Skip to content

docs(mcp): describe current heuristic summary sources #2439

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
r3dbars merged 1 commit into from
Nov 12, 2026
Merged

docs(mcp): describe current heuristic summary sources #2439

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Tools/TranscriptedMCP/AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ captures/*.md -> TranscriptLoader (direct reads: read_meeting/read_dictation/rea
```

- Index tables: meetings, speakers and utterance rows, `meeting_summary_items` (one row per Decision / Action Item with owner / Open Question, `kind` discriminator, FTS5), dictation days and entries, `writing_days` / `writing_entries` + FTS5. Schema version is 6 (`TranscriptIndex.swift`); an older `user_version` rebuilds from disk. DDL is in `TranscriptIndex+Schema.swift`.
- Summary items come from `TranscriptedCaptureKit.CaptureSummaryParser` over legacy artifacts (inline summary or `<stem>.summary.md` sidecar) during `indexMeeting`. Current app capture does not create new AI summaries. Cross-meeting queries go through `TranscriptIndex.listSummaryItems(kind:owner:dateFrom:dateTo:)`.
- Summary items come from `TranscriptedCaptureKit.CaptureSummaryParser` during `indexMeeting`: heuristic `auto_summary_*` frontmatter from the current meeting-save pipeline, older `local_summary_*` fields and inline blocks, or a legacy `<stem>.summary.md` sidecar. The current heuristic extraction does not use an AI model; meetings without indexable summary fields contribute no summary rows. Cross-meeting queries go through `TranscriptIndex.listSummaryItems(kind:owner:dateFrom:dateTo:)`.
- `FileWatcher` debounces 500ms and also scans on a 5-minute timer.

## Semantic search
Expand Down
7 changes: 4 additions & 3 deletions Tools/TranscriptedMCP/Sources/TranscriptedMCP/TranscriptLoader.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,9 +57,10 @@ enum TranscriptLoader {
)
}

/// Structured summary for a legacy saved meeting. It prefers an inline
/// summary block, then falls back to a `<stem>.summary.md` sidecar so old
/// artifacts remain readable. Current capture does not create new summaries.
/// Structured summary for a saved meeting. It prefers summary fields inside
/// the transcript (`auto_summary_*` heuristic frontmatter or older local
/// summary fields and blocks), then falls back to a legacy
/// `<stem>.summary.md` sidecar so old artifacts remain readable.
///
/// The sidecar branch is a legacy-compat fallback; a sidecar edited in
/// isolation does not bump the parent transcript's mtime, so its items only
Expand Down
Loading