[chhoumann]

Summary

Goal: no PodNotes user stays on an old transcription model. The curated list in src/services/transcription/providers/*.ts is the source of truth, so a maintainer needs a weekly signal when OpenRouter retires one or ships a newer one. This is tooling only and adds no plugin bytes.

• scripts/model-review.mjs (npm run review:models) reads the curated IDs from the provider files, fetches the public GET https://openrouter.ai/api/v1/models?output_modalities=transcription (no key), and prints a short Markdown report: curated OpenRouter models missing from the catalog or carrying an expiration_date, catalog models newer than a curated model of the same vendor family (direct providers count, so deepgram/nova-4 is newer than nova-3), and uncurated models listed once as candidates. It exits 1 only when a curated OpenRouter model is gone or past its end date (same ends <= today rule the registry uses). --catalog <file> reads a saved catalog.
• .github/workflows/model-review.yml runs it Mondays 06:00 UTC and by workflow_dispatch, never on pull requests. It uses the default GITHUB_TOKEN with contents: read and issues: write, creates or edits one open model-review issue with the report, and then fails the run when the script exited 1. It is not in protect-master.json, has no concurrency block, and pins actions to the same SHAs as test.yml.
• AGENTS.md lists the command in Common Commands.

Base is feat/transcription-openrouter (#540), where the curated lists live.

Verification

Node 22.23.2 via fnm. All pass on this branch: npm run lint, npm run format:check, npm run typecheck, npm run test:tooling (9 files, 54 tests), npm run test (125 files, 2882 tests), npm run build. Not run: docs:build (no docs change) and Obsidian runtime checks (no plugin code change).

Tests:

• tests/tooling/modelReview.test.ts runs the report on tests/fixtures/transcription/openrouter-catalog.json (trimmed live entries plus a deliberately retired x-ai/grok-stt-2.0 and a deliberately newer deepgram/nova-4) and runs the CLI for exit codes.
• scripts/model-review.test.ts proves the IDs read from the provider files equal what PROVIDERS in the registry offers, so the reader cannot drift from the code.

Plants (npm run plant, each must type-check, fail the named test, and pass once restored):

Plant	Caught by
else if (model.expiration_date) { to else if (model.expiration_date === "never") { (drops the expiration check)	model review > reports a curated model past its end date
own.every((curatedModel) => compare(version, curatedModel.version) > 0) to own.every(() => false) (drops the family check)	model review > reports a model newer than a curated model of its family

The workflow itself has not run: GitHub runs schedule only from the default branch, so the first real run needs a manual workflow_dispatch after merge to master.

Live run on 2026-11-14 (npm run --silent review:models, exit 0, 31 catalog models, every curated model present with no end date):

# Transcription model review

Checked 2026-11-14 against the OpenRouter catalog (31 models).

## Candidates, not curated

- `moondream/parakeet-ultra` (Moondream: Parakeet Ultra)
- `nvidia/nemotron-3.5-transcribe` (NVIDIA: Nemotron 3.5 Transcribe)
- `mistralai/voxtral-small-transcribe-3-0` (Mistral: Voxtral Small Transcribe 3)
- `mistralai/voxtral-mini-transcribe-3-0` (Mistral: Voxtral Mini Transcribe 3)
- `assemblyai/universal-3-6-pro` (AssemblyAI: Universal-3.6 Pro)
- `elevenlabs/scribe-v2-medical` (ElevenLabs: Scribe v2 Medical)
- `google/gemini-3.5-transcribe` (Google: Gemini 3.5 Transcribe)
- `fish-audio/transcribe-1-pro` (Fish Audio: Transcribe 1 Pro)
- `assemblyai/universal-3-5-pro` (AssemblyAI: Universal-3.5 Pro)
- `meta/muse-voice-transcribe-1.0` (Meta: Muse Voice Transcribe 1.0)
- `nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b` (NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B)
- `mistralai/voxtral-small-24b-2507-stt` (Mistral: Voxtral Small 24B 2507 STT)
- `mistralai/voxtral-mini-3b-2507` (Mistral: Voxtral Mini 3B 2507)
- `qwen/qwen3-asr-1.7b` (Qwen: Qwen3 ASR 1.7B)
- `qwen/qwen3-asr-0.6b` (Qwen: Qwen3 ASR 0.6B)
- `fish-audio/transcribe-1` (Fish Audio: Transcribe 1)
- `nvidia/parakeet-tdt-0.6b-v3` (NVIDIA: Parakeet TDT 0.6B v3)
- `mistralai/voxtral-mini-transcribe` (Mistral: Voxtral Mini Transcribe)
- `google/chirp-3` (Google: Chirp 3)
- `openai/gpt-4o-mini-transcribe` (OpenAI: GPT-4o Mini Transcribe)
- `openai/whisper-large-v3` (OpenAI: Whisper Large V3)
- `openai/whisper-large-v3-turbo` (OpenAI: Whisper Large V3 Turbo)
- `openai/whisper-1` (OpenAI: Whisper 1)
- `openai/gpt-4o-transcribe` (OpenAI: GPT-4o Transcribe)

Release impact

None. No plugin, settings, storage, API, or URI change. Conventional type chore does not trigger a release.

Note

Add weekly model-review workflow and npm run review:models CLI

• Adds model-review.mjs, a CLI that compares curated transcription provider IDs (read from provider source files) against the OpenRouter catalog. It reports missing, expired, and newer models in Markdown and exits 1 when a curated model is gone or past its end date.
• Adds a review:models npm script and a scheduled workflow that runs Mondays at 06:00 UTC or manually. It writes the report to the step summary, force-updates a model-review label, edits or creates an issue with that label, then fails the job if the review reported problems.
• Includes tests for comparison logic and the CLI, plus an OpenRouter catalog fixture. Documents the command and workflow in AGENTS.md.
• Risk: the workflow uses a force-push label update (model-review), so any existing issue with that label gets its body overwritten by the report.

^{Macroscope summarized 9f091c1.}

---

Note

Low Risk
Tooling-only change with no plugin runtime impact; the workflow only reads the repo and writes/updates issues using the default token.

Overview
Adds npm run review:models and scripts/model-review.mjs, which read curated transcription model IDs from provider files, compare them to the public OpenRouter transcription catalog (live fetch or --catalog), and emit a Markdown report for missing or expiring curated OpenRouter models, newer family versions, and uncurated candidates. The command exits 1 when a curated OpenRouter model is absent or past its end date.

A new Model review GitHub Actions workflow runs that script weekly (Mondays) and on manual dispatch, publishes the report to the job summary, and creates or updates a single model-review issue when action is needed (without reopening on candidates-only reports). AGENTS.md and package.json document the npm script.

Coverage includes unit/CLI tests with a catalog fixture and a check that parsed provider IDs stay aligned with the transcription registry.

^{Reviewed by Cursor Bugbot for commit 9f091c1. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cloudflare-workers-and-pages]

Deploying podnotes with    Cloudflare Pages

Latest commit:	9f091c1
Status:	✅  Deploy successful!
Preview URL:	https://5580bef7.podnotes.pages.dev
Branch Preview URL:	https://chore-model-review.podnotes.pages.dev

View logs