refactor(core): use Effect config for diagnostics

feat(core): gate prompt diagnostics by flag
test(core): assert prompt cache prefix stability
2026-07-27 13:41:34 -04:00 · 2026-07-27 13:26:33 -04:00 · 2026-07-27 12:21:07 -04:00 · 2026-07-27 12:18:17 -04:00 · 2026-07-27 12:18:17 -04:00 · 2026-07-27 12:18:17 -04:00
753 changed files with 54934 additions and 97040 deletions
@@ -1,7 +0,0 @@
---
-"@opencode-ai/client": patch
-"@opencode-ai/protocol": patch
-"@opencode-ai/cli": patch
---
-
-Expose background-service lifecycle status, preserve one process-held owner through startup and failure, reconnect TUIs without activating replacement, and stop exact service instances gracefully.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/cli": patch
---
-
-Expose a TUI plugin slot at the top of the session view.
@@ -1,8 +0,0 @@
---
-"@opencode-ai/plugin": minor
-"@opencode-ai/sdk": minor
-"@opencode-ai/client": minor
-"@opencode-ai/protocol": minor
---
-
-Replace the V2 tool result model with one canonical representation per fact. Tools lose `structured`, projection callbacks, the `Structured` generic, and the exported `Tool.settle` interpreter; tool responses carry schema-validated `output`, model-visible `content`, and optional compact JSON `metadata`. Code Mode receives the validated encoded output. Durable tool success stores non-empty model content plus optional metadata; failure stores one error plus the final bounded partial snapshot. Progress carries metadata only, while `execute.after` hooks receive the canonical terminal outcome and managed `outputPaths`. A one-time migration rewrites existing projected tool rows and moves provider-hosted result payloads into provider-owned result state.
@@ -1,7 +0,0 @@
---
-"@opencode-ai/client": patch
-"@opencode-ai/plugin": patch
-"@opencode-ai/protocol": patch
---
-
-Expose transient, read-only session generation through the HTTP API, generated clients, and V2 plugin session context.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/cli": patch
---
-
-Expose a TUI plugin slot above the session composer.
@@ -0,0 +1,37 @@
+name: deploy-www
+
+on:
+  push:
+    branches:
+      - dev
+      - v2
+  workflow_dispatch:
+
+concurrency:
+  group: deploy-www-${{ github.ref_name }}
+  cancel-in-progress: false
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+    if: github.repository == 'anomalyco/opencode' && (github.ref_name == 'dev' || github.ref_name == 'v2')
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@f43a0e5ff2bd294095638e18286ca9a3d1956744 # v3.6.0
+
+      - uses: ./.github/actions/setup-bun
+
+      - name: Build
+        working-directory: packages/www
+        run: bun run build
+        env:
+          BLUME_ENV: ${{ github.ref_name == 'v2' && 'production' || 'dev' }}
+          CLOUDFLARE_ENV: ${{ github.ref_name == 'v2' && 'production' || 'dev' }}
+
+      - name: Deploy
+        working-directory: packages/www
+        run: bun run deploy
+        env:
+          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
@@ -99,7 +99,7 @@ jobs:

      - name: Check generated documentation
        if: runner.os == 'Linux'
-        working-directory: packages/docs
+        working-directory: packages/www
        run: bun run check:generated

  e2e:
@@ -1,4 +1,3 @@
- To regenerate the legacy JavaScript SDK, run `./packages/sdk/js/script/build.ts`.
 - After changing the public Protocol or Server `HttpApi`, run `bun run generate` from `packages/client`. Do not edit `src/generated` or `src/generated-effect` directly.
 - Keep runtime dependencies directed from Schema to Core and Protocol, then from Core and Protocol to Server. Client runtime code may depend on Schema and Protocol but never Core or Server; `sdk-next` composes Client, Core, and Server.
 - Do not modify `packages/opencode` unless the user explicitly asks for V1 work. `packages/opencode` is the V1 implementation and is present for reference only. New implementation changes should land in the V2 package set: `packages/core`, `packages/cli`, `packages/server`, `packages/protocol`, `packages/schema`, and related generated client surfaces when required.
@@ -2,7 +2,7 @@
 exact = true
 # Only install newly resolved package versions published at least 3 days ago.
 minimumReleaseAge = 259200
-minimumReleaseAgeExcludes = ["@ai-sdk/amazon-bedrock", "@ai-sdk/anthropic", "@opentui/core", "@opentui/core-darwin-arm64", "@opentui/core-darwin-x64", "@opentui/core-linux-arm64", "@opentui/core-linux-arm64-musl", "@opentui/core-linux-x64", "@opentui/core-linux-x64-musl", "@opentui/core-win32-arm64", "@opentui/core-win32-x64", "@opentui/keymap", "@opentui/solid", "opentui-spinner", "gitlab-ai-provider", "opencode-gitlab-auth", "@ff-labs/fff-node", "@ff-labs/fff-bun", "@ff-labs/fff-bin-darwin-arm64", "@ff-labs/fff-bin-darwin-x64", "@ff-labs/fff-bin-linux-arm64-gnu", "@ff-labs/fff-bin-linux-arm64-musl", "@ff-labs/fff-bin-linux-x64-gnu", "@ff-labs/fff-bin-linux-x64-musl", "@ff-labs/fff-bin-win32-arm64", "@ff-labs/fff-bin-win32-x64", "@pierre/diffs", "@pierre/theming", "app-builder-lib", "dmg-builder", "electron-builder", "electron-publish"]
+minimumReleaseAgeExcludes = ["@ai-sdk/amazon-bedrock", "@ai-sdk/anthropic", "@opencode-ai/sdk", "@opentui/core", "@opentui/core-darwin-arm64", "@opentui/core-darwin-x64", "@opentui/core-linux-arm64", "@opentui/core-linux-arm64-musl", "@opentui/core-linux-x64", "@opentui/core-linux-x64-musl", "@opentui/core-win32-arm64", "@opentui/core-win32-x64", "@opentui/keymap", "@opentui/solid", "opentui-spinner", "gitlab-ai-provider", "opencode-gitlab-auth", "@ff-labs/fff-node", "@ff-labs/fff-bun", "@ff-labs/fff-bin-darwin-arm64", "@ff-labs/fff-bin-darwin-x64", "@ff-labs/fff-bin-linux-arm64-gnu", "@ff-labs/fff-bin-linux-arm64-musl", "@ff-labs/fff-bin-linux-x64-gnu", "@ff-labs/fff-bin-linux-x64-musl", "@ff-labs/fff-bin-win32-arm64", "@ff-labs/fff-bin-win32-x64", "@pierre/diffs", "@pierre/theming", "app-builder-lib", "dmg-builder", "electron-builder", "electron-publish"]

 [test]
 root = "./do-not-run-tests-from-root"
@@ -15,6 +15,6 @@
    "@actions/github": "6.0.1",
    "@octokit/graphql": "9.0.1",
    "@octokit/rest": "catalog:",
-    "@opencode-ai/sdk": "workspace:*"
+    "@opencode-ai/sdk": "1.18.5"
  }
 }
@@ -33,13 +33,12 @@
      "packages/*",
      "packages/console/*",
      "packages/stats/*",
-      "packages/sdk/js",
      "packages/slack"
    ],
    "catalog": {
-      "@effect/opentelemetry": "4.0.0-beta.98",
-      "@effect/platform-node": "4.0.0-beta.98",
-      "@effect/sql-sqlite-bun": "4.0.0-beta.98",
+      "@effect/opentelemetry": "4.0.0-beta.101",
+      "@effect/platform-node": "4.0.0-beta.101",
+      "@effect/sql-sqlite-bun": "4.0.0-beta.101",
      "@npmcli/arborist": "9.4.0",
      "@types/bun": "1.3.13",
      "@types/cross-spawn": "6.0.6",
@@ -51,6 +50,7 @@
      "@opentui/solid": "0.4.5",
      "@tanstack/solid-virtual": "3.13.32",
      "@shikijs/stream": "4.2.0",
+      "@standard-schema/spec": "1.1.0",
      "ulid": "3.0.1",
      "@kobalte/core": "0.13.11",
      "@corvu/drawer": "0.2.4",
@@ -69,7 +69,7 @@
      "dompurify": "3.3.1",
      "drizzle-kit": "1.0.0-rc.2",
      "drizzle-orm": "1.0.0-rc.2",
-      "effect": "4.0.0-beta.98",
+      "effect": "4.0.0-beta.101",
      "ai": "6.0.168",
      "cross-spawn": "7.0.6",
      "hono": "4.10.7",
@@ -124,7 +124,7 @@
    "@aws-sdk/client-s3": "3.933.0",
    "@opencode-ai/plugin": "workspace:*",
    "@opencode-ai/script": "workspace:*",
-    "@opencode-ai/sdk": "workspace:*",
+    "@opencode-ai/sdk": "1.18.5",
    "heap-snapshot-toolkit": "1.1.3",
    "typescript": "catalog:"
  },
@@ -152,7 +152,8 @@
    "@opentui/keymap": "catalog:",
    "@opentui/solid": "catalog:",
    "@types/bun": "catalog:",
-    "@types/node": "catalog:"
+    "@types/node": "catalog:",
+    "effect": "catalog:"
  },
  "patchedDependencies": {
    "@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
@@ -166,7 +167,7 @@
    "@ai-sdk/google@3.0.73": "patches/@ai-sdk%2Fgoogle@3.0.73.patch",
    "@pierre/trees@1.0.0-beta.4": "patches/@pierre%2Ftrees@1.0.0-beta.4.patch",
    "@modelcontextprotocol/sdk@1.29.0": "patches/@modelcontextprotocol%2Fsdk@1.29.0.patch",
-    "effect@4.0.0-beta.98": "patches/effect@4.0.0-beta.98.patch",
+    "effect@4.0.0-beta.101": "patches/effect@4.0.0-beta.101.patch",
    "@tanstack/virtual-core@3.17.3": "patches/@tanstack%2Fvirtual-core@3.17.3.patch"
  }
 }
@@ -54,7 +54,7 @@ Filter or narrow `LLMEvent` streams with `LLMEvent.is.*` (camelCase guards, e.g.

 A route is the registered, runnable composition of four orthogonal pieces:

- **`Protocol`** (`src/route/protocol.ts`) — semantic API contract. Owns request body construction (`body.from`), the body schema (`body.schema`), the streaming-event schema (`stream.event`), and the event-to-`LLMEvent` state machine (`stream.step`). `Route.make(...)` validates and JSON-encodes the body from `body.schema` and decodes frames with `stream.event`. Examples: `OpenAIChat.protocol`, `OpenAIResponses.protocol`, `AnthropicMessages.protocol`, `Gemini.protocol`, `BedrockConverse.protocol`.
+- **`Protocol`** (`src/route/protocol.ts`) — semantic API contract. Owns request body construction (`body.from`), the body schema (`body.schema`), the streaming-event schema (`stream.event`), and the event-to-`LLMEvent` state machine (`stream.step`). `Route.make(...)` validates and JSON-encodes the body from `body.schema` and decodes frames with `stream.event`. Examples: `OpenAIChat.protocol`, `OpenResponses.protocol`, `OpenAIResponses.protocol`, `AnthropicMessages.protocol`, `Gemini.protocol`, `BedrockConverse.protocol`.
 - **`Endpoint`** (`src/route/endpoint.ts`) — URL construction. The host, path, and route query live on the endpoint. `Endpoint.path("/chat/completions", { baseURL })` is the common case; pass a function for paths that embed the model id or a body field (e.g. `Endpoint.path(({ body }) => `/model/${body.modelId}/converse-stream`)`).
 - **`Auth`** (`src/route/auth.ts`) — per-request transport authentication. Provider facades configure credentials onto the route before model selection, usually via `Auth.bearer(apiKey)` or `Auth.header(name, apiKey)`. Routes that need per-request signing (Bedrock SigV4, future Vertex IAM, Azure AAD) implement `Auth` as a function that signs the body and merges signed headers into the result.
 - **`Framing`** (`src/route/framing.ts`) — bytes → frames. SSE (`Framing.sse`) is shared; Bedrock keeps its AWS event-stream framing as a typed `Framing<object>` value alongside its protocol.
@@ -158,13 +158,14 @@ packages/ai/src/
  protocols/
    shared.ts               ProviderShared toolkit used inside protocol impls
    openai-chat.ts          protocol + route (compose OpenAIChat.protocol)
-    openai-responses.ts
+    open-responses.ts         provider-neutral Responses protocol baseline
+    openai-responses.ts       OpenAI tools/events/transports composed over OpenResponses
    anthropic-messages.ts
    gemini.ts
    bedrock-converse.ts
    bedrock-event-stream.ts framing for AWS event-stream binary frames
    openai-compatible-chat.ts route that reuses OpenAIChat.protocol, no canonical URL
-    openai-compatible-responses.ts route that reuses OpenAIResponses.protocol, no canonical URL
+    openai-compatible-responses.ts deployment adapter that reuses OpenResponses.protocol, no canonical URL
    utils/                  per-protocol helpers (auth, cache, media, tool-stream, ...)
  providers/
    openai-compatible.ts    generic Chat helper + family model helpers
@@ -175,7 +176,7 @@ packages/ai/src/
  tool-runtime.ts           narrow one-call typed tool dispatcher
 ```

-The dependency arrow points down: `providers/*.ts` files import protocol routes and auth-option utilities; protocol modules import `endpoint`, `auth`, `framing`, and transport pieces. Protocols do not import provider facades. Lower-level modules know nothing about provider catalog metadata.
+The dependency arrow points down: `providers/*.ts` files import protocol routes and auth-option utilities; protocol modules import `endpoint`, `auth`, `framing`, and transport pieces. Protocols do not import provider facades. Lower-level modules know nothing about provider catalog metadata. `OpenAIResponses` composes the provider-neutral `OpenResponses` protocol; the baseline never imports the OpenAI extension.

 ### Shared protocol helpers

@@ -240,7 +241,7 @@ const get_weather = tool({

 const tools = { get_weather, get_time, ... }
 const events = yield* LLM.stream(
-  LLM.updateRequest(request, { tools: Tool.toDefinitions(tools) }),
+  LLMRequest.update(request, { tools: Tool.toDefinitions(tools) }),
 ).pipe(Stream.runCollect)

 const call = Array.from(events).find(LLMEvent.is.toolCall)
@@ -315,7 +315,8 @@ const longer = {
 }
 ```

-There is no `LLM.updateRequest(...)` helper and no request Schema class.
+There is no `LLM.updateRequest(...)` helper. The current Schema-backed implementation
+uses `LLMRequest.update(...)` when canonical request data must be derived.

 ### Conversation history

@@ -436,7 +437,7 @@ const call = Array.from(events).find(LLMEvent.is.toolCall)

 if (call && !call.providerExecuted) {
  const dispatched = yield * ToolRuntime.dispatch(tools, call)
-  const followUp = LLM.updateRequest(request, {
+  const followUp = LLMRequest.update(request, {
    messages: [...request.messages, Message.assistant([call]), Message.tool({ ...call, result: dispatched.result })],
  })
  // Caller must invoke the provider again and repeat the loop.
@@ -207,7 +207,9 @@ Prompt caching is **on by default**. Every `LLMRequest` resolves to `cache: "aut

 ### Auto placement

-`"auto"` places three breakpoints — last tool definition, last system part, latest user message. The last-user-message boundary is the load-bearing detail: in a tool-use loop, a single user turn expands into many assistant/tool round-trips, all sharing that prefix. Caching at that boundary lets every intra-turn API call hit.
+`"auto"` places up to four breakpoints — the last tool definition, the first system part, the last system part when distinct, and the final message boundary. These expose successively larger reusable prefixes for tools, the base agent, project instructions, and the active conversation. The rolling final-message boundary is the load-bearing detail in tool loops: it advances on every request so the previous cache entry stays within Anthropic's 20-block lookback.
+
+Tools precede every system and conversation block in the provider prefix, so tool definitions must remain byte-stable and deterministically ordered for downstream breakpoints to remain reusable.

 The math justifies the default: Anthropic's 5-minute cache write is 1.25× base, read is 0.1×, so a single reuse within 5 minutes already wins. One-shot completions below the per-model minimum-cacheable-token threshold silently no-op on the wire, so the worst case is harmless.

@@ -235,7 +237,7 @@ cache: {

 ### Manual hints

-Inline `CacheHint` on any text / system / tool / tool-result part overrides automatic placement. The auto policy preserves manual hints; it only fills gaps.
+Inline `CacheHint` on any text / system / tool / tool-result part overrides automatic placement. The auto policy preserves manual hints, counts them against Anthropic and Bedrock's four-breakpoint limit, and only fills the remaining slots.

 ```ts
 LLM.request({
@@ -251,8 +253,8 @@ LLM.request({

 | Protocol                | `cache: "auto"`                                                           |
 | ----------------------- | ------------------------------------------------------------------------- |
-| Anthropic Messages      | emits up to 3 `cache_control` markers (4-breakpoint cap enforced)         |
-| Bedrock Converse        | emits up to 3 `cachePoint` blocks (4-breakpoint cap enforced)             |
+| Anthropic Messages      | emits up to 4 `cache_control` markers (4-breakpoint cap enforced)         |
+| Bedrock Converse        | emits up to 4 `cachePoint` blocks (4-breakpoint cap enforced)             |
 | OpenAI Chat / Responses | no-op (implicit caching above 1024 tokens)                                |
 | Gemini                  | no-op (implicit caching on 2.5+; explicit `CachedContent` is out-of-band) |

@@ -300,7 +302,7 @@ OpenAI Chat and OpenAI Responses are separate semantic entrypoints:
 - `@opencode-ai/ai/providers/google-vertex/responses`
 - `@opencode-ai/ai/providers/google-vertex/messages`

-Responses HTTP versus WebSocket is a scoped `transport` setting on the OpenAI Responses entrypoint, not another entrypoint. Azure follows the same Chat/Responses split at `providers/azure/chat` and `providers/azure/responses`. Generic OpenAI-compatible Chat remains at `providers/openai-compatible`; compatible Responses is separate at `providers/openai-compatible/responses`. Generic Anthropic Messages-compatible providers use `providers/anthropic-compatible`, which the named Anthropic provider composes. Google Gemini and Amazon Bedrock expose their single native API through their existing provider paths.
+Responses HTTP versus WebSocket is a scoped `transport` setting on the OpenAI Responses entrypoint, not another entrypoint. Azure follows the same Chat/Responses split at `providers/azure/chat` and `providers/azure/responses`. Generic OpenAI-compatible Chat remains at `providers/openai-compatible`; the Responses adapter at `providers/openai-compatible/responses` uses the provider-neutral Open Responses protocol. OpenAI Responses extends that baseline with OpenAI tools, event variants, metadata, defaults, and transports. Generic Anthropic Messages-compatible providers use `providers/anthropic-compatible`, which the named Anthropic provider composes. Google Gemini and Amazon Bedrock expose their single native API through their existing provider paths.

 Vertex Gemini, Vertex Chat, Vertex Responses, and Vertex Messages are separate API entrypoints. All accept `project`, `location`, and an optional `accessToken`; when no explicit token or auth override is supplied they lazily use Google Application Default Credentials. Vertex Gemini instead selects express mode when `apiKey` or `GOOGLE_VERTEX_API_KEY` is present. Vertex Chat targets MaaS models through the OpenAI-compatible Chat Completions endpoint, while Vertex Responses targets Grok models and defaults `store` to `false` as required by Vertex. `providers/google-vertex` remains the default alias for `providers/google-vertex/gemini`.

@@ -1,6 +1,6 @@
 # LLM Provider Parity Status

-Last reviewed: 2026-07-17
+Last reviewed: 2026-07-24

 This file tracks the gap between the native `@opencode-ai/ai` package and the AI SDK provider packages that opencode still depends on for many catalog/runtime paths.

@@ -13,26 +13,26 @@ This file tracks the gap between the native `@opencode-ai/ai` package and the AI

 ## Current Implementation Snapshot

-| Native slice                       | Source                                                                                         | Current state                                                                                                                                                            | Main gaps                                                                                                                                                                                                                                                 |
-| ---------------------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| OpenAI Chat                        | `src/protocols/openai-chat.ts`, `src/providers/openai.ts`                                      | Usable. Streams text, reasoning deltas, tool calls, usage, images, and common generation controls.                                                                       | No typed structured-output / `response_format` path. Limited typed OpenAI option surface compared with SDK escape hatches.                                                                                                                                |
-| OpenAI Responses HTTP              | `src/protocols/openai-responses.ts`, `src/providers/openai.ts`                                 | Usable. Supports hosted-tool event surfacing, reasoning replay metadata, GPT-5 defaults, and cache usage.                                                                | No explicit `previous_response_id` path. Typed options cover only a subset of Responses fields. Structured output is still mostly synthetic-tool based.                                                                                                   |
-| OpenAI Responses WebSocket         | `src/protocols/openai-responses.ts`, `src/route/transport/websocket.ts`                        | Present as `OpenAI.responsesWebSocket(...)`.                                                                                                                             | Runner/catalog support explicitly must not downgrade WebSocket routes; broader runtime selection is not complete.                                                                                                                                         |
-| OpenAI-compatible Chat             | `src/protocols/openai-compatible-chat.ts`, `src/providers/openai-compatible.ts`                | Usable for generic Chat and several profiles: Baseten, Cerebras, DeepInfra, DeepSeek, Fireworks, Groq, TogetherAI.                                                       | Family quirks are mostly endpoint defaults, not full typed behavior.                                                                                                                                                                                      |
-| OpenAI-compatible Responses        | `src/protocols/openai-compatible-responses.ts`, `src/providers/openai-compatible-responses.ts` | Usable for deployments that implement the OpenAI Responses wire protocol.                                                                                                | No named family profiles or recorded deployment coverage yet.                                                                                                                                                                                             |
-| Anthropic-compatible Messages      | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic-compatible.ts`                 | Usable for deployments that implement the Anthropic Messages wire protocol. Named Anthropic composes this base; MiniMax M3 has recorded text and tool-loop coverage.       | No named compatible family profiles yet.                                                                                                                                                                                                                  |
-| Anthropic Messages                 | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic.ts`                            | Usable. Supports tools, thinking, cache control, images, server-hosted tool events, and usage.                                                                           | Provider option surface is small. Beta/header handling, metadata, and newer Messages fields need a typed parity pass.                                                                                                                                     |
-| Gemini Developer API               | `src/protocols/gemini.ts`, `src/providers/google.ts`                                           | Usable for Google API key flow. Supports text, images, tools, thinking signatures, and cache usage.                                                                      | This is not Vertex. Typed provider options are narrow; many Gemini request fields currently require raw `http.body` overlays.                                                                                                                             |
-| Vertex Gemini                      | `src/protocols/gemini.ts`, `src/providers/google-vertex.ts`                                    | Usable through API-key express mode, explicit OAuth tokens, or ADC with project/location endpoint derivation, including tuned `endpoints/...` deployments.               | Core runner/catalog mapping and recorded provider coverage are missing.                                                                                                                                                                                   |
-| Vertex Chat                        | `src/protocols/openai-chat.ts`, `src/providers/google-vertex-chat.ts`                          | Usable for MaaS models through OpenAI-compatible Chat Completions with explicit OAuth tokens or ADC and project/location endpoint derivation.                            | Core runner/catalog mapping and recorded provider coverage are missing; MaaS family-specific request parity needs review.                                                                                                                                 |
-| Vertex Responses                   | `src/protocols/openai-responses.ts`, `src/providers/google-vertex-responses.ts`                | Usable for Grok models through OpenAI-compatible Responses with explicit OAuth tokens or ADC, project/location endpoint derivation, and storage disabled by default.     | Core runner/catalog mapping and recorded provider coverage are missing; stateful continuation is not supported by Vertex.                                                                                                                                 |
-| Vertex Messages                    | `src/protocols/anthropic-messages.ts`, `src/providers/google-vertex-messages.ts`               | Usable through explicit OAuth tokens or ADC, including global, regional, and `eu`/`us` multi-region endpoints.                                                           | Core runner/catalog mapping and recorded provider coverage are missing; Vertex-specific hosted-tool parity needs review.                                                                                                                                  |
-| Bedrock Converse                   | `src/protocols/bedrock-converse.ts`, `src/providers/amazon-bedrock.ts`                         | Partial but real. Supports AWS event-stream framing, SigV4 with supplied credentials, bearer auth, tools, reasoning signatures, media, cache points, and recorded tests. | Native facade does not mirror the AI SDK plugin's default AWS credential chain/profile behavior. Runner/catalog mapping is missing. Guardrails, inference profiles, region-specific model ID fixes, and model-specific request fields need a parity pass. |
-| Azure OpenAI                       | `src/providers/azure.ts` using OpenAI Chat/Responses protocols                                 | Partial. Supports resource/base URL setup, API key auth, API version query, Chat, and Responses selectors.                                                               | Core runner does not map `@ai-sdk/azure` to this native facade. AAD/token auth and Azure-specific endpoint variants need review.                                                                                                                          |
-| Cloudflare AI Gateway / Workers AI | `src/providers/cloudflare.ts`                                                                  | Present via OpenAI-compatible Chat routes.                                                                                                                               | Useful but not part of the critical AI SDK replacement set yet. Needs per-product recorded coverage before relying on it broadly.                                                                                                                         |
-| OpenRouter                         | `src/providers/openrouter.ts`                                                                  | Present with OpenRouter-specific usage/reasoning/prompt-cache options over Chat.                                                                                         | Responses-style OpenRouter support is absent.                                                                                                                                                                                                             |
-| xAI                                | `src/providers/xai.ts`                                                                         | Present with Responses and Chat selectors.                                                                                                                               | Needs package-parity review against the AI SDK xAI provider.                                                                                                                                                                                              |
-| GitHub Copilot                     | `src/providers/github-copilot.ts`                                                              | Present as explicit-base-URL OpenAI Chat/Responses facade.                                                                                                               | Runtime/catalog integration remains specialized and should stay separate from public OpenAI-compatible defaults.                                                                                                                                          |
+| Native slice                       | Source                                                                                                                            | Current state                                                                                                                                                            | Main gaps                                                                                                                                                                                                                                                 |
+| ---------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| OpenAI Chat                        | `src/protocols/openai-chat.ts`, `src/providers/openai.ts`                                                                         | Usable. Streams text, reasoning deltas, tool calls, usage, images, and common generation controls.                                                                       | No typed structured-output / `response_format` path. Limited typed OpenAI option surface compared with SDK escape hatches.                                                                                                                                |
+| OpenAI Responses HTTP              | `src/protocols/open-responses.ts`, `src/protocols/openai-responses.ts`, `src/providers/openai.ts`                                 | Usable. Extends the Open Responses baseline with hosted-tool event surfacing, reasoning replay metadata, GPT-5 defaults, and cache usage.                                | No explicit `previous_response_id` path. Typed options cover only a subset of Responses fields. Structured output is still mostly synthetic-tool based.                                                                                                   |
+| OpenAI Responses WebSocket         | `src/protocols/openai-responses.ts`, `src/route/transport/websocket.ts`                                                           | Present as `OpenAI.responsesWebSocket(...)`.                                                                                                                             | Runner/catalog support explicitly must not downgrade WebSocket routes; broader runtime selection is not complete.                                                                                                                                         |
+| OpenAI-compatible Chat             | `src/protocols/openai-compatible-chat.ts`, `src/providers/openai-compatible.ts`                                                   | Usable for generic Chat and several profiles: Baseten, Cerebras, DeepInfra, DeepSeek, Fireworks, Groq, TogetherAI.                                                       | Family quirks are mostly endpoint defaults, not full typed behavior.                                                                                                                                                                                      |
+| Open Responses-compatible          | `src/protocols/open-responses.ts`, `src/protocols/openai-compatible-responses.ts`, `src/providers/openai-compatible-responses.ts` | Usable for deployments that implement the provider-neutral Open Responses protocol. The deployment adapter does not inherit OpenAI tools, events, metadata, or defaults. | No named family profiles or recorded deployment coverage yet.                                                                                                                                                                                             |
+| Anthropic-compatible Messages      | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic-compatible.ts`                                                    | Usable for deployments that implement the Anthropic Messages wire protocol. Named Anthropic composes this base; MiniMax M3 has recorded text and tool-loop coverage.     | No named compatible family profiles yet.                                                                                                                                                                                                                  |
+| Anthropic Messages                 | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic.ts`                                                               | Usable. Supports tools, thinking, cache control, images, server-hosted tool events, and usage.                                                                           | Provider option surface is small. Beta/header handling, metadata, and newer Messages fields need a typed parity pass.                                                                                                                                     |
+| Gemini Developer API               | `src/protocols/gemini.ts`, `src/providers/google.ts`                                                                              | Usable for Google API key flow. Supports text, images, tools, thinking signatures, and cache usage.                                                                      | This is not Vertex. Typed provider options are narrow; many Gemini request fields currently require raw `http.body` overlays.                                                                                                                             |
+| Vertex Gemini                      | `src/protocols/gemini.ts`, `src/providers/google-vertex.ts`                                                                       | Usable through API-key express mode, explicit OAuth tokens, or ADC with project/location endpoint derivation, including tuned `endpoints/...` deployments.               | Core runner/catalog mapping and recorded provider coverage are missing.                                                                                                                                                                                   |
+| Vertex Chat                        | `src/protocols/openai-chat.ts`, `src/providers/google-vertex-chat.ts`                                                             | Usable for MaaS models through OpenAI-compatible Chat Completions with explicit OAuth tokens or ADC and project/location endpoint derivation.                            | Core runner/catalog mapping and recorded provider coverage are missing; MaaS family-specific request parity needs review.                                                                                                                                 |
+| Vertex Responses                   | `src/protocols/open-responses.ts`, `src/providers/google-vertex-responses.ts`                                                     | Usable for Grok models through Open Responses with explicit OAuth tokens or ADC, project/location endpoint derivation, and an explicit `store: false` Vertex default.    | Core runner/catalog mapping and recorded provider coverage are missing; stateful continuation is not supported by Vertex.                                                                                                                                 |
+| Vertex Messages                    | `src/protocols/anthropic-messages.ts`, `src/providers/google-vertex-messages.ts`                                                  | Usable through explicit OAuth tokens or ADC, including global, regional, and `eu`/`us` multi-region endpoints.                                                           | Core runner/catalog mapping and recorded provider coverage are missing; Vertex-specific hosted-tool parity needs review.                                                                                                                                  |
+| Bedrock Converse                   | `src/protocols/bedrock-converse.ts`, `src/providers/amazon-bedrock.ts`                                                            | Partial but real. Supports AWS event-stream framing, SigV4 with supplied credentials, bearer auth, tools, reasoning signatures, media, cache points, and recorded tests. | Native facade does not mirror the AI SDK plugin's default AWS credential chain/profile behavior. Runner/catalog mapping is missing. Guardrails, inference profiles, region-specific model ID fixes, and model-specific request fields need a parity pass. |
+| Azure OpenAI                       | `src/providers/azure.ts` using OpenAI Chat/Responses protocols                                                                    | Partial. Supports resource/base URL setup, API key auth, API version query, Chat, and Responses selectors.                                                               | Core runner does not map `@ai-sdk/azure` to this native facade. AAD/token auth and Azure-specific endpoint variants need review.                                                                                                                          |
+| Cloudflare AI Gateway / Workers AI | `src/providers/cloudflare.ts`                                                                                                     | Present via OpenAI-compatible Chat routes.                                                                                                                               | Useful but not part of the critical AI SDK replacement set yet. Needs per-product recorded coverage before relying on it broadly.                                                                                                                         |
+| OpenRouter                         | `src/providers/openrouter.ts`                                                                                                     | Present with OpenRouter-specific usage/reasoning/prompt-cache options over Chat.                                                                                         | Responses-style OpenRouter support is absent.                                                                                                                                                                                                             |
+| xAI                                | `src/providers/xai.ts`                                                                                                            | Present with Responses and Chat selectors.                                                                                                                               | Needs package-parity review against the AI SDK xAI provider.                                                                                                                                                                                              |
+| GitHub Copilot                     | `src/providers/github-copilot.ts`                                                                                                 | Present as explicit-base-URL OpenAI Chat/Responses facade.                                                                                                               | Runtime/catalog integration remains specialized and should stay separate from public OpenAI-compatible defaults.                                                                                                                                          |

 ## V2 Runner Status

@@ -65,7 +65,7 @@ Other `aisdk:` packages, including Google Vertex, Azure, and Bedrock, currently
 ## Highest-Risk Gaps

 1. Runner support is narrower than the LLM package. The package has native provider facades for Google, Azure, and Bedrock, but the V2 Session runner only maps OpenAI, Anthropic, and explicit OpenAI-compatible Chat from `aisdk` catalog metadata.
-2. OpenAI-compatible Responses is available as a separate package entrypoint, but the V2 runner still maps `@ai-sdk/openai-compatible` to Chat only. Catalog selection must become API-aware before Responses deployments can use it.
+2. The Open Responses adapter is available through a separate package entrypoint, but the V2 runner still maps `@ai-sdk/openai-compatible` to Chat only. Catalog selection must become API-aware before Responses deployments can use it.
 3. Bedrock native auth is not AI SDK parity. The AI SDK plugin uses the default AWS provider chain, profile, container credentials, and Bedrock bearer token env behavior. Native Bedrock currently expects explicit credentials or bearer auth on the facade.
 4. Vertex Gemini, Vertex Chat, Vertex Responses, and Vertex Messages now have native package entrypoints, but the core runner does not map catalog metadata to them yet and recorded provider coverage is still missing.
 5. Azure is only a provider facade, not a full runtime replacement. Native Azure exists, but the catalog runner does not select it, and token auth/resource variants need review.
@@ -83,13 +83,13 @@ These are implementation/API slices, not separate npm packages.
 | OpenAI Chat                   | `@opencode-ai/ai/providers/openai/chat`                 | OpenAI `/chat/completions` semantics.                                        |
 | OpenAI Responses              | `@opencode-ai/ai/providers/openai/responses`            | OpenAI `/responses` semantics with HTTP/WebSocket selected through settings. |
 | OpenAI-compatible Chat        | `@opencode-ai/ai/providers/openai-compatible`           | Generic OpenAI-compatible `/chat/completions`.                               |
-| OpenAI-compatible Responses   | `@opencode-ai/ai/providers/openai-compatible/responses` | Generic OpenAI-compatible `/responses`.                                      |
+| Open Responses-compatible     | `@opencode-ai/ai/providers/openai-compatible/responses` | Generic provider-neutral `/responses`.                                       |
 | Anthropic-compatible Messages | `@opencode-ai/ai/providers/anthropic-compatible`        | Generic Anthropic-compatible `/messages`.                                    |
 | Anthropic Messages            | `@opencode-ai/ai/providers/anthropic`                   | Anthropic Messages API.                                                      |
 | Gemini Developer API          | `@opencode-ai/ai/providers/google`                      | Google AI Studio Gemini API.                                                 |
 | Vertex Gemini                 | `@opencode-ai/ai/providers/google-vertex/gemini`        | Vertex Gemini API; `providers/google-vertex` is the default alias.           |
 | Vertex Chat                   | `@opencode-ai/ai/providers/google-vertex/chat`          | Vertex OpenAI-compatible Chat Completions for MaaS models.                   |
-| Vertex Responses              | `@opencode-ai/ai/providers/google-vertex/responses`     | Vertex OpenAI-compatible Responses for Grok models.                          |
+| Vertex Responses              | `@opencode-ai/ai/providers/google-vertex/responses`     | Vertex Open Responses for Grok models.                                       |
 | Vertex Messages               | `@opencode-ai/ai/providers/google-vertex/messages`      | Vertex-hosted Anthropic Messages API.                                        |
 | Bedrock Converse              | `@opencode-ai/ai/providers/amazon-bedrock`              | AWS Bedrock Converse API.                                                    |
 | Bedrock Mantle                | Missing                                                 | AWS Bedrock Mantle OpenAI-compatible APIs.                                   |
@@ -1,5 +1,5 @@
 import { Config, Effect, Formatter, Layer, Schema, Stream } from "effect"
-import { LLM, LLMClient, Message, ProviderID, Tool, ToolRuntime } from "@opencode-ai/ai"
+import { LLM, LLMClient, LLMRequest, Message, ProviderID, Tool, ToolRuntime } from "@opencode-ai/ai"
 import { Route, Auth, Endpoint, Framing, Protocol, RequestExecutor, WebSocketExecutor } from "@opencode-ai/ai/route"
 import { OpenAI } from "@opencode-ai/ai/providers"

@@ -116,7 +116,7 @@ const streamWithTools = Effect.gen(function* () {

    // A durable agent would persist these messages before starting another
    // raw model turn. This tutorial keeps the boundary visible instead.
-    const followUp = LLM.updateRequest(request, {
+    const followUp = LLMRequest.update(request, {
      messages: [
        ...request.messages,
        Message.assistant([event]),
@@ -2,32 +2,31 @@
 // the policy designates. Runs once at compile time, before the per-protocol
 // body builder, so the existing inline-hint lowering path handles the rest.
 //
-// The default `"auto"` shape places one breakpoint at the last tool definition,
-// one at the last system part, and one at the latest user message. This
-// matches what production agent harnesses (LangChain's caching middleware,
-// kern-ai's 10x cost-reduction playbook) converge on for tool-use loops: the
-// latest user message stays put while a single turn explodes into many
-// assistant/tool round-trips, so caching at that boundary lets every
-// intra-turn API call hit the prefix.
+// The default `"auto"` shape places breakpoints at the last tool definition,
+// the first and last distinct system parts, and the conversation tail. This
+// exposes reusable tool, base-agent, project, and session prefixes while
+// advancing the tail after each tool result keeps the previous cache entry
+// within Anthropic's 20-block lookback during long agent turns.
 //
-// Manual `cache: CacheHint` placements on individual parts are preserved —
-// this function only fills gaps the caller left empty.
+// Manual `cache: CacheHint` placements on individual parts are preserved and
+// count against the four-breakpoint budget; auto only fills remaining slots.
 import { CacheHint, type CachePolicy, type CachePolicyObject } from "./schema/options"
 import { LLMRequest, Message, ToolDefinition, type ContentPart } from "./schema/messages"

 const AUTO: CachePolicyObject = {
  tools: true,
  system: true,
-  messages: "latest-user-message",
+  messages: { tail: 1 },
 }

 const NONE: CachePolicyObject = {}
+const BREAKPOINT_CAP = 4

 // Resolution rules:
 //   - undefined   → "auto" — caching is on by default. The math favors it:
 //                   Anthropic 5m-cache write is 1.25x base, read is 0.1x,
 //                   so a single reuse within 5 minutes already wins.
-//   - "auto"      → tools + system + latest user msg.
+//   - "auto"      → tools + first/last system + final message boundary.
 //   - "none"      → no auto placement; manual `CacheHint`s still flow.
 //   - object form → exactly what the caller asked for.
 const resolve = (policy: CachePolicy | undefined): CachePolicyObject => {
@@ -44,18 +43,32 @@ const RESPECTS_INLINE_HINTS = new Set(["anthropic-messages", "bedrock-converse"]
 const makeHint = (ttlSeconds: number | undefined): CacheHint =>
  ttlSeconds !== undefined ? new CacheHint({ type: "ephemeral", ttlSeconds }) : new CacheHint({ type: "ephemeral" })

-const markLastTool = (tools: ReadonlyArray<ToolDefinition>, hint: CacheHint): ReadonlyArray<ToolDefinition> => {
+interface Budget {
+  remaining: number
+}
+
+const markLastTool = (
+  tools: ReadonlyArray<ToolDefinition>,
+  hint: CacheHint,
+  budget: Budget,
+): ReadonlyArray<ToolDefinition> => {
  if (tools.length === 0) return tools
  const last = tools.length - 1
-  if (tools[last]!.cache) return tools
+  if (tools[last]!.cache || budget.remaining === 0) return tools
+  budget.remaining -= 1
  return tools.map((tool, i) => (i === last ? new ToolDefinition({ ...tool, cache: hint }) : tool))
 }

-const markLastSystem = (system: LLMRequest["system"], hint: CacheHint): LLMRequest["system"] => {
+const markSystemBoundaries = (system: LLMRequest["system"], hint: CacheHint, budget: Budget): LLMRequest["system"] => {
  if (system.length === 0) return system
-  const last = system.length - 1
-  if (system[last]!.cache) return system
-  return system.map((part, i) => (i === last ? { ...part, cache: hint } : part))
+  let changed = false
+  const next = system.map((part, index) => {
+    if ((index !== 0 && index !== system.length - 1) || part.cache || budget.remaining === 0) return part
+    budget.remaining -= 1
+    changed = true
+    return { ...part, cache: hint }
+  })
+  return changed ? next : system
 }

 const lastIndexOfRole = (messages: ReadonlyArray<Message>, role: Message["role"]): number =>
@@ -64,14 +77,20 @@ const lastIndexOfRole = (messages: ReadonlyArray<Message>, role: Message["role"]
 // Mark the last text part of `messages[index]`. If no text part exists, mark
 // the last content part regardless of type — that's the breakpoint position
 // in tool-result-only messages too.
-const markMessageAt = (messages: ReadonlyArray<Message>, index: number, hint: CacheHint): ReadonlyArray<Message> => {
+const markMessageAt = (
+  messages: ReadonlyArray<Message>,
+  index: number,
+  hint: CacheHint,
+  budget: Budget,
+): ReadonlyArray<Message> => {
  if (index < 0 || index >= messages.length) return messages
  const target = messages[index]!
  if (target.content.length === 0) return messages
  const lastTextIndex = target.content.findLastIndex((part) => part.type === "text")
  const markAt = lastTextIndex >= 0 ? lastTextIndex : target.content.length - 1
  const existing = target.content[markAt]!
-  if ("cache" in existing && existing.cache) return messages
+  if (("cache" in existing && existing.cache) || budget.remaining === 0) return messages
+  budget.remaining -= 1
  const nextContent = target.content.map((part, i) => (i === markAt ? ({ ...part, cache: hint } as ContentPart) : part))
  const next = new Message({ ...target, content: nextContent })
  // Single pass over `messages`, substituting the one updated entry. Long
@@ -86,25 +105,42 @@ const markMessages = (
  messages: ReadonlyArray<Message>,
  strategy: NonNullable<CachePolicyObject["messages"]>,
  hint: CacheHint,
+  budget: Budget,
 ): ReadonlyArray<Message> => {
  if (messages.length === 0) return messages
-  if (strategy === "latest-user-message") return markMessageAt(messages, lastIndexOfRole(messages, "user"), hint)
-  if (strategy === "latest-assistant") return markMessageAt(messages, lastIndexOfRole(messages, "assistant"), hint)
+  if (strategy === "latest-user-message")
+    return markMessageAt(messages, lastIndexOfRole(messages, "user"), hint, budget)
+  if (strategy === "latest-assistant")
+    return markMessageAt(messages, lastIndexOfRole(messages, "assistant"), hint, budget)
  const start = Math.max(0, messages.length - strategy.tail)
  let next = messages
-  for (let i = start; i < messages.length; i++) next = markMessageAt(next, i, hint)
+  for (let i = start; i < messages.length; i++) next = markMessageAt(next, i, hint, budget)
  return next
 }

+const countHints = (request: LLMRequest) =>
+  request.tools.reduce((count, tool) => count + (tool.cache === undefined ? 0 : 1), 0) +
+  request.system.reduce((count, part) => count + (part.cache === undefined ? 0 : 1), 0) +
+  request.messages.reduce(
+    (count, message) =>
+      count +
+      message.content.reduce(
+        (contentCount, part) => contentCount + ("cache" in part && part.cache !== undefined ? 1 : 0),
+        0,
+      ),
+    0,
+  )
+
 export const applyCachePolicy = (request: LLMRequest): LLMRequest => {
  if (!RESPECTS_INLINE_HINTS.has(request.model.route.id)) return request
  const policy = resolve(request.cache)
  if (!policy.tools && !policy.system && !policy.messages) return request

  const hint = makeHint(policy.ttlSeconds)
-  const tools = policy.tools ? markLastTool(request.tools, hint) : request.tools
-  const system = policy.system ? markLastSystem(request.system, hint) : request.system
-  const messages = policy.messages ? markMessages(request.messages, policy.messages, hint) : request.messages
+  const budget = { remaining: Math.max(0, BREAKPOINT_CAP - countHints(request)) }
+  const tools = policy.tools ? markLastTool(request.tools, hint, budget) : request.tools
+  const system = policy.system ? markSystemBoundaries(request.system, hint, budget) : request.system
+  const messages = policy.messages ? markMessages(request.messages, policy.messages, hint, budget) : request.messages

  if (tools === request.tools && system === request.system && messages === request.messages) return request
  return LLMRequest.update(request, { tools, system, messages })
@@ -9,24 +9,13 @@ import {
  LLMRequest,
  LLMResponse,
  Message,
-  type ModelInput as SchemaModelInput,
  SystemPart,
  ToolChoice,
  ToolDefinition,
  type ContentPart,
-  ToolResultPart,
 } from "./schema"
 import { make as makeTool, toDefinitions, type ToolSchema } from "./tool"

-export type ModelInput = SchemaModelInput
-
-export type MessageInput = Message.Input
-
-export type ToolChoiceInput = ToolChoice.Input
-export type ToolChoiceMode = ToolChoice.Mode
-
-export type ToolResultInput = Parameters<typeof ToolResultPart.make>[0]
-
 /** Input accepted by `LLM.request`, normalized into the canonical `LLMRequest` class. */
 export type RequestInput = Omit<
  ConstructorParameters<typeof LLMRequest>[0],
@@ -34,9 +23,9 @@ export type RequestInput = Omit<
 > & {
  readonly system?: string | SystemPart | ReadonlyArray<SystemPart>
  readonly prompt?: string | ContentPart | ReadonlyArray<ContentPart>
-  readonly messages?: ReadonlyArray<Message | MessageInput>
+  readonly messages?: ReadonlyArray<Message | Message.Input>
  readonly tools?: ReadonlyArray<ToolDefinition.Input>
-  readonly toolChoice?: ToolChoiceInput
+  readonly toolChoice?: ToolChoice.Input
  readonly generation?: GenerationOptions.Input
  readonly providerOptions?: ConstructorParameters<typeof LLMRequest>[0]["providerOptions"]
  readonly http?: HttpOptions.Input
@@ -46,10 +35,6 @@ export const generate = LLMClient.generate

 export const stream = LLMClient.stream

-export const requestInput = (input: LLMRequest): RequestInput => ({
-  ...LLMRequest.input(input),
-})
-
 export const request = (input: RequestInput) => {
  const {
    system: requestSystem,
@@ -74,9 +59,6 @@ export const request = (input: RequestInput) => {
  })
 }

-export const updateRequest = (input: LLMRequest, patch: Partial<RequestInput>) =>
-  request({ ...requestInput(input), ...patch })
-
 const GENERATE_OBJECT_TOOL_NAME = "generate_object"

 const GENERATE_OBJECT_TOOL_DESCRIPTION = "Return the structured result by calling this tool."
@@ -1,4 +1,5 @@
 import { Effect, Schema } from "effect"
+import { Tool } from "@opencode-ai/schema/tool"
 import { Route } from "../route/client"
 import { Auth } from "../route/auth"
 import { Endpoint } from "../route/endpoint"
@@ -7,16 +8,18 @@ import { Protocol } from "../route/protocol"
 import {
  LLMError,
  LLMEvent,
+  mergeJsonRecords,
  Usage,
  type CacheHint,
+  type FinishReasonDetails,
  type FinishReason,
  type JsonSchema,
  type LLMRequest,
  type MediaPart,
+  type ProviderOptions,
  type ProviderMetadata,
  type ToolCallPart,
  type ToolDefinition,
-  type ToolContent,
  type ToolResultPart,
 } from "../schema"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared"
@@ -31,6 +34,29 @@ const MEDIA_MIMES = new Set<string>([...ProviderShared.IMAGE_MIMES, ...ProviderS
 export const DEFAULT_BASE_URL = "https://api.anthropic.com/v1"
 export const PATH = "/messages"

+export type ThinkingInput =
+  | {
+      readonly type: "adaptive"
+      readonly display?: "summarized" | "omitted"
+    }
+  | {
+      readonly type: "disabled"
+    }
+  | ({ readonly type: "enabled" } & (
+      | { readonly budgetTokens: number; readonly budget_tokens?: number }
+      | { readonly budgetTokens?: number; readonly budget_tokens: number }
+    ))
+
+export interface OptionsInput {
+  readonly [key: string]: unknown
+  readonly thinking?: ThinkingInput
+  readonly effort?: string
+}
+
+export type ProviderOptionsInput = ProviderOptions & {
+  readonly anthropic?: OptionsInput
+}
+
 // =============================================================================
 // Request Body Schema
 // =============================================================================
@@ -209,12 +235,27 @@ const AnthropicBodyFields = {
 export const AnthropicMessagesBody = Schema.Struct(AnthropicBodyFields)
 export type AnthropicMessagesBody = Schema.Schema.Type<typeof AnthropicMessagesBody>

-const AnthropicUsage = Schema.Struct({
-  input_tokens: Schema.optional(Schema.Number),
-  output_tokens: Schema.optional(Schema.Number),
-  cache_creation_input_tokens: optionalNull(Schema.Number),
-  cache_read_input_tokens: optionalNull(Schema.Number),
-})
+const AnthropicUsage = Schema.StructWithRest(
+  Schema.Struct({
+    input_tokens: Schema.optional(Schema.Number),
+    output_tokens: Schema.optional(Schema.Number),
+    cache_creation_input_tokens: optionalNull(Schema.Number),
+    cache_read_input_tokens: optionalNull(Schema.Number),
+    server_tool_use: optionalNull(
+      Schema.StructWithRest(
+        Schema.Struct({ web_search_requests: Schema.optional(Schema.Number) }),
+        [Schema.Record(Schema.String, Schema.Unknown)],
+      ),
+    ),
+    output_tokens_details: optionalNull(
+      Schema.StructWithRest(
+        Schema.Struct({ thinking_tokens: Schema.optional(Schema.Number) }),
+        [Schema.Record(Schema.String, Schema.Unknown)],
+      ),
+    ),
+  }),
+  [Schema.Record(Schema.String, Schema.Unknown)],
+)
 type AnthropicUsage = Schema.Schema.Type<typeof AnthropicUsage>

 const AnthropicStreamBlock = Schema.Struct({
@@ -264,7 +305,12 @@ type AnthropicEvent = Schema.Schema.Type<typeof AnthropicEvent>

 interface ParserState {
  readonly tools: ToolStream.State<number>
+  readonly reasoningSignatures: Readonly<Record<number, string>>
  readonly usage?: Usage
+  readonly pendingFinish?: {
+    readonly reason: FinishReasonDetails
+    readonly providerMetadata?: ProviderMetadata
+  }
  readonly lifecycle: Lifecycle.State
 }

@@ -379,7 +425,7 @@ const lowerMedia = Effect.fn("AnthropicMessages.lowerMedia")(function* (part: Me
 // Tool results may carry structured text, images, and documents. Keep media as provider-native
 // content instead of JSON-stringifying base64 into a prompt string.
 const lowerToolResultContentItem = Effect.fn("AnthropicMessages.lowerToolResultContentItem")(function* (
-  item: ToolContent,
+  item: Tool.Content,
 ) {
  if (item.type === "text") return { type: "text" as const, text: item.text } satisfies AnthropicTextBlock
  return yield* lowerMedia({ type: "media", mediaType: item.mime, data: item.uri, filename: item.name })
@@ -390,7 +436,7 @@ const lowerToolResultContent = Effect.fn("AnthropicMessages.lowerToolResultConte
  // with existing cassettes and provider expectations.
  if (part.result.type !== "content") return ProviderShared.toolResultText(part)
  // Preserve the narrowed array element type when compiled through a consumer package.
-  const content: ReadonlyArray<ToolContent> = part.result.value
+  const content: ReadonlyArray<Tool.Content> = part.result.value
  return yield* Effect.forEach(content, lowerToolResultContentItem)
 })

@@ -537,37 +583,38 @@ const lowerMessages = Effect.fn("AnthropicMessages.lowerMessages")(function* (
  return messages
 })

-const anthropicOptions = (request: LLMRequest) => request.providerOptions?.anthropic
+const resolveOptions = Effect.fn("AnthropicMessages.resolveOptions")(function* (request: LLMRequest) {
+  const input = request.providerOptions?.anthropic
+  return {
+    thinking: yield* resolveThinking(input?.thinking),
+    effort: typeof input?.effort === "string" ? input.effort : undefined,
+  }
+})

-const lowerThinking = Effect.fn("AnthropicMessages.lowerThinking")(function* (request: LLMRequest) {
-  const thinking = anthropicOptions(request)?.thinking
-  if (!ProviderShared.isRecord(thinking)) return undefined
-  if (thinking.type === "adaptive") {
+const resolveThinking = Effect.fn("AnthropicMessages.resolveThinking")(function* (input: unknown) {
+  if (!ProviderShared.isRecord(input)) return undefined
+  if (input.type === "adaptive") {
    const display =
-      thinking.display === "summarized"
+      input.display === "summarized"
        ? ("summarized" as const)
-        : thinking.display === "omitted"
+        : input.display === "omitted"
          ? ("omitted" as const)
          : undefined
    return { type: "adaptive" as const, ...(display === undefined ? {} : { display }) }
  }
-  if (thinking.type === "disabled") return { type: "disabled" as const }
-  if (thinking.type !== "enabled") return undefined
+  if (input.type === "disabled") return { type: "disabled" as const }
+  if (input.type !== "enabled") return undefined
  const budget =
-    typeof thinking.budgetTokens === "number"
-      ? thinking.budgetTokens
-      : typeof thinking.budget_tokens === "number"
-        ? thinking.budget_tokens
+    typeof input.budgetTokens === "number"
+      ? input.budgetTokens
+      : typeof input.budget_tokens === "number"
+        ? input.budget_tokens
        : undefined
-  if (budget === undefined) return yield* invalid("Anthropic thinking provider option requires budgetTokens")
+  if (budget === undefined)
+    return yield* ProviderShared.invalidRequest("Anthropic thinking provider option requires budgetTokens")
  return { type: "enabled" as const, budget_tokens: budget }
 })

-const outputConfig = (request: LLMRequest) => {
-  const effort = anthropicOptions(request)?.effort
-  return typeof effort === "string" ? { effort } : undefined
-}
-
 const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (request: LLMRequest) {
  const generation = request.generation
  const toolSchemaCompatibility = request.model.compatibility?.toolSchema
@@ -587,8 +634,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
          ),
        )
  // 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 toolChoice = tools === undefined || !request.toolChoice ? undefined : yield* lowerToolChoice(request.toolChoice)
  const system =
    request.system.length === 0
      ? undefined
@@ -603,6 +649,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
      `Anthropic Messages: dropped ${breakpoints.dropped} cache breakpoint(s); the API allows at most ${ANTHROPIC_BREAKPOINT_CAP} per request.`,
    )
  }
+  const options = yield* resolveOptions(request)
  return {
    model: request.model.id,
    system,
@@ -615,8 +662,8 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
    top_p: generation?.topP,
    top_k: generation?.topK,
    stop_sequences: generation?.stop,
-    thinking: yield* lowerThinking(request),
-    output_config: outputConfig(request),
+    thinking: options.thinking,
+    output_config: options.effort === undefined ? undefined : { effort: options.effort },
  }
 })

@@ -635,9 +682,8 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
 // `input_tokens` is the *non-cached* count per the Messages API docs, with
 // cache reads and writes as separate fields. We sum them to derive the
 // inclusive `inputTokens` the rest of the contract expects. Extended
-// thinking tokens are *not* broken out by Anthropic — they're billed as
-// part of `output_tokens`, so `reasoningTokens` stays `undefined` and
-// `outputTokens` carries the combined total.
+// thinking tokens are included in `output_tokens`; newer responses also
+// expose that subset through `output_tokens_details.thinking_tokens`.
 const mapUsage = (usage: AnthropicUsage | undefined): Usage | undefined => {
  if (!usage) return undefined
  const nonCached = usage.input_tokens
@@ -650,6 +696,7 @@ const mapUsage = (usage: AnthropicUsage | undefined): Usage | undefined => {
    nonCachedInputTokens: nonCached,
    cacheReadInputTokens: cacheRead,
    cacheWriteInputTokens: cacheWrite,
+    reasoningTokens: usage.output_tokens_details?.thinking_tokens,
    totalTokens: ProviderShared.totalTokens(inputTokens, usage.output_tokens, undefined),
    providerMetadata: { anthropic: usage },
  })
@@ -668,18 +715,18 @@ const mergeUsage = (left: Usage | undefined, right: Usage | undefined) => {
  const cacheWriteInputTokens = right.cacheWriteInputTokens ?? left.cacheWriteInputTokens
  const inputTokens = ProviderShared.sumTokens(nonCachedInputTokens, cacheReadInputTokens, cacheWriteInputTokens)
  const outputTokens = right.outputTokens ?? left.outputTokens
+  const reasoningTokens = right.reasoningTokens ?? left.reasoningTokens
  return new Usage({
    inputTokens,
    outputTokens,
    nonCachedInputTokens,
    cacheReadInputTokens,
    cacheWriteInputTokens,
+    reasoningTokens,
    totalTokens: ProviderShared.totalTokens(inputTokens, outputTokens, undefined),
    providerMetadata: {
-      anthropic: {
-        ...left.providerMetadata?.["anthropic"],
-        ...right.providerMetadata?.["anthropic"],
-      },
+      anthropic:
+        mergeJsonRecords(left.providerMetadata?.["anthropic"], right.providerMetadata?.["anthropic"]) ?? {},
    },
  })
 }
@@ -738,6 +785,10 @@ const onContentBlockStart = (state: ParserState, event: AnthropicEvent): StepRes
        tools: ToolStream.start(state.tools, event.index, {
          id: block.id ?? String(event.index),
          name: block.name ?? "",
+          input:
+            block.input !== undefined && (!ProviderShared.isRecord(block.input) || Object.keys(block.input).length > 0)
+              ? ProviderShared.encodeJson(block.input)
+              : undefined,
          providerExecuted: block.type === "server_tool_use",
        }),
      },
@@ -752,20 +803,31 @@ const onContentBlockStart = (state: ParserState, event: AnthropicEvent): StepRes
    ]
  }

-  if (block.type === "text" && block.text) {
+  if (block.type === "text" && block.text !== undefined) {
    const events: LLMEvent[] = []
+    const id = `text-${event.index ?? 0}`
+    const lifecycle = Lifecycle.textStart(state.lifecycle, events, id)
    return [
-      { ...state, lifecycle: Lifecycle.textDelta(state.lifecycle, events, `text-${event.index ?? 0}`, block.text) },
+      { ...state, lifecycle: block.text ? Lifecycle.textDelta(lifecycle, events, id, block.text) : lifecycle },
      events,
    ]
  }

-  if (block.type === "thinking" && block.thinking) {
+  if (block.type === "thinking" && block.thinking !== undefined) {
    const events: LLMEvent[] = []
+    const id = `reasoning-${event.index ?? 0}`
+    const providerMetadata = block.signature === undefined ? undefined : anthropicMetadata({ signature: block.signature })
+    const lifecycle = Lifecycle.reasoningStart(state.lifecycle, events, id, providerMetadata)
    return [
      {
        ...state,
-        lifecycle: Lifecycle.reasoningDelta(state.lifecycle, events, `reasoning-${event.index ?? 0}`, block.thinking),
+        lifecycle: block.thinking
+          ? Lifecycle.reasoningDelta(lifecycle, events, id, block.thinking, providerMetadata)
+          : lifecycle,
+        reasoningSignatures:
+          event.index === undefined || block.signature === undefined
+            ? state.reasoningSignatures
+            : { ...state.reasoningSignatures, [event.index]: block.signature },
      },
      events,
    ]
@@ -774,7 +836,7 @@ const onContentBlockStart = (state: ParserState, event: AnthropicEvent): StepRes
  // Redacted thinking surfaces as an empty reasoning part carrying the opaque
  // payload as `redactedData` metadata (same model as Vercel's
  // @ai-sdk/anthropic). The existing content_block_stop closes the part.
-  if (block.type === "redacted_thinking" && block.data) {
+  if (block.type === "redacted_thinking" && block.data !== undefined) {
    const events: LLMEvent[] = []
    return [
      {
@@ -822,18 +884,13 @@ const onContentBlockDelta = Effect.fn("AnthropicMessages.onContentBlockDelta")(f
  }

  if (delta?.type === "signature_delta" && delta.signature) {
-    const events: LLMEvent[] = []
+    const index = event.index ?? 0
    return [
      {
        ...state,
-        lifecycle: Lifecycle.reasoningEnd(
-          state.lifecycle,
-          events,
-          `reasoning-${event.index ?? 0}`,
-          anthropicMetadata({ signature: delta.signature }),
-        ),
+        reasoningSignatures: { ...state.reasoningSignatures, [index]: delta.signature },
      },
-      events,
+      NO_EVENTS,
    ] satisfies StepResult
  }

@@ -864,31 +921,53 @@ const onContentBlockStop = Effect.fn("AnthropicMessages.onContentBlockStop")(fun
  const result = yield* ToolStream.finish(ADAPTER, state.tools, event.index)
  const events: LLMEvent[] = []
  const resultEvents = result.events ?? []
+  const signature = state.reasoningSignatures[event.index]
  const lifecycle = resultEvents.length
    ? Lifecycle.stepStart(state.lifecycle, events)
    : Lifecycle.reasoningEnd(
        Lifecycle.textEnd(state.lifecycle, events, `text-${event.index}`),
        events,
        `reasoning-${event.index}`,
+        signature === undefined ? undefined : anthropicMetadata({ signature }),
      )
  events.push(...resultEvents)
-  return [{ ...state, lifecycle, tools: result.tools }, events] satisfies StepResult
+  const reasoningSignatures = { ...state.reasoningSignatures }
+  delete reasoningSignatures[event.index]
+  return [{ ...state, lifecycle, tools: result.tools, reasoningSignatures }, events] satisfies StepResult
 })

 const onMessageDelta = (state: ParserState, event: AnthropicEvent): StepResult => {
  const usage = mergeUsage(state.usage, mapUsage(event.usage))
+  return [
+    {
+      ...state,
+      usage,
+      pendingFinish: {
+        reason: {
+          normalized: mapFinishReason(event.delta?.stop_reason),
+          raw: event.delta?.stop_reason ?? undefined,
+        },
+        providerMetadata:
+          event.delta?.stop_sequence === null || event.delta?.stop_sequence === undefined
+            ? undefined
+            : anthropicMetadata({ stopSequence: event.delta.stop_sequence }),
+      },
+    },
+    NO_EVENTS,
+  ]
+}
+
+const onMessageStop = (state: ParserState): StepResult => {
  const events: LLMEvent[] = []
  const lifecycle = Lifecycle.finish(state.lifecycle, events, {
-    reason: {
-      normalized: mapFinishReason(event.delta?.stop_reason),
-      raw: event.delta?.stop_reason ?? undefined,
+    reason: state.pendingFinish?.reason ?? {
+      normalized: "unknown",
+      raw: undefined,
    },
-    usage,
-    providerMetadata: event.delta?.stop_sequence
-      ? anthropicMetadata({ stopSequence: event.delta.stop_sequence })
-      : undefined,
+    usage: state.usage,
+    providerMetadata: state.pendingFinish?.providerMetadata,
  })
-  return [{ ...state, lifecycle, usage }, events]
+  return [{ ...state, lifecycle }, events]
 }

 // Prefix `error.type` so overloads, rate limits, and quota errors are visible
@@ -913,6 +992,7 @@ const step = (state: ParserState, event: AnthropicEvent) => {
  if (event.type === "content_block_delta") return onContentBlockDelta(state, event)
  if (event.type === "content_block_stop") return onContentBlockStop(state, event)
  if (event.type === "message_delta") return Effect.succeed(onMessageDelta(state, event))
+  if (event.type === "message_stop") return Effect.succeed(onMessageStop(state))
  if (event.type === "error") return onError(event)
  return Effect.succeed<StepResult>([state, NO_EVENTS])
 }
@@ -933,7 +1013,11 @@ export const protocol = Protocol.make({
  },
  stream: {
    event: Protocol.jsonEvent(AnthropicEvent),
-    initial: () => ({ tools: ToolStream.empty<number>(), lifecycle: Lifecycle.initial() }),
+    initial: () => ({
+      tools: ToolStream.empty<number>(),
+      reasoningSignatures: {},
+      lifecycle: Lifecycle.initial(),
+    }),
    step,
  },
 })
@@ -66,14 +66,15 @@ const BedrockToolResultBlock = Schema.Struct({
 type BedrockToolResultBlock = Schema.Schema.Type<typeof BedrockToolResultBlock>

 const BedrockReasoningBlock = Schema.Struct({
-  reasoningContent: Schema.Struct({
-    reasoningText: Schema.optional(
-      Schema.Struct({
+  reasoningContent: Schema.Union([
+    Schema.Struct({
+      reasoningText: Schema.Struct({
        text: Schema.String,
        signature: Schema.optional(Schema.String),
      }),
-    ),
-  }),
+    }),
+    Schema.Struct({ redactedContent: Schema.String }),
+  ]),
 })

 const BedrockUserBlock = Schema.Union([
@@ -154,6 +155,12 @@ const BedrockUsageSchema = Schema.Struct({
 })
 type BedrockUsageSchema = Schema.Schema.Type<typeof BedrockUsageSchema>

+const BedrockStreamException = Schema.Struct({
+  message: Schema.optional(Schema.String),
+  originalMessage: Schema.optional(Schema.String),
+  originalStatusCode: Schema.optional(Schema.Number),
+})
+
 // Streaming event shape — the AWS event stream wraps each JSON payload by its
 // `:event-type` header (e.g. `messageStart`, `contentBlockDelta`). We
 // reconstruct that wrapping in `decodeFrames` below so the event schema can
@@ -181,6 +188,11 @@ const BedrockEvent = Schema.Struct({
            Schema.Struct({
              text: Schema.optional(Schema.String),
              signature: Schema.optional(Schema.String),
+              // Blob fields in Bedrock's JSON event stream are base64 strings.
+              redactedContent: Schema.optional(Schema.String),
+              // Vercel's Bedrock provider exposes the same delta under
+              // Anthropic's shorter `data` spelling.
+              data: Schema.optional(Schema.String),
            }),
          ),
        }),
@@ -200,11 +212,11 @@ const BedrockEvent = Schema.Struct({
      metrics: Schema.optional(Schema.Unknown),
    }),
  ),
-  internalServerException: Schema.optional(Schema.Struct({ message: Schema.String })),
-  modelStreamErrorException: Schema.optional(Schema.Struct({ message: Schema.String })),
-  validationException: Schema.optional(Schema.Struct({ message: Schema.String })),
-  throttlingException: Schema.optional(Schema.Struct({ message: Schema.String })),
-  serviceUnavailableException: Schema.optional(Schema.Struct({ message: Schema.String })),
+  internalServerException: Schema.optional(BedrockStreamException),
+  modelStreamErrorException: Schema.optional(BedrockStreamException),
+  validationException: Schema.optional(BedrockStreamException),
+  throttlingException: Schema.optional(BedrockStreamException),
+  serviceUnavailableException: Schema.optional(BedrockStreamException),
 })
 type BedrockEvent = Schema.Schema.Type<typeof BedrockEvent>

@@ -260,6 +272,13 @@ const reasoningSignature = (part: ReasoningPart) => {
  )
 }

+const reasoningRedactedData = (part: ReasoningPart) => {
+  const bedrock = part.providerMetadata?.bedrock
+  return ProviderShared.isRecord(bedrock) && typeof bedrock.redactedData === "string"
+    ? bedrock.redactedData
+    : undefined
+}
+
 const lowerToolCall = (part: ToolCallPart): BedrockToolUseBlock => ({
  toolUse: {
    toolUseId: part.id,
@@ -349,11 +368,13 @@ const lowerMessages = Effect.fn("BedrockConverse.lowerMessages")(function* (
          continue
        }
        if (part.type === "reasoning") {
-          content.push({
-            reasoningContent: {
-              reasoningText: { text: part.text, signature: reasoningSignature(part) },
-            },
-          })
+          const signature = reasoningSignature(part)
+          const redactedData = reasoningRedactedData(part)
+          if (signature === undefined && redactedData !== undefined) {
+            content.push({ reasoningContent: { redactedContent: redactedData } })
+            continue
+          }
+          content.push({ reasoningContent: { reasoningText: { text: part.text, signature } } })
          continue
        }
        if (part.type === "tool-call") {
@@ -519,12 +540,26 @@ const step = (state: ParserState, event: BedrockEvent) =>
      const index = event.contentBlockDelta.contentBlockIndex
      const reasoning = event.contentBlockDelta.delta.reasoningContent
      const events: LLMEvent[] = []
+      const redactedData = reasoning.redactedContent ?? reasoning.data
+      const providerMetadata = reasoning.signature
+        ? bedrockMetadata({ signature: reasoning.signature })
+        : redactedData !== undefined
+          ? bedrockMetadata({ redactedData })
+          : undefined
+      const lifecycle =
+        reasoning.text !== undefined || providerMetadata !== undefined
+          ? Lifecycle.reasoningDelta(
+              state.lifecycle,
+              events,
+              `reasoning-${index}`,
+              reasoning.text ?? "",
+              providerMetadata,
+            )
+          : state.lifecycle
      return [
        {
          ...state,
-          lifecycle: reasoning.text
-            ? Lifecycle.reasoningDelta(state.lifecycle, events, `reasoning-${index}`, reasoning.text)
-            : state.lifecycle,
+          lifecycle,
          reasoningSignatures: reasoning.signature
            ? { ...state.reasoningSignatures, [index]: reasoning.signature }
            : state.reasoningSignatures,
@@ -598,7 +633,7 @@ const step = (state: ParserState, event: BedrockEvent) =>
    }

    if (event.metadata) {
-      const usage = mapUsage(event.metadata.usage)
+      const usage = mapUsage(event.metadata.usage) ?? state.pendingFinish?.usage
      return [
        {
          ...state,
@@ -625,7 +660,7 @@ const step = (state: ParserState, event: BedrockEvent) =>
        module: ADAPTER,
        method: "stream",
        reason: classifyProviderFailure({
-          message: exception[1]?.message ?? "Bedrock Converse stream error",
+          message: exception[1]?.message ?? exception[1]?.originalMessage ?? "Bedrock Converse stream error",
          code: exception[0],
        }),
      })
@@ -53,8 +53,22 @@ const consumeFrames = (route: string) => (state: FrameBufferState, chunk: Uint8A
      })
      cursor = { buffer: cursor.buffer, offset: cursor.offset + totalLength }

-      if (decoded.headers[":message-type"]?.value !== "event") continue
-      const eventType = decoded.headers[":event-type"]?.value
+      const messageType = decoded.headers[":message-type"]?.value
+      if (messageType === "error") {
+        const code = decoded.headers[":error-code"]?.value
+        const message = decoded.headers[":error-message"]?.value
+        return yield* ProviderShared.eventError(
+          route,
+          [code, message].filter((value): value is string => typeof value === "string").join(": ") ||
+            "Bedrock Converse event-stream error",
+        )
+      }
+      const eventType =
+        messageType === "event"
+          ? decoded.headers[":event-type"]?.value
+          : messageType === "exception"
+            ? decoded.headers[":exception-type"]?.value
+            : undefined
      if (typeof eventType !== "string") continue
      const payload = utf8.decode(decoded.body)
      if (!payload) continue
@@ -1,4 +1,5 @@
 import { Effect, Schema } from "effect"
+import { Tool } from "@opencode-ai/schema/tool"
 import { Route } from "../route/client"
 import { Auth } from "../route/auth"
 import { Endpoint } from "../route/endpoint"
@@ -11,11 +12,11 @@ import {
  type JsonSchema,
  type LLMRequest,
  type MediaPart,
+  type ProviderOptions,
  type ProviderMetadata,
  type TextPart,
  type ToolCallPart,
  type ToolDefinition,
-  type ToolContent,
 } from "../schema"
 import { JsonObject, optionalArray, ProviderShared } from "./shared"
 import { GeminiToolSchema } from "./utils/gemini-tool-schema"
@@ -26,6 +27,18 @@ const ADAPTER = "gemini"
 const MEDIA_MIMES = new Set<string>(ProviderShared.MEDIA_MIMES)
 export const DEFAULT_BASE_URL = "https://generativelanguage.googleapis.com/v1beta"

+export interface OptionsInput {
+  readonly [key: string]: unknown
+  readonly thinkingConfig?: {
+    readonly thinkingBudget?: number
+    readonly includeThoughts?: boolean
+  }
+}
+
+export type ProviderOptionsInput = ProviderOptions & {
+  readonly gemini?: OptionsInput
+}
+
 // =============================================================================
 // Request Body Schema
 // =============================================================================
@@ -203,7 +216,9 @@ const thoughtSignature = (providerMetadata: ProviderMetadata | undefined) => {

 const functionCallId = (providerMetadata: ProviderMetadata | undefined) => {
  const google = providerMetadata?.google
-  return ProviderShared.isRecord(google) && typeof google.functionCallId === "string" ? google.functionCallId : undefined
+  return ProviderShared.isRecord(google) && typeof google.functionCallId === "string"
+    ? google.functionCallId
+    : undefined
 }

 const lowerToolCall = (part: ToolCallPart) => ({
@@ -274,7 +289,7 @@ const lowerMessages = Effect.fn("Gemini.lowerMessages")(function* (request: LLMR
        })
        continue
      }
-      const content: ReadonlyArray<ToolContent> = part.result.value
+      const content: ReadonlyArray<Tool.Content> = part.result.value
      const text = content.filter((item) => item.type === "text").map((item) => item.text)
      const media: GeminiInlineDataPart[] = []
      for (const item of content) {
@@ -300,21 +315,22 @@ const lowerMessages = Effect.fn("Gemini.lowerMessages")(function* (request: LLMR
  return contents
 })

-const geminiOptions = (request: LLMRequest) => request.providerOptions?.gemini
-
-const thinkingConfig = (request: LLMRequest) => {
-  const value = geminiOptions(request)?.thinkingConfig
-  if (!ProviderShared.isRecord(value)) return undefined
-  const result = {
+const resolveOptions = (request: LLMRequest) => {
+  const value = request.providerOptions?.gemini?.thinkingConfig
+  if (!ProviderShared.isRecord(value)) return {}
+  const thinkingConfig = {
    thinkingBudget: typeof value.thinkingBudget === "number" ? value.thinkingBudget : undefined,
    includeThoughts: typeof value.includeThoughts === "boolean" ? value.includeThoughts : undefined,
  }
-  return Object.values(result).some((item) => item !== undefined) ? result : undefined
+  return {
+    thinkingConfig: Object.values(thinkingConfig).some((item) => item !== undefined) ? thinkingConfig : undefined,
+  }
 }

 const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMRequest) {
  const hasTools = request.tools.length > 0
  const generation = request.generation
+  const options = resolveOptions(request)
  const toolSchemaCompatibility = request.model.compatibility?.toolSchema
  const generationConfig = {
    maxOutputTokens: generation?.maxTokens,
@@ -322,7 +338,7 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
    topP: generation?.topP,
    topK: generation?.topK,
    stopSequences: generation?.stop,
-    thinkingConfig: thinkingConfig(request),
+    thinkingConfig: options.thinkingConfig,
  }

  return {
@@ -6,3 +6,4 @@ export * as OpenAIImages from "./openai-images"
 export * as OpenAICompatibleChat from "./openai-compatible-chat"
 export * as OpenAICompatibleResponses from "./openai-compatible-responses"
 export * as OpenAIResponses from "./openai-responses"
+export * as OpenResponses from "./open-responses"
@@ -1,4 +1,5 @@
 import { Effect, Schema } from "effect"
+import { Tool } from "@opencode-ai/schema/tool"
 import { Route } from "../route/client"
 import { Auth } from "../route/auth"
 import { Endpoint } from "../route/endpoint"
@@ -17,7 +18,6 @@ import {
  type TextPart,
  type ToolCallPart,
  type ToolDefinition,
-  type ToolContent,
 } from "../schema"
 import { classifyProviderFailure } from "../provider-error"
 import { isRecord, JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared"
@@ -131,6 +131,7 @@ const OpenAIChatUsage = Schema.Struct({
  prompt_tokens_details: optionalNull(
    Schema.Struct({
      cached_tokens: Schema.optional(Schema.Number),
+      cache_write_tokens: Schema.optional(Schema.Number),
    }),
  ),
  completion_tokens_details: optionalNull(
@@ -334,7 +335,7 @@ const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (m
      messages.push({ role: "tool", tool_call_id: part.id, content: ProviderShared.toolResultText(part) })
      continue
    }
-    const content: ReadonlyArray<ToolContent> = part.result.value
+    const content: ReadonlyArray<Tool.Content> = part.result.value
    const text = content.filter((item) => item.type === "text").map((item) => item.text)
    messages.push({ role: "tool", tool_call_id: part.id, content: text.join("\n") })
    const files = content.filter((item) => item.type === "file")
@@ -396,14 +397,13 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
  return messages
 })

-const lowerOptions = Effect.fn("OpenAIChat.lowerOptions")(function* (request: LLMRequest) {
-  const store = OpenAIOptions.store(request)
-  const reasoningEffort = OpenAIOptions.reasoningEffort(request)
+const lowerOptions = (request: LLMRequest) => {
+  const options = OpenAIOptions.resolve(request)
  return {
-    ...(store !== undefined ? { store } : {}),
-    ...(reasoningEffort ? { reasoning_effort: reasoningEffort } : {}),
+    ...(options.store !== undefined ? { store: options.store } : {}),
+    ...(options.reasoningEffort ? { reasoning_effort: options.reasoningEffort } : {}),
  }
-})
+}

 const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (request: LLMRequest) {
  // `fromRequest` returns the provider body only. Endpoint, auth, framing,
@@ -434,7 +434,7 @@ const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (request: LLMR
    presence_penalty: generation?.presencePenalty,
    seed: generation?.seed,
    stop: generation?.stop,
-    ...(yield* lowerOptions(request)),
+    ...lowerOptions(request),
  }
 })

@@ -454,20 +454,22 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
 }

 // OpenAI Chat reports `prompt_tokens` (inclusive total) with a
-// `cached_tokens` subset, and `completion_tokens` (inclusive total) with
-// a `reasoning_tokens` subset. We pass the inclusive totals through and
-// derive the non-cached breakdown so the `LLM.Usage` contract is
+// cached-read and cache-write subsets, and `completion_tokens` (inclusive
+// total) with a `reasoning_tokens` subset. We pass the inclusive totals
+// through and derive the non-cached breakdown so the `LLM.Usage` contract is
 // satisfied on both sides.
 const mapUsage = (usage: OpenAIChatEvent["usage"]): Usage | undefined => {
  if (!usage) return undefined
  const cached = usage.prompt_tokens_details?.cached_tokens
+  const cacheWrite = usage.prompt_tokens_details?.cache_write_tokens
  const reasoning = usage.completion_tokens_details?.reasoning_tokens
-  const nonCached = ProviderShared.subtractTokens(usage.prompt_tokens, cached)
+  const nonCached = ProviderShared.subtractTokens(usage.prompt_tokens, ProviderShared.sumTokens(cached, cacheWrite))
  return new Usage({
    inputTokens: usage.prompt_tokens,
    outputTokens: usage.completion_tokens,
    nonCachedInputTokens: nonCached,
    cacheReadInputTokens: cached,
+    cacheWriteInputTokens: cacheWrite,
    reasoningTokens: reasoning,
    totalTokens: ProviderShared.totalTokens(usage.prompt_tokens, usage.completion_tokens, usage.total_tokens),
    providerMetadata: { openai: usage },
@@ -1,23 +1,22 @@
 import { Route, type RouteRoutedModelInput } from "../route/client"
 import { Endpoint } from "../route/endpoint"
-import { OpenAIResponses } from "./openai-responses"
+import { OpenResponses } from "./open-responses"

 const ADAPTER = "openai-compatible-responses"

 export type OpenAICompatibleResponsesModelInput = RouteRoutedModelInput

 /**
- * Route for providers that expose an OpenAI Responses-compatible `/responses`
- * endpoint. Provider helpers configure identity, endpoint, and auth before
- * model selection while this route reuses the OpenAI Responses protocol.
+ * Deployment adapter for providers that expose an Open Responses-compatible
+ * `/responses` endpoint. Provider helpers configure identity, endpoint, and
+ * auth while the semantic protocol remains provider-neutral.
 */
 export const route = Route.make({
  id: ADAPTER,
-  providerMetadataKey: "openai",
-  protocol: OpenAIResponses.protocol,
-  endpoint: Endpoint.path(OpenAIResponses.PATH),
-  transport: OpenAIResponses.httpTransport,
-  defaults: { providerOptions: { openai: { store: false } } },
+  providerMetadataKey: "openresponses",
+  protocol: OpenResponses.protocol,
+  endpoint: Endpoint.path(OpenResponses.PATH),
+  transport: OpenResponses.httpTransport,
 })

 export * as OpenAICompatibleResponses from "./openai-compatible-responses"
@@ -1,4 +1,5 @@
 import { Buffer } from "node:buffer"
+import { Tool } from "@opencode-ai/schema/tool"
 import { Effect, Schema, Stream } from "effect"
 import * as Sse from "effect/unstable/encoding/Sse"
 import { Headers, HttpClientRequest } from "effect/unstable/http"
@@ -9,7 +10,6 @@ import {
  type ContentPart,
  type LLMRequest,
  type MediaPart,
-  type ToolFileContent,
  type TextPart,
  type ToolResultPart,
 } from "../schema"
@@ -206,7 +206,7 @@ export const validateMedia = Effect.fn("ProviderShared.validateMedia")(function*
  return { mime, base64, dataUrl: `data:${mime};base64,${base64}`, bytes } satisfies ValidatedMedia
 })

-export const validateToolFile = (route: string, part: ToolFileContent, supportedMimes: ReadonlySet<string>) =>
+export const validateToolFile = (route: string, part: Tool.FileContent, supportedMimes: ReadonlySet<string>) =>
  validateMedia(route, { type: "media", mediaType: part.mime, data: part.uri, filename: part.name }, supportedMimes)

 export const trimBaseUrl = (value: string) => value.replace(/\/+$/, "")
@@ -14,16 +14,19 @@ export const stepStart = (state: State, events: LLMEvent[]): State => {
  return { ...state, stepStarted: true }
 }

-export const textDelta = (state: State, events: LLMEvent[], id: string, text: string): State => {
+export const textStart = (state: State, events: LLMEvent[], id: string, providerMetadata?: ProviderMetadata): State => {
+  if (state.text.has(id)) return state
  const stepped = stepStart(state, events)
-  if (stepped.text.has(id)) {
-    events.push(LLMEvent.textDelta({ id, text }))
-    return stepped
-  }
-  events.push(LLMEvent.textStart({ id }), LLMEvent.textDelta({ id, text }))
+  events.push(LLMEvent.textStart({ id, providerMetadata }))
  return { ...stepped, text: new Set([...stepped.text, id]) }
 }

+export const textDelta = (state: State, events: LLMEvent[], id: string, text: string): State => {
+  const started = textStart(state, events, id)
+  events.push(LLMEvent.textDelta({ id, text }))
+  return started
+}
+
 export const reasoningStart = (
  state: State,
  events: LLMEvent[],
@@ -0,0 +1,65 @@
+import { Schema } from "effect"
+import { TextVerbosity, type LLMRequest } from "../../schema"
+
+export const ResponseIncludables = [
+  "file_search_call.results",
+  "web_search_call.results",
+  "web_search_call.action.sources",
+  "message.input_image.image_url",
+  "computer_call_output.output.image_url",
+  "code_interpreter_call.outputs",
+  "reasoning.encrypted_content",
+  "message.output_text.logprobs",
+] as const
+export type ResponseIncludable = (typeof ResponseIncludables)[number]
+
+export const ServiceTiers = ["auto", "default", "flex", "priority"] as const
+export type ServiceTier = (typeof ServiceTiers)[number]
+
+const TEXT_VERBOSITY = new Set<string>(["low", "medium", "high"])
+const INCLUDABLES = new Set<string>(ResponseIncludables)
+const SERVICE_TIERS = new Set<string>(ServiceTiers)
+
+const isTextVerbosity = (value: unknown): value is Schema.Schema.Type<typeof TextVerbosity> =>
+  typeof value === "string" && TEXT_VERBOSITY.has(value)
+
+const isServiceTier = (value: unknown): value is ServiceTier => typeof value === "string" && SERVICE_TIERS.has(value)
+
+export const ReasoningEffort = Schema.String
+export const TextVerbositySchema = TextVerbosity
+export const ResponseIncludableSchema = Schema.Literals(ResponseIncludables)
+export const ServiceTierSchema = Schema.Literals(ServiceTiers)
+
+export interface Resolved {
+  readonly instructions?: string
+  readonly store?: boolean
+  readonly promptCacheKey?: string
+  readonly reasoningEffort?: string
+  readonly reasoningSummary?: "auto" | "concise" | "detailed"
+  readonly include?: ReadonlyArray<ResponseIncludable>
+  readonly textVerbosity?: Schema.Schema.Type<typeof TextVerbosity>
+  readonly serviceTier?: ServiceTier
+}
+
+export const resolve = (request: LLMRequest): Resolved => {
+  const input = request.providerOptions?.[request.model.route.providerMetadataKey ?? "openresponses"]
+  const include = Array.isArray(input?.include)
+    ? input.include.filter((entry): entry is ResponseIncludable => INCLUDABLES.has(entry))
+    : []
+  const reasoningSummary = input?.reasoningSummary
+  return {
+    instructions: typeof input?.instructions === "string" ? input.instructions : undefined,
+    store: typeof input?.store === "boolean" ? input.store : undefined,
+    promptCacheKey: typeof input?.promptCacheKey === "string" ? input.promptCacheKey : undefined,
+    reasoningEffort: typeof input?.reasoningEffort === "string" ? input.reasoningEffort : undefined,
+    reasoningSummary:
+      reasoningSummary === "auto" || reasoningSummary === "concise" || reasoningSummary === "detailed"
+        ? reasoningSummary
+        : undefined,
+    include: include.length > 0 ? include : undefined,
+    textVerbosity: isTextVerbosity(input?.textVerbosity) ? input.textVerbosity : undefined,
+    serviceTier: isServiceTier(input?.serviceTier) ? input.serviceTier : undefined,
+  }
+}
+
+export * as OpenResponsesOptions from "./open-responses-options"
@@ -1,85 +1,23 @@
-import { Schema } from "effect"
-import type { LLMRequest, TextVerbosity as TextVerbosityValue } from "../../schema"
-import { ReasoningEfforts, TextVerbosity } from "../../schema"
+import { ReasoningEfforts } from "../../schema"
+import { OpenResponsesOptions } from "./open-responses-options"

 export const OpenAIReasoningEfforts = ReasoningEfforts
 export type OpenAIReasoningEffort = string

 // Mirrors OpenAI's `ResponseIncludable` union from the official SDK. Keep this
 // in lockstep with `openai-node/src/resources/responses/responses.ts`.
-export const OpenAIResponseIncludables = [
-  "file_search_call.results",
-  "web_search_call.results",
-  "web_search_call.action.sources",
-  "message.input_image.image_url",
-  "computer_call_output.output.image_url",
-  "code_interpreter_call.outputs",
-  "reasoning.encrypted_content",
-  "message.output_text.logprobs",
-] as const
-export type OpenAIResponseIncludable = (typeof OpenAIResponseIncludables)[number]
-export const OpenAIServiceTiers = ["auto", "default", "flex", "priority"] as const
-export type OpenAIServiceTier = (typeof OpenAIServiceTiers)[number]
+export const OpenAIResponseIncludables = OpenResponsesOptions.ResponseIncludables
+export type OpenAIResponseIncludable = OpenResponsesOptions.ResponseIncludable
+export const OpenAIServiceTiers = OpenResponsesOptions.ServiceTiers
+export type OpenAIServiceTier = OpenResponsesOptions.ServiceTier

-const TEXT_VERBOSITY = new Set<string>(["low", "medium", "high"])
-const INCLUDABLES = new Set<string>(OpenAIResponseIncludables)
-const SERVICE_TIERS = new Set<string>(OpenAIServiceTiers)
-
-export const OpenAIReasoningEffort = Schema.String
-export const OpenAITextVerbosity = TextVerbosity
-export const OpenAIResponseIncludable = Schema.Literals(OpenAIResponseIncludables)
-export const OpenAIServiceTier = Schema.Literals(OpenAIServiceTiers)
+export const OpenAIReasoningEffort = OpenResponsesOptions.ReasoningEffort
+export const OpenAITextVerbosity = OpenResponsesOptions.TextVerbositySchema
+export const OpenAIResponseIncludable = OpenResponsesOptions.ResponseIncludableSchema
+export const OpenAIServiceTier = OpenResponsesOptions.ServiceTierSchema

 export const isReasoningEffort = (effort: unknown): effort is OpenAIReasoningEffort => typeof effort === "string"

-const isTextVerbosity = (value: unknown): value is TextVerbosityValue =>
-  typeof value === "string" && TEXT_VERBOSITY.has(value)
-
-const options = (request: LLMRequest) => request.providerOptions?.openai
-
-export const store = (request: LLMRequest): boolean | undefined => {
-  const value = options(request)?.store
-  return typeof value === "boolean" ? value : undefined
-}
-
-export const reasoningEffort = (request: LLMRequest): string | undefined => {
-  const value = options(request)?.reasoningEffort
-  return typeof value === "string" ? value : undefined
-}
-
-export const reasoningSummary = (request: LLMRequest): "auto" | undefined =>
-  options(request)?.reasoningSummary === "auto" ? "auto" : undefined
-
-// Resolve the OpenAI Responses `include` field. Filters out unknown
-// includable values defensively so a typo in upstream config drops the
-// invalid entry instead of poisoning the wire body. An empty array (either
-// passed directly or produced by filtering) is treated as "no include" and
-// returns undefined so the request body omits the field entirely.
-export const include = (request: LLMRequest): ReadonlyArray<OpenAIResponseIncludable> | undefined => {
-  const value = options(request)?.include
-  if (!Array.isArray(value)) return undefined
-  const filtered = value.filter((entry): entry is OpenAIResponseIncludable => INCLUDABLES.has(entry))
-  return filtered.length > 0 ? filtered : undefined
-}
-
-export const promptCacheKey = (request: LLMRequest) => {
-  const value = options(request)?.promptCacheKey
-  return typeof value === "string" ? value : undefined
-}
-
-export const textVerbosity = (request: LLMRequest) => {
-  const value = options(request)?.textVerbosity
-  return isTextVerbosity(value) ? value : undefined
-}
-
-export const serviceTier = (request: LLMRequest) => {
-  const value = options(request)?.serviceTier
-  return typeof value === "string" && SERVICE_TIERS.has(value) ? (value as OpenAIServiceTier) : undefined
-}
-
-export const instructions = (request: LLMRequest) => {
-  const value = options(request)?.instructions
-  return typeof value === "string" ? value : undefined
-}
+export const resolve = OpenResponsesOptions.resolve

 export * as OpenAIOptions from "./openai-options"
@@ -63,6 +63,8 @@ const openAI = (schema: JsonSchema): JsonSchema => {
  return isRecord(normalized) ? normalized : { type: "object" }
 }

+const responses = openAI
+
 const gemini = (schema: JsonSchema): JsonSchema => GeminiToolSchema.convert(schema) ?? {}

 const modelCompatibility = (
@@ -83,4 +85,5 @@ export const ToolSchemaProjection = {
  modelCompatibility,
  moonshot,
  openAI,
+  responses,
 } as const
@@ -5,12 +5,17 @@ import type { ProviderAuthOption } from "../route/auth-options"
 import type { RouteDefaultsInput } from "../route/client"
 import { ProviderID, type ModelID } from "../schema"

+export type AnthropicOptionsInput = AnthropicMessages.OptionsInput
+export type AnthropicProviderOptionsInput = AnthropicMessages.ProviderOptionsInput
+export type AnthropicThinkingInput = AnthropicMessages.ThinkingInput
+
 export const id = ProviderID.make("anthropic-compatible")

 export type Config = RouteDefaultsInput &
  ProviderAuthOption<"optional"> & {
    readonly provider?: string
    readonly baseURL: string
+    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
  }

 export type Settings = ProviderPackage.Settings &
@@ -20,6 +25,7 @@ export type Settings = ProviderPackage.Settings &
  ) & {
    readonly baseURL: string
    readonly provider?: string
+    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
  }

 export const routes = [AnthropicMessages.route]
@@ -61,6 +67,7 @@ export const model: ProviderPackage.Definition<Settings>["model"] = (modelID, se
    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
    limits: settings.limits,
    provider: settings.provider,
+    providerOptions: settings.providerOptions,
  }).model(modelID)
 }

@@ -6,11 +6,19 @@ import { ProviderID, type ModelID } from "../schema"
 import { AnthropicMessages } from "../protocols/anthropic-messages"
 import { AnthropicCompatible } from "./anthropic-compatible"

+export type AnthropicOptionsInput = AnthropicMessages.OptionsInput
+export type AnthropicProviderOptionsInput = AnthropicMessages.ProviderOptionsInput
+export type AnthropicThinkingInput = AnthropicMessages.ThinkingInput
+
 export const id = ProviderID.make("anthropic")

 export const routes = [AnthropicMessages.route]

-export type Config = RouteDefaultsInput & ProviderAuthOption<"optional"> & { readonly baseURL?: string }
+export type Config = RouteDefaultsInput &
+  ProviderAuthOption<"optional"> & {
+    readonly baseURL?: string
+    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
+  }

 export type Settings = ProviderPackage.Settings &
  (
@@ -18,6 +26,7 @@ export type Settings = ProviderPackage.Settings &
    | { readonly apiKey?: never; readonly authToken?: string }
  ) & {
    readonly baseURL?: string
+    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
  }

 const auth = (options: ProviderAuthOption<"optional">) => {
@@ -52,5 +61,6 @@ export const model: ProviderPackage.Definition<Settings>["model"] = (modelID, se
    headers: settings.headers === undefined ? undefined : { ...settings.headers },
    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
    limits: settings.limits,
+    providerOptions: settings.providerOptions,
  }).model(modelID)
 }
@@ -6,9 +6,13 @@ import { Route, type RouteDefaultsInput } from "../route/client"
 import { Endpoint } from "../route/endpoint"
 import { Framing } from "../route/framing"
 import { Protocol } from "../route/protocol"
-import { ProviderID, type ModelID, type ProviderOptions } from "../schema"
+import { ProviderID, type ModelID } from "../schema"
 import { GoogleVertexShared } from "./google-vertex-shared"

+export type AnthropicOptionsInput = AnthropicMessages.OptionsInput
+export type AnthropicProviderOptionsInput = AnthropicMessages.ProviderOptionsInput
+export type AnthropicThinkingInput = AnthropicMessages.ThinkingInput
+
 const VERSION = "vertex-2023-10-16" as const

 // models.dev uses this provider id even though the API contract is Anthropic Messages.
@@ -19,6 +23,7 @@ export type Config = RouteDefaultsInput &
    readonly baseURL?: string
    readonly location?: string
    readonly project?: string
+    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
  }

 export interface Settings extends ProviderPackage.Settings {
@@ -27,7 +32,7 @@ export interface Settings extends ProviderPackage.Settings {
  readonly baseURL?: string
  readonly location?: string
  readonly project?: string
-  readonly providerOptions?: ProviderOptions
+  readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
 }

 const route = Route.make({
@@ -25,6 +25,7 @@ export interface Settings extends ProviderPackage.Settings {
 const route = OpenAICompatibleResponses.route.with({
  id: "google-vertex-responses",
  provider: id,
+  providerOptions: { openresponses: { store: false } },
 })

 export const routes = [route]
@@ -4,9 +4,12 @@ import { Auth } from "../route/auth"
 import { Route, type RouteDefaultsInput } from "../route/client"
 import { Endpoint } from "../route/endpoint"
 import { Framing } from "../route/framing"
-import { ProviderID, type ModelID, type ProviderOptions } from "../schema"
+import { ProviderID, type ModelID } from "../schema"
 import { GoogleVertexShared } from "./google-vertex-shared"

+export type GeminiOptionsInput = Gemini.OptionsInput
+export type GeminiProviderOptionsInput = Gemini.ProviderOptionsInput
+
 export const id = ProviderID.make("google-vertex")

 export type Config = RouteDefaultsInput &
@@ -14,6 +17,7 @@ export type Config = RouteDefaultsInput &
    readonly baseURL?: string
    readonly location?: string
    readonly project?: string
+    readonly providerOptions?: Gemini.ProviderOptionsInput
  }

 export type Settings = ProviderPackage.Settings &
@@ -24,7 +28,7 @@ export type Settings = ProviderPackage.Settings &
    readonly baseURL?: string
    readonly location?: string
    readonly project?: string
-    readonly providerOptions?: ProviderOptions
+    readonly providerOptions?: Gemini.ProviderOptionsInput
  }

 const route = Route.make({
@@ -2,11 +2,13 @@ import type { RouteDefaultsInput } from "../route/client"
 import { Auth } from "../route/auth"
 import type { ProviderAuthOption } from "../route/auth-options"
 import type { ProviderPackage } from "../provider-package"
-import { HttpOptions, ProviderID, mergeHttpOptions, type ModelID, type ProviderOptions } from "../schema"
+import { HttpOptions, ProviderID, mergeHttpOptions, type ModelID } from "../schema"
 import { Gemini } from "../protocols/gemini"
 import { GoogleImages } from "../protocols/google-images"

 export type { GoogleImageOptions } from "../protocols/google-images"
+export type GeminiOptionsInput = Gemini.OptionsInput
+export type GeminiProviderOptionsInput = Gemini.ProviderOptionsInput

 export const id = ProviderID.make("google")

@@ -15,12 +17,13 @@ export const routes = [Gemini.route]
 export type Config = RouteDefaultsInput &
  ProviderAuthOption<"optional"> & {
    readonly baseURL?: string
+    readonly providerOptions?: Gemini.ProviderOptionsInput
  }

 export interface Settings extends ProviderPackage.Settings {
  readonly apiKey?: string
  readonly baseURL?: string
-  readonly providerOptions?: ProviderOptions
+  readonly providerOptions?: Gemini.ProviderOptionsInput
 }

 const auth = (options: ProviderAuthOption<"optional">) => {
@@ -0,0 +1,20 @@
+import type { ResponseIncludable, ServiceTier } from "../protocols/utils/open-responses-options"
+import type { ProviderOptions, ReasoningEffort, TextVerbosity } from "../schema"
+
+export interface OpenResponsesOptionsInput {
+  readonly [key: string]: unknown
+  readonly instructions?: string
+  readonly store?: boolean
+  readonly promptCacheKey?: string
+  readonly reasoningEffort?: ReasoningEffort
+  readonly reasoningSummary?: "auto" | "concise" | "detailed"
+  readonly include?: ReadonlyArray<ResponseIncludable>
+  readonly textVerbosity?: TextVerbosity
+  readonly serviceTier?: ServiceTier
+}
+
+export type OpenResponsesProviderOptionsInput = ProviderOptions & {
+  readonly openresponses?: OpenResponsesOptionsInput
+}
+
+export * as OpenResponsesProviderOptions from "./open-responses-options"
@@ -3,7 +3,9 @@ import { OpenAICompatibleResponses } from "../protocols/openai-compatible-respon
 import { AuthOptions, type ProviderAuthOption } from "../route/auth-options"
 import type { RouteDefaultsInput } from "../route/client"
 import { ProviderID, type ModelID } from "../schema"
-import type { OpenAIProviderOptionsInput } from "./openai-options"
+import type { OpenResponsesProviderOptionsInput } from "./open-responses-options"
+
+export type { OpenResponsesOptionsInput, OpenResponsesProviderOptionsInput } from "./open-responses-options"

 export const id = ProviderID.make("openai-compatible")

@@ -11,13 +13,14 @@ export type Config = RouteDefaultsInput &
  ProviderAuthOption<"optional"> & {
    readonly provider?: string
    readonly baseURL: string
+    readonly providerOptions?: OpenResponsesProviderOptionsInput
  }

 export interface Settings extends ProviderPackage.Settings {
  readonly apiKey?: string
  readonly baseURL: string
  readonly provider?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
+  readonly providerOptions?: OpenResponsesProviderOptionsInput
 }

 export const routes = [OpenAICompatibleResponses.route]
@@ -1,22 +1,10 @@
-import type { ProviderOptions, ReasoningEffort, TextVerbosity } from "../schema"
+import type { ProviderOptions } from "../schema"
 import { mergeProviderOptions } from "../schema"
-import type { OpenAIResponseIncludable, OpenAIServiceTier } from "../protocols/utils/openai-options"
+import type { OpenResponsesOptionsInput } from "./open-responses-options"

 export type { OpenAIResponseIncludable, OpenAIServiceTier } from "../protocols/utils/openai-options"

-export interface OpenAIOptionsInput {
-  readonly [key: string]: unknown
-  readonly store?: boolean
-  readonly promptCacheKey?: string
-  readonly reasoningEffort?: ReasoningEffort
-  readonly reasoningSummary?: "auto"
-  // OpenAI Responses `include` wire field. Mirrors the official SDK's
-  // `ResponseIncludable[]` union exactly so AI SDK callers and direct
-  // native-SDK callers share one shape and no translation is required.
-  readonly include?: ReadonlyArray<OpenAIResponseIncludable>
-  readonly textVerbosity?: TextVerbosity
-  readonly serviceTier?: OpenAIServiceTier
-}
+export type OpenAIOptionsInput = OpenResponsesOptionsInput

 export type OpenAIProviderOptionsInput = ProviderOptions & {
  readonly openai?: OpenAIOptionsInput
@@ -12,7 +12,8 @@ import type { LLMError, LLMEvent, LLMRequest, ProtocolID } from "../schema"
 * Examples:
 *
 * - `OpenAIChat.protocol` — chat completions style
- * - `OpenAIResponses.protocol` — responses API
+ * - `OpenResponses.protocol` — provider-neutral Responses API baseline
+ * - `OpenAIResponses.protocol` — OpenAI extensions to that baseline
 * - `AnthropicMessages.protocol` — messages API with content blocks
 * - `Gemini.protocol` — generateContent
 * - `BedrockConverse.protocol` — Converse with binary event-stream framing
@@ -1,4 +1,5 @@
 import { Schema } from "effect"
+import { Tool } from "@opencode-ai/schema/tool"
 import { ModelID, ProviderID, ProviderMetadata, RouteID } from "./ids"

 export const ProviderFailureClassification = Schema.Literal("context-overflow")
@@ -152,8 +153,4 @@ export class LLMError extends Schema.TaggedErrorClass<LLMError>()("LLM.Error", {
 * Anything thrown or yielded by a handler that is not a `ToolFailure` is
 * treated as a defect and fails the stream.
 */
-export class ToolFailure extends Schema.TaggedErrorClass<ToolFailure>()("LLM.ToolFailure", {
-  message: Schema.String,
-  error: Schema.optional(Schema.Defect()),
-  metadata: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
-}) {}
+export class ToolFailure extends Tool.Error {}
@@ -40,9 +40,9 @@ import { ProviderFailureClassification } from "./errors"
 * - Anthropic and Bedrock report the input breakdown natively: Anthropic's
 *   `input_tokens` and Bedrock's `inputTokens` are non-cached only. Their
 *   mappers sum the breakdown to derive the inclusive `inputTokens`.
- *   Anthropic does *not* break extended-thinking out of `output_tokens`, so
- *   `reasoningTokens` is `undefined` and `outputTokens` carries the
- *   combined total — a documented limitation of the Anthropic API.
+ *   Anthropic's `outputTokens` includes extended thinking. Newer responses
+ *   expose that subset as `output_tokens_details.thinking_tokens`, which maps
+ *   to `reasoningTokens`; older responses leave it undefined.
 *
 * `providerMetadata` always carries the provider's raw usage payload —
 * keyed by provider name (`{ openai: ... }`, `{ anthropic: ... }`, etc.)
@@ -1,5 +1,5 @@
 import { Schema } from "effect"
-import { ToolContent, ToolFileContent, ToolTextContent } from "@opencode-ai/schema/llm"
+import { Tool } from "@opencode-ai/schema/tool"
 import { JsonSchema, MessageRole, ProviderMetadata } from "./ids"
 import { CacheHint, CachePolicy, GenerationOptions, HttpOptions, ModelSchema, ProviderOptions } from "./options"
 import { isRecord } from "../utils/record"
@@ -40,8 +40,6 @@ export const MediaPart = Schema.Struct({
 }).annotate({ identifier: "LLM.Content.Media" })
 export type MediaPart = Schema.Schema.Type<typeof MediaPart>

-export { ToolContent, ToolFileContent, ToolTextContent }
-
 const isToolResultValue = (value: unknown): value is ToolResultValue =>
  isRecord(value) &&
  (value.type === "text" || value.type === "json" || value.type === "error" || value.type === "content") &&
@@ -63,7 +61,7 @@ export const ToolResultValue = Object.assign(
    }),
    Schema.Struct({
      type: Schema.Literal("content"),
-      value: Schema.Array(ToolContent),
+      value: Schema.Array(Tool.Content),
    }),
  ]).annotate({ identifier: "LLM.ToolResult" }),
  {
@@ -79,16 +77,16 @@ export type ToolResultValue = Schema.Schema.Type<typeof ToolResultValue>

 export interface ToolOutput {
  readonly structured: unknown
-  readonly content: ReadonlyArray<ToolContent>
+  readonly content: ReadonlyArray<Tool.Content>
 }

 export const ToolOutput = Object.assign(
  Schema.Struct({
    structured: Schema.Unknown,
-    content: Schema.Array(ToolContent),
+    content: Schema.Array(Tool.Content),
  }).annotate({ identifier: "LLM.ToolOutput" }),
  {
-    make: (structured: unknown, content: ReadonlyArray<ToolContent> = []): ToolOutput => ({ structured, content }),
+    make: (structured: unknown, content: ReadonlyArray<Tool.Content> = []): ToolOutput => ({ structured, content }),
    fromResultValue: (result: ToolResultValue): ToolOutput | undefined => {
      switch (result.type) {
        case "json":
@@ -251,11 +251,11 @@ export class CacheHint extends Schema.Class<CacheHint>("LLM.CacheHint")({
 // Auto-placement policy for prompt caching. The protocol-neutral lowering step
 // reads this and injects `CacheHint`s at the configured boundaries; the
 // per-protocol body builders then translate those hints into wire markers as
-// usual. `"auto"` is the recommended default for agent loops — it places one
-// breakpoint at the last tool definition, one at the last system part, and one
-// at the latest user message. The combination of provider invalidation
-// hierarchy (tools → system → messages) and Anthropic/Bedrock's 20-block
-// lookback means three trailing breakpoints reliably cover the static prefix.
+// usual. `"auto"` is the recommended default for agent loops — it places
+// breakpoints at the last tool definition, the first and last distinct system
+// parts, and the conversation tail. The rolling message breakpoint keeps a
+// prior cache entry within Anthropic/Bedrock's 20-block lookback during long
+// tool loops.
 //
 // Pass `"none"` to opt out entirely (the legacy behavior). Pass the granular
 // object form to override individual choices.
@@ -28,7 +28,7 @@ export const dispatch = (tools: Tools, call: ToolCallPart): Effect.Effect<Dispat

  return decodeAndExecute(tool, call).pipe(
    Effect.map((value) => result(call, value)),
-    Effect.catchTag("LLM.ToolFailure", (failure) =>
+    Effect.catchTag("Tool.Error", (failure) =>
      Effect.succeed(result(call, { type: "error", value: failure.message }, failure.error)),
    ),
  )
@@ -1,7 +1,7 @@
 import { Effect, JsonSchema, Schema } from "effect"
+import { Tool } from "@opencode-ai/schema/tool"
 import type {
  ToolCallPart,
-  ToolContent,
  ToolDefinition as ToolDefinitionClass,
  ToolOutput as ToolOutputType,
 } from "./schema"
@@ -31,7 +31,7 @@ export interface ToolModelOutputInput<Parameters, Output> {

 export type ToolToModelOutput<Parameters extends ToolSchema<any>, Success extends ToolSchema<any>> = (
  input: ToolModelOutputInput<Schema.Schema.Type<Parameters>, Success["Encoded"]>,
-) => ReadonlyArray<ToolContent>
+) => ReadonlyArray<Tool.Content>

 /**
 * A type-safe LLM tool. Each tool bundles its own description, parameter
@@ -95,7 +95,7 @@ type DynamicToolConfig = {
  readonly jsonSchema: JsonSchema.JsonSchema
  readonly outputSchema?: JsonSchema.JsonSchema
  readonly execute?: (params: unknown, context?: ToolExecuteContext) => Effect.Effect<unknown, ToolFailure>
-  readonly toModelOutput?: (input: ToolModelOutputInput<unknown, unknown>) => ReadonlyArray<ToolContent>
+  readonly toModelOutput?: (input: ToolModelOutputInput<unknown, unknown>) => ReadonlyArray<Tool.Content>
  readonly toStructuredOutput?: (output: unknown) => unknown
 }

@@ -151,7 +151,7 @@ export function make(config: {
  readonly jsonSchema: JsonSchema.JsonSchema
  readonly outputSchema?: JsonSchema.JsonSchema
  readonly execute: (params: unknown, context?: ToolExecuteContext) => Effect.Effect<unknown, ToolFailure>
-  readonly toModelOutput?: (input: ToolModelOutputInput<unknown, unknown>) => ReadonlyArray<ToolContent>
+  readonly toModelOutput?: (input: ToolModelOutputInput<unknown, unknown>) => ReadonlyArray<Tool.Content>
  readonly toStructuredOutput?: (output: unknown) => unknown
 }): AnyExecutableTool
 export function make(config: {
@@ -159,7 +159,7 @@ export function make(config: {
  readonly jsonSchema: JsonSchema.JsonSchema
  readonly outputSchema?: JsonSchema.JsonSchema
  readonly execute?: undefined
-  readonly toModelOutput?: (input: ToolModelOutputInput<unknown, unknown>) => ReadonlyArray<ToolContent>
+  readonly toModelOutput?: (input: ToolModelOutputInput<unknown, unknown>) => ReadonlyArray<Tool.Content>
  readonly toStructuredOutput?: (output: unknown) => unknown
 }): AnyTool
 export function make(config: TypedToolConfig | DynamicToolConfig): AnyTool {
@@ -236,7 +236,7 @@ const toJsonSchema = (schema: Schema.Top): JsonSchema.JsonSchema => {
 }

 const project = (
-  toModelOutput: ((input: ToolModelOutputInput<any, any>) => ReadonlyArray<ToolContent>) | undefined,
+  toModelOutput: ((input: ToolModelOutputInput<any, any>) => ReadonlyArray<Tool.Content>) | undefined,
  toStructuredOutput: ((output: unknown) => unknown) | undefined,
  parameters: unknown,
  callID: ToolCallPart["id"],
@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect, Schema, Stream } from "effect"
-import { LLM, LLMResponse } from "../src"
+import { LLM, LLMRequest, LLMResponse } from "../src"
 import { Route, Endpoint, LLMClient, Protocol, type FramingDef } from "../src/route"
 import { Model } from "../src/schema"
 import { testEffect } from "./lib/effect"
@@ -141,7 +141,7 @@ describe("llm route", () => {
    Effect.gen(function* () {
      const llm = yield* LLMClient.Service
      const prepared = yield* llm.prepare(
-        LLM.updateRequest(request, { model: updateModel(request.model, { route: configuredGemini }) }),
+        LLMRequest.update(request, { model: updateModel(request.model, { route: configuredGemini }) }),
      )

      expect(prepared.route).toBe("gemini-fake")
@@ -174,7 +174,7 @@ describe("llm route", () => {
      })

      const prepared = yield* (yield* LLMClient.Service).prepare(
-        LLM.updateRequest(request, { model: updateModel(request.model, { route: duplicate }) }),
+        LLMRequest.update(request, { model: updateModel(request.model, { route: duplicate }) }),
      )

      expect(prepared.body).toEqual({ body: "late-default" })
@@ -137,15 +137,26 @@ Azure.configure({ apiKey: "azure-key", resourceName: "resource" }).chat("deploym
 Azure.configure({ resourceName: "resource", apiKey: "azure-key", auth: Auth.header("api-key", "override") })

 Anthropic.configure({ apiKey: "anthropic-key" }).model("claude-haiku")
+Anthropic.configure({
+  apiKey: "anthropic-key",
+  providerOptions: {
+    anthropic: { thinking: { type: "enabled", budgetTokens: 1_024 }, effort: "high" },
+  },
+}).model("claude-haiku")
 // @ts-expect-error Anthropic model selectors only accept model ids.
 Anthropic.configure({ apiKey: "anthropic-key" }).model("claude-haiku", {})
 // @ts-expect-error Anthropic package settings accept only one auth source.
 Anthropic.model("claude-sonnet-4-6", { apiKey: "anthropic-key", authToken: "anthropic-token" })
+// @ts-expect-error Enabled Anthropic thinking requires a token budget.
+Anthropic.configure({ providerOptions: { anthropic: { thinking: { type: "enabled" } } } })
+// @ts-expect-error Anthropic thinking budgets must be numbers.
+Anthropic.configure({ providerOptions: { anthropic: { thinking: { type: "enabled", budgetTokens: "large" } } } })

 AnthropicCompatible.configure({
  apiKey: "messages-key",
  baseURL: "https://messages.example.com/v1",
  provider: "example",
+  providerOptions: { anthropic: { thinking: { type: "disabled" } } },
 }).model("compatible-model")
 // @ts-expect-error Anthropic-compatible providers require a base URL.
 AnthropicCompatible.configure({ apiKey: "messages-key" })
@@ -159,10 +170,19 @@ AnthropicCompatible.model("compatible-model", {
 })

 Google.configure({ apiKey: "google-key" }).model("gemini-2.5-flash")
+Google.configure({
+  apiKey: "google-key",
+  providerOptions: { gemini: { thinkingConfig: { thinkingBudget: 0, includeThoughts: false } } },
+}).model("gemini-2.5-flash")
 // @ts-expect-error Google model selectors only accept model ids.
 Google.configure({ apiKey: "google-key" }).model("gemini-2.5-flash", {})
+// @ts-expect-error Gemini thinking budgets must be numbers.
+Google.configure({ providerOptions: { gemini: { thinkingConfig: { thinkingBudget: "large" } } } })

-GoogleVertex.configure({ apiKey: "vertex-key" }).model("gemini-3.5-flash")
+GoogleVertex.configure({
+  apiKey: "vertex-key",
+  providerOptions: { gemini: { thinkingConfig: { thinkingBudget: 1_024 } } },
+}).model("gemini-3.5-flash")
 GoogleVertex.configure({ accessToken: "vertex-token", project: "project" }).model("gemini-3.5-flash")
 GoogleVertex.configure({ auth: Auth.bearer("vertex-token"), project: "project" }).model("gemini-3.5-flash")
 // @ts-expect-error Vertex Gemini model selectors only accept model ids.
@@ -208,7 +228,11 @@ GoogleVertexResponses.configure({
  project: "project",
 })

-GoogleVertexMessages.configure({ accessToken: "vertex-token", project: "project" }).model("claude-sonnet-4-6")
+GoogleVertexMessages.configure({
+  accessToken: "vertex-token",
+  project: "project",
+  providerOptions: { anthropic: { thinking: { type: "adaptive", display: "omitted" }, effort: "low" } },
+}).model("claude-sonnet-4-6")
 // @ts-expect-error Vertex Messages package settings do not accept API keys.
 GoogleVertexMessages.model("claude-sonnet-4-6", { apiKey: "vertex-key", project: "project" })
 GoogleVertexMessages.configure({ auth: Auth.bearer("vertex-token"), project: "project" }).model("claude-sonnet-4-6")
@@ -39,8 +39,8 @@ describe("applyCachePolicy", () => {
        }),
      )

-      // No explicit cache field → auto policy fires → last system part + latest
-      // user message both get cache_control markers.
+      // A single system block is both the first and last boundary, so the auto
+      // policy deduplicates it and still marks the conversation tail.
      expect(prepared.body).toMatchObject({
        system: [{ type: "text", text: "You are concise.", cache_control: { type: "ephemeral" } }],
        messages: [{ role: "user", content: [{ type: "text", text: "hi", cache_control: { type: "ephemeral" } }] }],
@@ -48,12 +48,15 @@ describe("applyCachePolicy", () => {
    }),
  )

-  it.effect("'auto' marks the last tool, last system part, and latest user message on Anthropic", () =>
+  it.effect("'auto' marks the last tool, first and last system parts, and final message boundary on Anthropic", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare(
        LLM.request({
          model: anthropicModel,
-          system: "Sys A",
+          system: [
+            { type: "text", text: "Base agent" },
+            { type: "text", text: "Project instructions" },
+          ],
          tools: [{ name: "t1", description: "t1", inputSchema: { type: "object", properties: {} } }],
          messages: [
            Message.user("first user"),
@@ -66,7 +69,10 @@ describe("applyCachePolicy", () => {

      expect(prepared.body).toMatchObject({
        tools: [{ name: "t1", cache_control: { type: "ephemeral" } }],
-        system: [{ type: "text", text: "Sys A", cache_control: { type: "ephemeral" } }],
+        system: [
+          { type: "text", text: "Base agent", cache_control: { type: "ephemeral" } },
+          { type: "text", text: "Project instructions", cache_control: { type: "ephemeral" } },
+        ],
        messages: [
          { role: "user", content: [{ type: "text", text: "first user" }] },
          { role: "assistant", content: [{ type: "text", text: "assistant reply" }] },
@@ -120,7 +126,10 @@ describe("applyCachePolicy", () => {
      const prepared = yield* LLMClient.prepare(
        LLM.request({
          model: bedrockModel,
-          system: "Sys",
+          system: [
+            { type: "text", text: "Base agent" },
+            { type: "text", text: "Project instructions" },
+          ],
          tools: [{ name: "t1", description: "t1", inputSchema: { type: "object", properties: {} } }],
          messages: [Message.user("first user"), Message.assistant("reply"), Message.user("latest user")],
          cache: "auto",
@@ -131,7 +140,12 @@ describe("applyCachePolicy", () => {
        toolConfig: {
          tools: [{ toolSpec: { name: "t1" } }, { cachePoint: { type: "default" } }],
        },
-        system: [{ text: "Sys" }, { cachePoint: { type: "default" } }],
+        system: [
+          { text: "Base agent" },
+          { cachePoint: { type: "default" } },
+          { text: "Project instructions" },
+          { cachePoint: { type: "default" } },
+        ],
        messages: [
          { role: "user", content: [{ text: "first user" }] },
          { role: "assistant", content: [{ text: "reply" }] },
@@ -193,9 +207,55 @@ describe("applyCachePolicy", () => {
        }),
      )

-      const body = prepared.body as { system: Array<{ text: string; cache_control?: unknown }> }
+      const body = prepared.body as {
+        system: Array<{ text: string; cache_control?: unknown }>
+        messages: Array<{ content: Array<{ cache_control?: unknown }> }>
+      }
      expect(body.system[0]?.cache_control).toEqual({ type: "ephemeral", ttl: "1h" })
      expect(body.system[1]?.cache_control).toEqual({ type: "ephemeral" })
+      expect(body.messages[0]?.content[0]?.cache_control).toEqual({ type: "ephemeral" })
+    }),
+  )
+
+  it.effect("auto policy stays within the four-breakpoint cap when preserving manual hints", () =>
+    Effect.gen(function* () {
+      const request = LLM.request({
+        model: anthropicModel,
+        system: [
+          { type: "text", text: "Base agent" },
+          {
+            type: "text",
+            text: "Manual context",
+            cache: new CacheHint({ type: "ephemeral", ttlSeconds: 3600 }),
+          },
+          { type: "text", text: "Project instructions" },
+        ],
+        tools: [{ name: "t1", description: "t1", inputSchema: { type: "object", properties: {} } }],
+        prompt: "hi",
+        cache: "auto",
+      })
+      const applied = applyCachePolicy(request)
+      expect(applied.tools[0]?.cache).toBeDefined()
+      expect(applied.system.map((part) => part.cache !== undefined)).toEqual([true, true, true])
+      const tail = applied.messages[0]!.content[0]!
+      expect("cache" in tail ? tail.cache : undefined).toBeUndefined()
+      expect(applyCachePolicy(applied)).toBe(applied)
+
+      const prepared = yield* LLMClient.prepare(request)
+
+      const body = prepared.body as {
+        tools: Array<{ cache_control?: unknown }>
+        system: Array<{ cache_control?: unknown }>
+        messages: Array<{ content: Array<{ cache_control?: unknown }> }>
+      }
+      const marked = [
+        ...body.tools.map((tool) => tool.cache_control),
+        ...body.system.map((part) => part.cache_control),
+        ...body.messages.flatMap((message) => message.content.map((part) => part.cache_control)),
+      ].filter((cache) => cache !== undefined)
+      expect(marked).toHaveLength(4)
+      expect(body.system[1]?.cache_control).toEqual({ type: "ephemeral", ttl: "1h" })
+      expect(body.messages[0]?.content[0]?.cache_control).toBeUndefined()
    }),
  )

@@ -11,7 +11,13 @@ import {
  XAI,
 } from "@opencode-ai/ai/providers"
 import * as GitHubCopilot from "@opencode-ai/ai/providers/github-copilot"
-import { OpenAIChat, OpenAICompatibleChat, OpenAICompatibleResponses, OpenAIResponses } from "@opencode-ai/ai/protocols"
+import {
+  OpenAIChat,
+  OpenAICompatibleChat,
+  OpenAICompatibleResponses,
+  OpenAIResponses,
+  OpenResponses,
+} from "@opencode-ai/ai/protocols"
 import * as AnthropicMessages from "@opencode-ai/ai/protocols/anthropic-messages"

 describe("public exports", () => {
@@ -74,7 +80,9 @@ describe("public exports", () => {
  test("protocol barrels expose supported low-level routes", () => {
    expect(OpenAIChat.route.id).toBe("openai-chat")
    expect(OpenAICompatibleChat.route.id).toBe("openai-compatible-chat")
+    expect(OpenResponses.protocol.id).toBe("open-responses")
    expect(OpenAICompatibleResponses.route.id).toBe("openai-compatible-responses")
+    expect(OpenAICompatibleResponses.route.protocol).toBe("open-responses")
    expect(OpenAIResponses.route.id).toBe("openai-responses")
    expect(OpenAIResponses.webSocketRoute.id).toBe("openai-responses-websocket")
    expect(AnthropicMessages.route.id).toBe("anthropic-messages")
@@ -2,7 +2,16 @@ import { describe, expect, test } from "bun:test"
 import { CacheHint, LLM, LLMResponse } from "../src"
 import * as OpenAIChat from "../src/protocols/openai-chat"
 import * as OpenAIResponses from "../src/protocols/openai-responses"
-import { LLMRequest, Message, Model, ToolCallPart, ToolChoice, ToolDefinition, ToolResultPart } from "../src/schema"
+import {
+  GenerationOptions,
+  LLMRequest,
+  Message,
+  Model,
+  ToolCallPart,
+  ToolChoice,
+  ToolDefinition,
+  ToolResultPart,
+} from "../src/schema"

 const chatRoute = OpenAIChat.route
 const responsesRoute = OpenAIResponses.route
@@ -31,8 +40,8 @@ describe("llm constructors", () => {
      model: Model.make({ id: "fake-model", provider: "fake", route: chatRoute }),
      prompt: "Say hello.",
    })
-    const updated = LLM.updateRequest(base, {
-      generation: { maxTokens: 20 },
+    const updated = LLMRequest.update(base, {
+      generation: GenerationOptions.make({ maxTokens: 20 }),
      messages: [...base.messages, Message.assistant("Hi.")],
    })

@@ -59,7 +59,7 @@ describe("provider package entrypoints", () => {
      headers: { "x-application": "opencode" },
      body: { service_tier: "priority" },
      limits: { context: 200_000, output: 64_000 },
-      providerOptions: { openai: { reasoningEffort: "low", store: true } },
+      providerOptions: { openresponses: { reasoningEffort: "low", store: true } },
    })

    expect(String(selected.provider)).toBe("example")
@@ -72,7 +72,7 @@ describe("provider package entrypoints", () => {
    expect(selected.route.defaults.http?.body).toEqual({ service_tier: "priority" })
    expect(selected.route.defaults.limits).toEqual({ context: 200_000, output: 64_000 })
    expect(selected.route.defaults.providerOptions).toEqual({
-      openai: { reasoningEffort: "low", store: true },
+      openresponses: { reasoningEffort: "low", store: true },
    })
  })

@@ -85,6 +85,7 @@ describe("provider package entrypoints", () => {
      headers: { "x-application": "opencode" },
      body: { metadata: { user_id: "user_1" } },
      limits: { context: 200_000, output: 64_000 },
+      providerOptions: { anthropic: { effort: "low" } },
    })

    expect(String(selected.provider)).toBe("example")
@@ -96,6 +97,19 @@ describe("provider package entrypoints", () => {
    expect(selected.route.defaults.headers).toEqual({ "x-application": "opencode" })
    expect(selected.route.defaults.http?.body).toEqual({ metadata: { user_id: "user_1" } })
    expect(selected.route.defaults.limits).toEqual({ context: 200_000, output: 64_000 })
+    expect(selected.route.defaults.providerOptions).toEqual({ anthropic: { effort: "low" } })
+  })
+
+  test("maps Anthropic provider options onto the executable model", async () => {
+    const Anthropic = await import("@opencode-ai/ai/providers/anthropic")
+    const selected = Anthropic.model("claude-sonnet-4-6", {
+      apiKey: "fixture",
+      providerOptions: { anthropic: { thinking: { type: "adaptive" } } },
+    })
+
+    expect(selected.route.defaults.providerOptions).toEqual({
+      anthropic: { thinking: { type: "adaptive" } },
+    })
  })

  test("requires an Anthropic-compatible base URL at runtime", async () => {
@@ -235,12 +249,12 @@ describe("provider package entrypoints", () => {
      path: "/chat/completions",
    })
    expect(responses.route.id).toBe("google-vertex-responses")
-    expect(responses.route.protocol).toBe("openai-responses")
+    expect(responses.route.protocol).toBe("open-responses")
    expect(responses.route.endpoint).toMatchObject({
      baseURL: "https://aiplatform.googleapis.com/v1/projects/vertex-project/locations/global/endpoints/openapi",
      path: "/responses",
    })
-    expect(responses.route.defaults.providerOptions).toEqual({ openai: { store: false } })
+    expect(responses.route.defaults.providerOptions).toEqual({ openresponses: { store: false } })
  })

  test("rejects conflicting Vertex auth settings at runtime", async () => {
@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { CacheHint, LLM } from "../../src"
+import { CacheHint, LLM, LLMRequest, Message, ToolCallPart, ToolDefinition } from "../../src"
 import { LLMClient } from "../../src/route"
 import * as Anthropic from "../../src/providers/anthropic"
 import { LARGE_CACHEABLE_SYSTEM } from "../recorded-scenarios"
@@ -24,6 +24,39 @@ const cacheRequest = LLM.request({
  generation: { maxTokens: 16, temperature: 0 },
 })

+const lookup = ToolDefinition.make({
+  name: "lookup",
+  description: "Look up a fixture value.",
+  inputSchema: {
+    type: "object",
+    properties: { index: { type: "number" } },
+    required: ["index"],
+    additionalProperties: false,
+  },
+})
+const longToolTurn = [
+  Message.user("Run the fixture lookups."),
+  ...Array.from({ length: 11 }, (_, index) => {
+    const id = `lookup_${index}`
+    return [
+      Message.assistant(ToolCallPart.make({ id, name: lookup.name, input: { index } })),
+      Message.tool({
+        id,
+        name: lookup.name,
+        result: `Fixture result ${index}. `.repeat(80),
+      }),
+    ]
+  }).flat(),
+]
+const longToolTurnRequest = LLM.request({
+  id: "recorded_anthropic_cache_long_tool_turn",
+  model,
+  system: LARGE_CACHEABLE_SYSTEM,
+  messages: longToolTurn,
+  tools: [lookup],
+  generation: { maxTokens: 16, temperature: 0 },
+})
+
 const recorded = recordedTests({
  prefix: "anthropic-messages-cache",
  provider: "anthropic",
@@ -50,4 +83,28 @@ describe("Anthropic Messages cache recorded", () => {
      expect(second.usage?.cacheReadInputTokens ?? 0).toBeGreaterThan(0)
    }),
  )
+
+  recorded.effect.with("keeps a long tool turn inside the cache lookback", { tags: ["cache", "tool"] }, () =>
+    Effect.gen(function* () {
+      const first = yield* LLMClient.generate(longToolTurnRequest)
+      const firstRead = first.usage?.cacheReadInputTokens ?? 0
+      const firstWrite = first.usage?.cacheWriteInputTokens ?? 0
+      const firstCached = firstRead + firstWrite
+      // The prefix may already be warm when recording, so either a read or a
+      // write establishes that Anthropic recognized the cache boundary.
+      expect(firstCached).toBeGreaterThan(0)
+
+      const second = yield* LLMClient.generate(
+        LLMRequest.update(longToolTurnRequest, {
+          messages: [
+            ...longToolTurn,
+            Message.assistant("The fixture lookups are complete."),
+            Message.user("Reply exactly: OK"),
+          ],
+        }),
+      )
+      expect(second.usage?.cacheReadInputTokens ?? 0).toBeGreaterThanOrEqual(firstCached)
+      expect(second.usage?.cacheWriteInputTokens ?? 0).toBeLessThan(firstCached)
+    }),
+  )
 })
@@ -1,7 +1,7 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
-import { CacheHint, LLM, LLMError, Message, ToolCallPart, Usage } from "../../src"
+import { CacheHint, LLM, LLMError, LLMRequest, Message, ToolCallPart, ToolDefinition, Usage } from "../../src"
 import { Auth, LLMClient } from "../../src/route"
 import * as AnthropicMessages from "../../src/protocols/anthropic-messages"
 import { continuationRequest, nativeAnthropicMessagesContinuation } from "../continuation-scenarios"
@@ -60,7 +60,7 @@ describe("Anthropic Messages route", () => {
  it.effect("lowers adaptive thinking settings with effort", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
-        LLM.updateRequest(request, {
+        LLMRequest.update(request, {
          providerOptions: {
            anthropic: { thinking: { type: "adaptive", display: "summarized" }, effort: "low" },
          },
@@ -74,6 +74,42 @@ describe("Anthropic Messages route", () => {
    }),
  )

+  it.effect("normalizes enabled and disabled thinking settings", () =>
+    Effect.gen(function* () {
+      const enabled = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
+        LLMRequest.update(request, {
+          providerOptions: { anthropic: { thinking: { type: "enabled", budgetTokens: 1_024 } } },
+        }),
+      )
+      const legacy = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
+        LLMRequest.update(request, {
+          providerOptions: { anthropic: { thinking: { type: "enabled", budget_tokens: 2_048 } } },
+        }),
+      )
+      const disabled = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
+        LLMRequest.update(request, {
+          providerOptions: { anthropic: { thinking: { type: "disabled" } } },
+        }),
+      )
+
+      expect(enabled.body.thinking).toEqual({ type: "enabled", budget_tokens: 1_024 })
+      expect(legacy.body.thinking).toEqual({ type: "enabled", budget_tokens: 2_048 })
+      expect(disabled.body.thinking).toEqual({ type: "disabled" })
+    }),
+  )
+
+  it.effect("rejects enabled thinking without a budget", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.prepare(
+        LLMRequest.update(request, {
+          providerOptions: { anthropic: { thinking: { type: "enabled" } } },
+        }),
+      ).pipe(Effect.flip)
+
+      expect(error.message).toContain("Anthropic thinking provider option requires budgetTokens")
+    }),
+  )
+
  it.effect("lowers chronological system updates natively for Claude Opus 4.8 with cache hints", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
@@ -470,6 +506,7 @@ describe("Anthropic Messages route", () => {
      expect(response.events.find((event) => event.type === "reasoning-end")).toMatchObject({
        providerMetadata: { anthropic: { signature: "sig_1" } },
      })
+      expect(response.events.find((event) => event.type === "reasoning-delta" && event.text === "")).toBeUndefined()
      expect(response.message.content).toEqual([
        { type: "text", text: "Hello!" },
        { type: "reasoning", text: "thinking", providerMetadata: { anthropic: { signature: "sig_1" } } },
@@ -482,6 +519,199 @@ describe("Anthropic Messages route", () => {
    }),
  )

+  it.effect("requires message_stop before completing a streamed message", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              { type: "content_block_start", index: 0, content_block: { type: "text", text: "" } },
+              { type: "content_block_delta", index: 0, delta: { type: "text_delta", text: "Hello" } },
+              { type: "content_block_stop", index: 0 },
+              { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 1 } },
+            ),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error.reason).toMatchObject({
+        _tag: "InvalidProviderOutput",
+        message: "Provider stream ended without a terminal finish event",
+      })
+    }),
+  )
+
+  it.effect("maps thinking tokens and preserves unknown Anthropic usage fields", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              {
+                type: "message_start",
+                message: {
+                  usage: {
+                    input_tokens: 5,
+                    cache_read_input_tokens: 2,
+                    service_tier: "standard",
+                    cache_creation: { ephemeral_5m_input_tokens: 1 },
+                    server_tool_use: { web_search_requests: 1, start_counter: 2 },
+                    output_tokens_details: { thinking_tokens: 3, start_detail: "preserved" },
+                  },
+                },
+              },
+              {
+                type: "message_delta",
+                delta: { stop_reason: "end_turn" },
+                usage: {
+                  output_tokens: 8,
+                  server_tool_use: { web_search_requests: 2, terminal_counter: 3 },
+                  output_tokens_details: { terminal_detail: "preserved" },
+                  future_terminal: { requests: 4 },
+                },
+              },
+              { type: "message_stop" },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.usage).toMatchObject({
+        inputTokens: 7,
+        outputTokens: 8,
+        reasoningTokens: 3,
+        totalTokens: 15,
+        providerMetadata: {
+          anthropic: {
+            input_tokens: 5,
+            cache_read_input_tokens: 2,
+            service_tier: "standard",
+            cache_creation: { ephemeral_5m_input_tokens: 1 },
+            server_tool_use: { web_search_requests: 2, start_counter: 2, terminal_counter: 3 },
+            output_tokens: 8,
+            output_tokens_details: {
+              thinking_tokens: 3,
+              start_detail: "preserved",
+              terminal_detail: "preserved",
+            },
+            future_terminal: { requests: 4 },
+          },
+        },
+      })
+    }),
+  )
+
+  it.effect("round-trips omitted thinking carried only by a signature delta", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              {
+                type: "content_block_start",
+                index: 0,
+                content_block: { type: "thinking", thinking: "", signature: "" },
+              },
+              { type: "content_block_delta", index: 0, delta: { type: "signature_delta", signature: "sig_1" } },
+              { type: "content_block_stop", index: 0 },
+              { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 1 } },
+              { type: "message_stop" },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.message.content).toEqual([
+        { type: "reasoning", text: "", providerMetadata: { anthropic: { signature: "sig_1" } } },
+      ])
+
+      const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
+        LLM.request({ model, messages: [response.message], cache: "none" }),
+      )
+      expect(prepared.body.messages).toEqual([
+        { role: "assistant", content: [{ type: "thinking", thinking: "", signature: "sig_1" }] },
+      ])
+    }),
+  )
+
+  it.effect("retains a thinking signature supplied in content_block_start", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              {
+                type: "content_block_start",
+                index: 0,
+                content_block: { type: "thinking", thinking: "", signature: "sig_1" },
+              },
+              { type: "content_block_stop", index: 0 },
+              { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 1 } },
+              { type: "message_stop" },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.message.content).toEqual([
+        { type: "reasoning", text: "", providerMetadata: { anthropic: { signature: "sig_1" } } },
+      ])
+      expect(response.events.find((event) => event.type === "reasoning-end")).toMatchObject({
+        providerMetadata: { anthropic: { signature: "sig_1" } },
+      })
+    }),
+  )
+
+  it.effect("retains complete tool input from content_block_start", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              {
+                type: "content_block_start",
+                index: 0,
+                content_block: { type: "tool_use", id: "call_1", name: "lookup", input: { query: "weather" } },
+              },
+              { type: "content_block_stop", index: 0 },
+              { type: "message_delta", delta: { stop_reason: "tool_use" }, usage: { output_tokens: 1 } },
+              { type: "message_stop" },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.toolCalls).toMatchObject([
+        { id: "call_1", name: "lookup", input: { query: "weather" } },
+      ])
+    }),
+  )
+
+  it.effect("retains empty text blocks", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              { type: "content_block_start", index: 0, content_block: { type: "text", text: "" } },
+              { type: "content_block_stop", index: 0 },
+              { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 1 } },
+              { type: "message_stop" },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.message.content).toEqual([{ type: "text", text: "" }])
+    }),
+  )
+
  it.effect("parses redacted thinking into empty reasoning with redactedData metadata", () =>
    Effect.gen(function* () {
      const body = sseEvents(
@@ -512,8 +742,8 @@ describe("Anthropic Messages route", () => {
      // contents are provider-owned and must be replayed without inspection.
      const redactedData = "cmVkYWN0ZWQtdGhpbmtpbmc="
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(
        Effect.provide(
@@ -551,7 +781,7 @@ describe("Anthropic Messages route", () => {
            response.message,
            Message.tool({ id: "call_1", name: "lookup", result: "sunny", resultType: "text" }),
          ],
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
          cache: "none",
        }),
      )
@@ -593,6 +823,7 @@ describe("Anthropic Messages route", () => {
                delta: { stop_reason: "model_context_window_exceeded" },
                usage: { output_tokens: 1 },
              },
+              { type: "message_stop" },
            ),
          ),
        ),
@@ -610,6 +841,7 @@ describe("Anthropic Messages route", () => {
            sseEvents(
              { type: "message_start", message: { usage: { input_tokens: 5 } } },
              { type: "message_delta", delta: { stop_reason: "pause_turn" }, usage: { output_tokens: 1 } },
+              { type: "message_stop" },
            ),
          ),
        ),
@@ -628,10 +860,11 @@ describe("Anthropic Messages route", () => {
        { type: "content_block_delta", index: 0, delta: { type: "input_json_delta", partial_json: ':"weather"}' } },
        { type: "content_block_stop", index: 0 },
        { type: "message_delta", delta: { stop_reason: "tool_use" }, usage: { output_tokens: 1 } },
+        { type: "message_stop" },
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))
      const usage = new Usage({
@@ -813,10 +1046,13 @@ describe("Anthropic Messages route", () => {
        { type: "content_block_delta", index: 2, delta: { type: "text_delta", text: "Found it." } },
        { type: "content_block_stop", index: 2 },
        { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 8 } },
+        { type: "message_stop" },
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "web_search", description: "Web search", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [
+            ToolDefinition.make({ name: "web_search", description: "Web search", inputSchema: { type: "object" } }),
+          ],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -874,10 +1110,13 @@ describe("Anthropic Messages route", () => {
        },
        { type: "content_block_stop", index: 1 },
        { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 1 } },
+        { type: "message_stop" },
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "web_search", description: "Web search", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [
+            ToolDefinition.make({ name: "web_search", description: "Web search", inputSchema: { type: "object" } }),
+          ],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -993,7 +1232,10 @@ describe("Anthropic Messages route", () => {
                    content: [
                      { type: "text", text: "What is in this image?" },
                      { type: "image", source: { type: "base64", media_type: "image/png", data: "AAECAw==" } },
-                      { type: "document", source: { type: "base64", media_type: "application/pdf", data: "JVBERi0xLjQ=" } },
+                      {
+                        type: "document",
+                        source: { type: "base64", media_type: "application/pdf", data: "JVBERi0xLjQ=" },
+                      },
                    ],
                  },
                ],
@@ -2,7 +2,16 @@ import { EventStreamCodec } from "@smithy/eventstream-codec"
 import { fromUtf8, toUtf8 } from "@smithy/util-utf8"
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { CacheHint, LLM, Message, ToolCallPart, ToolChoice } from "../../src"
+import {
+  CacheHint,
+  GenerationOptions,
+  LLM,
+  LLMRequest,
+  Message,
+  ToolCallPart,
+  ToolChoice,
+  ToolDefinition,
+} from "../../src"
 import { LLMClient } from "../../src/route"
 import { AmazonBedrock } from "../../src/providers"
 import * as BedrockConverse from "../../src/protocols/bedrock-converse"
@@ -34,6 +43,26 @@ const eventFrame = (type: string, payload: object) =>
    body: utf8Encoder.encode(JSON.stringify(payload)),
  })

+const exceptionFrame = (type: string, payload: object) =>
+  codec.encode({
+    headers: {
+      ":message-type": { type: "string", value: "exception" },
+      ":exception-type": { type: "string", value: type },
+      ":content-type": { type: "string", value: "application/json" },
+    },
+    body: utf8Encoder.encode(JSON.stringify(payload)),
+  })
+
+const errorFrame = (code: string, message: string) =>
+  codec.encode({
+    headers: {
+      ":message-type": { type: "string", value: "error" },
+      ":error-code": { type: "string", value: code },
+      ":error-message": { type: "string", value: message },
+    },
+    body: new Uint8Array(),
+  })
+
 const concat = (frames: ReadonlyArray<Uint8Array>) => {
  const total = frames.reduce((sum, frame) => sum + frame.length, 0)
  const out = new Uint8Array(total)
@@ -86,7 +115,9 @@ describe("Bedrock Converse route", () => {
  it.effect("passes topK through additionalModelRequestFields as top_k", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
-        LLM.updateRequest(baseRequest, { generation: { maxTokens: 64, temperature: 0, topK: 40 } }),
+        LLMRequest.update(baseRequest, {
+          generation: GenerationOptions.make({ maxTokens: 64, temperature: 0, topK: 40 }),
+        }),
      )

      // Converse's inferenceConfig has no topK; Anthropic/Nova read it from
@@ -123,13 +154,13 @@ describe("Bedrock Converse route", () => {
  it.effect("prepares tool config with toolSpec and toolChoice", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare(
-        LLM.updateRequest(baseRequest, {
+        LLMRequest.update(baseRequest, {
          tools: [
-            {
+            ToolDefinition.make({
              name: "lookup",
              description: "Lookup data",
              inputSchema: { type: "object", properties: { query: { type: "string" } }, required: ["query"] },
-            },
+            }),
          ],
          toolChoice: ToolChoice.make({ type: "required" }),
        }),
@@ -157,13 +188,13 @@ describe("Bedrock Converse route", () => {
  it.effect("keeps tools and omits the unsupported choice when tool choice is none", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare(
-        LLM.updateRequest(baseRequest, {
+        LLMRequest.update(baseRequest, {
          tools: [
-            {
+            ToolDefinition.make({
              name: "lookup",
              description: "Lookup data",
              inputSchema: { type: "object", properties: { query: { type: "string" } } },
-            },
+            }),
          ],
          toolChoice: ToolChoice.make({ type: "none" }),
        }),
@@ -352,6 +383,19 @@ describe("Bedrock Converse route", () => {
    }),
  )

+  it.effect("preserves usage across later metadata events without usage", () =>
+    Effect.gen(function* () {
+      const body = eventStreamBody(
+        ["messageStop", { stopReason: "end_turn" }],
+        ["metadata", { usage: { inputTokens: 5, outputTokens: 2, totalTokens: 7 } }],
+        ["metadata", { metrics: { latencyMs: 100 } }],
+      )
+      const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
+
+      expect(response.usage).toMatchObject({ inputTokens: 5, outputTokens: 2, totalTokens: 7 })
+    }),
+  )
+
  it.effect("assembles streamed tool call input", () =>
    Effect.gen(function* () {
      const body = eventStreamBody(
@@ -369,8 +413,8 @@ describe("Bedrock Converse route", () => {
        ["messageStop", { stopReason: "tool_use" }],
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(baseRequest, {
-          tools: [{ name: "lookup", description: "Lookup", inputSchema: { type: "object" } }],
+        LLMRequest.update(baseRequest, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedBytes(body)))

@@ -467,12 +511,170 @@ describe("Bedrock Converse route", () => {
    }),
  )

-  it.effect("classifies throttlingException as a rate limit", () =>
+  it.effect("preserves reasoning signatures when contentBlockStop is missing", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(baseRequest).pipe(
+        Effect.provide(
+          fixedBytes(
+            eventStreamBody(
+              ["messageStart", { role: "assistant" }],
+              [
+                "contentBlockDelta",
+                { contentBlockIndex: 0, delta: { reasoningContent: { text: "Let me think." } } },
+              ],
+              [
+                "contentBlockDelta",
+                { contentBlockIndex: 0, delta: { reasoningContent: { signature: "sig_1" } } },
+              ],
+              ["messageStop", { stopReason: "end_turn" }],
+            ),
+          ),
+        ),
+      )
+
+      expect(response.events.find((event) => event.type === "reasoning-delta" && event.text === "")).toEqual({
+        type: "reasoning-delta",
+        id: "reasoning-0",
+        text: "",
+        providerMetadata: { bedrock: { signature: "sig_1" } },
+      })
+      expect(response.message.content).toEqual([
+        {
+          type: "reasoning",
+          text: "Let me think.",
+          providerMetadata: { bedrock: { signature: "sig_1" } },
+        },
+      ])
+
+      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
+        LLM.request({ model, messages: [response.message], cache: "none" }),
+      )
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "assistant",
+          content: [{ reasoningContent: { reasoningText: { text: "Let me think.", signature: "sig_1" } } }],
+        },
+      ])
+    }),
+  )
+
+  it.effect("preserves signature-only reasoning blocks", () =>
    Effect.gen(function* () {
      const body = eventStreamBody(
        ["messageStart", { role: "assistant" }],
-        ["throttlingException", { message: "Slow down" }],
+        [
+          "contentBlockDelta",
+          { contentBlockIndex: 0, delta: { reasoningContent: { signature: "sig_1" } } },
+        ],
+        ["contentBlockStop", { contentBlockIndex: 0 }],
+        ["messageStop", { stopReason: "end_turn" }],
      )
+      const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
+
+      expect(response.message.content).toEqual([
+        { type: "reasoning", text: "", providerMetadata: { bedrock: { signature: "sig_1" } } },
+      ])
+    }),
+  )
+
+  it.effect("accepts Vercel-compatible redacted reasoning data deltas", () =>
+    Effect.gen(function* () {
+      const redactedData = "cmVkYWN0ZWQtdGhpbmtpbmc="
+      const body = eventStreamBody(
+        ["messageStart", { role: "assistant" }],
+        ["contentBlockDelta", { contentBlockIndex: 0, delta: { reasoningContent: { data: redactedData } } }],
+        ["contentBlockStop", { contentBlockIndex: 0 }],
+        ["messageStop", { stopReason: "end_turn" }],
+      )
+      const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
+
+      expect(response.events.find((event) => event.type === "reasoning-delta" && event.text === "")).toEqual({
+        type: "reasoning-delta",
+        id: "reasoning-0",
+        text: "",
+        providerMetadata: { bedrock: { redactedData } },
+      })
+      expect(response.message.content).toEqual([
+        { type: "reasoning", text: "", providerMetadata: { bedrock: { redactedData } } },
+      ])
+    }),
+  )
+
+  it.effect("round-trips streamed redacted reasoning with tool use into a continuation request", () =>
+    Effect.gen(function* () {
+      // Bedrock represents redactedContent blobs as base64 strings on its JSON
+      // wire. The provider owns the payload and requires byte-exact replay.
+      const redactedData = "cmVkYWN0ZWQtdGhpbmtpbmc="
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(baseRequest, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(
+        Effect.provide(
+          fixedBytes(
+            eventStreamBody(
+              ["messageStart", { role: "assistant" }],
+              [
+                "contentBlockDelta",
+                { contentBlockIndex: 0, delta: { reasoningContent: { redactedContent: redactedData } } },
+              ],
+              ["contentBlockStop", { contentBlockIndex: 0 }],
+              [
+                "contentBlockStart",
+                {
+                  contentBlockIndex: 1,
+                  start: { toolUse: { toolUseId: "tool_1", name: "lookup" } },
+                },
+              ],
+              ["contentBlockDelta", { contentBlockIndex: 1, delta: { toolUse: { input: '{"query":"weather"}' } } }],
+              ["contentBlockStop", { contentBlockIndex: 1 }],
+              ["messageStop", { stopReason: "tool_use" }],
+            ),
+          ),
+        ),
+      )
+      expect(response.events.find((event) => event.type === "reasoning-delta" && event.text === "")).toEqual({
+        type: "reasoning-delta",
+        id: "reasoning-0",
+        text: "",
+        providerMetadata: { bedrock: { redactedData } },
+      })
+      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Say hello."),
+            response.message,
+            Message.tool({ id: "tool_1", name: "lookup", result: "sunny", resultType: "text" }),
+          ],
+          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+          cache: "none",
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([
+        { role: "user", content: [{ text: "Say hello." }] },
+        {
+          role: "assistant",
+          content: [
+            { reasoningContent: { redactedContent: redactedData } },
+            { toolUse: { toolUseId: "tool_1", name: "lookup", input: { query: "weather" } } },
+          ],
+        },
+        {
+          role: "user",
+          content: [{ toolResult: { toolUseId: "tool_1", content: [{ text: "sunny" }], status: "success" } }],
+        },
+      ])
+    }),
+  )
+
+  it.effect("classifies throttlingException as a rate limit", () =>
+    Effect.gen(function* () {
+      const body = concat([
+        eventFrame("messageStart", { role: "assistant" }),
+        exceptionFrame("throttlingException", { message: "Slow down" }),
+      ])
      const error = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)), Effect.flip)

      expect(error.reason).toMatchObject({ _tag: "RateLimit", message: "Slow down" })
@@ -483,7 +685,7 @@ describe("Bedrock Converse route", () => {
    Effect.gen(function* () {
      const error = yield* LLMClient.generate(baseRequest).pipe(
        Effect.provide(
-          fixedBytes(eventStreamBody(["validationException", { message: "Input is too long for requested model" }])),
+          fixedBytes(exceptionFrame("validationException", { message: "Input is too long for requested model" })),
        ),
        Effect.flip,
      )
@@ -496,12 +698,44 @@ describe("Bedrock Converse route", () => {
    }),
  )

+  it.effect("uses originalMessage from model stream exception frames", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(baseRequest).pipe(
+        Effect.provide(
+          fixedBytes(
+            exceptionFrame("modelStreamErrorException", {
+              originalMessage: "Upstream model failed",
+              originalStatusCode: 500,
+            }),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error.reason).toMatchObject({ _tag: "ProviderInternal", message: "Upstream model failed" })
+    }),
+  )
+
+  it.effect("fails unmodeled AWS event-stream errors", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(baseRequest).pipe(
+        Effect.provide(fixedBytes(errorFrame("BadStream", "Stream failed"))),
+        Effect.flip,
+      )
+
+      expect(error.reason).toMatchObject({
+        _tag: "InvalidProviderOutput",
+        message: "BadStream: Stream failed",
+      })
+    }),
+  )
+
  it.effect("rejects requests with no auth path", () =>
    Effect.gen(function* () {
      const unsignedModel = AmazonBedrock.configure({
        baseURL: "https://bedrock-runtime.test",
      }).model("anthropic.claude-3-5-sonnet-20240620-v1:0")
-      const error = yield* LLMClient.generate(LLM.updateRequest(baseRequest, { model: unsignedModel })).pipe(
+      const error = yield* LLMClient.generate(LLMRequest.update(baseRequest, { model: unsignedModel })).pipe(
        Effect.provide(fixedBytes(eventStreamBody(["messageStop", { stopReason: "end_turn" }]))),
        Effect.flip,
      )
@@ -520,7 +754,7 @@ describe("Bedrock Converse route", () => {
          secretAccessKey: "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
        },
      }).model("anthropic.claude-3-5-sonnet-20240620-v1:0")
-      const prepared = yield* LLMClient.prepare(LLM.updateRequest(baseRequest, { model: signed }))
+      const prepared = yield* LLMClient.prepare(LLMRequest.update(baseRequest, { model: signed }))

      expect(prepared.route).toBe("bedrock-converse")
      expect(prepared.model).toBe(signed)
@@ -705,6 +939,7 @@ describe("Bedrock Converse route", () => {
      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
        LLM.request({
          model,
+          cache: "none",
          messages: [
            Message.assistant([ToolCallPart.make({ id: "call_1", name: "read", input: { path: "report.pdf" } })]),
            Message.tool({
@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { LLM, LLMError, Message, ToolCallPart, Usage } from "../../src"
+import { LLM, LLMError, LLMRequest, Message, ToolCallPart, ToolDefinition, Usage } from "../../src"
 import { Auth, LLMClient } from "../../src/route"
 import * as Gemini from "../../src/protocols/gemini"
 import { ProviderShared } from "../../src/protocols/shared"
@@ -36,6 +36,27 @@ describe("Gemini route", () => {
    }),
  )

+  it.effect("normalizes Gemini thinking options", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<Gemini.GeminiBody>(
+        LLMRequest.update(request, {
+          providerOptions: { gemini: { thinkingConfig: { thinkingBudget: 0, includeThoughts: false } } },
+        }),
+      )
+      const filtered = yield* LLMClient.prepare<Gemini.GeminiBody>(
+        LLMRequest.update(request, {
+          providerOptions: { gemini: { thinkingConfig: { thinkingBudget: "invalid", includeThoughts: false } } },
+        }),
+      )
+
+      expect(prepared.body.generationConfig?.thinkingConfig).toEqual({
+        thinkingBudget: 0,
+        includeThoughts: false,
+      })
+      expect(filtered.body.generationConfig?.thinkingConfig).toEqual({ includeThoughts: false })
+    }),
+  )
+
  it.effect("lowers chronological system updates to wrapped user text in order", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare<Gemini.GeminiBody>(
@@ -240,7 +261,7 @@ describe("Gemini route", () => {
          id: "req_tool_choice_none",
          model,
          prompt: "Say hello.",
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
          toolChoice: { type: "none" },
        }),
      )
@@ -410,8 +431,8 @@ describe("Gemini route", () => {
        ],
      })
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))
      const reasoning = response.events.find((event) => event.type === "reasoning-start")
@@ -501,8 +522,8 @@ describe("Gemini route", () => {
        usageMetadata: { promptTokenCount: 5, candidatesTokenCount: 1 },
      })
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))
      const usage = new Usage({
@@ -568,8 +589,8 @@ describe("Gemini route", () => {
        ],
      })
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -1,7 +1,18 @@
 import { describe, expect } from "bun:test"
 import { Effect, Schema, Stream } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
-import { LLM, LLMError, LLMEvent, Message, Model, ToolCallPart, Usage } from "../../src"
+import {
+  HttpOptions,
+  LLM,
+  LLMError,
+  LLMEvent,
+  LLMRequest,
+  Message,
+  Model,
+  ToolCallPart,
+  ToolDefinition,
+  Usage,
+} from "../../src"
 import * as Azure from "../../src/providers/azure"
 import * as OpenAI from "../../src/providers/openai"
 import * as OpenAIChat from "../../src/protocols/openai-chat"
@@ -162,7 +173,7 @@ describe("OpenAI Chat route", () => {

  it.effect("adds native query params to the Chat Completions URL", () =>
    LLMClient.generate(
-      LLM.updateRequest(request, {
+      LLMRequest.update(request, {
        model: Model.update(model, { route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }) }),
      }),
    ).pipe(
@@ -182,7 +193,7 @@ describe("OpenAI Chat route", () => {

  it.effect("uses Azure api-key header for static OpenAI Chat keys", () =>
    LLMClient.generate(
-      LLM.updateRequest(request, {
+      LLMRequest.update(request, {
        model: Azure.configure({
          baseURL: "https://opencode-test.openai.azure.com/openai/v1/",
          apiKey: "azure-key",
@@ -208,15 +219,15 @@ describe("OpenAI Chat route", () => {

  it.effect("applies serializable HTTP overlays after payload lowering", () =>
    LLMClient.generate(
-      LLM.updateRequest(request, {
+      LLMRequest.update(request, {
        model: model.route
          .with({ auth: Auth.bearer("fresh-key"), headers: { authorization: "Bearer stale" } })
          .model({ id: model.id }),
-        http: {
+        http: HttpOptions.make({
          body: { metadata: { source: "test" } },
          headers: { authorization: "Bearer request", "x-custom": "yes" },
          query: { debug: "1" },
-        },
+        }),
      }),
    ).pipe(
      Effect.provide(
@@ -539,7 +550,7 @@ describe("OpenAI Chat route", () => {
          prompt_tokens: 5,
          completion_tokens: 2,
          total_tokens: 7,
-          prompt_tokens_details: { cached_tokens: 1 },
+          prompt_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
          completion_tokens_details: { reasoning_tokens: 0 },
        }),
      )
@@ -547,8 +558,9 @@ describe("OpenAI Chat route", () => {
      const usage = new Usage({
        inputTokens: 5,
        outputTokens: 2,
-        nonCachedInputTokens: 4,
+        nonCachedInputTokens: 2,
        cacheReadInputTokens: 1,
+        cacheWriteInputTokens: 2,
        reasoningTokens: 0,
        totalTokens: 7,
        providerMetadata: {
@@ -556,7 +568,7 @@ describe("OpenAI Chat route", () => {
            prompt_tokens: 5,
            completion_tokens: 2,
            total_tokens: 7,
-            prompt_tokens_details: { cached_tokens: 1 },
+            prompt_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
            completion_tokens_details: { reasoning_tokens: 0 },
          },
        },
@@ -618,7 +630,7 @@ describe("OpenAI Chat route", () => {
  it.effect("parses and replays a configured custom reasoning field", () =>
    Effect.gen(function* () {
      const custom = Model.update(model, { compatibility: { reasoningField: "vendor_reasoning" } })
-      const response = yield* LLMClient.generate(LLM.updateRequest(request, { model: custom })).pipe(
+      const response = yield* LLMClient.generate(LLMRequest.update(request, { model: custom })).pipe(
        Effect.provide(
          fixedResponse(
            sseEvents(
@@ -638,9 +650,7 @@ describe("OpenAI Chat route", () => {
      const replay = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
        LLM.request({ model: custom, messages: [response.message] }),
      )
-      expect(replay.body.messages).toEqual([
-        { role: "assistant", content: "Hello", vendor_reasoning: "thinking" },
-      ])
+      expect(replay.body.messages).toEqual([{ role: "assistant", content: "Hello", vendor_reasoning: "thinking" }])
    }),
  )

@@ -651,8 +661,8 @@ describe("OpenAI Chat route", () => {
        { type: "reasoning.encrypted", data: "opaque", format: "anthropic-claude-v1", index: 1 },
      ]
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(
        Effect.provide(
@@ -1024,8 +1034,8 @@ describe("OpenAI Chat route", () => {
        deltaChunk({}, "tool_calls"),
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -1067,8 +1077,8 @@ describe("OpenAI Chat route", () => {
        deltaChunk({}, "tool_calls"),
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -1089,8 +1099,8 @@ describe("OpenAI Chat route", () => {
        deltaChunk({}, "tool_calls"),
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -1107,8 +1117,8 @@ describe("OpenAI Chat route", () => {
        deltaChunk({}, "tool_calls"),
      )
      const error = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)), Effect.flip)

@@ -1125,8 +1135,8 @@ describe("OpenAI Chat route", () => {
        }),
        deltaChunk({ tool_calls: [{ index: 0, function: { arguments: ':"weather"}' } }] }),
      )
-      const input = LLM.updateRequest(request, {
-        tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+      const input = LLMRequest.update(request, {
+        tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
      })
      const events: LLMEvent[] = []
      const streamError = yield* LLMClient.stream(input).pipe(
@@ -1,7 +1,7 @@
 import { describe, expect } from "bun:test"
 import { Effect, Schema } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
-import { LLM, Message, ToolCallPart } from "../../src"
+import { LLM, LLMRequest, Message, ToolCallPart, ToolChoice, ToolDefinition } from "../../src"
 import { Auth, LLMClient } from "../../src/route"
 import * as OpenAICompatible from "../../src/providers/openai-compatible"
 import * as OpenAICompatibleChat from "../../src/protocols/openai-compatible-chat"
@@ -53,9 +53,9 @@ describe("OpenAI-compatible Chat route", () => {
  it.effect("prepares generic Chat target", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
-          toolChoice: { type: "required" },
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+          toolChoice: ToolChoice.make({ type: "required" }),
        }),
      )

@@ -1,17 +1,22 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { LLM } from "../../src"
+import { LLM, LLMEvent, Message } from "../../src"
 import { configure } from "../../src/providers/openai-compatible-responses"
+import { OpenAI } from "../../src/providers"
+import { OpenResponses } from "../../src/protocols/open-responses"
 import { OpenAICompatibleResponses } from "../../src/protocols/openai-compatible-responses"
 import { OpenAIResponses } from "../../src/protocols/openai-responses"
 import { LLMClient } from "../../src/route"
 import { it } from "../lib/effect"
+import { fixedResponse } from "../lib/http"
+import { sseEvents } from "../lib/sse"

-describe("OpenAI-compatible Responses route", () => {
-  it.effect("reuses the OpenAI Responses protocol for a configured deployment", () =>
+describe("Open Responses-compatible route", () => {
+  it.effect("uses the Open Responses baseline for a configured deployment", () =>
    Effect.gen(function* () {
-      expect(OpenAICompatibleResponses.route.body).toBe(OpenAIResponses.protocol.body)
-      expect(OpenAICompatibleResponses.route.transport).toBe(OpenAIResponses.httpTransport)
+      expect(OpenAICompatibleResponses.route.body).toBe(OpenResponses.protocol.body)
+      expect(OpenAICompatibleResponses.route.transport).toBe(OpenResponses.httpTransport)
+      expect(OpenAICompatibleResponses.route.body).not.toBe(OpenAIResponses.protocol.body)

      const model = configure({
        apiKey: "test-key",
@@ -27,7 +32,7 @@ describe("OpenAI-compatible Responses route", () => {
      )

      expect(prepared.route).toBe("openai-compatible-responses")
-      expect(prepared.protocol).toBe("openai-responses")
+      expect(prepared.protocol).toBe("open-responses")
      expect(prepared.model).toMatchObject({
        id: "example-model",
        provider: "example",
@@ -45,9 +50,92 @@ describe("OpenAI-compatible Responses route", () => {
          { role: "system", content: "You are concise." },
          { role: "user", content: [{ type: "input_text", text: "Say hello." }] },
        ],
-        store: false,
        stream: true,
      })
    }),
  )
+
+  it.effect("rejects OpenAI-native tools", () =>
+    Effect.gen(function* () {
+      const model = configure({
+        apiKey: "test-key",
+        baseURL: "https://responses.example.test/v1",
+      }).model("example-model")
+      const error = yield* LLMClient.prepare(
+        LLM.request({ model, prompt: "Draw.", tools: [OpenAI.imageGeneration()] }),
+      ).pipe(Effect.flip)
+
+      expect(error.reason._tag).toBe("InvalidRequest")
+      expect(error.message).toContain("Open Responses does not support provider-native tool image_generation")
+    }),
+  )
+
+  it.effect("omits OpenAI-only nullable phases from the Open Responses baseline", () =>
+    Effect.gen(function* () {
+      const model = configure({
+        apiKey: "test-key",
+        baseURL: "https://responses.example.test/v1",
+      }).model("example-model")
+      const prepared = yield* LLMClient.prepare(
+        LLM.request({
+          model,
+          messages: [
+            Message.assistant({
+              type: "text",
+              text: "Unclassified.",
+              providerMetadata: { openresponses: { phase: null } },
+            }),
+          ],
+        }),
+      )
+
+      expect(prepared.body).toMatchObject({
+        input: [{ role: "assistant", content: [{ type: "output_text", text: "Unclassified." }] }],
+      })
+    }),
+  )
+
+  it.effect("reads standard options from the Open Responses namespace", () =>
+    Effect.gen(function* () {
+      const model = configure({
+        apiKey: "test-key",
+        baseURL: "https://responses.example.test/v1",
+        providerOptions: { openresponses: { reasoningEffort: "low", store: true } },
+      }).model("example-model")
+      const prepared = yield* LLMClient.prepare(LLM.request({ model, prompt: "Think." }))
+
+      expect(prepared.body).toMatchObject({
+        reasoning: { effort: "low" },
+        store: true,
+      })
+    }),
+  )
+
+  it.effect("does not interpret OpenAI hosted-tool items", () =>
+    Effect.gen(function* () {
+      const model = configure({
+        apiKey: "test-key",
+        baseURL: "https://responses.example.test/v1",
+        provider: "example",
+      }).model("example-model")
+      const response = yield* LLMClient.generate(LLM.request({ model, prompt: "Search." })).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              {
+                type: "response.output_item.done",
+                item: { type: "web_search_call", id: "ws_1", status: "completed", action: { query: "news" } },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.toolCalls).toEqual([])
+      expect(response.events.find(LLMEvent.is.finish)).toMatchObject({
+        providerMetadata: { openresponses: { responseId: "resp_1" } },
+      })
+    }),
+  )
 })
@@ -1,7 +1,18 @@
 import { describe, expect } from "bun:test"
 import { ConfigProvider, Effect, Layer, Stream } from "effect"
 import { Headers, HttpClientRequest } from "effect/unstable/http"
-import { LLM, LLMError, LLMEvent, Message, Model, ToolCallPart, ToolResultPart, Usage } from "../../src"
+import {
+  LLM,
+  LLMError,
+  LLMEvent,
+  LLMRequest,
+  Message,
+  Model,
+  ToolCallPart,
+  ToolDefinition,
+  ToolResultPart,
+  Usage,
+} from "../../src"
 import { Auth, LLMClient, RequestExecutor, WebSocketExecutor } from "../../src/route"
 import * as Azure from "../../src/providers/azure"
 import * as OpenAI from "../../src/providers/openai"
@@ -96,7 +107,7 @@ describe("OpenAI Responses route", () => {

  it.effect("lowers semantic service tier options", () =>
    Effect.gen(function* () {
-      const input = LLM.updateRequest(request, { providerOptions: { openai: { serviceTier: "priority" } } })
+      const input = LLMRequest.update(request, { providerOptions: { openai: { serviceTier: "priority" } } })
      expect(input.providerOptions).toEqual({ openai: { serviceTier: "priority" } })
      const prepared = yield* LLMClient.prepare(input)

@@ -108,7 +119,7 @@ describe("OpenAI Responses route", () => {
  it.effect("passes through custom OpenAI reasoning effort strings", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
-        LLM.updateRequest(request, { providerOptions: { openai: { reasoningEffort: "experimental" } } }),
+        LLMRequest.update(request, { providerOptions: { openai: { reasoningEffort: "experimental" } } }),
      )

      expect(prepared.body.reasoning).toEqual({ effort: "experimental" })
@@ -118,7 +129,7 @@ describe("OpenAI Responses route", () => {
  it.effect("omits unsupported semantic service tiers", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare(
-        LLM.updateRequest(request, { providerOptions: { openai: { serviceTier: "unsupported" } } }),
+        LLMRequest.update(request, { providerOptions: { openai: { serviceTier: "unsupported" } } }),
      )

      expect(prepared.body).not.toHaveProperty("service_tier")
@@ -128,9 +139,9 @@ describe("OpenAI Responses route", () => {
  it.effect("flattens top-level object unions in function schemas", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
-        LLM.updateRequest(request, {
+        LLMRequest.update(request, {
          tools: [
-            {
+            ToolDefinition.make({
              name: "read",
              description: "Read a path or resource.",
              inputSchema: {
@@ -152,7 +163,7 @@ describe("OpenAI Responses route", () => {
                  },
                ],
              },
-            },
+            }),
          ],
        }),
      )
@@ -207,7 +218,7 @@ describe("OpenAI Responses route", () => {
  it.effect("prepares OpenAI Responses WebSocket target", () =>
    Effect.gen(function* () {
      const prepared = yield* LLMClient.prepare(
-        LLM.updateRequest(request, {
+        LLMRequest.update(request, {
          model: OpenAIResponses.webSocketRoute
            .with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
            .model({ id: "gpt-4.1-mini" }),
@@ -291,7 +302,7 @@ describe("OpenAI Responses route", () => {
  it.effect("adds native query params to the Responses URL", () =>
    Effect.gen(function* () {
      yield* LLMClient.generate(
-        LLM.updateRequest(request, {
+        LLMRequest.update(request, {
          model: Model.update(model, { route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }) }),
        }),
      ).pipe(
@@ -313,7 +324,7 @@ describe("OpenAI Responses route", () => {
  it.effect("uses Azure api-key header for static OpenAI Responses keys", () =>
    Effect.gen(function* () {
      yield* LLMClient.generate(
-        LLM.updateRequest(request, {
+        LLMRequest.update(request, {
          model: Azure.configure({
            baseURL: "https://opencode-test.openai.azure.com/openai/v1/",
            apiKey: "azure-key",
@@ -340,7 +351,7 @@ describe("OpenAI Responses route", () => {

  it.effect("loads OpenAI default auth from Effect Config", () =>
    LLMClient.generate(
-      LLM.updateRequest(request, {
+      LLMRequest.update(request, {
        model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/" }).responses("gpt-4.1-mini"),
      }),
    ).pipe(
@@ -361,7 +372,7 @@ describe("OpenAI Responses route", () => {

  it.effect("lets explicit auth override OpenAI default API key auth", () =>
    LLMClient.generate(
-      LLM.updateRequest(request, {
+      LLMRequest.update(request, {
        model: OpenAI.configure({
          baseURL: "https://api.openai.test/v1/",
          auth: Auth.bearer("oauth-token"),
@@ -821,7 +832,7 @@ describe("OpenAI Responses route", () => {
              input_tokens: 5,
              output_tokens: 2,
              total_tokens: 7,
-              input_tokens_details: { cached_tokens: 1 },
+              input_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
              output_tokens_details: { reasoning_tokens: 0 },
            },
          },
@@ -831,8 +842,9 @@ describe("OpenAI Responses route", () => {
      const usage = new Usage({
        inputTokens: 5,
        outputTokens: 2,
-        nonCachedInputTokens: 4,
+        nonCachedInputTokens: 2,
        cacheReadInputTokens: 1,
+        cacheWriteInputTokens: 2,
        reasoningTokens: 0,
        totalTokens: 7,
        providerMetadata: {
@@ -840,7 +852,7 @@ describe("OpenAI Responses route", () => {
            input_tokens: 5,
            output_tokens: 2,
            total_tokens: 7,
-            input_tokens_details: { cached_tokens: 1 },
+            input_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
            output_tokens_details: { reasoning_tokens: 0 },
          },
        },
@@ -870,6 +882,121 @@ describe("OpenAI Responses route", () => {
    }),
  )

+  it.effect("preserves and replays assistant message phases", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              {
+                type: "response.output_item.added",
+                item: { type: "message", id: "msg_commentary" },
+              },
+              { type: "response.output_text.delta", item_id: "msg_commentary", delta: "Checking." },
+              { type: "response.output_text.done", item_id: "msg_commentary" },
+              {
+                type: "response.output_item.done",
+                item: { type: "message", id: "msg_commentary", phase: "commentary" },
+              },
+              {
+                type: "response.output_item.added",
+                item: { type: "message", id: "msg_final", phase: "final_answer" },
+              },
+              { type: "response.output_text.done", item_id: "msg_final", text: "Finished." },
+              {
+                type: "response.output_item.done",
+                item: { type: "message", id: "msg_final", phase: "final_answer" },
+              },
+              { type: "response.output_item.added", item: { type: "message", id: "msg_null", phase: null } },
+              { type: "response.output_text.delta", item_id: "msg_null", delta: "Unclassified." },
+              { type: "response.output_item.done", item: { type: "message", id: "msg_null", phase: null } },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.message.content).toEqual([
+        {
+          type: "text",
+          text: "Checking.",
+          providerMetadata: { openai: { phase: "commentary" } },
+        },
+        {
+          type: "text",
+          text: "Finished.",
+          providerMetadata: { openai: { phase: "final_answer" } },
+        },
+        {
+          type: "text",
+          text: "Unclassified.",
+          providerMetadata: { openai: { phase: null } },
+        },
+      ])
+
+      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
+        LLM.request({ model, messages: [response.message] }),
+      )
+      expect(prepared.body.input).toEqual([
+        {
+          role: "assistant",
+          content: [{ type: "output_text", text: "Checking." }],
+          phase: "commentary",
+        },
+        {
+          role: "assistant",
+          content: [{ type: "output_text", text: "Finished." }],
+          phase: "final_answer",
+        },
+        {
+          role: "assistant",
+          content: [{ type: "output_text", text: "Unclassified." }],
+          phase: null,
+        },
+      ])
+    }),
+  )
+
+  it.effect("rejects output text events without the spec-required item id", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "response.output_text.delta", delta: "orphaned" },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error.reason._tag).toBe("InvalidProviderOutput")
+      expect(error.message).toContain("response.output_text.delta is missing item_id")
+    }),
+  )
+
+  it.effect("rejects reasoning events without the spec-required item id", () =>
+    Effect.gen(function* () {
+      const events = [
+        { type: "response.reasoning_summary_part.added", summary_index: 0 },
+        { type: "response.reasoning_summary_part.done", summary_index: 0 },
+        { type: "response.reasoning_text.done" },
+      ]
+
+      for (const event of events) {
+        const error = yield* LLMClient.generate(request).pipe(
+          Effect.provide(
+            fixedResponse(sseEvents(event, { type: "response.completed", response: { id: "resp_1" } })),
+          ),
+          Effect.flip,
+        )
+        expect(error.reason._tag).toBe("InvalidProviderOutput")
+        expect(error.message).toContain(`${event.type} is missing item_id`)
+      }
+    }),
+  )
+
  it.effect("maps incomplete response reasons", () =>
    Effect.gen(function* () {
      const generate = (incompleteDetails: object) =>
@@ -889,12 +1016,7 @@ describe("OpenAI Responses route", () => {
      const unknown = yield* generate({})
      const custom = yield* generate({ reason: "provider_limit" })

-      expect([
-        length.finishReason,
-        contentFilter.finishReason,
-        unknown.finishReason,
-        custom.finishReason,
-      ]).toEqual([
+      expect([length.finishReason, contentFilter.finishReason, unknown.finishReason, custom.finishReason]).toEqual([
        { normalized: "length", raw: "max_output_tokens" },
        { normalized: "content-filter", raw: "content_filter" },
        { normalized: "unknown", raw: undefined },
@@ -999,7 +1121,7 @@ describe("OpenAI Responses route", () => {
  it.effect("streams each reasoning summary part as a separate block", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, { providerOptions: { openai: { store: false } } }),
+        LLMRequest.update(request, { providerOptions: { openai: { store: false } } }),
      ).pipe(
        Effect.provide(
          fixedResponse(
@@ -1054,7 +1176,7 @@ describe("OpenAI Responses route", () => {
  it.effect("closes reasoning summary parts when storage is not disabled", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, { providerOptions: { openai: { store: true } } }),
+        LLMRequest.update(request, { providerOptions: { openai: { store: true } } }),
      ).pipe(
        Effect.provide(
          fixedResponse(
@@ -1381,8 +1503,8 @@ describe("OpenAI Responses route", () => {
        { type: "response.completed", response: { usage: { input_tokens: 5, output_tokens: 1 } } },
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))
      const usage = new Usage({
@@ -1467,8 +1589,8 @@ describe("OpenAI Responses route", () => {
        { type: "response.completed", response: { usage: { input_tokens: 5, output_tokens: 1 } } },
      )
      const response = yield* LLMClient.generate(
-        LLM.updateRequest(request, {
-          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
        }),
      ).pipe(Effect.provide(fixedResponse(body)))

@@ -3,6 +3,7 @@ import { Effect, Schema } from "effect"
 import {
  LLM,
  LLMEvent,
+  LLMRequest,
  LLMResponse,
  Message,
  ToolRuntime,
@@ -11,7 +12,6 @@ import {
  toDefinitions,
  type ContentPart,
  type FinishReason,
-  type LLMRequest,
  type Model,
 } from "../src"
 import { LLMClient } from "../src/route"
@@ -91,7 +91,7 @@ const restroomImage = () =>
 export const runWeatherToolLoop = (request: LLMRequest) =>
  Effect.gen(function* () {
    const tools = { [weatherToolName]: weatherRuntimeTool }
-    let next = LLM.updateRequest(request, { tools: toDefinitions(tools) })
+    let next = LLMRequest.update(request, { tools: toDefinitions(tools) })
    const events: LLMEvent[] = []

    for (let step = 0; step < 10; step++) {
@@ -108,7 +108,7 @@ export const runWeatherToolLoop = (request: LLMRequest) =>
        ToolRuntime.dispatch(tools, call).pipe(Effect.map((result) => [call, result] as const)),
      )
      events.push(...dispatched.flatMap(([, result]) => result.events))
-      next = LLM.updateRequest(next, {
+      next = LLMRequest.update(next, {
        messages: [
          ...next.messages,
          Message.assistant(assistantContent(response.events)),
@@ -123,10 +123,8 @@ export const runWeatherToolLoop = (request: LLMRequest) =>
 const assistantContent = (events: ReadonlyArray<LLMEvent>) =>
  events.reduce(LLMResponse.reduce, LLMResponse.empty()).message.content

-export const expectFinish = (
-  events: ReadonlyArray<LLMEvent>,
-  reason: FinishReason,
-) => expect(events.at(-1)).toMatchObject({ type: "finish", reason: { normalized: reason } })
+export const expectFinish = (events: ReadonlyArray<LLMEvent>, reason: FinishReason) =>
+  expect(events.at(-1)).toMatchObject({ type: "finish", reason: { normalized: reason } })

 export const expectWeatherToolCall = (response: LLMResponse) =>
  expect(response.toolCalls).toMatchObject([
@@ -1,4 +1,5 @@
 import { describe, expect } from "bun:test"
+import { Content } from "@opencode-ai/schema/tool"
 import { Effect, Schema, Stream } from "effect"
 import {
  GenerationOptions,
@@ -7,7 +8,6 @@ import {
  LLMRequest,
  LLMResponse,
  ToolChoice,
-  ToolContent,
  ToolOutput,
  toDefinitions,
 } from "../src"
@@ -279,7 +279,7 @@ describe("LLMClient tools", () => {

  it.effect("models canonical tool files with URIs", () =>
    Effect.sync(() => {
-      const decode = Schema.decodeUnknownSync(ToolContent)
+      const decode = Schema.decodeUnknownSync(Content)

      expect(decode({ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" })).toEqual({
        type: "file",
@@ -539,6 +539,7 @@ describe("LLMClient tools", () => {
                  },
                  { type: "content_block_stop", index: 1 },
                  { type: "message_delta", delta: { stop_reason: "tool_use" }, usage: { output_tokens: 5 } },
+                  { type: "message_stop" },
                )
              : sseEvents(
                  { type: "message_start", message: { usage: { input_tokens: 5 } } },
@@ -546,6 +547,7 @@ describe("LLMClient tools", () => {
                  { type: "content_block_delta", index: 0, delta: { type: "text_delta", text: "Done." } },
                  { type: "content_block_stop", index: 0 },
                  { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 1 } },
+                  { type: "message_stop" },
                ),
            { headers: { "content-type": "text/event-stream" } },
          )
@@ -553,7 +555,7 @@ describe("LLMClient tools", () => {
      )

      yield* TestToolRuntime.runTools({
-        request: LLM.updateRequest(baseRequest, {
+        request: LLMRequest.update(baseRequest, {
          model: AnthropicMessages.route
            .with({ auth: Auth.header("x-api-key", "test") })
            .model({ id: "claude-sonnet-4-5" }),
@@ -801,6 +803,7 @@ describe("LLMClient tools", () => {
              { type: "content_block_delta", index: 2, delta: { type: "text_delta", text: "Done." } },
              { type: "content_block_stop", index: 2 },
              { type: "message_delta", delta: { stop_reason: "end_turn" }, usage: { output_tokens: 8 } },
+              { type: "message_stop" },
            ),
            { headers: { "content-type": "text/event-stream" } },
          )
@@ -808,7 +811,7 @@ describe("LLMClient tools", () => {
      )
      const events = Array.from(
        yield* TestToolRuntime.runTools({
-          request: LLM.updateRequest(baseRequest, {
+          request: LLMRequest.update(baseRequest, {
            model: AnthropicMessages.route
              .with({ auth: Auth.header("x-api-key", "test") })
              .model({ id: "claude-sonnet-4-5" }),
@@ -56,7 +56,7 @@
    "@opencode-ai/client": "file:vendor/opencode-ai-client-1.17.13.tgz",
    "@opencode-ai/core": "workspace:*",
    "@opencode-ai/schema": "workspace:*",
-    "@opencode-ai/sdk": "workspace:*",
+    "@opencode-ai/sdk": "1.18.5",
    "@opencode-ai/session-ui": "workspace:*",
    "@opencode-ai/ui": "workspace:*",
    "@pierre/trees": "1.0.0-beta.4",
@@ -8,8 +8,8 @@ import type {
  QuestionRequest,
  Session,
  SessionStatus,
-  FileDiffInfo,
 } from "@opencode-ai/sdk/v2/client"
+import type { SessionDiff } from "@/utils/diffs"
 import type { State, VcsCache } from "./types"
 import { trimSessions } from "./session-trim"
 import { dropSessionCaches } from "./session-cache"
@@ -171,7 +171,7 @@ export function applyDirectoryEvent(input: {
      break
    }
    case "session.diff": {
-      const props = event.properties as { sessionID: string; diff: FileDiffInfo[] }
+      const props = event.properties as { sessionID: string; diff: SessionDiff[] }
      input.setStore("session_diff", props.sessionID, reconcile(list(props.diff), { key: "file" }))
      break
    }
@@ -5,8 +5,8 @@ import type {
  PermissionRequest,
  QuestionRequest,
  SessionStatus,
-  FileDiffInfo,
 } from "@opencode-ai/sdk/v2/client"
+import type { SessionDiff } from "@/utils/diffs"
 import { dropSessionCaches, pickSessionCacheEvictions } from "./session-cache"

 const msg = (id: string, sessionID: string) =>
@@ -32,7 +32,7 @@ describe("app session cache", () => {
  test("dropSessionCaches clears orphaned parts without message rows", () => {
    const store: {
      session_status: Record<string, SessionStatus | undefined>
-      session_diff: Record<string, FileDiffInfo[] | undefined>
+      session_diff: Record<string, SessionDiff[] | undefined>
      message: Record<string, Message[] | undefined>
      part: Record<string, Part[] | undefined>
      permission: Record<string, PermissionRequest[] | undefined>
@@ -63,7 +63,7 @@ describe("app session cache", () => {
    const m = msg("msg_1", "ses_1")
    const store: {
      session_status: Record<string, SessionStatus | undefined>
-      session_diff: Record<string, FileDiffInfo[] | undefined>
+      session_diff: Record<string, SessionDiff[] | undefined>
      message: Record<string, Message[] | undefined>
      part: Record<string, Part[] | undefined>
      permission: Record<string, PermissionRequest[] | undefined>
@@ -4,14 +4,14 @@ import type {
  PermissionRequest,
  QuestionRequest,
  SessionStatus,
-  FileDiffInfo,
 } from "@opencode-ai/sdk/v2/client"
+import type { SessionDiff } from "@/utils/diffs"

 export const SESSION_CACHE_LIMIT = 40

 type SessionCache = {
  session_status: Record<string, SessionStatus | undefined>
-  session_diff: Record<string, FileDiffInfo[] | undefined>
+  session_diff: Record<string, SessionDiff[] | undefined>
  message: Record<string, Message[] | undefined>
  part: Record<string, Part[] | undefined>
  permission: Record<string, PermissionRequest[] | undefined>
@@ -13,9 +13,9 @@ import type {
  ReferenceInfo,
  Session,
  SessionStatus,
-  FileDiffInfo,
  VcsInfo,
 } from "@opencode-ai/sdk/v2/client"
+import type { SessionDiff } from "@/utils/diffs"
 import { NormalizedProviderListResponse } from "@opencode-ai/session-ui/context"
 import type { Accessor } from "solid-js"
 import type { SetStoreFunction, Store } from "solid-js/store"
@@ -50,7 +50,7 @@ export type State = {
  }
  session_working(id: string): boolean
  session_diff: {
-    [sessionID: string]: FileDiffInfo[]
+    [sessionID: string]: SessionDiff[]
  }
  permission: {
    [sessionID: string]: PermissionRequest[]
@@ -25,7 +25,7 @@ describe("adaptServerEvent", () => {
    } as OpenCodeEvent

    expect(adaptServerEvent(current)).toMatchObject({
-      type: "permission.asked",
+      type: "permission.v2.asked",
      properties: { id: "perm_1", sessionID: "ses_1", permission: "read", patterns: ["src/**"] },
      current,
    })
@@ -1,5 +1,5 @@
 import type { OpenCodeEvent } from "@opencode-ai/client/promise"
-import type { Event } from "@opencode-ai/sdk/v2/client"
+import type { Event, PermissionRequest } from "@opencode-ai/sdk/v2/client"
 import { createSimpleContext } from "@opencode-ai/ui/context"
 import { createGlobalEmitter } from "@solid-primitives/event-bus"
 import { makeEventListener } from "@solid-primitives/event-listener"
@@ -18,7 +18,15 @@ const isAbortError = (error: unknown) =>
  error !== null && typeof error === "object" && "name" in error && error.name === "AbortError"

 const isStreamClosed = (error: unknown, signal?: AbortSignal) => isAbortError(error) || signal?.aborted === true
-export type ServerEvent = Event & { current?: OpenCodeEvent }
+type PermissionEvent = {
+  id: string
+  type: "permission.v2.asked"
+  properties: PermissionRequest
+  current?: OpenCodeEvent
+}
+export type ServerEvent = (Event | PermissionEvent) & {
+  current?: OpenCodeEvent
+}
 type QueuedServerEvent = { directory: string; payload: ServerEvent }
 type CurrentDelta = Extract<
  OpenCodeEvent,
@@ -29,7 +37,7 @@ export function adaptServerEvent(event: OpenCodeEvent): ServerEvent {
  if (event.type === "permission.v2.asked") {
    return {
      id: event.id,
-      type: "permission.asked",
+      type: "permission.v2.asked",
      properties: {
        id: event.data.id,
        sessionID: event.data.sessionID,
@@ -43,16 +51,16 @@ export function adaptServerEvent(event: OpenCodeEvent): ServerEvent {
            : undefined,
      },
      current: event,
-    } as ServerEvent
+    }
  }
  if (event.type === "permission.v2.replied")
-    return { id: event.id, type: "permission.replied", properties: event.data, current: event } as ServerEvent
+    return { id: event.id, type: "permission.v2.replied", properties: event.data, current: event } as ServerEvent
  if (event.type === "question.v2.asked")
-    return { id: event.id, type: "question.asked", properties: event.data, current: event } as ServerEvent
+    return { id: event.id, type: "question.v2.asked", properties: event.data, current: event } as ServerEvent
  if (event.type === "question.v2.replied")
-    return { id: event.id, type: "question.replied", properties: event.data, current: event } as ServerEvent
+    return { id: event.id, type: "question.v2.replied", properties: event.data, current: event } as ServerEvent
  if (event.type === "question.v2.rejected")
-    return { id: event.id, type: "question.rejected", properties: event.data, current: event } as ServerEvent
+    return { id: event.id, type: "question.v2.rejected", properties: event.data, current: event } as ServerEvent
  return { id: event.id, type: event.type, properties: event.data, current: event } as ServerEvent
 }

@@ -8,8 +8,8 @@ import type {
  QuestionRequest,
  Session,
  SessionStatus,
-  FileDiffInfo,
 } from "@opencode-ai/sdk/v2/client"
+import type { SessionDiff } from "@/utils/diffs"
 import { batch } from "solid-js"
 import { createStore, produce, reconcile } from "solid-js/store"
 import { diffs as cleanDiffs, message as cleanMessage } from "@/utils/diffs"
@@ -140,7 +140,7 @@ export function createServerSession(client: OpencodeClient, options?: { retry?:
  const [data, setData] = createStore({
    info: {} as Record<string, Session | undefined>,
    session_status: {} as Record<string, SessionStatus>,
-    session_diff: {} as Record<string, FileDiffInfo[]>,
+    session_diff: {} as Record<string, SessionDiff[]>,
    permission: {} as Record<string, PermissionRequest[]>,
    question: {} as Record<string, QuestionRequest[]>,
    message: {} as Record<string, Message[]>,
@@ -773,7 +773,7 @@ export function createServerSession(client: OpencodeClient, options?: { retry?:
        return
      }
      case "session.diff": {
-        const props = event.properties as { sessionID: string; diff: FileDiffInfo[] }
+        const props = event.properties as { sessionID: string; diff: SessionDiff[] }
        setData("session_diff", props.sessionID, reconcile(cleanDiffs(props.diff), { key: "file" }))
        return
      }
@@ -909,13 +909,8 @@ export default function Page() {
  )

  const stopVcs = sdk().event.listen((evt) => {
-    if (evt.details.type !== "filesystem.changed") return
-    const props =
-      typeof evt.details.properties === "object" && evt.details.properties
-        ? (evt.details.properties as Record<string, unknown>)
-        : undefined
-    const file = typeof props?.file === "string" ? props.file : undefined
-    if (!file || file.startsWith(".git/")) return
+    if (evt.details.type !== "file.watcher.updated") return
+    if (evt.details.properties.file.startsWith(".git/")) return
    refreshVcs()
  })
  onCleanup(stopVcs)
@@ -1,6 +1,7 @@
 import { createEffect, onCleanup, type JSX } from "solid-js"
 import { makeEventListener } from "@solid-primitives/event-listener"
-import type { FileDiffInfo, VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { SessionDiff } from "@/utils/diffs"
 import { SessionReview } from "@opencode-ai/session-ui/session-review"
 import type {
  SessionReviewCommentActions,
@@ -14,7 +15,7 @@ import type { LineComment } from "@/context/comments"

 export type DiffStyle = "unified" | "split"

-type ReviewDiff = FileDiffInfo | VcsFileDiff
+type ReviewDiff = SessionDiff | VcsFileDiff

 export interface SessionReviewTabProps {
  title?: JSX.Element
@@ -23,7 +23,8 @@ import { Mark } from "@opencode-ai/ui/logo"
 import { IconButtonV2 } from "@opencode-ai/ui/v2/icon-button-v2"
 import { KeybindV2 } from "@opencode-ai/ui/v2/keybind-v2"
 import { TooltipV2 } from "@opencode-ai/ui/v2/tooltip-v2"
-import type { FileDiffInfo, VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { SessionDiff } from "@/utils/diffs"
 import { ConstrainDragYAxis, getDraggableId } from "@/utils/solid-dnd"
 import { useDialog } from "@opencode-ai/ui/context/dialog"

@@ -59,7 +60,7 @@ import type { RenderDiff } from "@/pages/session/v2/review-diff-kinds"

 export function SessionSidePanel(props: {
  canReview: () => boolean
-  diffs: () => (FileDiffInfo | VcsFileDiff)[]
+  diffs: () => (SessionDiff | VcsFileDiff)[]
  diffsReady: () => boolean
  empty: () => string
  hasReview: () => boolean
@@ -1,8 +1,9 @@
-import type { FileDiffInfo, VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { SessionDiff } from "@/utils/diffs"
 import type { Kind } from "@/components/file-tree-v2"
 import { normalizeFileTreeV2Path } from "@/components/file-tree-v2-model"

-export type RenderDiff = FileDiffInfo | VcsFileDiff
+export type RenderDiff = SessionDiff | VcsFileDiff

 export function normalizePath(p: string) {
  return normalizeFileTreeV2Path(p)
@@ -1,5 +1,6 @@
 import { createMemo, createResource, createSignal, Show, type JSX } from "solid-js"
-import type { FileDiffInfo, VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { VcsFileDiff } from "@opencode-ai/sdk/v2"
+import type { SessionDiff } from "@/utils/diffs"
 import {
  SESSION_REVIEW_V2_SIDEBAR_WIDTH_MAX,
  SESSION_REVIEW_V2_SIDEBAR_WIDTH_MIN,
@@ -29,7 +30,7 @@ import {
 import type { ReviewPanelV2State } from "@/pages/session/v2/review-panel-v2-state"
 import { applyFileListKeyDown, SessionFileListV2 } from "@/pages/session/v2/session-file-list-v2"

-type ReviewDiff = FileDiffInfo | VcsFileDiff
+type ReviewDiff = SessionDiff | VcsFileDiff

 export type ReviewPanelV2Props = {
  title?: JSX.Element
@@ -1,5 +1,5 @@
 import { describe, expect, test } from "bun:test"
-import type { FileDiffInfo } from "@opencode-ai/sdk/v2"
+import type { SnapshotFileDiff } from "@opencode-ai/sdk/v2"
 import type { Message } from "@opencode-ai/sdk/v2/client"
 import { diffs, message } from "./diffs"

@@ -9,7 +9,7 @@ const item = {
  additions: 1,
  deletions: 1,
  status: "modified",
-} satisfies FileDiffInfo
+} satisfies SnapshotFileDiff

 describe("diffs", () => {
  test("keeps valid arrays", () => {
@@ -1,9 +1,9 @@
-import type { FileDiffInfo } from "@opencode-ai/sdk/v2"
+import type { SnapshotFileDiff } from "@opencode-ai/sdk/v2"
 import type { Message } from "@opencode-ai/sdk/v2/client"

-type Diff = FileDiffInfo
+export type SessionDiff = SnapshotFileDiff & { file: string; patch: string }

-function diff(value: unknown): value is Diff {
+function diff(value: unknown): value is SessionDiff {
  if (!value || typeof value !== "object" || Array.isArray(value)) return false
  if (!("file" in value) || typeof value.file !== "string") return false
  if (!("patch" in value) || typeof value.patch !== "string") return false
@@ -17,7 +17,7 @@ function object(value: unknown): value is Record<string, unknown> {
  return !!value && typeof value === "object" && !Array.isArray(value)
 }

-export function diffs(value: unknown): Diff[] {
+export function diffs(value: unknown): SessionDiff[] {
  if (Array.isArray(value) && value.every(diff)) return value
  if (Array.isArray(value)) return value.filter(diff)
  if (diff(value)) return [value]
@@ -71,7 +71,7 @@ export async function streamTurn(input: {
      const next = await stream.next()
      if (next.done) throw new Error("event stream disconnected during prompt execution")
      const event = next.value
-      if (event.type === "permission.v2.asked" && event.data.sessionID === input.sessionID) {
+      if (event.type === "permission.asked" && event.data.sessionID === input.sessionID) {
        const tool = event.data.source?.callID ? tools.get(event.data.source.callID) : undefined
        await replyPermission({
          client: input.client,
@@ -5,7 +5,7 @@ import { Result } from "effect"
 import { isAbsolute, resolve } from "node:path"
 import { pendingToolCall, stringValue, toLocations, toToolKind, type ToolInput } from "./tool"

-type PermissionEvent = Extract<EventSubscribeOutput, { type: "permission.v2.asked" }>
+type PermissionEvent = Extract<EventSubscribeOutput, { type: "permission.asked" }>
 type Connection = Pick<AgentSideConnection, "requestPermission"> & Partial<Pick<AgentSideConnection, "writeTextFile">>
 type Tool = { readonly name: string; readonly input: ToolInput }

@@ -44,6 +44,7 @@ export function toLocations(toolName: string, input: ToolInput, cwd?: string): T
      return workdir ? [{ path: workdir }] : []
    }
    case "read":
+      return locationFrom(input.path)
    case "edit":
    case "write":
    case "patch":
@@ -9,8 +9,8 @@ import {
  Provider,
  Reference,
  Skill,
-} from "@opencode-ai/plugin/v2/effect"
-import { Tool } from "@opencode-ai/plugin/v2/effect/tool"
+} from "@opencode-ai/plugin/effect"
+import { Tool } from "@opencode-ai/schema/tool"

 const key = Symbol.for("opencode.plugin.v2.effect")
 ;(globalThis as typeof globalThis & { [key]?: unknown })[key] = {
@@ -24,5 +24,5 @@ const key = Symbol.for("opencode.plugin.v2.effect")
  Provider,
  Reference,
  Skill,
-  Tool,
+  Tool: { Error: Tool.Error },
 }
@@ -9,8 +9,7 @@ import {
  Provider,
  Reference,
  Skill,
-} from "@opencode-ai/plugin/v2"
-import { Tool } from "@opencode-ai/plugin/v2/tool"
+} from "@opencode-ai/plugin"

 const key = Symbol.for("opencode.plugin.v2.promise")
 ;(globalThis as typeof globalThis & { [key]?: unknown })[key] = {
@@ -24,5 +23,4 @@ const key = Symbol.for("opencode.plugin.v2.promise")
  Provider,
  Reference,
  Skill,
-  Tool,
 }
@@ -177,7 +177,7 @@ export async function runNonInteractivePrompt(input: Input) {
      }
      const event = next.value

-      if (event.type === "permission.v2.asked" && submitted && event.data.sessionID === input.sessionID) {
+      if (event.type === "permission.asked" && submitted && event.data.sessionID === input.sessionID) {
        await replyPermission(event.data)
        continue
      }
@@ -13,11 +13,13 @@ type Options = {
  readonly command?: ReadonlyArray<string>
 }

+const startupDirectory = process.cwd()
+
 function command(password: string, options: Options) {
  const [executable, ...args] = options.command ?? [...selfCommand(), "serve"]
  if (!executable) throw new Error("Failed to resolve standalone server command")
  return ChildProcess.make(executable, [...args, "--stdio", "--port", "0"], {
-    cwd: process.cwd(),
+    cwd: startupDirectory,
    // Explicit entry wins over anything inherited, so a user-exported
    // OPENCODE_PASSWORD cannot shadow the child's lease credential.
    env: { OPENCODE_PASSWORD: password },
@@ -1,11 +1,13 @@
 import path from "node:path"

+const entrypoint = process.argv[1] ? path.resolve(process.argv[1]) : undefined
+
 export function selfCommand() {
  const runtime = path.basename(process.execPath, path.extname(process.execPath)).toLowerCase()
  if (runtime !== "bun" && runtime !== "node" && runtime !== "nodejs") return [process.execPath]
-  if (!process.argv[1]) throw new Error("Failed to resolve CLI entrypoint")
-  if (runtime === "node" || runtime === "nodejs") return [process.execPath, ...nodeFlags(), process.argv[1]]
-  return [process.execPath, process.argv[1]]
+  if (!entrypoint) throw new Error("Failed to resolve CLI entrypoint")
+  if (runtime === "node" || runtime === "nodejs") return [process.execPath, ...nodeFlags(), entrypoint]
+  return [process.execPath, entrypoint]
 }

 function nodeFlags() {
@@ -502,7 +502,7 @@ function permissionAsked(
    readonly source?: { readonly type: "tool"; readonly messageID: string; readonly callID: string }
  } = {},
 ) {
-  return ephemeralEvent("permission.v2.asked", {
+  return ephemeralEvent("permission.asked", {
    id,
    sessionID,
    action: input.action ?? "shell",
@@ -28,7 +28,7 @@ describe("acp tools", () => {
  })

  test("extracts file locations from tool input", () => {
-    expect(toLocations("read", { filePath: "/tmp/a.ts" })).toEqual([{ path: "/tmp/a.ts" }])
+    expect(toLocations("read", { path: "/tmp/a.ts" })).toEqual([{ path: "/tmp/a.ts" }])
    expect(toLocations("edit", { filePath: "/tmp/b.ts" })).toEqual([{ path: "/tmp/b.ts" }])
    expect(toLocations("write", { filePath: "/tmp/c.ts" })).toEqual([{ path: "/tmp/c.ts" }])
    expect(toLocations("grep", { path: "/repo/src" })).toEqual([{ path: "/repo/src" }])
@@ -43,7 +43,7 @@ describe("acp tools", () => {
    ])
    expect(toLocations("bash", { command: "pwd", workdir: "/abs/dir" }, "/workspace")).toEqual([{ path: "/abs/dir" }])
    expect(toLocations("bash", { command: "printf hello" })).toEqual([])
-    expect(toLocations("read", { path: "/tmp/missing-file-path.ts" })).toEqual([])
+    expect(toLocations("read", { path: "/tmp/missing-file-path.ts" })).toEqual([{ path: "/tmp/missing-file-path.ts" }])
  })

  test("builds completed content with text and image attachments", () => {
@@ -205,12 +205,13 @@ describe("acp tools", () => {
      runningToolUpdate({
        toolCallId: "call",
        toolName: "read",
-        state: { input: { filePath: "/tmp/a" } },
+        state: { input: { path: "/tmp/a" } },
        content: [{ type: "text", text: "done" }],
      }),
    ).toMatchObject({
      toolCallId: "call",
      status: "in_progress",
+      locations: [{ path: "/tmp/a" }],
      content: [{ type: "content", content: { type: "text", text: "done" } }],
    })
  })
@@ -273,7 +274,7 @@ describe("acp tools", () => {
      errorToolUpdate({
        toolCallId: "call",
        toolName: "read",
-        input: { filePath: "/tmp/a" },
+        input: { path: "/tmp/a" },
        content: [{ type: "text", text: "partial output" }],
        metadata: { path: "/tmp/a" },
        error: "failed",
@@ -284,7 +285,7 @@ describe("acp tools", () => {
      kind: "read",
      title: "read",
      locations: [{ path: "/tmp/a" }],
-      rawInput: { filePath: "/tmp/a" },
+      rawInput: { path: "/tmp/a" },
      content: [
        { type: "content", content: { type: "text", text: "partial output" } },
        { type: "content", content: { type: "text", text: "failed" } },
@@ -3,12 +3,14 @@ import { Service } from "@opencode-ai/client/effect/service"
 import path from "node:path"
 import { Standalone } from "../../src/services/standalone"

-process.argv[1] = path.join(import.meta.dir, "../../src/index.ts")
+process.chdir(path.join(import.meta.dir, "../../../.."))

 await Effect.runPromise(
  Effect.scoped(
    Effect.gen(function* () {
-      const endpoint = yield* Standalone.start()
+      const endpoint = yield* Standalone.start({
+        command: [process.execPath, path.join(import.meta.dir, "../../src/index.ts"), "serve"],
+      })
      const response = yield* Effect.promise(() =>
        fetch(new URL("/api/health", endpoint.url), { headers: Service.headers(endpoint) }),
      )
@@ -75,20 +75,11 @@ export const define = sdk.Plugin.define`
  const effectPluginModule = promisePluginModule
    .replace("opencode.plugin.v2.promise", "opencode.plugin.v2.effect")
    .replace("Promise plugin", "Effect plugin")
-  const promiseToolModule = `const sdk = globalThis[Symbol.for("opencode.plugin.v2.promise")]
-if (!sdk) throw new Error("OpenCode Promise plugin SDK is unavailable")
-export const Tool = sdk.Tool
-export const make = sdk.Tool.make`
+  const promiseToolModule = `export {}`
  const effectToolModule = `const sdk = globalThis[Symbol.for("opencode.plugin.v2.effect")]
 if (!sdk) throw new Error("OpenCode Effect plugin SDK is unavailable")
-export const Tool = sdk.Tool
-export const Failure = sdk.Tool.Failure
-export const RegistrationError = sdk.Tool.RegistrationError
-export const make = sdk.Tool.make
-export const validateName = sdk.Tool.validateName
-export const registrationEntries = sdk.Tool.registrationEntries
-export const validateNamespace = sdk.Tool.validateNamespace
-export const toLLMDefinition = sdk.Tool.toLLMDefinition`
+export const Error = sdk.Tool.Error
+`
  return `#!/usr/bin/env -S node ${nodeExecArgv.join(" ")}
 import __cjs_mod__ from "node:module"
 import { chmodSync as __ocChmod, existsSync as __ocExists, lstatSync as __ocLstat, mkdirSync as __ocMkdir, renameSync as __ocRename, rmSync as __ocRm, writeFileSync as __ocWrite } from "node:fs"
@@ -100,17 +91,17 @@ const __filename = import.meta.filename
 const __dirname = import.meta.dirname
 const require = __cjs_mod__.createRequire(import.meta.url)
 const __ocPluginModules = ${JSON.stringify({
-    "@opencode-ai/plugin/v2": "opencode:plugin-v2",
-    "@opencode-ai/plugin/v2/plugin": "opencode:plugin-v2-plugin",
-    "@opencode-ai/plugin/v2/tool": "opencode:plugin-v2-tool",
-    "@opencode-ai/plugin/v2/effect": "opencode:plugin-v2-effect",
-    "@opencode-ai/plugin/v2/effect/plugin": "opencode:plugin-v2-effect-plugin",
-    "@opencode-ai/plugin/v2/effect/tool": "opencode:plugin-v2-effect-tool",
+    "@opencode-ai/plugin": "opencode:plugin-v2",
+    "@opencode-ai/plugin/promise/plugin": "opencode:plugin-promise-plugin",
+    "@opencode-ai/plugin/promise/tool": "opencode:plugin-promise-tool",
+    "@opencode-ai/plugin/effect": "opencode:plugin-v2-effect",
+    "@opencode-ai/plugin/effect/plugin": "opencode:plugin-v2-effect-plugin",
+    "@opencode-ai/plugin/effect/tool": "opencode:plugin-v2-effect-tool",
  })}
 const __ocPluginSources = ${JSON.stringify({
    "opencode:plugin-v2": promiseModule,
-    "opencode:plugin-v2-plugin": promisePluginModule,
-    "opencode:plugin-v2-tool": promiseToolModule,
+    "opencode:plugin-promise-plugin": promisePluginModule,
+    "opencode:plugin-promise-tool": promiseToolModule,
    "opencode:plugin-v2-effect": effectModule,
    "opencode:plugin-v2-effect-plugin": effectPluginModule,
    "opencode:plugin-v2-effect-tool": effectToolModule,
@@ -36,7 +36,7 @@
    "@opencode-ai/protocol": "workspace:*"
  },
  "peerDependencies": {
-    "effect": "4.0.0-beta.98"
+    "effect": "4.0.0-beta.101"
  },
  "peerDependenciesMeta": {
    "effect": {
@@ -6,11 +6,86 @@ import {
  groupNames,
  promiseOmitEndpoints,
 } from "@opencode-ai/protocol/client"
-import { Effect } from "effect"
+import { Agent } from "@opencode-ai/schema/agent"
+import { Command } from "@opencode-ai/schema/command"
+import { Credential } from "@opencode-ai/schema/credential"
+import { Event } from "@opencode-ai/schema/event"
+import { EventLog } from "@opencode-ai/schema/event-log"
+import { FileDiff } from "@opencode-ai/schema/file-diff"
+import { FileSystem } from "@opencode-ai/schema/filesystem"
+import { Form } from "@opencode-ai/schema/form"
+import { InstructionEntry } from "@opencode-ai/schema/instruction-entry"
+import { Integration } from "@opencode-ai/schema/integration"
+import { Location } from "@opencode-ai/schema/location"
+import { Mcp } from "@opencode-ai/schema/mcp"
+import { Model } from "@opencode-ai/schema/model"
+import { Permission } from "@opencode-ai/schema/permission"
+import { PermissionSaved } from "@opencode-ai/schema/permission-saved"
+import { Plugin } from "@opencode-ai/schema/plugin"
+import { Project } from "@opencode-ai/schema/project"
+import { ProjectCopy } from "@opencode-ai/schema/project-copy"
+import { AgentAttachment, FileAttachment, Prompt, PromptMention } from "@opencode-ai/schema/prompt"
+import { PromptInput } from "@opencode-ai/schema/prompt-input"
+import { Provider } from "@opencode-ai/schema/provider"
+import { Pty } from "@opencode-ai/schema/pty"
+import { PtyTicket } from "@opencode-ai/schema/pty-ticket"
+import { Question } from "@opencode-ai/schema/question"
+import { Reference } from "@opencode-ai/schema/reference"
+import { AbsolutePath, PositiveInt, RelativePath } from "@opencode-ai/schema/schema"
+import { Session } from "@opencode-ai/schema/session"
+import { SessionMessage } from "@opencode-ai/schema/session-message"
+import { SessionPending } from "@opencode-ai/schema/session-pending"
+import { Shell } from "@opencode-ai/schema/shell"
+import { Skill } from "@opencode-ai/schema/skill"
+import { Vcs } from "@opencode-ai/schema/vcs"
+import { WebSearch } from "@opencode-ai/schema/websearch"
+import { Workspace } from "@opencode-ai/schema/workspace"
+import { Effect, Schema } from "effect"
 import { fileURLToPath } from "url"

 const promiseContract = compile(ClientApi, { groupNames, omitEndpoints: promiseOmitEndpoints })
 const effectContract = compile(ClientApi, { groupNames, omitEndpoints: effectOmitEndpoints })
+const effectTypeReferences = [
+  ...namespaceTypes("Agent", "@opencode-ai/schema/agent", Agent),
+  ...namespaceTypes("Command", "@opencode-ai/schema/command", Command),
+  ...namespaceTypes("Credential", "@opencode-ai/schema/credential", Credential),
+  ...namespaceTypes("Event", "@opencode-ai/schema/event", Event),
+  ...namespaceTypes("EventLog", "@opencode-ai/schema/event-log", EventLog),
+  ...namespaceTypes("FileDiff", "@opencode-ai/schema/file-diff", FileDiff),
+  ...namespaceTypes("FileSystem", "@opencode-ai/schema/filesystem", FileSystem),
+  ...namespaceTypes("Form", "@opencode-ai/schema/form", Form),
+  ...namespaceTypes("InstructionEntry", "@opencode-ai/schema/instruction-entry", InstructionEntry),
+  ...namespaceTypes("Integration", "@opencode-ai/schema/integration", Integration),
+  ...namespaceTypes("Location", "@opencode-ai/schema/location", Location),
+  ...namespaceTypes("Mcp", "@opencode-ai/schema/mcp", Mcp),
+  ...namespaceTypes("Model", "@opencode-ai/schema/model", Model),
+  ...namespaceTypes("Permission", "@opencode-ai/schema/permission", Permission),
+  ...namespaceTypes("PermissionSaved", "@opencode-ai/schema/permission-saved", PermissionSaved),
+  ...namespaceTypes("Plugin", "@opencode-ai/schema/plugin", Plugin),
+  ...namespaceTypes("Project", "@opencode-ai/schema/project", Project),
+  ...namespaceTypes("ProjectCopy", "@opencode-ai/schema/project-copy", ProjectCopy),
+  ...namespaceTypes("PromptInput", "@opencode-ai/schema/prompt-input", PromptInput),
+  ...namespaceTypes("Provider", "@opencode-ai/schema/provider", Provider),
+  ...namespaceTypes("Pty", "@opencode-ai/schema/pty", Pty),
+  ...namespaceTypes("PtyTicket", "@opencode-ai/schema/pty-ticket", PtyTicket),
+  ...namespaceTypes("Question", "@opencode-ai/schema/question", Question),
+  ...namespaceTypes("Reference", "@opencode-ai/schema/reference", Reference),
+  ...namespaceTypes("Session", "@opencode-ai/schema/session", Session),
+  ...namespaceTypes("SessionMessage", "@opencode-ai/schema/session-message", SessionMessage),
+  ...namespaceTypes("SessionPending", "@opencode-ai/schema/session-pending", SessionPending),
+  ...namespaceTypes("Shell", "@opencode-ai/schema/shell", Shell),
+  ...namespaceTypes("Skill", "@opencode-ai/schema/skill", Skill),
+  ...namespaceTypes("Vcs", "@opencode-ai/schema/vcs", Vcs),
+  ...namespaceTypes("WebSearch", "@opencode-ai/schema/websearch", WebSearch),
+  ...namespaceTypes("Workspace", "@opencode-ai/schema/workspace", Workspace),
+  typeReference("Prompt", "@opencode-ai/schema/prompt", Prompt),
+  typeReference("PromptMention", "@opencode-ai/schema/prompt", PromptMention),
+  typeReference("FileAttachment", "@opencode-ai/schema/prompt", FileAttachment),
+  typeReference("AgentAttachment", "@opencode-ai/schema/prompt", AgentAttachment),
+  typeReference("AbsolutePath", "@opencode-ai/schema/schema", AbsolutePath),
+  typeReference("PositiveInt", "@opencode-ai/schema/schema", PositiveInt),
+  typeReference("RelativePath", "@opencode-ai/schema/schema", RelativePath),
+]

 await Effect.runPromise(
  Effect.all(
@@ -22,14 +97,40 @@ await Effect.runPromise(
        fileURLToPath(new URL("../src/promise/generated", import.meta.url)),
      ),
      write(
-        emitEffectImported(effectContract, { module: "../../contract", api: "ClientApi" }),
+        emitEffectImported(effectContract, {
+          module: "../../contract",
+          api: "ClientApi",
+          shapeModule: "../api/api.js",
+        }),
        fileURLToPath(new URL("../src/effect/generated", import.meta.url)),
      ),
      write(
-        emitEffectShape(effectContract, { module: "../../contract", api: "ClientApi" }),
+        emitEffectShape(effectContract, {
+          typeReferences: effectTypeReferences,
+          outputTypes: {
+            "event.subscribe": {
+              name: "OpenCodeEvent",
+              import: 'import type { OpenCodeEvent } from "@opencode-ai/protocol/groups/event"',
+            },
+          },
+        }),
        fileURLToPath(new URL("../src/effect/api", import.meta.url)),
      ),
    ],
    { concurrency: 3, discard: true },
  ).pipe(Effect.provide(NodeFileSystem.layer)),
 )
+
+function namespaceTypes(namespace: string, module: string, values: object) {
+  return Object.entries(values).flatMap(([name, schema]) =>
+    Schema.isSchema(schema) ? [typeReference(`${namespace}.${name}`, module, schema)] : [],
+  )
+}
+
+function typeReference(name: string, module: string, schema: Schema.Top) {
+  return {
+    schema,
+    name,
+    import: `import type { ${name.split(".")[0]} } from ${JSON.stringify(module)}`,
+  }
+}
@@ -1,7 +1,9 @@
-import type { ModelApi, ProviderApi } from "./api/api.js"
+import type { ModelApi, ProviderApi, WebsearchApi } from "./api/api.js"

 export type * from "./api/api.js"

+export type WebSearchApi<E = never> = WebsearchApi<E>
+
 export interface CatalogApi<E = never> {
  readonly provider: ProviderApi<E>
  readonly model: ModelApi<E>
@@ -14,6 +14,7 @@ export type {
  PluginApi,
  ProviderApi,
  ReferenceApi,
+  WebSearchApi,
  SessionApi,
  SkillApi,
 } from "./api.js"
@@ -35,6 +36,7 @@ export { Provider } from "@opencode-ai/schema/provider"
 export { Pty } from "@opencode-ai/schema/pty"
 export { Question } from "@opencode-ai/schema/question"
 export { Reference } from "@opencode-ai/schema/reference"
+export { WebSearch } from "@opencode-ai/schema/websearch"
 export { AbsolutePath, RelativePath } from "@opencode-ai/schema/schema"
 export { Session } from "@opencode-ai/schema/session"
 export { SessionPending } from "@opencode-ai/schema/session-pending"
@@ -8,6 +8,7 @@ export type ModelApi = Client["model"]
 export type PluginApi = Client["plugin"]
 export type ProviderApi = Client["provider"]
 export type ReferenceApi = Client["reference"]
+export type WebSearchApi = Client["websearch"]
 export type SessionApi = Client["session"]
 export type SkillApi = Client["skill"]

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Kit Langton	0778f17f47	refactor(core): use Effect config for diagnostics	2026-07-27 13:26:33 -04:00
Kit Langton	1e479c45dd	feat(core): gate prompt diagnostics by flag	2026-07-27 12:21:07 -04:00
Kit Langton	669bdb4771	test(core): assert prompt cache prefix stability	2026-07-27 12:18:17 -04:00
Kit Langton	babeea33ba	refactor(core): simplify prompt cache diagnostics	2026-07-27 12:18:17 -04:00
Kit Langton	2842480f6c	feat(core): log prompt cache prefix changes	2026-07-27 12:18:17 -04:00
opencode-agent[bot]	33e3d1ebca	fix(core): tolerate missing tool input schemas (#39130 ) Co-authored-by: Dax Raad <d@ironbay.co>	2026-07-27 11:21:47 -04:00
Kit Langton	1f2c59a1b6	fix(core): commit state before finalize publishes (#38983 )	2026-07-27 11:04:04 -04:00
Aiden Cline	65d2a4e00c	feat(core): improve read tool parity (#39126 )	2026-07-27 09:58:37 -05:00
Shoubhit Dash	7d4de3d9e4	fix(core): clarify web search provider prompt (#39123 )	2026-07-27 19:52:36 +05:30
Aiden Cline	9977ef0160	refactor(core): tag read outputs (#39122 )	2026-07-27 09:09:44 -05:00
Simon Klee	9a55d125f6	tui: render mini compaction boundaries (#39103 )	2026-07-27 14:19:03 +02:00
Simon Klee	766aaf448d	tui: add settings to command palette search (#39058 )	2026-07-27 10:45:35 +02:00
Simon Klee	f14d78afeb	tui: skip abort on mini session close (#39067 )	2026-07-27 10:42:37 +02:00
Dax Raad	0261f04b90	fix(core): handle oversized ripgrep matches	2026-07-27 03:17:08 -04:00
Aiden Cline	9b49e7bec9	test(core): implement catalog host model list (#39053 )	2026-07-26 23:32:33 -05:00
Aiden Cline	93cb113cef	fix(util): declare node tracing dependency (#39050 )	2026-07-26 23:12:36 -05:00
Aiden Cline	4216d35e4b	fix(server): declare schema dependency (#39043 )	2026-07-26 22:46:46 -05:00
Dax Raad	863645c671	test(core): update grep error assertion	2026-07-26 20:17:31 -04:00
Dax Raad	5592f5225b	fix(app): update remote sdk contracts	2026-07-26 20:16:58 -04:00
Dax Raad	8db7487c89	refactor(core): consolidate tool architecture	2026-07-26 20:16:58 -04:00
Aiden Cline	0fd73a2976	fix(core): align grep behavior and guidance (#38999 )	2026-07-26 17:29:27 -05:00
Dax Raad	80865407e0	refactor(sdk): remove local legacy package	2026-07-26 02:47:43 -04:00
Dax Raad	28f4284bd7	fix(www): canonicalize production routes	2026-07-26 02:39:12 -04:00
Aiden Cline	7affee529b	fix(core): harden grep search behavior (#38922 )	2026-07-25 23:23:53 -05:00
Aiden Cline	79c7e9446e	fix(core): clarify custom question answers (#38919 )	2026-07-25 23:00:26 -05:00
Shoubhit Dash	efb629a33a	feat(core): add pluggable web search (#35558 ) Co-authored-by: Dax Raad <d@ironbay.co>	2026-07-26 03:55:05 +00:00
Dax Raad	2ddc91a0e8	fix(tui): show shell working directory in prompt	2026-07-25 23:42:53 -04:00
Dax Raad	c7871e14d4	fix(www): remove deployment environment gate	2026-07-25 21:21:57 -04:00
Dax Raad	9840f63b12	chore(www): simplify worker routes	2026-07-25 21:17:25 -04:00
Dax Raad	56a9c0150a	fix(www): mark deploy script as module	2026-07-25 21:17:25 -04:00
Dax Raad	203a0613b8	feat(www): migrate docs to Blume	2026-07-25 21:17:25 -04:00
Aiden Cline	7d8f1bdab3	tweak(core): simplify skill tool description (#38900 )	2026-07-25 17:09:20 -05:00
Aiden Cline	9eea5bc925	fix(core): tweak glob tool description/parameters (#38899 )	2026-07-25 16:52:36 -05:00
Aiden Cline	f753103e82	fix(core): reject file glob roots (#38890 )	2026-07-25 14:43:18 -05:00
Aiden Cline	1e35d33ecb	fix(codemode): search nested namespaces (#38887 )	2026-07-25 14:17:49 -05:00
Aiden Cline	c5bf4edb10	fix(ai): preserve response message phases (#38777 )	2026-07-25 14:06:00 -05:00
Aiden Cline	cce8bb0e1c	fix(core): clarify empty Code Mode guidance (#38883 )	2026-07-25 13:20:16 -05:00
Dax Raad	02c66c5fc1	docs(core): fix OpenCode skill links	2026-07-25 14:08:29 -04:00
Aiden Cline	33390cc457	fix(core): keep execute tool cache stable (#38783 )	2026-07-25 13:01:05 -05:00
Kit Langton	b2afb35527	refactor(core): settle steps lock-free by joining tool fibers first (#38743 )	2026-07-25 13:43:17 -04:00
opencode-agent[bot]	828148909d	fix(tui): preserve workspace while reconnecting (#38788 )	2026-07-25 03:48:42 +00:00
opencode-agent[bot]	454145fe65	fix(tui): preserve workspace while reconnecting (#38788 )	2026-07-25 02:22:47 +00:00
Aiden Cline	1291dc1f11	fix(core): clarify code mode tool boundary (#38785 )	2026-07-24 20:49:55 -05:00
Aiden Cline	c7d7f61146	fix(ai): preserve Anthropic usage metadata (#38751 )	2026-07-24 16:23:51 -05:00
Aiden Cline	13b6845e7e	fix(core): scope MCP execute guidance to Code Mode (#38753 )	2026-07-24 16:02:57 -05:00
Aiden Cline	d1d97014b4	refactor(core): move static Code Mode guidance (#38746 )	2026-07-24 14:46:59 -05:00
Aiden Cline	b31747124b	fix(core): stream Code Mode tool progress (#38718 )	2026-07-24 14:46:46 -05:00
Aiden Cline	49bec25ae5	fix(ai): align Anthropic stream handling (#38733 )	2026-07-24 14:23:35 -05:00
Aiden Cline	d66d0cb904	fix(core): clarify Code Mode tool availability (#38745 )	2026-07-24 13:44:59 -05:00
Kit Langton	3193f3aa95	fix(tui): flag likely cache busts accurately (#38727 )	2026-07-24 18:35:13 +00:00
Aiden Cline	ee5460a152	fix(codemode): report interrupted tool calls (#38741 )	2026-07-24 13:32:54 -05:00
Kit Langton	b09a066fb5	fix(ai): report OpenAI cache writes (#38735 )	2026-07-24 18:26:30 +00:00
Aiden Cline	423fad730c	fix(core): authorize external glob paths (#38714 )	2026-07-24 13:24:23 -05:00
Kit Langton	5ae2d6d3f6	refactor(core): settle declined tool calls durably with typed reasons (#38734 )	2026-07-24 18:18:02 +00:00
Kit Langton	993f046dd9	fix(ai): layer prompt cache breakpoints (#38725 )	2026-07-24 18:02:35 +00:00
opencode-agent[bot]	9b640cf97d	test(core): remove flaky npm install test (#38729 ) Co-authored-by: Aiden Cline <rekram1-node@users.noreply.github.com>	2026-07-24 12:33:28 -05:00
Kit Langton	2200d100d0	refactor(core): name the unsettled-tool sweep scope and untangle hosted settlement (#38724 )	2026-07-24 13:32:14 -04:00
Kit Langton	68ef893818	fix(core): start all suspended sessions promptly (#38720 )	2026-07-24 16:58:50 +00:00
Kit Langton	7ab3dd04ad	refactor(core): unify tool fiber bookkeeping into one owned structure (#38719 )	2026-07-24 16:55:43 +00:00
Aiden Cline	4f201f87a9	fix(ai): align Bedrock stream handling (#38712 )	2026-07-24 11:15:23 -05:00
Kit Langton	5aa276c117	refactor(core): mint assistant message identity before the step runs (#38717 )	2026-07-24 16:11:31 +00:00
Aiden Cline	4605308be2	feat(core): render CodeMode catalog deltas from structured snapshots (#38183 )	2026-07-24 10:20:26 -05:00
Aiden Cline	c64d813347	fix(core): report truncated glob results (#38631 )	2026-07-24 10:17:37 -05:00
Kit Langton	6e4a972bb9	refactor(core): clean up callModel readability (#38706 )	2026-07-24 11:17:20 -04:00
Kit Langton	835149e42b	refactor(core): select small model without sorting (#38707 )	2026-07-24 11:08:57 -04:00
Kit Langton	0f3c30118c	refactor(core): simplify session runner loop and pending input scopes (#38602 )	2026-07-24 14:27:23 +00:00
Shoubhit Dash	35d31d8ec1	refactor(ai): remove dead LLM exports (#38700 )	2026-07-24 14:19:07 +00:00
Shoubhit Dash	0374d29232	refactor(ai): colocate provider options (#38698 )	2026-07-24 19:08:36 +05:30
Shoubhit Dash	d90da82be2	refactor(ai): normalize provider option parsing (#38695 )	2026-07-24 19:02:02 +05:30
Shoubhit Dash	c06186a9d9	fix(ai): forward Anthropic provider options (#38694 )	2026-07-24 18:50:20 +05:30
Shoubhit Dash	c5680a206e	refactor(ai): make OpenAI Responses extend Open Responses (#38681 )	2026-07-24 18:36:35 +05:30
Simon Klee	edaee143d9	mini: reserve headroom before showing usage (#38659 )	2026-07-24 11:23:53 +02:00
Simon Klee	4184149b90	mini: monochrome rendered markdown only (#38656 )	2026-07-24 11:14:48 +02:00
Simon Klee	00f063b381	mini: pack statusline by content width (#38646 )	2026-07-24 10:54:30 +02:00
Aiden Cline	ea010ab3a4	feat(ai): round-trip Bedrock redacted reasoning (#38623 )	2026-07-24 01:06:58 -05:00