narratio/README.md

# narratio

`narratio` is a Go orchestration application for processing D&D session audio into transcripts and generated 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:

- `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

Pipeline config lookup for CLI commands:

- if `--config <path>` is provided, Narratio uses that path
- if `--config` is omitted, Narratio searches in this order:
  - `/usr/local/etc/narratio/pipeline.yml`
  - `/etc/narratio/pipeline.yml`

Session config lookup for CLI commands:

- if `--session <path>` is provided, Narratio uses that path
- if `--session` is omitted, Narratio searches in this order:
  - `./session.yml`
  - `/usr/local/etc/narratio/session.yml`
  - `/etc/narratio/session.yml`

Session template support:

- Narratio renders `session.yml` templates before strict YAML decode.
- `--session-id <value>` provides the `session_id` template variable.
- Supported placeholder forms:
  - `{{session_id}}`
  - `{{ session_id }}`
- unresolved template placeholders fail with a clear error.
- strict YAML validation still runs after rendering.
- concrete `session.yml` files without templates remain fully supported.

Optional secrets-from-files config:

- `pipeline.secrets.env_dir` may point to a directory of secret files
- each top-level file with an env-var-style name is loaded as an environment variable:
  - file name = env var name
  - file contents = env var value (trailing newline/CRLF trimmed)
- process environment wins: existing env vars are not overwritten
- if configured, Narratio fails fast when `env_dir` is missing/unreadable
- relative `env_dir` values resolve from Narratio’s current working directory

YAML decoding is strict (`KnownFields(true)`), so unknown fields fail fast.

## Storage And Archive Foundations

Narratio now includes configuration and path-model foundations for archive support, plus implemented prepare-stage S3 audio input.

Implemented foundations:

- `pipeline.storage.s3` config shape (`bucket`, `root_prefix`, `region`, `endpoint`, `force_path_style`, `access_key_id_env`, `secret_access_key_env`)
- `pipeline.spool` config shape (`root`, `delete_audio_after_archive`)
- `pipeline.archive` config shape (`enabled`, `upload_run`, `promote_artifacts`)
- promotion-rule validation (`from`/`to` required, relative-only paths, traversal rejected)
- `session.campaign` requirement for campaign-aware path construction
- optional `session.inputs.audio_s3.prefix` modeling and prepare-stage S3 audio download
- run ID generation and S3/local path helper foundations
- manifest run/path identity fields

Current defaults:

- `pipeline.storage.s3.root_prefix`: `dnd`
- `pipeline.storage.s3.access_key_id_env`: `OBJECT_STORAGE_KEY_ID`
- `pipeline.storage.s3.secret_access_key_env`: `OBJECT_STORAGE_KEY`
- `pipeline.workspace.cleanup_after_archive`: `false`
- `pipeline.spool.root`: `/var/spool/narratio`
- `pipeline.spool.delete_audio_after_archive`: `false`
- `pipeline.archive.enabled`: `true`
- `pipeline.archive.upload_run`: `true`
- default `pipeline.archive.promote_artifacts`:
  - `transcripts/trimmed.json` -> `transcripts/trimmed.json` (`required: true`)
  - `artifacts/session_recap.md` -> `artifacts/session_recap.md` (`required: true`)

Current boundaries:

- local development audio (`audio_dir` / `audio_files`) still works
- `audio_dir`/`audio_files` and `audio_s3` are mutually exclusive
- real S3-compatible backend now exists in the storage adapter package
- storage backend tests use fake storage and do not require live S3
- archive uploads successful run records under `runs/{run_id}/`
- archive does not upload local audio by default
- archive uploads promoted outputs to session-level keys using `archive.promote_artifacts`
- archive uploads `current/manifest.json`
- archive uploads `current/run_id.txt` last as the effective commit marker
- required missing promotions fail archive
- optional missing promotions are skipped and recorded
- cleanup remains conservative and opt-in:
  - `pipeline.spool.delete_audio_after_archive: true` removes only the run-scoped spool audio directory after successful archive commit
  - `pipeline.workspace.cleanup_after_archive: true` removes only the run-scoped local workdir after successful archive commit
  - cleanup executes only after all selected stages for the command invocation succeed
  - cleanup does not run for failed, incomplete, skipped, or unarchived runs
- local development `audio_dir`/`audio_files` source inputs are never deleted by spool cleanup
- S3 credentials are resolved from configured env-var names when both are present; if either is missing, Narratio falls back to the AWS SDK default credential chain

S3 input details and current boundaries are documented in [docs/s3-audio-input.md](docs/s3-audio-input.md).

## Remote Storage Backend

Narratio includes an object-store backend layer for future prepare/archive work:

- `List(ctx, prefix)`
- `Download(ctx, key, localPath)`
- `Upload(ctx, localPath, key, opts)`
- `Exists(ctx, key)`

Implemented backends:

- fake storage backend for deterministic tests
- S3-compatible backend built from `pipeline.storage.s3`

Key invariant:

- callers pass full bucket-relative object keys
- storage backends do not prepend `root_prefix` and do not infer session/campaign paths

Current boundary:

- `prepare` uses `List` + `Download` through the backend when `session.inputs.audio_s3` is configured
- `archive` uses `Upload` through the backend for successful run-record uploads
- `archive` also uses `Upload` for promotion writes and current pointers
- no failed or incomplete runs are uploaded
- local audio is not re-uploaded by default

Archive run-upload details and boundaries are documented in [docs/archive-storage.md](docs/archive-storage.md).

## 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

## Seriatim Configuration

`pipeline.seriatim` configures the Seriatim subprocess adapter used by `merge`, `normalize`, and `trim`.

Minimal behavior:

- `pipeline.seriatim` may be omitted entirely.
- when omitted, Narratio defaults to:
  - `binary: seriatim`
  - `timeout: 10m`
  - `output_schema: seriatim-intermediate`
  - `coalesce_gap: 3.0`
  - `report: true`

Optional overrides in `pipeline.seriatim` continue to work, including explicit binary paths and advanced `env` tuning values.

## Audita Configuration

`pipeline.audita` configures the real Audita subprocess adapter used by `polish`.

Minimal behavior:

- `pipeline.audita` may be omitted entirely.
- when omitted, Narratio defaults to:
  - `binary: audita`
  - `timeout: 3h`
  - `report: true`

Optional:

- `llm_api_key_env` (when set, Narratio requires that env var and passes it to Audita as `AUDITA_LLM_API_KEY`)
- `modules` override list (when empty/omitted, Narratio does not pass `--modules`)
- `base_url` (when omitted, Narratio does not pass `--base-url`; Audita runtime defaults/config may apply)
- `model` (when omitted, Narratio does not pass `--model`; Audita runtime defaults/config may apply)
- `transcript_description`
- `config_path`
- `output_schema` (`bare-segments` or `audita-v1`)
- `work_dir_retention` (`always`, `auto`, or `never`)
- `total_llm_concurrency` (> 0 when provided)
- `proposal_llm_concurrency` (> 0 when provided)
- `validation_model`
- `validation_llm_concurrency` (> 0 when provided)
- `report` (defaults to `true`)

Narratio passes only configured optional Audita flags. Omitted optional values are left to Audita runtime defaults/config.

## 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` defaults to `scriptorium` 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.

If `pipeline.secrets.env_dir` is configured, keep only references and secret files there; secret values are still not written to manifests, generated configs, or Narratio-managed logs.

## 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/pipeline.audita-overrides.yml`
- `examples/session.minimal.yml`
- `examples/session.template.yml`
- `examples/speakers.yml`

## Commands

Run tests:

```bash
go test ./...
```

Plan a run:

```bash
go run ./cmd/narratio plan --session examples/session.minimal.yml
```

Use `--config <path>` to override default pipeline lookup when needed.

Run with a discoverable session template:

```bash
go run ./cmd/narratio run --session-id 2026-04-04
```

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
```

Resume with a template session ID:

```bash
go run ./cmd/narratio resume --config examples/pipeline.minimal.yml --session examples/session.template.yml --session-id 2026-04-04
```

## 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