eric/narratio
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 15 Wiki Activity

Add normalized transcript analysis source

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-10 21:43:50 +00:00
parent 515b19c4d4
commit 532dee6c0b
4 changed files with 128 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
architecture.md
View File

@@ -227,8 +227,10 @@ Behavior:
- if enabled artifacts exist but `session_recap` is not enabled, analyze fails clearly
- `session_recap` should use `trimmed_transcript` input (`transcripts/trimmed.json`) for in-universe recap generation
- `trimmed_transcript` input is resolved from manifest (`trim` output kind `transcript_trimmed`) when available, otherwise fallback path `work/<session_id>/transcripts/trimmed.json`
- `normalized_transcript` input is resolved from manifest (`normalize` output kind `transcript_normalized`) when available, otherwise fallback path `work/<session_id>/transcripts/normalized.json`
- `processed_transcript` input is resolved from manifest (`polish` output kind `transcript_processed`) when available, otherwise fallback path `work/<session_id>/transcripts/processed.json`
- `processed_transcript` remains available for future table/meta-analysis artifacts
- `normalized_transcript` is the preferred full-transcript source for future table/meta-analysis artifacts
- `processed_transcript` remains available for advanced/debug use cases
- transcript inputs are validated as JSON with top-level `segments` array
- configured inputs are resolved by source
- optional `previous_recap` is omitted when unavailable