Repository navigation
chore(tooling): review transcription models weekly - #541
Conversation
gpt-4o-transcribe-diarize rejects requests with more than 1400 s of audio, but MP3 chunks were split by size alone. Any MP3 under about 120 kbps put more than 1400 s in a 20 MB chunk, so every chunk failed. For diarization, split MP3 at frame boundaries into the fewest equal parts that stay under both 20 MB and 1400 s. Whisper keeps its size-only chunks. Fixes #532
A chunk that OpenAI rejected with a status such as 400 or 401 was sent three times, although each send fails the same way. A long diarized episode went up three times before the error showed. Retry only the statuses openai-node retries: 408, 409, 429 and 5xx, plus network errors. Refs #532
gpt-4o-transcribe-diarize takes up to 0.58 s per second of audio, measured over 81 requests, so the 1,072 s parts a 54 min episode got would take about 10 min each, at the request timeout. Parts are now at most 600 s, which the model answers in under 6 min. Refs #532
Each test passes on the hand-written code. Together they catch wrong derivations that no existing test sees: the -1 SecretStorage ID suffix that released versions accept, the provider an export error names, the kind a settings key row adopts a secret for, and the key migration notices.
CREDENTIALS in src/types/Credentials.ts holds each kind's settings field, export key and label. The credential repository, settings decoder, settings transfer, settings tab and key migration notice loop over it. IPodNotesSettings takes its key fields from it, so a kind with no default in DEFAULT_SETTINGS fails typecheck. The plaintext key map from before 2.19.0 stays fixed.
The published transcript renderer is the reader of the format that stays when the diarization folder goes. The default template now lives only in DEFAULT_SETTINGS, so src/constants.ts imports no service code.
src/services/transcription/ turns an episode into a transcript with any provider. A provider is one file: its models, its request, and how to read its answers. OpenAI (gpt-transcribe) and Deepgram (nova-3) are the first two. The engine owns what providers share: - audioSource.ts decides whether a provider may be given the episode's address. Only an address that a saved public feed lists, that carries no credential, and that names a public host passes. All other audio is uploaded. - split.ts is audioChunker.ts with the caps as arguments and a start time on each part. - http.ts sends a request at most three times, and only after a 429, a 5xx, or a lost connection. Its failure sentences never include the provider's own text, which can quote a private address. - cues.ts turns words or text into the shapes of a published transcript. Nothing calls the engine yet. Lint rejects an import of the folder's files from outside it, except its index.
TranscriptionService keeps its queue, the published-transcript path, the progress notice, and note saving. It calls the engine for audio. - OpenAI transcribes with gpt-transcribe. whisper-1 and gpt-4o-transcribe-diarize, which OpenAI shuts down on 2027-02-26, are gone. A tooling test searches the built main.js for them. - With speaker labels on and OpenAI selected, the transcript is saved without labels. A notice that stays until clicked names the providers that label speakers. - Deepgram transcripts go through renderTranscriptBody, so each paragraph has a timestamp. Speakers are numbered in the order they first speak. - Deepgram gets the address of a public episode and downloads it itself. - A failure notice stays until clicked. Parts go out one at a time, and a 401, 402, 404, or 400 stops the job before the next part. Deletes src/services/diarization/, openaiTranscription.ts, the Whisper worker pool, and createBinaryChunkFiles. getEpisodeAudioBuffer no longer returns a basename, because uploads are named for their format only.
net.mjs answers OpenAI with { text } and Deepgram with the words of two
speakers, and logs the content type of each request. fixtures.mjs serves a
feed at priv3.supercast.com, an address that PodNotes keeps private. The
transcripts recipe covers OpenAI in parts, and Deepgram by address and by
upload.
The marketplace review test called TranscriptionService.waitForRetry, which the engine replaced. An aborted run now rejects through waitForLifecycle, so the test aborts a pending wait there and expects the same Error.
An aborted job no longer downloads the episode or decodes it into parts. Until now only its requests were refused. A 429 or a 5xx that asks to wait over a minute is sent once. A sooner send would only upload the audio to be refused again.
… feat/transcription-providers
A provider's name was written twice: once in its credential row and once in its provider file. The row now owns it, so a provider file holds only its models and its request. Each model gains the name the settings will show.
The provider was derived from the speaker settings: Deepgram with speaker labels on, OpenAI otherwise. It is now stored as transcript.provider, with transcript.model beside it, where "" follows the provider's recommended model. schemaVersion stays 2 and both fields are additions, so a device on 2.24.0 keeps loading the library and keeps the fields on its own saves. A library that has no transcript.provider gets the provider it ran with: Deepgram for speaker labels with Deepgram, with or without its key, and OpenAI otherwise. The migration reads only the stored document, adds no decode warning, and gives the same answer on every load until a save stores it. transcript.diarization.provider belongs to versions up to 2.24.0. This version reads it for that migration alone, never writes it, keeps it in data.json as found, and leaves it out of settings exports. Importing a 2.24.0 export that labels speakers with Deepgram selects Deepgram. A provider or model ID this version does not have is kept as stored and shown under that name. An unknown provider refuses to transcribe with a notice. An unknown model runs the recommended model and the notice says so. The Transcripts settings now read: Transcription provider, the chosen provider's API key, Model, Speaker labels, Speaker label format, then the path and template. Speaker labels is disabled for a model that cannot label speakers. The Diarization provider row is gone.
ElevenLabs is a credential row, one provider file and a registry line. Its key reference is the new root field elevenLabsSecretId, stored in SecretStorage as podnotes-elevenlabs-api-key, and a settings export carries the key as secrets.elevenLabs. The export envelope stays at version 2. A public episode goes to ElevenLabs by its address, so nothing is downloaded. Any other episode is uploaded in one request. Word times and speakers reach the note, and turning speaker labels off asks for none. ElevenLabs answers 401 for a used-up quota as for a rejected key, and 400 for a model the key may not use as for an address it could not download, so the provider reads detail.code. Only the last of these is followed by an upload. A request waits 10 minutes for its answer. A new install starts on ElevenLabs with speaker labels on. A library saved up to 2.24.0 that holds no OpenAI key and has speaker labels off moves to ElevenLabs too, because it never set transcription up. A library that never stored the speaker labels choice keeps them off. The notice for a model without speaker labels now names ElevenLabs first.
A journey now seeds its transcription provider with its key, because a new vault is on ElevenLabs. The OpenAI journeys choose OpenAI. A new journey runs the default: a public episode goes to ElevenLabs by its address, no audio is fetched, and the note has timestamps and speaker labels. The ElevenLabs stub answers with the words ElevenLabs returns and records what each request named. The settings tab test walks the new Transcripts rows, and the key recovery test links the ElevenLabs key, the one a new vault shows.
The fixture provider answers api.elevenlabs.io with ElevenLabs' words, two speakers with the second 12 s in, and logs the address a request named in place of a file. The transcript guide follows the new settings rows and adds the ElevenLabs runs and a 2.24.0 library check.
…choice The provider row decided for itself whether the stored provider is one this version has, and the Speaker label format row read the stored speaker setting. Both now ask transcriptionChoice, as the key rows, the model row and the Speaker labels row do. The engine no longer exports a type nothing imports.
The Transcripts tests looked each control up by a CSS selector inside its row and asserted on a hidden row's inline style. They now query by role and by the row's name, as a user or a screen reader finds a control, so a hidden row is one the query does not find.
…ings measure The transcription engine left main.js at 103,795 gzip bytes. The provider and model settings, their migration and the ElevenLabs provider add 866, which takes it to 104,661 and over the 104,000 budget. The budget rises by those 866 bytes to 104,866, so the 205 bytes of headroom stay as they were.
…m library 2.24.0 imports the diarization object whole and fills a missing provider with OpenAI, so omitting the field moved Deepgram libraries to OpenAI. Imports here keep the provider this library stored.
A library migrated with OpenAI speaker labels on could not turn them off, so every transcription repeated the notice.
… one The tests for a provider and a model a newer PodNotes stored used OpenRouter and Grok STT 2.0, which this version is about to run. They now use AssemblyAI and universal-3-6-pro.
OpenRouter is a credential row, one provider file and a registry line. Its key reference is the new root field openRouterSecretId, stored in SecretStorage as podnotes-openrouter-api-key, and a settings export carries the key as secrets.openRouter. It offers three models, each with the request measured to give word times and speakers: - Grok STT 2.0, recommended: base64 JSON with verbose_json and word and segment times, routed to xAI with provider.only, which takes diarize from provider.options.xai. A request routed elsewhere is answered with no speakers. - ElevenLabs Scribe v2: multipart with diarize beside the model, or JSON with input_audio.url for an episode a saved public feed lists. - MAI-Transcribe 2: multipart with diarize beside the model. With speaker labels off, no request carries diarize. Sounds Scribe v2 lists as audio_event items are left out. OpenRouter takes 25 MB a request and gives the model 60 s, so an upload goes in parts of at most 18 MB and 1,800 s. Parts of 24 MB were answered in 20 to 31 s. A 402 says the account is out of credit, a 401 that the key was rejected, and a 404 that the model is not offered. A 404 whose message names the account's data policy or zero data retention says the model is not offered under the account's OpenRouter privacy settings. Each ends the job at the first part, and none quotes OpenRouter.
…t each part A note saved with speaker labels asked for and none returned now says so: "Saved without speaker labels, because Grok STT 2.0 returned none." OpenRouter answers 200 with no speakers when a request reaches a route that ignores the speaker option, so this is checked for every provider. Labels from two parts already name different speakers. An episode sent in parts now also says that its labels restart in each part, so one person can have several labels, until labels are merged across parts.
…ll lists PodNotes reads OpenRouter's public catalog of transcription models, without the key, when the Model row draws and when an OpenRouter job starts. It keeps the read in memory for 24 hours. A read that fails is not kept, so the next one asks again, and the tested list is offered as it is. The catalog only takes models away. A model it does not list is not offered, and one whose expiration_date has come is skipped. A model with a later end date reads "Grok STT 2.0, ends <date>" in the Model row. A catalog that would leave no model is not followed. A chosen model the catalog no longer lists stays selected in the Model row as "<label>, no longer offered". A job runs the first offered model instead and says "OpenRouter no longer offers ElevenLabs Scribe v2, so PodNotes used Grok STT 2.0." The row redraws when a read lands while it is open. A provider gets its catalog through an optional catalog() beside failure(), so the registry owns the cache and the filter for any provider that has one.
A stub answers OpenRouter's transcriptions with two speakers, the second 12 s in, and its model catalog with the three models PodNotes offers. It records what each request named and a hash of the audio it carried, decoded from base64 for JSON. J-TR-09 plays a public episode on Scribe v2: one JSON request names the episode's address, and the episode's audio is never fetched. J-TR-10 plays it on the recommended Grok STT 2.0: one JSON request carries the audio as base64, the same bytes the fixture server holds. Both notes have timestamps and numbered speakers, and the catalog is read once, with no Authorization. A journey seeds any provider by its credential row, and a model with it.
…eads them The fixture provider answers openrouter.ai transcriptions with verbose_json words from two speakers, the second 12 s in, and the model catalog with the three models PodNotes offers. The log keeps openrouter.ai paths and reads the address a JSON request names in input_audio.url. The transcript guide adds the OpenRouter rows, its runs (Scribe v2 by address, Grok by base64, a long MP3 in parts) and the notices that now name OpenRouter.
Audio frames inside a tag's declared size were counted and could be cut through, sending an undecodable first part, and frame-like bytes in a trailing tag added a part.
…engine # Conflicts: # src/services/TranscriptionService.test.ts # src/services/TranscriptionService.ts # src/services/audioChunker.test.ts # src/services/audioChunker.ts # src/services/diarization/openaiProvider.ts # src/services/diarization/types.ts # src/services/openaiTranscription.test.ts # src/services/openaiTranscription.ts # tests/mocks/openaiFailures.ts
…h cap A file in a format other than MP3 under the size cap went whole whatever its length, so a long .m4a passed a model's maxSeconds. Its length now comes from its metadata through a media element, without decoding it, and audio over the cap is decoded into WAV parts that fit both caps. Audio of an unknown length still goes whole.
A public feed's enclosure with AWS or Google Cloud signing parameters passed the feed credential check, so Deepgram got the whole signed address. A query parameter whose name holds signature, credential or token, or Akamai's hdnts, now uploads the audio instead.
…nload A WebView may load no metadata for media it does not play, so the length probe could wait forever, and an unload could not stop it before a decode. The probe now reads the length as unknown after 5 s or when the job is aborted, and an aborted job decodes nothing.
…nscription-providers # Conflicts: # AGENTS.md # scripts/size-baseline.md # scripts/size.mjs # scripts/size.test.ts # src/persistence/settingsCodec.ts # src/settingsTransfer.ts # src/types/Credentials.ts # src/ui/settings/PodNotesSettingsTab.ts
…nscription-openrouter # Conflicts: # AGENTS.md # scripts/size-baseline.md # scripts/size.mjs # scripts/size.test.ts
…address An address goes in one request, so Scribe v2 on OpenRouter got a public episode of any length by address, past the 1,800 s its parts are capped at for OpenRouter's 60 s limit. An episode the feed says is longer than the model's cap is now uploaded in parts. One of unknown length still goes by address.
|
Retargeted to
|
|
FAIL
|
Two overlapping runs could each find no open model-review issue and each open one.
|
Fixed in 644c92b. No test was added. GitHub's queueing cannot run locally, and a test that only asserts the block exists would be a tautology. The YAML parses, and lint, format:check and test:tooling (55) pass. The note that an existing issue gets "Nothing to review." but stays open is intended. The maintainer closes it after acting on the review. |
|
PASS+NOTES
|
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 644c92b. Configure here.
The review dropped every catalog model with an end date, so a successor in a curated family that OpenRouter still offers went unreported. It is now reported until its end date, as the plugin offers it. A model with an end date is still no candidate to start using.
|
PASS
|

Summary
Goal: no PodNotes user stays on an old transcription model. The curated list in
src/services/transcription/providers/*.tsis 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 publicGET 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 anexpiration_date, catalog models newer than a curated model of the same vendor family (direct providers count, sodeepgram/nova-4is newer thannova-3), and uncurated models listed once as candidates. It exits 1 only when a curated OpenRouter model is gone or past its end date (sameends <= todayrule the registry uses).--catalog <file>reads a saved catalog..github/workflows/model-review.ymlruns it Mondays 06:00 UTC and byworkflow_dispatch, never on pull requests. It uses the defaultGITHUB_TOKENwithcontents: readandissues: write, creates or edits one openmodel-reviewissue with the report, and then fails the run when the script exited 1. It is not inprotect-master.json, runs one at a time in themodel-reviewconcurrency group so two runs cannot each open an issue, and pins actions to the same SHAs astest.yml.AGENTS.mdlists the command in Common Commands.Base is
master, since #540 merged with the curated OpenRouter list.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.tsruns the report ontests/fixtures/transcription/openrouter-catalog.json(trimmed live entries plus a deliberately retiredx-ai/grok-stt-2.0and a deliberately newerdeepgram/nova-4) and runs the CLI for exit codes.scripts/model-review.test.tsproves the IDs read from the provider files equal whatPROVIDERSin 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):else if (model.expiration_date) {toelse if (model.expiration_date === "never") {(drops the expiration check)model review > reports a curated model past its end dateown.every((curatedModel) => compare(version, curatedModel.version) > 0)toown.every(() => false)(drops the family check)model review > reports a model newer than a curated model of its familyThe workflow itself has not run: GitHub runs
scheduleonly from the default branch, so the first real run needs a manualworkflow_dispatchafter merge tomaster.Live run on 2026-11-14 (
npm run --silent review:models, exit 0, 31 catalog models, every curated model present with no end date):Release impact
None. No plugin, settings, storage, API, or URI change. Conventional type
choredoes not trigger a release.Note
Add weekly transcription model review workflow and CLI
model-reviewCLI (model-review.mjs) that reads curated model IDs from transcription provider sources, compares them to the OpenRouter catalog (fetched live or from a saved file), and reports missing curated models, models past their end date, newer models in curated families, and uncurated candidatesnpm run review:models, writes the report to the step summary, and creates or updates amodel-reviewissue when the report has a curated-model problemMacroscope summarized eb87b1f.
Note
Low Risk
Tooling-only changes with no plugin runtime impact; the workflow only reads the repo and writes/updates a labeled GitHub issue using the default token.
Overview
Adds weekly maintainer tooling to keep curated OpenRouter transcription models in sync with the live catalog—no plugin or runtime changes.
A new
npm run review:modelscommand (scripts/model-review.mjs) scrapes model IDs fromsrc/services/transcription/providers/*.ts, loads the public OpenRouter transcription catalog (or--catalogfor offline runs), and emits a Markdown report for gone/missing curated models, upcoming or past expiration dates, newer models in the same vendor family (including cross-mapping between OpenRouter and direct provider IDs), and uncurated catalog candidates. The process exits with code 1 only when a curated OpenRouter model is missing or already past its end date..github/workflows/model-review.ymlruns that script on Mondays and viaworkflow_dispatch, appends the report to the job summary, and maintains a single openmodel-reviewGitHub issue (update in place, or create only when curated gaps or family upgrades need attention—candidate-only churn does not reopen a closed issue). The job also fails when the script signals a critical curated-model problem. Amodel-reviewconcurrency group prevents duplicate issues.Tests cover comparison logic, CLI exit codes, a catalog fixture, and a guard that file-scanned IDs stay aligned with
PROVIDERSin the registry.AGENTS.mddocuments the command and workflow concurrency behavior.Reviewed by Cursor Bugbot for commit eb87b1f. Bugbot is set up for automated code reviews on this repo. Configure here.