refactor(ai): keep Meta tool schema local

Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>

.changeset/directory-page-heading.md

@@ -1,5 +0,0 @@
----
-"@opencode/core": patch
----
-
-Correct directory page headings when the read offset is zero.

.github/workflows/publish.yml

@@ -24,6 +24,10 @@ on:
         description: "Override version (optional)"
         required: false
         type: string
+      release_notes:
+        description: "Reviewed V2 release notes for the Discord announcement (optional)"
+        required: false
+        type: string
 
 concurrency: ${{ github.workflow }}-${{ github.ref }}-${{ (github.ref_name == 'v2' && (inputs.version || inputs.bump) && 'release') || inputs.version || inputs.bump }}
 
@@ -653,3 +657,19 @@ jobs:
           OPENCODE_DESKTOP_DIST: /tmp/desktop
           CLOUDFLARE_ACCOUNT_ID: 15d29c8639fd3733b1b5486a2acfd968
           CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+
+  notify-discord-v2:
+    needs:
+      - version
+      - publish
+    if: github.repository == 'anomalyco/opencode' && github.ref_name == 'v2' && needs.version.outputs.release && needs.publish.result == 'success'
+    runs-on: blacksmith-4vcpu-ubuntu-2404
+    steps:
+      # Unlike dev, V2 publishes a tag rather than a GitHub Release event.
+      - name: Announce V2 release in Discord
+        uses: SethCohen/github-releases-to-discord@24d166886aee4646d448c8a389ff9e1ebcab3682 # v1.20.0
+        with:
+          webhook_url: ${{ secrets.DISCORD_WEBHOOK }}
+          release_name: OpenCode V2 ${{ needs.version.outputs.tag }}
+          release_body: ${{ inputs.release_notes }}
+          release_html_url: https://github.com/${{ github.repository }}/tree/${{ needs.version.outputs.tag }}

flake.lock

@@ -2,11 +2,11 @@
   "nodes": {
     "nixpkgs": {
       "locked": {
-        "lastModified": 1776683584,
-        "narHash": "sha256-NuTLMrr10Tng72hurYG8jYQ4XKK8wnpJmOGcPiis96g=",
+        "lastModified": 1790510107,
+        "narHash": "sha256-EVMNYv7hYDDD9TGVT/hIyTYgpiXA8y3m5xIEIxuGNU0=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "9dd5558b06dbdacbf635a3dd36dce1b1a7ee3a89",
+        "rev": "3181085bfd08663b6b9e60bc7a8395c2aaa741bd",
         "type": "github"
       },
       "original": {

packages/ai/AGENTS.md

@@ -98,11 +98,11 @@ When a provider supports multiple physical transports, selection remains executi
 
 Media does not fit the SSE-frames-to-event-state-machine LLM route. `MediaRoute.inline(...)` / `queued(...)` / `stream(...)` (`src/route/media.ts`) compose a `MediaProtocol` kind with `Endpoint` and `Auth` and own the transport plumbing: `http` option merging, URL/query rendering, auth headers, JSON vs multipart encoding, and handing the response back to the protocol. `MediaProtocol.inline` (`src/route/media-protocol.ts`) is `body.from(request)` plus `response.decode(response, context)`; each protocol declares `const route = MediaProtocol.identity({ id, name, provider })` once and decodes through `route.decodeJson` / `route.text` / `route.decodeStarted` so decode failures retain the raw body and HTTP context, raising `route.unsupported(operation, message)` for requests it cannot lower, and passes `route` as the first argument to `MediaProtocol.inline` / `queued` / `stream`. `Generation` (`src/generation.ts`) is the provider-neutral handle for a queued generation over a `GenerationRoute` (`status`, `result`, `cancel`). Image protocol files follow the same section order as LLM protocols and declare unsupported common fields once through the protocol's `unsupported` list.
 
-`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.
+`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`; a `failed` generation maps the provider's error code through a per-protocol `FAILURE` table via `MediaProtocol.failure` so rejected inputs are not reported as retryable `ProviderInternal`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.
 
 `MediaProtocol.stream` is the incremental kind every speech route uses, with the same discipline as LLM protocols. `MediaRoute.stream` submits the caller's request as `MediaProtocol.Addressed<Request>` (`{ ...request, mode }`, `mode: "generate" | "stream"`), so one provider stays one protocol: `body.from`, the endpoint path, and `frames` read `request.mode` to pick the body, path, and framing. `frames(bytes, context)` returns frames — `Framing.sse`, `Framing.lines`, `Framing.document` (a single-document response shaped like a streamed record), or the raw `bytes` for chunked audio. `initial()` is fresh per-response parser state; `step` folds each frame into it and emits modality events; `finish(state, context)` runs once after the last frame with the request, body, and observed `http` (header-only usage lives there) and emits exactly one terminal event or fails with `route.incomplete()`. Keep parser state to real accumulators and derive anything the request or body determines in `finish`. `generate` runs the same stream and folds it with the modality's `collect`. Request-derived URL parameters go on the body's `query` (array values repeat the parameter), applied before route and caller `http.query`. Decode frames with `route.decodeFrame` and raise stream-time failures with `route.frameError` (the frame stays on `reason.body`); protocols never thread HTTP context, because the route fills `reason.http` on stream errors that lack it. Speech protocols share `protocols/utils/speech-stream.ts` for deltas, timestamps, voice ids, PCM and container descriptions, and the terminal asset.
 
-Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram is inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
+Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram and ElevenLabs are inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
 
 ### URL Construction
 

packages/ai/README.md

@@ -129,8 +129,9 @@ VercelAIGateway.configure().experimental.evaluation("typesafe-ai/jev")
 
 OpenRouter reads `OPENROUTER_API_KEY`. Vercel reads `AI_GATEWAY_API_KEY`, then `VERCEL_OIDC_TOKEN`.
 The common API uses `boolean`; System One routes lower it to native `noul`.
-Choice and score confidence plus score legends remain available in provider metadata, and the
-provider's rounded probabilities are returned unchanged.
+Choice and score answers include `confidence` when the provider returns it, such as
+`response.answers.department.confidence`. Score legends remain available in provider metadata, and
+the provider's rounded probabilities are returned unchanged.
 
 ## Alibaba Cloud Model Studio
 
@@ -752,7 +753,10 @@ const events = Video.stream({ model: Runway.configure({ apiKey }).video("gen4.5"
 
 Status polls, result fetches, cancels, and asset downloads all run through the same request executor with the route's
 auth. `Generation.await` and `Generation.events` fail with a
-`Timeout` reason when `poll.timeout` (default 10 minutes) elapses. Failed,
+`Timeout` reason when `poll.timeout` (default 10 minutes) elapses. Status polls and result fetches retry transient
+failures (rate limits, provider 5xx, network errors) with backoff that honors `retry-after`, always within
+`poll.timeout`; submits and cancels never retry. Interrupting a wait (or aborting its `signal`) does not cancel the
+provider job, which keeps running and billing: call `cancel()` to stop it. Failed,
 cancelled, and expired generations fail typed with the provider's terminal document on `reason.body`; moderation
 outcomes (Veo `raiMediaFilteredReasons`, xAI `respect_moderation`, Runway `SAFETY.*` codes) surface as `notices` when
 a video is still returned and as a `ContentPolicy` reason when nothing is.
@@ -773,7 +777,9 @@ Provider notes:
 The promise client exposes the same surface: `ai.video.start(...)` resolves to a handle with `await`, `events`,
 `result`, `refresh`, `cancel`, and `token`; `ai.video.generate`, `ai.video.resume(model, token)`, and
 `ai.video.stream` mirror the Effect API. The handle's `status` and `progress` are a snapshot from when it was
-created; `refresh()` resolves to a new handle.
+created; `refresh()` resolves to a new handle. Every promise method and stream accepts `{ signal }`: like `fetch`,
+aborting rejects the Promise or throws from the `for await` loop with `signal.reason` (an `AbortError` `DOMException`
+unless `abort(reason)` passed one), while `break` stops a stream without throwing.
 
 ```ts
 import { ai } from "@opencode/ai/promise"
@@ -871,11 +877,12 @@ for await (const event of ai.speech.stream({ model, text: "Hello from OpenCode."
 ## Transcription
 
 Transcription (speech-to-text) is the one modality whose providers use every route kind: OpenAI and Gemini stream,
-Deepgram answers inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream` work on all of
-them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with `UnsupportedOperation`
-elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`, `Deepgram`, and `AssemblyAI`
-facades. Common fields (`language`, `prompt`, `timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower
-natively or fail with a typed `AIError` before any network call; a route may return more than asked.
+Deepgram and ElevenLabs answer inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream`
+work on all of them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with
+`UnsupportedOperation` elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`,
+`Deepgram`, `ElevenLabs`, and `AssemblyAI` facades. Common fields (`language`, `prompt`,
+`timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower natively or fail with a typed `AIError` before
+any network call; a route may return more than asked.
 
 ```ts
 import { Console, Effect, Stream } from "effect"
@@ -887,7 +894,7 @@ const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY })
 const program = Effect.gen(function* () {
   const audio = yield* Media.file("./call.mp3")
 
-  // Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0").
+  // Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0", "speaker_0").
   const response = yield* Transcription.generate({
     model: Deepgram.configure({ apiKey }).transcription("nova-3"),
     audio,
@@ -897,7 +904,7 @@ const program = Effect.gen(function* () {
   response.text // "Hello from OpenCode."
   response.segments // [{ text, startSeconds, endSeconds, speaker: "0" }]
   response.words // [{ text, startSeconds, endSeconds, speaker, confidence }]
-  response.language // the provider's own value, lowercased ("en", "english", "en_us")
+  response.language // the provider's own value, lowercased ("en", "eng", "english", "en_us")
 
   // Text deltas as the model transcribes, then one finish carrying the whole transcript.
   yield* Transcription.stream({ model: openai.transcription("gpt-4o-mini-transcribe"), audio }).pipe(
@@ -921,7 +928,12 @@ Provider notes:
 - **OpenAI** takes inline audio only; `diarize` needs `gpt-4o-transcribe-diarize`, timestamps need `whisper-1`, and `whisper-1` does not stream.
 - **Gemini** needs a transcribe model (`gemini-3.5-transcribe`); `prompt` and `speakers` fail typed.
 - **Deepgram** detects the language unless `language` is set; vocabulary goes in `providerOptions.keyterm`.
-- **AssemblyAI** uploads inline audio before submitting and is the only route that accepts `speakers`.
+- **ElevenLabs** (`scribe_v2`) uploads inline audio as the multipart `file` and sends a URL as `source_url`. Words
+  always carry timestamps, and segments are speaker turns, so `diarize`, `timestamps: "segment"`, or `speakers` turns
+  on diarization. `speakers` is an upper bound (`num_speakers`); `prompt` fails typed (vocabulary goes in
+  `providerOptions.keyterms`), as do webhook delivery and per-channel output (`use_multi_channel` without
+  `multichannel_output_style: "combined"`).
+- **AssemblyAI** uploads inline audio before submitting and treats `speakers` as the exact speaker count.
 
 The promise client mirrors the Effect API:
 

packages/ai/docs/media-design.md

@@ -1,7 +1,6 @@
 # Media generation in `@opencode/ai` — public API direction
 
-Status: phases 1–4 implemented (through Image queued routes and partial images; ElevenLabs Scribe transcription
-pending); phase 5 proposal.
+Status: phases 1–4 implemented (through Image queued routes and partial images); phase 5 proposal.
 
 ## Goal
 
@@ -271,8 +270,8 @@ Deferred: `Speech.session(...)` — input-streaming TTS where text arrives incre
 #### Transcription (STT)
 
 Shipped as the second half of phase 3 (`src/transcription.ts`, `src/transcription-client.ts`, protocols
-`openai-transcription`, `google-transcription`, `deepgram-transcription`, `assemblyai-transcription`; new `AssemblyAI`
-facade).
+`openai-transcription`, `google-transcription`, `deepgram-transcription`, `elevenlabs-transcription`,
+`assemblyai-transcription`; new `AssemblyAI` facade).
 
 ```ts
 const request = Transcription.request({
@@ -281,7 +280,7 @@ const request = Transcription.request({
   language: "en",                                  // provider-native passthrough
   timestamps: "segment",                           // none | segment | word
   diarize: true,
-  speakers: 2,                                     // exact speaker count (AssemblyAI only)
+  speakers: 2,                                     // speaker count (AssemblyAI exact, ElevenLabs maximum)
   providerOptions: { known_speaker_names: ["agent"] },
 })
 
@@ -309,17 +308,23 @@ upload); `packages/ai/AGENTS.md` (Media Routes) describes both.
 Settled rules:
 
 - **Timestamps.** A granularity the selected route or model cannot produce fails as `UnsupportedOperation`
-  (`media.timestamps`), following Speech; a route that returns more than asked (Deepgram and AssemblyAI always return
-  words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
+  (`media.timestamps`), following Speech; a route that returns more than asked (Deepgram, ElevenLabs, and AssemblyAI
+  always return words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
   word offsets, so segment timestamps and diarization also request word offsets there.
 - **Diarization.** `diarize` means segments (and words, where the provider labels them) carry `speaker`. Labels are
-  provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A` — with no
-  cross-provider speaker model. `speakers` is the exact number of speakers to label, which AssemblyAI (`speakers_expected`, the only route that
-  accepts it) treats as a constraint rather than a hint.
+  provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A`,
+  ElevenLabs `speaker_0` — with no cross-provider speaker model. `speakers` is the number of speakers to label:
+  AssemblyAI (`speakers_expected`) treats it as an exact constraint rather than a hint, and ElevenLabs
+  (`num_speakers`) as the maximum. Both turn on diarization for it; the other routes reject it.
+- **Segments from words.** ElevenLabs returns only a token list (`word`, `spacing`, `audio_event`), so its segments
+  are speaker turns: consecutive words and spacing with one `speaker_id`, text joined from the provider's own spacing
+  tokens. `words` drops spacing and audio events. Segments therefore need diarization, which `timestamps: "segment"`
+  turns on, as AssemblyAI's utterances need speaker labels.
 - **Language** is passed through (`language`, OpenAI `gpt-transcribe` `languages[]`, Gemini `languageCodes`,
-  AssemblyAI `language_code`). `response.language` is the provider's own value, lowercased but not normalized: an
-  ISO code on most routes (AssemblyAI's detection returns `en`), `english` from whisper-1. Deepgram and AssemblyAI
-  assume English unless asked to detect, so a missing `language` enables their detection.
+  AssemblyAI and ElevenLabs `language_code`). `response.language` is the provider's own value, lowercased but not
+  normalized: an ISO code on most routes (AssemblyAI's detection returns `en`, ElevenLabs ISO 639-3 `eng`), `english`
+  from whisper-1. Deepgram and AssemblyAI assume English unless asked to detect, so a missing `language` enables their
+  detection.
 - **Gemini** requires a transcribe model; other model ids fail with `UnsupportedOperation` before the call, because
   general models ignore `audioTranscriptionConfig` and answer conversationally. Streamed chunks carry whole speaker
   turns (one part per turn), which join with a space.
@@ -332,11 +337,12 @@ Settled rules:
 | OpenAI | stream (`stream: true` in `stream` mode; `whisper-1` ignores `stream`, so it emits only `finish`) | multipart `file` (inline only) | `whisper-1` (`verbose_json`); diarize model: `segment` | `gpt-4o-transcribe-diarize` (`diarized_json`) | `speakers`; `prompt` on the diarize model | `tokens` or `seconds` |
 | Gemini | stream (`generateContent` / `streamGenerateContent`) | `inlineData` or Gemini Files `fileData` | `audioTranscriptionConfig.wordTimestamp` | `audioTranscriptionConfig.diarization` | `prompt`, `speakers` | `tokens` |
 | Deepgram | inline | raw body, or JSON `{ url }` | words always; `segment` → `utterances` | `diarize_model=latest` + `utterances` | `prompt`, `speakers` | `seconds` (`metadata.duration`) |
+| ElevenLabs | inline | multipart `file`, or `source_url` | words always; `segment` → `diarize` (speaker turns) | `diarize` | `prompt`; `webhook`, per-channel `use_multi_channel` | `seconds` (`audio_duration_secs`) |
 | AssemblyAI | queued (upload → submit → poll) | `/v2/upload` then `audio_url`, or a URL | words always; `segment` → `speaker_labels` | `speaker_labels` | — | `seconds` (`audio_duration`) |
 
 Deferred: `Transcription.session(...)` — realtime STT over WebSocket (Deepgram live, AssemblyAI streaming, ElevenLabs
 realtime, OpenAI realtime transcription) — is the same future scoped `session` shape as input-streaming TTS and ships
-with the realtime work in phase 5. ElevenLabs Scribe is not implemented yet.
+with the realtime work in phase 5.
 
 ### `Generation` — shared async execution
 
@@ -361,6 +367,10 @@ Poll = { interval?: Duration; timeout?: Duration }
 
 `Generation` is not video-specific. Image routes on BFL, fal, Replicate, and Stability `upscale()` are queued; `Image.start` exists for them. A route declares itself `inline` or `queued`; `generate` on a queued route is `start` then `await`.
 
+Status polls and result reads retry transient failures (rate limits, provider 5xx, and transport errors, classified by the same `isRetryable` the Session runner uses) inside `MediaRoute.queued`. Only the HTTP exchange retries, never the decoded document: a terminal `failed` generation also surfaces as `ProviderInternal` and must not be re-read. Gaps grow exponentially from 1s with jitter, up to 30s each, honoring a provider `retry-after` up to that cap, for at most 8 retries. `await`, `events`, and `Video.stream` cut retries off at `poll.timeout` and fail with `Timeout`, so retries never extend the caller's deadline; a direct `result()` or `resume` read is bounded by the retry cap alone. `start` and `cancel` never retry: a repeated submit can start and bill a second job. The policy is internal; there is no option for it.
+
+Interrupting `await`, `events`, or `Video.stream` (or aborting the promise API's `signal`) stops waiting only. The provider job keeps running and billing; call `cancel()` explicitly to stop it.
+
 ### Usage
 
 ```ts
@@ -402,7 +412,7 @@ for await (const event of ai.llm.stream(request)) { … }
 await ai.dispose()
 ```
 
-Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown as-is. `AbortSignal` maps to interruption. Nothing in `src/*` except this entrypoint knows about promises.
+Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown as-is. Aborting an `AbortSignal` interrupts the work and, like `fetch`, rejects the Promise or throws from the stream with `signal.reason` instead of ending the stream as if complete. Nothing in `src/*` except this entrypoint knows about promises.
 
 ### Providers
 
@@ -414,7 +424,7 @@ implemented):
 | `OpenAI` | responses (default), chat | Images API (stream) | *Sora skipped (decision 8)* | ✓ | ✓ | |
 | `Google` | Gemini | Gemini-native | Veo | Gemini TTS | `gemini-3.5-transcribe` | |
 | `XAI` | ✓ | ✓ | ✓ | | | |
-| `ElevenLabs` | | | | ✓ | *Scribe (pending)* | *soundEffect, music (phase 5)* |
+| `ElevenLabs` | | | | ✓ | Scribe | *soundEffect, music (phase 5)* |
 | `Cartesia` | | | | ✓ | | |
 | `Deepgram` | | | | Aura | ✓ | |
 | `Fal` | | ✓ (queued) | ✓ | | | |
@@ -467,7 +477,7 @@ Foundation + Image ship together as the reference implementation, serially. Vide
 
 1. **Foundation** — per-modality selectors, `Media`, `Generation`, `Poll`, `Usage` union, `MediaProtocol` kinds, `@opencode/ai/promise` with `llm` + `image`. Port the five existing image protocols onto it. Unify `MediaPart` and add the `media` LLM event (fixes Gemini image output being dropped).
 2. **Video** — ✅ Veo, xAI, fal, Runway shipped (`MediaProtocol.queued`, `Video.start/generate/resume/stream`, promise `ai.video`). Deferred: `Video.complete` (webhooks), Luma, Kling, MiniMax, Replicate.
-3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Pending: ElevenLabs Scribe. Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
+3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, ElevenLabs Scribe, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
 4. **Image queued routes and partials** — ✅ BFL, fal, Replicate, and Stability creative upscale queued; Stability generate inline; OpenAI `partial_images` streaming (`image-partial` restored). Imagen dropped: shut down on the Gemini API and discontinued on Vertex (2026-06-30). Deferred: Stability's synchronous edit and fast/conservative upscale endpoints.
 5. **Later** — ElevenLabs music/SFX, Lyria, `Speech.session` / `Transcription.session`, realtime.
 

packages/ai/src/cache-policy.ts

@@ -38,8 +38,15 @@ const resolve = (policy: CachePolicy | undefined): CachePolicyObject => {
 // prefix caching, Gemini's implicit + out-of-band CachedContent). Skip the
 // whole policy pass for these — emitting hints would be harmless but pointless.
 const RESPECTS_INLINE_HINTS = new Set([
+  "alibaba-messages",
   "anthropic-messages",
+  "anthropic-compatible-messages",
+  "cloudflare-ai-gateway-messages",
   "google-vertex-messages",
+  "meta-messages",
+  "minimax-messages",
+  "moonshot-messages",
+  "zai-coding-messages",
   "bedrock-converse",
   "openrouter",
 ])

packages/ai/src/experimental/evaluation.ts

@@ -63,6 +63,7 @@ export const ChoiceAnswer = Schema.Struct({
   type: Schema.Literal("choice"),
   choice: Schema.String,
   probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ChoiceAnswer = Schema.Schema.Type<typeof ChoiceAnswer>
 
@@ -70,6 +71,7 @@ export const ScoreAnswer = Schema.Struct({
   type: Schema.Literal("score"),
   score: Schema.Number,
   probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ScoreAnswer = Schema.Schema.Type<typeof ScoreAnswer>
 
@@ -92,6 +94,7 @@ export type AnswerFor<Question extends EvaluationQuestion> = Question extends {
       readonly type: "choice"
       readonly choice: Extract<keyof Criteria, string>
       readonly probabilities?: Readonly<Record<Extract<keyof Criteria, string>, number>>
+      readonly confidence?: number
     }
   : Question extends { readonly type: "score" }
     ? ScoreAnswer

packages/ai/src/experimental/system-one.ts

@@ -142,32 +142,37 @@ export const model = <Options extends EvaluationOptions = EvaluationOptions>(cfg
             Effect.mapError((cause) => fail("System One returned an invalid response", cause, text)),
           )
 
-          const confidence: Record<string, number> = {}
           const legend: Record<string, Record<string, Schema.Json>> = {}
           const answers = Object.fromEntries(
             Object.entries(data.answers).map(([id, answer]): [string, EvaluationAnswer] => {
               if (answer.type === "noul") return [id, { type: "boolean", probability: answer.noul }]
               if (answer.type === "choice") {
-                if (answer.confidence !== undefined) confidence[id] = answer.confidence
                 return [
                   id,
                   {
                     type: "choice",
                     choice: answer.choice,
                     probabilities: answer.probabilities,
+                    ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
                   },
                 ]
               }
-              if (answer.confidence !== undefined) confidence[id] = answer.confidence
               if (answer.legend !== undefined) legend[id] = answer.legend
-              return [id, { type: "score", score: answer.score, probabilities: answer.probabilities }]
+              return [
+                id,
+                {
+                  type: "score",
+                  score: answer.score,
+                  probabilities: answer.probabilities,
+                  ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
+                },
+              ]
             }),
           )
           const meta = {
             ...(data.id === undefined ? {} : { responseId: data.id }),
             ...(data.provider === undefined ? {} : { provider: data.provider }),
             ...data.provider_metadata?.[cfg.providerMetadataKey],
-            ...(Object.keys(confidence).length === 0 ? {} : { confidence }),
             ...(Object.keys(legend).length === 0 ? {} : { legend }),
           }
           return new EvaluationResponse({

packages/ai/src/generation.ts

@@ -102,7 +102,7 @@ export class Generation<Response> {
     return settled.pipe(
       // Non-completed terminal states also go through `result` so the route can surface its provider failure body.
       Effect.flatMap((generation) => generation.result()),
-      Effect.timeoutOrElse({ duration: timeout, orElse: () => this.timeoutError(timeout) }),
+      Effect.timeoutOrElse({ duration: timeout, orElse: () => timeoutError(this.id, timeout) }),
     )
   }
 
@@ -123,20 +123,7 @@ export class Generation<Response> {
       Clock.currentTimeMillis.pipe(
         Effect.map((start) => {
           const deadline = start + Duration.toMillis(timeout)
-          // Fail before polling once the deadline has passed: a fast status request could otherwise win the zero-budget
-          // race and schedule another zero-delay poll.
-          const refresh = Clock.currentTimeMillis.pipe(
-            Effect.flatMap((now) =>
-              now >= deadline
-                ? this.timeoutError(timeout)
-                : this.refresh().pipe(
-                    Effect.timeoutOrElse({
-                      duration: Duration.millis(deadline - now),
-                      orElse: () => this.timeoutError(timeout),
-                    }),
-                  ),
-            ),
-          )
+          const refresh = within(this.refresh(), this.id, timeout, deadline)
           const schedule = this.schedule(options?.poll).pipe(
             Schedule.modifyDelay((meta) =>
               Effect.succeed(Duration.min(meta.duration, Duration.millis(Math.max(0, deadline - meta.now)))),
@@ -157,15 +144,6 @@ export class Generation<Response> {
     return { type: "generation-progress", id: this.id, progress: this.progress }
   }
 
-  private timeoutError(timeout: Duration.Duration) {
-    return new AIError({
-      reason: new TimeoutError({
-        message: `Generation ${this.id} did not finish within ${Duration.format(timeout)}`,
-        timeoutMs: Duration.toMillis(timeout),
-      }),
-    })
-  }
-
   private poll(poll: Poll | undefined) {
     return this.refresh().pipe(
       Effect.repeat({ schedule: this.schedule(poll), until: (generation) => generation.terminal }),
@@ -177,12 +155,53 @@ export class Generation<Response> {
   }
 }
 
+/** `events` followed by the expanded result, with the result fetch bounded by the same `poll.timeout` deadline. */
 export const resultEvents = <Response, A>(
   generation: Generation<Response>,
   expand: (response: Response) => ReadonlyArray<A>,
   options?: AwaitOptions,
-): Stream.Stream<Observation | A, AIError> =>
-  generation.events(options).pipe(
-    Stream.filter((event): event is Observation => event.type !== "generation-finished"),
-    Stream.concat(Stream.fromIterableEffect(Effect.map(generation.result(), expand))),
+): Stream.Stream<Observation | A, AIError> => {
+  const timeout = Duration.fromInputUnsafe(options?.poll?.timeout ?? DEFAULT_POLL_TIMEOUT)
+  return Stream.unwrap(
+    Clock.currentTimeMillis.pipe(
+      Effect.map((start) =>
+        generation.events(options).pipe(
+          Stream.filter((event): event is Observation => event.type !== "generation-finished"),
+          Stream.concat(
+            Stream.fromIterableEffect(
+              within(generation.result(), generation.id, timeout, start + Duration.toMillis(timeout)).pipe(
+                Effect.map(expand),
+              ),
+            ),
+          ),
+        ),
+      ),
+    ),
   )
+}
+
+/**
+ * Run `effect` within the time left until `deadline`. Fails before starting once the deadline has passed: a fast
+ * request could otherwise win the zero-budget race and schedule another zero-delay poll.
+ */
+const within = <A>(effect: Effect.Effect<A, AIError>, id: string, timeout: Duration.Duration, deadline: number) =>
+  Clock.currentTimeMillis.pipe(
+    Effect.flatMap((now) =>
+      now >= deadline
+        ? Effect.fail(timeoutError(id, timeout))
+        : effect.pipe(
+            Effect.timeoutOrElse({
+              duration: Duration.millis(deadline - now),
+              orElse: () => Effect.fail(timeoutError(id, timeout)),
+            }),
+          ),
+    ),
+  )
+
+const timeoutError = (id: string, timeout: Duration.Duration) =>
+  new AIError({
+    reason: new TimeoutError({
+      message: `Generation ${id} did not finish within ${Duration.format(timeout)}`,
+      timeoutMs: Duration.toMillis(timeout),
+    }),
+  })

packages/ai/src/index.ts

@@ -4,7 +4,7 @@ export { ImageClient } from "./image-client.js"
 export { Auth } from "./route/auth.js"
 export { Provider } from "./provider.js"
 export { ProviderPackage } from "./provider-package.js"
-export { isContextOverflow, isContextOverflowFailure } from "./provider-error.js"
+export { isContextOverflow, isContextOverflowFailure, isRetryable } from "./provider-error.js"
 export type {
   RouteLanguageModelInput,
   RouteRoutedLanguageModelInput,

packages/ai/src/promise.ts

@@ -42,7 +42,7 @@ export type GenerationHandle<Response> = Snapshot & {
   /** Serializable JSON; pass it back to `resume` from another process. */
   readonly token: unknown
   readonly await: (options?: AwaitOptions & RunOptions) => Promise<Response>
-  /** Status observations until the first terminal one, polling like `await`; abort ends iteration without throwing. */
+  /** Status observations until the first terminal one, polling like `await`; abort throws `signal.reason`. */
   readonly events: (options?: AwaitOptions & RunOptions) => AsyncIterable<Event>
   /** The result without polling; fails when the generation has not completed. */
   readonly result: (options?: RunOptions) => Promise<Response>
@@ -50,15 +50,16 @@ export type GenerationHandle<Response> = Snapshot & {
   readonly cancel: (options?: RunOptions) => Promise<void>
 }
 
+// Fails with `signal.reason` so aborted calls reject and aborted streams throw like `fetch`: an `AbortError` by default.
 const abortEffect = (signal: AbortSignal | undefined) =>
   signal === undefined
     ? Effect.never
-    : Effect.callback<void>((resume) => {
+    : Effect.callback<never, unknown>((resume) => {
         if (signal.aborted) {
-          resume(Effect.void)
+          resume(Effect.fail(signal.reason))
           return
         }
-        const onAbort = () => resume(Effect.void)
+        const onAbort = () => resume(Effect.fail(signal.reason))
         signal.addEventListener("abort", onAbort, { once: true })
         return Effect.sync(() => signal.removeEventListener("abort", onAbort))
       })
@@ -68,14 +69,14 @@ export const make = (options: Options = {}) => {
 
   /** Run any package Effect (for example `LLMClient.compact(...)`) inside this runtime. */
   const run = <A, E>(effect: Effect.Effect<A, E, Services>, options?: RunOptions) =>
-    runtime.runPromise(effect, { signal: options?.signal })
+    runtime.runPromise(Effect.raceFirst(effect, abortEffect(options?.signal)))
 
   const iterate = <A, E>(stream: Stream.Stream<A, E, Services>, options?: RunOptions): AsyncIterable<A> =>
     Stream.toAsyncIterable(
       Stream.unwrap(
         runtime.contextEffect.pipe(
           Effect.map(
-            (context): Stream.Stream<A, E> =>
+            (context): Stream.Stream<A, unknown> =>
               stream.pipe(Stream.interruptWhen(abortEffect(options?.signal)), Stream.provideContext(context)),
           ),
         ),

packages/ai/src/protocols/deepgram-transcription.ts

@@ -6,6 +6,7 @@ import { mergeJsonRecords, type OpenString } from "../schema/index.js"
 import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
 import { ProviderShared } from "./shared.js"
 import { MediaInput } from "./utils/media-input.js"
+import { SpeakerTurns } from "./utils/speaker-turns.js"
 
 const route = MediaProtocol.identity({ id: "deepgram-transcription", name: "Deepgram", provider: "deepgram" })
 export const DEFAULT_BASE_URL = "https://api.deepgram.com"
@@ -115,16 +116,6 @@ const speaker = (value: number | undefined) => (value === undefined ? undefined
 
 const wordText = (word: typeof Word.Type) => word.punctuated_word ?? word.word
 
-// Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when its
-// words change speaker, so segments split each utterance at speaker changes.
-const speakerTurns = (words: ReadonlyArray<typeof Word.Type>) =>
-  words.reduce<Array<Array<typeof Word.Type>>>((turns, word) => {
-    const last = turns.at(-1)
-    if (last === undefined || last[0].speaker !== word.speaker) return [...turns, [word]]
-    last.push(word)
-    return turns
-  }, [])
-
 const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(function* (
   response: HttpClientResponse.HttpClientResponse,
 ) {
@@ -136,6 +127,8 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
   const requestID = output.value.metadata?.request_id
   return new TranscriptionResponse({
     text: alternative.transcript,
+    // Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when
+    // its words change speaker, so segments split each utterance at speaker changes.
     segments: output.value.results.utterances?.flatMap((utterance) =>
       utterance.words === undefined || utterance.words.length === 0
         ? [
@@ -146,7 +139,7 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
               speaker: speaker(utterance.speaker),
             },
           ]
-        : speakerTurns(utterance.words).map((turn) => ({
+        : SpeakerTurns.group(utterance.words, (word) => word.speaker).map((turn) => ({
             text: turn.map(wordText).join(" "),
             startSeconds: turn[0].start,
             endSeconds: turn[turn.length - 1].end,

packages/ai/src/protocols/elevenlabs-transcription.ts

@@ -0,0 +1,211 @@
+import { Effect, Schema } from "effect"
+import type { HttpClientResponse } from "effect/unstable/http"
+import { MediaProtocol } from "../route/media-protocol.js"
+import { MediaRoute } from "../route/media.js"
+import { mergeJsonRecords, type OpenString } from "../schema/index.js"
+import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
+import { mediaTypeExtension } from "../utils/media-type.js"
+import { ProviderShared, optionalNull } from "./shared.js"
+import { MediaInput } from "./utils/media-input.js"
+import { SpeakerTurns } from "./utils/speaker-turns.js"
+
+const route = MediaProtocol.identity({
+  id: "elevenlabs-transcription",
+  name: "ElevenLabs Transcription",
+  provider: "elevenlabs",
+})
+export const DEFAULT_BASE_URL = "https://api.elevenlabs.io"
+export const PATH = "/v1/speech-to-text"
+
+// ---------------------------------------------------------------------------
+// 1. Public model input
+// ---------------------------------------------------------------------------
+
+export type ElevenLabsTranscriptionOptions = {
+  readonly tag_audio_events?: boolean
+  readonly timestamps_granularity?: OpenString<"none" | "word" | "character">
+  readonly diarization_threshold?: number
+  readonly file_format?: OpenString<"pcm_s16le_16" | "other">
+  readonly temperature?: number
+  readonly seed?: number
+  readonly keyterms?: ReadonlyArray<string>
+  readonly no_verbatim?: boolean
+  readonly detect_speaker_roles?: boolean
+  readonly use_speaker_library?: boolean
+  readonly entity_detection?: string | ReadonlyArray<string>
+  readonly entity_redaction?: string | ReadonlyArray<string>
+  readonly entity_redaction_mode?: OpenString<"redacted" | "entity_type" | "enumerated_entity_type">
+} & Record<string, unknown>
+
+export type Request = TranscriptionRequestFor<ElevenLabsTranscriptionOptions>
+
+// ---------------------------------------------------------------------------
+// 2. Response schema
+// ---------------------------------------------------------------------------
+
+/** `type` is `word`, `spacing` (the whitespace between words), or `audio_event` (`(laughter)`). */
+const Token = Schema.Struct({
+  text: Schema.String,
+  type: Schema.String,
+  start: optionalNull(Schema.Number),
+  end: optionalNull(Schema.Number),
+  speaker_id: optionalNull(Schema.String),
+  logprob: optionalNull(Schema.Number),
+})
+type Token = Schema.Schema.Type<typeof Token>
+
+const Transcript = Schema.Struct({
+  language_code: optionalNull(Schema.String),
+  text: Schema.String,
+  words: optionalNull(Schema.Array(Token)),
+  transcription_id: optionalNull(Schema.String),
+  audio_duration_secs: optionalNull(Schema.Number),
+})
+
+// ---------------------------------------------------------------------------
+// 5. Request body construction
+// ---------------------------------------------------------------------------
+
+/** Speaker turns are the only segments ElevenLabs can produce, and `num_speakers` only applies to diarization. */
+const diarizes = (request: Request) =>
+  request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
+
+const RESERVED_FORM_FIELDS = new Set([
+  "file",
+  "cloud_storage_url",
+  "source_url",
+  "model_id",
+  "language_code",
+  "diarize",
+  "num_speakers",
+])
+
+const validate = (request: Request, overlay: Record<string, unknown>) => {
+  // Webhook requests return 202 with no transcript; the result arrives at a configured webhook instead.
+  if (overlay.webhook === true)
+    return Effect.fail(route.unsupported("transcription.webhook", `${route.name} does not deliver to webhooks`))
+  // Separate multichannel output replaces the transcript with one transcript per channel.
+  if (overlay.use_multi_channel === true && overlay.multichannel_output_style !== "combined")
+    return Effect.fail(
+      route.unsupported(
+        "transcription.multichannel",
+        `${route.name} returns a single transcript; set multichannel_output_style: "combined" to merge channels`,
+      ),
+    )
+  if (overlay.timestamps_granularity === "none" && (request.timestamps === "word" || diarizes(request)))
+    return Effect.fail(
+      route.unsupported(
+        "media.timestamps",
+        `${route.name} cannot return word timestamps or speaker turns with timestamps_granularity: "none"`,
+      ),
+    )
+  return Effect.void
+}
+
+const fromRequest = Effect.fn("ElevenLabsTranscription.fromRequest")(function* (request: Request) {
+  const overlay = mergeJsonRecords(request.providerOptions, request.http?.body) ?? {}
+  yield* validate(request, overlay)
+  const form = new FormData()
+  const url = ProviderShared.mediaUrl(request.audio)
+  if (url === undefined) {
+    const extension = mediaTypeExtension(request.audio.mediaType)
+    const audio = yield* MediaInput.inlineBytes(route.id, request.audio)
+    form.append(
+      "file",
+      MediaInput.blob(audio, request.audio.mediaType),
+      extension === undefined ? "audio" : `audio.${extension}`,
+    )
+  }
+  MediaInput.appendFields(
+    form,
+    {
+      model_id: request.model.id,
+      // `cloud_storage_url` is deprecated in favor of `source_url`, which accepts any hosted audio or video URL.
+      source_url: url,
+      language_code: request.language,
+      diarize: diarizes(request) ? true : undefined,
+      num_speakers: request.speakers,
+    },
+    { overlay, reserved: RESERVED_FORM_FIELDS, repeatArrays: "key" },
+  )
+  return MediaProtocol.multipart(form)
+})
+
+// ---------------------------------------------------------------------------
+// 6. Response decoding
+// ---------------------------------------------------------------------------
+
+const decodeTranscript = route.decodeJson(Transcript)
+
+type TimedWord = Token & { readonly start: number; readonly end: number }
+
+const isTimedWord = (token: Token): token is TimedWord =>
+  token.type === "word" && typeof token.start === "number" && typeof token.end === "number"
+
+/** Turn text keeps the provider's own spacing tokens, so languages written without spaces are not re-spaced. */
+const speakerTurns = (tokens: ReadonlyArray<Token>) =>
+  SpeakerTurns.group(
+    tokens.filter((token) => token.type === "word" || token.type === "spacing"),
+    (token) => token.speaker_id,
+  ).flatMap((turn) => {
+    const words = turn.filter(isTimedWord)
+    if (words.length === 0) return []
+    return [
+      {
+        text: turn
+          .map((token) => token.text)
+          .join("")
+          .trim(),
+        startSeconds: words[0].start,
+        endSeconds: words[words.length - 1].end,
+        speaker: turn[0].speaker_id ?? undefined,
+      },
+    ]
+  })
+
+const decodeResponse = Effect.fn("ElevenLabsTranscription.decodeResponse")(function* (
+  response: HttpClientResponse.HttpClientResponse,
+  context: MediaProtocol.DecodeContext<Request>,
+) {
+  const output = yield* decodeTranscript(response)
+  const transcript = output.value
+  const tokens = transcript.words ?? []
+  const duration = transcript.audio_duration_secs ?? undefined
+  const transcriptionID = transcript.transcription_id ?? undefined
+  return new TranscriptionResponse({
+    text: transcript.text,
+    segments: diarizes(context.request) ? speakerTurns(tokens) : undefined,
+    words: tokens.filter(isTimedWord).map((word) => ({
+      text: word.text,
+      startSeconds: word.start,
+      endSeconds: word.end,
+      speaker: word.speaker_id ?? undefined,
+      confidence: typeof word.logprob === "number" ? Math.exp(word.logprob) : undefined,
+    })),
+    language: transcript.language_code?.toLowerCase(),
+    durationSeconds: duration,
+    usage: duration === undefined ? undefined : { type: "seconds", seconds: duration },
+    providerMetadata: transcriptionID === undefined ? undefined : { elevenlabs: { transcriptionId: transcriptionID } },
+  })
+})
+
+// ---------------------------------------------------------------------------
+// 7. Protocol and route
+// ---------------------------------------------------------------------------
+
+export const protocol = MediaProtocol.inline<Request, TranscriptionResponse>(route, {
+  unsupported: ["prompt"],
+  body: { from: fromRequest },
+  response: { decode: decodeResponse },
+})
+
+export const model = (input: MediaRoute.ModelInput) =>
+  TranscriptionModel.fromRoute<ElevenLabsTranscriptionOptions>(
+    { protocol, baseURL: DEFAULT_BASE_URL, path: PATH },
+    input,
+  )
+
+export const ElevenLabsTranscription = {
+  protocol,
+  model,
+} as const

packages/ai/src/protocols/google-video.ts

@@ -36,7 +36,9 @@ const StartResponse = Schema.Struct({ name: Schema.String })
 
 const Operation = Schema.Struct({
   done: Schema.optional(Schema.Boolean),
-  error: Schema.optional(Schema.Struct({ message: Schema.optional(Schema.String) })),
+  error: Schema.optional(
+    Schema.Struct({ code: Schema.optional(Schema.Number), message: Schema.optional(Schema.String) }),
+  ),
   response: Schema.optional(
     Schema.Struct({
       generateVideoResponse: Schema.optional(
@@ -60,6 +62,16 @@ const Operation = Schema.Struct({
   metadata: Schema.optional(Schema.Unknown),
 })
 
+// Operation errors are `google.rpc.Status`; unlisted codes (INTERNAL, UNAVAILABLE, ...) are provider-side.
+const FAILURE = {
+  3: "InvalidRequest", // INVALID_ARGUMENT
+  7: "Authentication", // PERMISSION_DENIED
+  8: "RateLimit", // RESOURCE_EXHAUSTED
+  9: "InvalidRequest", // FAILED_PRECONDITION
+  11: "InvalidRequest", // OUT_OF_RANGE
+  16: "Authentication", // UNAUTHENTICATED
+} as const satisfies Record<number, MediaProtocol.Failure>
+
 // ---------------------------------------------------------------------------
 // 5. Request body construction
 // ---------------------------------------------------------------------------
@@ -154,6 +166,7 @@ const decodeResult = Effect.fn("GoogleVideo.decodeResult")(function* (
     return yield* output.ended(
       "failed",
       `${route.name} operation failed${operation.error?.message === undefined ? "" : `: ${operation.error.message}`}`,
+      MediaProtocol.failure(FAILURE, operation.error?.code),
     )
   const generated = operation.response?.generateVideoResponse
   // Downloads require the same API key as the poll; the asset carries it transiently and follows the redirect.

packages/ai/src/protocols/meta-messages.ts

@@ -10,14 +10,15 @@ const WebSearch = Schema.Struct({
   name: Schema.Literal("web_search"),
   user_location: MetaResponses.WebSearch.fields.user_location,
 })
+const FunctionTool = Schema.Struct({
+  name: Schema.String,
+  description: Schema.String,
+  input_schema: JsonObject,
+  cache_control: AnthropicMessages.AnthropicMessagesBody.fields.cache_control,
+})
 const Body = Schema.Struct({
   ...AnthropicMessages.AnthropicMessagesBody.fields,
-  tools: optionalArray(
-    Schema.Union([
-      Schema.Struct({ name: Schema.String, description: Schema.String, input_schema: JsonObject }),
-      WebSearch,
-    ]),
-  ),
+  tools: optionalArray(Schema.Union([FunctionTool, WebSearch])),
 })
 
 const fromRequest = Effect.fn("MetaMessages.fromRequest")(function* (request: LLMRequest) {

packages/ai/src/protocols/openai-chat.ts

@@ -64,6 +64,14 @@ const OpenAIChatTool = Schema.Struct({
 })
 type OpenAIChatTool = Schema.Schema.Type<typeof OpenAIChatTool>
 
+// Gemini's OpenAI-compatible surface carries thought signatures in tool call
+// `extra_content` and rejects replayed parallel calls without them:
+// https://ai.google.dev/gemini-api/docs/thinking#signatures
+const ExtraContent = Schema.Struct({
+  google: Schema.Struct({ thought_signature: Schema.String }),
+})
+const decodeExtraContent = (value: unknown) => Option.getOrUndefined(Schema.decodeUnknownOption(ExtraContent)(value))
+
 const OpenAIChatAssistantToolCall = Schema.Struct({
   id: Schema.String,
   type: Schema.tag("function"),
@@ -71,6 +79,7 @@ const OpenAIChatAssistantToolCall = Schema.Struct({
     name: Schema.String,
     arguments: Schema.String,
   }),
+  extra_content: Schema.optional(ExtraContent),
 })
 type OpenAIChatAssistantToolCall = Schema.Schema.Type<typeof OpenAIChatAssistantToolCall>
 
@@ -112,12 +121,6 @@ const decodeReasoningDetail = Schema.decodeUnknownOption(ReasoningDetail)
 const knownReasoningDetails = (details: ReadonlyArray<unknown>) =>
   details.flatMap((detail) => Option.toArray(decodeReasoningDetail(detail)))
 
-// Intentionally omit Gemini's provider-specific `extra_content.google.thought_signature`
-// extension until direct Google OpenAI-compatible routing is supported here:
-// https://github.com/vercel/ai/issues/11590
-// https://github.com/vercel/ai/pull/11745
-// https://ai.google.dev/gemini-api/docs/thought-signatures#openai
-
 const OpenAIChatUserContent = Schema.Union([
   Schema.Struct({
     type: Schema.Literal("text"),
@@ -242,6 +245,7 @@ const OpenAIChatToolCallDelta = Schema.Struct({
   index: optionalNull(Schema.Number),
   id: optionalNull(Schema.String),
   function: optionalNull(OpenAIChatToolCallDeltaFunction),
+  extra_content: optionalNull(Schema.Unknown),
 })
 type OpenAIChatToolCallDelta = Schema.Schema.Type<typeof OpenAIChatToolCallDelta>
 
@@ -294,6 +298,7 @@ interface PendingToolDelta {
   readonly id?: string
   readonly name?: string
   readonly input: string
+  readonly extraContent?: Schema.Schema.Type<typeof ExtraContent>
 }
 
 export interface ParserState {
@@ -347,13 +352,17 @@ const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
     tool: (name) => ({ type: "function" as const, function: { name } }),
   })
 
-const lowerToolCall = (part: ToolCallPart, options: LoweringOptions): OpenAIChatAssistantToolCall => ({
+const lowerToolCall = (
+  part: ToolCallPart,
+  options: LoweringOptions & { readonly providerMetadataKey: string },
+): OpenAIChatAssistantToolCall => ({
   id: options.toolCallID?.(part.id) ?? part.id,
   type: "function",
   function: {
     name: part.name,
     arguments: ProviderShared.encodeJson(part.input === undefined ? {} : part.input),
   },
+  extra_content: decodeExtraContent(part.providerMetadata?.[options.providerMetadataKey]?.extraContent),
 })
 
 const lowerMedia = Effect.fn("OpenAIChat.lowerMedia")(function* (part: MediaPart) {
@@ -721,7 +730,9 @@ const detectSupportsStore = (provider: string, baseURL: string | undefined): boo
     p === "vercel-ai-gateway" || url.includes("ai-gateway.vercel.sh") || url.includes("vercel.sh")
   const isAntLing = p === "ant-ling" || url.includes("api.ant-ling.com")
   const isOpencode = p === "opencode" || url.includes("opencode.ai")
+  const isGemini = url.includes("generativelanguage.googleapis.com")
   const isNonStandard =
+    isGemini ||
     isNvidia ||
     isCerebras ||
     isXai ||
@@ -1114,12 +1125,13 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
       const id = current?.id ?? pending?.id ?? (tool.id || undefined)
       const name = current?.name ?? pending?.name ?? (tool.function?.name || undefined)
       const text = `${pending?.input ?? ""}${tool.function?.arguments ?? ""}`
+      const extraContent = pending?.extraContent ?? decodeExtraContent(tool.extra_content)
       latestToolIndex = index
       nextToolIndex = Math.max(nextToolIndex, index + 1)
       if (!current && (!id || !name)) {
         pendingTools = {
           ...pendingTools,
-          [index]: { id: id || undefined, name: name || undefined, input: text },
+          [index]: { id: id || undefined, name: name || undefined, input: text, extraContent },
         }
         continue
       }
@@ -1131,7 +1143,12 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
         ADAPTER,
         tools,
         index,
-        { id: id || undefined, name: name || undefined, text },
+        {
+          id: id || undefined,
+          name: name || undefined,
+          text,
+          providerMetadata: extraContent && { [state.providerMetadataKey]: { extraContent } },
+        },
         "OpenAI Chat tool call delta is missing id or name",
       )
       if (ToolStream.isError(result))

packages/ai/src/protocols/openai-transcription.ts

@@ -193,7 +193,7 @@ const fromRequest = Effect.fn("OpenAITranscription.fromRequest")(function* (requ
     {
       overlay: mergeJsonRecords(request.providerOptions, request.http?.body),
       reserved: RESERVED_FORM_FIELDS,
-      repeatArrays: true,
+      repeatArrays: "key[]",
     },
   )
   return MediaProtocol.multipart(form)

packages/ai/src/protocols/runway-video.ts

@@ -137,7 +137,12 @@ const decodeResult = Effect.fn("RunwayVideo.decodeResult")(function* (
     const message = `${route.name} task failed${code === undefined ? "" : ` (${code})`}${task.failure ? `: ${task.failure}` : ""}`
     // Runway failure codes are dotted paths; every moderation outcome carries a SAFETY segment.
     if (code !== undefined && /(^|\.)SAFETY(\.|$)/.test(code)) return yield* output.contentPolicy(message)
-    return yield* output.ended("failed", message)
+    // ASSET.INVALID rejects the caller's input media; Runway documents it as not retryable.
+    return yield* output.ended(
+      "failed",
+      message,
+      code !== undefined && /^ASSET\.INVALID(\.|$)/.test(code) ? "InvalidRequest" : "ProviderInternal",
+    )
   }
   if (status === "cancelled")
     return yield* output.ended("cancelled", `${route.name} task ${context.token.taskID} was cancelled`)

packages/ai/src/protocols/utils/media-input.ts

@@ -71,8 +71,9 @@ export const imageOutput = (
 }
 
 /**
- * Append multipart text fields: strings as-is, other values as JSON, or arrays as repeated `key[]` parts with
- * `repeatArrays`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace route-owned fields.
+ * Append multipart text fields: strings as-is, other values as JSON, or scalar arrays as one part per item with
+ * `repeatArrays`, named `key[]` or `key`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace
+ * route-owned fields.
  */
 export const appendFields = (
   form: FormData,
@@ -80,13 +81,13 @@ export const appendFields = (
   options: {
     readonly overlay?: Record<string, unknown>
     readonly reserved: ReadonlySet<string>
-    readonly repeatArrays?: true
+    readonly repeatArrays?: "key[]" | "key"
   },
 ) => {
   const overlay = Object.entries(options.overlay ?? {}).filter(([key]) => !options.reserved.has(key))
   Object.entries(mergeJsonRecords(fields, Object.fromEntries(overlay)) ?? {}).forEach(([key, value]) => {
-    if (Array.isArray(value) && options.repeatArrays)
-      return value.forEach((item) => form.append(`${key}[]`, String(item)))
+    if (Array.isArray(value) && value.every(isScalar) && options.repeatArrays !== undefined)
+      return value.forEach((item) => form.append(options.repeatArrays === "key[]" ? `${key}[]` : key, String(item)))
     form.append(key, typeof value === "string" ? value : encodeJson(value))
   })
 }

packages/ai/src/protocols/utils/speaker-turns.ts

@@ -0,0 +1,10 @@
+/** Split an ordered token list into runs of consecutive tokens with the same speaker. */
+export const group = <Item>(items: ReadonlyArray<Item>, speaker: (item: Item) => unknown) =>
+  items.reduce<Array<Array<Item>>>((turns, item) => {
+    const last = turns.at(-1)
+    if (last === undefined || speaker(last[0]) !== speaker(item)) return [...turns, [item]]
+    last.push(item)
+    return turns
+  }, [])
+
+export * as SpeakerTurns from "./speaker-turns.js"

packages/ai/src/protocols/utils/tool-stream.ts

@@ -147,7 +147,12 @@ export const appendOrStart = <K extends StreamKey>(
   route: string,
   tools: State<K>,
   key: K,
-  delta: { readonly id?: string; readonly name?: string; readonly text: string },
+  delta: {
+    readonly id?: string
+    readonly name?: string
+    readonly text: string
+    readonly providerMetadata?: ProviderMetadata
+  },
   missingToolMessage: string,
 ): AppendOutcome<K> | AIError => {
   const current = tools[key]
@@ -161,7 +166,7 @@ export const appendOrStart = <K extends StreamKey>(
     namespace: current?.namespace,
     input: `${current?.input ?? ""}${delta.text}`,
     providerExecuted: current?.providerExecuted,
-    providerMetadata: current?.providerMetadata,
+    providerMetadata: current?.providerMetadata ?? delta.providerMetadata,
   }
   if (current && delta.text.length === 0 && current.id === id && current.name === name)
     return { tools, tool: current, events: [] }

packages/ai/src/protocols/xai-video.ts

@@ -65,6 +65,13 @@ const STATUS = {
   expired: "expired",
 } as const satisfies Record<string, Status>
 
+// Documented video error codes; `service_unavailable`, `internal_error`, and unknown codes are provider-side.
+const FAILURE = {
+  invalid_argument: "InvalidRequest",
+  failed_precondition: "InvalidRequest",
+  permission_denied: "Authentication",
+} as const satisfies Record<string, MediaProtocol.Failure>
+
 // ---------------------------------------------------------------------------
 // 5. Request body construction
 // ---------------------------------------------------------------------------
@@ -143,6 +150,7 @@ const decodeResult = Effect.fn("XAIVideo.decodeResult")(function* (
     return yield* output.ended(
       "failed",
       `${route.name} generation failed${code === undefined ? "" : ` (${code})`}${message === undefined ? "" : `: ${message}`}`,
+      MediaProtocol.failure(FAILURE, code),
     )
   }
   if (status !== "completed")

packages/ai/src/provider-error.ts

@@ -58,6 +58,47 @@ export const isContextOverflowFailure = (failure: unknown) =>
     ? failure.reason._tag === "InvalidRequest" && failure.reason.classification === "context-overflow"
     : Schema.is(ProviderErrorEvent)(failure) && failure.classification === "context-overflow"
 
+/**
+ * Whether a failed call may succeed when sent again: rate limits, provider-side failures, transport failures that did
+ * not deliver an accepted write, and unrecognized failures. Callers decide which calls are safe to repeat.
+ */
+export const isRetryable = (error: AIError) => {
+  const override = error.reason.http?.headers["x-should-retry"]
+  if (override === "true") return true
+  if (override === "false") return false
+  switch (error.reason._tag) {
+    case "RateLimit":
+    case "ProviderInternal":
+      return true
+    // A WebSocket acknowledgment marks delivery accepted before model output may exist.
+    // Read failures can still recover; the caller chooses retry versus continuation from durable output.
+    case "Transport":
+      return (
+        error.reason.delivery !== "rejected" &&
+        (error.reason.delivery !== "accepted" || error.reason.operation === "read")
+      )
+    case "InvalidProviderOutput":
+      return error.reason.classification === "incomplete-stream"
+    // Unrecognized failures retry: classification records affirmative
+    // deterministic evidence, and transient failures are exactly the ones
+    // that arrive in shapes no classifier anticipates.
+    case "UnknownProvider":
+      return true
+    case "Authentication":
+    case "QuotaExceeded":
+    case "ContentPolicy":
+    case "InvalidRequest":
+    case "UnsupportedOperation":
+    case "NoRoute":
+    case "Timeout":
+      return false
+    default: {
+      const exhaustive: never = error.reason
+      return exhaustive
+    }
+  }
+}
+
 const decodeJson = Schema.decodeUnknownOption(Schema.fromJsonString(Schema.Unknown))
 // OpenCode Zen reports account caps as typed 429/402 errors that are not throttles.
 const QUOTA_CODES = new Set([
@@ -68,7 +109,8 @@ const QUOTA_CODES = new Set([
   "freeusagelimiterror",
   "creditlimitexceeded",
 ])
-const AUTH_CODES = new Set(["authentication_error", "permission_error"])
+// Google reports an invalid API key as HTTP 400 INVALID_ARGUMENT with this `details[].reason`.
+const AUTH_CODES = new Set(["authentication_error", "permission_error", "api_key_invalid"])
 const SERVER_CODES = new Set([
   "api_error",
   "internal_error",
@@ -218,6 +260,10 @@ function providerCodes(value: unknown) {
     error?.type,
     error?.status,
     error?.error_type,
+    // Google `google.rpc.ErrorInfo` details carry the specific reason.
+    ...(Array.isArray(error?.details)
+      ? error.details.map((detail) => (isRecord(detail) ? detail.reason : undefined))
+      : []),
     inner?.code,
     metadata?.error_type,
     responseError?.code,

packages/ai/src/providers/anthropic-compatible.ts

@@ -28,7 +28,8 @@ export type Settings = ProviderPackage.Settings &
     readonly provider?: string
   }
 
-export const routes = [AnthropicMessages.route]
+const compatibleRoute = AnthropicMessages.route.with({ id: "anthropic-compatible-messages", provider: id })
+export const routes = [compatibleRoute]
 
 const auth = (input: ProviderAuthOption<"optional">) => {
   if ("auth" in input && input.auth) return input.auth
@@ -43,7 +44,7 @@ export const configure = (input: Config) => {
       message: "Anthropic-compatible providers require a baseURL",
     })
   const { provider: _, baseURL, apiKey: _apiKey, auth: _auth, ...rest } = input
-  const route = AnthropicMessages.route.with({
+  const route = (provider === "anthropic" ? AnthropicMessages.route : compatibleRoute).with({
     ...rest,
     provider,
     endpoint: { baseURL },

packages/ai/src/providers/elevenlabs.ts

@@ -3,8 +3,10 @@ import type { ProviderAuthOption } from "../route/auth-options.js"
 import { MediaRoute } from "../route/media.js"
 import { type HttpOptions, ProviderID, type ModelID } from "../schema/index.js"
 import { ElevenLabsSpeech } from "../protocols/elevenlabs-speech.js"
+import { ElevenLabsTranscription } from "../protocols/elevenlabs-transcription.js"
 
 export type { ElevenLabsOutputFormat, ElevenLabsSpeechOptions } from "../protocols/elevenlabs-speech.js"
+export type { ElevenLabsTranscriptionOptions } from "../protocols/elevenlabs-transcription.js"
 
 export const id = ProviderID.make("elevenlabs")
 
@@ -24,12 +26,15 @@ const auth = (options: ProviderAuthOption<"optional">) => {
 export const configure = (input: Config = {}) => {
   const media = MediaRoute.deployment(input, auth(input))
   const speech = (modelID: string | ModelID) => ElevenLabsSpeech.model({ ...media, id: modelID })
+  const transcription = (modelID: string | ModelID) => ElevenLabsTranscription.model({ ...media, id: modelID })
   return {
     id,
     speech,
+    transcription,
     configure,
   }
 }
 
 export const provider = configure()
 export const speech = provider.speech
+export const transcription = provider.transcription

packages/ai/src/providers/xai.ts

@@ -35,13 +35,13 @@ const RESPONSES_WEBSOCKET_ROTATE_AFTER_MS = 24 * 60 * 1000
 
 const responsesRoute = Route.make({
   compact: { endpoint: XAIResponses.compact },
-  id: "openai-responses",
+  id: "xai-responses",
   provider: id,
   providerMetadataKey: "xai",
   protocol: XAIResponses.protocol,
   endpoint: Endpoint.path("/responses", { baseURL }),
   transport: OpenResponsesChannel.transport({
-    id: "openai-responses",
+    id: "xai-responses",
     name: "xAI Responses",
     rotateAfterMs: RESPONSES_WEBSOCKET_ROTATE_AFTER_MS,
     // xAI continues a chain only from stored responses: with `store: false` (the route default) `previous_response_id`
@@ -53,7 +53,7 @@ const responsesRoute = Route.make({
 })
 
 const chatRoute = Route.make({
-  id: "openai-compatible-chat",
+  id: "xai-chat",
   provider: id,
   providerMetadataKey: "xai",
   protocol: OpenAIChat.protocol,

packages/ai/src/route/media-protocol.ts

@@ -5,12 +5,14 @@ import { Media } from "../media.js"
 import type { AuthInput } from "./auth.js"
 import {
   AIError,
+  AuthenticationError,
   ContentPolicyError,
   HttpContext,
   InvalidProviderOutputError,
   InvalidRequestError,
   ProviderID,
   ProviderInternalError,
+  RateLimitError,
   UnsupportedOperationError,
 } from "../schema/index.js"
 
@@ -188,6 +190,16 @@ export const stream = <Request, Event, Frame, State>(
 // Response helpers
 // ---------------------------------------------------------------------------
 
+/** Reasons a provider can report for a `failed` generation; anything it does not classify is `ProviderInternal`. */
+const FAILURES = {
+  InvalidRequest: InvalidRequestError,
+  Authentication: AuthenticationError,
+  RateLimit: RateLimitError,
+  ProviderInternal: ProviderInternalError,
+}
+
+export type Failure = keyof typeof FAILURES
+
 const context = (response: HttpClientResponse.HttpClientResponse) =>
   new HttpContext({ url: response.request.url, status: response.status, headers: response.headers })
 
@@ -199,9 +211,10 @@ export const identity = (input: { readonly id: string; readonly name: string; re
 
   /**
    * Read a text body while retaining the original payload and HTTP context on every downstream error. `invalid` is a
-   * malformed provider document; `ended` is a generation that reached a terminal status without output (`failed` is
-   * provider-side, `cancelled`/`expired` mean the result will never exist); `pending` is a `result()` read before the
-   * generation finished, which is caller misuse; `contentPolicy` is a moderated result.
+   * malformed provider document; `ended` is a generation that reached a terminal status without output (`failed`
+   * carries the provider's classification, defaulting to `ProviderInternal`; `cancelled`/`expired` mean the result
+   * will never exist); `pending` is a `result()` read before the generation finished, which is caller misuse;
+   * `contentPolicy` is a moderated result.
    */
   const text = Effect.fn("MediaProtocol.text")(function* (response: HttpClientResponse.HttpClientResponse) {
     const http = context(response)
@@ -223,11 +236,15 @@ export const identity = (input: { readonly id: string; readonly name: string; re
       http,
       invalid: (message: string, cause?: unknown) =>
         new AIError({ reason: new InvalidProviderOutputError({ route: input.id, message, body, http, cause }) }),
-      ended: (status: Exclude<Status, "queued" | "running" | "completed">, message: string) =>
+      ended: (
+        status: Exclude<Status, "queued" | "running" | "completed">,
+        message: string,
+        failure: Failure = "ProviderInternal",
+      ) =>
         new AIError({
           reason:
             status === "failed"
-              ? new ProviderInternalError({ message, body, http })
+              ? new FAILURES[failure]({ message, body, http })
               : new InvalidRequestError({ message, body, http }),
         }),
       pending: (id: string) =>
@@ -303,6 +320,10 @@ export const status = <Table extends Record<string, Status>>(
   return Effect.succeed(table[raw])
 }
 
+/** Map a provider error code through the protocol's table; missing or unmapped codes are `ProviderInternal`. */
+export const failure = (table: Readonly<Record<string, Failure>>, code: string | number | undefined): Failure =>
+  code !== undefined && Object.hasOwn(table, code) ? table[code] : "ProviderInternal"
+
 /** A `url` asset whose provider-declared retention window starts now. */
 export const expiringUrl = (url: string, retention: Duration.Duration, options?: Parameters<typeof Media.url>[1]) =>
   Clock.currentTimeMillis.pipe(

packages/ai/src/route/media.ts

@@ -1,4 +1,4 @@
-import { Effect, Schema, Stream } from "effect"
+import { Duration, Effect, Schedule, Schema, Stream } from "effect"
 import { Headers, HttpClientRequest, type HttpClientResponse } from "effect/unstable/http"
 import { Auth, type AuthInput } from "./auth.js"
 import { Endpoint } from "./endpoint.js"
@@ -7,6 +7,7 @@ import { RequestExecutor } from "./executor.js"
 import { MediaProtocol } from "./media-protocol.js"
 import { Generation, isTerminal } from "../generation.js"
 import type { Media } from "../media.js"
+import { isRetryable } from "../provider-error.js"
 import {
   AIError,
   AIErrorReason,
@@ -137,6 +138,32 @@ export const inline = <Request extends MediaRequest, Response>(
   }
 }
 
+const READ_RETRY_MAX_DELAY = Duration.seconds(30)
+
+/**
+ * Status and result reads retry transient failures; `start` and `cancel` never do. Gaps grow exponentially from 1s,
+ * jittered, up to 30s each, for at most 8 retries (about two minutes when every attempt fails), so a direct
+ * `Generation.result()` stays bounded; `await` and `events` also cut retries off at `poll.timeout`. A provider
+ * `retryAfterMs` raises the gap, still capped at 30s.
+ */
+const READ_RETRY = Schedule.max([
+  Schedule.min([Schedule.exponential("1 second"), Schedule.spaced(READ_RETRY_MAX_DELAY)]),
+  Schedule.recurs(8),
+]).pipe(
+  Schedule.jittered,
+  Schedule.setInputType<AIError>(),
+  Schedule.modifyDelay(({ input, duration }) =>
+    Effect.succeed(
+      Duration.min(
+        input.reason._tag === "RateLimit" || input.reason._tag === "ProviderInternal"
+          ? Duration.max(duration, Duration.millis(input.reason.retryAfterMs ?? 0))
+          : duration,
+        READ_RETRY_MAX_DELAY,
+      ),
+    ),
+  ),
+)
+
 /**
  * Compose a queued media protocol the same way, adding `start`/`resume` handles whose polls reuse the route's auth,
  * deployment headers, and (for `start`) the request's `http` overlay. The token is decoded once at the boundary and
@@ -154,6 +181,8 @@ export const queued = <Request extends MediaRequest, Response, Token>(
   const generationRoute = (token: Token, http: HttpOptions | undefined, execute: Execute) => {
     const materialize = (asset: Media.Asset) =>
       asset.materialize().pipe(Effect.provideService(RequestExecutorService, { execute }))
+    // Only the GET exchange retries: a decoded terminal failure (`output.ended`) can be a `ProviderInternal` too, and
+    // re-reading it would spin until the caller's deadline.
     const poll = <A>(operation: {
       readonly path: (token: Token) => string
       readonly decode: (
@@ -161,9 +190,10 @@ export const queued = <Request extends MediaRequest, Response, Token>(
         context: MediaProtocol.PollContext<Token>,
       ) => Effect.Effect<A, AIError>
     }) =>
-      transport
-        .call("GET", operation.path(token), http, execute)
-        .pipe(Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })))
+      transport.call("GET", operation.path(token), http, execute).pipe(
+        Effect.retry({ schedule: READ_RETRY, while: isRetryable }),
+        Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })),
+      )
     const status = poll(protocol.status)
     const cancel = protocol.cancel
     const send =

packages/ai/src/transcription.ts

@@ -103,7 +103,7 @@ export type TranscriptionRequestInput<Model extends TranscriptionModel = Transcr
 // Response and events
 // ---------------------------------------------------------------------------
 
-/** Speaker labels are provider-native (`A`, `0`, `spk:0`, or a known speaker name). */
+/** Speaker labels are provider-native (`A`, `0`, `spk:0`, `speaker_0`, or a known speaker name). */
 export const TranscriptionSegment = Schema.Struct({
   text: Schema.String,
   startSeconds: Schema.Number,

packages/ai/test/cache-policy.test.ts

@@ -3,7 +3,17 @@ import { Effect } from "effect"
 import { CacheHint, LLM, Message } from "../src/index.js"
 import { Auth } from "../src/route.js"
 import { compileRequest } from "../src/route/client.js"
-import { AmazonBedrock, GoogleVertexMessages } from "../src/providers.js"
+import {
+  Alibaba,
+  AmazonBedrock,
+  AnthropicCompatible,
+  CloudflareAIGateway,
+  GoogleVertexMessages,
+  Meta,
+  MiniMax,
+  Moonshot,
+  ZAICodingPlan,
+} from "../src/providers.js"
 import * as AnthropicMessages from "../src/protocols/anthropic-messages.js"
 import * as Gemini from "../src/protocols/gemini.js"
 import * as OpenAIChat from "../src/protocols/openai-chat.js"
@@ -107,6 +117,54 @@ describe("applyCachePolicy", () => {
     }),
   )
 
+  it.effect("'auto' emits Anthropic cache markers on Anthropic-compatible routes", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model: AnthropicCompatible.configure({ apiKey: "test", baseURL: "https://messages.example.test/v1" }).model(
+            "compatible",
+          ),
+          system: "You are concise.",
+          prompt: "hi",
+        }),
+      )
+
+      expect(prepared.route).toBe("anthropic-compatible-messages")
+      expect(prepared.body).toMatchObject({
+        system: [{ type: "text", text: "You are concise.", cache_control: { type: "ephemeral" } }],
+        messages: [{ role: "user", content: [{ type: "text", text: "hi", cache_control: { type: "ephemeral" } }] }],
+      })
+    }),
+  )
+
+  const messagesModels = [
+    ["alibaba-messages", Alibaba.configure({ region: "ap-southeast-1", apiKey: "test" }).messages("qwen3.8-max")],
+    [
+      "cloudflare-ai-gateway-messages",
+      CloudflareAIGateway.configure({ accountId: "test", gatewayId: "test", apiKey: "test" }).model(
+        "anthropic/claude-sonnet-4-6",
+      ),
+    ],
+    ["meta-messages", Meta.configure({ apiKey: "test" }).messages("muse-spark-1.3")],
+    ["minimax-messages", MiniMax.configure({ apiKey: "test" }).model("MiniMax-M3")],
+    ["moonshot-messages", Moonshot.configure({ apiKey: "test" }).messages("kimi-k3")],
+    ["zai-coding-messages", ZAICodingPlan.configure({ apiKey: "test" }).messages("glm-5.3")],
+  ] as const
+
+  messagesModels.forEach(([route, model]) =>
+    it.effect(`'auto' emits cache markers on ${route}`, () =>
+      Effect.gen(function* () {
+        const prepared = yield* compileRequest(LLM.request({ model, system: "Sys", prompt: "hi" }))
+
+        expect(prepared.route).toBe(route)
+        expect(prepared.body).toMatchObject({
+          system: [{ type: "text", text: "Sys", cache_control: { type: "ephemeral" } }],
+          messages: [{ role: "user", content: [{ type: "text", text: "hi", cache_control: { type: "ephemeral" } }] }],
+        })
+      }),
+    ),
+  )
+
   it.effect("'auto' is a no-op on OpenAI (implicit caching protocol)", () =>
     Effect.gen(function* () {
       const prepared = yield* compileRequest(

packages/ai/test/evaluation.test.ts

@@ -39,17 +39,18 @@ describe("experimental Evaluation", () => {
         type: "choice",
         choice: "billing",
         probabilities: { billing: 0.9, technical: 0.1 },
+        confidence: 0.8,
       })
       expect(response.answers.urgency).toEqual({
         type: "score",
         score: 1.2,
         probabilities: { "0": 0, "1": 0.8, "2": 0.2 },
+        confidence: 0.6,
       })
       expect(response.answers.refund).toEqual({ type: "boolean", probability: 0.97 })
       expect(response.usage?.totalTokens).toBe(36)
       expect(response.providerMetadata).toEqual({
         typesafe: {
-          confidence: { department: 0.8, urgency: 0.6 },
           legend: { urgency: { "0": "Can wait", "1": "Needs attention", "2": "Blocking" } },
         },
       })

packages/ai/test/evaluation.types.ts

@@ -26,8 +26,10 @@ const request = Evaluation.request({
 const result = EvaluationClient.evaluate(request)
 type Result = Success<typeof result>
 type Choice = Assert<Equal<Result["answers"]["topic"]["choice"], "billing" | "support">>
+type Confidence = Assert<Equal<Result["answers"]["topic"]["confidence"], number | undefined>>
 type ClientRequirements = Assert<Equal<Requirements<typeof result>, Service>>
 void (true satisfies Choice)
+void (true satisfies Confidence)
 void (true satisfies ClientRequirements)
 
 Effect.gen(function* () {

packages/ai/test/exports.test.ts

@@ -154,8 +154,8 @@ describe("public exports", () => {
     expect(XAI.model).toBeFunction()
     expect(XAI.provider.responses).toBe(XAI.responses)
     expect(XAI.provider.chat).toBe(XAI.chat)
-    expect(XAI.configure({ apiKey: "fixture" }).responses("grok-4.3").route.id).toBe("openai-responses")
-    expect(XAI.configure({ apiKey: "fixture" }).chat("grok-4.3").route.id).toBe("openai-compatible-chat")
+    expect(XAI.configure({ apiKey: "fixture" }).responses("grok-4.3").route.id).toBe("xai-responses")
+    expect(XAI.configure({ apiKey: "fixture" }).chat("grok-4.3").route.id).toBe("xai-chat")
     expect(OpenAI.configure({ apiKey: "fixture" }).image("gpt-image-2").route.id).toBe("openai-images")
     expect(OpenAI.provider.image).toBe(OpenAI.image)
     expect(Google.configure({ apiKey: "fixture" }).image("imagen-4.0-generate-001").route.id).toBe("google-images")
@@ -197,6 +197,11 @@ describe("public exports", () => {
     expect(Google.configure({ apiKey: "fixture" }).transcription("gemini-3.5-transcribe").route.kind).toBe("stream")
     expect(Deepgram.configure({ apiKey: "fixture" }).transcription("nova-3").route.kind).toBe("inline")
     expect(AssemblyAI.configure({ apiKey: "fixture" }).transcription("universal-3-5-pro").route.kind).toBe("queued")
+    expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.id).toBe(
+      "elevenlabs-transcription",
+    )
+    expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.kind).toBe("inline")
+    expect(ElevenLabs.provider.transcription).toBe(ElevenLabs.transcription)
   })
 
   test("protocol barrels expose supported low-level routes", () => {

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-7-plus-streams-thinking-disabled.json

@@ -21,7 +21,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
+        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-7-plus-streams-thinking-enabled.json

@@ -21,7 +21,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"enabled\",\"budget_tokens\":1024}}"
+        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"enabled\",\"budget_tokens\":1024}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-follows-a-json-schema.json

@@ -20,7 +20,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object with one key \\\"city\\\" set to the capital city of France.\"}]}],\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"disabled\"},\"output_config\":{\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object with one key \\\"city\\\" set to the capital city of France.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"disabled\"},\"output_config\":{\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-obeys-named-tool-choice.json

@@ -21,7 +21,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Find the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"]}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Find the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"]},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-replays-reasoning-through-a-tool-loop-and-follow-up.json

@@ -23,7 +23,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"We have a budget of 38000 dollars for 219 trips costing 173 dollars each. Calculate whether that is affordable. If it is, use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"We have a budget of 38000 dollars for 219 trips costing 173 dollars each. Calculate whether that is affordable. If it is, use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
       },
       "response": {
         "status": 200,
@@ -41,7 +41,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"We have a budget of 38000 dollars for 219 trips costing 173 dollars each. Calculate whether that is affordable. If it is, use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"I need to investigate this further. Let me check the details.\\n\\n219 × 173 = 37,887. Budget is 38,000. Since 37,887 ≤ 38,000, it can be covered. Call get_weather for Paris.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"We have a budget of 38000 dollars for 219 trips costing 173 dollars each. Calculate whether that is affordable. If it is, use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"I need to investigate this further. Let me check the details.\\n\\n219 × 173 = 37,887. Budget is 38,000. Since 37,887 ≤ 38,000, it can be covered. Call get_weather for Paris.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
       },
       "response": {
         "status": 200,
@@ -59,7 +59,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"We have a budget of 38000 dollars for 219 trips costing 173 dollars each. Calculate whether that is affordable. If it is, use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"I need to investigate this further. Let me check the details.\\n\\n219 × 173 = 37,887. Budget is 38,000. Since 37,887 ≤ 38,000, it can be covered. Call get_weather for Paris.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"Wait, I should have calculated it first, but the call was made anyway. Calculation: 219 × 173 = 37,887 ≤ 38,000, so it can be covered. I'll report the weather briefly.\",\"signature\":\"\"},{\"type\":\"text\",\"text\":\"Yes, it's affordable: 219 trips × $173 = $37,887, which fits within the $38,000 budget (leaving $113 to spare).\\n\\nIt's currently sunny in Paris at 18°C.\"}]},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What temperature did the tool report? Reply with only the temperature.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"We have a budget of 38000 dollars for 219 trips costing 173 dollars each. Calculate whether that is affordable. If it is, use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"I need to investigate this further. Let me check the details.\\n\\n219 × 173 = 37,887. Budget is 38,000. Since 37,887 ≤ 38,000, it can be covered. Call get_weather for Paris.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"toolu_5d1ba8ca72bd49889ca838f2\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"Wait, I should have calculated it first, but the call was made anyway. Calculation: 219 × 173 = 37,887 ≤ 38,000, so it can be covered. I'll report the weather briefly.\",\"signature\":\"\"},{\"type\":\"text\",\"text\":\"Yes, it's affordable: 219 trips × $173 = $37,887, which fits within the $38,000 budget (leaving $113 to spare).\\n\\nIt's currently sunny in Paris at 18°C.\"}]},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What temperature did the tool report? Reply with only the temperature.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-streams-default-effort.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-streams-high-effort.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"high\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"high\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-streams-low-effort.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-streams-max-effort.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"max\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"max\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-streams-medium-effort.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"medium\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/alibaba-messages/qwen-3-8-max-streams-xhigh-effort.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"xhigh\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"xhigh\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/elevenlabs-transcription/groups-diarized-words-into-speaker-turns.json

@@ -0,0 +1,32 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:elevenlabs-transcription",
+      "provider:elevenlabs",
+      "protocol:elevenlabs-transcription"
+    ],
+    "name": "elevenlabs-transcription/groups-diarized-words-into-speaker-turns",
+    "recordedAt": "2026-09-27T09:35:28.265Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundary356bdc14864a477dbacbfcf60d1ecceb"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.9495430588722229,\"text\":\"Did the release ship? Yes, it shipped this morning\",\"words\":[{\"text\":\"Did\",\"start\":0.34,\"end\":0.44,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.7881377516459906e-6},{\"text\":\" \",\"start\":0.44,\"end\":0.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\"the\",\"start\":0.48,\"end\":0.56,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\" \",\"start\":0.56,\"end\":0.6,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\"release\",\"start\":0.6,\"end\":0.92,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\" \",\"start\":0.92,\"end\":0.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-8.344646857949556e-7},{\"text\":\"ship?\",\"start\":0.94,\"end\":1.26,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.414704032271402e-6},{\"text\":\" \",\"start\":1.26,\"end\":1.26,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-0.0009363081189803779},{\"text\":\"Yes,\",\"start\":1.68,\"end\":2.02,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.003542040009030245},{\"text\":\" \",\"start\":2.02,\"end\":2.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\"it\",\"start\":2.48,\"end\":2.62,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\" \",\"start\":2.62,\"end\":2.64,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\"shipped\",\"start\":2.66,\"end\":2.9,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\" \",\"start\":2.9,\"end\":2.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\"this\",\"start\":2.94,\"end\":3.12,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\" \",\"start\":3.12,\"end\":3.18,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7},{\"text\":\"morning\",\"start\":3.18,\"end\":3.5,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7}],\"transcription_id\":\"cs3I2282TH8hjw12brNg\",\"audio_duration_secs\":3.5526875}"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/elevenlabs-transcription/transcribes-audio-with-word-timestamps.json

@@ -0,0 +1,50 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:elevenlabs-transcription",
+      "provider:elevenlabs",
+      "protocol:elevenlabs-transcription"
+    ],
+    "name": "elevenlabs-transcription/transcribes-audio-with-word-timestamps",
+    "recordedAt": "2026-09-27T09:35:27.686Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundarye2be7b31e94441bbbeb35a9c890a9d74"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000014781842764932662},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-3.814689989667386e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-3.814689989667386e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.018268775194883347},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1251817401498556}],\"transcription_id\":\"D4VfnANM2ArCHTujIb9q\",\"audio_duration_secs\":1.54125}"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundaryfb80d0e44d9e44d299416ed546a04056"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000023007127310847864},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-2.3841830625315197e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-2.3841830625315197e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.008306833915412426},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1075385226868093}],\"transcription_id\":\"SkYplzfq1DW8Ae3bWnoy\",\"audio_duration_secs\":1.54125}"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/meta-messages/replays-encrypted-thinking-through-a-tool-loop.json

@@ -2,9 +2,16 @@
   "version": 1,
   "metadata": {
     "model": "muse-spark-1.3",
-    "tags": ["prefix:meta-messages", "provider:meta", "protocol:meta-messages", "tool", "tool-loop", "reasoning"],
+    "tags": [
+      "prefix:meta-messages",
+      "provider:meta",
+      "protocol:meta-messages",
+      "tool",
+      "tool-loop",
+      "reasoning"
+    ],
     "name": "meta-messages/replays-encrypted-thinking-through-a-tool-loop",
-    "recordedAt": "2026-09-07T17:27:03.540Z"
+    "recordedAt": "2026-09-29T01:28:54.992Z"
   },
   "interactions": [
     {
@@ -15,14 +22,14 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\"}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,
         "headers": {
           "content-type": "text/event-stream"
         },
-        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6a9ef3e5a96d9a155dd4463b\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgGyJ4hIKk41uslnSV0PGvrTkwJ5D-t5skfjtkIt-ABXsehMcLKJJ8RJHRKW2-XhkpPrex0aOkIdqWl99vpCgtOHIFFaSc4b3oGxA8XDx4T_2aKANfYrR1DYwYzGe6ZZ-DQnU0bnpVUzCcXkghkLdyTcJr2p8cvVo1rymFpB0wZsbQRBhxCMR6PrY4i0aOTe8_waq_Po1a4l3YzKnzZIIvYP090o5kltv7MAwqChXjQeTJlKq7ECFa6HVeoTa43oiLmoD2Bzih0VfvBvQfbSh2uDypRM7-f65sp35-VuZfwsM33ZTvefzDbd8zd0D50I6wcybsj8gulDhWWpY7cxoN1Xasy-ImvisACGeppIN66maIFq5dMT2s8_CQ8a2EQ0hw9kwJaIiygZCdRofs-T1yaGWvnQxL6MpNh6SXux9T1ZfuexNrXOhz5cR3_s1euhq3-hI3GDCUDLAtkjiigSE3w6PExrwHTHnvkuAOTP0Lw7DH4NtKv-RFFeZaQOk_0Bi2EV43tR0Hq_chtEDiSpoezDjexPWfdZvhRIaO6PwyJaQ8jVOaLUr6bh6jQ3IM19lv6R7lY4Neno8fLxMwTbf7v7q02lfhOaZe3jR1fqOFUq8e4VXV76_rJBgzThqPNqO8OI_betgX5d2KMcwWAkaZjmrP3rxA7g5xp_Q7bkFiBaaTd3HbYIk_cKbtLOS6TIIphb4SX6ADA2qJ0zoo98P2NOceZODT2WrLjKCHl5dT6b9l2feH9m21pW576ULfKhVSMzuy0cmmWI7rv2P4q-2Fw2klsDVJAc6q22bFjfDgzhybKuhuM_p1SYb8aswNrgggV-cqHWDpF1FdVpL5fHMO74l1uD8Sj_9wuuD0asMQustuvsnYq2EdI0lLvONFMApWCU0s3QA8_P0Iyf0YoCZOm5QGnA7l3O5nAPkFF4kxLSsgRe9zuP6A4oKBDLN8EHwZ3pB4WZGWpUT12cJxplmT3_n8xKaMgaz13qs27uvUm3wMI1seyfpkMwUPHmt1ftpk9f_1OAg3fvQgIkWPTp6K9NzVzEry6SP7zbPfls8yn529Qrbki7ZM_oz3xEvDg367ZCe97eVnjiqRrYsYM2MmDsQq9lUwkgXb84kpK6a4pEzX9NDvhTqhw7RI6RL9E-2Ki4ciUfHv5LVTZ0rNweCo6SYXC11f8FCeObIW_Esr2mqYpORFS4SDMU-4I1HQfD9z6cPjL22APpv9a7Pp1phI8x_aQZkPU7LkyBWyVNDeusI7wq_LC0UgJ0vCAguKcAvN7gxwpCo5MEEZivRuYBldEMwRo4he2WQQke9KEokqREdlPF3Lvaav0fqPfXqhJyHAq8bYBHWdzMjDJ_dJwhdbLQ-iNLmrK5JNg2vPDglWSznBXbrSX4iyMFk1Ni2Y1SQUIOOxS_InIwCg\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"I'll look up the current weather in Paris.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"id\":\"call_01a07ce8bb767c109c12f0a202e2ac19\",\"input\":{},\"name\":\"lookup_weather\",\"type\":\"tool_use\"},\"index\":2,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"type\":\"input_json_delta\"},\"index\":2,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":2,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":113,\"input_tokens\":451,\"output_tokens\":155,\"output_tokens_details\":{\"thinking_tokens\":87}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6abb1450e0ed8e1e797a4593\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgE2zFV4z-iti1sAin0m3ZgA3g3J378FnoM-67YAWaauWcy7CtUxupuxEDJW48cPMnSXcWEcrSFUvt-qFtzHr_pmyxo6Z3_TiuB043J3j5grxJo3YY4oD6ATnbY1nYhtxKwX9AAI0jysyK5QNuOnIG9De0q7OYqSokBDv9hvu9ZVIXQVTzUY1p7C3JUU_poYtT1H9F_PwPx1RTm3LHCgWuczXvEgq4OIat1-VjbZWdLmwmm5xPbX77dLkmvl-iN9Awpxd8cXzHxgRHuYWCWyNKVbaiRfsL8JKtFCWpi3x76ci4QCZ8cbea8Lazo8I3R3cPUaN4pxjd1IFbjA992Jpg33ERdG_qeO6v7Tx1EIqQvy3Q9OvawHbumAt5LNk6PK3gWjDFCJnnWiNarGvQk4lGvB7sRjiMI_Q1jfotows4bitJNn_d-d4GuYsBjekGSMJ6J1rpMcUhcoQn6L4mJnb4LBYpAbypfNV_CXY5kxSF66Mo0YKK1UecbtL41P1euWI1Tob-x3yvtc-le2PKfBZwFCPLBQ7HDUNIsx-CsPyjns4_lMhYmdGEHNCLkBQKWh7Z8vOXjN3qo9UfNkXKhTnzmKs-FGHBPYeVsi9nMelyBAz2Gfida0Y-rSCmvSrz4fS7eszQiIj9fI7Tzhucr-GfplyO8FBisej9_421VNtR1jY3iX-KTvQEvN4OEpxDCDaluV-aKCOoMOHryAK8j7YCrhFp9sNOVTx0GCQx2wDMz8VueJMblfMxjXniqONLUHo8k_jk4D3Phz_xfXBgECXUanBr1neWf35PE5ny3m7bnHjPc41WwjXfr8WrZBDyFfIJ7WaEaWRtKMGtv08vYYAjKapiYUgOT_poJjg-aAuebM6sYPtaAF3GK9TMv35kPmPgty_GC59RoR0F-ryCA746KGUDMf1dPq5J20LQ8bp-q0xNT2gjHZcDqOrK84VFmakvs3M2PERhDSVNNAEFzNeXh6DM5jvUSDonneyyE8al75YmmZNY0lvXK_uCVNIPY57UuZ5rs_MwwUL8_mwySLni6zmclGZe1NdpyVyQuUD9bmA256mLzPM2mj2_UJ6D30DKiX6ckLFaoQl1iR5X3_Vil12bNuX-AdbFF5aGT6UyP-TO-TBLujAXAk6AwRfjHMyo84H4yiOA7UhBlxMKBUCwIz_QiTYVaPsjANG9X5ggDYwqMDAWKmjLyhpShxdyInhsyR0o7RyKgr_MwAliTBGl8lL2JG-rFVqkpRgeVqkp2miyq2wgRmb33_YVoL2dgY_gzpZuJBA7ovlG3Q1NnIUqbLpQJ0LnoxzcVHNFV-1JmSpzRrmt-nAxjIm4iRe6RQ9zhWIerExA8-os1Qs0scbwVsix5Hhtus7U6sZZuk6Ouim3UQLPfya69UILsuvEN6LbMnTO6393Y4PD9Oad32E-K5iQqLoNnhvAMxYa1K-xLmQ1AkshYxnE2Y9M21-DFgACmhWdImVQIKNN4XZoWdAeAOz36rw03RWD0WDqxEyFip40OAVUfkJGSRxmm9sTDnighIVUN_n73PFgfuoG3gzcq8tN5ybmmMgSWo5a-L5C1Fya82s0Qlhwe-ixTzE0UzK08xva5d9TGqdO9QXDp3r_FUY4K5FAkKB4k2ZjXYf9wzA0ER8trYBfemtywt9shraVsshJiZuufALeMo1R4yyUEUkUSeDfRKUkxOqz_kNSc1_TecgjOFFaXvW5f-amhfVUXkfgjl31QIZzZMtpyBn97gTvCJps0yqjOF3EH_AzRQ5OWj3iCNy_ZH7K7IM4XJO1gGXrFF-UZzxIK-kWWzar734ZTwgM220vmCCyjsfh6FzLyIuF21H061SYJ7D977iAzWndpX4bbipn1ELTTctd1sd9bvgJ6GsU4pquyAQ8oNSOhUSVz-7diWSDgPntxdLSwbvlgbZOyD53bOsrW7U1qFAu_LX5N7mt0u1Om8cm9YqBpwIyqtMssEZFG6k4pYG0hYJGK7Wtzq_wbaLBXKpnlQdZIeIm6pF3ntRwuFzY8sNYACIOCdlN7Rub7skTewkeRJ4yB1qT9lAwa5p4ktDMrAgmU4c-T-PWYfFmqIhPrBFuCw3aToFa-u1Furzxj6-Q6jkXHKcz8cMelcSs3jAmrGVZm_QUJnbz96sFosD0xmS6bbcaSgAou_0pys-S2iA0O69Yu7fniRBUJpzXWfwZG5BsVNpAVOiM-olHrulDIDnjTa1N4QVgNm-Vc9hK3wSG7N5iO_s_d70eqpAzS-xLqcAtAxVZRs9qA9-Jh90-QHcQ9_eG4f8P8TyilwCFgTuckcFHhx4JTPSbEbLDOGGQuq8sS3Ah2tBs4RKaZ-pgXCwFGDZ0TfMAMrBP1fNlIOm8UcFijzCcIh_NmsfAOTDL3rhRiCXZzEm9ax1xjLX6ss5heO7Ia7840Z0NEroFqHTugl6KUEm5_4t-Xdqmj7JrwEF9M2_abEK33A64lqCGPPKB6CY7Rgd4ql0MyC2C4r6CAey7VAY-1wU53-jn1vvPvDkqruh30dQvmXvd37oy_5U7LyfXRZXIm-7tklO3y-Ih2NWUdQ_wGIAGU_fLedL2uPQ6sS1BT-xwMi2bkkzvs4aZbJiynFnfW1MBjR6_0tMKbrNEj7E59K2VaIgdRhOWFBo4ZlNzEiafkjEQac5OP0dyYrAvbxVHDi74kY0py-QXnc1rKRX3IL5xO2dvH9TZAlVu4wwMB2Moc39GpScORARKQzMMIeMhlFjxeKfhtHRaOBqdQCY4HzsBLcgbxLhzefI-TjwYwf1pw\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"I'll look up the current weather in Paris.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"id\":\"call_01a0eac763d671fcac6e807a3f49c0ce\",\"input\":{},\"name\":\"lookup_weather\",\"type\":\"tool_use\"},\"index\":2,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"type\":\"input_json_delta\"},\"index\":2,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":2,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":113,\"input_tokens\":451,\"output_tokens\":310,\"output_tokens_details\":{\"thinking_tokens\":242}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
       }
     },
     {
@@ -33,14 +40,14 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"redacted_thinking\",\"data\":\"Q-PaDgGyJ4hIKk41uslnSV0PGvrTkwJ5D-t5skfjtkIt-ABXsehMcLKJJ8RJHRKW2-XhkpPrex0aOkIdqWl99vpCgtOHIFFaSc4b3oGxA8XDx4T_2aKANfYrR1DYwYzGe6ZZ-DQnU0bnpVUzCcXkghkLdyTcJr2p8cvVo1rymFpB0wZsbQRBhxCMR6PrY4i0aOTe8_waq_Po1a4l3YzKnzZIIvYP090o5kltv7MAwqChXjQeTJlKq7ECFa6HVeoTa43oiLmoD2Bzih0VfvBvQfbSh2uDypRM7-f65sp35-VuZfwsM33ZTvefzDbd8zd0D50I6wcybsj8gulDhWWpY7cxoN1Xasy-ImvisACGeppIN66maIFq5dMT2s8_CQ8a2EQ0hw9kwJaIiygZCdRofs-T1yaGWvnQxL6MpNh6SXux9T1ZfuexNrXOhz5cR3_s1euhq3-hI3GDCUDLAtkjiigSE3w6PExrwHTHnvkuAOTP0Lw7DH4NtKv-RFFeZaQOk_0Bi2EV43tR0Hq_chtEDiSpoezDjexPWfdZvhRIaO6PwyJaQ8jVOaLUr6bh6jQ3IM19lv6R7lY4Neno8fLxMwTbf7v7q02lfhOaZe3jR1fqOFUq8e4VXV76_rJBgzThqPNqO8OI_betgX5d2KMcwWAkaZjmrP3rxA7g5xp_Q7bkFiBaaTd3HbYIk_cKbtLOS6TIIphb4SX6ADA2qJ0zoo98P2NOceZODT2WrLjKCHl5dT6b9l2feH9m21pW576ULfKhVSMzuy0cmmWI7rv2P4q-2Fw2klsDVJAc6q22bFjfDgzhybKuhuM_p1SYb8aswNrgggV-cqHWDpF1FdVpL5fHMO74l1uD8Sj_9wuuD0asMQustuvsnYq2EdI0lLvONFMApWCU0s3QA8_P0Iyf0YoCZOm5QGnA7l3O5nAPkFF4kxLSsgRe9zuP6A4oKBDLN8EHwZ3pB4WZGWpUT12cJxplmT3_n8xKaMgaz13qs27uvUm3wMI1seyfpkMwUPHmt1ftpk9f_1OAg3fvQgIkWPTp6K9NzVzEry6SP7zbPfls8yn529Qrbki7ZM_oz3xEvDg367ZCe97eVnjiqRrYsYM2MmDsQq9lUwkgXb84kpK6a4pEzX9NDvhTqhw7RI6RL9E-2Ki4ciUfHv5LVTZ0rNweCo6SYXC11f8FCeObIW_Esr2mqYpORFS4SDMU-4I1HQfD9z6cPjL22APpv9a7Pp1phI8x_aQZkPU7LkyBWyVNDeusI7wq_LC0UgJ0vCAguKcAvN7gxwpCo5MEEZivRuYBldEMwRo4he2WQQke9KEokqREdlPF3Lvaav0fqPfXqhJyHAq8bYBHWdzMjDJ_dJwhdbLQ-iNLmrK5JNg2vPDglWSznBXbrSX4iyMFk1Ni2Y1SQUIOOxS_InIwCg\"},{\"type\":\"text\",\"text\":\"I'll look up the current weather in Paris.\"},{\"type\":\"tool_use\",\"id\":\"call_01a07ce8bb767c109c12f0a202e2ac19\",\"name\":\"lookup_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a07ce8bb767c109c12f0a202e2ac19\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\"}\"}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"redacted_thinking\",\"data\":\"Q-PaDgE2zFV4z-iti1sAin0m3ZgA3g3J378FnoM-67YAWaauWcy7CtUxupuxEDJW48cPMnSXcWEcrSFUvt-qFtzHr_pmyxo6Z3_TiuB043J3j5grxJo3YY4oD6ATnbY1nYhtxKwX9AAI0jysyK5QNuOnIG9De0q7OYqSokBDv9hvu9ZVIXQVTzUY1p7C3JUU_poYtT1H9F_PwPx1RTm3LHCgWuczXvEgq4OIat1-VjbZWdLmwmm5xPbX77dLkmvl-iN9Awpxd8cXzHxgRHuYWCWyNKVbaiRfsL8JKtFCWpi3x76ci4QCZ8cbea8Lazo8I3R3cPUaN4pxjd1IFbjA992Jpg33ERdG_qeO6v7Tx1EIqQvy3Q9OvawHbumAt5LNk6PK3gWjDFCJnnWiNarGvQk4lGvB7sRjiMI_Q1jfotows4bitJNn_d-d4GuYsBjekGSMJ6J1rpMcUhcoQn6L4mJnb4LBYpAbypfNV_CXY5kxSF66Mo0YKK1UecbtL41P1euWI1Tob-x3yvtc-le2PKfBZwFCPLBQ7HDUNIsx-CsPyjns4_lMhYmdGEHNCLkBQKWh7Z8vOXjN3qo9UfNkXKhTnzmKs-FGHBPYeVsi9nMelyBAz2Gfida0Y-rSCmvSrz4fS7eszQiIj9fI7Tzhucr-GfplyO8FBisej9_421VNtR1jY3iX-KTvQEvN4OEpxDCDaluV-aKCOoMOHryAK8j7YCrhFp9sNOVTx0GCQx2wDMz8VueJMblfMxjXniqONLUHo8k_jk4D3Phz_xfXBgECXUanBr1neWf35PE5ny3m7bnHjPc41WwjXfr8WrZBDyFfIJ7WaEaWRtKMGtv08vYYAjKapiYUgOT_poJjg-aAuebM6sYPtaAF3GK9TMv35kPmPgty_GC59RoR0F-ryCA746KGUDMf1dPq5J20LQ8bp-q0xNT2gjHZcDqOrK84VFmakvs3M2PERhDSVNNAEFzNeXh6DM5jvUSDonneyyE8al75YmmZNY0lvXK_uCVNIPY57UuZ5rs_MwwUL8_mwySLni6zmclGZe1NdpyVyQuUD9bmA256mLzPM2mj2_UJ6D30DKiX6ckLFaoQl1iR5X3_Vil12bNuX-AdbFF5aGT6UyP-TO-TBLujAXAk6AwRfjHMyo84H4yiOA7UhBlxMKBUCwIz_QiTYVaPsjANG9X5ggDYwqMDAWKmjLyhpShxdyInhsyR0o7RyKgr_MwAliTBGl8lL2JG-rFVqkpRgeVqkp2miyq2wgRmb33_YVoL2dgY_gzpZuJBA7ovlG3Q1NnIUqbLpQJ0LnoxzcVHNFV-1JmSpzRrmt-nAxjIm4iRe6RQ9zhWIerExA8-os1Qs0scbwVsix5Hhtus7U6sZZuk6Ouim3UQLPfya69UILsuvEN6LbMnTO6393Y4PD9Oad32E-K5iQqLoNnhvAMxYa1K-xLmQ1AkshYxnE2Y9M21-DFgACmhWdImVQIKNN4XZoWdAeAOz36rw03RWD0WDqxEyFip40OAVUfkJGSRxmm9sTDnighIVUN_n73PFgfuoG3gzcq8tN5ybmmMgSWo5a-L5C1Fya82s0Qlhwe-ixTzE0UzK08xva5d9TGqdO9QXDp3r_FUY4K5FAkKB4k2ZjXYf9wzA0ER8trYBfemtywt9shraVsshJiZuufALeMo1R4yyUEUkUSeDfRKUkxOqz_kNSc1_TecgjOFFaXvW5f-amhfVUXkfgjl31QIZzZMtpyBn97gTvCJps0yqjOF3EH_AzRQ5OWj3iCNy_ZH7K7IM4XJO1gGXrFF-UZzxIK-kWWzar734ZTwgM220vmCCyjsfh6FzLyIuF21H061SYJ7D977iAzWndpX4bbipn1ELTTctd1sd9bvgJ6GsU4pquyAQ8oNSOhUSVz-7diWSDgPntxdLSwbvlgbZOyD53bOsrW7U1qFAu_LX5N7mt0u1Om8cm9YqBpwIyqtMssEZFG6k4pYG0hYJGK7Wtzq_wbaLBXKpnlQdZIeIm6pF3ntRwuFzY8sNYACIOCdlN7Rub7skTewkeRJ4yB1qT9lAwa5p4ktDMrAgmU4c-T-PWYfFmqIhPrBFuCw3aToFa-u1Furzxj6-Q6jkXHKcz8cMelcSs3jAmrGVZm_QUJnbz96sFosD0xmS6bbcaSgAou_0pys-S2iA0O69Yu7fniRBUJpzXWfwZG5BsVNpAVOiM-olHrulDIDnjTa1N4QVgNm-Vc9hK3wSG7N5iO_s_d70eqpAzS-xLqcAtAxVZRs9qA9-Jh90-QHcQ9_eG4f8P8TyilwCFgTuckcFHhx4JTPSbEbLDOGGQuq8sS3Ah2tBs4RKaZ-pgXCwFGDZ0TfMAMrBP1fNlIOm8UcFijzCcIh_NmsfAOTDL3rhRiCXZzEm9ax1xjLX6ss5heO7Ia7840Z0NEroFqHTugl6KUEm5_4t-Xdqmj7JrwEF9M2_abEK33A64lqCGPPKB6CY7Rgd4ql0MyC2C4r6CAey7VAY-1wU53-jn1vvPvDkqruh30dQvmXvd37oy_5U7LyfXRZXIm-7tklO3y-Ih2NWUdQ_wGIAGU_fLedL2uPQ6sS1BT-xwMi2bkkzvs4aZbJiynFnfW1MBjR6_0tMKbrNEj7E59K2VaIgdRhOWFBo4ZlNzEiafkjEQac5OP0dyYrAvbxVHDi74kY0py-QXnc1rKRX3IL5xO2dvH9TZAlVu4wwMB2Moc39GpScORARKQzMMIeMhlFjxeKfhtHRaOBqdQCY4HzsBLcgbxLhzefI-TjwYwf1pw\"},{\"type\":\"text\",\"text\":\"I'll look up the current weather in Paris.\"},{\"type\":\"tool_use\",\"id\":\"call_01a0eac763d671fcac6e807a3f49c0ce\",\"name\":\"lookup_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a0eac763d671fcac6e807a3f49c0ce\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\"}\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,
         "headers": {
           "content-type": "text/event-stream"
         },
-        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6a9ef3e77f6ef36fdd8f4925\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgH-GUZkiqnb_seFaP70it_GxAEIUjt2BLllpyzfckiBOUVwr72xGQsSnj0y9aOhoaQ24A_HB0MHh4XWyYziVdRgq6lDPLHkJlmMzbusZxUZUx7D7B8kD8HrBbiTeIFbFlHaM9MiZW_PpYY9fpkdc7aeuX0mORdK8XTT3JPjvW1HPp4Qqp_iEOl9G2iM2Y6xno8SqeTcbc4EQs1LePaKrq86dBPmXBjkgQbYfvIw57o0SBEyelcudtnzJnaluOyOQdV2Ytk_r_xrYSCoBwgbf2KBCOFjdeQyruuwVZZ32JJdVOpWLw8eopUwAo2xYOZP0g8S8hTmOFvDKuzXipm1OoAXwD8Swm6ED3IIo0hHA5xSfMygDCee47nd-EpShNPamkCKodfX1QvePEJsIQK2iTgkh8IGUeEEne5dxgLuXvEAbeqGDvEy6T7IoSgZnc-KPtH6SoWM_kgc_eF_oN73Nxg2prMyCqTUNg5Qs2WLPjA9wSLmmnCoiDr1bYNIuQyn6adgv0-nZZXETJoRAHJBj65Asa8kbLyCYesb192178xCj2aBSdwyj-jc0i328sa9STS7mUSI7KvOt0Yi3kllLs1aSnHW-ogsUJUM7tTf83VO9fRRU_aW4H6qr4OAr8jbBKSD3bxE0AekDd24ZS-8YIjiP1tMOAPZ2JGQrNqbxnaeqhCZzD2nl-E8TMXaAJIk4L3oZtV80xJiUW7mLEf_jQBPAWhph4ujbkDaufGvNrl4FXyBJ-XpKMIA5z0jAYU2b3ul5-Qn5Km7Oc8fPu1M_0XGAOKG-pF9ppr4y-an4B4mKDYoAiSHp3cjv-fW57D87wBfQPaJRjOzWhzqENO-5MlB0CEsnDtrLveE2ui8wSECszParUNk5SEaeSYvrXLY0QkaE7CTK9ljwTKjJM34r1a8o16KFxGuzMrloNlxIYIaO_suM9CDuf8wNwe8KkAV2Kt28g9LwkL5b3mtI7ZSjTdHYOOhFFMzs-sjXboQoGAJGOhMnCQNc3E5-goSzvOzEIXehSTs8Mzyq8d3C2k5F9PSgdO6ZouHVURDgbEXTqWqoqjQ8huk5AbrUX16QwhJambd6P-3i--Idz9CbIVuWIqiMm80TvYlMttobYxTyFDIJrKJTrVA0PkAOFvOMfYt27d7z2ZMrTf6Vtm_DNniuhVbvVU3ZcWbb4LO-XkwH3bfHB-sckpwURP34KzOMvogaqWaMAZlabdd-lQKCc7tMhmo9BrYwHHvLxAELD2qQnyym43Yo1iJNAyrqoUAFk6K029fDon7h9ybmKZdBxRtS3arUesY_91Xep0tA0Y1UYUKo8zKjK3Op_DbVyC5OoR8rxpumKiqk2PtG7RPf-WjEXGkleGqZtxix7ILSkQXxW6McY1r_6LAh2Nv0nUzqS019tTb7mx2OLyt2g\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"It's sunny in Paris.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":210,\"output_tokens\":50,\"output_tokens_details\":{\"thinking_tokens\":35}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6abb14564f2fae50d0ed42a8\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgEJfY7iuPSD4c3a9QQXKCb1oK9Ji4ou0DnOqz_zAKUS88wOj9Q9hfh3-wxfkn4XnZUgF6iqCVOUp572Iu03n_hxReZu1uW_IWTkCGdwqFFs3n22PWDMF6iMnw7x_FwgXgoG1xOuZCXxfdOFbCJdfUCfmMZcULjzt2TWG0w_J-UUf5-BY0SPLAOHvx4NG04U4k5BvRvjRfjzSNUlF1PR32YOKENLNO7Th_kRMvm-Kgyk6vG9expua2NE8Peag3Yv7dFozscLaruHDq-DOVIzAznN8U9VFTGk4RiMlmh6c9f0QFBwVpo4kzTdMDOjtN-VcYSMAUoo883YgY5pOw54_M7fAdvvLwtXoNVVN4Y1sqvujsR2szJyLhwClbYh9iGdI9rGOVuOPhCwb_QxWuIhwTk2a07ml-Cl8JOFRW7WIuaTRQ5LeG5Q_Y7xTH2xMao50Rdpib7zyEKg2eqH6jGBGuGN18QMgU07J5M5Xu2Rp-6Q2FqmCgbamJwd6dEU2rPRWrdRApAkro2G13plSafc-_YoQ7csHWj4PP8xEqKFxzx0Tc6VrdZP_mgtArDAkRPqeIvMviV625ceDRmS6F-IacwClY1-w_ISNR4fOuhXKajRXEd92OHYhymy8gwJs7eB8AYGGcYe8tVpUHRqhB6ORRPJRG7S2tIPM0b5lMbGOgEaUdrsFL3eJ1MsZ5OZzQCy1eoSNx8YdOMgxM29kuLutBRoGRC5xlKuWp0H_CqE-XZqhXBytc_RMffb4EoB2LtoU5ZpczK1o7b0Sb2KkIhiOLyjwz9WR0VT4ceJptrCREcvfJaufXKvWGyqHDswcOeDuyIszVqhoR9bFzwItC7rDAYsTeIHvilAjDLrFXhzuEr_L2790dgcyoS7hXccVrPhattMCPnjLbRAH9_BzyLVbVDZLrSYbJ33VR2Nv-Q7XaZ0-YuyfWHrgz_gjwuX0TFfBrlIaSJxsEfU-hqpTvXZtLXg5zPtovtHBcqPJWvKdR2Zyh5rn39iU4nqbZMPS0iSKiiOWjVGWuuG6DgSFf7trFuNmkCKc_KPjG3610WZ5jZiMHDQXvKkvobewcrvXZC2GFbqBoOq0Z2LIkl1WEMsQq5k2bVuZHrYQz7dBnYpf_WCXoQ4BsjXfiVissy7xoKwjHJPLhbyO736uEV63ZOrTONbOWIVrNrK0FxWSK4yt3wpQC618eJ46-ymKL_1vgmT90Siyw-jVFawyJcfhYpGqG2xdq3IljWGMHX8DmDjkmGvTT5VFgChCXdObWTXSFBbqfXQs34vvJKjYJHitMIyTcRsLsy-dbWe8Qw_1pg2acITWkSMO6snUp-qjU48qAP9nMfkc7eYsVYTo8eu5AsikmkkTYq8Bi0BiszbnB6zRCwiEUHLFshWrBIrg5VMxx4IcaXfdzg9mCDZ8g\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"It's sunny in Paris right now.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":365,\"output_tokens\":97,\"output_tokens_details\":{\"thinking_tokens\":80}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
       }
     }
   ]

packages/ai/test/fixtures/recordings/meta-messages/streams-text-with-adaptive-thinking.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/meta-messages/streams-text-with-enabled-thinking.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"enabled\",\"budget_tokens\":1024,\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"enabled\",\"budget_tokens\":1024,\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/minimax-messages/m2-7-streams-default-thinking.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"MiniMax-M2.7\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":1536}"
+        "body": "{\"model\":\"MiniMax-M2.7\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1536}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/minimax-messages/m3-continues-a-tool-loop-with-adaptive-thinking.json

@@ -24,7 +24,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
       },
       "response": {
         "status": 200,
@@ -42,7 +42,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user wants me to look up the current weather in Paris using the get_weather tool, then report it in one short sentence. Let me call the tool.\",\"signature\":\"f05cb5f4873950f23d194289c41d79b96ebd37c9411a45b306ed44f135a910d4\"},{\"type\":\"tool_use\",\"id\":\"call_01a07cc9f2d47d83a6424ff3\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a07cc9f2d47d83a6424ff3\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user wants me to look up the current weather in Paris using the get_weather tool, then report it in one short sentence. Let me call the tool.\",\"signature\":\"f05cb5f4873950f23d194289c41d79b96ebd37c9411a45b306ed44f135a910d4\"},{\"type\":\"tool_use\",\"id\":\"call_01a07cc9f2d47d83a6424ff3\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a07cc9f2d47d83a6424ff3\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/minimax-messages/m3-generates-a-named-tool-call-with-default-thinking-off.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":512}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":512}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/minimax-messages/m3-streams-adaptive-thinking.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/minimax-messages/m3-streams-text-with-thinking-disabled.json

@@ -22,7 +22,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"disabled\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"disabled\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-respects-tool-choice-none.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-respects-tool-choice-required.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"any\"},\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"any\"},\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-returns-native-structured-output.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object containing the capital city of France.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\",\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object containing the capital city of France.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\",\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-streams-text-with-default-effort.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-streams-text-with-high-effort.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"high\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"high\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-streams-text-with-low-effort.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/k3-streams-text-with-max-effort.json

@@ -15,7 +15,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"max\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"max\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/moonshot-messages/kimi-k3-preserves-reasoning-through-a-tool-loop-and-follow-up.json

@@ -24,7 +24,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,
@@ -42,7 +42,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user explicitly asks to use get_weather for Paris then report one short sentence. Need call get_weather. Then final concise sentence based on result. Ensure after receiving result report weather in one short sentence. Call now.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"get_weather_0\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"get_weather_0\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user explicitly asks to use get_weather for Paris then report one short sentence. Need call get_weather. Then final concise sentence based on result. Ensure after receiving result report weather in one short sentence. Call now.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"get_weather_0\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"get_weather_0\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,
@@ -60,7 +60,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user explicitly asks to use get_weather for Paris then report one short sentence. Need call get_weather. Then final concise sentence based on result. Ensure after receiving result report weather in one short sentence. Call now.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"get_weather_0\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"get_weather_0\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"Need final one short sentence. Report weather in Paris: sunny, 18C. Ensure no extra.\",\"signature\":\"\"},{\"type\":\"text\",\"text\":\"The current weather in Paris is sunny with a temperature of 18°C.\"}]},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What temperature did the tool report? Reply with only the temperature.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user explicitly asks to use get_weather for Paris then report one short sentence. Need call get_weather. Then final concise sentence based on result. Ensure after receiving result report weather in one short sentence. Call now.\",\"signature\":\"\"},{\"type\":\"tool_use\",\"id\":\"get_weather_0\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"get_weather_0\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"Need final one short sentence. Report weather in Paris: sunny, 18C. Ensure no extra.\",\"signature\":\"\"},{\"type\":\"text\",\"text\":\"The current weather in Paris is sunny with a temperature of 18°C.\"}]},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What temperature did the tool report? Reply with only the temperature.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/openai-compatible-chat/gemini-parallel-tool-signatures.json

@@ -0,0 +1,54 @@
+{
+  "version": 1,
+  "metadata": {
+    "model": "gemini-3.8-flash",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:google",
+      "protocol:openai-chat",
+      "tool",
+      "tool-loop",
+      "continuation"
+    ],
+    "name": "gemini-parallel-tool-signatures",
+    "recordedAt": "2026-09-28T03:12:05.083Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}},\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723181\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":16,\"prompt_tokens\":74,\"total_tokens\":132}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723184\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565124,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: [DONE]\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_723181\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}}},{\"id\":\"call_723184\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_723181\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"},{\"role\":\"tool\",\"tool_call_id\":\"call_723184\",\"content\":\"{\\\"temperature\\\":0,\\\"condition\\\":\\\"unknown\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"content\":\"It is currently sunny and 22°C in Paris,\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":13,\"prompt_tokens\":150,\"total_tokens\":226}}\n\ndata: {\"choices\":[{\"delta\":{\"content\":\" while Tokyo is 0°C.\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":150,\"total_tokens\":234}}\n\ndata: {\"choices\":[{\"delta\":{\"extra_content\":{\"google\":{\"thought_signature\":\"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\"}},\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":192,\"total_tokens\":276}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/promise.test.ts

@@ -22,7 +22,8 @@ const chatBody = sseEvents(
 /**
  * Executor layer that answers chat completions with SSE text, image generations with one base64 PNG, Runway video
  * tasks with a queued submission that succeeds on the second poll, speech with raw audio or SSE audio deltas, OpenAI
- * transcription with JSON or SSE text deltas, and AssemblyAI transcripts that complete on the first poll.
+ * transcription with JSON or SSE text deltas, AssemblyAI transcripts that complete on the first poll, and `slow.test`
+ * chat completions that send one text delta and never finish.
  */
 const executor = (seen: Array<string>) =>
   RequestExecutor.layer.pipe(
@@ -55,6 +56,18 @@ const executor = (seen: Array<string>) =>
               output: "https://replicate.test/a.webp",
               urls: { get: "https://replicate.test/p_1", cancel: "https://replicate.test/p_1/cancel" },
             })
+          if (web.url.startsWith("https://slow.test"))
+            return input.respond(
+              new ReadableStream({
+                start: (controller) =>
+                  controller.enqueue(
+                    new TextEncoder().encode(
+                      `data: ${JSON.stringify({ choices: [{ delta: { content: "Hello" } }] })}\n\n`,
+                    ),
+                  ),
+              }),
+              { headers: { "content-type": "text/event-stream" } },
+            )
           if (web.url.endsWith("/chat/completions"))
             return input.respond(chatBody, { headers: { "content-type": "text/event-stream" } })
           if (web.url.endsWith("/audio/speech"))
@@ -304,6 +317,77 @@ describe("AI promise client", () => {
     await ai.dispose()
   })
 
+  test("aborted calls reject and aborted streams throw with the signal's reason", async () => {
+    const ai = AI.make({ layer: executor([]) })
+    const slow = OpenAI.configure({ apiKey: "test", baseURL: "https://slow.test/v1" }).chat("gpt-4o-mini")
+    const aborted = new AbortController()
+    aborted.abort()
+    const reason = new Error("mine")
+
+    const rejected = await ai.run(Effect.never, { signal: aborted.signal }).catch((error: unknown) => error)
+    expect(rejected).toBe(aborted.signal.reason)
+    expect(rejected).toMatchObject({ name: "AbortError" })
+
+    const inFlight = new AbortController()
+    setTimeout(() => inFlight.abort(reason), 10)
+    expect(
+      await ai.llm
+        .generate({ model: slow, prompt: "Hello" }, { signal: inFlight.signal })
+        .catch((error: unknown) => error),
+    ).toBe(reason)
+
+    const preAborted = await Array.fromAsync(
+      ai.speech.stream({ model: openai.speech("gpt-4o-mini-tts"), text: "Hello" }, { signal: aborted.signal }),
+    ).catch((error: unknown) => error)
+    expect(preAborted).toBe(aborted.signal.reason)
+    expect(preAborted).toMatchObject({ name: "AbortError" })
+
+    const midStream = new AbortController()
+    const deltas: Array<string> = []
+    const midStreamFailure = await Array.fromAsync(
+      ai.llm.stream({ model: slow, prompt: "Hello" }, { signal: midStream.signal }),
+      (event) => {
+        if (!LLMEvent.is.textDelta(event)) return
+        deltas.push(event.text)
+        midStream.abort()
+      },
+    ).catch((error: unknown) => error)
+    expect(deltas).toEqual(["Hello"])
+    expect(midStreamFailure).toBe(midStream.signal.reason)
+    expect(midStreamFailure).toMatchObject({ name: "AbortError" })
+
+    const model = Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5")
+    const generation = await ai.video.start({ model, prompt: "A kite" })
+    const polling = new AbortController()
+    const events: Array<string> = []
+    const eventsFailure = await Array.fromAsync(
+      generation.events({ poll: { interval: 60_000 }, signal: polling.signal }),
+      (event) => {
+        events.push(event.type)
+        polling.abort(reason)
+      },
+    ).catch((error: unknown) => error)
+    expect(events).toEqual(["generation-progress"])
+    expect(eventsFailure).toBe(reason)
+
+    await ai.dispose()
+  })
+
+  test("breaking out of an abortable stream cleans up without throwing", async () => {
+    const ai = AI.make({ layer: executor([]) })
+    const slow = OpenAI.configure({ apiKey: "test", baseURL: "https://slow.test/v1" }).chat("gpt-4o-mini")
+    const controller = new AbortController()
+    const deltas: Array<string> = []
+    for await (const event of ai.llm.stream({ model: slow, prompt: "Hello" }, { signal: controller.signal })) {
+      if (!LLMEvent.is.textDelta(event)) continue
+      deltas.push(event.text)
+      break
+    }
+    controller.abort()
+    expect(deltas).toEqual(["Hello"])
+    await ai.dispose()
+  })
+
   test("the default client is created lazily and can be disposed", async () => {
     expect(typeof AI.ai.llm.generate).toBe("function")
     expect(typeof AI.ai.image.generate).toBe("function")

packages/ai/test/provider-error.test.ts

@@ -355,6 +355,32 @@ describe("provider error rawBody classification", () => {
     }
   })
 
+  test("classifies Google invalid API keys as authentication failures", () => {
+    const rawBody = JSON.stringify({
+      error: {
+        code: 400,
+        message: "API key not valid. Please pass a valid API key.",
+        status: "INVALID_ARGUMENT",
+        details: [
+          {
+            "@type": "type.googleapis.com/google.rpc.ErrorInfo",
+            reason: "API_KEY_INVALID",
+            domain: "googleapis.com",
+          },
+          {
+            "@type": "type.googleapis.com/google.rpc.LocalizedMessage",
+            locale: "en-US",
+            message: "API key not valid. Please pass a valid API key.",
+          },
+        ],
+      },
+    })
+    expect(
+      classifyProviderFailure({ message: "API key not valid. Please pass a valid API key.", status: 400, rawBody })
+        ._tag,
+    ).toBe("Authentication")
+  })
+
   test("classifies overflow signals buried in the raw payload when the summary is vague", () => {
     const reason = classifyProviderFailure({
       message: "Request failed",

packages/ai/test/provider-package.test.ts

@@ -300,7 +300,9 @@ describe("provider package entrypoints", () => {
     })
 
     expect(String(selected.provider)).toBe("example")
-    expect(selected.route.id).toBe("anthropic-messages")
+    expect(selected.route.id).toBe("anthropic-compatible-messages")
+    expect(selected.route.protocol).toBe("anthropic-messages")
+    expect(selected.route.providerMetadataKey).toBe("example")
     expect(selected.route.endpoint).toMatchObject({
       baseURL: "https://messages.example.test/v1",
     })
@@ -319,6 +321,7 @@ describe("provider package entrypoints", () => {
       thinking: { type: "adaptive" },
     })
 
+    expect(selected.route.id).toBe("anthropic-messages")
     expect(selected.route.defaults.providerOptions).toEqual({ thinking: { type: "adaptive" } })
   })
 

packages/ai/test/provider/elevenlabs-transcription.recorded.test.ts

@@ -0,0 +1,50 @@
+import { describe, expect } from "bun:test"
+import { Effect, Stream } from "effect"
+import { Transcription } from "../../src/index.js"
+import { ElevenLabs } from "../../src/providers.js"
+import { recordedTests } from "../recorded-test.js"
+import { TRANSCRIPT, audio, audioRecording, dialog } from "./transcription-recording.js"
+
+const model = ElevenLabs.configure({ apiKey: process.env.ELEVENLABS_API_KEY ?? "fixture" }).transcription("scribe_v2")
+
+const recorded = recordedTests({
+  prefix: "elevenlabs-transcription",
+  provider: "elevenlabs",
+  protocol: "elevenlabs-transcription",
+  requires: ["ELEVENLABS_API_KEY"],
+  options: audioRecording,
+})
+
+describe("ElevenLabs Transcription recorded", () => {
+  recorded.effect("transcribes audio with word timestamps", () =>
+    Effect.gen(function* () {
+      const request = Transcription.request({ model, audio: yield* audio, timestamps: "word" })
+      const response = yield* Transcription.generate(request)
+
+      expect(response.text).toMatch(TRANSCRIPT)
+      expect(response.words?.map((word) => word.text)).toEqual(["Hello", "from", "OpenCode"])
+      expect(response.words?.every((word) => word.speaker === undefined && (word.confidence ?? 0) > 0)).toBe(true)
+      expect(response.segments).toBeUndefined()
+      expect(response.language).toBe("eng")
+      expect(response.durationSeconds).toBeGreaterThan(0)
+      expect(response.usage).toEqual({ type: "seconds", seconds: response.durationSeconds })
+      expect(response.providerMetadata?.elevenlabs?.transcriptionId).toEqual(expect.any(String))
+
+      const events = Array.from(yield* Stream.runCollect(Transcription.stream(request)))
+      expect(events.map((event) => event.type)).toEqual(["finish"])
+    }),
+  )
+
+  recorded.effect("groups diarized words into speaker turns", () =>
+    Effect.gen(function* () {
+      const response = yield* Transcription.generate({ model, audio: yield* dialog, diarize: true })
+
+      expect(response.segments?.map((segment) => segment.speaker)).toEqual(["speaker_0", "speaker_1"])
+      expect(response.segments?.[0].text).toMatch(/^Did the release ship\?$/)
+      expect(response.segments?.[1].text).toMatch(/^Yes, it shipped this morning\.?$/)
+      expect(response.segments?.map((segment) => segment.text).join(" ")).toBe(response.text)
+      expect(response.words?.some((word) => word.text.trim() === "")).toBe(false)
+      expect(new Set(response.words?.map((word) => word.speaker))).toEqual(new Set(["speaker_0", "speaker_1"]))
+    }),
+  )
+})

packages/ai/test/provider/evaluation.recorded.test.ts

@@ -92,5 +92,6 @@ const assertEvaluation = <Options extends EvaluationOptions>(
     expect(response.answers.refund.probability).toBeGreaterThan(0.5)
     expect(response.usage?.inputTokens).toBeGreaterThan(0)
     expect(response.usage?.outputTokens).toBeGreaterThan(0)
-    expect(response.providerMetadata?.[metadataKey]?.confidence).toBeDefined()
+    expect(response.answers.department.confidence).toBeGreaterThan(0)
+    expect(response.answers.urgency.confidence).toBeGreaterThan(0)
   })

packages/ai/test/provider/gemini-openai-chat.recorded.test.ts

@@ -0,0 +1,68 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, LLMEvent, LLMRequest, Message, ToolRuntime, toDefinitions } from "../../src/index.js"
+import * as OpenAICompatible from "../../src/providers/openai-compatible.js"
+import { LLMClient } from "../../src/route.js"
+import { compileRequest } from "../../src/route/client.js"
+import { recordedTests } from "../recorded-test.js"
+import { weatherRuntimeTool, weatherToolName } from "../recorded-scenarios.js"
+
+const model = OpenAICompatible.configure({
+  provider: "google",
+  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai",
+  apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY ?? "fixture",
+}).model("gemini-3.8-flash")
+
+const recorded = recordedTests({
+  prefix: "openai-compatible-chat",
+  provider: "google",
+  protocol: "openai-chat",
+  requires: ["GOOGLE_GENERATIVE_AI_API_KEY"],
+  tags: ["tool", "tool-loop", "continuation"],
+  metadata: { model: model.id },
+})
+
+describe("Gemini OpenAI-compatible Chat recorded", () => {
+  recorded.effect.with(
+    "replays thought signatures through a parallel tool loop",
+    { cassette: "openai-compatible-chat/gemini-parallel-tool-signatures" },
+    () =>
+      Effect.gen(function* () {
+        const tools = { [weatherToolName]: weatherRuntimeTool }
+        const request = LLM.request({
+          model,
+          system: "Call get_weather for every requested city in parallel, then answer in one short sentence.",
+          prompt: "What is the weather in Paris and in Tokyo?",
+          tools: toDefinitions(tools),
+          cache: "none",
+        })
+        const first = yield* LLMClient.generate(request)
+        const calls = first.events.filter(LLMEvent.is.toolCall)
+        expect(calls.map((call) => call.input)).toEqual([{ city: "Paris" }, { city: "Tokyo" }])
+        const extraContent = calls[0]?.providerMetadata?.google?.extraContent
+        expect(extraContent).toEqual({ google: { thought_signature: expect.any(String) } })
+
+        const results = yield* Effect.forEach(calls, (call) => ToolRuntime.dispatch(tools, call))
+        const continuation = LLMRequest.update(request, {
+          messages: [
+            ...request.messages,
+            first.message,
+            ...calls.map((call, index) =>
+              Message.tool({ id: call.id, name: call.name, result: results[index]!.result }),
+            ),
+          ],
+        })
+        const prepared = yield* compileRequest(continuation)
+        const assistant = prepared.body.messages.find((message) => message.role === "assistant")
+        expect(assistant?.role === "assistant" ? assistant.tool_calls?.[0]?.extra_content : undefined).toEqual(
+          extraContent,
+        )
+
+        const second = yield* LLMClient.generate(continuation)
+        expect(second.events.filter(LLMEvent.is.toolCall)).toHaveLength(0)
+        expect(second.text).toMatch(/Paris/)
+        expect(second.text).toMatch(/Tokyo/)
+      }),
+    60_000,
+  )
+})

packages/ai/test/provider/meta-capabilities.test.ts

@@ -33,7 +33,12 @@ it.effect("Meta selects Messages and lowers native search alongside ordinary fun
       output_config: { effort: "low" },
       tools: [
         { type: "web_search", name: "web_search", user_location: { type: "approximate", country: "US" } },
-        { name: "lookup", description: "Lookup", input_schema: { type: "object" } },
+        {
+          name: "lookup",
+          description: "Lookup",
+          input_schema: { type: "object" },
+          cache_control: { type: "ephemeral" },
+        },
       ],
     })
     const entrypoint = yield* Effect.promise(() => import("@opencode/ai/providers/meta/messages"))

packages/ai/test/provider/openai-chat.test.ts

@@ -472,6 +472,45 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("replays Gemini thought signatures as tool call extra content", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Weather in Paris and Tokyo?"),
+            Message.assistant([
+              ToolCallPart.make({
+                id: "call_1",
+                name: "lookup",
+                input: { city: "Paris" },
+                providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+              }),
+              ToolCallPart.make({ id: "call_2", name: "lookup", input: { city: "Tokyo" } }),
+            ]),
+            Message.tool({ id: "call_1", name: "lookup", result: "Sunny" }),
+            Message.tool({ id: "call_2", name: "lookup", result: "Rainy" }),
+          ],
+        }),
+      )
+
+      const assistant = prepared.body.messages[1]
+      expect(assistant?.role === "assistant" ? assistant.tool_calls : undefined).toEqual([
+        {
+          id: "call_1",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Paris" }) },
+          extra_content: { google: { thought_signature: "sig_1" } },
+        },
+        {
+          id: "call_2",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Tokyo" }) },
+        },
+      ])
+    }),
+  )
+
   it.effect("limits OpenAI and Azure Chat tool call IDs to 40 characters", () =>
     Effect.gen(function* () {
       const id = `call_${"a".repeat(48)}`
@@ -1805,6 +1844,78 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("preserves Gemini thought signatures on streamed parallel tool calls", () =>
+    Effect.gen(function* () {
+      // Gemini's OpenAI-compatible endpoint omits `index`, streams each call whole,
+      // and signs only the first call of a parallel batch.
+      const body = sseEvents(
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [
+            {
+              extra_content: { google: { thought_signature: "sig_1" } },
+              id: "call_1",
+              type: "function",
+              function: { name: "lookup", arguments: '{"city":"Paris"}' },
+            },
+          ],
+        }),
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [{ id: "call_2", type: "function", function: { name: "lookup", arguments: '{"city":"Tokyo"}' } }],
+        }),
+        deltaChunk({}, "stop"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall)).toEqual([
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { city: "Paris" },
+          providerExecuted: undefined,
+          providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+        },
+        {
+          type: "tool-call",
+          id: "call_2",
+          name: "lookup",
+          input: { city: "Tokyo" },
+          providerExecuted: undefined,
+          providerMetadata: undefined,
+        },
+      ])
+    }),
+  )
+
+  it.effect("keeps extra content that arrives before the tool identity", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({
+          tool_calls: [
+            { index: 0, extra_content: { google: { thought_signature: "sig_1" } }, function: { arguments: "{" } },
+          ],
+        }),
+        deltaChunk({ tool_calls: [{ index: 0, id: "call_1", function: { name: "lookup", arguments: "}" } }] }),
+        deltaChunk({}, "tool_calls"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall).map((event) => event.providerMetadata)).toEqual([
+        { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+      ])
+    }),
+  )
+
   it.effect("does not finalize streamed tool calls when content is filtered", () =>
     Effect.gen(function* () {
       const body = sseEvents(

packages/ai/test/provider/xai-responses.test.ts

@@ -56,7 +56,9 @@ describe("xAI Responses route", () => {
       expect(XAIResponses.protocol.body).not.toBe(OpenAIResponses.protocol.body)
 
       const prepared = yield* compileRequest(LLM.request({ model, prompt: "Hello" }))
+      expect(prepared.route).toBe("xai-responses")
       expect(prepared.protocol).toBe("xai-responses")
+      expect(prepared.model.route.providerMetadataKey).toBe("xai")
       expect(prepared.body.store).toBe(false)
       expect(prepared.body.include).toEqual(["reasoning.encrypted_content"])
     }),
@@ -298,3 +300,14 @@ describe("xAI Responses route", () => {
     }),
   )
 })
+
+it.effect("names the xAI Chat route separately from its OpenAI Chat protocol", () =>
+  Effect.gen(function* () {
+    const prepared = yield* compileRequest(
+      LLM.request({ model: XAI.configure({ apiKey: "test" }).chat("grok-4.6"), prompt: "Hello" }),
+    )
+    expect(prepared.route).toBe("xai-chat")
+    expect(prepared.protocol).toBe("openai-chat")
+    expect(prepared.model.route.providerMetadataKey).toBe("xai")
+  }),
+)

packages/ai/test/transcription.test.ts

@@ -3,7 +3,7 @@ import { Effect, Fiber, Layer, Stream } from "effect"
 import * as TestClock from "effect/testing/TestClock"
 import { HttpClientRequest } from "effect/unstable/http"
 import { Media, Transcription, TranscriptionClient, type TranscriptionEvent } from "../src/index.js"
-import { AssemblyAI, Deepgram, Google, OpenAI } from "../src/providers.js"
+import { AssemblyAI, Deepgram, ElevenLabs, Google, OpenAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
 import { dynamicResponse, json, observe, type Call } from "./lib/http.js"
 import { sseEvents } from "./lib/sse.js"
@@ -35,6 +35,9 @@ const formFields = (call: Call) =>
 const assemblyai = AssemblyAI.configure({ apiKey: "aai-key", baseURL: "https://assemblyai.test" }).transcription(
   "universal-3-5-pro",
 )
+const elevenlabs = ElevenLabs.configure({ apiKey: "test", baseURL: "https://elevenlabs.test" }).transcription(
+  "scribe_v2",
+)
 
 describe("Transcription", () => {
   it.effect("rejects what a route cannot honor before sending anything", () =>
@@ -459,6 +462,115 @@ describe("Transcription", () => {
     }),
   )
 
+  it.effect("rejects ElevenLabs prompts, webhooks, per-channel transcripts, and untimed diarization", () =>
+    Effect.gen(function* () {
+      const errors = yield* Effect.all(
+        [
+          Transcription.generate({ model: elevenlabs, audio, prompt: "OpenCode" }),
+          Transcription.generate({ model: elevenlabs, audio, providerOptions: { webhook: true } }),
+          Transcription.generate({ model: elevenlabs, audio, http: { body: { use_multi_channel: true } } }),
+          Transcription.generate({
+            model: elevenlabs,
+            audio,
+            diarize: true,
+            providerOptions: { timestamps_granularity: "none" },
+          }),
+          Transcription.generate({
+            model: elevenlabs,
+            audio: Media.ref("file_1", { provider: "elevenlabs", mediaType: "audio/mpeg" }),
+          }),
+        ].map((effect) => Effect.flip(effect)),
+      )
+      expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
+        [
+          ["UnsupportedOperation", "media.prompt"],
+          ["UnsupportedOperation", "transcription.webhook"],
+          ["UnsupportedOperation", "transcription.multichannel"],
+          ["UnsupportedOperation", "media.timestamps"],
+          ["InvalidRequest", false],
+        ],
+      )
+    }).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
+  )
+
+  it.effect("sends ElevenLabs URL audio as source_url and groups diarized words into speaker turns", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const token = (text: string, type: string, start: number, end: number, speaker_id?: string) => ({
+        text,
+        type,
+        start,
+        end,
+        speaker_id,
+        logprob: 0,
+      })
+      const response = yield* Transcription.generate({
+        model: elevenlabs,
+        audio: Media.url("https://a.test/call.mp3"),
+        language: "en",
+        speakers: 2,
+        providerOptions: { keyterms: ["OpenCode", "Scribe"], tag_audio_events: true, diarize: false },
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            observe(calls, input).pipe(
+              Effect.as(
+                json(input, {
+                  language_code: "ENG",
+                  text: "Ready? (laughs) Yes. Go",
+                  words: [
+                    token("Ready?", "word", 0, 0.5, "speaker_0"),
+                    token(" ", "spacing", 0.5, 0.6, "speaker_0"),
+                    token("(laughs)", "audio_event", 0.6, 1, "speaker_0"),
+                    token(" ", "spacing", 1, 1.1, "speaker_0"),
+                    token("Yes.", "word", 1.2, 1.5, "speaker_1"),
+                    token(" ", "spacing", 1.5, 1.6, "speaker_1"),
+                    token("Go", "word", 1.6, 1.9, "speaker_0"),
+                  ],
+                  transcription_id: "tr_1",
+                  audio_duration_secs: 2,
+                }),
+              ),
+            ),
+          ),
+        ),
+      )
+
+      // `observe` re-encodes the FormData with a new boundary, so read the boundary from the sent body.
+      const boundary = /^--(\S+)/.exec(calls[0].body)?.[1]
+      const form = yield* Effect.promise(() =>
+        new Response(calls[0].body, {
+          headers: { "content-type": `multipart/form-data; boundary=${boundary}` },
+        }).formData(),
+      )
+      expect(calls[0].url).toBe("https://elevenlabs.test/v1/speech-to-text")
+      expect(calls[0].headers.get("xi-api-key")).toBe("test")
+      expect(Array.from(form.entries())).toEqual([
+        ["model_id", "scribe_v2"],
+        ["source_url", "https://a.test/call.mp3"],
+        ["language_code", "en"],
+        ["diarize", "true"],
+        ["num_speakers", "2"],
+        ["keyterms", "OpenCode"],
+        ["keyterms", "Scribe"],
+        ["tag_audio_events", "true"],
+      ])
+      expect(response.segments).toEqual([
+        { text: "Ready?", startSeconds: 0, endSeconds: 0.5, speaker: "speaker_0" },
+        { text: "Yes.", startSeconds: 1.2, endSeconds: 1.5, speaker: "speaker_1" },
+        { text: "Go", startSeconds: 1.6, endSeconds: 1.9, speaker: "speaker_0" },
+      ])
+      expect(response.words?.map((word) => [word.text, word.speaker, word.confidence])).toEqual([
+        ["Ready?", "speaker_0", 1],
+        ["Yes.", "speaker_1", 1],
+        ["Go", "speaker_0", 1],
+      ])
+      expect(response.language).toBe("eng")
+      expect(response.usage).toEqual({ type: "seconds", seconds: 2 })
+      expect(response.providerMetadata).toEqual({ elevenlabs: { transcriptionId: "tr_1" } })
+    }),
+  )
+
   it.effect("rejects reading an AssemblyAI result before the transcript finishes", () =>
     Effect.gen(function* () {
       const generation = yield* Transcription.resume(assemblyai, { transcriptID: "tr_1" })

packages/ai/test/video.test.ts

@@ -1,9 +1,10 @@
 import { describe, expect } from "bun:test"
-import { Effect, Layer, Stream } from "effect"
+import { Effect, Fiber, Layer, Stream } from "effect"
+import * as TestClock from "effect/testing/TestClock"
 import { Media, Video, VideoClient, type GenerationEvent, type VideoEvent } from "../src/index.js"
 import { Fal, Google, Runway, XAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
-import { dynamicResponse, json, observe, settle, type Call } from "./lib/http.js"
+import { dynamicResponse, json, observe, settle, type Call, type HandlerInput } from "./lib/http.js"
 
 const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
   VideoClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -162,27 +163,39 @@ describe("Video / Google Veo", () => {
     ),
   )
 
-  it.effect("surfaces an operation error as a failed generation with the provider body", () =>
-    Effect.gen(function* () {
-      const failure = {
-        name: operation,
-        done: true,
-        error: { code: 3, message: "Prompt violates policy", status: "INVALID_ARGUMENT" },
-      }
-      const error = yield* Video.generate({ model, prompt: "nope" }).pipe(
-        Effect.flip,
-        Effect.provide(
-          layer((input) =>
-            Effect.succeed(input.request.method === "POST" ? json(input, { name: operation }) : json(input, failure)),
-          ),
-        ),
-      )
-      expect(error.reason._tag).toBe("ProviderInternal")
-      expect(error.message).toBe("Google Veo operation failed: Prompt violates policy")
-      expect(error.reason.body).toBe(JSON.stringify(failure))
-      expect(error.reason.http?.status).toBe(200)
-    }),
-  )
+  for (const terminal of [
+    { error: { code: 3, message: "Prompt violates policy", status: "INVALID_ARGUMENT" }, tag: "InvalidRequest" },
+    { error: { code: 9, message: "Unsupported resolution", status: "FAILED_PRECONDITION" }, tag: "InvalidRequest" },
+    { error: { code: 11, message: "Duration out of range", status: "OUT_OF_RANGE" }, tag: "InvalidRequest" },
+    { error: { code: 7, message: "Permission denied", status: "PERMISSION_DENIED" }, tag: "Authentication" },
+    { error: { code: 16, message: "Invalid credentials", status: "UNAUTHENTICATED" }, tag: "Authentication" },
+    { error: { code: 8, message: "Quota exceeded", status: "RESOURCE_EXHAUSTED" }, tag: "RateLimit" },
+    { error: { code: 13, message: "Internal error", status: "INTERNAL" }, tag: "ProviderInternal" },
+    { error: { code: 14, message: "Service unavailable", status: "UNAVAILABLE" }, tag: "ProviderInternal" },
+    { error: { message: "Something broke" }, tag: "ProviderInternal" },
+  ]) {
+    it.effect(
+      `surfaces ${terminal.error.status ?? "an uncoded"} operation error as ${terminal.tag} with the provider body`,
+      () =>
+        Effect.gen(function* () {
+          const failure = { name: operation, done: true, error: terminal.error }
+          const error = yield* Video.generate({ model, prompt: "nope" }).pipe(
+            Effect.flip,
+            Effect.provide(
+              layer((input) =>
+                Effect.succeed(
+                  input.request.method === "POST" ? json(input, { name: operation }) : json(input, failure),
+                ),
+              ),
+            ),
+          )
+          expect(error.reason._tag).toBe(terminal.tag)
+          expect(error.message).toBe(`Google Veo operation failed: ${terminal.error.message}`)
+          expect(error.reason.body).toBe(JSON.stringify(failure))
+          expect(error.reason.http?.status).toBe(200)
+        }),
+    )
+  }
 
   it.effect("reports fully filtered output as a content policy failure", () =>
     Effect.gen(function* () {
@@ -332,12 +345,37 @@ describe("Video / xAI", () => {
   for (const terminal of [
     {
       body: { status: "failed", error: { code: "invalid_argument", message: "Prompt cannot be empty." } },
-      tag: "ProviderInternal",
+      tag: "InvalidRequest",
       message: "xAI Video generation failed (invalid_argument): Prompt cannot be empty.",
     },
+    {
+      body: { status: "failed", error: { code: "failed_precondition", message: "Extension is not supported." } },
+      tag: "InvalidRequest",
+      message: "xAI Video generation failed (failed_precondition): Extension is not supported.",
+    },
+    {
+      body: { status: "failed", error: { code: "permission_denied", message: "Team lacks access." } },
+      tag: "Authentication",
+      message: "xAI Video generation failed (permission_denied): Team lacks access.",
+    },
+    {
+      body: { status: "failed", error: { code: "service_unavailable", message: "Overloaded." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (service_unavailable): Overloaded.",
+    },
+    {
+      body: { status: "failed", error: { code: "internal_error", message: "Generation failed." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (internal_error): Generation failed.",
+    },
+    {
+      body: { status: "failed", error: { code: "constructor", message: "Future code." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (constructor): Future code.",
+    },
     { body: { status: "expired" }, tag: "InvalidRequest", message: "xAI Video request req_1 expired" },
   ]) {
-    it.effect(`surfaces ${terminal.body.status} generations with the provider body`, () =>
+    it.effect(`surfaces ${terminal.body.error?.code ?? terminal.body.status} generations with the provider body`, () =>
       Effect.gen(function* () {
         const error = yield* Video.generate({ model, prompt: "x" }).pipe(Effect.flip)
         expect(error.reason._tag).toBe(terminal.tag)
@@ -558,7 +596,10 @@ describe("Video / fal", () => {
   ]) {
     it.effect(`fails await for ${failure.name} with the response_url body and HTTP context`, () =>
       Effect.gen(function* () {
-        const error = yield* Video.generate({ model, prompt: "x" }).pipe(Effect.flip)
+        // A transient 500 on the result fetch is retried first; the body and HTTP context survive the final failure.
+        const fiber = yield* Effect.forkChild(Video.generate({ model, prompt: "x" }).pipe(Effect.flip))
+        yield* TestClock.adjust("5 minutes")
+        const error = yield* Fiber.join(fiber)
         expect(error.reason._tag).toBe(failure.tag)
         expect(error.reason.body).toBe(JSON.stringify(failure.result.body))
         expect(error.reason.http).toMatchObject({ url: urls.response, status: failure.result.status })
@@ -765,6 +806,11 @@ describe("Video / Runway", () => {
       tag: "ProviderInternal",
       message: "Runway task failed (INTERNAL.BAD_OUTPUT.CODE01): Something broke",
     },
+    {
+      body: { status: "FAILED", failure: "Unsupported dimensions", failureCode: "ASSET.INVALID" },
+      tag: "InvalidRequest",
+      message: "Runway task failed (ASSET.INVALID): Unsupported dimensions",
+    },
     { body: { status: "CANCELLED" }, tag: "InvalidRequest", message: "Runway task task_1 was cancelled" },
   ]) {
     it.effect(`surfaces ${terminal.body.failureCode ?? terminal.body.status} with the task body`, () =>
@@ -908,6 +954,169 @@ describe("Video / Runway", () => {
   )
 })
 
+// ---------------------------------------------------------------------------
+// Transient read failures
+// ---------------------------------------------------------------------------
+
+describe("Video / transient read failures", () => {
+  const model = Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5")
+  const succeeded = { id: "task_1", status: "SUCCEEDED", output: ["https://runway.test/out.mp4"] }
+  const failure = (input: HandlerInput, status: number, headers?: Record<string, string>) =>
+    json(input, { error: `HTTP ${status}` }, { status, headers })
+  const methods = (calls: ReadonlyArray<Call>) => calls.map((call) => call.method)
+
+  it.effect("retries a 503 status poll and a 503 result read, then returns the result", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const response = yield* settle(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second" } }),
+        5,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              // 1: status fails, 2: status succeeds, 3: result fails, 4: result succeeds.
+              if (nth === 1 || nth === 3) return failure(input, 503)
+              return json(input, succeeded)
+            }),
+          ),
+        ),
+      )
+      expect(response.video.source).toMatchObject({ type: "url", url: "https://runway.test/out.mp4" })
+      expect(methods(calls)).toEqual(["POST", "GET", "GET", "GET", "GET"])
+    }),
+  )
+
+  it.effect("waits for a 429 retry-after before polling again", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const fiber = yield* Effect.forkChild(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second" } }).pipe(
+          Effect.provide(
+            layer((input) =>
+              Effect.gen(function* () {
+                const { call, nth } = yield* observe(calls, input)
+                if (call.method === "POST") return json(input, { id: "task_1" })
+                if (nth === 1) return failure(input, 429, { "retry-after": "10" })
+                return json(input, succeeded)
+              }),
+            ),
+          ),
+        ),
+      )
+      yield* TestClock.adjust("9 seconds")
+      expect(methods(calls)).toEqual(["POST", "GET"])
+      yield* TestClock.adjust("1 second")
+      yield* Fiber.join(fiber)
+      expect(methods(calls)).toEqual(["POST", "GET", "GET", "GET"])
+    }),
+  )
+
+  it.effect("fails a 400 status poll without retrying", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Video.generate({ model, prompt: "x" }).pipe(
+        Effect.flip,
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              return call.method === "POST" ? json(input, { id: "task_1" }) : failure(input, 400)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("InvalidRequest")
+      expect(methods(calls)).toEqual(["POST", "GET"])
+    }),
+  )
+
+  it.effect("stops retrying at poll.timeout with a Timeout reason", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* settle(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second", timeout: "5 seconds" } }).pipe(
+          Effect.flip,
+        ),
+        6,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              return call.method === "POST" ? json(input, { id: "task_1" }) : failure(input, 503)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("Timeout")
+      expect(calls.filter((call) => call.method === "GET").length).toBeGreaterThan(1)
+    }),
+  )
+
+  it.effect("bounds a streamed result read's retries by poll.timeout", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* settle(
+        Video.stream({ model, prompt: "x" }, { poll: { interval: "1 second", timeout: "5 seconds" } }).pipe(
+          Stream.runCollect,
+          Effect.flip,
+        ),
+        6,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              return nth === 1 ? json(input, succeeded) : failure(input, 503)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("Timeout")
+      expect(calls.filter((call) => call.method === "GET").length).toBeGreaterThan(2)
+    }),
+  )
+
+  it.effect("never retries a failed submit", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Video.generate({ model, prompt: "x" }).pipe(
+        Effect.flip,
+        Effect.provide(layer((input) => observe(calls, input).pipe(Effect.map(() => failure(input, 503))))),
+      )
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(methods(calls)).toEqual(["POST"])
+    }),
+  )
+
+  it.effect("never retries a failed cancel", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Effect.gen(function* () {
+        const generation = yield* Video.start({ model, prompt: "x" })
+        return yield* generation.cancel().pipe(Effect.flip)
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              if (call.method === "DELETE") return failure(input, 503)
+              return json(input, { id: "task_1", status: "RUNNING" })
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(methods(calls)).toEqual(["POST", "GET", "DELETE"])
+    }),
+  )
+})
+
 // ---------------------------------------------------------------------------
 // Shared queued behavior
 // ---------------------------------------------------------------------------

packages/cli/src/commands/commands.ts

@@ -51,7 +51,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
     ),
     session: Flag.string("session").pipe(
       Flag.withAlias("s"),
-      Flag.withDescription("Session ID to continue"),
+      Flag.withDescription("Session ID to continue, or to create if it does not exist"),
       Flag.optional,
     ),
     prompt: Flag.string("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
@@ -328,7 +328,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         ),
         session: Flag.string("session").pipe(
           Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
           Flag.optional,
         ),
         fork: Flag.boolean("fork").pipe(
@@ -368,7 +368,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         ),
         session: Flag.string("session").pipe(
           Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
           Flag.optional,
         ),
         fork: Flag.boolean("fork").pipe(

packages/cli/src/commands/handlers/default.ts

@@ -11,6 +11,10 @@ import { UpdatePreflight } from "../../services/update-preflight"
 import { Npm } from "@opencode/util/npm"
 import { OPENCODE_ARTIFACT, OPENCODE_CHANNEL, OPENCODE_VERSION } from "../../version"
 import { Env } from "../../env"
+import { Service } from "@opencode/client/effect/service"
+import { OpenCode } from "@opencode/client/promise"
+import { findSession } from "../../session-target"
+import { errorMessage } from "../../util/error"
 
 export default Runtime.handler(Commands, (input) =>
   Effect.gen(function* () {
@@ -46,6 +50,15 @@ export default Runtime.handler(Commands, (input) =>
         Effect.promise(() => preflight.fail("OpenCode update could not start the new background service")),
       ),
     )
+    const session = Option.getOrUndefined(input.session)
+    // A missing --session ID becomes the ID of the session the first prompt creates.
+    const sessionExists =
+      session !== undefined &&
+      (yield* Effect.tryPromise({
+        try: () =>
+          findSession(OpenCode.make({ baseUrl: server.endpoint.url, headers: Service.headers(server.endpoint) }), session),
+        catch: (cause) => new Error(errorMessage(cause)),
+      })) !== undefined
     const updater = yield* Updater.Service
     let installing: string | undefined
     const updateListeners = new Set<(version: string) => void>()
@@ -81,7 +94,8 @@ export default Runtime.handler(Commands, (input) =>
       },
       args: {
         continue: input.continue,
-        sessionID: Option.getOrUndefined(input.session),
+        sessionID: sessionExists ? session : undefined,
+        newSessionID: sessionExists ? undefined : session,
         prompt: Option.getOrUndefined(input.prompt),
         auto: input.auto || input.yolo || input.dangerouslySkipPermissions,
       },

packages/cli/src/run/noninteractive.ts

@@ -135,6 +135,7 @@ export async function runNonInteractivePrompt(input: Input) {
   const replyPermission = async (request: { id: string; action: string; resources: ReadonlyArray<string> }) => {
     if (!input.auto) {
       permissionRejected = true
+      if (input.compatibility !== "v1") process.exitCode = 1
       UI.println(
         UI.Style.TEXT_WARNING_BOLD + "!",
         UI.Style.TEXT_NORMAL +
@@ -163,6 +164,7 @@ export async function runNonInteractivePrompt(input: Input) {
       if (!formAlreadySettled(error)) throw error
     }
     formCancelled = true
+    if (input.compatibility !== "v1") process.exitCode = 1
   }
 
   const consume = async () => {
@@ -493,7 +495,8 @@ export async function runNonInteractivePrompt(input: Input) {
       if (event.type === "session.execution.interrupted") {
         if (input.compatibility === "v1" && (permissionRejected || formCancelled)) return
         if (event.data.reason === "user" && interrupted) process.exitCode = 130
-        if (event.data.reason !== "user" && !emittedError) {
+        // A declined tool call ends the step with an interruption; it was already reported above.
+        if (event.data.reason !== "user" && !emittedError && !permissionRejected && !formCancelled) {
           emittedError = true
           process.exitCode = 1
           const error = { type: "aborted" as const, message: `Session interrupted: ${event.data.reason}` }
@@ -620,7 +623,9 @@ export async function runNonInteractivePrompt(input: Input) {
         UI.error(item.state.error.message)
       }
 
-      if (message.error && !emittedError) {
+      // A declined tool call ends its step with an interrupted-step error that is
+      // only a consequence of our own rejection; it was already reported above.
+      if (message.error && !emittedError && !permissionRejected && !formCancelled) {
         emittedError = true
         process.exitCode = 1
         if (!emit("error", timestamp, { error: message.error })) UI.error(message.error.message)

packages/cli/src/session-target.ts

@@ -63,6 +63,7 @@ export async function resolveSessionTarget(input: {
     (await input.client.session
       .create(
         {
+          id: input.session,
           agent: prepared.agent,
           model: prepared.model,
           location: { directory: location.directory },
@@ -101,14 +102,11 @@ async function selectSession(input: {
   fork?: boolean
   signal?: AbortSignal
 }) {
-  const explicit = input.session
-    ? await input.client.session.get({ sessionID: input.session }, ...requestOptions(input.signal)).catch((error) => {
-        if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError")
-          return undefined
-        throw error
-      })
-    : undefined
-  if (input.session && !explicit) throw new Error("Session not found")
+  const explicit = input.session ? await findSession(input.client, input.session, input.signal) : undefined
+  if (input.session && !explicit) {
+    if (input.fork) throw new Error("Session not found")
+    return { session: undefined }
+  }
   if (explicit)
     return {
       session: input.fork
@@ -133,6 +131,13 @@ async function selectSession(input: {
   }
 }
 
+export function findSession(client: OpenCodeClient, sessionID: string, signal?: AbortSignal) {
+  return client.session.get({ sessionID }, ...requestOptions(signal)).catch((error) => {
+    if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError") return undefined
+    throw error
+  })
+}
+
 async function latestSession(
   client: OpenCodeClient,
   location: LocationGetOutput,

packages/cli/test/run/noninteractive.test.ts

@@ -309,6 +309,7 @@ async function capture(input: Parameters<typeof run>[0]) {
 
 afterEach(() => {
   mock.restore()
+  process.exitCode = 0
 })
 
 describe("runNonInteractivePrompt", () => {
@@ -433,6 +434,7 @@ describe("runNonInteractivePrompt", () => {
     expect(sdk.form.list).toHaveBeenCalledWith({
       location: { directory: "/work tree" },
     })
+    expect(process.exitCode).toBe(1)
   })
 
   test("attach mode cancels only session-owned forms", async () => {
@@ -448,6 +450,7 @@ describe("runNonInteractivePrompt", () => {
       { sessionID: "global", formID: "frm_pending_global" },
       expect.anything(),
     )
+    expect(process.exitCode).toBe(1)
   })
 
   test("V1 JSON output flushes step_start before an unrelated step failure", async () => {

packages/cli/test/session-target.test.ts

@@ -42,6 +42,28 @@ describe("session target resolver", () => {
     })
   })
 
+  test("creates a missing explicit Session with its ID", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.session, "get").mockRejectedValue({ _tag: "SessionNotFoundError" })
+    spyOn(client.location, "get").mockResolvedValue(location("/project"))
+    const create = spyOn(client.session, "create").mockResolvedValue(session("ses_chosen", "/project"))
+
+    const target = await resolveSessionTarget({ client, session: "ses_chosen", prepare })
+    expect(create).toHaveBeenCalledWith(expect.objectContaining({ id: "ses_chosen" }))
+    expect(target).toMatchObject({ session: { id: "ses_chosen" }, resume: false })
+  })
+
+  test("does not create a missing explicit Session to fork", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.session, "get").mockRejectedValue({ _tag: "SessionNotFoundError" })
+    const create = spyOn(client.session, "create")
+
+    await expect(resolveSessionTarget({ client, session: "ses_chosen", fork: true, prepare })).rejects.toThrow(
+      "Session not found",
+    )
+    expect(create).not.toHaveBeenCalled()
+  })
+
   test("paginates to continue the exact directory", async () => {
     const client = OpenCode.make({ baseUrl: "https://opencode.test" })
     spyOn(client.location, "get").mockResolvedValue(location("/project"))

packages/core/package.json

@@ -66,12 +66,6 @@
       "node": "./src/shell/parser-wasm.node.ts",
       "default": "./src/shell/parser-wasm.bun.ts"
     },
-    "#process-lock-ffi": {
-      "workerd": "./src/util/process-lock-ffi.workerd.ts",
-      "bun": "./src/util/process-lock-ffi.bun.ts",
-      "node": "./src/util/process-lock-ffi.node.ts",
-      "default": "./src/util/process-lock-ffi.bun.ts"
-    },
     "#v1-migration": {
       "types": "./src/database/v1-migration.bun.ts",
       "bun": "./src/database/v1-migration.bun.ts",

packages/core/script/build.ts

@@ -26,7 +26,6 @@ const result = await Bun.build({
     "#fff",
     "#photon-wasm",
     "#shell-parser-wasm",
-    "#process-lock-ffi",
     "#v1-migration",
   ],
   splitting: true,

packages/core/src/file-access.ts

@@ -30,12 +30,6 @@ export interface ExternalDirectoryAuthorization {
   readonly save: string
 }
 
-export const externalDirectoryPermission = (input: ExternalDirectoryAuthorization) => ({
-  action: input.action,
-  resources: [input.resource],
-  save: [input.save],
-})
-
 export interface Target {
   readonly absolute: AbsolutePath
   /** Location-relative for internal paths, absolute for external paths. */

packages/core/src/file.ts

@@ -1,6 +0,0 @@
-export * as File from "./file.js"
-
-import { FileDiff } from "@opencode/schema/file-diff"
-
-export const Diff = FileDiff.Info
-export type Diff = typeof Diff.Type

packages/core/src/generate.ts

@@ -1,6 +1,7 @@
 export * as Generate from "./generate.js"
 
 import { LLM, LLMClient, AIError } from "@opencode/ai"
+import { SessionID } from "@opencode/schema/session-id"
 import { Context, Effect, Layer, Schema } from "effect"
 import { makeLocationNode } from "@opencode/util/effect/app-node"
 import { llmClient } from "./effect/app-node-platform.js"
@@ -60,15 +61,24 @@ export const layer = Layer.effect(
             ? `Model unavailable: ${input.model.providerID}/${input.model.id}`
             : "No model specified and no supported model is available",
         })
-      const response = yield* llm.generate(LLM.request({ model: resolved.model, prompt: input.prompt })).pipe(
-        Effect.mapError(
-          (error: AIError) =>
-            new UnavailableError({
-              message: error.message,
-              service: resolved.ref.providerID,
-            }),
-        ),
-      )
+      const response = yield* llm
+        .generate(
+          LLM.request({
+            model: resolved.model,
+            prompt: input.prompt,
+            // Gateways require session attribution even for a stateless call; no Session is stored.
+            http: { headers: { "x-opencode-session": SessionID.create() } },
+          }),
+        )
+        .pipe(
+          Effect.mapError(
+            (error: AIError) =>
+              new UnavailableError({
+                message: error.message,
+                service: resolved.ref.providerID,
+              }),
+          ),
+        )
       return response.text
     })
 

packages/core/src/git.ts

@@ -7,7 +7,7 @@ import { AbsolutePath, RelativePath } from "./schema.js"
 import { FSUtil } from "@opencode/util/fs-util"
 import { AppProcess } from "@opencode/util/process"
 import { makeGlobalNode } from "@opencode/util/effect/app-node"
-import { File } from "./file.js"
+import { FileDiff } from "@opencode/schema/file-diff"
 import { KeyedMutex } from "./effect/keyed-mutex.js"
 import { VcsPatch } from "./vcs/patch.js"
 import { gitExecutable } from "./util/git-executable.js"
@@ -152,7 +152,7 @@ export interface Interface {
       to: TreeID
       context?: number
       paths?: readonly RelativePath[]
-    }) => Effect.Effect<readonly File.Diff[], OperationError>
+    }) => Effect.Effect<readonly FileDiff.Info[], OperationError>
     readonly restore: (input: {
       repository: Repository
       files: ReadonlyMap<RelativePath, TreeID>
@@ -571,7 +571,7 @@ const layer = Layer.effect(
           additions: stat?.additions ?? 0,
           deletions: stat?.deletions ?? 0,
           patch: stat?.binary ? "" : (patches.get(entry.file) ?? VcsPatch.emptyPatch(entry.file)),
-        } satisfies File.Diff
+        } satisfies FileDiff.Info
       })
     })
 

packages/core/src/instance.ts

@@ -152,7 +152,7 @@ export function layer(ref: Location.Ref, options: Options = {}): Layer.Layer<Ser
   const replacements: LayerNode.Replacements = [
     ...(options.discovery === false ? vanillaReplacements : []),
     ...(options.replacements ?? []),
-    Location.node.replace(Location.boundNode(ref, { discovery: options.discovery })),
+    Location.node.replace(Location.boundNode(ref)),
     InstancePlugins.node.replace(InstancePlugins.bound(options.plugins ?? [])),
   ]
 

packages/core/src/instructions/builtins.ts

@@ -2,13 +2,12 @@ export * as InstructionBuiltIns from "./builtins.js"
 
 import { makeLocationNode } from "@opencode/util/effect/app-node"
 import { Context, DateTime, Effect, Layer, Schema } from "effect"
-import type { Session } from "@opencode/schema/session"
 import { Global } from "@opencode/util/global"
 import { Location } from "../location.js"
 import { Instructions } from "./index.js"
 
 export interface Interface {
-  readonly load: (sessionID: Session.ID) => Effect.Effect<Instructions.List>
+  readonly load: () => Effect.Effect<Instructions.List>
 }
 
 export class Service extends Context.Service<Service, Interface>()("@opencode/InstructionBuiltIns") {}
@@ -19,16 +18,24 @@ const layer = Layer.effect(
     const global = yield* Global.Service
     const location = yield* Location.Service
     return Service.of({
-      load: (sessionID) =>
+      load: () =>
         Effect.succeed(
           Instructions.combine([
+            Instructions.make({
+              key: Instructions.Key.make("core/date"),
+              codec: Schema.toCodecJson(Schema.String),
+              read: DateTime.nowAsDate.pipe(Effect.map((date) => date.toDateString())),
+              render: {
+                initial: (date) => `Today's date: ${date}`,
+                changed: (_previous, date) => `Today's date is now: ${date}`,
+              },
+            }),
             Instructions.make({
               key: Instructions.Key.make("core/environment"),
               codec: Schema.toCodecJson(Schema.String),
               read: Effect.sync(() =>
                 [
                   "<env>",
-                  `  Current conversation session ID: ${sessionID}`,
                   `  Working directory: ${location.directory}`,
                   `  Workspace root folder: ${location.project.directory}`,
                   `  Is directory a git repo: ${location.vcs?.type === "git" ? "yes" : "no"}`,
@@ -44,15 +51,6 @@ const layer = Layer.effect(
                   ["The environment you are running in is now:", environment].join("\n"),
               },
             }),
-            Instructions.make({
-              key: Instructions.Key.make("core/date"),
-              codec: Schema.toCodecJson(Schema.String),
-              read: DateTime.nowAsDate.pipe(Effect.map((date) => date.toDateString())),
-              render: {
-                initial: (date) => `Today's date: ${date}`,
-                changed: (_previous, date) => `Today's date is now: ${date}`,
-              },
-            }),
           ]),
         ),
     })

packages/core/src/location-mutation.ts

@@ -1,3 +0,0 @@
-/** @deprecated Use FileAccess for path resolution and authorization. */
-export { FileAccess as LocationMutation } from "./file-access.js"
-export * from "./file-access.js"

packages/core/src/location-services.ts

@@ -8,7 +8,6 @@ import { LocationServiceMap } from "./location-service-map.js"
 export { LocationServiceMap } from "./location-service-map.js"
 
 export type LocationServices = Instance.Services
-export type LocationError = Instance.Error
 
 export function buildLocationServiceMap(
   replacements: LayerNode.Replacements = [],

packages/core/src/location.ts

@@ -16,12 +16,12 @@ export class Service extends Context.Service<Service, Interface>()("@opencode/Lo
 
 export const node = LayerNode.unbound(Service, tags.values.location)
 
-const layer = (ref: Ref, options?: { readonly discovery?: boolean }) =>
+const layer = (ref: Ref) =>
   Layer.effect(
     Service,
     Effect.gen(function* () {
       const project = yield* Project.Service
-      const resolved = yield* project.resolve(ref.directory, options)
+      const resolved = yield* project.resolve(ref.directory)
       return Service.of({
         directory: ref.directory,
         workspaceID: ref.workspaceID,
@@ -31,9 +31,9 @@ const layer = (ref: Ref, options?: { readonly discovery?: boolean }) =>
     }),
   )
 
-export const boundNode = (ref: Ref, options?: { readonly discovery?: boolean }) =>
+export const boundNode = (ref: Ref) =>
   makeLocationNode({
     service: Service,
-    layer: layer(ref, options),
+    layer: layer(ref),
     deps: [Project.node],
   })

packages/core/src/mcp/index.ts

@@ -45,8 +45,6 @@ export const ResourceTemplate = Mcp.ResourceTemplate
 export type ResourceTemplate = Mcp.ResourceTemplate
 export const ResourceCatalog = Mcp.ResourceCatalog
 export type ResourceCatalog = Mcp.ResourceCatalog
-export const ResourceContentPart = Mcp.ResourceContentPart
-export type ResourceContentPart = Mcp.ResourceContentPart
 export const ResourceContent = Mcp.ResourceContent
 export type ResourceContent = Mcp.ResourceContent
 

packages/core/src/plugin/provider/cloudflare-ai-gateway.ts

@@ -1,55 +1,62 @@
 import { Effect } from "effect"
+import { isArrayNonEmpty } from "effect/Array"
 import { define } from "@opencode/plugin/effect/plugin"
 import { Form } from "@opencode/schema/form"
 import { Provider } from "../../provider.js"
-import { iife } from "../../util/iife.js"
 import { configuredSettings } from "./configured.js"
 
 const providerID = Provider.ID.make("cloudflare-ai-gateway")
 
+const accountIdField = Form.StringField.make({
+  type: "string",
+  key: "accountId",
+  title: "Enter your Cloudflare Account ID",
+  placeholder: "e.g. 1234567890abcdef1234567890abcdef",
+  required: true,
+})
+
+const gatewayIdField = Form.StringField.make({
+  type: "string",
+  key: "gatewayId",
+  title: "Enter your Cloudflare AI Gateway ID",
+  placeholder: "e.g. my-gateway",
+  required: true,
+})
+
 export const CloudflareAIGatewayPlugin = define({
   id: "opencode.provider.cloudflare.ai.gateway",
   effect: Effect.fn(function* (ctx) {
+    const accountId = process.env.CLOUDFLARE_ACCOUNT_ID
+    const gatewayId = process.env.CLOUDFLARE_GATEWAY_ID
     const configured = yield* configuredSettings(providerID)
-    const form = iife(() => {
-      if (typeof configured?.baseURL === "string") return
-      const accountId = process.env.CLOUDFLARE_ACCOUNT_ID || stringOption(configured ?? {}, "accountId")
-      const gatewayId =
-        process.env.CLOUDFLARE_GATEWAY_ID ||
-        stringOption(configured ?? {}, "gatewayId") ||
-        stringOption(configured ?? {}, "gateway")
-      if (accountId && gatewayId) return
-      const accountIdForm = Form.StringField.make({
-        type: "string",
-        key: "accountId",
-        title: "Enter your Cloudflare Account ID",
-        placeholder: "e.g. 1234567890abcdef1234567890abcdef",
-        required: true,
-      })
-      const gatewayIdForm = Form.StringField.make({
-        type: "string",
-        key: "gatewayId",
-        title: "Enter your Cloudflare AI Gateway ID",
-        placeholder: "e.g. my-gateway",
-        required: true,
-      })
-      if (accountId) return Form.Fields.make([gatewayIdForm])
-      if (gatewayId) return Form.Fields.make([accountIdForm])
-      return Form.Fields.make([accountIdForm, gatewayIdForm])
-    })
+    const fields =
+      typeof configured?.baseURL === "string"
+        ? []
+        : [
+            ...(accountId || typeof configured?.accountId === "string" ? [] : [accountIdField]),
+            ...(gatewayId || typeof configured?.gatewayId === "string" ? [] : [gatewayIdField]),
+          ]
     yield* ctx.integration.transform((editor) => {
       editor.method.update({
         integrationID: providerID,
         method: {
           type: "key",
           label: "Gateway API token",
-          form,
+          form: isArrayNonEmpty(fields) ? Form.Fields.make(fields) : undefined,
         },
       })
     })
+    yield* ctx.provider.transform((evt) => {
+      const item = evt.get(providerID)
+      if (!item || (!accountId && !gatewayId)) return
+      evt.update(item.provider.id, (provider) => {
+        if (typeof provider.settings?.baseURL === "string") return
+        provider.settings = {
+          ...(accountId ? { accountId } : {}),
+          ...(gatewayId ? { gatewayId } : {}),
+          ...provider.settings,
+        }
+      })
+    })
   }),
 })
-
-function stringOption(options: Record<string, unknown>, key: string) {
-  return typeof options[key] === "string" ? options[key] : undefined
-}

packages/core/src/plugin/provider/cloudflare-workers-ai.ts

@@ -50,7 +50,7 @@ export const CloudflareWorkersAIPlugin = define({
 })
 
 function resolveAccountId(options: Record<string, unknown>) {
-  return process.env.CLOUDFLARE_ACCOUNT_ID ?? stringOption(options, "accountId")
+  return stringOption(options, "accountId") ?? process.env.CLOUDFLARE_ACCOUNT_ID
 }
 
 function workersEndpoint(accountId: string) {

packages/core/src/plugin/provider/github-copilot.ts

@@ -11,6 +11,7 @@ import { Model } from "../../model.js"
 import { Agent } from "../../agent.js"
 import { define } from "@opencode/plugin/effect/plugin"
 import { Provider } from "../../provider.js"
+import { SessionAffinity } from "../../session/affinity.js"
 import type { PluginInternal } from "../internal.js"
 
 const clientID = "Ov23li8tweQw6odWQebz"
@@ -272,7 +273,7 @@ export const GithubCopilotPlugin = define({
             .pipe(Effect.orElseSucceed(() => undefined))
           const interaction = interactionType(evt.kind, session?.parentID !== undefined)
           evt.headers["X-Interaction-Type"] = interaction
-          evt.headers["X-Interaction-Id"] = evt.sessionID
+          evt.headers["X-Interaction-Id"] = session ? SessionAffinity.get(session) : evt.sessionID
           if (interaction !== "conversation-agent") evt.headers["x-initiator"] = "agent"
         }),
       { providerID: Provider.ID.githubCopilot },