Compare commits
19 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 539601bd16 | |||
| 6ca1c8d6b0 | |||
| 4b7b50981b | |||
| 33f7ae8f2e | |||
| d5a9ad38f8 | |||
| 6fbefb9867 | |||
| 1665359486 | |||
| 03f2543927 | |||
| fe9c348092 | |||
| f7f8f1a949 | |||
| d40c91acde | |||
| ed4dcf1ef7 | |||
| 24cce49a70 | |||
| 1e6db89dd4 | |||
| 0454296c81 | |||
| 58c6ab2d54 | |||
| 7995c41675 | |||
| 62551d43a0 | |||
| 8395c12dd3 |
3
.gitignore
vendored
3
.gitignore
vendored
@@ -22,6 +22,9 @@ AGENTS.md
|
||||
# Dependency directories (remove the comment below to include it)
|
||||
# vendor/
|
||||
|
||||
# Go cache
|
||||
.gocache
|
||||
|
||||
# Go workspace file
|
||||
go.work
|
||||
go.work.sum
|
||||
|
||||
175
README.md
175
README.md
@@ -16,7 +16,6 @@ Implemented now:
|
||||
|
||||
Not implemented yet:
|
||||
|
||||
- `archive` stage behavior
|
||||
- `notify` stage behavior
|
||||
- additional analyze artifacts beyond `session_recap`
|
||||
- generic DAG orchestration
|
||||
@@ -35,8 +34,118 @@ Pipeline config lookup for CLI commands:
|
||||
- `/usr/local/etc/narratio/pipeline.yml`
|
||||
- `/etc/narratio/pipeline.yml`
|
||||
|
||||
Session config lookup for CLI commands:
|
||||
|
||||
- if `--session <path>` is provided, Narratio uses that path
|
||||
- if `--session` is omitted, Narratio searches in this order:
|
||||
- `./session.yml`
|
||||
- `/usr/local/etc/narratio/session.yml`
|
||||
- `/etc/narratio/session.yml`
|
||||
|
||||
Session template support:
|
||||
|
||||
- Narratio renders `session.yml` templates before strict YAML decode.
|
||||
- `--session-id <value>` provides the `session_id` template variable.
|
||||
- Supported placeholder forms:
|
||||
- `{{session_id}}`
|
||||
- `{{ session_id }}`
|
||||
- unresolved template placeholders fail with a clear error.
|
||||
- strict YAML validation still runs after rendering.
|
||||
- concrete `session.yml` files without templates remain fully supported.
|
||||
|
||||
Optional secrets-from-files config:
|
||||
|
||||
- `pipeline.secrets.env_dir` may point to a directory of secret files
|
||||
- each top-level file with an env-var-style name is loaded as an environment variable:
|
||||
- file name = env var name
|
||||
- file contents = env var value (trailing newline/CRLF trimmed)
|
||||
- process environment wins: existing env vars are not overwritten
|
||||
- if configured, Narratio fails fast when `env_dir` is missing/unreadable
|
||||
- relative `env_dir` values resolve from Narratio’s current working directory
|
||||
|
||||
YAML decoding is strict (`KnownFields(true)`), so unknown fields fail fast.
|
||||
|
||||
## Storage And Archive Foundations
|
||||
|
||||
Narratio now includes configuration and path-model foundations for archive support, plus implemented prepare-stage S3 audio input.
|
||||
|
||||
Implemented foundations:
|
||||
|
||||
- `pipeline.storage.s3` config shape (`bucket`, `root_prefix`, `region`, `endpoint`, `force_path_style`, `access_key_id_env`, `secret_access_key_env`)
|
||||
- `pipeline.spool` config shape (`root`, `delete_audio_after_archive`)
|
||||
- `pipeline.archive` config shape (`enabled`, `upload_run`, `promote_artifacts`)
|
||||
- promotion-rule validation (`from`/`to` required, relative-only paths, traversal rejected)
|
||||
- `session.campaign` requirement for campaign-aware path construction
|
||||
- optional `session.inputs.audio_s3.prefix` modeling and prepare-stage S3 audio download
|
||||
- run ID generation and S3/local path helper foundations
|
||||
- manifest run/path identity fields
|
||||
|
||||
Current defaults:
|
||||
|
||||
- `pipeline.storage.s3.root_prefix`: `dnd`
|
||||
- `pipeline.storage.s3.access_key_id_env`: `OBJECT_STORAGE_KEY_ID`
|
||||
- `pipeline.storage.s3.secret_access_key_env`: `OBJECT_STORAGE_KEY`
|
||||
- `pipeline.workspace.cleanup_after_archive`: `false`
|
||||
- `pipeline.spool.root`: `/var/spool/narratio`
|
||||
- `pipeline.spool.delete_audio_after_archive`: `false`
|
||||
- `pipeline.archive.enabled`: `true`
|
||||
- `pipeline.archive.upload_run`: `true`
|
||||
- default `pipeline.archive.promote_artifacts`:
|
||||
- `transcripts/trimmed.json` -> `transcripts/trimmed.json` (`required: true`)
|
||||
- `artifacts/session_recap.md` -> `artifacts/session_recap.md` (`required: true`)
|
||||
|
||||
Current boundaries:
|
||||
|
||||
- local development audio (`audio_dir` / `audio_files`) still works
|
||||
- `audio_dir`/`audio_files` and `audio_s3` are mutually exclusive
|
||||
- real S3-compatible backend now exists in the storage adapter package
|
||||
- storage backend tests use fake storage and do not require live S3
|
||||
- archive uploads successful run records under `runs/{run_id}/`
|
||||
- archive does not upload local audio by default
|
||||
- archive uploads promoted outputs to session-level keys using `archive.promote_artifacts`
|
||||
- archive uploads `current/manifest.json`
|
||||
- archive uploads `current/run_id.txt` last as the effective commit marker
|
||||
- required missing promotions fail archive
|
||||
- optional missing promotions are skipped and recorded
|
||||
- cleanup remains conservative and opt-in:
|
||||
- `pipeline.spool.delete_audio_after_archive: true` removes only the run-scoped spool audio directory after successful archive commit
|
||||
- `pipeline.workspace.cleanup_after_archive: true` removes only the run-scoped local workdir after successful archive commit
|
||||
- cleanup executes only after all selected stages for the command invocation succeed
|
||||
- cleanup does not run for failed, incomplete, skipped, or unarchived runs
|
||||
- local development `audio_dir`/`audio_files` source inputs are never deleted by spool cleanup
|
||||
- S3 credentials are resolved from configured env-var names when both are present; if either is missing, Narratio falls back to the AWS SDK default credential chain
|
||||
|
||||
S3 input details and current boundaries are documented in [docs/s3-audio-input.md](docs/s3-audio-input.md).
|
||||
|
||||
## Remote Storage Backend
|
||||
|
||||
Narratio includes an object-store backend layer for future prepare/archive work:
|
||||
|
||||
- `List(ctx, prefix)`
|
||||
- `Download(ctx, key, localPath)`
|
||||
- `Upload(ctx, localPath, key, opts)`
|
||||
- `Exists(ctx, key)`
|
||||
|
||||
Implemented backends:
|
||||
|
||||
- fake storage backend for deterministic tests
|
||||
- S3-compatible backend built from `pipeline.storage.s3`
|
||||
|
||||
Key invariant:
|
||||
|
||||
- callers pass full bucket-relative object keys
|
||||
- storage backends do not prepend `root_prefix` and do not infer session/campaign paths
|
||||
|
||||
Current boundary:
|
||||
|
||||
- `prepare` uses `List` + `Download` through the backend when `session.inputs.audio_s3` is configured
|
||||
- `archive` uses `Upload` through the backend for successful run-record uploads
|
||||
- `archive` also uses `Upload` for promotion writes and current pointers
|
||||
- no failed or incomplete runs are uploaded
|
||||
- local audio is not re-uploaded by default
|
||||
|
||||
Archive run-upload details and boundaries are documented in [docs/archive-storage.md](docs/archive-storage.md).
|
||||
|
||||
## Canonical Stage Order
|
||||
|
||||
1. `prepare`
|
||||
@@ -56,6 +165,52 @@ YAML decoding is strict (`KnownFields(true)`), so unknown fields fail fast.
|
||||
- `transcripts/normalized.json`: Seriatim-normalized transcript from the normalize stage
|
||||
- `transcripts/trimmed.json`: gameplay-only normalized polished transcript from trim stage
|
||||
|
||||
## Seriatim Configuration
|
||||
|
||||
`pipeline.seriatim` configures the Seriatim subprocess adapter used by `merge`, `normalize`, and `trim`.
|
||||
|
||||
Minimal behavior:
|
||||
|
||||
- `pipeline.seriatim` may be omitted entirely.
|
||||
- when omitted, Narratio defaults to:
|
||||
- `binary: seriatim`
|
||||
- `timeout: 10m`
|
||||
- `output_schema: seriatim-intermediate`
|
||||
- `coalesce_gap: 3.0`
|
||||
- `report: true`
|
||||
|
||||
Optional overrides in `pipeline.seriatim` continue to work, including explicit binary paths and advanced `env` tuning values.
|
||||
|
||||
## Audita Configuration
|
||||
|
||||
`pipeline.audita` configures the real Audita subprocess adapter used by `polish`.
|
||||
|
||||
Minimal behavior:
|
||||
|
||||
- `pipeline.audita` may be omitted entirely.
|
||||
- when omitted, Narratio defaults to:
|
||||
- `binary: audita`
|
||||
- `timeout: 3h`
|
||||
- `report: true`
|
||||
|
||||
Optional:
|
||||
|
||||
- `llm_api_key_env` (when set, Narratio requires that env var and passes it to Audita as `AUDITA_LLM_API_KEY`)
|
||||
- `modules` override list (when empty/omitted, Narratio does not pass `--modules`)
|
||||
- `base_url` (when omitted, Narratio does not pass `--base-url`; Audita runtime defaults/config may apply)
|
||||
- `model` (when omitted, Narratio does not pass `--model`; Audita runtime defaults/config may apply)
|
||||
- `transcript_description`
|
||||
- `config_path`
|
||||
- `output_schema` (`bare-segments` or `audita-v1`)
|
||||
- `work_dir_retention` (`always`, `auto`, or `never`)
|
||||
- `total_llm_concurrency` (> 0 when provided)
|
||||
- `proposal_llm_concurrency` (> 0 when provided)
|
||||
- `validation_model`
|
||||
- `validation_llm_concurrency` (> 0 when provided)
|
||||
- `report` (defaults to `true`)
|
||||
|
||||
Narratio passes only configured optional Audita flags. Omitted optional values are left to Audita runtime defaults/config.
|
||||
|
||||
## Normalize Configuration
|
||||
|
||||
`pipeline.normalize` is optional. When omitted, Narratio defaults to:
|
||||
@@ -149,7 +304,7 @@ Render-debug files are diagnostics and are not treated as canonical stage output
|
||||
|
||||
Key points:
|
||||
|
||||
- `scriptorium.binary` is required when section is present
|
||||
- `scriptorium.binary` defaults to `scriptorium` when section is present
|
||||
- `scriptorium.config_path` is optional
|
||||
- `scriptorium.timeout` defaults to `10m` when omitted
|
||||
- `scriptorium.render_debug` enables render diagnostics globally
|
||||
@@ -199,6 +354,8 @@ Prompt IDs and profile IDs are configuration values. They are not hardcoded in a
|
||||
|
||||
Do not put secrets in `pipeline.yml`. If API-key behavior is configured, use env var names only.
|
||||
|
||||
If `pipeline.secrets.env_dir` is configured, keep only references and secret files there; secret values are still not written to manifests, generated configs, or Narratio-managed logs.
|
||||
|
||||
## Scriptorium Runtime Behavior
|
||||
|
||||
Narratio integrates with Scriptorium through the public CLI subprocess contract:
|
||||
@@ -235,7 +392,9 @@ Expected session output paths:
|
||||
Starter files:
|
||||
|
||||
- `examples/pipeline.minimal.yml`
|
||||
- `examples/pipeline.audita-overrides.yml`
|
||||
- `examples/session.minimal.yml`
|
||||
- `examples/session.template.yml`
|
||||
- `examples/speakers.yml`
|
||||
|
||||
## Commands
|
||||
@@ -254,6 +413,12 @@ go run ./cmd/narratio plan --session examples/session.minimal.yml
|
||||
|
||||
Use `--config <path>` to override default pipeline lookup when needed.
|
||||
|
||||
Run with a discoverable session template:
|
||||
|
||||
```bash
|
||||
go run ./cmd/narratio run --session-id 2026-04-04
|
||||
```
|
||||
|
||||
Run full pipeline:
|
||||
|
||||
```bash
|
||||
@@ -266,6 +431,12 @@ Run analyze only:
|
||||
go run ./cmd/narratio run-stage --config examples/pipeline.minimal.yml --session examples/session.minimal.yml analyze
|
||||
```
|
||||
|
||||
Resume with a template session ID:
|
||||
|
||||
```bash
|
||||
go run ./cmd/narratio resume --config examples/pipeline.minimal.yml --session examples/session.template.yml --session-id 2026-04-04
|
||||
```
|
||||
|
||||
## Operational Note
|
||||
|
||||
Checksum-based stale detection is not implemented yet.
|
||||
|
||||
182
architecture.md
182
architecture.md
@@ -22,10 +22,24 @@ Implemented:
|
||||
- real `trim` stage producing `transcripts/trimmed.json`
|
||||
- real `analyze` stage for initial `session_recap` generation
|
||||
- optional Scriptorium render diagnostics (`render_debug`) before production run
|
||||
- storage/archive configuration and validation foundations for:
|
||||
- `pipeline.storage.s3`
|
||||
- `pipeline.spool`
|
||||
- `pipeline.archive` promotion rules
|
||||
- `session.inputs.audio_s3`
|
||||
- run identity and path-model foundations:
|
||||
- run ID generation (`YYYYMMDDTHHMMSSZ-xxxxxxxx`)
|
||||
- S3 session/run/current key builders
|
||||
- campaign/session/run local work/spool path helpers
|
||||
- manifest run/path identity fields (`campaign`, `run_id`, local and S3 prefixes)
|
||||
- remote storage backend layer:
|
||||
- narrow object-store interface (`List`, `Download`, `Upload`, `Exists`)
|
||||
- fake storage backend for deterministic tests (no network dependency)
|
||||
- S3-compatible backend using AWS SDK v2
|
||||
- config-based object-store construction helper
|
||||
|
||||
Still placeholder/future:
|
||||
|
||||
- `archive` stage behavior
|
||||
- `notify` stage behavior
|
||||
- additional Scriptorium artifact types beyond `session_recap`
|
||||
- artifact-to-artifact workflows beyond the initial single-artifact implementation
|
||||
@@ -101,12 +115,175 @@ CLI pipeline config path resolution:
|
||||
- `/usr/local/etc/narratio/pipeline.yml`
|
||||
- `/etc/narratio/pipeline.yml`
|
||||
|
||||
CLI session config path resolution:
|
||||
|
||||
- when `--session <path>` is provided, that path is used
|
||||
- when `--session` is omitted, Narratio searches defaults in order:
|
||||
- `./session.yml`
|
||||
- `/usr/local/etc/narratio/session.yml`
|
||||
- `/etc/narratio/session.yml`
|
||||
|
||||
Session template rendering:
|
||||
|
||||
- session templates are rendered before strict YAML decode
|
||||
- `--session-id <value>` provides the `session_id` template variable
|
||||
- supported placeholders:
|
||||
- `{{session_id}}`
|
||||
- `{{ session_id }}`
|
||||
- unresolved placeholders fail clearly
|
||||
- strict `KnownFields(true)` YAML validation still applies after rendering
|
||||
- if rendered `session.session_id` conflicts with `--session-id`, load fails clearly
|
||||
|
||||
Optional pipeline secrets directory:
|
||||
|
||||
- `pipeline.secrets.env_dir` enables loading environment variables from local files before command execution
|
||||
- file name = env var name; file contents = env var value (trailing newline/CRLF trimmed)
|
||||
- only env-var-style file names are considered; other entries are ignored
|
||||
- existing process environment values are preserved (not overwritten)
|
||||
- if configured, unreadable/missing `env_dir` fails command execution early
|
||||
- relative `env_dir` values are resolved from current working directory
|
||||
|
||||
Storage and archive foundations:
|
||||
|
||||
- `pipeline.storage.s3` is available for modeling S3 coordinates:
|
||||
- `bucket`
|
||||
- `root_prefix` (default `dnd`)
|
||||
- `region`
|
||||
- `endpoint`
|
||||
- `force_path_style` (default `false`)
|
||||
- `access_key_id_env` (default `OBJECT_STORAGE_KEY_ID`)
|
||||
- `secret_access_key_env` (default `OBJECT_STORAGE_KEY`)
|
||||
- `pipeline.spool.root` defaults to `/var/spool/narratio`
|
||||
- `pipeline.workspace.cleanup_after_archive` defaults to `false`
|
||||
- `pipeline.spool.delete_audio_after_archive` defaults to `false`
|
||||
- `pipeline.archive` is optional and defaults to:
|
||||
- `enabled: true`
|
||||
- `upload_run: true`
|
||||
- default `promote_artifacts`:
|
||||
- `transcripts/trimmed.json`
|
||||
- `artifacts/session_recap.md`
|
||||
- archive promotion rules enforce safe relative paths:
|
||||
- `from` and `to` are required
|
||||
- absolute paths are rejected
|
||||
- traversal segments such as `..` are rejected
|
||||
|
||||
Session input foundations:
|
||||
|
||||
- `session.campaign` is required
|
||||
- local audio remains supported through `session.inputs.audio_dir` or `session.inputs.audio_files`
|
||||
- optional S3 audio input shape is `session.inputs.audio_s3.prefix`
|
||||
- `audio_dir`/`audio_files` and `audio_s3` are mutually exclusive
|
||||
- when `audio_s3` is configured, `prepare` lists and downloads `.flac` objects through the object-store backend
|
||||
|
||||
Cross-config validation scope:
|
||||
|
||||
- `pipeline.storage.s3.bucket` is required only when an S3-dependent feature is explicitly configured (for current foundations, that includes `session.inputs.audio_s3`, and archive upload intent when using `storage.backend: s3`)
|
||||
- no AWS credential values are stored in Narratio config; only env-var names are configured
|
||||
- when both configured credential env vars resolve to non-empty values, the S3 backend uses them as static credentials
|
||||
- when either configured credential value is missing, the S3 backend falls back to the AWS SDK default credential chain
|
||||
|
||||
Remote object-store backend scope:
|
||||
|
||||
- remote storage APIs are isolated to `internal/adapters/storage`
|
||||
- AWS SDK types remain contained within the S3 backend implementation package
|
||||
- S3 key/session path semantics remain outside the backend, with this invariant:
|
||||
- callers pass full bucket-relative object keys
|
||||
- backend methods do not prepend `root_prefix` or infer campaign/session/run paths
|
||||
- `prepare` now uses object-store `List` and `Download` for S3 audio input
|
||||
- `archive` now uses object-store `Upload` for successful run-record upload under the run prefix
|
||||
- `archive` now uses object-store `Upload` for promoted outputs and current pointers
|
||||
|
||||
Prepare S3 audio behavior (implemented):
|
||||
|
||||
- compute session prefix as `{root_prefix}/campaigns/{campaign}/sessions/{session_id}/`
|
||||
- resolve `session.inputs.audio_s3.prefix` under that session prefix
|
||||
- list objects under the computed audio prefix and filter `.flac` keys
|
||||
- fail clearly when no `.flac` objects are found
|
||||
- download selected objects to spool audio path:
|
||||
- `{spool.root}/{campaign}/{session_id}/{run_id}/audio/`
|
||||
- materialize audio files into workdir audio path:
|
||||
- `{workspace.root}/work/{campaign}/{session_id}/{run_id}/audio/`
|
||||
- record S3 provenance in manifest input records (bucket/key/metadata/local paths/checksum)
|
||||
- no AWS SDK types are used in stage code; storage implementation details stay in storage adapter packages
|
||||
|
||||
Archive publishing behavior (implemented):
|
||||
|
||||
- `archive` verifies prerequisite stage success before upload:
|
||||
- `prepare`, `transcribe`, `merge`, `polish`, `normalize`, `trim`, `analyze`
|
||||
- only successful/completed runs are uploaded
|
||||
- uploaded run record destination is:
|
||||
- `{root_prefix}/campaigns/{campaign}/sessions/{session_id}/runs/{run_id}/`
|
||||
- uploaded existing local paths include:
|
||||
- `inputs/`, `transcripts/`, `artifacts/`, optional `reports/`, `config/`, `logs/`, and `manifest.json`
|
||||
- local `audio/` is intentionally excluded from upload by default
|
||||
- file upload order is deterministic (sorted relative paths)
|
||||
- `archive.enabled: false` and `archive.upload_run: false` skip upload cleanly
|
||||
- stage metadata records non-secret upload context:
|
||||
- run upload details, promoted output details, current manifest key, current pointer key
|
||||
- no secrets, transcript contents, prompt contents, or environment dumps
|
||||
- promotion rules:
|
||||
- `from` resolves from local workdir
|
||||
- `to` resolves under session-level S3 root
|
||||
- missing required source fails archive
|
||||
- missing optional source is skipped and recorded
|
||||
- default promoted outputs:
|
||||
- `transcripts/trimmed.json`
|
||||
- `artifacts/session_recap.md`
|
||||
- current pointers:
|
||||
- `current/manifest.json` uploaded after run upload and promotions
|
||||
- `current/run_id.txt` uploaded last with `{run_id}\n`
|
||||
- `current/run_id.txt` is the effective commit marker
|
||||
- if promotion or current-manifest upload fails, archive returns failure and does not write `current/run_id.txt`
|
||||
- failed/incomplete runs remain local and are not uploaded
|
||||
- post-archive local cleanup (implemented, opt-in):
|
||||
- cleanup runs only after archive succeeded and wrote `current/run_id.txt`
|
||||
- cleanup is executed after all selected stages in the command invocation succeed (for example, a later `notify` failure leaves local files intact)
|
||||
- `pipeline.spool.delete_audio_after_archive: true` removes only `{spool.root}/{campaign}/{session_id}/{run_id}/audio/`
|
||||
- `pipeline.workspace.cleanup_after_archive: true` removes only `{workspace.root}/work/{campaign}/{session_id}/{run_id}/`
|
||||
- cleanup does not run when archive is skipped/disabled/fails or when run upload is disabled
|
||||
- local development `audio_dir`/`audio_files` inputs are never removed by spool cleanup
|
||||
|
||||
`pipeline.scriptorium` is optional. Existing pipelines without Scriptorium continue to work.
|
||||
|
||||
`pipeline.trim` is optional. Existing pipelines without trim config continue to work.
|
||||
|
||||
`pipeline.normalize` is optional. Existing pipelines without normalize config continue to work.
|
||||
|
||||
`pipeline.audita` drives the real Audita subprocess adapter for the `polish` stage.
|
||||
|
||||
Audita defaulted fields:
|
||||
|
||||
- `binary` defaults to `audita`
|
||||
- `timeout` defaults to `3h`
|
||||
- `report` defaults to `true`
|
||||
|
||||
Audita optional fields:
|
||||
|
||||
- `llm_api_key_env` (enforced only when configured)
|
||||
- `modules` override list (when omitted/empty, Narratio does not pass `--modules`)
|
||||
- `base_url` (when omitted, Narratio does not pass `--base-url`)
|
||||
- `model` (when omitted, Narratio does not pass `--model`)
|
||||
- `transcript_description`
|
||||
- `config_path`
|
||||
- `output_schema` (`bare-segments` or `audita-v1`)
|
||||
- `work_dir_retention` (`always`, `auto`, `never`)
|
||||
- `total_llm_concurrency` (> 0 when provided)
|
||||
- `proposal_llm_concurrency` (> 0 when provided)
|
||||
- `validation_model`
|
||||
- `validation_llm_concurrency` (> 0 when provided)
|
||||
- `report` override
|
||||
|
||||
Narratio passes only configured optional Audita flags; omitted optional values defer to Audita runtime defaults/config.
|
||||
|
||||
Seriatim defaults:
|
||||
|
||||
- `pipeline.seriatim` may be omitted
|
||||
- `binary` defaults to `seriatim`
|
||||
- `timeout` defaults to `10m`
|
||||
- `output_schema` defaults to `seriatim-intermediate`
|
||||
- `coalesce_gap` defaults to `3.0`
|
||||
- `report` defaults to `true`
|
||||
|
||||
When `pipeline.normalize` is omitted, defaults are applied:
|
||||
|
||||
- `output_path: transcripts/normalized.json`
|
||||
@@ -139,7 +316,7 @@ When `pipeline.trim.enabled: true`:
|
||||
|
||||
When `pipeline.scriptorium` is present:
|
||||
|
||||
- `binary` is required and non-empty
|
||||
- `binary` defaults to `scriptorium` when omitted
|
||||
- `config_path` is optional; when provided it must be non-empty
|
||||
- `timeout` is optional; when provided it must parse as a Go duration
|
||||
- default `timeout` is `10m`
|
||||
@@ -288,6 +465,7 @@ Current expected paths for `session_recap`:
|
||||
|
||||
- do not store secrets in pipeline YAML, generated invocation YAML, logs, or manifest metadata
|
||||
- if API-key integration is configured, pass env var names only (never raw key values)
|
||||
- with `pipeline.secrets.env_dir`, secret file values are loaded into process env only and are not persisted in manifest metadata or generated configs
|
||||
- avoid logging transcript content or rendered prompt content by default
|
||||
- treat generated artifacts and logs as potentially sensitive session material
|
||||
|
||||
|
||||
119
docs/archive-storage.md
Normal file
119
docs/archive-storage.md
Normal file
@@ -0,0 +1,119 @@
|
||||
# Archive Storage
|
||||
|
||||
This document describes implemented archive-stage publish behavior.
|
||||
|
||||
## S3 Paths
|
||||
|
||||
Session root:
|
||||
|
||||
`{root_prefix}/campaigns/{campaign}/sessions/{session_id}/`
|
||||
|
||||
Run prefix:
|
||||
|
||||
`{root_prefix}/campaigns/{campaign}/sessions/{session_id}/runs/{run_id}/`
|
||||
|
||||
## Scope
|
||||
|
||||
Implemented:
|
||||
|
||||
- archive uploads successful run records to remote object storage through the storage backend abstraction.
|
||||
- archive uploads configured promoted outputs to session-level keys.
|
||||
- archive uploads `current/manifest.json`.
|
||||
- archive uploads `current/run_id.txt` last as the effective commit marker.
|
||||
- optional post-archive local cleanup:
|
||||
- `pipeline.spool.delete_audio_after_archive: true` removes only the run-scoped spool audio directory
|
||||
- `pipeline.workspace.cleanup_after_archive: true` removes only the run-scoped local workdir
|
||||
- tests use fake storage and do not require live S3.
|
||||
|
||||
Future work:
|
||||
|
||||
- `notify` stage behavior
|
||||
- stale detection
|
||||
- optional future source-audio upload mode
|
||||
- additional artifact generation beyond current implemented set
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Archive verifies these stages succeeded before upload:
|
||||
|
||||
- `prepare`
|
||||
- `transcribe`
|
||||
- `merge`
|
||||
- `polish`
|
||||
- `normalize`
|
||||
- `trim`
|
||||
- `analyze`
|
||||
|
||||
If any prerequisite is missing or not succeeded, archive fails and does not upload.
|
||||
Failed or incomplete runs remain local only.
|
||||
|
||||
## Run Upload
|
||||
|
||||
Archive uploads existing files from the run workdir when present:
|
||||
|
||||
- `inputs/`
|
||||
- `transcripts/`
|
||||
- `artifacts/`
|
||||
- `reports/` (optional)
|
||||
- `config/`
|
||||
- `logs/`
|
||||
- `manifest.json`
|
||||
|
||||
Relative paths are preserved under `runs/{run_id}/`.
|
||||
|
||||
## Promotion Rules
|
||||
|
||||
Archive applies `archive.promote_artifacts` in config order.
|
||||
|
||||
Rule behavior:
|
||||
|
||||
- `from`: local workdir-relative source path
|
||||
- `to`: session-root-relative destination key
|
||||
- `required: true`: missing source fails archive
|
||||
- `required: false`: missing source is skipped and recorded
|
||||
|
||||
Default promoted outputs:
|
||||
|
||||
- `transcripts/trimmed.json`
|
||||
- `artifacts/session_recap.md`
|
||||
|
||||
## Current Pointers
|
||||
|
||||
Archive writes:
|
||||
|
||||
1. `current/manifest.json` (after run upload + promotions)
|
||||
2. `current/run_id.txt` last
|
||||
|
||||
`current/run_id.txt` contains exactly:
|
||||
|
||||
- `{run_id}` plus trailing newline
|
||||
|
||||
Writing `current/run_id.txt` last makes it the effective commit marker for published session state.
|
||||
|
||||
If any required run upload, promotion upload, or current-manifest upload fails, archive returns failure and does not write `current/run_id.txt`.
|
||||
Cleanup runs only after this commit-marker write has succeeded.
|
||||
|
||||
## Audio Upload Policy
|
||||
|
||||
Archive does not upload local `audio/` by default.
|
||||
Original audio is expected at the session-level audio prefix and is not duplicated under `runs/{run_id}/`.
|
||||
|
||||
## Config Controls
|
||||
|
||||
- `archive.enabled: false` skips archive cleanly.
|
||||
- `archive.upload_run: false` skips run upload cleanly.
|
||||
- both skip cases also skip post-archive local cleanup.
|
||||
|
||||
## Metadata
|
||||
|
||||
Archive stage metadata includes non-secret upload context (for example):
|
||||
|
||||
- `s3_bucket`
|
||||
- `s3_run_prefix`
|
||||
- run upload counts/paths
|
||||
- promoted upload counts/paths
|
||||
- skipped optional promotions
|
||||
- `current_manifest_key`
|
||||
- `current_run_id_key`
|
||||
- `current_pointer_written`
|
||||
- `audio_upload_skipped`
|
||||
@@ -1,147 +1,96 @@
|
||||
# Audita
|
||||
# Audita Subprocess Operations
|
||||
|
||||
Audita is a framework-first transcript correction application. The public `audita` package provides:
|
||||
This document describes how parent processes should invoke `audita process` safely in production orchestration.
|
||||
|
||||
- deterministic transcript normalization
|
||||
- token-batched module orchestration
|
||||
- concrete `glossary`, `homophones`, `spoken_word`, and `grammar` modules built on reusable proposal / validator contracts
|
||||
- structured run reporting and work-dir diagnostics
|
||||
## Recommended command form
|
||||
|
||||
The previous working implementation has been preserved as `audita_prototype` inside this repository. Its full regression suite lives under `tests/audita_prototype`.
|
||||
|
||||
## Development
|
||||
|
||||
This project is set up for `uv`.
|
||||
Use explicit file outputs for orchestrated runs:
|
||||
|
||||
```sh
|
||||
uv sync --extra dev
|
||||
uv run pytest
|
||||
audita process <transcript.json> \
|
||||
--transcript-description "Brief context that may help resolve ambiguous terms." \
|
||||
--glossary <glossary.yaml> \
|
||||
--output <output-transcript.json> \
|
||||
--report-json <report.json>
|
||||
```
|
||||
|
||||
## Usage
|
||||
Additional flags that may be situationally appropriate:
|
||||
- `--config <path>` to select an explicit versioned config file.
|
||||
- `--output-schema <bare-segments|audita-v1>` to select transcript output shape.
|
||||
- `--work-dir <dir>` to control diagnostics location.
|
||||
- `--work-dir-retention <always|auto|never>` to control retained run directories.
|
||||
- `--total-llm-concurrency`, `--proposal-llm-concurrency`, and `--validation-llm-concurrency` when orchestration needs to set explicit LLM throughput controls.
|
||||
- `--modules ...` only when intentionally overriding the default sequence.
|
||||
|
||||
Process a transcript with the current framework implementation:
|
||||
For config-driven orchestration, validate config files in CI/preflight:
|
||||
|
||||
```sh
|
||||
uv run audita process transcript.json --glossary glossary.yaml --output corrected.json
|
||||
audita config validate --config <path>
|
||||
```
|
||||
|
||||
The framework currently runs this default module sequence:
|
||||
## Stdout behavior
|
||||
|
||||
1. `glossary`
|
||||
2. `homophones`
|
||||
3. `glossary`
|
||||
4. `spoken_word`
|
||||
5. `grammar`
|
||||
- With `--output`: stdout is expected to be empty on success.
|
||||
- Without `--output`: stdout contains transcript JSON only on success.
|
||||
- Report JSON is never written to stdout.
|
||||
|
||||
Resolved run instance names are auto-numbered for repeats, so the default report pipeline is:
|
||||
## Stderr behavior
|
||||
|
||||
1. `glossary_1`
|
||||
2. `homophones`
|
||||
3. `glossary_2`
|
||||
4. `spoken_word`
|
||||
5. `grammar`
|
||||
- Success path should be quiet or minimal human-readable logs.
|
||||
- Failure path writes concise human-readable errors.
|
||||
- When a diagnostics run directory exists, failure stderr includes its path.
|
||||
- Prompt/response diagnostic payloads are not streamed to stderr.
|
||||
|
||||
The default module sequence is fully implemented today:
|
||||
## Output file behavior
|
||||
|
||||
- `glossary` proposes glossary-supported acoustic corrections
|
||||
- `homophones` proposes conservative homophone and mistranscription corrections
|
||||
- `spoken_word` proposes conservative dysfluency cleanup
|
||||
- `grammar` proposes punctuation, capitalization, and spacing cleanup only
|
||||
- `--output` writes transcript JSON in the selected output schema to the provided path.
|
||||
- Output write failures return nonzero and surface actionable errors.
|
||||
- The command does not silently ignore output write errors.
|
||||
|
||||
To run a custom module sequence, pass `--modules`:
|
||||
## Report JSON behavior
|
||||
|
||||
```sh
|
||||
uv run audita process transcript.json --glossary glossary.yaml --modules grammar --output corrected.json
|
||||
```
|
||||
- `--report-json` writes a machine-readable process report to the requested path.
|
||||
- Run-directory `report.json` is written independently under diagnostics.
|
||||
- Best-effort failure reports are emitted when possible without masking the primary failure.
|
||||
- Report write failures return nonzero with clear stderr messaging.
|
||||
- Report diagnostics metadata references run-directory artifacts including utilization diagnostics and correction ledger paths when available.
|
||||
|
||||
To also write a structured JSON report:
|
||||
## Diagnostics directory behavior
|
||||
|
||||
```sh
|
||||
uv run audita process transcript.json --glossary glossary.yaml --output corrected.json --report-json report.json
|
||||
```
|
||||
- Each run creates (when possible) a per-run diagnostics directory.
|
||||
- Typical artifacts include transcript, normalization, chunking, invocation, effective config, LLM diagnostics, `utilization-diagnostics.json`, `correction-ledger.json`, `report.json`, and `error.log` on failure.
|
||||
- Failed runs retain diagnostics.
|
||||
- Under `auto` retention, successful runs with skipped/rejected corrections are retained; clean successful runs may be removed.
|
||||
|
||||
From a checked-out repository, you can also use the root launcher:
|
||||
## Exit codes
|
||||
|
||||
```sh
|
||||
./audita process transcript.json --glossary glossary.yaml --output corrected.json
|
||||
```
|
||||
- `0`: success.
|
||||
- Nonzero: failure (input/schema/config/module/LLM/runtime/output/report/diagnostics errors).
|
||||
|
||||
For a system-wide command, install the source tree under `/usr/local/src/audita`, sync dependencies there, and symlink the root launcher into your `PATH`:
|
||||
Treat any nonzero as a failed subprocess invocation.
|
||||
|
||||
```sh
|
||||
cd /usr/local/src/audita
|
||||
uv sync --extra dev
|
||||
ln -s /usr/local/src/audita/audita /usr/local/bin/audita
|
||||
audita process transcript.json --glossary glossary.yaml --output corrected.json
|
||||
```
|
||||
## Timeout and cancellation
|
||||
|
||||
Without `--output`, Audita writes the corrected transcript JSON to stdout and progress logs to stderr.
|
||||
`--report-json` writes a separate machine-readable run report and never mixes report data into stdout.
|
||||
- Runtime operations propagate context cancellation and request timeouts through LLM/scheduler paths.
|
||||
- On cancellation or timeout, the process exits nonzero and should not hang.
|
||||
- If diagnostics were initialized before failure, failure artifacts remain available for debugging.
|
||||
|
||||
Useful configuration can be supplied by CLI flag or environment variable. CLI flags take precedence over environment variables. Normal runs now require LLM API credentials, because the `glossary`, `homophones`, `spoken_word`, and `grammar` modules make real LLM calls. `AUDITA_LLM_API_KEY` and `--llm-api-key` are the preferred provider-neutral credential surfaces, while `OPENROUTER_API_KEY` remains supported as a backward-compatible fallback.
|
||||
## Secret redaction expectations
|
||||
|
||||
| Environment variable | CLI flag | Default | Purpose |
|
||||
| --- | --- | --- | --- |
|
||||
| `AUDITA_MODULES` | `--modules` | `glossary,homophones,glossary,spoken_word,grammar` | Comma-separated logical module keys to run; CLI overrides the environment value |
|
||||
| `AUDITA_LLM_API_KEY` | `--llm-api-key` | unset | Preferred provider-neutral LLM API credential; CLI overrides both environment-key variants |
|
||||
| `AUDITA_VALIDATION_LLM_API_KEY` | `--validation-llm-api-key` | unset | Validation-phase LLM API credential; defaults to the primary LLM API key |
|
||||
| `AUDITA_MODEL` | `--model` | `openrouter/google/gemma-4-31b-it` | LLM model name sent to the configured OpenAI-compatible endpoint |
|
||||
| `AUDITA_VALIDATION_MODEL` | `--validation-model` | unset | Validation-phase LLM model; defaults to `AUDITA_MODEL` |
|
||||
| `AUDITA_BASE_URL` | `--base-url` | `https://openrouter.ai/api/v1` | OpenAI-compatible API base URL |
|
||||
| `AUDITA_VALIDATION_BASE_URL` | `--validation-base-url` | unset | Validation-phase OpenAI-compatible API base URL; defaults to `AUDITA_BASE_URL` |
|
||||
| `AUDITA_LLM_TIMEOUT_SECONDS` | `--llm-timeout-seconds` | `600` | Per-request timeout in seconds for LLM calls to the configured OpenAI-compatible endpoint |
|
||||
| `AUDITA_VALIDATION_LLM_TIMEOUT_SECONDS` | `--validation-llm-timeout-seconds` | unset | Validation-phase per-request timeout in seconds; defaults to `AUDITA_LLM_TIMEOUT_SECONDS` |
|
||||
| `AUDITA_VALIDATION_MAX_PROMPT_TOKENS` | `--validation-max-prompt-tokens` | `2048` | Maximum estimated tokens per validation-phase LLM prompt batch |
|
||||
| `AUDITA_TARGET_SECTIONS` | `--target-sections` | unset | Exact number of contiguous proposal-stage transcript sections; errors if min/max token bounds cannot be satisfied |
|
||||
| `AUDITA_MAX_RETRIES` | `--max-retries` | `3` | Maximum Instructor retries for structured responses |
|
||||
| `AUDITA_VALIDATION_MAX_RETRIES` | `--validation-max-retries` | unset | Validation-phase structured-output retries; defaults to `AUDITA_MAX_RETRIES` |
|
||||
| `AUDITA_VALIDATION_LLM_CONCURRENCY` | `--validation-llm-concurrency` | unset | Validation-phase LLM concurrency; defaults to `AUDITA_LLM_CONCURRENCY` |
|
||||
| `AUDITA_MAX_SECTION_TOKENS` | `--max-section-tokens` | `8192` | Maximum estimated tokens per proposal-stage transcript section |
|
||||
| `AUDITA_MIN_SECTION_TOKENS` | `--min-section-tokens` | `2048` | Minimum estimated tokens per proposal-stage transcript section when balancing for concurrency |
|
||||
| `AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD` | `--glossary-confidence-threshold` | `0.8` | Minimum confidence required for glossary proposals to survive validation |
|
||||
| `AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD` | `--grammar-confidence-threshold` | `0.8` | Minimum confidence required for grammar proposals to survive validation |
|
||||
| `AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD` | `--homophones-confidence-threshold` | `0.8` | Minimum confidence required for homophone proposals to survive validation |
|
||||
| `AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD` | `--spoken-word-confidence-threshold` | `0.8` | Minimum confidence required for spoken-word proposals to survive validation |
|
||||
| `AUDITA_NORMALIZE_MAX_SEGMENT_GAP` | `--normalize-max-segment-gap` | `4.0` | Same-speaker gaps eligible for deterministic merging |
|
||||
| `AUDITA_NORMALIZE_ELLIPSIS_GAP` | `--normalize-ellipsis-gap` | `3.5` | Same-speaker gaps above this value are joined with ` ... ` |
|
||||
| `AUDITA_NORMALIZE_MAX_SEGMENT_DURATION` | `--normalize-max-segment-duration` | `60.0` | Maximum merged segment duration |
|
||||
| `AUDITA_NORMALIZE_MAX_SEGMENT_TOKENS` | `--normalize-max-segment-tokens` | `2048` | Maximum merged segment prompt payload size |
|
||||
| `AUDITA_WORK_DIR` | `--work-dir` | `/tmp/audita` | Per-run scratch diagnostics directory |
|
||||
| `AUDITA_WORK_DIR_RETENTION` | `--work-dir-retention` | `auto` | Whether to retain the per-run work directory: `auto`, `always`, or `never` |
|
||||
API keys and configured secret values are redacted from:
|
||||
- reports (`--report-json` and run-dir `report.json`);
|
||||
- diagnostics artifacts (including effective config and LLM interaction artifacts);
|
||||
- surfaced adapter/runtime errors;
|
||||
- test fixtures and regression outputs.
|
||||
|
||||
Set `AUDITA_MODULES=grammar` to run only the grammar module by default, or override it per command with `--modules`.
|
||||
Parent-process logs should still avoid printing raw environment variables.
|
||||
|
||||
Validation-phase LLM settings inherit from the primary `AUDITA_*` LLM settings by default. Set any of the `AUDITA_VALIDATION_*` values only when you want LLM-backed validators to use a different model, endpoint, credential, timeout, retry budget, or concurrency level.
|
||||
## Parent-process pipe guidance
|
||||
|
||||
OpenRouter remains the default out of the box:
|
||||
To avoid deadlocks in orchestrators:
|
||||
- always read both stdout and stderr concurrently when invoking as a subprocess;
|
||||
- prefer file outputs (`--output`, `--report-json`) for machine workflows;
|
||||
- treat stderr as human-readable diagnostics, not structured data;
|
||||
- parse structured results from output/report files.
|
||||
|
||||
```sh
|
||||
export AUDITA_LLM_API_KEY=your-openrouter-key
|
||||
audita process transcript.json --glossary glossary.yaml --output corrected.json
|
||||
```
|
||||
|
||||
You can point Audita at any OpenAI-compatible endpoint by changing `AUDITA_BASE_URL` and, if needed, `AUDITA_MODEL`. For example, a local vLLM server:
|
||||
|
||||
```sh
|
||||
export AUDITA_LLM_API_KEY=local-dev-key
|
||||
export AUDITA_BASE_URL=http://localhost:8000/v1
|
||||
export AUDITA_MODEL=meta-llama/Llama-3.1-8B-Instruct
|
||||
audita process transcript.json --glossary glossary.yaml --output corrected.json
|
||||
```
|
||||
|
||||
Or the actual OpenAI API:
|
||||
|
||||
```sh
|
||||
export AUDITA_LLM_API_KEY=your-openai-key
|
||||
export AUDITA_BASE_URL=https://api.openai.com/v1
|
||||
export AUDITA_MODEL=gpt-4.1-mini
|
||||
audita process transcript.json --glossary glossary.yaml --output corrected.json
|
||||
```
|
||||
|
||||
`AUDITA_WORK_DIR` stores per-run diagnostics while processing. Under the default `AUDITA_WORK_DIR_RETENTION=auto`, clean successful runs are removed, while failed runs and successful runs with final skipped corrections are preserved. Use `always` to keep every run directory and `never` to remove successful run directories even when skips remain.
|
||||
Failed runs always preserve the run directory and include an authoritative `report.json` alongside normalization and prompt/response diagnostics.
|
||||
|
||||
## Prototype Archive
|
||||
|
||||
The archived prototype remains importable as `audita_prototype` and is still covered by its original regression suite. This is intentional: the new `audita` package is a framework-oriented rewrite, not a thin wrapper around the old code.
|
||||
For Go callers, prefer `exec.CommandContext` with explicit timeout/cancellation and buffered/streamed readers for both pipes.
|
||||
|
||||
1063
docs/roadmap/narratio-s3-archive-implementation-plan.md
Normal file
1063
docs/roadmap/narratio-s3-archive-implementation-plan.md
Normal file
File diff suppressed because it is too large
Load Diff
35
docs/runbooks/s3-archive-foundations.md
Normal file
35
docs/runbooks/s3-archive-foundations.md
Normal file
@@ -0,0 +1,35 @@
|
||||
# S3 Archive Foundations Runbook
|
||||
|
||||
This runbook documents the currently implemented storage/archive foundations and the boundaries of current behavior.
|
||||
|
||||
## Implemented Now
|
||||
|
||||
- config modeling for:
|
||||
- `pipeline.storage.s3`
|
||||
- `pipeline.spool`
|
||||
- `pipeline.archive`
|
||||
- `session.inputs.audio_s3`
|
||||
- promotion rule validation for safe relative paths
|
||||
- run ID generation and path/key helper functions
|
||||
- manifest run/path identity fields
|
||||
- remote storage backend layer:
|
||||
- object-store interface (`List`, `Download`, `Upload`, `Exists`)
|
||||
- fake backend for deterministic tests
|
||||
- S3-compatible backend using AWS SDK v2
|
||||
- config-based backend construction helper
|
||||
|
||||
## Not Implemented Yet
|
||||
|
||||
- prepare-stage S3 object listing or download
|
||||
- archive-stage S3 upload or promotion writes
|
||||
- writing `current/manifest.json` or `current/run_id.txt` in S3
|
||||
|
||||
## Operational Notes
|
||||
|
||||
- local audio workflows remain the active development path (`audio_dir` or `audio_files`)
|
||||
- `audio_s3` and local audio config are mutually exclusive
|
||||
- do not place AWS credentials in Narratio config files
|
||||
|
||||
## Next Implementation Target
|
||||
|
||||
Use the storage backend layer in prepare-stage session audio discovery/download flow, while preserving local audio input support.
|
||||
84
docs/s3-audio-input.md
Normal file
84
docs/s3-audio-input.md
Normal file
@@ -0,0 +1,84 @@
|
||||
# S3 Audio Input
|
||||
|
||||
This document describes implemented S3 audio input behavior in `prepare`.
|
||||
|
||||
## Scope
|
||||
|
||||
Implemented:
|
||||
|
||||
- `prepare` can acquire source audio from S3 when `session.inputs.audio_s3.prefix` is configured.
|
||||
- object listing and download go through the storage backend abstraction.
|
||||
- tests use fake storage; no live S3 service is required for test runs.
|
||||
|
||||
Not implemented:
|
||||
|
||||
- uploads of failed runs
|
||||
|
||||
## Required Configuration
|
||||
|
||||
`pipeline.yml`:
|
||||
|
||||
- `storage.s3.bucket` must be set when S3 audio input is used.
|
||||
- `storage.s3.root_prefix` defaults to `dnd`.
|
||||
- `storage.s3.access_key_id_env` defaults to `OBJECT_STORAGE_KEY_ID`.
|
||||
- `storage.s3.secret_access_key_env` defaults to `OBJECT_STORAGE_KEY`.
|
||||
- `spool.root` defaults to `/var/spool/narratio`.
|
||||
|
||||
`session.yml`:
|
||||
|
||||
- configure `session.campaign` and `session.session_id`.
|
||||
- configure `session.inputs.audio_s3.prefix` for S3 audio input.
|
||||
- do not configure `inputs.audio_dir` or `inputs.audio_files` at the same time as `inputs.audio_s3`.
|
||||
|
||||
## Prefix Shape
|
||||
|
||||
Session S3 root:
|
||||
|
||||
`{root_prefix}/campaigns/{campaign}/sessions/{session_id}/`
|
||||
|
||||
Audio prefix:
|
||||
|
||||
`{session_root}/{audio_s3.prefix}`
|
||||
|
||||
Example:
|
||||
|
||||
`dnd/campaigns/forsaken/sessions/2026-04-19/audio/`
|
||||
|
||||
Audio files must already exist in S3 before running Narratio.
|
||||
|
||||
## Prepare Behavior
|
||||
|
||||
When `inputs.audio_s3.prefix` is configured, `prepare`:
|
||||
|
||||
1. lists objects under the computed S3 audio prefix
|
||||
2. filters to `.flac` objects
|
||||
3. fails when no `.flac` objects are found
|
||||
4. downloads selected objects to spool audio:
|
||||
- `{spool.root}/{campaign}/{session_id}/{run_id}/audio/`
|
||||
5. materializes audio into workdir audio:
|
||||
- `{workspace.root}/work/{campaign}/{session_id}/{run_id}/audio/`
|
||||
6. records input provenance in the manifest (bucket, key, metadata, local paths, checksum)
|
||||
|
||||
Notes:
|
||||
|
||||
- `.flac` filtering is case-insensitive.
|
||||
- ETag is recorded as provider metadata only and is not treated as a checksum.
|
||||
|
||||
## Local Audio Development
|
||||
|
||||
Local audio workflows remain supported:
|
||||
|
||||
- `inputs.audio_dir`
|
||||
- `inputs.audio_files`
|
||||
|
||||
These options are mutually exclusive with `inputs.audio_s3`.
|
||||
|
||||
## Archive Boundary
|
||||
|
||||
Current archive behavior relevant to S3 audio input:
|
||||
|
||||
- successful runs are uploaded by archive under `runs/{run_id}/`
|
||||
- configured promotions are uploaded to session-level destinations
|
||||
- `current/manifest.json` and `current/run_id.txt` are published
|
||||
- local source audio is not re-uploaded by default
|
||||
- failed or incomplete runs are not uploaded
|
||||
62
docs/storage-backends.md
Normal file
62
docs/storage-backends.md
Normal file
@@ -0,0 +1,62 @@
|
||||
# Storage Backends
|
||||
|
||||
This document describes the currently implemented remote object storage backend layer used by Narratio, and its intended role in later prepare/archive work.
|
||||
|
||||
## Implemented
|
||||
|
||||
Remote object store abstraction:
|
||||
|
||||
- `List(ctx, prefix)`
|
||||
- `Download(ctx, key, localPath)`
|
||||
- `Upload(ctx, localPath, key, opts)`
|
||||
- `Exists(ctx, key)`
|
||||
|
||||
Object metadata model includes:
|
||||
|
||||
- key
|
||||
- size
|
||||
- ETag (provider metadata only)
|
||||
- last modified time when available
|
||||
|
||||
Backends:
|
||||
|
||||
- fake storage backend for deterministic tests
|
||||
- S3-compatible backend implemented with AWS SDK for Go v2
|
||||
|
||||
Construction:
|
||||
|
||||
- config-based constructor builds S3 backend from `pipeline.storage.s3` values:
|
||||
- bucket
|
||||
- region
|
||||
- endpoint
|
||||
- force_path_style
|
||||
- access_key_id_env
|
||||
- secret_access_key_env
|
||||
|
||||
## Key Invariant
|
||||
|
||||
- callers pass full bucket-relative object keys
|
||||
- storage backends do not prepend `root_prefix`
|
||||
- storage backends do not infer campaign/session/run paths
|
||||
|
||||
S3 session/run key builders remain separate and continue to live outside backend implementations.
|
||||
|
||||
## Security Boundary
|
||||
|
||||
- do not store AWS credentials in Narratio config
|
||||
- Narratio first checks configured env-var names (`access_key_id_env`, `secret_access_key_env`);
|
||||
when both are present and non-empty, it uses static credentials from those values
|
||||
- when either configured credential value is missing, Narratio falls back to the standard AWS SDK credential chain
|
||||
- AWS SDK-specific types remain isolated to the storage adapter package
|
||||
|
||||
## Testing
|
||||
|
||||
- fake storage tests cover list/download/upload/exists and error paths
|
||||
- S3 backend tests use injected fake S3 API clients
|
||||
- tests do not require live S3 services, AWS credentials, or network access
|
||||
|
||||
## Not Implemented Yet
|
||||
|
||||
- prepare-stage S3 object listing or downloads
|
||||
- archive-stage S3 uploads or promotion writes
|
||||
- writing `current/manifest.json` or `current/run_id.txt` to S3
|
||||
26
examples/pipeline.audita-overrides.yml
Normal file
26
examples/pipeline.audita-overrides.yml
Normal file
@@ -0,0 +1,26 @@
|
||||
workspace:
|
||||
root: ./tmp/narratio-workspace
|
||||
|
||||
whisperx:
|
||||
transcribe_url: "https://transcription.example.com/transcribe"
|
||||
|
||||
seriatim:
|
||||
binary: "seriatim"
|
||||
timeout: "10m"
|
||||
output_schema: "seriatim-intermediate"
|
||||
coalesce_gap: 3.0
|
||||
|
||||
audita:
|
||||
binary: "audita"
|
||||
timeout: "3h"
|
||||
base_url: "https://openrouter.ai/api/v1"
|
||||
model: "openrouter/google/gemma-4-31b-it"
|
||||
llm_api_key_env: "AUDITA_LLM_API_KEY"
|
||||
modules: ["glossary", "homophones", "spoken_word", "grammar"]
|
||||
output_schema: "audita-v1"
|
||||
work_dir_retention: "auto"
|
||||
total_llm_concurrency: 2
|
||||
proposal_llm_concurrency: 1
|
||||
validation_model: "openrouter/google/gemma-4-31b-it"
|
||||
validation_llm_concurrency: 1
|
||||
report: true
|
||||
@@ -1,97 +1,51 @@
|
||||
workspace:
|
||||
root: ./tmp/narratio-workspace
|
||||
cleanup_after_archive: false
|
||||
|
||||
storage:
|
||||
backend: local
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: "my-dnd-archive"
|
||||
root_prefix: "dnd"
|
||||
region: "us-east-1"
|
||||
# Optional credential env-var names (defaulted when omitted):
|
||||
# access_key_id_env: "OBJECT_STORAGE_KEY_ID"
|
||||
# secret_access_key_env: "OBJECT_STORAGE_KEY"
|
||||
|
||||
spool:
|
||||
root: "/var/spool/narratio"
|
||||
delete_audio_after_archive: false
|
||||
|
||||
archive:
|
||||
enabled: true
|
||||
upload_run: true
|
||||
|
||||
whisperx:
|
||||
transcribe_url: "https://transcription.example.com/transcribe"
|
||||
language: "en"
|
||||
timeout: "30m"
|
||||
retries: 3
|
||||
retry_delay: "2s"
|
||||
concurrency: 2
|
||||
|
||||
seriatim:
|
||||
binary: "seriatim"
|
||||
timeout: "10m"
|
||||
output_schema: "seriatim-intermediate"
|
||||
coalesce_gap: 3.0
|
||||
report: true
|
||||
env:
|
||||
overlap_word_run_gap: 1.0
|
||||
overlap_word_run_reorder_window: 1.0
|
||||
backchannel_max_duration: 2.0
|
||||
filler_max_duration: 1.25
|
||||
# Optional. When omitted entirely, Narratio defaults to seriatim binary + runtime defaults.
|
||||
seriatim: {}
|
||||
|
||||
# Optional runtime overrides. Model/provider can be owned by Audita runtime config.
|
||||
audita:
|
||||
binary: "audita"
|
||||
timeout: "3h"
|
||||
config_path: "/usr/local/etc/audita/config.yml"
|
||||
llm_api_key_env: "AUDITA_LLM_API_KEY"
|
||||
modules:
|
||||
- glossary
|
||||
- homophones
|
||||
- glossary
|
||||
- spoken_word
|
||||
- grammar
|
||||
- homophones
|
||||
- glossary
|
||||
base_url: "https://openrouter.ai/api/v1"
|
||||
model: "openrouter/google/gemma-4-31b-it"
|
||||
llm_concurrency: 1
|
||||
validation_model: ""
|
||||
validation_llm_concurrency: 1
|
||||
report: true
|
||||
|
||||
normalize:
|
||||
# Session-workdir-relative when not absolute.
|
||||
output_path: "transcripts/normalized.json"
|
||||
output_schema: "seriatim-intermediate"
|
||||
report: true
|
||||
|
||||
trim:
|
||||
enabled: true
|
||||
# Session-workdir-relative when not absolute.
|
||||
output_path: "transcripts/trimmed.json"
|
||||
bounds:
|
||||
prompt_id: "dnd_session.bounds"
|
||||
# Empty means use prompt default profile.
|
||||
profile_id: ""
|
||||
transcript_input_name: "transcript"
|
||||
output_path: "artifacts/session_bounds.json"
|
||||
timeout: "10m"
|
||||
render_debug: false
|
||||
render_output_path: "artifacts/session_bounds.render.json"
|
||||
seriatim:
|
||||
report: false
|
||||
|
||||
# Optional Scriptorium integration for analyze artifacts.
|
||||
scriptorium:
|
||||
binary: "scriptorium"
|
||||
config_path: "/etc/scriptorium/config.yml"
|
||||
timeout: "10m"
|
||||
render_debug: false
|
||||
config_path: "/usr/local/etc/scriptorium/config.yml"
|
||||
artifacts:
|
||||
session_recap:
|
||||
enabled: true
|
||||
prompt_id: "dnd.session_recap"
|
||||
profile_id: "local-quality"
|
||||
output_path: "artifacts/session_recap.md"
|
||||
timeout: "10m"
|
||||
# Optional per-artifact override of global scriptorium.render_debug.
|
||||
# render_debug: true
|
||||
inputs:
|
||||
transcript:
|
||||
# Available transcript sources:
|
||||
# - trimmed_transcript (recommended for session_recap)
|
||||
# - normalized_transcript (recommended for future full-session analysis)
|
||||
# - processed_transcript (raw Audita-polished output)
|
||||
source: "trimmed_transcript"
|
||||
required: true
|
||||
previous_recap:
|
||||
source: "previous_session_artifact"
|
||||
artifact: "session_recap"
|
||||
# Optional: set when previous recap is available.
|
||||
path: ""
|
||||
required: false
|
||||
vars:
|
||||
session_id: true
|
||||
@@ -99,11 +53,3 @@ scriptorium:
|
||||
campaign_name: true
|
||||
previous_session_id: true
|
||||
output_kind: "session_recap"
|
||||
|
||||
analyzer:
|
||||
timeout: 20m
|
||||
artifacts:
|
||||
output_dir: artifacts
|
||||
|
||||
notification:
|
||||
timeout: 10s
|
||||
|
||||
@@ -4,7 +4,10 @@ date: 2026-05-03
|
||||
title: Sample Session
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
# Optional S3 input alternative. Do not configure with audio_dir/audio_files.
|
||||
# Narratio prepare lists this prefix and downloads .flac files.
|
||||
# audio_s3:
|
||||
# prefix: "audio/"
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
|
||||
|
||||
12
examples/session.template.yml
Normal file
12
examples/session.template.yml
Normal file
@@ -0,0 +1,12 @@
|
||||
session_id: "{{ session_id }}"
|
||||
campaign: sample-campaign
|
||||
date: ""
|
||||
title: ""
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
# Optional S3 input alternative. Do not configure with audio_dir/audio_files.
|
||||
# audio_s3:
|
||||
# prefix: "audio/{{ session_id }}/"
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
25
go.mod
25
go.mod
@@ -2,4 +2,27 @@ module gitea.maximumdirect.net/eric/narratio
|
||||
|
||||
go 1.25.0
|
||||
|
||||
require gopkg.in/yaml.v3 v3.0.1
|
||||
require (
|
||||
github.com/aws/aws-sdk-go-v2/config v1.32.17
|
||||
github.com/aws/aws-sdk-go-v2/service/s3 v1.101.0
|
||||
github.com/aws/smithy-go v1.25.1
|
||||
gopkg.in/yaml.v3 v3.0.1
|
||||
)
|
||||
|
||||
require (
|
||||
github.com/aws/aws-sdk-go-v2 v1.41.7 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.10 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/credentials v1.19.16 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.23 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.23 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.23 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.24 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.9 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.15 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.23 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.23 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/signin v1.0.11 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/sso v1.30.17 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.21 // indirect
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.42.1 // indirect
|
||||
)
|
||||
|
||||
36
go.sum
36
go.sum
@@ -1,3 +1,39 @@
|
||||
github.com/aws/aws-sdk-go-v2 v1.41.7 h1:DWpAJt66FmnnaRIOT/8ASTucrvuDPZASqhhLey6tLY8=
|
||||
github.com/aws/aws-sdk-go-v2 v1.41.7/go.mod h1:4LAfZOPHNVNQEckOACQx60Y8pSRjIkNZQz1w92xpMJc=
|
||||
github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.10 h1:gx1AwW1Iyk9Z9dD9F4akX5gnN3QZwUB20GGKH/I+Rho=
|
||||
github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.10/go.mod h1:qqY157uZoqm5OXq/amuaBJyC9hgBCBQnsaWnPe905GY=
|
||||
github.com/aws/aws-sdk-go-v2/config v1.32.17 h1:FpL4/758/diKwqbytU0prpuiu60fgXKUWCpDJtApclU=
|
||||
github.com/aws/aws-sdk-go-v2/config v1.32.17/go.mod h1:OXqUMzgXytfoF9JaKkhrOYsyh72t9G+MJH8mMRaexOE=
|
||||
github.com/aws/aws-sdk-go-v2/credentials v1.19.16 h1:r3RJBuU7X9ibt8RHbMjWE6y60QbKBiII6wSrXnapxSU=
|
||||
github.com/aws/aws-sdk-go-v2/credentials v1.19.16/go.mod h1:6cx7zqDENJDbBIIWX6P8s0h6hqHC8Avbjh9Dseo27ug=
|
||||
github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.23 h1:UuSfcORqNSz/ey3VPRS8TcVH2Ikf0/sC+Hdj400QI6U=
|
||||
github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.23/go.mod h1:+G/OSGiOFnSOkYloKj/9M35s74LgVAdJBSD5lsFfqKg=
|
||||
github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.23 h1:GpT/TrnBYuE5gan2cZbTtvP+JlHsutdmlV2YfEyNde0=
|
||||
github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.23/go.mod h1:xYWD6BS9ywC5bS3sz9Xh04whO/hzK2plt2Zkyrp4JuA=
|
||||
github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.23 h1:bpd8vxhlQi2r1hiueOw02f/duEPTMK59Q4QMAoTTtTo=
|
||||
github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.23/go.mod h1:15DfR2nw+CRHIk0tqNyifu3G1YdAOy68RftkhMDDwYk=
|
||||
github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.24 h1:OQqn11BtaYv1WLUowvcA30MpzIu8Ti4pcLPIIyoKZrA=
|
||||
github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.24/go.mod h1:X5ZJyfwVrWA96GzPmUCWFQaEARPR7gCrpq2E92PJwAE=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.9 h1:FLudkZLt5ci0ozzgkVo8BJGwvqNaZbTWb3UcucAateA=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.9/go.mod h1:w7wZ/s9qK7c8g4al+UyoF1Sp/Z45UwMGcqIzLWVQHWk=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.15 h1:ieLCO1JxUWuxTZ1cRd0GAaeX7O6cIxnwk7tc1LsQhC4=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.15/go.mod h1:e3IzZvQ3kAWNykvE0Tr0RDZCMFInMvhku3qNpcIQXhM=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.23 h1:pbrxO/kuIwgEsOPLkaHu0O+m4fNgLU8B3vxQ+72jTPw=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.23/go.mod h1:/CMNUqoj46HpS3MNRDEDIwcgEnrtZlKRaHNaHxIFpNA=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.23 h1:03xatSQO4+AM1lTAbnRg5OK528EUg744nW7F73U8DKw=
|
||||
github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.23/go.mod h1:M8l3mwgx5ToK7wot2sBBce/ojzgnPzZXUV445gTSyE8=
|
||||
github.com/aws/aws-sdk-go-v2/service/s3 v1.101.0 h1:etqBTKY581iwLL/H/S2sVgk3C9lAsTJFeXWFDsDcWOU=
|
||||
github.com/aws/aws-sdk-go-v2/service/s3 v1.101.0/go.mod h1:L2dcoOgS2VSgbPLvpak2NyUPsO1TBN7M45Z4H7DlRc4=
|
||||
github.com/aws/aws-sdk-go-v2/service/signin v1.0.11 h1:TdJ+HdzOBhU8+iVAOGUTU63VXopcumCOF1paFulHWZc=
|
||||
github.com/aws/aws-sdk-go-v2/service/signin v1.0.11/go.mod h1:R82ZRExE/nheo0N+T8zHPcLRTcH8MGsnR3BiVGX0TwI=
|
||||
github.com/aws/aws-sdk-go-v2/service/sso v1.30.17 h1:7byT8HUWrgoRp6sXjxtZwgOKfhss5fW6SkLBtqzgRoE=
|
||||
github.com/aws/aws-sdk-go-v2/service/sso v1.30.17/go.mod h1:xNWknVi4Ezm1vg1QsB/5EWpAJURq22uqd38U8qKvOJc=
|
||||
github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.21 h1:+1Kl1zx6bWi4X7cKi3VYh29h8BvsCoHQEQ6ST9X8w7w=
|
||||
github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.21/go.mod h1:4vIRDq+CJB2xFAXZ+YgGUTiEft7oAQlhIs71xcSeuVg=
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.42.1 h1:F/M5Y9I3nwr2IEpshZgh1GeHpOItExNM9L1euNuh/fk=
|
||||
github.com/aws/aws-sdk-go-v2/service/sts v1.42.1/go.mod h1:mTNxImtovCOEEuD65mKW7DCsL+2gjEH+RPEAexAzAio=
|
||||
github.com/aws/smithy-go v1.25.1 h1:J8ERsGSU7d+aCmdQur5Txg6bVoYelvQJgtZehD12GkI=
|
||||
github.com/aws/smithy-go v1.25.1/go.mod h1:YE2RhdIuDbA5E5bTdciG9KrW3+TiEONeUWCqxX9i1Fc=
|
||||
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
|
||||
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
|
||||
@@ -24,6 +24,12 @@ type PolishRequest struct {
|
||||
Modules []string
|
||||
BaseURL string
|
||||
Model string
|
||||
TranscriptDescription string
|
||||
ConfigPath string
|
||||
OutputSchema string
|
||||
WorkDirRetention string
|
||||
TotalLLMConcurrency *int
|
||||
ProposalLLMConcurrency *int
|
||||
ValidationModel string
|
||||
ValidationLLMConcurrency *int
|
||||
StdoutLogPath string
|
||||
|
||||
@@ -21,7 +21,12 @@ type SubprocessRunnerConfig struct {
|
||||
Modules []string
|
||||
BaseURL string
|
||||
Model string
|
||||
LLMConcurrency *int
|
||||
TranscriptDescription string
|
||||
ConfigPath string
|
||||
OutputSchema string
|
||||
WorkDirRetention string
|
||||
TotalLLMConcurrency *int
|
||||
ProposalLLMConcurrency *int
|
||||
ValidationModel string
|
||||
ValidationLLMConcurrency *int
|
||||
Report bool
|
||||
@@ -35,7 +40,12 @@ type SubprocessRunner struct {
|
||||
modules []string
|
||||
baseURL string
|
||||
model string
|
||||
llmConcurrency *int
|
||||
transcriptDescription string
|
||||
configPath string
|
||||
outputSchema string
|
||||
workDirRetention string
|
||||
totalLLMConcurrency *int
|
||||
proposalLLMConcurrency *int
|
||||
validationModel string
|
||||
validationLLMConcurrency *int
|
||||
report bool
|
||||
@@ -49,7 +59,12 @@ func NewSubprocessRunnerFromConfigValues(
|
||||
modules []string,
|
||||
baseURL string,
|
||||
model string,
|
||||
llmConcurrency *int,
|
||||
transcriptDescription string,
|
||||
configPath string,
|
||||
outputSchema string,
|
||||
workDirRetention string,
|
||||
totalLLMConcurrency *int,
|
||||
proposalLLMConcurrency *int,
|
||||
validationModel string,
|
||||
validationLLMConcurrency *int,
|
||||
report bool,
|
||||
@@ -68,7 +83,12 @@ func NewSubprocessRunnerFromConfigValues(
|
||||
Modules: modules,
|
||||
BaseURL: baseURL,
|
||||
Model: model,
|
||||
LLMConcurrency: llmConcurrency,
|
||||
TranscriptDescription: transcriptDescription,
|
||||
ConfigPath: configPath,
|
||||
OutputSchema: outputSchema,
|
||||
WorkDirRetention: workDirRetention,
|
||||
TotalLLMConcurrency: totalLLMConcurrency,
|
||||
ProposalLLMConcurrency: proposalLLMConcurrency,
|
||||
ValidationModel: validationModel,
|
||||
ValidationLLMConcurrency: validationLLMConcurrency,
|
||||
Report: report,
|
||||
@@ -83,33 +103,39 @@ func NewSubprocessRunner(cfg SubprocessRunnerConfig) (*SubprocessRunner, error)
|
||||
if cfg.Timeout <= 0 {
|
||||
return nil, fmt.Errorf("audita timeout must be > 0")
|
||||
}
|
||||
if len(cfg.Modules) == 0 {
|
||||
return nil, fmt.Errorf("audita modules must include at least one module")
|
||||
}
|
||||
for i, module := range cfg.Modules {
|
||||
if strings.TrimSpace(module) == "" {
|
||||
return nil, fmt.Errorf("audita module at index %d is empty", i)
|
||||
}
|
||||
}
|
||||
if strings.TrimSpace(cfg.BaseURL) == "" {
|
||||
return nil, fmt.Errorf("audita base url is required")
|
||||
}
|
||||
u, err := url.Parse(cfg.BaseURL)
|
||||
if err != nil || u.Scheme == "" || u.Host == "" {
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("audita base url %q is invalid: %w", cfg.BaseURL, err)
|
||||
if strings.TrimSpace(cfg.BaseURL) != "" {
|
||||
u, err := url.Parse(cfg.BaseURL)
|
||||
if err != nil || u.Scheme == "" || u.Host == "" {
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("audita base url %q is invalid: %w", cfg.BaseURL, err)
|
||||
}
|
||||
return nil, fmt.Errorf("audita base url %q is invalid", cfg.BaseURL)
|
||||
}
|
||||
return nil, fmt.Errorf("audita base url %q is invalid", cfg.BaseURL)
|
||||
}
|
||||
if strings.TrimSpace(cfg.Model) == "" {
|
||||
return nil, fmt.Errorf("audita model is required")
|
||||
if cfg.TotalLLMConcurrency != nil && *cfg.TotalLLMConcurrency <= 0 {
|
||||
return nil, fmt.Errorf("audita total llm concurrency must be > 0 when provided")
|
||||
}
|
||||
if cfg.LLMConcurrency != nil && *cfg.LLMConcurrency <= 0 {
|
||||
return nil, fmt.Errorf("audita llm concurrency must be > 0 when provided")
|
||||
if cfg.ProposalLLMConcurrency != nil && *cfg.ProposalLLMConcurrency <= 0 {
|
||||
return nil, fmt.Errorf("audita proposal llm concurrency must be > 0 when provided")
|
||||
}
|
||||
if cfg.ValidationLLMConcurrency != nil && *cfg.ValidationLLMConcurrency <= 0 {
|
||||
return nil, fmt.Errorf("audita validation llm concurrency must be > 0 when provided")
|
||||
}
|
||||
switch strings.TrimSpace(cfg.OutputSchema) {
|
||||
case "", "bare-segments", "audita-v1":
|
||||
default:
|
||||
return nil, fmt.Errorf("audita output schema must be one of: bare-segments, audita-v1")
|
||||
}
|
||||
switch strings.TrimSpace(cfg.WorkDirRetention) {
|
||||
case "", "always", "auto", "never":
|
||||
default:
|
||||
return nil, fmt.Errorf("audita work dir retention must be one of: always, auto, never")
|
||||
}
|
||||
|
||||
modules := make([]string, len(cfg.Modules))
|
||||
for i, m := range cfg.Modules {
|
||||
@@ -123,7 +149,12 @@ func NewSubprocessRunner(cfg SubprocessRunnerConfig) (*SubprocessRunner, error)
|
||||
modules: modules,
|
||||
baseURL: strings.TrimSpace(cfg.BaseURL),
|
||||
model: strings.TrimSpace(cfg.Model),
|
||||
llmConcurrency: cfg.LLMConcurrency,
|
||||
transcriptDescription: strings.TrimSpace(cfg.TranscriptDescription),
|
||||
configPath: strings.TrimSpace(cfg.ConfigPath),
|
||||
outputSchema: strings.TrimSpace(cfg.OutputSchema),
|
||||
workDirRetention: strings.TrimSpace(cfg.WorkDirRetention),
|
||||
totalLLMConcurrency: cfg.TotalLLMConcurrency,
|
||||
proposalLLMConcurrency: cfg.ProposalLLMConcurrency,
|
||||
validationModel: strings.TrimSpace(cfg.ValidationModel),
|
||||
validationLLMConcurrency: cfg.ValidationLLMConcurrency,
|
||||
report: cfg.Report,
|
||||
@@ -152,7 +183,7 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
|
||||
}
|
||||
|
||||
reqModules := req.Modules
|
||||
if len(reqModules) == 0 {
|
||||
if reqModules == nil {
|
||||
reqModules = append([]string(nil), r.modules...)
|
||||
}
|
||||
args := r.buildArgs(req, reqModules)
|
||||
@@ -168,14 +199,9 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
|
||||
env["AUDITA_LLM_API_KEY"] = credential
|
||||
credentialPresent = true
|
||||
}
|
||||
primaryConcurrencyViaEnv := false
|
||||
if r.llmConcurrency != nil {
|
||||
env["AUDITA_LLM_CONCURRENCY"] = strconv.Itoa(*r.llmConcurrency)
|
||||
primaryConcurrencyViaEnv = true
|
||||
}
|
||||
|
||||
if req.GeneratedConfigPath != "" {
|
||||
if err := r.writeInvocationConfig(req, args, reqModules, credentialPresent, primaryConcurrencyViaEnv); err != nil {
|
||||
if err := r.writeInvocationConfig(req, args, reqModules, credentialPresent); err != nil {
|
||||
return PolishResult{}, fmt.Errorf("write audita invocation config %q: %w", req.GeneratedConfigPath, err)
|
||||
}
|
||||
}
|
||||
@@ -196,7 +222,7 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
|
||||
req.StderrLogPath,
|
||||
)
|
||||
wrappedMessage = addSubprocessStreamHint(wrappedMessage, err)
|
||||
return r.failureResult(req, reqModules, runRes, credentialPresent, primaryConcurrencyViaEnv), fmt.Errorf(
|
||||
return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf(
|
||||
"%s: %w",
|
||||
wrappedMessage,
|
||||
err,
|
||||
@@ -204,11 +230,11 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
|
||||
}
|
||||
|
||||
if err := validateProcessedOutput(req.OutputProcessedPath); err != nil {
|
||||
return r.failureResult(req, reqModules, runRes, credentialPresent, primaryConcurrencyViaEnv), fmt.Errorf("validate audita processed output %q: %w", req.OutputProcessedPath, err)
|
||||
return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf("validate audita processed output %q: %w", req.OutputProcessedPath, err)
|
||||
}
|
||||
if r.report {
|
||||
if err := validateJSONFile(req.ReportPath); err != nil {
|
||||
return r.failureResult(req, reqModules, runRes, credentialPresent, primaryConcurrencyViaEnv), fmt.Errorf("validate audita report output %q: %w", req.ReportPath, err)
|
||||
return r.failureResult(req, reqModules, runRes, credentialPresent), fmt.Errorf("validate audita report output %q: %w", req.ReportPath, err)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -223,21 +249,25 @@ func (r *SubprocessRunner) Run(ctx context.Context, req PolishRequest) (PolishRe
|
||||
Duration: runRes.Duration,
|
||||
InvokedBinary: r.binary,
|
||||
Metadata: map[string]any{
|
||||
"adapter": "audita_subprocess",
|
||||
"modules": reqModules,
|
||||
"base_url": r.baseURL,
|
||||
"model": r.model,
|
||||
"validation_model": r.validationModel,
|
||||
"validation_llm_concurrency": r.validationLLMConcurrency,
|
||||
"credential_env_var": r.llmAPIKeyEnv,
|
||||
"credential_present": credentialPresent,
|
||||
"primary_llm_concurrency_via_env": primaryConcurrencyViaEnv,
|
||||
"primary_llm_concurrency_env_name": "AUDITA_LLM_CONCURRENCY",
|
||||
"adapter": "audita_subprocess",
|
||||
"modules": reqModules,
|
||||
"base_url": r.baseURL,
|
||||
"model": r.model,
|
||||
"transcript_description": r.transcriptDescription,
|
||||
"config_path": r.configPath,
|
||||
"output_schema": r.outputSchema,
|
||||
"work_dir_retention": r.workDirRetention,
|
||||
"validation_model": r.validationModel,
|
||||
"total_llm_concurrency": r.totalLLMConcurrency,
|
||||
"proposal_llm_concurrency": r.proposalLLMConcurrency,
|
||||
"validation_llm_concurrency": r.validationLLMConcurrency,
|
||||
"credential_env_var": r.llmAPIKeyEnv,
|
||||
"credential_present": credentialPresent,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, runRes subprocess.RunResult, credentialPresent bool, primaryConcurrencyViaEnv bool) PolishResult {
|
||||
func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, runRes subprocess.RunResult, credentialPresent bool) PolishResult {
|
||||
return PolishResult{
|
||||
ProcessedTranscriptPath: req.OutputProcessedPath,
|
||||
ReportPath: req.ReportPath,
|
||||
@@ -249,16 +279,20 @@ func (r *SubprocessRunner) failureResult(req PolishRequest, modules []string, ru
|
||||
Duration: runRes.Duration,
|
||||
InvokedBinary: r.binary,
|
||||
Metadata: map[string]any{
|
||||
"adapter": "audita_subprocess",
|
||||
"modules": modules,
|
||||
"base_url": r.baseURL,
|
||||
"model": r.model,
|
||||
"validation_model": r.validationModel,
|
||||
"validation_llm_concurrency": r.validationLLMConcurrency,
|
||||
"credential_env_var": r.llmAPIKeyEnv,
|
||||
"credential_present": credentialPresent,
|
||||
"primary_llm_concurrency_via_env": primaryConcurrencyViaEnv,
|
||||
"primary_llm_concurrency_env_name": "AUDITA_LLM_CONCURRENCY",
|
||||
"adapter": "audita_subprocess",
|
||||
"modules": modules,
|
||||
"base_url": r.baseURL,
|
||||
"model": r.model,
|
||||
"transcript_description": r.transcriptDescription,
|
||||
"config_path": r.configPath,
|
||||
"output_schema": r.outputSchema,
|
||||
"work_dir_retention": r.workDirRetention,
|
||||
"validation_model": r.validationModel,
|
||||
"total_llm_concurrency": r.totalLLMConcurrency,
|
||||
"proposal_llm_concurrency": r.proposalLLMConcurrency,
|
||||
"validation_llm_concurrency": r.validationLLMConcurrency,
|
||||
"credential_env_var": r.llmAPIKeyEnv,
|
||||
"credential_present": credentialPresent,
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -269,14 +303,38 @@ func (r *SubprocessRunner) buildArgs(req PolishRequest, modules []string) []stri
|
||||
req.MergedTranscriptPath,
|
||||
"--glossary", req.GlossaryPath,
|
||||
"--output", req.OutputProcessedPath,
|
||||
"--modules", strings.Join(modules, ","),
|
||||
"--base-url", r.baseURL,
|
||||
"--model", r.model,
|
||||
"--work-dir", req.WorkDir,
|
||||
}
|
||||
if r.baseURL != "" {
|
||||
args = append(args, "--base-url", r.baseURL)
|
||||
}
|
||||
if r.model != "" {
|
||||
args = append(args, "--model", r.model)
|
||||
}
|
||||
if len(modules) > 0 {
|
||||
args = append(args, "--modules", strings.Join(modules, ","))
|
||||
}
|
||||
if r.report {
|
||||
args = append(args, "--report-json", req.ReportPath)
|
||||
}
|
||||
if r.transcriptDescription != "" {
|
||||
args = append(args, "--transcript-description", r.transcriptDescription)
|
||||
}
|
||||
if r.configPath != "" {
|
||||
args = append(args, "--config", r.configPath)
|
||||
}
|
||||
if r.outputSchema != "" {
|
||||
args = append(args, "--output-schema", r.outputSchema)
|
||||
}
|
||||
if r.workDirRetention != "" {
|
||||
args = append(args, "--work-dir-retention", r.workDirRetention)
|
||||
}
|
||||
if r.totalLLMConcurrency != nil {
|
||||
args = append(args, "--total-llm-concurrency", strconv.Itoa(*r.totalLLMConcurrency))
|
||||
}
|
||||
if r.proposalLLMConcurrency != nil {
|
||||
args = append(args, "--proposal-llm-concurrency", strconv.Itoa(*r.proposalLLMConcurrency))
|
||||
}
|
||||
if r.validationModel != "" {
|
||||
args = append(args, "--validation-model", r.validationModel)
|
||||
}
|
||||
@@ -286,29 +344,31 @@ func (r *SubprocessRunner) buildArgs(req PolishRequest, modules []string) []stri
|
||||
return args
|
||||
}
|
||||
|
||||
func (r *SubprocessRunner) writeInvocationConfig(req PolishRequest, args []string, modules []string, credentialPresent bool, primaryConcurrencyViaEnv bool) error {
|
||||
func (r *SubprocessRunner) writeInvocationConfig(req PolishRequest, args []string, modules []string, credentialPresent bool) error {
|
||||
payload := map[string]any{
|
||||
"schema": "audita.generated.v1",
|
||||
"binary": r.binary,
|
||||
"args": args,
|
||||
"timeout": r.timeout.String(),
|
||||
"modules": modules,
|
||||
"base_url": r.baseURL,
|
||||
"model": r.model,
|
||||
"validation_model": r.validationModel,
|
||||
"validation_llm_concurrency": r.validationLLMConcurrency,
|
||||
"report_enabled": r.report,
|
||||
"merged_transcript_path": req.MergedTranscriptPath,
|
||||
"glossary_path": req.GlossaryPath,
|
||||
"output_path": req.OutputProcessedPath,
|
||||
"report_path": req.ReportPath,
|
||||
"work_dir": req.WorkDir,
|
||||
"credential_env_var": r.llmAPIKeyEnv,
|
||||
"credential_present": credentialPresent,
|
||||
"primary_llm_concurrency_via_env": primaryConcurrencyViaEnv,
|
||||
}
|
||||
if r.llmConcurrency != nil {
|
||||
payload["llm_concurrency"] = *r.llmConcurrency
|
||||
"schema": "audita.generated.v1",
|
||||
"binary": r.binary,
|
||||
"args": args,
|
||||
"timeout": r.timeout.String(),
|
||||
"modules": modules,
|
||||
"base_url": r.baseURL,
|
||||
"model": r.model,
|
||||
"transcript_description": r.transcriptDescription,
|
||||
"config_path": r.configPath,
|
||||
"output_schema": r.outputSchema,
|
||||
"work_dir_retention": r.workDirRetention,
|
||||
"validation_model": r.validationModel,
|
||||
"total_llm_concurrency": r.totalLLMConcurrency,
|
||||
"proposal_llm_concurrency": r.proposalLLMConcurrency,
|
||||
"validation_llm_concurrency": r.validationLLMConcurrency,
|
||||
"report_enabled": r.report,
|
||||
"merged_transcript_path": req.MergedTranscriptPath,
|
||||
"glossary_path": req.GlossaryPath,
|
||||
"output_path": req.OutputProcessedPath,
|
||||
"report_path": req.ReportPath,
|
||||
"work_dir": req.WorkDir,
|
||||
"credential_env_var": r.llmAPIKeyEnv,
|
||||
"credential_present": credentialPresent,
|
||||
}
|
||||
return subprocess.WriteYAMLAtomic(req.GeneratedConfigPath, payload, 0o644)
|
||||
}
|
||||
|
||||
@@ -25,7 +25,8 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
|
||||
|
||||
wrapper := writeAuditaHelperWrapper(t)
|
||||
llmConcurrency := 1
|
||||
totalLLMConcurrency := 3
|
||||
proposalLLMConcurrency := 2
|
||||
validationLLMConcurrency := 2
|
||||
runner, err := NewSubprocessRunner(SubprocessRunnerConfig{
|
||||
Binary: wrapper,
|
||||
@@ -34,7 +35,12 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
|
||||
Modules: []string{"glossary", "homophones", "glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
TranscriptDescription: "Campaign Session 42",
|
||||
ConfigPath: "/etc/audita/config.yml",
|
||||
OutputSchema: "audita-v1",
|
||||
WorkDirRetention: "auto",
|
||||
TotalLLMConcurrency: &totalLLMConcurrency,
|
||||
ProposalLLMConcurrency: &proposalLLMConcurrency,
|
||||
ValidationModel: "openrouter/google/gemma-4-31b-it",
|
||||
ValidationLLMConcurrency: &validationLLMConcurrency,
|
||||
Report: true,
|
||||
@@ -93,11 +99,17 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
|
||||
"process", req.MergedTranscriptPath,
|
||||
"--glossary", req.GlossaryPath,
|
||||
"--output", req.OutputProcessedPath,
|
||||
"--modules", "glossary,homophones,glossary",
|
||||
"--work-dir", req.WorkDir,
|
||||
"--base-url", "https://openrouter.ai/api/v1",
|
||||
"--model", "openrouter/google/gemma-4-31b-it",
|
||||
"--work-dir", req.WorkDir,
|
||||
"--modules", "glossary,homophones,glossary",
|
||||
"--report-json", req.ReportPath,
|
||||
"--transcript-description", "Campaign Session 42",
|
||||
"--config", "/etc/audita/config.yml",
|
||||
"--output-schema", "audita-v1",
|
||||
"--work-dir-retention", "auto",
|
||||
"--total-llm-concurrency", "3",
|
||||
"--proposal-llm-concurrency", "2",
|
||||
"--validation-model", "openrouter/google/gemma-4-31b-it",
|
||||
"--validation-llm-concurrency", "2",
|
||||
}
|
||||
@@ -107,8 +119,8 @@ func TestSubprocessRunnerSuccessArgsEnvAndValidation(t *testing.T) {
|
||||
if rec.Env["AUDITA_LLM_API_KEY"] != "super-secret" {
|
||||
t.Fatalf("AUDITA_LLM_API_KEY = %q, want propagated secret", rec.Env["AUDITA_LLM_API_KEY"])
|
||||
}
|
||||
if rec.Env["AUDITA_LLM_CONCURRENCY"] != "1" {
|
||||
t.Fatalf("AUDITA_LLM_CONCURRENCY = %q, want 1", rec.Env["AUDITA_LLM_CONCURRENCY"])
|
||||
if rec.Env["AUDITA_LLM_CONCURRENCY"] != "" {
|
||||
t.Fatalf("AUDITA_LLM_CONCURRENCY = %q, want empty/omitted", rec.Env["AUDITA_LLM_CONCURRENCY"])
|
||||
}
|
||||
|
||||
cfgData, err := os.ReadFile(req.GeneratedConfigPath)
|
||||
@@ -124,16 +136,14 @@ func TestSubprocessRunnerMissingConfiguredCredentialFails(t *testing.T) {
|
||||
if runtime.GOOS == "windows" {
|
||||
t.Skip("helper wrapper script uses /bin/sh")
|
||||
}
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "MISSING_AUDITA_KEY",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: false,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "MISSING_AUDITA_KEY",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
|
||||
@@ -155,16 +165,14 @@ func TestSubprocessRunnerUnconfiguredCredentialEnvOmitsCredential(t *testing.T)
|
||||
recordPath := filepath.Join(t.TempDir(), "record.json")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: false,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
|
||||
@@ -211,6 +219,65 @@ func TestSubprocessRunnerInheritsParentEnvironment(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestSubprocessRunnerOmitsModulesFlagWhenNotConfigured(t *testing.T) {
|
||||
if runtime.GOOS == "windows" {
|
||||
t.Skip("helper wrapper script uses /bin/sh")
|
||||
}
|
||||
t.Setenv("GO_WANT_AUDITA_HELPER", "1")
|
||||
t.Setenv("AUDITA_HELPER_MODE", "success")
|
||||
recordPath := filepath.Join(t.TempDir(), "record.json")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
|
||||
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "",
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
if _, err := runner.Run(context.Background(), req); err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
rec := readAuditaHelperRecord(t, recordPath)
|
||||
for i := 0; i < len(rec.Args); i++ {
|
||||
if rec.Args[i] == "--modules" {
|
||||
t.Fatalf("args contained --modules unexpectedly: %#v", rec.Args)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestSubprocessRunnerOmitsBaseURLAndModelFlagsWhenNotConfigured(t *testing.T) {
|
||||
if runtime.GOOS == "windows" {
|
||||
t.Skip("helper wrapper script uses /bin/sh")
|
||||
}
|
||||
t.Setenv("GO_WANT_AUDITA_HELPER", "1")
|
||||
t.Setenv("AUDITA_HELPER_MODE", "success")
|
||||
recordPath := filepath.Join(t.TempDir(), "record.json")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", recordPath)
|
||||
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
if _, err := runner.Run(context.Background(), req); err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
rec := readAuditaHelperRecord(t, recordPath)
|
||||
for i := 0; i < len(rec.Args); i++ {
|
||||
if rec.Args[i] == "--base-url" {
|
||||
t.Fatalf("args contained --base-url unexpectedly: %#v", rec.Args)
|
||||
}
|
||||
if rec.Args[i] == "--model" {
|
||||
t.Fatalf("args contained --model unexpectedly: %#v", rec.Args)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestSubprocessRunnerSubprocessFailure(t *testing.T) {
|
||||
if runtime.GOOS == "windows" {
|
||||
t.Skip("helper wrapper script uses /bin/sh")
|
||||
@@ -220,16 +287,14 @@ func TestSubprocessRunnerSubprocessFailure(t *testing.T) {
|
||||
t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: true,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: true,
|
||||
})
|
||||
req := auditaReqForTest(t, true)
|
||||
_, err := runner.Run(context.Background(), req)
|
||||
@@ -256,16 +321,14 @@ func TestSubprocessRunnerSubprocessFailureAddsStderrDescriptorHint(t *testing.T)
|
||||
t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: true,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: true,
|
||||
})
|
||||
req := auditaReqForTest(t, true)
|
||||
_, err := runner.Run(context.Background(), req)
|
||||
@@ -286,16 +349,14 @@ func TestSubprocessRunnerMissingOutputFails(t *testing.T) {
|
||||
t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: false,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
_, err := runner.Run(context.Background(), req)
|
||||
@@ -316,16 +377,14 @@ func TestSubprocessRunnerInvalidOutputJSONFails(t *testing.T) {
|
||||
t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: false,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
_, err := runner.Run(context.Background(), req)
|
||||
@@ -346,16 +405,14 @@ func TestSubprocessRunnerSegmentsMissingFails(t *testing.T) {
|
||||
t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: false,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: false,
|
||||
})
|
||||
req := auditaReqForTest(t, false)
|
||||
_, err := runner.Run(context.Background(), req)
|
||||
@@ -376,16 +433,14 @@ func TestSubprocessRunnerInvalidReportJSONFails(t *testing.T) {
|
||||
t.Setenv("OPENAI_KEY_SOURCE", "super-secret")
|
||||
t.Setenv("AUDITA_HELPER_RECORD_PATH", filepath.Join(t.TempDir(), "record.json"))
|
||||
|
||||
llmConcurrency := 1
|
||||
runner := mustAuditaRunner(t, SubprocessRunnerConfig{
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
Report: true,
|
||||
Binary: writeAuditaHelperWrapper(t),
|
||||
Timeout: mustParseAuditaDuration(t, "2s"),
|
||||
LLMAPIKeyEnv: "OPENAI_KEY_SOURCE",
|
||||
Modules: []string{"glossary"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
Report: true,
|
||||
})
|
||||
req := auditaReqForTest(t, true)
|
||||
_, err := runner.Run(context.Background(), req)
|
||||
@@ -398,11 +453,11 @@ func TestSubprocessRunnerInvalidReportJSONFails(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestSubprocessRunnerConstructorValidation(t *testing.T) {
|
||||
_, err := NewSubprocessRunnerFromConfigValues("", "3h", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", nil, "", nil, true)
|
||||
_, err := NewSubprocessRunnerFromConfigValues("", "3h", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", "", "", "", "", nil, nil, "", nil, true)
|
||||
if err == nil {
|
||||
t.Fatal("expected binary validation error")
|
||||
}
|
||||
_, err = NewSubprocessRunnerFromConfigValues("audita", "bad", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", nil, "", nil, true)
|
||||
_, err = NewSubprocessRunnerFromConfigValues("audita", "bad", "AUDITA_LLM_API_KEY", []string{"glossary"}, "https://openrouter.ai/api/v1", "openrouter/google/gemma-4-31b-it", "", "", "", "", nil, nil, "", nil, true)
|
||||
if err == nil {
|
||||
t.Fatal("expected timeout parse error")
|
||||
}
|
||||
|
||||
29
internal/adapters/storage/factory.go
Normal file
29
internal/adapters/storage/factory.go
Normal file
@@ -0,0 +1,29 @@
|
||||
package storage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
// NewObjectStoreFromConfig constructs a remote object store from resolved config.
|
||||
func NewObjectStoreFromConfig(ctx context.Context, cfg *config.Config) (ObjectStore, error) {
|
||||
if cfg == nil || cfg.Pipeline == nil {
|
||||
return nil, fmt.Errorf("pipeline config is required")
|
||||
}
|
||||
|
||||
if strings.EqualFold(strings.TrimSpace(cfg.Pipeline.Storage.Backend), "s3") {
|
||||
if cfg.Pipeline.Storage.S3 == nil {
|
||||
return nil, fmt.Errorf("pipeline.storage.s3 is required when pipeline.storage.backend is s3")
|
||||
}
|
||||
return NewS3BackendFromConfig(ctx, *cfg.Pipeline.Storage.S3)
|
||||
}
|
||||
|
||||
if cfg.Pipeline.Storage.S3 != nil && strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket) != "" {
|
||||
return NewS3BackendFromConfig(ctx, *cfg.Pipeline.Storage.S3)
|
||||
}
|
||||
|
||||
return nil, fmt.Errorf("no remote object store backend is configured")
|
||||
}
|
||||
56
internal/adapters/storage/factory_test.go
Normal file
56
internal/adapters/storage/factory_test.go
Normal file
@@ -0,0 +1,56 @@
|
||||
package storage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
func TestNewObjectStoreFromConfigBuildsS3WhenBackendIsS3(t *testing.T) {
|
||||
original := newS3Client
|
||||
t.Cleanup(func() { newS3Client = original })
|
||||
newS3Client = func(_ context.Context, _ s3ClientOptions) (s3API, error) {
|
||||
return &fakeS3API{}, nil
|
||||
}
|
||||
|
||||
store, err := NewObjectStoreFromConfig(context.Background(), &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Storage: config.StorageConfig{
|
||||
Backend: "s3",
|
||||
S3: &config.StorageS3Config{
|
||||
Bucket: "my-archive",
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("NewObjectStoreFromConfig() error = %v", err)
|
||||
}
|
||||
if _, ok := store.(*S3Backend); !ok {
|
||||
t.Fatalf("store type = %T, want *S3Backend", store)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewObjectStoreFromConfigRequiresS3ConfigWhenBackendIsS3(t *testing.T) {
|
||||
_, err := NewObjectStoreFromConfig(context.Background(), &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Storage: config.StorageConfig{Backend: "s3"},
|
||||
},
|
||||
})
|
||||
if err == nil || !strings.Contains(err.Error(), "pipeline.storage.s3 is required") {
|
||||
t.Fatalf("NewObjectStoreFromConfig() error = %v, want missing storage.s3 error", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewObjectStoreFromConfigNoRemoteBackendConfigured(t *testing.T) {
|
||||
_, err := NewObjectStoreFromConfig(context.Background(), &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Storage: config.StorageConfig{Backend: "local"},
|
||||
},
|
||||
})
|
||||
if err == nil || !strings.Contains(err.Error(), "no remote object store backend is configured") {
|
||||
t.Fatalf("NewObjectStoreFromConfig() error = %v, want no-backend error", err)
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,14 @@
|
||||
package storage
|
||||
|
||||
import "context"
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// NoopBackend is a deterministic no-op archive/storage adapter.
|
||||
type NoopBackend struct{}
|
||||
@@ -18,6 +26,21 @@ type FakeBackend struct {
|
||||
Requests []ArchiveRequest
|
||||
Err error
|
||||
Result ArchiveResult
|
||||
|
||||
Objects map[string]FakeObject
|
||||
Uploads []FakeUploadCall
|
||||
|
||||
ListErr error
|
||||
DownloadErr error
|
||||
UploadErr error
|
||||
ExistsErr error
|
||||
}
|
||||
|
||||
// FakeUploadCall captures one upload invocation in call order.
|
||||
type FakeUploadCall struct {
|
||||
LocalPath string
|
||||
Key string
|
||||
Options UploadOptions
|
||||
}
|
||||
|
||||
// Archive records request and returns configured response.
|
||||
@@ -38,3 +61,148 @@ func (f *FakeBackend) Archive(ctx context.Context, req ArchiveRequest) (ArchiveR
|
||||
}
|
||||
return res, nil
|
||||
}
|
||||
|
||||
// FakeObject is a deterministic fake object-store record.
|
||||
type FakeObject struct {
|
||||
Key string
|
||||
Data []byte
|
||||
Metadata map[string]string
|
||||
ETag string
|
||||
LastModified *time.Time
|
||||
}
|
||||
|
||||
// SeedObject inserts or replaces an object in the fake object store.
|
||||
func (f *FakeBackend) SeedObject(obj FakeObject) {
|
||||
if f.Objects == nil {
|
||||
f.Objects = map[string]FakeObject{}
|
||||
}
|
||||
key := normalizeObjectKey(obj.Key)
|
||||
obj.Key = key
|
||||
obj.Data = append([]byte(nil), obj.Data...)
|
||||
obj.Metadata = copyMetadata(obj.Metadata)
|
||||
f.Objects[key] = obj
|
||||
}
|
||||
|
||||
// List returns deterministic prefix-filtered objects.
|
||||
func (f *FakeBackend) List(ctx context.Context, prefix string) ([]ObjectInfo, error) {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if f.ListErr != nil {
|
||||
return nil, f.ListErr
|
||||
}
|
||||
|
||||
normalizedPrefix := normalizeObjectKey(prefix)
|
||||
keys := make([]string, 0, len(f.Objects))
|
||||
for key := range f.Objects {
|
||||
if strings.HasPrefix(key, normalizedPrefix) {
|
||||
keys = append(keys, key)
|
||||
}
|
||||
}
|
||||
sort.Strings(keys)
|
||||
|
||||
out := make([]ObjectInfo, 0, len(keys))
|
||||
for _, key := range keys {
|
||||
obj := f.Objects[key]
|
||||
out = append(out, ObjectInfo{
|
||||
Key: obj.Key,
|
||||
Size: int64(len(obj.Data)),
|
||||
ETag: obj.ETag,
|
||||
LastModified: obj.LastModified,
|
||||
})
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// Download writes one object to a local path.
|
||||
func (f *FakeBackend) Download(ctx context.Context, key, localPath string) error {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return err
|
||||
}
|
||||
if f.DownloadErr != nil {
|
||||
return f.DownloadErr
|
||||
}
|
||||
if strings.TrimSpace(localPath) == "" {
|
||||
return fmt.Errorf("download object: local path is required")
|
||||
}
|
||||
|
||||
obj, ok := f.Objects[normalizeObjectKey(key)]
|
||||
if !ok {
|
||||
return fmt.Errorf("download object %q: %w", key, os.ErrNotExist)
|
||||
}
|
||||
|
||||
if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
|
||||
return fmt.Errorf("download object %q: create parent directory: %w", key, err)
|
||||
}
|
||||
if err := os.WriteFile(localPath, obj.Data, 0o644); err != nil {
|
||||
return fmt.Errorf("download object %q: write local file: %w", key, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Upload reads a local file and stores it under key.
|
||||
func (f *FakeBackend) Upload(ctx context.Context, localPath, key string, opts UploadOptions) (ObjectInfo, error) {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return ObjectInfo{}, err
|
||||
}
|
||||
if f.UploadErr != nil {
|
||||
return ObjectInfo{}, f.UploadErr
|
||||
}
|
||||
if strings.TrimSpace(localPath) == "" {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object: local path is required")
|
||||
}
|
||||
if strings.TrimSpace(key) == "" {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object: key is required")
|
||||
}
|
||||
|
||||
data, err := os.ReadFile(localPath)
|
||||
if err != nil {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object %q from %q: %w", key, localPath, err)
|
||||
}
|
||||
|
||||
normalizedKey := normalizeObjectKey(key)
|
||||
f.Uploads = append(f.Uploads, FakeUploadCall{
|
||||
LocalPath: localPath,
|
||||
Key: normalizedKey,
|
||||
Options: UploadOptions{
|
||||
Metadata: copyMetadata(opts.Metadata),
|
||||
ContentType: opts.ContentType,
|
||||
},
|
||||
})
|
||||
now := time.Now().UTC()
|
||||
obj := FakeObject{
|
||||
Key: normalizedKey,
|
||||
Data: data,
|
||||
Metadata: copyMetadata(opts.Metadata),
|
||||
LastModified: &now,
|
||||
}
|
||||
f.SeedObject(obj)
|
||||
return ObjectInfo{
|
||||
Key: normalizedKey,
|
||||
Size: int64(len(data)),
|
||||
LastModified: &now,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Exists checks object presence.
|
||||
func (f *FakeBackend) Exists(ctx context.Context, key string) (bool, error) {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return false, err
|
||||
}
|
||||
if f.ExistsErr != nil {
|
||||
return false, f.ExistsErr
|
||||
}
|
||||
_, ok := f.Objects[normalizeObjectKey(key)]
|
||||
return ok, nil
|
||||
}
|
||||
|
||||
func copyMetadata(in map[string]string) map[string]string {
|
||||
if len(in) == 0 {
|
||||
return nil
|
||||
}
|
||||
out := make(map[string]string, len(in))
|
||||
for k, v := range in {
|
||||
out[k] = v
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -3,6 +3,9 @@ package storage
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
@@ -29,3 +32,84 @@ func TestFakeBackendError(t *testing.T) {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFakeBackendListPrefixFiltering(t *testing.T) {
|
||||
fake := &FakeBackend{}
|
||||
fake.SeedObject(FakeObject{Key: "dnd/campaigns/forsaken/audio/a.flac", Data: []byte("a")})
|
||||
fake.SeedObject(FakeObject{Key: "dnd/campaigns/forsaken/audio/b.flac", Data: []byte("b")})
|
||||
fake.SeedObject(FakeObject{Key: "dnd/campaigns/other/audio/c.flac", Data: []byte("c")})
|
||||
|
||||
items, err := fake.List(context.Background(), "dnd/campaigns/forsaken/audio/")
|
||||
if err != nil {
|
||||
t.Fatalf("List() error = %v", err)
|
||||
}
|
||||
if len(items) != 2 {
|
||||
t.Fatalf("List() len = %d, want 2", len(items))
|
||||
}
|
||||
if items[0].Key != "dnd/campaigns/forsaken/audio/a.flac" || items[1].Key != "dnd/campaigns/forsaken/audio/b.flac" {
|
||||
t.Fatalf("List() keys = %#v", items)
|
||||
}
|
||||
}
|
||||
|
||||
func TestFakeBackendDownload(t *testing.T) {
|
||||
fake := &FakeBackend{}
|
||||
fake.SeedObject(FakeObject{Key: "audio/a.flac", Data: []byte("audio-a")})
|
||||
|
||||
dst := filepath.Join(t.TempDir(), "nested", "a.flac")
|
||||
if err := fake.Download(context.Background(), "audio/a.flac", dst); err != nil {
|
||||
t.Fatalf("Download() error = %v", err)
|
||||
}
|
||||
data, err := os.ReadFile(dst)
|
||||
if err != nil {
|
||||
t.Fatalf("ReadFile() error = %v", err)
|
||||
}
|
||||
if string(data) != "audio-a" {
|
||||
t.Fatalf("downloaded content = %q, want %q", string(data), "audio-a")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFakeBackendUploadAndExists(t *testing.T) {
|
||||
fake := &FakeBackend{}
|
||||
|
||||
local := filepath.Join(t.TempDir(), "upload.txt")
|
||||
if err := os.WriteFile(local, []byte("payload"), 0o644); err != nil {
|
||||
t.Fatalf("WriteFile() error = %v", err)
|
||||
}
|
||||
|
||||
info, err := fake.Upload(context.Background(), local, `runs\id\artifact.txt`, UploadOptions{
|
||||
Metadata: map[string]string{"kind": "artifact"},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("Upload() error = %v", err)
|
||||
}
|
||||
if info.Key != "runs/id/artifact.txt" {
|
||||
t.Fatalf("Upload() key = %q, want normalized key", info.Key)
|
||||
}
|
||||
|
||||
ok, err := fake.Exists(context.Background(), "runs/id/artifact.txt")
|
||||
if err != nil {
|
||||
t.Fatalf("Exists() error = %v", err)
|
||||
}
|
||||
if !ok {
|
||||
t.Fatal("Exists() = false, want true")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFakeBackendObjectErrors(t *testing.T) {
|
||||
fake := &FakeBackend{DownloadErr: errors.New("download fail"), UploadErr: errors.New("upload fail"), ListErr: errors.New("list fail"), ExistsErr: errors.New("exists fail")}
|
||||
|
||||
if _, err := fake.List(context.Background(), "x"); err == nil || !strings.Contains(err.Error(), "list fail") {
|
||||
t.Fatalf("List() error = %v, want list fail", err)
|
||||
}
|
||||
if err := fake.Download(context.Background(), "x", filepath.Join(t.TempDir(), "x")); err == nil || !strings.Contains(err.Error(), "download fail") {
|
||||
t.Fatalf("Download() error = %v, want download fail", err)
|
||||
}
|
||||
local := filepath.Join(t.TempDir(), "x.txt")
|
||||
_ = os.WriteFile(local, []byte("x"), 0o644)
|
||||
if _, err := fake.Upload(context.Background(), local, "x", UploadOptions{}); err == nil || !strings.Contains(err.Error(), "upload fail") {
|
||||
t.Fatalf("Upload() error = %v, want upload fail", err)
|
||||
}
|
||||
if _, err := fake.Exists(context.Background(), "x"); err == nil || !strings.Contains(err.Error(), "exists fail") {
|
||||
t.Fatalf("Exists() error = %v, want exists fail", err)
|
||||
}
|
||||
}
|
||||
|
||||
8
internal/adapters/storage/keys.go
Normal file
8
internal/adapters/storage/keys.go
Normal file
@@ -0,0 +1,8 @@
|
||||
package storage
|
||||
|
||||
import "strings"
|
||||
|
||||
func normalizeObjectKey(key string) string {
|
||||
normalized := strings.ReplaceAll(strings.TrimSpace(key), "\\", "/")
|
||||
return strings.TrimLeft(normalized, "/")
|
||||
}
|
||||
21
internal/adapters/storage/keys_test.go
Normal file
21
internal/adapters/storage/keys_test.go
Normal file
@@ -0,0 +1,21 @@
|
||||
package storage
|
||||
|
||||
import "testing"
|
||||
|
||||
func TestNormalizeObjectKey(t *testing.T) {
|
||||
tests := []struct {
|
||||
in string
|
||||
want string
|
||||
}{
|
||||
{in: `dnd\campaigns\forsaken\a.flac`, want: "dnd/campaigns/forsaken/a.flac"},
|
||||
{in: " /dnd/campaigns/forsaken/a.flac ", want: "dnd/campaigns/forsaken/a.flac"},
|
||||
{in: "//dnd/campaigns/forsaken/a.flac", want: "dnd/campaigns/forsaken/a.flac"},
|
||||
{in: "", want: ""},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
if got := normalizeObjectKey(tt.in); got != tt.want {
|
||||
t.Fatalf("normalizeObjectKey(%q) = %q, want %q", tt.in, got, tt.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
32
internal/adapters/storage/object_store.go
Normal file
32
internal/adapters/storage/object_store.go
Normal file
@@ -0,0 +1,32 @@
|
||||
package storage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
)
|
||||
|
||||
// ObjectStore is a remote object storage boundary used by future prepare/archive work.
|
||||
//
|
||||
// Key invariant:
|
||||
// callers pass full bucket-relative object keys. Backend implementations do not
|
||||
// infer Narratio session semantics and do not prepend root prefixes.
|
||||
type ObjectStore interface {
|
||||
List(ctx context.Context, prefix string) ([]ObjectInfo, error)
|
||||
Download(ctx context.Context, key, localPath string) error
|
||||
Upload(ctx context.Context, localPath, key string, opts UploadOptions) (ObjectInfo, error)
|
||||
Exists(ctx context.Context, key string) (bool, error)
|
||||
}
|
||||
|
||||
// ObjectInfo describes one object in remote storage.
|
||||
type ObjectInfo struct {
|
||||
Key string
|
||||
Size int64
|
||||
ETag string
|
||||
LastModified *time.Time
|
||||
}
|
||||
|
||||
// UploadOptions configures optional object upload metadata.
|
||||
type UploadOptions struct {
|
||||
Metadata map[string]string
|
||||
ContentType string
|
||||
}
|
||||
275
internal/adapters/storage/s3_backend.go
Normal file
275
internal/adapters/storage/s3_backend.go
Normal file
@@ -0,0 +1,275 @@
|
||||
package storage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
awsconfig "github.com/aws/aws-sdk-go-v2/config"
|
||||
"github.com/aws/aws-sdk-go-v2/credentials"
|
||||
"github.com/aws/aws-sdk-go-v2/service/s3"
|
||||
"github.com/aws/aws-sdk-go-v2/service/s3/types"
|
||||
"github.com/aws/smithy-go"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
type s3API interface {
|
||||
ListObjectsV2(ctx context.Context, params *s3.ListObjectsV2Input, optFns ...func(*s3.Options)) (*s3.ListObjectsV2Output, error)
|
||||
GetObject(ctx context.Context, params *s3.GetObjectInput, optFns ...func(*s3.Options)) (*s3.GetObjectOutput, error)
|
||||
PutObject(ctx context.Context, params *s3.PutObjectInput, optFns ...func(*s3.Options)) (*s3.PutObjectOutput, error)
|
||||
HeadObject(ctx context.Context, params *s3.HeadObjectInput, optFns ...func(*s3.Options)) (*s3.HeadObjectOutput, error)
|
||||
}
|
||||
|
||||
// S3Backend is an ObjectStore implementation backed by S3-compatible APIs.
|
||||
type S3Backend struct {
|
||||
bucket string
|
||||
client s3API
|
||||
}
|
||||
|
||||
type s3ClientOptions struct {
|
||||
Region string
|
||||
Endpoint string
|
||||
ForcePathStyle bool
|
||||
AccessKeyID string
|
||||
SecretKey string
|
||||
}
|
||||
|
||||
var newS3Client = func(ctx context.Context, opts s3ClientOptions) (s3API, error) {
|
||||
loadOpts := make([]func(*awsconfig.LoadOptions) error, 0, 1)
|
||||
if strings.TrimSpace(opts.Region) != "" {
|
||||
loadOpts = append(loadOpts, awsconfig.WithRegion(strings.TrimSpace(opts.Region)))
|
||||
}
|
||||
if strings.TrimSpace(opts.AccessKeyID) != "" && strings.TrimSpace(opts.SecretKey) != "" {
|
||||
loadOpts = append(loadOpts, awsconfig.WithCredentialsProvider(
|
||||
credentials.NewStaticCredentialsProvider(
|
||||
strings.TrimSpace(opts.AccessKeyID),
|
||||
strings.TrimSpace(opts.SecretKey),
|
||||
"",
|
||||
),
|
||||
))
|
||||
}
|
||||
awsCfg, err := awsconfig.LoadDefaultConfig(ctx, loadOpts...)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("load aws config: %w", err)
|
||||
}
|
||||
|
||||
return s3.NewFromConfig(awsCfg, func(o *s3.Options) {
|
||||
if strings.TrimSpace(opts.Endpoint) != "" {
|
||||
endpoint := strings.TrimSpace(opts.Endpoint)
|
||||
o.BaseEndpoint = &endpoint
|
||||
}
|
||||
o.UsePathStyle = opts.ForcePathStyle
|
||||
}), nil
|
||||
}
|
||||
|
||||
// NewS3BackendFromConfig builds an S3 backend from resolved config.
|
||||
func NewS3BackendFromConfig(ctx context.Context, cfg config.StorageS3Config) (*S3Backend, error) {
|
||||
bucket := strings.TrimSpace(cfg.Bucket)
|
||||
if bucket == "" {
|
||||
return nil, fmt.Errorf("storage.s3.bucket is required")
|
||||
}
|
||||
|
||||
client, err := newS3Client(ctx, s3ClientOptions{
|
||||
Region: cfg.Region,
|
||||
Endpoint: cfg.Endpoint,
|
||||
ForcePathStyle: cfg.ForcePathStyle,
|
||||
AccessKeyID: s3CredentialFromEnv(orDefaultEnvName(cfg.AccessKeyIDEnv, config.DefaultS3AccessKeyIDEnv)),
|
||||
SecretKey: s3CredentialFromEnv(orDefaultEnvName(cfg.SecretKeyEnv, config.DefaultS3SecretAccessKeyEnv)),
|
||||
})
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("build s3 client: %w", err)
|
||||
}
|
||||
|
||||
return &S3Backend{
|
||||
bucket: bucket,
|
||||
client: client,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func s3CredentialFromEnv(envVarName string) string {
|
||||
name := strings.TrimSpace(envVarName)
|
||||
if name == "" {
|
||||
return ""
|
||||
}
|
||||
value, ok := os.LookupEnv(name)
|
||||
if !ok {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSpace(value)
|
||||
}
|
||||
|
||||
func orDefaultEnvName(name, fallback string) string {
|
||||
trimmed := strings.TrimSpace(name)
|
||||
if trimmed == "" {
|
||||
return fallback
|
||||
}
|
||||
return trimmed
|
||||
}
|
||||
|
||||
// List returns objects under prefix.
|
||||
func (b *S3Backend) List(ctx context.Context, prefix string) ([]ObjectInfo, error) {
|
||||
normalizedPrefix := normalizeObjectKey(prefix)
|
||||
out := make([]ObjectInfo, 0)
|
||||
var token *string
|
||||
|
||||
for {
|
||||
resp, err := b.client.ListObjectsV2(ctx, &s3.ListObjectsV2Input{
|
||||
Bucket: &b.bucket,
|
||||
Prefix: &normalizedPrefix,
|
||||
ContinuationToken: token,
|
||||
})
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("list objects under %q: %w", normalizedPrefix, err)
|
||||
}
|
||||
|
||||
for _, item := range resp.Contents {
|
||||
var lastModified *time.Time
|
||||
if item.LastModified != nil {
|
||||
t := *item.LastModified
|
||||
lastModified = &t
|
||||
}
|
||||
out = append(out, ObjectInfo{
|
||||
Key: normalizeObjectKey(valueOrEmpty(item.Key)),
|
||||
Size: valueOrZeroInt64(item.Size),
|
||||
ETag: strings.Trim(valueOrEmpty(item.ETag), "\""),
|
||||
LastModified: lastModified,
|
||||
})
|
||||
}
|
||||
|
||||
if !valueOrFalseBool(resp.IsTruncated) || resp.NextContinuationToken == nil {
|
||||
break
|
||||
}
|
||||
token = resp.NextContinuationToken
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// Download retrieves one object to localPath, creating parent directories as needed.
|
||||
func (b *S3Backend) Download(ctx context.Context, key, localPath string) error {
|
||||
normalizedKey := normalizeObjectKey(key)
|
||||
if strings.TrimSpace(localPath) == "" {
|
||||
return fmt.Errorf("download object: local path is required")
|
||||
}
|
||||
|
||||
resp, err := b.client.GetObject(ctx, &s3.GetObjectInput{
|
||||
Bucket: &b.bucket,
|
||||
Key: &normalizedKey,
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("download object %q: %w", normalizedKey, err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
if err := os.MkdirAll(filepath.Dir(localPath), 0o755); err != nil {
|
||||
return fmt.Errorf("download object %q: create parent directory: %w", normalizedKey, err)
|
||||
}
|
||||
dst, err := os.Create(localPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("download object %q: create local file: %w", normalizedKey, err)
|
||||
}
|
||||
defer dst.Close()
|
||||
|
||||
if _, err := io.Copy(dst, resp.Body); err != nil {
|
||||
return fmt.Errorf("download object %q: copy body: %w", normalizedKey, err)
|
||||
}
|
||||
if err := dst.Sync(); err != nil {
|
||||
return fmt.Errorf("download object %q: sync local file: %w", normalizedKey, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Upload sends a local file to key.
|
||||
func (b *S3Backend) Upload(ctx context.Context, localPath, key string, opts UploadOptions) (ObjectInfo, error) {
|
||||
normalizedKey := normalizeObjectKey(key)
|
||||
if strings.TrimSpace(localPath) == "" {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object: local path is required")
|
||||
}
|
||||
if normalizedKey == "" {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object: key is required")
|
||||
}
|
||||
|
||||
file, err := os.Open(localPath)
|
||||
if err != nil {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object %q from %q: %w", normalizedKey, localPath, err)
|
||||
}
|
||||
defer file.Close()
|
||||
|
||||
stat, err := file.Stat()
|
||||
if err != nil {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object %q from %q: stat local file: %w", normalizedKey, localPath, err)
|
||||
}
|
||||
|
||||
input := &s3.PutObjectInput{
|
||||
Bucket: &b.bucket,
|
||||
Key: &normalizedKey,
|
||||
Body: file,
|
||||
Metadata: copyMetadata(opts.Metadata),
|
||||
}
|
||||
if strings.TrimSpace(opts.ContentType) != "" {
|
||||
ct := strings.TrimSpace(opts.ContentType)
|
||||
input.ContentType = &ct
|
||||
}
|
||||
|
||||
resp, err := b.client.PutObject(ctx, input)
|
||||
if err != nil {
|
||||
return ObjectInfo{}, fmt.Errorf("upload object %q from %q: %w", normalizedKey, localPath, err)
|
||||
}
|
||||
|
||||
return ObjectInfo{
|
||||
Key: normalizedKey,
|
||||
Size: stat.Size(),
|
||||
ETag: strings.Trim(valueOrEmpty(resp.ETag), "\""),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Exists checks whether one object key exists.
|
||||
func (b *S3Backend) Exists(ctx context.Context, key string) (bool, error) {
|
||||
normalizedKey := normalizeObjectKey(key)
|
||||
_, err := b.client.HeadObject(ctx, &s3.HeadObjectInput{
|
||||
Bucket: &b.bucket,
|
||||
Key: &normalizedKey,
|
||||
})
|
||||
if err == nil {
|
||||
return true, nil
|
||||
}
|
||||
|
||||
var notFound *types.NotFound
|
||||
if errors.As(err, ¬Found) {
|
||||
return false, nil
|
||||
}
|
||||
var apiErr smithy.APIError
|
||||
if errors.As(err, &apiErr) {
|
||||
switch apiErr.ErrorCode() {
|
||||
case "NotFound", "NoSuchKey", "404":
|
||||
return false, nil
|
||||
}
|
||||
}
|
||||
return false, fmt.Errorf("head object %q: %w", normalizedKey, err)
|
||||
}
|
||||
|
||||
func valueOrEmpty(v *string) string {
|
||||
if v == nil {
|
||||
return ""
|
||||
}
|
||||
return *v
|
||||
}
|
||||
|
||||
func valueOrZeroInt64(v *int64) int64 {
|
||||
if v == nil {
|
||||
return 0
|
||||
}
|
||||
return *v
|
||||
}
|
||||
|
||||
func valueOrFalseBool(v *bool) bool {
|
||||
if v == nil {
|
||||
return false
|
||||
}
|
||||
return *v
|
||||
}
|
||||
253
internal/adapters/storage/s3_backend_test.go
Normal file
253
internal/adapters/storage/s3_backend_test.go
Normal file
@@ -0,0 +1,253 @@
|
||||
package storage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/aws/aws-sdk-go-v2/service/s3"
|
||||
"github.com/aws/aws-sdk-go-v2/service/s3/types"
|
||||
"github.com/aws/smithy-go"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
type fakeS3API struct {
|
||||
listOut *s3.ListObjectsV2Output
|
||||
listErr error
|
||||
|
||||
getBody io.ReadCloser
|
||||
getErr error
|
||||
|
||||
putOut *s3.PutObjectOutput
|
||||
putErr error
|
||||
|
||||
headErr error
|
||||
|
||||
lastList *s3.ListObjectsV2Input
|
||||
lastGet *s3.GetObjectInput
|
||||
lastPut *s3.PutObjectInput
|
||||
lastHead *s3.HeadObjectInput
|
||||
}
|
||||
|
||||
func (f *fakeS3API) ListObjectsV2(_ context.Context, params *s3.ListObjectsV2Input, _ ...func(*s3.Options)) (*s3.ListObjectsV2Output, error) {
|
||||
f.lastList = params
|
||||
if f.listErr != nil {
|
||||
return nil, f.listErr
|
||||
}
|
||||
if f.listOut == nil {
|
||||
return &s3.ListObjectsV2Output{}, nil
|
||||
}
|
||||
return f.listOut, nil
|
||||
}
|
||||
|
||||
func (f *fakeS3API) GetObject(_ context.Context, params *s3.GetObjectInput, _ ...func(*s3.Options)) (*s3.GetObjectOutput, error) {
|
||||
f.lastGet = params
|
||||
if f.getErr != nil {
|
||||
return nil, f.getErr
|
||||
}
|
||||
body := f.getBody
|
||||
if body == nil {
|
||||
body = io.NopCloser(strings.NewReader(""))
|
||||
}
|
||||
return &s3.GetObjectOutput{Body: body}, nil
|
||||
}
|
||||
|
||||
func (f *fakeS3API) PutObject(_ context.Context, params *s3.PutObjectInput, _ ...func(*s3.Options)) (*s3.PutObjectOutput, error) {
|
||||
f.lastPut = params
|
||||
if f.putErr != nil {
|
||||
return nil, f.putErr
|
||||
}
|
||||
if f.putOut == nil {
|
||||
return &s3.PutObjectOutput{}, nil
|
||||
}
|
||||
return f.putOut, nil
|
||||
}
|
||||
|
||||
func (f *fakeS3API) HeadObject(_ context.Context, params *s3.HeadObjectInput, _ ...func(*s3.Options)) (*s3.HeadObjectOutput, error) {
|
||||
f.lastHead = params
|
||||
if f.headErr != nil {
|
||||
return nil, f.headErr
|
||||
}
|
||||
return &s3.HeadObjectOutput{}, nil
|
||||
}
|
||||
|
||||
func TestS3BackendListAndKeyNormalization(t *testing.T) {
|
||||
lastModified := time.Date(2026, 5, 16, 12, 0, 0, 0, time.UTC)
|
||||
client := &fakeS3API{
|
||||
listOut: &s3.ListObjectsV2Output{
|
||||
Contents: []types.Object{
|
||||
{Key: strPtr(`dnd\campaigns\forsaken\a.flac`), Size: int64Ptr(7), ETag: strPtr(`"abc"`), LastModified: &lastModified},
|
||||
},
|
||||
},
|
||||
}
|
||||
backend := &S3Backend{bucket: "bucket-1", client: client}
|
||||
|
||||
items, err := backend.List(context.Background(), `dnd\campaigns\`)
|
||||
if err != nil {
|
||||
t.Fatalf("List() error = %v", err)
|
||||
}
|
||||
if len(items) != 1 {
|
||||
t.Fatalf("List() len = %d, want 1", len(items))
|
||||
}
|
||||
if items[0].Key != "dnd/campaigns/forsaken/a.flac" {
|
||||
t.Fatalf("List() key = %q, want normalized slash key", items[0].Key)
|
||||
}
|
||||
if items[0].ETag != "abc" {
|
||||
t.Fatalf("List() ETag = %q, want %q", items[0].ETag, "abc")
|
||||
}
|
||||
if client.lastList == nil || *client.lastList.Prefix != "dnd/campaigns/" {
|
||||
t.Fatalf("List() prefix = %#v, want normalized prefix", client.lastList)
|
||||
}
|
||||
}
|
||||
|
||||
func TestS3BackendDownloadCreatesParentDirectory(t *testing.T) {
|
||||
client := &fakeS3API{getBody: io.NopCloser(strings.NewReader("audio"))}
|
||||
backend := &S3Backend{bucket: "bucket-1", client: client}
|
||||
|
||||
dst := filepath.Join(t.TempDir(), "nested", "clip.flac")
|
||||
if err := backend.Download(context.Background(), `audio\clip.flac`, dst); err != nil {
|
||||
t.Fatalf("Download() error = %v", err)
|
||||
}
|
||||
|
||||
data, err := os.ReadFile(dst)
|
||||
if err != nil {
|
||||
t.Fatalf("ReadFile() error = %v", err)
|
||||
}
|
||||
if string(data) != "audio" {
|
||||
t.Fatalf("downloaded content = %q, want %q", string(data), "audio")
|
||||
}
|
||||
if client.lastGet == nil || *client.lastGet.Key != "audio/clip.flac" {
|
||||
t.Fatalf("GetObject key = %#v, want normalized key", client.lastGet)
|
||||
}
|
||||
}
|
||||
|
||||
func TestS3BackendUploadAndExists(t *testing.T) {
|
||||
client := &fakeS3API{putOut: &s3.PutObjectOutput{ETag: strPtr(`"etag123"`)}}
|
||||
backend := &S3Backend{bucket: "bucket-1", client: client}
|
||||
|
||||
local := filepath.Join(t.TempDir(), "artifact.txt")
|
||||
if err := os.WriteFile(local, []byte("artifact"), 0o644); err != nil {
|
||||
t.Fatalf("WriteFile() error = %v", err)
|
||||
}
|
||||
|
||||
info, err := backend.Upload(context.Background(), local, `runs\id\artifact.txt`, UploadOptions{
|
||||
Metadata: map[string]string{"kind": "artifact"},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("Upload() error = %v", err)
|
||||
}
|
||||
if info.Key != "runs/id/artifact.txt" {
|
||||
t.Fatalf("Upload key = %q, want normalized key", info.Key)
|
||||
}
|
||||
if info.ETag != "etag123" {
|
||||
t.Fatalf("Upload ETag = %q, want %q", info.ETag, "etag123")
|
||||
}
|
||||
if client.lastPut == nil || *client.lastPut.Key != "runs/id/artifact.txt" {
|
||||
t.Fatalf("PutObject key = %#v, want normalized key", client.lastPut)
|
||||
}
|
||||
|
||||
ok, err := backend.Exists(context.Background(), "runs/id/artifact.txt")
|
||||
if err != nil {
|
||||
t.Fatalf("Exists() error = %v", err)
|
||||
}
|
||||
if !ok {
|
||||
t.Fatal("Exists() = false, want true")
|
||||
}
|
||||
}
|
||||
|
||||
func TestS3BackendUploadMissingLocalFile(t *testing.T) {
|
||||
backend := &S3Backend{bucket: "bucket-1", client: &fakeS3API{}}
|
||||
_, err := backend.Upload(context.Background(), filepath.Join(t.TempDir(), "missing.txt"), "key.txt", UploadOptions{})
|
||||
if err == nil || !strings.Contains(err.Error(), "no such file") {
|
||||
t.Fatalf("Upload() error = %v, want missing local file error", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestS3BackendExistsNotFound(t *testing.T) {
|
||||
backend := &S3Backend{
|
||||
bucket: "bucket-1",
|
||||
client: &fakeS3API{
|
||||
headErr: &smithy.GenericAPIError{Code: "NotFound", Message: "missing"},
|
||||
},
|
||||
}
|
||||
ok, err := backend.Exists(context.Background(), "missing-key")
|
||||
if err != nil {
|
||||
t.Fatalf("Exists() error = %v", err)
|
||||
}
|
||||
if ok {
|
||||
t.Fatal("Exists() = true, want false")
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewS3BackendFromConfigUsesClientOptions(t *testing.T) {
|
||||
original := newS3Client
|
||||
t.Cleanup(func() { newS3Client = original })
|
||||
t.Setenv("OBJECT_STORAGE_KEY_ID", "id-123")
|
||||
t.Setenv("OBJECT_STORAGE_KEY", "secret-abc")
|
||||
|
||||
var got s3ClientOptions
|
||||
newS3Client = func(_ context.Context, opts s3ClientOptions) (s3API, error) {
|
||||
got = opts
|
||||
return &fakeS3API{}, nil
|
||||
}
|
||||
|
||||
backend, err := NewS3BackendFromConfig(context.Background(), config.StorageS3Config{
|
||||
Bucket: "my-archive",
|
||||
Region: "us-east-1",
|
||||
Endpoint: "http://localhost:9000",
|
||||
ForcePathStyle: true,
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("NewS3BackendFromConfig() error = %v", err)
|
||||
}
|
||||
if backend.bucket != "my-archive" {
|
||||
t.Fatalf("backend.bucket = %q, want %q", backend.bucket, "my-archive")
|
||||
}
|
||||
if got.Region != "us-east-1" || got.Endpoint != "http://localhost:9000" || !got.ForcePathStyle {
|
||||
t.Fatalf("client options = %#v, want region/endpoint/path-style values", got)
|
||||
}
|
||||
if got.AccessKeyID != "id-123" || got.SecretKey != "secret-abc" {
|
||||
t.Fatalf("client options credentials = %#v, want env-resolved static credentials", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewS3BackendFromConfigRequiresBucket(t *testing.T) {
|
||||
_, err := NewS3BackendFromConfig(context.Background(), config.StorageS3Config{})
|
||||
if err == nil || !strings.Contains(err.Error(), "bucket is required") {
|
||||
t.Fatalf("NewS3BackendFromConfig() error = %v, want bucket validation", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewS3BackendFromConfigFallsBackWhenCredentialEnvMissing(t *testing.T) {
|
||||
original := newS3Client
|
||||
t.Cleanup(func() { newS3Client = original })
|
||||
|
||||
var got s3ClientOptions
|
||||
newS3Client = func(_ context.Context, opts s3ClientOptions) (s3API, error) {
|
||||
got = opts
|
||||
return &fakeS3API{}, nil
|
||||
}
|
||||
|
||||
_, err := NewS3BackendFromConfig(context.Background(), config.StorageS3Config{
|
||||
Bucket: "my-archive",
|
||||
Region: "us-east-1",
|
||||
AccessKeyIDEnv: "MISSING_ACCESS_KEY_ID",
|
||||
SecretKeyEnv: "MISSING_SECRET_KEY",
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("NewS3BackendFromConfig() error = %v", err)
|
||||
}
|
||||
if got.AccessKeyID != "" || got.SecretKey != "" {
|
||||
t.Fatalf("client options credentials = %#v, want empty fallback values", got)
|
||||
}
|
||||
}
|
||||
|
||||
func strPtr(v string) *string { return &v }
|
||||
func int64Ptr(v int64) *int64 { return &v }
|
||||
|
||||
var _ s3API = (*fakeS3API)(nil)
|
||||
@@ -64,12 +64,12 @@ func TestExecuteMissingRequiredFlags(t *testing.T) {
|
||||
args []string
|
||||
want string
|
||||
}{
|
||||
{name: "run missing flags", args: []string{"run"}, want: "run: --session is required"},
|
||||
{name: "plan missing flags", args: []string{"plan"}, want: "plan: --session is required"},
|
||||
{name: "run missing flags", args: []string{"run"}, want: "run: no pipeline config path provided and no default pipeline config found; searched:"},
|
||||
{name: "plan missing flags", args: []string{"plan"}, want: "plan: no pipeline config path provided and no default pipeline config found; searched:"},
|
||||
{name: "status missing flags", args: []string{"status"}, want: "status: --manifest is required"},
|
||||
{name: "resume missing flags", args: []string{"resume"}, want: "resume: --session is required"},
|
||||
{name: "resume missing flags", args: []string{"resume"}, want: "resume: no pipeline config path provided and no default pipeline config found; searched:"},
|
||||
{name: "run-stage missing name", args: []string{"run-stage", "--config", "a", "--session", "b"}, want: "run-stage: expected exactly one stage name"},
|
||||
{name: "run-stage missing config flags", args: []string{"run-stage", "polish"}, want: "run-stage: --session is required"},
|
||||
{name: "run-stage missing config flags", args: []string{"run-stage", "polish"}, want: "run-stage: no pipeline config path provided and no default pipeline config found; searched:"},
|
||||
{name: "run missing config uses defaults", args: []string{"run", "--session", "session.yml"}, want: "run: no pipeline config path provided and no default pipeline config found; searched:"},
|
||||
}
|
||||
|
||||
@@ -170,6 +170,133 @@ func TestExecuteRunStageTranscribeUsesConfiguredWhisperXServer(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestExecuteRunStagePolishLoadsCredentialFromSecretsDir(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
configDir := t.TempDir()
|
||||
sessionID := "2026-05-03"
|
||||
secretsDir := filepath.Join(configDir, "secrets")
|
||||
if err := os.MkdirAll(secretsDir, 0o755); err != nil {
|
||||
t.Fatalf("MkdirAll(%q): %v", secretsDir, err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(secretsDir, "OPENROUTER_API_KEY"), []byte("from-secret-file\n"), 0o600); err != nil {
|
||||
t.Fatalf("write OPENROUTER_API_KEY secret file: %v", err)
|
||||
}
|
||||
|
||||
seriatimBinary := writeSeriatimAppTestWrapper(t)
|
||||
auditaBinary := writeAuditaAppTestWrapper(t)
|
||||
t.Setenv("GO_WANT_APP_SERIATIM_HELPER", "1")
|
||||
t.Setenv("GO_WANT_APP_AUDITA_HELPER", "1")
|
||||
|
||||
pipelinePath := filepath.Join(configDir, "pipeline.yml")
|
||||
sessionPath := filepath.Join(configDir, "session.yml")
|
||||
pipelineYAML := `workspace:
|
||||
root: ` + workspaceRoot + `
|
||||
storage:
|
||||
backend: local
|
||||
secrets:
|
||||
env_dir: ./secrets
|
||||
whisperx:
|
||||
transcribe_url: https://example.com/transcribe
|
||||
seriatim:
|
||||
binary: ` + seriatimBinary + `
|
||||
audita:
|
||||
binary: ` + auditaBinary + `
|
||||
llm_api_key_env: OPENROUTER_API_KEY
|
||||
analyzer:
|
||||
timeout: 20m
|
||||
notification:
|
||||
timeout: 10s
|
||||
`
|
||||
sessionYAML := `session_id: ` + sessionID + `
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
|
||||
t.Fatalf("write pipeline.yml: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
originalWD, err := os.Getwd()
|
||||
if err != nil {
|
||||
t.Fatalf("Getwd(): %v", err)
|
||||
}
|
||||
if err := os.Chdir(configDir); err != nil {
|
||||
t.Fatalf("Chdir(%q): %v", configDir, err)
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
_ = os.Chdir(originalWD)
|
||||
})
|
||||
|
||||
workRoot := filepath.Join(workspaceRoot, "work", sessionID)
|
||||
mustWriteTestFile(t, filepath.Join(workRoot, "transcripts", "merged.json"), `{"schema":"seriatim-intermediate","segments":[]}`)
|
||||
mustWriteTestFile(t, filepath.Join(workRoot, "inputs", "glossary.yml"), "[]\n")
|
||||
|
||||
var stdout bytes.Buffer
|
||||
var stderr bytes.Buffer
|
||||
code := Execute([]string{"run-stage", "--config", pipelinePath, "--session", sessionPath, "--force", "polish"}, &stdout, &stderr)
|
||||
if code != 0 {
|
||||
t.Fatalf("exit code = %d, want 0; stderr=%q", code, stderr.String())
|
||||
}
|
||||
if !strings.Contains(stdout.String(), "stage=polish executed=1 skipped=0") {
|
||||
t.Fatalf("stdout = %q, want polish execution", stdout.String())
|
||||
}
|
||||
}
|
||||
|
||||
func TestExecuteRunFailsWhenConfiguredSecretsDirMissing(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
configDir := t.TempDir()
|
||||
pipelinePath := filepath.Join(configDir, "pipeline.yml")
|
||||
sessionPath := filepath.Join(configDir, "session.yml")
|
||||
|
||||
pipelineYAML := `workspace:
|
||||
root: ` + workspaceRoot + `
|
||||
storage:
|
||||
backend: local
|
||||
secrets:
|
||||
env_dir: ./missing-secrets
|
||||
whisperx:
|
||||
transcribe_url: https://example.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
analyzer:
|
||||
timeout: 20m
|
||||
notification:
|
||||
timeout: 10s
|
||||
`
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
|
||||
t.Fatalf("write pipeline.yml: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
var stdout bytes.Buffer
|
||||
var stderr bytes.Buffer
|
||||
code := Execute([]string{"run", "--config", pipelinePath, "--session", sessionPath}, &stdout, &stderr)
|
||||
if code == 0 {
|
||||
t.Fatal("exit code = 0, want non-zero")
|
||||
}
|
||||
if !strings.Contains(stderr.String(), "read secrets env_dir") {
|
||||
t.Fatalf("stderr = %q, want secrets read-dir error context", stderr.String())
|
||||
}
|
||||
}
|
||||
|
||||
func TestExecuteUsesDefaultPipelineConfigPathWhenConfigFlagOmitted(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
@@ -252,6 +379,11 @@ func writeValidConfigFiles(t *testing.T, workspaceRoot string, transcribeURL ...
|
||||
root: ` + workspaceRoot + `
|
||||
storage:
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: test-bucket
|
||||
archive:
|
||||
enabled: true
|
||||
upload_run: false
|
||||
whisperx:
|
||||
transcribe_url: ` + url + `
|
||||
timeout: 2s
|
||||
@@ -275,6 +407,7 @@ notification:
|
||||
`
|
||||
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
|
||||
@@ -5,9 +5,12 @@ import (
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"os"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/logging"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
|
||||
)
|
||||
|
||||
@@ -18,9 +21,11 @@ func Plan(ctx context.Context, args []string, out io.Writer) error {
|
||||
|
||||
var pipelinePath string
|
||||
var sessionPath string
|
||||
var sessionID string
|
||||
var force bool
|
||||
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
|
||||
fs.StringVar(&sessionPath, "session", "", "path to session.yml")
|
||||
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
|
||||
fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
|
||||
|
||||
if err := fs.Parse(args); err != nil {
|
||||
@@ -29,22 +34,27 @@ func Plan(ctx context.Context, args []string, out io.Writer) error {
|
||||
if fs.NArg() != 0 {
|
||||
return fmt.Errorf("plan: unexpected positional arguments")
|
||||
}
|
||||
if sessionPath == "" {
|
||||
return fmt.Errorf("plan: --session is required")
|
||||
}
|
||||
|
||||
resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("plan: %w", err)
|
||||
}
|
||||
resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("plan: %w", err)
|
||||
}
|
||||
|
||||
cfg, err := config.Load(resolvedPipelinePath, sessionPath)
|
||||
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
|
||||
SessionID: sessionID,
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("plan: %w", err)
|
||||
}
|
||||
if err := config.Validate(cfg); err != nil {
|
||||
return fmt.Errorf("plan: %w", err)
|
||||
}
|
||||
if _, err := loadSecretsFromConfig(cfg, logging.NewLogger(os.Stderr, slog.LevelInfo)); err != nil {
|
||||
return fmt.Errorf("plan: %w", err)
|
||||
}
|
||||
|
||||
store := artifacts.NewLocalStore(cfg.Pipeline.Workspace.Root)
|
||||
paths, err := store.EnsureLayout(cfg.Session.SessionID)
|
||||
|
||||
@@ -89,6 +89,54 @@ func TestPlanShowsRunAndSkipFromManifest(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestPlanFailsWhenConfiguredSecretsDirMissing(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
configDir := t.TempDir()
|
||||
pipelinePath := filepath.Join(configDir, "pipeline.yml")
|
||||
sessionPath := filepath.Join(configDir, "session.yml")
|
||||
|
||||
pipelineYAML := `workspace:
|
||||
root: ` + workspaceRoot + `
|
||||
storage:
|
||||
backend: local
|
||||
secrets:
|
||||
env_dir: ./missing-secrets
|
||||
whisperx:
|
||||
transcribe_url: https://example.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
analyzer:
|
||||
timeout: 20m
|
||||
notification:
|
||||
timeout: 10s
|
||||
`
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
|
||||
t.Fatalf("write pipeline.yml: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
var out bytes.Buffer
|
||||
err := Plan(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath}, &out)
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "read secrets env_dir") {
|
||||
t.Fatalf("error = %q, want secrets read error context", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func assertDir(t *testing.T, path string) {
|
||||
t.Helper()
|
||||
info, err := os.Stat(path)
|
||||
|
||||
208
internal/app/post_archive_cleanup.go
Normal file
208
internal/app/post_archive_cleanup.go
Normal file
@@ -0,0 +1,208 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
|
||||
)
|
||||
|
||||
func runPostArchiveCleanup(ctx context.Context, env *Env, manifestPath string, m *manifest.Manifest, executed []string) error {
|
||||
if env == nil || env.Config == nil || env.Config.Pipeline == nil || m == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
spoolRequested := env.Config.Pipeline.Spool.DeleteAudioAfterArchive
|
||||
workRequested := env.Config.Pipeline.Workspace.CleanupAfterArchive
|
||||
if !spoolRequested && !workRequested {
|
||||
return nil
|
||||
}
|
||||
|
||||
sr := archiveStageRecordForCleanup(m, executed)
|
||||
if sr == nil {
|
||||
return nil
|
||||
}
|
||||
if sr.Metadata == nil {
|
||||
sr.Metadata = map[string]any{}
|
||||
}
|
||||
sr.Metadata["spool_cleanup_requested"] = spoolRequested
|
||||
sr.Metadata["workdir_cleanup_requested"] = workRequested
|
||||
|
||||
eligible, reason := archiveCleanupEligible(env.Config, sr)
|
||||
if !eligible {
|
||||
sr.Metadata["cleanup_skipped"] = true
|
||||
sr.Metadata["cleanup_skipped_reason"] = reason
|
||||
if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
|
||||
return fmt.Errorf("save manifest cleanup skip metadata %q: %w", manifestPath, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
spoolDir := strings.TrimSpace(m.LocalSpoolDir)
|
||||
if spoolDir == "" {
|
||||
spoolDir = artifacts.SessionSpoolAudioDir(
|
||||
env.Config.Pipeline.Spool.Root,
|
||||
strings.TrimSpace(env.Config.Session.Campaign),
|
||||
strings.TrimSpace(env.Config.Session.SessionID),
|
||||
strings.TrimSpace(m.RunID),
|
||||
)
|
||||
}
|
||||
workDir := strings.TrimSpace(m.LocalWorkDir)
|
||||
if workDir == "" {
|
||||
workDir = artifacts.SessionRunWorkDir(
|
||||
env.Config.Pipeline.Workspace.Root,
|
||||
strings.TrimSpace(env.Config.Session.Campaign),
|
||||
strings.TrimSpace(env.Config.Session.SessionID),
|
||||
strings.TrimSpace(m.RunID),
|
||||
)
|
||||
}
|
||||
|
||||
if spoolRequested {
|
||||
if err := removeRunScopedDir(strings.TrimSpace(env.Config.Pipeline.Spool.Root), spoolDir, "pipeline.spool.delete_audio_after_archive"); err != nil {
|
||||
sr.Metadata["cleanup_failed"] = true
|
||||
sr.Metadata["cleanup_failed_policy"] = "pipeline.spool.delete_audio_after_archive"
|
||||
sr.Metadata["cleanup_failed_path"] = spoolDir
|
||||
_ = env.ManifestStore.Save(ctx, manifestPath, m)
|
||||
return err
|
||||
}
|
||||
sr.Metadata["spool_cleanup_deleted"] = filepath.Clean(spoolDir)
|
||||
}
|
||||
|
||||
if !workRequested {
|
||||
sr.Metadata["cleanup_completed"] = true
|
||||
sr.Metadata["cleanup_skipped"] = false
|
||||
if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
|
||||
return fmt.Errorf("save manifest cleanup metadata %q: %w", manifestPath, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
if err := removeRunScopedDir(strings.TrimSpace(env.Config.Pipeline.Workspace.Root), workDir, "pipeline.workspace.cleanup_after_archive"); err != nil {
|
||||
sr.Metadata["cleanup_failed"] = true
|
||||
sr.Metadata["cleanup_failed_policy"] = "pipeline.workspace.cleanup_after_archive"
|
||||
sr.Metadata["cleanup_failed_path"] = workDir
|
||||
_ = env.ManifestStore.Save(ctx, manifestPath, m)
|
||||
return err
|
||||
}
|
||||
|
||||
sr.Metadata["workdir_cleanup_deleted"] = filepath.Clean(workDir)
|
||||
sr.Metadata["cleanup_completed"] = true
|
||||
sr.Metadata["cleanup_skipped"] = false
|
||||
return nil
|
||||
}
|
||||
|
||||
func archiveStageRecordForCleanup(m *manifest.Manifest, executed []string) *manifest.StageRecord {
|
||||
if m == nil {
|
||||
return nil
|
||||
}
|
||||
archiveRan := false
|
||||
for _, name := range executed {
|
||||
if name == "archive" {
|
||||
archiveRan = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !archiveRan {
|
||||
return nil
|
||||
}
|
||||
sr := m.Stages["archive"]
|
||||
if sr == nil || sr.Status != manifest.StatusSucceeded {
|
||||
return nil
|
||||
}
|
||||
return sr
|
||||
}
|
||||
|
||||
func archiveCleanupEligible(cfg *config.Config, sr *manifest.StageRecord) (bool, string) {
|
||||
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Archive == nil {
|
||||
return false, "archive configuration is missing"
|
||||
}
|
||||
enabled := true
|
||||
if cfg.Pipeline.Archive.Enabled != nil {
|
||||
enabled = *cfg.Pipeline.Archive.Enabled
|
||||
}
|
||||
if !enabled {
|
||||
return false, "archive.enabled is false"
|
||||
}
|
||||
uploadRun := true
|
||||
if cfg.Pipeline.Archive.UploadRun != nil {
|
||||
uploadRun = *cfg.Pipeline.Archive.UploadRun
|
||||
}
|
||||
if !uploadRun {
|
||||
return false, "archive.upload_run is false"
|
||||
}
|
||||
if sr == nil || sr.Metadata == nil {
|
||||
return false, "archive metadata is missing"
|
||||
}
|
||||
if skipped, _ := sr.Metadata["skipped"].(bool); skipped {
|
||||
return false, "archive stage was skipped"
|
||||
}
|
||||
if uploaded, _ := sr.Metadata["uploaded"].(bool); !uploaded {
|
||||
return false, "archive did not upload run record"
|
||||
}
|
||||
if pointer, _ := sr.Metadata["current_pointer_written"].(bool); !pointer {
|
||||
return false, "archive did not write current pointer"
|
||||
}
|
||||
if strings.TrimSpace(asString(sr.Metadata["current_run_id_key"])) == "" {
|
||||
return false, "archive current run pointer key is missing"
|
||||
}
|
||||
return true, ""
|
||||
}
|
||||
|
||||
func removeRunScopedDir(root, target, policy string) error {
|
||||
cleanRoot := strings.TrimSpace(root)
|
||||
cleanTarget := strings.TrimSpace(target)
|
||||
if cleanRoot == "" {
|
||||
return fmt.Errorf("cleanup policy %s: root path is required", policy)
|
||||
}
|
||||
if cleanTarget == "" {
|
||||
return fmt.Errorf("cleanup policy %s: target path is required", policy)
|
||||
}
|
||||
|
||||
rootAbs, err := filepath.Abs(cleanRoot)
|
||||
if err != nil {
|
||||
return fmt.Errorf("cleanup policy %s: resolve root %q: %w", policy, cleanRoot, err)
|
||||
}
|
||||
targetAbs, err := filepath.Abs(cleanTarget)
|
||||
if err != nil {
|
||||
return fmt.Errorf("cleanup policy %s: resolve target %q: %w", policy, cleanTarget, err)
|
||||
}
|
||||
|
||||
rel, err := filepath.Rel(rootAbs, targetAbs)
|
||||
if err != nil {
|
||||
return fmt.Errorf("cleanup policy %s: relative path from %q to %q: %w", policy, rootAbs, targetAbs, err)
|
||||
}
|
||||
if rel == "." {
|
||||
return fmt.Errorf("cleanup policy %s: refusing to delete root directory %q", policy, rootAbs)
|
||||
}
|
||||
if rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
|
||||
return fmt.Errorf("cleanup policy %s: refusing to delete path outside root: root=%q target=%q", policy, rootAbs, targetAbs)
|
||||
}
|
||||
|
||||
info, err := os.Lstat(targetAbs)
|
||||
if err != nil {
|
||||
if os.IsNotExist(err) {
|
||||
return nil
|
||||
}
|
||||
return fmt.Errorf("cleanup policy %s: stat target %q: %w", policy, targetAbs, err)
|
||||
}
|
||||
if info.Mode()&os.ModeSymlink != 0 {
|
||||
return fmt.Errorf("cleanup policy %s: refusing to delete symlink path %q", policy, targetAbs)
|
||||
}
|
||||
if !info.IsDir() {
|
||||
return fmt.Errorf("cleanup policy %s: target %q is not a directory", policy, targetAbs)
|
||||
}
|
||||
if err := os.RemoveAll(targetAbs); err != nil {
|
||||
return fmt.Errorf("cleanup policy %s: remove %q: %w", policy, targetAbs, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func asString(v any) string {
|
||||
s, _ := v.(string)
|
||||
return s
|
||||
}
|
||||
396
internal/app/post_archive_cleanup_test.go
Normal file
396
internal/app/post_archive_cleanup_test.go
Normal file
@@ -0,0 +1,396 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/stage"
|
||||
)
|
||||
|
||||
type archiveSuccessStage struct {
|
||||
metadata map[string]any
|
||||
}
|
||||
|
||||
func (archiveSuccessStage) Name() string { return "archive" }
|
||||
func (archiveSuccessStage) Declares() stage.IODecl { return stage.IODecl{} }
|
||||
func (s archiveSuccessStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
|
||||
md := map[string]any{
|
||||
"stage": "archive",
|
||||
"uploaded": true,
|
||||
"current_pointer_written": true,
|
||||
"current_run_id_key": "dnd/campaigns/sample-campaign/sessions/2026-05-03/current/run_id.txt",
|
||||
}
|
||||
for k, v := range s.metadata {
|
||||
md[k] = v
|
||||
}
|
||||
return &stage.StageResult{Metadata: md}, nil
|
||||
}
|
||||
|
||||
type notifyFailStage struct{}
|
||||
|
||||
func (notifyFailStage) Name() string { return "notify" }
|
||||
func (notifyFailStage) Declares() stage.IODecl { return stage.IODecl{} }
|
||||
func (notifyFailStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
|
||||
return nil, errors.New("notify failed")
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupDisabledKeepsLocalDirs(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = false
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = false
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
assertExists(t, seed.localSourceAudio)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupSpoolOnly(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = false
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertMissing(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
assertExists(t, seed.localSourceAudio)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupWorkdirOnly(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = false
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertExists(t, cfg.Pipeline.Workspace.Root)
|
||||
assertExists(t, seed.otherRunDir)
|
||||
assertMissing(t, seed.runWorkDir)
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupBothPolicies(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertMissing(t, seed.spoolAudioDir)
|
||||
assertMissing(t, seed.runWorkDir)
|
||||
assertExists(t, seed.otherRunDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenArchiveFails(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
|
||||
_, err := executeStages(context.Background(), cfg, []stage.Stage{failingStage{name: "archive", err: errors.New("archive failed")}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
|
||||
if err == nil || !strings.Contains(err.Error(), "stage \"archive\" failed") {
|
||||
t.Fatalf("executeStages() error = %v, want archive failure", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenArchiveSkipped(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{metadata: map[string]any{"skipped": true}}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenCurrentPointerMissing(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{metadata: map[string]any{"current_pointer_written": false}}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenArchiveUploadDisabled(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
cfg.Pipeline.Archive.UploadRun = boolPtr(false)
|
||||
|
||||
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
|
||||
t.Fatalf("executeStages() error = %v", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupWaitsUntilAllStagesSucceed(t *testing.T) {
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
|
||||
_, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}, notifyFailStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
|
||||
if err == nil || !strings.Contains(err.Error(), "stage \"notify\" failed") {
|
||||
t.Fatalf("executeStages() error = %v, want notify failure", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupFailsOnUnsafePath(t *testing.T) {
|
||||
cfg, _ := cleanupFixtureConfig(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = false
|
||||
|
||||
manifestPath := manifestPathFor(cfg)
|
||||
store := &manifest.LocalStore{}
|
||||
m, err := store.Load(context.Background(), manifestPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
m.LocalSpoolDir = filepath.Join(filepath.Dir(cfg.Pipeline.Spool.Root), "outside-spool")
|
||||
if err := store.Save(context.Background(), manifestPath, m); err != nil {
|
||||
t.Fatalf("Save() error = %v", err)
|
||||
}
|
||||
|
||||
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
|
||||
if err == nil || !strings.Contains(err.Error(), "refusing to delete path outside root") {
|
||||
t.Fatalf("executeStages() error = %v, want safe-path failure", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenPromotionIsMissing(t *testing.T) {
|
||||
cfg, seed, runID := archiveStageCleanupFixture(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
cfg.Pipeline.Archive.PromoteArtifacts = []config.ArchivePromotionRule{
|
||||
{From: "artifacts/missing.md", To: "artifacts/missing.md", Required: boolPtr(true)},
|
||||
}
|
||||
|
||||
archiveStageImpl, err := stage.Select("archive")
|
||||
if err != nil {
|
||||
t.Fatalf("Select(archive) error = %v", err)
|
||||
}
|
||||
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
|
||||
if err == nil || !strings.Contains(err.Error(), "required promotion source missing") {
|
||||
t.Fatalf("executeStages() error = %v, want promotion-missing failure", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
assertExists(t, filepath.Join(seed.runWorkDir, "manifest.json"))
|
||||
assertExists(t, artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID))
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenCurrentManifestUploadFails(t *testing.T) {
|
||||
cfg, seed, _ := archiveStageCleanupFixture(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
failKey := seed.sessionPrefix + "current/manifest.json"
|
||||
|
||||
archiveStageImpl, err := stage.Select("archive")
|
||||
if err != nil {
|
||||
t.Fatalf("Select(archive) error = %v", err)
|
||||
}
|
||||
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{
|
||||
Env: &Env{ObjectStore: &failKeyStore{delegate: &storage.FakeBackend{}, failKey: failKey}},
|
||||
})
|
||||
if err == nil || !strings.Contains(err.Error(), "current manifest") {
|
||||
t.Fatalf("executeStages() error = %v, want current-manifest failure", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
func TestPostArchiveCleanupNotRunWhenCurrentPointerUploadFails(t *testing.T) {
|
||||
cfg, seed, _ := archiveStageCleanupFixture(t)
|
||||
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
|
||||
cfg.Pipeline.Workspace.CleanupAfterArchive = true
|
||||
failKey := seed.sessionPrefix + "current/run_id.txt"
|
||||
|
||||
archiveStageImpl, err := stage.Select("archive")
|
||||
if err != nil {
|
||||
t.Fatalf("Select(archive) error = %v", err)
|
||||
}
|
||||
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{
|
||||
Env: &Env{ObjectStore: &failKeyStore{delegate: &storage.FakeBackend{}, failKey: failKey}},
|
||||
})
|
||||
if err == nil || !strings.Contains(err.Error(), "current run pointer") {
|
||||
t.Fatalf("executeStages() error = %v, want current-run-pointer failure", err)
|
||||
}
|
||||
|
||||
assertExists(t, seed.spoolAudioDir)
|
||||
assertExists(t, seed.runWorkDir)
|
||||
}
|
||||
|
||||
type cleanupSeed struct {
|
||||
runWorkDir string
|
||||
otherRunDir string
|
||||
spoolAudioDir string
|
||||
localSourceAudio string
|
||||
sessionPrefix string
|
||||
}
|
||||
|
||||
func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) {
|
||||
t.Helper()
|
||||
|
||||
cfg := testConfig(t)
|
||||
cfg.Pipeline.Archive = &config.ArchiveConfig{Enabled: boolPtr(true), UploadRun: boolPtr(true)}
|
||||
cfg.Pipeline.Spool.Root = filepath.Join(t.TempDir(), "spool")
|
||||
|
||||
runID := "20260516T010203Z-1a2b3c4d"
|
||||
runWorkDir := artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
|
||||
otherRunDir := artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, "20260516T010204Z-5e6f7a8b")
|
||||
spoolAudioDir := artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
|
||||
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "logs", "stage.log"), "log\n")
|
||||
mustWriteFile(t, filepath.Join(otherRunDir, "logs", "stage.log"), "other\n")
|
||||
mustWriteFile(t, filepath.Join(spoolAudioDir, "speaker.flac"), "flac\n")
|
||||
|
||||
localSourceAudio := filepath.Join(filepath.Dir(cfg.SessionPath), "audio", "alice.flac")
|
||||
mustWriteFile(t, localSourceAudio, "source\n")
|
||||
|
||||
seed := manifest.New(cfg.Session.SessionID, time.Now().UTC())
|
||||
seed.Campaign = cfg.Session.Campaign
|
||||
seed.RunID = runID
|
||||
seed.LocalWorkDir = runWorkDir
|
||||
seed.LocalSpoolDir = spoolAudioDir
|
||||
seed.S3Bucket = "my-dnd-archive"
|
||||
seed.S3SessionPrefix = "dnd/campaigns/sample-campaign/sessions/2026-05-03/"
|
||||
seed.S3RunPrefix = seed.S3SessionPrefix + "runs/" + runID + "/"
|
||||
|
||||
store := &manifest.LocalStore{}
|
||||
if err := os.MkdirAll(filepath.Dir(manifestPathFor(cfg)), 0o755); err != nil {
|
||||
t.Fatalf("MkdirAll() error = %v", err)
|
||||
}
|
||||
if err := store.Save(context.Background(), manifestPathFor(cfg), seed); err != nil {
|
||||
t.Fatalf("seed manifest save error = %v", err)
|
||||
}
|
||||
|
||||
return cfg, cleanupSeed{
|
||||
runWorkDir: runWorkDir,
|
||||
otherRunDir: otherRunDir,
|
||||
spoolAudioDir: spoolAudioDir,
|
||||
localSourceAudio: localSourceAudio,
|
||||
sessionPrefix: seed.S3SessionPrefix,
|
||||
}
|
||||
}
|
||||
|
||||
func archiveStageCleanupFixture(t *testing.T) (*config.Config, cleanupSeed, string) {
|
||||
t.Helper()
|
||||
|
||||
cfg, seed := cleanupFixtureConfig(t)
|
||||
runID := "20260516T010203Z-1a2b3c4d"
|
||||
cfg.Pipeline.Storage.S3 = &config.StorageS3Config{
|
||||
Bucket: "my-dnd-archive",
|
||||
RootPrefix: "dnd",
|
||||
}
|
||||
cfg.Pipeline.Archive = &config.ArchiveConfig{
|
||||
Enabled: boolPtr(true),
|
||||
UploadRun: boolPtr(true),
|
||||
PromoteArtifacts: []config.ArchivePromotionRule{
|
||||
{From: "transcripts/trimmed.json", To: "transcripts/trimmed.json", Required: boolPtr(true)},
|
||||
{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md", Required: boolPtr(true)},
|
||||
},
|
||||
}
|
||||
writeArchiveFixtureRunFiles(t, seed.runWorkDir)
|
||||
|
||||
store := &manifest.LocalStore{}
|
||||
seedManifest, err := store.Load(context.Background(), manifestPathFor(cfg))
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze"} {
|
||||
seedManifest.MarkStageSucceeded(name, time.Now().UTC(), nil)
|
||||
}
|
||||
seedManifest.S3SessionPrefix = artifacts.S3SessionPrefix("dnd", cfg.Session.Campaign, cfg.Session.SessionID)
|
||||
seedManifest.S3RunPrefix = artifacts.S3RunPrefix(seedManifest.S3SessionPrefix, runID)
|
||||
if err := store.Save(context.Background(), manifestPathFor(cfg), seedManifest); err != nil {
|
||||
t.Fatalf("Save() error = %v", err)
|
||||
}
|
||||
seed.sessionPrefix = seedManifest.S3SessionPrefix
|
||||
return cfg, seed, runID
|
||||
}
|
||||
|
||||
func writeArchiveFixtureRunFiles(t *testing.T, runWorkDir string) {
|
||||
t.Helper()
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "inputs", "session.yml"), "session_id: 2026-05-03\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "transcripts", "raw", "speaker.json"), "{}\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "transcripts", "trimmed.json"), "{}\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "artifacts", "session_recap.md"), "# recap\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "reports", "audita.report.json"), "{}\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "config", "audita.generated.yml"), "key: value\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "logs", "audita.stderr.log"), "stderr\n")
|
||||
mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
|
||||
}
|
||||
|
||||
type failKeyStore struct {
|
||||
delegate *storage.FakeBackend
|
||||
failKey string
|
||||
}
|
||||
|
||||
func (s *failKeyStore) List(ctx context.Context, prefix string) ([]storage.ObjectInfo, error) {
|
||||
return s.delegate.List(ctx, prefix)
|
||||
}
|
||||
|
||||
func (s *failKeyStore) Download(ctx context.Context, key, localPath string) error {
|
||||
return s.delegate.Download(ctx, key, localPath)
|
||||
}
|
||||
|
||||
func (s *failKeyStore) Upload(ctx context.Context, localPath, key string, opts storage.UploadOptions) (storage.ObjectInfo, error) {
|
||||
if strings.TrimSpace(key) == strings.TrimSpace(s.failKey) {
|
||||
return storage.ObjectInfo{}, errors.New("forced upload failure")
|
||||
}
|
||||
return s.delegate.Upload(ctx, localPath, key, opts)
|
||||
}
|
||||
|
||||
func (s *failKeyStore) Exists(ctx context.Context, key string) (bool, error) {
|
||||
return s.delegate.Exists(ctx, key)
|
||||
}
|
||||
|
||||
func assertExists(t *testing.T, path string) {
|
||||
t.Helper()
|
||||
if _, err := os.Stat(path); err != nil {
|
||||
t.Fatalf("expected path to exist %q: %v", path, err)
|
||||
}
|
||||
}
|
||||
|
||||
func assertMissing(t *testing.T, path string) {
|
||||
t.Helper()
|
||||
if _, err := os.Stat(path); !os.IsNotExist(err) {
|
||||
t.Fatalf("expected path to be removed %q, stat err=%v", path, err)
|
||||
}
|
||||
}
|
||||
@@ -17,9 +17,11 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
|
||||
|
||||
var pipelinePath string
|
||||
var sessionPath string
|
||||
var sessionID string
|
||||
var force bool
|
||||
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
|
||||
fs.StringVar(&sessionPath, "session", "", "path to session.yml")
|
||||
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
|
||||
fs.BoolVar(&force, "force", false, "force stage execution")
|
||||
|
||||
if err := fs.Parse(args); err != nil {
|
||||
@@ -28,16 +30,18 @@ func Resume(ctx context.Context, args []string, out io.Writer) error {
|
||||
if fs.NArg() != 0 {
|
||||
return fmt.Errorf("resume: unexpected positional arguments")
|
||||
}
|
||||
if sessionPath == "" {
|
||||
return fmt.Errorf("resume: --session is required")
|
||||
}
|
||||
|
||||
resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("resume: %w", err)
|
||||
}
|
||||
resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("resume: %w", err)
|
||||
}
|
||||
|
||||
cfg, err := config.Load(resolvedPipelinePath, sessionPath)
|
||||
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
|
||||
SessionID: sessionID,
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("resume: %w", err)
|
||||
}
|
||||
|
||||
@@ -16,9 +16,11 @@ func Run(ctx context.Context, args []string, out io.Writer) error {
|
||||
|
||||
var pipelinePath string
|
||||
var sessionPath string
|
||||
var sessionID string
|
||||
var force bool
|
||||
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
|
||||
fs.StringVar(&sessionPath, "session", "", "path to session.yml")
|
||||
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
|
||||
fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
|
||||
|
||||
if err := fs.Parse(args); err != nil {
|
||||
@@ -27,16 +29,18 @@ func Run(ctx context.Context, args []string, out io.Writer) error {
|
||||
if fs.NArg() != 0 {
|
||||
return fmt.Errorf("run: unexpected positional arguments")
|
||||
}
|
||||
if sessionPath == "" {
|
||||
return fmt.Errorf("run: --session is required")
|
||||
}
|
||||
|
||||
resolvedPipelinePath, err := resolvePipelineConfigPath(pipelinePath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("run: %w", err)
|
||||
}
|
||||
resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("run: %w", err)
|
||||
}
|
||||
|
||||
cfg, err := config.Load(resolvedPipelinePath, sessionPath)
|
||||
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
|
||||
SessionID: sessionID,
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("run: %w", err)
|
||||
}
|
||||
|
||||
@@ -16,9 +16,11 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
|
||||
|
||||
var pipelinePath string
|
||||
var sessionPath string
|
||||
var sessionID string
|
||||
var force bool
|
||||
fs.StringVar(&pipelinePath, "config", "", "path to pipeline.yml (optional; defaults searched)")
|
||||
fs.StringVar(&sessionPath, "session", "", "path to session.yml")
|
||||
fs.StringVar(&sessionID, "session-id", "", "session identifier for session.yml templates")
|
||||
fs.BoolVar(&force, "force", false, "force stage execution (reserved for future behavior)")
|
||||
|
||||
if err := fs.Parse(args); err != nil {
|
||||
@@ -27,10 +29,6 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
|
||||
if fs.NArg() != 1 {
|
||||
return fmt.Errorf("run-stage: expected exactly one stage name")
|
||||
}
|
||||
if sessionPath == "" {
|
||||
return fmt.Errorf("run-stage: --session is required")
|
||||
}
|
||||
|
||||
stageName := fs.Arg(0)
|
||||
stages, err := BuildSingleStagePlan(stageName)
|
||||
if err != nil {
|
||||
@@ -41,8 +39,14 @@ func RunStage(ctx context.Context, args []string, out io.Writer) error {
|
||||
if err != nil {
|
||||
return fmt.Errorf("run-stage: %w", err)
|
||||
}
|
||||
resolvedSessionPath, err := resolveSessionConfigPath(sessionPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("run-stage: %w", err)
|
||||
}
|
||||
|
||||
cfg, err := config.Load(resolvedPipelinePath, sessionPath)
|
||||
cfg, err := config.LoadWithSessionOptions(resolvedPipelinePath, resolvedSessionPath, config.SessionLoadOptions{
|
||||
SessionID: sessionID,
|
||||
})
|
||||
if err != nil {
|
||||
return fmt.Errorf("run-stage: %w", err)
|
||||
}
|
||||
|
||||
@@ -51,6 +51,9 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
|
||||
if env.Logger == nil {
|
||||
env.Logger = logging.NewLogger(os.Stderr, slog.LevelInfo)
|
||||
}
|
||||
if _, err := loadSecretsFromConfig(env.Config, env.Logger); err != nil {
|
||||
return nil, fmt.Errorf("load secrets from files: %w", err)
|
||||
}
|
||||
if env.WhisperX == nil {
|
||||
client, err := buildDefaultWhisperXClient(env.Config)
|
||||
if err != nil {
|
||||
@@ -78,6 +81,13 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
|
||||
if env.Storage == nil {
|
||||
env.Storage = &storage.NoopBackend{}
|
||||
}
|
||||
if env.ObjectStore == nil && needsObjectStoreForRun(env.Config, stages) {
|
||||
objectStore, err := storage.NewObjectStoreFromConfig(ctx, env.Config)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("initialize object store backend: %w", err)
|
||||
}
|
||||
env.ObjectStore = objectStore
|
||||
}
|
||||
if env.Notifier == nil {
|
||||
env.Notifier = ¬ify.NoopSender{}
|
||||
}
|
||||
@@ -101,6 +111,15 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
identityChanged, err := ensureManifestIdentity(cfg, m)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("initialize manifest identity: %w", err)
|
||||
}
|
||||
if identityChanged {
|
||||
if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
|
||||
return nil, fmt.Errorf("save manifest identity %q: %w", manifestPath, err)
|
||||
}
|
||||
}
|
||||
|
||||
stageEnv := env
|
||||
|
||||
@@ -149,6 +168,10 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
|
||||
env.Logger.Info("stage succeeded", "stage", s.Name())
|
||||
}
|
||||
|
||||
if err := runPostArchiveCleanup(ctx, env, manifestPath, m, executed); err != nil {
|
||||
return nil, fmt.Errorf("post-archive cleanup: %w", err)
|
||||
}
|
||||
|
||||
return &RunSummary{
|
||||
SessionID: cfg.Session.SessionID,
|
||||
ManifestPath: manifestPath,
|
||||
@@ -227,7 +250,7 @@ func buildDefaultAuditaRunner(cfg *config.Config) (audita.Runner, error) {
|
||||
}
|
||||
|
||||
a := cfg.Pipeline.Audita
|
||||
if strings.TrimSpace(a.Binary) == "" || strings.TrimSpace(a.Timeout) == "" || len(a.Modules) == 0 || strings.TrimSpace(a.BaseURL) == "" || strings.TrimSpace(a.Model) == "" {
|
||||
if strings.TrimSpace(a.Binary) == "" || strings.TrimSpace(a.Timeout) == "" {
|
||||
// Compatibility fallback for tests or internal call paths that bypass config validation/defaults.
|
||||
return &audita.NoopRunner{}, nil
|
||||
}
|
||||
@@ -244,7 +267,12 @@ func buildDefaultAuditaRunner(cfg *config.Config) (audita.Runner, error) {
|
||||
append([]string(nil), a.Modules...),
|
||||
a.BaseURL,
|
||||
a.Model,
|
||||
a.LLMConcurrency,
|
||||
a.TranscriptDescription,
|
||||
a.ConfigPath,
|
||||
a.OutputSchema,
|
||||
a.WorkDirRetention,
|
||||
a.TotalLLMConcurrency,
|
||||
a.ProposalLLMConcurrency,
|
||||
a.ValidationModel,
|
||||
a.ValidationLLMConcurrency,
|
||||
report,
|
||||
@@ -330,6 +358,89 @@ func applyStageResultToManifest(m *manifest.Manifest, stageName string, result *
|
||||
}
|
||||
}
|
||||
|
||||
func ensureManifestIdentity(cfg *config.Config, m *manifest.Manifest) (bool, error) {
|
||||
if cfg == nil || cfg.Pipeline == nil || cfg.Session == nil || m == nil {
|
||||
return false, nil
|
||||
}
|
||||
|
||||
changed := false
|
||||
campaign := strings.TrimSpace(cfg.Session.Campaign)
|
||||
sessionID := strings.TrimSpace(cfg.Session.SessionID)
|
||||
if sessionID == "" {
|
||||
sessionID = strings.TrimSpace(m.SessionID)
|
||||
}
|
||||
|
||||
if m.Campaign == "" && campaign != "" {
|
||||
m.Campaign = campaign
|
||||
changed = true
|
||||
}
|
||||
if m.RunID == "" {
|
||||
runID, err := artifacts.NewRunID()
|
||||
if err != nil {
|
||||
return false, err
|
||||
}
|
||||
m.RunID = runID
|
||||
changed = true
|
||||
}
|
||||
if m.LocalWorkDir == "" && campaign != "" && sessionID != "" && m.RunID != "" {
|
||||
m.LocalWorkDir = artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, campaign, sessionID, m.RunID)
|
||||
changed = true
|
||||
}
|
||||
if m.LocalSpoolDir == "" && campaign != "" && sessionID != "" && m.RunID != "" && strings.TrimSpace(cfg.Pipeline.Spool.Root) != "" {
|
||||
m.LocalSpoolDir = artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, campaign, sessionID, m.RunID)
|
||||
changed = true
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3 != nil {
|
||||
if m.S3Bucket == "" && strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket) != "" {
|
||||
m.S3Bucket = strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket)
|
||||
changed = true
|
||||
}
|
||||
sessionPrefix := artifacts.S3SessionPrefix(cfg.Pipeline.Storage.S3.RootPrefix, campaign, sessionID)
|
||||
if m.S3SessionPrefix == "" && sessionPrefix != "" {
|
||||
m.S3SessionPrefix = sessionPrefix
|
||||
changed = true
|
||||
}
|
||||
runPrefix := artifacts.S3RunPrefix(sessionPrefix, m.RunID)
|
||||
if m.S3RunPrefix == "" && runPrefix != "" {
|
||||
m.S3RunPrefix = runPrefix
|
||||
changed = true
|
||||
}
|
||||
}
|
||||
|
||||
return changed, nil
|
||||
}
|
||||
|
||||
func manifestPathFor(cfg *config.Config) string {
|
||||
return filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.SessionID, "manifest.json")
|
||||
}
|
||||
|
||||
func needsObjectStoreForRun(cfg *config.Config, stages []stage.Stage) bool {
|
||||
if cfg == nil || cfg.Pipeline == nil || cfg.Session == nil {
|
||||
return false
|
||||
}
|
||||
stageRequested := func(name string) bool {
|
||||
for _, s := range stages {
|
||||
if s != nil && s.Name() == name {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
if cfg.Session.Inputs.AudioS3 != nil && stageRequested("prepare") {
|
||||
return true
|
||||
}
|
||||
if !stageRequested("archive") {
|
||||
return false
|
||||
}
|
||||
if cfg.Pipeline.Archive == nil {
|
||||
return false
|
||||
}
|
||||
if cfg.Pipeline.Archive.Enabled != nil && !*cfg.Pipeline.Archive.Enabled {
|
||||
return false
|
||||
}
|
||||
if cfg.Pipeline.Archive.UploadRun != nil && !*cfg.Pipeline.Archive.UploadRun {
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
@@ -144,6 +144,15 @@ func TestExecuteStagesPlaceholderSuccessUpdatesManifest(t *testing.T) {
|
||||
}
|
||||
continue
|
||||
}
|
||||
if name == "archive" {
|
||||
if sr.Metadata == nil || sr.Metadata["stage"] != "archive" {
|
||||
t.Fatalf("archive metadata missing stage=archive: %#v", sr.Metadata)
|
||||
}
|
||||
if sr.Metadata["skipped"] != true {
|
||||
t.Fatalf("archive metadata missing skipped=true for test config without archive section: %#v", sr.Metadata)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if sr.Metadata == nil || sr.Metadata["placeholder"] != true {
|
||||
t.Fatalf("stage %q missing placeholder metadata", name)
|
||||
}
|
||||
@@ -315,7 +324,7 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
|
||||
{name: "merge", env: &Env{Seriatim: &seriatim.FakeRunner{Err: errors.New("merge fail")}}},
|
||||
{name: "polish", env: &Env{Audita: &audita.FakeRunner{Err: errors.New("polish fail")}}},
|
||||
{name: "analyze", env: &Env{Scriptorium: &scriptorium.FakeRunner{RunErr: errors.New("analyze fail")}}},
|
||||
{name: "archive", env: &Env{Storage: &storage.FakeBackend{Err: errors.New("archive fail")}}},
|
||||
{name: "archive", env: &Env{ObjectStore: &storage.FakeBackend{UploadErr: errors.New("archive fail")}}},
|
||||
{name: "notify", env: &Env{Notifier: ¬ify.FakeSender{Err: errors.New("notify fail")}}},
|
||||
}
|
||||
|
||||
@@ -400,6 +409,41 @@ func TestAdapterBackedStageFailureMarksManifestFailed(t *testing.T) {
|
||||
},
|
||||
}
|
||||
}
|
||||
if tc.name == "archive" {
|
||||
cfg.Pipeline.Archive = &config.ArchiveConfig{
|
||||
Enabled: boolPtr(true),
|
||||
UploadRun: boolPtr(true),
|
||||
}
|
||||
cfg.Pipeline.Storage.S3 = &config.StorageS3Config{
|
||||
Bucket: "my-dnd-archive",
|
||||
RootPrefix: "dnd",
|
||||
}
|
||||
runID := "20260516T010203Z-0a1b2c3d"
|
||||
runWorkDir := filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.Campaign, cfg.Session.SessionID, runID)
|
||||
if err := os.MkdirAll(filepath.Join(runWorkDir, "inputs"), 0o755); err != nil {
|
||||
t.Fatalf("mkdir archive inputs dir: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(runWorkDir, "inputs", "session.yml"), []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
|
||||
t.Fatalf("write archive fixture session.yml: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(runWorkDir, "manifest.json"), []byte("{}\n"), 0o644); err != nil {
|
||||
t.Fatalf("write archive fixture manifest.json: %v", err)
|
||||
}
|
||||
|
||||
seed := manifest.New(cfg.Session.SessionID, time.Now().UTC())
|
||||
seed.Campaign = cfg.Session.Campaign
|
||||
seed.RunID = runID
|
||||
seed.LocalWorkDir = runWorkDir
|
||||
seed.S3Bucket = "my-dnd-archive"
|
||||
seed.S3SessionPrefix = "dnd/campaigns/" + cfg.Session.Campaign + "/sessions/" + cfg.Session.SessionID + "/"
|
||||
seed.S3RunPrefix = seed.S3SessionPrefix + "runs/" + runID + "/"
|
||||
for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze"} {
|
||||
seed.MarkStageSucceeded(name, time.Now().UTC(), nil)
|
||||
}
|
||||
if err := tc.env.ManifestStore.Save(context.Background(), manifestPathFor(cfg), seed); err != nil {
|
||||
t.Fatalf("seed archive manifest: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
_, runErr := executeStages(context.Background(), cfg, []stage.Stage{selected}, RunOptions{Env: tc.env})
|
||||
if runErr == nil {
|
||||
@@ -430,7 +474,7 @@ func testConfig(t *testing.T) *config.Config {
|
||||
pipelinePath := filepath.Join(cfgDir, "pipeline.yml")
|
||||
|
||||
mustWriteFile(t, pipelinePath, "workspace:\n root: "+workspace+"\n")
|
||||
mustWriteFile(t, sessionPath, "session_id: 2026-05-03\n")
|
||||
mustWriteFile(t, sessionPath, "session_id: 2026-05-03\ncampaign: sample-campaign\n")
|
||||
mustWriteFile(t, filepath.Join(cfgDir, "speakers.yml"), "alice: alice.flac\n")
|
||||
mustWriteFile(t, filepath.Join(cfgDir, "autocorrect.yml"), "[]\n")
|
||||
mustWriteFile(t, filepath.Join(cfgDir, "glossary.yml"), "[]\n")
|
||||
@@ -442,6 +486,7 @@ func testConfig(t *testing.T) *config.Config {
|
||||
SessionPath: sessionPath,
|
||||
Session: &config.SessionConfig{
|
||||
SessionID: "2026-05-03",
|
||||
Campaign: "sample-campaign",
|
||||
Inputs: config.SessionInputsConfig{
|
||||
AudioDir: "./audio",
|
||||
SpeakersFile: "./speakers.yml",
|
||||
@@ -452,6 +497,55 @@ func testConfig(t *testing.T) *config.Config {
|
||||
}
|
||||
}
|
||||
|
||||
func TestBuildDefaultRunnersWithOmittedToolSections(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
pipelinePath := filepath.Join(dir, "pipeline.yml")
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
pipelineYAML := `workspace:
|
||||
root: ` + t.TempDir() + `
|
||||
whisperx:
|
||||
transcribe_url: https://example.com/transcribe
|
||||
analyzer:
|
||||
timeout: 20m
|
||||
notification:
|
||||
timeout: 10s
|
||||
`
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
mustWriteFile(t, pipelinePath, pipelineYAML)
|
||||
mustWriteFile(t, sessionPath, sessionYAML)
|
||||
|
||||
cfg, err := config.Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
if err := config.Validate(cfg); err != nil {
|
||||
t.Fatalf("Validate() error = %v", err)
|
||||
}
|
||||
|
||||
serRunner, err := buildDefaultSeriatimRunner(cfg)
|
||||
if err != nil {
|
||||
t.Fatalf("buildDefaultSeriatimRunner() error = %v", err)
|
||||
}
|
||||
if _, ok := serRunner.(*seriatim.SubprocessRunner); !ok {
|
||||
t.Fatalf("seriatim runner type = %T, want *seriatim.SubprocessRunner", serRunner)
|
||||
}
|
||||
|
||||
audRunner, err := buildDefaultAuditaRunner(cfg)
|
||||
if err != nil {
|
||||
t.Fatalf("buildDefaultAuditaRunner() error = %v", err)
|
||||
}
|
||||
if _, ok := audRunner.(*audita.SubprocessRunner); !ok {
|
||||
t.Fatalf("audita runner type = %T, want *audita.SubprocessRunner", audRunner)
|
||||
}
|
||||
}
|
||||
|
||||
func mustWriteFile(t *testing.T, path, contents string) {
|
||||
t.Helper()
|
||||
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
|
||||
@@ -461,3 +555,8 @@ func mustWriteFile(t *testing.T, path, contents string) {
|
||||
t.Fatalf("WriteFile(%q): %v", path, err)
|
||||
}
|
||||
}
|
||||
|
||||
func boolPtr(v bool) *bool {
|
||||
p := v
|
||||
return &p
|
||||
}
|
||||
|
||||
88
internal/app/secrets_env.go
Normal file
88
internal/app/secrets_env.go
Normal file
@@ -0,0 +1,88 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
var envVarNamePattern = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
|
||||
|
||||
type secretsLoadStats struct {
|
||||
Dir string
|
||||
Loaded int
|
||||
PreservedExisting int
|
||||
Skipped int
|
||||
}
|
||||
|
||||
func loadSecretsFromConfig(cfg *config.Config, logger *slog.Logger) (*secretsLoadStats, error) {
|
||||
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Secrets == nil {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
rawDir := strings.TrimSpace(cfg.Pipeline.Secrets.EnvDir)
|
||||
if rawDir == "" {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
resolvedDir := rawDir
|
||||
if !filepath.IsAbs(resolvedDir) {
|
||||
cwd, err := os.Getwd()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("resolve secrets env_dir %q from current working directory: %w", rawDir, err)
|
||||
}
|
||||
resolvedDir = filepath.Join(cwd, resolvedDir)
|
||||
}
|
||||
resolvedDir = filepath.Clean(resolvedDir)
|
||||
|
||||
entries, err := os.ReadDir(resolvedDir)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("read secrets env_dir %q: %w", resolvedDir, err)
|
||||
}
|
||||
|
||||
stats := &secretsLoadStats{Dir: resolvedDir}
|
||||
for _, entry := range entries {
|
||||
name := entry.Name()
|
||||
if !envVarNamePattern.MatchString(name) {
|
||||
stats.Skipped++
|
||||
continue
|
||||
}
|
||||
if entry.IsDir() {
|
||||
stats.Skipped++
|
||||
continue
|
||||
}
|
||||
|
||||
secretPath := filepath.Join(resolvedDir, name)
|
||||
bytes, err := os.ReadFile(secretPath)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("read secret file %q: %w", secretPath, err)
|
||||
}
|
||||
value := strings.TrimRight(string(bytes), "\r\n")
|
||||
|
||||
if _, exists := os.LookupEnv(name); exists {
|
||||
stats.PreservedExisting++
|
||||
continue
|
||||
}
|
||||
if err := os.Setenv(name, value); err != nil {
|
||||
return nil, fmt.Errorf("set environment variable %q from %q: %w", name, secretPath, err)
|
||||
}
|
||||
stats.Loaded++
|
||||
}
|
||||
|
||||
if logger != nil {
|
||||
logger.Info(
|
||||
"loaded secret environment variables from filesystem",
|
||||
"secrets_env_dir", stats.Dir,
|
||||
"loaded", stats.Loaded,
|
||||
"preserved_existing", stats.PreservedExisting,
|
||||
"skipped", stats.Skipped,
|
||||
)
|
||||
}
|
||||
|
||||
return stats, nil
|
||||
}
|
||||
155
internal/app/secrets_env_test.go
Normal file
155
internal/app/secrets_env_test.go
Normal file
@@ -0,0 +1,155 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
func TestLoadSecretsFromConfigLoadsValidFiles(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
mustWriteSecretFile(t, filepath.Join(dir, "NARRATIO_TEST_SECRET_A"), "value-1\n")
|
||||
mustWriteSecretFile(t, filepath.Join(dir, "NARRATIO_TEST_SECRET_B"), "value-2\r\n")
|
||||
mustWriteSecretFile(t, filepath.Join(dir, "not-valid-name.txt"), "ignored")
|
||||
|
||||
cfg := &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Secrets: &config.SecretsConfig{EnvDir: dir},
|
||||
},
|
||||
}
|
||||
|
||||
stats, err := loadSecretsFromConfig(cfg, nil)
|
||||
if err != nil {
|
||||
t.Fatalf("loadSecretsFromConfig() error = %v", err)
|
||||
}
|
||||
if stats == nil {
|
||||
t.Fatal("stats = nil, want non-nil")
|
||||
}
|
||||
if stats.Loaded != 2 {
|
||||
t.Fatalf("Loaded = %d, want 2", stats.Loaded)
|
||||
}
|
||||
if stats.PreservedExisting != 0 {
|
||||
t.Fatalf("PreservedExisting = %d, want 0", stats.PreservedExisting)
|
||||
}
|
||||
if stats.Skipped == 0 {
|
||||
t.Fatalf("Skipped = %d, want > 0 for invalid filename", stats.Skipped)
|
||||
}
|
||||
if got := os.Getenv("NARRATIO_TEST_SECRET_A"); got != "value-1" {
|
||||
t.Fatalf("NARRATIO_TEST_SECRET_A = %q, want value-1", got)
|
||||
}
|
||||
if got := os.Getenv("NARRATIO_TEST_SECRET_B"); got != "value-2" {
|
||||
t.Fatalf("NARRATIO_TEST_SECRET_B = %q, want value-2", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSecretsFromConfigPreservesExistingEnv(t *testing.T) {
|
||||
t.Setenv("OBJECT_STORAGE_KEY", "existing")
|
||||
|
||||
dir := t.TempDir()
|
||||
mustWriteSecretFile(t, filepath.Join(dir, "OBJECT_STORAGE_KEY"), "from-file\n")
|
||||
|
||||
cfg := &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Secrets: &config.SecretsConfig{EnvDir: dir},
|
||||
},
|
||||
}
|
||||
|
||||
stats, err := loadSecretsFromConfig(cfg, nil)
|
||||
if err != nil {
|
||||
t.Fatalf("loadSecretsFromConfig() error = %v", err)
|
||||
}
|
||||
if stats.PreservedExisting != 1 {
|
||||
t.Fatalf("PreservedExisting = %d, want 1", stats.PreservedExisting)
|
||||
}
|
||||
if got := os.Getenv("OBJECT_STORAGE_KEY"); got != "existing" {
|
||||
t.Fatalf("OBJECT_STORAGE_KEY = %q, want existing", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSecretsFromConfigRelativeDirUsesCWD(t *testing.T) {
|
||||
cwd := t.TempDir()
|
||||
secretsDir := filepath.Join(cwd, "secrets")
|
||||
if err := os.MkdirAll(secretsDir, 0o755); err != nil {
|
||||
t.Fatalf("MkdirAll(%q): %v", secretsDir, err)
|
||||
}
|
||||
mustWriteSecretFile(t, filepath.Join(secretsDir, "OBJECT_STORAGE_KEY_ID"), "id-123\n")
|
||||
|
||||
originalWD, err := os.Getwd()
|
||||
if err != nil {
|
||||
t.Fatalf("Getwd(): %v", err)
|
||||
}
|
||||
if err := os.Chdir(cwd); err != nil {
|
||||
t.Fatalf("Chdir(%q): %v", cwd, err)
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
_ = os.Chdir(originalWD)
|
||||
})
|
||||
|
||||
cfg := &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Secrets: &config.SecretsConfig{EnvDir: "./secrets"},
|
||||
},
|
||||
}
|
||||
if _, err := loadSecretsFromConfig(cfg, nil); err != nil {
|
||||
t.Fatalf("loadSecretsFromConfig() error = %v", err)
|
||||
}
|
||||
if got := os.Getenv("OBJECT_STORAGE_KEY_ID"); got != "id-123" {
|
||||
t.Fatalf("OBJECT_STORAGE_KEY_ID = %q, want id-123", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSecretsFromConfigMissingDirFails(t *testing.T) {
|
||||
cfg := &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Secrets: &config.SecretsConfig{EnvDir: filepath.Join(t.TempDir(), "missing")},
|
||||
},
|
||||
}
|
||||
|
||||
_, err := loadSecretsFromConfig(cfg, nil)
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "read secrets env_dir") {
|
||||
t.Fatalf("error = %q, want read-dir context", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSecretsFromConfigUnreadableValidEntryFails(t *testing.T) {
|
||||
if runtime.GOOS == "windows" {
|
||||
t.Skip("symlink behavior differs on windows")
|
||||
}
|
||||
|
||||
dir := t.TempDir()
|
||||
broken := filepath.Join(dir, "OPENROUTER_API_KEY")
|
||||
if err := os.Symlink(filepath.Join(dir, "does-not-exist"), broken); err != nil {
|
||||
t.Fatalf("Symlink(%q): %v", broken, err)
|
||||
}
|
||||
|
||||
cfg := &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Secrets: &config.SecretsConfig{EnvDir: dir},
|
||||
},
|
||||
}
|
||||
|
||||
_, err := loadSecretsFromConfig(cfg, nil)
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "read secret file") {
|
||||
t.Fatalf("error = %q, want read secret file context", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func mustWriteSecretFile(t *testing.T, path, contents string) {
|
||||
t.Helper()
|
||||
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
|
||||
t.Fatalf("MkdirAll(%q): %v", path, err)
|
||||
}
|
||||
if err := os.WriteFile(path, []byte(contents), 0o600); err != nil {
|
||||
t.Fatalf("WriteFile(%q): %v", path, err)
|
||||
}
|
||||
}
|
||||
86
internal/app/session_cli_test.go
Normal file
86
internal/app/session_cli_test.go
Normal file
@@ -0,0 +1,86 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestPlanUsesDiscoveredSessionTemplateWithSessionID(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
|
||||
|
||||
sessionTemplate := `session_id: "{{ session_id }}"
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionTemplate), 0o644); err != nil {
|
||||
t.Fatalf("write session template: %v", err)
|
||||
}
|
||||
|
||||
cwd := filepath.Dir(sessionPath)
|
||||
originalWD, err := os.Getwd()
|
||||
if err != nil {
|
||||
t.Fatalf("Getwd(): %v", err)
|
||||
}
|
||||
if err := os.Chdir(cwd); err != nil {
|
||||
t.Fatalf("Chdir(%q): %v", cwd, err)
|
||||
}
|
||||
t.Cleanup(func() { _ = os.Chdir(originalWD) })
|
||||
|
||||
var out bytes.Buffer
|
||||
if err := Plan(context.Background(), []string{"--config", pipelinePath, "--session-id", "2026-04-04"}, &out); err != nil {
|
||||
t.Fatalf("Plan() error = %v", err)
|
||||
}
|
||||
if !strings.Contains(out.String(), "narratio plan: workdir prepared") {
|
||||
t.Fatalf("output = %q, want plan output", out.String())
|
||||
}
|
||||
}
|
||||
|
||||
func TestPlanFailsWhenSessionIDMismatchesConcreteSession(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
|
||||
|
||||
var out bytes.Buffer
|
||||
err := Plan(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath, "--session-id", "2026-04-04"}, &out)
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "session_id mismatch") {
|
||||
t.Fatalf("error = %q, want mismatch context", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunStageAcceptsSessionIDFlagAndParsesStageName(t *testing.T) {
|
||||
workspaceRoot := t.TempDir()
|
||||
pipelinePath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
|
||||
|
||||
var out bytes.Buffer
|
||||
err := RunStage(context.Background(), []string{"--config", pipelinePath, "--session", sessionPath, "--session-id", "2026-05-03", "prepare"}, &out)
|
||||
if err != nil {
|
||||
t.Fatalf("RunStage() error = %v", err)
|
||||
}
|
||||
if !strings.Contains(out.String(), "stage=prepare") {
|
||||
t.Fatalf("output = %q, want stage output", out.String())
|
||||
}
|
||||
}
|
||||
|
||||
func TestResolveSessionConfigPathErrorIncludesSearchedPaths(t *testing.T) {
|
||||
_, err := resolveSessionConfigPathWithCandidates("", []string{"./session.yml", "/usr/local/etc/narratio/session.yml", "/etc/narratio/session.yml"})
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "searched") {
|
||||
t.Fatalf("error = %q, want searched paths", err.Error())
|
||||
}
|
||||
if !strings.Contains(err.Error(), "pass --session") {
|
||||
t.Fatalf("error = %q, want explicit-session guidance", err.Error())
|
||||
}
|
||||
}
|
||||
49
internal/app/session_config_path.go
Normal file
49
internal/app/session_config_path.go
Normal file
@@ -0,0 +1,49 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/config"
|
||||
)
|
||||
|
||||
func resolveSessionConfigPath(flagValue string) (string, error) {
|
||||
return resolveSessionConfigPathWithCandidates(flagValue, config.DefaultSessionConfigSearchPaths)
|
||||
}
|
||||
|
||||
func resolveSessionConfigPathWithCandidates(flagValue string, candidates []string) (string, error) {
|
||||
if explicit := strings.TrimSpace(flagValue); explicit != "" {
|
||||
return explicit, nil
|
||||
}
|
||||
|
||||
ordered := make([]string, 0, len(candidates))
|
||||
for _, raw := range candidates {
|
||||
path := strings.TrimSpace(raw)
|
||||
if path == "" {
|
||||
continue
|
||||
}
|
||||
ordered = append(ordered, path)
|
||||
info, err := os.Stat(path)
|
||||
if err == nil {
|
||||
if info.IsDir() {
|
||||
continue
|
||||
}
|
||||
return filepath.Clean(path), nil
|
||||
}
|
||||
if errors.Is(err, os.ErrNotExist) {
|
||||
continue
|
||||
}
|
||||
return "", fmt.Errorf("check default session config %q: %w", path, err)
|
||||
}
|
||||
|
||||
if len(ordered) == 0 {
|
||||
return "", fmt.Errorf("no session config path provided and no default locations configured")
|
||||
}
|
||||
return "", fmt.Errorf(
|
||||
"no session config path provided and no default session config found; searched: %s; pass --session to use an explicit path",
|
||||
strings.Join(ordered, ", "),
|
||||
)
|
||||
}
|
||||
68
internal/app/session_config_path_test.go
Normal file
68
internal/app/session_config_path_test.go
Normal file
@@ -0,0 +1,68 @@
|
||||
package app
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestResolveSessionConfigPathWithCandidatesExplicitWins(t *testing.T) {
|
||||
got, err := resolveSessionConfigPathWithCandidates(" ./custom/session.yml ", []string{"./session.yml", "/a", "/b"})
|
||||
if err != nil {
|
||||
t.Fatalf("resolveSessionConfigPathWithCandidates() error = %v", err)
|
||||
}
|
||||
if got != "./custom/session.yml" {
|
||||
t.Fatalf("resolved path = %q, want explicit path", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestResolveSessionConfigPathWithCandidatesUsesFirstExisting(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
first := filepath.Join(dir, "first.yml")
|
||||
second := filepath.Join(dir, "second.yml")
|
||||
if err := os.WriteFile(second, []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
|
||||
t.Fatalf("write second default: %v", err)
|
||||
}
|
||||
|
||||
got, err := resolveSessionConfigPathWithCandidates("", []string{first, second})
|
||||
if err != nil {
|
||||
t.Fatalf("resolveSessionConfigPathWithCandidates() error = %v", err)
|
||||
}
|
||||
if got != filepath.Clean(second) {
|
||||
t.Fatalf("resolved path = %q, want %q", got, filepath.Clean(second))
|
||||
}
|
||||
}
|
||||
|
||||
func TestResolveSessionConfigPathWithCandidatesPrecedence(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
first := filepath.Join(dir, "first.yml")
|
||||
second := filepath.Join(dir, "second.yml")
|
||||
if err := os.WriteFile(first, []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
|
||||
t.Fatalf("write first default: %v", err)
|
||||
}
|
||||
if err := os.WriteFile(second, []byte("session_id: 2026-05-03\n"), 0o644); err != nil {
|
||||
t.Fatalf("write second default: %v", err)
|
||||
}
|
||||
|
||||
got, err := resolveSessionConfigPathWithCandidates("", []string{first, second})
|
||||
if err != nil {
|
||||
t.Fatalf("resolveSessionConfigPathWithCandidates() error = %v", err)
|
||||
}
|
||||
if got != filepath.Clean(first) {
|
||||
t.Fatalf("resolved path = %q, want first candidate %q", got, filepath.Clean(first))
|
||||
}
|
||||
}
|
||||
|
||||
func TestResolveSessionConfigPathWithCandidatesMissing(t *testing.T) {
|
||||
_, err := resolveSessionConfigPathWithCandidates("", []string{"/does/not/exist/one.yml", "/does/not/exist/two.yml"})
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "no default session config found") {
|
||||
t.Fatalf("error = %q, want missing-defaults context", err.Error())
|
||||
}
|
||||
if !strings.Contains(err.Error(), "pass --session") {
|
||||
t.Fatalf("error = %q, want explicit-path guidance", err.Error())
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,8 @@
|
||||
package artifacts
|
||||
|
||||
import "path/filepath"
|
||||
import (
|
||||
"path/filepath"
|
||||
)
|
||||
|
||||
// SessionPaths contains canonical local paths for one session work directory.
|
||||
type SessionPaths struct {
|
||||
@@ -23,6 +25,16 @@ func SessionWorkDir(rootDir, sessionID string) string {
|
||||
return filepath.Join(rootDir, "work", sessionID)
|
||||
}
|
||||
|
||||
// SessionRunWorkDir returns the campaign/session/run scoped local work directory.
|
||||
func SessionRunWorkDir(rootDir, campaign, sessionID, runID string) string {
|
||||
return filepath.Join(rootDir, "work", campaign, sessionID, runID)
|
||||
}
|
||||
|
||||
// SessionSpoolAudioDir returns the campaign/session/run scoped local spool audio path.
|
||||
func SessionSpoolAudioDir(spoolRoot, campaign, sessionID, runID string) string {
|
||||
return filepath.Join(spoolRoot, campaign, sessionID, runID, "audio")
|
||||
}
|
||||
|
||||
func buildSessionPaths(workspaceRoot, sessionID string) SessionPaths {
|
||||
root := SessionWorkDir(workspaceRoot, sessionID)
|
||||
transcripts := filepath.Join(root, "transcripts")
|
||||
|
||||
24
internal/artifacts/paths_model_test.go
Normal file
24
internal/artifacts/paths_model_test.go
Normal file
@@ -0,0 +1,24 @@
|
||||
package artifacts
|
||||
|
||||
import (
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestSessionRunWorkDir(t *testing.T) {
|
||||
root := "/tmp/workspace"
|
||||
got := SessionRunWorkDir(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4")
|
||||
want := filepath.Join(root, "work", "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4")
|
||||
if got != want {
|
||||
t.Fatalf("SessionRunWorkDir() = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestSessionSpoolAudioDir(t *testing.T) {
|
||||
root := "/var/spool/narratio"
|
||||
got := SessionSpoolAudioDir(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4")
|
||||
want := filepath.Join(root, "forsaken", "2026-04-19", "20260515T031522Z-a1b2c3d4", "audio")
|
||||
if got != want {
|
||||
t.Fatalf("SessionSpoolAudioDir() = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
30
internal/artifacts/run_id.go
Normal file
30
internal/artifacts/run_id.go
Normal file
@@ -0,0 +1,30 @@
|
||||
package artifacts
|
||||
|
||||
import (
|
||||
"crypto/rand"
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"io"
|
||||
"time"
|
||||
)
|
||||
|
||||
// NewRunID returns a run ID in format: YYYYMMDDTHHMMSSZ-xxxxxxxx.
|
||||
func NewRunID() (string, error) {
|
||||
return NewRunIDWith(time.Now().UTC(), rand.Reader)
|
||||
}
|
||||
|
||||
// NewRunIDWith returns a run ID in format: YYYYMMDDTHHMMSSZ-xxxxxxxx
|
||||
// using an injected timestamp and randomness source.
|
||||
func NewRunIDWith(now time.Time, random io.Reader) (string, error) {
|
||||
if random == nil {
|
||||
random = rand.Reader
|
||||
}
|
||||
|
||||
var suffix [4]byte
|
||||
if _, err := io.ReadFull(random, suffix[:]); err != nil {
|
||||
return "", fmt.Errorf("generate run id random suffix: %w", err)
|
||||
}
|
||||
|
||||
ts := now.UTC().Format("20060102T150405Z")
|
||||
return ts + "-" + hex.EncodeToString(suffix[:]), nil
|
||||
}
|
||||
37
internal/artifacts/run_id_test.go
Normal file
37
internal/artifacts/run_id_test.go
Normal file
@@ -0,0 +1,37 @@
|
||||
package artifacts
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"regexp"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
func TestNewRunIDWithFormat(t *testing.T) {
|
||||
now := time.Date(2026, 5, 15, 3, 15, 22, 0, time.UTC)
|
||||
random := bytes.NewReader([]byte{0xa1, 0xb2, 0xc3, 0xd4})
|
||||
|
||||
runID, err := NewRunIDWith(now, random)
|
||||
if err != nil {
|
||||
t.Fatalf("NewRunIDWith() error = %v", err)
|
||||
}
|
||||
if runID != "20260515T031522Z-a1b2c3d4" {
|
||||
t.Fatalf("runID = %q, want %q", runID, "20260515T031522Z-a1b2c3d4")
|
||||
}
|
||||
}
|
||||
|
||||
func TestNewRunIDWithShape(t *testing.T) {
|
||||
runID, err := NewRunIDWith(time.Now().UTC(), bytes.NewReader([]byte{0x01, 0x02, 0x03, 0x04}))
|
||||
if err != nil {
|
||||
t.Fatalf("NewRunIDWith() error = %v", err)
|
||||
}
|
||||
pattern := regexp.MustCompile(`^\d{8}T\d{6}Z-[0-9a-f]{8}$`)
|
||||
if !pattern.MatchString(runID) {
|
||||
t.Fatalf("runID = %q, want pattern %q", runID, pattern.String())
|
||||
}
|
||||
suffix := runID[len(runID)-8:]
|
||||
if strings.ToLower(suffix) != suffix {
|
||||
t.Fatalf("runID suffix = %q, want lowercase", suffix)
|
||||
}
|
||||
}
|
||||
73
internal/artifacts/s3_keys.go
Normal file
73
internal/artifacts/s3_keys.go
Normal file
@@ -0,0 +1,73 @@
|
||||
package artifacts
|
||||
|
||||
import (
|
||||
"path"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// S3SessionPrefix builds the canonical S3 session prefix.
|
||||
// Format: {root_prefix}/campaigns/{campaign}/sessions/{session_id}/
|
||||
func S3SessionPrefix(rootPrefix, campaign, sessionID string) string {
|
||||
prefix := path.Join(
|
||||
cleanS3PathPart(rootPrefix),
|
||||
"campaigns",
|
||||
cleanS3PathPart(campaign),
|
||||
"sessions",
|
||||
cleanS3PathPart(sessionID),
|
||||
)
|
||||
return ensureS3TrailingSlash(prefix)
|
||||
}
|
||||
|
||||
// S3RunPrefix builds the canonical S3 run prefix.
|
||||
// Format: {session_prefix}/runs/{run_id}/
|
||||
func S3RunPrefix(sessionPrefix, runID string) string {
|
||||
prefix := path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), "runs", cleanS3PathPart(runID))
|
||||
return ensureS3TrailingSlash(prefix)
|
||||
}
|
||||
|
||||
// S3AudioPrefix builds the session audio prefix from configured audio_s3.prefix.
|
||||
// Format: {session_prefix}/{audio_s3.prefix}
|
||||
func S3AudioPrefix(sessionPrefix, audioPrefix string) string {
|
||||
key := path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), cleanS3Key(audioPrefix))
|
||||
return ensureS3TrailingSlash(key)
|
||||
}
|
||||
|
||||
// S3CurrentManifestKey returns the current manifest pointer key.
|
||||
// Format: {session_prefix}/current/manifest.json
|
||||
func S3CurrentManifestKey(sessionPrefix string) string {
|
||||
return path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), "current", "manifest.json")
|
||||
}
|
||||
|
||||
// S3CurrentRunPointerKey returns the current run pointer key.
|
||||
// Format: {session_prefix}/current/run_id.txt
|
||||
func S3CurrentRunPointerKey(sessionPrefix string) string {
|
||||
return path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), "current", "run_id.txt")
|
||||
}
|
||||
|
||||
// S3PromotedArtifactKey returns the destination key for one promoted artifact.
|
||||
// Format: {session_prefix}/{promotion.to}
|
||||
func S3PromotedArtifactKey(sessionPrefix, to string) string {
|
||||
return path.Join(strings.TrimSuffix(cleanS3Key(sessionPrefix), "/"), cleanS3Key(to))
|
||||
}
|
||||
|
||||
// S3RunRelativeDestinationKey returns a run-scoped key for a workdir-relative path.
|
||||
// Format: {run_prefix}/{relative_workdir_path}
|
||||
func S3RunRelativeDestinationKey(runPrefix, relativeWorkdirPath string) string {
|
||||
return path.Join(strings.TrimSuffix(cleanS3Key(runPrefix), "/"), cleanS3Key(relativeWorkdirPath))
|
||||
}
|
||||
|
||||
func ensureS3TrailingSlash(v string) string {
|
||||
key := cleanS3Key(v)
|
||||
if key == "" {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSuffix(key, "/") + "/"
|
||||
}
|
||||
|
||||
func cleanS3PathPart(v string) string {
|
||||
return strings.Trim(strings.ReplaceAll(strings.TrimSpace(v), "\\", "/"), "/")
|
||||
}
|
||||
|
||||
func cleanS3Key(v string) string {
|
||||
return strings.ReplaceAll(strings.TrimSpace(v), "\\", "/")
|
||||
}
|
||||
45
internal/artifacts/s3_keys_test.go
Normal file
45
internal/artifacts/s3_keys_test.go
Normal file
@@ -0,0 +1,45 @@
|
||||
package artifacts
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestS3KeyConstruction(t *testing.T) {
|
||||
runID := "20260515T031522Z-a1b2c3d4"
|
||||
sessionPrefix := S3SessionPrefix("dnd", "forsaken", "2026-04-19")
|
||||
if sessionPrefix != "dnd/campaigns/forsaken/sessions/2026-04-19/" {
|
||||
t.Fatalf("sessionPrefix = %q", sessionPrefix)
|
||||
}
|
||||
|
||||
audioPrefix := S3AudioPrefix(sessionPrefix, "audio/")
|
||||
if audioPrefix != "dnd/campaigns/forsaken/sessions/2026-04-19/audio/" {
|
||||
t.Fatalf("audioPrefix = %q", audioPrefix)
|
||||
}
|
||||
|
||||
runPrefix := S3RunPrefix(sessionPrefix, runID)
|
||||
wantRunPrefix := "dnd/campaigns/forsaken/sessions/2026-04-19/runs/" + runID + "/"
|
||||
if runPrefix != wantRunPrefix {
|
||||
t.Fatalf("runPrefix = %q, want %q", runPrefix, wantRunPrefix)
|
||||
}
|
||||
|
||||
runPointer := S3CurrentRunPointerKey(sessionPrefix)
|
||||
if runPointer != "dnd/campaigns/forsaken/sessions/2026-04-19/current/run_id.txt" {
|
||||
t.Fatalf("run pointer key = %q", runPointer)
|
||||
}
|
||||
|
||||
manifestKey := S3CurrentManifestKey(sessionPrefix)
|
||||
if manifestKey != "dnd/campaigns/forsaken/sessions/2026-04-19/current/manifest.json" {
|
||||
t.Fatalf("manifest key = %q", manifestKey)
|
||||
}
|
||||
|
||||
promoted := S3PromotedArtifactKey(sessionPrefix, "transcripts/trimmed.json")
|
||||
if promoted != "dnd/campaigns/forsaken/sessions/2026-04-19/transcripts/trimmed.json" {
|
||||
t.Fatalf("promoted key = %q", promoted)
|
||||
}
|
||||
|
||||
runRelative := S3RunRelativeDestinationKey(runPrefix, `logs\whisperx.stdout.log`)
|
||||
if !strings.HasSuffix(runRelative, "/logs/whisperx.stdout.log") {
|
||||
t.Fatalf("runRelative key = %q, want normalized forward slashes", runRelative)
|
||||
}
|
||||
}
|
||||
@@ -12,6 +12,9 @@ type Config struct {
|
||||
type PipelineConfig struct {
|
||||
Workspace WorkspaceConfig `yaml:"workspace"`
|
||||
Storage StorageConfig `yaml:"storage"`
|
||||
Spool SpoolConfig `yaml:"spool"`
|
||||
Archive *ArchiveConfig `yaml:"archive"`
|
||||
Secrets *SecretsConfig `yaml:"secrets"`
|
||||
WhisperX WhisperXConfig `yaml:"whisperx"`
|
||||
Seriatim SeriatimConfig `yaml:"seriatim"`
|
||||
Audita AuditaConfig `yaml:"audita"`
|
||||
@@ -33,14 +36,52 @@ type SessionConfig struct {
|
||||
|
||||
// WorkspaceConfig configures local workspace behavior.
|
||||
type WorkspaceConfig struct {
|
||||
Root string `yaml:"root"`
|
||||
Root string `yaml:"root"`
|
||||
CleanupAfterArchive bool `yaml:"cleanup_after_archive"`
|
||||
}
|
||||
|
||||
// SecretsConfig configures optional local filesystem secret loading.
|
||||
type SecretsConfig struct {
|
||||
EnvDir string `yaml:"env_dir"`
|
||||
}
|
||||
|
||||
// StorageConfig configures storage backends and related parameters.
|
||||
type StorageConfig struct {
|
||||
Backend string `yaml:"backend"`
|
||||
Bucket string `yaml:"bucket"`
|
||||
Prefix string `yaml:"prefix"`
|
||||
Backend string `yaml:"backend"`
|
||||
Bucket string `yaml:"bucket"`
|
||||
Prefix string `yaml:"prefix"`
|
||||
S3 *StorageS3Config `yaml:"s3"`
|
||||
}
|
||||
|
||||
// StorageS3Config configures S3 storage coordinates.
|
||||
type StorageS3Config struct {
|
||||
Bucket string `yaml:"bucket"`
|
||||
RootPrefix string `yaml:"root_prefix"`
|
||||
Region string `yaml:"region"`
|
||||
Endpoint string `yaml:"endpoint"`
|
||||
ForcePathStyle bool `yaml:"force_path_style"`
|
||||
AccessKeyIDEnv string `yaml:"access_key_id_env"`
|
||||
SecretKeyEnv string `yaml:"secret_access_key_env"`
|
||||
}
|
||||
|
||||
// SpoolConfig configures local spool storage for staged data.
|
||||
type SpoolConfig struct {
|
||||
Root string `yaml:"root"`
|
||||
DeleteAudioAfterArchive bool `yaml:"delete_audio_after_archive"`
|
||||
}
|
||||
|
||||
// ArchiveConfig configures archive behavior and artifact promotions.
|
||||
type ArchiveConfig struct {
|
||||
Enabled *bool `yaml:"enabled"`
|
||||
UploadRun *bool `yaml:"upload_run"`
|
||||
PromoteArtifacts []ArchivePromotionRule `yaml:"promote_artifacts"`
|
||||
}
|
||||
|
||||
// ArchivePromotionRule configures one artifact promotion mapping.
|
||||
type ArchivePromotionRule struct {
|
||||
From string `yaml:"from"`
|
||||
To string `yaml:"to"`
|
||||
Required *bool `yaml:"required"`
|
||||
}
|
||||
|
||||
// WhisperXConfig configures WhisperX adapter settings.
|
||||
@@ -79,9 +120,14 @@ type AuditaConfig struct {
|
||||
Modules []string `yaml:"modules"`
|
||||
BaseURL string `yaml:"base_url"`
|
||||
Model string `yaml:"model"`
|
||||
LLMConcurrency *int `yaml:"llm_concurrency"`
|
||||
TotalLLMConcurrency *int `yaml:"total_llm_concurrency"`
|
||||
ProposalLLMConcurrency *int `yaml:"proposal_llm_concurrency"`
|
||||
ValidationModel string `yaml:"validation_model"`
|
||||
ValidationLLMConcurrency *int `yaml:"validation_llm_concurrency"`
|
||||
TranscriptDescription string `yaml:"transcript_description"`
|
||||
ConfigPath string `yaml:"config_path"`
|
||||
OutputSchema string `yaml:"output_schema"`
|
||||
WorkDirRetention string `yaml:"work_dir_retention"`
|
||||
Report *bool `yaml:"report"`
|
||||
}
|
||||
|
||||
@@ -169,9 +215,15 @@ type ArtifactSettings struct {
|
||||
|
||||
// SessionInputsConfig contains per-session input references.
|
||||
type SessionInputsConfig struct {
|
||||
AudioDir string `yaml:"audio_dir"`
|
||||
AudioFiles []string `yaml:"audio_files"`
|
||||
SpeakersFile string `yaml:"speakers_file"`
|
||||
AutocorrectFile string `yaml:"autocorrect_file"`
|
||||
GlossaryFile string `yaml:"glossary_file"`
|
||||
AudioDir string `yaml:"audio_dir"`
|
||||
AudioFiles []string `yaml:"audio_files"`
|
||||
AudioS3 *SessionAudioS3Input `yaml:"audio_s3"`
|
||||
SpeakersFile string `yaml:"speakers_file"`
|
||||
AutocorrectFile string `yaml:"autocorrect_file"`
|
||||
GlossaryFile string `yaml:"glossary_file"`
|
||||
}
|
||||
|
||||
// SessionAudioS3Input configures S3 session-audio input discovery.
|
||||
type SessionAudioS3Input struct {
|
||||
Prefix string `yaml:"prefix"`
|
||||
}
|
||||
|
||||
@@ -5,6 +5,11 @@ package config
|
||||
const (
|
||||
DefaultPipelineConfigPathUsrLocal = "/usr/local/etc/narratio/pipeline.yml"
|
||||
DefaultPipelineConfigPathEtc = "/etc/narratio/pipeline.yml"
|
||||
DefaultSessionConfigPathLocal = "./session.yml"
|
||||
DefaultSessionConfigPathUsrLocal = "/usr/local/etc/narratio/session.yml"
|
||||
DefaultSessionConfigPathEtc = "/etc/narratio/session.yml"
|
||||
DefaultS3AccessKeyIDEnv = "OBJECT_STORAGE_KEY_ID"
|
||||
DefaultS3SecretAccessKeyEnv = "OBJECT_STORAGE_KEY"
|
||||
)
|
||||
|
||||
// DefaultPipelineConfigSearchPaths defines the default search order for
|
||||
@@ -16,3 +21,14 @@ var DefaultPipelineConfigSearchPaths = []string{
|
||||
DefaultPipelineConfigPathUsrLocal,
|
||||
DefaultPipelineConfigPathEtc,
|
||||
}
|
||||
|
||||
// DefaultSessionConfigSearchPaths defines the default search order for
|
||||
// session.yml when callers do not provide an explicit path.
|
||||
//
|
||||
// Keep this in a variable so future defaults can be extended without changing
|
||||
// call sites.
|
||||
var DefaultSessionConfigSearchPaths = []string{
|
||||
DefaultSessionConfigPathLocal,
|
||||
DefaultSessionConfigPathUsrLocal,
|
||||
DefaultSessionConfigPathEtc,
|
||||
}
|
||||
|
||||
@@ -5,6 +5,8 @@ import (
|
||||
"io"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"gopkg.in/yaml.v3"
|
||||
)
|
||||
@@ -21,21 +23,56 @@ func LoadPipeline(path string) (*PipelineConfig, error) {
|
||||
|
||||
// LoadSession loads session configuration from a YAML file with strict field checking.
|
||||
func LoadSession(path string) (*SessionConfig, error) {
|
||||
var cfg SessionConfig
|
||||
if err := decodeStrictYAML("session", path, &cfg); err != nil {
|
||||
return LoadSessionWithOptions(path, SessionLoadOptions{})
|
||||
}
|
||||
|
||||
// SessionLoadOptions configures session template rendering behavior.
|
||||
type SessionLoadOptions struct {
|
||||
SessionID string
|
||||
}
|
||||
|
||||
// LoadSessionWithOptions loads session configuration from a YAML file with
|
||||
// strict field checking after template rendering.
|
||||
func LoadSessionWithOptions(path string, opts SessionLoadOptions) (*SessionConfig, error) {
|
||||
sessionBytes, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("load session config: session file %q: open: %w", path, err)
|
||||
}
|
||||
|
||||
rendered, err := renderSessionTemplate(string(sessionBytes), opts)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("load session config: %w", err)
|
||||
}
|
||||
|
||||
var cfg SessionConfig
|
||||
if err := decodeStrictYAMLFromReader("session", path, strings.NewReader(rendered), &cfg); err != nil {
|
||||
return nil, fmt.Errorf("load session config: %w", err)
|
||||
}
|
||||
if strings.TrimSpace(opts.SessionID) != "" && strings.TrimSpace(cfg.SessionID) != "" && strings.TrimSpace(cfg.SessionID) != strings.TrimSpace(opts.SessionID) {
|
||||
return nil, fmt.Errorf(
|
||||
"load session config: session file %q: session_id mismatch: --session-id %q does not match rendered session_id %q",
|
||||
path,
|
||||
strings.TrimSpace(opts.SessionID),
|
||||
strings.TrimSpace(cfg.SessionID),
|
||||
)
|
||||
}
|
||||
return &cfg, nil
|
||||
}
|
||||
|
||||
// Load loads and resolves combined pipeline and session configuration.
|
||||
func Load(pipelinePath, sessionPath string) (*Config, error) {
|
||||
return LoadWithSessionOptions(pipelinePath, sessionPath, SessionLoadOptions{})
|
||||
}
|
||||
|
||||
// LoadWithSessionOptions loads and resolves combined pipeline and session
|
||||
// configuration with session template options.
|
||||
func LoadWithSessionOptions(pipelinePath, sessionPath string, sessionOpts SessionLoadOptions) (*Config, error) {
|
||||
pipelineCfg, err := LoadPipeline(pipelinePath)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
sessionCfg, err := LoadSession(sessionPath)
|
||||
sessionCfg, err := LoadSessionWithOptions(sessionPath, sessionOpts)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -55,7 +92,11 @@ func decodeStrictYAML(kind, path string, out any) error {
|
||||
}
|
||||
defer f.Close()
|
||||
|
||||
dec := yaml.NewDecoder(f)
|
||||
return decodeStrictYAMLFromReader(kind, path, f, out)
|
||||
}
|
||||
|
||||
func decodeStrictYAMLFromReader(kind, path string, r io.Reader, out any) error {
|
||||
dec := yaml.NewDecoder(r)
|
||||
dec.KnownFields(true)
|
||||
if err := dec.Decode(out); err != nil {
|
||||
return fmt.Errorf("%s file %q: strict decode failed: %w", kind, path, err)
|
||||
@@ -69,6 +110,36 @@ func decodeStrictYAML(kind, path string, out any) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
var sessionTemplatePattern = regexp.MustCompile(`\{\{\s*([a-zA-Z_][a-zA-Z0-9_]*)\s*\}\}`)
|
||||
|
||||
func renderSessionTemplate(content string, opts SessionLoadOptions) (string, error) {
|
||||
sessionID := strings.TrimSpace(opts.SessionID)
|
||||
rendered := content
|
||||
if sessionID != "" {
|
||||
rendered = strings.ReplaceAll(rendered, "{{session_id}}", sessionID)
|
||||
rendered = strings.ReplaceAll(rendered, "{{ session_id }}", sessionID)
|
||||
}
|
||||
|
||||
unresolved := sessionTemplatePattern.FindAllStringSubmatch(rendered, -1)
|
||||
if len(unresolved) > 0 {
|
||||
vars := make([]string, 0, len(unresolved))
|
||||
for _, m := range unresolved {
|
||||
if len(m) > 1 {
|
||||
vars = append(vars, m[1])
|
||||
}
|
||||
}
|
||||
if len(vars) > 0 {
|
||||
return "", fmt.Errorf(
|
||||
"session file template rendering failed: unresolved template variable(s): %s; pass --session-id when using {{ session_id }}",
|
||||
strings.Join(vars, ", "),
|
||||
)
|
||||
}
|
||||
return "", fmt.Errorf("session file template rendering failed: unresolved template placeholders remain")
|
||||
}
|
||||
|
||||
return rendered, nil
|
||||
}
|
||||
|
||||
func shortName(path, fallback string) string {
|
||||
base := filepath.Base(path)
|
||||
if base == "." || base == string(filepath.Separator) {
|
||||
@@ -81,6 +152,9 @@ func applyPipelineDefaults(cfg *PipelineConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
applyStorageDefaults(&cfg.Storage)
|
||||
applySpoolDefaults(&cfg.Spool)
|
||||
applyArchiveDefaults(&cfg.Archive)
|
||||
applyWhisperXDefaults(&cfg.WhisperX)
|
||||
applySeriatimDefaults(&cfg.Seriatim)
|
||||
applyAuditaDefaults(&cfg.Audita)
|
||||
@@ -92,6 +166,60 @@ func applyPipelineDefaults(cfg *PipelineConfig) {
|
||||
applyScriptoriumDefaults(cfg.Scriptorium)
|
||||
}
|
||||
|
||||
func applyStorageDefaults(cfg *StorageConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
if cfg.S3 == nil {
|
||||
cfg.S3 = &StorageS3Config{}
|
||||
}
|
||||
if cfg.S3.RootPrefix == "" {
|
||||
cfg.S3.RootPrefix = "dnd"
|
||||
}
|
||||
if cfg.S3.AccessKeyIDEnv == "" {
|
||||
cfg.S3.AccessKeyIDEnv = DefaultS3AccessKeyIDEnv
|
||||
}
|
||||
if cfg.S3.SecretKeyEnv == "" {
|
||||
cfg.S3.SecretKeyEnv = DefaultS3SecretAccessKeyEnv
|
||||
}
|
||||
}
|
||||
|
||||
func applySpoolDefaults(cfg *SpoolConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
if cfg.Root == "" {
|
||||
cfg.Root = "/var/spool/narratio"
|
||||
}
|
||||
}
|
||||
|
||||
func applyArchiveDefaults(cfg **ArchiveConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
if *cfg == nil {
|
||||
*cfg = &ArchiveConfig{}
|
||||
}
|
||||
|
||||
if (*cfg).Enabled == nil {
|
||||
(*cfg).Enabled = boolPtr(true)
|
||||
}
|
||||
if (*cfg).UploadRun == nil {
|
||||
(*cfg).UploadRun = boolPtr(true)
|
||||
}
|
||||
if len((*cfg).PromoteArtifacts) == 0 {
|
||||
(*cfg).PromoteArtifacts = []ArchivePromotionRule{
|
||||
{From: "transcripts/trimmed.json", To: "transcripts/trimmed.json", Required: boolPtr(true)},
|
||||
{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md", Required: boolPtr(true)},
|
||||
}
|
||||
}
|
||||
for i := range (*cfg).PromoteArtifacts {
|
||||
if (*cfg).PromoteArtifacts[i].Required == nil {
|
||||
(*cfg).PromoteArtifacts[i].Required = boolPtr(true)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func applyWhisperXDefaults(cfg *WhisperXConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
@@ -122,6 +250,9 @@ func applySeriatimDefaults(cfg *SeriatimConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
if cfg.Binary == "" {
|
||||
cfg.Binary = "seriatim"
|
||||
}
|
||||
if cfg.Timeout == "" {
|
||||
cfg.Timeout = "10m"
|
||||
}
|
||||
@@ -140,32 +271,12 @@ func applyAuditaDefaults(cfg *AuditaConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
if cfg.Binary == "" {
|
||||
cfg.Binary = "audita"
|
||||
}
|
||||
if cfg.Timeout == "" {
|
||||
cfg.Timeout = "3h"
|
||||
}
|
||||
if cfg.Modules == nil {
|
||||
cfg.Modules = []string{
|
||||
"glossary",
|
||||
"homophones",
|
||||
"glossary",
|
||||
"spoken_word",
|
||||
"grammar",
|
||||
"homophones",
|
||||
"glossary",
|
||||
}
|
||||
}
|
||||
if cfg.BaseURL == "" {
|
||||
cfg.BaseURL = "https://openrouter.ai/api/v1"
|
||||
}
|
||||
if cfg.Model == "" {
|
||||
cfg.Model = "openrouter/google/gemma-4-31b-it"
|
||||
}
|
||||
if cfg.LLMConcurrency == nil {
|
||||
cfg.LLMConcurrency = intPtr(1)
|
||||
}
|
||||
if cfg.ValidationLLMConcurrency == nil {
|
||||
cfg.ValidationLLMConcurrency = intPtr(1)
|
||||
}
|
||||
if cfg.Report == nil {
|
||||
cfg.Report = boolPtr(true)
|
||||
}
|
||||
@@ -175,6 +286,9 @@ func applyScriptoriumDefaults(cfg *ScriptoriumConfig) {
|
||||
if cfg == nil {
|
||||
return
|
||||
}
|
||||
if cfg.Binary == "" {
|
||||
cfg.Binary = "scriptorium"
|
||||
}
|
||||
if cfg.Timeout == "" {
|
||||
cfg.Timeout = "10m"
|
||||
}
|
||||
|
||||
@@ -37,6 +37,26 @@ inputs:
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
checkDefault: true,
|
||||
},
|
||||
{
|
||||
name: "seriatim and audita sections can be omitted",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
analyzer:
|
||||
timeout: 20m
|
||||
notification:
|
||||
timeout: 15s
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
checkDefault: true,
|
||||
},
|
||||
@@ -72,6 +92,46 @@ inputs:
|
||||
`,
|
||||
wantLoadErr: "strict decode failed",
|
||||
},
|
||||
{
|
||||
name: "unknown secrets field fails",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
secrets:
|
||||
bogus: true
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantLoadErr: "strict decode failed",
|
||||
},
|
||||
{
|
||||
name: "empty secrets env_dir fails",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
secrets:
|
||||
env_dir: " "
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.secrets.env_dir must be non-empty when pipeline.secrets is configured",
|
||||
},
|
||||
{
|
||||
name: "unknown session field fails",
|
||||
pipelineYAML: `workspace:
|
||||
@@ -256,7 +316,7 @@ inputs:
|
||||
wantLoadErr: "strict decode failed",
|
||||
},
|
||||
{
|
||||
name: "missing seriatim binary fails",
|
||||
name: "missing seriatim binary uses default",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
@@ -271,7 +331,6 @@ inputs:
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.seriatim.binary is required",
|
||||
},
|
||||
{
|
||||
name: "invalid seriatim timeout fails",
|
||||
@@ -372,7 +431,7 @@ inputs:
|
||||
wantLoadErr: "strict decode failed",
|
||||
},
|
||||
{
|
||||
name: "missing audita binary fails",
|
||||
name: "missing audita binary uses default",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
@@ -389,7 +448,6 @@ inputs:
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.binary is required",
|
||||
},
|
||||
{
|
||||
name: "invalid audita timeout fails",
|
||||
@@ -413,7 +471,7 @@ inputs:
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.timeout must be a valid duration",
|
||||
},
|
||||
{
|
||||
name: "empty audita modules fails",
|
||||
name: "empty audita modules is valid override",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
@@ -431,7 +489,6 @@ inputs:
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.modules must include at least one module",
|
||||
},
|
||||
{
|
||||
name: "empty audita module item fails",
|
||||
@@ -501,7 +558,7 @@ inputs:
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.base_url must be a valid URL",
|
||||
},
|
||||
{
|
||||
name: "invalid audita llm_concurrency fails",
|
||||
name: "legacy audita llm_concurrency field fails strict decode",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
@@ -510,7 +567,7 @@ seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
llm_concurrency: 0
|
||||
llm_concurrency: 1
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
@@ -519,7 +576,49 @@ inputs:
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.llm_concurrency must be > 0",
|
||||
wantLoadErr: "strict decode failed",
|
||||
},
|
||||
{
|
||||
name: "invalid audita total_llm_concurrency fails",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
total_llm_concurrency: 0
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.total_llm_concurrency must be > 0",
|
||||
},
|
||||
{
|
||||
name: "invalid audita proposal_llm_concurrency fails",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
proposal_llm_concurrency: 0
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.proposal_llm_concurrency must be > 0",
|
||||
},
|
||||
{
|
||||
name: "invalid audita validation_llm_concurrency fails",
|
||||
@@ -542,6 +641,48 @@ inputs:
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.validation_llm_concurrency must be > 0",
|
||||
},
|
||||
{
|
||||
name: "invalid audita output_schema fails",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
output_schema: bad
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.output_schema must be one of: bare-segments, audita-v1",
|
||||
},
|
||||
{
|
||||
name: "invalid audita work_dir_retention fails",
|
||||
pipelineYAML: `workspace:
|
||||
root: /tmp/narratio
|
||||
whisperx:
|
||||
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
||||
seriatim:
|
||||
binary: seriatim
|
||||
audita:
|
||||
binary: audita
|
||||
work_dir_retention: sometimes
|
||||
`,
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.work_dir_retention must be one of: always, auto, never",
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
@@ -590,6 +731,9 @@ inputs:
|
||||
if cfg.Pipeline.Seriatim.Timeout != "10m" {
|
||||
t.Fatalf("seriatim.timeout = %q, want %q", cfg.Pipeline.Seriatim.Timeout, "10m")
|
||||
}
|
||||
if cfg.Pipeline.Seriatim.Binary != "seriatim" {
|
||||
t.Fatalf("seriatim.binary = %q, want %q", cfg.Pipeline.Seriatim.Binary, "seriatim")
|
||||
}
|
||||
if cfg.Pipeline.Seriatim.OutputSchema != "seriatim-intermediate" {
|
||||
t.Fatalf("seriatim.output_schema = %q, want %q", cfg.Pipeline.Seriatim.OutputSchema, "seriatim-intermediate")
|
||||
}
|
||||
@@ -602,26 +746,32 @@ inputs:
|
||||
if cfg.Pipeline.Audita.Timeout != "3h" {
|
||||
t.Fatalf("audita.timeout = %q, want %q", cfg.Pipeline.Audita.Timeout, "3h")
|
||||
}
|
||||
if cfg.Pipeline.Audita.Binary != "audita" {
|
||||
t.Fatalf("audita.binary = %q, want %q", cfg.Pipeline.Audita.Binary, "audita")
|
||||
}
|
||||
if cfg.Pipeline.Audita.LLMAPIKeyEnv != "" {
|
||||
t.Fatalf("audita.llm_api_key_env = %q, want empty by default", cfg.Pipeline.Audita.LLMAPIKeyEnv)
|
||||
}
|
||||
if got := strings.Join(cfg.Pipeline.Audita.Modules, ","); got != "glossary,homophones,glossary,spoken_word,grammar,homophones,glossary" {
|
||||
t.Fatalf("audita.modules = %q, want default sequence", got)
|
||||
if cfg.Pipeline.Audita.Modules != nil {
|
||||
t.Fatalf("audita.modules = %#v, want nil default (optional override)", cfg.Pipeline.Audita.Modules)
|
||||
}
|
||||
if cfg.Pipeline.Audita.BaseURL != "https://openrouter.ai/api/v1" {
|
||||
t.Fatalf("audita.base_url = %q, want %q", cfg.Pipeline.Audita.BaseURL, "https://openrouter.ai/api/v1")
|
||||
if cfg.Pipeline.Audita.BaseURL != "" {
|
||||
t.Fatalf("audita.base_url = %q, want empty default", cfg.Pipeline.Audita.BaseURL)
|
||||
}
|
||||
if cfg.Pipeline.Audita.Model != "openrouter/google/gemma-4-31b-it" {
|
||||
t.Fatalf("audita.model = %q, want %q", cfg.Pipeline.Audita.Model, "openrouter/google/gemma-4-31b-it")
|
||||
}
|
||||
if cfg.Pipeline.Audita.LLMConcurrency == nil || *cfg.Pipeline.Audita.LLMConcurrency != 1 {
|
||||
t.Fatalf("audita.llm_concurrency = %v, want 1", cfg.Pipeline.Audita.LLMConcurrency)
|
||||
if cfg.Pipeline.Audita.Model != "" {
|
||||
t.Fatalf("audita.model = %q, want empty default", cfg.Pipeline.Audita.Model)
|
||||
}
|
||||
if cfg.Pipeline.Audita.ValidationModel != "" {
|
||||
t.Fatalf("audita.validation_model = %q, want empty default", cfg.Pipeline.Audita.ValidationModel)
|
||||
}
|
||||
if cfg.Pipeline.Audita.ValidationLLMConcurrency == nil || *cfg.Pipeline.Audita.ValidationLLMConcurrency != 1 {
|
||||
t.Fatalf("audita.validation_llm_concurrency = %v, want 1", cfg.Pipeline.Audita.ValidationLLMConcurrency)
|
||||
if cfg.Pipeline.Audita.TotalLLMConcurrency != nil {
|
||||
t.Fatalf("audita.total_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.TotalLLMConcurrency)
|
||||
}
|
||||
if cfg.Pipeline.Audita.ProposalLLMConcurrency != nil {
|
||||
t.Fatalf("audita.proposal_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.ProposalLLMConcurrency)
|
||||
}
|
||||
if cfg.Pipeline.Audita.ValidationLLMConcurrency != nil {
|
||||
t.Fatalf("audita.validation_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.ValidationLLMConcurrency)
|
||||
}
|
||||
if cfg.Pipeline.Audita.Report == nil || *cfg.Pipeline.Audita.Report != true {
|
||||
t.Fatalf("audita.report = %v, want true", cfg.Pipeline.Audita.Report)
|
||||
@@ -685,7 +835,8 @@ func TestValidateMissingAudioSource(t *testing.T) {
|
||||
Modules: []string{"glossary", "homophones"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: intPtr(1),
|
||||
TotalLLMConcurrency: intPtr(1),
|
||||
ProposalLLMConcurrency: intPtr(1),
|
||||
ValidationModel: "",
|
||||
ValidationLLMConcurrency: intPtr(1),
|
||||
Report: boolPtr(true),
|
||||
@@ -693,6 +844,7 @@ func TestValidateMissingAudioSource(t *testing.T) {
|
||||
},
|
||||
Session: &SessionConfig{
|
||||
SessionID: "2026-05-03",
|
||||
Campaign: "sample-campaign",
|
||||
Inputs: SessionInputsConfig{
|
||||
SpeakersFile: "speakers.yml",
|
||||
AutocorrectFile: "autocorrect.yml",
|
||||
@@ -705,7 +857,7 @@ func TestValidateMissingAudioSource(t *testing.T) {
|
||||
if err == nil {
|
||||
t.Fatal("expected validation error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "audio_dir or at least one audio_files") {
|
||||
if !strings.Contains(err.Error(), "audio_dir, at least one audio_files entry, or audio_s3") {
|
||||
t.Fatalf("error = %q, want audio source guidance", err.Error())
|
||||
}
|
||||
if !strings.Contains(err.Error(), "session config") {
|
||||
@@ -734,6 +886,12 @@ func writeConfigFiles(t *testing.T, pipelineYAML, sessionYAML string) (string, s
|
||||
}
|
||||
pipelineYAML += "audita:\n binary: audita\n"
|
||||
}
|
||||
if !strings.Contains(sessionYAML, "\ncampaign:") && !strings.HasPrefix(sessionYAML, "campaign:") {
|
||||
if !strings.HasSuffix(sessionYAML, "\n") {
|
||||
sessionYAML += "\n"
|
||||
}
|
||||
sessionYAML += "campaign: sample-campaign\n"
|
||||
}
|
||||
|
||||
dir := t.TempDir()
|
||||
pipelinePath := filepath.Join(dir, "pipeline.yml")
|
||||
|
||||
@@ -49,11 +49,19 @@ func TestScriptoriumLoadAndValidate(t *testing.T) {
|
||||
wantLoadErr: "strict decode failed",
|
||||
},
|
||||
{
|
||||
name: "missing binary fails when section present",
|
||||
name: "missing binary defaults when section present",
|
||||
scriptoriumYAML: `scriptorium:
|
||||
timeout: 10m
|
||||
`,
|
||||
wantValidateErr: "pipeline.scriptorium.binary is required",
|
||||
assert: func(t *testing.T, cfg *Config) {
|
||||
t.Helper()
|
||||
if cfg.Pipeline.Scriptorium == nil {
|
||||
t.Fatal("scriptorium config should be present")
|
||||
}
|
||||
if cfg.Pipeline.Scriptorium.Binary != "scriptorium" {
|
||||
t.Fatalf("scriptorium.binary = %q, want scriptorium", cfg.Pipeline.Scriptorium.Binary)
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "enabled artifact missing prompt id fails",
|
||||
|
||||
156
internal/config/session_template_test.go
Normal file
156
internal/config/session_template_test.go
Normal file
@@ -0,0 +1,156 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestLoadSessionWithOptionsRendersCompactPlaceholder(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
sessionYAML := `session_id: "{{session_id}}"
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
cfg, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
|
||||
if err != nil {
|
||||
t.Fatalf("LoadSessionWithOptions() error = %v", err)
|
||||
}
|
||||
if cfg.SessionID != "2026-04-04" {
|
||||
t.Fatalf("SessionID = %q, want 2026-04-04", cfg.SessionID)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSessionWithOptionsRendersSpacedPlaceholder(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
sessionYAML := `session_id: "{{ session_id }}"
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
cfg, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
|
||||
if err != nil {
|
||||
t.Fatalf("LoadSessionWithOptions() error = %v", err)
|
||||
}
|
||||
if cfg.SessionID != "2026-04-04" {
|
||||
t.Fatalf("SessionID = %q, want 2026-04-04", cfg.SessionID)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSessionWithOptionsUnresolvedPlaceholderFails(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
sessionYAML := `session_id: "{{ session_id }}"
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
_, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{})
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "unresolved template variable") {
|
||||
t.Fatalf("error = %q, want unresolved-variable context", err.Error())
|
||||
}
|
||||
if !strings.Contains(err.Error(), "session_id") {
|
||||
t.Fatalf("error = %q, want session_id variable", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSessionWithOptionsMismatchFails(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
_, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "session_id mismatch") {
|
||||
t.Fatalf("error = %q, want mismatch context", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSessionWithOptionsUnknownFieldStillRejectedAfterRendering(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
sessionYAML := `session_id: "{{ session_id }}"
|
||||
campaign: sample-campaign
|
||||
unknown_field: true
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
_, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{SessionID: "2026-04-04"})
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "strict decode failed") {
|
||||
t.Fatalf("error = %q, want strict-decode context", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoadSessionWithOptionsConcreteSessionStillLoads(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
sessionPath := filepath.Join(dir, "session.yml")
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: sample-campaign
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
||||
t.Fatalf("write session.yml: %v", err)
|
||||
}
|
||||
|
||||
cfg, err := LoadSessionWithOptions(sessionPath, SessionLoadOptions{})
|
||||
if err != nil {
|
||||
t.Fatalf("LoadSessionWithOptions() error = %v", err)
|
||||
}
|
||||
if cfg.SessionID != "2026-05-03" {
|
||||
t.Fatalf("SessionID = %q, want 2026-05-03", cfg.SessionID)
|
||||
}
|
||||
}
|
||||
315
internal/config/storage_archive_test.go
Normal file
315
internal/config/storage_archive_test.go
Normal file
@@ -0,0 +1,315 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestStorageS3DefaultsAndValidation(t *testing.T) {
|
||||
pipelineYAML := testPipelineBaseYAML + `
|
||||
storage:
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: my-dnd-archive
|
||||
`
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, testSessionBaseYAML)
|
||||
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3 == nil {
|
||||
t.Fatal("storage.s3 should be initialized")
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3.RootPrefix != "dnd" {
|
||||
t.Fatalf("storage.s3.root_prefix = %q, want dnd", cfg.Pipeline.Storage.S3.RootPrefix)
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3.AccessKeyIDEnv != DefaultS3AccessKeyIDEnv {
|
||||
t.Fatalf("storage.s3.access_key_id_env = %q, want %q", cfg.Pipeline.Storage.S3.AccessKeyIDEnv, DefaultS3AccessKeyIDEnv)
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3.SecretKeyEnv != DefaultS3SecretAccessKeyEnv {
|
||||
t.Fatalf("storage.s3.secret_access_key_env = %q, want %q", cfg.Pipeline.Storage.S3.SecretKeyEnv, DefaultS3SecretAccessKeyEnv)
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3.ForcePathStyle {
|
||||
t.Fatalf("storage.s3.force_path_style = true, want false default")
|
||||
}
|
||||
|
||||
if err := Validate(cfg); err != nil {
|
||||
t.Fatalf("Validate() error = %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStorageS3CredentialEnvNamesLoadAndValidate(t *testing.T) {
|
||||
pipelineYAML := testPipelineBaseYAML + `
|
||||
storage:
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: my-dnd-archive
|
||||
access_key_id_env: CUSTOM_KEY_ID
|
||||
secret_access_key_env: CUSTOM_SECRET
|
||||
`
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, testSessionBaseYAML)
|
||||
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3.AccessKeyIDEnv != "CUSTOM_KEY_ID" {
|
||||
t.Fatalf("storage.s3.access_key_id_env = %q, want CUSTOM_KEY_ID", cfg.Pipeline.Storage.S3.AccessKeyIDEnv)
|
||||
}
|
||||
if cfg.Pipeline.Storage.S3.SecretKeyEnv != "CUSTOM_SECRET" {
|
||||
t.Fatalf("storage.s3.secret_access_key_env = %q, want CUSTOM_SECRET", cfg.Pipeline.Storage.S3.SecretKeyEnv)
|
||||
}
|
||||
if err := Validate(cfg); err != nil {
|
||||
t.Fatalf("Validate() error = %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStorageS3CredentialEnvValidation(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
pipelineYML string
|
||||
wantErr string
|
||||
}{
|
||||
{
|
||||
name: "invalid access key env name",
|
||||
pipelineYML: testPipelineBaseYAML + `
|
||||
storage:
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: my-dnd-archive
|
||||
access_key_id_env: "123BAD"
|
||||
`,
|
||||
wantErr: "pipeline.storage.s3.access_key_id_env must be a valid environment variable name",
|
||||
},
|
||||
{
|
||||
name: "invalid secret key env name",
|
||||
pipelineYML: testPipelineBaseYAML + `
|
||||
storage:
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: my-dnd-archive
|
||||
secret_access_key_env: "bad-name"
|
||||
`,
|
||||
wantErr: "pipeline.storage.s3.secret_access_key_env must be a valid environment variable name",
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, tt.pipelineYML, testSessionBaseYAML)
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
err = Validate(cfg)
|
||||
if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
|
||||
t.Fatalf("Validate() error = %v, want to contain %q", err, tt.wantErr)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestSpoolAndArchiveDefaults(t *testing.T) {
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, testPipelineBaseYAML, testSessionBaseYAML)
|
||||
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
|
||||
if cfg.Pipeline.Spool.Root != "/var/spool/narratio" {
|
||||
t.Fatalf("spool.root = %q, want /var/spool/narratio", cfg.Pipeline.Spool.Root)
|
||||
}
|
||||
if cfg.Pipeline.Spool.DeleteAudioAfterArchive {
|
||||
t.Fatalf("spool.delete_audio_after_archive = true, want false")
|
||||
}
|
||||
if cfg.Pipeline.Workspace.CleanupAfterArchive {
|
||||
t.Fatalf("workspace.cleanup_after_archive = true, want false")
|
||||
}
|
||||
if cfg.Pipeline.Archive == nil {
|
||||
t.Fatal("archive should be initialized by defaults")
|
||||
}
|
||||
if cfg.Pipeline.Archive.Enabled == nil || !*cfg.Pipeline.Archive.Enabled {
|
||||
t.Fatalf("archive.enabled = %#v, want true", cfg.Pipeline.Archive.Enabled)
|
||||
}
|
||||
if cfg.Pipeline.Archive.UploadRun == nil || !*cfg.Pipeline.Archive.UploadRun {
|
||||
t.Fatalf("archive.upload_run = %#v, want true", cfg.Pipeline.Archive.UploadRun)
|
||||
}
|
||||
if len(cfg.Pipeline.Archive.PromoteArtifacts) != 2 {
|
||||
t.Fatalf("archive.promote_artifacts len = %d, want 2 defaults", len(cfg.Pipeline.Archive.PromoteArtifacts))
|
||||
}
|
||||
for i, item := range cfg.Pipeline.Archive.PromoteArtifacts {
|
||||
if item.Required == nil || !*item.Required {
|
||||
t.Fatalf("archive.promote_artifacts[%d].required = %#v, want true", i, item.Required)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchivePromotionPathValidation(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
ruleYML string
|
||||
wantErr string
|
||||
}{
|
||||
{
|
||||
name: "absolute from path rejected",
|
||||
ruleYML: `archive:
|
||||
promote_artifacts:
|
||||
- from: "/transcripts/trimmed.json"
|
||||
to: "transcripts/trimmed.json"
|
||||
`,
|
||||
wantErr: "must be a relative path",
|
||||
},
|
||||
{
|
||||
name: "traversal to path rejected",
|
||||
ruleYML: `archive:
|
||||
promote_artifacts:
|
||||
- from: "transcripts/trimmed.json"
|
||||
to: "../trimmed.json"
|
||||
`,
|
||||
wantErr: "must not contain path traversal",
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
pipelineYAML := testPipelineBaseYAML + "\n" + tt.ruleYML
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, testSessionBaseYAML)
|
||||
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
err = Validate(cfg)
|
||||
if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
|
||||
t.Fatalf("Validate() error = %v, want to contain %q", err, tt.wantErr)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestSessionAudioS3Validation(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
sessionYAML string
|
||||
wantErr string
|
||||
}{
|
||||
{
|
||||
name: "valid audio_s3 prefix",
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
campaign: forsaken
|
||||
inputs:
|
||||
audio_s3:
|
||||
prefix: audio/
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
},
|
||||
{
|
||||
name: "invalid audio_s3 absolute prefix",
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
campaign: forsaken
|
||||
inputs:
|
||||
audio_s3:
|
||||
prefix: /audio/
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantErr: "session.inputs.audio_s3.prefix must be a relative path",
|
||||
},
|
||||
{
|
||||
name: "invalid audio_s3 traversal prefix",
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
campaign: forsaken
|
||||
inputs:
|
||||
audio_s3:
|
||||
prefix: ../audio/
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantErr: "session.inputs.audio_s3.prefix must not contain path traversal",
|
||||
},
|
||||
{
|
||||
name: "local and s3 audio conflict",
|
||||
sessionYAML: `session_id: 2026-05-03
|
||||
campaign: forsaken
|
||||
inputs:
|
||||
audio_dir: ./audio
|
||||
audio_s3:
|
||||
prefix: audio/
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`,
|
||||
wantErr: "mutually exclusive",
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
pipelineYAML := testPipelineBaseYAML + `
|
||||
storage:
|
||||
backend: s3
|
||||
s3:
|
||||
bucket: my-dnd-archive
|
||||
`
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, tt.sessionYAML)
|
||||
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
err = Validate(cfg)
|
||||
if tt.wantErr != "" {
|
||||
if err == nil || !strings.Contains(err.Error(), tt.wantErr) {
|
||||
t.Fatalf("Validate() error = %v, want to contain %q", err, tt.wantErr)
|
||||
}
|
||||
return
|
||||
}
|
||||
if err != nil {
|
||||
t.Fatalf("Validate() error = %v", err)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestStorageS3BucketRequiredWhenS3DependentFeatureEnabled(t *testing.T) {
|
||||
pipelineYAML := testPipelineBaseYAML + `
|
||||
storage:
|
||||
backend: s3
|
||||
`
|
||||
sessionYAML := `session_id: 2026-05-03
|
||||
campaign: forsaken
|
||||
inputs:
|
||||
audio_s3:
|
||||
prefix: audio/
|
||||
speakers_file: ./speakers.yml
|
||||
autocorrect_file: ./autocorrect.yml
|
||||
glossary_file: ./glossary.yml
|
||||
`
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, pipelineYAML, sessionYAML)
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
|
||||
err = Validate(cfg)
|
||||
if err == nil || !strings.Contains(err.Error(), "pipeline.storage.s3.bucket is required") {
|
||||
t.Fatalf("Validate() error = %v, want bucket requirement", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLocalAudioConfigStillValid(t *testing.T) {
|
||||
pipelinePath, sessionPath := writeConfigFiles(t, testPipelineBaseYAML, testSessionBaseYAML)
|
||||
cfg, err := Load(pipelinePath, sessionPath)
|
||||
if err != nil {
|
||||
t.Fatalf("Load() error = %v", err)
|
||||
}
|
||||
if err := Validate(cfg); err != nil {
|
||||
t.Fatalf("Validate() error = %v", err)
|
||||
}
|
||||
}
|
||||
@@ -3,6 +3,8 @@ package config
|
||||
import (
|
||||
"fmt"
|
||||
"net/url"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
@@ -25,6 +27,9 @@ func Validate(cfg *Config) error {
|
||||
if err := validateSession(cfg.Session); err != nil {
|
||||
return fmt.Errorf("session config %q invalid: %w", shortName(cfg.SessionPath, "session.yml"), err)
|
||||
}
|
||||
if err := validateCrossConfig(cfg.Pipeline, cfg.Session); err != nil {
|
||||
return fmt.Errorf("pipeline/session config invalid: %w", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
@@ -33,6 +38,18 @@ func validatePipeline(cfg *PipelineConfig) error {
|
||||
if strings.TrimSpace(cfg.Workspace.Root) == "" {
|
||||
return fmt.Errorf("pipeline.workspace.root is required")
|
||||
}
|
||||
if err := validateSecrets(cfg.Secrets); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := validateStorage(cfg.Storage); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := validateSpool(cfg.Spool); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := validateArchive(cfg.Archive); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := validateWhisperX(cfg.WhisperX); err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -61,6 +78,64 @@ func validatePipeline(cfg *PipelineConfig) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateStorage(cfg StorageConfig) error {
|
||||
if cfg.S3 == nil {
|
||||
return nil
|
||||
}
|
||||
if strings.TrimSpace(cfg.S3.RootPrefix) == "" {
|
||||
return fmt.Errorf("pipeline.storage.s3.root_prefix must be non-empty")
|
||||
}
|
||||
if err := validateRelativeSafePath("pipeline.storage.s3.root_prefix", cfg.S3.RootPrefix); err != nil {
|
||||
return err
|
||||
}
|
||||
if cfg.S3.Endpoint != "" && strings.TrimSpace(cfg.S3.Endpoint) == "" {
|
||||
return fmt.Errorf("pipeline.storage.s3.endpoint must be non-empty when provided")
|
||||
}
|
||||
if err := validateEnvVarNameField("pipeline.storage.s3.access_key_id_env", cfg.S3.AccessKeyIDEnv); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := validateEnvVarNameField("pipeline.storage.s3.secret_access_key_env", cfg.S3.SecretKeyEnv); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateSpool(cfg SpoolConfig) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateArchive(cfg *ArchiveConfig) error {
|
||||
if cfg == nil {
|
||||
return nil
|
||||
}
|
||||
for i, item := range cfg.PromoteArtifacts {
|
||||
prefix := fmt.Sprintf("pipeline.archive.promote_artifacts[%d]", i)
|
||||
if strings.TrimSpace(item.From) == "" {
|
||||
return fmt.Errorf("%s.from is required", prefix)
|
||||
}
|
||||
if strings.TrimSpace(item.To) == "" {
|
||||
return fmt.Errorf("%s.to is required", prefix)
|
||||
}
|
||||
if err := validateRelativeSafePath(prefix+".from", item.From); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := validateRelativeSafePath(prefix+".to", item.To); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateSecrets(cfg *SecretsConfig) error {
|
||||
if cfg == nil {
|
||||
return nil
|
||||
}
|
||||
if strings.TrimSpace(cfg.EnvDir) == "" {
|
||||
return fmt.Errorf("pipeline.secrets.env_dir must be non-empty when pipeline.secrets is configured")
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateNormalize(cfg *NormalizeConfig) error {
|
||||
if cfg == nil {
|
||||
return nil
|
||||
@@ -187,15 +262,12 @@ func validateAudita(cfg AuditaConfig) error {
|
||||
if err := validateDuration("pipeline.audita.timeout", cfg.Timeout); err != nil {
|
||||
return err
|
||||
}
|
||||
if len(cfg.Modules) == 0 {
|
||||
return fmt.Errorf("pipeline.audita.modules must include at least one module")
|
||||
}
|
||||
for i, mod := range cfg.Modules {
|
||||
m := strings.TrimSpace(mod)
|
||||
if m == "" {
|
||||
for i, m := range cfg.Modules {
|
||||
module := strings.TrimSpace(m)
|
||||
if module == "" {
|
||||
return fmt.Errorf("pipeline.audita.modules[%d] must be non-empty", i)
|
||||
}
|
||||
switch m {
|
||||
switch module {
|
||||
case "glossary", "homophones", "spoken_word", "grammar":
|
||||
default:
|
||||
return fmt.Errorf("pipeline.audita.modules[%d] must be one of: glossary, homophones, spoken_word, grammar", i)
|
||||
@@ -210,21 +282,31 @@ func validateAudita(cfg AuditaConfig) error {
|
||||
return fmt.Errorf("pipeline.audita.base_url must be a valid URL")
|
||||
}
|
||||
}
|
||||
if strings.TrimSpace(cfg.Model) == "" {
|
||||
return fmt.Errorf("pipeline.audita.model is required")
|
||||
if cfg.TotalLLMConcurrency != nil && *cfg.TotalLLMConcurrency <= 0 {
|
||||
return fmt.Errorf("pipeline.audita.total_llm_concurrency must be > 0")
|
||||
}
|
||||
if cfg.LLMConcurrency == nil {
|
||||
return fmt.Errorf("pipeline.audita.llm_concurrency must be set (defaults should populate this)")
|
||||
if cfg.ProposalLLMConcurrency != nil && *cfg.ProposalLLMConcurrency <= 0 {
|
||||
return fmt.Errorf("pipeline.audita.proposal_llm_concurrency must be > 0")
|
||||
}
|
||||
if *cfg.LLMConcurrency <= 0 {
|
||||
return fmt.Errorf("pipeline.audita.llm_concurrency must be > 0")
|
||||
}
|
||||
if cfg.ValidationLLMConcurrency == nil {
|
||||
return fmt.Errorf("pipeline.audita.validation_llm_concurrency must be set (defaults should populate this)")
|
||||
}
|
||||
if *cfg.ValidationLLMConcurrency <= 0 {
|
||||
if cfg.ValidationLLMConcurrency != nil && *cfg.ValidationLLMConcurrency <= 0 {
|
||||
return fmt.Errorf("pipeline.audita.validation_llm_concurrency must be > 0")
|
||||
}
|
||||
if strings.TrimSpace(cfg.TranscriptDescription) == "" && cfg.TranscriptDescription != "" {
|
||||
return fmt.Errorf("pipeline.audita.transcript_description must be non-empty when provided")
|
||||
}
|
||||
if strings.TrimSpace(cfg.ConfigPath) == "" && cfg.ConfigPath != "" {
|
||||
return fmt.Errorf("pipeline.audita.config_path must be non-empty when provided")
|
||||
}
|
||||
switch strings.TrimSpace(cfg.OutputSchema) {
|
||||
case "", "bare-segments", "audita-v1":
|
||||
default:
|
||||
return fmt.Errorf("pipeline.audita.output_schema must be one of: bare-segments, audita-v1")
|
||||
}
|
||||
switch strings.TrimSpace(cfg.WorkDirRetention) {
|
||||
case "", "always", "auto", "never":
|
||||
default:
|
||||
return fmt.Errorf("pipeline.audita.work_dir_retention must be one of: always, auto, never")
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -284,6 +366,9 @@ func validateSession(cfg *SessionConfig) error {
|
||||
if strings.TrimSpace(cfg.SessionID) == "" {
|
||||
return fmt.Errorf("session.session_id is required")
|
||||
}
|
||||
if strings.TrimSpace(cfg.Campaign) == "" {
|
||||
return fmt.Errorf("session.campaign is required")
|
||||
}
|
||||
|
||||
if strings.TrimSpace(cfg.Inputs.SpeakersFile) == "" {
|
||||
return fmt.Errorf("session.inputs.speakers_file is required")
|
||||
@@ -297,13 +382,91 @@ func validateSession(cfg *SessionConfig) error {
|
||||
|
||||
hasAudioDir := strings.TrimSpace(cfg.Inputs.AudioDir) != ""
|
||||
hasAudioFiles := len(cfg.Inputs.AudioFiles) > 0
|
||||
if !hasAudioDir && !hasAudioFiles {
|
||||
return fmt.Errorf("session.inputs requires audio_dir or at least one audio_files entry")
|
||||
hasAudioS3 := cfg.Inputs.AudioS3 != nil
|
||||
if hasAudioS3 {
|
||||
if strings.TrimSpace(cfg.Inputs.AudioS3.Prefix) == "" {
|
||||
return fmt.Errorf("session.inputs.audio_s3.prefix is required when session.inputs.audio_s3 is configured")
|
||||
}
|
||||
if err := validateRelativeSafePath("session.inputs.audio_s3.prefix", cfg.Inputs.AudioS3.Prefix); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
if hasAudioS3 && (hasAudioDir || hasAudioFiles) {
|
||||
return fmt.Errorf("session.inputs.audio_dir/audio_files and session.inputs.audio_s3 are mutually exclusive")
|
||||
}
|
||||
if !hasAudioDir && !hasAudioFiles && !hasAudioS3 {
|
||||
return fmt.Errorf("session.inputs requires audio_dir, at least one audio_files entry, or audio_s3")
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateCrossConfig(pipeline *PipelineConfig, session *SessionConfig) error {
|
||||
if pipeline == nil || session == nil {
|
||||
return nil
|
||||
}
|
||||
if pipeline.Storage.S3 == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
audioS3Enabled := session.Inputs.AudioS3 != nil
|
||||
archiveUploadEnabled := archiveUploadConfiguredForS3(pipeline)
|
||||
if (audioS3Enabled || archiveUploadEnabled) && strings.TrimSpace(pipeline.Storage.S3.Bucket) == "" {
|
||||
return fmt.Errorf("pipeline.storage.s3.bucket is required when S3 session audio or archive upload is enabled")
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func archiveUploadConfiguredForS3(pipeline *PipelineConfig) bool {
|
||||
if pipeline == nil || pipeline.Archive == nil {
|
||||
return false
|
||||
}
|
||||
if !strings.EqualFold(strings.TrimSpace(pipeline.Storage.Backend), "s3") {
|
||||
return false
|
||||
}
|
||||
enabled := true
|
||||
if pipeline.Archive.Enabled != nil {
|
||||
enabled = *pipeline.Archive.Enabled
|
||||
}
|
||||
upload := true
|
||||
if pipeline.Archive.UploadRun != nil {
|
||||
upload = *pipeline.Archive.UploadRun
|
||||
}
|
||||
return enabled && upload
|
||||
}
|
||||
|
||||
var windowsAbsPathRE = regexp.MustCompile(`^[A-Za-z]:[\\/].*`)
|
||||
var envVarNameRE = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
|
||||
|
||||
func validateEnvVarNameField(fieldName, value string) error {
|
||||
trimmed := strings.TrimSpace(value)
|
||||
if trimmed == "" {
|
||||
return fmt.Errorf("%s must be non-empty", fieldName)
|
||||
}
|
||||
if !envVarNameRE.MatchString(trimmed) {
|
||||
return fmt.Errorf("%s must be a valid environment variable name", fieldName)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateRelativeSafePath(fieldName, value string) error {
|
||||
trimmed := strings.TrimSpace(value)
|
||||
if trimmed == "" {
|
||||
return fmt.Errorf("%s must be non-empty", fieldName)
|
||||
}
|
||||
if filepath.IsAbs(trimmed) || strings.HasPrefix(trimmed, "/") || strings.HasPrefix(trimmed, "\\") || windowsAbsPathRE.MatchString(trimmed) {
|
||||
return fmt.Errorf("%s must be a relative path", fieldName)
|
||||
}
|
||||
|
||||
normalized := strings.ReplaceAll(trimmed, "\\", "/")
|
||||
for _, segment := range strings.Split(normalized, "/") {
|
||||
if segment == ".." {
|
||||
return fmt.Errorf("%s must not contain path traversal", fieldName)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func validateDuration(fieldName, value string) error {
|
||||
trimmed := strings.TrimSpace(value)
|
||||
if trimmed == "" {
|
||||
|
||||
@@ -14,9 +14,15 @@ type ErrorRecord struct {
|
||||
|
||||
// InputRecord captures one resolved input and optional checksum.
|
||||
type InputRecord struct {
|
||||
Kind string `json:"kind"`
|
||||
Path string `json:"path"`
|
||||
Checksum string `json:"checksum,omitempty"`
|
||||
Kind string `json:"kind"`
|
||||
Path string `json:"path"`
|
||||
Checksum string `json:"checksum,omitempty"`
|
||||
Source string `json:"source,omitempty"`
|
||||
S3Bucket string `json:"s3_bucket,omitempty"`
|
||||
S3Key string `json:"s3_key,omitempty"`
|
||||
S3Size int64 `json:"s3_size,omitempty"`
|
||||
S3ETag string `json:"s3_etag,omitempty"`
|
||||
SpoolPath string `json:"spool_path,omitempty"`
|
||||
}
|
||||
|
||||
// ArtifactRecord captures one produced artifact and optional remote metadata.
|
||||
@@ -45,6 +51,13 @@ type StageRecord struct {
|
||||
// Manifest is the durable run-state record for a session execution.
|
||||
type Manifest struct {
|
||||
SessionID string `json:"session_id"`
|
||||
Campaign string `json:"campaign,omitempty"`
|
||||
RunID string `json:"run_id,omitempty"`
|
||||
LocalWorkDir string `json:"local_workdir,omitempty"`
|
||||
LocalSpoolDir string `json:"local_spool_dir,omitempty"`
|
||||
S3Bucket string `json:"s3_bucket,omitempty"`
|
||||
S3SessionPrefix string `json:"s3_session_prefix,omitempty"`
|
||||
S3RunPrefix string `json:"s3_run_prefix,omitempty"`
|
||||
PipelineVersion string `json:"pipeline_version,omitempty"`
|
||||
CreatedAt time.Time `json:"created_at"`
|
||||
UpdatedAt time.Time `json:"updated_at"`
|
||||
|
||||
@@ -22,6 +22,13 @@ func TestLocalStoreCreateSaveLoadRoundTrip(t *testing.T) {
|
||||
now := time.Date(2026, 5, 3, 12, 0, 0, 0, time.UTC)
|
||||
m.MarkStageRunning("prepare", now)
|
||||
m.MarkStageSucceeded("prepare", now.Add(2*time.Second), []ArtifactRecord{{Kind: "transcript", LocalPath: "transcripts/merged.json"}})
|
||||
m.Campaign = "forsaken"
|
||||
m.RunID = "20260515T031522Z-a1b2c3d4"
|
||||
m.LocalWorkDir = "/var/lib/narratio/work/forsaken/2026-05-03/20260515T031522Z-a1b2c3d4"
|
||||
m.LocalSpoolDir = "/var/spool/narratio/forsaken/2026-05-03/20260515T031522Z-a1b2c3d4/audio"
|
||||
m.S3Bucket = "my-dnd-archive"
|
||||
m.S3SessionPrefix = "dnd/campaigns/forsaken/sessions/2026-05-03/"
|
||||
m.S3RunPrefix = "dnd/campaigns/forsaken/sessions/2026-05-03/runs/20260515T031522Z-a1b2c3d4/"
|
||||
|
||||
path := filepath.Join(t.TempDir(), "manifest.json")
|
||||
if err := store.Save(ctx, path, m); err != nil {
|
||||
@@ -36,6 +43,12 @@ func TestLocalStoreCreateSaveLoadRoundTrip(t *testing.T) {
|
||||
if loaded.SessionID != "2026-05-03" {
|
||||
t.Fatalf("SessionID = %q, want %q", loaded.SessionID, "2026-05-03")
|
||||
}
|
||||
if loaded.Campaign != "forsaken" {
|
||||
t.Fatalf("Campaign = %q, want %q", loaded.Campaign, "forsaken")
|
||||
}
|
||||
if loaded.RunID != "20260515T031522Z-a1b2c3d4" {
|
||||
t.Fatalf("RunID = %q, want run id", loaded.RunID)
|
||||
}
|
||||
stage, ok := loaded.Stages["prepare"]
|
||||
if !ok {
|
||||
t.Fatalf("stage prepare not found")
|
||||
|
||||
525
internal/stage/archive.go
Normal file
525
internal/stage/archive.go
Normal file
@@ -0,0 +1,525 @@
|
||||
package stage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
"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"
|
||||
)
|
||||
|
||||
type archiveStage struct{}
|
||||
|
||||
var archivePrerequisiteStages = []string{
|
||||
"prepare",
|
||||
"transcribe",
|
||||
"merge",
|
||||
"polish",
|
||||
"normalize",
|
||||
"trim",
|
||||
"analyze",
|
||||
}
|
||||
|
||||
var archiveRunUploadDirs = []string{
|
||||
"inputs",
|
||||
"transcripts",
|
||||
"artifacts",
|
||||
"reports",
|
||||
"config",
|
||||
"logs",
|
||||
}
|
||||
|
||||
func (archiveStage) Name() string { return "archive" }
|
||||
|
||||
func (archiveStage) Declares() IODecl {
|
||||
return IODecl{
|
||||
Inputs: []artifacts.Ref{
|
||||
{Kind: "manifest", Category: "input", RelativePath: "manifest.json"},
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
func (archiveStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*StageResult, error) {
|
||||
if env == nil || env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil {
|
||||
return nil, fmt.Errorf("archive: resolved config must include pipeline and session")
|
||||
}
|
||||
|
||||
if archiveDisabled(env) {
|
||||
return &StageResult{
|
||||
Metadata: map[string]any{
|
||||
"stage": "archive",
|
||||
"skipped": true,
|
||||
"archive_enabled": false,
|
||||
"audio_upload_skipped": true,
|
||||
"current_pointer_written": false,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
if archiveRunUploadDisabled(env) {
|
||||
return &StageResult{
|
||||
Metadata: map[string]any{
|
||||
"stage": "archive",
|
||||
"skipped": true,
|
||||
"upload_run_enabled": false,
|
||||
"audio_upload_skipped": true,
|
||||
"current_pointer_written": false,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
|
||||
if err := validateArchivePrerequisites(m); err != nil {
|
||||
return nil, fmt.Errorf("archive: %w", err)
|
||||
}
|
||||
if env.ObjectStore == nil {
|
||||
return nil, fmt.Errorf("archive: remote object store backend is required when archive run upload is enabled")
|
||||
}
|
||||
|
||||
workDir, err := archiveWorkDir(env, m)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: resolve local workdir: %w", err)
|
||||
}
|
||||
workDirInfo, err := os.Stat(workDir)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: local workdir %q: %w", workDir, err)
|
||||
}
|
||||
if !workDirInfo.IsDir() {
|
||||
return nil, fmt.Errorf("archive: local workdir %q is not a directory", workDir)
|
||||
}
|
||||
|
||||
runPrefix, err := archiveRunPrefix(env, m)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: resolve s3 run prefix: %w", err)
|
||||
}
|
||||
sessionPrefix, err := archiveSessionPrefix(env, m)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: resolve s3 session prefix: %w", err)
|
||||
}
|
||||
bucket := archiveBucket(env, m)
|
||||
if bucket == "" {
|
||||
return nil, fmt.Errorf("archive: resolve s3 bucket: bucket is required")
|
||||
}
|
||||
runID := strings.TrimSpace(m.RunID)
|
||||
if runID == "" {
|
||||
return nil, fmt.Errorf("archive: run id is required")
|
||||
}
|
||||
|
||||
runFiles, err := collectArchiveRunFiles(workDir)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: collect run files: %w", err)
|
||||
}
|
||||
promotions, err := resolveArchivePromotions(workDir, env.Config.Pipeline.Archive.PromoteArtifacts)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: resolve promotion rules: %w", err)
|
||||
}
|
||||
currentManifestSource := filepath.Join(workDir, "manifest.json")
|
||||
if info, err := os.Stat(currentManifestSource); err != nil {
|
||||
return nil, fmt.Errorf("archive: current manifest source %q: %w", currentManifestSource, err)
|
||||
} else if info.IsDir() {
|
||||
return nil, fmt.Errorf("archive: current manifest source %q is a directory", currentManifestSource)
|
||||
}
|
||||
|
||||
runUploaded := make([]string, 0, len(runFiles))
|
||||
for _, rel := range runFiles {
|
||||
localPath := filepath.Join(workDir, filepath.FromSlash(rel))
|
||||
key := artifacts.S3RunRelativeDestinationKey(runPrefix, rel)
|
||||
if _, err := env.ObjectStore.Upload(ctx, localPath, key, storage.UploadOptions{}); err != nil {
|
||||
return nil, fmt.Errorf("archive: upload run file %q to %q: %w", rel, key, err)
|
||||
}
|
||||
runUploaded = append(runUploaded, rel)
|
||||
}
|
||||
|
||||
promotedUploaded := make([]string, 0, len(promotions))
|
||||
skippedOptional := make([]string, 0)
|
||||
for _, promotion := range promotions {
|
||||
if !promotion.Exists {
|
||||
if promotion.Required {
|
||||
return nil, fmt.Errorf("archive: required promotion source missing: %q", promotion.From)
|
||||
}
|
||||
skippedOptional = append(skippedOptional, promotion.To)
|
||||
continue
|
||||
}
|
||||
key := artifacts.S3PromotedArtifactKey(sessionPrefix, promotion.To)
|
||||
if _, err := env.ObjectStore.Upload(ctx, promotion.LocalPath, key, storage.UploadOptions{}); err != nil {
|
||||
return nil, fmt.Errorf("archive: upload promoted output %q to %q: %w", promotion.From, key, err)
|
||||
}
|
||||
promotedUploaded = append(promotedUploaded, promotion.To)
|
||||
}
|
||||
|
||||
currentManifestKey := artifacts.S3CurrentManifestKey(sessionPrefix)
|
||||
manifestTempPath, err := writeCurrentManifestSnapshot(m, archiveMetadataPreview(
|
||||
bucket,
|
||||
runPrefix,
|
||||
sessionPrefix,
|
||||
runUploaded,
|
||||
promotedUploaded,
|
||||
skippedOptional,
|
||||
currentManifestKey,
|
||||
))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: build current manifest snapshot: %w", err)
|
||||
}
|
||||
defer func() { _ = os.Remove(manifestTempPath) }()
|
||||
|
||||
if _, err := env.ObjectStore.Upload(ctx, manifestTempPath, currentManifestKey, storage.UploadOptions{
|
||||
ContentType: "application/json",
|
||||
}); err != nil {
|
||||
return nil, fmt.Errorf("archive: upload current manifest to %q: %w", currentManifestKey, err)
|
||||
}
|
||||
|
||||
currentRunPointerKey := artifacts.S3CurrentRunPointerKey(sessionPrefix)
|
||||
runIDTempPath, err := writeCurrentRunIDPointer(runID)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("archive: build current run id pointer: %w", err)
|
||||
}
|
||||
defer func() { _ = os.Remove(runIDTempPath) }()
|
||||
|
||||
if _, err := env.ObjectStore.Upload(ctx, runIDTempPath, currentRunPointerKey, storage.UploadOptions{
|
||||
ContentType: "text/plain; charset=utf-8",
|
||||
}); err != nil {
|
||||
return nil, fmt.Errorf("archive: upload current run pointer to %q: %w", currentRunPointerKey, err)
|
||||
}
|
||||
|
||||
return &StageResult{
|
||||
Metadata: map[string]any{
|
||||
"stage": "archive",
|
||||
"uploaded": true,
|
||||
"s3_bucket": bucket,
|
||||
"s3_run_prefix": runPrefix,
|
||||
"run_files_uploaded": len(runUploaded),
|
||||
"run_uploaded_paths": runUploaded,
|
||||
"promoted_files_uploaded": len(promotedUploaded),
|
||||
"promoted_paths": promotedUploaded,
|
||||
"skipped_optional_promotions": skippedOptional,
|
||||
"current_manifest_key": currentManifestKey,
|
||||
"current_run_id_key": currentRunPointerKey,
|
||||
"current_pointer_written": true,
|
||||
"audio_upload_skipped": true,
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
|
||||
type archivePromotion struct {
|
||||
From string
|
||||
To string
|
||||
Required bool
|
||||
LocalPath string
|
||||
Exists bool
|
||||
}
|
||||
|
||||
func archiveDisabled(env *Env) bool {
|
||||
cfg := env.Config.Pipeline.Archive
|
||||
if cfg == nil {
|
||||
return true
|
||||
}
|
||||
return cfg.Enabled != nil && !*cfg.Enabled
|
||||
}
|
||||
|
||||
func archiveRunUploadDisabled(env *Env) bool {
|
||||
cfg := env.Config.Pipeline.Archive
|
||||
if cfg == nil {
|
||||
return true
|
||||
}
|
||||
return cfg.UploadRun != nil && !*cfg.UploadRun
|
||||
}
|
||||
|
||||
func validateArchivePrerequisites(m *manifest.Manifest) error {
|
||||
if m == nil {
|
||||
return fmt.Errorf("manifest is required")
|
||||
}
|
||||
for _, stageName := range archivePrerequisiteStages {
|
||||
sr := m.Stages[stageName]
|
||||
if sr == nil {
|
||||
return fmt.Errorf("prerequisite stage %q has not succeeded", stageName)
|
||||
}
|
||||
if sr.Status != manifest.StatusSucceeded {
|
||||
return fmt.Errorf("prerequisite stage %q status is %q (want %q)", stageName, sr.Status, manifest.StatusSucceeded)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func archiveWorkDir(env *Env, m *manifest.Manifest) (string, error) {
|
||||
workDir := strings.TrimSpace(m.LocalWorkDir)
|
||||
if workDir != "" {
|
||||
cleaned := filepath.Clean(workDir)
|
||||
if info, err := os.Stat(cleaned); err == nil && info.IsDir() {
|
||||
return cleaned, nil
|
||||
}
|
||||
}
|
||||
|
||||
sessionID := strings.TrimSpace(env.Config.Session.SessionID)
|
||||
if sessionID == "" {
|
||||
sessionID = strings.TrimSpace(m.SessionID)
|
||||
}
|
||||
campaign := strings.TrimSpace(env.Config.Session.Campaign)
|
||||
if campaign == "" {
|
||||
campaign = strings.TrimSpace(m.Campaign)
|
||||
}
|
||||
runID := strings.TrimSpace(m.RunID)
|
||||
if runID == "" {
|
||||
return "", fmt.Errorf("run id is required")
|
||||
}
|
||||
if campaign == "" || sessionID == "" {
|
||||
return "", fmt.Errorf("campaign and session id are required")
|
||||
}
|
||||
runScoped := artifacts.SessionRunWorkDir(env.Config.Pipeline.Workspace.Root, campaign, sessionID, runID)
|
||||
if info, err := os.Stat(runScoped); err == nil && info.IsDir() {
|
||||
return runScoped, nil
|
||||
}
|
||||
legacy := artifacts.SessionWorkDir(env.Config.Pipeline.Workspace.Root, sessionID)
|
||||
return legacy, nil
|
||||
}
|
||||
|
||||
func archiveRunPrefix(env *Env, m *manifest.Manifest) (string, error) {
|
||||
runPrefix := strings.TrimSpace(m.S3RunPrefix)
|
||||
if runPrefix != "" {
|
||||
return runPrefix, nil
|
||||
}
|
||||
|
||||
sessionPrefix, err := archiveSessionPrefix(env, m)
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
runID := strings.TrimSpace(m.RunID)
|
||||
if runID == "" {
|
||||
return "", fmt.Errorf("run id is required")
|
||||
}
|
||||
return artifacts.S3RunPrefix(sessionPrefix, runID), nil
|
||||
}
|
||||
|
||||
func archiveSessionPrefix(env *Env, m *manifest.Manifest) (string, error) {
|
||||
if m != nil && strings.TrimSpace(m.S3SessionPrefix) != "" {
|
||||
return strings.TrimSpace(m.S3SessionPrefix), nil
|
||||
}
|
||||
|
||||
sessionID := strings.TrimSpace(env.Config.Session.SessionID)
|
||||
if sessionID == "" {
|
||||
sessionID = strings.TrimSpace(m.SessionID)
|
||||
}
|
||||
campaign := strings.TrimSpace(env.Config.Session.Campaign)
|
||||
if campaign == "" {
|
||||
campaign = strings.TrimSpace(m.Campaign)
|
||||
}
|
||||
if env.Config.Pipeline.Storage.S3 == nil {
|
||||
return "", fmt.Errorf("pipeline.storage.s3 configuration is required")
|
||||
}
|
||||
sessionPrefix := artifacts.S3SessionPrefix(env.Config.Pipeline.Storage.S3.RootPrefix, campaign, sessionID)
|
||||
if strings.TrimSpace(sessionPrefix) == "" {
|
||||
return "", fmt.Errorf("session prefix is required")
|
||||
}
|
||||
return sessionPrefix, nil
|
||||
}
|
||||
|
||||
func archiveBucket(env *Env, m *manifest.Manifest) string {
|
||||
if m != nil && strings.TrimSpace(m.S3Bucket) != "" {
|
||||
return strings.TrimSpace(m.S3Bucket)
|
||||
}
|
||||
if env == nil || env.Config == nil || env.Config.Pipeline == nil || env.Config.Pipeline.Storage.S3 == nil {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSpace(env.Config.Pipeline.Storage.S3.Bucket)
|
||||
}
|
||||
|
||||
func resolveArchivePromotions(workDir string, rules []config.ArchivePromotionRule) ([]archivePromotion, error) {
|
||||
out := make([]archivePromotion, 0, len(rules))
|
||||
for _, rule := range rules {
|
||||
from := strings.TrimSpace(rule.From)
|
||||
to := strings.TrimSpace(rule.To)
|
||||
required := rule.Required == nil || *rule.Required
|
||||
|
||||
localPath, err := resolveWorkDirRelativePath(workDir, from)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("promotion from %q: %w", from, err)
|
||||
}
|
||||
info, err := os.Stat(localPath)
|
||||
exists := err == nil && !info.IsDir()
|
||||
if err != nil && !os.IsNotExist(err) {
|
||||
return nil, fmt.Errorf("promotion source %q: %w", from, err)
|
||||
}
|
||||
|
||||
out = append(out, archivePromotion{
|
||||
From: from,
|
||||
To: to,
|
||||
Required: required,
|
||||
LocalPath: localPath,
|
||||
Exists: exists,
|
||||
})
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
func resolveWorkDirRelativePath(workDir, rel string) (string, error) {
|
||||
rel = filepath.Clean(filepath.FromSlash(strings.TrimSpace(rel)))
|
||||
if rel == "." || rel == "" {
|
||||
return "", fmt.Errorf("relative path is required")
|
||||
}
|
||||
full := filepath.Join(workDir, rel)
|
||||
cleanedWork := filepath.Clean(workDir)
|
||||
cleanedFull := filepath.Clean(full)
|
||||
relative, err := filepath.Rel(cleanedWork, cleanedFull)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("compute relative path: %w", err)
|
||||
}
|
||||
if relative == ".." || strings.HasPrefix(relative, ".."+string(filepath.Separator)) {
|
||||
return "", fmt.Errorf("path escapes workdir")
|
||||
}
|
||||
return cleanedFull, nil
|
||||
}
|
||||
|
||||
func collectArchiveRunFiles(workDir string) ([]string, error) {
|
||||
files := make([]string, 0, 64)
|
||||
|
||||
for _, dirName := range archiveRunUploadDirs {
|
||||
fullDir := filepath.Join(workDir, dirName)
|
||||
info, err := os.Stat(fullDir)
|
||||
if err != nil {
|
||||
if os.IsNotExist(err) {
|
||||
continue
|
||||
}
|
||||
return nil, fmt.Errorf("stat %q: %w", fullDir, err)
|
||||
}
|
||||
if !info.IsDir() {
|
||||
continue
|
||||
}
|
||||
|
||||
if err := filepath.WalkDir(fullDir, func(path string, d fs.DirEntry, walkErr error) error {
|
||||
if walkErr != nil {
|
||||
return walkErr
|
||||
}
|
||||
if d.IsDir() {
|
||||
return nil
|
||||
}
|
||||
rel, err := filepath.Rel(workDir, path)
|
||||
if err != nil {
|
||||
return fmt.Errorf("relative path from %q to %q: %w", workDir, path, err)
|
||||
}
|
||||
rel = filepath.ToSlash(rel)
|
||||
files = append(files, rel)
|
||||
return nil
|
||||
}); err != nil {
|
||||
return nil, fmt.Errorf("walk %q: %w", fullDir, err)
|
||||
}
|
||||
}
|
||||
|
||||
manifestPath := filepath.Join(workDir, "manifest.json")
|
||||
manifestInfo, err := os.Stat(manifestPath)
|
||||
if err != nil {
|
||||
if os.IsNotExist(err) {
|
||||
return nil, fmt.Errorf("manifest.json not found in workdir %q", workDir)
|
||||
}
|
||||
return nil, fmt.Errorf("stat %q: %w", manifestPath, err)
|
||||
}
|
||||
if manifestInfo.IsDir() {
|
||||
return nil, fmt.Errorf("manifest path %q is a directory", manifestPath)
|
||||
}
|
||||
files = append(files, "manifest.json")
|
||||
|
||||
sort.Strings(files)
|
||||
return files, nil
|
||||
}
|
||||
|
||||
func writeCurrentManifestSnapshot(m *manifest.Manifest, archiveMetadata map[string]any) (string, error) {
|
||||
if m == nil {
|
||||
return "", fmt.Errorf("manifest is required")
|
||||
}
|
||||
clone := *m
|
||||
clone.Stages = make(map[string]*manifest.StageRecord, len(m.Stages))
|
||||
for name, sr := range m.Stages {
|
||||
if sr == nil {
|
||||
continue
|
||||
}
|
||||
stageCopy := *sr
|
||||
if sr.Outputs != nil {
|
||||
stageCopy.Outputs = append([]manifest.ArtifactRecord(nil), sr.Outputs...)
|
||||
}
|
||||
if sr.Logs != nil {
|
||||
stageCopy.Logs = append([]string(nil), sr.Logs...)
|
||||
}
|
||||
if sr.GeneratedConfigs != nil {
|
||||
stageCopy.GeneratedConfigs = append([]string(nil), sr.GeneratedConfigs...)
|
||||
}
|
||||
if sr.Metadata != nil {
|
||||
metaCopy := make(map[string]any, len(sr.Metadata))
|
||||
for k, v := range sr.Metadata {
|
||||
metaCopy[k] = v
|
||||
}
|
||||
stageCopy.Metadata = metaCopy
|
||||
}
|
||||
clone.Stages[name] = &stageCopy
|
||||
}
|
||||
|
||||
now := time.Now().UTC()
|
||||
clone.MarkStageSucceeded("archive", now, nil)
|
||||
if sr := clone.Stages["archive"]; sr != nil {
|
||||
sr.Metadata = archiveMetadata
|
||||
}
|
||||
|
||||
data, err := json.MarshalIndent(&clone, "", " ")
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("marshal manifest: %w", err)
|
||||
}
|
||||
data = append(data, '\n')
|
||||
|
||||
tmp, err := os.CreateTemp("", "narratio-current-manifest-*.json")
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("create temp file: %w", err)
|
||||
}
|
||||
path := tmp.Name()
|
||||
if _, err := tmp.Write(data); err != nil {
|
||||
_ = tmp.Close()
|
||||
return "", fmt.Errorf("write temp manifest: %w", err)
|
||||
}
|
||||
if err := tmp.Close(); err != nil {
|
||||
return "", fmt.Errorf("close temp manifest: %w", err)
|
||||
}
|
||||
return path, nil
|
||||
}
|
||||
|
||||
func writeCurrentRunIDPointer(runID string) (string, error) {
|
||||
tmp, err := os.CreateTemp("", "narratio-current-run-id-*.txt")
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("create temp file: %w", err)
|
||||
}
|
||||
path := tmp.Name()
|
||||
if _, err := tmp.WriteString(runID + "\n"); err != nil {
|
||||
_ = tmp.Close()
|
||||
return "", fmt.Errorf("write temp run id pointer: %w", err)
|
||||
}
|
||||
if err := tmp.Close(); err != nil {
|
||||
return "", fmt.Errorf("close temp run id pointer: %w", err)
|
||||
}
|
||||
return path, nil
|
||||
}
|
||||
|
||||
func archiveMetadataPreview(
|
||||
bucket, runPrefix, sessionPrefix string,
|
||||
runUploaded []string,
|
||||
promotedUploaded []string,
|
||||
skippedOptional []string,
|
||||
currentManifestKey string,
|
||||
) map[string]any {
|
||||
return map[string]any{
|
||||
"stage": "archive",
|
||||
"uploaded": true,
|
||||
"s3_bucket": bucket,
|
||||
"s3_run_prefix": runPrefix,
|
||||
"run_files_uploaded": len(runUploaded),
|
||||
"run_uploaded_paths": append([]string(nil), runUploaded...),
|
||||
"promoted_files_uploaded": len(promotedUploaded),
|
||||
"promoted_paths": append([]string(nil), promotedUploaded...),
|
||||
"skipped_optional_promotions": append([]string(nil), skippedOptional...),
|
||||
"current_manifest_key": currentManifestKey,
|
||||
"current_run_id_key": artifacts.S3CurrentRunPointerKey(sessionPrefix),
|
||||
"current_pointer_written": false,
|
||||
"audio_upload_skipped": true,
|
||||
}
|
||||
}
|
||||
322
internal/stage/archive_test.go
Normal file
322
internal/stage/archive_test.go
Normal file
@@ -0,0 +1,322 @@
|
||||
package stage
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"path/filepath"
|
||||
"reflect"
|
||||
"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 TestArchiveSkipsWhenDisabled(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
env.Config.Pipeline.Archive.Enabled = boolPtr(false)
|
||||
|
||||
result, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
if result.Metadata["skipped"] != true {
|
||||
t.Fatalf("metadata = %#v, want skipped=true", result.Metadata)
|
||||
}
|
||||
if len(env.ObjectStore.(*storage.FakeBackend).Uploads) != 0 {
|
||||
t.Fatalf("unexpected uploads when archive disabled")
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveSkipsRunUploadWhenDisabled(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
env.Config.Pipeline.Archive.UploadRun = boolPtr(false)
|
||||
|
||||
result, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
if result.Metadata["skipped"] != true {
|
||||
t.Fatalf("metadata = %#v, want skipped=true", result.Metadata)
|
||||
}
|
||||
if len(env.ObjectStore.(*storage.FakeBackend).Uploads) != 0 {
|
||||
t.Fatalf("unexpected uploads when upload_run disabled")
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveFailsWhenPrerequisiteNotSucceeded(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
m.Stages["trim"].Status = manifest.StatusFailed
|
||||
|
||||
_, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), `prerequisite stage "trim"`) {
|
||||
t.Fatalf("Run() error = %v, want prerequisite failure", err)
|
||||
}
|
||||
if len(env.ObjectStore.(*storage.FakeBackend).Uploads) != 0 {
|
||||
t.Fatalf("unexpected uploads on prerequisite failure")
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveUploadsRunRecordPromotionsAndCurrentPointer(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
fake := env.ObjectStore.(*storage.FakeBackend)
|
||||
|
||||
result, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
|
||||
runPrefix := m.S3RunPrefix
|
||||
sessionPrefix := m.S3SessionPrefix
|
||||
wantRunUploads := []string{
|
||||
"artifacts/session_recap.md",
|
||||
"config/audita.generated.yml",
|
||||
"inputs/session.yml",
|
||||
"logs/audita.stderr.log",
|
||||
"manifest.json",
|
||||
"reports/audita.report.json",
|
||||
"transcripts/raw/speaker.json",
|
||||
"transcripts/trimmed.json",
|
||||
}
|
||||
for _, rel := range wantRunUploads {
|
||||
key := runPrefix + rel
|
||||
if _, ok := fake.Objects[key]; !ok {
|
||||
t.Fatalf("missing run upload key %q", key)
|
||||
}
|
||||
}
|
||||
|
||||
trimmedKey := sessionPrefix + "transcripts/trimmed.json"
|
||||
recapKey := sessionPrefix + "artifacts/session_recap.md"
|
||||
if _, ok := fake.Objects[trimmedKey]; !ok {
|
||||
t.Fatalf("missing promoted key %q", trimmedKey)
|
||||
}
|
||||
if _, ok := fake.Objects[recapKey]; !ok {
|
||||
t.Fatalf("missing promoted key %q", recapKey)
|
||||
}
|
||||
|
||||
currentManifestKey := sessionPrefix + "current/manifest.json"
|
||||
currentRunIDKey := sessionPrefix + "current/run_id.txt"
|
||||
if _, ok := fake.Objects[currentManifestKey]; !ok {
|
||||
t.Fatalf("missing current manifest key %q", currentManifestKey)
|
||||
}
|
||||
if _, ok := fake.Objects[currentRunIDKey]; !ok {
|
||||
t.Fatalf("missing current run pointer key %q", currentRunIDKey)
|
||||
}
|
||||
if got := string(fake.Objects[currentRunIDKey].Data); got != m.RunID+"\n" {
|
||||
t.Fatalf("run pointer contents = %q, want %q", got, m.RunID+"\\n")
|
||||
}
|
||||
|
||||
audioKey := runPrefix + "audio/speaker.flac"
|
||||
if _, ok := fake.Objects[audioKey]; ok {
|
||||
t.Fatalf("audio key %q should not be uploaded", audioKey)
|
||||
}
|
||||
|
||||
uploads := fake.Uploads
|
||||
if len(uploads) == 0 {
|
||||
t.Fatal("expected uploads")
|
||||
}
|
||||
if uploads[len(uploads)-1].Key != currentRunIDKey {
|
||||
t.Fatalf("last upload key = %q, want current run pointer key %q", uploads[len(uploads)-1].Key, currentRunIDKey)
|
||||
}
|
||||
|
||||
if result.Metadata["current_pointer_written"] != true {
|
||||
t.Fatalf("metadata = %#v, want current_pointer_written=true", result.Metadata)
|
||||
}
|
||||
if result.Metadata["promoted_files_uploaded"] != 2 {
|
||||
t.Fatalf("metadata promoted_files_uploaded = %#v, want 2", result.Metadata["promoted_files_uploaded"])
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveUsesCustomPromotionRules(t *testing.T) {
|
||||
env, m, workDir := archiveFixture(t)
|
||||
env.Config.Pipeline.Archive.PromoteArtifacts = []config.ArchivePromotionRule{
|
||||
{From: "transcripts/trimmed.json", To: "published/trimmed.json", Required: boolPtr(true)},
|
||||
{From: "artifacts/session_recap.md", To: "published/recap.md", Required: boolPtr(true)},
|
||||
}
|
||||
writeStageTestFile(t, filepath.Join(workDir, "published", "ignored.txt"), "ignore\n")
|
||||
|
||||
_, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
|
||||
fake := env.ObjectStore.(*storage.FakeBackend)
|
||||
if _, ok := fake.Objects[m.S3SessionPrefix+"published/trimmed.json"]; !ok {
|
||||
t.Fatalf("missing custom promoted trimmed key")
|
||||
}
|
||||
if _, ok := fake.Objects[m.S3SessionPrefix+"published/recap.md"]; !ok {
|
||||
t.Fatalf("missing custom promoted recap key")
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveSkipsOptionalMissingPromotion(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
env.Config.Pipeline.Archive.PromoteArtifacts = []config.ArchivePromotionRule{
|
||||
{From: "transcripts/trimmed.json", To: "transcripts/trimmed.json", Required: boolPtr(true)},
|
||||
{From: "artifacts/optional.md", To: "artifacts/optional.md", Required: boolPtr(false)},
|
||||
}
|
||||
|
||||
result, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
t.Fatalf("Run() error = %v", err)
|
||||
}
|
||||
got, _ := result.Metadata["skipped_optional_promotions"].([]string)
|
||||
want := []string{"artifacts/optional.md"}
|
||||
if !reflect.DeepEqual(got, want) {
|
||||
t.Fatalf("skipped_optional_promotions = %#v, want %#v", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveFailsWhenRequiredPromotionMissing(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
env.Config.Pipeline.Archive.PromoteArtifacts = []config.ArchivePromotionRule{
|
||||
{From: "artifacts/missing.md", To: "artifacts/missing.md", Required: boolPtr(true)},
|
||||
}
|
||||
|
||||
_, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), "required promotion source missing") {
|
||||
t.Fatalf("Run() error = %v, want required promotion missing failure", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveDoesNotWriteCurrentPointerWhenPromotionUploadFails(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
fake := env.ObjectStore.(*storage.FakeBackend)
|
||||
trimmedKey := m.S3SessionPrefix + "transcripts/trimmed.json"
|
||||
|
||||
origUploadErr := fake.UploadErr
|
||||
fake.UploadErr = nil
|
||||
failingKey := trimmedKey
|
||||
fake.Uploads = nil
|
||||
|
||||
originalUpload := fake.Upload
|
||||
_ = originalUpload
|
||||
// Use UploadErr toggle by checking call sequence in postcondition.
|
||||
// First failure point is promotion upload; simulate by setting error immediately before promotion key write.
|
||||
// We cannot hook FakeBackend per-key without changing public behavior; use dedicated backend wrapper instead.
|
||||
env.ObjectStore = &promotionFailingStore{delegate: fake, failKey: failingKey}
|
||||
|
||||
_, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), "promoted output") {
|
||||
t.Fatalf("Run() error = %v, want promotion upload failure", err)
|
||||
}
|
||||
if _, ok := fake.Objects[m.S3SessionPrefix+"current/run_id.txt"]; ok {
|
||||
t.Fatalf("unexpected current pointer write on promotion failure")
|
||||
}
|
||||
fake.UploadErr = origUploadErr
|
||||
}
|
||||
|
||||
func TestArchiveDoesNotWriteCurrentPointerWhenCurrentManifestUploadFails(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
fake := env.ObjectStore.(*storage.FakeBackend)
|
||||
env.ObjectStore = &promotionFailingStore{delegate: fake, failKey: m.S3SessionPrefix + "current/manifest.json"}
|
||||
|
||||
_, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), "current manifest") {
|
||||
t.Fatalf("Run() error = %v, want current manifest upload failure", err)
|
||||
}
|
||||
if _, ok := fake.Objects[m.S3SessionPrefix+"current/run_id.txt"]; ok {
|
||||
t.Fatalf("unexpected current pointer write when current manifest upload fails")
|
||||
}
|
||||
}
|
||||
|
||||
func TestArchiveFailsWithoutObjectStore(t *testing.T) {
|
||||
env, m, _ := archiveFixture(t)
|
||||
env.ObjectStore = nil
|
||||
|
||||
_, err := archiveStage{}.Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), "object store") {
|
||||
t.Fatalf("Run() error = %v, want object store backend failure", err)
|
||||
}
|
||||
}
|
||||
|
||||
func archiveFixture(t *testing.T) (*Env, *manifest.Manifest, string) {
|
||||
t.Helper()
|
||||
|
||||
root := t.TempDir()
|
||||
runID := "20260516T010203Z-1a2b3c4d"
|
||||
campaign := "forsaken"
|
||||
sessionID := "2026-04-19"
|
||||
workDir := filepath.Join(root, "work", campaign, sessionID, runID)
|
||||
|
||||
writeStageTestFile(t, filepath.Join(workDir, "inputs", "session.yml"), "session_id: 2026-04-19\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "transcripts", "raw", "speaker.json"), "{}\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "transcripts", "trimmed.json"), "{}\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "artifacts", "session_recap.md"), "# recap\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "reports", "audita.report.json"), "{}\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "config", "audita.generated.yml"), "key: value\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "logs", "audita.stderr.log"), "stderr\n")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "audio", "speaker.flac"), "flac")
|
||||
writeStageTestFile(t, filepath.Join(workDir, "manifest.json"), "{}\n")
|
||||
|
||||
m := manifest.New(sessionID, time.Date(2026, 5, 16, 1, 2, 3, 0, time.UTC))
|
||||
m.Campaign = campaign
|
||||
m.RunID = runID
|
||||
m.LocalWorkDir = workDir
|
||||
m.S3Bucket = "my-dnd-archive"
|
||||
m.S3SessionPrefix = artifacts.S3SessionPrefix("dnd", campaign, sessionID)
|
||||
m.S3RunPrefix = artifacts.S3RunPrefix(m.S3SessionPrefix, runID)
|
||||
for _, name := range archivePrerequisiteStages {
|
||||
m.MarkStageSucceeded(name, time.Date(2026, 5, 16, 1, 2, 3, 0, time.UTC), nil)
|
||||
}
|
||||
|
||||
env := &Env{
|
||||
Config: &config.Config{
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Workspace: config.WorkspaceConfig{Root: root},
|
||||
Storage: config.StorageConfig{
|
||||
S3: &config.StorageS3Config{
|
||||
Bucket: "my-dnd-archive",
|
||||
RootPrefix: "dnd",
|
||||
},
|
||||
},
|
||||
Archive: &config.ArchiveConfig{
|
||||
Enabled: boolPtr(true),
|
||||
UploadRun: boolPtr(true),
|
||||
PromoteArtifacts: []config.ArchivePromotionRule{
|
||||
{From: "transcripts/trimmed.json", To: "transcripts/trimmed.json", Required: boolPtr(true)},
|
||||
{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md", Required: boolPtr(true)},
|
||||
},
|
||||
},
|
||||
},
|
||||
Session: &config.SessionConfig{
|
||||
SessionID: sessionID,
|
||||
Campaign: campaign,
|
||||
},
|
||||
},
|
||||
ObjectStore: &storage.FakeBackend{},
|
||||
}
|
||||
return env, m, workDir
|
||||
}
|
||||
|
||||
type promotionFailingStore struct {
|
||||
delegate *storage.FakeBackend
|
||||
failKey string
|
||||
}
|
||||
|
||||
func (s *promotionFailingStore) List(ctx context.Context, prefix string) ([]storage.ObjectInfo, error) {
|
||||
return s.delegate.List(ctx, prefix)
|
||||
}
|
||||
|
||||
func (s *promotionFailingStore) Download(ctx context.Context, key, localPath string) error {
|
||||
return s.delegate.Download(ctx, key, localPath)
|
||||
}
|
||||
|
||||
func (s *promotionFailingStore) Upload(ctx context.Context, localPath, key string, opts storage.UploadOptions) (storage.ObjectInfo, error) {
|
||||
if strings.TrimSpace(key) == strings.TrimSpace(s.failKey) {
|
||||
return storage.ObjectInfo{}, errors.New("forced upload failure")
|
||||
}
|
||||
return s.delegate.Upload(ctx, localPath, key, opts)
|
||||
}
|
||||
|
||||
func (s *promotionFailingStore) Exists(ctx context.Context, key string) (bool, error) {
|
||||
return s.delegate.Exists(ctx, key)
|
||||
}
|
||||
|
||||
func boolPtr(v bool) *bool {
|
||||
p := v
|
||||
return &p
|
||||
}
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/adapters/seriatim"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
|
||||
@@ -86,10 +87,15 @@ func (mergeStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*Sta
|
||||
stderrPath := filepath.Join(paths.LogsDir, "seriatim.stderr.log")
|
||||
genCfgPath := filepath.Join(paths.ConfigDir, "seriatim.generated.yml")
|
||||
|
||||
normalizedInputs, normalizeLogs, normalizeConfigs, normalizeMeta, err := normalizeMergeInputs(ctx, env, inputs, paths)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
reportEnabled := env.Config.Pipeline.Seriatim.Report != nil && *env.Config.Pipeline.Seriatim.Report
|
||||
req := seriatim.MergeRequest{
|
||||
GeneratedConfigPath: genCfgPath,
|
||||
InputTranscriptPaths: inputs,
|
||||
InputTranscriptPaths: normalizedInputs,
|
||||
OutputMergedTranscriptPath: mergedPath,
|
||||
ReportPath: "",
|
||||
SpeakersPath: speakersPath,
|
||||
@@ -146,8 +152,11 @@ func (mergeStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*Sta
|
||||
|
||||
meta := map[string]any{
|
||||
"stage": "merge",
|
||||
"input_transcripts_count": len(inputs),
|
||||
"input_transcripts_count": len(normalizedInputs),
|
||||
"input_transcript_paths": inputs,
|
||||
"normalized_inputs_count": len(normalizedInputs),
|
||||
"normalized_input_paths": normalizedInputs,
|
||||
"normalize_inputs": normalizeMeta,
|
||||
"output_schema": env.Config.Pipeline.Seriatim.OutputSchema,
|
||||
"coalesce_gap": coalesceGap,
|
||||
"report_enabled": reportEnabled,
|
||||
@@ -172,12 +181,93 @@ func (mergeStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*Sta
|
||||
|
||||
return &StageResult{
|
||||
Outputs: outputs,
|
||||
Logs: []string{stdoutPath, stderrPath},
|
||||
GeneratedConfigs: []string{genCfgPath},
|
||||
Logs: append(normalizeLogs, stdoutPath, stderrPath),
|
||||
GeneratedConfigs: append(normalizeConfigs, genCfgPath),
|
||||
Metadata: meta,
|
||||
}, nil
|
||||
}
|
||||
|
||||
type normalizeMergeInputMeta struct {
|
||||
InputPath string `json:"input_path"`
|
||||
OutputPath string `json:"output_path"`
|
||||
StdoutLogPath string `json:"stdout_log_path"`
|
||||
StderrLogPath string `json:"stderr_log_path"`
|
||||
GeneratedConfig string `json:"generated_config_path"`
|
||||
DurationMs int64 `json:"duration_ms"`
|
||||
ExitCode int `json:"exit_code"`
|
||||
InvokedBinary string `json:"invoked_binary"`
|
||||
OutputSchema string `json:"output_schema"`
|
||||
AdapterReportPath string `json:"adapter_report_path,omitempty"`
|
||||
AdapterOutputPath string `json:"adapter_output_path,omitempty"`
|
||||
}
|
||||
|
||||
func normalizeMergeInputs(ctx context.Context, env *Env, rawInputs []string, paths artifacts.SessionPaths) ([]string, []string, []string, []normalizeMergeInputMeta, error) {
|
||||
normalizedInputs := make([]string, 0, len(rawInputs))
|
||||
logs := make([]string, 0, len(rawInputs)*2)
|
||||
configs := make([]string, 0, len(rawInputs))
|
||||
meta := make([]normalizeMergeInputMeta, 0, len(rawInputs))
|
||||
|
||||
var timeout time.Duration
|
||||
timeoutRaw := strings.TrimSpace(env.Config.Pipeline.Seriatim.Timeout)
|
||||
if timeoutRaw != "" {
|
||||
parsed, err := time.ParseDuration(timeoutRaw)
|
||||
if err != nil {
|
||||
return nil, nil, nil, nil, fmt.Errorf("merge: parse seriatim timeout %q: %w", env.Config.Pipeline.Seriatim.Timeout, err)
|
||||
}
|
||||
timeout = parsed
|
||||
}
|
||||
for _, input := range rawInputs {
|
||||
base := strings.TrimSuffix(filepath.Base(input), filepath.Ext(input))
|
||||
outPath := filepath.Join(paths.TranscriptsRawDir, "normalized", base+".normalized.json")
|
||||
stdoutPath := filepath.Join(paths.LogsDir, "seriatim.normalize."+base+".stdout.log")
|
||||
stderrPath := filepath.Join(paths.LogsDir, "seriatim.normalize."+base+".stderr.log")
|
||||
cfgPath := filepath.Join(paths.ConfigDir, "seriatim.normalize."+base+".generated.yml")
|
||||
|
||||
req := seriatim.NormalizeRequest{
|
||||
Binary: env.Config.Pipeline.Seriatim.Binary,
|
||||
InputTranscriptPath: input,
|
||||
OutputNormalizedPath: outPath,
|
||||
OutputSchema: env.Config.Pipeline.Seriatim.OutputSchema,
|
||||
ReportPath: "",
|
||||
StdoutLogPath: stdoutPath,
|
||||
StderrLogPath: stderrPath,
|
||||
GeneratedConfigPath: cfgPath,
|
||||
Timeout: timeout,
|
||||
}
|
||||
res, err := env.Seriatim.Normalize(ctx, req)
|
||||
if err != nil {
|
||||
return nil, nil, nil, nil, fmt.Errorf("merge: normalize input %q failed: %w", input, err)
|
||||
}
|
||||
|
||||
finalOutputPath := outPath
|
||||
if strings.TrimSpace(res.OutputNormalizedPath) != "" {
|
||||
finalOutputPath = strings.TrimSpace(res.OutputNormalizedPath)
|
||||
}
|
||||
if err := validateTranscriptJSONFile(finalOutputPath); err != nil {
|
||||
return nil, nil, nil, nil, fmt.Errorf("merge: normalized transcript %q invalid (input %q): %w", finalOutputPath, input, err)
|
||||
}
|
||||
|
||||
normalizedInputs = append(normalizedInputs, finalOutputPath)
|
||||
logs = append(logs, stdoutPath, stderrPath)
|
||||
configs = append(configs, cfgPath)
|
||||
meta = append(meta, normalizeMergeInputMeta{
|
||||
InputPath: input,
|
||||
OutputPath: finalOutputPath,
|
||||
StdoutLogPath: stdoutPath,
|
||||
StderrLogPath: stderrPath,
|
||||
GeneratedConfig: cfgPath,
|
||||
DurationMs: res.Duration.Milliseconds(),
|
||||
ExitCode: res.ExitCode,
|
||||
InvokedBinary: res.InvokedBinary,
|
||||
OutputSchema: res.OutputSchema,
|
||||
AdapterReportPath: res.ReportPath,
|
||||
AdapterOutputPath: res.OutputNormalizedPath,
|
||||
})
|
||||
}
|
||||
|
||||
return normalizedInputs, logs, configs, meta, nil
|
||||
}
|
||||
|
||||
func discoverRawTranscripts(m *manifest.Manifest, paths artifacts.SessionPaths) ([]string, error) {
|
||||
fromManifest := make([]string, 0)
|
||||
if m != nil && m.Stages != nil {
|
||||
|
||||
@@ -54,6 +54,17 @@ func TestMergeStageMergesRawTranscriptsAndRecordsMetadata(t *testing.T) {
|
||||
if len(req.InputTranscriptPaths) != 2 {
|
||||
t.Fatalf("input transcripts = %#v, want 2", req.InputTranscriptPaths)
|
||||
}
|
||||
if len(fake.NormalizeRequests) != 2 {
|
||||
t.Fatalf("normalize requests = %#v, want 2", fake.NormalizeRequests)
|
||||
}
|
||||
if fake.NormalizeRequests[0].InputTranscriptPath != inA || fake.NormalizeRequests[1].InputTranscriptPath != inB {
|
||||
t.Fatalf("normalize request inputs = %#v", fake.NormalizeRequests)
|
||||
}
|
||||
for _, mergeIn := range req.InputTranscriptPaths {
|
||||
if !strings.Contains(mergeIn, filepath.Join("transcripts", "raw", "normalized")) {
|
||||
t.Fatalf("merge input path = %q, want normalized input path", mergeIn)
|
||||
}
|
||||
}
|
||||
|
||||
if len(result.Outputs) != 2 {
|
||||
t.Fatalf("outputs len = %d, want 2", len(result.Outputs))
|
||||
@@ -64,11 +75,11 @@ func TestMergeStageMergesRawTranscriptsAndRecordsMetadata(t *testing.T) {
|
||||
if result.Outputs[1].Kind != "seriatim_report" {
|
||||
t.Fatalf("output[1] kind = %q, want seriatim_report", result.Outputs[1].Kind)
|
||||
}
|
||||
if len(result.Logs) != 2 {
|
||||
t.Fatalf("logs = %#v, want 2 paths", result.Logs)
|
||||
if len(result.Logs) != 6 {
|
||||
t.Fatalf("logs = %#v, want 6 paths (4 normalize + 2 merge)", result.Logs)
|
||||
}
|
||||
if len(result.GeneratedConfigs) != 1 {
|
||||
t.Fatalf("generated configs = %#v, want 1 path", result.GeneratedConfigs)
|
||||
if len(result.GeneratedConfigs) != 3 {
|
||||
t.Fatalf("generated configs = %#v, want 3 paths (2 normalize + 1 merge)", result.GeneratedConfigs)
|
||||
}
|
||||
|
||||
meta := result.Metadata
|
||||
@@ -84,6 +95,12 @@ func TestMergeStageMergesRawTranscriptsAndRecordsMetadata(t *testing.T) {
|
||||
if meta["input_transcripts_count"] != 2 {
|
||||
t.Fatalf("metadata input_transcripts_count = %#v, want 2", meta["input_transcripts_count"])
|
||||
}
|
||||
if meta["normalized_inputs_count"] != 2 {
|
||||
t.Fatalf("metadata normalized_inputs_count = %#v, want 2", meta["normalized_inputs_count"])
|
||||
}
|
||||
if _, ok := meta["normalize_inputs"]; !ok {
|
||||
t.Fatalf("metadata normalize_inputs missing: %#v", meta)
|
||||
}
|
||||
}
|
||||
|
||||
func TestMergeStageFailsWhenNoRawTranscripts(t *testing.T) {
|
||||
@@ -152,6 +169,9 @@ func TestMergeStageFallsBackToRawDirectoryWhenTranscribeOutputsMissing(t *testin
|
||||
if len(fake.Requests) != 1 || len(fake.Requests[0].InputTranscriptPaths) != 1 {
|
||||
t.Fatalf("fallback inputs = %#v", fake.Requests)
|
||||
}
|
||||
if len(fake.NormalizeRequests) != 1 {
|
||||
t.Fatalf("normalize requests = %#v, want 1", fake.NormalizeRequests)
|
||||
}
|
||||
}
|
||||
|
||||
func TestMergeStageResolvesWorkspaceQualifiedManifestOutputsWithoutDuplication(t *testing.T) {
|
||||
@@ -180,8 +200,51 @@ func TestMergeStageResolvesWorkspaceQualifiedManifestOutputsWithoutDuplication(t
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("input transcript paths = %#v, want len 1", got)
|
||||
}
|
||||
if got[0] != filepath.Clean(rawPath) {
|
||||
t.Fatalf("resolved transcript path = %q, want %q", got[0], filepath.Clean(rawPath))
|
||||
if !strings.Contains(got[0], filepath.Join("transcripts", "raw", "normalized")) {
|
||||
t.Fatalf("resolved transcript path = %q, want normalized path under transcripts/raw/normalized", got[0])
|
||||
}
|
||||
}
|
||||
|
||||
func TestMergeStageFailsWhenNormalizeAdapterFails(t *testing.T) {
|
||||
env, m := setupMergeEnv(t)
|
||||
paths := env.ArtifactStore.SessionPaths(m.SessionID)
|
||||
in := filepath.Join(paths.TranscriptsRawDir, "alice.json")
|
||||
writeFile(t, in, `{"segments":[]}`)
|
||||
writeFile(t, filepath.Join(paths.InputsDir, "speakers.yml"), "match: []\n")
|
||||
writeFile(t, filepath.Join(paths.InputsDir, "autocorrect.yml"), "rules: []\n")
|
||||
env.Seriatim = &seriatim.FakeRunner{NormalizeErr: context.DeadlineExceeded}
|
||||
|
||||
_, err := (mergeStage{}).Run(context.Background(), env, m)
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "normalize input") {
|
||||
t.Fatalf("error = %q", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
func TestMergeStageFailsWhenNormalizedOutputInvalid(t *testing.T) {
|
||||
env, m := setupMergeEnv(t)
|
||||
paths := env.ArtifactStore.SessionPaths(m.SessionID)
|
||||
in := filepath.Join(paths.TranscriptsRawDir, "alice.json")
|
||||
writeFile(t, in, `{"segments":[]}`)
|
||||
writeFile(t, filepath.Join(paths.InputsDir, "speakers.yml"), "match: []\n")
|
||||
writeFile(t, filepath.Join(paths.InputsDir, "autocorrect.yml"), "rules: []\n")
|
||||
|
||||
badNormalized := filepath.Join(paths.ArtifactsDir, "bad.normalized.json")
|
||||
writeFile(t, badNormalized, "not-json")
|
||||
env.Seriatim = &seriatim.FakeRunner{
|
||||
NormalizeResult: seriatim.NormalizeResult{
|
||||
OutputNormalizedPath: badNormalized,
|
||||
},
|
||||
}
|
||||
|
||||
_, err := (mergeStage{}).Run(context.Background(), env, m)
|
||||
if err == nil {
|
||||
t.Fatal("expected error, got nil")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "normalized transcript") {
|
||||
t.Fatalf("error = %q", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -211,8 +274,8 @@ func TestMergeStageResolvesSessionRelativeManifestOutputs(t *testing.T) {
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("input transcript paths = %#v, want len 1", got)
|
||||
}
|
||||
if got[0] != filepath.Clean(rawPath) {
|
||||
t.Fatalf("resolved transcript path = %q, want %q", got[0], filepath.Clean(rawPath))
|
||||
if !strings.Contains(got[0], filepath.Join("transcripts", "raw", "normalized")) {
|
||||
t.Fatalf("resolved transcript path = %q, want normalized path under transcripts/raw/normalized", got[0])
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -3,10 +3,8 @@ package stage
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"path/filepath"
|
||||
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/adapters/notify"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
|
||||
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
|
||||
)
|
||||
@@ -47,25 +45,7 @@ func (s placeholderStage) Run(ctx context.Context, env *Env, m *manifest.Manifes
|
||||
return result, nil
|
||||
}
|
||||
|
||||
paths := env.ArtifactStore.SessionPaths(sessionID)
|
||||
|
||||
switch s.name {
|
||||
case "archive":
|
||||
if env.Storage != nil {
|
||||
req := storage.ArchiveRequest{
|
||||
SessionID: sessionID,
|
||||
ManifestPath: paths.ManifestPath,
|
||||
Items: []storage.ArchiveItem{{
|
||||
Kind: "artifact",
|
||||
LocalPath: filepath.Join(paths.ArtifactsDir, "session-log.md"),
|
||||
RemoteKey: "sessions/" + sessionID + "/artifacts/session-log.md",
|
||||
}},
|
||||
}
|
||||
_, err := env.Storage.Archive(ctx, req)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("placeholder archive adapter call failed: %w", err)
|
||||
}
|
||||
}
|
||||
case "notify":
|
||||
if env.Notifier != nil {
|
||||
req := notify.SendRequest{
|
||||
@@ -95,7 +75,7 @@ func All() []Stage {
|
||||
normalizeStage{},
|
||||
trimStage{},
|
||||
analyzeStage{},
|
||||
placeholderStage{name: "archive"},
|
||||
archiveStage{},
|
||||
placeholderStage{name: "notify"},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -49,7 +49,19 @@ func TestStagesReturnExpectedMetadata(t *testing.T) {
|
||||
Config: &config.Config{
|
||||
SessionPath: sessionPath,
|
||||
PipelinePath: pipelinePath,
|
||||
Pipeline: &config.PipelineConfig{Workspace: config.WorkspaceConfig{Root: root}},
|
||||
Pipeline: &config.PipelineConfig{
|
||||
Workspace: config.WorkspaceConfig{Root: root},
|
||||
Storage: config.StorageConfig{
|
||||
S3: &config.StorageS3Config{
|
||||
Bucket: "my-dnd-archive",
|
||||
RootPrefix: "dnd",
|
||||
},
|
||||
},
|
||||
Archive: &config.ArchiveConfig{
|
||||
Enabled: boolPtr(true),
|
||||
UploadRun: boolPtr(true),
|
||||
},
|
||||
},
|
||||
Session: &config.SessionConfig{
|
||||
SessionID: "2026-05-03",
|
||||
Inputs: config.SessionInputsConfig{
|
||||
@@ -66,10 +78,24 @@ func TestStagesReturnExpectedMetadata(t *testing.T) {
|
||||
Audita: af,
|
||||
Scriptorium: sc,
|
||||
Storage: st,
|
||||
ObjectStore: st,
|
||||
Notifier: nf,
|
||||
}
|
||||
|
||||
m := manifest.New("2026-05-03", time.Now().UTC())
|
||||
for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze"} {
|
||||
m.MarkStageSucceeded(name, time.Now().UTC(), nil)
|
||||
}
|
||||
m.RunID = "20260516T000000Z-abcdef12"
|
||||
m.Campaign = "sample-campaign"
|
||||
m.LocalWorkDir = filepath.Join(root, "work", "sample-campaign", "2026-05-03", m.RunID)
|
||||
m.S3RunPrefix = "dnd/campaigns/sample-campaign/sessions/2026-05-03/runs/" + m.RunID + "/"
|
||||
m.S3Bucket = "my-dnd-archive"
|
||||
if err := os.MkdirAll(filepath.Join(m.LocalWorkDir, "inputs"), 0o755); err != nil {
|
||||
t.Fatalf("mkdir workdir inputs: %v", err)
|
||||
}
|
||||
writeStageTestFile(t, filepath.Join(m.LocalWorkDir, "inputs", "session.yml"), "session_id: 2026-05-03\n")
|
||||
writeStageTestFile(t, filepath.Join(m.LocalWorkDir, "manifest.json"), "{}\n")
|
||||
for _, s := range stages {
|
||||
result, err := s.Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
@@ -150,6 +176,15 @@ func TestStagesReturnExpectedMetadata(t *testing.T) {
|
||||
}
|
||||
continue
|
||||
}
|
||||
if s.Name() == "archive" {
|
||||
if result.Metadata["stage"] != "archive" {
|
||||
t.Fatalf("archive metadata = %#v, want stage=archive", result.Metadata)
|
||||
}
|
||||
if result.Metadata["uploaded"] != true {
|
||||
t.Fatalf("archive metadata = %#v, want uploaded=true", result.Metadata)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if result.Metadata["placeholder"] != true {
|
||||
t.Fatalf("stage %q missing placeholder metadata", s.Name())
|
||||
}
|
||||
@@ -167,8 +202,11 @@ func TestStagesReturnExpectedMetadata(t *testing.T) {
|
||||
if len(sc.RunRequests) != 0 {
|
||||
t.Fatalf("scriptorium run calls = %d, want 0 when scriptorium config is absent", len(sc.RunRequests))
|
||||
}
|
||||
if len(st.Requests) != 1 {
|
||||
t.Fatalf("storage calls = %d, want 1", len(st.Requests))
|
||||
if len(st.Requests) != 0 {
|
||||
t.Fatalf("storage archive calls = %d, want 0", len(st.Requests))
|
||||
}
|
||||
if _, ok := st.Objects["dnd/campaigns/sample-campaign/sessions/2026-05-03/runs/"+m.RunID+"/manifest.json"]; !ok {
|
||||
t.Fatalf("archive upload missing manifest key in fake object store")
|
||||
}
|
||||
if len(nf.Requests) != 1 {
|
||||
t.Fatalf("notify calls = %d, want 1", len(nf.Requests))
|
||||
@@ -181,7 +219,6 @@ func TestPlaceholderAdapterErrorPropagation(t *testing.T) {
|
||||
env *Env
|
||||
wantErr string
|
||||
}{
|
||||
{stageName: "archive", env: &Env{Storage: &storage.FakeBackend{Err: errors.New("sterr")}}, wantErr: "archive"},
|
||||
{stageName: "notify", env: &Env{Notifier: ¬ify.FakeSender{Err: errors.New("nerr")}}, wantErr: "notify"},
|
||||
}
|
||||
|
||||
|
||||
@@ -90,6 +90,12 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
|
||||
Modules: append([]string(nil), env.Config.Pipeline.Audita.Modules...),
|
||||
BaseURL: env.Config.Pipeline.Audita.BaseURL,
|
||||
Model: env.Config.Pipeline.Audita.Model,
|
||||
TranscriptDescription: env.Config.Pipeline.Audita.TranscriptDescription,
|
||||
ConfigPath: env.Config.Pipeline.Audita.ConfigPath,
|
||||
OutputSchema: env.Config.Pipeline.Audita.OutputSchema,
|
||||
WorkDirRetention: env.Config.Pipeline.Audita.WorkDirRetention,
|
||||
TotalLLMConcurrency: env.Config.Pipeline.Audita.TotalLLMConcurrency,
|
||||
ProposalLLMConcurrency: env.Config.Pipeline.Audita.ProposalLLMConcurrency,
|
||||
ValidationModel: env.Config.Pipeline.Audita.ValidationModel,
|
||||
ValidationLLMConcurrency: env.Config.Pipeline.Audita.ValidationLLMConcurrency,
|
||||
StdoutLogPath: stdoutPath,
|
||||
@@ -141,44 +147,52 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
|
||||
if env.Config.Pipeline.Audita.ValidationLLMConcurrency != nil {
|
||||
validationConcurrency = *env.Config.Pipeline.Audita.ValidationLLMConcurrency
|
||||
}
|
||||
var llmConcurrency any
|
||||
if env.Config.Pipeline.Audita.LLMConcurrency != nil {
|
||||
llmConcurrency = *env.Config.Pipeline.Audita.LLMConcurrency
|
||||
var totalLLMConcurrency any
|
||||
if env.Config.Pipeline.Audita.TotalLLMConcurrency != nil {
|
||||
totalLLMConcurrency = *env.Config.Pipeline.Audita.TotalLLMConcurrency
|
||||
}
|
||||
var proposalLLMConcurrency any
|
||||
if env.Config.Pipeline.Audita.ProposalLLMConcurrency != nil {
|
||||
proposalLLMConcurrency = *env.Config.Pipeline.Audita.ProposalLLMConcurrency
|
||||
}
|
||||
|
||||
meta := map[string]any{
|
||||
"stage": "polish",
|
||||
"merged_transcript_path": mergedPath,
|
||||
"merged_transcript_source": source,
|
||||
"glossary_path": glossaryPath,
|
||||
"output_path": finalProcessedPath,
|
||||
"report_path": finalReportPath,
|
||||
"audita_work_dir": workDir,
|
||||
"report_enabled": reportEnabled,
|
||||
"modules": append([]string(nil), req.Modules...),
|
||||
"base_url": req.BaseURL,
|
||||
"model": req.Model,
|
||||
"validation_model": req.ValidationModel,
|
||||
"llm_concurrency": llmConcurrency,
|
||||
"validation_llm_concurrency": validationConcurrency,
|
||||
"llm_api_key_env": env.Config.Pipeline.Audita.LLMAPIKeyEnv,
|
||||
"timeout": env.Config.Pipeline.Audita.Timeout,
|
||||
"binary": env.Config.Pipeline.Audita.Binary,
|
||||
"generated_config_path": generatedConfigPath,
|
||||
"stdout_log_path": stdoutPath,
|
||||
"stderr_log_path": stderrPath,
|
||||
"adapter_duration_ms": res.Duration.Milliseconds(),
|
||||
"adapter_exit_code": res.ExitCode,
|
||||
"adapter_invoked_binary": res.InvokedBinary,
|
||||
"adapter_processed_output_path": res.ProcessedTranscriptPath,
|
||||
"adapter_report_path": res.ReportPath,
|
||||
"adapter_generated_config_path": res.GeneratedConfigPath,
|
||||
"adapter_work_dir": res.WorkDir,
|
||||
"adapter_stdout_log_path": res.StdoutLogPath,
|
||||
"adapter_stderr_log_path": res.StderrLogPath,
|
||||
"credential_env_var": env.Config.Pipeline.Audita.LLMAPIKeyEnv,
|
||||
"credential_present": false,
|
||||
"primary_llm_concurrency_via_env": false,
|
||||
"stage": "polish",
|
||||
"merged_transcript_path": mergedPath,
|
||||
"merged_transcript_source": source,
|
||||
"glossary_path": glossaryPath,
|
||||
"output_path": finalProcessedPath,
|
||||
"report_path": finalReportPath,
|
||||
"audita_work_dir": workDir,
|
||||
"report_enabled": reportEnabled,
|
||||
"modules": append([]string(nil), req.Modules...),
|
||||
"base_url": req.BaseURL,
|
||||
"model": req.Model,
|
||||
"transcript_description": req.TranscriptDescription,
|
||||
"config_path": req.ConfigPath,
|
||||
"output_schema": req.OutputSchema,
|
||||
"work_dir_retention": req.WorkDirRetention,
|
||||
"validation_model": req.ValidationModel,
|
||||
"total_llm_concurrency": totalLLMConcurrency,
|
||||
"proposal_llm_concurrency": proposalLLMConcurrency,
|
||||
"validation_llm_concurrency": validationConcurrency,
|
||||
"llm_api_key_env": env.Config.Pipeline.Audita.LLMAPIKeyEnv,
|
||||
"timeout": env.Config.Pipeline.Audita.Timeout,
|
||||
"binary": env.Config.Pipeline.Audita.Binary,
|
||||
"generated_config_path": generatedConfigPath,
|
||||
"stdout_log_path": stdoutPath,
|
||||
"stderr_log_path": stderrPath,
|
||||
"adapter_duration_ms": res.Duration.Milliseconds(),
|
||||
"adapter_exit_code": res.ExitCode,
|
||||
"adapter_invoked_binary": res.InvokedBinary,
|
||||
"adapter_processed_output_path": res.ProcessedTranscriptPath,
|
||||
"adapter_report_path": res.ReportPath,
|
||||
"adapter_generated_config_path": res.GeneratedConfigPath,
|
||||
"adapter_work_dir": res.WorkDir,
|
||||
"adapter_stdout_log_path": res.StdoutLogPath,
|
||||
"adapter_stderr_log_path": res.StderrLogPath,
|
||||
"credential_env_var": env.Config.Pipeline.Audita.LLMAPIKeyEnv,
|
||||
"credential_present": false,
|
||||
}
|
||||
if res.Metadata != nil {
|
||||
meta["adapter_metadata"] = res.Metadata
|
||||
@@ -188,9 +202,6 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
|
||||
if value, ok := res.Metadata["credential_env_var"]; ok {
|
||||
meta["credential_env_var"] = value
|
||||
}
|
||||
if value, ok := res.Metadata["primary_llm_concurrency_via_env"]; ok {
|
||||
meta["primary_llm_concurrency_via_env"] = value
|
||||
}
|
||||
}
|
||||
|
||||
return &StageResult{
|
||||
|
||||
@@ -60,6 +60,24 @@ func TestPolishStagePolishesMergedTranscriptAndRecordsMetadata(t *testing.T) {
|
||||
if req.ValidationModel != "openrouter/google/gemma-4-31b-it" {
|
||||
t.Fatalf("validation model = %q", req.ValidationModel)
|
||||
}
|
||||
if req.TranscriptDescription != "Campaign Session 42" {
|
||||
t.Fatalf("transcript description = %q", req.TranscriptDescription)
|
||||
}
|
||||
if req.ConfigPath != "/etc/audita/config.yml" {
|
||||
t.Fatalf("config path = %q", req.ConfigPath)
|
||||
}
|
||||
if req.OutputSchema != "audita-v1" {
|
||||
t.Fatalf("output schema = %q", req.OutputSchema)
|
||||
}
|
||||
if req.WorkDirRetention != "auto" {
|
||||
t.Fatalf("work dir retention = %q", req.WorkDirRetention)
|
||||
}
|
||||
if req.TotalLLMConcurrency == nil || *req.TotalLLMConcurrency != 3 {
|
||||
t.Fatalf("total llm concurrency = %#v, want 3", req.TotalLLMConcurrency)
|
||||
}
|
||||
if req.ProposalLLMConcurrency == nil || *req.ProposalLLMConcurrency != 2 {
|
||||
t.Fatalf("proposal llm concurrency = %#v, want 2", req.ProposalLLMConcurrency)
|
||||
}
|
||||
if req.ValidationLLMConcurrency == nil || *req.ValidationLLMConcurrency != 2 {
|
||||
t.Fatalf("validation llm concurrency = %#v, want 2", req.ValidationLLMConcurrency)
|
||||
}
|
||||
@@ -89,6 +107,15 @@ func TestPolishStagePolishesMergedTranscriptAndRecordsMetadata(t *testing.T) {
|
||||
if result.Metadata["audita_work_dir"] != filepath.Join(paths.ArtifactsDir, "audita-work") {
|
||||
t.Fatalf("metadata audita_work_dir = %#v", result.Metadata["audita_work_dir"])
|
||||
}
|
||||
if result.Metadata["total_llm_concurrency"] != 3 {
|
||||
t.Fatalf("metadata total_llm_concurrency = %#v, want 3", result.Metadata["total_llm_concurrency"])
|
||||
}
|
||||
if result.Metadata["proposal_llm_concurrency"] != 2 {
|
||||
t.Fatalf("metadata proposal_llm_concurrency = %#v, want 2", result.Metadata["proposal_llm_concurrency"])
|
||||
}
|
||||
if result.Metadata["output_schema"] != "audita-v1" {
|
||||
t.Fatalf("metadata output_schema = %#v, want audita-v1", result.Metadata["output_schema"])
|
||||
}
|
||||
}
|
||||
|
||||
func TestPolishStageFallsBackToMergedTranscriptPath(t *testing.T) {
|
||||
@@ -221,7 +248,8 @@ func setupPolishEnv(t *testing.T) (*Env, *manifest.Manifest) {
|
||||
writeFile(t, pipelinePath, "workspace:\n root: "+workspace+"\n")
|
||||
|
||||
report := true
|
||||
llmConcurrency := 1
|
||||
totalLLMConcurrency := 3
|
||||
proposalLLMConcurrency := 2
|
||||
validationLLMConcurrency := 2
|
||||
|
||||
cfg := &config.Config{
|
||||
@@ -236,8 +264,13 @@ func setupPolishEnv(t *testing.T) (*Env, *manifest.Manifest) {
|
||||
Modules: []string{"glossary", "homophones", "grammar"},
|
||||
BaseURL: "https://openrouter.ai/api/v1",
|
||||
Model: "openrouter/google/gemma-4-31b-it",
|
||||
TranscriptDescription: "Campaign Session 42",
|
||||
ConfigPath: "/etc/audita/config.yml",
|
||||
OutputSchema: "audita-v1",
|
||||
WorkDirRetention: "auto",
|
||||
ValidationModel: "openrouter/google/gemma-4-31b-it",
|
||||
LLMConcurrency: &llmConcurrency,
|
||||
TotalLLMConcurrency: &totalLLMConcurrency,
|
||||
ProposalLLMConcurrency: &proposalLLMConcurrency,
|
||||
ValidationLLMConcurrency: &validationLLMConcurrency,
|
||||
Report: &report,
|
||||
},
|
||||
|
||||
@@ -6,10 +6,12 @@ import (
|
||||
"encoding/hex"
|
||||
"fmt"
|
||||
"os"
|
||||
"path"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"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"
|
||||
@@ -33,7 +35,7 @@ func (prepareStage) Declares() IODecl {
|
||||
}
|
||||
}
|
||||
|
||||
func (prepareStage) Run(_ context.Context, env *Env, m *manifest.Manifest) (*StageResult, error) {
|
||||
func (prepareStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*StageResult, error) {
|
||||
if env == nil || env.Config == nil {
|
||||
return nil, fmt.Errorf("prepare: stage environment config is required")
|
||||
}
|
||||
@@ -89,13 +91,12 @@ func (prepareStage) Run(_ context.Context, env *Env, m *manifest.Manifest) (*Sta
|
||||
}
|
||||
}
|
||||
|
||||
resolvedAudio, err := resolveAudioFiles(sessionDir, env.Config.Session.Inputs)
|
||||
resolvedLocalAudio, useS3Audio, err := resolveAudioInputs(sessionDir, env.Config.Session.Inputs)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("prepare: resolve audio inputs: %w", err)
|
||||
}
|
||||
|
||||
copiedByDest := map[string]string{}
|
||||
inputs := make([]manifest.InputRecord, 0, 5+len(resolvedAudio))
|
||||
inputs := make([]manifest.InputRecord, 0, 5+len(resolvedLocalAudio))
|
||||
registerInput := func(kind, path, checksum string) {
|
||||
inputs = append(inputs, manifest.InputRecord{Kind: kind, Path: path, Checksum: checksum})
|
||||
}
|
||||
@@ -134,19 +135,14 @@ func (prepareStage) Run(_ context.Context, env *Env, m *manifest.Manifest) (*Sta
|
||||
registerInput(cfgFile.kind, cfgFile.dst, checksum)
|
||||
}
|
||||
|
||||
for _, src := range resolvedAudio {
|
||||
base := filepath.Base(src)
|
||||
if prev, exists := copiedByDest[base]; exists && prev != src {
|
||||
return nil, fmt.Errorf("prepare: duplicate audio basename %q from %q and %q", base, prev, src)
|
||||
if useS3Audio {
|
||||
if err := materializeS3AudioInputs(ctx, env, m, sessionID, &inputs); err != nil {
|
||||
return nil, fmt.Errorf("prepare: materialize s3 audio: %w", err)
|
||||
}
|
||||
copiedByDest[base] = src
|
||||
|
||||
dst := filepath.Join(paths.AudioDir, base)
|
||||
checksum, err := copyFileIfChanged(env.ArtifactStore, src, dst)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("prepare: materialize audio %q: %w", base, err)
|
||||
} else {
|
||||
if err := materializeLocalAudioInputs(env, paths, resolvedLocalAudio, registerInput); err != nil {
|
||||
return nil, fmt.Errorf("prepare: %w", err)
|
||||
}
|
||||
registerInput("audio", dst, checksum)
|
||||
}
|
||||
|
||||
sort.Slice(inputs, func(i, j int) bool {
|
||||
@@ -162,7 +158,7 @@ func (prepareStage) Run(_ context.Context, env *Env, m *manifest.Manifest) (*Sta
|
||||
"prepared": true,
|
||||
"stage": "prepare",
|
||||
"inputs_count": len(inputs),
|
||||
"audio_files_resolved": len(resolvedAudio),
|
||||
"audio_files_resolved": countAudioInputs(inputs),
|
||||
},
|
||||
}, nil
|
||||
}
|
||||
@@ -171,7 +167,23 @@ func renderResolvedPipeline(cfg *config.PipelineConfig) ([]byte, error) {
|
||||
return yaml.Marshal(cfg)
|
||||
}
|
||||
|
||||
func resolveAudioFiles(sessionDir string, inputs config.SessionInputsConfig) ([]string, error) {
|
||||
func resolveAudioInputs(sessionDir string, inputs config.SessionInputsConfig) ([]string, bool, error) {
|
||||
hasLocal := strings.TrimSpace(inputs.AudioDir) != "" || len(inputs.AudioFiles) > 0
|
||||
if inputs.AudioS3 != nil {
|
||||
if hasLocal {
|
||||
return nil, false, fmt.Errorf("audio_dir/audio_files and audio_s3 are mutually exclusive")
|
||||
}
|
||||
return nil, true, nil
|
||||
}
|
||||
|
||||
local, err := resolveLocalAudioFiles(sessionDir, inputs)
|
||||
if err != nil {
|
||||
return nil, false, err
|
||||
}
|
||||
return local, false, nil
|
||||
}
|
||||
|
||||
func resolveLocalAudioFiles(sessionDir string, inputs config.SessionInputsConfig) ([]string, error) {
|
||||
if len(inputs.AudioFiles) > 0 {
|
||||
out := make([]string, 0, len(inputs.AudioFiles))
|
||||
for _, p := range inputs.AudioFiles {
|
||||
@@ -223,6 +235,142 @@ func resolveAudioFiles(sessionDir string, inputs config.SessionInputsConfig) ([]
|
||||
return out, nil
|
||||
}
|
||||
|
||||
func materializeLocalAudioInputs(env *Env, paths artifacts.SessionPaths, resolvedAudio []string, registerInput func(kind, path, checksum string)) error {
|
||||
copiedByDest := map[string]string{}
|
||||
for _, src := range resolvedAudio {
|
||||
base := filepath.Base(src)
|
||||
if prev, exists := copiedByDest[base]; exists && prev != src {
|
||||
return fmt.Errorf("duplicate audio basename %q from %q and %q", base, prev, src)
|
||||
}
|
||||
copiedByDest[base] = src
|
||||
|
||||
dst := filepath.Join(paths.AudioDir, base)
|
||||
checksum, err := copyFileIfChanged(env.ArtifactStore, src, dst)
|
||||
if err != nil {
|
||||
return fmt.Errorf("materialize audio %q: %w", base, err)
|
||||
}
|
||||
registerInput("audio", dst, checksum)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func materializeS3AudioInputs(ctx context.Context, env *Env, m *manifest.Manifest, sessionID string, inputs *[]manifest.InputRecord) error {
|
||||
if env.ObjectStore == nil {
|
||||
return fmt.Errorf("s3 audio input requires object store backend")
|
||||
}
|
||||
if env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil || env.Config.Pipeline.Storage.S3 == nil || env.Config.Session.Inputs.AudioS3 == nil {
|
||||
return fmt.Errorf("s3 audio input requires pipeline.storage.s3 and session.inputs.audio_s3 configuration")
|
||||
}
|
||||
|
||||
campaign := strings.TrimSpace(env.Config.Session.Campaign)
|
||||
if campaign == "" {
|
||||
return fmt.Errorf("session campaign is required for s3 audio input")
|
||||
}
|
||||
runID := strings.TrimSpace(m.RunID)
|
||||
if runID == "" {
|
||||
return fmt.Errorf("run id is required for s3 audio input")
|
||||
}
|
||||
|
||||
sessionPrefix := artifacts.S3SessionPrefix(env.Config.Pipeline.Storage.S3.RootPrefix, campaign, sessionID)
|
||||
audioPrefix := artifacts.S3AudioPrefix(sessionPrefix, env.Config.Session.Inputs.AudioS3.Prefix)
|
||||
objects, err := env.ObjectStore.List(ctx, audioPrefix)
|
||||
if err != nil {
|
||||
return fmt.Errorf("list s3 audio objects under %q: %w", audioPrefix, err)
|
||||
}
|
||||
|
||||
audioObjects := make([]storage.ObjectInfo, 0, len(objects))
|
||||
for _, obj := range objects {
|
||||
key := strings.TrimSpace(obj.Key)
|
||||
if key == "" || strings.HasSuffix(key, "/") {
|
||||
continue
|
||||
}
|
||||
if !isFlac(key) {
|
||||
continue
|
||||
}
|
||||
audioObjects = append(audioObjects, obj)
|
||||
}
|
||||
sort.Slice(audioObjects, func(i, j int) bool {
|
||||
return audioObjects[i].Key < audioObjects[j].Key
|
||||
})
|
||||
if len(audioObjects) == 0 {
|
||||
return fmt.Errorf("no .flac files found under s3 audio prefix %q", audioPrefix)
|
||||
}
|
||||
|
||||
spoolAudioDir := strings.TrimSpace(m.LocalSpoolDir)
|
||||
if spoolAudioDir == "" {
|
||||
spoolAudioDir = artifacts.SessionSpoolAudioDir(env.Config.Pipeline.Spool.Root, campaign, sessionID, runID)
|
||||
}
|
||||
workAudioDir := filepath.Join(pathsWorkDirForManifest(env, m, sessionID), "audio")
|
||||
|
||||
if err := os.MkdirAll(spoolAudioDir, 0o755); err != nil {
|
||||
return fmt.Errorf("create spool audio directory %q: %w", spoolAudioDir, err)
|
||||
}
|
||||
if err := os.MkdirAll(workAudioDir, 0o755); err != nil {
|
||||
return fmt.Errorf("create work audio directory %q: %w", workAudioDir, err)
|
||||
}
|
||||
|
||||
seenBase := map[string]string{}
|
||||
for _, obj := range audioObjects {
|
||||
base := path.Base(obj.Key)
|
||||
if prev, exists := seenBase[base]; exists && prev != obj.Key {
|
||||
return fmt.Errorf("duplicate s3 audio basename %q from %q and %q", base, prev, obj.Key)
|
||||
}
|
||||
seenBase[base] = obj.Key
|
||||
|
||||
spoolPath := filepath.Join(spoolAudioDir, base)
|
||||
if err := env.ObjectStore.Download(ctx, obj.Key, spoolPath); err != nil {
|
||||
return fmt.Errorf("download s3 audio object %q: %w", obj.Key, err)
|
||||
}
|
||||
|
||||
workPath := filepath.Join(workAudioDir, base)
|
||||
checksum, err := copyFileIfChanged(env.ArtifactStore, spoolPath, workPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("materialize downloaded audio %q: %w", base, err)
|
||||
}
|
||||
|
||||
*inputs = append(*inputs, manifest.InputRecord{
|
||||
Kind: "audio",
|
||||
Path: workPath,
|
||||
Checksum: checksum,
|
||||
Source: "s3",
|
||||
S3Bucket: strings.TrimSpace(env.Config.Pipeline.Storage.S3.Bucket),
|
||||
S3Key: obj.Key,
|
||||
S3Size: obj.Size,
|
||||
S3ETag: obj.ETag,
|
||||
SpoolPath: spoolPath,
|
||||
})
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
func countAudioInputs(inputs []manifest.InputRecord) int {
|
||||
count := 0
|
||||
for _, in := range inputs {
|
||||
if in.Kind == "audio" {
|
||||
count++
|
||||
}
|
||||
}
|
||||
return count
|
||||
}
|
||||
|
||||
func pathsWorkDirForManifest(env *Env, m *manifest.Manifest, sessionID string) string {
|
||||
if env == nil || env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil {
|
||||
return ""
|
||||
}
|
||||
if m != nil && strings.TrimSpace(m.LocalWorkDir) != "" {
|
||||
return strings.TrimSpace(m.LocalWorkDir)
|
||||
}
|
||||
runID := ""
|
||||
if m != nil {
|
||||
runID = strings.TrimSpace(m.RunID)
|
||||
}
|
||||
if runID != "" {
|
||||
return artifacts.SessionRunWorkDir(env.Config.Pipeline.Workspace.Root, env.Config.Session.Campaign, sessionID, runID)
|
||||
}
|
||||
return artifacts.SessionWorkDir(env.Config.Pipeline.Workspace.Root, sessionID)
|
||||
}
|
||||
|
||||
func resolvePath(baseDir, p string) (string, error) {
|
||||
trimmed := strings.TrimSpace(p)
|
||||
if trimmed == "" {
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"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"
|
||||
@@ -150,6 +151,139 @@ func TestPrepareStageIdempotent(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrepareStageS3AudioDownloadAndMaterialization(t *testing.T) {
|
||||
env, m := setupPrepareEnv(t)
|
||||
env.Config.Session.Campaign = "forsaken"
|
||||
env.Config.Session.Inputs.AudioDir = ""
|
||||
env.Config.Session.Inputs.AudioFiles = nil
|
||||
env.Config.Session.Inputs.AudioS3 = &config.SessionAudioS3Input{Prefix: "audio/"}
|
||||
env.Config.Pipeline.Spool = config.SpoolConfig{Root: filepath.Join(t.TempDir(), "spool")}
|
||||
env.Config.Pipeline.Storage.S3 = &config.StorageS3Config{Bucket: "my-dnd-archive", RootPrefix: "dnd"}
|
||||
m.RunID = "20260515T031522Z-a1b2c3d4"
|
||||
m.LocalWorkDir = artifacts.SessionRunWorkDir(env.Config.Pipeline.Workspace.Root, "forsaken", m.SessionID, m.RunID)
|
||||
m.LocalSpoolDir = artifacts.SessionSpoolAudioDir(env.Config.Pipeline.Spool.Root, "forsaken", m.SessionID, m.RunID)
|
||||
|
||||
fake := &storage.FakeBackend{}
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/alice.flac", Data: []byte("alice")})
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/bob.FLAC", Data: []byte("bob")})
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/ignore.txt", Data: []byte("x")})
|
||||
env.ObjectStore = fake
|
||||
|
||||
result, err := (prepareStage{}).Run(context.Background(), env, m)
|
||||
if err != nil {
|
||||
t.Fatalf("prepare.Run() error = %v", err)
|
||||
}
|
||||
if result == nil || result.Metadata["audio_files_resolved"] != 2 {
|
||||
t.Fatalf("result metadata = %#v, want audio_files_resolved=2", result)
|
||||
}
|
||||
|
||||
aliceWork := filepath.Join(m.LocalWorkDir, "audio", "alice.flac")
|
||||
bobWork := filepath.Join(m.LocalWorkDir, "audio", "bob.FLAC")
|
||||
aliceSpool := filepath.Join(m.LocalSpoolDir, "alice.flac")
|
||||
bobSpool := filepath.Join(m.LocalSpoolDir, "bob.FLAC")
|
||||
for _, p := range []string{aliceWork, bobWork, aliceSpool, bobSpool} {
|
||||
if _, err := os.Stat(p); err != nil {
|
||||
t.Fatalf("expected file %q: %v", p, err)
|
||||
}
|
||||
}
|
||||
|
||||
audioInputs := 0
|
||||
for _, in := range m.Inputs {
|
||||
if in.Kind != "audio" {
|
||||
continue
|
||||
}
|
||||
audioInputs++
|
||||
if in.Source != "s3" {
|
||||
t.Fatalf("audio input source = %q, want s3", in.Source)
|
||||
}
|
||||
if in.S3Bucket != "my-dnd-archive" {
|
||||
t.Fatalf("audio input bucket = %q", in.S3Bucket)
|
||||
}
|
||||
if in.S3Key == "" || in.SpoolPath == "" || in.Checksum == "" {
|
||||
t.Fatalf("audio input missing provenance: %#v", in)
|
||||
}
|
||||
}
|
||||
if audioInputs != 2 {
|
||||
t.Fatalf("audio input count = %d, want 2", audioInputs)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrepareStageS3AudioFailures(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
setup func(env *Env, m *manifest.Manifest, fake *storage.FakeBackend)
|
||||
wantError string
|
||||
}{
|
||||
{
|
||||
name: "no flac files",
|
||||
setup: func(_ *Env, _ *manifest.Manifest, fake *storage.FakeBackend) {
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/readme.txt", Data: []byte("x")})
|
||||
},
|
||||
wantError: "no .flac files found",
|
||||
},
|
||||
{
|
||||
name: "list error",
|
||||
setup: func(_ *Env, _ *manifest.Manifest, fake *storage.FakeBackend) {
|
||||
fake.ListErr = os.ErrPermission
|
||||
},
|
||||
wantError: "list s3 audio objects",
|
||||
},
|
||||
{
|
||||
name: "download error",
|
||||
setup: func(_ *Env, _ *manifest.Manifest, fake *storage.FakeBackend) {
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/alice.flac", Data: []byte("alice")})
|
||||
fake.DownloadErr = os.ErrPermission
|
||||
},
|
||||
wantError: "download s3 audio object",
|
||||
},
|
||||
{
|
||||
name: "basename collision",
|
||||
setup: func(_ *Env, _ *manifest.Manifest, fake *storage.FakeBackend) {
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/a/alice.flac", Data: []byte("a")})
|
||||
fake.SeedObject(storage.FakeObject{Key: "dnd/campaigns/forsaken/sessions/2026-05-03/audio/b/alice.flac", Data: []byte("b")})
|
||||
},
|
||||
wantError: "duplicate s3 audio basename",
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
env, m := setupPrepareEnv(t)
|
||||
env.Config.Session.Campaign = "forsaken"
|
||||
env.Config.Session.Inputs.AudioDir = ""
|
||||
env.Config.Session.Inputs.AudioFiles = nil
|
||||
env.Config.Session.Inputs.AudioS3 = &config.SessionAudioS3Input{Prefix: "audio/"}
|
||||
env.Config.Pipeline.Spool = config.SpoolConfig{Root: filepath.Join(t.TempDir(), "spool")}
|
||||
env.Config.Pipeline.Storage.S3 = &config.StorageS3Config{Bucket: "my-dnd-archive", RootPrefix: "dnd"}
|
||||
m.RunID = "20260515T031522Z-a1b2c3d4"
|
||||
m.LocalWorkDir = artifacts.SessionRunWorkDir(env.Config.Pipeline.Workspace.Root, "forsaken", m.SessionID, m.RunID)
|
||||
m.LocalSpoolDir = artifacts.SessionSpoolAudioDir(env.Config.Pipeline.Spool.Root, "forsaken", m.SessionID, m.RunID)
|
||||
|
||||
fake := &storage.FakeBackend{}
|
||||
tt.setup(env, m, fake)
|
||||
env.ObjectStore = fake
|
||||
|
||||
_, err := (prepareStage{}).Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), tt.wantError) {
|
||||
t.Fatalf("error = %v, want %q", err, tt.wantError)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrepareStageAudioSourceConflictFails(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.AudioDir = "./audio"
|
||||
env.Config.Session.Inputs.AudioS3 = &config.SessionAudioS3Input{Prefix: "audio/"}
|
||||
|
||||
_, err := (prepareStage{}).Run(context.Background(), env, m)
|
||||
if err == nil || !strings.Contains(err.Error(), "mutually exclusive") {
|
||||
t.Fatalf("error = %v, want mutually exclusive error", err)
|
||||
}
|
||||
}
|
||||
|
||||
func setupPrepareEnv(t *testing.T) (*Env, *manifest.Manifest) {
|
||||
t.Helper()
|
||||
workspace := t.TempDir()
|
||||
@@ -170,6 +304,7 @@ func setupPrepareEnv(t *testing.T) (*Env, *manifest.Manifest) {
|
||||
PipelinePath: pipelinePath,
|
||||
Session: &config.SessionConfig{
|
||||
SessionID: "2026-05-03",
|
||||
Campaign: "sample-campaign",
|
||||
Inputs: config.SessionInputsConfig{
|
||||
AudioDir: "./audio",
|
||||
SpeakersFile: "./speakers.yml",
|
||||
|
||||
@@ -29,6 +29,7 @@ type Env struct {
|
||||
Scriptorium scriptorium.Runner
|
||||
Analyzer analyzer.Runner
|
||||
Storage storage.Backend
|
||||
ObjectStore storage.ObjectStore
|
||||
Notifier notify.Sender
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user