grant/ten31-transcripts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
050ae32e1dc6c0a5c84b77e42025f0c0e54456b9
ten31-transcripts/AGENTS.md
T

13 KiB
Raw Blame History

AGENTS.md — Ten31 Transcripts

Native macOS menu-bar app that detects video calls, records dual-track audio + watches the call window for active-speaker cues, and sends audio + a visual timeline to a self-hosted SparkControl backend that does transcription/diarization/naming — producing named transcripts and recaps.

Inbox check: At session start, if ~/Projects/standards/INBOX.md exists, scan it for items tagged (ten31-transcripts) and surface them before proposing next steps; triage with /triage.

Stack (versions that matter)

  • Swift 5.0, SwiftUI + AppKit, macOS 13.0 deployment target. LSUIElement (menu-bar only, no Dock icon).
  • Project is generated by XcodeGen from project.yml (brew install xcodegen). *.xcodeproj is gitignored — regenerate, don't edit.
  • Full Xcode lives at /Applications/Xcode.app, but xcode-select points at CommandLineTools → set DEVELOPER_DIR for every xcodebuild.
  • Bundle id xyz.ten31.transcripts; DEVELOPMENT_TEAM (Apple Team ID) is set in a gitignored Config/Signing.xcconfig (copy Config/Signing.xcconfig.example and set your team). Keep it stable — a constant signing identity is what preserves TCC grants across rebuilds.
  • Backend: SparkControl gateway at $SPARK_BACKEND_URL (a private LAN backend — IP or .local host; Start9 self-signed cert. Install the StartOS Root CA in the System keychain so normal TLS validation succeeds; skip-TLS is an opt-in, host-scoped escape hatch, off by default — see InsecureTrustDelegate). Resolution order: a value saved in Settings → SparkControl backend (UserDefaults) wins, else the SPARK_BACKEND_URL env var, else the placeholder default in AppSettings.swift. Diarization = Sortformer/TitaNet (mono-only, ~4 speakers/chunk); LLM = Qwen3 via OpenAI-compatible /v1/chat/completions; audio via /api/audio/label-merge.

Commands

First time on a machine — create the local signing config (else xcodegen generate/signing won't find a team):

cp Config/Signing.xcconfig.example Config/Signing.xcconfig   # then set DEVELOPMENT_TEAM

Regenerate the Xcode project (after adding/removing/renaming any source file):

xcodegen generate

Build + run all tests:

DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer xcodebuild test \
  -project Ten31Transcripts.xcodeproj -scheme Ten31Transcripts \
  -destination 'platform=macOS' -derivedDataPath /tmp/ten31-dd

Run a single test (target/class/method):

DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer xcodebuild test \
  -project Ten31Transcripts.xcodeproj -scheme Ten31Transcripts \
  -destination 'platform=macOS' -derivedDataPath /tmp/ten31-dd \
  -only-testing:Ten31TranscriptsTests/SpeakerReconcilerTests/testCosine

Build only: replace test with build. Lint/format: none configured (no SwiftLint/SwiftFormat/Makefile); adding one is tracked in ROADMAP.md. Build a standalone app and install/run it (Xcode does not need to stay open):

DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer xcodebuild \
  -project Ten31Transcripts.xcodeproj -scheme Ten31Transcripts \
  -configuration Release -derivedDataPath /tmp/ten31-release build
ditto /tmp/ten31-release/Build/Products/Release/Ten31Transcripts.app /Applications/Ten31Transcripts.app
open /Applications/Ten31Transcripts.app

Fast validation harness (preferred for visual/backend logic): compile the specific Ten31Transcripts/**.swift files plus a main.swift with xcrun --sdk macosx swiftc -O ... main.swift -o x and run against real fixtures (example-screenshots/) or saved sessions. Top-level code must live in the file literally named main.swift.

Layout (day one)

  • Ten31Transcripts/App/ — @main entry + AppDelegate.
  • Ten31Transcripts/Session/ — SessionController (state machine), TranscriptPipeline, SessionPackager (chunking), TranscriptAssembler, SpeakerReconciler, ChunkPlan (ChunkMode), SpeakersFile, SessionNaming (pure folder-name + recap-title logic).
  • Ten31Transcripts/Visual/ — VisualCapture/VisualObserver (ScreenCaptureKit, ~3fps), GridCallAnalyzer (+ FrameSampler, TextRecognizer, TimelineBuilder, VisualTimeline, SpeakerObservation).
  • Ten31Transcripts/Adapters/ — per-app screen-readers (MeetAdapter, ZoomAdapter, TeamsAdapter, SignalAdapter) + AdapterRegistry.
  • Ten31Transcripts/Audio/ — AudioRecorder, MicVAD, ChannelSelfVAD, AudioMixer, MonoTrackWriter, Resampler.
  • Ten31Transcripts/Backend/ — SparkControlClient, GatewayLLMClient, VoiceprintStore, SparkControlHealth, InsecureTrustDelegate (TLS skip).
  • Ten31Transcripts/Recap/ — RecapAnalyzer, RecapRenderer (writes transcript.md + recap.html), RecapModels, RecapTemplate, SpeakerEditing, RecapEditModel.
  • Ten31Transcripts/{Detection,Permissions,Settings,UI,Support}/ — CallDetector/AudioInputProcesses/MicActivityMonitor; PermissionsManager; AppSettings (UserDefaults); SwiftUI views + AppKit window hosts; Info.plist + entitlements.
  • Ten31TranscriptsTests/ — XCTest. example-screenshots/ — real fixtures (gitignored). docs/, README.md.
  • Runtime output (default ~/Ten31Transcripts/sessions/<ts>_<app>/, configurable in Settings): mic.wav, system.wav, mixed_mono_16k.wav, self_vad.json, visual_timeline.json, speakers.json (output), cluster_fingerprints.json, recap.{html,json}, transcript.md. The folder is created at session start as <yyyy-MM-dd'T'HH-mm-ss>_<app>; on stop the user can name the meeting and it's renamed to <date>_<name>_<app> (skipping keeps the auto stamp).

Conventions

  • Match the surrounding file's style; small reviewable diffs; comments explain why, not what.
  • Write/extend XCTest alongside non-trivial changes; pure logic (chunking, reconciliation, analyzer math) is unit-tested offline.
  • Commits: imperative mood, concise; authored by Grant. Push to the self-hosted Gitea remote origin (branch main, over SSH) after committing, with my approval; the remote URL lives in .git/config, kept out of source. Work on main — don't create feature branches unless I ask.
  • Gitea push gotcha: origin's URL uses a raw .local mDNS host that intermittently fails to resolve (Could not resolve hostname, or a push that connects then stalls). The gitea-home SSH alias (in ~/.ssh/config) points at the same Gitea server (port 59916, user git) via a reliable HostName — the sibling standards repo uses it. Reliable fallback: git push gitea-home:grant/ten31-transcripts.git main then git update-ref refs/remotes/origin/main main. Repointing origin to the alias would make this permanent (not yet done).
  • Never commit recordings, transcripts, screenshots, or the generated *.xcodeproj.
  • No API keys/tokens/passwords in the repo. The backend host ($SPARK_BACKEND_URL) and the Apple Team ID (Config/Signing.xcconfig, gitignored) are kept out of source — real values live in Settings/UserDefaults and the local xcconfig. Build env vars: DEVELOPER_DIR (required) and optional SPARK_BACKEND_URL.
  • Git history scrubbed (2026-06-13): the private backend host + LAN IP were purged from all commits via git filter-repo (replaced with the your-spark-backend.local placeholder) and force-pushed; 0 hits across refs. Pre-rewrite backup bundle: ../ten31-transcripts-prehistory-rewrite.bundle. A second rewrite the same day purged two backend LAN IPs that had slipped into a docs/test commit, replacing them with RFC 5737 documentation IPs (192.0.2.1/192.0.2.2) and force-pushing; 0 hits across refs; backup bundle ../ten31-transcripts-pre-ip-scrub.bundle. The Apple Team ID was intentionally not scrubbed (it's public in every signed binary) — don't re-flag it.

Always

  • Set DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer on every xcodebuild.
  • Run xcodegen generate after adding/removing/renaming source files.
  • Treat the backend as the owner of transcription, diarization, and speaker naming; the app only records, watches, packages, and reconciles hints.
  • Identify self by the mic channel + the single name in Settings → Your name, and keep that name reserved so the LLM never assigns it to another speaker.
  • Treat visual active-speaker cues as naming hints over audio diarization (the backbone): prefer sparse-but-correct detection over dense-but-wrong.
  • Send the backend dual-channel (mic_file + system_file) when the system track is healthy, else the mono mixed_mono_16k.wav; keep backend calls sequential (one in flight).
  • After any code change, rebuild Release + ditto to /Applications — the installed copy does not auto-update.

Never

  • Never write video frames to disk — analyze in-memory and release immediately (privacy non-negotiable).
  • Never add Co-Authored-By / "Generated with" / any AI or tool attribution to commits or PRs.
  • Never commit secrets, recordings, transcripts, or example-screenshots/ (faces + contact names).
  • Never do per-platform display-name matching for self (Zoom/Meet/Signal names differ) — channel + one canonical name only.
  • Never treat a solid camera-off avatar tile (Meet's orange/magenta fill) as an active speaker — the real cue is a thin hollow coloured ring; require thin-edge + hue gate (see GridCallAnalyzer.isHollow, FrameSampler.thinColoredPoints).
  • Never collapse adjacent same-speaker transcript segments (reverted by request) — one line per diarized utterance.
  • Never let a session-folder name put the meeting name where the app label is parsed from: the app must stay the last _-segment (SessionController.appLabel(from:) reads .split("_").last; SessionNaming enforces this and disambiguates collisions on the name segment). Renames happen at finish()-time after files are closed — re-derive track URLs from the (possibly moved) folder, never from RecordingResult's start-time paths.
  • Never send call audio to a raw IP the user didn't configure. Offline backend checks: a .local mDNS host can't be resolved by a plain swiftc/URLSession binary (-1009) — use the real app or curl; but a configured raw IP is reachable from a plain swiftc URLSession binary (that's how the TLS fix was verified offline).
  • Never force-push a shared branch, and never push without my approval. (Work on main — don't create feature branches unless I ask.)

Current state

Present tense; overwritten each session. main clean and pushed (HEAD a5c227e, pushed via the gitea-home alias — origin's .local host wouldn't resolve); /Applications/Ten31Transcripts.app rebuilt + installed from HEAD. Full suite re-run: 91 pass (was 73; +18 SessionNamingTests).

  • This session (2026-06-17) — meeting-name prompt + folder rename: on stop, an NSAlert asks for a meeting name (Save/Skip) and the session folder is renamed <ts>_<app> → <date>_<name>_<app> (HH-MM-SS dropped; Skip/blank keeps the stamp). Pure logic in SessionNaming (sanitize, leaf compose, recapTitle for both forms); app label stays the last _-segment; collisions disambiguate on the name segment; finish() re-derives track URLs post-rename; quit never prompts and aborts an open prompt. Reviewer-reviewed; its P1 (quit-during-modal) + two P2s fixed.
  • Backend connected end-to-end: real LAN URL saved in Settings → SparkControl backend (off-repo: defaults read xyz.ten31.transcripts backendBaseURL); committed default stays the placeholder.
  • Working: backend hand-off (live), call detection (Meet/Zoom/Teams/Signal), dual-track capture, dual-channel + chunked send, speaker reconciliation, recap, speaker editor, configurable chunk length, standalone Settings, meeting-name prompt + readable folders.
  • Verify next (real app): the naming prompt + rename is unit-tested + builds but not yet exercised on a live stop — run a real recording, stop, name it, confirm the folder renames and backend output lands in the renamed folder.
  • Next up: (a) repoint origin to gitea-home so pushes stop hitting the flaky .local host (see Conventions); (b) backend URL primary→fallback + the mmss() NaN/∞ guard freebie (sketch first; keep real IPs out of source — use 192.0.2.x).
  • In progress / unverified: the Meet visual fix (reject solid camera-off tiles) still has no clean end-to-end run — re-process the saved Meet session + a fresh Meet call (needs real app + backend).
  • Known bugs / loose end: sparse Meet speaking-detection (faint blue border); sub-second junk "self" mic fragments; desktop-mic vs phone doesn't unify by voiceprint. Doc loose end: docs/01 §5/docs/02 §2.4 still list "AppleScript" as a Meet name source though the code uses window titles.
Reference in New Issue View Git Blame Copy Permalink