@opencode/ai 0.0.0-dev-20175 → 0.0.0-dev-20180

package/README.md

@@ -699,7 +699,7 @@ const program = Effect.gen(function* () {
 })
 ```
 
-The hosted result is represented as a provider-executed tool call and tool result, and the generated image is also emitted as a first-class `media` `LLMEvent` (`response.message` then carries a `media` part). Gemini image-capable models emit the same `media` event for inline image output. Retaining `response.message` preserves the generated image for continuation on both routes.
+The hosted result is represented as a provider-executed tool call and a tool result whose content carries the generated image as a file. Gemini image-capable models instead emit a first-class `media` `LLMEvent` for inline image output (`response.message` then carries a `media` part). Retaining `response.message` preserves the generated image for continuation on both routes.
 
 ## Video generation
 
@@ -840,9 +840,10 @@ Provider notes:
 - **OpenAI** streams over SSE (`stream_format: "sse"`), which is also the only place it reports token usage; `tts-1`
   and `tts-1-hd` do not support SSE and stream the raw audio body instead. `pcm` is 24 kHz 16-bit mono. `language`
   and `timestamps` are not supported.
-- **Gemini TTS** returns raw 16-bit PCM only (`audio/L16;codec=pcm;rate=24000`), so any `format` other than `pcm`
-  fails typed; wrap the samples yourself. Style is directed in the text, so `instructions` and `speed` fail typed.
-  Only `gemini-3.1-flash-tts-preview` and later support streaming. Two-speaker audio goes through
+- **Gemini TTS** returns the provider's default output: WAV for Gemini 3.8 TTS `generate`, raw 16-bit PCM
+  (`audio/L16;codec=pcm;rate=24000`) otherwise. `pcm` is the only explicit `format` it accepts, and it fails typed on
+  Gemini 3.8 `generate`; the route never wraps PCM as WAV. Style is directed in the text, so `instructions` and
+  `speed` fail typed. Only `gemini-3.1-flash-tts-preview` and later support streaming. Two-speaker audio goes through
   `providerOptions.speechConfig.multiSpeakerVoiceConfig`.
 - **ElevenLabs** requires `voice` (the path voice id) and authenticates with `xi-api-key`. `format` maps to the
   `output_format` query parameter (`mp3_44100_128`, `pcm_24000`, `wav_24000`, `opus_48000_64`);
@@ -944,6 +945,7 @@ const transcript = await generation.await({ poll: { interval: 3_000 } })
 - **`ImageClient`** — Effect service and layer for image execution, parallel to `LLMClient`.
 - **`Media`** — the shared asset type (`Media.Asset`, `Media.Source`) and constructors used by messages, tool results, and media requests.
 - **`Generation`** — provider-neutral handle for an in-flight media generation (`await`, `refresh`, `cancel`, `events`) used by queued media routes.
+- **`Video.request` / `generate` / `stream` / `start` / `resume`** — queued video generation through a provider-neutral request; `VideoClient` is its Effect service and layer.
 - **`Speech.request` / `Speech.generate` / `Speech.stream`** — text-to-speech through a provider-neutral request; `SpeechClient` is its Effect service and layer.
 - **`Transcription.request` / `generate` / `stream` / `start` / `resume`** — speech-to-text over inline, streaming, and queued routes; `TranscriptionClient` is its Effect service and layer.
 - **`AIClient.layer` / `AIClient.layerWith(executor)`** — every modality client plus the request executor in one layer.

package/dist/generation.d.ts

@@ -65,9 +65,10 @@ export declare class Generation<Response> {
     await(options?: AwaitOptions): Effect.Effect<Response, AIError>;
     cancel(): Effect.Effect<void, AIError>;
     /**
-     * Status observations as a stream, ending after the first terminal observation. Each poll is bounded by the time
-     * remaining until `poll.timeout`, so a hung status request fails the stream instead of stalling it. (`Stream.interruptWhen`
-     * would express this directly but deadlocks under `TestClock` when the source completes while the timer sleeps.)
+     * Status observations as a stream, ending after the first terminal observation. Each poll and each sleep between polls
+     * is bounded by the time remaining until `poll.timeout`, so a hung status request or a long interval fails the stream at
+     * the deadline instead of stalling it. (`Stream.interruptWhen` would express this directly but deadlocks under
+     * `TestClock` when the source completes while the timer sleeps.)
      */
     events(options?: AwaitOptions): Stream.Stream<Event, AIError>;
     private event;

package/dist/generation.js

@@ -62,9 +62,10 @@ export class Generation {
         return this.route.cancel ?? Effect.void;
     }
     /**
-     * Status observations as a stream, ending after the first terminal observation. Each poll is bounded by the time
-     * remaining until `poll.timeout`, so a hung status request fails the stream instead of stalling it. (`Stream.interruptWhen`
-     * would express this directly but deadlocks under `TestClock` when the source completes while the timer sleeps.)
+     * Status observations as a stream, ending after the first terminal observation. Each poll and each sleep between polls
+     * is bounded by the time remaining until `poll.timeout`, so a hung status request or a long interval fails the stream at
+     * the deadline instead of stalling it. (`Stream.interruptWhen` would express this directly but deadlocks under
+     * `TestClock` when the source completes while the timer sleeps.)
      */
     events(options) {
         if (this.terminal)
@@ -72,11 +73,16 @@ export class Generation {
         const timeout = Duration.fromInputUnsafe(options?.poll?.timeout ?? DEFAULT_POLL_TIMEOUT);
         return Stream.unwrap(Clock.currentTimeMillis.pipe(Effect.map((start) => {
             const deadline = start + Duration.toMillis(timeout);
-            const refresh = Clock.currentTimeMillis.pipe(Effect.flatMap((now) => this.refresh().pipe(Effect.timeoutOrElse({
-                duration: Duration.millis(Math.max(0, deadline - now)),
-                orElse: () => this.timeoutError(timeout),
-            }))));
-            return Stream.fromEffectSchedule(refresh, this.schedule(options?.poll)).pipe(Stream.takeUntil((generation) => generation.terminal), Stream.map((generation) => generation.event()));
+            // 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 schedule = this.schedule(options?.poll).pipe(Schedule.modifyDelay((meta) => Effect.succeed(Duration.min(meta.duration, Duration.millis(Math.max(0, deadline - meta.now))))));
+            return Stream.fromEffectSchedule(refresh, schedule).pipe(Stream.takeUntil((generation) => generation.terminal), Stream.map((generation) => generation.event()));
         })));
     }
     event() {

package/dist/protocols/deepgram-speech.js

@@ -38,6 +38,9 @@ const queryParameters = (request) => {
     });
 };
 const fromRequest = Effect.fn("DeepgramSpeech.fromRequest")(function* (request) {
+    // Not in `unsupported`: that list would also reject `timestamps: false`, which asks for nothing.
+    if (request.timestamps === true)
+        return yield* route.unsupported("media.timestamps", `${route.name} does not return timestamps`);
     if (request.format !== undefined &&
         FORMATS[request.format] === undefined &&
         request.providerOptions?.encoding === undefined)
@@ -74,7 +77,7 @@ const finish = (state, context) => {
 // 7. Protocol and route
 // ---------------------------------------------------------------------------
 export const protocol = MediaProtocol.stream(route, {
-    unsupported: ["voice", "language", "instructions", "timestamps"],
+    unsupported: ["voice", "language", "instructions"],
     body: { from: fromRequest },
     frames: (bytes) => bytes,
     initial: () => ({ chunks: [] }),

package/dist/protocols/google-speech.js

@@ -20,6 +20,9 @@ const decodeChunk = route.decodeFrame(GenerateContentChunk);
 // 5. Request body construction
 // ---------------------------------------------------------------------------
 const fromRequest = Effect.fn("GoogleSpeech.fromRequest")(function* (request) {
+    // Not in `unsupported`: that list would also reject `timestamps: false`, which asks for nothing.
+    if (request.timestamps === true)
+        return yield* route.unsupported("media.timestamps", `${route.name} does not return timestamps`);
     if (request.format === "pcm" && request.mode === "generate" && /^gemini-3\.8-.*-tts(?:-|$)/.test(request.model.id))
         return yield* route.unsupported("media.format", `${route.name} returns WAV by default for Gemini 3.8 TTS unary requests; omit the format to accept it`);
     if (request.format !== undefined && request.format !== "pcm")
@@ -66,7 +69,7 @@ const finish = (state, context) => {
 // 7. Protocol and route
 // ---------------------------------------------------------------------------
 export const protocol = MediaProtocol.stream(route, {
-    unsupported: ["instructions", "speed", "timestamps"],
+    unsupported: ["instructions", "speed"],
     body: { from: fromRequest },
     frames: (bytes, context) => GeminiGenerateContent.frames(bytes, context.request.mode),
     initial: () => ({ chunks: [] }),

package/dist/protocols/openai-speech.js

@@ -31,6 +31,9 @@ const decodeEvent = route.decodeFrame(SpeechStreamEvent);
 // `sse` is not supported for `tts-1` or `tts-1-hd`; those models stream the raw audio body instead.
 const supportsSse = (model) => !/^tts-1(-hd)?(-|$)/.test(model);
 const fromRequest = Effect.fn("OpenAISpeech.fromRequest")(function* (request) {
+    // Not in `unsupported`: that list would also reject `timestamps: false`, which asks for nothing.
+    if (request.timestamps === true)
+        return yield* route.unsupported("media.timestamps", `${route.name} does not return timestamps`);
     return MediaProtocol.json(mergeJsonRecords({
         model: request.model.id,
         input: request.text,
@@ -80,7 +83,7 @@ const finish = (state, context) => {
 // 7. Protocol and route
 // ---------------------------------------------------------------------------
 export const protocol = MediaProtocol.stream(route, {
-    unsupported: ["language", "timestamps"],
+    unsupported: ["language"],
     body: { from: fromRequest },
     frames: (bytes, context) => (isSse(context.body) ? Framing.sse.frame(bytes) : bytes),
     initial: () => ({ chunks: [], done: false }),

package/dist/route/media.js

@@ -196,7 +196,11 @@ const encode = (body, headers) => {
         apply: HttpClientRequest.bodyFormData(body.value),
     };
 };
-/** Common fields are never silently dropped: a present field the protocol declared unsupported fails typed. */
+/**
+ * Common fields are never silently dropped: a present field the protocol declared unsupported fails typed. `false`
+ * counts as present because some booleans mean something when false (video `audio`); protocols reject opt-in
+ * booleans such as speech `timestamps` with `=== true` in `body.from` instead of listing them.
+ */
 const rejectUnsupported = (route, provider, request, unsupported) => {
     const present = (unsupported ?? []).filter((field) => {
         const value = request[field];

package/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "0.0.0-dev-20175",
+  "version": "0.0.0-dev-20180",
   "name": "@opencode/ai",
   "type": "module",
   "license": "MIT",
@@ -34,7 +34,7 @@
   "devDependencies": {
     "@clack/prompts": "1.0.0-alpha.1",
     "@effect/platform-node": "4.0.0-rc.112",
-    "@opencode/http-recorder": "0.0.0-dev-20175",
+    "@opencode/http-recorder": "0.0.0-dev-20180",
     "@tsconfig/bun": "1.0.9",
     "@types/bun": "1.4.0",
     "@typescript/native-preview": "7.0.0-dev.20251207.1",
@@ -44,7 +44,7 @@
     "@aws-sdk/credential-providers": "3.1057.0",
     "@smithy/eventstream-codec": "4.2.14",
     "@smithy/util-utf8": "4.2.2",
-    "@opencode/schema": "0.0.0-dev-20175",
+    "@opencode/schema": "0.0.0-dev-20180",
     "aws4fetch": "1.0.20",
     "effect": "4.0.0-rc.112",
     "google-auth-library": "10.5.0"