Grant Gilliam 1c133c8970 Fix mis-attributed fragments + LLM naming guardrails + re-process saved sessions
Investigating Grant's real 38-min group call: 'Marty' was a GARBAGE cluster (192
segs, 0.37s mean, 186 ≤2 words, 125 single words flanked by the same other speaker —
diarization micro-fragments split mid-sentence, then LLM-named 'Marty'). Same for
'Message'/'HI'.

- SpeakerReconciler.smoothFragments: dissolve non-self clusters whose MEDIAN segment
  duration ≤ 1s (≥3 segs) — reassign each fragment to the temporally-nearest real
  speaker. (Median, not max, so one stray long segment can't rescue a fragment
  cluster — the bug in the first cut.) On the real call: 7 speakers (3 junk) → 4 real
  (Marty/Message/HI absorbed into Grant/Jonathan/Me/MH). Runs before LLM naming.
- LLM naming guardrails: forbid assigning the self name or ANY already-taken name to
  another voice (fixes 'Grant' = the user's name pinned on a remote speaker); prompt
  demands self-intro / direct-address evidence (mention ≠ presence), 'precision over
  coverage', one name per speaker.
- Open saved session now offers Open Editor vs Re-process, so newer logic can be
  applied to past calls (+ always-visible progress from the prior fix).

NOTE: the self-name guardrail needs the app to KNOW the user's name — selfName is still
'Me', so set it in Settings (e.g. 'Grant') so the LLM can't reuse it. 62/62 XCTest.
2026-06-08 12:45:17 -05:00

Ten31 Transcripts

Native macOS menu-bar app that auto-detects conference calls, records local audio, builds a visual-derived speaker timeline, and hands audio + timeline to the SparkControl backend for naming/transcription. See docs/ for the full spec.

This repo is at Phase 0 (scaffold, permissions, backend health check).

One-time setup

  1. Install Xcode from the Mac App Store (free; ~40 GB). Open it once and accept the license prompt.
  2. Install XcodeGen (generates the Xcode project from project.yml):
    brew install xcodegen
    
  3. Generate the project:
    xcodegen generate
    
    This creates Ten31Transcripts.xcodeproj (git-ignored — regenerate any time).
  4. Open it:
    open Ten31Transcripts.xcodeproj
    
  5. Signing is preconfigured: project.yml sets DEVELOPMENT_TEAM to the free personal team BK4Y6CXN35 with automatic signing, so Signing & Capabilities should already show the team — no manual selection needed. (If you ever sign with a different Apple ID, update DEVELOPMENT_TEAM in project.yml, not in Xcode — xcodegen generate overwrites Xcode-side changes.)
  6. Press Run (⌘R).

Note: after adding files in a new phase, re-run xcodegen generate and let Xcode reload the project. The signing team persists because it lives in project.yml, so macOS permissions stay granted across rebuilds.

What Phase 0 does

  • Launches as a menu-bar-only app (no Dock icon).
  • Menu panel shows live status for the three permissions it needs — Microphone, Screen Recording, Accessibility — with Grant / Open Settings buttons.
  • Shows a backend health check (GET /api/status) against the configured host.
  • Settings: backend base URL, skip-TLS toggle (on by default for the self-signed cert), output folder, and adapter toggles (inert this phase).

No audio capture, call detection, screen reading, or backend hand-off yet — those arrive in Phases 16 (docs/04_BUILD_PLAN.md).

Project layout

project.yml                     # XcodeGen recipe → generates the .xcodeproj
Ten31Transcripts/
  App/        Ten31TranscriptsApp.swift, AppDelegate.swift
  UI/         MenuBarView, SettingsView, PermissionRow
  Permissions/PermissionsManager.swift
  Backend/    SparkControlHealth.swift, InsecureTrustDelegate.swift
  Settings/   AppSettings.swift
  Support/    Info.plist, Ten31Transcripts.entitlements
Ten31TranscriptsTests/          # placeholder; real tests land in Phase 3

Notes

  • App Sandbox is off and Hardened Runtime is off — this is a personal, LAN-only tool that must observe other apps. Revisit only if distributing.
  • The default backend host is https://your-spark-backend.local:62419 (editable in Settings).
S
Description
No description provided
Readme 890 KiB
Languages
Swift 100%