fix(codemode): enumerate inherited keys in for...in, intern tool references, freeze template objects, and delegate Array and Error toString

Co-authored-by: nexxeln <95541290+nexxeln@users.noreply.github.com>

bun.lock

@@ -597,8 +597,8 @@
       },
       "peerDependencies": {
         "@opencode/theme": "workspace:*",
-        "@opentui/core": ">=0.5.10",
-        "@opentui/solid": ">=0.5.10",
+        "@opentui/core": ">=0.5.12",
+        "@opentui/solid": ">=0.5.12",
         "solid-js": ">=1.9.0",
       },
       "optionalPeers": [
@@ -1114,9 +1114,9 @@
     "@npmcli/arborist": "9.4.0",
     "@octokit/rest": "22.0.0",
     "@openauthjs/openauth": "0.0.0-20250322224806",
-    "@opentui/core": "0.5.10",
-    "@opentui/keymap": "0.5.10",
-    "@opentui/solid": "0.5.10",
+    "@opentui/core": "0.5.12",
+    "@opentui/keymap": "0.5.12",
+    "@opentui/solid": "0.5.12",
     "@pierre/diffs": "1.2.10",
     "@playwright/test": "1.59.1",
     "@sentry/solid": "10.71.0",
@@ -2252,27 +2252,27 @@
 
     "@opentelemetry/semantic-conventions": ["@opentelemetry/semantic-conventions@1.43.0", "", {}, "sha512-eSYWTm620tTk45EKSedaUL8MFYI8hW164hIXsgIHyxu3VobUB3fFCu5t0hQby6OoWRPsG1KkKUG2M5UadiLiVg=="],
 
-    "@opentui/core": ["@opentui/core@0.5.10", "", { "dependencies": { "bun-ffi-structs": "0.3.1", "diff": "9.0.0", "marked": "17.0.1", "string-width": "7.2.0", "strip-ansi": "7.1.2" }, "optionalDependencies": { "@opentui/core-darwin-arm64": "0.5.10", "@opentui/core-darwin-x64": "0.5.10", "@opentui/core-linux-arm64": "0.5.10", "@opentui/core-linux-arm64-musl": "0.5.10", "@opentui/core-linux-x64": "0.5.10", "@opentui/core-linux-x64-musl": "0.5.10", "@opentui/core-win32-arm64": "0.5.10", "@opentui/core-win32-x64": "0.5.10" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-C3a2UbmefeAjIxAgm4BqjuSxKT4oqutfvYFwVvUgMxmGRHkNbBc/s7sukV0JgwcxFcV3uMFrXxo+E+BQtvuOiw=="],
+    "@opentui/core": ["@opentui/core@0.5.12", "", { "dependencies": { "bun-ffi-structs": "0.3.1", "diff": "9.0.0", "marked": "17.0.1", "string-width": "7.2.0", "strip-ansi": "7.1.2" }, "optionalDependencies": { "@opentui/core-darwin-arm64": "0.5.12", "@opentui/core-darwin-x64": "0.5.12", "@opentui/core-linux-arm64": "0.5.12", "@opentui/core-linux-arm64-musl": "0.5.12", "@opentui/core-linux-x64": "0.5.12", "@opentui/core-linux-x64-musl": "0.5.12", "@opentui/core-win32-arm64": "0.5.12", "@opentui/core-win32-x64": "0.5.12" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-ZXBE5gmvdovmV8zJQrOQf6E44v1tJRDEgrM2MYhEglzgXZ+smIUp95O8zeRYGsuIzQIiMPMgQqKtTJuzvAb7BQ=="],
 
-    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.5.10", "", { "os": "darwin", "cpu": "arm64" }, "sha512-Vyb+nTbhab8ZcRy5gg1loEEGwRcIbjAeVRIBfHBcbFDqmITBOg7x2gqJ+x/TnoOy4uwMhCmICUN2wiyREw3r1Q=="],
+    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.5.12", "", { "os": "darwin", "cpu": "arm64" }, "sha512-YdVnP0tAyerBNl0mIcmQEOotPeZzW1VnSXKBl5cyZ5e6nDd2Y+ui/8eRPpn1oqcamf1NCnzS4ohMgejOvna8Zg=="],
 
-    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.5.10", "", { "os": "darwin", "cpu": "x64" }, "sha512-tTFLcM7Oj1gTyhm/bUdAt3C6grZdCxPk6+/g2azcZBUlI3/62LwbeRS6HbQKFFmm+1fUmX8cq6kWrtul885mVg=="],
+    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.5.12", "", { "os": "darwin", "cpu": "x64" }, "sha512-uRrQJdHmLUSj3PV23QPi3WSimYTTxcXnVouxF6U4xMXlOv4N3SxnHfVwMRQkPqbGOfvVWHeLE6FdK4C+ubU0sQ=="],
 
-    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.5.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-ncJXcgudhBf2GdJyF3xVQN/Ec+1F7GOL+pRrURmgBYSj2v1w6EyoDQFAACtPTK2c3R38W6fvZwL4JSLlm4EFXQ=="],
+    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.5.12", "", { "os": "linux", "cpu": "arm64" }, "sha512-XeKhuIaEtgipvuPHbl4qPOBj+Ut+2zObmsxMVM1jDcjz/FatG9PGeGQPx1G1SnvH2AgpT4K+eCu7DUF0+yIqoQ=="],
 
-    "@opentui/core-linux-arm64-musl": ["@opentui/core-linux-arm64-musl@0.5.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-dGMphDKexSdeYqwl0wgoFBP88Ta/cdi1Zc1mk29/ENkSCGz+74zlCHgqTHRNGLmI8W5TfuUtCyktQH11/Z+TBQ=="],
+    "@opentui/core-linux-arm64-musl": ["@opentui/core-linux-arm64-musl@0.5.12", "", { "os": "linux", "cpu": "arm64" }, "sha512-VZ2sNMw1d/r1SLPjUbOP9LKscKz1CQjID8adTL6gG8Lrrq+mYcIUxutyB+P/eG0J/7oRZLPR6OMt7dUOap6RTg=="],
 
-    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.5.10", "", { "os": "linux", "cpu": "x64" }, "sha512-5qtYaOgwVycZD1GaGshTRsi0rXPAmVExO03N1JQaHu+NYxK/vXSOc7Bu4QW0sPXx3Sp0SpzpP+FHjXABfoK66g=="],
+    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.5.12", "", { "os": "linux", "cpu": "x64" }, "sha512-eZiCjEzwbb6qClPPfk32Nha9xmr9obt69Xj0+9SKsXxWLBKkjQEGOMRoh/R9ObaQF4aq8If1xV3VEY0sD9W9vg=="],
 
-    "@opentui/core-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.10", "", { "os": "linux", "cpu": "x64" }, "sha512-Oj4H9hApuvuTKPWxh4SoZAgGJorR7vbvnrZA/cAkSMAk2VGSoHRRcqeXQbcH8IcdjVZ0KFpv8Zkl/D5Ye+2mew=="],
+    "@opentui/core-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.12", "", { "os": "linux", "cpu": "x64" }, "sha512-WWW0hVBoSYZ3D6AgZ4u2Y5/u/IyIq2pDb+4yI3WgJ70Wyt6ofHy+6kRGRgbXFn1p+rPInAHjCXD2v6C7iEKSrA=="],
 
-    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.5.10", "", { "os": "win32", "cpu": "arm64" }, "sha512-A9VhgvTxQoUdZ+8LmUumEng1sQNbj9QQQT3NYG9mSxI54qTANi7vOWNSphMiY6RMVsr22pgm6nUvSSvJXv7Jog=="],
+    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.5.12", "", { "os": "win32", "cpu": "arm64" }, "sha512-aLbm6870Ybls6CYL4zMOCImTBPLZHZMUXJFGqMI44lIWxitkAtT6zg5lYA4oRqFRzzryDclxr29+hDgT3p3Blw=="],
 
-    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.5.10", "", { "os": "win32", "cpu": "x64" }, "sha512-u3KHa7kEeWrmKVDRJYpxSGO+g5E9cMGlrmTsPN3GVPHUmQMiREUawLXUvsU8+IHaQnqG3Q5nuE1yf4fPBzS+Qw=="],
+    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.5.12", "", { "os": "win32", "cpu": "x64" }, "sha512-KTwtwpfd2zF9opVh3SyRJYDd1o3Xv4XL8OZb8Zi+CqWUel6Y2IDCiVivCv8fGJt3J7wOIXXtuZI9ZUkLyKJCiQ=="],
 
-    "@opentui/keymap": ["@opentui/keymap@0.5.10", "", { "dependencies": { "@opentui/core": "0.5.10" }, "peerDependencies": { "@opentui/react": "0.5.10", "@opentui/solid": "0.5.10", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-8vDJF+ltXscSnLEv3rgCa4m7PcoYZeUT9BngugpFCmVoNevbaRtYijjdfiUuLmXfT61lO5QbR6nEhn2RZMK8ow=="],
+    "@opentui/keymap": ["@opentui/keymap@0.5.12", "", { "dependencies": { "@opentui/core": "0.5.12" }, "peerDependencies": { "@opentui/react": "0.5.12", "@opentui/solid": "0.5.12", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-yWPvJjRhJTRoRSUucQq9Ua8ZW7n/2YQ/j6JxWq5Qekm4WuFiTplEkebR/Aj2/xA8tX68NOE5qv1LrY0Jk3NLNQ=="],
 
-    "@opentui/solid": ["@opentui/solid@0.5.10", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.5.10", "babel-plugin-module-resolver": "5.0.2", "babel-preset-solid": "1.9.12", "entities": "7.0.1", "s-js": "^0.4.9" }, "peerDependencies": { "solid-js": "1.9.12" } }, "sha512-KrmMIsHiKBHOABTC0brOwqWm+sGq1ZX2sGCAx6WgtBbE3STMup9n8TAy/6gUYhwcjC9zugT53ytfSVwCwVWZUg=="],
+    "@opentui/solid": ["@opentui/solid@0.5.12", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.5.12", "babel-plugin-module-resolver": "5.0.2", "babel-preset-solid": "1.9.12", "entities": "7.0.1", "s-js": "^0.4.9" }, "peerDependencies": { "solid-js": "1.9.12" } }, "sha512-hAiVlVMtT7AkHGblKwcW1YAuXtxkSy1XSf/RRc4j3IlG3mTNX0bhJdnGOo3Xw14EqeZMp41Mcp5WzHAzMm/DzA=="],
 
     "@oslojs/asn1": ["@oslojs/asn1@1.0.0", "", { "dependencies": { "@oslojs/binary": "1.0.0" } }, "sha512-zw/wn0sj0j0QKbIXfIlnEcTviaCzYOY3V5rAyjR6YtOByFtJiT574+8p9Wlach0lZH9fddD4yb9laEAIl4vXQA=="],
 

nix/hashes.json

@@ -1,8 +1,8 @@
 {
   "nodeModules": {
-    "x86_64-linux": "sha256-+Clo0VPDdruHSoBNvV/wKAM8iR6HJPtB00oa8yl9ujU=",
-    "aarch64-linux": "sha256-4wU5v36GTXjwyt5ls4FH+5G43Ujd+dKVSJR21w3lhbA=",
-    "aarch64-darwin": "sha256-pThjoD6baddQ6biy7k1ByXwGwLAeWe/+w0tcYmt1uWs=",
-    "x86_64-darwin": "sha256-bCBl63CqBiqilb+YdaOLBYYZx/yf47c1aqgDOkgdegg="
+    "x86_64-linux": "sha256-aQQQhaUlAhpfqzH0vNi0IJ1cg7FQHIKYzxeq5d8PZoU=",
+    "aarch64-linux": "sha256-r9aDFu3UYmudmmYPhzCrpFvQlaejXc8V1IzLtG3jZPc=",
+    "aarch64-darwin": "sha256-B0m41LelD7d61vPHGIZZSO/cU7gbjHDJHt6oxNRRM8Q=",
+    "x86_64-darwin": "sha256-9TWJsyI3Y6BMomtGSgqA1th9LpxpqP4F5Tl/GyexVYw="
   }
 }

package.json

@@ -52,9 +52,9 @@
       "@octokit/rest": "22.0.0",
       "@hono/standard-validator": "0.2.0",
       "@hono/zod-validator": "0.4.2",
-      "@opentui/core": "0.5.10",
-      "@opentui/keymap": "0.5.10",
-      "@opentui/solid": "0.5.10",
+      "@opentui/core": "0.5.12",
+      "@opentui/keymap": "0.5.12",
+      "@opentui/solid": "0.5.12",
       "@tanstack/solid-virtual": "3.13.37",
       "@shikijs/stream": "4.4.3",
       "@standard-schema/spec": "1.1.0",

packages/ai/AGENTS.md

@@ -10,7 +10,7 @@
 
 ## Conventions
 
-Per-type constructors live on the type, not as top-level re-exports. Use `Message.system(...)`, `Message.user(...)`, `Message.assistant(...)`, `Message.tool(...)`, `Message.media(...)`, `LanguageModel.make(...)`, `ToolDefinition.make(...)`, `ToolCallPart.make(...)`, `ToolResultPart.make(...)`, `ToolChoice.make(...)`, `ToolChoice.named(...)`, `SystemPart.make(...)`, and `GenerationOptions.make(...)` directly. The top-level `LLM` namespace is reserved for request-shaped call APIs: `LLM.request`, `LLM.generate`, `LLM.stream`, and `LLM.generateObject`. Use `LLMRequest.update(...)` when deriving canonical request data; do not add a duplicate `LLM.updateRequest(...)` path. Two ways to construct the same thing is one too many.
+Per-type constructors live on the type, not as top-level re-exports. Use `Message.system(...)`, `Message.user(...)`, `Message.assistant(...)`, `Message.tool(...)`, `Message.media(...)`, `LanguageModel.make(...)`, `ToolDefinition.make(...)`, `ToolCallPart.make(...)`, `ToolResultPart.make(...)`, `ToolChoice.make(...)`, `ToolChoice.named(...)`, `SystemPart.make(...)`, and `GenerationOptions.make(...)` directly. The top-level `LLM` namespace is reserved for request-shaped call APIs: `LLM.request`, `LLM.generate`, `LLM.stream`, and `LLM.generateObject`. `LLM.generate`/`LLM.stream` and Promise `ai.llm.generate`/`ai.llm.stream` accept ergonomic input or an `LLMRequest`; both paths use the same canonical request. Core still builds, logs, replays, and updates that durable `LLMRequest` boundary. Use `LLMRequest.update(...)` when deriving canonical request data; do not add a duplicate `LLM.updateRequest(...)` path.
 
 Modality namespaces mirror `LLM` exactly: `Image.request`, `Image.generate`, `Image.stream` (later `Video`, `Speech`, `Transcription`). Common request fields (`images`, `mask`, `n`, `size`, `aspectRatio`, `seed`, `format`) lower natively or fail with a typed `AIError`; provider-native controls always live under `providerOptions`, never under a modality-specific `options` key.
 
@@ -102,7 +102,7 @@ Media does not fit the SSE-frames-to-event-state-machine LLM route. `MediaRoute.
 
 `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.
 
-Transcription uses all three kinds (OpenAI and Gemini stream, Deepgram is inline, AssemblyAI is queued): every route carries its `kind` and `TranscriptionClient` dispatches on it. `ImageRoute` is the same union; both clients dispatch through `MediaRoute.dispatch` and models compose through `composeAnyRoute`, and 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 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`).
 
 ### URL Construction
 
@@ -275,6 +275,7 @@ Use this order for every protocol module:
 ### Rules
 
 - Keep protocol files focused on the protocol. Move provider-specific projection, signing, media normalization, or other bulky transformations into `src/protocols/utils/*`.
+- Send `tool.inputSchema` as given. `prepareRequest` applies the tool schema rules (`ToolSchemaProjection.tools`) once per request, including tools in namespaces. A protocol whose API needs a model family's rules for every model declares `sanitizer` instead of transforming schemas itself.
 - Use `Effect.fn("Provider.fromRequest")` for request body construction entrypoints. Use `Effect.fn(...)` for event handlers that yield effects; keep purely synchronous handlers as plain functions returning a `StepResult` that the dispatcher lifts via `Effect.succeed(...)`.
 - Parser state owns terminal information. The state machine records finish reason, usage, and pending tool calls; emit one terminal `finish` event (or `provider-error`) for each completed response. If a provider splits reason and usage across events, merge them in parser state before flushing.
 - Emit exactly one terminal `finish` event for a completed response, normally after a matching `step-finish`. Use `stream.terminal` to stop reading when the provider has a completion sentinel; use `stream.onHalt` when the final event must be flushed after the framed stream ends.

packages/ai/README.md

@@ -9,15 +9,13 @@ import { OpenAI } from "@opencode/ai/providers"
 
 const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY })
 
-const request = LLM.request({
-  model: openai.responses("gpt-4o-mini"), // `.chat(...)` selects the Chat Completions API instead
-  system: "You are concise.",
-  prompt: "Say hello in one short sentence.",
-  generation: { maxTokens: 40 },
-})
-
 const program = Effect.gen(function* () {
-  const response = yield* LLM.generate(request)
+  const response = yield* LLM.generate({
+    model: openai.responses("gpt-4o-mini"), // `.chat(...)` selects the Chat Completions API instead
+    system: "You are concise.",
+    prompt: "Say hello in one short sentence.",
+    generation: { maxTokens: 40 },
+  })
   console.log(response.text)
 })
 
@@ -25,7 +23,8 @@ const program = Effect.gen(function* () {
 await Effect.runPromise(program.pipe(Effect.provide(AIClient.layer)))
 ```
 
-Run `LLM.stream(request)` instead of `generate` when you want incremental `LLMEvent`s. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses,
+Run `LLM.stream(...)` instead of `generate` when you want incremental `LLMEvent`s. Both accept input or a prebuilt
+`LLM.request(...)`. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses,
 Anthropic Messages, Gemini, Bedrock Converse, and any OpenAI-compatible deployment.
 
 The same configured facade names image, video, speech, and transcription models. `Image.generate` resolves the
@@ -72,10 +71,11 @@ helpers; `ai.file` and `ai.write` load `node:fs/promises` on first use, so no Ef
 import { AI } from "@opencode/ai/promise"
 
 const ai = AI.make()
-const text = await ai.llm.generate({ model: openai.responses("gpt-4o-mini"), prompt: "Say hello." })
+const input = { model: openai.responses("gpt-4o-mini"), prompt: "Say hello." }
+const text = await ai.llm.generate(input)
 const generated = await ai.image.generate({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" })
 await ai.write(generated.image, "./lighthouse.png") // also ai.file(path), ai.bytes(asset), ai.base64(asset), ai.materialize(asset)
-for await (const event of ai.llm.stream({ model: openai.responses("gpt-4o-mini"), prompt: "Stream hello." })) {
+for await (const event of ai.llm.stream(ai.llm.request(input))) {
   // LLMEvent
 }
 await ai.dispose()
@@ -936,7 +936,7 @@ const transcript = await generation.await({ poll: { interval: 3_000 } })
 ## Public API
 
 - **`LLM.request({...})`** — build a provider-neutral `LLMRequest`. Accepts ergonomic inputs (`system: string`, `prompt: string`) that normalize into the canonical Schema classes.
-- **`LLM.generate` / `LLM.stream`** — re-exported from `LLMClient` for one-import use.
+- **`LLM.generate` / `LLM.stream`** — run direct input or an `LLMRequest` through `LLMClient` for one-import use.
 - **`Message.user(...)` / `Message.assistant(...)` / `Message.tool(...)`** — message constructors from the canonical schema model.
 - **`LanguageModel.make(...)` / `ToolCallPart.make(...)` / `ToolResultPart.make(...)` / `ToolDefinition.make(...)`** — model and tool-related constructors from the canonical schema model.
 - **`LLMEvent.is.*`** — typed guards (`is.textDelta`, `is.toolCall`, `is.finish`, …) for filtering streams.

packages/ai/docs/media-design.md

@@ -140,7 +140,7 @@ portability matrix.
 
 Editing is not a separate function; `images`/`mask` on the request select the edit path in the route (OpenAI `/images/edits`, Gemini multimodal parts, xAI `/images/edits`). Routes that cannot honor `mask` fail with `Unsupported`.
 
-`ImageRoute` is the inline | stream | queued union, dispatched on `route.kind`. `Image.stream` on a streaming route emits `image-partial` previews before each `image`; on a queued route it emits `generation-queued` / `generation-progress` observations, then the result's `image` and `finish` events.
+`ImageRoute` is the inline | stream | queued union, dispatched on `route.kind`, like every modality route. `Image.stream` on a streaming route emits `image-partial` previews before each `image`; on a queued route it emits `generation-queued` / `generation-progress` observations, then the result's `image` and `finish` events.
 
 #### Video
 
@@ -215,7 +215,7 @@ const request = Speech.request({
 })
 
 const response = yield* Speech.generate(request)   // SpeechResponse: audio: Media.Asset, timestamps?, usage?, providerMetadata?
-yield* Speech.stream(request)                      // Stream<SpeechEvent>: audio-delta { chunk } | timestamps { items } | finish { audio, usage? }
+yield* Speech.stream(request)                      // Stream<SpeechEvent>: generation-queued | generation-progress | audio-delta { chunk } | timestamps { items } | finish { audio, usage? }
 ```
 
 Execution is `MediaProtocol.stream` for every provider: one request whose body is framed and folded by a `step`
@@ -389,7 +389,8 @@ for await (const event of generation.events({ poll: { interval: 10_000 } })) {
 const video = await generation.await({ poll: { interval: 10_000 }, signal })
 const resumed = await ai.video.resume(model, JSON.parse(saved)) // persist provider + model ID with the token
 
-const text = await ai.llm.generate({ model, prompt })
+const request = ai.llm.request({ model, prompt })
+const text = await ai.llm.generate(request)
 for await (const event of ai.llm.stream(request)) { … }
 
 await ai.dispose()
@@ -419,7 +420,7 @@ Existing facades gain per-modality selectors; the modality routes each facade pr
 
 New facades follow the existing one-file-per-provider rule. The facade selector is the public path for media models; modality-specific package entrypoints (for example `@opencode/ai/providers/openai/images`) are deferred until Core has a modality-aware model resolver.
 
-`ImageModel<Options>` gives typed `providerOptions` per model; `VideoModel`, `SpeechModel`, and `TranscriptionModel` follow the same generic. They share an internal `MediaModel` base class (ids, route, `http` overlays) that is not part of the public exports; `Generation` and the promise client work with the concrete modality models.
+`ImageModel<Options>` gives typed `providerOptions` per model; `VideoModel`, `SpeechModel`, and `TranscriptionModel` follow the same generic. As with `LanguageModel`, the route type does not carry `Options`, so `ImageModel<OpenAIImageOptions>` is an `ImageModel` and client methods take plain `ImageRequestFor`. They share an internal `MediaModel` base class (ids, route, `http` overlays) that is not part of the public exports; `Generation` and the promise client work with the concrete modality models.
 
 ### Routes and protocols
 

packages/ai/src/image-client.ts

@@ -1,99 +1,30 @@
-import { Context, Effect, Layer, Stream } from "effect"
-import type { AwaitOptions, Generation } from "./generation.js"
-import { RequestExecutor } from "./route/executor.js"
-import { MediaRoute } from "./route/media.js"
-import type { AIError } from "./schema/index.js"
+import { Context } from "effect"
+import { MediaClient } from "./media-client.js"
 import {
-  responseEvents,
+  ImageOutputEvent,
+  ImageFinishEvent,
   type ImageEvent,
-  type ImageModel,
-  type ImageOptions,
   type ImageRequestFor,
   type ImageResponse,
 } from "./image.js"
 
-export interface Interface {
-  readonly generate: <Options extends ImageOptions>(
-    request: ImageRequestFor<Options>,
-    options?: AwaitOptions,
-  ) => Effect.Effect<ImageResponse, AIError>
-  readonly stream: <Options extends ImageOptions>(
-    request: ImageRequestFor<Options>,
-    options?: AwaitOptions,
-  ) => Stream.Stream<ImageEvent, AIError>
-  readonly start: <Options extends ImageOptions>(
-    request: ImageRequestFor<Options>,
-  ) => Effect.Effect<Generation<ImageResponse>, AIError>
-  readonly resume: <Options extends ImageOptions>(
-    model: ImageModel<Options>,
-    token: unknown,
-  ) => Effect.Effect<Generation<ImageResponse>, AIError>
-}
+export type Interface = MediaClient.Interface<ImageRequestFor, ImageEvent, ImageResponse>
 
 export class ImageClientService extends Context.Service<ImageClientService, Interface>()("@opencode/ImageClient") {}
 export const Service = ImageClientService
 export type Service = ImageClientService
 
-export const generate = <Options extends ImageOptions>(
-  request: ImageRequestFor<Options>,
-  options?: AwaitOptions,
-): Effect.Effect<ImageResponse, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.generate(request, options)
-  })
-
-export const stream = <Options extends ImageOptions>(
-  request: ImageRequestFor<Options>,
-  options?: AwaitOptions,
-): Stream.Stream<ImageEvent, AIError, Service> =>
-  Stream.unwrap(
-    Effect.gen(function* () {
-      const client = yield* Service
-      return client.stream(request, options)
-    }),
-  )
-
-export const start = <Options extends ImageOptions>(
-  request: ImageRequestFor<Options>,
-): Effect.Effect<Generation<ImageResponse>, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.start(request)
-  })
-
-export const resume = <Options extends ImageOptions>(
-  model: ImageModel<Options>,
-  token: unknown,
-): Effect.Effect<Generation<ImageResponse>, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.resume(model, token)
-  })
-
-export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
-  Service,
-  Effect.gen(function* () {
-    const executor = yield* RequestExecutor.Service
-    const dispatch = MediaRoute.dispatch<ImageEvent, ImageResponse>({
-      modality: "image",
-      execute: executor.execute,
-      responseEvents,
-    })
-    return Service.of({
-      start: (request) => dispatch.start(request.model.route, request),
-      resume: (model, token) => dispatch.resume(model.route, model, token),
-      generate: (request, options) => dispatch.generate(request.model.route, request, options),
-      stream: (request, options) => dispatch.stream(request.model.route, request, options),
-    })
-  }),
-)
-
 export const ImageClient = {
   Service,
-  layer,
-  generate,
-  stream,
-  start,
-  resume,
+  ...MediaClient.make(Service, {
+    modality: "image",
+    responseEvents: (response: ImageResponse) => [
+      ...response.images.map((image, index) => ImageOutputEvent.make({ index, image })),
+      ImageFinishEvent.make({
+        usage: response.usage,
+        notices: response.notices,
+        providerMetadata: response.providerMetadata,
+      }),
+    ],
+  }),
 } as const

packages/ai/src/image.ts

@@ -1,9 +1,8 @@
 import { Effect, Schema, Stream } from "effect"
 import { Generation, ProgressEvent, QueuedEvent, type AwaitOptions } from "./generation.js"
 import { Media } from "./media.js"
-import { MediaModel, composeAnyRoute, tryRequest } from "./media-model.js"
+import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
-import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata, type OpenString } from "./schema/index.js"
 import { ImageClient, Service } from "./image-client.js"
 
@@ -11,75 +10,39 @@ import { ImageClient, Service } from "./image-client.js"
 // Model
 // ---------------------------------------------------------------------------
 
-export type ImageOptions = Record<string, unknown>
+export type ImageOptions = MediaModel.Options
 
-export type ImageRoute<Options extends ImageOptions = ImageOptions> = MediaRoute.AnyRoute<
-  ImageRequestFor<Options>,
-  ImageEvent,
-  ImageResponse
->
+export type ImageRoute = MediaRoute.AnyRoute<ImageRequestFor, ImageEvent, ImageResponse>
 
-export class ImageModel<Options extends ImageOptions = ImageOptions> extends MediaModel<ImageRoute<Options>, Options> {
+export class ImageModel<Options extends ImageOptions = ImageOptions> extends MediaModel<ImageRoute, Options> {
   declare protected readonly _ImageModel: void
 
-  static make<Options extends ImageOptions = ImageOptions>(input: MediaModel.Input<ImageRoute<Options>>) {
-    return new ImageModel<Options>(input)
-  }
-
   /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
   static fromRoute<Options extends ImageOptions>(
-    route: ImageModel.InlineRouteInput<Options>,
+    route: MediaModel.InlineRouteInput<ImageRequestFor<Options>, ImageResponse>,
     input: MediaRoute.ModelInput,
   ): ImageModel<Options>
   static fromRoute<Options extends ImageOptions, Frame, State>(
-    route: ImageModel.StreamRouteInput<Options, Frame, State>,
+    route: MediaModel.StreamRouteInput<ImageRequestFor<Options>, ImageEvent, Frame, State>,
     input: MediaRoute.ModelInput,
   ): ImageModel<Options>
   static fromRoute<Options extends ImageOptions, Token>(
-    route: ImageModel.QueuedRouteInput<Options, Token>,
+    route: MediaModel.QueuedRouteInput<ImageRequestFor<Options>, ImageResponse, Token>,
     input: MediaRoute.ModelInput,
   ): ImageModel<Options>
   static fromRoute<Options extends ImageOptions, Frame, State, Token>(
-    route: ImageModel.RouteInput<Options, Frame, State, Token>,
+    route: MediaModel.AnyRouteInput<ImageRequestFor<Options>, ImageEvent, ImageResponse, Frame, State, Token>,
     input: MediaRoute.ModelInput,
   ) {
     return new ImageModel<Options>({
       id: input.id,
       provider: route.protocol.provider,
       http: input.http,
-      route: composeAnyRoute(route, input, collectResponse),
+      route: composeRoute(route, input, collectResponse) as ImageRoute,
     })
   }
 }
 
-export namespace ImageModel {
-  export type InlineRouteInput<Options extends ImageOptions = ImageOptions> = MediaModel.RouteInput<
-    ImageRequestFor<Options>,
-    MediaProtocol.Inline<ImageRequestFor<Options>, ImageResponse>
-  >
-
-  export type StreamRouteInput<
-    Options extends ImageOptions = ImageOptions,
-    Frame = unknown,
-    State = unknown,
-  > = MediaModel.RouteInput<
-    MediaProtocol.Addressed<ImageRequestFor<Options>>,
-    MediaProtocol.Streamed<ImageRequestFor<Options>, ImageEvent, Frame, State>
-  >
-
-  export type QueuedRouteInput<Options extends ImageOptions = ImageOptions, Token = unknown> = MediaModel.RouteInput<
-    ImageRequestFor<Options>,
-    MediaProtocol.Queued<ImageRequestFor<Options>, ImageResponse, Token>
-  >
-
-  export type RouteInput<
-    Options extends ImageOptions = ImageOptions,
-    Frame = unknown,
-    State = unknown,
-    Token = unknown,
-  > = MediaModel.AnyRouteInput<ImageRequestFor<Options>, ImageEvent, ImageResponse, Frame, State, Token>
-}
-
 export const ImageModelSchema = Schema.declare((value): value is ImageModel => value instanceof ImageModel, {
   expected: "Image.Model",
 })
@@ -190,15 +153,6 @@ export const ImageEvent = Object.assign(imageEventTagged, {
 })
 export type ImageEvent = Schema.Schema.Type<typeof imageEventTagged>
 
-export const responseEvents = (response: ImageResponse): ReadonlyArray<ImageEvent> => [
-  ...response.images.map((image, index) => ImageOutputEvent.make({ index, image })),
-  ImageFinishEvent.make({
-    usage: response.usage,
-    notices: response.notices,
-    providerMetadata: response.providerMetadata,
-  }),
-]
-
 const collectResponse = (events: ReadonlyArray<ImageEvent>): Effect.Effect<ImageResponse> => {
   const finish = events.find(ImageEvent.is.finish)
   // Every image protocol's `finish` emits the terminal event or fails, so a completed stream always has one.
@@ -232,36 +186,31 @@ export function request(input: ImageRequest | ImageRequestInput) {
 const requestEffect = (input: ImageRequest | ImageRequestInput) => tryRequest(() => request(input))
 
 export function generate<const Model extends ImageModel>(
-  input: ImageRequestInput<Model>,
+  input: ImageRequest | ImageRequestInput<Model>,
   options?: AwaitOptions,
 ): Effect.Effect<ImageResponse, AIError, Service>
-export function generate(input: ImageRequest, options?: AwaitOptions): Effect.Effect<ImageResponse, AIError, Service>
 export function generate(input: ImageRequest | ImageRequestInput, options?: AwaitOptions) {
   return requestEffect(input).pipe(Effect.flatMap((request) => ImageClient.generate(request, options)))
 }
 
 export function stream<const Model extends ImageModel>(
-  input: ImageRequestInput<Model>,
+  input: ImageRequest | ImageRequestInput<Model>,
   options?: AwaitOptions,
 ): Stream.Stream<ImageEvent, AIError, Service>
-export function stream(input: ImageRequest, options?: AwaitOptions): Stream.Stream<ImageEvent, AIError, Service>
 export function stream(input: ImageRequest | ImageRequestInput, options?: AwaitOptions) {
   return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => ImageClient.stream(request, options))))
 }
 
 /** Inline and streaming routes fail with `UnsupportedOperation`. */
 export function start<const Model extends ImageModel>(
-  input: ImageRequestInput<Model>,
+  input: ImageRequest | ImageRequestInput<Model>,
 ): Effect.Effect<Generation<ImageResponse>, AIError, Service>
-export function start(input: ImageRequest): Effect.Effect<Generation<ImageResponse>, AIError, Service>
 export function start(input: ImageRequest | ImageRequestInput) {
   return requestEffect(input).pipe(Effect.flatMap((request) => ImageClient.start(request)))
 }
 
-export const resume = <Options extends ImageOptions>(
-  model: ImageModel<Options>,
-  token: unknown,
-): Effect.Effect<Generation<ImageResponse>, AIError, Service> => ImageClient.resume(model, token)
+export const resume = (model: ImageModel, token: unknown): Effect.Effect<Generation<ImageResponse>, AIError, Service> =>
+  ImageClient.resume(model, token)
 
 export const Image = {
   request,

packages/ai/src/llm.ts

@@ -1,5 +1,6 @@
-import { Effect, JsonSchema, Schema } from "effect"
-import { LLMClient, Service } from "./route/client.js"
+import { Effect, JsonSchema, Schema, Stream } from "effect"
+import { tryRequest } from "./media-model.js"
+import { LLMClient, Service, type StreamOptions } from "./route/client.js"
 import {
   GenerationOptions,
   HttpOptions,
@@ -35,9 +36,26 @@ export type RequestInput<SelectedLanguageModel extends LanguageModel = LanguageM
   readonly http?: HttpOptions.Input
 }
 
-export const generate = LLMClient.generate
+export function generate<const Model extends LanguageModel>(
+  input: RequestInput<Model>,
+  options?: StreamOptions,
+): Effect.Effect<LLMResponse, AIError, Service>
+export function generate(input: LLMRequest, options?: StreamOptions): Effect.Effect<LLMResponse, AIError, Service>
+export function generate(input: RequestInput | LLMRequest, options?: StreamOptions) {
+  return requestEffect(input).pipe(Effect.flatMap((request) => LLMClient.generate(request, options)))
+}
 
-export const stream = LLMClient.stream
+export function stream<const Model extends LanguageModel>(
+  input: RequestInput<Model>,
+  options?: StreamOptions,
+): Stream.Stream<LLMEvent, AIError, Service>
+export function stream(input: LLMRequest, options?: StreamOptions): Stream.Stream<LLMEvent, AIError, Service>
+export function stream(input: RequestInput | LLMRequest, options?: StreamOptions) {
+  return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => LLMClient.stream(request, options))))
+}
+
+const requestEffect = (input: RequestInput | LLMRequest) =>
+  input instanceof LLMRequest ? Effect.succeed(input) : tryRequest(() => request(input))
 
 export const request = <const SelectedLanguageModel extends LanguageModel>(
   input: RequestInput<SelectedLanguageModel>,

packages/ai/src/media-client.ts

@@ -0,0 +1,77 @@
+import { type Context, Effect, Layer, Stream } from "effect"
+import { resultEvents, type AwaitOptions, type Generation, type Observation } from "./generation.js"
+import { RequestExecutor } from "./route/executor.js"
+import type { MediaRoute } from "./route/media.js"
+import { AIError, UnsupportedOperationError } from "./schema/index.js"
+
+/** A media request whose model carries the route that executes it. */
+export interface RoutedRequest<Self extends MediaRoute.MediaRequest, Event, Response> extends MediaRoute.MediaRequest {
+  readonly model: MediaRoute.MediaRequest["model"] & { readonly route: MediaRoute.AnyRoute<Self, Event, Response> }
+}
+
+/** `start` and `resume` fail with `UnsupportedOperation` on inline and stream routes. */
+export interface Interface<Req extends RoutedRequest<Req, Event, Response>, Event, Response> {
+  readonly generate: (request: Req, options?: AwaitOptions) => Effect.Effect<Response, AIError>
+  readonly stream: (request: Req, options?: AwaitOptions) => Stream.Stream<Event | Observation, AIError>
+  readonly start: (request: Req) => Effect.Effect<Generation<Response>, AIError>
+  readonly resume: (model: Req["model"], token: unknown) => Effect.Effect<Generation<Response>, AIError>
+}
+
+/** One modality's layer and service accessors, dispatching each request on its route's `kind`. */
+export const make = <Self, Req extends RoutedRequest<Req, Event, Response>, Event, Response>(
+  service: Context.Service<Self, Interface<Req, Event, Response>>,
+  input: {
+    readonly modality: string
+    /** A completed response expanded into the streaming event shape. */
+    readonly responseEvents: (response: Response) => ReadonlyArray<Event>
+  },
+) => ({
+  layer: Layer.effect(
+    service,
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const notQueued = (route: MediaRoute.AnyRoute<Req, Event, Response>, operation: string) =>
+        new AIError({
+          reason: new UnsupportedOperationError({
+            operation: `${input.modality}.${operation}`,
+            provider: route.provider,
+            route: route.id,
+            message: `${route.provider}/${route.id} is not a queued route; use generate or stream`,
+          }),
+        })
+      const start = (request: Req) => {
+        const route = request.model.route
+        if (route.kind !== "queued") return Effect.fail(notQueued(route, "start"))
+        return route.start(request, executor.execute)
+      }
+      return service.of({
+        start,
+        resume: (model, token) => {
+          if (model.route.kind !== "queued") return Effect.fail(notQueued(model.route, "resume"))
+          return model.route.resume(model, token, executor.execute)
+        },
+        generate: (request, options) => {
+          const route = request.model.route
+          if (route.kind !== "queued") return route.generate(request, executor.execute)
+          return start(request).pipe(Effect.flatMap((generation) => generation.await(options)))
+        },
+        stream: (request, options) => {
+          const route = request.model.route
+          if (route.kind === "stream") return route.stream(request, executor.execute)
+          if (route.kind === "queued")
+            return Stream.unwrap(
+              start(request).pipe(Effect.map((generation) => resultEvents(generation, input.responseEvents, options))),
+            )
+          return Stream.fromIterableEffect(Effect.map(route.generate(request, executor.execute), input.responseEvents))
+        },
+      })
+    }),
+  ),
+  generate: (request: Req, options?: AwaitOptions) => service.use((client) => client.generate(request, options)),
+  stream: (request: Req, options?: AwaitOptions) =>
+    Stream.unwrap(service.useSync((client) => client.stream(request, options))),
+  start: (request: Req) => service.use((client) => client.start(request)),
+  resume: (model: Req["model"], token: unknown) => service.use((client) => client.resume(model, token)),
+})
+
+export * as MediaClient from "./media-client.js"

packages/ai/src/media-model.ts

@@ -6,11 +6,13 @@ import { AIError, HttpOptions, InvalidRequestError, ModelID, ProviderID } from "
 
 /**
  * What every media model carries: ids, the configured route, and deployment `http` overlays. Modality classes
- * (`ImageModel`, `VideoModel`, `SpeechModel`) extend it with their route type and a nominal marker so one cannot stand
- * in for the other in requests.
+ * (`ImageModel`, `VideoModel`, `SpeechModel`, `TranscriptionModel`) extend it with their route type and a nominal
+ * marker so one cannot stand in for the other in requests.
  */
 export class MediaModel<Route, Options> {
-  declare protected readonly _Options: (options: Options) => Options
+  // As with `LanguageModel`, the route type is erased over `Options`; `fromRoute` and the constructor trust that the
+  // route accepts every request this model's `Options` admit.
+  declare protected readonly _Options: Options
   readonly id: ModelID
   readonly provider: ProviderID
   readonly route: Route
@@ -25,6 +27,8 @@ export class MediaModel<Route, Options> {
 }
 
 export namespace MediaModel {
+  export type Options = Record<string, unknown>
+
   export interface Input<Route> {
     readonly id: string | ModelID
     readonly provider: string | ProviderID
@@ -41,48 +45,56 @@ export namespace MediaModel {
     readonly headers?: Record<string, string>
   }
 
+  export type InlineRouteInput<Request extends MediaRoute.MediaRequest, Response> = RouteInput<
+    Request,
+    MediaProtocol.Inline<Request, Response>
+  >
+
+  export type StreamRouteInput<Request extends MediaRoute.MediaRequest, Event, Frame, State> = RouteInput<
+    MediaProtocol.Addressed<Request>,
+    MediaProtocol.Streamed<Request, Event, Frame, State>
+  >
+
+  export type QueuedRouteInput<Request extends MediaRoute.MediaRequest, Response, Token> = RouteInput<
+    Request,
+    MediaProtocol.Queued<Request, Response, Token>
+  >
+
   export type AnyRouteInput<Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token> =
-    | RouteInput<Request, MediaProtocol.Inline<Request, Response>>
-    | RouteInput<MediaProtocol.Addressed<Request>, MediaProtocol.Streamed<Request, Event, Frame, State>>
-    | RouteInput<Request, MediaProtocol.Queued<Request, Response, Token>>
+    | InlineRouteInput<Request, Response>
+    | StreamRouteInput<Request, Event, Frame, State>
+    | QueuedRouteInput<Request, Response, Token>
 }
 
 /** Compose a protocol route input with one deployment through `MediaRoute.inline`, `queued`, or `stream`. */
-export const composeRoute = <Request extends MediaRoute.MediaRequest, Protocol, Route>(
-  compose: (input: MediaRoute.Composition<Request> & { readonly protocol: Protocol }) => Route,
-  route: MediaModel.RouteInput<Request, Protocol>,
-  input: MediaRoute.ModelInput,
-): Route =>
-  compose({
-    protocol: route.protocol,
-    endpoint: Endpoint.path(route.path, { baseURL: input.baseURL ?? route.baseURL }),
-    auth: input.auth,
-    headers:
-      route.headers === undefined && input.headers === undefined ? undefined : { ...route.headers, ...input.headers },
-  })
-
-export const composeAnyRoute = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
+export const composeRoute = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
   route: MediaModel.AnyRouteInput<Request, Event, Response, Frame, State, Token>,
   input: MediaRoute.ModelInput,
   collect: (events: ReadonlyArray<Event>) => Effect.Effect<Response, AIError>,
 ): MediaRoute.AnyRoute<Request, Event, Response> => {
-  if (isStreamInput(route))
-    return composeRoute((composition) => MediaRoute.stream({ ...composition, collect }), route, input)
-  if (isQueuedInput(route)) return composeRoute(MediaRoute.queued, route, input)
-  return composeRoute(MediaRoute.inline, route, input)
+  if (isStreamInput(route)) return MediaRoute.stream({ ...composition(route, input), collect })
+  if (isQueuedInput(route)) return MediaRoute.queued(composition(route, input))
+  return MediaRoute.inline(composition(route, input))
 }
 
+const composition = <Request extends MediaRoute.MediaRequest, Protocol>(
+  route: MediaModel.RouteInput<Request, Protocol>,
+  input: MediaRoute.ModelInput,
+): MediaRoute.Composition<Request> & { readonly protocol: Protocol } => ({
+  protocol: route.protocol,
+  endpoint: Endpoint.path(route.path, { baseURL: input.baseURL ?? route.baseURL }),
+  auth: input.auth,
+  headers:
+    route.headers === undefined && input.headers === undefined ? undefined : { ...route.headers, ...input.headers },
+})
+
 const isStreamInput = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
   route: MediaModel.AnyRouteInput<Request, Event, Response, Frame, State, Token>,
-): route is MediaModel.RouteInput<
-  MediaProtocol.Addressed<Request>,
-  MediaProtocol.Streamed<Request, Event, Frame, State>
-> => route.protocol.kind === "stream"
+): route is MediaModel.StreamRouteInput<Request, Event, Frame, State> => route.protocol.kind === "stream"
 
 const isQueuedInput = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
   route: MediaModel.AnyRouteInput<Request, Event, Response, Frame, State, Token>,
-): route is MediaModel.RouteInput<Request, MediaProtocol.Queued<Request, Response, Token>> =>
-  route.protocol.kind === "queued"
+): route is MediaModel.QueuedRouteInput<Request, Response, Token> => route.protocol.kind === "queued"
 
 /** Lift a synchronous Schema-class constructor into a typed `InvalidRequest` failure. */
 export const tryRequest = <A>(make: () => A): Effect.Effect<A, AIError> =>

packages/ai/src/promise.ts

@@ -1,23 +1,22 @@
 import { Effect, Layer, ManagedRuntime, Stream } from "effect"
 import { AIClient } from "./ai-client.js"
 import type { AwaitOptions, Event, Generation, Snapshot } from "./generation.js"
-import { Image, ImageModel, ImageRequest, type ImageOptions, type ImageRequestInput } from "./image.js"
+import { Image, type ImageModel, type ImageRequest, type ImageRequestInput } from "./image.js"
 import { LLM } from "./index.js"
 import { Media } from "./media.js"
 import { tryRequest } from "./media-model.js"
 import { RequestExecutor } from "./route/executor.js"
 import { AIError, InvalidRequestError, LanguageModel, LLMRequest } from "./schema/index.js"
 import type { RequestInput } from "./llm.js"
-import { Speech, SpeechModel, SpeechRequest, type SpeechRequestInput } from "./speech.js"
+import { Speech, type SpeechModel, type SpeechRequest, type SpeechRequestInput } from "./speech.js"
 import {
   Transcription,
-  TranscriptionModel,
-  TranscriptionRequest,
-  type TranscriptionOptions,
+  type TranscriptionModel,
+  type TranscriptionRequest,
   type TranscriptionRequestInput,
 } from "./transcription.js"
 import { fileMediaType } from "./utils/media-type.js"
-import { Video, VideoModel, VideoRequest, type VideoOptions, type VideoRequestInput } from "./video.js"
+import { Video, type VideoModel, type VideoRequest, type VideoRequestInput } from "./video.js"
 
 /**
  * Promise-first entrypoint for scripts and non-Effect callers. One `ManagedRuntime` hosts the LLM, image, video, speech,
@@ -93,17 +92,8 @@ export const make = (options: Options = {}) => {
     cancel: (options) => run(generation.cancel(), options),
   })
 
-  // The typed `generate`/`stream` overloads take a concrete input or a request, not the union; normalize once here.
   const llmRequest = (input: RequestInput | LLMRequest) =>
     input instanceof LLMRequest ? Effect.succeed(input) : tryRequest(() => LLM.request(input))
-  const imageRequest = (input: ImageRequestInput | ImageRequest) =>
-    input instanceof ImageRequest ? input : Image.request(input)
-  const videoRequest = (input: VideoRequestInput | VideoRequest) =>
-    input instanceof VideoRequest ? input : Video.request(input)
-  const speechRequest = (input: SpeechRequestInput | SpeechRequest) =>
-    input instanceof SpeechRequest ? input : Speech.request(input)
-  const transcriptionRequest = (input: TranscriptionRequestInput | TranscriptionRequest) =>
-    input instanceof TranscriptionRequest ? input : Transcription.request(input)
 
   return {
     run,
@@ -155,61 +145,58 @@ export const make = (options: Options = {}) => {
       generate: <const Model extends ImageModel>(
         input: ImageRequestInput<Model> | ImageRequest,
         options?: AwaitOptions & RunOptions,
-      ) => run(Image.generate(imageRequest(input), { poll: options?.poll }), options),
+      ) => run(Image.generate(input, { poll: options?.poll }), options),
       stream: <const Model extends ImageModel>(
         input: ImageRequestInput<Model> | ImageRequest,
         options?: AwaitOptions & RunOptions,
-      ) => iterate(Image.stream(imageRequest(input), { poll: options?.poll }), options),
+      ) => iterate(Image.stream(input, { poll: options?.poll }), options),
       start: <const Model extends ImageModel>(input: ImageRequestInput<Model> | ImageRequest, options?: RunOptions) =>
-        run(Image.start(imageRequest(input)), options).then(handle),
-      resume: <Options extends ImageOptions>(model: ImageModel<Options>, token: unknown, options?: RunOptions) =>
+        run(Image.start(input), options).then(handle),
+      resume: (model: ImageModel, token: unknown, options?: RunOptions) =>
         run(Image.resume(model, token), options).then(handle),
     },
     video: {
       request: Video.request,
       start: <const Model extends VideoModel>(input: VideoRequestInput<Model> | VideoRequest, options?: RunOptions) =>
-        run(Video.start(videoRequest(input)), options).then(handle),
+        run(Video.start(input), options).then(handle),
       generate: <const Model extends VideoModel>(
         input: VideoRequestInput<Model> | VideoRequest,
         options?: AwaitOptions & RunOptions,
-      ) => run(Video.generate(videoRequest(input), { poll: options?.poll }), options),
-      resume: <Options extends VideoOptions>(model: VideoModel<Options>, token: unknown, options?: RunOptions) =>
+      ) => run(Video.generate(input, { poll: options?.poll }), options),
+      resume: (model: VideoModel, token: unknown, options?: RunOptions) =>
         run(Video.resume(model, token), options).then(handle),
       stream: <const Model extends VideoModel>(
         input: VideoRequestInput<Model> | VideoRequest,
         options?: AwaitOptions & RunOptions,
-      ) => iterate(Video.stream(videoRequest(input), { poll: options?.poll }), options),
+      ) => iterate(Video.stream(input, { poll: options?.poll }), options),
     },
     speech: {
       request: Speech.request,
       generate: <const Model extends SpeechModel>(
         input: SpeechRequestInput<Model> | SpeechRequest,
         options?: RunOptions,
-      ) => run(Speech.generate(speechRequest(input)), options),
+      ) => run(Speech.generate(input), options),
       stream: <const Model extends SpeechModel>(
         input: SpeechRequestInput<Model> | SpeechRequest,
         options?: RunOptions,
-      ) => iterate(Speech.stream(speechRequest(input)), options),
+      ) => iterate(Speech.stream(input), options),
     },
     transcription: {
       request: Transcription.request,
       generate: <const Model extends TranscriptionModel>(
         input: TranscriptionRequestInput<Model> | TranscriptionRequest,
         options?: AwaitOptions & RunOptions,
-      ) => run(Transcription.generate(transcriptionRequest(input), { poll: options?.poll }), options),
+      ) => run(Transcription.generate(input, { poll: options?.poll }), options),
       stream: <const Model extends TranscriptionModel>(
         input: TranscriptionRequestInput<Model> | TranscriptionRequest,
         options?: AwaitOptions & RunOptions,
-      ) => iterate(Transcription.stream(transcriptionRequest(input), { poll: options?.poll }), options),
+      ) => iterate(Transcription.stream(input, { poll: options?.poll }), options),
       start: <const Model extends TranscriptionModel>(
         input: TranscriptionRequestInput<Model> | TranscriptionRequest,
         options?: RunOptions,
-      ) => run(Transcription.start(transcriptionRequest(input)), options).then(handle),
-      resume: <Options extends TranscriptionOptions>(
-        model: TranscriptionModel<Options>,
-        token: unknown,
-        options?: RunOptions,
-      ) => run(Transcription.resume(model, token), options).then(handle),
+      ) => run(Transcription.start(input), options).then(handle),
+      resume: (model: TranscriptionModel, token: unknown, options?: RunOptions) =>
+        run(Transcription.resume(model, token), options).then(handle),
     },
     dispose: () => runtime.dispose(),
   }

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

@@ -70,7 +70,11 @@ export const protocol = Protocol.make({
       return {
         ...(yield* OpenAIChat.protocol.body.from(req)),
         enable_thinking: opts.enableThinking,
-        thinking_budget: opts.thinkingBudget,
+        // Alibaba also rejects an explicit budget that is not below `max_completion_tokens`.
+        thinking_budget:
+          opts.thinkingBudget === undefined
+            ? undefined
+            : ProviderShared.fitThinkingBudget(opts.thinkingBudget, req.generation?.maxTokens),
         preserve_thinking: opts.preserveThinking,
         clear_thinking: opts.clearThinking,
         thinking: opts.thinking,

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

@@ -26,18 +26,21 @@ export const protocol = Protocol.make({
     from: Effect.fn("AlibabaMessages.fromRequest")(function* (req) {
       const opts = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))(req.providerOptions ?? {})
       // Model Studio accepts enabled thinking without Anthropic's mandatory token budget.
+      const body = yield* AnthropicMessages.protocol.body.from(
+        LLMRequest.update(req, {
+          providerOptions: { ...req.providerOptions, thinking: undefined },
+        }),
+      )
+      const budget = opts.thinking?.budgetTokens ?? opts.thinking?.budget_tokens
       return {
-        ...(yield* AnthropicMessages.protocol.body.from(
-          LLMRequest.update(req, {
-            providerOptions: { ...req.providerOptions, thinking: undefined },
-          }),
-        )),
+        ...body,
         thinking:
           opts.thinking === undefined
             ? undefined
             : {
                 type: opts.thinking.type,
-                budget_tokens: opts.thinking.budgetTokens ?? opts.thinking.budget_tokens,
+                budget_tokens:
+                  budget === undefined ? undefined : ProviderShared.fitThinkingBudget(budget, body.max_tokens),
               },
       }
     }),

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

@@ -18,7 +18,6 @@ import {
   type CacheHint,
   type FinishReasonDetails,
   type FinishReason,
-  type JsonSchema,
   type MediaPart,
   type ProviderMetadata,
   type ProviderOptions,
@@ -31,13 +30,13 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { effortUpdate, resolveEffortUpdates } from "../effort-updates.js"
 import * as Cache from "./utils/cache.js"
 import { Lifecycle } from "./utils/lifecycle.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"
 
 const ADAPTER = "anthropic-messages"
 export const DEFAULT_BASE_URL = "https://api.anthropic.com/v1"
 export const PATH = "/messages"
 export const DEFAULT_MAX_TOKENS = 32_000
+const MIN_THINKING_BUDGET = 1_024
 const DEFAULT_EFFORT = "high"
 
 const SSE_EVENTS = new Set([
@@ -524,10 +523,10 @@ const redactedDataFromMetadata = (metadata: ProviderMetadata | undefined, key: s
   return typeof provider.redactedData === "string" ? provider.redactedData : undefined
 }
 
-const lowerTool = (breakpoints: Cache.Breakpoints, tool: ToolDefinition, inputSchema: JsonSchema): AnthropicTool => ({
+const lowerTool = (breakpoints: Cache.Breakpoints, tool: ToolDefinition): AnthropicTool => ({
   name: tool.name,
   description: tool.description,
-  input_schema: inputSchema,
+  input_schema: tool.inputSchema,
   cache_control: cacheControl(breakpoints, tool.cache),
 })
 
@@ -1027,6 +1026,15 @@ const applyThinkingBindingDefault = (model: LLMRequest["model"], thinking: Anthr
   }
 }
 
+// Anthropic also requires an explicit thinking budget below `max_tokens` and at or above its minimum.
+const fitThinking = (thinking: AnthropicThinking | undefined, maxTokens: number) =>
+  thinking?.type === "enabled"
+    ? {
+        ...thinking,
+        budget_tokens: ProviderShared.fitThinkingBudget(thinking.budget_tokens, maxTokens, MIN_THINKING_BUDGET),
+      }
+    : thinking
+
 const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (request: LLMRequest) {
   const options = yield* decodeOptions(request.providerOptions ?? {})
   const management = options.contextManagement
@@ -1039,12 +1047,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
   // over-mark we keep their tool hints and shed the message-tail ones first.
   const breakpoints = Cache.newBreakpoints(ANTHROPIC_BREAKPOINT_CAP)
   const flattened = ProviderShared.flattenToolRequest(updates.request)
-  const tools =
-    flattened.tools.length === 0
-      ? undefined
-      : flattened.tools.map((tool) =>
-          lowerTool(breakpoints, tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model)),
-        )
+  const tools = flattened.tools.length === 0 ? undefined : flattened.tools.map((tool) => lowerTool(breakpoints, tool))
   // Anthropic rejects tool_choice when tools are absent; "none" is only meaningful with tools present.
   const toolChoice = tools === undefined || !request.toolChoice ? undefined : yield* lowerToolChoice(request.toolChoice)
   const systemParts = request.system.filter((part) => part.text.length > 0)
@@ -1064,6 +1067,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
   }
   const output_config =
     updates.effort === undefined && format === undefined ? undefined : { effort: updates.effort, format }
+  const maxTokens = generation?.maxTokens ?? DEFAULT_MAX_TOKENS
   const body = {
     model: request.model.id,
     system,
@@ -1071,12 +1075,12 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
     tools,
     tool_choice: toolChoice,
     stream: true as const,
-    max_tokens: generation?.maxTokens ?? DEFAULT_MAX_TOKENS,
+    max_tokens: maxTokens,
     temperature: generation?.temperature,
     top_p: generation?.topP,
     top_k: generation?.topK,
     stop_sequences: generation?.stop,
-    thinking: applyThinkingBindingDefault(request.model, options.thinking),
+    thinking: applyThinkingBindingDefault(request.model, fitThinking(options.thinking, maxTokens)),
     output_config,
     // top-level passthrough per SDK MessageCreateParamsBase:4638,4643,4649,4654,4670
     cache_control: options.cache_control ?? options.cacheControl,

packages/ai/src/protocols/bedrock-converse.ts

@@ -9,7 +9,6 @@ import {
   type CacheHint,
   type FinishReason,
   type FinishReasonDetails,
-  type JsonSchema,
   type LLMRequest,
   type LanguageModel,
   type ProviderMetadata,
@@ -26,7 +25,6 @@ import { BedrockCache } from "./utils/bedrock-cache.js"
 import { BedrockMedia } from "./utils/bedrock-media.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { MistralToolID } from "./utils/mistral-tool-id.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"
 import { concatBytes } from "../utils/bytes.js"
 
@@ -221,22 +219,18 @@ type BedrockEvent = Schema.Schema.Type<typeof BedrockEvent>
 // =============================================================================
 // Request Lowering
 // =============================================================================
-const lowerToolSpec = (tool: ToolDefinition, inputSchema: JsonSchema): BedrockToolSpec => ({
+const lowerToolSpec = (tool: ToolDefinition): BedrockToolSpec => ({
   toolSpec: {
     name: tool.name,
     ...(tool.description.trim().length > 0 ? { description: tool.description } : {}),
-    inputSchema: { json: inputSchema },
+    inputSchema: { json: tool.inputSchema },
   },
 })
 
-const lowerTools = (
-  model: LanguageModel,
-  breakpoints: BedrockCache.Breakpoints,
-  tools: ReadonlyArray<ToolDefinition>,
-): BedrockTool[] => {
+const lowerTools = (breakpoints: BedrockCache.Breakpoints, tools: ReadonlyArray<ToolDefinition>): BedrockTool[] => {
   const result: BedrockTool[] = []
   for (const tool of tools) {
-    result.push(lowerToolSpec(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, model)))
+    result.push(lowerToolSpec(tool))
     const cachePoint = BedrockCache.block(breakpoints, tool.cache)
     if (cachePoint) result.push(cachePoint)
   }
@@ -441,19 +435,39 @@ const isHighReasoningEffort = Schema.is(
   }),
 )
 
+const Options = Schema.Struct({
+  thinking: Schema.optional(Schema.Struct({ type: Schema.Literal("enabled"), budgetTokens: Schema.Number })),
+})
+export type OptionsInput = typeof Options.Type
+const decodeOptions = ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))
+// Claude on Bedrock requires the thinking budget below `maxTokens`, with a minimum of 1,024.
+const MIN_THINKING_BUDGET = 1_024
+
 const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request: LLMRequest) {
   const toolChoice = request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined
   const flattened = ProviderShared.flattenToolRequest(request)
   const generation = request.generation
+  const options = yield* decodeOptions(request.providerOptions ?? {})
   const maxTokens =
     isNova2(request.model) && isHighReasoningEffort(request.http?.body) ? undefined : generation?.maxTokens
+  const thinking =
+    options.thinking === undefined
+      ? undefined
+      : {
+          type: "enabled",
+          budget_tokens: ProviderShared.fitThinkingBudget(
+            options.thinking.budgetTokens,
+            maxTokens,
+            MIN_THINKING_BUDGET,
+          ),
+        }
   // Bedrock-Claude shares Anthropic's 4-breakpoint cap. Spend the budget in
   // tools → system → messages order to favour the highest-impact prefixes.
   const breakpoints = BedrockCache.breakpoints(request.model.id)
   const toolConfig = (() => {
     if (flattened.tools.length === 0) return undefined
     return {
-      tools: lowerTools(request.model, breakpoints, flattened.tools),
+      tools: lowerTools(breakpoints, flattened.tools),
       // Converse has no native "none". Keep definitions stable for prompt
       // caching and omit only the unsupported choice.
       toolChoice,
@@ -487,9 +501,15 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
     system,
     inferenceConfig,
     toolConfig,
-    // Converse's base inferenceConfig has no topK; Anthropic/Nova accept it
-    // as a model-specific field, so it goes through additionalModelRequestFields.
-    additionalModelRequestFields: generation?.topK === undefined ? undefined : { top_k: generation.topK },
+    // Converse's base inferenceConfig has no topK or thinking; Anthropic/Nova accept them
+    // as model-specific fields, so they go through additionalModelRequestFields.
+    additionalModelRequestFields:
+      generation?.topK === undefined && thinking === undefined
+        ? undefined
+        : {
+            ...(generation?.topK === undefined ? {} : { top_k: generation.topK }),
+            ...(thinking === undefined ? {} : { thinking }),
+          },
   }
 })
 

packages/ai/src/protocols/gemini.ts

@@ -11,7 +11,6 @@ import {
   Usage,
   type FinishReason,
   type LLMRequest,
-  type LanguageModel,
   type MediaPart,
   type ProviderMetadata,
   type ProviderOptions,
@@ -24,11 +23,12 @@ import { Media } from "../media.js"
 import { JsonObject, knownString, lenient, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { GeminiGenerateContent } from "./utils/gemini-generate-content.js"
 import { Lifecycle } from "./utils/lifecycle.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 
 const ADAPTER = "gemini"
 // Google documents this sentinel for replaying Gemini 3 function calls after their original signature was lost.
 const SKIP_THOUGHT_SIGNATURE_VALIDATOR = "skip_thought_signature_validator"
+// Gemini 2.5 rejects a budget under the model's minimum: 512 on Flash-Lite, the highest, and 128 on Pro.
+const MIN_THINKING_BUDGET = 512
 export const DEFAULT_BASE_URL = "https://generativelanguage.googleapis.com/v1beta"
 
 // Gemini 3 rejects replayed function calls without a thought signature. Google's SDKs avoid that in normal chats by
@@ -268,12 +268,11 @@ interface ParserState {
 // =============================================================================
 // Request Lowering
 // =============================================================================
-// Tool schemas go in `parametersJsonSchema`, which accepts standard JSON Schema. Gemini's schema
-// rules are this API's default, including for tuned endpoints whose IDs do not name Gemini.
-const lowerTool = (tool: ToolDefinition, model: LanguageModel) => ({
+// Tool schemas go in `parametersJsonSchema`, which accepts standard JSON Schema.
+const lowerTool = (tool: ToolDefinition) => ({
   name: tool.name,
   description: tool.description,
-  parametersJsonSchema: ToolSchemaProjection.modelCompatibility(tool.inputSchema, model, "gemini"),
+  parametersJsonSchema: tool.inputSchema,
 })
 
 const lowerToolConfig = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
@@ -452,10 +451,22 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
     presencePenalty: generation?.presencePenalty,
     seed: generation?.seed,
     stopSequences: generation?.stop,
+    // Gemini accepts a budget above `maxOutputTokens`, but thinking then leaves the answer empty.
     thinkingConfig:
       options.thinkingConfig === undefined
         ? undefined
-        : { ...options.thinkingConfig, includeThoughts: options.thinkingConfig.includeThoughts ?? true },
+        : {
+            ...options.thinkingConfig,
+            includeThoughts: options.thinkingConfig.includeThoughts ?? true,
+            thinkingBudget:
+              options.thinkingConfig.thinkingBudget === undefined
+                ? undefined
+                : ProviderShared.fitThinkingBudget(
+                    options.thinkingConfig.thinkingBudget,
+                    generation?.maxTokens,
+                    MIN_THINKING_BUDGET,
+                  ),
+          },
   }
 
   return {
@@ -468,7 +479,7 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
     tools: hasTools
       ? [
           {
-            functionDeclarations: flattened.tools.map((tool) => lowerTool(tool, request.model)),
+            functionDeclarations: flattened.tools.map(lowerTool),
           },
         ]
       : undefined,
@@ -804,6 +815,8 @@ export const protocol = Protocol.make({
     schema: GeminiBody,
     from: fromRequest,
   },
+  // Gemini's schema rules are this API's default, including for tuned endpoints whose IDs do not name Gemini.
+  sanitizer: "gemini",
   stream: {
     event: Protocol.jsonEvent(GeminiEvent),
     initial: (request) => ({

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

@@ -56,10 +56,15 @@ interface State extends SpeechStream.Audio, GeminiGenerateContent.Metadata {
 // ---------------------------------------------------------------------------
 
 const fromRequest = Effect.fn("GoogleSpeech.fromRequest")(function* (request: MediaProtocol.Addressed<Request>) {
+  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")
     return yield* route.unsupported(
       "media.format",
-      `${route.name} only returns raw PCM; request format "pcm" or omit it, then wrap the samples yourself`,
+      `${route.name} only accepts raw PCM as an explicit format; omit it to accept the provider's default output`,
     )
   const voiceName = SpeechStream.voiceID(request.voice)
   return MediaProtocol.json(
@@ -97,10 +102,18 @@ const step = Effect.fn("GoogleSpeech.step")(function* (state: State, frame: stri
   return [next, audio.flatMap((part) => SpeechStream.delta(next, part.data)[1])] as const
 })
 
-const finish = (state: State) => {
+const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
   const sampleRate = SpeechStream.sampleRate(state.mimeType) ?? DEFAULT_SAMPLE_RATE
+  const output =
+    state.mimeType?.split(";")[0]?.toLowerCase() === "audio/wav"
+      ? SpeechStream.container("wav", sampleRate)
+      : SpeechStream.pcm("pcm_s16le", sampleRate, state.mimeType ?? `audio/L16;codec=pcm;rate=${sampleRate}`)
+  if (context.request.format === "pcm" && output.info.format !== "pcm")
+    return Effect.fail(
+      route.frameError(`Google Speech returned ${output.info.format} instead of the requested raw PCM`),
+    )
   return SpeechStream.finish(route, state, {
-    ...SpeechStream.pcm("pcm_s16le", sampleRate, state.mimeType ?? `audio/L16;codec=pcm;rate=${sampleRate}`),
+    ...output,
     usage: GeminiGenerateContent.usage(state.usage),
     providerMetadata: GeminiGenerateContent.providerMetadata(state),
     detail: state.finishReason === undefined ? undefined : `finish reason: ${state.finishReason}`,

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

@@ -5,7 +5,6 @@ import { LLMEvent, LLMRequest, Message, ToolResultPart } from "../schema/index.j
 import { OpenResponses } from "./open-responses.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { ResponsesHostedTools } from "./utils/responses-hosted-tools.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { detectMediaType } from "../utils/media-type.js"
 
 const ADAPTER = "meta-responses"
@@ -103,12 +102,7 @@ const fromRequest = Effect.fn("MetaResponses.fromRequest")(function* (request: L
         ? undefined
         : yield* Effect.forEach(projected.tools, (tool) =>
             Effect.gen(function* () {
-              if (tool.native === undefined)
-                return yield* OpenResponses.lowerTool(
-                  NAME,
-                  tool,
-                  ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model),
-                )
+              if (tool.native === undefined) return yield* OpenResponses.lowerTool(NAME, tool)
               return yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(NativeTool))(tool.native.meta)
             }),
           ),

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

@@ -13,7 +13,6 @@ import {
   UnknownProviderError,
   Usage,
   type FinishReasonDetails,
-  type JsonSchema,
   type LLMRequest,
   type MediaPart,
   type ToolCallPart,
@@ -23,7 +22,6 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { MistralToolID } from "./utils/mistral-tool-id.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"
 
 const ADAPTER = "mistral-chat"
@@ -368,9 +366,9 @@ const lowerMessages = Effect.fn("MistralChat.lowerMessages")(function* (request:
   return messages
 })
 
-const lowerTool = (tool: ToolDefinition, inputSchema: JsonSchema): MistralTool => ({
+const lowerTool = (tool: ToolDefinition): MistralTool => ({
   type: "function",
-  function: { name: tool.name, description: tool.description, parameters: inputSchema, strict: false },
+  function: { name: tool.name, description: tool.description, parameters: tool.inputSchema, strict: false },
 })
 
 export const fromRequest = Effect.fn("MistralChat.fromRequest")(function* (request: LLMRequest) {
@@ -396,12 +394,7 @@ export const fromRequest = Effect.fn("MistralChat.fromRequest")(function* (reque
   return {
     model: request.model.id,
     messages: yield* lowerMessages(flattened.request),
-    tools:
-      flattened.tools.length > 0
-        ? flattened.tools.map((tool) =>
-            lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model)),
-          )
-        : undefined,
+    tools: flattened.tools.length > 0 ? flattened.tools.map(lowerTool) : undefined,
     tool_choice: toolChoice,
     stream: true as const,
     max_tokens: request.generation?.maxTokens,

packages/ai/src/protocols/open-responses.ts

@@ -8,7 +8,6 @@ import {
   ProviderInternalError,
   Usage,
   type FinishReason,
-  type JsonSchema,
   type LLMRequest,
   type MediaPart,
   type ProviderMetadata,
@@ -24,7 +23,6 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { effortUpdate } from "../effort-updates.js"
 import { OpenResponsesOptions } from "./utils/open-responses-options.js"
 import { Lifecycle } from "./utils/lifecycle.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"
 
 const ADAPTER = "open-responses"
@@ -443,23 +441,24 @@ interface ReasoningStreamItem {
 // =============================================================================
 // Request Lowering
 // =============================================================================
-export const lowerTool = Effect.fn("OpenResponses.lowerTool")(function* (
-  protocolName: string,
-  tool: ToolDefinition,
-  inputSchema: JsonSchema,
-) {
+export const lowerTool = Effect.fn("OpenResponses.lowerTool")(function* (protocolName: string, tool: ToolDefinition) {
   if (tool.native !== undefined)
     return yield* ProviderShared.invalidRequest(`${protocolName} does not support provider-native tool ${tool.name}`)
   return {
     type: "function" as const,
     name: tool.name,
     description: tool.description,
-    parameters: inputSchema,
+    parameters: tool.inputSchema,
     // The common tool definition does not currently express Responses strict-schema policy.
     strict: false,
   }
 })
 
+export const lowerTools = (tools: ReadonlyArray<ToolDefinition>, adapter: ProviderAdapter) =>
+  Effect.forEach(tools, (tool) =>
+    tool.native !== undefined && adapter.nativeTool ? adapter.nativeTool(tool.native) : lowerTool(adapter.name, tool),
+  )
+
 export const lowerToolChoice = (protocolName: string, toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
   ProviderShared.matchToolChoice(protocolName, toolChoice, {
     auto: () => "auto" as const,
@@ -821,14 +820,7 @@ export const fromRequestWithAdapter = Effect.fn("OpenResponses.fromRequestWithAd
   return {
     ...(yield* lowerConversation(projected.request, adapter)),
     ...lowerGeneration(request),
-    tools:
-      projected.tools.length === 0
-        ? undefined
-        : yield* Effect.forEach(projected.tools, (tool) =>
-            tool.native !== undefined && adapter.nativeTool
-              ? adapter.nativeTool(tool.native)
-              : lowerTool(adapter.name, tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model)),
-          ),
+    tools: projected.tools.length === 0 ? undefined : yield* lowerTools(projected.tools, adapter),
     tool_choice:
       allowedToolChoice(request) ??
       (request.toolChoice ? yield* lowerToolChoice(adapter.name, request.toolChoice) : undefined),

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

@@ -17,7 +17,6 @@ import {
   type FinishReason,
   type FinishReasonDetails,
   type CacheHint,
-  type JsonSchema,
   type LLMRequest,
   type MediaPart,
   type ReasoningPart,
@@ -29,7 +28,6 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { isRecord, JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { OpenAIOptions } from "./utils/openai-options.js"
 import { Lifecycle } from "./utils/lifecycle.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"
 
 const ADAPTER = "openai-chat"
@@ -330,17 +328,12 @@ interface LoweringOptions {
   readonly toolCallID?: (id: string) => string
 }
 
-const lowerTool = (
-  tool: ToolDefinition,
-  inputSchema: JsonSchema,
-  options: LoweringOptions,
-  supportsStrictMode: boolean,
-): OpenAIChatTool => ({
+const lowerTool = (tool: ToolDefinition, options: LoweringOptions, supportsStrictMode: boolean): OpenAIChatTool => ({
   type: "function",
   function: {
     name: tool.name,
     description: tool.description,
-    parameters: inputSchema,
+    parameters: tool.inputSchema,
     ...(supportsStrictMode ? { strict: false } : {}),
   },
   cache_control: options.cacheControl?.(tool.cache),
@@ -825,14 +818,7 @@ export const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (
         ? hasHistory
           ? []
           : undefined
-        : flattened.tools.map((tool) =>
-            lowerTool(
-              tool,
-              ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model),
-              options,
-              supportsStrictMode,
-            ),
-          ),
+        : flattened.tools.map((tool) => lowerTool(tool, options, supportsStrictMode)),
     tool_choice: hasActiveTools && request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined,
     stream: true as const,
     ...(supportsUsageInStreaming ? { stream_options: { include_usage: true } } : {}),

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

@@ -5,20 +5,12 @@ import { Auth } from "../route/auth.js"
 import { Endpoint } from "../route/endpoint.js"
 import { Protocol } from "../route/protocol.js"
 import { HttpTransport } from "../route/transport/index.js"
-import {
-  LLMRequest,
-  mergeJsonRecords,
-  type JsonSchema,
-  type LanguageModel,
-  type ToolDefinition,
-  type ToolEntry,
-} from "../schema/index.js"
+import { LLMRequest, type ToolDefinition, type ToolEntry } from "../schema/index.js"
 import { resolveEffortUpdates } from "../effort-updates.js"
 import { OpenResponses } from "./open-responses.js"
 import { OpenResponsesOptions } from "./utils/open-responses-options.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { ResponsesHostedTools } from "./utils/responses-hosted-tools.js"
-import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { OpenResponsesChannel } from "./open-responses-channel.js"
 import { ResponsesCompaction } from "./utils/responses-compaction.js"
 import { ResponsesCheckpoint } from "./utils/responses-checkpoint.js"
@@ -143,11 +135,6 @@ export const CompactionTrigger = Schema.Struct({ type: Schema.Literal("compactio
 const CheckpointBody = Schema.Struct({
   ...OpenAIResponsesBody.fields,
   input: Schema.Array(Schema.Union([OpenAIResponsesInputItem, CompactionTrigger])),
-  store: Schema.Literal(false),
-  prompt_cache_retention: optionalNull(Schema.String),
-  prompt_cache_options: optionalNull(
-    Schema.Struct({ mode: Schema.optional(Schema.String), ttl: Schema.optional(Schema.String) }),
-  ),
 })
 
 const adapter = {
@@ -174,20 +161,19 @@ const nativeImageTool = (tool: ToolDefinition) => {
   return Schema.is(OpenAIResponsesImageGenerationTool)(native) ? native : undefined
 }
 
-const lowerTool = Effect.fn("OpenAIResponses.lowerTool")(function* (tool: ToolDefinition, inputSchema: JsonSchema) {
+const lowerTool = Effect.fn("OpenAIResponses.lowerTool")(function* (tool: ToolDefinition) {
   const native = nativeImageToolInput(tool)
   if (native !== undefined) {
     if (Schema.is(OpenAIResponsesImageGenerationTool)(native)) return native
     return yield* ProviderShared.invalidRequest("OpenAI Responses image generation tool options are invalid")
   }
-  return yield* OpenResponses.lowerTool(NAME, tool, inputSchema)
+  return yield* OpenResponses.lowerTool(NAME, tool)
 })
 
 // Native namespaces hold only function tools, so deeper levels flatten into
 // the leaf names the same way non-native protocols flatten the whole tree.
-const lowerToolEntry = Effect.fn("OpenAIResponses.lowerToolEntry")(function* (tool: ToolEntry, model: LanguageModel) {
-  if (tool.type === "tool")
-    return yield* lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, model))
+const lowerToolEntry = Effect.fn("OpenAIResponses.lowerToolEntry")(function* (tool: ToolEntry) {
+  if (tool.type === "tool") return yield* lowerTool(tool)
   // OpenAI requires a namespace description; fall back to a generic one so a
   // missing description never blocks the request.
   return {
@@ -195,11 +181,13 @@ const lowerToolEntry = Effect.fn("OpenAIResponses.lowerToolEntry")(function* (to
     name: tool.name,
     description: tool.description ?? `Tools in the ${tool.name} namespace.`,
     tools: yield* Effect.forEach(ProviderShared.flattenTools(tool.tools), (leaf) =>
-      OpenResponses.lowerTool(NAME, leaf, ToolSchemaProjection.modelCompatibility(leaf.inputSchema, model)),
+      OpenResponses.lowerTool(NAME, leaf),
     ),
   }
 })
 
+const lowerTools = (request: LLMRequest) => Effect.forEach(request.tools, lowerToolEntry)
+
 const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>, tools: ReadonlyArray<ToolEntry>) =>
   ProviderShared.matchToolChoice(NAME, toolChoice, {
     auto: () => "auto" as const,
@@ -223,10 +211,7 @@ const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request:
     ...(yield* OpenResponses.lowerConversation(updates.request, adapter)),
     ...OpenResponses.lowerGeneration(request, { ...options, reasoningEffort: updates.effort }),
     context_management: management?.map((edit) => ({ type: edit.type, compact_threshold: edit.compactThreshold })),
-    tools:
-      request.tools.length === 0
-        ? undefined
-        : yield* Effect.forEach(request.tools, (tool) => lowerToolEntry(tool, request.model)),
+    tools: request.tools.length === 0 ? undefined : yield* lowerTools(request),
     tool_choice:
       request.tools.length === 0
         ? undefined
@@ -238,7 +223,6 @@ const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request:
 const checkpointBody = {
   schema: CheckpointBody,
   from: Effect.fn("OpenAIResponses.checkpointBody")(function* (request: LLMRequest) {
-    const native = yield* fromRequest(LLMRequest.update(request, { toolChoice: undefined }))
     const overlay = request.http?.body
     // Complete history is required for stateless replay and SSE recovery. Raw input overrides bypass that contract.
     if (
@@ -249,18 +233,13 @@ const checkpointBody = {
       return yield* ProviderShared.invalidRequest(
         "Trigger compaction requires complete canonical history, not an input or continuation override",
       )
-    return yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(CheckpointBody))({
-      ...mergeJsonRecords(native, overlay),
-      input: [...native.input, { type: "compaction_trigger" }],
-      stream: true,
-      store: false,
-      parallel_tool_calls: true,
-      tool_choice: undefined,
-      context_management: undefined,
-      text: undefined,
-      max_output_tokens: undefined,
-      max_tool_calls: undefined,
-    })
+    if (overlay?.stream !== undefined && overlay.stream !== true)
+      return yield* ProviderShared.invalidRequest("Trigger compaction requires a streamed response")
+    const native = yield* fromRequest(request)
+    return {
+      ...native,
+      input: [...native.input, { type: "compaction_trigger" as const }],
+    }
   }),
 }
 
@@ -342,7 +321,10 @@ export const transport = channelTransport({
 })
 
 export const route = Route.make({
-  compact: { endpoint: ResponsesCompaction.make(adapter), trigger: ResponsesCheckpoint.make(checkpointBody) },
+  compact: {
+    endpoint: ResponsesCompaction.make(adapter, lowerTools),
+    trigger: ResponsesCheckpoint.make(checkpointBody),
+  },
   id: ADAPTER,
   provider: "openai",
   providerMetadataKey: "openai",

packages/ai/src/protocols/shared.ts

@@ -110,6 +110,14 @@ export const sumTokens = (...values: ReadonlyArray<number | undefined>): number
   return values.reduce((acc: number, value) => acc + (value ?? 0), 0)
 }
 
+/**
+ * Caps an explicit thinking budget at half the output limit. Thinking counts against the output limit, so a budget
+ * near it leaves the answer, a tool call, or a summary without room. Smaller budgets, special values such as `-1` and
+ * `0`, and requests without an output limit pass through unchanged.
+ */
+export const fitThinkingBudget = (budget: number, maxTokens: number | undefined, minimum = 1) =>
+  maxTokens === undefined || budget <= maxTokens / 2 ? budget : Math.max(minimum, Math.floor(maxTokens / 2))
+
 export const eventError = (route: string, message: string, body?: string, cause?: unknown) =>
   new AIError({
     reason: new InvalidProviderOutputError({ route, message, body, cause }),

packages/ai/src/protocols/utils/responses-checkpoint.ts

@@ -1,7 +1,7 @@
 import { Effect, Schema, Stream } from "effect"
 import { Route, type RouteBody, type TriggerCompactOperation } from "../../route/client.js"
 import { Protocol } from "../../route/protocol.js"
-import { CompactionCheckpointResponse, HttpOptions, LLMEvent, LLMRequest } from "../../schema/index.js"
+import { CompactionCheckpointResponse, LLMEvent, LLMRequest } from "../../schema/index.js"
 import { OpenResponses } from "../open-responses.js"
 import { ProviderShared } from "../shared.js"
 
@@ -109,12 +109,8 @@ export const make = <Body>(body: RouteBody<Body>): TriggerCompactOperation =>
       transport: source.transport,
     })
     const native = yield* body.from(request)
-    // The body builder already applied and validated overlays. Do not let transport reapply them.
-    const preparedRequest = LLMRequest.update(request, {
-      http: request.http === undefined ? undefined : new HttpOptions({ ...request.http, body: undefined }),
-    })
-    const prepared = yield* route.prepareTransport(native, preparedRequest, options)
-    yield* route.streamPrepared(prepared, preparedRequest, { http: executor }, options).pipe(Stream.runDrain)
+    const prepared = yield* route.prepareTransport(native, request, options)
+    yield* route.streamPrepared(prepared, request, { http: executor }, options).pipe(Stream.runDrain)
     if (!result) return yield* ProviderShared.eventError(source.id, "Compaction response ended without a checkpoint")
     return result
   })

packages/ai/src/protocols/utils/responses-compaction.ts

@@ -19,12 +19,18 @@ import { OpenResponses } from "../open-responses.js"
 import { JsonObject, optionalNull, ProviderShared } from "../shared.js"
 import { Media } from "../../media.js"
 
+// /compact has a smaller wire contract than /responses; keep the request controls it accepts.
 const Body = Schema.Struct({
   model: Schema.String,
   input: Schema.Array(Schema.Unknown),
   instructions: optionalNull(Schema.String),
   previous_response_id: optionalNull(Schema.String),
   service_tier: optionalNull(Schema.String),
+  reasoning: Schema.optional(JsonObject),
+  text: Schema.optional(JsonObject),
+  include: OpenResponses.coreFields.include,
+  parallel_tool_calls: OpenResponses.coreFields.parallel_tool_calls,
+  tools: Schema.optional(Schema.Array(JsonObject)),
   prompt_cache_key: optionalNull(Schema.String),
   prompt_cache_retention: optionalNull(Schema.String),
   prompt_cache_options: optionalNull(
@@ -74,17 +80,27 @@ const Response = Schema.Struct({
   usage: Schema.optional(Schema.StructWithRest(OpenResponses.OpenResponsesUsage, [JsonObject])),
 })
 
-export const make = (adapter: OpenResponses.ProviderAdapter): CompactOperation =>
+export const make = (
+  adapter: OpenResponses.ProviderAdapter,
+  lowerTools: (request: LLMRequest) => Effect.Effect<ReadonlyArray<Record<string, unknown>>, AIError>,
+): CompactOperation =>
   Effect.fn("ResponsesCompaction.execute")(function* (request, executor, options) {
     const route = request.model.route
     // The standalone compaction endpoint rejects histories containing configuration updates.
     const native = yield* OpenResponses.lowerConversation(stripEffortUpdates(request), adapter)
+    const generation = OpenResponses.lowerGeneration(request)
+    const tools = request.tools.length === 0 ? undefined : yield* lowerTools(request)
     const body = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Body))(
       mergeJsonRecords(
         {
           ...native,
-          service_tier: request.providerOptions?.serviceTier,
-          prompt_cache_key: ProviderShared.promptCacheKey(request),
+          service_tier: generation.service_tier,
+          reasoning: generation.reasoning,
+          text: generation.text,
+          include: generation.include,
+          parallel_tool_calls: generation.parallel_tool_calls,
+          tools,
+          prompt_cache_key: generation.prompt_cache_key,
         },
         request.http?.body,
       ),

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

@@ -1,4 +1,4 @@
-import type { JsonSchema, LanguageModel, LanguageModelSanitizerCompatibility } from "../../schema/index.js"
+import { ToolDefinition, type JsonSchema, type LanguageModel, type LLMRequest } from "../../schema/index.js"
 import { isRecord } from "../../utils/record.js"
 import { GeminiJsonSchema } from "./gemini-json-schema.js"
 
@@ -70,13 +70,13 @@ const objectRoot = (schema: JsonSchema): JsonSchema => {
 // Otherwise the protocol's own default applies (the Gemini API always uses Gemini's rules), then the
 // model name selects the family's rules so models reached through gateways and OpenAI-compatible
 // endpoints get the same handling.
-const modelCompatibility = (
-  schema: JsonSchema,
-  model: LanguageModel,
-  protocolDefault?: LanguageModelSanitizerCompatibility,
-): JsonSchema => {
+const modelCompatibility = (schema: JsonSchema, model: LanguageModel): JsonSchema => {
   const root = objectRoot(schema)
-  switch (model.compatibility?.sanitizer ?? protocolDefault ?? MODEL_NAMES.find(([name]) => name.test(model.id))?.[1]) {
+  switch (
+    model.compatibility?.sanitizer ??
+    model.route.sanitizer ??
+    MODEL_NAMES.find(([name]) => name.test(model.id))?.[1]
+  ) {
     case "gemini":
       return gemini(root)
     case "moonshot":
@@ -87,10 +87,18 @@ const modelCompatibility = (
   }
 }
 
+// Applied once to every request before any protocol builds its body, including tools in namespaces.
+const tools = (entries: LLMRequest["tools"], model: LanguageModel): LLMRequest["tools"] =>
+  entries.map((tool) =>
+    tool.type === "tool"
+      ? new ToolDefinition({ ...tool, inputSchema: modelCompatibility(tool.inputSchema, model) })
+      : { ...tool, tools: tools(tool.tools, model) },
+  )
+
 export const ToolSchemaProjection = {
   gemini,
-  modelCompatibility,
   moonshot,
   openAI,
   responses,
+  tools,
 } as const

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

@@ -50,7 +50,8 @@ const fromRequest = Effect.fn("XAIResponses.fromRequest")(function* (request: LL
       operation: "in-band-compaction",
       provider: request.model.provider,
       route: request.model.route.id,
-      message: "xAI requires explicit compaction through LLMClient.compact; automatic context management is not supported",
+      message:
+        "xAI requires explicit compaction through LLMClient.compact; automatic context management is not supported",
     })
   return yield* decodeBody(yield* OpenResponses.fromRequestWithAdapter(request, adapter))
 })
@@ -93,6 +94,8 @@ export const protocol = Protocol.make({
   },
 })
 
-export const compact = ResponsesCompaction.make(adapter)
+export const compact = ResponsesCompaction.make(adapter, (request) =>
+  OpenResponses.lowerTools(ProviderShared.flattenTools(request.tools), adapter),
+)
 
 export * as XAIResponses from "./xai-responses.js"

packages/ai/src/provider-error.ts

@@ -80,7 +80,13 @@ const SERVER_CODES = new Set([
   "slow_down",
   "serviceunavailableexception",
 ])
-const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error", "validationexception"])
+// `invalid_request` is the Vercel AI Gateway's code for an upstream request rejection.
+const INVALID_REQUEST_CODES = new Set([
+  "invalid_prompt",
+  "invalid_request",
+  "invalid_request_error",
+  "validationexception",
+])
 // Azure OpenAI reports `content_filter` with `innererror.code` ResponsibleAIPolicyViolation.
 // OpenRouter tags provider failures with a typed `error_type`; its Responses skin also
 // emits `image_content_policy_violation` as the native code.

packages/ai/src/providers/amazon-bedrock.ts

@@ -31,6 +31,7 @@ export interface Settings extends ProviderPackage.Settings {
   readonly profile?: string
   readonly region?: string
   readonly topP?: number
+  readonly thinking?: BedrockConverse.OptionsInput["thinking"]
 }
 export const routes = [BedrockConverse.route]
 
@@ -71,6 +72,7 @@ export const model: ProviderPackage.Definition<Settings>["model"] = (modelID, se
     generation: settings.topP === undefined ? undefined : { topP: settings.topP },
     headers: settings.headers === undefined ? undefined : { ...settings.headers },
     http: settings.body === undefined ? undefined : { body: { ...settings.body } },
+    providerOptions: settings.thinking === undefined ? undefined : { thinking: settings.thinking },
     profile: settings.profile,
     region: settings.region,
   }).model(modelID)

packages/ai/src/providers/openai-options.ts

@@ -32,10 +32,7 @@ const openAIProviderOptions = (options: OpenAIOptionsInput | undefined): Provide
   return result
 }
 
-export const gpt5DefaultOptions = (
-  modelID: string,
-  options: { readonly textVerbosity?: boolean } = {},
-): ProviderOptions | undefined => {
+export const gpt5DefaultOptions = (modelID: string): ProviderOptions | undefined => {
   const id = modelID.toLowerCase()
   if (!id.includes("gpt-5") || id.includes("gpt-5-chat") || id.includes("gpt-5-pro")) return undefined
   return openAIProviderOptions({
@@ -47,27 +44,19 @@ export const gpt5DefaultOptions = (
     // this, callers using the default model facade get reasoning summaries
     // they cannot replay statelessly.
     include: ["reasoning.encrypted_content"],
-    textVerbosity:
-      options.textVerbosity === true && id.includes("gpt-5.") && !id.includes("codex") && !id.includes("-chat")
-        ? "low"
-        : undefined,
   })
 }
 
-export const openAIDefaultOptions = (
-  modelID: string,
-  options: { readonly textVerbosity?: boolean } = {},
-): ProviderOptions | undefined =>
-  mergeProviderOptions(openAIProviderOptions({ store: false }), gpt5DefaultOptions(modelID, options))
+export const openAIDefaultOptions = (modelID: string): ProviderOptions | undefined =>
+  mergeProviderOptions(openAIProviderOptions({ store: false }), gpt5DefaultOptions(modelID))
 
 export const withOpenAIOptions = <Options extends { readonly providerOptions?: OpenAIProviderOptionsInput }>(
   modelID: string,
   options: Options,
-  defaults: { readonly textVerbosity?: boolean } = {},
 ): Omit<Options, "providerOptions"> & { readonly providerOptions?: ProviderOptions } => {
   return {
     ...options,
-    providerOptions: mergeProviderOptions(openAIDefaultOptions(modelID, defaults), options.providerOptions),
+    providerOptions: mergeProviderOptions(openAIDefaultOptions(modelID), options.providerOptions),
   }
 }
 

packages/ai/src/providers/openai.ts

@@ -100,7 +100,7 @@ export const configure = (input: Config = {}) => {
   const modelDefaults = defaults(input)
   const responses = (id: string | ModelID) =>
     responsesRoute
-      .with(withOpenAIOptions(id, modelDefaults, { textVerbosity: true }))
+      .with(withOpenAIOptions(id, modelDefaults))
       .model<OpenAIProviderOptionsInput>({ id })
   const chat = (id: string | ModelID) =>
     chatRoute.with(withOpenAIOptions(id, modelDefaults)).model<OpenAIProviderOptionsInput>({

packages/ai/src/providers/openrouter.ts

@@ -8,7 +8,7 @@ import type { ProviderPackage } from "../provider-package.js"
 import { SystemOne } from "../experimental/system-one.js"
 import { OpenAIChat } from "../protocols/openai-chat.js"
 import { newBreakpoints, ttlBucket } from "../protocols/utils/cache.js"
-import { isRecord } from "../protocols/shared.js"
+import { isRecord, ProviderShared } from "../protocols/shared.js"
 
 export const id = ProviderID.make("openrouter")
 const baseURL = "https://openrouter.ai/api/v1"
@@ -123,7 +123,7 @@ export const protocol = Protocol.make({
           return {
             ...body,
             messages,
-            ...bodyOptions(request.providerOptions),
+            ...bodyOptions(request.providerOptions, request.generation?.maxTokens),
           } as OpenRouterBody
         }),
       ),
@@ -143,7 +143,14 @@ const cacheControl = () => {
   }
 }
 
-const bodyOptions = (input: unknown) => {
+// OpenRouter forwards `reasoning.max_tokens` as the upstream thinking budget. Upstreams such as Anthropic and Alibaba
+// reject one that is not below the output limit; 1,024 is Anthropic's minimum budget.
+const fitReasoning = (reasoning: Record<string, unknown>, maxTokens: number | undefined) =>
+  typeof reasoning.max_tokens === "number"
+    ? { ...reasoning, max_tokens: ProviderShared.fitThinkingBudget(reasoning.max_tokens, maxTokens, 1_024) }
+    : reasoning
+
+const bodyOptions = (input: unknown, maxTokens: number | undefined) => {
   const openrouter = isRecord(input) ? input : {}
   const { usage, models, provider, plugins, web_search_options, debug, user, reasoning, promptCacheKey, ...options } =
     openrouter
@@ -162,7 +169,7 @@ const bodyOptions = (input: unknown) => {
     ...(isRecord(web_search_options) ? { web_search_options } : {}),
     ...(isRecord(debug) ? { debug } : {}),
     ...(typeof user === "string" ? { user } : {}),
-    ...(isRecord(reasoning) ? { reasoning } : {}),
+    ...(isRecord(reasoning) ? { reasoning: fitReasoning(reasoning, maxTokens) } : {}),
   }
 }
 

packages/ai/src/route/client.ts

@@ -11,7 +11,8 @@ import { applyEffortUpdates } from "../effort-updates.js"
 import { normalizeToolHistory } from "../tool-history.js"
 import { sanitizeSurrogates } from "../utils/sanitize.js"
 import * as ProviderShared from "../protocols/shared.js"
-import type { ProtocolID, ProviderOptions } from "../schema/index.js"
+import { ToolSchemaProjection } from "../protocols/utils/tool-schema.js"
+import type { LanguageModelSanitizerCompatibility, ProtocolID, ProviderOptions } from "../schema/index.js"
 import {
   AIError,
   CompactionResponse,
@@ -57,6 +58,7 @@ export interface Route<
   readonly defaults: RouteDefaults
   readonly body: RouteBody<Body>
   readonly supportsEffortUpdates?: (request: LLMRequest) => boolean
+  readonly sanitizer?: LanguageModelSanitizerCompatibility
   readonly with: {
     <Next extends CompactionOperations | undefined>(
       patch: RoutePatch<Body, Prepared> & { readonly compact: Next },
@@ -388,6 +390,7 @@ function makeFromTransport<Body, Prepared, Frame, Event, State>(
       defaults: routeInput.defaults ?? {},
       body: protocol.body,
       supportsEffortUpdates: protocol.supportsEffortUpdates,
+      sanitizer: protocol.sanitizer,
       with: (patch: RoutePatch<Body, Prepared>) => {
         const { compact, id, provider, providerMetadataKey, auth, transport, endpoint, ...defaults } = patch
         return build({
@@ -559,7 +562,9 @@ const prepareRequest = (request: LLMRequest) => {
       tool.type === "tool" ? tool : { ...tool, tools: dedupe(tool.tools) },
     )
   const resolved = applyCachePolicy(
-    applyEffortUpdates(LLMRequest.update(sanitized, { tools: dedupe(sanitized.tools) })),
+    applyEffortUpdates(
+      LLMRequest.update(sanitized, { tools: ToolSchemaProjection.tools(dedupe(sanitized.tools), sanitized.model) }),
+    ),
   )
   const headers = resolved.model.route.headers?.({ request: resolved })
   return headers === undefined

packages/ai/src/route/media.ts

@@ -5,7 +5,7 @@ import { Endpoint } from "./endpoint.js"
 import { RequestExecutorService, type Interface } from "./executor-service.js"
 import { RequestExecutor } from "./executor.js"
 import { MediaProtocol } from "./media-protocol.js"
-import { Generation, resultEvents, type AwaitOptions, type Observation } from "../generation.js"
+import { Generation } from "../generation.js"
 import type { Media } from "../media.js"
 import {
   AIError,
@@ -52,7 +52,7 @@ export const deployment = (
 // ---------------------------------------------------------------------------
 
 /** One request, one response. */
-export interface Route<Request extends MediaRequest, Response> {
+export interface InlineRoute<Request extends MediaRequest, Response> {
   readonly kind: "inline"
   readonly id: string
   readonly provider: ProviderID
@@ -86,7 +86,7 @@ export interface StreamRoute<Request extends MediaRequest, Event, Response> {
 }
 
 export type AnyRoute<Request extends MediaRequest, Event, Response> =
-  | Route<Request, Response>
+  | InlineRoute<Request, Response>
   | StreamRoute<Request, Event, Response>
   | QueuedRoute<Request, Response>
 
@@ -119,7 +119,7 @@ export interface StreamInput<Request extends MediaRequest, Event, Response, Fram
  */
 export const inline = <Request extends MediaRequest, Response>(
   input: InlineInput<Request, Response>,
-): Route<Request, Response> => {
+): InlineRoute<Request, Response> => {
   const transport = makeTransport(input)
   return {
     kind: "inline",
@@ -267,59 +267,6 @@ export const stream = <Request extends MediaRequest, Event, Response, Frame, Sta
   }
 }
 
-export const dispatch = <Event, Response>(input: {
-  readonly modality: string
-  readonly execute: Execute
-  readonly responseEvents: (response: Response) => ReadonlyArray<Event>
-}) => {
-  const notQueued = (route: { readonly provider: ProviderID; readonly id: string }, operation: string) =>
-    new AIError({
-      reason: new UnsupportedOperationError({
-        operation: `${input.modality}.${operation}`,
-        provider: route.provider,
-        route: route.id,
-        message: `${route.provider}/${route.id} is not a queued route; use generate or stream`,
-      }),
-    })
-  const start = <Request extends MediaRequest>(route: AnyRoute<Request, Event, Response>, request: Request) => {
-    if (route.kind !== "queued") return Effect.fail(notQueued(route, "start"))
-    return route.start(request, input.execute)
-  }
-  return {
-    start,
-    resume: <Request extends MediaRequest>(
-      route: AnyRoute<Request, Event, Response>,
-      model: MediaRequest["model"],
-      token: unknown,
-    ) => {
-      if (route.kind !== "queued") return Effect.fail(notQueued(route, "resume"))
-      return route.resume(model, token, input.execute)
-    },
-    generate: <Request extends MediaRequest>(
-      route: AnyRoute<Request, Event, Response>,
-      request: Request,
-      options?: AwaitOptions,
-    ) => {
-      if (route.kind !== "queued") return route.generate(request, input.execute)
-      return start(route, request).pipe(Effect.flatMap((generation) => generation.await(options)))
-    },
-    stream: <Request extends MediaRequest>(
-      route: AnyRoute<Request, Event, Response>,
-      request: Request,
-      options?: AwaitOptions,
-    ): Stream.Stream<Event | Observation, AIError> => {
-      if (route.kind === "stream") return route.stream(request, input.execute)
-      if (route.kind === "queued")
-        return Stream.unwrap(
-          start(route, request).pipe(
-            Effect.map((generation) => resultEvents(generation, input.responseEvents, options)),
-          ),
-        )
-      return Stream.fromIterableEffect(Effect.map(route.generate(request, input.execute), input.responseEvents))
-    },
-  }
-}
-
 // ---------------------------------------------------------------------------
 // Transport plumbing shared by every kind
 // ---------------------------------------------------------------------------

packages/ai/src/route/protocol.ts

@@ -1,5 +1,5 @@
 import { Schema, type Effect } from "effect"
-import type { AIError, LLMEvent, LLMRequest, ProtocolID } from "../schema/index.js"
+import type { AIError, LanguageModelSanitizerCompatibility, LLMEvent, LLMRequest, ProtocolID } from "../schema/index.js"
 
 /**
  * The semantic API contract of one model server family.
@@ -43,6 +43,8 @@ export interface Protocol<Body, Frame, Event, State> {
   readonly stream: ProtocolStream<Frame, Event, State>
   /** Whether `body.from` lowers `Message.effort(...)` markers; wrappers around another `body.from` must forward it. */
   readonly supportsEffortUpdates?: (request: LLMRequest) => boolean
+  /** Tool schema sanitizer for every model on this protocol unless the model's compatibility sets one; wrappers around another `body.from` must forward it. */
+  readonly sanitizer?: LanguageModelSanitizerCompatibility
 }
 
 export interface ProtocolBody<Body> {

packages/ai/src/speech-client.ts

@@ -1,53 +1,31 @@
-import { Context, Effect, Layer, Stream } from "effect"
-import { RequestExecutor } from "./route/executor.js"
-import type { AIError } from "./schema/index.js"
-import type { SpeechEvent, SpeechOptions, SpeechRequestFor, SpeechResponse } from "./speech.js"
+import { Context } from "effect"
+import { MediaClient } from "./media-client.js"
+import {
+  SpeechTimestampsEvent,
+  SpeechFinishEvent,
+  type SpeechEvent,
+  type SpeechRequestFor,
+  type SpeechResponse,
+} from "./speech.js"
 
-export interface Interface {
-  readonly generate: <Options extends SpeechOptions>(
-    request: SpeechRequestFor<Options>,
-  ) => Effect.Effect<SpeechResponse, AIError>
-  readonly stream: <Options extends SpeechOptions>(
-    request: SpeechRequestFor<Options>,
-  ) => Stream.Stream<SpeechEvent, AIError>
-}
+export type Interface = MediaClient.Interface<SpeechRequestFor, SpeechEvent, SpeechResponse>
 
 export class SpeechClientService extends Context.Service<SpeechClientService, Interface>()("@opencode/SpeechClient") {}
 export const Service = SpeechClientService
 export type Service = SpeechClientService
 
-export const generate = <Options extends SpeechOptions>(
-  request: SpeechRequestFor<Options>,
-): Effect.Effect<SpeechResponse, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.generate(request)
-  })
-
-export const stream = <Options extends SpeechOptions>(
-  request: SpeechRequestFor<Options>,
-): Stream.Stream<SpeechEvent, AIError, Service> =>
-  Stream.unwrap(
-    Effect.gen(function* () {
-      const client = yield* Service
-      return client.stream(request)
-    }),
-  )
-
-export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
-  Service,
-  Effect.gen(function* () {
-    const executor = yield* RequestExecutor.Service
-    return Service.of({
-      generate: (request) => request.model.route.generate(request, executor.execute),
-      stream: (request) => request.model.route.stream(request, executor.execute),
-    })
-  }),
-)
-
 export const SpeechClient = {
   Service,
-  layer,
-  generate,
-  stream,
+  ...MediaClient.make(Service, {
+    modality: "speech",
+    responseEvents: (response: SpeechResponse) => [
+      ...(response.timestamps === undefined ? [] : [SpeechTimestampsEvent.make({ items: response.timestamps })]),
+      SpeechFinishEvent.make({
+        audio: response.audio,
+        usage: response.usage,
+        notices: response.notices,
+        providerMetadata: response.providerMetadata,
+      }),
+    ],
+  }),
 } as const

packages/ai/src/speech.ts

@@ -1,8 +1,8 @@
 import { Effect, Schema, Stream } from "effect"
+import { ProgressEvent, QueuedEvent } from "./generation.js"
 import { Media } from "./media.js"
 import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
-import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata, type OpenString } from "./schema/index.js"
 import { SpeechClient, Service } from "./speech-client.js"
 
@@ -10,53 +10,39 @@ import { SpeechClient, Service } from "./speech-client.js"
 // Model
 // ---------------------------------------------------------------------------
 
-export type SpeechOptions = Record<string, unknown>
+export type SpeechOptions = MediaModel.Options
 
-export type SpeechRoute<Options extends SpeechOptions = SpeechOptions> = MediaRoute.StreamRoute<
-  SpeechRequestFor<Options>,
-  SpeechEvent,
-  SpeechResponse
->
+export type SpeechRoute = MediaRoute.AnyRoute<SpeechRequestFor, SpeechEvent, SpeechResponse>
 
-export class SpeechModel<Options extends SpeechOptions = SpeechOptions> extends MediaModel<
-  SpeechRoute<Options>,
-  Options
-> {
+export class SpeechModel<Options extends SpeechOptions = SpeechOptions> extends MediaModel<SpeechRoute, Options> {
   declare protected readonly _SpeechModel: void
 
-  static make<Options extends SpeechOptions = SpeechOptions>(input: MediaModel.Input<SpeechRoute<Options>>) {
-    return new SpeechModel<Options>(input)
-  }
-
-  /** Compose a streaming speech protocol with its canonical path into a model for one deployment. */
-  static fromRoute<Options extends SpeechOptions = SpeechOptions, Frame = unknown, State = unknown>(
-    route: SpeechModel.RouteInput<Options, Frame, State>,
+  /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
+  static fromRoute<Options extends SpeechOptions>(
+    route: MediaModel.InlineRouteInput<SpeechRequestFor<Options>, SpeechResponse>,
+    input: MediaRoute.ModelInput,
+  ): SpeechModel<Options>
+  static fromRoute<Options extends SpeechOptions, Frame, State>(
+    route: MediaModel.StreamRouteInput<SpeechRequestFor<Options>, SpeechEvent, Frame, State>,
+    input: MediaRoute.ModelInput,
+  ): SpeechModel<Options>
+  static fromRoute<Options extends SpeechOptions, Token>(
+    route: MediaModel.QueuedRouteInput<SpeechRequestFor<Options>, SpeechResponse, Token>,
+    input: MediaRoute.ModelInput,
+  ): SpeechModel<Options>
+  static fromRoute<Options extends SpeechOptions, Frame, State, Token>(
+    route: MediaModel.AnyRouteInput<SpeechRequestFor<Options>, SpeechEvent, SpeechResponse, Frame, State, Token>,
     input: MediaRoute.ModelInput,
   ) {
     return new SpeechModel<Options>({
       id: input.id,
       provider: route.protocol.provider,
       http: input.http,
-      route: composeRoute(
-        (composition) => MediaRoute.stream({ ...composition, collect: collectResponse }),
-        route,
-        input,
-      ),
+      route: composeRoute(route, input, collectResponse) as SpeechRoute,
     })
   }
 }
 
-export namespace SpeechModel {
-  export type RouteInput<
-    Options extends SpeechOptions = SpeechOptions,
-    Frame = unknown,
-    State = unknown,
-  > = MediaModel.RouteInput<
-    MediaProtocol.Addressed<SpeechRequestFor<Options>>,
-    MediaProtocol.Streamed<SpeechRequestFor<Options>, SpeechEvent, Frame, State>
-  >
-}
-
 export const SpeechModelSchema = Schema.declare((value): value is SpeechModel => value instanceof SpeechModel, {
   expected: "Speech.Model",
 })
@@ -148,11 +134,17 @@ export const SpeechFinishEvent = Schema.Struct({
   providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "Speech.Event.Finish" })
 
-const speechEventTagged = Schema.Union([SpeechAudioDeltaEvent, SpeechTimestampsEvent, SpeechFinishEvent]).pipe(
-  Schema.toTaggedUnion("type"),
-)
+const speechEventTagged = Schema.Union([
+  QueuedEvent,
+  ProgressEvent,
+  SpeechAudioDeltaEvent,
+  SpeechTimestampsEvent,
+  SpeechFinishEvent,
+]).pipe(Schema.toTaggedUnion("type"))
 export const SpeechEvent = Object.assign(speechEventTagged, {
   is: {
+    generationQueued: speechEventTagged.guards["generation-queued"],
+    generationProgress: speechEventTagged.guards["generation-progress"],
     audioDelta: speechEventTagged.guards["audio-delta"],
     timestamps: speechEventTagged.guards.timestamps,
     finish: speechEventTagged.guards.finish,
@@ -195,17 +187,15 @@ export function request(input: SpeechRequest | SpeechRequestInput) {
 const requestEffect = (input: SpeechRequest | SpeechRequestInput) => tryRequest(() => request(input))
 
 export function generate<const Model extends SpeechModel>(
-  input: SpeechRequestInput<Model>,
+  input: SpeechRequest | SpeechRequestInput<Model>,
 ): Effect.Effect<SpeechResponse, AIError, Service>
-export function generate(input: SpeechRequest): Effect.Effect<SpeechResponse, AIError, Service>
 export function generate(input: SpeechRequest | SpeechRequestInput) {
   return requestEffect(input).pipe(Effect.flatMap((request) => SpeechClient.generate(request)))
 }
 
 export function stream<const Model extends SpeechModel>(
-  input: SpeechRequestInput<Model>,
+  input: SpeechRequest | SpeechRequestInput<Model>,
 ): Stream.Stream<SpeechEvent, AIError, Service>
-export function stream(input: SpeechRequest): Stream.Stream<SpeechEvent, AIError, Service>
 export function stream(input: SpeechRequest | SpeechRequestInput) {
   return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => SpeechClient.stream(request))))
 }

packages/ai/src/transcription-client.ts

@@ -1,34 +1,13 @@
-import { Context, Effect, Layer, Stream } from "effect"
-import type { AwaitOptions, Generation } from "./generation.js"
-import { RequestExecutor } from "./route/executor.js"
-import { MediaRoute } from "./route/media.js"
-import type { AIError } from "./schema/index.js"
+import { Context } from "effect"
+import { MediaClient } from "./media-client.js"
 import {
-  responseEvents,
+  TranscriptionFinishEvent,
   type TranscriptionEvent,
-  type TranscriptionModel,
-  type TranscriptionOptions,
   type TranscriptionRequestFor,
   type TranscriptionResponse,
 } from "./transcription.js"
 
-export interface Interface {
-  readonly generate: <Options extends TranscriptionOptions>(
-    request: TranscriptionRequestFor<Options>,
-    options?: AwaitOptions,
-  ) => Effect.Effect<TranscriptionResponse, AIError>
-  readonly stream: <Options extends TranscriptionOptions>(
-    request: TranscriptionRequestFor<Options>,
-    options?: AwaitOptions,
-  ) => Stream.Stream<TranscriptionEvent, AIError>
-  readonly start: <Options extends TranscriptionOptions>(
-    request: TranscriptionRequestFor<Options>,
-  ) => Effect.Effect<Generation<TranscriptionResponse>, AIError>
-  readonly resume: <Options extends TranscriptionOptions>(
-    model: TranscriptionModel<Options>,
-    token: unknown,
-  ) => Effect.Effect<Generation<TranscriptionResponse>, AIError>
-}
+export type Interface = MediaClient.Interface<TranscriptionRequestFor, TranscriptionEvent, TranscriptionResponse>
 
 export class TranscriptionClientService extends Context.Service<TranscriptionClientService, Interface>()(
   "@opencode/TranscriptionClient",
@@ -36,66 +15,10 @@ export class TranscriptionClientService extends Context.Service<TranscriptionCli
 export const Service = TranscriptionClientService
 export type Service = TranscriptionClientService
 
-export const generate = <Options extends TranscriptionOptions>(
-  request: TranscriptionRequestFor<Options>,
-  options?: AwaitOptions,
-): Effect.Effect<TranscriptionResponse, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.generate(request, options)
-  })
-
-export const stream = <Options extends TranscriptionOptions>(
-  request: TranscriptionRequestFor<Options>,
-  options?: AwaitOptions,
-): Stream.Stream<TranscriptionEvent, AIError, Service> =>
-  Stream.unwrap(
-    Effect.gen(function* () {
-      const client = yield* Service
-      return client.stream(request, options)
-    }),
-  )
-
-export const start = <Options extends TranscriptionOptions>(
-  request: TranscriptionRequestFor<Options>,
-): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.start(request)
-  })
-
-export const resume = <Options extends TranscriptionOptions>(
-  model: TranscriptionModel<Options>,
-  token: unknown,
-): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.resume(model, token)
-  })
-
-export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
-  Service,
-  Effect.gen(function* () {
-    const executor = yield* RequestExecutor.Service
-    const dispatch = MediaRoute.dispatch<TranscriptionEvent, TranscriptionResponse>({
-      modality: "transcription",
-      execute: executor.execute,
-      responseEvents,
-    })
-    return Service.of({
-      start: (request) => dispatch.start(request.model.route, request),
-      resume: (model, token) => dispatch.resume(model.route, model, token),
-      generate: (request, options) => dispatch.generate(request.model.route, request, options),
-      stream: (request, options) => dispatch.stream(request.model.route, request, options),
-    })
-  }),
-)
-
 export const TranscriptionClient = {
   Service,
-  layer,
-  generate,
-  stream,
-  start,
-  resume,
+  ...MediaClient.make(Service, {
+    modality: "transcription",
+    responseEvents: (response: TranscriptionResponse) => [TranscriptionFinishEvent.make({ ...response })],
+  }),
 } as const

packages/ai/src/transcription.ts

@@ -1,9 +1,8 @@
 import { Effect, Schema, Stream } from "effect"
 import { Generation, ProgressEvent, QueuedEvent, type AwaitOptions } from "./generation.js"
 import { Media } from "./media.js"
-import { MediaModel, composeAnyRoute, tryRequest } from "./media-model.js"
+import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
-import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata } from "./schema/index.js"
 import { TranscriptionClient, Service } from "./transcription-client.js"
 
@@ -11,90 +10,49 @@ import { TranscriptionClient, Service } from "./transcription-client.js"
 // Model
 // ---------------------------------------------------------------------------
 
-export type TranscriptionOptions = Record<string, unknown>
+export type TranscriptionOptions = MediaModel.Options
 
-export type TranscriptionRoute<Options extends TranscriptionOptions = TranscriptionOptions> = MediaRoute.AnyRoute<
-  TranscriptionRequestFor<Options>,
-  TranscriptionEvent,
-  TranscriptionResponse
->
+export type TranscriptionRoute = MediaRoute.AnyRoute<TranscriptionRequestFor, TranscriptionEvent, TranscriptionResponse>
 
 export class TranscriptionModel<Options extends TranscriptionOptions = TranscriptionOptions> extends MediaModel<
-  TranscriptionRoute<Options>,
+  TranscriptionRoute,
   Options
 > {
   declare protected readonly _TranscriptionModel: void
 
-  static make<Options extends TranscriptionOptions = TranscriptionOptions>(
-    input: MediaModel.Input<TranscriptionRoute<Options>>,
-  ) {
-    return new TranscriptionModel<Options>(input)
-  }
-
   /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
   static fromRoute<Options extends TranscriptionOptions>(
-    route: TranscriptionModel.InlineRouteInput<Options>,
+    route: MediaModel.InlineRouteInput<TranscriptionRequestFor<Options>, TranscriptionResponse>,
     input: MediaRoute.ModelInput,
   ): TranscriptionModel<Options>
   static fromRoute<Options extends TranscriptionOptions, Frame, State>(
-    route: TranscriptionModel.StreamRouteInput<Options, Frame, State>,
+    route: MediaModel.StreamRouteInput<TranscriptionRequestFor<Options>, TranscriptionEvent, Frame, State>,
     input: MediaRoute.ModelInput,
   ): TranscriptionModel<Options>
   static fromRoute<Options extends TranscriptionOptions, Token>(
-    route: TranscriptionModel.QueuedRouteInput<Options, Token>,
+    route: MediaModel.QueuedRouteInput<TranscriptionRequestFor<Options>, TranscriptionResponse, Token>,
     input: MediaRoute.ModelInput,
   ): TranscriptionModel<Options>
   static fromRoute<Options extends TranscriptionOptions, Frame, State, Token>(
-    route: TranscriptionModel.RouteInput<Options, Frame, State, Token>,
+    route: MediaModel.AnyRouteInput<
+      TranscriptionRequestFor<Options>,
+      TranscriptionEvent,
+      TranscriptionResponse,
+      Frame,
+      State,
+      Token
+    >,
     input: MediaRoute.ModelInput,
   ) {
     return new TranscriptionModel<Options>({
       id: input.id,
       provider: route.protocol.provider,
       http: input.http,
-      route: composeAnyRoute(route, input, collectResponse),
+      route: composeRoute(route, input, collectResponse) as TranscriptionRoute,
     })
   }
 }
 
-export namespace TranscriptionModel {
-  export type InlineRouteInput<Options extends TranscriptionOptions = TranscriptionOptions> = MediaModel.RouteInput<
-    TranscriptionRequestFor<Options>,
-    MediaProtocol.Inline<TranscriptionRequestFor<Options>, TranscriptionResponse>
-  >
-
-  export type StreamRouteInput<
-    Options extends TranscriptionOptions = TranscriptionOptions,
-    Frame = unknown,
-    State = unknown,
-  > = MediaModel.RouteInput<
-    MediaProtocol.Addressed<TranscriptionRequestFor<Options>>,
-    MediaProtocol.Streamed<TranscriptionRequestFor<Options>, TranscriptionEvent, Frame, State>
-  >
-
-  export type QueuedRouteInput<
-    Options extends TranscriptionOptions = TranscriptionOptions,
-    Token = unknown,
-  > = MediaModel.RouteInput<
-    TranscriptionRequestFor<Options>,
-    MediaProtocol.Queued<TranscriptionRequestFor<Options>, TranscriptionResponse, Token>
-  >
-
-  export type RouteInput<
-    Options extends TranscriptionOptions = TranscriptionOptions,
-    Frame = unknown,
-    State = unknown,
-    Token = unknown,
-  > = MediaModel.AnyRouteInput<
-    TranscriptionRequestFor<Options>,
-    TranscriptionEvent,
-    TranscriptionResponse,
-    Frame,
-    State,
-    Token
-  >
-}
-
 export const TranscriptionModelSchema = Schema.declare(
   (value): value is TranscriptionModel => value instanceof TranscriptionModel,
   { expected: "Transcription.Model" },
@@ -212,10 +170,6 @@ export const TranscriptionEvent = Object.assign(transcriptionEventTagged, {
 })
 export type TranscriptionEvent = Schema.Schema.Type<typeof transcriptionEventTagged>
 
-export const responseEvents = (response: TranscriptionResponse): ReadonlyArray<TranscriptionEvent> => [
-  TranscriptionFinishEvent.make({ ...response }),
-]
-
 const collectResponse = (events: ReadonlyArray<TranscriptionEvent>): Effect.Effect<TranscriptionResponse> => {
   const finish = events.find(TranscriptionEvent.is.finish)
   // Every transcription protocol's `finish` emits the terminal event or fails, so a completed stream always has one.
@@ -243,11 +197,7 @@ export function request(input: TranscriptionRequest | TranscriptionRequestInput)
 const requestEffect = (input: TranscriptionRequest | TranscriptionRequestInput) => tryRequest(() => request(input))
 
 export function generate<const Model extends TranscriptionModel>(
-  input: TranscriptionRequestInput<Model>,
-  options?: AwaitOptions,
-): Effect.Effect<TranscriptionResponse, AIError, Service>
-export function generate(
-  input: TranscriptionRequest,
+  input: TranscriptionRequest | TranscriptionRequestInput<Model>,
   options?: AwaitOptions,
 ): Effect.Effect<TranscriptionResponse, AIError, Service>
 export function generate(input: TranscriptionRequest | TranscriptionRequestInput, options?: AwaitOptions) {
@@ -255,11 +205,7 @@ export function generate(input: TranscriptionRequest | TranscriptionRequestInput
 }
 
 export function stream<const Model extends TranscriptionModel>(
-  input: TranscriptionRequestInput<Model>,
-  options?: AwaitOptions,
-): Stream.Stream<TranscriptionEvent, AIError, Service>
-export function stream(
-  input: TranscriptionRequest,
+  input: TranscriptionRequest | TranscriptionRequestInput<Model>,
   options?: AwaitOptions,
 ): Stream.Stream<TranscriptionEvent, AIError, Service>
 export function stream(input: TranscriptionRequest | TranscriptionRequestInput, options?: AwaitOptions) {
@@ -268,15 +214,14 @@ export function stream(input: TranscriptionRequest | TranscriptionRequestInput,
 
 /** Inline and streaming routes fail with `UnsupportedOperation`. */
 export function start<const Model extends TranscriptionModel>(
-  input: TranscriptionRequestInput<Model>,
+  input: TranscriptionRequest | TranscriptionRequestInput<Model>,
 ): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service>
-export function start(input: TranscriptionRequest): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service>
 export function start(input: TranscriptionRequest | TranscriptionRequestInput) {
   return requestEffect(input).pipe(Effect.flatMap((request) => TranscriptionClient.start(request)))
 }
 
-export const resume = <Options extends TranscriptionOptions>(
-  model: TranscriptionModel<Options>,
+export const resume = (
+  model: TranscriptionModel,
   token: unknown,
 ): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service> => TranscriptionClient.resume(model, token)
 

packages/ai/src/video-client.ts

@@ -1,98 +1,30 @@
-import { Context, Effect, Layer, Stream } from "effect"
-import { resultEvents, type AwaitOptions, type Generation } from "./generation.js"
-import { RequestExecutor } from "./route/executor.js"
-import type { AIError } from "./schema/index.js"
+import { Context } from "effect"
+import { MediaClient } from "./media-client.js"
 import {
-  responseEvents,
+  VideoOutputEvent,
+  VideoFinishEvent,
   type VideoEvent,
-  type VideoModel,
-  type VideoOptions,
   type VideoRequestFor,
   type VideoResponse,
 } from "./video.js"
 
-export interface Interface {
-  readonly start: <Options extends VideoOptions>(
-    request: VideoRequestFor<Options>,
-  ) => Effect.Effect<Generation<VideoResponse>, AIError>
-  readonly resume: <Options extends VideoOptions>(
-    model: VideoModel<Options>,
-    token: unknown,
-  ) => Effect.Effect<Generation<VideoResponse>, AIError>
-  readonly generate: <Options extends VideoOptions>(
-    request: VideoRequestFor<Options>,
-    options?: AwaitOptions,
-  ) => Effect.Effect<VideoResponse, AIError>
-  readonly stream: <Options extends VideoOptions>(
-    request: VideoRequestFor<Options>,
-    options?: AwaitOptions,
-  ) => Stream.Stream<VideoEvent, AIError>
-}
+export type Interface = MediaClient.Interface<VideoRequestFor, VideoEvent, VideoResponse>
 
 export class VideoClientService extends Context.Service<VideoClientService, Interface>()("@opencode/VideoClient") {}
 export const Service = VideoClientService
 export type Service = VideoClientService
 
-export const start = <Options extends VideoOptions>(
-  request: VideoRequestFor<Options>,
-): Effect.Effect<Generation<VideoResponse>, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.start(request)
-  })
-
-export const resume = <Options extends VideoOptions>(
-  model: VideoModel<Options>,
-  token: unknown,
-): Effect.Effect<Generation<VideoResponse>, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.resume(model, token)
-  })
-
-export const generate = <Options extends VideoOptions>(
-  request: VideoRequestFor<Options>,
-  options?: AwaitOptions,
-): Effect.Effect<VideoResponse, AIError, Service> =>
-  Effect.gen(function* () {
-    const client = yield* Service
-    return yield* client.generate(request, options)
-  })
-
-export const stream = <Options extends VideoOptions>(
-  request: VideoRequestFor<Options>,
-  options?: AwaitOptions,
-): Stream.Stream<VideoEvent, AIError, Service> =>
-  Stream.unwrap(
-    Effect.gen(function* () {
-      const client = yield* Service
-      return client.stream(request, options)
-    }),
-  )
-
-export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
-  Service,
-  Effect.gen(function* () {
-    const executor = yield* RequestExecutor.Service
-    const start = <Options extends VideoOptions>(request: VideoRequestFor<Options>) =>
-      request.model.route.start(request, executor.execute)
-    return Service.of({
-      start,
-      resume: (model, token) => model.route.resume(model, token, executor.execute),
-      generate: (request, options) => start(request).pipe(Effect.flatMap((generation) => generation.await(options))),
-      stream: (request, options) =>
-        Stream.unwrap(
-          start(request).pipe(Effect.map((generation) => resultEvents(generation, responseEvents, options))),
-        ),
-    })
-  }),
-)
-
 export const VideoClient = {
   Service,
-  layer,
-  start,
-  resume,
-  generate,
-  stream,
+  ...MediaClient.make(Service, {
+    modality: "video",
+    responseEvents: (response: VideoResponse) => [
+      ...response.videos.map((video, index) => VideoOutputEvent.make({ index, video })),
+      VideoFinishEvent.make({
+        usage: response.usage,
+        notices: response.notices,
+        providerMetadata: response.providerMetadata,
+      }),
+    ],
+  }),
 } as const

packages/ai/src/video.ts

@@ -3,7 +3,6 @@ import { Generation, ProgressEvent, QueuedEvent, type AwaitOptions } from "./gen
 import { Media } from "./media.js"
 import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
-import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata, type OpenString } from "./schema/index.js"
 import { VideoClient, Service } from "./video-client.js"
 
@@ -11,41 +10,39 @@ import { VideoClient, Service } from "./video-client.js"
 // Model
 // ---------------------------------------------------------------------------
 
-export type VideoOptions = Record<string, unknown>
+export type VideoOptions = MediaModel.Options
 
-export type VideoRoute<Options extends VideoOptions = VideoOptions> = MediaRoute.QueuedRoute<
-  VideoRequestFor<Options>,
-  VideoResponse
->
+export type VideoRoute = MediaRoute.AnyRoute<VideoRequestFor, VideoEvent, VideoResponse>
 
-export class VideoModel<Options extends VideoOptions = VideoOptions> extends MediaModel<VideoRoute<Options>, Options> {
+export class VideoModel<Options extends VideoOptions = VideoOptions> extends MediaModel<VideoRoute, Options> {
   declare protected readonly _VideoModel: void
 
-  static make<Options extends VideoOptions = VideoOptions>(input: MediaModel.Input<VideoRoute<Options>>) {
-    return new VideoModel<Options>(input)
-  }
-
-  /** Compose a queued video protocol with its canonical start path into a model for one deployment. */
-  static fromRoute<Options extends VideoOptions = VideoOptions, Token = unknown>(
-    route: VideoModel.RouteInput<Options, Token>,
+  /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
+  static fromRoute<Options extends VideoOptions>(
+    route: MediaModel.InlineRouteInput<VideoRequestFor<Options>, VideoResponse>,
+    input: MediaRoute.ModelInput,
+  ): VideoModel<Options>
+  static fromRoute<Options extends VideoOptions, Frame, State>(
+    route: MediaModel.StreamRouteInput<VideoRequestFor<Options>, VideoEvent, Frame, State>,
+    input: MediaRoute.ModelInput,
+  ): VideoModel<Options>
+  static fromRoute<Options extends VideoOptions, Token>(
+    route: MediaModel.QueuedRouteInput<VideoRequestFor<Options>, VideoResponse, Token>,
+    input: MediaRoute.ModelInput,
+  ): VideoModel<Options>
+  static fromRoute<Options extends VideoOptions, Frame, State, Token>(
+    route: MediaModel.AnyRouteInput<VideoRequestFor<Options>, VideoEvent, VideoResponse, Frame, State, Token>,
     input: MediaRoute.ModelInput,
   ) {
     return new VideoModel<Options>({
       id: input.id,
       provider: route.protocol.provider,
       http: input.http,
-      route: composeRoute(MediaRoute.queued, route, input),
+      route: composeRoute(route, input, collectResponse) as VideoRoute,
     })
   }
 }
 
-export namespace VideoModel {
-  export type RouteInput<Options extends VideoOptions = VideoOptions, Token = unknown> = MediaModel.RouteInput<
-    VideoRequestFor<Options>,
-    MediaProtocol.Queued<VideoRequestFor<Options>, VideoResponse, Token>
-  >
-}
-
 export const VideoModelSchema = Schema.declare((value): value is VideoModel => value instanceof VideoModel, {
   expected: "Video.Model",
 })
@@ -149,15 +146,19 @@ export const VideoEvent = Object.assign(videoEventTagged, {
 })
 export type VideoEvent = Schema.Schema.Type<typeof videoEventTagged>
 
-/** A completed response expanded into the streaming event shape. */
-export const responseEvents = (response: VideoResponse): ReadonlyArray<VideoEvent> => [
-  ...response.videos.map((video, index) => VideoOutputEvent.make({ index, video })),
-  VideoFinishEvent.make({
-    usage: response.usage,
-    notices: response.notices,
-    providerMetadata: response.providerMetadata,
-  }),
-]
+const collectResponse = (events: ReadonlyArray<VideoEvent>): Effect.Effect<VideoResponse> => {
+  const finish = events.find(VideoEvent.is.finish)
+  // A streaming video protocol's `finish` emits the terminal event or fails, so a completed stream always has one.
+  if (finish === undefined) return Effect.die(new Error("The video stream completed without a finish event"))
+  return Effect.succeed(
+    new VideoResponse({
+      videos: events.filter(VideoEvent.is.video).map((event) => event.video),
+      usage: finish.usage,
+      notices: finish.notices,
+      providerMetadata: finish.providerMetadata,
+    }),
+  )
+}
 
 // ---------------------------------------------------------------------------
 // Request-shaped call API
@@ -178,33 +179,28 @@ export function request(input: VideoRequest | VideoRequestInput) {
 const requestEffect = (input: VideoRequest | VideoRequestInput) => tryRequest(() => request(input))
 
 export function start<const Model extends VideoModel>(
-  input: VideoRequestInput<Model>,
+  input: VideoRequest | VideoRequestInput<Model>,
 ): Effect.Effect<Generation<VideoResponse>, AIError, Service>
-export function start(input: VideoRequest): Effect.Effect<Generation<VideoResponse>, AIError, Service>
 export function start(input: VideoRequest | VideoRequestInput) {
   return requestEffect(input).pipe(Effect.flatMap((request) => VideoClient.start(request)))
 }
 
 export function generate<const Model extends VideoModel>(
-  input: VideoRequestInput<Model>,
+  input: VideoRequest | VideoRequestInput<Model>,
   options?: AwaitOptions,
 ): Effect.Effect<VideoResponse, AIError, Service>
-export function generate(input: VideoRequest, options?: AwaitOptions): Effect.Effect<VideoResponse, AIError, Service>
 export function generate(input: VideoRequest | VideoRequestInput, options?: AwaitOptions) {
   return requestEffect(input).pipe(Effect.flatMap((request) => VideoClient.generate(request, options)))
 }
 
 /** Rebuild a generation handle from a persisted `Generation.token`, refreshing its status once. */
-export const resume = <Options extends VideoOptions>(
-  model: VideoModel<Options>,
-  token: unknown,
-): Effect.Effect<Generation<VideoResponse>, AIError, Service> => VideoClient.resume(model, token)
+export const resume = (model: VideoModel, token: unknown): Effect.Effect<Generation<VideoResponse>, AIError, Service> =>
+  VideoClient.resume(model, token)
 
 export function stream<const Model extends VideoModel>(
-  input: VideoRequestInput<Model>,
+  input: VideoRequest | VideoRequestInput<Model>,
   options?: AwaitOptions,
 ): Stream.Stream<VideoEvent, AIError, Service>
-export function stream(input: VideoRequest, options?: AwaitOptions): Stream.Stream<VideoEvent, AIError, Service>
 export function stream(input: VideoRequest | VideoRequestInput, options?: AwaitOptions) {
   return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => VideoClient.stream(request, options))))
 }

packages/ai/test/exports.test.ts

@@ -54,6 +54,19 @@ import { TestLLM } from "@opencode/ai/testing"
 import { Evaluation, EvaluationClient } from "@opencode/ai/experimental"
 
 describe("public exports", () => {
+  test("modality, provider, and protocol entrypoints load first in a fresh process", async () => {
+    const results = await Promise.all(
+      ["image", "video", "speech", "transcription", "providers", "protocols"].map(async (entry) => {
+        const child = Bun.spawn(
+          [process.execPath, "-e", `await import(${JSON.stringify(`${import.meta.dir}/../src/${entry}.ts`)})`],
+          { stderr: "pipe" },
+        )
+        return { entry, exitCode: await child.exited, stderr: await new Response(child.stderr).text() }
+      }),
+    )
+    expect(results.filter((result) => result.exitCode !== 0)).toEqual([])
+  })
+
   test("root exposes app-facing runtime APIs", () => {
     expect(LLM.request).toBeFunction()
     expect(LLMClient.Service).toBeFunction()

packages/ai/test/fixtures/recordings/openai-responses-websocket/continues-a-tool-call-over-one-socket.json

@@ -30,7 +30,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":50}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":50}"
         },
         {
           "direction": "server",
@@ -525,7 +525,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"function_call_output\",\"call_id\":\"call_hejtTYDa1IfLyNIzb3fq9gJs\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":50,\"previous_response_id\":\"resp_0d9a44b6df400533016aa8c8e36de887d1be260913d131b2ca\"}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"function_call_output\",\"call_id\":\"call_hejtTYDa1IfLyNIzb3fq9gJs\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":50,\"previous_response_id\":\"resp_0d9a44b6df400533016aa8c8e36de887d1be260913d131b2ca\"}"
         },
         {
           "direction": "server",

packages/ai/test/fixtures/recordings/openai-responses-websocket/reconstructs-full-context-after-reconnect.json

@@ -30,7 +30,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
         },
         {
           "direction": "server",
@@ -109,7 +109,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_0a6277dd90b94da1016aa8c946e33487d1b725d8e9dc874d82\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMlHtG6yltzgW_UjUcYxvl2hoMkk7cSEH5SJMe9CR5gKIaCwCh4peUo8XZrd-EU-tPCXthv7JzHxYXGVG1fIgTJ7BjBoOh-jgd_oGlyCHj2jVPj7nVoB763tZHdyw_ovL3V7GpJ6VeLGIsRGqNTnBz47ZuKikTKrbTDupn6fT2wOM_69zwdg4-UVnoF2J9E_jIS0E5XRtRwOidqANl61HCwo7LV-Ut1aqCbXb-59vkrVGWPxD_8n4smf7Qjywc0FCH9zwuEDX4cPdqj3MmjvYPrn0jand9LKkAy9rblaKFJSQfVuritbHrdQrnF7hLxu7QCpehOzNXOkpNEqTmXnAZjfMc53hq-ahH6_KoyYlZpompwyGPngFeI2fKRqP8rlpDilD1BHBsh-bl7kXzI8HQ_jameXwPZ1La6gjtFkThXp53BD6BOx11SB9Nypqolu2at5rR32UYcGrYeGtTu-HmYGp0oHVFkHumTNuHKmGXV14dI9swgryfygLhX8EAJrWrjm3e8rvAkHKpAZ0IkmlCcp15UCFDKNeS560fQVRaKXWnQ7m0Ih3C1xG0ifJ89j27c8GHo1kAhEJk-lSB1-FZr9Ls_w7N772kmZ2a7LLswu3kNW78kPas_CtcOnBOHwE1DhcVh5YpxwNftOHZnK1v8NPNF8EWqio4ArZy1thMCzH5zXBNcFzgd8tePMFukBblSP8QGQoVYRqTne2sFoOZXjslXnDvEe-Ycj8X38zWgRiwAk7guOloFC7Se36KCDP357773Vah86gWCt55mSEyhVW_GF1oTuHvJ18GZsXcyN21scF1PSr8YaCM_jR7ZkU1GYXbQK2Y4oTAV9XDptQA5YzEREnn7muC_6v5ZTAglZF1lhn9Q0NwmylZEAXJdSGHaqXt1Hv-vQlprA_9m22vrreBOTLPnVK946J8absKrwfe-jK_1n_9YQR43uwH8XwFBFND0c4lICCQGbxwM8pX4ACWR0c19aORCYm-M5FrJsxmG29_aDVNhcvkoQ3mlP7ITQeqzkrjfytSwLb2BYpXYZKjEHNfV9j3JoxJobUkK5hrxXBhTvZzbVBnE0LSXQNwR-JAcOliP_jXBEeQ-28B-aGW8TI1vEP2i260QKgzOzPC-pOoFp0-vCvxojNO0kE16ECVTLfDNLNGSMZs9vekdLJP2akBp6PsUXsQUTbWO_wr1E2oNU7ctfMRxoh-yP0ZW2_xz_NjE72O5LF_6zuDVV7Q==\"},{\"type\":\"message\",\"id\":\"msg_0a6277dd90b94da1016aa8c947253887d184c150fcbcbcd8da\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Alpha.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Beta.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_0a6277dd90b94da1016aa8c946e33487d1b725d8e9dc874d82\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMlHtG6yltzgW_UjUcYxvl2hoMkk7cSEH5SJMe9CR5gKIaCwCh4peUo8XZrd-EU-tPCXthv7JzHxYXGVG1fIgTJ7BjBoOh-jgd_oGlyCHj2jVPj7nVoB763tZHdyw_ovL3V7GpJ6VeLGIsRGqNTnBz47ZuKikTKrbTDupn6fT2wOM_69zwdg4-UVnoF2J9E_jIS0E5XRtRwOidqANl61HCwo7LV-Ut1aqCbXb-59vkrVGWPxD_8n4smf7Qjywc0FCH9zwuEDX4cPdqj3MmjvYPrn0jand9LKkAy9rblaKFJSQfVuritbHrdQrnF7hLxu7QCpehOzNXOkpNEqTmXnAZjfMc53hq-ahH6_KoyYlZpompwyGPngFeI2fKRqP8rlpDilD1BHBsh-bl7kXzI8HQ_jameXwPZ1La6gjtFkThXp53BD6BOx11SB9Nypqolu2at5rR32UYcGrYeGtTu-HmYGp0oHVFkHumTNuHKmGXV14dI9swgryfygLhX8EAJrWrjm3e8rvAkHKpAZ0IkmlCcp15UCFDKNeS560fQVRaKXWnQ7m0Ih3C1xG0ifJ89j27c8GHo1kAhEJk-lSB1-FZr9Ls_w7N772kmZ2a7LLswu3kNW78kPas_CtcOnBOHwE1DhcVh5YpxwNftOHZnK1v8NPNF8EWqio4ArZy1thMCzH5zXBNcFzgd8tePMFukBblSP8QGQoVYRqTne2sFoOZXjslXnDvEe-Ycj8X38zWgRiwAk7guOloFC7Se36KCDP357773Vah86gWCt55mSEyhVW_GF1oTuHvJ18GZsXcyN21scF1PSr8YaCM_jR7ZkU1GYXbQK2Y4oTAV9XDptQA5YzEREnn7muC_6v5ZTAglZF1lhn9Q0NwmylZEAXJdSGHaqXt1Hv-vQlprA_9m22vrreBOTLPnVK946J8absKrwfe-jK_1n_9YQR43uwH8XwFBFND0c4lICCQGbxwM8pX4ACWR0c19aORCYm-M5FrJsxmG29_aDVNhcvkoQ3mlP7ITQeqzkrjfytSwLb2BYpXYZKjEHNfV9j3JoxJobUkK5hrxXBhTvZzbVBnE0LSXQNwR-JAcOliP_jXBEeQ-28B-aGW8TI1vEP2i260QKgzOzPC-pOoFp0-vCvxojNO0kE16ECVTLfDNLNGSMZs9vekdLJP2akBp6PsUXsQUTbWO_wr1E2oNU7ctfMRxoh-yP0ZW2_xz_NjE72O5LF_6zuDVV7Q==\"},{\"type\":\"message\",\"id\":\"msg_0a6277dd90b94da1016aa8c947253887d184c150fcbcbcd8da\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Alpha.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Beta.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
         },
         {
           "direction": "server",

packages/ai/test/fixtures/recordings/openai-responses-websocket/recovers-from-explicit-continuation-rejection.json

@@ -30,7 +30,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
         },
         {
           "direction": "server",
@@ -109,7 +109,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30,\"previous_response_id\":\"resp_01cc0cda24c36acf016aa8ca3c1d3c87d1853283f43675e411\"}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30,\"previous_response_id\":\"resp_01cc0cda24c36acf016aa8ca3c1d3c87d1853283f43675e411\"}"
         },
         {
           "direction": "server",
@@ -119,7 +119,7 @@
         {
           "direction": "client",
           "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_01cc0cda24c36acf016aa8ca3ced8c87d1a14c5c6a2ced8544\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMo9M9B15LsV1CLsXpNJpI08GiwCAK97hTheQ2s1lAkKgARMs1HIIXVeAr-tbUq88yN51fiQE8HvGwdF9ZcNI6bZle8D2PS7m8O7UE7C1Z_HX_fz2f0pRHyRfWpVAT2gYQWIDeZu6UdgxbKPBW0lXWzlk_relHG5x6nXkYzZoEeVasqavWoyMMSX7cexe-IYJh6e_3DgRpOchueS8Z-70P0w5R83Ea7UXZQNhMA0yDEYu_td2PmE2Pd2PUTOB3mxF2pb1z7-2t6S0UryhHx0az7Gh2eT60GGUqz9CIZzNE_FX--tszeuO0eI92Cen5tirOUHBTyyDqE0eG26DRl_p_U-xDZwaQONbtYbvkvrj-G7FA2oZXxjJPHuQZsNgBslXS-H0KT1lx3Y8XJ9QMVjFLFaucFG64wCmXPfCH8dYtX_YqfYQR4lwNfiSbyJEX2oDvTVVD_aCJ9NRo7c0aCTtmKBvr6fvvAy3MAFxAp_Sm2nMx4P5GYO4qAmJDByywKw-VK1vHlv3NRmVsAgbArIFgm-axoCs2PLpvZjDqeQGPavaq8zKWTyZYqBsEzKZUtGOZfYjD4mud0Z08I4i2H4K-L00ccVauode3548ZipOIuslbhJxonQXsF6TFdW2Hj8E5JjoEr5IbmwHyI0PBcDWW5AmkjHLwr9v08mFppRoD-2wzPAd5igROAuUbvJhiQd2A-uOaohwMjdpFxrjyUqgGTlI5g7tmI1ceeQWms0bKm8Pd0wIqVM3Nq6YvV7XfEyeogfRMVUQezr_lES42ZMVAoKBSFzMysDwCFkhVNVclcTUpcUUbVp21FChG7Ag-xuq8Cl6OGLA8nWX1C0aCf2HNa-n3dkYr1DtUziurh1MD-UIs5jdGiq3ptrc0VaVZwNdD4jVfAoHB_Ws7GiISXuclfpqsG3DTJEfzlbukI1vxXrt3FArsHiQvQjW5UM7gGel32M6p8AlXRxnez9PgIuU1WrtBUJetk7m39AZwp_aqbqC-AJ-MF70xP1VJZwFN-GeNL3VZsRHePFG4h7Pj---CCZRGlmzuE1-b-sIE7Bn_gbue_qHFMZJhAY55MO25vfZbSoLWHZCGmLMjJVHOYCPoy6l7zyxNmoIcC58QILNWal31KLCDmCsASmZC-xQRjyFwt-kvLbvk38Dc02IKcP3ujhf6WRRr1A0hh1K-gXmv_XI_MUFDcOVIjjhB-rXgjWSCoKfaKI9GCIsb9mnNaBq65BWg==\"},{\"type\":\"message\",\"id\":\"msg_01cc0cda24c36acf016aa8ca3d4a0087d1950121aed4802434\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Ready.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_01cc0cda24c36acf016aa8ca3ced8c87d1a14c5c6a2ced8544\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMo9M9B15LsV1CLsXpNJpI08GiwCAK97hTheQ2s1lAkKgARMs1HIIXVeAr-tbUq88yN51fiQE8HvGwdF9ZcNI6bZle8D2PS7m8O7UE7C1Z_HX_fz2f0pRHyRfWpVAT2gYQWIDeZu6UdgxbKPBW0lXWzlk_relHG5x6nXkYzZoEeVasqavWoyMMSX7cexe-IYJh6e_3DgRpOchueS8Z-70P0w5R83Ea7UXZQNhMA0yDEYu_td2PmE2Pd2PUTOB3mxF2pb1z7-2t6S0UryhHx0az7Gh2eT60GGUqz9CIZzNE_FX--tszeuO0eI92Cen5tirOUHBTyyDqE0eG26DRl_p_U-xDZwaQONbtYbvkvrj-G7FA2oZXxjJPHuQZsNgBslXS-H0KT1lx3Y8XJ9QMVjFLFaucFG64wCmXPfCH8dYtX_YqfYQR4lwNfiSbyJEX2oDvTVVD_aCJ9NRo7c0aCTtmKBvr6fvvAy3MAFxAp_Sm2nMx4P5GYO4qAmJDByywKw-VK1vHlv3NRmVsAgbArIFgm-axoCs2PLpvZjDqeQGPavaq8zKWTyZYqBsEzKZUtGOZfYjD4mud0Z08I4i2H4K-L00ccVauode3548ZipOIuslbhJxonQXsF6TFdW2Hj8E5JjoEr5IbmwHyI0PBcDWW5AmkjHLwr9v08mFppRoD-2wzPAd5igROAuUbvJhiQd2A-uOaohwMjdpFxrjyUqgGTlI5g7tmI1ceeQWms0bKm8Pd0wIqVM3Nq6YvV7XfEyeogfRMVUQezr_lES42ZMVAoKBSFzMysDwCFkhVNVclcTUpcUUbVp21FChG7Ag-xuq8Cl6OGLA8nWX1C0aCf2HNa-n3dkYr1DtUziurh1MD-UIs5jdGiq3ptrc0VaVZwNdD4jVfAoHB_Ws7GiISXuclfpqsG3DTJEfzlbukI1vxXrt3FArsHiQvQjW5UM7gGel32M6p8AlXRxnez9PgIuU1WrtBUJetk7m39AZwp_aqbqC-AJ-MF70xP1VJZwFN-GeNL3VZsRHePFG4h7Pj---CCZRGlmzuE1-b-sIE7Bn_gbue_qHFMZJhAY55MO25vfZbSoLWHZCGmLMjJVHOYCPoy6l7zyxNmoIcC58QILNWal31KLCDmCsASmZC-xQRjyFwt-kvLbvk38Dc02IKcP3ujhf6WRRr1A0hh1K-gXmv_XI_MUFDcOVIjjhB-rXgjWSCoKfaKI9GCIsb9mnNaBq65BWg==\"},{\"type\":\"message\",\"id\":\"msg_01cc0cda24c36acf016aa8ca3d4a0087d1950121aed4802434\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Ready.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
         },
         {
           "direction": "server",

packages/ai/test/fixtures/recordings/openai-responses/openai-responses-gpt-5-5-reasoning-continuation.json

@@ -26,7 +26,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":120,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"max_output_tokens\":120,\"stream\":true}"
       },
       "response": {
         "status": 200,
@@ -44,7 +44,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]},{\"type\":\"reasoning\",\"id\":\"rs_052e7ec551f55289016aa8c8d63eac87d19d6b921611f123e7\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMjWZ2Eei8_Gf-5FeEFAYp-gSzFL4D4lQBKL_fyyTYXv5iJ-2jql1mOq0wZpqHL8O9MWxebQGW56Ahd-p21qrDD52CyUBqKKlF87eC1d-cTgjXQlFMsPxvwyQeuU6A2l8tanTtJ48sKtzZtHrDuBXZ35u-lONnovjFGMX3Q83xoqG_um_w5rT420TA_SyU4fGt7oiQvOPS1q4PNo97O824oRnI7n_BC1jPYCaJhl2I1rPJg4afuOpjG-u7JcXRD4JPwZdqMa5o2d0uDKHuUYwP25qiPKKDqTTqFka5cDJjZNPF3ZkVHR-cagjZGvMnizXXxgUpPJ9j83gqY4QJLKCkzcaBj9H7mAL-v9yl4I5kn_9_DhpMILs2SZkC8AvIYNgmel3sDV_BG4XZ2JXciZz86ukQ6DwXgQqS4HOB91g-sGHOWMU1ohsZlEvvJBjGkJ_rAdXVMqAbvi2zvE3_NI4sTAGUrIugGJePrQYTe8gqL8f9NsYac6pzHNQL1e_jQNUvp49bu7EsPzCP3KPYVvZCFohDdwe7sMd6wrztrCJwM4CLdAQK61A7sYzU0HyglLtPidmS5QkSmV6U_xgih7JbKnY0oAeCyYw4ADYqdNTi0axmBErh-lbh-XKNG_TnoMa-2IS3X041N8OsDfSdQp3QsAm53fF8seQuLFa27Iaq2etMj3yGeqWVjA-Mae3K34mt2YPGjQ-HbIOMVmYXBLzNr-s2fT35Sp6SDEsFyvzXb0Vij58s1wW5zkuKgaJiroGgkY86NImuaa3_-wpMK3_9O_wwAbRwV4uBCVzT_rY6rDQHR9-VkM0MbGK8drbdtjXwy3KtAzkux4N4g2nadYU0IIIEUNj_JChUFSHC7VRg7L7LpZMgAFGwHmaUyzQt31LyiVix9WFtcKfBgzehoRV6vstln-oBRd-vFjUW-7WLm7R_lFNHQZ0CKUvKCSpQxdIevczpYT0_lQiDU7Rfp1UBBnicndpq4YQwgRppdZX-QHG5IZxxHNWYdIBtn3eO3ooDXmI-rYryyVcFG6VY5xqssf8GgXqgNy84X_SgYfhGmNiPPQTl5wIBa49f1sxAI-7ri1xLr6FJhQMasOoxm_VuZYNkq6NrAXprtKa70cBRpm1wWBNcPdMul4GNMDQatQZRDENcNLe45iMX-HB1YYSvyc-y5rfSJkP4EgKXC-OqcrzxAlRfB3Bm4jOQL_PSsNBbh26CWAdAYSftM88fbnuqZX2w==\"},{\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hello!\"}],\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Now reply exactly with: Done.\"}]}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":40,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]},{\"type\":\"reasoning\",\"id\":\"rs_052e7ec551f55289016aa8c8d63eac87d19d6b921611f123e7\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMjWZ2Eei8_Gf-5FeEFAYp-gSzFL4D4lQBKL_fyyTYXv5iJ-2jql1mOq0wZpqHL8O9MWxebQGW56Ahd-p21qrDD52CyUBqKKlF87eC1d-cTgjXQlFMsPxvwyQeuU6A2l8tanTtJ48sKtzZtHrDuBXZ35u-lONnovjFGMX3Q83xoqG_um_w5rT420TA_SyU4fGt7oiQvOPS1q4PNo97O824oRnI7n_BC1jPYCaJhl2I1rPJg4afuOpjG-u7JcXRD4JPwZdqMa5o2d0uDKHuUYwP25qiPKKDqTTqFka5cDJjZNPF3ZkVHR-cagjZGvMnizXXxgUpPJ9j83gqY4QJLKCkzcaBj9H7mAL-v9yl4I5kn_9_DhpMILs2SZkC8AvIYNgmel3sDV_BG4XZ2JXciZz86ukQ6DwXgQqS4HOB91g-sGHOWMU1ohsZlEvvJBjGkJ_rAdXVMqAbvi2zvE3_NI4sTAGUrIugGJePrQYTe8gqL8f9NsYac6pzHNQL1e_jQNUvp49bu7EsPzCP3KPYVvZCFohDdwe7sMd6wrztrCJwM4CLdAQK61A7sYzU0HyglLtPidmS5QkSmV6U_xgih7JbKnY0oAeCyYw4ADYqdNTi0axmBErh-lbh-XKNG_TnoMa-2IS3X041N8OsDfSdQp3QsAm53fF8seQuLFa27Iaq2etMj3yGeqWVjA-Mae3K34mt2YPGjQ-HbIOMVmYXBLzNr-s2fT35Sp6SDEsFyvzXb0Vij58s1wW5zkuKgaJiroGgkY86NImuaa3_-wpMK3_9O_wwAbRwV4uBCVzT_rY6rDQHR9-VkM0MbGK8drbdtjXwy3KtAzkux4N4g2nadYU0IIIEUNj_JChUFSHC7VRg7L7LpZMgAFGwHmaUyzQt31LyiVix9WFtcKfBgzehoRV6vstln-oBRd-vFjUW-7WLm7R_lFNHQZ0CKUvKCSpQxdIevczpYT0_lQiDU7Rfp1UBBnicndpq4YQwgRppdZX-QHG5IZxxHNWYdIBtn3eO3ooDXmI-rYryyVcFG6VY5xqssf8GgXqgNy84X_SgYfhGmNiPPQTl5wIBa49f1sxAI-7ri1xLr6FJhQMasOoxm_VuZYNkq6NrAXprtKa70cBRpm1wWBNcPdMul4GNMDQatQZRDENcNLe45iMX-HB1YYSvyc-y5rfSJkP4EgKXC-OqcrzxAlRfB3Bm4jOQL_PSsNBbh26CWAdAYSftM88fbnuqZX2w==\"},{\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hello!\"}],\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Now reply exactly with: Done.\"}]}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"max_output_tokens\":40,\"stream\":true}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/openai-responses/openai-responses-gpt-5-5-reasoning.json

@@ -24,7 +24,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":120,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"max_output_tokens\":120,\"stream\":true}"
       },
       "response": {
         "status": 200,

packages/ai/test/fixtures/recordings/openai-responses/openai-responses-gpt-5-5-tool-loop.json

@@ -25,7 +25,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":80,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":80,\"stream\":true}"
       },
       "response": {
         "status": 200,
@@ -43,7 +43,7 @@
         "headers": {
           "content-type": "application/json"
         },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]},{\"type\":\"function_call\",\"id\":\"fc_09525c04931d1487016aa8c8d8e12887d193bd327a0f313bd7\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},{\"type\":\"function_call_output\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":80,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]},{\"type\":\"function_call\",\"id\":\"fc_09525c04931d1487016aa8c8d8e12887d193bd327a0f313bd7\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},{\"type\":\"function_call_output\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":80,\"stream\":true}"
       },
       "response": {
         "status": 200,

packages/ai/test/image.types.ts

@@ -7,7 +7,6 @@ import {
   type ImageModelOptions,
   type ImageOptions,
   type ImageRequestFor,
-  type ImageRoute,
 } from "../src/index.js"
 import type { Service } from "../src/image-client.js"
 import { Anthropic, BlackForestLabs, Google, OpenAI, Stability, XAI, ZAI } from "../src/providers.js"
@@ -21,8 +20,7 @@ type GoogleLikeOptions = {
   readonly thinkingLevel?: "LOW" | "HIGH"
 } & Record<string, unknown>
 
-declare const route: ImageRoute<GoogleLikeOptions>
-const google = ImageModel.make<GoogleLikeOptions>({ id: "gemini-image", provider: "google", route })
+declare const google: ImageModel<GoogleLikeOptions>
 // @ts-expect-error Extracted model options retain known provider fields.
 const invalidGoogleOptions: ImageModelOptions<typeof google> = { imageSize: "8K" }
 void invalidGoogleOptions
@@ -152,6 +150,8 @@ Image.generate({ model: zai, prompt: "A lighthouse", providerOptions: { quality:
 Image.generate({ model: zai, prompt: "A lighthouse", providerOptions: { userID: 1 } })
 
 declare const generic: ImageModel<ImageOptions>
+const widenImage = <Options extends ImageOptions>(model: ImageModel<Options>): ImageModel => model
+void widenImage
 Image.generate({ model: generic, prompt: "A lighthouse", providerOptions: { arbitrary: true } })
 const explicitAsset: Media.Asset = Media.url("https://example.com/image.png")
 void explicitAsset

packages/ai/test/llm-option-types.types.ts

@@ -6,6 +6,7 @@ import {
   type LanguageModelProviderOptions,
   type ProviderOptions,
 } from "../src/index.js"
+import { ai } from "../src/promise.js"
 import { OpenAIChat } from "../src/protocols.js"
 
 interface ExampleOptions {
@@ -31,6 +32,10 @@ const generated = LLM.generate(LLM.request({ model, prompt: "Hello" }))
 type GenerateRequirements = Assert<Equal<Requirements<typeof generated>, LLMClientService>>
 const streamed = LLM.stream(LLM.request({ model, prompt: "Hello" }))
 type StreamClientRequirements = Assert<Equal<StreamRequirements<typeof streamed>, LLMClientService>>
+const generatedFromInput = LLM.generate({ model, prompt: "Hello", providerOptions: { mode: "fast" } })
+type InputGenerateRequirements = Assert<Equal<Requirements<typeof generatedFromInput>, LLMClientService>>
+const streamedFromInput = LLM.stream({ model, prompt: "Hello", providerOptions: { mode: "thorough" } })
+type InputStreamRequirements = Assert<Equal<StreamRequirements<typeof streamedFromInput>, LLMClientService>>
 
 LLM.request({
   model,
@@ -39,6 +44,11 @@ LLM.request({
   providerOptions: { mode: "slow" },
 })
 
+// @ts-expect-error Direct input keeps the selected model's provider option types.
+LLM.generate({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
+// @ts-expect-error Stream input keeps the selected model's provider option types.
+LLM.stream({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
+
 const generatedObject = LLM.generateObject({
   model,
   prompt: "Hello",
@@ -69,5 +79,16 @@ const options: LanguageModelProviderOptions<typeof model> = { mode: "fast" }
 void (options satisfies LanguageModelProviderOptions<typeof model>)
 void (true satisfies GenerateRequirements)
 void (true satisfies StreamClientRequirements)
+void (true satisfies InputGenerateRequirements)
+void (true satisfies InputStreamRequirements)
 void (true satisfies GenerateObjectRequirements)
 void (true satisfies GenerateDynamicObjectRequirements)
+
+void ai.llm.generate({ model, prompt: "Hello", providerOptions: { mode: "fast" } })
+void ai.llm.stream({ model, prompt: "Hello", providerOptions: { mode: "thorough" } })
+void ai.llm.generate(ai.llm.request({ model, prompt: "Hello" }))
+void ai.llm.stream(ai.llm.request({ model, prompt: "Hello" }))
+// @ts-expect-error Promise direct input keeps the selected model's provider option types.
+void ai.llm.generate({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
+// @ts-expect-error Promise stream input keeps the selected model's provider option types.
+void ai.llm.stream({ model, prompt: "Hello", providerOptions: { mode: "slow" } })

packages/ai/test/llm.test.ts

@@ -1,6 +1,7 @@
 import { describe, expect, test } from "bun:test"
-import { Schema } from "effect"
-import { CacheHint, LLM, LLMResponse, ToolEntry, ToolNamespace } from "../src/index.js"
+import { Effect, Schema, Stream } from "effect"
+import { CacheHint, LLM, LLMEvent, LLMResponse, ToolEntry, ToolNamespace } from "../src/index.js"
+import { OpenAI } from "../src/providers.js"
 import * as OpenAIChat from "../src/protocols/openai-chat.js"
 import * as OpenAIResponses from "../src/protocols/openai-responses.js"
 import {
@@ -13,6 +14,8 @@ import {
   ToolDefinition,
   ToolResultPart,
 } from "../src/schema/index.js"
+import { fixedResponse } from "./lib/http.js"
+import { sseEvents } from "./lib/sse.js"
 
 const chatRoute = OpenAIChat.route
 const responsesRoute = OpenAIResponses.route
@@ -240,6 +243,26 @@ describe("llm constructors", () => {
     expect(request.messages.map((message) => message.role)).toEqual(["user", "system"])
   })
 
+  test("generates and streams from input or a prebuilt request", async () => {
+    const model = OpenAI.configure({ apiKey: "test", baseURL: "https://openai.test/v1" }).chat("gpt-4o-mini")
+    const layer = fixedResponse(
+      sseEvents({ choices: [{ delta: { content: "Hello" } }] }, { choices: [{ delta: {}, finish_reason: "stop" }] }),
+    )
+    const input = { model, prompt: "Say hello." }
+    const request = LLM.request(input)
+    const generated = await Effect.runPromise(LLM.generate(input).pipe(Effect.provide(layer)))
+    const generatedFromRequest = await Effect.runPromise(LLM.generate(request).pipe(Effect.provide(layer)))
+    expect(generated.text).toBe("Hello")
+    expect(generatedFromRequest.text).toBe(generated.text)
+
+    const streamed = await Effect.runPromise(LLM.stream(input).pipe(Stream.runCollect, Effect.provide(layer)))
+    const streamedFromRequest = await Effect.runPromise(
+      LLM.stream(request).pipe(Stream.runCollect, Effect.provide(layer)),
+    )
+    expect(Array.from(streamed).some(LLMEvent.is.textDelta)).toBe(true)
+    expect(streamedFromRequest).toEqual(streamed)
+  })
+
   test("extracts output text from response events", () => {
     expect(
       LLMResponse.text({

packages/ai/test/promise.test.ts

@@ -116,19 +116,32 @@ describe("AI promise client", () => {
     const seen: Array<string> = []
     const ai = AI.make({ layer: executor(seen) })
 
-    const text = await ai.llm.generate({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })
+    const request = ai.llm.request({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })
+    const text = await ai.llm.generate(request)
     expect(text.text).toBe("Hello world")
+    expect((await ai.llm.generate({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })).text).toBe(
+      "Hello world",
+    )
 
     const image = await ai.image.generate({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" })
     expect(image.image).toBeInstanceOf(Media.Asset)
     expect(image.image.mediaType).toBe("image/png")
     expect(await ai.run(image.image.bytes())).toEqual(Uint8Array.from([1, 2, 3]))
+    const requested = await ai.image.generate(
+      ai.image.request({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" }),
+    )
+    expect(requested.image.mediaType).toBe("image/png")
 
     const deltas: Array<string> = []
-    for await (const event of ai.llm.stream({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })) {
+    for await (const event of ai.llm.stream(request)) {
       if (LLMEvent.is.textDelta(event)) deltas.push(event.text)
     }
     expect(deltas).toEqual(["Hello", " world"])
+    const directDeltas: Array<string> = []
+    for await (const event of ai.llm.stream({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })) {
+      if (LLMEvent.is.textDelta(event)) directDeltas.push(event.text)
+    }
+    expect(directDeltas).toEqual(deltas)
 
     const imageEvents: Array<string> = []
     for await (const event of ai.image.stream({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" })) {
@@ -137,8 +150,11 @@ describe("AI promise client", () => {
     expect(imageEvents).toEqual(["image-partial", "image", "finish"])
 
     expect(seen).toEqual([
+      "https://openai.test/v1/chat/completions",
       "https://openai.test/v1/chat/completions",
       "https://openai.test/v1/images/generations",
+      "https://openai.test/v1/images/generations",
+      "https://openai.test/v1/chat/completions",
       "https://openai.test/v1/chat/completions",
       "https://openai.test/v1/images/generations",
     ])
@@ -260,22 +276,27 @@ describe("AI promise client", () => {
     const ai = AI.make({ layer: executor([]) })
 
     const failure = await ai.llm
-      .generate({ model: openai.responses("gpt-5"), prompt: "Hello" })
+      .generate(ai.llm.request({ model: openai.responses("gpt-5"), prompt: "Hello" }))
       .then(() => undefined)
       .catch((error: unknown) => error)
     expect(failure).toBeInstanceOf(AIError)
     expect(failure instanceof AIError && failure.reason.http?.status).toBe(404)
 
-    const invalid = await ai.llm
-      // @ts-expect-error Invalid input must reject with AIError, not throw synchronously.
+    const invalidLLM = await ai.llm
+      // @ts-expect-error Invalid input must reject with AIError instead of throwing synchronously.
       .generate({ model: openai.responses("gpt-5"), messages: [{ role: "bogus" }] })
       .catch((error: unknown) => error)
+    expect(invalidLLM instanceof AIError && invalidLLM.reason._tag).toBe("InvalidRequest")
+
+    const invalid = await ai.image
+      .generate({ model: openai.image("gpt-image-2"), prompt: "A lighthouse", n: 1.5 })
+      .catch((error: unknown) => error)
     expect(invalid instanceof AIError && invalid.reason._tag).toBe("InvalidRequest")
 
     const controller = new AbortController()
     controller.abort()
     const aborted = await ai.llm
-      .generate({ model: openai.chat("gpt-4o-mini"), prompt: "Hello" }, { signal: controller.signal })
+      .generate(ai.llm.request({ model: openai.chat("gpt-4o-mini"), prompt: "Hello" }), { signal: controller.signal })
       .then(() => "completed")
       .catch(() => "aborted")
     expect(aborted).toBe("aborted")

packages/ai/test/provider/alibaba.test.ts

@@ -216,6 +216,33 @@ it.effect("Alibaba keeps native reasoning controls and future efforts on their s
   }),
 )
 
+it.effect("Alibaba fits explicit thinking budgets to half the output limit", () =>
+  Effect.gen(function* () {
+    const provider = Alibaba.configure({ region: "ap-southeast-1", apiKey: "fixture" })
+    const chat = (maxTokens?: number) =>
+      compileRequest(
+        LLM.request({
+          model: provider.chat("qwen3.7-plus"),
+          prompt: "hi",
+          ...(maxTokens === undefined ? {} : { generation: { maxTokens } }),
+          providerOptions: { enableThinking: true, thinkingBudget: 131_071 },
+        }),
+      ).pipe(Effect.map((prepared) => prepared.body.thinking_budget))
+    const messages = yield* compileRequest(
+      LLM.request({
+        model: provider.messages("qwen3.7-plus"),
+        prompt: "hi",
+        generation: { maxTokens: 32_000 },
+        providerOptions: { thinking: { type: "enabled", budgetTokens: 131_071 } },
+      }),
+    )
+
+    expect(yield* chat(32_000)).toBe(16_000)
+    expect(yield* chat()).toBe(131_071)
+    expect(messages.body.thinking).toEqual({ type: "enabled", budget_tokens: 16_000 })
+  }),
+)
+
 it.effect("Alibaba validates malformed options before execution", () =>
   Effect.gen(function* () {
     const provider = Alibaba.configure({ region: "ap-southeast-1", apiKey: "fixture" })

packages/ai/test/provider/anthropic-messages.test.ts

@@ -148,11 +148,13 @@ describe("Anthropic Messages route", () => {
     Effect.gen(function* () {
       const enabled = yield* compileRequest(
         LLMRequest.update(request, {
+          generation: { maxTokens: 4_096 },
           providerOptions: { thinking: { type: "enabled", budgetTokens: 1_024 } },
         }),
       )
       const legacy = yield* compileRequest(
         LLMRequest.update(request, {
+          generation: { maxTokens: 4_096 },
           providerOptions: { thinking: { type: "enabled", budget_tokens: 2_048 } },
         }),
       )
@@ -168,6 +170,22 @@ describe("Anthropic Messages route", () => {
     }),
   )
 
+  it.effect("fits the thinking budget to half the output limit", () =>
+    Effect.gen(function* () {
+      const thinking = (maxTokens: number) =>
+        compileRequest(
+          LLMRequest.update(request, {
+            generation: { maxTokens },
+            providerOptions: { thinking: { type: "enabled", budgetTokens: 31_999 } },
+          }),
+        ).pipe(Effect.map((prepared) => prepared.body.thinking))
+
+      expect(yield* thinking(64_000)).toEqual({ type: "enabled", budget_tokens: 31_999 })
+      expect(yield* thinking(20_000)).toEqual({ type: "enabled", budget_tokens: 10_000 })
+      expect(yield* thinking(1_500)).toEqual({ type: "enabled", budget_tokens: 1_024 })
+    }),
+  )
+
   it.effect("rejects enabled thinking without a budget", () =>
     Effect.gen(function* () {
       const error = yield* compileRequest(

packages/ai/test/provider/bedrock-converse.test.ts

@@ -244,6 +244,29 @@ describe("Bedrock Converse route", () => {
     }),
   )
 
+  it.effect("fits a Claude thinking budget below maxTokens", () =>
+    Effect.gen(function* () {
+      const fields = (maxTokens: number, budgetTokens: number, topK?: number) =>
+        compileRequest(
+          LLMRequest.update(baseRequest, {
+            model: AmazonBedrock.model("us.anthropic.claude-haiku-4-5-20251001-v1:0", {
+              baseURL: "https://bedrock-runtime.test",
+              apiKey: "test-bearer",
+              thinking: { type: "enabled", budgetTokens },
+            }),
+            generation: GenerationOptions.make({ maxTokens, topK }),
+          }),
+        ).pipe(Effect.map((prepared) => prepared.body.additionalModelRequestFields))
+
+      expect(yield* fields(64_000, 31_999)).toEqual({ thinking: { type: "enabled", budget_tokens: 31_999 } })
+      expect(yield* fields(20_000, 31_999, 40)).toEqual({
+        top_k: 40,
+        thinking: { type: "enabled", budget_tokens: 10_000 },
+      })
+      expect(yield* fields(1_500, 31_999)).toEqual({ thinking: { type: "enabled", budget_tokens: 1_024 } })
+    }),
+  )
+
   it.effect("omits additionalModelRequestFields when topK is unset", () =>
     Effect.gen(function* () {
       const prepared = yield* compileRequest(baseRequest)

packages/ai/test/provider/checkpoint.test.ts

@@ -22,21 +22,22 @@ testEffect(
       expect(body).toMatchObject({
         model: "fixture",
         stream: true,
-        store: false,
+        store: true,
         instructions: "Keep the context",
-        parallel_tool_calls: true,
+        parallel_tool_calls: false,
         prompt_cache_key: "session-key",
         service_tier: "priority",
         reasoning: { effort: "high", summary: "auto" },
+        context_management: [{ type: "compaction" }],
+        max_tool_calls: 1,
+        tool_choice: "required",
+        text: { verbosity: "high", format: { type: "json_object" } },
         prompt_cache_retention: "24h",
         prompt_cache_options: { mode: "session", ttl: "1h" },
         input: [{ role: "user", content: [{ type: "input_text", text: "hello" }] }, { type: "compaction_trigger" }],
       })
       expect(body.tools).toHaveLength(1)
       expect(body.tools[0].name).toBe("lookup")
-      expect(body.tool_choice).toBeUndefined()
-      expect(body.context_management).toBeUndefined()
-      expect(body.text).toBeUndefined()
       expect(body.max_output_tokens).toBeUndefined()
       expect(body.previous_response_id).toBeUndefined()
       return respond(
@@ -57,7 +58,7 @@ testEffect(
       )
     }),
   ),
-).effect("trigger uses normal request preparation, configured deployment, and supplied subscription headers", () =>
+).effect("trigger keeps request controls, configured deployment, and supplied subscription headers", () =>
   Effect.gen(function* () {
     const calls: string[] = []
     const input = LLM.request({
@@ -67,12 +68,14 @@ testEffect(
       promptCacheKey: "session-key",
       tools: [{ name: "lookup", description: "Lookup", inputSchema: { type: "object", properties: {} } }],
       toolChoice: { type: "tool", name: "lookup" },
-      generation: { maxTokens: 1 },
       providerOptions: {
         store: true,
         reasoningEffort: "high",
         reasoningSummary: "auto",
         contextManagement: [{ type: "compaction" }],
+        parallelToolCalls: false,
+        maxToolCalls: 1,
+        textVerbosity: "low",
       },
       http: {
         headers: { "chatgpt-account-id": "fixture-account", "x-codex-beta-features": "remote_compaction_v2" },
@@ -82,8 +85,7 @@ testEffect(
           prompt_cache_retention: "24h",
           prompt_cache_options: { mode: "session", ttl: "1h" },
           store: true,
-          stream: false,
-          text: { format: { type: "json_object" } },
+          text: { verbosity: "high", format: { type: "json_object" } },
           tool_choice: "required",
         },
       },
@@ -114,6 +116,75 @@ testEffect(
   }),
 )
 
+testEffect(
+  dynamicResponse(({ text, respond }) =>
+    Effect.sync(() => {
+      expect(JSON.parse(text).text).toEqual({ verbosity: "low", format: { type: "json_object" } })
+      return respond(sseEvents({ type: "response.completed", response: { id: "resp_1", output: [checkpoint] } }), {
+        headers: { "content-type": "text/event-stream" },
+      })
+    }),
+  ),
+).effect("keeps explicit verbosity on a trigger checkpoint for prompt cache reuse", () =>
+  LLMClient.compact(
+    LLM.request({
+      model: OpenAI.configure({ apiKey: "fixture" }).responses("gpt-5.5"),
+      prompt: "Hello.",
+      providerOptions: { textVerbosity: "low" },
+      http: { body: { text: { format: { type: "json_object" } } } },
+    }),
+    trigger,
+  ),
+)
+
+testEffect(
+  dynamicResponse(({ text, respond }) =>
+    Effect.sync(() => {
+      const body = JSON.parse(text)
+      expect(body.text).toEqual({ verbosity: "high", format: { type: "json_object" } })
+      expect(body.max_output_tokens).toBe(20_000)
+      return respond(sseEvents({ type: "response.completed", response: { id: "resp_1", output: [checkpoint] } }), {
+        headers: { "content-type": "text/event-stream" },
+      })
+    }),
+  ),
+).effect("keeps the effective body-overlay verbosity and text formatting", () =>
+  LLMClient.compact(
+    LLM.request({
+      model: OpenAI.configure({ apiKey: "fixture" }).responses("gpt-5.5"),
+      prompt: "Hello.",
+      generation: { maxTokens: 20_000 },
+      providerOptions: { textVerbosity: "low" },
+      http: { body: { text: { verbosity: "high", format: { type: "json_object" } } } },
+    }),
+    trigger,
+  ),
+)
+
+testEffect(
+  dynamicResponse(({ text, respond }) =>
+    Effect.sync(() => {
+      expect(JSON.parse(text).max_output_tokens).toBe(128)
+      return respond(JSON.stringify({ error: { message: "max_output_tokens must be at least 20000" } }), {
+        status: 400,
+        headers: { "content-type": "application/json" },
+      })
+    }),
+  ),
+).effect("passes configured output limits through and leaves rejection to the provider", () =>
+  Effect.gen(function* () {
+    const error = yield* LLMClient.compact(
+      LLM.request({
+        model: OpenAI.configure({ apiKey: "fixture" }).responses("gpt-5.5"),
+        prompt: "Hello.",
+        generation: { maxTokens: 128 },
+      }),
+      trigger,
+    ).pipe(Effect.flip)
+    expect(error.message).toContain("at least 20000")
+  }),
+)
+
 const idless = { type: "compaction", encrypted_content: "opaque" }
 testEffect(
   fixedResponse(
@@ -184,7 +255,7 @@ testEffect(fixedResponse(sseEvents({ type: "response.output_item.done", item: ch
       expect(error.reason._tag).toBe("InvalidProviderOutput")
     }),
 )
-for (const body of [{ input: [] }, { previous_response_id: "stale" }]) {
+for (const body of [{ input: [] }, { previous_response_id: "stale" }, { stream: false }]) {
   testEffect(dynamicResponse(() => Effect.die("Must reject before sending"))).effect(
     `rejects caller-supplied ${Object.keys(body)[0]} before sending trigger`,
     () =>

packages/ai/test/provider/explicit-compaction.test.ts

@@ -110,11 +110,16 @@ for (const model of [
     dynamicResponse(({ request, text, respond }) =>
       Effect.sync(() => {
         expect(new URL(request.url).pathname).toEndWith("/responses/compact")
-        expect(JSON.parse(text)).toEqual({ model: "fixture", input: [item], instructions: "Keep the context" })
+        expect(JSON.parse(text)).toEqual({
+          model: "fixture",
+          input: [item],
+          instructions: "Keep the context",
+          include: ["reasoning.encrypted_content"],
+        })
         return respond(JSON.stringify({ object: "response.compaction", output: [checkpoint] }))
       }),
     ),
-  ).effect(`${model.provider} compacts provider-specific history without lowering generation settings`, () =>
+  ).effect(`${model.provider} validates tools but ignores unrelated unsupported generation settings`, () =>
     Effect.gen(function* () {
       const request = LLM.request({
         model,
@@ -151,6 +156,11 @@ for (const model of [
       ] as const) {
         const error = yield* LLMClient.generate(candidate).pipe(Effect.flip)
         expect(error.reason._tag).toBe(tag)
+        if (candidate.tools.length > 0) {
+          const compactError = yield* LLMClient.compact(candidate).pipe(Effect.flip)
+          expect(compactError.reason._tag).toBe("InvalidRequest")
+          continue
+        }
         const response = yield* LLMClient.compact(candidate)
         expect(response.replacement[0]?.content[0]?.type).toBe("compaction")
       }
@@ -255,6 +265,13 @@ for (const overlay of [undefined, { service_tier: "priority", prompt_cache_key:
           model: "fixture",
           input: [{ type: "message", role: "user", content: [{ type: "input_text", text: "hello" }] }],
           service_tier: overlay?.service_tier ?? "flex",
+          reasoning: { effort: "low" },
+          text: { verbosity: "low", format: { type: "json_object" } },
+          include: ["reasoning.encrypted_content"],
+          parallel_tool_calls: false,
+          tools: [
+            { type: "function", name: "lookup", description: "Lookup", parameters: { type: "object" }, strict: false },
+          ],
           prompt_cache_key: overlay?.prompt_cache_key ?? "affinity",
           prompt_cache_retention: "24h",
           prompt_cache_options: { mode: "explicit", ttl: "30m" },
@@ -268,12 +285,20 @@ for (const overlay of [undefined, { service_tier: "priority", prompt_cache_key:
         model: OpenAI.configure({ apiKey: "test" }).responses("fixture"),
         prompt: "hello",
         promptCacheKey: "affinity",
-        providerOptions: { serviceTier: "flex" },
+        providerOptions: {
+          serviceTier: "flex",
+          reasoningEffort: "low",
+          textVerbosity: "low",
+          include: ["reasoning.encrypted_content"],
+          parallelToolCalls: false,
+        },
         generation: { maxTokens: 100 },
+        tools: [{ name: "lookup", description: "Lookup", inputSchema: {} }],
         http: {
           body: {
             stream: true,
             store: false,
+            text: { format: { type: "json_object" } },
             prompt_cache_retention: "24h",
             prompt_cache_options: { mode: "explicit", ttl: "30m" },
             ...overlay,
@@ -396,6 +421,8 @@ for (const model of [
             model: model.id,
             input: [{ type: "message", role: "user", content: [{ type: "input_text", text: "original" }] }],
             instructions: "system",
+            include: ["reasoning.encrypted_content"],
+            ...(model.id === "gpt-5.3-codex" ? { reasoning: { effort: "medium", summary: "auto" } } : {}),
           })
           return respond(
             JSON.stringify({
@@ -407,7 +434,10 @@ for (const model of [
           )
         }
         expect(new URL(request.url).pathname.endsWith("/responses")).toBe(true)
-        expect(body.input).toEqual([...output, { type: "message", role: "user", content: [{ type: "input_text", text: "continue" }] }])
+        expect(body.input).toEqual([
+          ...output,
+          { type: "message", role: "user", content: [{ type: "input_text", text: "continue" }] },
+        ])
         return respond(sseEvents({ type: "response.completed", response: { id: "resp_1", output: [] } }), {
           headers: { "content-type": "text/event-stream" },
         })

packages/ai/test/provider/gemini.test.ts

@@ -90,6 +90,23 @@ describe("Gemini route", () => {
     }),
   )
 
+  it.effect("fits the thinking budget to half the output limit", () =>
+    Effect.gen(function* () {
+      const thinkingBudget = (budget: number, maxTokens = 32_000) =>
+        compileRequest(
+          LLMRequest.update(request, {
+            generation: { maxTokens },
+            providerOptions: { thinkingConfig: { thinkingBudget: budget } },
+          }),
+        ).pipe(Effect.map((prepared) => prepared.body.generationConfig?.thinkingConfig?.thinkingBudget))
+
+      expect(yield* thinkingBudget(32_768)).toBe(16_000)
+      expect(yield* thinkingBudget(8_000)).toBe(8_000)
+      expect(yield* thinkingBudget(-1)).toBe(-1)
+      expect(yield* thinkingBudget(8_192, 1_000)).toBe(512)
+    }),
+  )
+
   it.effect("forwards standard Gemini generation options", () =>
     Effect.gen(function* () {
       const prepared = yield* compileRequest(

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

@@ -1945,7 +1945,7 @@ describe("OpenAI Responses route", () => {
       expect(prepared.body.prompt_cache_key).toBe("session_123")
       expect(prepared.body.include).toEqual(["reasoning.encrypted_content"])
       expect(prepared.body.reasoning).toEqual({ effort: "high", summary: "auto" })
-      expect(prepared.body.text).toEqual({ verbosity: "low" })
+      expect(prepared.body.text).toBeUndefined()
       expect(prepared.body.metadata).toEqual({ environment: "test", tenant: "acme" })
       expect(prepared.body.safety_identifier).toBe("user_123")
       expect(prepared.body.stream_options).toEqual({ include_obfuscation: false })

packages/ai/test/provider/openrouter.test.ts

@@ -152,6 +152,27 @@ describe("OpenRouter", () => {
     }),
   )
 
+  it.effect("fits the reasoning budget to half the output limit", () =>
+    Effect.gen(function* () {
+      const reasoning = (maxTokens: number | undefined, value: Record<string, unknown>) =>
+        compileRequest(
+          LLM.request({
+            model: OpenRouter.configure({ apiKey: "test-key" }).model("qwen/qwen3.8-flash"),
+            cache: "none",
+            prompt: "Hello",
+            ...(maxTokens === undefined ? {} : { generation: { maxTokens } }),
+            providerOptions: { reasoning: value },
+          }),
+        ).pipe(Effect.map((prepared) => prepared.body.reasoning))
+
+      expect(yield* reasoning(32_000, { max_tokens: 131_071 })).toEqual({ max_tokens: 16_000 })
+      expect(yield* reasoning(131_072, { max_tokens: 65_536 })).toEqual({ max_tokens: 65_536 })
+      expect(yield* reasoning(1_500, { max_tokens: 65_536 })).toEqual({ max_tokens: 1_024 })
+      expect(yield* reasoning(undefined, { max_tokens: 131_071 })).toEqual({ max_tokens: 131_071 })
+      expect(yield* reasoning(32_000, { effort: "high" })).toEqual({ effort: "high" })
+    }),
+  )
+
   it.effect("applies OpenRouter payload options from the model helper", () =>
     Effect.gen(function* () {
       const prepared = yield* compileRequest(

packages/ai/test/speech.test.ts

@@ -28,10 +28,49 @@ const cartesia = Cartesia.configure({ apiKey: "test", baseURL: "https://cartesia
 const google = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).speech(
   "gemini-2.5-flash-preview-tts",
 )
+const google38 = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).speech(
+  "gemini-3.8-flash-tts",
+)
+const google38Lite = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).speech(
+  "gemini-3.8-flash-lite-tts",
+)
 const deepgram = Deepgram.configure({ apiKey: "test", baseURL: "https://deepgram.test" }).speech("aura-2-thalia-en")
 const voice = "JBFqnCBsd6RMkjVDRZzb"
 
 describe("Speech", () => {
+  it.effect("preserves Google's WAV output instead of describing it as raw PCM", () =>
+    Effect.gen(function* () {
+      const bytes = new TextEncoder().encode("RIFF....WAVEfmt ")
+      const response = yield* Speech.generate({ model: google38, text: "Hi" }).pipe(
+        Effect.provide(
+          respond(
+            JSON.stringify({
+              candidates: [
+                { content: { parts: [{ inlineData: { mimeType: "audio/wav", data: Encoding.encodeBase64(bytes) } }] } },
+              ],
+            }),
+            "application/json",
+          ),
+        ),
+      )
+      expect(response.audio.mediaType).toBe("audio/wav")
+      expect(response.audio.info?.format).toBe("wav")
+      expect(response.audio.info?.encoding).toBeUndefined()
+      expect(yield* response.audio.bytes()).toEqual(bytes)
+    }),
+  )
+
+  it.effect("rejects raw PCM for Gemini 3.8 unary requests before sending", () =>
+    Effect.gen(function* () {
+      const errors = yield* Effect.all(
+        [google38, google38Lite].map((model) =>
+          Speech.generate({ model, text: "Hi", format: "pcm" }).pipe(Effect.flip),
+        ),
+      ).pipe(Effect.provide(layer(() => Effect.die("An unsupported request reached the network"))))
+      expect(errors.map((error) => error.reason._tag)).toEqual(["UnsupportedOperation", "UnsupportedOperation"])
+    }),
+  )
+
   it.effect("rejects what a provider cannot produce before sending anything", () =>
     Effect.gen(function* () {
       const errors = yield* Effect.all(

packages/ai/test/speech.types.ts

@@ -1,5 +1,5 @@
 import type { Stream } from "effect"
-import { Speech, type SpeechEvent } from "../src/index.js"
+import { Speech, SpeechModel, type SpeechEvent, type SpeechOptions } from "../src/index.js"
 import { ElevenLabs, OpenAI, Runway } from "../src/providers.js"
 
 type StreamItem<T> = T extends Stream.Stream<infer A, infer _E, infer _R> ? A : never
@@ -7,6 +7,8 @@ type Equal<A, B> = [A, B] extends [B, A] ? true : false
 type Assert<T extends true> = T
 
 const elevenlabs = ElevenLabs.configure({ apiKey: "test" }).speech("eleven_flash_v2_5")
+const widenSpeech = <Options extends SpeechOptions>(model: SpeechModel<Options>): SpeechModel => model
+void widenSpeech
 
 Speech.generate({
   model: elevenlabs,

packages/ai/test/transcription.types.ts

@@ -1,5 +1,11 @@
 import type { Stream } from "effect"
-import { Media, Transcription, type TranscriptionEvent } from "../src/index.js"
+import {
+  Media,
+  Transcription,
+  TranscriptionModel,
+  type TranscriptionEvent,
+  type TranscriptionOptions,
+} from "../src/index.js"
 import { AssemblyAI, Deepgram, OpenAI } from "../src/providers.js"
 
 type StreamItem<T> = T extends Stream.Stream<infer A, infer _E, infer _R> ? A : never
@@ -8,6 +14,10 @@ type Assert<T extends true> = T
 
 const audio = Media.url("https://example.com/call.mp3")
 const deepgram = Deepgram.configure({ apiKey: "test" }).transcription("nova-3")
+const widenTranscription = <Options extends TranscriptionOptions>(
+  model: TranscriptionModel<Options>,
+): TranscriptionModel => model
+void widenTranscription
 
 Transcription.generate({
   model: deepgram,

packages/ai/test/video.types.ts

@@ -9,7 +9,6 @@ import {
   type VideoModelOptions,
   type VideoOptions,
   type VideoRequestFor,
-  type VideoRoute,
 } from "../src/index.js"
 import type { Service } from "../src/video-client.js"
 import { Anthropic, Fal, Google, OpenAI, Runway, XAI } from "../src/providers.js"
@@ -23,8 +22,7 @@ type VeoLikeOptions = {
   readonly personGeneration?: "allow_all" | "allow_adult"
 } & Record<string, unknown>
 
-declare const route: VideoRoute<VeoLikeOptions>
-const veo = VideoModel.make<VeoLikeOptions>({ id: "veo", provider: "google", route })
+declare const veo: VideoModel<VeoLikeOptions>
 // @ts-expect-error Extracted model options retain known provider fields.
 const invalidVeoOptions: VideoModelOptions<typeof veo> = { personGeneration: "everyone" }
 void invalidVeoOptions
@@ -99,6 +97,8 @@ Video.generate({ model: google, prompt: "A kitten", durationSeconds: "8s" })
 Video.generate({ model: google, prompt: "A kitten", options: { personGeneration: "allow_all" } })
 
 declare const generic: VideoModel<VideoOptions>
+const widenVideo = <Options extends VideoOptions>(model: VideoModel<Options>): VideoModel => model
+void widenVideo
 Video.generate({ model: generic, prompt: "A kitten", providerOptions: { arbitrary: true } })
 
 const request = Video.request({ model: veo, prompt: "A kitten", providerOptions: { personGeneration: "allow_all" } })

packages/app/component-tests/browser-pane.fixture.tsx

@@ -2,7 +2,7 @@ import { DialogProvider } from "@opencode/ui/context/dialog"
 import { Browser } from "@opencode/plugin-browser/rpc"
 import { For, Show } from "solid-js"
 import { createStore } from "solid-js/store"
-import { render } from "solid-js/web"
+import { Portal, render } from "solid-js/web"
 import { LanguageProvider, UiI18nBridge } from "../src/runtime/i18n/language"
 import type { BrowserPaneLayout, BrowserPaneRegistration } from "../src/runtime/platform/browser-pane"
 import type { createSessionBrowser } from "../src/session/browser/model"
@@ -27,7 +27,12 @@ export function mountBrowserPane() {
       loadErrors: {} as Record<string, string | undefined>,
       error: undefined as string | undefined,
       layouts: {} as Record<string, BrowserPaneLayout | undefined>,
+      covered: false,
+      captures: 0,
+      holdCapture: false,
     })
+    // Each capture waits until the fixture releases it, so a spec can observe the pending state.
+    const held: (() => void)[] = []
     const tabs = ["Alpha", "Beta"].map((name) => ({
       id: Browser.TabID.make(`tab_${name === "Alpha" ? "11111111" : "22222222"}-1111-1111-1111-111111111111`),
       title: name,
@@ -44,6 +49,17 @@ export function mountBrowserPane() {
         {
           setLayout: (layout) => setStore("layouts", tab.title, layout),
           command: async () => undefined,
+          capture: async () => {
+            setStore("captures", (count) => count + 1)
+            if (store.holdCapture) await new Promise<void>((resolve) => held.push(resolve))
+            const canvas = new OffscreenCanvas(4, 4)
+            const paint = canvas.getContext("2d")
+            if (paint) {
+              paint.fillStyle = "#3b82f6"
+              paint.fillRect(0, 0, 4, 4)
+            }
+            return canvas.convertToBlob()
+          },
           close: () => undefined,
         },
       ]),
@@ -118,12 +134,34 @@ export function mountBrowserPane() {
             Complete navigation
           </button>
           <button onClick={() => setStore("visible", (visible) => !visible)}>Toggle Review tab</button>
+          <button onClick={() => setStore("holdCapture", true)}>Hold capture</button>
+          <button onClick={() => held.splice(0).forEach((resolve) => resolve())}>Release capture</button>
+          <button onClick={() => setStore("covered", (covered) => !covered)}>Toggle popover</button>
         </nav>
-        <div style={{ width: "640px", height: "360px", border: "1px solid #555" }}>
+        <p>Captures: {store.captures}</p>
+        <div style={{ position: "relative", width: "640px", height: "360px", border: "1px solid #555" }}>
           <Show when={store.mounted}>
             <SessionBrowserPane browser={browser} visible={store.visible} />
           </Show>
         </div>
+        <Show when={store.covered}>
+          {/* Floating content portals into <body> like a menu or hover card over the page. */}
+          <Portal mount={document.body}>
+            <div
+              data-popper-positioner
+              data-testid="fixture-popover"
+              style={{
+                position: "fixed",
+                top: "0",
+                left: "0",
+                width: "320px",
+                height: "480px",
+                "z-index": "1001",
+                "pointer-events": "none",
+              }}
+            />
+          </Portal>
+        </Show>
         <h2 style={{ "font-size": "18px", margin: "20px 0 12px" }}>Native layout recorder</h2>
         <p>The desktop boundary keeps each session's page visible until its registration is hidden.</p>
         <For each={tabs}>

packages/app/component-tests/browser-pane.spec.ts

@@ -58,6 +58,27 @@ story("hides the native view immediately while the pane stays mounted", async ({
   await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "true")
 })
 
+story("keeps a still of the page under floating content that covers it", async ({ page }, testInfo) => {
+  const root = page.getByTestId("browser-pane-fixture")
+  const still = root.locator("#browser-panel img")
+  await root.getByRole("button", { name: "Hold capture", exact: true }).click()
+  await root.getByRole("button", { name: "Toggle popover", exact: true }).click()
+  await expect(root.getByText("Captures: 1", { exact: true })).toBeVisible()
+  // The native page stays up until its still is ready, so the pane never shows blank.
+  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "true")
+  await expect(still).toHaveCount(0)
+
+  await root.getByRole("button", { name: "Release capture", exact: true }).click()
+  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "false")
+  await expect(still).toBeVisible()
+  await page.screenshot({ path: testInfo.outputPath("covered.png") })
+
+  await root.getByRole("button", { name: "Toggle popover", exact: true }).click()
+  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "true")
+  await expect(still).toHaveCount(0)
+  await expect(root.getByText("Captures: 1", { exact: true })).toBeVisible()
+})
+
 story("shows the empty state over a blank native page and restores navigation", async ({ page }) => {
   const root = page.getByTestId("browser-pane-fixture")
   await root.getByRole("button", { name: "Blank page", exact: true }).click()

packages/app/e2e/regression/session-queue.spec.ts

@@ -1,5 +1,5 @@
 import { expect, test, type Page } from "@playwright/test"
-import type { OpenCodeEvent, SessionMessageInfo } from "@opencode/client/promise"
+import type { OpenCodeEvent, SessionInboxInfo, SessionMessageInfo } from "@opencode/client/promise"
 import { base64Encode } from "@opencode/util/encode"
 import { mockOpenCodeServer } from "../utils/mock-server"
 import { expectAppVisible } from "../utils/waits"
@@ -14,7 +14,12 @@ type InboxRow = {
   sessionID: string
   time: { created: number }
   type: "user"
-  payload: { text: string; metadata?: Record<string, unknown> }
+  payload: {
+    text: string
+    metadata?: Record<string, unknown>
+    files?: Extract<SessionInboxInfo, { type: "user" }>["payload"]["files"]
+    agents?: Extract<SessionInboxInfo, { type: "user" }>["payload"]["agents"]
+  }
   delivery: "steer" | "queue"
 }
 
@@ -29,7 +34,7 @@ function createQueueMock(seed: string[], messages: SessionMessageInfo[] = []) {
   }))
   const events: OpenCodeEvent[] = []
   const prompts: Record<string, unknown>[] = []
-  const changes: { inboxID: string; action: "cancel" | "steer" }[] = []
+  const changes: { inboxID: string; action: "cancel" | "steer" | "queue" }[] = []
   const log: string[] = []
   let sequence = 0
   const emit = <Type extends OpenCodeEvent["type"]>(
@@ -234,6 +239,108 @@ test("editing restores the existing draft and replaces only the original queue p
   expect(mock.log[0]).toBe("prompt:queue")
 })
 
+test("Undo cancels only the selected queued prompt and focuses the restored input", async ({ page }) => {
+  const mock = createQueueMock(["first queued prompt", "second queued prompt", "third queued prompt"])
+  const view = await openSession(page, mock)
+  await expect(view.rows).toHaveCount(3)
+
+  const row = view.rows.filter({ hasText: "second queued prompt" })
+  const actions = row.locator('[data-slot="session-queue-actions"] button')
+  await expect(actions).toHaveCount(3)
+  expect(
+    await actions.evaluateAll((buttons) =>
+      buttons.map((button) => button.getAttribute("aria-label") ?? button.textContent?.trim()),
+    ),
+  ).toEqual(["Steer", "Undo", "Remove"])
+  const undo = row.getByRole("button", { name: "Undo" })
+  await expect(undo).toHaveText("")
+  await expect(undo.locator("svg use")).toHaveAttribute("href", "#opencode-v2-icon-arrow-down-to-line")
+  await undo.hover()
+  await expect(page.getByRole("tooltip")).toHaveText("Undo")
+  await undo.click()
+  await expect(view.rows.locator('[data-action="session-queue-edit"]')).toHaveText([
+    "first queued prompt",
+    "third queued prompt",
+  ])
+  await expect(view.input).toHaveText("second queued prompt")
+  await expect(view.input).toBeFocused()
+  expect(mock.changes).toEqual([{ inboxID: "inb_seed_2", action: "cancel" }])
+  expect(mock.prompts).toEqual([])
+})
+
+test("Undo appends to an existing draft and restores inline attachments", async ({ page }) => {
+  const mock = createQueueMock(["queued with image"])
+  mock.rows[0].payload.files = [
+    {
+      data: "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVQIHWP4z8DwHwAFgAI/ScL/nwAAAABJRU5ErkJggg==",
+      mime: "image/png",
+      source: { type: "inline" },
+      name: "shot.png",
+    },
+  ]
+  const view = await openSession(page, mock)
+  await view.input.fill("my draft")
+  await view.rows.getByRole("button", { name: "Undo" }).click()
+  await expect(view.rows).toHaveCount(0)
+  await expect(view.input).toHaveText("my draft\n\nqueued with image")
+  await expect(view.input).toBeFocused()
+  await expect(view.composer.getByRole("img", { name: "shot.png" })).toBeVisible()
+  expect(mock.changes).toEqual([{ inboxID: "inb_seed_1", action: "cancel" }])
+})
+
+test("Undo stays usable with a long queue on a narrow screen", async ({ page }, testInfo) => {
+  await page.setViewportSize({ width: 390, height: 844 })
+  const text = "Review the detailed error report and check every step of the retry path ".repeat(4)
+  const mock = createQueueMock([text, ...Array.from({ length: 6 }, (_, index) => `queued follow-up ${index + 1}`)])
+  const view = await openSession(page, mock)
+  await expect(view.rows).toHaveCount(7)
+  const row = view.rows.filter({ hasText: text })
+  await row.getByRole("button", { name: "Undo" }).hover()
+  await expect(page.getByRole("tooltip")).toHaveText("Undo")
+  await page.screenshot({ path: testInfo.outputPath("undo-narrow-queue.png") })
+  await row.getByRole("button", { name: "Undo" }).click()
+  await expect(view.rows).toHaveCount(6)
+  await expect(view.input).toHaveText(text)
+  await expect(view.input).toBeFocused()
+  expect(mock.changes).toEqual([{ inboxID: "inb_seed_1", action: "cancel" }])
+})
+
+test("Undo preserves mentioned file and agent references on resubmission", async ({ page }) => {
+  const mock = createQueueMock(["inspect @main.ts with @build"])
+  mock.rows[0].payload.files = [
+    {
+      data: "aGk=",
+      mime: "text/plain",
+      source: { type: "uri", uri: "file:///repo/main.ts" },
+      name: "main.ts",
+      mention: { start: 8, end: 16, text: "@main.ts" },
+    },
+  ]
+  mock.rows[0].payload.agents = [{ name: "build", mention: { start: 22, end: 28, text: "@build" } }]
+  const view = await openSession(page, mock)
+  await view.rows.getByRole("button", { name: "Undo" }).click()
+  await expect(view.input).toHaveText("inspect @main.ts with @build")
+  await view.input.press("Enter")
+  await expect.poll(() => mock.prompts.length).toBe(1)
+  expect(mock.prompts[0].files).toMatchObject([
+    { uri: "data:text/plain;base64,aGk=", mention: { text: "@main.ts", start: 8, end: 16 } },
+  ])
+  expect(mock.prompts[0].agents).toMatchObject([{ name: "build", mention: { text: "@build" } }])
+})
+
+test("Undo does not discard hidden file context", async ({ page }) => {
+  const mock = createQueueMock(["inspect this file"])
+  mock.rows[0].payload.files = [
+    { data: "aGk=", mime: "text/plain", source: { type: "uri", uri: "file:///repo/main.ts" }, name: "main.ts" },
+  ]
+  const view = await openSession(page, mock)
+  await view.rows.getByRole("button", { name: "Undo" }).click()
+  await expect(page.getByText("Edit this prompt in the queue to preserve its file context")).toBeVisible()
+  await expect(view.rows).toHaveCount(1)
+  await expect(view.input).toHaveText("")
+  expect(mock.changes).toEqual([])
+})
+
 for (const delivery of ["steer", "queue"] as const) {
   test(`keeps finished tools above a pending ${delivery === "queue" ? "queue-to-steer" : "steer"} follow-up`, async ({
     page,

packages/app/src/composer/adapter.ts

@@ -47,6 +47,7 @@ export type ComposerDelivery = "steer" | "queue"
 // is loaded in the editor.
 export type ComposerQueue = {
   count: Accessor<number>
+  undoing: Accessor<boolean>
   // Delivery a plain submit uses right now.
   delivery: Accessor<ComposerDelivery>
   // Delivery offered on Mod+Enter and the toolbar hint button; undefined hides the hint.

packages/app/src/composer/composer.stories.tsx

@@ -168,6 +168,7 @@ function ComposerStory(props: {
               alternate: () => props.alternate,
               editing: () => undefined,
               confirmEdit() {},
+              undoing: () => false,
               cancelEdit() {},
               editFirst: () => false,
             }

packages/app/src/composer/composer.tsx

@@ -16,6 +16,7 @@ export function Composer(props: {
   class?: string
   model: ComposerModel
   borderUnderlay?: boolean
+  readOnly?: boolean
   suggestionBoundary?: () => HTMLElement | undefined
 }) {
   const dialog = useDialog()
@@ -27,6 +28,7 @@ export function Composer(props: {
       <ComposerEditor
         controller={props.model}
         borderUnderlay={props.borderUnderlay}
+        readOnly={props.readOnly}
         class={props.class}
         modelControlsVisible={!props.model.model.loading}
         attachKeybind={command.keybindParts("file.attach")}

packages/app/src/composer/model.ts

@@ -371,6 +371,7 @@ export function createComposerModel(adapter: ComposerAdapter, options?: { queue?
         onSubmit: (submitOptions) => {
           if (!available()) return
           const queue = options?.queue
+          if (queue?.undoing()) return
           // Confirming an edit re-admits the queued prompt instead of sending
           // the composer value as a new prompt. Enter keeps it queued in
           // place; the alternate action sends it as a steer.

packages/app/src/home/sessions/controller.tsx

@@ -86,6 +86,7 @@ export function createHomeSessionsController(home: HomeController) {
       sessions: indexedSessions,
       projectDirectories,
       projects: home.project.list,
+      resolveProject: (session) => home.server.focusedContext()?.projects.forSession(session),
     }),
   )
   const records = createMemo(() => allRecords().slice(0, HOME_SESSION_LIMIT))
@@ -291,6 +292,7 @@ export function createHomeSessionsController(home: HomeController) {
           sessions: () => [result],
           projectDirectories,
           projects: home.project.list,
+          resolveProject: ctx.projects.forSession,
         })[0]
       },
       create: home.project.openNewSession,

packages/app/src/home/sessions/records.ts

@@ -18,6 +18,7 @@ export function buildHomeSessionRecords(input: {
   sessions: () => SessionInfo[]
   projectDirectories: () => string[] | undefined
   projects: () => LocalProject[]
+  resolveProject?: (session: SessionInfo) => LocalProject | undefined
 }) {
   const selected = input.projectDirectories()
   const directories = selected ? new Set(selected.map(pathKey)) : undefined
@@ -27,11 +28,12 @@ export function buildHomeSessionRecords(input: {
   return [...new Map(sessions.map((session) => [session.id, session] as const)).values()]
     .sort(compareSessionTime)
     .map((session) => {
-      const project = homeProjectForSession(session, input.projects()) ?? {
-        id: session.projectID,
-        worktree: session.location.directory,
-        expanded: false,
-      }
+      const project = input.resolveProject?.(session) ??
+        homeProjectForSession(session, input.projects()) ?? {
+          id: session.projectID,
+          worktree: session.location.directory,
+          expanded: false,
+        }
       return { session, project, projectName: displayName(project) }
     })
 }

packages/app/src/runtime/i18n/en.ts

@@ -874,6 +874,9 @@ export const dict = {
   "session.queue.send": "Send",
   "session.queue.steerTooltip": "Send without interrupting",
   "session.queue.remove": "Remove",
+  "session.queue.undo": "Undo",
+  "session.queue.undoShell": "Leave shell mode before undoing a queued prompt",
+  "session.queue.undoUnavailable": "Edit this prompt in the queue to preserve its file context",
   "session.queue.reorder": "Reorder queued prompt",
   "session.queue.attachments.one": "{{count}} attachment",
   "session.queue.attachments.other": "{{count}} attachments",
@@ -1439,6 +1442,15 @@ export const dict = {
   "settings.providers.section.connected": "Connected providers",
   "settings.providers.connected.empty": "No connected providers",
   "settings.providers.connected.environmentDescription": "Connected from your environment variables",
+  "settings.providers.account.manage": "Manage {{provider}} accounts",
+  "settings.providers.account.group": "Accounts",
+  "settings.providers.account.add": "Add account",
+  "settings.providers.account.remove": "Remove account…",
+  "settings.providers.account.active": "Active",
+  "settings.providers.account.switched.title": "{{provider}} account switched",
+  "settings.providers.account.switched.description": "Now using {{account}}.",
+  "settings.providers.account.removed.title": "{{account}} removed",
+  "settings.providers.account.removed.description": "{{provider}} will no longer use this account.",
   "settings.providers.console.available.one": "{{count}} provider available",
   "settings.providers.console.available.other": "{{count}} providers available",
   "settings.providers.section.popular": "Popular providers",

packages/app/src/runtime/platform/browser-pane.ts

@@ -25,6 +25,8 @@ export type BrowserPaneEvent =
 export type BrowserPaneRegistration = {
   setLayout(layout?: BrowserPaneLayout): void
   command(command: BrowserPaneCommand): Promise<void>
+  /** Captures the shown page, or resolves null when nothing is on screen. */
+  capture(tabID: Browser.TabID): Promise<Blob | null>
   close(): void
 }
 

packages/app/src/runtime/server/runtime.tsx

@@ -18,6 +18,8 @@ import { showToast } from "@/shell/notifications/toast"
 import { formatServerError } from "./errors"
 import { useSettings } from "@/settings/model"
 import { timelinePreset } from "@opencode/session-ui/timeline/detail"
+import type { SessionInfo } from "@opencode/client/promise"
+import { resolveProjectForSession, resolveSessionDetailsProject } from "@/shell/layout/helpers"
 
 export const { use: useGlobal, provider: GlobalProvider } = createSimpleContext({
   name: "Global",
@@ -180,6 +182,13 @@ function createServerController(
   }
 
   const projectsList = createMemo(() => projects.list().map(enrich))
+  const forSession = (session: SessionInfo) => {
+    const project = resolveProjectForSession(session, projectsList(), sync.data.project)
+    if (!project) return
+    return "expanded" in project ? project : { ...project, expanded: false }
+  }
+  const detailsForSession = (session: SessionInfo) =>
+    resolveSessionDetailsProject(session, projectsList(), sync.data.project)
   const recentlyClosedList = createMemo(() => {
     const known = new Set(sync.data.project.map((project) => pathKey(project.worktree)))
     return projects
@@ -200,6 +209,8 @@ function createServerController(
     projects: {
       ...projects,
       list: projectsList,
+      forSession,
+      detailsForSession,
       resolve: enrich,
       recentlyClosed: recentlyClosedList,
     },

packages/app/src/session/browser/connection.test.ts

@@ -43,6 +43,9 @@ function fixture() {
           async command(command) {
             call.commands.push(command)
           },
+          async capture() {
+            return null
+          },
           close() {
             call.closed = true
           },

packages/app/src/session/browser/pane.tsx

@@ -11,6 +11,7 @@ import { createStore } from "solid-js/store"
 import { useLanguage } from "@/runtime/i18n/language"
 import { usePlatform } from "@/runtime/platform/platform"
 import { useCommand } from "@/shell/commands/command"
+import type { Browser } from "@opencode/plugin-browser/rpc"
 import type { createSessionBrowser } from "./model"
 
 export function SessionBrowserPane(props: { browser: ReturnType<typeof createSessionBrowser>; visible: boolean }) {
@@ -30,6 +31,8 @@ export function SessionBrowserPane(props: { browser: ReturnType<typeof createSes
     // A submitted navigation the browser has not reported yet; keeps the empty state hidden meanwhile.
     navigating: false,
     visible: typeof document === "undefined" || document.visibilityState === "visible",
+    // A still of the page shown in the DOM while floating content covers the hidden native view.
+    snapshot: undefined as { tabID: Browser.TabID; url: string } | undefined,
   })
   const empty = () => !address() && !state()?.loading && !store.navigating
   let surface: HTMLDivElement | undefined
@@ -37,6 +40,8 @@ export function SessionBrowserPane(props: { browser: ReturnType<typeof createSes
   let frame: number | undefined
   let layout: string | undefined
   let until = 0
+  let capturing: Browser.TabID | undefined
+  let release: ReturnType<typeof setTimeout> | undefined
   const canvas = document.createElement("canvas")
   canvas.width = canvas.height = 1
   const paint = canvas.getContext("2d", { willReadFrequently: true })
@@ -69,6 +74,45 @@ export function SessionBrowserPane(props: { browser: ReturnType<typeof createSes
       const r = el.getBoundingClientRect()
       return r.width > 0 && r.left < rect.right && r.right > rect.left && r.top < rect.bottom && r.bottom > rect.top
     })
+  const replaceSnapshot = (next?: { tabID: Browser.TabID; url: string }) => {
+    if (store.snapshot?.url) URL.revokeObjectURL(store.snapshot.url)
+    setStore("snapshot", next)
+  }
+  // Keep the page on screen as a still under the floating content. The native view
+  // stays visible until the still has decoded, so the pane never flashes blank.
+  const freeze = (tabID: Browser.TabID) => {
+    clearTimeout(release)
+    release = undefined
+    if (store.snapshot?.tabID === tabID || capturing === tabID) return
+    capturing = tabID
+    void (registration()?.capture(tabID) ?? Promise.resolve(null))
+      .catch(() => null)
+      .then(async (blob) => {
+        const url = blob ? URL.createObjectURL(blob) : ""
+        if (url) {
+          const image = new Image()
+          image.src = url
+          await image.decode().catch(() => undefined)
+        }
+        if (capturing !== tabID) {
+          if (url) URL.revokeObjectURL(url)
+          return
+        }
+        capturing = undefined
+        // A failed capture still hides the page; the pane shows its background as before.
+        replaceSnapshot({ tabID, url })
+        schedule()
+      })
+  }
+  const thaw = () => {
+    capturing = undefined
+    if (!store.snapshot || release !== undefined) return
+    // Keep the still under the native view until the view has painted again.
+    release = setTimeout(() => {
+      release = undefined
+      replaceSnapshot()
+    }, 150)
+  }
   const measure = () => {
     if (!surface) return
     const tab = state()
@@ -84,7 +128,11 @@ export function SessionBrowserPane(props: { browser: ReturnType<typeof createSes
     const bottom = Math.round(rect.bottom * zoom)
     // The desktop page hides blank and loading documents itself; only hide here
     // while the pane shows its own empty or failed state over the surface.
-    const visible = props.visible && store.visible && !empty() && !failed() && !dialog.active && !covered(rect)
+    const shown = props.visible && store.visible && !empty() && !failed() && !dialog.active
+    const cover = covered(rect)
+    if (shown && cover) freeze(tab.id)
+    if (!cover) thaw()
+    const visible = shown && !(cover && store.snapshot?.tabID === tab.id)
     // The cutout exposes the app backdrop outside the rounded Review card,
     // not the browser surface inside it.
     const color = getComputedStyle(
@@ -186,6 +234,9 @@ export function SessionBrowserPane(props: { browser: ReturnType<typeof createSes
   createEventListener(document, "visibilitychange", () => setStore("visible", document.visibilityState === "visible"))
   onCleanup(() => {
     if (frame !== undefined) cancelAnimationFrame(frame)
+    clearTimeout(release)
+    capturing = undefined
+    replaceSnapshot()
   })
 
   return (
@@ -296,7 +347,17 @@ export function SessionBrowserPane(props: { browser: ReturnType<typeof createSes
           {error()}
         </div>
       </Show>
-      <div ref={surface} class="min-h-0 flex-1 bg-v2-background-bg-base flex items-center justify-center">
+      <div ref={surface} class="relative min-h-0 flex-1 bg-v2-background-bg-base flex items-center justify-center">
+        <Show when={store.snapshot?.tabID === state()?.id && !empty() && !failed() && store.snapshot?.url}>
+          {(url) => (
+            <img
+              src={url()}
+              alt=""
+              draggable={false}
+              class="absolute inset-0 size-full pointer-events-none select-none"
+            />
+          )}
+        </Show>
         <Show when={(empty() || failed()) && !props.browser.suspended()}>
           {/* Add the 40px toolbar to the file empty state's 160px bottom padding to align their centers. */}
           <div

packages/app/src/session/composer/queue-panel.tsx

@@ -175,6 +175,18 @@ function SessionQueueRow(props: { queue: SessionQueueView; id: string; index: nu
                   {props.queue.working() ? language.t("session.queue.steer") : language.t("session.queue.send")}
                 </Button>
               </Tooltip>
+              <Tooltip placement="top" value={language.t("session.queue.undo")}>
+                <IconButton
+                  data-action="session-queue-undo"
+                  type="button"
+                  size="small"
+                  variant="ghost-muted"
+                  icon={<Icon name="arrow-down-to-line" />}
+                  disabled={props.queue.busy()}
+                  aria-label={language.t("session.queue.undo")}
+                  onClick={() => props.queue.undo(props.id)}
+                />
+              </Tooltip>
             </Show>
             <Tooltip placement="top" value={language.t("session.queue.remove")}>
               <IconButton

packages/app/src/session/composer/queue.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test"
 import type { SessionInboxInfo } from "@opencode/client/promise"
-import { queuedPromptAttachments, queuedPromptRows } from "./queue"
+import { queuedPromptAttachments, queuedPromptUndoDraft, queuedPromptRows } from "./queue"
 
 const queued = [
   {
@@ -104,3 +104,43 @@ describe("queuedPromptAttachments", () => {
     expect(queuedPromptAttachments(item)).toEqual([])
   })
 })
+
+describe("queuedPromptUndoDraft", () => {
+  test("keeps full text, structured mentions, and inline images", () => {
+    const item = {
+      ...queued[0],
+      payload: {
+        text: "inspect @main.ts with @build",
+        files: [
+          {
+            data: "aGk=",
+            mime: "text/plain",
+            source: { type: "uri" as const, uri: "file:///repo/main.ts" },
+            name: "main.ts",
+            mention: { start: 8, end: 16, text: "@main.ts" },
+          },
+          { data: "aGk=", mime: "image/png", source: { type: "inline" as const }, name: "shot.png" },
+        ],
+        agents: [{ name: "build", mention: { start: 22, end: 28, text: "@build" } }],
+      },
+    } satisfies SessionInboxInfo
+    expect(queuedPromptUndoDraft(item)).toMatchObject([
+      { type: "text", content: "inspect " },
+      { type: "file", content: "@main.ts", url: "data:text/plain;base64,aGk=" },
+      { type: "text", content: " with " },
+      { type: "agent", content: "@build", name: "build" },
+      { type: "image", filename: "shot.png" },
+    ])
+  })
+
+  test("does not drop hidden file context", () => {
+    const item = {
+      ...queued[0],
+      payload: {
+        text: "inspect this",
+        files: [{ data: "aGk=", mime: "text/plain", source: { type: "uri" as const, uri: "file:///repo/main.ts" } }],
+      },
+    } satisfies SessionInboxInfo
+    expect(queuedPromptUndoDraft(item)).toBeUndefined()
+  })
+})

packages/app/src/session/composer/queue.ts

@@ -3,10 +3,11 @@ import { createStore } from "solid-js/store"
 import { useMutation } from "@tanstack/solid-query"
 import type { SessionInboxInfo } from "@opencode/client/promise"
 import { SessionMessage } from "@opencode/schema/session-message"
+import { Skill } from "@opencode/schema/skill"
 import type { ComposerDelivery } from "@/composer/adapter"
 import type { ComposerStateTarget } from "@/composer/submission-state"
 import type { ImageAttachmentPart, PathAttachmentPart, Prompt } from "@/composer/state"
-import { clonePrompt, isAttachment, promptLength } from "@/composer/prompt-parts"
+import { appendPrompt, clonePrompt, isAttachment, promptLength } from "@/composer/prompt-parts"
 import { buildPromptRequest } from "@/composer/request"
 import { blobDataUrl, createLegacyBlobReference } from "@/runtime/persistence/drafts"
 import { readPromptPresentation } from "@/composer/comment-note"
@@ -42,6 +43,7 @@ export function createSessionQueue(input: {
     mutationFn: async (
       change:
         | { type: "reorder"; inboxIDs: string[] }
+        | { type: "undo"; item: QueuedPrompt; prompt: Prompt }
         | {
             type: "edit"
             inboxIDs: string[]
@@ -54,6 +56,16 @@ export function createSessionQueue(input: {
           },
     ) => {
       if (change.type === "reorder") return rewrite(change.inboxIDs)
+      if (change.type === "undo") {
+        await server.api.session.inbox.cancel({ sessionID: input.sessionID, inboxID: change.item.id })
+        const draft = input.draft.current()
+        const prompt = promptLength(draft)
+          ? appendPrompt(draft, change.prompt)
+          : [...change.prompt, ...draft.filter(isAttachment)]
+        input.draft.set(prompt, promptLength(prompt))
+        input.restoreFocus(promptLength(prompt))
+        return
+      }
       const replacement = await editedPromptInput(
         input.sessionID,
         location().directory,
@@ -139,6 +151,21 @@ export function createSessionQueue(input: {
     if (state.editing?.id === id) cancelEdit()
     return server.api.session.inbox.cancel({ sessionID: input.sessionID, inboxID: id }).catch(() => notify())
   }
+  const undo = (id: string) => {
+    if (mutation.isPending || state.editing) return
+    const item = queued().find((entry) => entry.id === id)
+    if (!item) return
+    if (input.draft.mode.current() !== "normal") {
+      showToast({ title: language.t("session.queue.undoShell") })
+      return
+    }
+    const prompt = queuedPromptUndoDraft(item)
+    if (!prompt) {
+      showToast({ title: language.t("session.queue.undoUnavailable") })
+      return
+    }
+    mutation.mutate({ type: "undo", item, prompt })
+  }
   const reorder = (inboxIDs: string[]) => {
     if (mutation.isPending) return Promise.resolve()
     return mutation.mutateAsync({ type: "reorder", inboxIDs }).catch(() => undefined)
@@ -226,9 +253,11 @@ export function createSessionQueue(input: {
     editFirst,
     rows,
     busy: () => mutation.isPending,
+    undoing: () => mutation.isPending && mutation.variables?.type === "undo",
     working: input.working,
     steer,
     remove,
+    undo,
     edit,
     reorder,
   }
@@ -239,7 +268,7 @@ export type SessionQueue = ReturnType<typeof createSessionQueue>
 // The slice of the queue the panel renders and drives.
 export type SessionQueueView = Pick<
   SessionQueue,
-  "rows" | "editing" | "working" | "busy" | "steer" | "remove" | "edit" | "reorder"
+  "rows" | "editing" | "working" | "busy" | "steer" | "remove" | "undo" | "edit" | "reorder"
 >
 
 export function queuedPromptRows(items: QueuedPrompt[], replacement?: { original: string; replacement: string }) {
@@ -249,7 +278,8 @@ export function queuedPromptRows(items: QueuedPrompt[], replacement?: { original
     .map((item) => ({
       id: item.id,
       text: queuedPromptText(item),
-      attachments: (item.payload.files?.length ?? 0) + (readPromptPresentation(item.payload.metadata)?.attachments.length ?? 0),
+      attachments:
+        (item.payload.files?.length ?? 0) + (readPromptPresentation(item.payload.metadata)?.attachments.length ?? 0),
     }))
 }
 
@@ -287,6 +317,88 @@ export function queuedPromptAttachments(item: QueuedPrompt): (ImageAttachmentPar
   ]
 }
 
+// Use the full model-visible text so comment notes and path references remain
+// in the draft. Convert mentioned files, agents, and skills back into editor
+// parts; a detached draft cannot represent non-mentioned file context.
+export function queuedPromptUndoDraft(item: QueuedPrompt): Prompt | undefined {
+  if (
+    item.payload.files?.some((file) => !isComposerAttachment(file) && !file.mention) ||
+    item.payload.agents?.some((agent) => !agent.mention) ||
+    item.payload.skills?.some((skill) => !skill.mention)
+  )
+    return
+  const text = item.payload.text
+  const references = [
+    ...(item.payload.files ?? []).flatMap((file) =>
+      file.mention
+        ? [
+            {
+              type: "file" as const,
+              content: file.mention.text,
+              start: file.mention.start,
+              end: file.mention.end,
+              path: file.name ?? file.mention.text.replace(/^@/, ""),
+              filename: file.name,
+              mime: file.mime,
+              url: `data:${file.mime};base64,${file.data}`,
+            },
+          ]
+        : [],
+    ),
+    ...(item.payload.agents ?? []).flatMap((agent) =>
+      agent.mention
+        ? [
+            {
+              type: "agent" as const,
+              content: agent.mention.text,
+              start: agent.mention.start,
+              end: agent.mention.end,
+              name: agent.name,
+            },
+          ]
+        : [],
+    ),
+    ...(item.payload.skills ?? []).flatMap((skill) =>
+      skill.mention
+        ? [
+            {
+              type: "skill" as const,
+              content: skill.mention.text,
+              start: skill.mention.start,
+              end: skill.mention.end,
+              id: Skill.ID.make(skill.id),
+              name: Skill.Name.make(skill.name),
+            },
+          ]
+        : [],
+    ),
+  ].sort((left, right) => left.start - right.start)
+  if (
+    references.some(
+      (part, index) =>
+        part.start < (references[index - 1]?.end ?? 0) || text.slice(part.start, part.end) !== part.content,
+    )
+  )
+    return
+  const parts: Prompt = references.flatMap((part, index) => {
+    const start = references[index - 1]?.end ?? 0
+    return [
+      ...(part.start > start
+        ? [{ type: "text" as const, content: text.slice(start, part.start), start, end: part.start }]
+        : []),
+      part,
+    ]
+  })
+  const start = references.at(-1)?.end ?? 0
+  return [
+    ...parts,
+    ...(text.length > start || !parts.length
+      ? [{ type: "text" as const, content: text.slice(start), start, end: text.length }]
+      : []),
+    ...queuedPromptAttachments(item).filter((part) => part.type === "image"),
+  ]
+}
+
 function isComposerAttachment(file: NonNullable<QueuedPrompt["payload"]["files"]>[number]) {
   return !file.mention && file.source.type === "inline"
 }

packages/app/src/session/composer/region.tsx

@@ -224,7 +224,12 @@ export function ActiveSessionComposerRegion(props: {
         <div class="relative">
           <SessionQueuePanel queue={props.model.queue} />
           <div class="relative z-10">
-            <Composer model={props.model.composer} borderUnderlay suggestionBoundary={props.suggestionBoundary} />
+            <Composer
+              model={props.model.composer}
+              borderUnderlay
+              readOnly={props.model.queue.undoing()}
+              suggestionBoundary={props.suggestionBoundary}
+            />
           </div>
         </div>
       }

packages/app/src/session/screen.tsx

@@ -14,7 +14,6 @@ import { createStore } from "solid-js/store"
 import { ResizeHandle } from "@opencode/ui/resize-handle"
 import { MessageTimeline } from "@/session/timeline/message-timeline"
 import { useServer } from "@/runtime/server/current"
-import { projectForSession } from "@/shell/layout/helpers"
 import { ComposerDropzone } from "@/composer/dropzone"
 import type { SessionModel } from "@/session/model"
 import { SESSION_PANEL_WIDTH_MIN } from "@/session/session-panel-width"
@@ -66,7 +65,7 @@ function SessionScreenContent(props: { session: SessionModel; browser: ReturnTyp
   const server = useServer()
   const detailsProject = createMemo(() => {
     const info = session.data.info()
-    return info ? projectForSession(info, server.ctx.sync.data.project) : undefined
+    return info ? server.ctx.projects.detailsForSession(info) : undefined
   })
   const isDesktop = session.isDesktop
   const btw = createSessionBtw(session)

packages/app/src/session/session-identity-header.tsx

@@ -12,7 +12,7 @@ import { useServer } from "@/runtime/server/current"
 import { ServerConnection } from "@/runtime/server/registry"
 import { useLanguage } from "@/runtime/i18n/language"
 import { usePlatform } from "@/runtime/platform/platform"
-import { displayName, errorMessage, getProjectAvatarSource, projectForSession } from "@/shell/layout/helpers"
+import { displayName, errorMessage, getProjectAvatarSource } from "@/shell/layout/helpers"
 import { getProjectAvatarVariant, useLayout, type LocalProject } from "@/shell/state/layout"
 import { tabKey, useTabs } from "@/shell/tabs/tabs"
 import { useSettingsSurface } from "@/settings/surface"
@@ -319,11 +319,8 @@ export function SessionIdentityHeader(props: { sessionID: string; session?: Sess
       : sessionTitle(props.session?.title ?? (parentID() ? undefined : info()?.title)),
   )
   const project = createMemo(() => {
+    if (props.session) return server.ctx.projects.forSession(props.session)
     const projects = server.ctx.projects.list()
-    if (props.session)
-      return (
-        projectForSession(props.session, projects) ?? projectForSession(props.session, server.ctx.sync.data.project)
-      )
     const value = directory()
     if (!value) return undefined
     const key = pathKey(value)

packages/app/src/session/summary/panel.tsx

@@ -1,7 +1,7 @@
 import { DiffChanges } from "@opencode/ui/diff-changes"
 import { Icon } from "@opencode/ui/icon"
 import { getFilename } from "@opencode/util/path"
-import { createMemo, Show, type JSX } from "solid-js"
+import { createMemo, Show } from "solid-js"
 import { useLanguage } from "@/runtime/i18n/language"
 import type { Project } from "@/runtime/server/types"
 import { useSettings } from "@/settings/model"
@@ -16,7 +16,6 @@ export function SessionSummaryPanel(props: {
   shown?: boolean
   mobile?: boolean
   project: Project
-  avatar?: JSX.Element
   directory: string
   local: boolean
   branch?: string
@@ -44,7 +43,7 @@ export function SessionSummaryPanel(props: {
   return (
     <div data-component="session-summary-panel" data-mobile={props.mobile || undefined}>
       <div>
-        <ProjectSummaryCard project={props.project} avatar={props.avatar}>
+        <ProjectSummaryCard project={props.project}>
           <SessionWorkspaceMenu
             eligible={props.moveEligible}
             sessionID={props.sessionID}

packages/app/src/session/summary/project-card.tsx

@@ -1,16 +1,14 @@
 import { Icon } from "@opencode/ui/icon"
-import { ProjectAvatar } from "@opencode/ui/project-avatar"
-import { createUniqueId, Show, type ParentProps, type JSX } from "solid-js"
+import { createUniqueId, Show, type ParentProps } from "solid-js"
 import type { Project } from "@/runtime/server/types"
 import { useSettings } from "@/settings/model"
-import { displayName, getProjectAvatarSource } from "@/shell/layout/helpers"
-import { getProjectAvatarVariant } from "@/shell/state/layout"
+import { displayName } from "@/shell/layout/helpers"
+import { ProjectIcon } from "@/shell/layout/project-icon"
 import "./summary.css"
 
 export function ProjectSummaryCard(
   props: ParentProps<{
     project: Pick<Project, "name" | "worktree" | "icon"> & { id?: string }
-    avatar?: JSX.Element
   }>,
 ) {
   const settings = useSettings()
@@ -26,13 +24,7 @@ export function ProjectSummaryCard(
         aria-controls={contentID}
         onClick={() => settings.sessionSummary.setProjectExpanded(!expanded())}
       >
-        {props.avatar ?? (
-          <ProjectAvatar
-            fallback={displayName(props.project)}
-            src={getProjectAvatarSource(props.project.id, props.project.icon)}
-            variant={getProjectAvatarVariant(props.project.icon?.color)}
-          />
-        )}
+        <ProjectIcon project={props.project} />
         <span dir="auto" class="session-summary-label">
           {displayName(props.project)}
         </span>

packages/app/src/session/timeline/message-timeline.tsx

@@ -31,7 +31,6 @@ import { getReadyMarkdown, preloadMarkdown } from "@opencode/session-ui/markdown
 import { createTimelineController, type TimelineController, type TimelineSessionSource } from "./controller"
 import { createTimelineVirtualizer } from "./virtualizer"
 import { containsDirectory, isWorkspaceDirectory } from "@/workspaces/paths"
-import { projectForSession } from "@/shell/layout/helpers"
 import { parseCommentNote, readPromptPresentation } from "@/composer/comment-note"
 import { useCommand } from "@/shell/commands/command"
 import { SessionAncestorTrail, SessionProjectMenu, SessionTitleHeader } from "../session-identity-header"
@@ -143,14 +142,14 @@ function MessageTimelineView(
     const session = props.session.data.info()
     const projects = server.ctx.sync.data.project
     return session
-      ? projectForSession(session, projects)
+      ? server.ctx.projects.detailsForSession(session)
       : projects.find((item) => containsDirectory(item.worktree, sessionDirectory()))
   })
   const workspaceSession = createMemo(() => isWorkspaceDirectory(project(), sessionDirectory()))
-  const avatarProject = createMemo(() => {
+  const headerProject = createMemo(() => {
     const session = props.session.data.info()
     if (!session) return
-    return projectForSession(session, server.ctx.projects.list()) ?? project()
+    return server.ctx.projects.forSession(session)
   })
   createEffect(() => {
     const directory = project()?.worktree
@@ -408,7 +407,7 @@ function MessageTimelineView(
               <div class="flex items-center gap-1 min-w-0 flex-1">
                 <div class="flex items-center gap-0.5 min-w-0 flex-1 w-full">
                   <SessionProjectMenu
-                    project={avatarProject()}
+                    project={headerProject()}
                     directory={sessionDirectory()}
                     workspace={workspaceSession()}
                   />

packages/app/src/settings/providers/accounts.test.ts

@@ -0,0 +1,34 @@
+import { describe, expect, test } from "bun:test"
+import type { IntegrationInfo } from "@opencode/client/promise"
+import { activeProviderAccount, providerAccounts } from "./accounts"
+
+const integration = (connections: IntegrationInfo["connections"]): IntegrationInfo => ({
+  id: "openai",
+  name: "OpenAI",
+  methods: [],
+  connections,
+})
+
+describe("provider accounts", () => {
+  test("preserves the server's active-first credential order", () => {
+    const value = integration([
+      { type: "credential", id: "cred_work", label: "Work", method: "key" },
+      { type: "env", name: "OPENAI_API_KEY" },
+      { type: "credential", id: "cred_personal", label: "Personal", method: "oauth" },
+    ])
+
+    expect(providerAccounts(value)).toEqual([
+      { type: "credential", id: "cred_work", label: "Work", method: "key" },
+      { type: "credential", id: "cred_personal", label: "Personal", method: "oauth" },
+    ])
+    expect(activeProviderAccount(value)).toEqual({ type: "credential", id: "cred_work", label: "Work", method: "key" })
+  })
+
+  test("returns no active account for environment-only integrations", () => {
+    const value = integration([{ type: "env", name: "OPENAI_API_KEY" }])
+
+    expect(providerAccounts(value)).toEqual([])
+    expect(activeProviderAccount(value)).toBeUndefined()
+    expect(providerAccounts(undefined)).toEqual([])
+  })
+})

packages/app/src/settings/providers/accounts.ts

@@ -0,0 +1,11 @@
+import type { ConnectionInfo, IntegrationInfo } from "@opencode/client/promise"
+
+export type ProviderAccount = Extract<ConnectionInfo, { type: "credential" }>
+
+export function providerAccounts(integration: IntegrationInfo | undefined) {
+  return integration?.connections.filter((connection): connection is ProviderAccount => connection.type === "credential") ?? []
+}
+
+export function activeProviderAccount(integration: IntegrationInfo | undefined) {
+  return providerAccounts(integration)[0]
+}

packages/app/src/settings/providers/providers.tsx

@@ -2,6 +2,7 @@ import { Button } from "@opencode/ui/button"
 import { Badge } from "@opencode/ui/badge"
 import { useDialog } from "@opencode/ui/context/dialog"
 import { Icon } from "@opencode/ui/icon"
+import { Menu } from "@opencode/ui/menu"
 import { OpenCodeLogo } from "@/providers/opencode-logo"
 import { showToast } from "@/shell/notifications/toast"
 import { popularProviders, useProviders } from "@/providers/catalog/providers"
@@ -16,6 +17,7 @@ import { CONSOLE_INTEGRATION, CONSOLE_PROVIDERS } from "@/providers/connect/cont
 import { DialogConnectProvider, useProviderConnectController } from "@/providers/connect/dialog"
 import { ProviderModelIcon } from "@/providers/models/provider-group"
 import { SettingsList } from "@/settings/list"
+import { activeProviderAccount, providerAccounts, type ProviderAccount } from "./accounts"
 import "@/settings/settings.css"
 
 type ProviderSource = "env" | "api" | "account" | "config" | "custom"
@@ -47,6 +49,7 @@ export const SettingsProviders: Component<{
     disconnecting: {} as Record<string, "removing" | "removed" | "absent" | undefined>,
     consoleExpanded: false,
     connecting: false,
+    credentialID: undefined as string | undefined,
   })
   const updateDisconnecting = (ids: string[], status: "removing" | "removed" | "absent" | undefined) =>
     setState("disconnecting", (current) => ({
@@ -190,6 +193,8 @@ export const SettingsProviders: Component<{
     return currentSource !== "env" && currentSource !== "config"
   }
 
+  const canManageAccounts = (item: ProviderItem) => providerAccounts(integration(item)).length > 0
+
   const note = (id: string) => PROVIDER_NOTES.find((item) => item.match(id))?.key
 
   const disconnect = async (item: ProviderItem, name: string) => {
@@ -230,6 +235,132 @@ export const SettingsProviders: Component<{
       })
   }
 
+  const refreshAccounts = async () => {
+    const location = props.directory ? { directory: props.directory } : undefined
+    data.location.integration.invalidate(location)
+    data.location.provider.invalidate(location)
+    data.location.model.invalidate(location)
+    await Promise.all([
+      data.location.integration.sync(location),
+      data.location.provider.sync(location),
+      data.location.model.sync(location),
+    ])
+  }
+
+  const accountError = (error: unknown) => {
+    const message = error instanceof Error ? error.message : String(error)
+    showToast({ title: language.t("common.requestFailed"), description: message })
+  }
+
+  const activate = async (provider: ProviderItem, providerName: string, account: ProviderAccount) => {
+    if (activeProviderAccount(integration(provider))?.id === account.id) return
+    setState("credentialID", account.id)
+    await serverSdk.api.credential
+      .activate({ credentialID: account.id })
+      .then(refreshAccounts)
+      .then(() =>
+        showToast({
+          variant: "success",
+          icon: "circle-check",
+          title: language.t("settings.providers.account.switched.title", { provider: providerName }),
+          description: language.t("settings.providers.account.switched.description", { account: account.label }),
+        }),
+      )
+      .catch(accountError)
+      .finally(() => setState("credentialID", undefined))
+  }
+
+  const remove = async (provider: ProviderItem, providerName: string, account: ProviderAccount) => {
+    const final = providerAccounts(integration(provider)).length === 1
+    setState("credentialID", account.id)
+    await serverSdk.api.credential
+      .remove({ credentialID: account.id })
+      .then(refreshAccounts)
+      .then(() =>
+        showToast({
+          variant: "success",
+          icon: "circle-check",
+          title: language.t(
+            final ? "provider.disconnect.toast.disconnected.title" : "settings.providers.account.removed.title",
+            final ? { provider: providerName } : { account: account.label },
+          ),
+          description: language.t(
+            final
+              ? "provider.disconnect.toast.disconnected.description"
+              : "settings.providers.account.removed.description",
+            { provider: providerName },
+          ),
+        }),
+      )
+      .catch(accountError)
+      .finally(() => setState("credentialID", undefined))
+  }
+
+  function AccountMenu(menuProps: { provider: ProviderItem; name?: string }) {
+    const accounts = () => providerAccounts(integration(menuProps.provider))
+    const active = () => activeProviderAccount(integration(menuProps.provider))
+    const name = () => menuProps.name ?? menuProps.provider.name
+
+    return (
+      <Menu placement="bottom-end" gutter={6}>
+        <Menu.Trigger
+          as={Button}
+          size="normal"
+          variant="ghost-muted"
+          class="settings-provider-account-trigger"
+          aria-label={language.t("settings.providers.account.manage", { provider: name() })}
+        >
+          <span>{active()?.label}</span>
+          <Icon name="chevron-down" size="small" />
+        </Menu.Trigger>
+        <Menu.Portal>
+          <Menu.Content class="settings-provider-account-menu" onEscapeKeyDown={(event) => event.stopPropagation()}>
+            <Menu.Group>
+              <Menu.GroupLabel>{language.t("settings.providers.account.group")}</Menu.GroupLabel>
+              <Menu.RadioGroup
+                class="settings-provider-account-list"
+                value={active()?.id}
+                onChange={(credentialID) => {
+                  const account = accounts().find((item) => item.id === credentialID)
+                  if (account) void activate(menuProps.provider, name(), account)
+                }}
+              >
+                <For each={accounts()}>
+                  {(account) => (
+                    <Menu.RadioItem value={account.id} closeOnSelect disabled={state.credentialID !== undefined}>
+                      <span class="settings-provider-account-label">{account.label}</span>
+                    </Menu.RadioItem>
+                  )}
+                </For>
+              </Menu.RadioGroup>
+            </Menu.Group>
+            <Menu.Separator />
+            <Menu.Item disabled={state.credentialID !== undefined} onSelect={() => connect(menuProps.provider.id)}>
+              {language.t("settings.providers.account.add")}
+            </Menu.Item>
+            <Menu.Sub placement="left-start">
+              <Menu.SubTrigger disabled={state.credentialID !== undefined || accounts().length === 0}>
+                {language.t("settings.providers.account.remove")}
+              </Menu.SubTrigger>
+              <Menu.SubContent class="settings-provider-account-submenu">
+                <For each={accounts()}>
+                  {(account) => (
+                    <Menu.Item
+                      badge={account.id === active()?.id ? language.t("settings.providers.account.active") : undefined}
+                      onSelect={() => void remove(menuProps.provider, name(), account)}
+                    >
+                      <span class="settings-provider-account-label">{account.label}</span>
+                    </Menu.Item>
+                  )}
+                </For>
+              </Menu.SubContent>
+            </Menu.Sub>
+          </Menu.Content>
+        </Menu.Portal>
+      </Menu>
+    )
+  }
+
   return (
     <>
       <div class="settings-tab-header">
@@ -268,22 +399,27 @@ export const SettingsProviders: Component<{
                             </div>
                           </div>
                           <Show
-                            when={canDisconnect(item)}
+                            when={canManageAccounts(item)}
                             fallback={
-                              <span class="settings-provider-env-hint">
-                                {language.t("settings.providers.connected.environmentDescription")}
-                              </span>
+                              <Show
+                                when={canDisconnect(item)}
+                                fallback={
+                                  <span class="settings-provider-env-hint">
+                                    {language.t("settings.providers.connected.environmentDescription")}
+                                  </span>
+                                }
+                              >
+                                <Button
+                                  size="normal"
+                                  variant="ghost-muted"
+                                  onClick={() => void disconnect(item, item.name)}
+                                >
+                                  {language.t("common.disconnect")}
+                                </Button>
+                              </Show>
                             }
                           >
-                            <Button
-                              size="normal"
-                              variant="ghost-muted"
-                              onClick={() =>
-                                void disconnect(item, item.name)
-                              }
-                            >
-                              {language.t("common.disconnect")}
-                            </Button>
+                            <AccountMenu provider={item} />
                           </Show>
                         </div>
                       }
@@ -326,13 +462,20 @@ export const SettingsProviders: Component<{
                                 </Show>
                               </div>
                             </div>
-                            <Button
-                              size="normal"
-                              variant="ghost-muted"
-                              onClick={() => void disconnect(item, language.t("provider.connect.opencode.name"))}
+                            <Show
+                              when={canManageAccounts(item)}
+                              fallback={
+                                <Button
+                                  size="normal"
+                                  variant="ghost-muted"
+                                  onClick={() => void disconnect(item, language.t("provider.connect.opencode.name"))}
+                                >
+                                  {language.t("common.disconnect")}
+                                </Button>
+                              }
                             >
-                              {language.t("common.disconnect")}
-                            </Button>
+                              <AccountMenu provider={item} name={language.t("provider.connect.opencode.name")} />
+                            </Show>
                           </div>
                           <Show when={state.consoleExpanded}>
                             <div class="settings-provider-console-list">

packages/app/src/settings/settings.css

@@ -887,6 +887,47 @@
   opacity: 1;
 }
 
+.settings-provider-account-trigger {
+  min-width: 0;
+  max-width: min(240px, 45%);
+}
+
+.settings-provider-account-trigger > span {
+  min-width: 0;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+
+.settings-provider-account-menu[data-component="menu-v2-content"] {
+  width: min(260px, calc(100vw - 32px));
+  overflow: visible;
+}
+
+.settings-provider-account-list {
+  max-height: min(240px, calc(var(--kb-popper-content-available-height) - 120px));
+  overflow-y: auto;
+}
+
+.settings-provider-account-submenu[data-component="menu-v2-content"] {
+  width: min(260px, calc(100vw - 32px));
+  max-height: min(360px, var(--kb-popper-content-available-height));
+  overflow-y: auto;
+}
+
+.settings-provider-account-label {
+  min-width: 0;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+
+@container settings-panel (max-width: 520px) {
+  .settings-provider-account-trigger {
+    max-width: 100%;
+  }
+}
+
 .settings-providers-view-all {
   margin-top: 20px;
   padding: 0;

packages/app/src/shell/commands/palette.ts

@@ -11,7 +11,7 @@ import { useLayout, type LocalProject } from "@/shell/state/layout"
 import { ServerConnection } from "@/runtime/server/registry"
 import { useServerSDK } from "@/runtime/server/client"
 import { useTabs } from "@/shell/tabs/tabs"
-import { displayName, projectForSession } from "@/shell/layout/helpers"
+import { displayName, resolveProjectForSession } from "@/shell/layout/helpers"
 import { createSessionTabs } from "@/session/helpers"
 import { useSessionLayout } from "@/session/session-layout"
 import { useServer } from "@/runtime/server/current"
@@ -253,9 +253,7 @@ export function createServerSessionEntries(props: {
     })
     if (current.signal.aborted) return []
     const opened = props.opened()
-    const openedByID = new Map(opened.flatMap((project) => (project.id ? [[project.id, project] as const] : [])))
     const stored = props.stored().map((project) => ({ ...project, expanded: false }))
-    const storedByID = new Map(stored.map((project) => [project.id, project] as const))
     return Promise.all([
       props.load(search, current.signal).then(
         (result) => result.data,
@@ -271,8 +269,7 @@ export function createServerSessionEntries(props: {
       [...new Map([...exact, ...listed].map((session) => [session.id, session] as const)).values()]
         .filter((session) => !session.time.archived)
         .map((session) => {
-          const project =
-            projectForSession(session, opened, openedByID) ?? projectForSession(session, stored, storedByID)
+          const project = resolveProjectForSession(session, opened, stored)
           return {
             id: `session:${props.server}:${session.id}`,
             type: "session" as const,

packages/app/src/shell/layout/helpers.ts

@@ -50,6 +50,17 @@ export const childSessionOnPath = (sessions: SessionInfo[] | undefined, rootID:
 export const displayName = (project: { name?: string; worktree: string }) =>
   project.name || getFilename(project.worktree) || project.worktree
 
+type ProjectAppearance = {
+  name?: string
+  worktree: string
+  icon?: { color?: string; url?: string; override?: string }
+}
+
+function withProjectAppearance<T extends ProjectAppearance>(metadata: T, appearance?: ProjectAppearance) {
+  if (!appearance || appearance === metadata) return metadata
+  return { ...metadata, name: displayName(appearance), icon: appearance.icon }
+}
+
 export function toggleHomeProjectSelection(
   current: HomeProjectSelection | undefined,
   server: ServerConnection.Key,
@@ -97,11 +108,59 @@ export function getProjectAvatarSource(id?: string, icon?: { color?: string; url
 export function projectForSession<T extends { id?: string; worktree: string; sandboxes?: string[] }>(
   session: SessionInfo,
   projects: T[],
-  byID: Map<string, T> = new Map(projects.flatMap((project) => (project.id ? [[project.id, project] as const] : []))),
 ) {
-  const direct = byID.get(session.projectID)
-  if (direct) return direct
-  return projects.find((project) => isProjectDirectory(project, session.location.directory))
+  const matching = projects.filter((project) => project.id === session.projectID)
+  if (matching.length === 1) return matching[0]
+  if (matching.length > 1) {
+    const directory = pathKey(session.location.directory)
+    const exact =
+      matching.find((project) => pathKey(project.worktree) === directory) ??
+      matching.find((project) => project.sandboxes?.some((sandbox) => pathKey(sandbox) === directory))
+    if (exact) return exact
+    return (
+      matching
+        .filter((project) => isProjectDirectory(project, session.location.directory))
+        .sort((a, b) => b.worktree.length - a.worktree.length)[0] ?? matching.at(-1)
+    )
+  }
+  const directory = pathKey(session.location.directory)
+  const exact =
+    projects.find((project) => pathKey(project.worktree) === directory) ??
+    projects.find((project) => project.sandboxes?.some((sandbox) => pathKey(sandbox) === directory))
+  if (exact) return exact
+  return projects
+    .filter((project) => isProjectDirectory(project, session.location.directory))
+    .sort((a, b) => b.worktree.length - a.worktree.length)[0]
+}
+
+export function resolveProjectForSession<
+  T extends { id?: string; worktree: string; sandboxes?: string[] },
+  U extends { id?: string; worktree: string; sandboxes?: string[] },
+>(session: SessionInfo, opened: T[], stored: U[]) {
+  const current = projectForSession(session, opened)
+  if (current?.id === session.projectID) {
+    const unresolved = opened.find(
+      (project) => !project.id && pathKey(project.worktree) === pathKey(session.location.directory),
+    )
+    if (!unresolved) return current
+    const canonical = projectForSession(session, stored)
+    if (canonical?.id === session.projectID && pathKey(canonical.worktree) === pathKey(unresolved.worktree))
+      return unresolved
+    return current
+  }
+  const synced = projectForSession(session, stored)
+  if (synced?.id !== session.projectID) return current ?? synced
+  if (current && !current.id && pathKey(current.worktree) === pathKey(session.location.directory)) return current
+  return synced
+}
+
+export function resolveSessionDetailsProject<
+  T extends ProjectAppearance & { id?: string; sandboxes?: string[] },
+  U extends ProjectAppearance & { id?: string; sandboxes?: string[] },
+>(session: SessionInfo, opened: T[], stored: U[]) {
+  const metadata = projectForSession(session, stored)
+  if (!metadata) return
+  return withProjectAppearance(metadata, resolveProjectForSession(session, opened, stored))
 }
 
 export const errorMessage = (err: unknown, fallback: string) => {

packages/app/src/shell/layout/project-icon.tsx

@@ -4,7 +4,7 @@ import { displayName, getProjectAvatarSource } from "@/shell/layout/helpers"
 import { getProjectAvatarVariant, type LocalProject } from "@/shell/state/layout"
 
 type ProjectIconProps = Omit<ProjectAvatarProps, "fallback" | "src" | "variant"> & {
-  project: LocalProject
+  project: Pick<LocalProject, "id" | "name" | "worktree" | "icon">
   fallback?: string
   icon?: LocalProject["icon"]
 }

packages/app/src/shell/titlebar/tab-nav.tsx

@@ -9,7 +9,7 @@ import { Menu } from "@opencode/ui/menu"
 import { useGlobal, useServerCtx } from "@/runtime/server/runtime"
 import { useLanguage } from "@/runtime/i18n/language"
 import { ServerConnection, serverName, useServers } from "@/runtime/server/registry"
-import { displayName, projectForSession } from "@/shell/layout/helpers"
+import { displayName } from "@/shell/layout/helpers"
 import { SessionTabAvatar } from "@/shell/layout/session-tab-avatar"
 import { SessionProgressIndicatorV2 } from "@opencode/session-ui/v2/session-progress-indicator-v2"
 import type { SessionInfo } from "@opencode/client/promise"
@@ -57,7 +57,7 @@ export function TabNavItem(props: {
   const project = createMemo(() => {
     const session = props.session
     if (!session) return
-    return projectForSession(session, serverCtx()?.projects.list() ?? [])
+    return serverCtx()?.projects.forSession(session)
   })
   const title = createMemo(() => {
     const session = props.session

packages/app/src/shell/titlebar/titlebar.tsx

@@ -29,7 +29,6 @@ import { MobileDrawer, MobileDrawerContent, MobileDrawerLabel, MobileDrawerTrigg
 import { sessionTabTitle } from "./tab-title"
 import { SessionTabAvatar } from "@/shell/layout/session-tab-avatar"
 import { SessionProgressIndicatorV2 } from "@opencode/session-ui/v2/session-progress-indicator-v2"
-import { projectForSession } from "@/shell/layout/helpers"
 import { useSettingsDialog } from "@/settings/command"
 import { updaterAction } from "@/shell/updates/action"
 import type { UpdaterState } from "@/shell/updates/types"
@@ -441,7 +440,7 @@ export function Titlebar(props: {
               const value = session()
               if (!tab || !value) return
               const conn = global.servers.list().find((item) => ServerConnection.key(item) === tab.server)
-              return projectForSession(value, conn ? global.ensureServerCtx(conn).projects.list() : [])
+              return conn ? global.ensureServerCtx(conn).projects.forSession(value) : undefined
             })
             const currentTitle = () => {
               const tab = currentTab()

packages/cli/package.json

@@ -21,7 +21,7 @@
     "build:node": "bun run script/build-node.ts",
     "dev": "bun run src/index.ts",
     "test": "bun test --timeout 30000 --only-failures",
-    "typecheck": "tsgo --noEmit"
+    "typecheck": "tsgo -b"
   },
   "dependencies": {
     "@agentclientprotocol/sdk": "1.2.1",

packages/cli/tsconfig.json

@@ -7,5 +7,6 @@
     "lib": ["ESNext", "DOM", "DOM.Iterable", "DOM.AsyncIterable"],
     "noUncheckedIndexedAccess": false
   },
-  "exclude": ["dist", "dist-node"]
+  "exclude": ["dist", "dist-node"],
+  "references": [{ "path": "../core" }]
 }