13 Commits

Author SHA1 Message Date
bc2ade38d9 Finalize previous-session artifact documentation and restore-analyze continuity coverage 2026-05-20 15:17:04 +00:00
5be831eb13 Restore archived previous-session cache files with session state 2026-05-20 15:05:48 +00:00
cae4d99a89 Archive durable previous-session cache files with session state 2026-05-20 15:03:30 +00:00
e09dc0512d Add analyze integration coverage for previous-session inputs 2026-05-20 15:01:27 +00:00
ae82bc1ce0 Resolve canonical previous-session artifact sources from prepared previous cache 2026-05-20 14:59:28 +00:00
01eb7aa1aa Add prepare rerun guidance for unresolved previous-session analyze inputs 2026-05-20 14:55:44 +00:00
2ca700195c Integrate previous-session artifact hydration into prepare stage 2026-05-20 14:53:22 +00:00
2b08c34539 Add prepare helper to hydrate previous-session artifacts from archive 2026-05-20 14:49:22 +00:00
79f1fc1e09 Add helper to collect previous-session artifact input requirements 2026-05-20 14:37:02 +00:00
9c753270bd Add canonical previous-session artifact source parsing and validation 2026-05-20 14:34:23 +00:00
b907cb01aa Add previous-session workspace path helpers and layout support 2026-05-20 14:31:03 +00:00
7824afd4a5 Add previous session ID templating and CLI support 2026-05-20 14:26:32 +00:00
2a4e1e912c Update documentation to include a roadmap for previous session artifact support 2026-05-20 09:12:17 -05:00
51 changed files with 3696 additions and 913 deletions

View File

@@ -30,6 +30,7 @@ For config semantics, see [docs/config.md](./config.md). For operator lifecycle
- `--config <path>`: optional explicit `pipeline.yml` path. - `--config <path>`: optional explicit `pipeline.yml` path.
- `--session <path>`: optional explicit `session.yml` path. - `--session <path>`: optional explicit `session.yml` path.
- `--session-id <value>`: session template variable value. - `--session-id <value>`: session template variable value.
- `--previous-session-id <value>`: previous-session template variable value.
- `--force`: force stage execution. - `--force`: force stage execution.
- `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated). - `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated).
@@ -38,6 +39,7 @@ For config semantics, see [docs/config.md](./config.md). For operator lifecycle
- `--config <path>` - `--config <path>`
- `--session <path>` - `--session <path>`
- `--session-id <value>` - `--session-id <value>`
- `--previous-session-id <value>`
- `--force` - `--force`
### `resume` ### `resume`
@@ -45,6 +47,7 @@ For config semantics, see [docs/config.md](./config.md). For operator lifecycle
- `--config <path>` - `--config <path>`
- `--session <path>` - `--session <path>`
- `--session-id <value>` - `--session-id <value>`
- `--previous-session-id <value>`
- `--force` - `--force`
- `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated). - `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated).
@@ -53,6 +56,7 @@ For config semantics, see [docs/config.md](./config.md). For operator lifecycle
- `--config <path>` - `--config <path>`
- `--session <path>` - `--session <path>`
- `--session-id <value>` - `--session-id <value>`
- `--previous-session-id <value>`
- `--force` - `--force`
- `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated). - `--artifacts <names>`: analyze artifact keys to execute (repeatable or comma-separated).
- positional `<stage>`: required stage name. - positional `<stage>`: required stage name.
@@ -74,6 +78,7 @@ Valid stage names:
- `--config <path>` - `--config <path>`
- `--session <path>` - `--session <path>`
- `--session-id <value>` - `--session-id <value>`
- `--previous-session-id <value>`
- `--dry-run`: plan restore actions without writing local files. - `--dry-run`: plan restore actions without writing local files.
- `--force`: overwrite local conflicting files with remote archive files. - `--force`: overwrite local conflicting files with remote archive files.
- `--include-audio`: include durable archived `audio/**` files in restore scope. - `--include-audio`: include durable archived `audio/**` files in restore scope.
@@ -92,7 +97,7 @@ Purpose:
Syntax: Syntax:
```bash ```bash
narratio run [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] [--artifacts <name[,name...]>] narratio run [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--previous-session-id <id>] [--force] [--artifacts <name[,name...]>]
``` ```
Success output: Success output:
@@ -112,7 +117,7 @@ Purpose:
Syntax: Syntax:
```bash ```bash
narratio plan [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] narratio plan [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--previous-session-id <id>] [--force]
``` ```
Success output includes: Success output includes:
@@ -132,7 +137,7 @@ Purpose:
Syntax: Syntax:
```bash ```bash
narratio resume [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] [--artifacts <name[,name...]>] narratio resume [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--previous-session-id <id>] [--force] [--artifacts <name[,name...]>]
``` ```
Success output: Success output:
@@ -172,7 +177,7 @@ Purpose:
Syntax: Syntax:
```bash ```bash
narratio run-stage [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--force] [--artifacts <name[,name...]>] <stage> narratio run-stage [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--previous-session-id <id>] [--force] [--artifacts <name[,name...]>] <stage>
``` ```
Success output: Success output:
@@ -191,12 +196,12 @@ Common failure cases:
### `restore` ### `restore`
Purpose: Purpose:
- Restore durable session state (`manifest.json`, `transcripts/**`, `artifacts/**`, and optional `audio/**`) from the committed remote archive current state. - Restore durable session state (`manifest.json`, `transcripts/**`, `artifacts/**`, `previous/**`, and optional `audio/**`) from the committed remote archive current state.
Syntax: Syntax:
```bash ```bash
narratio restore [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--dry-run] [--force] [--include-audio] narratio restore [--config <pipeline.yml>] [--session <session.yml>] [--session-id <id>] [--previous-session-id <id>] [--dry-run] [--force] [--include-audio]
``` ```
Success output (dry-run): Success output (dry-run):
@@ -260,6 +265,12 @@ narratio restore --session-id 2026-04-04
narratio run-stage --session-id 2026-04-04 --force analyze narratio run-stage --session-id 2026-04-04 --force analyze
``` ```
Rehydrate canonical previous-session inputs after artifact-input changes:
```bash
narratio run-stage --session-id 2026-04-04 --force prepare
```
## Diagnostic / Recovery Commands ## Diagnostic / Recovery Commands
Inspect stage status: Inspect stage status:

View File

@@ -48,9 +48,13 @@ Template behavior:
- supported placeholders: - supported placeholders:
- `{{session_id}}` - `{{session_id}}`
- `{{ session_id }}` - `{{ session_id }}`
- `{{previous_session_id}}`
- `{{ previous_session_id }}`
- `--session-id <value>` supplies the placeholder value. - `--session-id <value>` supplies the placeholder value.
- `--previous-session-id <value>` supplies the previous-session placeholder value.
- unresolved placeholders fail load. - unresolved placeholders fail load.
- if rendered `session_id` mismatches `--session-id`, load fails. - if rendered `session_id` mismatches `--session-id`, load fails.
- if rendered `previous_session_id` mismatches `--previous-session-id`, load fails.
## 4. Minimal pipeline config ## 4. Minimal pipeline config
@@ -83,6 +87,23 @@ Usage:
narratio run --config /path/to/pipeline.yml --session ./session.yml --session-id 2026-05-03 narratio run --config /path/to/pipeline.yml --session ./session.yml --session-id 2026-05-03
``` ```
Previous-session-enabled variant:
```yaml
session_id: "{{ session_id }}"
previous_session_id: "{{ previous_session_id }}"
campaign: sample-campaign
inputs:
audio_dir: ./audio
speakers_file: ./examples/speakers.yml
autocorrect_file: ./examples/autocorrect.yml
glossary_file: ./examples/glossary.yml
```
```bash
narratio run --config /path/to/pipeline.yml --session ./session.yml --session-id 2026-05-03 --previous-session-id 2026-04-26
```
## 6. Production-oriented config ## 6. Production-oriented config
```yaml ```yaml
@@ -127,6 +148,9 @@ scriptorium:
transcript: transcript:
source: narratio.transcript.trimmed source: narratio.transcript.trimmed
required: true required: true
previous_recap:
source: narratio.previous_session.artifact.session_recap
required: false
``` ```
Operational notes: Operational notes:
@@ -243,13 +267,14 @@ Scriptorium artifact-key and dependency rules:
Allowed `pipeline.scriptorium.artifacts.<name>.inputs.<key>.source` values: Allowed `pipeline.scriptorium.artifacts.<name>.inputs.<key>.source` values:
- `previous_session_artifact` - `narratio.previous_session.artifact.<configured_artifact_key>`
- `narratio.transcript.merged` - `narratio.transcript.merged`
- `narratio.transcript.polished` - `narratio.transcript.polished`
- `narratio.transcript.full` - `narratio.transcript.full`
- `narratio.transcript.trimmed` - `narratio.transcript.trimmed`
- `narratio.bounds.session` - `narratio.bounds.session`
- `narratio.artifact.<configured_artifact_key>` - `narratio.artifact.<configured_artifact_key>`
- `previous_session_artifact` (legacy path-based source; uses `inputs.<key>.path`)
`pipeline.archive.promote_artifacts[].source` values: `pipeline.archive.promote_artifacts[].source` values:
@@ -272,13 +297,14 @@ Archive promotion destination rules:
Restore-related implications: Restore-related implications:
- restore remote identity requires archive S3 identity to resolve (`pipeline.storage.s3.bucket` and session prefix derivation inputs). - restore remote identity requires archive S3 identity to resolve (`pipeline.storage.s3.bucket` and session prefix derivation inputs).
- restore scope considers only committed current state and durable paths (`manifest.json`, `transcripts/**`, `artifacts/**`, optional `audio/**`). - restore scope considers committed current state and durable paths (`manifest.json`, `transcripts/**`, `artifacts/**`, `previous/**`, optional `audio/**`).
## 8. Full session reference ## 8. Full session reference
| Path | Type | Required | Default | | Path | Type | Required | Default |
| --- | --- | --- | --- | | --- | --- | --- | --- |
| `session.session_id` | string | Yes | none | | `session.session_id` | string | Yes | none |
| `session.previous_session_id` | string | No | empty |
| `session.campaign` | string | Yes | none | | `session.campaign` | string | Yes | none |
| `session.date` | string | No | empty | | `session.date` | string | No | empty |
| `session.title` | string | No | empty | | `session.title` | string | No | empty |
@@ -297,6 +323,11 @@ Audio-source rule:
- `audio_s3.prefix` - `audio_s3.prefix`
- `audio_s3` cannot be combined with local audio fields. - `audio_s3` cannot be combined with local audio fields.
Previous-session rule:
- if `session.previous_session_id` is set, it must not equal `session.session_id`.
- canonical previous-session sources (`narratio.previous_session.artifact.<name>`) are hydrated during `prepare` from archive current state when required by enabled configured artifacts.
## 9. Secrets ## 9. Secrets
Narratio supports filesystem-based secret injection via `pipeline.secrets.env_dir`. Narratio supports filesystem-based secret injection via `pipeline.secrets.env_dir`.

View File

@@ -1,41 +1,35 @@
# Internal: Artifacts # Internal: Artifacts
## Purpose ## Purpose
Define Narratio's artifact identity and resolution model for built-in transcript/bounds artifacts and runtime-configured analyze artifacts. Define Narratio artifact identity, catalog, and source-resolution behavior for:
- built-in session artifacts;
- configured analyze artifacts;
- canonical previous-session artifact sources.
## Inputs and outputs ## Inputs and outputs
Inputs: Inputs:
- artifact sources from config/runtime (`pipeline.scriptorium.artifacts.*.inputs.*.source`) - configured input sources (`pipeline.scriptorium.artifacts.*.inputs.*.source`);
- session paths and optional session manifest stage outputs - session paths and manifest inputs/outputs;
- runtime artifact catalog state for configured artifact sources - runtime catalog state.
Outputs: Outputs:
- resolved local artifact path and provenance (`ResolvedSessionArtifact`) - resolved artifact path + provenance (`ResolvedSessionArtifact`);
- runtime catalog entries for planned/executable/available artifacts - runtime catalog entries for built-ins and configured artifacts;
- validation errors for unsupported, missing, or invalid artifact sources - requirement sets for canonical previous-session inputs.
## Boundaries ## Boundaries
Owns: Owns:
- built-in artifact registry and content validation rules - built-in source registry and validation;
- runtime artifact catalog for configured artifact source IDs - configured artifact catalog identity (`narratio.artifact.<name>`);
- source resolution behavior for built-in and configured artifact sources - canonical previous-session source parsing and resolution;
- previous-session requirement collection (`CollectPreviousArtifactRequirements`).
Does not own: Does not own:
- artifact generation (stages produce files) - prepare-stage remote hydration;
- manifest transition policy - stage success/skip transitions;
- archive promotion behavior - archive upload orchestration.
## 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:
## Built-in IDs
| Artifact ID | Canonical file | Producer stage | Output kind | | Artifact ID | Canonical file | Producer stage | Output kind |
| --- | --- | --- | --- | | --- | --- | --- | --- |
| `narratio.transcript.merged` | `transcripts/merged.json` | `merge` | `transcript_merged` | | `narratio.transcript.merged` | `transcripts/merged.json` | `merge` | `transcript_merged` |
@@ -44,44 +38,58 @@ Built-in registry entries:
| `narratio.transcript.trimmed` | `transcripts/trimmed.json` | `trim` | `transcript_trimmed` | | `narratio.transcript.trimmed` | `transcripts/trimmed.json` | `trim` | `transcript_trimmed` |
| `narratio.bounds.session` | `artifacts/session_bounds.json` | `trim` | `session_bounds` | | `narratio.bounds.session` | `artifacts/session_bounds.json` | `trim` | `session_bounds` |
Runtime catalog entries include built-ins and configured `narratio.artifact.<name>` sources. ## Source families
- built-in: `narratio.transcript.*`, `narratio.bounds.session`
- configured artifact: `narratio.artifact.<artifact_key>`
- canonical previous-session artifact: `narratio.previous_session.artifact.<artifact_key>`
Catalog states: ## Runtime catalog model
- `planned`: source is registered and known for this run Catalog entries track:
- `executable`: configured artifact is selected for analyze execution - `planned`: source is registered for this run;
- `available`: artifact has a usable file path (generated this run or reused from disk) - `executable`: configured artifact is selected for analyze execution;
- `available`: usable local file exists (generated this run or reused from disk).
Resolution behavior: Configured artifact provenance values include:
- 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` - `generated.current_analyze_run`
- `filesystem.disabled_artifact_output` - `filesystem.disabled_artifact_output`
Content validation: Previous-session canonical provenance values include:
- transcript built-ins: JSON with top-level `segments` array - `manifest.inputs.previous_cache`
- bounds built-in: valid JSON - `current_session.previous_cache`
- configured artifacts: non-empty text file
## Skip and resume behavior ## Resolution behavior
- resolver and catalog have no direct skip/resume decisions - Built-ins resolve via manifest producer outputs first, then canonical fallback paths.
- stage/runner skip-resume behavior consumes catalog/resolver results - Configured `narratio.artifact.<name>` sources resolve through catalog availability.
- Canonical previous-session sources resolve to current-session `previous/` cache candidates derived from configured artifact canonical output paths.
- Previous-session canonical resolution prefers manifest-recorded input paths when present, then filesystem fallback under `previous/artifacts/**`.
## Previous-session requirement scanning
`CollectPreviousArtifactRequirements`:
- scans enabled configured artifacts only;
- includes canonical previous-session sources only;
- deduplicates by artifact key;
- merges required/optional references (`required` wins);
- records deterministic sorted source locations for diagnostics.
## Validation behavior
- transcript built-ins: JSON with top-level `segments` array;
- bounds built-in: valid JSON;
- configured and previous-session artifact files: non-empty text content.
## Failure behavior ## Failure behavior
- unsupported source -> source validation error - unsupported source or malformed canonical previous source: validation/resolution error;
- known source unavailable -> `ErrSessionArtifactNotFound` - known source unavailable: `ErrSessionArtifactNotFound`;
- configured source without catalog -> resolution error - configured/previous canonical source without catalog: error;
- resolved file with invalid content -> validation error - resolved invalid file content: validation error.
## Tests to inspect before changing ## Tests to inspect before changing
- `internal/artifacts/artifact_resolver_test.go` - `internal/artifacts/artifact_resolver_test.go`
- `internal/artifacts/catalog_test.go` - `internal/artifacts/catalog_test.go`
- `internal/artifacts/previous_requirements_test.go`
- `internal/stage/prepare_previous_test.go`
- `internal/stage/analyze_test.go` - `internal/stage/analyze_test.go`
- `internal/config/scriptorium_test.go`
## Architectural invariants ## Architectural invariants
- built-in IDs are static and registry-backed - Built-in source IDs are static.
- configured artifact IDs are runtime-derived (`narratio.artifact.<name>`) and catalog-backed - Configured and previous-session source IDs are artifact-key based and validation-gated.
- built-in/source resolution remains deterministic and validation-gated - Resolution behavior remains deterministic and manifest-aware.

View File

@@ -1,11 +1,11 @@
# Internal: Command Restore # Internal: Command Restore
## Purpose ## Purpose
Define the implemented `narratio restore` command contract: committed remote-state discovery, deterministic planning, safe file installation, conflict policy, and restore reporting. Define the implemented `narratio restore` contract: committed remote-state discovery, deterministic plan classification, safe file install semantics, and restore reporting.
## Inputs and outputs ## Inputs and outputs
Inputs: Inputs:
- CLI flags: `--config`, `--session`, `--session-id`, `--dry-run`, `--force`, `--include-audio`. - CLI flags: `--config`, `--session`, `--session-id`, `--previous-session-id`, `--dry-run`, `--force`, `--include-audio`.
- Resolved/validated `pipeline.yml` and `session.yml`. - Resolved/validated `pipeline.yml` and `session.yml`.
- Configured remote object store. - Configured remote object store.
- Remote committed current-state markers (`current/run_id.txt`, `current/manifest.json`). - Remote committed current-state markers (`current/run_id.txt`, `current/manifest.json`).
@@ -54,6 +54,21 @@ Does not own:
- existing local manifest is preserved if restored manifest validation/install fails. - existing local manifest is preserved if restored manifest validation/install fails.
- Non-dry-run report persists summary/action status metadata in `reports/restore-latest.json`. - Non-dry-run report persists summary/action status metadata in `reports/restore-latest.json`.
Restore path scope:
- includes:
- `manifest.json`
- `transcripts/**`
- `artifacts/**`
- `previous/**`
- `audio/**` only when `--include-audio` is set
- excludes:
- `runs/**`
- `logs/**`
- `reports/**`
- `config/**`
- `inputs/**`
- remote `current/**` pointer files as local restore targets
## Skip and resume behavior ## Skip and resume behavior
- Restore does not participate in stage skip/resume decisions. - Restore does not participate in stage skip/resume decisions.
- Restore provides durable local state so subsequent stage commands can resume or rerun based on restored manifest state. - Restore provides durable local state so subsequent stage commands can resume or rerun based on restored manifest state.
@@ -80,7 +95,7 @@ Does not own:
- `current/run_id.txt` is the remote commit marker; restore must not infer committed state from incidental files. - `current/run_id.txt` is the remote commit marker; restore must not infer committed state from incidental files.
- Local path mapping is traversal-safe and constrained to session root. - Local path mapping is traversal-safe and constrained to session root.
- Restore scope is deterministic and path-classified: - Restore scope is deterministic and path-classified:
- include `manifest.json`, `transcripts/**`, `artifacts/**` - include `manifest.json`, `transcripts/**`, `artifacts/**`, `previous/**`
- include `audio/**` only with `--include-audio` - include `audio/**` only with `--include-audio`
- exclude `runs/**`, `logs/**`, `reports/**`, `config/**`, `inputs/**` - exclude `runs/**`, `logs/**`, `reports/**`, `config/**`, `inputs/**`
- Command remains standalone; no implicit `run --restore` behavior. - Command remains standalone; no implicit `run --restore` behavior.

View File

@@ -3,31 +3,36 @@
## Purpose ## Purpose
Execute selected configured Scriptorium artifacts in deterministic dependency order and promote successful outputs to canonical session artifact paths. Execute selected configured Scriptorium artifacts in deterministic dependency order and promote successful outputs to canonical session artifact paths.
## Inputs and Outputs ## Inputs and outputs
Inputs: Inputs:
- configured artifact definitions from `pipeline.scriptorium.artifacts` - configured artifact definitions from `pipeline.scriptorium.artifacts`;
- selected artifact filter from runtime (`--artifacts`) when provided - selected artifact filter (`--artifacts`) when provided;
- resolved artifact input sources declared per artifact (`inputs.*.source`) - resolved artifact sources from resolver/catalog.
- optional previous-session file inputs (`previous_session_artifact`)
Source types used by analyze:
- built-ins: `narratio.transcript.*`, `narratio.bounds.session`;
- configured artifacts: `narratio.artifact.<artifact_key>`;
- canonical previous-session artifacts: `narratio.previous_session.artifact.<artifact_key>`;
- legacy path-based previous-session source: `previous_session_artifact` (uses `inputs.*.path`).
Outputs: Outputs:
- one promoted output file per executed configured artifact at that artifact's configured `output_path` - promoted configured artifact files at each configured `output_path`;
- stage metadata containing generated artifact entries and reused disabled-artifact entries - stage metadata (`generated_artifacts`, `reused_artifacts`, selected/order info).
## Boundaries ## Boundaries
Owns: Owns:
- runtime artifact catalog construction for analyze execution - runtime artifact catalog construction;
- selected-artifact planning and dependency ordering - selected-artifact planning and dependency ordering;
- per-artifact input resolution, var resolution, timeout/render-debug resolution - per-input resolution and required/optional handling;
- Scriptorium run/render invocation for each selected artifact - Scriptorium render/run invocation;
- run-local output generation and canonical promotion - run-local output generation and canonical promotion.
Does not own: Does not own:
- transcript generation/processing stages - prepare-time previous-session hydration;
- archive promotion policy - object-store access for previous-session sources;
- per-artifact resume semantics - archive promotion policy.
## Config Fields Used ## Config fields used
- `session.session_id` - `session.session_id`
- `session.campaign` - `session.campaign`
- `pipeline.workspace.root` - `pipeline.workspace.root`
@@ -36,49 +41,41 @@ Does not own:
- `pipeline.scriptorium.timeout` - `pipeline.scriptorium.timeout`
- `pipeline.scriptorium.render_debug` - `pipeline.scriptorium.render_debug`
- `pipeline.scriptorium.artifacts.<name>.*` - `pipeline.scriptorium.artifacts.<name>.*`
- `enabled`
- `depends_on`
- `prompt_id`
- `profile_id`
- `timeout`
- `output_path`
- `render_debug`
- `inputs`
- `vars`
## External Adapters Used ## External adapters used
- Scriptorium adapter: - Scriptorium adapter:
- optional `RenderArtifact` (render debug) - optional `RenderArtifact` when render-debug is enabled;
- `RunArtifact` (artifact generation) - `RunArtifact` for artifact generation.
## State and Manifest Behavior ## State and manifest behavior
- If `pipeline.scriptorium` is absent, stage returns success metadata with `skipped=true`. - If Scriptorium config is absent, or no artifacts are executable after filtering, analyze returns success metadata with `skipped=true`.
- If no artifacts are configured, stage returns success metadata with `skipped=true`. - Builds runtime catalog with built-ins and configured `narratio.artifact.<name>` entries.
- If zero artifacts are executable after `enabled` + `--artifacts` filtering, stage returns success metadata with `skipped=true`. - Non-executable configured artifacts may still be marked available from existing canonical output files.
- Builds runtime catalog with built-ins and configured artifacts. - Resolves canonical previous-session sources from local prepared `previous/` cache:
- Non-executable configured artifacts are marked available only when their configured output file exists and is valid on disk. - prefers manifest-backed previous input paths when present;
- Executes selected configured artifacts in topological order with deterministic tie-breaking. - may fall back to current-session `previous/` filesystem paths.
- For each generated artifact, records metadata fields including `name`, `source_id`, `output_kind`, `path`, `prompt_id`, `profile_id`, and `provenance`. - Analyze does not call object storage for canonical previous-session source resolution.
- Reused disabled artifacts are recorded separately in `reused_artifacts` with provenance `filesystem.disabled_artifact_output`. - Required canonical previous-session input missing:
- fails with guidance to run `narratio run-stage --force prepare`.
- Optional missing sources are omitted from adapter input paths.
## Skip and Resume Behavior ## Skip and resume behavior
- Runner-level skip applies when analyze is already `succeeded` and `--force` is not set. - 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. - Analyze is stage-scoped for resume; no per-artifact manifest resume state.
- `--artifacts` filters which configured artifacts are executable when analyze runs; it does not imply `--force`. - `--artifacts` filters executable artifacts but does not imply force rerun.
## Failure Behavior ## 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. - Fails on dependency-order violations, missing required inputs, resolver validation failures, adapter errors, and missing/empty generated outputs.
- Required configured dependency missing from catalog availability fails clearly before invocation. - Required unavailable configured artifact source (`narratio.artifact.<name>`) fails before invocation.
- Optional missing inputs are omitted. - Required canonical previous-session source fails with prepare-rerun guidance.
## Tests to Inspect Before Changing ## Tests to inspect before changing
- `internal/stage/analyze_test.go` - `internal/stage/analyze_test.go`
- `internal/artifacts/catalog_test.go` - `internal/artifacts/catalog_test.go`
- `internal/artifacts/artifact_resolver_test.go` - `internal/artifacts/artifact_resolver_test.go`
- `internal/adapters/scriptorium/subprocess_test.go` - `internal/app/restore_workflow_test.go`
## Architectural Invariants ## Architectural invariants
- Configured artifacts are identified by `narratio.artifact.<name>` source IDs. - Canonical previous-session behavior is local-cache only during analyze.
- Artifact-to-artifact references rely on explicit `depends_on` declarations validated in config. - Generated outputs are validated and promoted before stage success is recorded.
- Generated analyze outputs are treated uniformly as Scriptorium artifacts. - Resolver/catalog decisions stay deterministic and validation-gated.
- Successful outputs must exist and be non-empty before promotion.

View File

@@ -1,17 +1,19 @@
# Stage: archive # Stage: archive
## Purpose ## Purpose
Publish run records and promoted session artifacts to object storage, then atomically advance the remote current pointer. Publish durable run/session state to object storage, then atomically advance remote current state.
## Inputs and Outputs ## Inputs and Outputs
Inputs: Inputs:
- session manifest and prerequisite stage records - session manifest and prerequisite stage records
- run root contents under `runs/{run_id}/` - run root contents under `runs/{run_id}/`
- promotion rules with artifact `source` IDs and archive `dest` paths (`archive.promote_artifacts`) - promotion rules with artifact `source` IDs and archive `dest` paths (`archive.promote_artifacts`)
- session-level `previous/**` cache files when present
Outputs: Outputs:
- uploaded run files under `{session_prefix}/runs/{run_id}/...` - uploaded run files under `{session_prefix}/runs/{run_id}/...`
- uploaded promoted artifacts under `{session_prefix}/...` - uploaded promoted artifacts under `{session_prefix}/...`
- uploaded session previous-cache files under `{session_prefix}/previous/...` when present
- `{session_prefix}/current/manifest.json` - `{session_prefix}/current/manifest.json`
- `{session_prefix}/current/run_id.txt` written last - `{session_prefix}/current/run_id.txt` written last
@@ -21,6 +23,7 @@ Owns:
- Prerequisite stage success enforcement - Prerequisite stage success enforcement
- Run file collection and upload (excluding `audio/`) - Run file collection and upload (excluding `audio/`)
- Promotion rule resolution and upload - Promotion rule resolution and upload
- Session previous-cache file collection/upload
- Commit pointer publish order - Commit pointer publish order
Does not own: Does not own:
@@ -43,8 +46,10 @@ Does not own:
## State and Manifest Behavior ## State and Manifest Behavior
- Requires `prepare`, `transcribe`, `merge`, `polish`, `normalize`, `trim`, and `analyze` status `succeeded`. - Requires `prepare`, `transcribe`, `merge`, `polish`, `normalize`, `trim`, and `analyze` status `succeeded`.
- Resolves bucket/prefix from manifest identity first, then config fallback. - Resolves bucket/prefix from manifest identity first, then config fallback.
- Uploads session `previous/**` files as durable session state when the local `previous/` directory exists.
- Writes metadata including: - Writes metadata including:
- upload counts/paths - upload counts/paths
- `previous_files_uploaded` and `previous_uploaded_paths`
- `current_manifest_key` - `current_manifest_key`
- `current_run_id_key` - `current_run_id_key`
- `current_pointer_written` - `current_pointer_written`
@@ -64,5 +69,6 @@ Does not own:
## Architectural Invariants ## Architectural Invariants
- Run upload excludes `audio/` subtree. - Run upload excludes `audio/` subtree.
- Session `previous/**` is archiveable durable input/provenance state, not run-local output.
- `current/manifest.json` uploads before `current/run_id.txt`. - `current/manifest.json` uploads before `current/run_id.txt`.
- `current/run_id.txt` is the remote publish commit marker. - `current/run_id.txt` is the remote publish commit marker.

View File

@@ -1,40 +1,49 @@
# Stage: prepare # Stage: prepare
## Purpose ## Purpose
Materialize all required session inputs into canonical local workspace paths and record input provenance in the session manifest. Materialize canonical current-session input state and provenance before downstream stages run.
## Inputs and Outputs Prepare owns:
- local input file materialization (`inputs/**`);
- audio input materialization (`audio/**`);
- previous-session cache hydration (`previous/**`) for canonical previous-session artifact sources.
## Inputs and outputs
Inputs: Inputs:
- `session.yml` (resolved session config) - resolved config/session (`pipeline.yml`, `session.yml`);
- `pipeline.resolved.yml` (materialized from resolved pipeline config) - session-local input files (`speakers`, `autocorrect`, `glossary`);
- `speakers.yml`
- `autocorrect.yml`
- `glossary.yml`
- audio source: - audio source:
- local (`session.inputs.audio_dir` or `session.inputs.audio_files`), or - local: `session.inputs.audio_dir` or `session.inputs.audio_files`;
- S3 (`session.inputs.audio_s3.prefix`) - S3: `session.inputs.audio_s3.prefix`;
- configured enabled Scriptorium artifact inputs (for previous-session requirement scanning);
- remote previous-session current archive state when previous hydration is required.
Outputs: Outputs:
- `inputs/session.yml` - `inputs/session.yml`;
- `inputs/pipeline.resolved.yml` - `inputs/pipeline.resolved.yml`;
- `inputs/speakers.yml` - `inputs/speakers.yml`;
- `inputs/autocorrect.yml` - `inputs/autocorrect.yml`;
- `inputs/glossary.yml` - `inputs/glossary.yml`;
- `audio/*.flac` in session workdir - `audio/*.flac` in canonical session `audio/`;
- `manifest.Inputs` records with checksums and source metadata - optional `previous/manifest.json`;
- optional `previous/artifacts/**`;
- deterministic `manifest.Inputs` records with checksums and provenance metadata.
## Boundaries ## Boundaries
Owns: Owns:
- Input path resolution and validation - input path resolution and materialization;
- Local copy/materialization of configs and audio files - S3 audio list/download/copy flow;
- S3 audio download to run-scoped spool, then copy into work audio dir - previous-session artifact requirement collection from enabled configured artifacts;
- previous cache lifecycle when requirements exist (clear and rehydrate managed `previous/` state).
Does not own: Does not own:
- Transcript generation/processing - transcript or artifact generation;
- Archive publish behavior - analyze-stage source resolution;
- archive commit behavior.
## Config Fields Used ## Config fields used
- `session.session_id` - `session.session_id`
- `session.previous_session_id`
- `session.campaign` - `session.campaign`
- `session.inputs.speakers_file` - `session.inputs.speakers_file`
- `session.inputs.autocorrect_file` - `session.inputs.autocorrect_file`
@@ -46,29 +55,56 @@ Does not own:
- `pipeline.spool.root` - `pipeline.spool.root`
- `pipeline.storage.s3.bucket` - `pipeline.storage.s3.bucket`
- `pipeline.storage.s3.root_prefix` - `pipeline.storage.s3.root_prefix`
- `pipeline.scriptorium.artifacts.<name>.enabled`
- `pipeline.scriptorium.artifacts.<name>.inputs.<key>.source`
- `pipeline.scriptorium.artifacts.<name>.inputs.<key>.required`
## External Adapters Used ## External adapters used
- Object storage backend (`env.ObjectStore`) for S3 audio list/download when `audio_s3` is configured. - `storage.ObjectStore` for:
- S3 audio listing/downloads;
- previous-session current pointer/manifest/artifact object checks and downloads.
## State and Manifest Behavior ## State and manifest behavior
- Ensures workspace layout exists. - Ensures workspace layout exists.
- Writes resolved config and input files to canonical `inputs/` paths. - Materializes canonical input files and audio files.
- Records all prepared inputs into `manifest.Inputs` (sorted deterministically by kind/path). - Scans enabled configured artifact inputs for canonical sources:
- For S3 audio, records `S3Bucket`, `S3Key`, `S3Size`, `S3ETag`, and `SpoolPath` in each audio input record. - `narratio.previous_session.artifact.<artifact_key>`
- If one or more canonical previous-session requirements exist:
- clears managed `previous/` state;
- hydrates required/optional previous artifacts from the configured previous sessions committed archive current state;
- writes `previous/manifest.json` and hydrated `previous/artifacts/**`;
- records hydrated previous inputs in `manifest.Inputs` with source `previous_session_archive.current`.
- If no canonical previous-session requirements exist, prepare does not manage `previous/`.
- `manifest.Inputs` is sorted deterministically by `(kind, path)`.
## Skip and Resume Behavior ## Required and optional previous-session behavior
- Runner-level skip applies when stage already `succeeded` and `--force` is not set. - `previous_session_id` unset:
- Stage itself is deterministic/idempotent for unchanged inputs (`copyFileIfChanged`, `writeBytesIfChanged`). - if any referenced previous artifact is required: fail;
- if all referenced previous artifacts are optional: continue and omit them.
- Previous session archive current pointer or manifest missing:
- if any referenced previous artifact is required: fail;
- if all referenced previous artifacts are optional: continue and omit missing ones.
- Missing required previous artifact object: fail.
- Missing optional previous artifact object: omit.
- Downloaded previous artifacts must validate as non-empty files.
## Failure Behavior ## Skip and resume 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. - Runner-level skip remains authoritative:
- if `prepare` already succeeded and run is not forced, `prepare` does not run and no hydration/download occurs.
- If `prepare` runs (including with `--force`), it owns managed `previous/` state for canonical previous-session inputs.
## Tests to Inspect Before Changing ## Failure behavior
- Fails on missing required input files, invalid audio-source combinations, empty/duplicate audio inputs, missing object store for S3 modes, and remote access/download/validation errors.
- For required canonical previous-session inputs, analyze-time missing-input guidance is to rerun:
- `narratio run-stage --force prepare`
## Tests to inspect before changing
- `internal/stage/prepare_test.go` - `internal/stage/prepare_test.go`
- `internal/app/session_cli_test.go` - `internal/stage/prepare_previous_test.go`
- `internal/config/load_validate_test.go` - `internal/artifacts/previous_requirements_test.go`
- `internal/app/runner_test.go`
## Architectural Invariants ## Architectural invariants
- `audio_dir`/`audio_files` and `audio_s3` are mutually exclusive. - `audio_dir`/`audio_files` and `audio_s3` are mutually exclusive.
- Audio files must be `.flac`. - Storage keys are computed by callers using archive/path helpers; storage adapter receives explicit keys.
- Canonical `inputs/*` and `audio/*` paths are the durable source for downstream stages. - `prepare` is the only stage that hydrates canonical previous-session cache state.

View File

@@ -17,7 +17,8 @@ Outputs:
## Boundaries ## Boundaries
Owns: Owns:
- Session-level path layout (`inputs/`, `audio/`, `transcripts/`, `artifacts/`, `reports/`, `logs/`, `config/`, `current/`, `runs/`) - Session-level path layout (`inputs/`, `audio/`, `transcripts/`, `artifacts/`, `reports/`, `logs/`, `config/`, `current/`, `runs/`, `previous/`)
- `previous/manifest.json` and `previous/artifacts/**` are reserved for prepared previous-session state
- Run-local stage sandbox layout under `runs/{run_id}/{stage}/` - Run-local stage sandbox layout under `runs/{run_id}/{stage}/`
- Session lock acquisition/release (`.lock`) - Session lock acquisition/release (`.lock`)
@@ -65,4 +66,5 @@ None directly in this subsystem. Stages may use object storage adapters and then
- Session root is campaign-aware: `{workspace.root}/work/{campaign}/{session_id}`. - Session root is campaign-aware: `{workspace.root}/work/{campaign}/{session_id}`.
- Run roots are always nested: `runs/{run_id}` under the session root. - Run roots are always nested: `runs/{run_id}` under the session root.
- Run-local output promotion must end in canonical session paths. - Run-local output promotion must end in canonical session paths.
- `previous/**` is session-durable state and must not be treated as run-local output scratch state.
- Cleanup only targets run-scoped directories and must never delete configured root directories. - Cleanup only targets run-scoped directories and must never delete configured root directories.

View File

@@ -48,7 +48,7 @@ Restore source-of-truth:
- remote current manifest: `current/manifest.json` - remote current manifest: `current/manifest.json`
Restore default scope: Restore default scope:
- includes `manifest.json`, `transcripts/**`, `artifacts/**` - includes `manifest.json`, `transcripts/**`, `artifacts/**`, `previous/**`
- includes `audio/**` only with `--include-audio` - includes `audio/**` only with `--include-audio`
- excludes `runs/**`, `logs/**`, `reports/**`, `config/**`, `inputs/**`, and `current/**` (except remote `current/manifest.json` as source) - excludes `runs/**`, `logs/**`, `reports/**`, `config/**`, `inputs/**`, and `current/**` (except remote `current/manifest.json` as source)
@@ -67,6 +67,7 @@ Canonical session directories:
- `audio/` - `audio/`
- `transcripts/` - `transcripts/`
- `artifacts/` - `artifacts/`
- `previous/`
- `reports/` - `reports/`
- `logs/` - `logs/`
- `config/` - `config/`
@@ -99,6 +100,12 @@ Configured artifact source reuse:
- accepted on `run`, `resume`, and `run-stage analyze`. - accepted on `run`, `resume`, and `run-stage analyze`.
- filters analyze execution only; does not force stage rerun. - filters analyze execution only; does not force stage rerun.
Canonical previous-session input behavior:
- canonical sources use `narratio.previous_session.artifact.<artifact_key>`.
- these inputs are hydrated by `prepare`, not `analyze`.
- if analyze fails due to missing canonical previous cache, rerun:
- `narratio run-stage --session-id <id> --force prepare`
## Remote archive layout and publish contract ## Remote archive layout and publish contract
When archive is enabled and run upload is enabled, archive publishes under: When archive is enabled and run upload is enabled, archive publishes under:

629
docs/roadmap/previous.md Normal file
View File

@@ -0,0 +1,629 @@
# Roadmap: Previous-Session Artifacts
## Status
Completed.
This roadmap describes the implementation strategy for first-class previous-session artifact support in Narratio. It belongs under `docs/roadmap/previous.md` until the feature is implemented. After implementation, current behavior should be documented in the appropriate user-facing and internal documentation files, and this roadmap should be removed or marked complete according to the documentation policy.
## Summary
Narratio should support using artifacts from a previous session as inputs to artifacts generated for the current session.
The primary use case is session recap continuity: a current session recap should be able to consume the previous session recap. The design should support arbitrary previous-session artifacts from the start, not just `session_recap`.
The canonical source syntax should be:
```yaml
source: narratio.previous_session.artifact.<artifact_name>
```
For example:
```yaml
source: narratio.previous_session.artifact.session_recap
```
Previous-session artifacts are materialized during the `prepare` stage into a current-session top-level `previous/` directory. Downstream stages consume only the local `previous/` copies. The S3 backend is authoritative for previous-session state.
## Design Decisions
### 1. Add `previous_session_id` to `session.yml`
Add an optional top-level session key:
```yaml
session_id: "{{ session_id }}"
previous_session_id: "{{ previous_session_id }}"
campaign: sample-campaign
```
Rules:
- `previous_session_id` is optional.
- If present, it identifies the previous session within the same campaign.
- It must not equal `session_id`.
- It should use the same validation rules as `session_id`.
- It may be supplied through session templating.
- Add a CLI/template value such as `--previous-session-id <id>` if required by the existing session templating implementation.
- If a template placeholder for `previous_session_id` is present and no value is supplied, loading should fail with a clear unresolved-template error.
### 2. Use canonical previous-session artifact source IDs
Support this source pattern in Scriptorium artifact input definitions:
```text
narratio.previous_session.artifact.<artifact_name>
```
Examples:
```yaml
inputs:
previous_recap:
source: narratio.previous_session.artifact.session_recap
required: false
previous_quest_log:
source: narratio.previous_session.artifact.quest_log
required: true
```
Rules:
- `<artifact_name>` must be a valid configured artifact key.
- Use the same artifact key validation rules as current-session runtime artifacts.
- Do not special-case `session_recap`.
- Do not limit implementation to a fixed list of previous artifacts.
### 3. Add a top-level `previous/` workspace directory
Extend the session workspace layout with:
```text
previous/
manifest.json
artifacts/
<artifact outputs copied from the previous session>
```
The `previous/` directory is current-session state. It is a prepared input cache, not a full mirror of the previous session workspace.
Conceptually:
```text
work/<campaign>/<current_session_id>/
previous/
manifest.json
artifacts/
session_recap.md
quest_log.json
```
The current session should not read directly from the previous session's local workspace during ordinary operation.
### 4. S3 is authoritative for previous-session state
For this initial implementation, previous-session artifacts should be downloaded from the configured S3 backend.
Do not compare local and remote copies.
Do not prefer local previous-session workspace state.
Do not implement a `--local` override in this roadmap. That can be considered later.
The simplified stage behavior is:
1. If the local manifest indicates `prepare` already succeeded and `--force` is not supplied, the runner skips `prepare`. No previous-session download occurs.
2. If `prepare` has not succeeded, `prepare` runs and downloads referenced previous-session artifacts from S3.
3. If `prepare` previously succeeded but `--force` is supplied, `prepare` runs again and overwrites local `previous/` state from S3.
### 5. Materialize only referenced previous-session artifacts
During `prepare`, scan the current resolved pipeline/session configuration for Scriptorium artifact inputs whose source matches:
```text
narratio.previous_session.artifact.<artifact_name>
```
Only those referenced previous-session artifacts need to be downloaded.
Do not blindly download every previous-session artifact.
If no previous-session artifact sources are referenced, `prepare` should not require `previous_session_id` and should not touch `previous/`.
### 6. Preserve stage boundaries
`prepare` owns previous-session artifact materialization because these files are inputs to later stages.
`analyze` should not talk to S3.
The Scriptorium adapter should not know about previous sessions.
The storage adapter should not infer campaign, session, run, or root-prefix semantics. Callers should continue to provide explicit bucket-relative keys.
### 7. Archive and restore `previous/`
After implementation:
- `archive` should include `previous/` as durable current-session prepared input state.
- `restore` should restore `previous/` along with the rest of the durable session state it already restores.
- `previous/` should not be treated as current-session generated artifacts.
- `previous/` entries should be recorded as inputs/provenance, not as outputs produced by the current session.
## Target User Workflow
A typical session config:
```yaml
session_id: "{{ session_id }}"
previous_session_id: "{{ previous_session_id }}"
campaign: sample-campaign
inputs:
audio_dir: ./audio
speakers_file: ./examples/speakers.yml
autocorrect_file: ./examples/autocorrect.yml
glossary_file: ./examples/glossary.yml
```
A typical artifact config:
```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
previous_recap:
source: narratio.previous_session.artifact.session_recap
required: false
```
Typical command:
```bash
narratio run --session-id 2026-04-11 --previous-session-id 2026-04-04
```
Expected behavior:
1. `prepare` sees a referenced previous-session artifact: `session_recap`.
2. `prepare` downloads the previous session's `narratio.artifact.session_recap` from S3.
3. `prepare` writes it under the current session workspace, for example `previous/artifacts/session_recap.md`.
4. `prepare` records provenance in the current session manifest.
5. `analyze` resolves `narratio.previous_session.artifact.session_recap` from the local `previous/` directory.
6. Scriptorium receives the previous recap as a normal input file.
## Implementation Plan
### Phase 1: Session config and templating
Update session configuration structs to include:
```yaml
previous_session_id: ""
```
Implementation steps:
1. Add `PreviousSessionID` or equivalent to the session config type.
2. Add validation:
- optional;
- same format constraints as `session_id`;
- must not equal `session_id`.
3. Extend session templating support to include:
- `{{previous_session_id}}`
- `{{ previous_session_id }}`
4. Add a CLI flag if required by current templating flow:
- `--previous-session-id <id>`
5. Ensure unresolved `previous_session_id` placeholders fail clearly.
6. Update config tests for:
- no previous session;
- valid previous session;
- previous session equal to current session;
- unresolved placeholder;
- CLI/template rendering.
Do not add future workflow flags in this phase.
### Phase 2: Workspace path helpers
Add centralized path helpers for current-session previous-state paths.
Suggested helpers:
```text
SessionPreviousDir()
SessionPreviousManifestPath()
SessionPreviousArtifactsDir()
SessionPreviousArtifactPath(name or relative output path)
```
The exact names should match existing path-helper style.
Rules:
- Do not construct `previous/` paths through scattered string concatenation.
- Keep paths session-relative where possible.
- Ensure workspace layout creation includes `previous/` only when appropriate, or creates it idempotently with the rest of the layout if simpler.
Tests:
- path helper tests;
- workspace layout tests;
- ensure cleanup logic does not accidentally delete configured roots;
- ensure `previous/` is treated as session-durable state, not run-local state.
### Phase 3: Previous-session source parsing
Add parsing/recognition for:
```text
narratio.previous_session.artifact.<artifact_name>
```
Implementation steps:
1. Add constants/helpers in the artifact/source parsing layer.
2. Validate artifact names using the same rules as current runtime artifact keys.
3. Add helpers such as:
- `IsPreviousSessionArtifactSource(source string) bool`
- `PreviousSessionArtifactName(source string) (string, bool)`
4. Ensure config validation accepts this source pattern.
5. Ensure invalid sources fail clearly.
Tests:
- valid previous-session artifact source;
- invalid/missing artifact name;
- invalid artifact key characters;
- ordinary current-session sources still validate;
- unknown sources still fail.
### Phase 4: Scan configured artifacts for previous-session inputs
Add a helper that inspects resolved Scriptorium artifact definitions and returns the set of referenced previous-session artifact names.
Rules:
- Scan enabled artifacts according to current artifact-enable semantics.
- Include all inputs whose source matches `narratio.previous_session.artifact.<name>`.
- Deduplicate artifact names.
- Sort results deterministically.
- Preserve required/optional information per reference.
- If the same previous artifact is referenced both required and optional, treat it as required.
Suggested output model:
```go
type PreviousArtifactRequirement struct {
Name string
Required bool
Sources []string // optional diagnostics
}
```
Tests:
- no artifacts;
- no previous inputs;
- one optional previous input;
- one required previous input;
- duplicate references;
- required plus optional reference to the same artifact;
- deterministic ordering.
### Phase 5: Resolve previous-session archive keys
Implement a narrow service/helper used by `prepare` to resolve previous-session artifact files from S3.
Responsibilities:
1. Locate the previous session's current remote state.
2. Download the previous session manifest, or the minimum remote metadata needed to resolve artifact source IDs.
3. Resolve `narratio.artifact.<name>` inside the previous session's artifact catalog/manifest.
4. Download the resolved artifact into the current session's `previous/` directory.
5. Download/store the previous session manifest as `previous/manifest.json`.
6. Return provenance records for manifest input recording.
Important archive invariant:
- Remote current state must be based on the committed archive marker.
- Do not treat incomplete archive uploads as current state.
- Use the existing archive/current remote layout and commit-marker rules.
- `current/run_id.txt` is the final remote commit marker and should be respected when locating current remote state.
Do not put prefix semantics into the storage adapter. Compute explicit bucket-relative keys in app/stage/archive helper code, then call the storage adapter.
Required vs optional behavior:
- Required previous artifact missing from S3/current manifest: fail `prepare`.
- Optional previous artifact missing from S3/current manifest: continue without materializing that input.
- Previous session missing entirely:
- fail if any referenced previous artifact is required;
- continue if all referenced previous artifacts are optional.
- If previous_session_id is unset:
- fail if any referenced previous artifact is required;
- continue and omit all previous-session inputs if all are optional.
Validation behavior:
- Downloaded artifacts should pass the same validation rules as current-session artifacts where practical.
- Generic Scriptorium artifacts should at least be non-empty.
- Invalid required artifact: fail.
- Invalid optional artifact: prefer fail if the object exists but is invalid, because invalid archived data is usually an operator problem rather than absence.
Tests:
- downloads previous manifest;
- downloads required previous artifact;
- skips missing optional previous artifact;
- fails missing required previous artifact;
- fails required previous artifact when previous_session_id is unset;
- optional previous artifact with no previous_session_id does not fail;
- respects current remote commit marker;
- does not use local previous-session workspace state;
- uses storage adapter with explicit keys.
### Phase 6: Integrate with `prepare`
Extend the `prepare` stage:
1. Run existing input materialization as before.
2. Detect previous-session artifact requirements.
3. If requirements exist, hydrate `previous/` from S3 according to the rules above.
4. Record hydrated previous artifacts in `manifest.Inputs`.
5. Preserve existing prepare outputs and provenance behavior.
Overwrite behavior:
- If `prepare` runs, it owns `previous/`.
- Before hydrating, clear the managed `previous/` directory, or clear the managed previous artifact paths.
- Prefer clearing the whole `previous/` directory if no other feature writes there.
- Under `--force`, this naturally overwrites local `previous/` state.
- Do not compare local and remote copies.
Skip behavior:
- Do not add stage-local skip logic.
- Runner-level skip remains authoritative.
- If the manifest says `prepare` succeeded and `--force` is not supplied, `prepare` does not run and no S3 downloads occur.
- If users add a new previous-session input after `prepare` already succeeded, they must rerun prepare with `--force`.
Error message requirement:
If an analyze-stage input cannot be resolved because `previous/` is missing or stale, the error should tell the operator to run:
```bash
narratio run-stage --force prepare
```
or the appropriate existing CLI command shape.
Tests:
- ordinary prepare without previous_session_id remains unchanged;
- prepare with optional previous artifact and no previous_session_id succeeds;
- prepare with required previous artifact and no previous_session_id fails;
- prepare with required previous artifact downloads to `previous/`;
- force prepare overwrites `previous/`;
- prepare records manifest inputs for previous artifacts;
- prepare skip behavior remains controlled by runner tests;
- no regression in S3 audio prepare behavior.
### Phase 7: Artifact resolver support
Update artifact resolution so Scriptorium inputs can resolve:
```text
narratio.previous_session.artifact.<artifact_name>
```
from the current session's `previous/` directory.
Rules:
- The resolver should not call S3.
- The resolver should not read the previous session's local workspace.
- The resolver should map the previous-session source ID to the local prepared copy under `previous/`.
- Resolution should use manifest input records when available.
- Fallback to the local `previous/` path may be allowed if consistent with existing resolver behavior, but manifest provenance should be preferred.
- Missing required input should fail with a clear prepare-oriented message.
- Optional missing input should be omitted.
Suggested provenance:
```text
previous_session.manifest.outputs
previous_session.archive.current
current_session.previous_cache
```
Use names that fit the existing manifest/resolver vocabulary.
Tests:
- resolves prepared previous artifact through manifest input record;
- resolves or fails appropriately when only filesystem copy exists, depending on chosen fallback policy;
- missing optional previous artifact is omitted;
- missing required previous artifact fails clearly;
- current-session `narratio.artifact.<name>` behavior is unchanged.
### Phase 8: Analyze-stage integration
The analyze stage should require little or no special previous-session logic if the resolver is designed correctly.
Confirm:
- Scriptorium input resolution accepts previous-session source IDs.
- The Scriptorium adapter receives a normal local input path.
- Render-debug and run modes behave the same as for ordinary inputs.
- Stage metadata includes useful input provenance if current structures support it.
Tests:
- configured artifact receives previous recap input;
- optional previous recap omitted when not prepared;
- required previous recap fails when not prepared;
- render-debug path works with previous-session inputs;
- no S3 calls occur from analyze.
### Phase 9: Archive `previous/`
Update archive behavior so the current session's durable `previous/` directory is uploaded/preserved.
Rules:
- `previous/` is current-session input/provenance state.
- It is not a generated current-session artifact.
- Archive it with the current session's durable state, alongside other durable session files according to the current archive layout.
- Preserve existing archive commit ordering.
- Do not make `previous/` upload the final commit marker.
- Do not treat missing `previous/` as an error when no previous-session inputs were prepared.
Tests:
- archive includes `previous/manifest.json` and prepared previous artifacts when present;
- archive omits or tolerates absent `previous/` when unused;
- archive commit ordering remains valid;
- cleanup behavior does not delete durable `previous/` before archive commit.
### Phase 10: Restore `previous/`
Update `narratio restore` so it restores the current session's archived `previous/` directory.
Rules:
- Restore `previous/` as durable current-session state.
- Do not infer or restore the previous session workspace merely because `previous_session_id` exists.
- Do not redownload previous-session artifacts from the previous session archive during restore; restore the current session's archived `previous/` cache.
- Respect existing restore flags and overwrite behavior.
Tests:
- restore downloads `previous/` when present;
- restore succeeds when `previous/` is absent;
- restore with force overwrites local `previous/` according to existing restore semantics;
- restored current session can run analyze using `previous/` without needing previous session archive access.
### Phase 11: Documentation updates after implementation
After implementation, update current-behavior docs. Do not document implemented behavior only in this roadmap.
Likely files:
- `docs/config.md`
- `docs/cli.md`
- `docs/operations.md`
- `docs/internal/stage-prepare.md`
- `docs/internal/artifacts.md`
- `docs/internal/storage.md` only if storage contracts change
- `docs/internal/workspace.md`
- relevant maintained examples under `examples/`
Docs should explain:
- `session.previous_session_id`;
- `--previous-session-id` if added;
- `narratio.previous_session.artifact.<artifact_name>`;
- `previous/` workspace directory;
- S3-authoritative previous-session behavior;
- required vs optional previous-session artifact handling;
- when to run `narratio run-stage --force prepare`.
Do not document future `--local` support as current behavior.
## Future Work
These items are explicitly out of scope for the initial implementation.
### `--local` previous-session source
A future flag may allow `prepare` to copy previous-session artifacts from a local previous session workspace instead of S3.
Possible future command shape:
```bash
narratio run-stage --force prepare --local
```
or a more specific flag such as:
```bash
narratio run-stage --force prepare --previous-source local
```
Do not implement this now.
### `narratio run --restore`
A future flag may run `narratio restore` before starting the regular pipeline:
```bash
narratio run --restore --session-id 2026-04-11
```
Do not implement this as part of previous-session artifact support unless it already exists and only requires documentation.
### Multi-previous-session support
A future design may support more than one previous/reference session.
Do not implement this now.
### Previous-session artifact version pinning
A future design may pin previous-session artifact inputs to a specific previous run ID or checksum.
Do not implement this now.
## Test Plan Summary
Run at least:
```bash
go test ./internal/config -v
go test ./internal/artifacts -v
go test ./internal/stage -run Prepare -v
go test ./internal/stage -run Analyze -v
go test ./internal/app -run TestExecute -v
go test ./...
```
Add focused tests for:
- session config and templating;
- previous-session source parsing;
- previous artifact requirement scanning;
- S3-backed previous artifact download;
- prepare skip/force semantics;
- manifest input provenance;
- resolver behavior;
- analyze integration;
- archive/restore `previous/` persistence;
- examples load/validate.
## Acceptance Criteria
The feature is complete when:
1. `session.yml` supports optional `previous_session_id`.
2. Session templating supports `previous_session_id`.
3. Scriptorium artifact inputs accept `narratio.previous_session.artifact.<artifact_name>`.
4. `prepare` scans enabled Scriptorium artifacts for previous-session artifact inputs.
5. `prepare` downloads referenced previous-session artifacts from S3 into `previous/`.
6. Required/optional behavior is correct.
7. `prepare` uses stage-level skip/force behavior and does not compare local and remote copies.
8. `analyze` resolves previous-session artifacts only from local prepared `previous/` state.
9. `archive` persists `previous/`.
10. `restore` restores `previous/`.
11. Tests cover config, prepare, resolver, analyze, archive, and restore behavior.
12. Current-behavior docs and maintained examples are updated after implementation.
13. No storage adapter implementation infers campaign/session/root-prefix semantics.
14. No previous-session S3 logic is added to `analyze` or the Scriptorium adapter.

View File

@@ -1,715 +0,0 @@
# Roadmap: `narratio restore` Subcommand
## Status
Implemented through Step 8. This document remains as roadmap and design history for the restore feature, and as the home for future restore-related ideas (for example `run --restore`).
## Summary
Add a new `narratio restore` subcommand that hydrates a local session workspace from the current committed remote archive state.
The primary operator workflow is:
```bash
narratio restore --session-id 2026-04-04
narratio run-stage --force analyze
```
This should allow a new machine with no local workspace state to restore the durable session manifest, transcripts, and generated artifacts from S3, then generate new Scriptorium artifacts without re-running transcription, merge, normalize, polish, or trim.
This is intentionally a separate command. Do not fold this behavior into the `prepare` stage. The existing `prepare` stage should remain focused on materializing configured local/S3 inputs for a pipeline run.
## Goals
- Add a first-class `narratio restore` command.
- Restore the current committed remote session state into the canonical local session workspace.
- Use the existing object storage adapter boundary.
- Preserve archive commit semantics: only restore from a remote state that has a valid current commit marker.
- Restore durable session-level outputs needed for downstream stages, especially `analyze`.
- Provide safe conflict behavior by default.
- Support `--dry-run`, `--force`, and `--include-audio`.
- Keep the implementation explicit, testable, and narrow.
## Non-goals
- Do not make `restore` a pipeline stage.
- Do not change the `prepare` stage behavior as part of this work.
- Do not add implicit restore behavior to `narratio run` in this implementation.
- Do not restore historical run-local sandboxes by default.
- Do not implement a generic remote synchronization engine.
- Do not implement bidirectional sync.
- Do not delete local files merely because they are absent remotely.
- Do not merge remote and local manifests in the first implementation.
- Do not require live S3 for the ordinary unit test suite.
## Future work explicitly out of scope
A future change may add:
```bash
narratio run --restore
```
That future flag should run `narratio restore` before starting the normal pipeline. Mention this as future work in roadmap/docs if useful, but do not implement it now.
## Existing architecture to preserve
### `prepare` remains input materialization
The `prepare` stage currently materializes required session inputs into canonical local workspace paths and records input provenance. It owns local copying/materialization of config and audio inputs, including S3 audio download when `session.inputs.audio_s3.prefix` is configured. It does not own transcript generation/processing or archive publish behavior.
`restore` should not be implemented by expanding `prepare`. It should be an app-level command that reuses shared helpers where appropriate.
### Workspace model
The local durable session workspace is campaign-aware:
```text
{workspace.root}/work/{campaign}/{session_id}/
```
It contains durable session paths such as:
```text
manifest.json
inputs/
audio/
transcripts/
artifacts/
reports/
logs/
config/
current/
runs/
```
Run-local sandboxes live below:
```text
runs/{run_id}/
```
Restore should target durable session-level paths, not old run-local stage sandboxes.
### Storage boundary
The storage adapter owns object-store primitives only: `List`, `Download`, `Upload`, and `Exists`.
The storage adapter must not infer root prefixes, campaign names, session IDs, run IDs, or archive layout. Restore code must construct full bucket-relative keys before calling storage.
### Archive commit boundary
A remote run is current only after the archive stage has uploaded the run record, 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.
Restore must not treat incomplete, skipped, failed, or uncommitted archive attempts as current remote state.
## User-facing command
Add:
```bash
narratio restore [flags]
```
The command should use the same configuration/session discovery conventions as `run`, `plan`, `resume`, and `run-stage` where practical:
```bash
narratio restore --config /path/to/pipeline.yml --session ./session.yml --session-id 2026-04-04
```
Required effective inputs:
- resolved pipeline config;
- resolved session config;
- `session.campaign`;
- `session.session_id`;
- configured remote storage backend.
Supported flags:
```text
--config <path> Existing pipeline config path behavior.
--session <path> Existing session config path behavior.
--session-id <value> Existing session template behavior.
--dry-run Plan restore actions without writing local files.
--force Overwrite conflicting local files with remote files.
--include-audio Include archived session-level audio files.
```
Do not add `--restore` to `run` in this implementation.
## Default restore scope
By default, restore:
1. Validates and reads the current remote commit marker.
2. Downloads the current remote manifest into the local session manifest path.
3. Downloads durable transcript files.
4. Downloads durable generated artifact files.
Default included remote/local durable paths:
```text
manifest.json from remote current manifest
transcripts/**
artifacts/**
```
Default excluded paths:
```text
audio/** unless --include-audio is passed
runs/** always excluded for this implementation
logs/** excluded for this implementation
reports/** excluded for this implementation unless needed for current manifest validation
config/** excluded for this implementation
inputs/** excluded for this implementation
current/** remote control metadata only; do not mirror blindly
```
If the existing archive implementation stores promoted files in a different remote layout, use the existing archive/path helpers and current archive semantics rather than inventing a parallel layout.
## Remote state discovery
Implement restore around the current committed archive state.
Expected algorithm:
1. Resolve pipeline/session config.
2. Ensure storage is configured.
3. Ensure local workspace layout exists.
4. Acquire the session lock.
5. Build the remote session archive prefix using the same helpers/policy used by archive code.
6. Check for the remote `current/run_id.txt` commit marker.
7. Read the committed run ID.
8. Download `current/manifest.json` to a temporary file.
9. Validate that the manifest is parseable and belongs to the requested campaign/session.
10. Build a restore plan from the committed remote state.
11. Execute the restore plan unless `--dry-run` is set.
12. Emit a concise summary.
Important: `current/run_id.txt` is the commit marker. Do not restore from a remote session prefix merely because files exist under `transcripts/` or `artifacts/`.
## Restore planning
Create a planning layer before writing files.
A restore plan entry should include at least:
```go
type RestoreAction struct {
Kind RestoreActionKind
RemoteKey string
LocalPath string
Size int64
ETag string
ExistsLocal bool
SameLocal bool
Conflict bool
Reason string
}
```
Suggested action kinds:
```text
download
skip_same
skip_missing_optional
conflict
```
The restore planner should be deterministic:
- sort remote objects by key;
- sort planned actions by local path or stable restore priority;
- write/report stable output for tests.
## Conflict and overwrite policy
Default behavior should be safe.
For each planned file:
```text
local absent:
download
local present and same as remote:
skip
local present and different:
conflict; fail restore unless --force is set
--force:
overwrite local conflicting files with remote versions
--dry-run:
do not write any files; report what would happen
```
The first implementation may use size and checksum/hash comparison where available. If remote ETag cannot be treated as a content hash, compare by downloading to a temporary file and hashing locally before deciding whether a local file is the same. Prefer correctness over assuming provider-specific ETag semantics.
Do not delete local files that are not present remotely.
## File writing and transactionality
Restore should avoid partial writes.
Implementation requirements:
- download each remote object to a temporary file under the session workspace or OS temp dir;
- validate downloaded content where possible before replacing local files;
- create parent directories as needed;
- atomically rename/copy into place only after successful download;
- do not overwrite local files unless `--force` is set;
- if a later file fails, preserve already-restored files but return a failure summary;
- never corrupt an existing local manifest on failed manifest download/parse.
Manifest restore is especially sensitive:
- download remote `current/manifest.json` to a temporary file;
- parse and validate it;
- if no local manifest exists, install it;
- if a local manifest exists and is equivalent, skip;
- if a local manifest exists and differs, fail unless `--force` is set;
- with `--force`, replace the local manifest with the remote manifest after validation;
- do not attempt a manifest merge in the initial implementation.
## Manifest semantics
`restore` is not a pipeline run and should not mark stages as running/succeeded/failed.
The restored remote manifest becomes the local session manifest. That is what allows a subsequent command such as:
```bash
narratio run-stage --force analyze
```
to see existing upstream stage state and canonical durable outputs.
Do not create a new run manifest for `restore`.
It is acceptable to write a restore diagnostic report outside the manifest, for example:
```text
reports/restore-latest.json
```
or a timestamped report, if that pattern fits the existing codebase. The report must not contain secrets.
## Local workspace locking
`restore` should acquire the same session lock used by ordinary pipeline operations before modifying session workspace state.
If the lock is held, fail fast with the same lock-conflict behavior used elsewhere.
`--dry-run` may still acquire the lock for consistency, but it is acceptable to avoid the lock if the codebase already has a clear read-only command pattern. Prefer safety and simplicity.
## Audio behavior
By default, do not restore audio.
If `--include-audio` is passed:
- restore archived durable session-level audio files only;
- do not use run-scoped spool paths;
- do not mutate or delete spool state;
- do not infer original `session.inputs.audio_s3.prefix` behavior;
- respect the same conflict/force/dry-run behavior used for transcripts/artifacts.
If the archive does not contain durable audio files, `--include-audio` should report that no archived audio was found rather than failing, unless the final implementation chooses to treat explicit audio restore as required. Prefer non-failure for absent archived audio unless tests or existing archive semantics suggest otherwise.
## Remote object selection
Prefer using manifest/artifact metadata when it reliably identifies durable outputs.
Also support listing committed durable archive prefixes so restore can retrieve all top-level session artifacts that may not yet be fully represented in manifest metadata.
The implementation should inspect existing archive code before choosing the final object-selection method. Do not duplicate archive path construction.
Recommended selection priority:
1. Remote current manifest path.
2. Durable promoted transcript/artifact outputs recorded in the manifest or archive metadata, if available.
3. Objects under committed durable `transcripts/` and `artifacts/` archive prefixes.
4. Objects under durable `audio/` only when `--include-audio` is passed.
Always exclude:
```text
runs/**
```
for the first implementation.
## Package and file organization
Expected areas to inspect and update:
```text
cmd/narratio/
internal/app/
internal/adapters/storage/
internal/artifacts/
internal/manifest/
docs/
examples/
```
Suggested implementation shape:
```text
internal/app/restore.go
internal/app/restore_test.go
internal/archive/restore/
planner.go
executor.go
report.go
keys.go
*_test.go
```
The exact package name may vary. Use whatever best fits the existing repository, but keep these boundaries clear:
- `internal/app` owns CLI command handling, config/session loading, lock acquisition, and wiring.
- Restore planning/execution owns remote key discovery, conflict detection, downloads, and reporting.
- `internal/adapters/storage` remains a transport boundary only.
- Workspace/path helpers remain centralized; do not scatter string concatenation.
If the repository already has an `internal/archive` or archive-stage helper package, prefer extending that rather than creating a conflicting package layout.
## CLI output
`narratio restore` should print a concise operator summary.
Example successful output:
```text
Restored session archive for sample-campaign/2026-04-04
Remote run: 20260504T031500Z-a1b2c3
Downloaded: 4
Skipped unchanged: 2
Conflicts: 0
```
Example dry run:
```text
Restore plan for sample-campaign/2026-04-04
Remote run: 20260504T031500Z-a1b2c3
Would download: transcripts/processed.json
Would download: transcripts/trimmed.json
Would skip unchanged: artifacts/session_recap.md
```
Example conflict:
```text
restore conflict: local artifacts/session_recap.md differs from remote archive; rerun with --force to overwrite
```
Do not print transcript or artifact content.
## Error behavior
Fail clearly when:
- storage backend is not configured;
- S3 bucket/config is missing or invalid;
- remote current commit marker is missing;
- remote current manifest is missing;
- remote manifest is invalid;
- remote manifest does not match requested campaign/session;
- local file differs from remote and `--force` is not set;
- a required remote object download fails;
- a local path would escape the session workspace;
- a remote key maps to an unsafe local path.
Skip or report non-fatal conditions when:
- optional audio restore finds no archived audio;
- an included prefix has no objects;
- a local file already matches the remote file.
## Path safety
Every restored file must map to a safe path under the session root.
Validation rules:
- local restore paths must be relative to the session root;
- reject absolute paths;
- reject `..` traversal;
- reject paths that escape through symlinks if the codebase has symlink-safe path checks;
- do not restore remote keys directly without mapping/classification;
- do not mirror arbitrary remote keys.
## Testing plan
Add focused unit tests. Do not require live S3.
### CLI tests
Add or update `internal/app` command tests for:
- `narratio restore --help`;
- restore accepts `--config`, `--session`, and `--session-id`;
- restore accepts `--dry-run`;
- restore accepts `--force`;
- restore accepts `--include-audio`;
- restore fails when storage is not configured;
- restore does not run pipeline stages.
### Restore planner tests
Test:
- missing `current/run_id.txt` fails;
- missing `current/manifest.json` fails;
- invalid manifest fails;
- wrong campaign/session manifest fails;
- default scope includes manifest/transcripts/artifacts;
- default scope excludes audio/logs/reports/config/runs;
- `--include-audio` includes durable audio;
- run-local keys are excluded;
- keys are sorted deterministically;
- unsafe remote-to-local paths are rejected.
### Conflict policy tests
Test:
- absent local file downloads;
- matching local file skips;
- differing local file conflicts by default;
- `--force` overwrites conflicts;
- `--dry-run` writes nothing;
- partial failure does not corrupt an existing local manifest.
### Storage/fake tests
Use fake storage to simulate:
- object listing;
- object download;
- missing objects;
- download failures;
- metadata/ETag behavior.
### Workspace/lock tests
Test:
- session layout is created before restore;
- session lock conflict fails;
- restored files land under the expected campaign/session workspace;
- no files are written outside the session root.
### Follow-up command workflow test
Add at least one test that simulates:
```bash
narratio restore --session-id 2026-04-04
narratio run-stage --force analyze
```
The test does not need to run real Scriptorium. Use existing fake/stub behavior to verify that restored transcripts and manifest state are sufficient for analyze-stage input resolution.
## Documentation updates when implemented
When the feature is implemented, update current-behavior docs:
```text
docs/cli.md
docs/operations.md
docs/internal/storage.md or docs/internal/archive/restore.md
```
If the documentation set does not yet have an internal restore document, add one consistent with the existing internal-doc style:
```text
docs/internal/command-restore.md
```
or:
```text
docs/internal/archive-restore.md
```
Do not document future `narratio run --restore` behavior outside `docs/roadmap/` until implemented.
## Implementation phases
### Phase 1: Audit existing archive and path helpers (completed)
Before coding behavior, inspect:
```text
internal/app/
internal/stage/archive*
internal/adapters/storage/
internal/artifacts/
internal/manifest/
docs/internal/stage-archive.md, if present
```
Determine:
- exact remote archive key layout;
- how root prefix/campaign/session are modeled;
- how current commit marker keys are built;
- how current manifest is uploaded;
- where promoted outputs are uploaded;
- whether helper functions already exist for remote archive keys;
- whether local workspace path helpers can safely map restore destinations.
Deliverable:
- small code comments or internal helper selection;
- no large behavior change yet unless required by tests.
### Phase 2: Add CLI surface and command wiring (completed)
Add `narratio restore` command parsing.
Wire flags:
```text
--config
--session
--session-id
--dry-run
--force
--include-audio
```
Use the existing config/session load path where practical.
Deliverable:
- command exists;
- help output is sensible;
- command validates basic inputs;
- command returns a clear “not yet implemented” or calls an empty planner if phased commits are desired;
- CLI tests pass.
### Phase 3: Implement remote current-state discovery (completed)
Add restore code that:
- creates an object store from resolved config;
- builds remote current marker key;
- reads `current/run_id.txt`;
- reads/downloads `current/manifest.json`;
- validates manifest identity;
- returns remote current-state metadata.
Deliverable:
- fake-storage tests for current-state discovery;
- no local file writes beyond temporary files.
### Phase 4: Implement restore planning (completed)
Build deterministic restore plans for default scope and `--include-audio`.
Deliverable:
- plan lists manifest, transcript, artifact files;
- plan excludes run-local data;
- plan detects local same/conflict/missing states;
- dry-run output works;
- no real file overwrite yet except temp comparisons as needed.
### Phase 5: Implement restore execution (completed)
Execute the plan safely:
- create directories;
- download to temporary files;
- validate content where practical;
- atomically install files;
- enforce default conflict failure;
- support `--force`;
- preserve existing manifest unless safe to replace.
Deliverable:
- restore works end-to-end against fake storage;
- failures are clear and do not corrupt existing local manifest.
### Phase 6: Add restore report and operator summary (completed)
Add concise stdout summary and optional JSON restore report if consistent with project diagnostics.
Deliverable:
- user-friendly output;
- durable diagnostic report if implemented;
- no content leakage.
### Phase 7: Workflow integration test (completed)
Add a test for restoring a previous session and then forcing `analyze`.
Deliverable:
- restored manifest/transcripts/artifacts are sufficient for analyze input resolution;
- no upstream stages rerun;
- no reliance on live subprocesses or S3.
### Phase 8: Documentation update (completed)
Once implemented, update current-behavior docs and internal command docs.
Also leave future `narratio run --restore` in roadmap only.
## Definition of done
The feature is complete when:
- `narratio restore` exists and is documented.
- It uses the same config/session discovery semantics as other commands where practical.
- It requires configured remote storage.
- It restores only from a committed current archive state.
- It restores the current manifest, transcripts, and artifacts by default.
- It restores audio only with `--include-audio`.
- It excludes run-local sandboxes.
- It fails on local/remote conflicts by default.
- `--force` overwrites conflicts.
- `--dry-run` writes nothing.
- It uses fake storage in tests.
- It does not change `prepare` behavior.
- It does not implement `narratio run --restore`.
- It avoids AWS SDK leakage outside the storage adapter.
- It uses centralized path/key helpers rather than scattered string concatenation.
- `go test ./...` passes.
## Suggested test commands
Run focused tests first:
```bash
go test ./internal/app -run TestExecute -v
go test ./internal/adapters/storage -v
go test ./internal/artifacts -v
go test ./internal/manifest -v
```
Then run the full suite:
```bash
go test ./...
```
## Suggested commit message
```text
Add restore subcommand roadmap
```

View File

@@ -133,9 +133,7 @@ scriptorium:
source: narratio.transcript.trimmed source: narratio.transcript.trimmed
required: true required: true
previous_recap: previous_recap:
source: previous_session_artifact source: narratio.previous_session.artifact.session_recap
artifact: session_recap
path: ""
required: false required: false
vars: vars:
session_id: true session_id: true

View File

@@ -81,8 +81,7 @@ scriptorium:
source: narratio.transcript.trimmed source: narratio.transcript.trimmed
required: true required: true
previous_recap: previous_recap:
source: previous_session_artifact source: narratio.previous_session.artifact.session_recap
artifact: session_recap
required: false required: false
vars: vars:
session_id: true session_id: true

View File

@@ -22,10 +22,12 @@ func Plan(ctx context.Context, args []string, out io.Writer) error {
var pipelinePath string var pipelinePath string
var sessionPath string var sessionPath string
var sessionID string var sessionID string
var previousSessionID string
var force bool var force bool
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)") fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
fs.StringVar(&sessionPath, "session", "", "path to session.yml") fs.StringVar(&sessionPath, "session", "", "path to session.yml")
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates") fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
fs.StringVar(&previousSessionID, "previous-session-id", "", "previous session identifier for session.yml templates")
fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)") fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
if err := fs.Parse(args); err != nil { if err := fs.Parse(args); err != nil {
@@ -44,7 +46,8 @@ func Plan(ctx context.Context, args []string, out io.Writer) error {
} }
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{ cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
SessionID: sessionID, SessionID: sessionID,
PreviousSessionID: previousSessionID,
}) })
if err != nil { if err != nil {
return fmt.Errorf("plan: %w", err) return fmt.Errorf("plan: %w", err)

View File

@@ -82,6 +82,7 @@ func TestPostArchiveCleanupWorkdirOnly(t *testing.T) {
assertExists(t, cfg.Pipeline.Workspace.Root) assertExists(t, cfg.Pipeline.Workspace.Root)
assertExists(t, seed.otherRunDir) assertExists(t, seed.otherRunDir)
assertExists(t, seed.previousCachePath)
assertMissing(t, seed.runWorkDir) assertMissing(t, seed.runWorkDir)
assertExists(t, seed.spoolAudioDir) assertExists(t, seed.spoolAudioDir)
} }
@@ -98,6 +99,7 @@ func TestPostArchiveCleanupBothPolicies(t *testing.T) {
assertMissing(t, seed.spoolAudioDir) assertMissing(t, seed.spoolAudioDir)
assertMissing(t, seed.runWorkDir) assertMissing(t, seed.runWorkDir)
assertExists(t, seed.otherRunDir) assertExists(t, seed.otherRunDir)
assertExists(t, seed.previousCachePath)
} }
func TestPostArchiveCleanupNotRunWhenArchiveFails(t *testing.T) { func TestPostArchiveCleanupNotRunWhenArchiveFails(t *testing.T) {
@@ -256,11 +258,12 @@ func TestPostArchiveCleanupNotRunWhenCurrentPointerUploadFails(t *testing.T) {
} }
type cleanupSeed struct { type cleanupSeed struct {
runWorkDir string runWorkDir string
otherRunDir string otherRunDir string
spoolAudioDir string spoolAudioDir string
localSourceAudio string localSourceAudio string
sessionPrefix string previousCachePath string
sessionPrefix string
} }
func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) { func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) {
@@ -274,11 +277,18 @@ func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) {
runWorkDir := artifacts.SessionRunRootForCampaign(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID) 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") 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) spoolAudioDir := artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
previousCachePath := artifacts.SessionPreviousArtifactPathForCampaign(
cfg.Pipeline.Workspace.Root,
cfg.Session.Campaign,
cfg.Session.SessionID,
"session_recap.md",
)
mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n") mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
mustWriteFile(t, filepath.Join(runWorkDir, "logs", "stage.log"), "log\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(otherRunDir, "logs", "stage.log"), "other\n")
mustWriteFile(t, filepath.Join(spoolAudioDir, "speaker.flac"), "flac\n") mustWriteFile(t, filepath.Join(spoolAudioDir, "speaker.flac"), "flac\n")
mustWriteFile(t, previousCachePath, "# previous recap\n")
localSourceAudio := filepath.Join(filepath.Dir(cfg.SessionPath), "audio", "alice.flac") localSourceAudio := filepath.Join(filepath.Dir(cfg.SessionPath), "audio", "alice.flac")
mustWriteFile(t, localSourceAudio, "source\n") mustWriteFile(t, localSourceAudio, "source\n")
@@ -301,11 +311,12 @@ func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) {
} }
return cfg, cleanupSeed{ return cfg, cleanupSeed{
runWorkDir: runWorkDir, runWorkDir: runWorkDir,
otherRunDir: otherRunDir, otherRunDir: otherRunDir,
spoolAudioDir: spoolAudioDir, spoolAudioDir: spoolAudioDir,
localSourceAudio: localSourceAudio, localSourceAudio: localSourceAudio,
sessionPrefix: seed.S3SessionPrefix, previousCachePath: previousCachePath,
sessionPrefix: seed.S3SessionPrefix,
} }
} }

View File

@@ -28,17 +28,19 @@ func Restore(ctx context.Context, args []string, out io.Writer) error {
var pipelinePath string var pipelinePath string
var sessionPath string var sessionPath string
var sessionID string var sessionID string
var previousSessionID string
var dryRun bool var dryRun bool
var force bool var force bool
var includeAudio bool var includeAudio bool
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)") fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
fs.StringVar(&sessionPath, "session", "", "path to session.yml") fs.StringVar(&sessionPath, "session", "", "path to session.yml")
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates") fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
fs.StringVar(&previousSessionID, "previous-session-id", "", "previous session identifier for session.yml templates")
fs.BoolVar(&dryRun, "dry-run", false, "plan restore actions without writing local files") fs.BoolVar(&dryRun, "dry-run", false, "plan restore actions without writing local files")
fs.BoolVar(&force, "force", false, "overwrite local conflicts with remote state") fs.BoolVar(&force, "force", false, "overwrite local conflicts with remote state")
fs.BoolVar(&includeAudio, "include-audio", false, "include archived session-level audio objects") fs.BoolVar(&includeAudio, "include-audio", false, "include archived session-level audio objects")
fs.Usage = func() { fs.Usage = func() {
_, _ = fmt.Fprintln(out, "Usage: narratio restore [--config <path>] [--session <path>] [--session-id <value>] [--dry-run] [--force] [--include-audio]") _, _ = fmt.Fprintln(out, "Usage: narratio restore [--config <path>] [--session <path>] [--session-id <value>] [--previous-session-id <value>] [--dry-run] [--force] [--include-audio]")
_, _ = fmt.Fprintln(out) _, _ = fmt.Fprintln(out)
_, _ = fmt.Fprintln(out, "Flags:") _, _ = fmt.Fprintln(out, "Flags:")
fs.PrintDefaults() fs.PrintDefaults()
@@ -63,7 +65,8 @@ func Restore(ctx context.Context, args []string, out io.Writer) error {
} }
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{ cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
SessionID: sessionID, SessionID: sessionID,
PreviousSessionID: previousSessionID,
}) })
if err != nil { if err != nil {
return fmt.Errorf("restore: %w", err) return fmt.Errorf("restore: %w", err)

View File

@@ -87,6 +87,33 @@ func TestExecuteRestoreIncludeAudioRestoresAudio(t *testing.T) {
} }
} }
func TestExecuteRestoreRestoresPreviousCacheWhenPresent(t *testing.T) {
workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
fake := &storage.FakeBackend{}
cfg, sessionPrefix, _, _ := seedRestoreCommittedState(t, fake, pipelinePath, sessionPath)
seedRestoreObject(fake, sessionPrefix+"previous/manifest.json", []byte(`{"session_id":"2026-04-26"}`))
seedRestoreObject(fake, sessionPrefix+"previous/artifacts/session_recap.md", []byte("# previous recap\n"))
restoreWithStoreAndRealPhases(t, fake)
var stdout bytes.Buffer
var stderr bytes.Buffer
code := Execute([]string{"restore", "--config", pipelinePath, "--session", sessionPath}, &stdout, &stderr)
if code != 0 {
t.Fatalf("exit code = %d, want 0; stderr=%q", code, stderr.String())
}
sessionRoot := artifacts.SessionWorkDirForCampaign(workspaceRoot, cfg.Session.Campaign, cfg.Session.SessionID)
mustReadEquals(t, filepath.Join(sessionRoot, "previous", "manifest.json"), `{"session_id":"2026-04-26"}`)
mustReadEquals(t, filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md"), "# previous recap\n")
report := mustReadRestoreReport(t, filepath.Join(sessionRoot, "reports", "restore-latest.json"))
if report.Execution.Downloaded != 3 {
t.Fatalf("report execution.downloaded = %d, want 3", report.Execution.Downloaded)
}
}
func TestExecuteRestoreConflictWithoutForceDoesNotOverwrite(t *testing.T) { func TestExecuteRestoreConflictWithoutForceDoesNotOverwrite(t *testing.T) {
workspaceRoot := t.TempDir() workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot) pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
@@ -145,6 +172,28 @@ func TestExecuteRestoreForceOverwritesDifferingFile(t *testing.T) {
} }
} }
func TestExecuteRestoreForceOverwritesDifferingPreviousCacheFile(t *testing.T) {
workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
fake := &storage.FakeBackend{}
cfg, sessionPrefix, _, _ := seedRestoreCommittedState(t, fake, pipelinePath, sessionPath)
seedRestoreObject(fake, sessionPrefix+"previous/artifacts/session_recap.md", []byte("# remote previous recap\n"))
sessionRoot := artifacts.SessionWorkDirForCampaign(workspaceRoot, cfg.Session.Campaign, cfg.Session.SessionID)
mustWriteTestFile(t, filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md"), "# local previous recap\n")
restoreWithStoreAndRealPhases(t, fake)
var stdout bytes.Buffer
var stderr bytes.Buffer
code := Execute([]string{"restore", "--config", pipelinePath, "--session", sessionPath, "--force"}, &stdout, &stderr)
if code != 0 {
t.Fatalf("exit code = %d, want 0; stderr=%q", code, stderr.String())
}
mustReadEquals(t, filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md"), "# remote previous recap\n")
}
func TestExecuteRestoreLockConflictFailsAndWritesNothing(t *testing.T) { func TestExecuteRestoreLockConflictFailsAndWritesNothing(t *testing.T) {
workspaceRoot := t.TempDir() workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot) pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)

View File

@@ -194,6 +194,9 @@ func restoreLocalRelativePathForKey(sessionPrefix, currentManifestKey, key strin
if cleanRel == config.PathArtifactsDirSegment || strings.HasPrefix(cleanRel, config.PathArtifactsDirSegment+"/") { if cleanRel == config.PathArtifactsDirSegment || strings.HasPrefix(cleanRel, config.PathArtifactsDirSegment+"/") {
return cleanRel, true, nil return cleanRel, true, nil
} }
if cleanRel == config.PathPreviousDirSegment || strings.HasPrefix(cleanRel, config.PathPreviousDirSegment+"/") {
return cleanRel, true, nil
}
if includeAudio && (cleanRel == config.PathAudioDirSegment || strings.HasPrefix(cleanRel, config.PathAudioDirSegment+"/")) { if includeAudio && (cleanRel == config.PathAudioDirSegment || strings.HasPrefix(cleanRel, config.PathAudioDirSegment+"/")) {
return cleanRel, true, nil return cleanRel, true, nil
} }

View File

@@ -58,6 +58,27 @@ func TestRestorePlanIncludeAudio(t *testing.T) {
} }
} }
func TestRestorePlanIncludesPreviousCacheByDefault(t *testing.T) {
cfg := restorePlanConfig(t)
current := restorePlanCurrentState(t, cfg)
store := &storage.FakeBackend{}
seedRestoreObject(store, current.CurrentManifestKey, []byte(`{"session_id":"2026-05-03"}`))
seedRestoreObject(store, current.SessionPrefix+"previous/manifest.json", []byte(`{"session_id":"2026-04-26"}`))
seedRestoreObject(store, current.SessionPrefix+"previous/artifacts/session_recap.md", []byte("# previous recap\n"))
plan, err := buildRestorePlan(context.Background(), cfg, current, store, RestorePlanOptions{})
if err != nil {
t.Fatalf("buildRestorePlan() error = %v", err)
}
got := actionRelPaths(plan.Actions)
want := []string{"manifest.json", "previous/artifacts/session_recap.md", "previous/manifest.json"}
if !reflect.DeepEqual(got, want) {
t.Fatalf("action local paths = %#v, want %#v", got, want)
}
}
func TestRestorePlanClassifiesSameAndConflict(t *testing.T) { func TestRestorePlanClassifiesSameAndConflict(t *testing.T) {
cfg := restorePlanConfig(t) cfg := restorePlanConfig(t)
current := restorePlanCurrentState(t, cfg) current := restorePlanCurrentState(t, cfg)

View File

@@ -155,6 +155,116 @@ func TestRestoreThenRunStageForceAnalyzeUsesRestoredDurableState(t *testing.T) {
} }
} }
func TestRestoreThenAnalyzeUsesRestoredPreviousCacheWithoutObjectStore(t *testing.T) {
workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
appendRestoreWorkflowScriptoriumConfig(t, pipelinePath, `
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
previous_recap:
source: narratio.previous_session.artifact.session_recap
required: true
`)
fakeStore := &storage.FakeBackend{}
cfg, sessionPrefix, manifestKey, runIDKey := seedRestoreCommittedState(t, fakeStore, pipelinePath, sessionPath)
seedRestoreObject(fakeStore, runIDKey, []byte("20260519T010203Z-a1b2c3d4\n"))
seedRestoreObject(fakeStore, manifestKey, restoreWorkflowManifestJSON(t, cfg.Session.SessionID, cfg.Session.Campaign))
seedRestoreObject(fakeStore, sessionPrefix+"transcripts/trimmed.json", []byte(`{"segments":[]}`+"\n"))
seedRestoreObject(fakeStore, sessionPrefix+"previous/manifest.json", []byte(`{"session_id":"2026-04-26"}`))
seedRestoreObject(fakeStore, sessionPrefix+"previous/artifacts/session_recap.md", []byte("# previous recap\n"))
restoreWithStoreAndRealPhases(t, fakeStore)
var stdout bytes.Buffer
var stderr bytes.Buffer
restoreCode := Execute(
[]string{
"restore",
"--config", pipelinePath,
"--session", sessionPath,
"--session-id", cfg.Session.SessionID,
},
&stdout,
&stderr,
)
if restoreCode != 0 {
t.Fatalf("restore exit code = %d, want 0; stderr=%q", restoreCode, stderr.String())
}
if stderr.Len() != 0 {
t.Fatalf("restore stderr = %q, want empty", stderr.String())
}
sessionRoot := artifacts.SessionWorkDirForCampaign(workspaceRoot, cfg.Session.Campaign, cfg.Session.SessionID)
mustReadEquals(t, filepath.Join(sessionRoot, "transcripts", "trimmed.json"), `{"segments":[]}`+"\n")
mustReadEquals(t, filepath.Join(sessionRoot, "previous", "manifest.json"), `{"session_id":"2026-04-26"}`)
mustReadEquals(t, filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md"), "# previous recap\n")
scriptoriumFake := &scriptorium.FakeRunner{}
origExecuteStagesFn := executeStagesFn
origObjectStoreFn := newObjectStoreFromConfigFn
objectStoreConstructed := false
t.Cleanup(func() {
executeStagesFn = origExecuteStagesFn
newObjectStoreFromConfigFn = origObjectStoreFn
})
executeStagesFn = func(ctx context.Context, cfg *config.Config, stages []stage.Stage, opts RunOptions) (*RunSummary, error) {
if opts.Env == nil {
opts.Env = &Env{}
}
opts.Env.Scriptorium = scriptoriumFake
return executeStages(ctx, cfg, stages, opts)
}
newObjectStoreFromConfigFn = func(context.Context, *config.Config) (storage.ObjectStore, error) {
objectStoreConstructed = true
return nil, context.Canceled
}
stdout.Reset()
stderr.Reset()
runStageCode := Execute(
[]string{
"run-stage",
"--config", pipelinePath,
"--session", sessionPath,
"--session-id", cfg.Session.SessionID,
"--force",
"--artifacts", "session_recap",
"analyze",
},
&stdout,
&stderr,
)
if runStageCode != 0 {
t.Fatalf("run-stage exit code = %d, want 0; stderr=%q", runStageCode, stderr.String())
}
if stderr.Len() != 0 {
t.Fatalf("run-stage stderr = %q, want empty", stderr.String())
}
if objectStoreConstructed {
t.Fatal("analyze run-stage should not construct object store for previous-session input resolution")
}
if len(scriptoriumFake.RunRequests) != 1 {
t.Fatalf("scriptorium run requests = %d, want 1", len(scriptoriumFake.RunRequests))
}
req := scriptoriumFake.RunRequests[0]
if got := req.InputPaths["transcript"]; got != filepath.Join(sessionRoot, "transcripts", "trimmed.json") {
t.Fatalf("transcript input = %q, want trimmed transcript path", got)
}
if got := req.InputPaths["previous_recap"]; got != filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md") {
t.Fatalf("previous_recap input = %q, want restored previous cache path", got)
}
}
func restoreWorkflowManifestJSON(t *testing.T, sessionID, campaign string) []byte { func restoreWorkflowManifestJSON(t *testing.T, sessionID, campaign string) []byte {
t.Helper() t.Helper()
store := &manifest.LocalStore{} store := &manifest.LocalStore{}
@@ -176,3 +286,15 @@ func restoreWorkflowManifestJSON(t *testing.T, sessionID, campaign string) []byt
} }
return data return data
} }
func appendRestoreWorkflowScriptoriumConfig(t *testing.T, pipelinePath, extra string) {
t.Helper()
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()
if _, err := f.WriteString(extra); err != nil {
t.Fatalf("append pipeline config: %v", err)
}
}

View File

@@ -19,11 +19,13 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
var pipelinePath string var pipelinePath string
var sessionPath string var sessionPath string
var sessionID string var sessionID string
var previousSessionID string
var force bool var force bool
var selectedArtifacts artifactSelectionFlag var selectedArtifacts artifactSelectionFlag
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)") fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
fs.StringVar(&sessionPath, "session", "", "path to session.yml") fs.StringVar(&sessionPath, "session", "", "path to session.yml")
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates") fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
fs.StringVar(&previousSessionID, "previous-session-id", "", "previous session identifier for session.yml templates")
fs.BoolVar(&force, "force", false, "force stage execution") fs.BoolVar(&force, "force", false, "force stage execution")
fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)") fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)")
@@ -43,7 +45,8 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
} }
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{ cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
SessionID: sessionID, SessionID: sessionID,
PreviousSessionID: previousSessionID,
}) })
if err != nil { if err != nil {
return fmt.Errorf("resume: %w", err) return fmt.Errorf("resume: %w", err)

View File

@@ -17,11 +17,13 @@ func Run(ctx context.Context, args []string, out io.Writer) error {
var pipelinePath string var pipelinePath string
var sessionPath string var sessionPath string
var sessionID string var sessionID string
var previousSessionID string
var force bool var force bool
var selectedArtifacts artifactSelectionFlag var selectedArtifacts artifactSelectionFlag
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)") fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
fs.StringVar(&sessionPath, "session", "", "path to session.yml") fs.StringVar(&sessionPath, "session", "", "path to session.yml")
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates") fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
fs.StringVar(&previousSessionID, "previous-session-id", "", "previous session identifier for session.yml templates")
fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)") 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)") fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)")
@@ -41,7 +43,8 @@ func Run(ctx context.Context, args []string, out io.Writer) error {
} }
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{ cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
SessionID: sessionID, SessionID: sessionID,
PreviousSessionID: previousSessionID,
}) })
if err != nil { if err != nil {
return fmt.Errorf("run: %w", err) return fmt.Errorf("run: %w", err)

View File

@@ -17,11 +17,13 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
var pipelinePath string var pipelinePath string
var sessionPath string var sessionPath string
var sessionID string var sessionID string
var previousSessionID string
var force bool var force bool
var selectedArtifacts artifactSelectionFlag var selectedArtifacts artifactSelectionFlag
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)") fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
fs.StringVar(&sessionPath, "session", "", "path to session.yml") fs.StringVar(&sessionPath, "session", "", "path to session.yml")
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates") fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
fs.StringVar(&previousSessionID, "previous-session-id", "", "previous session identifier for session.yml templates")
fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)") 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)") fs.Var(&selectedArtifacts, "artifacts", "artifact names to execute during analyze (comma-separated or repeatable)")
@@ -54,7 +56,8 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
} }
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{ cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
SessionID: sessionID, SessionID: sessionID,
PreviousSessionID: previousSessionID,
}) })
if err != nil { if err != nil {
return fmt.Errorf("run-stage: %w", err) return fmt.Errorf("run-stage: %w", err)

View File

@@ -555,6 +555,12 @@ func needsObjectStoreForRun(cfg *config.Config, stages []stage.Stage) bool {
if cfg.Session.Inputs.AudioS3 != nil && stageRequested("prepare") { if cfg.Session.Inputs.AudioS3 != nil && stageRequested("prepare") {
return true return true
} }
if stageRequested("prepare") {
requirements := artifacts.CollectPreviousArtifactRequirements(configuredScriptoriumArtifacts(cfg))
if len(requirements) > 0 && strings.TrimSpace(cfg.Session.PreviousSessionID) != "" {
return true
}
}
if !stageRequested("archive") { if !stageRequested("archive") {
return false return false
} }
@@ -569,3 +575,10 @@ func needsObjectStoreForRun(cfg *config.Config, stages []stage.Stage) bool {
} }
return true return true
} }
func configuredScriptoriumArtifacts(cfg *config.Config) map[string]config.ScriptoriumArtifactConfig {
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Scriptorium == nil {
return nil
}
return cfg.Pipeline.Scriptorium.Artifacts
}

View File

@@ -199,6 +199,55 @@ func TestExecuteStagesAnalyzeOutputsPersistAsScriptoriumArtifacts(t *testing.T)
} }
} }
func TestNeedsObjectStoreForRunPrepareWithPreviousRequirements(t *testing.T) {
tests := []struct {
name string
previousSessionID string
want bool
}{
{
name: "previous session configured",
previousSessionID: "2026-05-10",
want: true,
},
{
name: "previous session missing",
previousSessionID: "",
want: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cfg := &config.Config{
Pipeline: &config.PipelineConfig{
Scriptorium: &config.ScriptoriumConfig{
Artifacts: map[string]config.ScriptoriumArtifactConfig{
"session_recap": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"previous_recap": {
Source: "narratio.previous_session.artifact.session_recap",
Required: true,
},
},
},
},
},
},
Session: &config.SessionConfig{
PreviousSessionID: tt.previousSessionID,
},
}
got := needsObjectStoreForRun(cfg, []stage.Stage{countingStage{name: "prepare", runs: new(int)}})
if got != tt.want {
t.Fatalf("needsObjectStoreForRun() = %v, want %v", got, tt.want)
}
})
}
}
func TestExecuteStagesArchiveFailsWhenRequiredRecapPromotionMissingForSelectedArtifacts(t *testing.T) { func TestExecuteStagesArchiveFailsWhenRequiredRecapPromotionMissingForSelectedArtifacts(t *testing.T) {
cfg := testConfig(t) cfg := testConfig(t)
cfg.Pipeline.Storage.S3 = &config.StorageS3Config{ cfg.Pipeline.Storage.S3 = &config.StorageS3Config{

View File

@@ -9,11 +9,12 @@ import (
"testing" "testing"
) )
func TestPlanUsesDiscoveredSessionTemplateWithSessionID(t *testing.T) { func TestPlanUsesDiscoveredSessionTemplateWithSessionIDs(t *testing.T) {
workspaceRoot := t.TempDir() workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot) pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
sessionTemplate := `session_id: "{{ session_id }}" sessionTemplate := `session_id: "{{ session_id }}"
previous_session_id: "{{ previous_session_id }}"
campaign: sample-campaign campaign: sample-campaign
inputs: inputs:
audio_dir: ./audio audio_dir: ./audio
@@ -36,7 +37,11 @@ inputs:
t.Cleanup(func() { _ = os.Chdir(originalWD) }) t.Cleanup(func() { _ = os.Chdir(originalWD) })
var out bytes.Buffer var out bytes.Buffer
if err := Plan(context.Background(), []string{"--config", pipelinePath, "--session-id", "2026-04-04"}, &out); err != nil { if err := Plan(context.Background(), []string{
"--config", pipelinePath,
"--session-id", "2026-04-04",
"--previous-session-id", "2026-03-28",
}, &out); err != nil {
t.Fatalf("Plan() error = %v", err) t.Fatalf("Plan() error = %v", err)
} }
if !strings.Contains(out.String(), "narratio plan: workdir prepared") { if !strings.Contains(out.String(), "narratio plan: workdir prepared") {
@@ -58,6 +63,38 @@ func TestPlanFailsWhenSessionIDMismatchesConcreteSession(t *testing.T) {
} }
} }
func TestPlanFailsWhenPreviousSessionIDMismatchesConcreteSession(t *testing.T) {
workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
sessionYAML := `session_id: 2026-05-03
previous_session_id: 2026-04-26
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)
}
var out bytes.Buffer
err := Plan(context.Background(), []string{
"--config", pipelinePath,
"--session", sessionPath,
"--session-id", "2026-05-03",
"--previous-session-id", "2026-04-25",
}, &out)
if err == nil {
t.Fatal("expected error, got nil")
}
if !strings.Contains(err.Error(), "previous_session_id mismatch") {
t.Fatalf("error = %q, want mismatch context", err.Error())
}
}
func TestRunStageAcceptsSessionIDFlagAndParsesStageName(t *testing.T) { func TestRunStageAcceptsSessionIDFlagAndParsesStageName(t *testing.T) {
workspaceRoot := t.TempDir() workspaceRoot := t.TempDir()
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot) pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)

View File

@@ -18,11 +18,15 @@ const (
ArtifactTranscriptFull = "narratio.transcript.full" ArtifactTranscriptFull = "narratio.transcript.full"
ArtifactTranscriptTrimmed = "narratio.transcript.trimmed" ArtifactTranscriptTrimmed = "narratio.transcript.trimmed"
ArtifactBoundsSession = "narratio.bounds.session" ArtifactBoundsSession = "narratio.bounds.session"
ArtifactProvenancePreviousCacheManifestInput = "manifest.inputs.previous_cache"
ArtifactProvenancePreviousCacheFilesystem = "current_session.previous_cache"
) )
// ErrSessionArtifactNotFound is returned when no readable artifact exists for a known ID. // ErrSessionArtifactNotFound is returned when no readable artifact exists for a known ID.
var ErrSessionArtifactNotFound = errors.New("session artifact not found") var ErrSessionArtifactNotFound = errors.New("session artifact not found")
var configuredArtifactSourceRE = regexp.MustCompile(`^narratio\.artifact\.[a-z][a-z0-9_]*$`) var configuredArtifactSourceRE = regexp.MustCompile(`^narratio\.artifact\.[a-z][a-z0-9_]*$`)
var previousSessionArtifactSourceRE = regexp.MustCompile(`^narratio\.previous_session\.artifact\.([a-z][a-z0-9_]*)$`)
type artifactContentKind string type artifactContentKind string
@@ -118,6 +122,21 @@ func IsConfiguredArtifactSource(source string) bool {
return configuredArtifactSourceRE.MatchString(strings.TrimSpace(source)) return configuredArtifactSourceRE.MatchString(strings.TrimSpace(source))
} }
// IsPreviousSessionArtifactSource returns true when source is narratio.previous_session.artifact.<name>.
func IsPreviousSessionArtifactSource(source string) bool {
_, ok := PreviousSessionArtifactName(source)
return ok
}
// PreviousSessionArtifactName extracts <name> from narratio.previous_session.artifact.<name>.
func PreviousSessionArtifactName(source string) (string, bool) {
matches := previousSessionArtifactSourceRE.FindStringSubmatch(strings.TrimSpace(source))
if len(matches) != 2 {
return "", false
}
return matches[1], true
}
// ResolveSessionArtifact resolves a symbolic source to a readable local session artifact path. // ResolveSessionArtifact resolves a symbolic source to a readable local session artifact path.
// Resolution order is manifest producer outputs first, then canonical session path fallback. // Resolution order is manifest producer outputs first, then canonical session path fallback.
func ResolveSessionArtifact(paths SessionPaths, m *manifest.Manifest, source string) (ResolvedSessionArtifact, error) { func ResolveSessionArtifact(paths SessionPaths, m *manifest.Manifest, source string) (ResolvedSessionArtifact, error) {
@@ -170,6 +189,9 @@ func ResolveSessionArtifact(paths SessionPaths, m *manifest.Manifest, source str
// configured narratio.artifact.<name> sources through runtime catalog availability. // configured narratio.artifact.<name> sources through runtime catalog availability.
func ResolveSessionArtifactWithCatalog(paths SessionPaths, m *manifest.Manifest, source string, catalog *ArtifactCatalog) (ResolvedSessionArtifact, error) { func ResolveSessionArtifactWithCatalog(paths SessionPaths, m *manifest.Manifest, source string, catalog *ArtifactCatalog) (ResolvedSessionArtifact, error) {
normalized := strings.TrimSpace(source) normalized := strings.TrimSpace(source)
if IsPreviousSessionArtifactSource(normalized) {
return ResolvePreviousSessionArtifactWithCatalog(paths, m, normalized, catalog)
}
if !IsConfiguredArtifactSource(normalized) { if !IsConfiguredArtifactSource(normalized) {
return ResolveSessionArtifact(paths, m, normalized) return ResolveSessionArtifact(paths, m, normalized)
} }
@@ -195,6 +217,72 @@ func ResolveSessionArtifactWithCatalog(paths SessionPaths, m *manifest.Manifest,
}, nil }, nil
} }
// ResolvePreviousSessionArtifactWithCatalog resolves one canonical previous-session source id
// to the prepared current-session previous-cache path.
func ResolvePreviousSessionArtifactWithCatalog(
paths SessionPaths,
m *manifest.Manifest,
source string,
catalog *ArtifactCatalog,
) (ResolvedSessionArtifact, error) {
artifactName, ok := PreviousSessionArtifactName(source)
if !ok {
return ResolvedSessionArtifact{}, fmt.Errorf("unsupported previous-session artifact source %q", source)
}
if catalog == nil {
return ResolvedSessionArtifact{}, fmt.Errorf("previous-session artifact source %q requires runtime artifact catalog", source)
}
configuredSourceID := ConfiguredArtifactSourceID(artifactName)
entry, ok := catalog.Lookup(configuredSourceID)
if !ok {
return ResolvedSessionArtifact{}, fmt.Errorf("unsupported previous-session artifact source %q", source)
}
candidates := previousSessionCacheCandidatePaths(paths, entry.CanonicalRelPath)
if len(candidates) == 0 {
return ResolvedSessionArtifact{}, &SessionArtifactNotFoundError{ArtifactID: source}
}
manifestInputPaths := manifestInputPathSet(paths, m)
fallback := ""
for _, candidate := range candidates {
exists, isDir, statErr := pathExists(candidate)
if statErr != nil {
return ResolvedSessionArtifact{}, fmt.Errorf("stat %q: %w", candidate, statErr)
}
if !exists || isDir {
continue
}
if err := validateResolvedContent(candidate, contentText); err != nil {
return ResolvedSessionArtifact{}, fmt.Errorf("validate %q: %w", source, err)
}
if _, ok := manifestInputPaths[candidate]; ok {
return ResolvedSessionArtifact{
ID: source,
Path: candidate,
ProducerStage: "prepare",
OutputKind: "previous_session_artifact",
Provenance: ArtifactProvenancePreviousCacheManifestInput,
}, nil
}
if fallback == "" {
fallback = candidate
}
}
if fallback != "" {
return ResolvedSessionArtifact{
ID: source,
Path: fallback,
ProducerStage: "prepare",
OutputKind: "previous_session_artifact",
Provenance: ArtifactProvenancePreviousCacheFilesystem,
}, nil
}
return ResolvedSessionArtifact{}, &SessionArtifactNotFoundError{ArtifactID: source}
}
func manifestArtifactCandidates(paths SessionPaths, m *manifest.Manifest, spec artifactSpec) []ResolvedSessionArtifact { func manifestArtifactCandidates(paths SessionPaths, m *manifest.Manifest, spec artifactSpec) []ResolvedSessionArtifact {
if m == nil || len(m.Stages) == 0 || spec.ProducerStage == "" || spec.OutputKind == "" { if m == nil || len(m.Stages) == 0 || spec.ProducerStage == "" || spec.OutputKind == "" {
return nil return nil
@@ -243,6 +331,50 @@ func dedupeResolvedArtifacts(values []ResolvedSessionArtifact) []ResolvedSession
return out return out
} }
func previousSessionCacheCandidatePaths(paths SessionPaths, canonicalRelPath string) []string {
trimmed := strings.TrimSpace(canonicalRelPath)
if trimmed == "" {
return nil
}
normalized := filepath.ToSlash(filepath.Clean(filepath.FromSlash(trimmed)))
if normalized == "." || normalized == "" || normalized == ".." || strings.HasPrefix(normalized, "../") || strings.HasPrefix(normalized, "/") {
return nil
}
relCandidates := []string{normalized}
const artifactsPrefix = "artifacts/"
if strings.HasPrefix(normalized, artifactsPrefix) && len(normalized) > len(artifactsPrefix) {
relCandidates = append(relCandidates, strings.TrimPrefix(normalized, artifactsPrefix))
}
out := make([]string, 0, len(relCandidates))
seen := map[string]struct{}{}
for _, rel := range relCandidates {
abs := filepath.Clean(SessionPreviousArtifactPath(paths, rel))
if _, ok := seen[abs]; ok {
continue
}
seen[abs] = struct{}{}
out = append(out, abs)
}
return out
}
func manifestInputPathSet(paths SessionPaths, m *manifest.Manifest) map[string]struct{} {
if m == nil || len(m.Inputs) == 0 {
return nil
}
out := make(map[string]struct{}, len(m.Inputs))
for _, in := range m.Inputs {
resolved := filepath.Clean(ResolveSessionLocalPathForRead(paths, in.Path))
if strings.TrimSpace(resolved) == "" {
continue
}
out[resolved] = struct{}{}
}
return out
}
func pathExists(path string) (exists bool, isDir bool, err error) { func pathExists(path string) (exists bool, isDir bool, err error) {
info, err := os.Stat(path) info, err := os.Stat(path)
if err == nil { if err == nil {

View File

@@ -45,6 +45,58 @@ func TestNormalizeSessionArtifactSource(t *testing.T) {
} }
} }
func TestPreviousSessionArtifactSourceHelpers(t *testing.T) {
tests := []struct {
name string
source string
wantName string
wantMatch bool
}{
{
name: "valid",
source: "narratio.previous_session.artifact.session_recap",
wantName: "session_recap",
wantMatch: true,
},
{
name: "valid with surrounding whitespace",
source: " narratio.previous_session.artifact.quest_log ",
wantName: "quest_log",
wantMatch: true,
},
{
name: "missing name",
source: "narratio.previous_session.artifact.",
wantMatch: false,
},
{
name: "invalid key characters",
source: "narratio.previous_session.artifact.session-recap",
wantMatch: false,
},
{
name: "wrong prefix",
source: "narratio.previous.artifact.session_recap",
wantMatch: false,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
name, ok := PreviousSessionArtifactName(tt.source)
if ok != tt.wantMatch {
t.Fatalf("PreviousSessionArtifactName(%q) ok = %t, want %t", tt.source, ok, tt.wantMatch)
}
if name != tt.wantName {
t.Fatalf("PreviousSessionArtifactName(%q) name = %q, want %q", tt.source, name, tt.wantName)
}
if got := IsPreviousSessionArtifactSource(tt.source); got != tt.wantMatch {
t.Fatalf("IsPreviousSessionArtifactSource(%q) = %t, want %t", tt.source, got, tt.wantMatch)
}
})
}
}
func TestResolveSessionArtifactPrefersManifestOutput(t *testing.T) { func TestResolveSessionArtifactPrefersManifestOutput(t *testing.T) {
workspace := t.TempDir() workspace := t.TempDir()
paths := buildSessionPaths(workspace, "campaign", "session") paths := buildSessionPaths(workspace, "campaign", "session")
@@ -266,3 +318,120 @@ func TestResolveSessionArtifactWithCatalogUnsupportedConfiguredSourceFails(t *te
t.Fatalf("error = %q, want unsupported artifact source", err.Error()) t.Fatalf("error = %q, want unsupported artifact source", err.Error())
} }
} }
func TestResolvePreviousSessionArtifactWithCatalogPrefersManifestInputRecord(t *testing.T) {
workspace := t.TempDir()
paths := buildSessionPaths(workspace, "campaign", "session")
manifestBackedPath := SessionPreviousArtifactPath(paths, "artifacts/session_recap.md")
fallbackPath := SessionPreviousArtifactPath(paths, "session_recap.md")
if err := os.MkdirAll(filepath.Dir(manifestBackedPath), 0o755); err != nil {
t.Fatalf("MkdirAll() error = %v", err)
}
if err := os.MkdirAll(filepath.Dir(fallbackPath), 0o755); err != nil {
t.Fatalf("MkdirAll() error = %v", err)
}
if err := os.WriteFile(manifestBackedPath, []byte("recap from manifest input\n"), 0o644); err != nil {
t.Fatalf("WriteFile() error = %v", err)
}
if err := os.WriteFile(fallbackPath, []byte("recap fallback\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)
}
m := manifest.New("session", time.Now().UTC())
m.Inputs = []manifest.InputRecord{
{Kind: "previous_artifact", Path: manifestBackedPath},
}
resolved, err := ResolvePreviousSessionArtifactWithCatalog(
paths,
m,
"narratio.previous_session.artifact.session_recap",
catalog,
)
if err != nil {
t.Fatalf("ResolvePreviousSessionArtifactWithCatalog() error = %v", err)
}
if resolved.Path != manifestBackedPath {
t.Fatalf("resolved path = %q, want %q", resolved.Path, manifestBackedPath)
}
if resolved.Provenance != ArtifactProvenancePreviousCacheManifestInput {
t.Fatalf("provenance = %q, want %q", resolved.Provenance, ArtifactProvenancePreviousCacheManifestInput)
}
}
func TestResolvePreviousSessionArtifactWithCatalogFallsBackToPreparedCachePath(t *testing.T) {
workspace := t.TempDir()
paths := buildSessionPaths(workspace, "campaign", "session")
fallbackPath := SessionPreviousArtifactPath(paths, "session_recap.md")
if err := os.MkdirAll(filepath.Dir(fallbackPath), 0o755); err != nil {
t.Fatalf("MkdirAll() error = %v", err)
}
if err := os.WriteFile(fallbackPath, []byte("recap fallback\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)
}
resolved, err := ResolvePreviousSessionArtifactWithCatalog(
paths,
nil,
"narratio.previous_session.artifact.session_recap",
catalog,
)
if err != nil {
t.Fatalf("ResolvePreviousSessionArtifactWithCatalog() error = %v", err)
}
if resolved.Path != fallbackPath {
t.Fatalf("resolved path = %q, want %q", resolved.Path, fallbackPath)
}
if resolved.Provenance != ArtifactProvenancePreviousCacheFilesystem {
t.Fatalf("provenance = %q, want %q", resolved.Provenance, ArtifactProvenancePreviousCacheFilesystem)
}
}
func TestResolvePreviousSessionArtifactWithCatalogMissingReturnsTypedError(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 := ResolvePreviousSessionArtifactWithCatalog(
paths,
nil,
"narratio.previous_session.artifact.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)
}
}

View File

@@ -73,6 +73,8 @@ func (s *LocalStore) ensureLayout(paths SessionPaths) (SessionPaths, error) {
paths.LogsDir, paths.LogsDir,
paths.CurrentDir, paths.CurrentDir,
paths.RunsDir, paths.RunsDir,
paths.PreviousDir,
paths.PreviousArtifactsDir,
} }
for _, dir := range dirs { for _, dir := range dirs {

View File

@@ -27,10 +27,15 @@ func TestEnsureLayoutCreatesExpectedDirectories(t *testing.T) {
checkDirExists(t, paths.LogsDir) checkDirExists(t, paths.LogsDir)
checkDirExists(t, paths.CurrentDir) checkDirExists(t, paths.CurrentDir)
checkDirExists(t, paths.RunsDir) checkDirExists(t, paths.RunsDir)
checkDirExists(t, paths.PreviousDir)
checkDirExists(t, paths.PreviousArtifactsDir)
if filepath.Base(paths.ManifestPath) != "manifest.json" { if filepath.Base(paths.ManifestPath) != "manifest.json" {
t.Fatalf("ManifestPath = %q, want basename manifest.json", paths.ManifestPath) t.Fatalf("ManifestPath = %q, want basename manifest.json", paths.ManifestPath)
} }
if filepath.Base(paths.PreviousManifestPath) != "manifest.json" {
t.Fatalf("PreviousManifestPath = %q, want basename manifest.json", paths.PreviousManifestPath)
}
if filepath.Base(paths.LockPath) != ".lock" { if filepath.Base(paths.LockPath) != ".lock" {
t.Fatalf("LockPath = %q, want basename .lock", paths.LockPath) t.Fatalf("LockPath = %q, want basename .lock", paths.LockPath)
} }

View File

@@ -23,6 +23,9 @@ type SessionPaths struct {
LogsDir string LogsDir string
CurrentDir string CurrentDir string
RunsDir string RunsDir string
PreviousDir string
PreviousManifestPath string
PreviousArtifactsDir string
ManifestPath string ManifestPath string
LockPath string LockPath string
} }
@@ -42,6 +45,29 @@ func SessionRunsDirForCampaign(rootDir, campaign, sessionID string) string {
return filepath.Join(SessionWorkDirForCampaign(rootDir, campaign, sessionID), config.PathRunsDirSegment) return filepath.Join(SessionWorkDirForCampaign(rootDir, campaign, sessionID), config.PathRunsDirSegment)
} }
// SessionPreviousDirForCampaign returns the canonical previous-session state directory.
func SessionPreviousDirForCampaign(rootDir, campaign, sessionID string) string {
return filepath.Join(SessionWorkDirForCampaign(rootDir, campaign, sessionID), config.PathPreviousDirSegment)
}
// SessionPreviousManifestPathForCampaign returns the canonical previous-session manifest cache path.
func SessionPreviousManifestPathForCampaign(rootDir, campaign, sessionID string) string {
return filepath.Join(SessionPreviousDirForCampaign(rootDir, campaign, sessionID), config.PathManifestFile)
}
// SessionPreviousArtifactsDirForCampaign returns the canonical previous-session artifact cache directory.
func SessionPreviousArtifactsDirForCampaign(rootDir, campaign, sessionID string) string {
return filepath.Join(SessionPreviousDirForCampaign(rootDir, campaign, sessionID), config.PathArtifactsDirSegment)
}
// SessionPreviousArtifactPathForCampaign returns a path under previous/artifacts for one artifact.
func SessionPreviousArtifactPathForCampaign(rootDir, campaign, sessionID, artifactRelativePath string) string {
return filepath.Join(
SessionPreviousArtifactsDirForCampaign(rootDir, campaign, sessionID),
filepath.FromSlash(artifactRelativePath),
)
}
// SessionRunRootForCampaign returns the canonical run root under runs/{run_id}. // SessionRunRootForCampaign returns the canonical run root under runs/{run_id}.
func SessionRunRootForCampaign(rootDir, campaign, sessionID, runID string) string { func SessionRunRootForCampaign(rootDir, campaign, sessionID, runID string) string {
return filepath.Join(SessionRunsDirForCampaign(rootDir, campaign, sessionID), runID) return filepath.Join(SessionRunsDirForCampaign(rootDir, campaign, sessionID), runID)
@@ -62,6 +88,26 @@ func SessionSpoolAudioDir(spoolRoot, campaign, sessionID, runID string) string {
return filepath.Join(spoolRoot, campaign, sessionID, runID, config.PathAudioDirSegment) return filepath.Join(spoolRoot, campaign, sessionID, runID, config.PathAudioDirSegment)
} }
// SessionPreviousDir returns the previous-session state directory for already-resolved session paths.
func SessionPreviousDir(paths SessionPaths) string {
return paths.PreviousDir
}
// SessionPreviousManifestPath returns the previous-session manifest path for already-resolved session paths.
func SessionPreviousManifestPath(paths SessionPaths) string {
return paths.PreviousManifestPath
}
// SessionPreviousArtifactsDir returns the previous-session artifact directory for already-resolved session paths.
func SessionPreviousArtifactsDir(paths SessionPaths) string {
return paths.PreviousArtifactsDir
}
// SessionPreviousArtifactPath returns a path under previous/artifacts for already-resolved session paths.
func SessionPreviousArtifactPath(paths SessionPaths, artifactRelativePath string) string {
return filepath.Join(paths.PreviousArtifactsDir, filepath.FromSlash(artifactRelativePath))
}
func buildSessionPaths(workspaceRoot, campaign, sessionID string) SessionPaths { func buildSessionPaths(workspaceRoot, campaign, sessionID string) SessionPaths {
root := SessionWorkDirForCampaign(workspaceRoot, campaign, sessionID) root := SessionWorkDirForCampaign(workspaceRoot, campaign, sessionID)
return buildSessionPathsFromRoot(workspaceRoot, campaign, sessionID, root) return buildSessionPathsFromRoot(workspaceRoot, campaign, sessionID, root)
@@ -84,6 +130,9 @@ func buildSessionPathsFromRoot(workspaceRoot, campaign, sessionID, root string)
LogsDir: filepath.Join(root, config.PathLogsDirSegment), LogsDir: filepath.Join(root, config.PathLogsDirSegment),
CurrentDir: filepath.Join(root, config.PathCurrentDirSegment), CurrentDir: filepath.Join(root, config.PathCurrentDirSegment),
RunsDir: filepath.Join(root, config.PathRunsDirSegment), RunsDir: filepath.Join(root, config.PathRunsDirSegment),
PreviousDir: filepath.Join(root, config.PathPreviousDirSegment),
PreviousManifestPath: filepath.Join(root, config.PathPreviousDirSegment, config.PathManifestFile),
PreviousArtifactsDir: filepath.Join(root, config.PathPreviousDirSegment, config.PathArtifactsDirSegment),
ManifestPath: filepath.Join(root, config.PathManifestFile), ManifestPath: filepath.Join(root, config.PathManifestFile),
LockPath: filepath.Join(root, config.PathLockFile), LockPath: filepath.Join(root, config.PathLockFile),
} }

View File

@@ -49,6 +49,52 @@ func TestSessionRunManifestPathForCampaign(t *testing.T) {
} }
} }
func TestSessionPreviousPathsForCampaign(t *testing.T) {
root := "/tmp/workspace"
previousDir := SessionPreviousDirForCampaign(root, "forsaken", "2026-04-19")
wantPreviousDir := filepath.Join(root, "work", "forsaken", "2026-04-19", "previous")
if previousDir != wantPreviousDir {
t.Fatalf("SessionPreviousDirForCampaign() = %q, want %q", previousDir, wantPreviousDir)
}
manifestPath := SessionPreviousManifestPathForCampaign(root, "forsaken", "2026-04-19")
wantManifestPath := filepath.Join(root, "work", "forsaken", "2026-04-19", "previous", "manifest.json")
if manifestPath != wantManifestPath {
t.Fatalf("SessionPreviousManifestPathForCampaign() = %q, want %q", manifestPath, wantManifestPath)
}
artifactsDir := SessionPreviousArtifactsDirForCampaign(root, "forsaken", "2026-04-19")
wantArtifactsDir := filepath.Join(root, "work", "forsaken", "2026-04-19", "previous", "artifacts")
if artifactsDir != wantArtifactsDir {
t.Fatalf("SessionPreviousArtifactsDirForCampaign() = %q, want %q", artifactsDir, wantArtifactsDir)
}
artifactPath := SessionPreviousArtifactPathForCampaign(root, "forsaken", "2026-04-19", "session_recap.md")
wantArtifactPath := filepath.Join(root, "work", "forsaken", "2026-04-19", "previous", "artifacts", "session_recap.md")
if artifactPath != wantArtifactPath {
t.Fatalf("SessionPreviousArtifactPathForCampaign() = %q, want %q", artifactPath, wantArtifactPath)
}
}
func TestSessionPreviousPathsFromSessionPaths(t *testing.T) {
paths := buildSessionPaths("/tmp/workspace", "forsaken", "2026-04-19")
if got := SessionPreviousDir(paths); got != paths.PreviousDir {
t.Fatalf("SessionPreviousDir() = %q, want %q", got, paths.PreviousDir)
}
if got := SessionPreviousManifestPath(paths); got != paths.PreviousManifestPath {
t.Fatalf("SessionPreviousManifestPath() = %q, want %q", got, paths.PreviousManifestPath)
}
if got := SessionPreviousArtifactsDir(paths); got != paths.PreviousArtifactsDir {
t.Fatalf("SessionPreviousArtifactsDir() = %q, want %q", got, paths.PreviousArtifactsDir)
}
got := SessionPreviousArtifactPath(paths, "quest_log.json")
want := filepath.Join(paths.PreviousArtifactsDir, "quest_log.json")
if got != want {
t.Fatalf("SessionPreviousArtifactPath() = %q, want %q", got, want)
}
}
func TestSessionSpoolAudioDir(t *testing.T) { func TestSessionSpoolAudioDir(t *testing.T) {
root := "/var/spool/narratio" root := "/var/spool/narratio"
got := SessionSpoolAudioDir(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4") got := SessionSpoolAudioDir(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4")

View File

@@ -0,0 +1,112 @@
package artifacts
import (
"fmt"
"sort"
"strings"
"gitea.maximumdirect.net/eric/narratio/internal/config"
)
// PreviousArtifactRequirement describes one previous-session artifact dependency.
type PreviousArtifactRequirement struct {
Name string
Required bool
Sources []string
}
// CollectPreviousArtifactRequirements scans enabled Scriptorium artifacts and returns
// deduplicated previous-session artifact requirements in deterministic order.
func CollectPreviousArtifactRequirements(
artifactsCfg map[string]config.ScriptoriumArtifactConfig,
) []PreviousArtifactRequirement {
if len(artifactsCfg) == 0 {
return nil
}
artifactNames := sortedScriptoriumArtifactNames(artifactsCfg)
byName := map[string]PreviousArtifactRequirement{}
for _, artifactName := range artifactNames {
artifactCfg := artifactsCfg[artifactName]
if !artifactCfg.Enabled {
continue
}
inputNames := sortedScriptoriumInputKeys(artifactCfg.Inputs)
for _, inputName := range inputNames {
inputCfg := artifactCfg.Inputs[inputName]
previousName, ok := PreviousSessionArtifactName(inputCfg.Source)
if !ok {
continue
}
location := fmt.Sprintf(
"pipeline.scriptorium.artifacts.%s.inputs.%s.source",
artifactName,
inputName,
)
requirement := byName[previousName]
requirement.Name = previousName
requirement.Required = requirement.Required || inputCfg.Required
requirement.Sources = append(requirement.Sources, location)
byName[previousName] = requirement
}
}
if len(byName) == 0 {
return nil
}
requirements := make([]PreviousArtifactRequirement, 0, len(byName))
for _, requirement := range byName {
requirement.Sources = dedupeAndSortStrings(requirement.Sources)
requirements = append(requirements, requirement)
}
sort.Slice(requirements, func(i, j int) bool {
return requirements[i].Name < requirements[j].Name
})
return requirements
}
func sortedScriptoriumArtifactNames(artifactsCfg map[string]config.ScriptoriumArtifactConfig) []string {
names := make([]string, 0, len(artifactsCfg))
for name := range artifactsCfg {
names = append(names, name)
}
sort.Strings(names)
return names
}
func sortedScriptoriumInputKeys(inputs map[string]config.ScriptoriumInputConfig) []string {
if len(inputs) == 0 {
return nil
}
names := make([]string, 0, len(inputs))
for name := range inputs {
names = append(names, name)
}
sort.Strings(names)
return names
}
func dedupeAndSortStrings(values []string) []string {
if len(values) == 0 {
return nil
}
seen := map[string]struct{}{}
out := make([]string, 0, len(values))
for _, value := range values {
trimmed := strings.TrimSpace(value)
if trimmed == "" {
continue
}
if _, ok := seen[trimmed]; ok {
continue
}
seen[trimmed] = struct{}{}
out = append(out, trimmed)
}
sort.Strings(out)
return out
}

View File

@@ -0,0 +1,190 @@
package artifacts
import (
"reflect"
"testing"
"gitea.maximumdirect.net/eric/narratio/internal/config"
)
func TestCollectPreviousArtifactRequirements(t *testing.T) {
tests := []struct {
name string
artifactsCfg map[string]config.ScriptoriumArtifactConfig
want []PreviousArtifactRequirement
}{
{
name: "no artifacts",
artifactsCfg: nil,
want: nil,
},
{
name: "no previous inputs",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"session_recap": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"transcript": {Source: "narratio.transcript.trimmed", Required: true},
},
},
},
want: nil,
},
{
name: "one optional previous input",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"session_recap": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"previous_recap": {Source: "narratio.previous_session.artifact.session_recap", Required: false},
},
},
},
want: []PreviousArtifactRequirement{
{
Name: "session_recap",
Required: false,
Sources: []string{"pipeline.scriptorium.artifacts.session_recap.inputs.previous_recap.source"},
},
},
},
{
name: "one required previous input",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"quest_log": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"previous_quest_log": {Source: "narratio.previous_session.artifact.quest_log", Required: true},
},
},
},
want: []PreviousArtifactRequirement{
{
Name: "quest_log",
Required: true,
Sources: []string{"pipeline.scriptorium.artifacts.quest_log.inputs.previous_quest_log.source"},
},
},
},
{
name: "duplicate references are deduped",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"a": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"x": {Source: "narratio.previous_session.artifact.session_recap", Required: false},
},
},
"b": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"y": {Source: "narratio.previous_session.artifact.session_recap", Required: false},
},
},
},
want: []PreviousArtifactRequirement{
{
Name: "session_recap",
Required: false,
Sources: []string{
"pipeline.scriptorium.artifacts.a.inputs.x.source",
"pipeline.scriptorium.artifacts.b.inputs.y.source",
},
},
},
},
{
name: "required plus optional reference becomes required",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"a": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"x": {Source: "narratio.previous_session.artifact.session_recap", Required: false},
},
},
"b": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"y": {Source: "narratio.previous_session.artifact.session_recap", Required: true},
},
},
},
want: []PreviousArtifactRequirement{
{
Name: "session_recap",
Required: true,
Sources: []string{
"pipeline.scriptorium.artifacts.a.inputs.x.source",
"pipeline.scriptorium.artifacts.b.inputs.y.source",
},
},
},
},
{
name: "disabled artifact references are ignored",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"disabled_artifact": {
Enabled: false,
Inputs: map[string]config.ScriptoriumInputConfig{
"x": {Source: "narratio.previous_session.artifact.session_recap", Required: true},
},
},
"enabled_artifact": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"y": {Source: "narratio.previous_session.artifact.quest_log", Required: false},
},
},
},
want: []PreviousArtifactRequirement{
{
Name: "quest_log",
Required: false,
Sources: []string{"pipeline.scriptorium.artifacts.enabled_artifact.inputs.y.source"},
},
},
},
{
name: "deterministic ordering",
artifactsCfg: map[string]config.ScriptoriumArtifactConfig{
"zz": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"b_input": {Source: "narratio.previous_session.artifact.quest_log", Required: false},
"a_input": {Source: "narratio.previous_session.artifact.session_recap", Required: false},
},
},
"aa": {
Enabled: true,
Inputs: map[string]config.ScriptoriumInputConfig{
"c_input": {Source: "narratio.previous_session.artifact.session_recap", Required: false},
},
},
},
want: []PreviousArtifactRequirement{
{
Name: "quest_log",
Required: false,
Sources: []string{"pipeline.scriptorium.artifacts.zz.inputs.b_input.source"},
},
{
Name: "session_recap",
Required: false,
Sources: []string{
"pipeline.scriptorium.artifacts.aa.inputs.c_input.source",
"pipeline.scriptorium.artifacts.zz.inputs.a_input.source",
},
},
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got := CollectPreviousArtifactRequirements(tt.artifactsCfg)
if !reflect.DeepEqual(got, tt.want) {
t.Fatalf("CollectPreviousArtifactRequirements() = %#v, want %#v", got, tt.want)
}
})
}
}

View File

@@ -27,11 +27,12 @@ type PipelineConfig struct {
// SessionConfig contains per-session inputs and metadata. // SessionConfig contains per-session inputs and metadata.
type SessionConfig struct { type SessionConfig struct {
SessionID string `yaml:"session_id"` SessionID string `yaml:"session_id"`
Campaign string `yaml:"campaign"` PreviousSessionID string `yaml:"previous_session_id"`
Date string `yaml:"date"` Campaign string `yaml:"campaign"`
Title string `yaml:"title"` Date string `yaml:"date"`
Inputs SessionInputsConfig `yaml:"inputs"` Title string `yaml:"title"`
Inputs SessionInputsConfig `yaml:"inputs"`
} }
// WorkspaceConfig configures local workspace behavior. // WorkspaceConfig configures local workspace behavior.

View File

@@ -56,6 +56,7 @@ const (
PathLogsDirSegment = "logs" PathLogsDirSegment = "logs"
PathCurrentDirSegment = "current" PathCurrentDirSegment = "current"
PathRunsDirSegment = "runs" PathRunsDirSegment = "runs"
PathPreviousDirSegment = "previous"
PathManifestFile = "manifest.json" PathManifestFile = "manifest.json"
PathLockFile = ".lock" PathLockFile = ".lock"
PathTranscriptMerged = "transcripts/merged.json" PathTranscriptMerged = "transcripts/merged.json"

View File

@@ -6,6 +6,7 @@ import (
"os" "os"
"path/filepath" "path/filepath"
"regexp" "regexp"
"sort"
"strings" "strings"
"gopkg.in/yaml.v3" "gopkg.in/yaml.v3"
@@ -28,7 +29,8 @@ func LoadSession(path string) (*SessionConfig, error) {
// SessionLoadOptions configures session template rendering behavior. // SessionLoadOptions configures session template rendering behavior.
type SessionLoadOptions struct { type SessionLoadOptions struct {
SessionID string SessionID string
PreviousSessionID string
} }
// LoadSessionWithOptions loads session configuration from a YAML file with // LoadSessionWithOptions loads session configuration from a YAML file with
@@ -56,6 +58,16 @@ func LoadSessionWithOptions(path string, opts SessionLoadOptions) (*SessionConfi
strings.TrimSpace(cfg.SessionID), strings.TrimSpace(cfg.SessionID),
) )
} }
if strings.TrimSpace(opts.PreviousSessionID) != "" &&
strings.TrimSpace(cfg.PreviousSessionID) != "" &&
strings.TrimSpace(cfg.PreviousSessionID) != strings.TrimSpace(opts.PreviousSessionID) {
return nil, fmt.Errorf(
"load session config: session file %q: previous_session_id mismatch: --previous-session-id %q does not match rendered previous_session_id %q",
path,
strings.TrimSpace(opts.PreviousSessionID),
strings.TrimSpace(cfg.PreviousSessionID),
)
}
return &cfg, nil return &cfg, nil
} }
@@ -114,24 +126,36 @@ var sessionTemplatePattern = regexp.MustCompile(`\{\{\s*([a-zA-Z_][a-zA-Z0-9_]*)
func renderSessionTemplate(content string, opts SessionLoadOptions) (string, error) { func renderSessionTemplate(content string, opts SessionLoadOptions) (string, error) {
sessionID := strings.TrimSpace(opts.SessionID) sessionID := strings.TrimSpace(opts.SessionID)
previousSessionID := strings.TrimSpace(opts.PreviousSessionID)
rendered := content rendered := content
if sessionID != "" { if sessionID != "" {
rendered = strings.ReplaceAll(rendered, "{{session_id}}", sessionID) rendered = replaceTemplateVariable(rendered, "session_id", sessionID)
rendered = strings.ReplaceAll(rendered, "{{ session_id }}", sessionID) }
if previousSessionID != "" {
rendered = replaceTemplateVariable(rendered, "previous_session_id", previousSessionID)
} }
unresolved := sessionTemplatePattern.FindAllStringSubmatch(rendered, -1) unresolved := sessionTemplatePattern.FindAllStringSubmatch(rendered, -1)
if len(unresolved) > 0 { if len(unresolved) > 0 {
seenVars := map[string]struct{}{}
vars := make([]string, 0, len(unresolved)) vars := make([]string, 0, len(unresolved))
for _, m := range unresolved { for _, m := range unresolved {
if len(m) > 1 { if len(m) > 1 {
vars = append(vars, m[1]) name := m[1]
if _, ok := seenVars[name]; ok {
continue
}
seenVars[name] = struct{}{}
vars = append(vars, name)
} }
} }
sort.Strings(vars)
if len(vars) > 0 { if len(vars) > 0 {
hints := unresolvedTemplateHints(vars)
return "", fmt.Errorf( return "", fmt.Errorf(
"session file template rendering failed: unresolved template variable(s): %s; pass --session-id when using {{ session_id }}", "session file template rendering failed: unresolved template variable(s): %s%s",
strings.Join(vars, ", "), strings.Join(vars, ", "),
hints,
) )
} }
return "", fmt.Errorf("session file template rendering failed: unresolved template placeholders remain") return "", fmt.Errorf("session file template rendering failed: unresolved template placeholders remain")
@@ -140,6 +164,35 @@ func renderSessionTemplate(content string, opts SessionLoadOptions) (string, err
return rendered, nil return rendered, nil
} }
func replaceTemplateVariable(content, name, value string) string {
rendered := strings.ReplaceAll(content, "{{"+name+"}}", value)
rendered = strings.ReplaceAll(rendered, "{{ "+name+" }}", value)
return rendered
}
func unresolvedTemplateHints(vars []string) string {
seen := map[string]struct{}{}
flags := make([]string, 0, 2)
for _, name := range vars {
switch name {
case "session_id":
if _, ok := seen["--session-id"]; !ok {
seen["--session-id"] = struct{}{}
flags = append(flags, "--session-id")
}
case "previous_session_id":
if _, ok := seen["--previous-session-id"]; !ok {
seen["--previous-session-id"] = struct{}{}
flags = append(flags, "--previous-session-id")
}
}
}
if len(flags) == 0 {
return ""
}
return "; pass " + strings.Join(flags, " and ") + " when using those template variable(s)"
}
func shortName(path, fallback string) string { func shortName(path, fallback string) string {
base := filepath.Base(path) base := filepath.Base(path)
if base == "." || base == string(filepath.Separator) { if base == "." || base == string(filepath.Separator) {

View File

@@ -187,6 +187,43 @@ inputs:
`, `,
wantValidate: "session config \"session.yml\" invalid: session.session_id is required", wantValidate: "session config \"session.yml\" invalid: session.session_id is required",
}, },
{
name: "valid previous_session_id passes",
pipelineYAML: `workspace:
root: /tmp/narratio
whisperx:
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
seriatim:
binary: seriatim
`,
sessionYAML: `session_id: 2026-05-03
previous_session_id: 2026-04-26
inputs:
audio_dir: ./audio
speakers_file: ./speakers.yml
autocorrect_file: ./autocorrect.yml
glossary_file: ./glossary.yml
`,
},
{
name: "previous_session_id equal to session_id fails",
pipelineYAML: `workspace:
root: /tmp/narratio
whisperx:
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
seriatim:
binary: seriatim
`,
sessionYAML: `session_id: 2026-05-03
previous_session_id: 2026-05-03
inputs:
audio_dir: ./audio
speakers_file: ./speakers.yml
autocorrect_file: ./autocorrect.yml
glossary_file: ./glossary.yml
`,
wantValidate: "session config \"session.yml\" invalid: session.previous_session_id must not equal session.session_id",
},
{ {
name: "missing transcribe_url fails", name: "missing transcribe_url fails",
pipelineYAML: `workspace: pipelineYAML: `workspace:

View File

@@ -116,6 +116,75 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
output_kind: session_recap output_kind: session_recap
`, `,
}, },
{
name: "canonical previous-session 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.polished
required: true
previous_recap:
source: narratio.previous_session.artifact.session_recap
required: false
vars:
session_id: true
output_kind: session_recap
`,
},
{
name: "canonical previous-session source missing artifact key fails validation",
scriptoriumYAML: `scriptorium:
binary: scriptorium
artifacts:
session_recap:
enabled: true
prompt_id: dnd.session_recap
output_path: artifacts/session_recap.md
inputs:
previous_recap:
source: narratio.previous_session.artifact.
required: false
`,
wantValidateErr: `pipeline.scriptorium.artifacts.session_recap.inputs.previous_recap.source "narratio.previous_session.artifact." must reference configured artifact key matching ^[a-z][a-z0-9_]*$`,
},
{
name: "canonical previous-session source invalid artifact key fails validation",
scriptoriumYAML: `scriptorium:
binary: scriptorium
artifacts:
session_recap:
enabled: true
prompt_id: dnd.session_recap
output_path: artifacts/session_recap.md
inputs:
previous_recap:
source: narratio.previous_session.artifact.session-recap
required: false
`,
wantValidateErr: `pipeline.scriptorium.artifacts.session_recap.inputs.previous_recap.source "narratio.previous_session.artifact.session-recap" must reference configured artifact key matching ^[a-z][a-z0-9_]*$`,
},
{
name: "canonical previous-session source unknown artifact fails validation",
scriptoriumYAML: `scriptorium:
binary: scriptorium
artifacts:
session_recap:
enabled: true
prompt_id: dnd.session_recap
output_path: artifacts/session_recap.md
inputs:
previous_recap:
source: narratio.previous_session.artifact.quest_log
required: false
`,
wantValidateErr: `pipeline.scriptorium.artifacts.session_recap.inputs.previous_recap.source "narratio.previous_session.artifact.quest_log" references unknown artifact "quest_log"`,
},
{ {
name: "canonical artifact source is accepted", name: "canonical artifact source is accepted",
scriptoriumYAML: `scriptorium: scriptoriumYAML: `scriptorium:

View File

@@ -55,6 +55,34 @@ inputs:
} }
} }
func TestLoadSessionWithOptionsRendersPreviousSessionPlaceholder(t *testing.T) {
dir := t.TempDir()
sessionPath := filepath.Join(dir, "session.yml")
sessionYAML := `session_id: "{{ session_id }}"
previous_session_id: "{{ previous_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",
PreviousSessionID: "2026-03-28",
})
if err != nil {
t.Fatalf("LoadSessionWithOptions() error = %v", err)
}
if cfg.PreviousSessionID != "2026-03-28" {
t.Fatalf("PreviousSessionID = %q, want 2026-03-28", cfg.PreviousSessionID)
}
}
func TestLoadSessionWithOptionsUnresolvedPlaceholderFails(t *testing.T) { func TestLoadSessionWithOptionsUnresolvedPlaceholderFails(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
sessionPath := filepath.Join(dir, "session.yml") sessionPath := filepath.Join(dir, "session.yml")
@@ -82,6 +110,37 @@ inputs:
} }
} }
func TestLoadSessionWithOptionsUnresolvedPreviousSessionPlaceholderFails(t *testing.T) {
dir := t.TempDir()
sessionPath := filepath.Join(dir, "session.yml")
sessionYAML := `session_id: 2026-05-03
previous_session_id: "{{ previous_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(), "previous_session_id") {
t.Fatalf("error = %q, want previous_session_id variable", err.Error())
}
if !strings.Contains(err.Error(), "--previous-session-id") {
t.Fatalf("error = %q, want previous-session-id guidance", err.Error())
}
}
func TestLoadSessionWithOptionsMismatchFails(t *testing.T) { func TestLoadSessionWithOptionsMismatchFails(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
sessionPath := filepath.Join(dir, "session.yml") sessionPath := filepath.Join(dir, "session.yml")
@@ -106,6 +165,34 @@ inputs:
} }
} }
func TestLoadSessionWithOptionsPreviousSessionMismatchFails(t *testing.T) {
dir := t.TempDir()
sessionPath := filepath.Join(dir, "session.yml")
sessionYAML := `session_id: 2026-05-03
previous_session_id: 2026-04-26
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: "2026-05-03",
PreviousSessionID: "2026-04-25",
})
if err == nil {
t.Fatal("expected error, got nil")
}
if !strings.Contains(err.Error(), "previous_session_id mismatch") {
t.Fatalf("error = %q, want mismatch context", err.Error())
}
}
func TestLoadSessionWithOptionsUnknownFieldStillRejectedAfterRendering(t *testing.T) { func TestLoadSessionWithOptionsUnknownFieldStillRejectedAfterRendering(t *testing.T) {
dir := t.TempDir() dir := t.TempDir()
sessionPath := filepath.Join(dir, "session.yml") sessionPath := filepath.Join(dir, "session.yml")

View File

@@ -487,8 +487,14 @@ func validateScriptorium(cfg *ScriptoriumConfig) error {
} }
func validateSession(cfg *SessionConfig) error { func validateSession(cfg *SessionConfig) error {
if strings.TrimSpace(cfg.SessionID) == "" { if err := validateSessionIdentifier("session.session_id", cfg.SessionID, true); err != nil {
return fmt.Errorf("session.session_id is required") return err
}
if err := validateSessionIdentifier("session.previous_session_id", cfg.PreviousSessionID, false); err != nil {
return err
}
if strings.TrimSpace(cfg.PreviousSessionID) != "" && strings.TrimSpace(cfg.PreviousSessionID) == strings.TrimSpace(cfg.SessionID) {
return fmt.Errorf("session.previous_session_id must not equal session.session_id")
} }
if strings.TrimSpace(cfg.Campaign) == "" { if strings.TrimSpace(cfg.Campaign) == "" {
return fmt.Errorf("session.campaign is required") return fmt.Errorf("session.campaign is required")
@@ -525,6 +531,16 @@ func validateSession(cfg *SessionConfig) error {
return nil return nil
} }
func validateSessionIdentifier(fieldName, value string, required bool) error {
if strings.TrimSpace(value) == "" {
if required {
return fmt.Errorf("%s is required", fieldName)
}
return nil
}
return nil
}
func validateCrossConfig(pipeline *PipelineConfig, session *SessionConfig) error { func validateCrossConfig(pipeline *PipelineConfig, session *SessionConfig) error {
if pipeline == nil || session == nil { if pipeline == nil || session == nil {
return nil return nil
@@ -563,12 +579,38 @@ var windowsAbsPathRE = regexp.MustCompile(`^[A-Za-z]:[\\/].*`)
var envVarNameRE = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`) var envVarNameRE = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
var scriptoriumArtifactKeyRE = regexp.MustCompile(`^[a-z][a-z0-9_]*$`) var scriptoriumArtifactKeyRE = regexp.MustCompile(`^[a-z][a-z0-9_]*$`)
var narratioArtifactSourceRE = regexp.MustCompile(`^narratio\.artifact\.([a-z][a-z0-9_]*)$`) var narratioArtifactSourceRE = regexp.MustCompile(`^narratio\.artifact\.([a-z][a-z0-9_]*)$`)
var narratioPreviousSessionArtifactSourceRE = regexp.MustCompile(`^narratio\.previous_session\.artifact\.([a-z][a-z0-9_]*)$`)
func validateScriptoriumInputSource(artifactName, inputName, source string, configuredArtifacts map[string]struct{}) (string, error) { func validateScriptoriumInputSource(artifactName, inputName, source string, configuredArtifacts map[string]struct{}) (string, error) {
if isStaticSupportedScriptoriumInputSource(source) { trimmedSource := strings.TrimSpace(source)
if isStaticSupportedScriptoriumInputSource(trimmedSource) {
return "", nil return "", nil
} }
matches := narratioArtifactSourceRE.FindStringSubmatch(source)
if strings.HasPrefix(trimmedSource, "narratio.previous_session.artifact") {
matches := narratioPreviousSessionArtifactSourceRE.FindStringSubmatch(trimmedSource)
if len(matches) != 2 {
return "", fmt.Errorf(
"pipeline.scriptorium.artifacts.%s.inputs.%s.source %q must reference configured artifact key matching ^[a-z][a-z0-9_]*$",
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 "", nil
}
matches := narratioArtifactSourceRE.FindStringSubmatch(trimmedSource)
if len(matches) != 2 { if len(matches) != 2 {
return "", fmt.Errorf( return "", fmt.Errorf(
"pipeline.scriptorium.artifacts.%s.inputs.%s.source %q is unsupported", "pipeline.scriptorium.artifacts.%s.inputs.%s.source %q is unsupported",
@@ -591,7 +633,7 @@ func validateScriptoriumInputSource(artifactName, inputName, source string, conf
} }
func isStaticSupportedScriptoriumInputSource(source string) bool { func isStaticSupportedScriptoriumInputSource(source string) bool {
switch strings.TrimSpace(source) { switch source {
case "previous_session_artifact": case "previous_session_artifact":
return true return true
case "narratio.transcript.merged": case "narratio.transcript.merged":

View File

@@ -631,6 +631,23 @@ func resolveScriptoriumInput(
runtimeCatalog *artifacts.ArtifactCatalog, runtimeCatalog *artifacts.ArtifactCatalog,
) (string, bool, *artifacts.ResolvedSessionArtifact, error) { ) (string, bool, *artifacts.ResolvedSessionArtifact, error) {
source := strings.TrimSpace(inputCfg.Source) source := strings.TrimSpace(inputCfg.Source)
if artifacts.IsPreviousSessionArtifactSource(source) {
resolved, err := artifacts.ResolvePreviousSessionArtifactWithCatalog(paths, m, source, runtimeCatalog)
if err == nil {
copy := resolved
return resolved.Path, true, &copy, nil
}
if errors.Is(err, artifacts.ErrSessionArtifactNotFound) {
if inputCfg.Required {
return "", false, nil, fmt.Errorf(
"required previous-session input source %q is unavailable; run narratio run-stage --force prepare",
source,
)
}
return "", false, nil, nil
}
return "", false, nil, err
}
switch source { switch source {
case "previous_session_artifact": case "previous_session_artifact":
if strings.TrimSpace(inputCfg.Path) == "" { if strings.TrimSpace(inputCfg.Path) == "" {

View File

@@ -10,6 +10,7 @@ import (
"time" "time"
"gitea.maximumdirect.net/eric/narratio/internal/adapters/scriptorium" "gitea.maximumdirect.net/eric/narratio/internal/adapters/scriptorium"
"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts" "gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config" "gitea.maximumdirect.net/eric/narratio/internal/config"
"gitea.maximumdirect.net/eric/narratio/internal/manifest" "gitea.maximumdirect.net/eric/narratio/internal/manifest"
@@ -717,6 +718,146 @@ func TestAnalyzeOmitsOptionalMissingConfiguredArtifactInput(t *testing.T) {
} }
} }
func TestAnalyzeRequiredPreviousSessionArtifactInputGuidesPrepareForce(t *testing.T) {
env, m, _ := setupAnalyzeEnv(t)
sessionRecap := env.Config.Pipeline.Scriptorium.Artifacts["session_recap"]
sessionRecap.Inputs["previous_recap"] = config.ScriptoriumInputConfig{
Source: "narratio.previous_session.artifact.session_recap",
Required: true,
}
env.Config.Pipeline.Scriptorium.Artifacts["session_recap"] = sessionRecap
_, err := (analyzeStage{}).Run(context.Background(), env, m)
if err == nil {
t.Fatal("expected error, got nil")
}
if !strings.Contains(err.Error(), "run narratio run-stage --force prepare") {
t.Fatalf("error = %q, want guidance to run force prepare", err.Error())
}
}
func TestAnalyzeResolvesCanonicalPreviousSessionArtifactFromManifestInput(t *testing.T) {
env, m, fake := setupAnalyzeEnv(t)
paths := sessionPathsForEnv(env, m.SessionID)
writeAnalyzeFile(t, filepath.Join(paths.TranscriptsDir, "trimmed.json"), `{"segments":[]}`)
previousPath := artifacts.SessionPreviousArtifactPath(paths, "artifacts/session_recap.md")
writeAnalyzeFile(t, previousPath, "previous recap\n")
m.Inputs = append(m.Inputs, manifest.InputRecord{
Kind: "previous_artifact",
Path: previousPath,
})
sessionRecap := env.Config.Pipeline.Scriptorium.Artifacts["session_recap"]
sessionRecap.Inputs["previous_recap"] = config.ScriptoriumInputConfig{
Source: "narratio.previous_session.artifact.session_recap",
Required: true,
}
env.Config.Pipeline.Scriptorium.Artifacts["session_recap"] = sessionRecap
_, err := (analyzeStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if len(fake.RunRequests) != 1 {
t.Fatalf("run requests = %d, want 1", len(fake.RunRequests))
}
if got := fake.RunRequests[0].InputPaths["previous_recap"]; got != previousPath {
t.Fatalf("previous_recap input = %q, want %q", got, previousPath)
}
}
func TestAnalyzeOmitsOptionalMissingCanonicalPreviousSessionArtifact(t *testing.T) {
env, m, fake := setupAnalyzeEnv(t)
paths := sessionPathsForEnv(env, m.SessionID)
writeAnalyzeFile(t, filepath.Join(paths.TranscriptsDir, "trimmed.json"), `{"segments":[]}`)
sessionRecap := env.Config.Pipeline.Scriptorium.Artifacts["session_recap"]
sessionRecap.Inputs["previous_recap"] = config.ScriptoriumInputConfig{
Source: "narratio.previous_session.artifact.session_recap",
Required: false,
}
env.Config.Pipeline.Scriptorium.Artifacts["session_recap"] = sessionRecap
_, err := (analyzeStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if len(fake.RunRequests) != 1 {
t.Fatalf("run requests = %d, want 1", len(fake.RunRequests))
}
if _, exists := fake.RunRequests[0].InputPaths["previous_recap"]; exists {
t.Fatalf("optional canonical previous_recap should be omitted when unavailable")
}
}
func TestAnalyzeRenderDebugWithCanonicalPreviousSessionInput(t *testing.T) {
env, m, fake := setupAnalyzeEnv(t)
paths := sessionPathsForEnv(env, m.SessionID)
writeAnalyzeFile(t, filepath.Join(paths.TranscriptsDir, "trimmed.json"), `{"segments":[]}`)
env.Config.Pipeline.Scriptorium.RenderDebug = true
previousPath := artifacts.SessionPreviousArtifactPath(paths, "artifacts/session_recap.md")
writeAnalyzeFile(t, previousPath, "previous recap\n")
m.Inputs = append(m.Inputs, manifest.InputRecord{
Kind: "previous_artifact",
Path: previousPath,
})
sessionRecap := env.Config.Pipeline.Scriptorium.Artifacts["session_recap"]
sessionRecap.Inputs["previous_recap"] = config.ScriptoriumInputConfig{
Source: "narratio.previous_session.artifact.session_recap",
Required: true,
}
env.Config.Pipeline.Scriptorium.Artifacts["session_recap"] = sessionRecap
_, err := (analyzeStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if len(fake.RenderRequests) != 1 || len(fake.RunRequests) != 1 {
t.Fatalf("render/run requests = %d/%d, want 1/1", len(fake.RenderRequests), len(fake.RunRequests))
}
if got := fake.RenderRequests[0].InputPaths["previous_recap"]; got != previousPath {
t.Fatalf("render previous_recap input = %q, want %q", got, previousPath)
}
if got := fake.RunRequests[0].InputPaths["previous_recap"]; got != previousPath {
t.Fatalf("run previous_recap input = %q, want %q", got, previousPath)
}
}
func TestAnalyzeDoesNotCallObjectStoreForCanonicalPreviousSessionInput(t *testing.T) {
env, m, _ := setupAnalyzeEnv(t)
paths := sessionPathsForEnv(env, m.SessionID)
writeAnalyzeFile(t, filepath.Join(paths.TranscriptsDir, "trimmed.json"), `{"segments":[]}`)
previousPath := artifacts.SessionPreviousArtifactPath(paths, "artifacts/session_recap.md")
writeAnalyzeFile(t, previousPath, "previous recap\n")
m.Inputs = append(m.Inputs, manifest.InputRecord{
Kind: "previous_artifact",
Path: previousPath,
})
sessionRecap := env.Config.Pipeline.Scriptorium.Artifacts["session_recap"]
sessionRecap.Inputs["previous_recap"] = config.ScriptoriumInputConfig{
Source: "narratio.previous_session.artifact.session_recap",
Required: true,
}
env.Config.Pipeline.Scriptorium.Artifacts["session_recap"] = sessionRecap
tracker := &analyzeObjectStoreTracker{}
env.ObjectStore = tracker
_, err := (analyzeStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if tracker.called {
t.Fatal("analyze should not call object store for previous-session input resolution")
}
}
func TestAnalyzeFailsWhenOutputPathMissing(t *testing.T) { func TestAnalyzeFailsWhenOutputPathMissing(t *testing.T) {
env, m, fake := setupAnalyzeEnv(t) env, m, fake := setupAnalyzeEnv(t)
paths := sessionPathsForEnv(env, m.SessionID) paths := sessionPathsForEnv(env, m.SessionID)
@@ -1145,3 +1286,27 @@ func mustArtifactEntryList(t *testing.T, metadata map[string]any, key string) []
} }
return out return out
} }
type analyzeObjectStoreTracker struct {
called bool
}
func (s *analyzeObjectStoreTracker) List(context.Context, string) ([]storage.ObjectInfo, error) {
s.called = true
return nil, errors.New("unexpected object store list call")
}
func (s *analyzeObjectStoreTracker) Download(context.Context, string, string) error {
s.called = true
return errors.New("unexpected object store download call")
}
func (s *analyzeObjectStoreTracker) Upload(context.Context, string, string, storage.UploadOptions) (storage.ObjectInfo, error) {
s.called = true
return storage.ObjectInfo{}, errors.New("unexpected object store upload call")
}
func (s *analyzeObjectStoreTracker) Exists(context.Context, string) (bool, error) {
s.called = true
return false, errors.New("unexpected object store exists call")
}

View File

@@ -118,6 +118,10 @@ func (archiveStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*S
return nil, fmt.Errorf("archive: collect run files: %w", err) return nil, fmt.Errorf("archive: collect run files: %w", err)
} }
sessionPaths := archiveSessionPaths(env, m) sessionPaths := archiveSessionPaths(env, m)
previousFiles, err := collectArchivePreviousFiles(sessionPaths.PreviousDir)
if err != nil {
return nil, fmt.Errorf("archive: collect previous files: %w", err)
}
runtimeCatalog, err := buildArchiveRuntimeArtifactCatalog(sessionPaths, env.Config.Pipeline.Scriptorium) runtimeCatalog, err := buildArchiveRuntimeArtifactCatalog(sessionPaths, env.Config.Pipeline.Scriptorium)
if err != nil { if err != nil {
return nil, fmt.Errorf("archive: build runtime artifact catalog: %w", err) return nil, fmt.Errorf("archive: build runtime artifact catalog: %w", err)
@@ -144,6 +148,15 @@ func (archiveStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*S
promotedUploaded = append(promotedUploaded, promotion.Dest) promotedUploaded = append(promotedUploaded, promotion.Dest)
} }
previousUploaded := make([]string, 0, len(previousFiles))
for _, file := range previousFiles {
key := artifacts.S3PromotedArtifactKey(sessionPrefix, file.RelativePath)
if _, err := env.ObjectStore.Upload(ctx, file.LocalPath, key, storage.UploadOptions{}); err != nil {
return nil, fmt.Errorf("archive: upload previous file %q to %q: %w", file.RelativePath, key, err)
}
previousUploaded = append(previousUploaded, file.RelativePath)
}
currentManifestKey, currentRunPointerKey := artifacts.ResolveArchiveCurrentStateKeys(sessionPrefix) currentManifestKey, currentRunPointerKey := artifacts.ResolveArchiveCurrentStateKeys(sessionPrefix)
manifestTempPath, err := writeCurrentManifestSnapshot(m, archiveMetadataPreview( manifestTempPath, err := writeCurrentManifestSnapshot(m, archiveMetadataPreview(
bucket, bucket,
@@ -151,6 +164,7 @@ func (archiveStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*S
sessionPrefix, sessionPrefix,
runUploaded, runUploaded,
promotedUploaded, promotedUploaded,
previousUploaded,
skippedOptional, skippedOptional,
currentManifestKey, currentManifestKey,
)) ))
@@ -187,6 +201,8 @@ func (archiveStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*S
"run_uploaded_paths": runUploaded, "run_uploaded_paths": runUploaded,
"promoted_files_uploaded": len(promotedUploaded), "promoted_files_uploaded": len(promotedUploaded),
"promoted_paths": promotedUploaded, "promoted_paths": promotedUploaded,
"previous_files_uploaded": len(previousUploaded),
"previous_uploaded_paths": previousUploaded,
"skipped_optional_promotions": skippedOptional, "skipped_optional_promotions": skippedOptional,
"current_manifest_key": currentManifestKey, "current_manifest_key": currentManifestKey,
"current_run_id_key": currentRunPointerKey, "current_run_id_key": currentRunPointerKey,
@@ -497,6 +513,51 @@ func collectArchiveRunFiles(runRoot, manifestPath string) ([]archiveUploadFile,
return files, nil return files, nil
} }
func collectArchivePreviousFiles(previousDir string) ([]archiveUploadFile, error) {
previousDir = filepath.Clean(strings.TrimSpace(previousDir))
if previousDir == "" {
return nil, fmt.Errorf("previous directory is required")
}
info, err := os.Stat(previousDir)
if err != nil {
if os.IsNotExist(err) {
return nil, nil
}
return nil, fmt.Errorf("stat %q: %w", previousDir, err)
}
if !info.IsDir() {
return nil, fmt.Errorf("previous path %q is not a directory", previousDir)
}
files := make([]archiveUploadFile, 0, 16)
err = filepath.WalkDir(previousDir, func(path string, d fs.DirEntry, walkErr error) error {
if walkErr != nil {
return walkErr
}
if d.IsDir() {
return nil
}
rel, err := filepath.Rel(previousDir, path)
if err != nil {
return fmt.Errorf("relative path from %q to %q: %w", previousDir, path, err)
}
rel = filepath.ToSlash(rel)
files = append(files, archiveUploadFile{
RelativePath: filepath.ToSlash(filepath.Join(config.PathPreviousDirSegment, rel)),
LocalPath: path,
})
return nil
})
if err != nil {
return nil, fmt.Errorf("walk %q: %w", previousDir, err)
}
sort.Slice(files, func(i, j int) bool {
return files[i].RelativePath < files[j].RelativePath
})
return files, nil
}
func resolveArchiveRunManifestSource(runRoot string) (string, error) { func resolveArchiveRunManifestSource(runRoot string) (string, error) {
path := filepath.Join(filepath.Clean(runRoot), "manifest.json") path := filepath.Join(filepath.Clean(runRoot), "manifest.json")
info, err := os.Stat(path) info, err := os.Stat(path)
@@ -600,6 +661,7 @@ func archiveMetadataPreview(
bucket, runPrefix, sessionPrefix string, bucket, runPrefix, sessionPrefix string,
runUploaded []string, runUploaded []string,
promotedUploaded []string, promotedUploaded []string,
previousUploaded []string,
skippedOptional []string, skippedOptional []string,
currentManifestKey string, currentManifestKey string,
) map[string]any { ) map[string]any {
@@ -612,6 +674,8 @@ func archiveMetadataPreview(
"run_uploaded_paths": append([]string(nil), runUploaded...), "run_uploaded_paths": append([]string(nil), runUploaded...),
"promoted_files_uploaded": len(promotedUploaded), "promoted_files_uploaded": len(promotedUploaded),
"promoted_paths": append([]string(nil), promotedUploaded...), "promoted_paths": append([]string(nil), promotedUploaded...),
"previous_files_uploaded": len(previousUploaded),
"previous_uploaded_paths": append([]string(nil), previousUploaded...),
"skipped_optional_promotions": append([]string(nil), skippedOptional...), "skipped_optional_promotions": append([]string(nil), skippedOptional...),
"current_manifest_key": currentManifestKey, "current_manifest_key": currentManifestKey,
"current_run_id_key": artifacts.S3CurrentRunPointerKey(sessionPrefix), "current_run_id_key": artifacts.S3CurrentRunPointerKey(sessionPrefix),

View File

@@ -130,6 +130,50 @@ func TestArchiveUploadsRunRecordPromotionsAndCurrentPointer(t *testing.T) {
if result.Metadata["promoted_files_uploaded"] != 2 { if result.Metadata["promoted_files_uploaded"] != 2 {
t.Fatalf("metadata promoted_files_uploaded = %#v, want 2", result.Metadata["promoted_files_uploaded"]) t.Fatalf("metadata promoted_files_uploaded = %#v, want 2", result.Metadata["promoted_files_uploaded"])
} }
if result.Metadata["previous_files_uploaded"] != 0 {
t.Fatalf("metadata previous_files_uploaded = %#v, want 0", result.Metadata["previous_files_uploaded"])
}
}
func TestArchiveUploadsPreviousCacheWhenPresent(t *testing.T) {
env, m, _ := archiveFixture(t)
fake := env.ObjectStore.(*storage.FakeBackend)
sessionRoot := artifacts.SessionWorkDirForCampaign(
env.Config.Pipeline.Workspace.Root,
env.Config.Session.Campaign,
env.Config.Session.SessionID,
)
writeStageTestFile(t, filepath.Join(sessionRoot, "previous", "manifest.json"), "{\"session_id\":\"2026-04-12\"}\n")
writeStageTestFile(t, filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md"), "# previous recap\n")
result, err := archiveStage{}.Run(context.Background(), env, m)
if err != nil {
t.Fatalf("Run() error = %v", err)
}
previousManifestKey := m.S3SessionPrefix + "previous/manifest.json"
previousRecapKey := m.S3SessionPrefix + "previous/artifacts/session_recap.md"
if _, ok := fake.Objects[previousManifestKey]; !ok {
t.Fatalf("missing archived previous manifest key %q", previousManifestKey)
}
if _, ok := fake.Objects[previousRecapKey]; !ok {
t.Fatalf("missing archived previous artifact key %q", previousRecapKey)
}
if result.Metadata["previous_files_uploaded"] != 2 {
t.Fatalf("metadata previous_files_uploaded = %#v, want 2", result.Metadata["previous_files_uploaded"])
}
}
func TestArchiveToleratesMissingPreviousCache(t *testing.T) {
env, m, _ := archiveFixture(t)
result, err := archiveStage{}.Run(context.Background(), env, m)
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if result.Metadata["previous_files_uploaded"] != 0 {
t.Fatalf("metadata previous_files_uploaded = %#v, want 0", result.Metadata["previous_files_uploaded"])
}
} }
func TestArchiveUsesCustomPromotionRules(t *testing.T) { func TestArchiveUsesCustomPromotionRules(t *testing.T) {

View File

@@ -145,6 +145,20 @@ func (prepareStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*S
} }
} }
previousRequirements := collectPreparePreviousRequirements(env.Config)
var previousHydration *previousSessionHydrationResult
if len(previousRequirements) > 0 {
if err := clearManagedPreviousState(paths); err != nil {
return nil, fmt.Errorf("prepare: clear previous-session cache: %w", err)
}
hydration, err := hydratePreviousSessionArtifacts(ctx, env, paths, previousRequirements)
if err != nil {
return nil, fmt.Errorf("prepare: hydrate previous-session artifacts: %w", err)
}
previousHydration = hydration
inputs = append(inputs, hydration.Inputs...)
}
sort.Slice(inputs, func(i, j int) bool { sort.Slice(inputs, func(i, j int) bool {
if inputs[i].Kind != inputs[j].Kind { if inputs[i].Kind != inputs[j].Kind {
return inputs[i].Kind < inputs[j].Kind return inputs[i].Kind < inputs[j].Kind
@@ -153,13 +167,27 @@ func (prepareStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*S
}) })
m.Inputs = inputs m.Inputs = inputs
metadata := map[string]any{
"prepared": true,
"stage": "prepare",
"inputs_count": len(inputs),
"audio_files_resolved": countAudioInputs(inputs),
}
if len(previousRequirements) > 0 {
metadata["previous_requirements_count"] = len(previousRequirements)
if previousHydration != nil {
metadata["previous_artifacts_hydrated"] = append([]string(nil), previousHydration.Hydrated...)
metadata["previous_artifacts_hydrated_count"] = len(previousHydration.Hydrated)
metadata["previous_artifacts_missing_optional"] = append([]string(nil), previousHydration.SkippedMissing...)
metadata["previous_artifacts_missing_optional_count"] = len(previousHydration.SkippedMissing)
if strings.TrimSpace(previousHydration.PreviousRunID) != "" {
metadata["previous_session_run_id"] = strings.TrimSpace(previousHydration.PreviousRunID)
}
}
}
return &StageResult{ return &StageResult{
Metadata: map[string]any{ Metadata: metadata,
"prepared": true,
"stage": "prepare",
"inputs_count": len(inputs),
"audio_files_resolved": countAudioInputs(inputs),
},
}, nil }, nil
} }
@@ -354,6 +382,35 @@ func countAudioInputs(inputs []manifest.InputRecord) int {
return count return count
} }
func collectPreparePreviousRequirements(cfg *config.Config) []artifacts.PreviousArtifactRequirement {
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Scriptorium == nil {
return nil
}
return artifacts.CollectPreviousArtifactRequirements(cfg.Pipeline.Scriptorium.Artifacts)
}
func clearManagedPreviousState(paths artifacts.SessionPaths) error {
previousDir := filepath.Clean(paths.PreviousDir)
sessionRoot := filepath.Clean(paths.Root)
if strings.TrimSpace(previousDir) == "" || strings.TrimSpace(sessionRoot) == "" {
return fmt.Errorf("previous/session root paths are required")
}
if previousDir == sessionRoot {
return fmt.Errorf("refusing to clear session root as previous cache: %q", previousDir)
}
prefix := sessionRoot + string(filepath.Separator)
if !strings.HasPrefix(previousDir, prefix) {
return fmt.Errorf("refusing to clear path outside session root: %q", previousDir)
}
if filepath.Base(previousDir) != config.PathPreviousDirSegment {
return fmt.Errorf("refusing to clear non-previous path %q", previousDir)
}
if err := os.RemoveAll(previousDir); err != nil {
return err
}
return os.MkdirAll(previousDir, 0o755)
}
func pathsWorkDirForManifest(env *Env, m *manifest.Manifest, sessionID string) string { func pathsWorkDirForManifest(env *Env, m *manifest.Manifest, sessionID string) string {
if env == nil || env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil { if env == nil || env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil {
return "" return ""

View File

@@ -0,0 +1,475 @@
package stage
import (
"context"
"fmt"
"os"
"path"
"path/filepath"
"sort"
"strings"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config"
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
)
const (
preparePreviousInputKindManifest = "previous_manifest"
preparePreviousInputKindArtifact = "previous_artifact"
preparePreviousInputSource = "previous_session_archive.current"
)
// previousSessionHydrationResult captures prepare-time previous-session cache materialization.
type previousSessionHydrationResult struct {
Inputs []manifest.InputRecord
Hydrated []string
SkippedMissing []string
PreviousRunID string
}
func hydratePreviousSessionArtifacts(
ctx context.Context,
env *Env,
paths artifacts.SessionPaths,
requirements []artifacts.PreviousArtifactRequirement,
) (*previousSessionHydrationResult, error) {
if len(requirements) == 0 {
return &previousSessionHydrationResult{}, nil
}
if env == nil || env.Config == nil || env.Config.Session == nil || env.Config.Pipeline == nil {
return nil, fmt.Errorf("resolved config with session/pipeline is required")
}
if env.ArtifactStore == nil {
return nil, fmt.Errorf("artifact store is required")
}
orderedRequirements := append([]artifacts.PreviousArtifactRequirement(nil), requirements...)
sort.Slice(orderedRequirements, func(i, j int) bool {
return orderedRequirements[i].Name < orderedRequirements[j].Name
})
requiredNames := requiredPreviousArtifactNames(orderedRequirements)
optionalNames := optionalPreviousArtifactNames(orderedRequirements)
previousSessionID := strings.TrimSpace(env.Config.Session.PreviousSessionID)
if previousSessionID == "" {
if len(requiredNames) > 0 {
return nil, fmt.Errorf(
"previous_session_id is required for required previous-session artifacts: %s",
strings.Join(requiredNames, ", "),
)
}
return &previousSessionHydrationResult{SkippedMissing: optionalNames}, nil
}
if env.ObjectStore == nil {
return nil, fmt.Errorf("previous-session artifact hydration requires object store backend")
}
if env.Config.Pipeline.Storage.S3 == nil {
return nil, fmt.Errorf("pipeline.storage.s3 configuration is required for previous-session artifact hydration")
}
campaign := strings.TrimSpace(env.Config.Session.Campaign)
if campaign == "" {
return nil, fmt.Errorf("session campaign is required for previous-session artifact hydration")
}
bucket := strings.TrimSpace(env.Config.Pipeline.Storage.S3.Bucket)
if bucket == "" {
return nil, fmt.Errorf("pipeline.storage.s3.bucket is required for previous-session artifact hydration")
}
previousSessionPrefix := artifacts.S3SessionPrefix(
env.Config.Pipeline.Storage.S3.RootPrefix,
campaign,
previousSessionID,
)
currentManifestKey, currentRunIDKey := artifacts.ResolveArchiveCurrentStateKeys(previousSessionPrefix)
result := &previousSessionHydrationResult{}
runPointerExists, err := env.ObjectStore.Exists(ctx, currentRunIDKey)
if err != nil {
return nil, fmt.Errorf("check previous-session current run pointer %q: %w", currentRunIDKey, err)
}
if !runPointerExists {
if len(requiredNames) > 0 {
return nil, fmt.Errorf("required previous-session artifacts unavailable: remote current run pointer missing: %q", currentRunIDKey)
}
result.SkippedMissing = optionalNames
return result, nil
}
runIDTemp, err := downloadObjectToTempStage(ctx, env.ObjectStore, currentRunIDKey, "narratio-prepare-previous-run-id-*.txt")
if err != nil {
return nil, fmt.Errorf("download previous-session current run pointer %q: %w", currentRunIDKey, err)
}
defer func() { _ = os.Remove(runIDTemp) }()
runIDBytes, err := os.ReadFile(runIDTemp)
if err != nil {
return nil, fmt.Errorf("read previous-session current run pointer %q: %w", currentRunIDKey, err)
}
previousRunID := strings.TrimSpace(string(runIDBytes))
if previousRunID == "" {
return nil, fmt.Errorf("previous-session current run pointer %q is empty", currentRunIDKey)
}
result.PreviousRunID = previousRunID
manifestExists, err := env.ObjectStore.Exists(ctx, currentManifestKey)
if err != nil {
return nil, fmt.Errorf("check previous-session current manifest %q: %w", currentManifestKey, err)
}
if !manifestExists {
if len(requiredNames) > 0 {
return nil, fmt.Errorf("required previous-session artifacts unavailable: remote current manifest missing: %q", currentManifestKey)
}
result.SkippedMissing = optionalNames
return result, nil
}
if err := os.MkdirAll(filepath.Dir(paths.PreviousManifestPath), 0o755); err != nil {
return nil, fmt.Errorf("create previous manifest directory: %w", err)
}
if err := env.ObjectStore.Download(ctx, currentManifestKey, paths.PreviousManifestPath); err != nil {
return nil, fmt.Errorf("download previous-session current manifest %q: %w", currentManifestKey, err)
}
manifestStore := &manifest.LocalStore{}
previousManifest, err := manifestStore.Load(ctx, paths.PreviousManifestPath)
if err != nil {
return nil, fmt.Errorf("decode downloaded previous-session manifest %q: %w", currentManifestKey, err)
}
if strings.TrimSpace(previousManifest.SessionID) != previousSessionID {
return nil, fmt.Errorf(
"previous-session manifest session_id %q does not match configured previous_session_id %q",
strings.TrimSpace(previousManifest.SessionID),
previousSessionID,
)
}
if strings.TrimSpace(previousManifest.Campaign) != campaign {
return nil, fmt.Errorf(
"previous-session manifest campaign %q does not match current campaign %q",
strings.TrimSpace(previousManifest.Campaign),
campaign,
)
}
if strings.TrimSpace(previousManifest.RunID) == "" {
return nil, fmt.Errorf("previous-session manifest run_id is required")
}
if strings.TrimSpace(previousManifest.RunID) != previousRunID {
return nil, fmt.Errorf(
"previous-session current run pointer %q references run %q but current manifest run_id is %q",
currentRunIDKey,
previousRunID,
strings.TrimSpace(previousManifest.RunID),
)
}
manifestChecksum, err := env.ArtifactStore.Checksum(paths.PreviousManifestPath)
if err != nil {
return nil, fmt.Errorf("checksum downloaded previous-session manifest: %w", err)
}
result.Inputs = append(result.Inputs, manifest.InputRecord{
Kind: preparePreviousInputKindManifest,
Path: paths.PreviousManifestPath,
Checksum: manifestChecksum,
Source: preparePreviousInputSource,
S3Bucket: bucket,
S3Key: currentManifestKey,
})
for _, requirement := range orderedRequirements {
candidates := previousArtifactRelativePathCandidates(requirement.Name, previousManifest, env.Config)
if len(candidates) == 0 {
if requirement.Required {
return nil, fmt.Errorf(
"required previous-session artifact %q is unavailable in previous-session manifest/archive",
requirement.Name,
)
}
result.SkippedMissing = append(result.SkippedMissing, requirement.Name)
continue
}
selectedRel := ""
selectedKey := ""
for _, candidate := range candidates {
remoteKey := artifacts.S3PromotedArtifactKey(previousSessionPrefix, candidate)
exists, err := env.ObjectStore.Exists(ctx, remoteKey)
if err != nil {
return nil, fmt.Errorf("check previous-session artifact object %q: %w", remoteKey, err)
}
if !exists {
continue
}
selectedRel = candidate
selectedKey = remoteKey
break
}
if selectedRel == "" {
if requirement.Required {
return nil, fmt.Errorf(
"required previous-session artifact %q object missing from archive candidate keys",
requirement.Name,
)
}
result.SkippedMissing = append(result.SkippedMissing, requirement.Name)
continue
}
localPath := artifacts.SessionPreviousArtifactPath(paths, selectedRel)
if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
return nil, fmt.Errorf("create previous-session artifact directory for %q: %w", localPath, err)
}
if err := env.ObjectStore.Download(ctx, selectedKey, localPath); err != nil {
return nil, fmt.Errorf("download previous-session artifact %q from %q: %w", requirement.Name, selectedKey, err)
}
if err := requireNonEmptyFile(localPath, "previous-session artifact "+requirement.Name); err != nil {
return nil, err
}
checksum, err := env.ArtifactStore.Checksum(localPath)
if err != nil {
return nil, fmt.Errorf("checksum previous-session artifact %q: %w", requirement.Name, err)
}
result.Inputs = append(result.Inputs, manifest.InputRecord{
Kind: preparePreviousInputKindArtifact,
Path: localPath,
Checksum: checksum,
Source: preparePreviousInputSource,
S3Bucket: bucket,
S3Key: selectedKey,
})
result.Hydrated = append(result.Hydrated, requirement.Name)
}
sort.Strings(result.Hydrated)
sort.Strings(result.SkippedMissing)
sort.Slice(result.Inputs, func(i, j int) bool {
if result.Inputs[i].Kind != result.Inputs[j].Kind {
return result.Inputs[i].Kind < result.Inputs[j].Kind
}
return result.Inputs[i].Path < result.Inputs[j].Path
})
return result, nil
}
func requiredPreviousArtifactNames(requirements []artifacts.PreviousArtifactRequirement) []string {
names := make([]string, 0, len(requirements))
for _, requirement := range requirements {
if requirement.Required {
names = append(names, strings.TrimSpace(requirement.Name))
}
}
sort.Strings(names)
return names
}
func optionalPreviousArtifactNames(requirements []artifacts.PreviousArtifactRequirement) []string {
names := make([]string, 0, len(requirements))
for _, requirement := range requirements {
if requirement.Required {
continue
}
names = append(names, strings.TrimSpace(requirement.Name))
}
sort.Strings(names)
return names
}
func previousArtifactRelativePathCandidates(
artifactName string,
previousManifest *manifest.Manifest,
cfg *config.Config,
) []string {
candidates := []string{}
appendCandidate := func(v string) {
normalized, err := normalizeArchiveRelativePath(v)
if err != nil {
return
}
candidates = append(candidates, normalized)
}
sourceID := artifacts.ConfiguredArtifactSourceID(artifactName)
if rel, ok := previousManifestArtifactRelativePathBySourceID(previousManifest, sourceID); ok {
appendCandidate(rel)
base := path.Base(rel)
for _, promoted := range previousManifestPromotedPaths(previousManifest) {
if path.Base(promoted) == base {
appendCandidate(promoted)
}
}
}
if cfg != nil && cfg.Pipeline != nil && cfg.Pipeline.Scriptorium != nil {
if artifactCfg, ok := cfg.Pipeline.Scriptorium.Artifacts[artifactName]; ok {
appendCandidate(artifactCfg.OutputPath)
}
}
return dedupeOrderedStrings(candidates)
}
func previousManifestArtifactRelativePathBySourceID(previousManifest *manifest.Manifest, sourceID string) (string, bool) {
if previousManifest == nil || len(previousManifest.Stages) == 0 {
return "", false
}
sourceID = strings.TrimSpace(sourceID)
if sourceID == "" {
return "", false
}
stageNames := make([]string, 0, len(previousManifest.Stages))
if _, ok := previousManifest.Stages["analyze"]; ok {
stageNames = append(stageNames, "analyze")
}
for stageName := range previousManifest.Stages {
if stageName == "analyze" {
continue
}
stageNames = append(stageNames, stageName)
}
start := 0
if len(stageNames) > 0 && stageNames[0] == "analyze" {
start = 1
}
sort.Strings(stageNames[start:])
for _, stageName := range stageNames {
sr := previousManifest.Stages[stageName]
if sr == nil {
continue
}
for _, out := range sr.Outputs {
if strings.TrimSpace(out.SourceID) != sourceID {
continue
}
rel, ok := derivePreviousManifestRelativePath(previousManifest, out.LocalPath)
if ok {
return rel, true
}
}
}
return "", false
}
func derivePreviousManifestRelativePath(previousManifest *manifest.Manifest, localPath string) (string, bool) {
trimmed := strings.TrimSpace(localPath)
if trimmed == "" {
return "", false
}
if !filepath.IsAbs(trimmed) {
normalized, err := normalizeArchiveRelativePath(filepath.ToSlash(trimmed))
if err != nil {
return "", false
}
return normalized, true
}
sessionRoot, ok := previousManifestSessionRoot(previousManifest)
if !ok {
return "", false
}
rel, err := filepath.Rel(sessionRoot, trimmed)
if err != nil {
return "", false
}
normalized, err := normalizeArchiveRelativePath(filepath.ToSlash(rel))
if err != nil {
return "", false
}
return normalized, true
}
func previousManifestSessionRoot(previousManifest *manifest.Manifest) (string, bool) {
if previousManifest == nil {
return "", false
}
runRoot := filepath.Clean(strings.TrimSpace(previousManifest.LocalWorkDir))
runID := strings.TrimSpace(previousManifest.RunID)
if runRoot == "" || runID == "" {
return "", false
}
if filepath.Base(runRoot) != runID {
return "", false
}
runsDir := filepath.Dir(runRoot)
if filepath.Base(runsDir) != config.PathRunsDirSegment {
return "", false
}
return filepath.Dir(runsDir), true
}
func previousManifestPromotedPaths(previousManifest *manifest.Manifest) []string {
if previousManifest == nil || len(previousManifest.Stages) == 0 {
return nil
}
sr := previousManifest.Stages["archive"]
if sr == nil || sr.Metadata == nil {
return nil
}
raw, ok := sr.Metadata["promoted_paths"]
if !ok {
return nil
}
values, ok := raw.([]any)
if !ok {
return nil
}
out := make([]string, 0, len(values))
for _, value := range values {
asString, ok := value.(string)
if !ok {
continue
}
normalized, err := normalizeArchiveRelativePath(asString)
if err != nil {
continue
}
out = append(out, normalized)
}
return dedupeOrderedStrings(out)
}
func dedupeOrderedStrings(values []string) []string {
if len(values) == 0 {
return nil
}
seen := map[string]struct{}{}
out := make([]string, 0, len(values))
for _, value := range values {
trimmed := strings.TrimSpace(value)
if trimmed == "" {
continue
}
if _, ok := seen[trimmed]; ok {
continue
}
seen[trimmed] = struct{}{}
out = append(out, trimmed)
}
return out
}
func downloadObjectToTempStage(
ctx context.Context,
store interface {
Download(context.Context, string, string) error
},
key, pattern string,
) (string, error) {
tmp, err := os.CreateTemp("", pattern)
if err != nil {
return "", fmt.Errorf("create temp file: %w", err)
}
path := tmp.Name()
if err := tmp.Close(); err != nil {
_ = os.Remove(path)
return "", fmt.Errorf("close temp file: %w", err)
}
if err := store.Download(ctx, key, path); err != nil {
_ = os.Remove(path)
return "", err
}
return path, nil
}

View File

@@ -0,0 +1,415 @@
package stage
import (
"context"
"encoding/json"
"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"
)
func TestHydratePreviousSessionArtifactsDownloadsManifestAndRequiredArtifact(t *testing.T) {
env, sessionPaths, fake := previousHydrationFixture(t)
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: true},
}
seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeArtifactObject: true,
artifactBody: "# previous recap\n",
})
result, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err != nil {
t.Fatalf("hydratePreviousSessionArtifacts() error = %v", err)
}
if result == nil {
t.Fatal("result is nil")
}
if len(result.Inputs) != 2 {
t.Fatalf("inputs len = %d, want 2", len(result.Inputs))
}
if !containsString(result.Hydrated, "session_recap") {
t.Fatalf("hydrated = %#v, want session_recap", result.Hydrated)
}
if len(result.SkippedMissing) != 0 {
t.Fatalf("skipped missing = %#v, want none", result.SkippedMissing)
}
if _, err := os.Stat(sessionPaths.PreviousManifestPath); err != nil {
t.Fatalf("previous manifest missing: %v", err)
}
recapPath := artifacts.SessionPreviousArtifactPath(sessionPaths, "artifacts/session_recap.md")
if _, err := os.Stat(recapPath); err != nil {
t.Fatalf("previous artifact missing: %v", err)
}
manifestInput := findInputByKind(result.Inputs, preparePreviousInputKindManifest)
if manifestInput == nil {
t.Fatalf("missing input kind %q", preparePreviousInputKindManifest)
}
if manifestInput.Source != preparePreviousInputSource {
t.Fatalf("manifest input source = %q, want %q", manifestInput.Source, preparePreviousInputSource)
}
artifactInput := findInputByKind(result.Inputs, preparePreviousInputKindArtifact)
if artifactInput == nil {
t.Fatalf("missing input kind %q", preparePreviousInputKindArtifact)
}
if artifactInput.Source != preparePreviousInputSource {
t.Fatalf("artifact input source = %q, want %q", artifactInput.Source, preparePreviousInputSource)
}
if artifactInput.Path != recapPath {
t.Fatalf("artifact input path = %q, want %q", artifactInput.Path, recapPath)
}
}
func TestHydratePreviousSessionArtifactsSkipsMissingOptionalArtifact(t *testing.T) {
env, sessionPaths, fake := previousHydrationFixture(t)
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: false},
}
seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeManifestObject: true,
includeArtifactObject: false,
})
result, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err != nil {
t.Fatalf("hydratePreviousSessionArtifacts() error = %v", err)
}
if result == nil {
t.Fatal("result is nil")
}
if !containsString(result.SkippedMissing, "session_recap") {
t.Fatalf("skipped missing = %#v, want session_recap", result.SkippedMissing)
}
if len(result.Hydrated) != 0 {
t.Fatalf("hydrated = %#v, want none", result.Hydrated)
}
manifestInput := findInputByKind(result.Inputs, preparePreviousInputKindManifest)
if manifestInput == nil {
t.Fatalf("missing input kind %q", preparePreviousInputKindManifest)
}
if findInputByKind(result.Inputs, preparePreviousInputKindArtifact) != nil {
t.Fatalf("unexpected %q input for missing optional artifact", preparePreviousInputKindArtifact)
}
}
func TestHydratePreviousSessionArtifactsFailsMissingRequiredArtifact(t *testing.T) {
env, sessionPaths, fake := previousHydrationFixture(t)
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: true},
}
seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeArtifactObject: false,
})
_, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err == nil || !strings.Contains(err.Error(), "required previous-session artifact") {
t.Fatalf("error = %v, want required artifact failure", err)
}
}
func TestHydratePreviousSessionArtifactsFailsRequiredWhenPreviousSessionIDUnset(t *testing.T) {
env, sessionPaths, _ := previousHydrationFixture(t)
env.Config.Session.PreviousSessionID = ""
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: true},
}
_, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err == nil || !strings.Contains(err.Error(), "previous_session_id is required") {
t.Fatalf("error = %v, want previous_session_id required failure", err)
}
}
func TestHydratePreviousSessionArtifactsOptionalWithNoPreviousSessionID(t *testing.T) {
env, sessionPaths, _ := previousHydrationFixture(t)
env.Config.Session.PreviousSessionID = ""
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: false},
}
result, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err != nil {
t.Fatalf("hydratePreviousSessionArtifacts() error = %v", err)
}
if result == nil {
t.Fatal("result is nil")
}
if len(result.Inputs) != 0 {
t.Fatalf("inputs len = %d, want 0", len(result.Inputs))
}
if !containsString(result.SkippedMissing, "session_recap") {
t.Fatalf("skipped missing = %#v, want session_recap", result.SkippedMissing)
}
if _, err := os.Stat(sessionPaths.PreviousManifestPath); !os.IsNotExist(err) {
t.Fatalf("previous manifest should not be created, stat err = %v", err)
}
}
func TestHydratePreviousSessionArtifactsRespectsCurrentCommitMarker(t *testing.T) {
env, sessionPaths, fake := previousHydrationFixture(t)
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: true},
}
seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: false,
includeArtifactObject: true,
artifactBody: "# previous recap\n",
})
_, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err == nil || !strings.Contains(err.Error(), "remote current run pointer missing") {
t.Fatalf("error = %v, want current run pointer missing failure", err)
}
}
func TestHydratePreviousSessionArtifactsDoesNotUseLocalPreviousWorkspaceState(t *testing.T) {
env, sessionPaths, fake := previousHydrationFixture(t)
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: true},
}
seed := seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeManifestObject: true,
includeArtifactObject: false,
})
// Write a local previous-session workspace file that should be ignored.
writeFile(t, filepath.Join(seed.PreviousSessionRoot, "artifacts", "session_recap.md"), "# local stale recap\n")
_, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err == nil || !strings.Contains(err.Error(), "object missing from archive") {
t.Fatalf("error = %v, want remote-object-missing failure", err)
}
}
func TestHydratePreviousSessionArtifactsUsesExplicitStorageKeys(t *testing.T) {
env, sessionPaths, fake := previousHydrationFixture(t)
requirements := []artifacts.PreviousArtifactRequirement{
{Name: "session_recap", Required: true},
}
seed := seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeArtifactObject: true,
artifactBody: "# previous recap\n",
})
capture := &preparePreviousCaptureStore{delegate: fake}
env.ObjectStore = capture
_, err := hydratePreviousSessionArtifacts(context.Background(), env, sessionPaths, requirements)
if err != nil {
t.Fatalf("hydratePreviousSessionArtifacts() error = %v", err)
}
if !containsString(capture.existsKeys, seed.RunPointerKey) {
t.Fatalf("exists keys = %#v, want %q", capture.existsKeys, seed.RunPointerKey)
}
if !containsString(capture.existsKeys, seed.ManifestKey) {
t.Fatalf("exists keys = %#v, want %q", capture.existsKeys, seed.ManifestKey)
}
if !containsString(capture.existsKeys, seed.ArtifactKey) {
t.Fatalf("exists keys = %#v, want %q", capture.existsKeys, seed.ArtifactKey)
}
if !containsString(capture.downloadKeys, seed.RunPointerKey) {
t.Fatalf("download keys = %#v, want %q", capture.downloadKeys, seed.RunPointerKey)
}
if !containsString(capture.downloadKeys, seed.ManifestKey) {
t.Fatalf("download keys = %#v, want %q", capture.downloadKeys, seed.ManifestKey)
}
if !containsString(capture.downloadKeys, seed.ArtifactKey) {
t.Fatalf("download keys = %#v, want %q", capture.downloadKeys, seed.ArtifactKey)
}
}
type previousStateSeedResult struct {
PreviousSessionPrefix string
PreviousSessionRoot string
ManifestKey string
RunPointerKey string
ArtifactKey string
}
type previousStateSeedOptions struct {
includeRunPointerObject bool
includeManifestObject bool
includeArtifactObject bool
artifactBody string
}
func seedPreviousCurrentState(
t *testing.T,
env *Env,
fake *storage.FakeBackend,
options previousStateSeedOptions,
) previousStateSeedResult {
t.Helper()
if !options.includeRunPointerObject && !options.includeManifestObject && !options.includeArtifactObject {
// Keep default behavior deterministic when caller omits explicit flags.
options.includeRunPointerObject = true
options.includeManifestObject = true
}
if options.includeManifestObject == false && options.includeArtifactObject {
options.includeManifestObject = true
}
previousSessionID := strings.TrimSpace(env.Config.Session.PreviousSessionID)
campaign := strings.TrimSpace(env.Config.Session.Campaign)
rootPrefix := strings.TrimSpace(env.Config.Pipeline.Storage.S3.RootPrefix)
previousSessionPrefix := artifacts.S3SessionPrefix(rootPrefix, campaign, previousSessionID)
manifestKey, runPointerKey := artifacts.ResolveArchiveCurrentStateKeys(previousSessionPrefix)
previousRunID := "20260510T010203Z-a1b2c3d4"
previousSessionRoot := filepath.Join(t.TempDir(), "work", campaign, previousSessionID)
artifactLocalPath := filepath.Join(previousSessionRoot, "artifacts", "session_recap.md")
previousManifest := buildPreviousManifestForSeed(
t,
previousSessionID,
campaign,
previousRunID,
filepath.Join(previousSessionRoot, "runs", previousRunID),
artifactLocalPath,
)
if options.includeRunPointerObject || (!options.includeRunPointerObject && !options.includeManifestObject && !options.includeArtifactObject) {
fake.SeedObject(storage.FakeObject{
Key: runPointerKey,
Data: []byte(previousRunID + "\n"),
})
}
if options.includeManifestObject || options.includeArtifactObject {
fake.SeedObject(storage.FakeObject{
Key: manifestKey,
Data: previousManifest,
})
}
artifactKey := artifacts.S3PromotedArtifactKey(previousSessionPrefix, "artifacts/session_recap.md")
if options.includeArtifactObject {
body := options.artifactBody
if body == "" {
body = "# previous recap\n"
}
fake.SeedObject(storage.FakeObject{
Key: artifactKey,
Data: []byte(body),
})
}
return previousStateSeedResult{
PreviousSessionPrefix: previousSessionPrefix,
PreviousSessionRoot: previousSessionRoot,
ManifestKey: manifestKey,
RunPointerKey: runPointerKey,
ArtifactKey: artifactKey,
}
}
func previousHydrationFixture(t *testing.T) (*Env, artifacts.SessionPaths, *storage.FakeBackend) {
t.Helper()
env, m := setupPrepareEnv(t)
env.Config.Session.Campaign = "forsaken"
env.Config.Session.PreviousSessionID = "2026-05-10"
env.Config.Pipeline.Storage.S3 = &config.StorageS3Config{
Bucket: "my-dnd-archive",
RootPrefix: "dnd",
}
env.Config.Pipeline.Scriptorium = &config.ScriptoriumConfig{
Artifacts: map[string]config.ScriptoriumArtifactConfig{
"session_recap": {
Enabled: true,
OutputPath: "artifacts/session_recap.md",
},
},
}
fake := &storage.FakeBackend{}
env.ObjectStore = fake
paths, err := ensureLayoutForEnv(env, m.SessionID)
if err != nil {
t.Fatalf("ensureLayoutForEnv() error = %v", err)
}
return env, paths, fake
}
func buildPreviousManifestForSeed(
t *testing.T,
sessionID, campaign, runID, runRoot, artifactPath string,
) []byte {
t.Helper()
now := time.Date(2026, 5, 19, 22, 0, 0, 0, time.UTC)
m := manifest.New(sessionID, now)
m.Campaign = campaign
m.RunID = runID
m.LocalWorkDir = runRoot
m.MarkStageSucceeded("analyze", now, []manifest.ArtifactRecord{
{
Kind: "scriptorium_artifact",
SourceID: artifacts.ConfiguredArtifactSourceID("session_recap"),
LocalPath: artifactPath,
},
})
m.MarkStageSucceeded("archive", now, nil)
m.Stages["archive"].Metadata = map[string]any{
"promoted_paths": []string{"artifacts/session_recap.md"},
}
data, err := json.MarshalIndent(m, "", " ")
if err != nil {
t.Fatalf("marshal manifest: %v", err)
}
return append(data, '\n')
}
type preparePreviousCaptureStore struct {
delegate storage.ObjectStore
existsKeys []string
downloadKeys []string
}
func (s *preparePreviousCaptureStore) List(ctx context.Context, prefix string) ([]storage.ObjectInfo, error) {
return s.delegate.List(ctx, prefix)
}
func (s *preparePreviousCaptureStore) Download(ctx context.Context, key, localPath string) error {
s.downloadKeys = append(s.downloadKeys, key)
return s.delegate.Download(ctx, key, localPath)
}
func (s *preparePreviousCaptureStore) Upload(ctx context.Context, localPath, key string, opts storage.UploadOptions) (storage.ObjectInfo, error) {
return s.delegate.Upload(ctx, localPath, key, opts)
}
func (s *preparePreviousCaptureStore) Exists(ctx context.Context, key string) (bool, error) {
s.existsKeys = append(s.existsKeys, key)
return s.delegate.Exists(ctx, key)
}
func findInputByKind(inputs []manifest.InputRecord, kind string) *manifest.InputRecord {
for i := range inputs {
if inputs[i].Kind == kind {
return &inputs[i]
}
}
return nil
}
func containsString(values []string, target string) bool {
for _, value := range values {
if value == target {
return true
}
}
return false
}

View File

@@ -284,6 +284,188 @@ func TestPrepareStageAudioSourceConflictFails(t *testing.T) {
} }
} }
func TestPrepareStageWithoutPreviousRequirementsDoesNotTouchPreviousState(t *testing.T) {
env, m := setupPrepareEnv(t)
root := filepath.Dir(env.Config.SessionPath)
writeFile(t, filepath.Join(root, "audio", "a.flac"), "a")
env.Config.Session.Inputs.AudioFiles = []string{"./audio/a.flac"}
paths := sessionPathsForEnv(env, m.SessionID)
stalePath := filepath.Join(paths.PreviousDir, "stale.txt")
writeFile(t, stalePath, "stale")
_, err := (prepareStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("prepare.Run() error = %v", err)
}
if _, err := os.Stat(stalePath); err != nil {
t.Fatalf("expected previous stale file to remain untouched: %v", err)
}
}
func TestPrepareStageOptionalPreviousArtifactWithoutPreviousSessionIDSucceeds(t *testing.T) {
env, m := setupPrepareEnv(t)
root := filepath.Dir(env.Config.SessionPath)
writeFile(t, filepath.Join(root, "audio", "a.flac"), "a")
env.Config.Session.Inputs.AudioFiles = []string{"./audio/a.flac"}
configurePreparePreviousArtifactSource(env, false)
env.Config.Session.PreviousSessionID = ""
paths := sessionPathsForEnv(env, m.SessionID)
writeFile(t, filepath.Join(paths.PreviousArtifactsDir, "stale.txt"), "stale")
result, err := (prepareStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("prepare.Run() error = %v", err)
}
if result.Metadata["previous_requirements_count"] != 1 {
t.Fatalf("metadata previous_requirements_count = %#v, want 1", result.Metadata["previous_requirements_count"])
}
if result.Metadata["previous_artifacts_hydrated_count"] != 0 {
t.Fatalf("metadata previous_artifacts_hydrated_count = %#v, want 0", result.Metadata["previous_artifacts_hydrated_count"])
}
if result.Metadata["previous_artifacts_missing_optional_count"] != 1 {
t.Fatalf("metadata previous_artifacts_missing_optional_count = %#v, want 1", result.Metadata["previous_artifacts_missing_optional_count"])
}
if _, err := os.Stat(filepath.Join(paths.PreviousArtifactsDir, "stale.txt")); !os.IsNotExist(err) {
t.Fatalf("expected stale previous state to be cleared, stat err = %v", err)
}
for _, in := range m.Inputs {
if in.Kind == preparePreviousInputKindManifest || in.Kind == preparePreviousInputKindArtifact {
t.Fatalf("unexpected previous input record: %#v", in)
}
}
}
func TestPrepareStageRequiredPreviousArtifactWithoutPreviousSessionIDFails(t *testing.T) {
env, m := setupPrepareEnv(t)
root := filepath.Dir(env.Config.SessionPath)
writeFile(t, filepath.Join(root, "audio", "a.flac"), "a")
env.Config.Session.Inputs.AudioFiles = []string{"./audio/a.flac"}
configurePreparePreviousArtifactSource(env, true)
env.Config.Session.PreviousSessionID = ""
_, err := (prepareStage{}).Run(context.Background(), env, m)
if err == nil || !strings.Contains(err.Error(), "previous_session_id is required") {
t.Fatalf("error = %v, want previous_session_id required failure", err)
}
}
func TestPrepareStageHydratesRequiredPreviousArtifactAndRecordsInputs(t *testing.T) {
env, m := setupPrepareEnv(t)
root := filepath.Dir(env.Config.SessionPath)
writeFile(t, filepath.Join(root, "audio", "a.flac"), "a")
env.Config.Session.Inputs.AudioFiles = []string{"./audio/a.flac"}
env.Config.Session.Campaign = "forsaken"
env.Config.Session.PreviousSessionID = "2026-05-10"
env.Config.Pipeline.Storage.S3 = &config.StorageS3Config{Bucket: "my-dnd-archive", RootPrefix: "dnd"}
configurePreparePreviousArtifactSource(env, true)
fake := &storage.FakeBackend{}
env.ObjectStore = fake
seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeArtifactObject: true,
artifactBody: "# prior recap\n",
})
paths := sessionPathsForEnv(env, m.SessionID)
result, err := (prepareStage{}).Run(context.Background(), env, m)
if err != nil {
t.Fatalf("prepare.Run() error = %v", err)
}
if _, err := os.Stat(paths.PreviousManifestPath); err != nil {
t.Fatalf("expected previous manifest: %v", err)
}
recapPath := artifacts.SessionPreviousArtifactPath(paths, "artifacts/session_recap.md")
if _, err := os.Stat(recapPath); err != nil {
t.Fatalf("expected previous artifact: %v", err)
}
var hasPreviousManifest, hasPreviousArtifact bool
for _, in := range m.Inputs {
if in.Kind == preparePreviousInputKindManifest {
hasPreviousManifest = true
}
if in.Kind == preparePreviousInputKindArtifact {
hasPreviousArtifact = true
}
}
if !hasPreviousManifest || !hasPreviousArtifact {
t.Fatalf("manifest inputs missing previous provenance: %#v", m.Inputs)
}
if result.Metadata["previous_artifacts_hydrated_count"] != 1 {
t.Fatalf("metadata previous_artifacts_hydrated_count = %#v, want 1", result.Metadata["previous_artifacts_hydrated_count"])
}
}
func TestPrepareStageRerunOverwritesPreviousCache(t *testing.T) {
env, m := setupPrepareEnv(t)
root := filepath.Dir(env.Config.SessionPath)
writeFile(t, filepath.Join(root, "audio", "a.flac"), "a")
env.Config.Session.Inputs.AudioFiles = []string{"./audio/a.flac"}
env.Config.Session.Campaign = "forsaken"
env.Config.Session.PreviousSessionID = "2026-05-10"
env.Config.Pipeline.Storage.S3 = &config.StorageS3Config{Bucket: "my-dnd-archive", RootPrefix: "dnd"}
configurePreparePreviousArtifactSource(env, true)
fake := &storage.FakeBackend{}
env.ObjectStore = fake
seed := seedPreviousCurrentState(t, env, fake, previousStateSeedOptions{
includeRunPointerObject: true,
includeArtifactObject: true,
artifactBody: "# old recap\n",
})
paths := sessionPathsForEnv(env, m.SessionID)
if _, err := (prepareStage{}).Run(context.Background(), env, m); err != nil {
t.Fatalf("first prepare run error = %v", err)
}
recapPath := artifacts.SessionPreviousArtifactPath(paths, "artifacts/session_recap.md")
firstBytes, err := os.ReadFile(recapPath)
if err != nil {
t.Fatalf("read first hydrated artifact: %v", err)
}
if strings.TrimSpace(string(firstBytes)) != "# old recap" {
t.Fatalf("first hydrated content = %q, want %q", strings.TrimSpace(string(firstBytes)), "# old recap")
}
writeFile(t, filepath.Join(paths.PreviousArtifactsDir, "stale.txt"), "stale")
fake.SeedObject(storage.FakeObject{Key: seed.ArtifactKey, Data: []byte("# new recap\n")})
if _, err := (prepareStage{}).Run(context.Background(), env, m); err != nil {
t.Fatalf("second prepare run error = %v", err)
}
secondBytes, err := os.ReadFile(recapPath)
if err != nil {
t.Fatalf("read second hydrated artifact: %v", err)
}
if strings.TrimSpace(string(secondBytes)) != "# new recap" {
t.Fatalf("second hydrated content = %q, want %q", strings.TrimSpace(string(secondBytes)), "# new recap")
}
if _, err := os.Stat(filepath.Join(paths.PreviousArtifactsDir, "stale.txt")); !os.IsNotExist(err) {
t.Fatalf("expected stale previous cache file to be removed, stat err = %v", err)
}
}
func configurePreparePreviousArtifactSource(env *Env, required bool) {
env.Config.Pipeline.Scriptorium = &config.ScriptoriumConfig{
Artifacts: map[string]config.ScriptoriumArtifactConfig{
"session_recap": {
Enabled: true,
OutputPath: "artifacts/session_recap.md",
Inputs: map[string]config.ScriptoriumInputConfig{
"previous_recap": {
Source: "narratio.previous_session.artifact.session_recap",
Required: required,
},
},
},
},
}
}
func setupPrepareEnv(t *testing.T) (*Env, *manifest.Manifest) { func setupPrepareEnv(t *testing.T) (*Env, *manifest.Manifest) {
t.Helper() t.Helper()
workspace := t.TempDir() workspace := t.TempDir()

View File

@@ -7,6 +7,7 @@ import (
"strings" "strings"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts" "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/manifest"
) )
@@ -99,6 +100,9 @@ func runLocalPathForCanonical(layout runStageLayout, sessionPaths artifacts.Sess
if rel == "." || rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) { if rel == "." || rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
return "", fmt.Errorf("canonical path %q is outside session root %q", cleanCanonical, sessionPaths.Root) return "", fmt.Errorf("canonical path %q is outside session root %q", cleanCanonical, sessionPaths.Root)
} }
if rel == config.PathPreviousDirSegment || strings.HasPrefix(rel, config.PathPreviousDirSegment+string(filepath.Separator)) {
return cleanCanonical, nil
}
localPath := filepath.Join(layout.OutputsDir, rel) localPath := filepath.Join(layout.OutputsDir, rel)
if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil { if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
return "", fmt.Errorf("create run-local output parent for %q: %w", localPath, err) return "", fmt.Errorf("create run-local output parent for %q: %w", localPath, err)

View File

@@ -33,3 +33,24 @@ func TestRunLocalPathForCanonicalCreatesParentDirectories(t *testing.T) {
t.Fatalf("expected run-local parent directory to exist: %v", err) t.Fatalf("expected run-local parent directory to exist: %v", err)
} }
} }
func TestRunLocalPathForCanonicalKeepsPreviousStateSessionDurable(t *testing.T) {
root := t.TempDir()
sessionRoot := filepath.Join(root, "work", "dilfs", "2026-05-17")
layout := runStageLayout{
Enabled: true,
OutputsDir: filepath.Join(sessionRoot, "runs", "run-1", "prepare", "outputs"),
}
if err := os.MkdirAll(layout.OutputsDir, 0o755); err != nil {
t.Fatalf("mkdir outputs dir: %v", err)
}
canonical := filepath.Join(sessionRoot, "previous", "artifacts", "session_recap.md")
got, err := runLocalPathForCanonical(layout, artifacts.SessionPaths{Root: sessionRoot}, canonical)
if err != nil {
t.Fatalf("runLocalPathForCanonical() error = %v", err)
}
if got != canonical {
t.Fatalf("runLocalPathForCanonical() = %q, want canonical %q", got, canonical)
}
}