidates() error = %v", err)
+	}
+	if got != filepath.Clean(first) {
+		t.Fatalf("resolved path = %q, want first candidate %q", got, filepath.Clean(first))
+	}
+}
+
+func TestResolveSessionConfigPathWithCandidatesMissing(t *testing.T) {
+	_, err := resolveSessionConfigPathWithCandidates("", []string{"/does/not/exist/one.yml", "/does/not/exist/two.yml"})
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "no default session config found") {
+		t.Fatalf("error = %q, want missing-defaults context", err.Error())
+	}
+	if !strings.Contains(err.Error(), "pass --session") {
+		t.Fatalf("error = %q, want explicit-path guidance", err.Error())
+	}
+}

internal/app/whisperx_wiring_test.go

@@ -63,7 +63,7 @@ func TestExecuteStagesDefaultWiringUsesWhisperXHTTPClient(t *testing.T) {
 		t.Fatal("audio file payload was empty")
 	}
 
-	outPath := filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.SessionID, "transcripts", "raw", "alice.json")
+	outPath := filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.Campaign, cfg.Session.SessionID, "transcripts", "raw", "alice.json")
 	data, err := os.ReadFile(outPath)
 	if err != nil {
 		t.Fatalf("ReadFile(%q) error = %v", outPath, err)

internal/artifacts/artifact_resolver.go

@@ -0,0 +1,313 @@
+package artifacts
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
+)
+
+const (
+	ArtifactTranscriptMerged   = "narratio.transcript.merged"
+	ArtifactTranscriptPolished = "narratio.transcript.polished"
+	ArtifactTranscriptFull     = "narratio.transcript.full"
+	ArtifactTranscriptTrimmed  = "narratio.transcript.trimmed"
+	ArtifactBoundsSession      = "narratio.bounds.session"
+)
+
+// ErrSessionArtifactNotFound is returned when no readable artifact exists for a known ID.
+var ErrSessionArtifactNotFound = errors.New("session artifact not found")
+var configuredArtifactSourceRE = regexp.MustCompile(`^narratio\.artifact\.[a-z][a-z0-9_]*$`)
+
+type artifactContentKind string
+
+const (
+	contentTranscriptJSON artifactContentKind = "transcript_json"
+	contentJSON           artifactContentKind = "json"
+	contentText           artifactContentKind = "text"
+)
+
+type artifactSpec struct {
+	ID               string
+	CanonicalRelPath string
+	ProducerStage    string
+	OutputKind       string
+	ContentKind      artifactContentKind
+}
+
+var artifactRegistry = map[string]artifactSpec{
+	ArtifactTranscriptMerged: {
+		ID:               ArtifactTranscriptMerged,
+		CanonicalRelPath: "transcripts/merged.json",
+		ProducerStage:    "merge",
+		OutputKind:       "transcript_merged",
+		ContentKind:      contentTranscriptJSON,
+	},
+	ArtifactTranscriptPolished: {
+		ID:               ArtifactTranscriptPolished,
+		CanonicalRelPath: "transcripts/processed.json",
+		ProducerStage:    "polish",
+		OutputKind:       "transcript_processed",
+		ContentKind:      contentTranscriptJSON,
+	},
+	ArtifactTranscriptFull: {
+		ID:               ArtifactTranscriptFull,
+		CanonicalRelPath: "transcripts/normalized.json",
+		ProducerStage:    "normalize",
+		OutputKind:       "transcript_normalized",
+		ContentKind:      contentTranscriptJSON,
+	},
+	ArtifactTranscriptTrimmed: {
+		ID:               ArtifactTranscriptTrimmed,
+		CanonicalRelPath: "transcripts/trimmed.json",
+		ProducerStage:    "trim",
+		OutputKind:       "transcript_trimmed",
+		ContentKind:      contentTranscriptJSON,
+	},
+	ArtifactBoundsSession: {
+		ID:               ArtifactBoundsSession,
+		CanonicalRelPath: "artifacts/session_bounds.json",
+		ProducerStage:    "trim",
+		OutputKind:       "session_bounds",
+		ContentKind:      contentJSON,
+	},
+}
+
+// ResolvedSessionArtifact describes one session-level artifact lookup result.
+type ResolvedSessionArtifact struct {
+	ID            string
+	Path          string
+	ProducerStage string
+	OutputKind    string
+	ProducerRunID string
+	Provenance    string
+}
+
+// SessionArtifactNotFoundError includes context when a known artifact cannot be read.
+type SessionArtifactNotFoundError struct {
+	ArtifactID string
+}
+
+func (e *SessionArtifactNotFoundError) Error() string {
+	return fmt.Sprintf("%s: %q", ErrSessionArtifactNotFound, e.ArtifactID)
+}
+
+func (e *SessionArtifactNotFoundError) Unwrap() error {
+	return ErrSessionArtifactNotFound
+}
+
+// NormalizeSessionArtifactSource validates canonical artifact IDs.
+func NormalizeSessionArtifactSource(source string) (string, error) {
+	normalized := strings.TrimSpace(source)
+	if normalized == "" {
+		return "", fmt.Errorf("artifact source is required")
+	}
+	if _, ok := artifactRegistry[normalized]; !ok {
+		return "", fmt.Errorf("unsupported artifact source %q", source)
+	}
+	return normalized, nil
+}
+
+// IsConfiguredArtifactSource returns true when source is narratio.artifact.<name>.
+func IsConfiguredArtifactSource(source string) bool {
+	return configuredArtifactSourceRE.MatchString(strings.TrimSpace(source))
+}
+
+// ResolveSessionArtifact resolves a symbolic source to a readable local session artifact path.
+// Resolution order is manifest producer outputs first, then canonical session path fallback.
+func ResolveSessionArtifact(paths SessionPaths, m *manifest.Manifest, source string) (ResolvedSessionArtifact, error) {
+	id, err := NormalizeSessionArtifactSource(source)
+	if err != nil {
+		return ResolvedSessionArtifact{}, err
+	}
+	spec := artifactRegistry[id]
+
+	for _, candidate := range manifestArtifactCandidates(paths, m, spec) {
+		exists, isDir, statErr := pathExists(candidate.Path)
+		if statErr != nil {
+			return ResolvedSessionArtifact{}, fmt.Errorf("stat %q: %w", candidate.Path, statErr)
+		}
+		if !exists || isDir {
+			continue
+		}
+		resolved := candidate
+		resolved.ID = spec.ID
+		resolved.ProducerStage = spec.ProducerStage
+		resolved.OutputKind = spec.OutputKind
+		if err := validateResolvedContent(resolved.Path, spec.ContentKind); err != nil {
+			return ResolvedSessionArtifact{}, fmt.Errorf("validate %q: %w", resolved.ID, err)
+		}
+		return resolved, nil
+	}
+
+	fallbackPath := filepath.Join(paths.Root, filepath.FromSlash(spec.CanonicalRelPath))
+	exists, isDir, statErr := pathExists(fallbackPath)
+	if statErr != nil {
+		return ResolvedSessionArtifact{}, fmt.Errorf("stat %q: %w", fallbackPath, statErr)
+	}
+	if exists && !isDir {
+		if err := validateResolvedContent(fallbackPath, spec.ContentKind); err != nil {
+			return ResolvedSessionArtifact{}, fmt.Errorf("validate %q: %w", spec.ID, err)
+		}
+		return ResolvedSessionArtifact{
+			ID:            spec.ID,
+			Path:          filepath.Clean(fallbackPath),
+			ProducerStage: spec.ProducerStage,
+			OutputKind:    spec.OutputKind,
+			Provenance:    "fallback.canonical_path",
+		}, nil
+	}
+
+	return ResolvedSessionArtifact{}, &SessionArtifactNotFoundError{ArtifactID: spec.ID}
+}
+
+// ResolveSessionArtifactWithCatalog resolves built-in sources using existing rules and resolves
+// configured narratio.artifact.<name> sources through runtime catalog availability.
+func ResolveSessionArtifactWithCatalog(paths SessionPaths, m *manifest.Manifest, source string, catalog *ArtifactCatalog) (ResolvedSessionArtifact, error) {
+	normalized := strings.TrimSpace(source)
+	if !IsConfiguredArtifactSource(normalized) {
+		return ResolveSessionArtifact(paths, m, normalized)
+	}
+	if catalog == nil {
+		return ResolvedSessionArtifact{}, fmt.Errorf("configured artifact source %q requires runtime artifact catalog", source)
+	}
+	entry, ok := catalog.Lookup(normalized)
+	if !ok {
+		return ResolvedSessionArtifact{}, fmt.Errorf("unsupported artifact source %q", source)
+	}
+	if !entry.Available {
+		return ResolvedSessionArtifact{}, &SessionArtifactNotFoundError{ArtifactID: normalized}
+	}
+	if err := validateResolvedContent(entry.Path, contentText); err != nil {
+		return ResolvedSessionArtifact{}, fmt.Errorf("validate %q: %w", normalized, err)
+	}
+	return ResolvedSessionArtifact{
+		ID:            normalized,
+		Path:          filepath.Clean(entry.Path),
+		ProducerStage: entry.ProducerStage,
+		OutputKind:    entry.OutputKind,
+		Provenance:    entry.Provenance,
+	}, nil
+}
+
+func manifestArtifactCandidates(paths SessionPaths, m *manifest.Manifest, spec artifactSpec) []ResolvedSessionArtifact {
+	if m == nil || len(m.Stages) == 0 || spec.ProducerStage == "" || spec.OutputKind == "" {
+		return nil
+	}
+	sr := m.Stages[spec.ProducerStage]
+	if sr == nil {
+		return nil
+	}
+
+	candidates := make([]ResolvedSessionArtifact, 0, len(sr.Outputs))
+	for _, out := range sr.Outputs {
+		if strings.TrimSpace(out.Kind) != spec.OutputKind {
+			continue
+		}
+		if strings.TrimSpace(out.LocalPath) == "" {
+			continue
+		}
+		resolved := filepath.Clean(ResolveSessionLocalPathForRead(paths, out.LocalPath))
+		if resolved == "" {
+			continue
+		}
+		candidates = append(candidates, ResolvedSessionArtifact{
+			Path:          resolved,
+			ProducerRunID: strings.TrimSpace(out.ProducerRunID),
+			Provenance:    "manifest." + spec.ProducerStage + ".outputs",
+		})
+	}
+	return dedupeResolvedArtifacts(candidates)
+}
+
+func dedupeResolvedArtifacts(values []ResolvedSessionArtifact) []ResolvedSessionArtifact {
+	seen := map[string]struct{}{}
+	out := make([]ResolvedSessionArtifact, 0, len(values))
+	for _, value := range values {
+		key := filepath.Clean(strings.TrimSpace(value.Path))
+		if key == "" {
+			continue
+		}
+		if _, ok := seen[key]; ok {
+			continue
+		}
+		seen[key] = struct{}{}
+		value.Path = key
+		out = append(out, value)
+	}
+	return out
+}
+
+func pathExists(path string) (exists bool, isDir bool, err error) {
+	info, err := os.Stat(path)
+	if err == nil {
+		return true, info.IsDir(), nil
+	}
+	if errors.Is(err, os.ErrNotExist) {
+		return false, false, nil
+	}
+	return false, false, err
+}
+
+func validateResolvedContent(path string, kind artifactContentKind) error {
+	switch kind {
+	case contentTranscriptJSON:
+		return validateTranscriptSegmentsJSON(path)
+	case contentJSON:
+		return validateJSONContent(path)
+	case contentText:
+		return validateNonEmptyContent(path)
+	default:
+		return fmt.Errorf("unsupported content kind %q", kind)
+	}
+}
+
+func validateTranscriptSegmentsJSON(path string) error {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return fmt.Errorf("read file: %w", err)
+	}
+	var payload map[string]any
+	if err := json.Unmarshal(data, &payload); err != nil {
+		return fmt.Errorf("decode json: %w", err)
+	}
+	segments, ok := payload["segments"]
+	if !ok {
+		return fmt.Errorf("top-level segments is required")
+	}
+	if _, ok := segments.([]any); !ok {
+		return fmt.Errorf("top-level segments must be an array")
+	}
+	return nil
+}
+
+func validateJSONContent(path string) error {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return fmt.Errorf("read file: %w", err)
+	}
+	var payload any
+	if err := json.Unmarshal(data, &payload); err != nil {
+		return fmt.Errorf("decode json: %w", err)
+	}
+	return nil
+}
+
+func validateNonEmptyContent(path string) error {
+	info, err := os.Stat(path)
+	if err != nil {
+		return fmt.Errorf("stat file: %w", err)
+	}
+	if info.IsDir() {
+		return fmt.Errorf("path is a directory")
+	}
+	if info.Size() <= 0 {
+		return fmt.Errorf("file is empty")
+	}
+	return nil
+}

internal/artifacts/artifact_resolver_test.go

@@ -0,0 +1,268 @@
+package artifacts
+
+import (
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/manifest"
+)
+
+func TestNormalizeSessionArtifactSource(t *testing.T) {
+	tests := []struct {
+		name    string
+		source  string
+		wantID  string
+		wantErr string
+	}{
+		{name: "legacy alias processed unsupported", source: "processed_transcript", wantErr: "unsupported artifact source"},
+		{name: "legacy alias normalized unsupported", source: "normalized_transcript", wantErr: "unsupported artifact source"},
+		{name: "legacy alias trimmed unsupported", source: "trimmed_transcript", wantErr: "unsupported artifact source"},
+		{name: "configured source unsupported in built-in normalization", source: "narratio.artifact.session_recap", wantErr: "unsupported artifact source"},
+		{name: "canonical", source: ArtifactTranscriptTrimmed, wantID: ArtifactTranscriptTrimmed},
+		{name: "unsupported", source: "narratio.unknown", wantErr: "unsupported artifact source"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := NormalizeSessionArtifactSource(tt.source)
+			if tt.wantErr != "" {
+				if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
+					t.Fatalf("NormalizeSessionArtifactSource() error = %v, want contains %q", err, tt.wantErr)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("NormalizeSessionArtifactSource() error = %v", err)
+			}
+			if got != tt.wantID {
+				t.Fatalf("NormalizeSessionArtifactSource() = %q, want %q", got, tt.wantID)
+			}
+		})
+	}
+}
+
+func TestResolveSessionArtifactPrefersManifestOutput(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	if err := os.MkdirAll(paths.ArtifactsDir, 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	manifestPath := filepath.Join(paths.ArtifactsDir, "normalized.from-manifest.json")
+	if err := os.WriteFile(manifestPath, []byte(`{"segments":[]}`), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+	canonicalPath := filepath.Join(paths.TranscriptsDir, "normalized.json")
+	if err := os.MkdirAll(filepath.Dir(canonicalPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := os.WriteFile(canonicalPath, []byte(`{"segments":[{"id":123}]}`), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	m := manifest.New("session", time.Now().UTC())
+	m.MarkStageSucceeded("normalize", time.Now().UTC(), []manifest.ArtifactRecord{
+		{Kind: "transcript_normalized", LocalPath: manifestPath, ProducerRunID: "run-123"},
+	})
+
+	resolved, err := ResolveSessionArtifact(paths, m, ArtifactTranscriptFull)
+	if err != nil {
+		t.Fatalf("ResolveSessionArtifact() error = %v", err)
+	}
+	if resolved.Path != manifestPath {
+		t.Fatalf("resolved path = %q, want %q", resolved.Path, manifestPath)
+	}
+	if resolved.Provenance != "manifest.normalize.outputs" {
+		t.Fatalf("provenance = %q, want manifest.normalize.outputs", resolved.Provenance)
+	}
+	if resolved.ProducerRunID != "run-123" {
+		t.Fatalf("producer run id = %q, want run-123", resolved.ProducerRunID)
+	}
+}
+
+func TestResolveSessionArtifactFallsBackToCanonicalPath(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	canonicalPath := filepath.Join(paths.TranscriptsDir, "trimmed.json")
+	if err := os.MkdirAll(filepath.Dir(canonicalPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := os.WriteFile(canonicalPath, []byte(`{"segments":[]}`), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	resolved, err := ResolveSessionArtifact(paths, nil, ArtifactTranscriptTrimmed)
+	if err != nil {
+		t.Fatalf("ResolveSessionArtifact() error = %v", err)
+	}
+	if resolved.Path != canonicalPath {
+		t.Fatalf("resolved path = %q, want %q", resolved.Path, canonicalPath)
+	}
+	if resolved.Provenance != "fallback.canonical_path" {
+		t.Fatalf("provenance = %q, want fallback.canonical_path", resolved.Provenance)
+	}
+}
+
+func TestResolveSessionArtifactMissingReturnsTypedError(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+
+	_, err := ResolveSessionArtifact(paths, nil, ArtifactTranscriptTrimmed)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !errors.Is(err, ErrSessionArtifactNotFound) {
+		t.Fatalf("errors.Is(err, ErrSessionArtifactNotFound) = false; err=%v", err)
+	}
+}
+
+func TestResolveSessionArtifactValidatesTranscriptShape(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	canonicalPath := filepath.Join(paths.TranscriptsDir, "processed.json")
+	if err := os.MkdirAll(filepath.Dir(canonicalPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := os.WriteFile(canonicalPath, []byte(`{"not_segments":[]}`), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	_, err := ResolveSessionArtifact(paths, nil, ArtifactTranscriptPolished)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "top-level segments is required") {
+		t.Fatalf("error = %q, want segments validation error", err.Error())
+	}
+}
+
+func TestResolveSessionArtifactWithCatalogBuiltInBehaviorUnchanged(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	canonicalPath := filepath.Join(paths.TranscriptsDir, "trimmed.json")
+	if err := os.MkdirAll(filepath.Dir(canonicalPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := os.WriteFile(canonicalPath, []byte(`{"segments":[]}`), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	resolved, err := ResolveSessionArtifactWithCatalog(paths, nil, ArtifactTranscriptTrimmed, NewArtifactCatalog())
+	if err != nil {
+		t.Fatalf("ResolveSessionArtifactWithCatalog() error = %v", err)
+	}
+	if resolved.Path != canonicalPath {
+		t.Fatalf("resolved.Path = %q, want %q", resolved.Path, canonicalPath)
+	}
+	if resolved.Provenance != "fallback.canonical_path" {
+		t.Fatalf("provenance = %q, want fallback.canonical_path", resolved.Provenance)
+	}
+}
+
+func TestResolveSessionArtifactWithCatalogConfiguredAvailableGenerated(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	outputPath := filepath.Join(paths.ArtifactsDir, "session_recap.md")
+	if err := os.MkdirAll(filepath.Dir(outputPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := os.WriteFile(outputPath, []byte("recap\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+	sourceID := ConfiguredArtifactSourceID("session_recap")
+	if err := catalog.MarkAvailableGenerated(sourceID, outputPath); err != nil {
+		t.Fatalf("MarkAvailableGenerated() error = %v", err)
+	}
+
+	resolved, err := ResolveSessionArtifactWithCatalog(paths, nil, sourceID, catalog)
+	if err != nil {
+		t.Fatalf("ResolveSessionArtifactWithCatalog() error = %v", err)
+	}
+	if resolved.Path != outputPath {
+		t.Fatalf("resolved.Path = %q, want %q", resolved.Path, outputPath)
+	}
+	if resolved.Provenance != ArtifactProvenanceGeneratedCurrentAnalyzeRun {
+		t.Fatalf("provenance = %q, want %q", resolved.Provenance, ArtifactProvenanceGeneratedCurrentAnalyzeRun)
+	}
+}
+
+func TestResolveSessionArtifactWithCatalogConfiguredAvailableFromDisk(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	outputPath := filepath.Join(paths.ArtifactsDir, "player_handout.md")
+	if err := os.MkdirAll(filepath.Dir(outputPath), 0o755); err != nil {
+		t.Fatalf("MkdirAll() error = %v", err)
+	}
+	if err := os.WriteFile(outputPath, []byte("handout\n"), 0o644); err != nil {
+		t.Fatalf("WriteFile() error = %v", err)
+	}
+
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"player_handout": {Enabled: false, OutputPath: "artifacts/player_handout.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+	sourceID := ConfiguredArtifactSourceID("player_handout")
+	if err := catalog.MarkAvailableFromDisk(sourceID, outputPath); err != nil {
+		t.Fatalf("MarkAvailableFromDisk() error = %v", err)
+	}
+
+	resolved, err := ResolveSessionArtifactWithCatalog(paths, nil, sourceID, catalog)
+	if err != nil {
+		t.Fatalf("ResolveSessionArtifactWithCatalog() error = %v", err)
+	}
+	if resolved.Provenance != ArtifactProvenanceDisabledFromDisk {
+		t.Fatalf("provenance = %q, want %q", resolved.Provenance, ArtifactProvenanceDisabledFromDisk)
+	}
+}
+
+func TestResolveSessionArtifactWithCatalogConfiguredPlannedButUnavailable(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+	_, err := ResolveSessionArtifactWithCatalog(paths, nil, ConfiguredArtifactSourceID("session_recap"), catalog)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !errors.Is(err, ErrSessionArtifactNotFound) {
+		t.Fatalf("errors.Is(err, ErrSessionArtifactNotFound)=false; err=%v", err)
+	}
+}
+
+func TestResolveSessionArtifactWithCatalogUnsupportedConfiguredSourceFails(t *testing.T) {
+	workspace := t.TempDir()
+	paths := buildSessionPaths(workspace, "campaign", "session")
+	catalog := NewArtifactCatalog()
+	_, err := ResolveSessionArtifactWithCatalog(paths, nil, "narratio.artifact.unknown", catalog)
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "unsupported artifact source") {
+		t.Fatalf("error = %q, want unsupported artifact source", err.Error())
+	}
+}

internal/artifacts/catalog.go

@@ -0,0 +1,224 @@
+package artifacts
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+)
+
+const (
+	ArtifactProvenanceGeneratedCurrentAnalyzeRun = "generated.current_analyze_run"
+	ArtifactProvenanceDisabledFromDisk           = "filesystem.disabled_artifact_output"
+)
+
+// ConfiguredArtifactDefinition describes one configured analyze artifact.
+type ConfiguredArtifactDefinition struct {
+	Enabled    bool
+	OutputPath string
+}
+
+// CatalogEntry is one runtime catalog entry resolved by source ID.
+type CatalogEntry struct {
+	SourceID         string
+	ConfiguredKey    string
+	CanonicalRelPath string
+	ProducerStage    string
+	OutputKind       string
+	Planned          bool
+	Executable       bool
+	Available        bool
+	Path             string
+	Provenance       string
+}
+
+// ArtifactCatalog tracks built-in and configured artifact definitions and runtime state.
+type ArtifactCatalog struct {
+	entries         map[string]CatalogEntry
+	configuredIndex map[string]string
+}
+
+// NewArtifactCatalog returns an empty runtime artifact catalog.
+func NewArtifactCatalog() *ArtifactCatalog {
+	return &ArtifactCatalog{
+		entries:         map[string]CatalogEntry{},
+		configuredIndex: map[string]string{},
+	}
+}
+
+// ConfiguredArtifactSourceID converts a configured artifact key into canonical source ID.
+func ConfiguredArtifactSourceID(key string) string {
+	return "narratio.artifact." + strings.TrimSpace(key)
+}
+
+// RegisterBuiltIns registers built-in source definitions used by runtime artifact resolution.
+func (c *ArtifactCatalog) RegisterBuiltIns() error {
+	for _, id := range runtimeBuiltInArtifactIDs() {
+		spec, ok := artifactRegistry[id]
+		if !ok {
+			return fmt.Errorf("register built-ins: source %q not found in artifact registry", id)
+		}
+		if err := c.addEntry(CatalogEntry{
+			SourceID:         spec.ID,
+			CanonicalRelPath: spec.CanonicalRelPath,
+			ProducerStage:    spec.ProducerStage,
+			OutputKind:       spec.OutputKind,
+			Planned:          true,
+		}); err != nil {
+			return fmt.Errorf("register built-ins: %w", err)
+		}
+	}
+	return nil
+}
+
+// RegisterConfiguredArtifacts registers configured artifacts and applies executable selection.
+func (c *ArtifactCatalog) RegisterConfiguredArtifacts(
+	configured map[string]ConfiguredArtifactDefinition,
+	selected []string,
+) error {
+	keys := make([]string, 0, len(configured))
+	for key := range configured {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+
+	selectedSet := map[string]struct{}{}
+	for _, key := range selected {
+		trimmed := strings.TrimSpace(key)
+		if trimmed == "" {
+			return fmt.Errorf("selected artifact keys must be non-empty")
+		}
+		selectedSet[trimmed] = struct{}{}
+	}
+
+	for _, key := range keys {
+		trimmed := strings.TrimSpace(key)
+		if trimmed == "" {
+			return fmt.Errorf("configured artifact keys must be non-empty")
+		}
+		def := configured[key]
+		sourceID := ConfiguredArtifactSourceID(trimmed)
+		if _, exists := c.configuredIndex[trimmed]; exists {
+			return fmt.Errorf("duplicate configured artifact key %q", trimmed)
+		}
+
+		executable := def.Enabled
+		if len(selectedSet) > 0 {
+			_, executable = selectedSet[trimmed]
+		}
+
+		if err := c.addEntry(CatalogEntry{
+			SourceID:         sourceID,
+			ConfiguredKey:    trimmed,
+			CanonicalRelPath: strings.TrimSpace(def.OutputPath),
+			ProducerStage:    "analyze",
+			OutputKind:       "scriptorium_artifact",
+			Planned:          true,
+			Executable:       executable,
+		}); err != nil {
+			return fmt.Errorf("register configured artifact %q: %w", trimmed, err)
+		}
+		c.configuredIndex[trimmed] = sourceID
+	}
+
+	if len(selectedSet) > 0 {
+		for key := range selectedSet {
+			if _, ok := c.configuredIndex[key]; !ok {
+				return fmt.Errorf("selected artifact %q is not configured", key)
+			}
+		}
+	}
+
+	return nil
+}
+
+// Lookup returns one catalog entry by source ID.
+func (c *ArtifactCatalog) Lookup(sourceID string) (CatalogEntry, bool) {
+	if c == nil {
+		return CatalogEntry{}, false
+	}
+	entry, ok := c.entries[strings.TrimSpace(sourceID)]
+	return entry, ok
+}
+
+// SourceIDForConfiguredKey returns canonical source ID for one configured key.
+func (c *ArtifactCatalog) SourceIDForConfiguredKey(key string) (string, bool) {
+	if c == nil {
+		return "", false
+	}
+	sourceID, ok := c.configuredIndex[strings.TrimSpace(key)]
+	return sourceID, ok
+}
+
+// ListConfigured returns configured entries sorted by configured key.
+func (c *ArtifactCatalog) ListConfigured() []CatalogEntry {
+	if c == nil || len(c.configuredIndex) == 0 {
+		return nil
+	}
+	keys := make([]string, 0, len(c.configuredIndex))
+	for key := range c.configuredIndex {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	out := make([]CatalogEntry, 0, len(keys))
+	for _, key := range keys {
+		sourceID := c.configuredIndex[key]
+		out = append(out, c.entries[sourceID])
+	}
+	return out
+}
+
+// MarkAvailableGenerated marks one source as available in current analyze execution.
+func (c *ArtifactCatalog) MarkAvailableGenerated(sourceID, path string) error {
+	return c.markAvailable(sourceID, path, ArtifactProvenanceGeneratedCurrentAnalyzeRun)
+}
+
+// MarkAvailableFromDisk marks one source as available from disabled artifact on disk.
+func (c *ArtifactCatalog) MarkAvailableFromDisk(sourceID, path string) error {
+	return c.markAvailable(sourceID, path, ArtifactProvenanceDisabledFromDisk)
+}
+
+func (c *ArtifactCatalog) markAvailable(sourceID, path, provenance string) error {
+	if c == nil {
+		return fmt.Errorf("artifact catalog is nil")
+	}
+	normalizedID := strings.TrimSpace(sourceID)
+	entry, ok := c.entries[normalizedID]
+	if !ok {
+		return fmt.Errorf("unknown artifact source %q", sourceID)
+	}
+	trimmedPath := strings.TrimSpace(path)
+	if trimmedPath == "" {
+		return fmt.Errorf("artifact path is required")
+	}
+	entry.Available = true
+	entry.Path = trimmedPath
+	entry.Provenance = provenance
+	c.entries[normalizedID] = entry
+	return nil
+}
+
+func (c *ArtifactCatalog) addEntry(entry CatalogEntry) error {
+	if c == nil {
+		return fmt.Errorf("artifact catalog is nil")
+	}
+	sourceID := strings.TrimSpace(entry.SourceID)
+	if sourceID == "" {
+		return fmt.Errorf("source id is required")
+	}
+	if _, exists := c.entries[sourceID]; exists {
+		return fmt.Errorf("source id %q is already registered", sourceID)
+	}
+	entry.SourceID = sourceID
+	c.entries[sourceID] = entry
+	return nil
+}
+
+func runtimeBuiltInArtifactIDs() []string {
+	return []string{
+		ArtifactTranscriptMerged,
+		ArtifactTranscriptPolished,
+		ArtifactTranscriptFull,
+		ArtifactTranscriptTrimmed,
+		ArtifactBoundsSession,
+	}
+}

internal/artifacts/catalog_test.go

@@ -0,0 +1,188 @@
+package artifacts
+
+import "testing"
+
+func TestArtifactCatalogRegisterBuiltInsAndLookup(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterBuiltIns(); err != nil {
+		t.Fatalf("RegisterBuiltIns() error = %v", err)
+	}
+
+	entry, ok := catalog.Lookup(ArtifactTranscriptFull)
+	if !ok {
+		t.Fatalf("Lookup(%q) ok = false, want true", ArtifactTranscriptFull)
+	}
+	if !entry.Planned {
+		t.Fatalf("entry.Planned = false, want true")
+	}
+	if entry.Executable {
+		t.Fatalf("entry.Executable = true, want false")
+	}
+	if entry.CanonicalRelPath != "transcripts/normalized.json" {
+		t.Fatalf("entry.CanonicalRelPath = %q, want transcripts/normalized.json", entry.CanonicalRelPath)
+	}
+}
+
+func TestArtifactCatalogRegisterConfiguredArtifactsDefaultsToEnabled(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(map[string]ConfiguredArtifactDefinition{
+		"player_handout": {Enabled: false, OutputPath: "artifacts/player_handout.md"},
+		"session_recap":  {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+	}, nil); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+
+	recapID, ok := catalog.SourceIDForConfiguredKey("session_recap")
+	if !ok {
+		t.Fatal("SourceIDForConfiguredKey(session_recap) ok = false, want true")
+	}
+	recap, ok := catalog.Lookup(recapID)
+	if !ok {
+		t.Fatalf("Lookup(%q) ok = false, want true", recapID)
+	}
+	if !recap.Executable {
+		t.Fatalf("recap.Executable = false, want true")
+	}
+
+	handoutID, ok := catalog.SourceIDForConfiguredKey("player_handout")
+	if !ok {
+		t.Fatal("SourceIDForConfiguredKey(player_handout) ok = false, want true")
+	}
+	handout, ok := catalog.Lookup(handoutID)
+	if !ok {
+		t.Fatalf("Lookup(%q) ok = false, want true", handoutID)
+	}
+	if handout.Executable {
+		t.Fatalf("handout.Executable = true, want false")
+	}
+}
+
+func TestArtifactCatalogRegisterConfiguredArtifactsSelectedSetOverridesEnabled(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap":  {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+			"player_handout": {Enabled: false, OutputPath: "artifacts/player_handout.md"},
+		},
+		[]string{"player_handout"},
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+
+	entries := catalog.ListConfigured()
+	if len(entries) != 2 {
+		t.Fatalf("ListConfigured() len = %d, want 2", len(entries))
+	}
+	if entries[0].ConfiguredKey != "player_handout" || entries[0].Executable != true {
+		t.Fatalf("entries[0] = %+v, want player_handout executable", entries[0])
+	}
+	if entries[1].ConfiguredKey != "session_recap" || entries[1].Executable != false {
+		t.Fatalf("entries[1] = %+v, want session_recap disabled by selection", entries[1])
+	}
+}
+
+func TestArtifactCatalogRejectsSelectedUnknownArtifact(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		[]string{"unknown"},
+	)
+	if err == nil {
+		t.Fatal("RegisterConfiguredArtifacts() error = nil, want non-nil")
+	}
+}
+
+func TestArtifactCatalogRejectsConfiguredSourceConflictAcrossRegistrations(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() first call error = %v", err)
+	}
+	err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	)
+	if err == nil {
+		t.Fatal("RegisterConfiguredArtifacts() error = nil, want non-nil")
+	}
+}
+
+func TestArtifactCatalogMarkAvailableGenerated(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+
+	sourceID, _ := catalog.SourceIDForConfiguredKey("session_recap")
+	if err := catalog.MarkAvailableGenerated(sourceID, "/tmp/session_recap.md"); err != nil {
+		t.Fatalf("MarkAvailableGenerated() error = %v", err)
+	}
+	entry, _ := catalog.Lookup(sourceID)
+	if !entry.Available {
+		t.Fatalf("entry.Available = false, want true")
+	}
+	if entry.Provenance != ArtifactProvenanceGeneratedCurrentAnalyzeRun {
+		t.Fatalf("entry.Provenance = %q, want %q", entry.Provenance, ArtifactProvenanceGeneratedCurrentAnalyzeRun)
+	}
+}
+
+func TestArtifactCatalogMarkAvailableFromDisk(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: false, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+
+	sourceID, _ := catalog.SourceIDForConfiguredKey("session_recap")
+	if err := catalog.MarkAvailableFromDisk(sourceID, "/tmp/session_recap.md"); err != nil {
+		t.Fatalf("MarkAvailableFromDisk() error = %v", err)
+	}
+	entry, _ := catalog.Lookup(sourceID)
+	if !entry.Available {
+		t.Fatalf("entry.Available = false, want true")
+	}
+	if entry.Provenance != ArtifactProvenanceDisabledFromDisk {
+		t.Fatalf("entry.Provenance = %q, want %q", entry.Provenance, ArtifactProvenanceDisabledFromDisk)
+	}
+}
+
+func TestArtifactCatalogLookupPlannedButUnavailable(t *testing.T) {
+	catalog := NewArtifactCatalog()
+	if err := catalog.RegisterConfiguredArtifacts(
+		map[string]ConfiguredArtifactDefinition{
+			"session_recap": {Enabled: true, OutputPath: "artifacts/session_recap.md"},
+		},
+		nil,
+	); err != nil {
+		t.Fatalf("RegisterConfiguredArtifacts() error = %v", err)
+	}
+
+	sourceID, _ := catalog.SourceIDForConfiguredKey("session_recap")
+	entry, ok := catalog.Lookup(sourceID)
+	if !ok {
+		t.Fatalf("Lookup(%q) ok = false, want true", sourceID)
+	}
+	if !entry.Planned {
+		t.Fatalf("entry.Planned = false, want true")
+	}
+	if entry.Available {
+		t.Fatalf("entry.Available = true, want false")
+	}
+}

internal/artifacts/local.go

@@ -30,13 +30,13 @@ func NewLocalStore(workspaceRoot string) *LocalStore {
 	return &LocalStore{WorkspaceRoot: workspaceRoot}
 }
 
-// SessionPaths resolves canonical paths for a session workdir.
-func (s *LocalStore) SessionPaths(sessionID string) SessionPaths {
-	return buildSessionPaths(s.WorkspaceRoot, sessionID)
+// SessionPathsFor resolves canonical campaign-aware paths for a session workdir.
+func (s *LocalStore) SessionPathsFor(campaign, sessionID string) SessionPaths {
+	return buildSessionPaths(s.WorkspaceRoot, campaign, sessionID)
 }
 
-// EnsureLayout creates and verifies the canonical session workdir directory layout.
-func (s *LocalStore) EnsureLayout(sessionID string) (SessionPaths, error) {
+// EnsureLayoutFor creates and verifies campaign-aware session layout.
+func (s *LocalStore) EnsureLayoutFor(campaign, sessionID string) (SessionPaths, error) {
 	if strings.TrimSpace(s.WorkspaceRoot) == "" {
 		return SessionPaths{}, fmt.Errorf("workspace root is required")
 	}
@@ -44,7 +44,22 @@ func (s *LocalStore) EnsureLayout(sessionID string) (SessionPaths, error) {
 		return SessionPaths{}, fmt.Errorf("sessionID is required")
 	}
 
-	paths := s.SessionPaths(sessionID)
+	campaign = strings.TrimSpace(campaign)
+	if campaign == "" {
+		return SessionPaths{}, fmt.Errorf("campaign is required")
+	}
+
+	return s.ensureLayout(s.SessionPathsFor(campaign, sessionID))
+}
+
+func (s *LocalStore) ensureLayout(paths SessionPaths) (SessionPaths, error) {
+	if strings.TrimSpace(s.WorkspaceRoot) == "" {
+		return SessionPaths{}, fmt.Errorf("workspace root is required")
+	}
+	if strings.TrimSpace(paths.SessionID) == "" {
+		return SessionPaths{}, fmt.Errorf("sessionID is required")
+	}
+
 	dirs := []string{
 		paths.Root,
 		paths.InputsDir,
@@ -53,8 +68,11 @@ func (s *LocalStore) EnsureLayout(sessionID string) (SessionPaths, error) {
 		paths.TranscriptsRawDir,
 		paths.TranscriptsTrimmedDir,
 		paths.ArtifactsDir,
+		paths.ReportsDir,
 		paths.ConfigDir,
 		paths.LogsDir,
+		paths.CurrentDir,
+		paths.RunsDir,
 	}
 
 	for _, dir := range dirs {
@@ -66,13 +84,16 @@ func (s *LocalStore) EnsureLayout(sessionID string) (SessionPaths, error) {
 	return paths, nil
 }
 
-// CopyInput copies an input file into the session workdir under destRelativePath.
-func (s *LocalStore) CopyInput(sessionID, srcPath, destRelativePath string) (Ref, error) {
-	paths, err := s.EnsureLayout(sessionID)
+// CopyInputFor copies an input file into the campaign-aware session workdir under destRelativePath.
+func (s *LocalStore) CopyInputFor(campaign, sessionID, srcPath, destRelativePath string) (Ref, error) {
+	paths, err := s.EnsureLayoutFor(campaign, sessionID)
 	if err != nil {
 		return Ref{}, err
 	}
+	return s.copyInputWithPaths(paths, sessionID, srcPath, destRelativePath)
+}
 
+func (s *LocalStore) copyInputWithPaths(paths SessionPaths, sessionID, srcPath, destRelativePath string) (Ref, error) {
 	destAbs, err := resolveInRoot(paths.Root, destRelativePath)
 	if err != nil {
 		return Ref{}, fmt.Errorf("copy input: %w", err)
@@ -173,13 +194,16 @@ func (s *LocalStore) Checksum(path string) (string, error) {
 	return digest, nil
 }
 
-// AcquireSessionLock acquires an exclusive lock file for a session workdir.
-func (s *LocalStore) AcquireSessionLock(sessionID string) (*LockHandle, error) {
-	paths, err := s.EnsureLayout(sessionID)
+// AcquireSessionLockFor acquires an exclusive lock file for a campaign/session workdir.
+func (s *LocalStore) AcquireSessionLockFor(campaign, sessionID string) (*LockHandle, error) {
+	paths, err := s.EnsureLayoutFor(campaign, sessionID)
 	if err != nil {
 		return nil, err
 	}
+	return s.acquireSessionLockForPaths(paths)
+}
 
+func (s *LocalStore) acquireSessionLockForPaths(paths SessionPaths) (*LockHandle, error) {
 	f, err := os.OpenFile(paths.LockPath, os.O_CREATE|os.O_EXCL|os.O_WRONLY, 0o644)
 	if err != nil {
 		if errors.Is(err, os.ErrExist) {

internal/artifacts/local_test.go

@@ -10,9 +10,9 @@ import (
 
 func TestEnsureLayoutCreatesExpectedDirectories(t *testing.T) {
 	store := NewLocalStore(t.TempDir())
-	paths, err := store.EnsureLayout("session-1")
+	paths, err := store.EnsureLayoutFor("sample-campaign", "session-1")
 	if err != nil {
-		t.Fatalf("EnsureLayout() error = %v", err)
+		t.Fatalf("EnsureLayoutFor() error = %v", err)
 	}
 
 	checkDirExists(t, paths.Root)
@@ -22,8 +22,11 @@ func TestEnsureLayoutCreatesExpectedDirectories(t *testing.T) {
 	checkDirExists(t, paths.TranscriptsRawDir)
 	checkDirExists(t, paths.TranscriptsTrimmedDir)
 	checkDirExists(t, paths.ArtifactsDir)
+	checkDirExists(t, paths.ReportsDir)
 	checkDirExists(t, paths.ConfigDir)
 	checkDirExists(t, paths.LogsDir)
+	checkDirExists(t, paths.CurrentDir)
+	checkDirExists(t, paths.RunsDir)
 
 	if filepath.Base(paths.ManifestPath) != "manifest.json" {
 		t.Fatalf("ManifestPath = %q, want basename manifest.json", paths.ManifestPath)
@@ -33,6 +36,17 @@ func TestEnsureLayoutCreatesExpectedDirectories(t *testing.T) {
 	}
 }
 
+func TestEnsureLayoutForRequiresCampaign(t *testing.T) {
+	store := NewLocalStore(t.TempDir())
+	_, err := store.EnsureLayoutFor("", "session-1")
+	if err == nil {
+		t.Fatal("expected campaign-required error, got nil")
+	}
+	if !strings.Contains(err.Error(), "campaign is required") {
+		t.Fatalf("error = %v, want campaign-required error", err)
+	}
+}
+
 func TestChecksumCalculation(t *testing.T) {
 	store := NewLocalStore(t.TempDir())
 	path := filepath.Join(t.TempDir(), "sample.txt")
@@ -53,9 +67,9 @@ func TestChecksumCalculation(t *testing.T) {
 func TestLockAcquireRelease(t *testing.T) {
 	store := NewLocalStore(t.TempDir())
 
-	lock, err := store.AcquireSessionLock("session-1")
+	lock, err := store.AcquireSessionLockFor("sample-campaign", "session-1")
 	if err != nil {
-		t.Fatalf("AcquireSessionLock() error = %v", err)
+		t.Fatalf("AcquireSessionLockFor() error = %v", err)
 	}
 
 	exists, err := store.Exists(lock.path)
@@ -81,15 +95,15 @@ func TestLockAcquireRelease(t *testing.T) {
 
 func TestLockConflict(t *testing.T) {
 	store := NewLocalStore(t.TempDir())
-	lock1, err := store.AcquireSessionLock("session-1")
+	lock1, err := store.AcquireSessionLockFor("sample-campaign", "session-1")
 	if err != nil {
-		t.Fatalf("first AcquireSessionLock() error = %v", err)
+		t.Fatalf("first AcquireSessionLockFor() error = %v", err)
 	}
 	defer func() {
 		_ = store.ReleaseSessionLock(lock1)
 	}()
 
-	_, err = store.AcquireSessionLock("session-1")
+	_, err = store.AcquireSessionLockFor("sample-campaign", "session-1")
 	if err == nil {
 		t.Fatal("expected lock conflict error, got nil")
 	}
@@ -138,9 +152,9 @@ func TestCopyInput(t *testing.T) {
 		t.Fatalf("WriteFile() error = %v", err)
 	}
 
-	ref, err := store.CopyInput("session-1", srcPath, "inputs/speakers.yml")
+	ref, err := store.CopyInputFor("sample-campaign", "session-1", srcPath, "inputs/speakers.yml")
 	if err != nil {
-		t.Fatalf("CopyInput() error = %v", err)
+		t.Fatalf("CopyInputFor() error = %v", err)
 	}
 
 	if ref.Kind != "input" {

internal/artifacts/paths.go

@@ -1,10 +1,16 @@
 package artifacts
 
-import "path/filepath"
+import (
+	"path/filepath"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
 
 // SessionPaths contains canonical local paths for one session work directory.
 type SessionPaths struct {
 	WorkspaceRoot         string
+	CampaignID            string
+	SessionID             string
 	Root                  string
 	InputsDir             string
 	AudioDir              string
@@ -12,32 +18,73 @@ type SessionPaths struct {
 	TranscriptsRawDir     string
 	TranscriptsTrimmedDir string
 	ArtifactsDir          string
+	ReportsDir            string
 	ConfigDir             string
 	LogsDir               string
+	CurrentDir            string
+	RunsDir               string
 	ManifestPath          string
 	LockPath              string
 }
 
-// SessionWorkDir returns the work directory for one session.
-func SessionWorkDir(rootDir, sessionID string) string {
-	return filepath.Join(rootDir, "work", sessionID)
+// SessionWorkDirForCampaign returns the canonical campaign-aware work directory for one session.
+func SessionWorkDirForCampaign(rootDir, campaign, sessionID string) string {
+	return filepath.Join(rootDir, config.PathWorkDirSegment, campaign, sessionID)
 }
 
-func buildSessionPaths(workspaceRoot, sessionID string) SessionPaths {
-	root := SessionWorkDir(workspaceRoot, sessionID)
-	transcripts := filepath.Join(root, "transcripts")
+// SessionManifestPathForCampaign returns the canonical session manifest path.
+func SessionManifestPathForCampaign(rootDir, campaign, sessionID string) string {
+	return filepath.Join(SessionWorkDirForCampaign(rootDir, campaign, sessionID), config.PathManifestFile)
+}
+
+// SessionRunsDirForCampaign returns the canonical runs directory for one session.
+func SessionRunsDirForCampaign(rootDir, campaign, sessionID string) string {
+	return filepath.Join(SessionWorkDirForCampaign(rootDir, campaign, sessionID), config.PathRunsDirSegment)
+}
+
+// SessionRunRootForCampaign returns the canonical run root under runs/{run_id}.
+func SessionRunRootForCampaign(rootDir, campaign, sessionID, runID string) string {
+	return filepath.Join(SessionRunsDirForCampaign(rootDir, campaign, sessionID), runID)
+}
+
+// SessionRunManifestPathForCampaign returns the canonical run manifest path under runs/{run_id}/manifest.json.
+func SessionRunManifestPathForCampaign(rootDir, campaign, sessionID, runID string) string {
+	return filepath.Join(SessionRunRootForCampaign(rootDir, campaign, sessionID, runID), config.PathManifestFile)
+}
+
+// SessionRunStageDirForCampaign returns the canonical stage directory under runs/{run_id}/{stage}.
+func SessionRunStageDirForCampaign(rootDir, campaign, sessionID, runID, stageName string) string {
+	return filepath.Join(SessionRunRootForCampaign(rootDir, campaign, sessionID, runID), stageName)
+}
+
+// SessionSpoolAudioDir returns the campaign/session/run scoped local spool audio path.
+func SessionSpoolAudioDir(spoolRoot, campaign, sessionID, runID string) string {
+	return filepath.Join(spoolRoot, campaign, sessionID, runID, config.PathAudioDirSegment)
+}
+
+func buildSessionPaths(workspaceRoot, campaign, sessionID string) SessionPaths {
+	root := SessionWorkDirForCampaign(workspaceRoot, campaign, sessionID)
+	return buildSessionPathsFromRoot(workspaceRoot, campaign, sessionID, root)
+}
+
+func buildSessionPathsFromRoot(workspaceRoot, campaign, sessionID, root string) SessionPaths {
 	return SessionPaths{
 		WorkspaceRoot:         workspaceRoot,
+		CampaignID:            campaign,
+		SessionID:             sessionID,
 		Root:                  root,
-		InputsDir:             filepath.Join(root, "inputs"),
-		AudioDir:              filepath.Join(root, "audio"),
-		TranscriptsDir:        transcripts,
-		TranscriptsRawDir:     filepath.Join(transcripts, "raw"),
-		TranscriptsTrimmedDir: filepath.Join(transcripts, "trimmed"),
-		ArtifactsDir:          filepath.Join(root, "artifacts"),
-		ConfigDir:             filepath.Join(root, "config"),
-		LogsDir:               filepath.Join(root, "logs"),
-		ManifestPath:          filepath.Join(root, "manifest.json"),
-		LockPath:              filepath.Join(root, ".lock"),
+		InputsDir:             filepath.Join(root, config.PathInputsDirSegment),
+		AudioDir:              filepath.Join(root, config.PathAudioDirSegment),
+		TranscriptsDir:        filepath.Join(root, config.PathTranscriptsSegment),
+		TranscriptsRawDir:     filepath.Join(root, filepath.FromSlash(config.PathTranscriptsRaw)),
+		TranscriptsTrimmedDir: filepath.Join(root, filepath.FromSlash(config.PathTranscriptsTrimmed)),
+		ArtifactsDir:          filepath.Join(root, config.PathArtifactsDirSegment),
+		ReportsDir:            filepath.Join(root, config.PathReportsDirSegment),
+		ConfigDir:             filepath.Join(root, config.PathConfigDirSegment),
+		LogsDir:               filepath.Join(root, config.PathLogsDirSegment),
+		CurrentDir:            filepath.Join(root, config.PathCurrentDirSegment),
+		RunsDir:               filepath.Join(root, config.PathRunsDirSegment),
+		ManifestPath:          filepath.Join(root, config.PathManifestFile),
+		LockPath:              filepath.Join(root, config.PathLockFile),
 	}
 }

internal/artifacts/paths_model_test.go

@@ -0,0 +1,59 @@
+package artifacts
+
+import (
+	"path/filepath"
+	"testing"
+)
+
+func TestSessionWorkDirForCampaign(t *testing.T) {
+	root := "/tmp/workspace"
+	got := SessionWorkDirForCampaign(root, "forsaken", "2026-04-19")
+	want := filepath.Join(root, "work", "forsaken", "2026-04-19")
+	if got != want {
+		t.Fatalf("SessionWorkDirForCampaign() = %q, want %q", got, want)
+	}
+}
+
+func TestSessionManifestPathForCampaign(t *testing.T) {
+	root := "/tmp/workspace"
+	got := SessionManifestPathForCampaign(root, "forsaken", "2026-04-19")
+	want := filepath.Join(root, "work", "forsaken", "2026-04-19", "manifest.json")
+	if got != want {
+		t.Fatalf("SessionManifestPathForCampaign() = %q, want %q", got, want)
+	}
+}
+
+func TestSessionRunRootAndStageDirForCampaign(t *testing.T) {
+	root := "/tmp/workspace"
+	runID := "20260515T031522Z-a1b2c3d4"
+	runRoot := SessionRunRootForCampaign(root, "forsaken", "2026-04-19", runID)
+	wantRoot := filepath.Join(root, "work", "forsaken", "2026-04-19", "runs", runID)
+	if runRoot != wantRoot {
+		t.Fatalf("SessionRunRootForCampaign() = %q, want %q", runRoot, wantRoot)
+	}
+
+	stageDir := SessionRunStageDirForCampaign(root, "forsaken", "2026-04-19", runID, "transcribe")
+	wantStage := filepath.Join(root, "work", "forsaken", "2026-04-19", "runs", runID, "transcribe")
+	if stageDir != wantStage {
+		t.Fatalf("SessionRunStageDirForCampaign() = %q, want %q", stageDir, wantStage)
+	}
+}
+
+func TestSessionRunManifestPathForCampaign(t *testing.T) {
+	root := "/tmp/workspace"
+	runID := "20260515T031522Z-a1b2c3d4"
+	got := SessionRunManifestPathForCampaign(root, "forsaken", "2026-04-19", runID)
+	want := filepath.Join(root, "work", "forsaken", "2026-04-19", "runs", runID, "manifest.json")
+	if got != want {
+		t.Fatalf("SessionRunManifestPathForCampaign() = %q, want %q", got, want)
+	}
+}
+
+func TestSessionSpoolAudioDir(t *testing.T) {
+	root := "/var/spool/narratio"
+	got := SessionSpoolAudioDir(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4")
+	want := filepath.Join(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4", "audio")
+	if got != want {
+		t.Fatalf("SessionSpoolAudioDir() = %q, want %q", got, want)
+	}
+}

internal/artifacts/resolve_test.go

@@ -8,7 +8,7 @@ import (
 
 func TestResolveSessionLocalPathForRead(t *testing.T) {
 	workspace := t.TempDir()
-	paths := buildSessionPaths(workspace, "s-1")
+	paths := buildSessionPaths(workspace, "sample-campaign", "s-1")
 	if err := os.MkdirAll(paths.TranscriptsRawDir, 0o755); err != nil {
 		t.Fatalf("MkdirAll() error = %v", err)
 	}
@@ -41,7 +41,7 @@ func TestResolveSessionLocalPathForReadRelativeWorkspaceRootQualifiedPath(t *tes
 		t.Fatalf("Rel() error = %v", err)
 	}
 
-	paths := buildSessionPaths(workspaceRel, "s-1")
+	paths := buildSessionPaths(workspaceRel, "sample-campaign", "s-1")
 	target := filepath.Join(paths.TranscriptsRawDir, "alice.json")
 	if err := os.MkdirAll(filepath.Dir(target), 0o755); err != nil {
 		t.Fatalf("MkdirAll() error = %v", err)
@@ -50,7 +50,7 @@ func TestResolveSessionLocalPathForReadRelativeWorkspaceRootQualifiedPath(t *tes
 		t.Fatalf("WriteFile() error = %v", err)
 	}
 
-	manifestPath := filepath.Join(workspaceRel, "work", "s-1", "transcripts", "raw", "alice.json")
+	manifestPath := filepath.Join(workspaceRel, "work", "sample-campaign", "s-1", "transcripts", "raw", "alice.json")
 	got := ResolveSessionLocalPathForRead(paths, manifestPath)
 	if got != filepath.Clean(manifestPath) {
 		t.Fatalf("resolution = %q, want %q", got, filepath.Clean(manifestPath))

internal/artifacts/run_id.go

@@ -0,0 +1,30 @@
+package artifacts
+
+import (
+	"crypto/rand"
+	"encoding/hex"
+	"fmt"
+	"io"
+	"time"
+)
+
+// NewRunID returns a run ID in format: YYYYMMDDTHHMMSSZ-xxxxxxxx.
+func NewRunID() (string, error) {
+	return NewRunIDWith(time.Now().UTC(), rand.Reader)
+}
+
+// NewRunIDWith returns a run ID in format: YYYYMMDDTHHMMSSZ-xxxxxxxx
+// using an injected timestamp and randomness source.
+func NewRunIDWith(now time.Time, random io.Reader) (string, error) {
+	if random == nil {
+		random = rand.Reader
+	}
+
+	var suffix [4]byte
+	if _, err := io.ReadFull(random, suffix[:]); err != nil {
+		return "", fmt.Errorf("generate run id random suffix: %w", err)
+	}
+
+	ts := now.UTC().Format("20060102T150405Z")
+	return ts + "-" + hex.EncodeToString(suffix[:]), nil
+}

internal/artifacts/run_id_test.go

@@ -0,0 +1,37 @@
+package artifacts
+
+import (
+	"bytes"
+	"regexp"
+	"strings"
+	"testing"
+	"time"
+)
+
+func TestNewRunIDWithFormat(t *testing.T) {
+	now := time.Date(2026, 5, 15, 3, 15, 22, 0, time.UTC)
+	random := bytes.NewReader([]byte{0xa1, 0xb2, 0xc3, 0xd4})
+
+	runID, err := NewRunIDWith(now, random)
+	if err != nil {
+		t.Fatalf("NewRunIDWith() error = %v", err)
+	}
+	if runID != "20260515T031522Z-a1b2c3d4" {
+		t.Fatalf("runID = %q, want %q", runID, "20260515T031522Z-a1b2c3d4")
+	}
+}
+
+func TestNewRunIDWithShape(t *testing.T) {
+	runID, err := NewRunIDWith(time.Now().UTC(), bytes.NewReader([]byte{0x01, 0x02, 0x03, 0x04}))
+	if err != nil {
+		t.Fatalf("NewRunIDWith() error = %v", err)
+	}
+	pattern := regexp.MustCompile(`^\d{8}T\d{6}Z-[0-9a-f]{8}$`)
+	if !pattern.MatchString(runID) {
+		t.Fatalf("runID = %q, want pattern %q", runID, pattern.String())
+	}
+	suffix := runID[len(runID)-8:]
+	if strings.ToLower(suffix) != suffix {
+		t.Fatalf("runID suffix = %q, want lowercase", suffix)
+	}
+}

internal/artifacts/s3.go

@@ -11,19 +11,19 @@ type S3Store struct {
 	Prefix string
 }
 
-// SessionPaths is not implemented for S3-backed storage.
-func (s *S3Store) SessionPaths(_ string) SessionPaths {
+// SessionPathsFor is not implemented for S3-backed storage.
+func (s *S3Store) SessionPathsFor(_, _ string) SessionPaths {
 	return SessionPaths{}
 }
 
-// EnsureLayout returns a not-yet-implemented error in the scaffold.
-func (s *S3Store) EnsureLayout(_ string) (SessionPaths, error) {
-	return SessionPaths{}, fmt.Errorf("artifacts s3 ensure layout: not yet implemented")
+// EnsureLayoutFor returns a not-yet-implemented error in the scaffold.
+func (s *S3Store) EnsureLayoutFor(_, _ string) (SessionPaths, error) {
+	return SessionPaths{}, fmt.Errorf("artifacts s3 ensure layout for campaign/session: not yet implemented")
 }
 
-// CopyInput returns a not-yet-implemented error in the scaffold.
-func (s *S3Store) CopyInput(_, _, _ string) (Ref, error) {
-	return Ref{}, fmt.Errorf("artifacts s3 copy input: not yet implemented")
+// CopyInputFor returns a not-yet-implemented error in the scaffold.
+func (s *S3Store) CopyInputFor(_, _, _, _ string) (Ref, error) {
+	return Ref{}, fmt.Errorf("artifacts s3 copy input for campaign/session: not yet implemented")
 }
 
 // Exists returns a not-yet-implemented error in the scaffold.
@@ -46,9 +46,9 @@ func (s *S3Store) Checksum(_ string) (string, error) {
 	return "", fmt.Errorf("artifacts s3 checksum: not yet implemented")
 }
 
-// AcquireSessionLock returns a not-yet-implemented error in the scaffold.
-func (s *S3Store) AcquireSessionLock(_ string) (*LockHandle, error) {
-	return nil, fmt.Errorf("artifacts s3 acquire lock: not yet implemented")
+// AcquireSessionLockFor returns a not-yet-implemented error in the scaffold.
+func (s *S3Store) AcquireSessionLockFor(_, _ string) (*LockHandle, error) {
+	return nil, fmt.Errorf("artifacts s3 acquire lock for campaign/session: not yet implemented")
 }
 
 // ReleaseSessionLock returns a not-yet-implemented error in the scaffold.

internal/artifacts/s3_keys.go

@@ -0,0 +1,75 @@
+package artifacts
+
+import (
+	"path"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/narratio/internal/config"
+)
+
+// S3SessionPrefix builds the canonical S3 session prefix.
+// Format: {root_prefix}/campaigns/{campaign}/sessions/{session_id}/
+func S3SessionPrefix(rootPrefix, campaign, sessionID string) string {
+	prefix := path.Join(
+		cleanS3PathPart(rootPrefix),
+		config.S3CampaignsSegment,
+		cleanS3PathPart(campaign),
+		config.S3SessionsSegment,
+		cleanS3PathPart(sessionID),
+	)
+	return ensureS3TrailingSlash(prefix)
+}
+
+// S3RunPrefix builds the canonical S3 run prefix.
+// Format: {session_prefix}/runs/{run_id}/
+func S3RunPrefix(sessionPrefix, runID string) string {
+	prefix := path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), config.S3RunsSegment, cleanS3PathPart(runID))
+	return ensureS3TrailingSlash(prefix)
+}
+
+// S3AudioPrefix builds the session audio prefix from configured audio_s3.prefix.
+// Format: {session_prefix}/{audio_s3.prefix}
+func S3AudioPrefix(sessionPrefix, audioPrefix string) string {
+	key := path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), cleanS3Key(audioPrefix))
+	return ensureS3TrailingSlash(key)
+}
+
+// S3CurrentManifestKey returns the current manifest pointer key.
+// Format: {session_prefix}/current/manifest.json
+func S3CurrentManifestKey(sessionPrefix string) string {
+	return path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), config.S3CurrentSegment, config.S3ManifestFile)
+}
+
+// S3CurrentRunPointerKey returns the current run pointer key.
+// Format: {session_prefix}/current/run_id.txt
+func S3CurrentRunPointerKey(sessionPrefix string) string {
+	return path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), config.S3CurrentSegment, config.S3RunIDFile)
+}
+
+// S3PromotedArtifactKey returns the destination key for one promoted artifact.
+// Format: {session_prefix}/{promotion.to}
+func S3PromotedArtifactKey(sessionPrefix, to string) string {
+	return path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), cleanS3Key(to))
+}
+
+// S3RunRelativeDestinationKey returns a run-scoped key for a workdir-relative path.
+// Format: {run_prefix}/{relative_workdir_path}
+func S3RunRelativeDestinationKey(runPrefix, relativeWorkdirPath string) string {
+	return path.Join(strings.TrimSuffix(cleanS3Key(runPrefix), "/"), cleanS3Key(relativeWorkdirPath))
+}
+
+func ensureS3TrailingSlash(v string) string {
+	key := cleanS3Key(v)
+	if key == "" {
+		return ""
+	}
+	return strings.TrimSuffix(key, "/") + "/"
+}
+
+func cleanS3PathPart(v string) string {
+	return strings.Trim(strings.ReplaceAll(strings.TrimSpace(v), "\\", "/"), "/")
+}
+
+func cleanS3Key(v string) string {
+	return strings.ReplaceAll(strings.TrimSpace(v), "\\", "/")
+}

internal/artifacts/s3_keys_test.go

@@ -0,0 +1,45 @@
+package artifacts
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestS3KeyConstruction(t *testing.T) {
+	runID := "20260515T031522Z-a1b2c3d4"
+	sessionPrefix := S3SessionPrefix("dnd", "forsaken", "2026-04-19")
+	if sessionPrefix != "dnd/campaigns/forsaken/sessions/2026-04-19/" {
+		t.Fatalf("sessionPrefix = %q", sessionPrefix)
+	}
+
+	audioPrefix := S3AudioPrefix(sessionPrefix, "audio/")
+	if audioPrefix != "dnd/campaigns/forsaken/sessions/2026-04-19/audio/" {
+		t.Fatalf("audioPrefix = %q", audioPrefix)
+	}
+
+	runPrefix := S3RunPrefix(sessionPrefix, runID)
+	wantRunPrefix := "dnd/campaigns/forsaken/sessions/2026-04-19/runs/" + runID + "/"
+	if runPrefix != wantRunPrefix {
+		t.Fatalf("runPrefix = %q, want %q", runPrefix, wantRunPrefix)
+	}
+
+	runPointer := S3CurrentRunPointerKey(sessionPrefix)
+	if runPointer != "dnd/campaigns/forsaken/sessions/2026-04-19/current/run_id.txt" {
+		t.Fatalf("run pointer key = %q", runPointer)
+	}
+
+	manifestKey := S3CurrentManifestKey(sessionPrefix)
+	if manifestKey != "dnd/campaigns/forsaken/sessions/2026-04-19/current/manifest.json" {
+		t.Fatalf("manifest key = %q", manifestKey)
+	}
+
+	promoted := S3PromotedArtifactKey(sessionPrefix, "transcripts/trimmed.json")
+	if promoted != "dnd/campaigns/forsaken/sessions/2026-04-19/transcripts/trimmed.json" {
+		t.Fatalf("promoted key = %q", promoted)
+	}
+
+	runRelative := S3RunRelativeDestinationKey(runPrefix, `logs\whisperx.stdout.log`)
+	if !strings.HasSuffix(runRelative, "/logs/whisperx.stdout.log") {
+		t.Fatalf("runRelative key = %q, want normalized forward slashes", runRelative)
+	}
+}

internal/artifacts/store.go

@@ -15,13 +15,13 @@ type Ref struct {
 
 // Store is the local artifact/workdir abstraction used by orchestration code.
 type Store interface {
-	SessionPaths(sessionID string) SessionPaths
-	EnsureLayout(sessionID string) (SessionPaths, error)
-	CopyInput(sessionID, srcPath, destRelativePath string) (Ref, error)
+	SessionPathsFor(campaign, sessionID string) SessionPaths
+	EnsureLayoutFor(campaign, sessionID string) (SessionPaths, error)
+	CopyInputFor(campaign, sessionID, srcPath, destRelativePath string) (Ref, error)
 	Exists(path string) (bool, error)
 	ExistsRef(ref Ref) (bool, error)
 	WriteFileAtomic(path string, data []byte, perm os.FileMode) error
 	Checksum(path string) (string, error)
-	AcquireSessionLock(sessionID string) (*LockHandle, error)
+	AcquireSessionLockFor(campaign, sessionID string) (*LockHandle, error)
 	ReleaseSessionLock(lock *LockHandle) error
 }

internal/config/config.go

@@ -12,6 +12,9 @@ type Config struct {
 type PipelineConfig struct {
 	Workspace    WorkspaceConfig    `yaml:"workspace"`
 	Storage      StorageConfig      `yaml:"storage"`
+	Spool        SpoolConfig        `yaml:"spool"`
+	Archive      *ArchiveConfig     `yaml:"archive"`
+	Secrets      *SecretsConfig     `yaml:"secrets"`
 	WhisperX     WhisperXConfig     `yaml:"whisperx"`
 	Seriatim     SeriatimConfig     `yaml:"seriatim"`
 	Audita       AuditaConfig       `yaml:"audita"`
@@ -33,14 +36,52 @@ type SessionConfig struct {
 
 // WorkspaceConfig configures local workspace behavior.
 type WorkspaceConfig struct {
-	Root string `yaml:"root"`
+	Root                string `yaml:"root"`
+	CleanupAfterArchive bool   `yaml:"cleanup_after_archive"`
+}
+
+// SecretsConfig configures optional local filesystem secret loading.
+type SecretsConfig struct {
+	EnvDir string `yaml:"env_dir"`
 }
 
 // StorageConfig configures storage backends and related parameters.
 type StorageConfig struct {
-	Backend string `yaml:"backend"`
-	Bucket  string `yaml:"bucket"`
-	Prefix  string `yaml:"prefix"`
+	Backend string           `yaml:"backend"`
+	Bucket  string           `yaml:"bucket"`
+	Prefix  string           `yaml:"prefix"`
+	S3      *StorageS3Config `yaml:"s3"`
+}
+
+// StorageS3Config configures S3 storage coordinates.
+type StorageS3Config struct {
+	Bucket         string `yaml:"bucket"`
+	RootPrefix     string `yaml:"root_prefix"`
+	Region         string `yaml:"region"`
+	Endpoint       string `yaml:"endpoint"`
+	ForcePathStyle bool   `yaml:"force_path_style"`
+	AccessKeyIDEnv string `yaml:"access_key_id_env"`
+	SecretKeyEnv   string `yaml:"secret_access_key_env"`
+}
+
+// SpoolConfig configures local spool storage for staged data.
+type SpoolConfig struct {
+	Root                    string `yaml:"root"`
+	DeleteAudioAfterArchive bool   `yaml:"delete_audio_after_archive"`
+}
+
+// ArchiveConfig configures archive behavior and artifact promotions.
+type ArchiveConfig struct {
+	Enabled          *bool                  `yaml:"enabled"`
+	UploadRun        *bool                  `yaml:"upload_run"`
+	PromoteArtifacts []ArchivePromotionRule `yaml:"promote_artifacts"`
+}
+
+// ArchivePromotionRule configures one artifact promotion mapping.
+type ArchivePromotionRule struct {
+	From     string `yaml:"from"`
+	To       string `yaml:"to"`
+	Required *bool  `yaml:"required"`
 }
 
 // WhisperXConfig configures WhisperX adapter settings.
@@ -79,9 +120,14 @@ type AuditaConfig struct {
 	Modules                  []string `yaml:"modules"`
 	BaseURL                  string   `yaml:"base_url"`
 	Model                    string   `yaml:"model"`
-	LLMConcurrency           *int     `yaml:"llm_concurrency"`
+	TotalLLMConcurrency      *int     `yaml:"total_llm_concurrency"`
+	ProposalLLMConcurrency   *int     `yaml:"proposal_llm_concurrency"`
 	ValidationModel          string   `yaml:"validation_model"`
 	ValidationLLMConcurrency *int     `yaml:"validation_llm_concurrency"`
+	TranscriptDescription    string   `yaml:"transcript_description"`
+	ConfigPath               string   `yaml:"config_path"`
+	OutputSchema             string   `yaml:"output_schema"`
+	WorkDirRetention         string   `yaml:"work_dir_retention"`
 	Report                   *bool    `yaml:"report"`
 }
 
@@ -130,6 +176,7 @@ type ScriptoriumConfig struct {
 // ScriptoriumArtifactConfig configures one named output artifact workflow.
 type ScriptoriumArtifactConfig struct {
 	Enabled     bool                              `yaml:"enabled"`
+	DependsOn   []string                          `yaml:"depends_on"`
 	RenderDebug *bool                             `yaml:"render_debug"`
 	PromptID    string                            `yaml:"prompt_id"`
 	ProfileID   string                            `yaml:"profile_id"`
@@ -169,9 +216,15 @@ type ArtifactSettings struct {
 
 // SessionInputsConfig contains per-session input references.
 type SessionInputsConfig struct {
-	AudioDir        string   `yaml:"audio_dir"`
-	AudioFiles      []string `yaml:"audio_files"`
-	SpeakersFile    string   `yaml:"speakers_file"`
-	AutocorrectFile string   `yaml:"autocorrect_file"`
-	GlossaryFile    string   `yaml:"glossary_file"`
+	AudioDir        string               `yaml:"audio_dir"`
+	AudioFiles      []string             `yaml:"audio_files"`
+	AudioS3         *SessionAudioS3Input `yaml:"audio_s3"`
+	SpeakersFile    string               `yaml:"speakers_file"`
+	AutocorrectFile string               `yaml:"autocorrect_file"`
+	GlossaryFile    string               `yaml:"glossary_file"`
+}
+
+// SessionAudioS3Input configures S3 session-audio input discovery.
+type SessionAudioS3Input struct {
+	Prefix string `yaml:"prefix"`
 }

internal/config/defaults.go

@@ -0,0 +1,100 @@
+package config
+
+// Default filesystem locations for pipeline configuration lookup when --config
+// is omitted. Order is highest to lowest precedence.
+const (
+	DefaultPipelineConfigPathUsrLocal = "/usr/local/etc/narratio/pipeline.yml"
+	DefaultPipelineConfigPathEtc      = "/etc/narratio/pipeline.yml"
+	DefaultSessionConfigPathLocal     = "./session.yml"
+	DefaultSessionConfigPathUsrLocal  = "/usr/local/etc/narratio/session.yml"
+	DefaultSessionConfigPathEtc       = "/etc/narratio/session.yml"
+	DefaultS3AccessKeyIDEnv           = "OBJECT_STORAGE_KEY_ID"
+	DefaultS3SecretAccessKeyEnv       = "OBJECT_STORAGE_KEY"
+	DefaultStorageS3RootPrefix        = "dnd"
+	DefaultWorkspaceRoot              = "/var/lib/narratio"
+	DefaultSpoolRoot                  = "/var/spool/narratio"
+
+	DefaultWhisperXLanguage    = "en"
+	DefaultWhisperXTimeout     = "30m"
+	DefaultWhisperXRetryDelay  = "2s"
+	DefaultWhisperXConcurrency = 2
+	DefaultWhisperXRetries     = 3
+
+	DefaultSeriatimBinary       = "seriatim"
+	DefaultSeriatimTimeout      = "10m"
+	DefaultSeriatimOutputSchema = "seriatim-intermediate"
+	DefaultSeriatimCoalesceGap  = 3.0
+	DefaultSeriatimReport       = true
+
+	DefaultAuditaBinary  = "audita"
+	DefaultAuditaTimeout = "3h"
+	DefaultAuditaReport  = true
+
+	DefaultScriptoriumBinary             = "scriptorium"
+	DefaultScriptoriumTimeout            = "10m"
+	DefaultScriptoriumArtifactOutputRoot = "artifacts"
+
+	DefaultTrimBoundsTimeout  = "10m"
+	DefaultTrimSeriatimReport = false
+
+	DefaultNormalizeOutputPath   = "transcripts/normalized.json"
+	DefaultNormalizeOutputSchema = "seriatim-intermediate"
+	DefaultNormalizeReport       = true
+
+	DefaultArchiveEnabled   = true
+	DefaultArchiveUploadRun = true
+
+	PathWorkDirSegment       = "work"
+	PathInputsDirSegment     = "inputs"
+	PathAudioDirSegment      = "audio"
+	PathTranscriptsSegment   = "transcripts"
+	PathTranscriptsRaw       = "transcripts/raw"
+	PathTranscriptsTrimmed   = "transcripts/trimmed"
+	PathArtifactsDirSegment  = "artifacts"
+	PathReportsDirSegment    = "reports"
+	PathConfigDirSegment     = "config"
+	PathLogsDirSegment       = "logs"
+	PathCurrentDirSegment    = "current"
+	PathRunsDirSegment       = "runs"
+	PathManifestFile         = "manifest.json"
+	PathLockFile             = ".lock"
+	PathTranscriptMerged     = "transcripts/merged.json"
+	PathTranscriptProcessed  = "transcripts/processed.json"
+	PathTranscriptNormalized = "transcripts/normalized.json"
+	PathTranscriptTrimmed    = "transcripts/trimmed.json"
+
+	S3CampaignsSegment = "campaigns"
+	S3SessionsSegment  = "sessions"
+	S3RunsSegment      = "runs"
+	S3CurrentSegment   = "current"
+	S3ManifestFile     = "manifest.json"
+	S3RunIDFile        = "run_id.txt"
+)
+
+// DefaultArchivePromoteArtifacts defines the default archive promotion rules.
+// Callers should copy this slice before mutating.
+var DefaultArchivePromoteArtifacts = []ArchivePromotionRule{
+	{From: PathTranscriptTrimmed, To: PathTranscriptTrimmed},
+	{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md"},
+}
+
+// DefaultPipelineConfigSearchPaths defines the default search order for
+// pipeline.yml when callers do not provide an explicit path.
+//
+// Keep this in a variable so future defaults can be extended without changing
+// call sites.
+var DefaultPipelineConfigSearchPaths = []string{
+	DefaultPipelineConfigPathUsrLocal,
+	DefaultPipelineConfigPathEtc,
+}
+
+// DefaultSessionConfigSearchPaths defines the default search order for
+// session.yml when callers do not provide an explicit path.
+//
+// Keep this in a variable so future defaults can be extended without changing
+// call sites.
+var DefaultSessionConfigSearchPaths = []string{
+	DefaultSessionConfigPathLocal,
+	DefaultSessionConfigPathUsrLocal,
+	DefaultSessionConfigPathEtc,
+}

internal/config/load.go

@@ -5,6 +5,8 @@ import (
 	"io"
 	"os"
 	"path/filepath"
+	"regexp"
+	"strings"
 
 	"gopkg.in/yaml.v3"
 )
@@ -21,21 +23,56 @@ func LoadPipeline(path string) (*PipelineConfig, error) {
 
 // LoadSession loads session configuration from a YAML file with strict field checking.
 func LoadSession(path string) (*SessionConfig, error) {
-	var cfg SessionConfig
-	if err := decodeStrictYAML("session", path, &cfg); err != nil {
+	return LoadSessionWithOptions(path, SessionLoadOptions{})
+}
+
+// SessionLoadOptions configures session template rendering behavior.
+type SessionLoadOptions struct {
+	SessionID string
+}
+
+// LoadSessionWithOptions loads session configuration from a YAML file with
+// strict field checking after template rendering.
+func LoadSessionWithOptions(path string, opts SessionLoadOptions) (*SessionConfig, error) {
+	sessionBytes, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("load session config: session file %q: open: %w", path, err)
+	}
+
+	rendered, err := renderSessionTemplate(string(sessionBytes), opts)
+	if err != nil {
 		return nil, fmt.Errorf("load session config: %w", err)
 	}
+
+	var cfg SessionConfig
+	if err := decodeStrictYAMLFromReader("session", path, strings.NewReader(rendered), &cfg); err != nil {
+		return nil, fmt.Errorf("load session config: %w", err)
+	}
+	if strings.TrimSpace(opts.SessionID) != "" && strings.TrimSpace(cfg.SessionID) != "" && strings.TrimSpace(cfg.SessionID) != strings.TrimSpace(opts.SessionID) {
+		return nil, fmt.Errorf(
+			"load session config: session file %q: session_id mismatch: --session-id %q does not match rendered session_id %q",
+			path,
+			strings.TrimSpace(opts.SessionID),
+			strings.TrimSpace(cfg.SessionID),
+		)
+	}
 	return &cfg, nil
 }
 
 // Load loads and resolves combined pipeline and session configuration.
 func Load(pipelinePath, sessionPath string) (*Config, error) {
+	return LoadWithSessionOptions(pipelinePath, sessionPath, SessionLoadOptions{})
+}
+
+// LoadWithSessionOptions loads and resolves combined pipeline and session
+// configuration with session template options.
+func LoadWithSessionOptions(pipelinePath, sessionPath string, sessionOpts SessionLoadOptions) (*Config, error) {
 	pipelineCfg, err := LoadPipeline(pipelinePath)
 	if err != nil {
 		return nil, err
 	}
 
-	sessionCfg, err := LoadSession(sessionPath)
+	sessionCfg, err := LoadSessionWithOptions(sessionPath, sessionOpts)
 	if err != nil {
 		return nil, err
 	}
@@ -55,7 +92,11 @@ func decodeStrictYAML(kind, path string, out any) error {
 	}
 	defer f.Close()
 
-	dec := yaml.NewDecoder(f)
+	return decodeStrictYAMLFromReader(kind, path, f, out)
+}
+
+func decodeStrictYAMLFromReader(kind, path string, r io.Reader, out any) error {
+	dec := yaml.NewDecoder(r)
 	dec.KnownFields(true)
 	if err := dec.Decode(out); err != nil {
 		return fmt.Errorf("%s file %q: strict decode failed: %w", kind, path, err)
@@ -69,6 +110,36 @@ func decodeStrictYAML(kind, path string, out any) error {
 	return nil
 }
 
+var sessionTemplatePattern = regexp.MustCompile(`\{\{\s*([a-zA-Z_][a-zA-Z0-9_]*)\s*\}\}`)
+
+func renderSessionTemplate(content string, opts SessionLoadOptions) (string, error) {
+	sessionID := strings.TrimSpace(opts.SessionID)
+	rendered := content
+	if sessionID != "" {
+		rendered = strings.ReplaceAll(rendered, "{{session_id}}", sessionID)
+		rendered = strings.ReplaceAll(rendered, "{{ session_id }}", sessionID)
+	}
+
+	unresolved := sessionTemplatePattern.FindAllStringSubmatch(rendered, -1)
+	if len(unresolved) > 0 {
+		vars := make([]string, 0, len(unresolved))
+		for _, m := range unresolved {
+			if len(m) > 1 {
+				vars = append(vars, m[1])
+			}
+		}
+		if len(vars) > 0 {
+			return "", fmt.Errorf(
+				"session file template rendering failed: unresolved template variable(s): %s; pass --session-id when using {{ session_id }}",
+				strings.Join(vars, ", "),
+			)
+		}
+		return "", fmt.Errorf("session file template rendering failed: unresolved template placeholders remain")
+	}
+
+	return rendered, nil
+}
+
 func shortName(path, fallback string) string {
 	base := filepath.Base(path)
 	if base == "." || base == string(filepath.Separator) {
@@ -81,6 +152,10 @@ func applyPipelineDefaults(cfg *PipelineConfig) {
 	if cfg == nil {
 		return
 	}
+	applyWorkspaceDefaults(&cfg.Workspace)
+	applyStorageDefaults(&cfg.Storage)
+	applySpoolDefaults(&cfg.Spool)
+	applyArchiveDefaults(&cfg.Archive)
 	applyWhisperXDefaults(&cfg.WhisperX)
 	applySeriatimDefaults(&cfg.Seriatim)
 	applyAuditaDefaults(&cfg.Audita)
@@ -92,24 +167,84 @@ func applyPipelineDefaults(cfg *PipelineConfig) {
 	applyScriptoriumDefaults(cfg.Scriptorium)
 }
 
+func applyWorkspaceDefaults(cfg *WorkspaceConfig) {
+	if cfg == nil {
+		return
+	}
+	if cfg.Root == "" {
+		cfg.Root = DefaultWorkspaceRoot
+	}
+}
+
+func applyStorageDefaults(cfg *StorageConfig) {
+	if cfg == nil {
+		return
+	}
+	if cfg.S3 == nil {
+		cfg.S3 = &StorageS3Config{}
+	}
+	if cfg.S3.RootPrefix == "" {
+		cfg.S3.RootPrefix = DefaultStorageS3RootPrefix
+	}
+	if cfg.S3.AccessKeyIDEnv == "" {
+		cfg.S3.AccessKeyIDEnv = DefaultS3AccessKeyIDEnv
+	}
+	if cfg.S3.SecretKeyEnv == "" {
+		cfg.S3.SecretKeyEnv = DefaultS3SecretAccessKeyEnv
+	}
+}
+
+func applySpoolDefaults(cfg *SpoolConfig) {
+	if cfg == nil {
+		return
+	}
+	if cfg.Root == "" {
+		cfg.Root = DefaultSpoolRoot
+	}
+}
+
+func applyArchiveDefaults(cfg **ArchiveConfig) {
+	if cfg == nil {
+		return
+	}
+	if *cfg == nil {
+		*cfg = &ArchiveConfig{}
+	}
+
+	if (*cfg).Enabled == nil {
+		(*cfg).Enabled = boolPtr(DefaultArchiveEnabled)
+	}
+	if (*cfg).UploadRun == nil {
+		(*cfg).UploadRun = boolPtr(DefaultArchiveUploadRun)
+	}
+	if len((*cfg).PromoteArtifacts) == 0 {
+		(*cfg).PromoteArtifacts = append([]ArchivePromotionRule(nil), DefaultArchivePromoteArtifacts...)
+	}
+	for i := range (*cfg).PromoteArtifacts {
+		if (*cfg).PromoteArtifacts[i].Required == nil {
+			(*cfg).PromoteArtifacts[i].Required = boolPtr(true)
+		}
+	}
+}
+
 func applyWhisperXDefaults(cfg *WhisperXConfig) {
 	if cfg == nil {
 		return
 	}
 	if cfg.Language == "" {
-		cfg.Language = "en"
+		cfg.Language = DefaultWhisperXLanguage
 	}
 	if cfg.Timeout == "" {
-		cfg.Timeout = "30m"
+		cfg.Timeout = DefaultWhisperXTimeout
 	}
 	if cfg.RetryDelay == "" {
-		cfg.RetryDelay = "2s"
+		cfg.RetryDelay = DefaultWhisperXRetryDelay
 	}
 	if cfg.Concurrency == nil {
-		cfg.Concurrency = intPtr(2)
+		cfg.Concurrency = intPtr(DefaultWhisperXConcurrency)
 	}
 	if cfg.Retries == nil {
-		cfg.Retries = intPtr(3)
+		cfg.Retries = intPtr(DefaultWhisperXRetries)
 	}
 }
 
@@ -122,17 +257,20 @@ func applySeriatimDefaults(cfg *SeriatimConfig) {
 	if cfg == nil {
 		return
 	}
+	if cfg.Binary == "" {
+		cfg.Binary = DefaultSeriatimBinary
+	}
 	if cfg.Timeout == "" {
-		cfg.Timeout = "10m"
+		cfg.Timeout = DefaultSeriatimTimeout
 	}
 	if cfg.OutputSchema == "" {
-		cfg.OutputSchema = "seriatim-intermediate"
+		cfg.OutputSchema = DefaultSeriatimOutputSchema
 	}
 	if cfg.CoalesceGap == nil {
-		cfg.CoalesceGap = float64Ptr(3.0)
+		cfg.CoalesceGap = float64Ptr(DefaultSeriatimCoalesceGap)
 	}
 	if cfg.Report == nil {
-		cfg.Report = boolPtr(true)
+		cfg.Report = boolPtr(DefaultSeriatimReport)
 	}
 }
 
@@ -140,34 +278,14 @@ func applyAuditaDefaults(cfg *AuditaConfig) {
 	if cfg == nil {
 		return
 	}
+	if cfg.Binary == "" {
+		cfg.Binary = DefaultAuditaBinary
+	}
 	if cfg.Timeout == "" {
-		cfg.Timeout = "3h"
-	}
-	if cfg.Modules == nil {
-		cfg.Modules = []string{
-			"glossary",
-			"homophones",
-			"glossary",
-			"spoken_word",
-			"grammar",
-			"homophones",
-			"glossary",
-		}
-	}
-	if cfg.BaseURL == "" {
-		cfg.BaseURL = "https://openrouter.ai/api/v1"
-	}
-	if cfg.Model == "" {
-		cfg.Model = "openrouter/google/gemma-4-31b-it"
-	}
-	if cfg.LLMConcurrency == nil {
-		cfg.LLMConcurrency = intPtr(1)
-	}
-	if cfg.ValidationLLMConcurrency == nil {
-		cfg.ValidationLLMConcurrency = intPtr(1)
+		cfg.Timeout = DefaultAuditaTimeout
 	}
 	if cfg.Report == nil {
-		cfg.Report = boolPtr(true)
+		cfg.Report = boolPtr(DefaultAuditaReport)
 	}
 }
 
@@ -175,8 +293,11 @@ func applyScriptoriumDefaults(cfg *ScriptoriumConfig) {
 	if cfg == nil {
 		return
 	}
+	if cfg.Binary == "" {
+		cfg.Binary = DefaultScriptoriumBinary
+	}
 	if cfg.Timeout == "" {
-		cfg.Timeout = "10m"
+		cfg.Timeout = DefaultScriptoriumTimeout
 	}
 }
 
@@ -185,10 +306,10 @@ func applyTrimDefaults(cfg *TrimConfig) {
 		return
 	}
 	if cfg.Bounds.Timeout == "" {
-		cfg.Bounds.Timeout = "10m"
+		cfg.Bounds.Timeout = DefaultTrimBoundsTimeout
 	}
 	if cfg.Seriatim.Report == nil {
-		cfg.Seriatim.Report = boolPtr(false)
+		cfg.Seriatim.Report = boolPtr(DefaultTrimSeriatimReport)
 	}
 }
 
@@ -197,13 +318,13 @@ func applyNormalizeDefaults(cfg *NormalizeConfig) {
 		return
 	}
 	if cfg.OutputSchema == "" {
-		cfg.OutputSchema = defaultNormalizeOutputSchema
+		cfg.OutputSchema = DefaultNormalizeOutputSchema
 	}
 	if cfg.OutputPath == "" && !cfg.outputPathWasSet() {
-		cfg.OutputPath = defaultNormalizeOutputPath
+		cfg.OutputPath = DefaultNormalizeOutputPath
 	}
 	if cfg.Report == nil {
-		cfg.Report = boolPtr(true)
+		cfg.Report = boolPtr(DefaultNormalizeReport)
 	}
 }
 

internal/config/load_validate_test.go

@@ -15,6 +15,7 @@ func TestLoadAndValidate(t *testing.T) {
 		wantLoadErr  string
 		wantValidate string
 		checkDefault bool
+		wantRoot     string
 	}{
 		{
 			name: "valid minimal config",
@@ -39,6 +40,47 @@ inputs:
   glossary_file: ./glossary.yml
 `,
 			checkDefault: true,
+			wantRoot:     "/tmp/narratio",
+		},
+		{
+			name: "seriatim and audita sections can be omitted",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+analyzer:
+  timeout: 20m
+notification:
+  timeout: 15s
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			checkDefault: true,
+			wantRoot:     "/tmp/narratio",
+		},
+		{
+			name: "workspace root defaults when omitted",
+			pipelineYAML: `whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+analyzer:
+  timeout: 20m
+notification:
+  timeout: 15s
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			checkDefault: true,
+			wantRoot:     DefaultWorkspaceRoot,
 		},
 		{
 			name: "unknown pipeline field fails",
@@ -72,6 +114,46 @@ inputs:
 `,
 			wantLoadErr: "strict decode failed",
 		},
+		{
+			name: "unknown secrets field fails",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+seriatim:
+  binary: seriatim
+secrets:
+  bogus: true
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantLoadErr: "strict decode failed",
+		},
+		{
+			name: "empty secrets env_dir fails",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+seriatim:
+  binary: seriatim
+secrets:
+  env_dir: "   "
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.secrets.env_dir must be non-empty when pipeline.secrets is configured",
+		},
 		{
 			name: "unknown session field fails",
 			pipelineYAML: `workspace:
@@ -256,7 +338,7 @@ inputs:
 			wantLoadErr: "strict decode failed",
 		},
 		{
-			name: "missing seriatim binary fails",
+			name: "missing seriatim binary uses default",
 			pipelineYAML: `workspace:
   root: /tmp/narratio
 whisperx:
@@ -271,7 +353,6 @@ inputs:
   autocorrect_file: ./autocorrect.yml
   glossary_file: ./glossary.yml
 `,
-			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.seriatim.binary is required",
 		},
 		{
 			name: "invalid seriatim timeout fails",
@@ -372,7 +453,7 @@ inputs:
 			wantLoadErr: "strict decode failed",
 		},
 		{
-			name: "missing audita binary fails",
+			name: "missing audita binary uses default",
 			pipelineYAML: `workspace:
   root: /tmp/narratio
 whisperx:
@@ -389,7 +470,6 @@ inputs:
   autocorrect_file: ./autocorrect.yml
   glossary_file: ./glossary.yml
 `,
-			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.binary is required",
 		},
 		{
 			name: "invalid audita timeout fails",
@@ -413,7 +493,7 @@ inputs:
 			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.timeout must be a valid duration",
 		},
 		{
-			name: "empty audita modules fails",
+			name: "empty audita modules is valid override",
 			pipelineYAML: `workspace:
   root: /tmp/narratio
 whisperx:
@@ -431,7 +511,6 @@ inputs:
   autocorrect_file: ./autocorrect.yml
   glossary_file: ./glossary.yml
 `,
-			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.modules must include at least one module",
 		},
 		{
 			name: "empty audita module item fails",
@@ -501,7 +580,7 @@ inputs:
 			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.base_url must be a valid URL",
 		},
 		{
-			name: "invalid audita llm_concurrency fails",
+			name: "legacy audita llm_concurrency field fails strict decode",
 			pipelineYAML: `workspace:
   root: /tmp/narratio
 whisperx:
@@ -510,7 +589,7 @@ seriatim:
   binary: seriatim
 audita:
   binary: audita
-  llm_concurrency: 0
+  llm_concurrency: 1
 `,
 			sessionYAML: `session_id: 2026-05-03
 inputs:
@@ -519,7 +598,49 @@ inputs:
   autocorrect_file: ./autocorrect.yml
   glossary_file: ./glossary.yml
 `,
-			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.llm_concurrency must be > 0",
+			wantLoadErr: "strict decode failed",
+		},
+		{
+			name: "invalid audita total_llm_concurrency fails",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+seriatim:
+  binary: seriatim
+audita:
+  binary: audita
+  total_llm_concurrency: 0
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.total_llm_concurrency must be > 0",
+		},
+		{
+			name: "invalid audita proposal_llm_concurrency fails",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+seriatim:
+  binary: seriatim
+audita:
+  binary: audita
+  proposal_llm_concurrency: 0
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.proposal_llm_concurrency must be > 0",
 		},
 		{
 			name: "invalid audita validation_llm_concurrency fails",
@@ -542,6 +663,48 @@ inputs:
 `,
 			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.validation_llm_concurrency must be > 0",
 		},
+		{
+			name: "invalid audita output_schema fails",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+seriatim:
+  binary: seriatim
+audita:
+  binary: audita
+  output_schema: bad
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.output_schema must be one of: bare-segments, audita-v1",
+		},
+		{
+			name: "invalid audita work_dir_retention fails",
+			pipelineYAML: `workspace:
+  root: /tmp/narratio
+whisperx:
+  transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
+seriatim:
+  binary: seriatim
+audita:
+  binary: audita
+  work_dir_retention: sometimes
+`,
+			sessionYAML: `session_id: 2026-05-03
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.work_dir_retention must be one of: always, auto, never",
+		},
 	}
 
 	for _, tt := range tests {
@@ -572,6 +735,9 @@ inputs:
 				t.Fatalf("SessionPath = %q, want %q", cfg.SessionPath, sessionPath)
 			}
 			if tt.checkDefault {
+				if tt.wantRoot != "" && cfg.Pipeline.Workspace.Root != tt.wantRoot {
+					t.Fatalf("workspace.root = %q, want %q", cfg.Pipeline.Workspace.Root, tt.wantRoot)
+				}
 				if cfg.Pipeline.WhisperX.Language != "en" {
 					t.Fatalf("whisperx.language = %q, want %q", cfg.Pipeline.WhisperX.Language, "en")
 				}
@@ -590,6 +756,9 @@ inputs:
 				if cfg.Pipeline.Seriatim.Timeout != "10m" {
 					t.Fatalf("seriatim.timeout = %q, want %q", cfg.Pipeline.Seriatim.Timeout, "10m")
 				}
+				if cfg.Pipeline.Seriatim.Binary != "seriatim" {
+					t.Fatalf("seriatim.binary = %q, want %q", cfg.Pipeline.Seriatim.Binary, "seriatim")
+				}
 				if cfg.Pipeline.Seriatim.OutputSchema != "seriatim-intermediate" {
 					t.Fatalf("seriatim.output_schema = %q, want %q", cfg.Pipeline.Seriatim.OutputSchema, "seriatim-intermediate")
 				}
@@ -602,26 +771,32 @@ inputs:
 				if cfg.Pipeline.Audita.Timeout != "3h" {
 					t.Fatalf("audita.timeout = %q, want %q", cfg.Pipeline.Audita.Timeout, "3h")
 				}
+				if cfg.Pipeline.Audita.Binary != "audita" {
+					t.Fatalf("audita.binary = %q, want %q", cfg.Pipeline.Audita.Binary, "audita")
+				}
 				if cfg.Pipeline.Audita.LLMAPIKeyEnv != "" {
 					t.Fatalf("audita.llm_api_key_env = %q, want empty by default", cfg.Pipeline.Audita.LLMAPIKeyEnv)
 				}
-				if got := strings.Join(cfg.Pipeline.Audita.Modules, ","); got != "glossary,homophones,glossary,spoken_word,grammar,homophones,glossary" {
-					t.Fatalf("audita.modules = %q, want default sequence", got)
+				if cfg.Pipeline.Audita.Modules != nil {
+					t.Fatalf("audita.modules = %#v, want nil default (optional override)", cfg.Pipeline.Audita.Modules)
 				}
-				if cfg.Pipeline.Audita.BaseURL != "https://openrouter.ai/api/v1" {
-					t.Fatalf("audita.base_url = %q, want %q", cfg.Pipeline.Audita.BaseURL, "https://openrouter.ai/api/v1")
+				if cfg.Pipeline.Audita.BaseURL != "" {
+					t.Fatalf("audita.base_url = %q, want empty default", cfg.Pipeline.Audita.BaseURL)
 				}
-				if cfg.Pipeline.Audita.Model != "openrouter/google/gemma-4-31b-it" {
-					t.Fatalf("audita.model = %q, want %q", cfg.Pipeline.Audita.Model, "openrouter/google/gemma-4-31b-it")
-				}
-				if cfg.Pipeline.Audita.LLMConcurrency == nil || *cfg.Pipeline.Audita.LLMConcurrency != 1 {
-					t.Fatalf("audita.llm_concurrency = %v, want 1", cfg.Pipeline.Audita.LLMConcurrency)
+				if cfg.Pipeline.Audita.Model != "" {
+					t.Fatalf("audita.model = %q, want empty default", cfg.Pipeline.Audita.Model)
 				}
 				if cfg.Pipeline.Audita.ValidationModel != "" {
 					t.Fatalf("audita.validation_model = %q, want empty default", cfg.Pipeline.Audita.ValidationModel)
 				}
-				if cfg.Pipeline.Audita.ValidationLLMConcurrency == nil || *cfg.Pipeline.Audita.ValidationLLMConcurrency != 1 {
-					t.Fatalf("audita.validation_llm_concurrency = %v, want 1", cfg.Pipeline.Audita.ValidationLLMConcurrency)
+				if cfg.Pipeline.Audita.TotalLLMConcurrency != nil {
+					t.Fatalf("audita.total_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.TotalLLMConcurrency)
+				}
+				if cfg.Pipeline.Audita.ProposalLLMConcurrency != nil {
+					t.Fatalf("audita.proposal_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.ProposalLLMConcurrency)
+				}
+				if cfg.Pipeline.Audita.ValidationLLMConcurrency != nil {
+					t.Fatalf("audita.validation_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.ValidationLLMConcurrency)
 				}
 				if cfg.Pipeline.Audita.Report == nil || *cfg.Pipeline.Audita.Report != true {
 					t.Fatalf("audita.report = %v, want true", cfg.Pipeline.Audita.Report)
@@ -685,7 +860,8 @@ func TestValidateMissingAudioSource(t *testing.T) {
 				Modules:                  []string{"glossary", "homophones"},
 				BaseURL:                  "https://openrouter.ai/api/v1",
 				Model:                    "openrouter/google/gemma-4-31b-it",
-				LLMConcurrency:           intPtr(1),
+				TotalLLMConcurrency:      intPtr(1),
+				ProposalLLMConcurrency:   intPtr(1),
 				ValidationModel:          "",
 				ValidationLLMConcurrency: intPtr(1),
 				Report:                   boolPtr(true),
@@ -693,6 +869,7 @@ func TestValidateMissingAudioSource(t *testing.T) {
 		},
 		Session: &SessionConfig{
 			SessionID: "2026-05-03",
+			Campaign:  "sample-campaign",
 			Inputs: SessionInputsConfig{
 				SpeakersFile:    "speakers.yml",
 				AutocorrectFile: "autocorrect.yml",
@@ -705,7 +882,7 @@ func TestValidateMissingAudioSource(t *testing.T) {
 	if err == nil {
 		t.Fatal("expected validation error, got nil")
 	}
-	if !strings.Contains(err.Error(), "audio_dir or at least one audio_files") {
+	if !strings.Contains(err.Error(), "audio_dir, at least one audio_files entry, or audio_s3") {
 		t.Fatalf("error = %q, want audio source guidance", err.Error())
 	}
 	if !strings.Contains(err.Error(), "session config") {
@@ -714,15 +891,59 @@ func TestValidateMissingAudioSource(t *testing.T) {
 }
 
 func TestExamplesLoadAndValidate(t *testing.T) {
-	pipelinePath := filepath.Join("..", "..", "examples", "pipeline.minimal.yml")
-	sessionPath := filepath.Join("..", "..", "examples", "session.minimal.yml")
-
-	cfg, err := Load(pipelinePath, sessionPath)
-	if err != nil {
-		t.Fatalf("Load(examples) error = %v", err)
+	examplesDir := filepath.Join("..", "..", "examples")
+	tests := []struct {
+		name         string
+		pipelineFile string
+		sessionFile  string
+		sessionOpts  SessionLoadOptions
+	}{
+		{
+			name:         "minimal pipeline with local audio session",
+			pipelineFile: "pipeline.minimal.yml",
+			sessionFile:  "session.local-audio.yml",
+		},
+		{
+			name:         "production pipeline with s3 audio session",
+			pipelineFile: "pipeline.production.yml",
+			sessionFile:  "session.s3-audio.yml",
+		},
+		{
+			name:         "full annotated pipeline with local audio session",
+			pipelineFile: "pipeline.full.annotated.yml",
+			sessionFile:  "session.local-audio.yml",
+		},
+		{
+			name:         "template session renders with session_id option",
+			pipelineFile: "pipeline.minimal.yml",
+			sessionFile:  "session.template.yml",
+			sessionOpts: SessionLoadOptions{
+				SessionID: "2026-05-03",
+			},
+		},
 	}
-	if err := Validate(cfg); err != nil {
-		t.Fatalf("Validate(examples) error = %v", err)
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			pipelinePath := filepath.Join(examplesDir, tt.pipelineFile)
+			sessionPath := filepath.Join(examplesDir, tt.sessionFile)
+
+			var (
+				cfg *Config
+				err error
+			)
+			if strings.TrimSpace(tt.sessionOpts.SessionID) == "" {
+				cfg, err = Load(pipelinePath, sessionPath)
+			} else {
+				cfg, err = LoadWithSessionOptions(pipelinePath, sessionPath, tt.sessionOpts)
+			}
+			if err != nil {
+				t.Fatalf("load example config error = %v", err)
+			}
+			if err := Validate(cfg); err != nil {
+				t.Fatalf("validate example config error = %v", err)
+			}
+		})
 	}
 }
 
@@ -734,6 +955,12 @@ func writeConfigFiles(t *testing.T, pipelineYAML, sessionYAML string) (string, s
 		}
 		pipelineYAML += "audita:\n  binary: audita\n"
 	}
+	if !strings.Contains(sessionYAML, "\ncampaign:") && !strings.HasPrefix(sessionYAML, "campaign:") {
+		if !strings.HasSuffix(sessionYAML, "\n") {
+			sessionYAML += "\n"
+		}
+		sessionYAML += "campaign: sample-campaign\n"
+	}
 
 	dir := t.TempDir()
 	pipelinePath := filepath.Join(dir, "pipeline.yml")

internal/config/normalize.go

@@ -6,11 +6,6 @@ import (
 	"gopkg.in/yaml.v3"
 )
 
-const (
-	defaultNormalizeOutputPath   = "transcripts/normalized.json"
-	defaultNormalizeOutputSchema = "seriatim-intermediate"
-)
-
 // UnmarshalYAML tracks explicit normalize.output_path presence so validation can
 // distinguish omitted vs explicitly empty values.
 func (cfg *NormalizeConfig) UnmarshalYAML(node *yaml.Node) error {

internal/config/scriptorium_test.go

@@ -24,7 +24,7 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
       output_path: artifacts/session_recap.md
       inputs:
         transcript:
-          source: processed_transcript
+          source: narratio.transcript.polished
           required: true
       vars:
         session_id: true
@@ -49,11 +49,19 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
 			wantLoadErr: "strict decode failed",
 		},
 		{
-			name: "missing binary fails when section present",
+			name: "missing binary defaults when section present",
 			scriptoriumYAML: `scriptorium:
   timeout: 10m
 `,
-			wantValidateErr: "pipeline.scriptorium.binary is required",
+			assert: func(t *testing.T, cfg *Config) {
+				t.Helper()
+				if cfg.Pipeline.Scriptorium == nil {
+					t.Fatal("scriptorium config should be present")
+				}
+				if cfg.Pipeline.Scriptorium.Binary != "scriptorium" {
+					t.Fatalf("scriptorium.binary = %q, want scriptorium", cfg.Pipeline.Scriptorium.Binary)
+				}
+			},
 		},
 		{
 			name: "enabled artifact missing prompt id fails",
@@ -96,7 +104,7 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
       output_path: artifacts/session_recap.md
       inputs:
         transcript:
-          source: processed_transcript
+          source: narratio.transcript.polished
           required: true
         previous_recap:
           source: previous_session_artifact
@@ -108,6 +116,37 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
         output_kind: session_recap
 `,
 		},
+		{
+			name: "canonical artifact source is accepted",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+`,
+		},
+		{
+			name: "unknown artifact source fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+      inputs:
+        transcript:
+          source: narratio.unknown
+          required: true
+`,
+			wantValidateErr: `pipeline.scriptorium.artifacts.session_recap.inputs.transcript.source "narratio.unknown" is unsupported`,
+		},
 		{
 			name: "artifact render_debug override is accepted",
 			scriptoriumYAML: `scriptorium:
@@ -121,7 +160,7 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
       output_path: artifacts/session_recap.md
       inputs:
         transcript:
-          source: processed_transcript
+          source: narratio.transcript.polished
           required: true
 `,
 			assert: func(t *testing.T, cfg *Config) {
@@ -143,7 +182,7 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
       output_path: artifacts/session_recap.md
       inputs:
         transcript:
-          source: processed_transcript
+          source: narratio.transcript.polished
           required: true
     player_summary:
       enabled: true
@@ -153,7 +192,7 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
       timeout: 3m
       inputs:
         transcript:
-          source: processed_transcript
+          source: narratio.transcript.polished
           required: true
 `,
 			assert: func(t *testing.T, cfg *Config) {
@@ -166,6 +205,195 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
 				}
 			},
 		},
+		{
+			name: "valid artifact dependency is accepted",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+      inputs:
+        transcript:
+          source: narratio.transcript.trimmed
+          required: true
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+`,
+		},
+		{
+			name: "valid dependency on disabled artifact with output path is accepted",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: false
+      output_path: artifacts/session_recap.md
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+`,
+		},
+		{
+			name: "invalid artifact name fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    SessionRecap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+`,
+			wantValidateErr: "pipeline.scriptorium.artifacts keys must match ^[a-z][a-z0-9_]*$",
+		},
+		{
+			name: "artifact output path outside artifacts root fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: transcripts/session_recap.md
+`,
+			wantValidateErr: "pipeline.scriptorium.artifacts.session_recap.output_path must be under artifacts/",
+		},
+		{
+			name: "missing depends_on for artifact source fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+      inputs:
+        transcript:
+          source: narratio.transcript.polished
+          required: true
+    player_handout:
+      enabled: true
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+`,
+			wantValidateErr: `pipeline.scriptorium.artifacts.player_handout.inputs.recap.source "narratio.artifact.session_recap" requires depends_on entry "session_recap"`,
+		},
+		{
+			name: "dependency on unknown artifact fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+`,
+			wantValidateErr: `pipeline.scriptorium.artifacts.player_handout.depends_on[0] "session_recap" is not a configured artifact key`,
+		},
+		{
+			name: "self dependency fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.session_recap
+      output_path: artifacts/session_recap.md
+`,
+			wantValidateErr: "pipeline.scriptorium.artifacts.session_recap.depends_on must not include itself",
+		},
+		{
+			name: "enabled dependency cycle fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    artifact_a:
+      enabled: true
+      depends_on:
+        - artifact_b
+      prompt_id: dnd.a
+      output_path: artifacts/a.md
+      inputs:
+        b:
+          source: narratio.artifact.artifact_b
+          required: true
+    artifact_b:
+      enabled: true
+      depends_on:
+        - artifact_a
+      prompt_id: dnd.b
+      output_path: artifacts/b.md
+      inputs:
+        a:
+          source: narratio.artifact.artifact_a
+          required: true
+`,
+			wantValidateErr: "pipeline.scriptorium.artifacts enabled dependencies must not contain cycles",
+		},
+		{
+			name: "artifact source typo fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    player_handout:
+      enabled: true
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session-recap
+          required: true
+`,
+			wantValidateErr: `pipeline.scriptorium.artifacts.player_handout.inputs.recap.source "narratio.artifact.session-recap" is unsupported`,
+		},
+		{
+			name: "referenced disabled artifact missing output path fails validation",
+			scriptoriumYAML: `scriptorium:
+  binary: scriptorium
+  artifacts:
+    session_recap:
+      enabled: false
+    player_handout:
+      enabled: true
+      depends_on:
+        - session_recap
+      prompt_id: dnd.player_handout
+      output_path: artifacts/player_handout.md
+      inputs:
+        recap:
+          source: narratio.artifact.session_recap
+          required: true
+`,
+			wantValidateErr: "pipeline.scriptorium.artifacts.session_recap.output_path is required when artifact is referenced",
+		},
 	}
 
 	for _, tt := range tests {
@@ -219,6 +447,7 @@ audita:
 `
 
 const testSessionBaseYAML = `session_id: 2026-05-03
+campaign: test-campaign
 inputs:
   audio_dir: ./audio
   speakers_file: ./speakers.yml

internal/config/session_template_test.go

@@ -0,0 +1,156 @@
+package config
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestLoadSessionWithOptionsRendersCompactPlaceholder(t *testing.T) {
+	dir := t.TempDir()
+	sessionPath := filepath.Join(dir, "session.yml")
+	sessionYAML := `session_id: "{{session_id}}"
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	cfg, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
+	if err != nil {
+		t.Fatalf("LoadSessionWithOptions() error = %v", err)
+	}
+	if cfg.SessionID != "2026-04-04" {
+		t.Fatalf("SessionID = %q, want 2026-04-04", cfg.SessionID)
+	}
+}
+
+func TestLoadSessionWithOptionsRendersSpacedPlaceholder(t *testing.T) {
+	dir := t.TempDir()
+	sessionPath := filepath.Join(dir, "session.yml")
+	sessionYAML := `session_id: "{{ session_id }}"
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	cfg, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
+	if err != nil {
+		t.Fatalf("LoadSessionWithOptions() error = %v", err)
+	}
+	if cfg.SessionID != "2026-04-04" {
+		t.Fatalf("SessionID = %q, want 2026-04-04", cfg.SessionID)
+	}
+}
+
+func TestLoadSessionWithOptionsUnresolvedPlaceholderFails(t *testing.T) {
+	dir := t.TempDir()
+	sessionPath := filepath.Join(dir, "session.yml")
+	sessionYAML := `session_id: "{{ session_id }}"
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	_, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{})
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "unresolved template variable") {
+		t.Fatalf("error = %q, want unresolved-variable context", err.Error())
+	}
+	if !strings.Contains(err.Error(), "session_id") {
+		t.Fatalf("error = %q, want session_id variable", err.Error())
+	}
+}
+
+func TestLoadSessionWithOptionsMismatchFails(t *testing.T) {
+	dir := t.TempDir()
+	sessionPath := filepath.Join(dir, "session.yml")
+	sessionYAML := `session_id: 2026-05-03
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	_, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "session_id mismatch") {
+		t.Fatalf("error = %q, want mismatch context", err.Error())
+	}
+}
+
+func TestLoadSessionWithOptionsUnknownFieldStillRejectedAfterRendering(t *testing.T) {
+	dir := t.TempDir()
+	sessionPath := filepath.Join(dir, "session.yml")
+	sessionYAML := `session_id: "{{ session_id }}"
+campaign: sample-campaign
+unknown_field: true
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	_, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
+	if err == nil {
+		t.Fatal("expected error, got nil")
+	}
+	if !strings.Contains(err.Error(), "strict decode failed") {
+		t.Fatalf("error = %q, want strict-decode context", err.Error())
+	}
+}
+
+func TestLoadSessionWithOptionsConcreteSessionStillLoads(t *testing.T) {
+	dir := t.TempDir()
+	sessionPath := filepath.Join(dir, "session.yml")
+	sessionYAML := `session_id: 2026-05-03
+campaign: sample-campaign
+inputs:
+  audio_dir: ./audio
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
+		t.Fatalf("write session.yml: %v", err)
+	}
+
+	cfg, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{})
+	if err != nil {
+		t.Fatalf("LoadSessionWithOptions() error = %v", err)
+	}
+	if cfg.SessionID != "2026-05-03" {
+		t.Fatalf("SessionID = %q, want 2026-05-03", cfg.SessionID)
+	}
+}

internal/config/storage_archive_test.go

@@ -0,0 +1,315 @@
+package config
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestStorageS3DefaultsAndValidation(t *testing.T) {
+	pipelineYAML := testPipelineBaseYAML + `
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+`
+	pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, testSessionBaseYAML)
+
+	cfg, err := Load(pipelinePath, sessionPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+	if cfg.Pipeline.Storage.S3 == nil {
+		t.Fatal("storage.s3 should be initialized")
+	}
+	if cfg.Pipeline.Storage.S3.RootPrefix != "dnd" {
+		t.Fatalf("storage.s3.root_prefix = %q, want dnd", cfg.Pipeline.Storage.S3.RootPrefix)
+	}
+	if cfg.Pipeline.Storage.S3.AccessKeyIDEnv != DefaultS3AccessKeyIDEnv {
+		t.Fatalf("storage.s3.access_key_id_env = %q, want %q", cfg.Pipeline.Storage.S3.AccessKeyIDEnv, DefaultS3AccessKeyIDEnv)
+	}
+	if cfg.Pipeline.Storage.S3.SecretKeyEnv != DefaultS3SecretAccessKeyEnv {
+		t.Fatalf("storage.s3.secret_access_key_env = %q, want %q", cfg.Pipeline.Storage.S3.SecretKeyEnv, DefaultS3SecretAccessKeyEnv)
+	}
+	if cfg.Pipeline.Storage.S3.ForcePathStyle {
+		t.Fatalf("storage.s3.force_path_style = true, want false default")
+	}
+
+	if err := Validate(cfg); err != nil {
+		t.Fatalf("Validate() error = %v", err)
+	}
+}
+
+func TestStorageS3CredentialEnvNamesLoadAndValidate(t *testing.T) {
+	pipelineYAML := testPipelineBaseYAML + `
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+    access_key_id_env: CUSTOM_KEY_ID
+    secret_access_key_env: CUSTOM_SECRET
+`
+	pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, testSessionBaseYAML)
+
+	cfg, err := Load(pipelinePath, sessionPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+	if cfg.Pipeline.Storage.S3.AccessKeyIDEnv != "CUSTOM_KEY_ID" {
+		t.Fatalf("storage.s3.access_key_id_env = %q, want CUSTOM_KEY_ID", cfg.Pipeline.Storage.S3.AccessKeyIDEnv)
+	}
+	if cfg.Pipeline.Storage.S3.SecretKeyEnv != "CUSTOM_SECRET" {
+		t.Fatalf("storage.s3.secret_access_key_env = %q, want CUSTOM_SECRET", cfg.Pipeline.Storage.S3.SecretKeyEnv)
+	}
+	if err := Validate(cfg); err != nil {
+		t.Fatalf("Validate() error = %v", err)
+	}
+}
+
+func TestStorageS3CredentialEnvValidation(t *testing.T) {
+	tests := []struct {
+		name        string
+		pipelineYML string
+		wantErr     string
+	}{
+		{
+			name: "invalid access key env name",
+			pipelineYML: testPipelineBaseYAML + `
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+    access_key_id_env: "123BAD"
+`,
+			wantErr: "pipeline.storage.s3.access_key_id_env must be a valid environment variable name",
+		},
+		{
+			name: "invalid secret key env name",
+			pipelineYML: testPipelineBaseYAML + `
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+    secret_access_key_env: "bad-name"
+`,
+			wantErr: "pipeline.storage.s3.secret_access_key_env must be a valid environment variable name",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			pipelinePath, sessionPath := writeConfigFiles(t, tt.pipelineYML, testSessionBaseYAML)
+			cfg, err := Load(pipelinePath, sessionPath)
+			if err != nil {
+				t.Fatalf("Load() error = %v", err)
+			}
+			err = Validate(cfg)
+			if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
+				t.Fatalf("Validate() error = %v, want to contain %q", err, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestSpoolAndArchiveDefaults(t *testing.T) {
+	pipelinePath, sessionPath := writeConfigFiles(t, testPipelineBaseYAML, testSessionBaseYAML)
+
+	cfg, err := Load(pipelinePath, sessionPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+
+	if cfg.Pipeline.Spool.Root != "/var/spool/narratio" {
+		t.Fatalf("spool.root = %q, want /var/spool/narratio", cfg.Pipeline.Spool.Root)
+	}
+	if cfg.Pipeline.Spool.DeleteAudioAfterArchive {
+		t.Fatalf("spool.delete_audio_after_archive = true, want false")
+	}
+	if cfg.Pipeline.Workspace.CleanupAfterArchive {
+		t.Fatalf("workspace.cleanup_after_archive = true, want false")
+	}
+	if cfg.Pipeline.Archive == nil {
+		t.Fatal("archive should be initialized by defaults")
+	}
+	if cfg.Pipeline.Archive.Enabled == nil || !*cfg.Pipeline.Archive.Enabled {
+		t.Fatalf("archive.enabled = %#v, want true", cfg.Pipeline.Archive.Enabled)
+	}
+	if cfg.Pipeline.Archive.UploadRun == nil || !*cfg.Pipeline.Archive.UploadRun {
+		t.Fatalf("archive.upload_run = %#v, want true", cfg.Pipeline.Archive.UploadRun)
+	}
+	if len(cfg.Pipeline.Archive.PromoteArtifacts) != 2 {
+		t.Fatalf("archive.promote_artifacts len = %d, want 2 defaults", len(cfg.Pipeline.Archive.PromoteArtifacts))
+	}
+	for i, item := range cfg.Pipeline.Archive.PromoteArtifacts {
+		if item.Required == nil || !*item.Required {
+			t.Fatalf("archive.promote_artifacts[%d].required = %#v, want true", i, item.Required)
+		}
+	}
+}
+
+func TestArchivePromotionPathValidation(t *testing.T) {
+	tests := []struct {
+		name    string
+		ruleYML string
+		wantErr string
+	}{
+		{
+			name: "absolute from path rejected",
+			ruleYML: `archive:
+  promote_artifacts:
+    - from: "/transcripts/trimmed.json"
+      to: "transcripts/trimmed.json"
+`,
+			wantErr: "must be a relative path",
+		},
+		{
+			name: "traversal to path rejected",
+			ruleYML: `archive:
+  promote_artifacts:
+    - from: "transcripts/trimmed.json"
+      to: "../trimmed.json"
+`,
+			wantErr: "must not contain path traversal",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			pipelineYAML := testPipelineBaseYAML + "\n" + tt.ruleYML
+			pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, testSessionBaseYAML)
+
+			cfg, err := Load(pipelinePath, sessionPath)
+			if err != nil {
+				t.Fatalf("Load() error = %v", err)
+			}
+			err = Validate(cfg)
+			if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
+				t.Fatalf("Validate() error = %v, want to contain %q", err, tt.wantErr)
+			}
+		})
+	}
+}
+
+func TestSessionAudioS3Validation(t *testing.T) {
+	tests := []struct {
+		name        string
+		sessionYAML string
+		wantErr     string
+	}{
+		{
+			name: "valid audio_s3 prefix",
+			sessionYAML: `session_id: 2026-05-03
+campaign: forsaken
+inputs:
+  audio_s3:
+    prefix: audio/
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+		},
+		{
+			name: "invalid audio_s3 absolute prefix",
+			sessionYAML: `session_id: 2026-05-03
+campaign: forsaken
+inputs:
+  audio_s3:
+    prefix: /audio/
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantErr: "session.inputs.audio_s3.prefix must be a relative path",
+		},
+		{
+			name: "invalid audio_s3 traversal prefix",
+			sessionYAML: `session_id: 2026-05-03
+campaign: forsaken
+inputs:
+  audio_s3:
+    prefix: ../audio/
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantErr: "session.inputs.audio_s3.prefix must not contain path traversal",
+		},
+		{
+			name: "local and s3 audio conflict",
+			sessionYAML: `session_id: 2026-05-03
+campaign: forsaken
+inputs:
+  audio_dir: ./audio
+  audio_s3:
+    prefix: audio/
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`,
+			wantErr: "mutually exclusive",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			pipelineYAML := testPipelineBaseYAML + `
+storage:
+  backend: s3
+  s3:
+    bucket: my-dnd-archive
+`
+			pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, tt.sessionYAML)
+
+			cfg, err := Load(pipelinePath, sessionPath)
+			if err != nil {
+				t.Fatalf("Load() error = %v", err)
+			}
+			err = Validate(cfg)
+			if tt.wantErr != "" {
+				if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
+					t.Fatalf("Validate() error = %v, want to contain %q", err, tt.wantErr)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("Validate() error = %v", err)
+			}
+		})
+	}
+}
+
+func TestStorageS3BucketRequiredWhenS3DependentFeatureEnabled(t *testing.T) {
+	pipelineYAML := testPipelineBaseYAML + `
+storage:
+  backend: s3
+`
+	sessionYAML := `session_id: 2026-05-03
+campaign: forsaken
+inputs:
+  audio_s3:
+    prefix: audio/
+  speakers_file: ./speakers.yml
+  autocorrect_file: ./autocorrect.yml
+  glossary_file: ./glossary.yml
+`
+	pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, sessionYAML)
+	cfg, err := Load(pipelinePath, sessionPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+
+	err = Validate(cfg)
+	if err == nil || !strings.Contains(err.Error(), "pipeline.storage.s3.bucket is required") {
+		t.Fatalf("Validate() error = %v, want bucket requirement", err)
+	}
+}
+
+func TestLocalAudioConfigStillValid(t *testing.T) {
+	pipelinePath, sessionPath := writeConfigFiles(t, testPipelineBaseYAML, testSessionBaseYAML)
+	cfg, err := Load(pipelinePath, sessionPath)
+	if err != nil {
+		t.Fatalf("Load() error = %v", err)
+	}
+	if err := Validate(cfg); err != nil {
+		t.Fatalf("Validate() error = %v", err)
+	}
+}

internal/config/validate.go

@@ -3,6 +3,8 @@ package config
 import (
 	"fmt"
 	"net/url"
+	"path/filepath"
+	"regexp"
 	"strings"
 	"time"
 )
@@ -25,6 +27,9 @@ func Validate(cfg *Config) error {
 	if err := validateSession(cfg.Session); err != nil {
 		return fmt.Errorf("session config %q invalid: %w", shortName(cfg.SessionPath, "session.yml"), err)
 	}
+	if err := validateCrossConfig(cfg.Pipeline, cfg.Session); err != nil {
+		return fmt.Errorf("pipeline/session config invalid: %w", err)
+	}
 
 	return nil
 }
@@ -33,6 +38,18 @@ func validatePipeline(cfg *PipelineConfig) error {
 	if strings.TrimSpace(cfg.Workspace.Root) == "" {
 		return fmt.Errorf("pipeline.workspace.root is required")
 	}
+	if err := validateSecrets(cfg.Secrets); err != nil {
+		return err
+	}
+	if err := validateStorage(cfg.Storage); err != nil {
+		return err
+	}
+	if err := validateSpool(cfg.Spool); err != nil {
+		return err
+	}
+	if err := validateArchive(cfg.Archive); err != nil {
+		return err
+	}
 	if err := validateWhisperX(cfg.WhisperX); err != nil {
 		return err
 	}
@@ -61,6 +78,64 @@ func validatePipeline(cfg *PipelineConfig) error {
 	return nil
 }
 
+func validateStorage(cfg StorageConfig) error {
+	if cfg.S3 == nil {
+		return nil
+	}
+	if strings.TrimSpace(cfg.S3.RootPrefix) == "" {
+		return fmt.Errorf("pipeline.storage.s3.root_prefix must be non-empty")
+	}
+	if err := validateRelativeSafePath("pipeline.storage.s3.root_prefix", cfg.S3.RootPrefix); err != nil {
+		return err
+	}
+	if cfg.S3.Endpoint != "" && strings.TrimSpace(cfg.S3.Endpoint) == "" {
+		return fmt.Errorf("pipeline.storage.s3.endpoint must be non-empty when provided")
+	}
+	if err := validateEnvVarNameField("pipeline.storage.s3.access_key_id_env", cfg.S3.AccessKeyIDEnv); err != nil {
+		return err
+	}
+	if err := validateEnvVarNameField("pipeline.storage.s3.secret_access_key_env", cfg.S3.SecretKeyEnv); err != nil {
+		return err
+	}
+	return nil
+}
+
+func validateSpool(cfg SpoolConfig) error {
+	return nil
+}
+
+func validateArchive(cfg *ArchiveConfig) error {
+	if cfg == nil {
+		return nil
+	}
+	for i, item := range cfg.PromoteArtifacts {
+		prefix := fmt.Sprintf("pipeline.archive.promote_artifacts[%d]", i)
+		if strings.TrimSpace(item.From) == "" {
+			return fmt.Errorf("%s.from is required", prefix)
+		}
+		if strings.TrimSpace(item.To) == "" {
+			return fmt.Errorf("%s.to is required", prefix)
+		}
+		if err := validateRelativeSafePath(prefix+".from", item.From); err != nil {
+			return err
+		}
+		if err := validateRelativeSafePath(prefix+".to", item.To); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func validateSecrets(cfg *SecretsConfig) error {
+	if cfg == nil {
+		return nil
+	}
+	if strings.TrimSpace(cfg.EnvDir) == "" {
+		return fmt.Errorf("pipeline.secrets.env_dir must be non-empty when pipeline.secrets is configured")
+	}
+	return nil
+}
+
 func validateNormalize(cfg *NormalizeConfig) error {
 	if cfg == nil {
 		return nil
@@ -187,15 +262,12 @@ func validateAudita(cfg AuditaConfig) error {
 	if err := validateDuration("pipeline.audita.timeout", cfg.Timeout); err != nil {
 		return err
 	}
-	if len(cfg.Modules) == 0 {
-		return fmt.Errorf("pipeline.audita.modules must include at least one module")
-	}
-	for i, mod := range cfg.Modules {
-		m := strings.TrimSpace(mod)
-		if m == "" {
+	for i, m := range cfg.Modules {
+		module := strings.TrimSpace(m)
+		if module == "" {
 			return fmt.Errorf("pipeline.audita.modules[%d] must be non-empty", i)
 		}
-		switch m {
+		switch module {
 		case "glossary", "homophones", "spoken_word", "grammar":
 		default:
 			return fmt.Errorf("pipeline.audita.modules[%d] must be one of: glossary, homophones, spoken_word, grammar", i)
@@ -210,21 +282,31 @@ func validateAudita(cfg AuditaConfig) error {
 			return fmt.Errorf("pipeline.audita.base_url must be a valid URL")
 		}
 	}
-	if strings.TrimSpace(cfg.Model) == "" {
-		return fmt.Errorf("pipeline.audita.model is required")
+	if cfg.TotalLLMConcurrency != nil && *cfg.TotalLLMConcurrency <= 0 {
+		return fmt.Errorf("pipeline.audita.total_llm_concurrency must be > 0")
 	}
-	if cfg.LLMConcurrency == nil {
-		return fmt.Errorf("pipeline.audita.llm_concurrency must be set (defaults should populate this)")
+	if cfg.ProposalLLMConcurrency != nil && *cfg.ProposalLLMConcurrency <= 0 {
+		return fmt.Errorf("pipeline.audita.proposal_llm_concurrency must be > 0")
 	}
-	if *cfg.LLMConcurrency <= 0 {
-		return fmt.Errorf("pipeline.audita.llm_concurrency must be > 0")
-	}
-	if cfg.ValidationLLMConcurrency == nil {
-		return fmt.Errorf("pipeline.audita.validation_llm_concurrency must be set (defaults should populate this)")
-	}
-	if *cfg.ValidationLLMConcurrency <= 0 {
+	if cfg.ValidationLLMConcurrency != nil && *cfg.ValidationLLMConcurrency <= 0 {
 		return fmt.Errorf("pipeline.audita.validation_llm_concurrency must be > 0")
 	}
+	if strings.TrimSpace(cfg.TranscriptDescription) == "" && cfg.TranscriptDescription != "" {
+		return fmt.Errorf("pipeline.audita.transcript_description must be non-empty when provided")
+	}
+	if strings.TrimSpace(cfg.ConfigPath) == "" && cfg.ConfigPath != "" {
+		return fmt.Errorf("pipeline.audita.config_path must be non-empty when provided")
+	}
+	switch strings.TrimSpace(cfg.OutputSchema) {
+	case "", "bare-segments", "audita-v1":
+	default:
+		return fmt.Errorf("pipeline.audita.output_schema must be one of: bare-segments, audita-v1")
+	}
+	switch strings.TrimSpace(cfg.WorkDirRetention) {
+	case "", "always", "auto", "never":
+	default:
+		return fmt.Errorf("pipeline.audita.work_dir_retention must be one of: always, auto, never")
+	}
 	return nil
 }
 
@@ -242,28 +324,78 @@ func validateScriptorium(cfg *ScriptoriumConfig) error {
 		return err
 	}
 
-	for artifactName, artifactCfg := range cfg.Artifacts {
-		trimmedArtifactName := strings.TrimSpace(artifactName)
-		if trimmedArtifactName == "" {
-			return fmt.Errorf("pipeline.scriptorium.artifacts keys must be non-empty")
+	configuredArtifacts := make(map[string]struct{}, len(cfg.Artifacts))
+	referencedArtifacts := make(map[string]struct{})
+	for artifactName := range cfg.Artifacts {
+		if !scriptoriumArtifactKeyRE.MatchString(strings.TrimSpace(artifactName)) {
+			return fmt.Errorf("pipeline.scriptorium.artifacts keys must match ^[a-z][a-z0-9_]*$")
 		}
+		configuredArtifacts[artifactName] = struct{}{}
+	}
+
+	for artifactName, artifactCfg := range cfg.Artifacts {
 		if artifactCfg.Enabled && strings.TrimSpace(artifactCfg.PromptID) == "" {
 			return fmt.Errorf("pipeline.scriptorium.artifacts.%s.prompt_id is required when enabled", artifactName)
 		}
 		if artifactCfg.Enabled && strings.TrimSpace(artifactCfg.OutputPath) == "" {
 			return fmt.Errorf("pipeline.scriptorium.artifacts.%s.output_path is required when enabled", artifactName)
 		}
+		if strings.TrimSpace(artifactCfg.OutputPath) != "" {
+			pathField := "pipeline.scriptorium.artifacts." + artifactName + ".output_path"
+			if err := validateRelativeSafePath(pathField, artifactCfg.OutputPath); err != nil {
+				return err
+			}
+			if err := validatePathWithinRoot(pathField, artifactCfg.OutputPath, DefaultScriptoriumArtifactOutputRoot); err != nil {
+				return err
+			}
+		}
 		if err := validateDuration("pipeline.scriptorium.artifacts."+artifactName+".timeout", artifactCfg.Timeout); err != nil {
 			return err
 		}
+
+		depSet := make(map[string]struct{}, len(artifactCfg.DependsOn))
+		for i, depName := range artifactCfg.DependsOn {
+			trimmedDep := strings.TrimSpace(depName)
+			field := fmt.Sprintf("pipeline.scriptorium.artifacts.%s.depends_on[%d]", artifactName, i)
+			if trimmedDep == "" {
+				return fmt.Errorf("%s must be non-empty", field)
+			}
+			if _, ok := configuredArtifacts[trimmedDep]; !ok {
+				return fmt.Errorf("%s %q is not a configured artifact key", field, depName)
+			}
+			if trimmedDep == artifactName {
+				return fmt.Errorf("pipeline.scriptorium.artifacts.%s.depends_on must not include itself", artifactName)
+			}
+			depSet[trimmedDep] = struct{}{}
+			referencedArtifacts[trimmedDep] = struct{}{}
+		}
+
 		for inputName, inputCfg := range artifactCfg.Inputs {
 			trimmedInputName := strings.TrimSpace(inputName)
 			if trimmedInputName == "" {
 				return fmt.Errorf("pipeline.scriptorium.artifacts.%s.inputs keys must be non-empty", artifactName)
 			}
-			if strings.TrimSpace(inputCfg.Source) == "" {
+			source := strings.TrimSpace(inputCfg.Source)
+			if source == "" {
 				return fmt.Errorf("pipeline.scriptorium.artifacts.%s.inputs.%s.source is required", artifactName, inputName)
 			}
+
+			referencedArtifact, err := validateScriptoriumInputSource(artifactName, inputName, source, configuredArtifacts)
+			if err != nil {
+				return err
+			}
+			if referencedArtifact != "" {
+				if _, ok := depSet[referencedArtifact]; !ok {
+					return fmt.Errorf(
+						"pipeline.scriptorium.artifacts.%s.inputs.%s.source %q requires depends_on entry %q",
+						artifactName,
+						inputName,
+						source,
+						referencedArtifact,
+					)
+				}
+				referencedArtifacts[referencedArtifact] = struct{}{}
+			}
 		}
 		for varName, varValue := range artifactCfg.Vars {
 			if strings.TrimSpace(varName) == "" {
@@ -277,6 +409,17 @@ func validateScriptorium(cfg *ScriptoriumConfig) error {
 		}
 	}
 
+	for artifactName := range referencedArtifacts {
+		artifactCfg := cfg.Artifacts[artifactName]
+		if strings.TrimSpace(artifactCfg.OutputPath) == "" {
+			return fmt.Errorf("pipeline.scriptorium.artifacts.%s.output_path is required when artifact is referenced", artifactName)
+		}
+	}
+
+	if err := validateEnabledArtifactDependencyCycles(cfg.Artifacts); err != nil {
+		return err
+	}
+
 	return nil
 }
 
@@ -284,6 +427,9 @@ func validateSession(cfg *SessionConfig) error {
 	if strings.TrimSpace(cfg.SessionID) == "" {
 		return fmt.Errorf("session.session_id is required")
 	}
+	if strings.TrimSpace(cfg.Campaign) == "" {
+		return fmt.Errorf("session.campaign is required")
+	}
 
 	if strings.TrimSpace(cfg.Inputs.SpeakersFile) == "" {
 		return fmt.Errorf("session.inputs.speakers_file is required")
@@ -297,13 +443,205 @@ func validateSession(cfg *SessionConfig) error {
 
 	hasAudioDir := strings.TrimSpace(cfg.Inputs.AudioDir) != ""
 	hasAudioFiles := len(cfg.Inputs.AudioFiles) > 0
-	if !hasAudioDir && !hasAudioFiles {
-		return fmt.Errorf("session.inputs requires audio_dir or at least one audio_files entry")
+	hasAudioS3 := cfg.Inputs.AudioS3 != nil
+	if hasAudioS3 {
+		if strings.TrimSpace(cfg.Inputs.AudioS3.Prefix) == "" {
+			return fmt.Errorf("session.inputs.audio_s3.prefix is required when session.inputs.audio_s3 is configured")
+		}
+		if err := validateRelativeSafePath("session.inputs.audio_s3.prefix", cfg.Inputs.AudioS3.Prefix); err != nil {
+			return err
+		}
+	}
+	if hasAudioS3 && (hasAudioDir || hasAudioFiles) {
+		return fmt.Errorf("session.inputs.audio_dir/audio_files and session.inputs.audio_s3 are mutually exclusive")
+	}
+	if !hasAudioDir && !hasAudioFiles && !hasAudioS3 {
+		return fmt.Errorf("session.inputs requires audio_dir, at least one audio_files entry, or audio_s3")
 	}
 
 	return nil
 }
 
+func validateCrossConfig(pipeline *PipelineConfig, session *SessionConfig) error {
+	if pipeline == nil || session == nil {
+		return nil
+	}
+	if pipeline.Storage.S3 == nil {
+		return nil
+	}
+
+	audioS3Enabled := session.Inputs.AudioS3 != nil
+	archiveUploadEnabled := archiveUploadConfiguredForS3(pipeline)
+	if (audioS3Enabled || archiveUploadEnabled) && strings.TrimSpace(pipeline.Storage.S3.Bucket) == "" {
+		return fmt.Errorf("pipeline.storage.s3.bucket is required when S3 session audio or archive upload is enabled")
+	}
+	return nil
+}
+
+func archiveUploadConfiguredForS3(pipeline *PipelineConfig) bool {
+	if pipeline == nil || pipeline.Archive == nil {
+		return false
+	}
+	if !strings.EqualFold(strings.TrimSpace(pipeline.Storage.Backend), "s3") {
+		return false
+	}
+	enabled := true
+	if pipeline.Archive.Enabled != nil {
+		enabled = *pipeline.Archive.Enabled
+	}
+	upload := true
+	if pipeline.Archive.UploadRun != nil {
+		upload = *pipeline.Archive.UploadRun
+	}
+	return enabled && upload
+}
+
+var windowsAbsPathRE = regexp.MustCompile(`^[A-Za-z]:[\\/].*`)
+var envVarNameRE = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
+var scriptoriumArtifactKeyRE = regexp.MustCompile(`^[a-z][a-z0-9_]*$`)
+var narratioArtifactSourceRE = regexp.MustCompile(`^narratio\.artifact\.([a-z][a-z0-9_]*)$`)
+
+func validateScriptoriumInputSource(artifactName, inputName, source string, configuredArtifacts map[string]struct{}) (string, error) {
+	if isStaticSupportedScriptoriumInputSource(source) {
+		return "", nil
+	}
+	matches := narratioArtifactSourceRE.FindStringSubmatch(source)
+	if len(matches) != 2 {
+		return "", fmt.Errorf(
+			"pipeline.scriptorium.artifacts.%s.inputs.%s.source %q is unsupported",
+			artifactName,
+			inputName,
+			source,
+		)
+	}
+	referenced := matches[1]
+	if _, ok := configuredArtifacts[referenced]; !ok {
+		return "", fmt.Errorf(
+			"pipeline.scriptorium.artifacts.%s.inputs.%s.source %q references unknown artifact %q",
+			artifactName,
+			inputName,
+			source,
+			referenced,
+		)
+	}
+	return referenced, nil
+}
+
+func isStaticSupportedScriptoriumInputSource(source string) bool {
+	switch strings.TrimSpace(source) {
+	case "previous_session_artifact":
+		return true
+	case "narratio.transcript.merged":
+		return true
+	case "narratio.transcript.polished":
+		return true
+	case "narratio.transcript.full":
+		return true
+	case "narratio.transcript.trimmed":
+		return true
+	case "narratio.bounds.session":
+		return true
+	default:
+		return false
+	}
+}
+
+func validateEnvVarNameField(fieldName, value string) error {
+	trimmed := strings.TrimSpace(value)
+	if trimmed == "" {
+		return fmt.Errorf("%s must be non-empty", fieldName)
+	}
+	if !envVarNameRE.MatchString(trimmed) {
+		return fmt.Errorf("%s must be a valid environment variable name", fieldName)
+	}
+	return nil
+}
+
+func validateRelativeSafePath(fieldName, value string) error {
+	trimmed := strings.TrimSpace(value)
+	if trimmed == "" {
+		return fmt.Errorf("%s must be non-empty", fieldName)
+	}
+	if filepath.IsAbs(trimmed) || strings.HasPrefix(trimmed, "/") || strings.HasPrefix(trimmed, "\\") || windowsAbsPathRE.MatchString(trimmed) {
+		return fmt.Errorf("%s must be a relative path", fieldName)
+	}
+
+	normalized := strings.ReplaceAll(trimmed, "\\", "/")
+	for _, segment := range strings.Split(normalized, "/") {
+		if segment == ".." {
+			return fmt.Errorf("%s must not contain path traversal", fieldName)
+		}
+	}
+	return nil
+}
+
+func validatePathWithinRoot(fieldName, value, root string) error {
+	normalizedValue := filepath.ToSlash(filepath.Clean(strings.TrimSpace(value)))
+	normalizedRoot := filepath.ToSlash(filepath.Clean(strings.TrimSpace(root)))
+	if normalizedValue == normalizedRoot {
+		return nil
+	}
+	if strings.HasPrefix(normalizedValue, normalizedRoot+"/") {
+		return nil
+	}
+	return fmt.Errorf("%s must be under %s/", fieldName, normalizedRoot)
+}
+
+func validateEnabledArtifactDependencyCycles(artifacts map[string]ScriptoriumArtifactConfig) error {
+	if len(artifacts) == 0 {
+		return nil
+	}
+
+	enabled := make(map[string]struct{}, len(artifacts))
+	graph := make(map[string][]string, len(artifacts))
+	for name, cfg := range artifacts {
+		if !cfg.Enabled {
+			continue
+		}
+		enabled[name] = struct{}{}
+	}
+	for name, cfg := range artifacts {
+		if !cfg.Enabled {
+			continue
+		}
+		for _, dep := range cfg.DependsOn {
+			trimmedDep := strings.TrimSpace(dep)
+			if _, ok := enabled[trimmedDep]; ok {
+				graph[name] = append(graph[name], trimmedDep)
+			}
+		}
+	}
+
+	visiting := make(map[string]bool, len(enabled))
+	visited := make(map[string]bool, len(enabled))
+
+	var visit func(node string) error
+	visit = func(node string) error {
+		if visiting[node] {
+			return fmt.Errorf("pipeline.scriptorium.artifacts enabled dependencies must not contain cycles")
+		}
+		if visited[node] {
+			return nil
+		}
+		visiting[node] = true
+		for _, dep := range graph[node] {
+			if err := visit(dep); err != nil {
+				return err
+			}
+		}
+		visiting[node] = false
+		visited[node] = true
+		return nil
+	}
+
+	for node := range enabled {
+		if err := visit(node); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
 func validateDuration(fieldName, value string) error {
 	trimmed := strings.TrimSpace(value)
 	if trimmed == "" {

internal/manifest/manifest.go

@@ -14,17 +14,26 @@ type ErrorRecord struct {
 
 // InputRecord captures one resolved input and optional checksum.
 type InputRecord struct {
-	Kind     string `json:"kind"`
-	Path     string `json:"path"`
-	Checksum string `json:"checksum,omitempty"`
+	Kind      string `json:"kind"`
+	Path      string `json:"path"`
+	Checksum  string `json:"checksum,omitempty"`
+	Source    string `json:"source,omitempty"`
+	S3Bucket  string `json:"s3_bucket,omitempty"`
+	S3Key     string `json:"s3_key,omitempty"`
+	S3Size    int64  `json:"s3_size,omitempty"`
+	S3ETag    string `json:"s3_etag,omitempty"`
+	SpoolPath string `json:"spool_path,omitempty"`
 }
 
 // ArtifactRecord captures one produced artifact and optional remote metadata.
 type ArtifactRecord struct {
 	Kind      string `json:"kind"`
+	SourceID  string `json:"source_id,omitempty"`
 	LocalPath string `json:"local_path"`
-	RemoteKey string `json:"remote_key,omitempty"`
-	Checksum  string `json:"checksum,omitempty"`
+	// ProducerRunID identifies the run that produced this durable artifact.
+	ProducerRunID string `json:"producer_run_id,omitempty"`
+	RemoteKey     string `json:"remote_key,omitempty"`
+	Checksum      string `json:"checksum,omitempty"`
 }
 
 // StageRecord tracks lifecycle and provenance for one pipeline stage.
@@ -45,6 +54,13 @@ type StageRecord struct {
 // Manifest is the durable run-state record for a session execution.
 type Manifest struct {
 	SessionID       string                  `json:"session_id"`
+	Campaign        string                  `json:"campaign,omitempty"`
+	RunID           string                  `json:"run_id,omitempty"`
+	LocalWorkDir    string                  `json:"local_workdir,omitempty"`
+	LocalSpoolDir   string                  `json:"local_spool_dir,omitempty"`
+	S3Bucket        string                  `json:"s3_bucket,omitempty"`
+	S3SessionPrefix string                  `json:"s3_session_prefix,omitempty"`
+	S3RunPrefix     string                  `json:"s3_run_prefix,omitempty"`
 	PipelineVersion string                  `json:"pipeline_version,omitempty"`
 	CreatedAt       time.Time               `json:"created_at"`
 	UpdatedAt       time.Time               `json:"updated_at"`
@@ -107,6 +123,15 @@ func (m *Manifest) MarkStageSkipped(name string, at time.Time, reason string) {
 	m.UpdatedAt = at
 }
 
+// MarkStageStale marks a stage as stale so it is not skipped as idempotently complete.
+func (m *Manifest) MarkStageStale(name string, at time.Time, reason string) {
+	s := m.ensureStage(name, at)
+	s.Status = StatusStale
+	s.Error = &ErrorRecord{Message: strings.TrimSpace(reason), Code: "stale", At: timePtr(at)}
+	s.UpdatedAt = at
+	m.UpdatedAt = at
+}
+
 func (m *Manifest) ensureStage(name string, at time.Time) *StageRecord {
 	if m.Stages == nil {
 		m.Stages = map[string]*StageRecord{}

internal/manifest/run_manifest.go

@@ -0,0 +1,164 @@
+package manifest
+
+import (
+	"strings"
+	"time"
+)
+
+type RunManifestStatus string
+
+const (
+	RunManifestStatusRunning   RunManifestStatus = "running"
+	RunManifestStatusSucceeded RunManifestStatus = "succeeded"
+	RunManifestStatusFailed    RunManifestStatus = "failed"
+)
+
+type RunStageAction string
+
+const (
+	RunStageActionRun  RunStageAction = "run"
+	RunStageActionSkip RunStageAction = "skip"
+)
+
+// RunStageRecord tracks lifecycle and provenance for one stage within a single invocation.
+type RunStageRecord struct {
+	Name             string           `json:"name"`
+	Action           RunStageAction   `json:"action"`
+	Status           StageStatus      `json:"status"`
+	CreatedAt        time.Time        `json:"created_at"`
+	UpdatedAt        time.Time        `json:"updated_at"`
+	StartedAt        *time.Time       `json:"started_at,omitempty"`
+	CompletedAt      *time.Time       `json:"completed_at,omitempty"`
+	Outputs          []ArtifactRecord `json:"outputs,omitempty"`
+	Logs             []string         `json:"logs,omitempty"`
+	GeneratedConfigs []string         `json:"generated_configs,omitempty"`
+	Error            *ErrorRecord     `json:"error,omitempty"`
+	Metadata         map[string]any   `json:"metadata,omitempty"`
+}
+
+// RunManifest is the invocation-scoped execution record under runs/{run_id}/manifest.json.
+type RunManifest struct {
+	SessionID           string                     `json:"session_id"`
+	Campaign            string                     `json:"campaign,omitempty"`
+	RunID               string                     `json:"run_id"`
+	Force               bool                       `json:"force"`
+	RequestedStages     []string                   `json:"requested_stages,omitempty"`
+	SessionManifestPath string                     `json:"session_manifest_path,omitempty"`
+	LocalWorkDir        string                     `json:"local_workdir,omitempty"`
+	LocalSpoolDir       string                     `json:"local_spool_dir,omitempty"`
+	S3Bucket            string                     `json:"s3_bucket,omitempty"`
+	S3SessionPrefix     string                     `json:"s3_session_prefix,omitempty"`
+	S3RunPrefix         string                     `json:"s3_run_prefix,omitempty"`
+	CreatedAt           time.Time                  `json:"created_at"`
+	UpdatedAt           time.Time                  `json:"updated_at"`
+	StartedAt           *time.Time                 `json:"started_at,omitempty"`
+	CompletedAt         *time.Time                 `json:"completed_at,omitempty"`
+	Status              RunManifestStatus          `json:"status"`
+	LastError           *ErrorRecord               `json:"last_error,omitempty"`
+	Stages              map[string]*RunStageRecord `json:"stages"`
+	Metadata            map[string]any             `json:"metadata,omitempty"`
+}
+
+// NewRun constructs a new run manifest with deterministic timestamps.
+func NewRun(sessionID, campaign, runID string, force bool, requestedStages []string, now time.Time) *RunManifest {
+	return &RunManifest{
+		SessionID:       strings.TrimSpace(sessionID),
+		Campaign:        strings.TrimSpace(campaign),
+		RunID:           strings.TrimSpace(runID),
+		Force:           force,
+		RequestedStages: append([]string(nil), requestedStages...),
+		CreatedAt:       now,
+		UpdatedAt:       now,
+		StartedAt:       timePtr(now),
+		Status:          RunManifestStatusRunning,
+		Stages:          map[string]*RunStageRecord{},
+	}
+}
+
+func (m *RunManifest) SetStageAction(name string, action RunStageAction, at time.Time) {
+	s := m.ensureStage(name, at)
+	s.Action = action
+	s.UpdatedAt = at
+	m.UpdatedAt = at
+}
+
+func (m *RunManifest) MarkStageRunning(name string, at time.Time) {
+	s := m.ensureStage(name, at)
+	s.Status = StatusRunning
+	s.StartedAt = timePtr(at)
+	s.CompletedAt = nil
+	s.Error = nil
+	s.UpdatedAt = at
+	m.UpdatedAt = at
+}
+
+func (m *RunManifest) MarkStageSucceeded(name string, at time.Time, outputs []ArtifactRecord) {
+	s := m.ensureStage(name, at)
+	s.Status = StatusSucceeded
+	s.CompletedAt = timePtr(at)
+	s.Error = nil
+	s.Outputs = append([]ArtifactRecord(nil), outputs...)
+	s.UpdatedAt = at
+	m.UpdatedAt = at
+}
+
+func (m *RunManifest) MarkStageFailed(name string, at time.Time, message string) {
+	s := m.ensureStage(name, at)
+	s.Status = StatusFailed
+	s.CompletedAt = timePtr(at)
+	s.Error = &ErrorRecord{Message: strings.TrimSpace(message), At: timePtr(at)}
+	s.UpdatedAt = at
+	m.LastError = &ErrorRecord{Message: strings.TrimSpace(message), At: timePtr(at)}
+	m.UpdatedAt = at
+	m.Status = RunManifestStatusFailed
+	m.CompletedAt = timePtr(at)
+}
+
+func (m *RunManifest) MarkStageSkipped(name string, at time.Time, reason string) {
+	s := m.ensureStage(name, at)
+	s.Status = StatusSkipped
+	s.CompletedAt = timePtr(at)
+	s.Error = &ErrorRecord{Message: strings.TrimSpace(reason), Code: "skipped", At: timePtr(at)}
+	s.UpdatedAt = at
+	m.UpdatedAt = at
+}
+
+func (m *RunManifest) MarkSucceeded(at time.Time) {
+	m.Status = RunManifestStatusSucceeded
+	m.CompletedAt = timePtr(at)
+	m.UpdatedAt = at
+}
+
+func (m *RunManifest) MarkFailed(at time.Time, message string) {
+	m.Status = RunManifestStatusFailed
+	m.CompletedAt = timePtr(at)
+	m.LastError = &ErrorRecord{Message: strings.TrimSpace(message), At: timePtr(at)}
+	m.UpdatedAt = at
+}
+
+func (m *RunManifest) ensureStage(name string, at time.Time) *RunStageRecord {
+	if m.Stages == nil {
+		m.Stages = map[string]*RunStageRecord{}
+	}
+
+	stageName := strings.TrimSpace(name)
+	s, ok := m.Stages[stageName]
+	if !ok || s == nil {
+		s = &RunStageRecord{
+			Name:      stageName,
+			Action:    RunStageActionRun,
+			Status:    StatusPending,
+			CreatedAt: at,
+			UpdatedAt: at,
+		}
+		m.Stages[stageName] = s
+	}
+	if s.Name == "" {
+		s.Name = stageName
+	}
+	if s.CreatedAt.IsZero() {
+		s.CreatedAt = at
+	}
+
+	return s
+}