@opencode/ai 0.0.0-dev-20170 → 0.0.0-dev-20180

package/README.md

@@ -475,18 +475,18 @@ const program = Effect.gen(function* () {
 Common fields are portable in shape, not in support. Unsupported fields fail with a typed `AIError` before any network
 call rather than being dropped, so check this table before swapping only the `model`:
 
-| Provider              | `n` | `size`    | `aspectRatio` | `seed` | `format` | `images`                  | `mask`              |
-| --------------------- | --- | --------- | ------------- | ------ | -------- | ------------------------- | ------------------- |
-| OpenAI                | ✓¹  | ✓         | ✗             | ✗      | ✓        | ✓                         | ✓                   |
-| Google (Gemini)       | 1   | ✗         | ✓             | ✓      | ✗        | ✓ (no public URLs)        | ✗                   |
-| xAI                   | ✓   | ✗         | ✓             | ✗      | ✗        | ✓                         | ✗                   |
-| Z.ai                  | ✗   | ✓         | ✗             | ✗      | ✗        | ✗                         | ✗                   |
-| Meta                  | ✓   | ✓ (hint)  | ✗             | ✗      | ✓        | ✓                         | ✗                   |
-| Black Forest Labs     | 1   | per model | per model     | ✓      | ✓        | per model (1–8)           | `flux-pro-1.0-fill` |
-| fal                   | ✓   | per model | per model     | ✓      | ✓        | 1 (several on `/edit`)    | ✓                   |
-| Replicate             | ✗   | ✗         | ✗             | ✗      | ✗        | ✗ (use `providerOptions`) | ✗                   |
-| Stability `image`     | 1   | ✗         | ✓             | ✓      | ✓        | 1 (not on `core`)         | ✗                   |
-| Stability `upscale()` | ✗   | ✗         | ✗             | ✓      | ✓        | exactly 1 (required)      | ✗                   |
+| Provider              | `n` | `size`    | `aspectRatio` | `seed` | `format` | `images`                         | `mask`              |
+| --------------------- | --- | --------- | ------------- | ------ | -------- | -------------------------------- | ------------------- |
+| OpenAI                | ✓¹  | ✓         | ✗             | ✗      | ✓        | ✓                                | ✓                   |
+| Google (Gemini)       | 1   | ✗         | ✓             | ✓      | ✗        | ✓ (no public URLs)               | ✗                   |
+| xAI                   | ✓   | ✗         | ✓             | ✗      | ✗        | ✓                                | ✗                   |
+| Z.ai                  | ✗   | ✓         | ✗             | ✗      | ✗        | ✗                                | ✗                   |
+| Meta                  | ✓   | ✓ (hint)  | ✗             | ✗      | ✓        | ✓                                | ✗                   |
+| Black Forest Labs     | 1   | per model | per model     | ✓      | ✓        | per model (1–8)                  | `flux-pro-1.0-fill` |
+| fal                   | ✓   | per model | per model     | ✓      | ✓        | 1 (several on `/edit`, `/multi`) | ✓                   |
+| Replicate             | ✗   | ✗         | ✗             | ✗      | ✗        | ✗ (use `providerOptions`)        | ✗                   |
+| Stability `image`     | 1   | ✗         | ✓             | ✓      | ✓        | 1 (not on `core`)                | ✗                   |
+| Stability `upscale()` | ✗   | ✗         | ✗             | ✓      | ✓        | exactly 1 (required)             | ✗                   |
 
 ✓ lowers natively; ✗ fails whenever the field is set (including `n: 1`); `1` means `n > 1` fails. ¹ `Image.stream` on OpenAI generates one image. fal
 rejects `size` and `aspectRatio` together; which one a fal or BFL model takes depends on the model.
@@ -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

@@ -44,6 +44,7 @@ export type Event = Observation | {
     readonly id: string;
     readonly status: Status;
 };
+export declare const isTerminal: (status: Status) => boolean;
 export declare class Generation<Response> {
     readonly route: Route<Response>;
     /** Route-owned serializable JSON; pass it to the modality's `resume` from another process. */
@@ -64,9 +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

@@ -14,6 +14,7 @@ export const ProgressEvent = Schema.Struct({
     progress: Schema.optional(Schema.Number),
 }).annotate({ identifier: "Generation.Event.Progress" });
 const TERMINAL = new Set(["completed", "failed", "cancelled", "expired"]);
+export const isTerminal = (status) => TERMINAL.has(status);
 export class Generation {
     route;
     token;
@@ -40,7 +41,7 @@ export class Generation {
         };
     }
     get terminal() {
-        return TERMINAL.has(this.status);
+        return isTerminal(this.status);
     }
     refresh() {
         return this.route.status.pipe(Effect.map((snapshot) => new Generation(this.route, this.token, snapshot)));
@@ -61,9 +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)
@@ -71,11 +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/assemblyai-transcription.js

@@ -64,8 +64,10 @@ const fromRequest = Effect.fn("AssemblyAITranscription.fromRequest")(function* (
         language_code: request.language,
         language_detection: request.language === undefined ? true : undefined,
         prompt: request.prompt,
-        // Turn-level `utterances`, the only segments AssemblyAI returns, require speaker labels.
-        speaker_labels: request.diarize === true || request.timestamps === "segment" ? true : undefined,
+        // Turn-level `utterances`, the only segments AssemblyAI returns, and `speakers_expected` require speaker labels.
+        speaker_labels: request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
+            ? true
+            : undefined,
         speakers_expected: request.speakers,
     }, request.providerOptions, request.http?.body) ?? {});
 });

package/dist/protocols/bfl-images.d.ts

@@ -12,21 +12,27 @@ export type BlackForestLabsImageOptions = {
     readonly steps?: number;
 } & Record<string, unknown>;
 export type Request = ImageRequestFor<BlackForestLabsImageOptions>;
-/** Regional clusters answer on different hosts, so the returned `polling_url` is followed verbatim. */
+/**
+ * Regional clusters answer on different hosts, so the returned `polling_url` is followed verbatim. BFL reports the
+ * credit cost on submit, so it rides on the token; it is optional so tokens persisted before it existed still decode.
+ */
 export declare const Token: Schema.Struct<{
     readonly id: Schema.String;
     readonly pollingURL: Schema.String;
+    readonly cost: Schema.optionalKey<Schema.Number>;
 }>;
 export type Token = Schema.Schema.Type<typeof Token>;
 export declare const protocol: MediaProtocol.Queued<Request, ImageResponse, {
     readonly id: string;
     readonly pollingURL: string;
+    readonly cost?: number | undefined;
 }>;
 export declare const model: (input: MediaRoute.ModelInput) => ImageModel<BlackForestLabsImageOptions>;
 export declare const BlackForestLabsImages: {
     readonly protocol: MediaProtocol.Queued<Request, ImageResponse, {
         readonly id: string;
         readonly pollingURL: string;
+        readonly cost?: number | undefined;
     }>;
     readonly model: (input: MediaRoute.ModelInput) => ImageModel<BlackForestLabsImageOptions>;
 };

package/dist/protocols/bfl-images.js

@@ -11,11 +11,19 @@ export const DEFAULT_BASE_URL = "https://api.bfl.ai";
 // ---------------------------------------------------------------------------
 // 2. Token and response schemas
 // ---------------------------------------------------------------------------
-/** Regional clusters answer on different hosts, so the returned `polling_url` is followed verbatim. */
-export const Token = Schema.Struct({ id: Schema.String, pollingURL: Schema.String });
+/**
+ * Regional clusters answer on different hosts, so the returned `polling_url` is followed verbatim. BFL reports the
+ * credit cost on submit, so it rides on the token; it is optional so tokens persisted before it existed still decode.
+ */
+export const Token = Schema.Struct({
+    id: Schema.String,
+    pollingURL: Schema.String,
+    cost: Schema.optionalKey(Schema.Number),
+});
 const StartResponse = Schema.Struct({
     id: Schema.String,
     polling_url: Schema.String,
+    cost: optionalNull(Schema.Number),
 });
 const Result = Schema.Struct({
     id: Schema.String,
@@ -93,7 +101,11 @@ const fromRequest = Effect.fn("BlackForestLabsImages.fromRequest")(function* (re
 // 6. Response decoding
 // ---------------------------------------------------------------------------
 const decodeStart = route.decodeStarted(StartResponse, (value) => ({
-    token: { id: value.id, pollingURL: value.polling_url },
+    token: {
+        id: value.id,
+        pollingURL: value.polling_url,
+        ...(value.cost === undefined || value.cost === null ? {} : { cost: value.cost }),
+    },
     snapshot: { id: value.id, status: "queued" },
 }));
 const decodeDocument = route.decodeJson(Result);
@@ -112,10 +124,12 @@ const decodeResult = Effect.fn("BlackForestLabsImages.decodeResult")(function* (
     if (status !== "completed" || document.result === undefined || document.result === null)
         return yield* output.invalid(`${route.name} generation ${context.token.id} has no result`);
     const { sample, seed, prompt, ...rest } = document.result;
+    // A settled `cost` on the result supersedes the submit-time cost carried on the token.
+    const cost = document.cost ?? context.token.cost;
     return new ImageResponse({
         // `sample` is a signed URL that expires 10 minutes after the result is ready, so it is downloaded now.
         images: [yield* context.materialize(Media.url(sample))],
-        usage: document.cost === undefined || document.cost === null ? undefined : { type: "credits", credits: document.cost },
+        usage: cost === undefined ? undefined : { type: "credits", credits: cost },
         providerMetadata: {
             bfl: { id: context.token.id, seed: seed ?? undefined, prompt: prompt ?? undefined, ...rest },
         },

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/fal-images.js

@@ -25,7 +25,7 @@ const QueueResult = Schema.StructWithRest(Schema.Struct({
 // 5. Request body construction
 // ---------------------------------------------------------------------------
 const sizing = (model) => {
-    if (/^fal-ai\/(nano-banana|flux-pro\/v1\.1-ultra)/.test(model))
+    if (/^fal-ai\/(nano-banana|flux-pro\/(v1\.1-ultra|kontext))/.test(model))
         return "aspect_ratio";
     if (model.startsWith("fal-ai/flux"))
         return "image_size";
@@ -40,16 +40,17 @@ const validate = (request) => {
         return Effect.fail(route.unsupported("media.size", `${id} sizes by aspectRatio`));
     if (request.aspectRatio !== undefined && field === "image_size")
         return Effect.fail(route.unsupported("media.aspectRatio", `${id} sizes by size (image_size)`));
-    if ((request.images?.length ?? 0) > 1 && !isEdit(id))
-        return Effect.fail(route.unsupported("media.images", `${id} takes one image_url; use an /edit endpoint for several images`));
+    if ((request.images?.length ?? 0) > 1 && !takesImageList(id))
+        return Effect.fail(route.unsupported("media.images", `${id} takes one image_url; use an /edit or /multi endpoint for several images`));
     return Effect.void;
 };
-// `/edit` endpoints take an `image_urls` list; image-to-image, fill, and Ultra take one `image_url` (beside `mask_url`).
-const isEdit = (model) => model.endsWith("/edit");
+// `/edit` and `/multi` (Kontext) endpoints take an `image_urls` list; image-to-image, fill, and Ultra take one
+// `image_url` (beside `mask_url`).
+const takesImageList = (model) => model.endsWith("/edit") || model.endsWith("/multi");
 const fromRequest = Effect.fn("FalImages.fromRequest")(function* (request) {
     yield* validate(request);
     const images = yield* Effect.forEach(request.images ?? [], (image) => FalQueue.mediaUrl(image, route.name));
-    const edit = isEdit(request.model.id);
+    const list = takesImageList(request.model.id);
     return MediaProtocol.json(mergeJsonRecords({
         prompt: request.prompt,
         num_images: request.n,
@@ -57,8 +58,8 @@ const fromRequest = Effect.fn("FalImages.fromRequest")(function* (request) {
         image_size: request.size === undefined ? undefined : MediaInput.dimensions(request.size),
         aspect_ratio: request.aspectRatio,
         output_format: request.format,
-        image_urls: edit && images.length > 0 ? images : undefined,
-        image_url: edit ? undefined : images[0],
+        image_urls: list && images.length > 0 ? images : undefined,
+        image_url: list ? undefined : images[0],
         mask_url: request.mask === undefined ? undefined : yield* FalQueue.mediaUrl(request.mask, route.name),
     }, request.providerOptions, request.http?.body) ?? {});
 });
@@ -74,10 +75,12 @@ const decodeResult = Effect.fn("FalImages.decodeResult")(function* (response, co
     // With the safety checker on, flagged images come back blacked out rather than omitted.
     const flagged = (has_nsfw_concepts ?? []).flatMap((value, index) => (value ? [index] : []));
     return new ImageResponse({
-        images: images.map((image) => Media.url(image.url, {
-            mediaType: image.content_type ?? undefined,
-            info: { width: image.width ?? undefined, height: image.height ?? undefined },
-        })),
+        images: images.map((image) => {
+            const info = { width: image.width ?? undefined, height: image.height ?? undefined };
+            // `sync_mode: true` returns data URIs instead of hosted URLs.
+            return (Media.parseDataUrl(image.url, { info }) ??
+                Media.url(image.url, { mediaType: image.content_type ?? undefined, info }));
+        }),
         notices: flagged.length === 0
             ? undefined
             : flagged.map((index) => ({

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-responses.js

@@ -111,14 +111,17 @@ const adapter = {
     name: NAME,
     restoreHostedToolItem: (item) => (Schema.is(OpenAIResponsesHostedToolItem)(item) ? item : undefined),
 };
-// Only GPT-6 Astra accepts `configuration_update`, and never alongside automatic `context_management` compaction.
+// GPT-6 Astra, Sol, and Luna accept `configuration_update` only in standard mode (not `reasoning.mode: "pro"` or
+// `-pro` slugs), and never alongside automatic `context_management` compaction.
 const supportsEffortUpdates = (request) => {
     if (request.providerOptions?.contextManagement !== undefined)
         return false;
+    if (Schema.is(Schema.Struct({ mode: Schema.Literal("pro") }))(request.http?.body?.reasoning))
+        return false;
     const override = request.model.compatibility?.supportsEffortUpdates;
     if (override !== undefined)
         return override;
-    return /(?:^|\/)gpt-6-astra$/i.test(request.model.id);
+    return /(?:^|\/)gpt-6-(?:astra|sol|luna)$/i.test(request.model.id);
 };
 const nativeImageToolInput = (tool) => {
     const native = tool.native?.openai;

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/protocols/runway-video.js

@@ -119,7 +119,7 @@ export const protocol = MediaProtocol.queued(route, {
     start: { body: { from: fromRequest }, decode: decodeStart },
     status: { path: taskPath, decode: decodeStatus },
     result: { path: taskPath, decode: decodeResult },
-    cancel: { method: "DELETE", path: taskPath },
+    cancel: { method: "DELETE", path: taskPath, activeOnly: true },
 });
 const startPath = (request) => {
     if (request.video !== undefined)

package/dist/route/media-protocol.d.ts

@@ -93,6 +93,11 @@ export interface Queued<Request, Response, Token> {
     readonly cancel?: {
         readonly method: AuthInput["method"];
         readonly path: (token: Token) => string;
+        /**
+         * Fetch a fresh status first and skip the call for terminal generations, for providers whose cancel endpoint
+         * destroys finished work (Runway's `DELETE /v1/tasks/{id}` deletes completed tasks and their outputs).
+         */
+        readonly activeOnly?: boolean;
     };
 }
 export declare const queued: <Request, Response, Token>(route: Identity, input: Omit<Queued<Request, Response, Token>, "kind" | "id" | "provider">) => Queued<Request, Response, Token>;

package/dist/route/media.js

@@ -5,7 +5,7 @@ import { Endpoint } from "./endpoint.js";
 import { RequestExecutorService } from "./executor-service.js";
 import { RequestExecutor } from "./executor.js";
 import { MediaProtocol } from "./media-protocol.js";
-import { Generation } from "../generation.js";
+import { Generation, isTerminal } from "../generation.js";
 import { AIError, AIErrorReason, HttpOptions, InvalidRequestError, ProviderID, UnsupportedOperationError, mergeHttpOptions, } from "../schema/index.js";
 import { encodeJson } from "../utils/json.js";
 import { sanitizeSurrogates } from "../utils/sanitize.js";
@@ -51,13 +51,17 @@ export const queued = (input) => {
         const poll = (operation) => transport
             .call("GET", operation.path(token), http, execute)
             .pipe(Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })));
+        const status = poll(protocol.status);
         const cancel = protocol.cancel;
+        const send = cancel === undefined
+            ? undefined
+            : transport.call(cancel.method, cancel.path(token), http, execute).pipe(Effect.asVoid);
         return {
-            status: poll(protocol.status),
+            status,
             result: poll(protocol.result),
-            cancel: cancel === undefined
-                ? undefined
-                : transport.call(cancel.method, cancel.path(token), http, execute).pipe(Effect.asVoid),
+            cancel: send !== undefined && cancel?.activeOnly
+                ? status.pipe(Effect.flatMap((snapshot) => (isTerminal(snapshot.status) ? Effect.void : send)))
+                : send,
         };
     };
     const start = Effect.fn("MediaRoute.start")(function* (request, execute) {
@@ -192,7 +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-20170",
+  "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-20170",
+    "@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-20170",
+    "@opencode/schema": "0.0.0-dev-20180",
     "aws4fetch": "1.0.20",
     "effect": "4.0.0-rc.112",
     "google-auth-library": "10.5.0"