fix(tui): display slash command aliases (#48544)

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

.github/workflows/publish.yml

@@ -168,7 +168,7 @@ jobs:
           fi
 
           found=0
-          for file in packages/cli/dist/cli-darwin-*/bin/opencode2; do
+          for file in packages/cli/dist/cli-darwin-*/bin/opencode; do
             if [ ! -f "$file" ]; then
               continue
             fi

AGENTS.md

@@ -8,9 +8,9 @@
 
 ## Live V2 TUI Testing
 
-- Run `bun run dev:live` from a development worktree to test its TUI against the currently elected `opencode2` background server and live sessions.
+- Run `bun run dev:live` from a development worktree to test its TUI against the currently elected `opencode` background server and live sessions.
 - Pass a directory after the script when needed, for example `bun run dev:live /path/to/project`.
-- The script discovers the server with `opencode2 service status`, injects its private local credential from `opencode2 service get password`, and uses the `dev` TUI storage channel so tabs and other client-local state match the installed client.
+- The script discovers the server with `opencode service status`, injects its private local credential from `opencode service get password`, and uses the `dev` TUI storage channel so tabs and other client-local state match the installed client.
 - Prefer `dev:live` over plain `bun run dev` for this workflow. An implicit managed-service connection may replace the live server when the worktree client version differs; explicit `--server` warns and continues without replacing it.
 
 ## V2 TUI Stories

install

@@ -1,6 +1,7 @@
 #!/usr/bin/env bash
 set -euo pipefail
-APP=opencode2
+APP=opencode
+SOURCE_APP=opencode
 
 MUTED='\033[0;2m'
 RED='\033[0;31m'
@@ -22,7 +23,7 @@ Options:
 Examples:
     curl -fsSL https://opencode.ai/v2/install | bash
     curl -fsSL https://opencode.ai/v2/install | bash -s -- --version 0.0.0-beta-17236
-    ./install --binary /path/to/opencode2
+    ./install --binary /path/to/opencode
 EOF
 }
 
@@ -201,9 +202,9 @@ else
 
     filename="cli-$target-$specific_version.tgz"
     url="https://registry.npmjs.org/$package_name/-/$filename"
-    binary_name="$APP"
+    binary_name="$SOURCE_APP"
     if [ "$os" = "windows" ]; then
-        binary_name="$APP.exe"
+        binary_name="$SOURCE_APP.exe"
     fi
 fi
 
@@ -230,12 +231,7 @@ check_version() {
         installed_version="${installed_version##* }"
         installed_version="${installed_version#v}"
 
-        if [[ "$installed_version" != "$specific_version" ]]; then
-            print_message info "${MUTED}Installed version: ${NC}$installed_version."
-        else
-            print_message info "${MUTED}Version ${NC}$specific_version${MUTED} already installed"
-            exit 0
-        fi
+        print_message info "${MUTED}Installed version: ${NC}$installed_version."
     fi
 }
 
@@ -340,15 +336,47 @@ download_and_install() {
     fi
 
     tar -xzf "$tmp_dir/$filename" -C "$tmp_dir"
-    mv "$tmp_dir/package/bin/$binary_name" "$INSTALL_DIR"
-    chmod 755 "${INSTALL_DIR}/$binary_name"
+    local installed_binary="$APP"
+    if [ "$os" = "windows" ]; then
+        installed_binary="$APP.exe"
+    fi
+    mv "$tmp_dir/package/bin/$binary_name" "$INSTALL_DIR/$installed_binary"
+    chmod 755 "$INSTALL_DIR/$installed_binary"
     rm -rf "$tmp_dir"
 }
 
 install_from_binary() {
     print_message info "\n${MUTED}Installing ${NC}$APP ${MUTED}from: ${NC}$binary_path"
-    cp "$binary_path" "${INSTALL_DIR}/$APP"
-    chmod 755 "${INSTALL_DIR}/$APP"
+    local installed_binary="$APP"
+    case "$(uname -s)" in
+        MINGW*|MSYS*|CYGWIN*) installed_binary="$APP.exe" ;;
+    esac
+    cp "$binary_path" "$INSTALL_DIR/$installed_binary"
+    chmod 755 "$INSTALL_DIR/$installed_binary"
+}
+
+install_legacy_shim() {
+    local shim_os="${os:-}"
+    if [[ -z "$shim_os" ]]; then
+        case "$(uname -s)" in
+            MINGW*|MSYS*|CYGWIN*) shim_os="windows" ;;
+        esac
+    fi
+    rm -f "$INSTALL_DIR/opencode2" "$INSTALL_DIR/opencode2.exe" "$INSTALL_DIR/opencode2.cmd"
+    if [[ "$shim_os" == "windows" ]]; then
+        cat > "$INSTALL_DIR/opencode2.cmd" <<'EOF'
+@echo off
+echo opencode2 is now just opencode. run opencode
+exit /b 1
+EOF
+        return
+    fi
+    cat > "$INSTALL_DIR/opencode2" <<'EOF'
+#!/bin/sh
+echo 'opencode2 is now just opencode. run opencode'
+exit 1
+EOF
+    chmod 755 "$INSTALL_DIR/opencode2"
 }
 
 if [ -n "$binary_path" ]; then
@@ -357,6 +385,7 @@ else
     check_version
     download_and_install
 fi
+install_legacy_shim
 
 
 add_to_path() {
@@ -453,7 +482,7 @@ echo -e ""
 echo -e "${MUTED}OpenCode includes free models, to start:${NC}"
 echo -e ""
 echo -e "cd <project>  ${MUTED}# Open directory${NC}"
-echo -e "opencode2     ${MUTED}# Run command${NC}"
+echo -e "opencode      ${MUTED}# Run command${NC}"
 echo -e ""
 echo -e "${MUTED}For more information visit ${NC}https://opencode.ai/v2/docs"
 echo -e ""

package.json

@@ -8,9 +8,9 @@
   "packageManager": "bun@1.4.2",
   "scripts": {
     "dev": "bun run --cwd packages/cli src/index.ts",
-    "dev:live": "sh -c 'OPENCODE_TUI_CHANNEL=dev OPENCODE_PASSWORD=\"$(opencode2 service get password)\" exec bun run dev \"$@\" --server \"$(opencode2 service status)\"' --",
+    "dev:live": "sh -c 'OPENCODE_TUI_CHANNEL=dev OPENCODE_PASSWORD=\"$(opencode service get password)\" exec bun run dev \"$@\" --server \"$(opencode service status)\"' --",
     "dev:vite": "bun run --cwd packages/cli --conditions=browser dev/vite.ts",
-    "dev:vite:live": "sh -c 'OPENCODE_TUI_CHANNEL=dev OPENCODE_PASSWORD=\"$(opencode2 service get password)\" exec bun run dev:vite \"$@\" --server \"$(opencode2 service status)\"' --",
+    "dev:vite:live": "sh -c 'OPENCODE_TUI_CHANNEL=dev OPENCODE_PASSWORD=\"$(opencode service get password)\" exec bun run dev:vite \"$@\" --server \"$(opencode service status)\"' --",
     "dev:desktop": "bun --cwd packages/desktop dev",
     "dev:web": "bun --cwd packages/app dev",
     "dev:console": "ulimit -n 10240 2>/dev/null; bun run --cwd packages/console/app dev",

packages/ai/AGENTS.md

@@ -122,13 +122,14 @@ Keep provider facades small and explicit:
 
 ### Provider Package Entrypoints
 
-Catalog-selected native providers use package-like export paths from `@opencode/ai`. They are internal entrypoints in one npm package, not separately published provider packages. Every entrypoint implements `ProviderPackage.Definition` and exposes `model(modelID, settings)`, where settings are serializable provider configuration plus common `headers`, `body`, and `limits` overlays.
+Catalog-selected native providers use package-like export paths from `@opencode/ai`. They are internal entrypoints in one npm package, not separately published provider packages. Every entrypoint implements `ProviderPackage.Definition` and exposes `model(modelID, settings)`, where settings are one flat serializable object: the connection keys the entrypoint declares (`apiKey`, `baseURL`, `region`, …), the common `headers` and `body` overlays, and the protocol's request options (`reasoningEffort`, `thinking`, …) side by side. Each entrypoint destructures its own connection keys and passes the rest to the route as `providerOptions`; there is no nested `providerOptions` at the entrypoint.
 
 ```ts
 import { model } from "@opencode/ai/providers/openai/responses"
 
 const selected = model("gpt-5", {
   apiKey,
+  reasoningEffort: "high",
 })
 ```
 

packages/ai/README.md

@@ -29,6 +29,78 @@ await Effect.runPromise(program.pipe(Effect.provide(llmLayer)))
 
 Run `LLMClient.stream(request)` instead of `generate` when you want incremental `LLMEvent`s. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini, Bedrock Converse, and any OpenAI-compatible deployment.
 
+## Alibaba Cloud Model Studio
+
+`Alibaba` provides standard Model Studio inference. Configure a region explicitly, then select
+Chat Completions (`.model` or `.chat`), Anthropic-compatible Messages (`.messages`), or OpenAI-compatible
+Responses (`.responses`). These routes use HTTP/SSE.
+
+```ts
+import { LLM } from "@opencode/ai"
+import { Alibaba } from "@opencode/ai/providers"
+
+const alibaba = Alibaba.configure({
+  region: "ap-southeast-1", // Singapore
+  apiKey: process.env.DASHSCOPE_API_KEY,
+  // workspaceID: "llm-your-workspace", // use a workspace-dedicated endpoint
+})
+
+const request = LLM.request({
+  model: alibaba.model("qwen3.8-max"),
+  prompt: "Explain this design.",
+  providerOptions: { reasoningEffort: "medium" },
+})
+```
+
+### Regions and credentials
+
+| Region              | `region`         | Shared host when `workspaceID` is omitted |
+| ------------------- | ---------------- | ----------------------------------------- |
+| Singapore           | `ap-southeast-1` | `dashscope-intl.aliyuncs.com`             |
+| China (Beijing)     | `cn-beijing`     | `dashscope.aliyuncs.com`                  |
+| China (Hong Kong)   | `cn-hongkong`    | `cn-hongkong.dashscope.aliyuncs.com`      |
+| US (Virginia)       | `us-east-1`      | `dashscope-us.aliyuncs.com`               |
+| Germany (Frankfurt) | `eu-central-1`   | Supply `workspaceID` or `baseURL`         |
+| Japan (Tokyo)       | `ap-northeast-1` | Supply `workspaceID` or `baseURL`         |
+
+With `workspaceID`, the host is `{workspaceID}.{region}.maas.aliyuncs.com`. A complete `baseURL`
+overrides regional setup, including the API prefix: `/compatible-mode/v1` for Chat/Responses,
+or `/apps/anthropic/v1` for Messages. The selector appends its operation path.
+
+Keys and model availability are region-specific. Auth resolves from explicit `auth` or `apiKey`,
+then `DASHSCOPE_API_KEY`, then `ALIBABA_API_KEY`.
+
+The access region and inference scope differ: Virginia's `-us` model IDs request US-only inference;
+some regions select scope through their workspace. Model IDs pass through unchanged.
+Alibaba's [regional guide](https://www.alibabacloud.com/help/en/model-studio/regions) and
+[base URL table](https://www.alibabacloud.com/help/en/model-studio/base-url) disagree about Virginia's
+shared host; the entry above follows the base URL table. Dedicated hosts can be copied from the console.
+
+### Native options
+
+- **Chat:** `reasoningEffort` → `reasoning_effort`, `enableThinking` → `enable_thinking`,
+  `thinkingBudget` → `thinking_budget`, and `preserveThinking` → `preserve_thinking`.
+  Replay complete `response.message` values to retain `reasoning_content` separately from answer text.
+  Qwen 3.8 defaults to preserving thinking; older models have different defaults.
+  Additional options include `toolStream`, `parallelToolCalls`, `repetitionPenalty`, `responseFormat`,
+  `enableSearch`, and native `searchOptions`. `generation.topK` lowers to `top_k`.
+  `clearThinking` is a hosted GLM control, and `thinking.type` is available for hosted MiniMax models.
+- **Messages:** `effort` → `output_config.effort`. `thinking.type` accepts enabled/disabled with an
+  optional `budgetTokens` (or native `budget_tokens`). `outputConfig.format` accepts a JSON schema.
+  Model Studio's empty thinking signatures are accepted; supplied signatures are replayed unchanged.
+- **Responses:** `reasoningEffort` → `reasoning.effort`, plus `enableThinking`, `store`,
+  `previousResponseId`, and `conversation`. Omitted `store` retains the API's default (`true`);
+  set it to `false` for client-managed history. `previousResponseId` requires a stored response.
+  Hosted tools are `Alibaba.webSearch()`, `Alibaba.webExtractor()`, and `Alibaba.codeInterpreter()`.
+  Web extraction is used together with web search. Hosted calls/results carry `providerExecuted: true`.
+
+Omitted options preserve provider defaults. Effort values pass through unchanged and accept future
+strings. Qwen 3.8 Chat rejects requests combining a thinking budget with effort.
+
+Package entrypoints are `@opencode/ai/providers/alibaba`, `alibaba/chat`, `alibaba/messages`,
+and `alibaba/responses`. Live recordings cover all three APIs in Singapore; regional URL construction
+is unit-tested for all six regions.
+
 ## Z.AI
 
 `ZAI` uses the standard API. Chat Completions is the default language-model API;

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

@@ -0,0 +1,92 @@
+import { Effect, Schema } from "effect"
+import { Protocol } from "../route/protocol.js"
+import type { LanguageModelCompatibility } from "../schema/index.js"
+import { OpenAIChat } from "./openai-chat.js"
+import { JsonObject, ProviderShared } from "./shared.js"
+import { OpenResponsesOptions } from "./utils/open-responses-options.js"
+
+export type ReasoningEffort = OpenResponsesOptions.ReasoningEffort
+
+const Options = Schema.Struct({
+  reasoningEffort: OpenResponsesOptions.Options.fields.reasoningEffort,
+  enableThinking: Schema.optional(Schema.Boolean),
+  thinkingBudget: Schema.optional(Schema.Int),
+  preserveThinking: Schema.optional(Schema.Boolean),
+  clearThinking: Schema.optional(Schema.Boolean),
+  thinking: Schema.optional(
+    Schema.Struct({
+      type: Schema.declare<"adaptive" | "disabled" | (string & {})>(Schema.is(Schema.String)),
+    }),
+  ),
+  toolStream: Schema.optional(Schema.Boolean),
+  parallelToolCalls: OpenResponsesOptions.Options.fields.parallelToolCalls,
+  repetitionPenalty: Schema.optional(Schema.Number),
+  responseFormat: Schema.optional(
+    Schema.Struct({
+      type: Schema.declare<"text" | "json_object" | "json_schema" | (string & {})>(Schema.is(Schema.String)),
+      json_schema: Schema.optional(JsonObject),
+    }),
+  ),
+  enableSearch: Schema.optional(Schema.Boolean),
+  searchOptions: Schema.optional(
+    Schema.Struct({
+      forced_search: Schema.optional(Schema.Boolean),
+      search_strategy: Schema.optional(
+        Schema.declare<"turbo" | "max" | "agent" | "agent_max" | (string & {})>(Schema.is(Schema.String)),
+      ),
+      enable_search_extension: Schema.optional(Schema.Boolean),
+    }),
+  ),
+})
+export type OptionsInput = typeof Options.Type
+
+export const compatibility = {
+  maxTokensField: "max_completion_tokens",
+  supportsStore: false,
+  supportsStrictMode: false,
+  reasoningField: "reasoning_content",
+  zaiToolStream: false,
+} satisfies LanguageModelCompatibility
+
+export const protocol = Protocol.make({
+  id: "alibaba-chat",
+  body: {
+    schema: Schema.Struct({
+      ...OpenAIChat.bodyFields,
+      enable_thinking: Options.fields.enableThinking,
+      thinking_budget: Options.fields.thinkingBudget,
+      preserve_thinking: Options.fields.preserveThinking,
+      clear_thinking: Options.fields.clearThinking,
+      thinking: Options.fields.thinking,
+      parallel_tool_calls: Options.fields.parallelToolCalls,
+      repetition_penalty: Options.fields.repetitionPenalty,
+      top_k: Schema.optional(Schema.Int),
+      response_format: Options.fields.responseFormat,
+      enable_search: Options.fields.enableSearch,
+      search_options: Options.fields.searchOptions,
+    }),
+    from: Effect.fn("AlibabaChat.fromRequest")(function* (req) {
+      const opts = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))(req.providerOptions ?? {})
+      return {
+        ...(yield* OpenAIChat.protocol.body.from(req)),
+        enable_thinking: opts.enableThinking,
+        thinking_budget: opts.thinkingBudget,
+        preserve_thinking: opts.preserveThinking,
+        clear_thinking: opts.clearThinking,
+        thinking: opts.thinking,
+        tool_stream: opts.toolStream,
+        parallel_tool_calls:
+          opts.parallelToolCalls ??
+          (req.toolChoice?.disableParallelToolUse === undefined ? undefined : !req.toolChoice.disableParallelToolUse),
+        repetition_penalty: opts.repetitionPenalty,
+        top_k: req.generation?.topK,
+        response_format: opts.responseFormat,
+        enable_search: opts.enableSearch,
+        search_options: opts.searchOptions,
+      }
+    }),
+  },
+  stream: OpenAIChat.protocol.stream,
+})
+
+export * as AlibabaChat from "./alibaba-chat.js"

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

@@ -0,0 +1,48 @@
+import { Effect, Schema } from "effect"
+import { Protocol } from "../route/protocol.js"
+import { LLMRequest } from "../schema/index.js"
+import { AnthropicMessages } from "./anthropic-messages.js"
+import { ProviderShared } from "./shared.js"
+import { OpenResponsesOptions } from "./utils/open-responses-options.js"
+
+const Options = Schema.Struct({
+  effort: Schema.optional(OpenResponsesOptions.ReasoningEffort),
+  thinking: Schema.optional(
+    Schema.Struct({
+      type: Schema.declare<"enabled" | "disabled" | (string & {})>(Schema.is(Schema.String)),
+      budgetTokens: Schema.optional(Schema.Int),
+      budget_tokens: Schema.optional(Schema.Int),
+    }),
+  ),
+})
+export type OptionsInput = typeof Options.Type & Pick<AnthropicMessages.OptionsInput, "outputConfig">
+export const protocol = Protocol.make({
+  id: "alibaba-messages",
+  body: {
+    schema: Schema.Struct({
+      ...AnthropicMessages.AnthropicMessagesBody.fields,
+      thinking: Schema.optional(Schema.Struct({ type: Schema.String, budget_tokens: Schema.optional(Schema.Int) })),
+    }),
+    from: Effect.fn("AlibabaMessages.fromRequest")(function* (req) {
+      const opts = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))(req.providerOptions ?? {})
+      // Model Studio accepts enabled thinking without Anthropic's mandatory token budget.
+      return {
+        ...(yield* AnthropicMessages.protocol.body.from(
+          LLMRequest.update(req, {
+            providerOptions: { ...req.providerOptions, thinking: undefined },
+          }),
+        )),
+        thinking:
+          opts.thinking === undefined
+            ? undefined
+            : {
+                type: opts.thinking.type,
+                budget_tokens: opts.thinking.budgetTokens ?? opts.thinking.budget_tokens,
+              },
+      }
+    }),
+  },
+  stream: AnthropicMessages.protocol.stream,
+})
+
+export * as AlibabaMessages from "./alibaba-messages.js"

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

@@ -0,0 +1,98 @@
+import { Effect, Schema } from "effect"
+import { Protocol } from "../route/protocol.js"
+import { OpenResponses } from "./open-responses.js"
+import { JsonObject, optionalArray, ProviderShared } from "./shared.js"
+import { OpenResponsesOptions } from "./utils/open-responses-options.js"
+import { ResponsesHostedTools } from "./utils/responses-hosted-tools.js"
+
+const Options = Schema.Struct({
+  reasoningEffort: OpenResponsesOptions.Options.fields.reasoningEffort,
+  enableThinking: Schema.optional(Schema.Boolean),
+  store: OpenResponsesOptions.Options.fields.store,
+  previousResponseId: Schema.optional(Schema.String),
+  conversation: Schema.optional(Schema.String),
+})
+export type OptionsInput = typeof Options.Type
+const NativeTool = Schema.Struct({ type: Schema.Literals(["web_search", "web_extractor", "code_interpreter"]) })
+const WebExtractorItem = Schema.StructWithRest(
+  Schema.Struct({
+    type: Schema.Literal("web_extractor_call"),
+    id: Schema.String,
+    urls: Schema.optional(Schema.Array(Schema.String)),
+    goal: Schema.optional(Schema.String),
+  }),
+  [JsonObject],
+)
+const Body = Schema.Struct({
+  ...OpenResponses.coreFields,
+  input: Schema.Array(Schema.Union([OpenResponses.InputItem, WebExtractorItem])),
+  tools: optionalArray(Schema.Union([OpenResponses.Tool, NativeTool])),
+  enable_thinking: Options.fields.enableThinking,
+  previous_response_id: Options.fields.previousResponseId,
+  conversation: Options.fields.conversation,
+  stream: Schema.Literal(true),
+})
+const adapter = {
+  id: "alibaba-responses",
+  name: "Alibaba Responses",
+  nativeTool: (native) => ProviderShared.validateWith(Schema.decodeUnknownEffect(NativeTool))(native.alibaba),
+  restoreHostedToolItem: (item: unknown) => (Schema.is(WebExtractorItem)(item) ? item : undefined),
+} satisfies OpenResponses.ProviderAdapter
+
+const tools = {
+  web_search_call: { name: "web_search", input: (item) => item.action ?? {} },
+  code_interpreter_call: { name: "code_interpreter", input: (item) => ({ code: item.code }) },
+} satisfies ResponsesHostedTools.Definitions
+
+export const protocol = Protocol.make({
+  id: adapter.id,
+  body: {
+    schema: Body,
+    from: Effect.fn("AlibabaResponses.fromRequest")(function* (req) {
+      const opts = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))(req.providerOptions ?? {})
+      const body = yield* OpenResponses.fromRequestWithAdapter(req, adapter)
+      const choice = body.tool_choice
+      return yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Body))({
+        ...body,
+        enable_thinking: opts.enableThinking,
+        previous_response_id: opts.previousResponseId,
+        conversation: opts.conversation,
+        // Model Studio expresses named selection through allowed_tools.
+        tool_choice:
+          typeof choice === "object" && choice.type === "function"
+            ? { type: "allowed_tools" as const, mode: "required" as const, tools: [choice] }
+            : choice,
+      })
+    }),
+  },
+  stream: {
+    event: OpenResponses.protocol.stream.event,
+    initial: (req) => OpenResponses.initial(req, adapter),
+    step: (state, input) =>
+      Effect.gen(function* () {
+        const event = OpenResponses.normalize(state, input)
+        if (event.type !== "response.output_item.done" || !event.item) return yield* OpenResponses.step(state, event)
+        if (event.item.type === "web_extractor_call") {
+          const item = yield* Schema.decodeUnknownEffect(WebExtractorItem)(event.item).pipe(
+            Effect.mapError((cause) =>
+              ProviderShared.eventError(
+                adapter.id,
+                "Alibaba returned an invalid web extraction item",
+                ProviderShared.encodeJson(event),
+                cause,
+              ),
+            ),
+          )
+          return yield* ResponsesHostedTools.onDone(state, item, {
+            web_extractor_call: { name: "web_extractor", input: () => ({ urls: item.urls, goal: item.goal }) },
+          })
+        }
+        if (ResponsesHostedTools.isItem(event.item, tools))
+          return yield* ResponsesHostedTools.onDone(state, event.item, tools)
+        return yield* OpenResponses.step(state, event)
+      }),
+    terminal: OpenResponses.terminal,
+  },
+})
+
+export * as AlibabaResponses from "./alibaba-responses.js"

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

@@ -1708,7 +1708,10 @@ export const transport = <
 }
 
 function requiredBetaHeaders(body: Pick<AnthropicMessagesBody, "messages" | "context_management" | "thinking">) {
-  const betas: string[] = []
+  // Always request interleaved thinking. The API accepts the header on any
+  // model and ignores it where unsupported, while manual-thinking models need
+  // it for thinking between tool calls.
+  const betas: string[] = ["interleaved-thinking-2025-05-14"]
   const requestsCompaction = (body.context_management?.edits.length ?? 0) > 0
   const replaysCompaction = body.messages.some((message) =>
     message.content.some((block) => block.type === "compaction"),

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

@@ -18,7 +18,6 @@ const WebSocketResponseCreate = Schema.StructWithRest(Schema.Struct({ type: Sche
 ])
 const decodeMessage = ProviderShared.validateWith(Schema.decodeUnknownEffect(WebSocketResponseCreate))
 const encodeMessage = Schema.encodeSync(Schema.fromJsonString(WebSocketResponseCreate))
-const decodeEvent = Schema.decodeUnknownEffect(OpenResponses.protocol.stream.event)
 
 export interface Options {
   readonly id: string
@@ -27,6 +26,7 @@ export interface Options {
   readonly enabled?: (url: string) => boolean
   readonly url?: (url: string) => string
   readonly headers?: (headers: Headers.Headers) => Headers.Headers
+  readonly continuation?: OpenResponsesContinuation.Shape
 }
 
 export interface Prepared {
@@ -60,7 +60,7 @@ const driver = (options: Options, body: string): WebSocketChannelDriver => {
       }),
     observe: (_create, frame) =>
       Effect.gen(function* () {
-        const event = yield* decodeEvent(frame).pipe(
+        const event = yield* OpenResponses.decodeChannelEvent(frame).pipe(
           Effect.mapError((cause) =>
             ProviderShared.eventError(options.id, `Invalid ${options.name} WebSocket event`, frame, cause),
           ),
@@ -163,6 +163,7 @@ export const transport = <Body>(options: Options): Transport<Body, Prepared, str
                     request: create.request,
                     message: create.message,
                     base,
+                    continuation: options.continuation,
                   }),
                 }
               })

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

@@ -6,7 +6,6 @@ import { OpenResponses } from "./open-responses.js"
 
 const PROTOCOL = "open-responses.websocket.v1"
 const VERSION = 1
-const decodeEvent = Schema.decodeUnknownEffect(OpenResponses.protocol.stream.event)
 
 interface CheckpointValue {
   readonly version: typeof VERSION
@@ -15,12 +14,19 @@ interface CheckpointValue {
   readonly output: ReadonlyArray<unknown>
 }
 
+/**
+ * Fields to send next to `previous_response_id` on an incremental step, or undefined to send the step in full.
+ * Whether omitted fields carry over from the continued response is provider behavior the route must know.
+ */
+export type Shape = (request: Readonly<Record<string, unknown>>) => Readonly<Record<string, unknown>> | undefined
+
 export interface DriverInput {
   readonly id: string
   readonly name: string
   readonly request: Readonly<Record<string, unknown>>
   readonly message: string
   readonly base: WebSocketChannelDriver
+  readonly continuation?: Shape
 }
 
 const checkpointValue = (checkpoint: ChannelCheckpoint | undefined): CheckpointValue | undefined => {
@@ -127,22 +133,26 @@ const rejected = (
 
 export const driver = (input: DriverInput): WebSocketChannelDriver => {
   const { previous_response_id: _previousResponseID, ...request } = input.request
+  const shape = input.continuation ?? ((fields: Readonly<Record<string, unknown>>) => fields)
   let output: OpenResponses.StreamItem[] = []
   return {
     create: (checkpoint) =>
       Effect.sync(() => {
         output = []
         const previous = checkpointValue(checkpoint)
-        const delta = previous ? incremental(request, previous) : undefined
-        if (!previous || !delta) return { message: ProviderShared.encodeJson(request), mode: "full" as const }
+        // Ask the route first: diffing the whole history is wasted when it declines the continuation.
+        const fields = previous ? shape(request) : undefined
+        const delta = previous && fields ? incremental(request, previous) : undefined
+        if (!previous || !fields || !delta)
+          return { message: ProviderShared.encodeJson(request), mode: "full" as const }
         return {
-          message: ProviderShared.encodeJson({ ...request, input: delta, previous_response_id: previous.responseID }),
+          message: ProviderShared.encodeJson({ ...fields, input: delta, previous_response_id: previous.responseID }),
           mode: "incremental" as const,
         }
       }),
     observe: (create, frame) =>
       Effect.gen(function* () {
-        const event = yield* decodeEvent(frame).pipe(
+        const event = yield* OpenResponses.decodeChannelEvent(frame).pipe(
           Effect.mapError((cause) =>
             ProviderShared.eventError(input.id, `Invalid ${input.name} WebSocket event`, frame, cause),
           ),
@@ -153,6 +163,15 @@ export const driver = (input: DriverInput): WebSocketChannelDriver => {
           const rejection = code(event)
           if (rejection === "previous_response_not_found") return rejected(observation, "retry-full")
           if (rejection === "websocket_connection_limit_reached") return rejected(observation, "rotate-and-retry-full")
+          // Only the continuation distinguishes an incremental send from a full one, so an unclassified
+          // invalid request there is retried full; Codex reports a stale previous_response_id that way, with
+          // no code. Classified failures such as context overflow keep their runner-owned recovery.
+          if (
+            create.mode === "incremental" &&
+            observation.error.reason._tag === "InvalidRequest" &&
+            observation.error.reason.classification === undefined
+          )
+            return rejected(observation, "retry-full")
         }
         if (observation.type !== "completed") return observation
         // A trigger installs a different context window. Clear the append baseline, retaining the socket.
@@ -172,7 +191,7 @@ export const driver = (input: DriverInput): WebSocketChannelDriver => {
               responseID,
               request,
               // Completion can re-encrypt reasoning. Callers replay the item already emitted by output_item.done.
-              output: event.response?.output
+              output: event.response?.output?.length
                 ? event.response.output.map((item) =>
                     item.type === "reasoning" && item.id !== undefined
                       ? (output.find((done) => done.type === item.type && done.id === item.id) ?? item)
@@ -186,4 +205,4 @@ export const driver = (input: DriverInput): WebSocketChannelDriver => {
   }
 }
 
-export const OpenResponsesContinuation = { driver } as const
+export * as OpenResponsesContinuation from "./open-responses-continuation.js"

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

@@ -1,4 +1,4 @@
-import { Effect, Option, Schema } from "effect"
+import { Effect, Option, Schema, SchemaGetter } from "effect"
 import type { Content } from "@opencode/schema/tool"
 import { HttpTransport } from "../route/transport/index.js"
 import { Protocol } from "../route/protocol.js"
@@ -325,9 +325,8 @@ export const StreamItem = Schema.StructWithRest(
 export type StreamItem = Schema.Schema.Type<typeof StreamItem>
 export type OutputItem = StreamItem & { readonly id: string }
 
-// The Responses schema puts streaming error details at the top level and
-// response failures under `response.error`. WebSocket failures use an
-// event-level `error` envelope, so accept all three shapes here.
+// Responses-compatible providers put streaming error details at the top level or
+// under `error`, and response failures under `response.error`. Accept all three shapes.
 // https://www.openresponses.org/specification
 const OpenResponsesErrorPayload = Schema.Struct({
   type: optionalNull(Schema.String),
@@ -401,13 +400,45 @@ export const Event = Schema.StructWithRest(
     headers: Schema.optional(Schema.Unknown),
   }),
   [Schema.Record(Schema.String, Schema.Unknown)],
+).pipe(
+  Schema.decode({
+    decode: SchemaGetter.transform((event) => {
+      if (event.type !== "error" || event.error != null) return event
+      const { code, message, param, ...rest } = event
+      if (code === undefined && message === undefined && param === undefined) return event
+      // Flat errors (for example, Meta's) can also arrive through generic Responses endpoints.
+      return { ...rest, error: { code, message, param } }
+    }),
+    encode: SchemaGetter.passthrough(),
+  }),
 )
 export type Event = Schema.Schema.Type<typeof Event>
 export type NormalizedEvent = Event & { readonly item?: OutputItem | null }
 
+const decodeEventValue = Schema.decodeUnknownEffect(Event)
+const decodeFrame = Schema.decodeUnknownEffect(ProviderShared.Json)
+
+/**
+ * Decodes one WebSocket frame. xAI answers a rejected `response.create` with `{ "error": { "message", "type" } }` and no
+ * event type; that envelope reads as an error event so the failure classifies instead of failing decoding.
+ */
+export const decodeChannelEvent = (frame: string) =>
+  decodeFrame(frame).pipe(
+    Effect.flatMap((value) =>
+      decodeEventValue(
+        ProviderShared.isRecord(value) && value.type === undefined && ProviderShared.isRecord(value.error)
+          ? { ...value, type: "error" }
+          : value,
+      ),
+    ),
+  )
+
 export interface ProviderAdapter {
   readonly id: string
   readonly name: string
+  readonly nativeTool?: (
+    native: NonNullable<ToolDefinition["native"]>,
+  ) => Effect.Effect<{ readonly type: string }, AIError>
   readonly lowerMedia?: (input: {
     readonly part: MediaPart
     readonly media: ProviderShared.NormalizedMedia
@@ -652,7 +683,8 @@ const lowerMessages = Effect.fn("OpenResponses.lowerMessages")(function* (
             type: "message" as const,
             ...(group.id === undefined ? {} : { id: group.id }),
             role: "assistant" as const,
-            status: metadata?.status,
+            // Replayed text is a finished input item, even if generation was cut short.
+            status: "completed",
             content: group.parts.map((part) => ({ type: "output_text" as const, text: part.text })),
             ...(group.phase === undefined ? {} : { phase: group.phase }),
           })),
@@ -819,11 +851,13 @@ export const fromRequestWithAdapter = Effect.fn("OpenResponses.fromRequestWithAd
       projected.tools.length === 0
         ? undefined
         : yield* Effect.forEach(projected.tools, (tool) =>
-            lowerTool(
-              adapter.name,
-              tool,
-              ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility),
-            ),
+            tool.native !== undefined && adapter.nativeTool
+              ? adapter.nativeTool(tool.native)
+              : lowerTool(
+                  adapter.name,
+                  tool,
+                  ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility),
+                ),
           ),
     tool_choice:
       allowedToolChoice(request) ??

packages/ai/src/provider-package.ts

@@ -1,6 +1,10 @@
 import type { LanguageModel, ProviderOptions } from "./schema/index.js"
 import type { CompactionOperations } from "./route/client.js"
 
+/**
+ * Flat, serializable settings for `model(modelID, settings)`. Each entrypoint declares the connection keys it
+ * reads; every other key is a request option for the route's protocol.
+ */
 export interface Settings extends Readonly<Record<string, unknown>> {
   readonly baseURL?: string
   readonly headers?: Readonly<Record<string, string>>

packages/ai/src/providers/alibaba.ts

@@ -0,0 +1,144 @@
+import { Struct } from "effect"
+import type { ProviderPackage } from "../provider-package.js"
+import { AlibabaChat } from "../protocols/alibaba-chat.js"
+import { AlibabaMessages } from "../protocols/alibaba-messages.js"
+import { AlibabaResponses } from "../protocols/alibaba-responses.js"
+import { AuthOptions, type AtLeastOne, type ProviderAuthOption } from "../route/auth-options.js"
+import { Route, type RouteDefaultsInput } from "../route/client.js"
+import { Endpoint } from "../route/endpoint.js"
+import { Framing } from "../route/framing.js"
+import { ProviderConfigurationError, ProviderID, ToolDefinition, type ModelID } from "../schema/index.js"
+
+export const id = ProviderID.make("alibaba")
+
+export type Region =
+  | "ap-southeast-1"
+  | "cn-beijing"
+  | "cn-hongkong"
+  | "us-east-1"
+  | "eu-central-1"
+  | "ap-northeast-1"
+  | (string & {})
+export type ChatOptionsInput = AlibabaChat.OptionsInput
+export type MessagesOptionsInput = AlibabaMessages.OptionsInput
+export type ResponsesOptionsInput = AlibabaResponses.OptionsInput
+
+type Location = AtLeastOne<{
+  readonly region: Region
+  /** Overrides the selected API's complete base URL, including its version prefix. */
+  readonly baseURL: string
+}> & { readonly workspaceID?: string }
+
+export type Config = Location &
+  Omit<RouteDefaultsInput, "providerOptions"> &
+  ProviderAuthOption<"optional"> & {
+    readonly providerOptions?: ChatOptionsInput | MessagesOptionsInput | ResponsesOptionsInput
+  }
+export type Settings<Options = ChatOptionsInput> = Location &
+  ProviderPackage.Settings &
+  Options & {
+    readonly apiKey?: string
+  }
+
+const hosts = new Map<string, string>([
+  ["ap-southeast-1", "dashscope-intl.aliyuncs.com"],
+  ["cn-beijing", "dashscope.aliyuncs.com"],
+  ["cn-hongkong", "cn-hongkong.dashscope.aliyuncs.com"],
+  ["us-east-1", "dashscope-us.aliyuncs.com"],
+])
+const chatRoute = Route.make({
+  id: "alibaba-chat",
+  provider: id,
+  providerMetadataKey: "alibaba",
+  protocol: AlibabaChat.protocol,
+  endpoint: Endpoint.path("/chat/completions"),
+  framing: Framing.sse,
+})
+const messagesRoute = Route.make({
+  id: "alibaba-messages",
+  provider: id,
+  providerMetadataKey: "alibaba",
+  protocol: AlibabaMessages.protocol,
+  endpoint: Endpoint.path("/messages"),
+  framing: Framing.sse,
+  headers: () => ({ "anthropic-version": "2023-06-01" }),
+})
+const responsesRoute = Route.make({
+  id: "alibaba-responses",
+  provider: id,
+  providerMetadataKey: "alibaba",
+  protocol: AlibabaResponses.protocol,
+  endpoint: Endpoint.path("/responses"),
+  framing: Framing.sse,
+})
+
+export const routes = [chatRoute, messagesRoute, responsesRoute]
+
+export const configure = (input: Config) => {
+  const { apiKey: _key, auth: _auth, region, workspaceID, baseURL, ...rest } = input
+  const host =
+    region === undefined
+      ? undefined
+      : workspaceID === undefined
+        ? hosts.get(region)
+        : `${workspaceID}.${region}.maas.aliyuncs.com`
+  if (baseURL === undefined) {
+    if (region === undefined)
+      throw new ProviderConfigurationError({ provider: id, message: "Alibaba requires region or baseURL" })
+    if (host === undefined)
+      throw new ProviderConfigurationError({
+        provider: id,
+        message: `Alibaba region ${region} requires workspaceID or baseURL`,
+      })
+  }
+  const opts = { ...rest, auth: AuthOptions.bearer(input, ["DASHSCOPE_API_KEY", "ALIBABA_API_KEY"]) }
+  const common = { ...opts, endpoint: { baseURL: baseURL ?? `https://${host}/compatible-mode/v1` } }
+  const chat = (id: string | ModelID) =>
+    chatRoute.with(common).model<ChatOptionsInput>({ id, compatibility: AlibabaChat.compatibility })
+  const messages = (id: string | ModelID) =>
+    messagesRoute
+      .with({
+        ...opts,
+        endpoint: { baseURL: baseURL ?? `https://${host}/apps/anthropic/v1` },
+      })
+      .model<MessagesOptionsInput>({ id, compatibility: { requireSignature: false } })
+  const responses = (id: string | ModelID) => responsesRoute.with(common).model<ResponsesOptionsInput>({ id })
+  return { id, model: chat, chat, messages, responses, configure }
+}
+
+export const provider = { id, configure }
+
+export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (id, input) =>
+  fromSettings(input).chat(id)
+export const messagesModel: ProviderPackage.Definition<
+  Settings<MessagesOptionsInput>,
+  MessagesOptionsInput
+>["model"] = (id, input) => fromSettings(input).messages(id)
+export const responsesModel: ProviderPackage.Definition<
+  Settings<ResponsesOptionsInput>,
+  ResponsesOptionsInput
+>["model"] = (id, input) => fromSettings(input).responses(id)
+
+function fromSettings(input: Settings<Config["providerOptions"]>) {
+  const { body, ...rest } = input
+  return configure({
+    ...rest,
+    http: body === undefined ? undefined : { body },
+    providerOptions: Struct.omit(rest, ["apiKey", "baseURL", "headers", "region", "workspaceID"]),
+  })
+}
+
+export const webSearch = () => hostedTool("web_search", "Search the web with Alibaba's hosted search tool.")
+export const webExtractor = () => hostedTool("web_extractor", "Extract web page content with Alibaba's hosted tool.")
+export const codeInterpreter = () => hostedTool("code_interpreter", "Execute code with Alibaba's hosted interpreter.")
+
+function hostedTool(type: "web_search" | "web_extractor" | "code_interpreter", description: string) {
+  return ToolDefinition.make({
+    name: type,
+    description,
+    inputSchema: { type: "object", properties: {} },
+    native: { alibaba: { type } },
+  })
+}
+
+export * as Alibaba from "./alibaba.js"

packages/ai/src/providers/alibaba/chat.ts

@@ -0,0 +1 @@
+export { model, type Settings } from "../alibaba.js"

packages/ai/src/providers/alibaba/messages.ts

@@ -0,0 +1,3 @@
+import type { Alibaba } from "../alibaba.js"
+export { messagesModel as model } from "../alibaba.js"
+export type Settings = Alibaba.Settings<Alibaba.MessagesOptionsInput>

packages/ai/src/providers/alibaba/responses.ts

@@ -0,0 +1,3 @@
+import type { Alibaba } from "../alibaba.js"
+export { responsesModel as model } from "../alibaba.js"
+export type Settings = Alibaba.Settings<Alibaba.ResponsesOptionsInput>

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

@@ -1,9 +1,10 @@
 import { Route, type RouteDefaultsInput } from "../route/client.js"
+import { Endpoint } from "../route/endpoint.js"
 import type { ProviderPackage } from "../provider-package.js"
 import { OpenAIChat } from "../protocols/openai-chat.js"
-import { OpenAIResponses } from "../protocols/openai-responses.js"
+import { OpenResponses } from "../protocols/open-responses.js"
 import { BedrockAuth, type Credentials } from "../protocols/utils/bedrock-auth.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import { withOpenAIOptions, type OpenAIProviderOptionsInput } from "./openai-options.js"
 
 export const id = ProviderID.make("amazon-bedrock")
@@ -22,26 +23,25 @@ export type Config = RouteDefaultsInput & {
   readonly providerOptions?: OpenAIProviderOptionsInput
 }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly auth?: "bearer" | "sigv4"
-  readonly baseURL?: string
-  readonly credentials?: Credentials
-  readonly profile?: string
-  readonly region?: string
-  readonly topP?: number
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly auth?: "bearer" | "sigv4"
+    readonly baseURL?: string
+    readonly credentials?: Credentials
+    readonly profile?: string
+    readonly region?: string
+    readonly topP?: number
+  }
 
 const responsesRoute = Route.make({
   id: "bedrock-mantle-responses",
   provider: id,
   providerMetadataKey: "mantle",
-  protocol: OpenAIResponses.protocol,
-  endpoint: OpenAIResponses.route.endpoint,
-  auth: OpenAIResponses.route.auth,
-  transport: OpenAIResponses.httpTransport,
-  defaults: OpenAIResponses.route.defaults,
+  protocol: OpenResponses.protocol,
+  endpoint: Endpoint.path(OpenResponses.PATH),
+  transport: OpenResponses.httpTransport,
+  defaults: { providerOptions: { store: false, include: ["reasoning.encrypted_content"] } },
 })
 
 const chatRoute = OpenAIChat.route.with({
@@ -79,9 +79,12 @@ const defaults = (input: Config) => {
 
 export const configure = (input: Config = {}) => {
   if (input.auth === "bearer" && input.apiKey === undefined && process.env.AWS_BEARER_TOKEN_BEDROCK === undefined)
-    throw new Error("Amazon Bedrock Mantle bearer auth requires apiKey")
+    throw new ProviderConfigurationError({ provider: id, message: "Amazon Bedrock Mantle bearer auth requires apiKey" })
   if (input.auth === "sigv4" && input.apiKey !== undefined)
-    throw new Error("Amazon Bedrock Mantle SigV4 auth does not accept apiKey")
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "Amazon Bedrock Mantle SigV4 auth does not accept apiKey",
+    })
   const configuredResponsesRoute = configuredRoute(responsesRoute, input)
   const configuredChatRoute = configuredRoute(chatRoute, input)
   const modelDefaults = defaults(input)
@@ -105,18 +108,29 @@ export const configure = (input: Config = {}) => {
 
 export const provider = configure()
 
-const fromSettings = (settings: Settings) =>
+const fromSettings = ({
+  apiKey,
+  auth,
+  baseURL,
+  body,
+  credentials,
+  headers,
+  profile,
+  region,
+  topP,
+  ...providerOptions
+}: Settings) =>
   configure({
-    apiKey: settings.apiKey,
-    auth: settings.auth,
-    baseURL: settings.baseURL,
-    credentials: settings.credentials,
-    generation: settings.topP === undefined ? undefined : { topP: settings.topP },
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    profile: settings.profile,
-    providerOptions: settings.providerOptions,
-    region: settings.region,
+    apiKey,
+    auth,
+    baseURL,
+    credentials,
+    generation: topP === undefined ? undefined : { topP },
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    profile,
+    providerOptions,
+    region,
   })
 
 export const chatModel: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (

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

@@ -1,6 +1,6 @@
 import type { RouteDefaultsInput } from "../route/client.js"
 import type { ProviderPackage } from "../provider-package.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import * as BedrockConverse from "../protocols/bedrock-converse.js"
 import type { BedrockCredentials } from "../protocols/bedrock-converse.js"
 import { BedrockAuth } from "../protocols/utils/bedrock-auth.js"
@@ -39,8 +39,9 @@ const bedrockBaseURL = (region: string) => `https://bedrock-runtime.${region}.am
 const configuredRoute = (input: Config) => {
   const { apiKey, auth, credentials, profile, region, baseURL, ...rest } = input
   if (auth === "bearer" && apiKey === undefined && process.env.AWS_BEARER_TOKEN_BEDROCK === undefined)
-    throw new Error("Amazon Bedrock bearer auth requires apiKey")
-  if (auth === "sigv4" && apiKey !== undefined) throw new Error("Amazon Bedrock SigV4 auth does not accept apiKey")
+    throw new ProviderConfigurationError({ provider: id, message: "Amazon Bedrock bearer auth requires apiKey" })
+  if (auth === "sigv4" && apiKey !== undefined)
+    throw new ProviderConfigurationError({ provider: id, message: "Amazon Bedrock SigV4 auth does not accept apiKey" })
   const resolvedRegion = BedrockAuth.resolveRegion(input)
   return BedrockConverse.route.with({
     ...rest,

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

@@ -3,7 +3,7 @@ import { AnthropicMessages } from "../protocols/anthropic-messages.js"
 import { Auth } from "../route/auth.js"
 import type { ProviderAuthOption } from "../route/auth-options.js"
 import type { RouteDefaultsInput } from "../route/client.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 
 export type AnthropicOptionsInput = AnthropicMessages.OptionsInput
 export type AnthropicProviderOptionsInput = AnthropicMessages.ProviderOptionsInput
@@ -19,13 +19,13 @@ export type Config = RouteDefaultsInput &
   }
 
 export type Settings = ProviderPackage.Settings &
+  AnthropicMessages.ProviderOptionsInput &
   (
     | { readonly apiKey?: string; readonly authToken?: never }
     | { readonly apiKey?: never; readonly authToken?: string }
   ) & {
     readonly baseURL: string
     readonly provider?: string
-    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
   }
 
 export const routes = [AnthropicMessages.route]
@@ -36,8 +36,12 @@ const auth = (input: ProviderAuthOption<"optional">) => {
 }
 
 export const configure = (input: Config) => {
-  if (!input.baseURL) throw new Error("Anthropic-compatible providers require a baseURL")
   const provider = input.provider ?? "anthropic-compatible"
+  if (!input.baseURL)
+    throw new ProviderConfigurationError({
+      provider: ProviderID.make(provider),
+      message: "Anthropic-compatible providers require a baseURL",
+    })
   const { provider: _, baseURL, apiKey: _apiKey, auth: _auth, ...rest } = input
   const route = AnthropicMessages.route.with({
     ...rest,
@@ -59,17 +63,20 @@ export const provider = {
 
 export const model: ProviderPackage.Definition<Settings, AnthropicMessages.ProviderOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, authToken, baseURL, body, headers, provider, ...providerOptions },
 ) => {
-  if (settings.apiKey !== undefined && settings.authToken !== undefined)
-    throw new Error("Anthropic-compatible apiKey cannot be combined with authToken")
+  if (apiKey !== undefined && authToken !== undefined)
+    throw new ProviderConfigurationError({
+      provider: ProviderID.make(provider ?? id),
+      message: "Anthropic-compatible apiKey cannot be combined with authToken",
+    })
   return configure({
-    ...(settings.authToken === undefined ? { apiKey: settings.apiKey } : { auth: Auth.bearer(settings.authToken) }),
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    provider: settings.provider,
-    providerOptions: settings.providerOptions,
+    ...(authToken === undefined ? { apiKey: apiKey } : { auth: Auth.bearer(authToken) }),
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    provider,
+    providerOptions,
   }).model(modelID)
 }
 

packages/ai/src/providers/anthropic.ts

@@ -2,7 +2,7 @@ import type { RouteDefaultsInput } from "../route/client.js"
 import { Auth } from "../route/auth.js"
 import type { ProviderAuthOption } from "../route/auth-options.js"
 import type { ProviderPackage } from "../provider-package.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import { AnthropicMessages } from "../protocols/anthropic-messages.js"
 import { AnthropicCompatible } from "./anthropic-compatible.js"
 
@@ -21,12 +21,12 @@ export type Config = RouteDefaultsInput &
   }
 
 export type Settings = ProviderPackage.Settings &
+  AnthropicMessages.ProviderOptionsInput &
   (
     | { readonly apiKey?: string; readonly authToken?: never }
     | { readonly apiKey?: never; readonly authToken?: string }
   ) & {
     readonly baseURL?: string
-    readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
   }
 
 const auth = (options: ProviderAuthOption<"optional">) => {
@@ -54,15 +54,18 @@ export const configure = (input: Config = {}) => {
 export const provider = configure()
 export const model: ProviderPackage.Definition<Settings, AnthropicMessages.ProviderOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, authToken, baseURL, body, headers, ...providerOptions },
 ) => {
-  if (settings.apiKey !== undefined && settings.authToken !== undefined)
-    throw new Error("Anthropic apiKey cannot be combined with authToken")
+  if (apiKey !== undefined && authToken !== undefined)
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "Anthropic apiKey cannot be combined with authToken",
+    })
   return configure({
-    ...(settings.authToken === undefined ? { apiKey: settings.apiKey } : { auth: Auth.bearer(settings.authToken) }),
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    ...(authToken === undefined ? { apiKey: apiKey } : { auth: Auth.bearer(authToken) }),
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 }

packages/ai/src/providers/azure.ts

@@ -3,7 +3,7 @@ import { Auth } from "../route/auth.js"
 import { type AtLeastOne, type ProviderAuthOption } from "../route/auth-options.js"
 import type { Route, RouteDefaultsInput, CompactionOperations } from "../route/client.js"
 import type { ProviderPackage } from "../provider-package.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import * as OpenAIChat from "../protocols/openai-chat.js"
 import * as OpenAIResponses from "../protocols/openai-responses.js"
 import { ProviderShared } from "../protocols/shared.js"
@@ -28,12 +28,12 @@ export type LanguageModelOptions = AzureURL &
 export type Config = LanguageModelOptions
 
 export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput &
   AzureURL & {
     readonly apiKey?: string
     readonly apiVersion?: string
     readonly queryParams?: Readonly<Record<string, string>>
     readonly useDeploymentBasedUrls?: boolean
-    readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
 const resourceBaseURL = (resourceName: string) => `https://${resourceName.trim()}.openai.azure.com/openai`
@@ -151,19 +151,29 @@ export const provider = {
   configure,
 }
 
-const config = (settings: Settings): Config => {
+const config = ({
+  apiKey,
+  apiVersion,
+  baseURL,
+  body,
+  headers,
+  queryParams,
+  resourceName,
+  useDeploymentBasedUrls,
+  ...providerOptions
+}: Settings): Config => {
   const common = {
-    apiKey: settings.apiKey,
-    apiVersion: settings.apiVersion,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
-    queryParams: settings.queryParams === undefined ? undefined : { ...settings.queryParams },
-    useDeploymentBasedUrls: settings.useDeploymentBasedUrls,
+    apiKey,
+    apiVersion,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
+    queryParams: queryParams === undefined ? undefined : { ...queryParams },
+    useDeploymentBasedUrls,
   }
-  if (settings.baseURL !== undefined) return { ...common, baseURL: settings.baseURL }
-  if (settings.resourceName !== undefined) return { ...common, resourceName: settings.resourceName }
-  throw new Error("Azure requires resourceName or baseURL")
+  if (baseURL !== undefined) return { ...common, baseURL }
+  if (resourceName !== undefined) return { ...common, resourceName }
+  throw new ProviderConfigurationError({ provider: id, message: "Azure requires resourceName or baseURL" })
 }
 
 export const responsesModel: ProviderPackage.Definition<

packages/ai/src/providers/baseten.ts

@@ -15,11 +15,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = Route.make({
   id: "baseten-chat",
@@ -48,13 +48,16 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as Baseten from "./baseten.js"

packages/ai/src/providers/cerebras.ts

@@ -15,11 +15,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = Route.make({
   id: "cerebras-chat",
@@ -52,11 +52,14 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)

packages/ai/src/providers/cloudflare-ai-gateway.ts

@@ -5,7 +5,7 @@ import { Auth } from "../route/auth.js"
 import type { AtLeastOne, ProviderAuthOption } from "../route/auth-options.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import type { OpenAIProviderOptionsInput } from "./openai-options.js"
 
 export const id = ProviderID.make("cloudflare-ai-gateway")
@@ -27,15 +27,19 @@ export type LanguageModelOptions = GatewayURL &
   }
 
 export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput &
   GatewayURL & {
     readonly apiKey?: string
     readonly gatewayApiKey?: string
-    readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
 export const baseURL = (input: GatewayURL) => {
   if (input.baseURL) return input.baseURL
-  if (!input.accountId) throw new Error("CloudflareAIGateway.configure requires accountId unless baseURL is supplied")
+  if (!input.accountId)
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "CloudflareAIGateway.configure requires accountId unless baseURL is supplied",
+    })
   return `https://gateway.ai.cloudflare.com/v1/${encodeURIComponent(input.accountId)}/${encodeURIComponent(input.gatewayId?.trim() || "default")}/compat`
 }
 
@@ -85,14 +89,25 @@ export const configure = (input: LanguageModelOptions) => {
 
 export const provider = { id, configure }
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
-  configure({
-    apiKey: settings.apiKey,
-    gatewayApiKey: settings.gatewayApiKey,
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) => {
+  const {
+    accountId: _,
+    apiKey,
+    baseURL: _url,
+    body,
+    gatewayApiKey,
+    gatewayId: _id,
+    headers,
+    ...providerOptions
+  } = settings
+  return configure({
+    apiKey,
+    gatewayApiKey,
     baseURL: baseURL(settings),
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
+}
 
 export * as CloudflareAIGateway from "./cloudflare-ai-gateway.js"

packages/ai/src/providers/cloudflare-workers-ai.ts

@@ -3,7 +3,7 @@ import { OpenAIChat } from "../protocols/openai-chat.js"
 import { AuthOptions, type AtLeastOne, type ProviderAuthOption } from "../route/auth-options.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import type { OpenAIProviderOptionsInput } from "./openai-options.js"
 
 export const id = ProviderID.make("cloudflare-workers-ai")
@@ -21,14 +21,18 @@ export type LanguageModelOptions = WorkersAIURL &
   }
 
 export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput &
   WorkersAIURL & {
     readonly apiKey?: string
-    readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
 export const baseURL = (input: WorkersAIURL) => {
   if (input.baseURL) return input.baseURL
-  if (!input.accountId) throw new Error("CloudflareWorkersAI.configure requires accountId unless baseURL is supplied")
+  if (!input.accountId)
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "CloudflareWorkersAI.configure requires accountId unless baseURL is supplied",
+    })
   return `https://api.cloudflare.com/client/v4/accounts/${encodeURIComponent(input.accountId)}/ai/v1`
 }
 
@@ -59,13 +63,15 @@ export const configure = (input: LanguageModelOptions) => {
 
 export const provider = { id, configure }
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
-  configure({
-    apiKey: settings.apiKey,
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) => {
+  const { accountId: _, apiKey, baseURL: _url, body, headers, ...providerOptions } = settings
+  return configure({
+    apiKey,
     baseURL: baseURL(settings),
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
+}
 
 export * as CloudflareWorkersAI from "./cloudflare-workers-ai.js"

packages/ai/src/providers/deepinfra.ts

@@ -15,11 +15,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = Route.make({
   id: "deepinfra-chat",
@@ -55,11 +55,14 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)

packages/ai/src/providers/deepseek.ts

@@ -15,11 +15,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = Route.make({
   id: "deepseek-chat",
@@ -52,13 +52,16 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as DeepSeek from "./deepseek.js"

packages/ai/src/providers/fireworks.ts

@@ -15,11 +15,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = Route.make({
   id: "fireworks-chat",
@@ -48,13 +48,16 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as Fireworks from "./fireworks.js"

packages/ai/src/providers/google-vertex-chat.ts

@@ -2,7 +2,7 @@ import type { ProviderPackage } from "../provider-package.js"
 import { OpenAIChat } from "../protocols/openai-chat.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import { GoogleVertexShared } from "./google-vertex-shared.js"
 import type { OpenAIProviderOptionsInput } from "./openai-options.js"
 
@@ -16,14 +16,14 @@ export type Config = RouteDefaultsInput &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly accessToken?: string
-  readonly apiKey?: never
-  readonly baseURL?: string
-  readonly location?: string
-  readonly project?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly accessToken?: string
+    readonly apiKey?: never
+    readonly baseURL?: string
+    readonly location?: string
+    readonly project?: string
+  }
 
 const route = Route.make({
   id: "google-vertex-chat",
@@ -37,7 +37,8 @@ const route = Route.make({
 export const routes = [route]
 
 const configuredRoute = (input: Config) => {
-  if ("apiKey" in input && input.apiKey !== undefined) throw new Error("Google Vertex Chat does not support API keys")
+  if ("apiKey" in input && input.apiKey !== undefined)
+    throw new ProviderConfigurationError({ provider: id, message: "Google Vertex Chat does not support API keys" })
   const {
     accessToken: _accessToken,
     auth: _auth,
@@ -73,15 +74,19 @@ export const provider = {
   configure,
 }
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) => {
-  if (settings.apiKey !== undefined) throw new Error("Google Vertex Chat does not support API keys")
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { accessToken, apiKey, baseURL, body, headers, location, project, ...providerOptions },
+) => {
+  if (apiKey !== undefined)
+    throw new ProviderConfigurationError({ provider: id, message: "Google Vertex Chat does not support API keys" })
   return configure({
-    accessToken: settings.accessToken,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    location: settings.location,
-    project: settings.project,
-    providerOptions: settings.providerOptions,
+    accessToken,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    location,
+    project,
+    providerOptions,
   }).model(modelID)
 }

packages/ai/src/providers/google-vertex-messages.ts

@@ -5,7 +5,7 @@ import { Auth } from "../route/auth.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
 import { Protocol } from "../route/protocol.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import { GoogleVertexShared } from "./google-vertex-shared.js"
 
 export type AnthropicOptionsInput = AnthropicMessages.OptionsInput
@@ -25,14 +25,14 @@ export type Config = RouteDefaultsInput &
     readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly accessToken?: string
-  readonly apiKey?: never
-  readonly baseURL?: string
-  readonly location?: string
-  readonly project?: string
-  readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  AnthropicMessages.ProviderOptionsInput & {
+    readonly accessToken?: string
+    readonly apiKey?: never
+    readonly baseURL?: string
+    readonly location?: string
+    readonly project?: string
+  }
 
 const route = Route.make({
   id: "google-vertex-messages",
@@ -67,7 +67,7 @@ export const routes = [route]
 
 const configuredRoute = (input: Config) => {
   if ("apiKey" in input && input.apiKey !== undefined)
-    throw new Error("Google Vertex Messages does not support API keys")
+    throw new ProviderConfigurationError({ provider: id, message: "Google Vertex Messages does not support API keys" })
   const {
     accessToken: _accessToken,
     auth: _auth,
@@ -105,16 +105,17 @@ export const provider = {
 
 export const model: ProviderPackage.Definition<Settings, AnthropicMessages.ProviderOptionsInput>["model"] = (
   modelID,
-  settings,
+  { accessToken, apiKey, baseURL, body, headers, location, project, ...providerOptions },
 ) => {
-  if (settings.apiKey !== undefined) throw new Error("Google Vertex Messages does not support API keys")
+  if (apiKey !== undefined)
+    throw new ProviderConfigurationError({ provider: id, message: "Google Vertex Messages does not support API keys" })
   return configure({
-    accessToken: settings.accessToken,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    location: settings.location,
-    project: settings.project,
-    providerOptions: settings.providerOptions,
+    accessToken,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    location,
+    project,
+    providerOptions,
   }).model(modelID)
 }

packages/ai/src/providers/google-vertex-responses.ts

@@ -2,7 +2,7 @@ import type { ProviderPackage } from "../provider-package.js"
 import { OpenResponses } from "../protocols/open-responses.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { ProviderID, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type ModelID } from "../schema/index.js"
 import { GoogleVertexShared } from "./google-vertex-shared.js"
 import type { OpenResponsesProviderOptionsInput } from "./open-responses-options.js"
 
@@ -16,14 +16,14 @@ export type Config = RouteDefaultsInput &
     readonly providerOptions?: OpenResponsesProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly accessToken?: string
-  readonly apiKey?: never
-  readonly baseURL?: string
-  readonly location?: string
-  readonly project?: string
-  readonly providerOptions?: OpenResponsesProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenResponsesProviderOptionsInput & {
+    readonly accessToken?: string
+    readonly apiKey?: never
+    readonly baseURL?: string
+    readonly location?: string
+    readonly project?: string
+  }
 
 const route = Route.make({
   id: "google-vertex-responses",
@@ -39,7 +39,7 @@ export const routes = [route]
 
 const configuredRoute = (input: Config) => {
   if ("apiKey" in input && input.apiKey !== undefined)
-    throw new Error("Google Vertex Responses does not support API keys")
+    throw new ProviderConfigurationError({ provider: id, message: "Google Vertex Responses does not support API keys" })
   const {
     accessToken: _accessToken,
     auth: _auth,
@@ -77,16 +77,17 @@ export const provider = {
 
 export const model: ProviderPackage.Definition<Settings, OpenResponsesProviderOptionsInput>["model"] = (
   modelID,
-  settings,
+  { accessToken, apiKey, baseURL, body, headers, location, project, ...providerOptions },
 ) => {
-  if (settings.apiKey !== undefined) throw new Error("Google Vertex Responses does not support API keys")
+  if (apiKey !== undefined)
+    throw new ProviderConfigurationError({ provider: id, message: "Google Vertex Responses does not support API keys" })
   return configure({
-    accessToken: settings.accessToken,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    location: settings.location,
-    project: settings.project,
-    providerOptions: settings.providerOptions,
+    accessToken,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    location,
+    project,
+    providerOptions,
   }).model(modelID)
 }

packages/ai/src/providers/google-vertex-shared.ts

@@ -1,8 +1,10 @@
 import type { AnyAuthClient } from "google-auth-library"
 import { Effect, Redacted } from "effect"
 import { Auth, MissingCredentialError } from "../route/auth.js"
+import { ProviderConfigurationError, ProviderID } from "../schema/index.js"
 
 const SCOPE = "https://www.googleapis.com/auth/cloud-platform"
+const id = ProviderID.make("google-vertex")
 
 export type OAuthOptions =
   | { readonly accessToken?: string; readonly auth?: never }
@@ -35,12 +37,18 @@ export const host = (location: string) => {
 
 export const requireProject = (value: string | undefined) => {
   if (value) return value
-  throw new Error("Google Vertex requires a project when baseURL is not configured")
+  throw new ProviderConfigurationError({
+    provider: id,
+    message: "Google Vertex requires a project when baseURL is not configured",
+  })
 }
 
 export const apiKey = (input: ApiKeyOptions) => {
   if (input.apiKey !== undefined && (input.accessToken !== undefined || input.auth !== undefined))
-    throw new Error("Google Vertex apiKey cannot be combined with accessToken or auth")
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "Google Vertex apiKey cannot be combined with accessToken or auth",
+    })
   if (input.accessToken !== undefined || input.auth !== undefined) return undefined
   return input.apiKey ?? process.env.GOOGLE_VERTEX_API_KEY
 }
@@ -68,7 +76,10 @@ const adc = (project?: string) => {
 
 export const oauth = (input: OAuthOptions, project?: string) => {
   if (input.accessToken !== undefined && input.auth !== undefined)
-    throw new Error("Google Vertex accessToken cannot be combined with auth")
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "Google Vertex accessToken cannot be combined with auth",
+    })
   if (input.auth) return input.auth
   if (input.accessToken !== undefined) return Auth.bearer(input.accessToken)
   return adc(project)

packages/ai/src/providers/google-vertex.ts

@@ -6,7 +6,7 @@ import { Auth } from "../route/auth.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
 import { Framing } from "../route/framing.js"
-import { ProviderID, type LLMRequest, type ModelID } from "../schema/index.js"
+import { ProviderConfigurationError, ProviderID, type LLMRequest, type ModelID } from "../schema/index.js"
 import { GoogleVertexShared } from "./google-vertex-shared.js"
 
 export interface GeminiOptionsInput extends Gemini.OptionsInput {
@@ -26,6 +26,7 @@ export type Config = RouteDefaultsInput &
   }
 
 export type Settings = ProviderPackage.Settings &
+  GeminiProviderOptionsInput &
   (
     | { readonly accessToken?: string; readonly apiKey?: never }
     | { readonly accessToken?: never; readonly apiKey?: string }
@@ -33,7 +34,6 @@ export type Settings = ProviderPackage.Settings &
     readonly baseURL?: string
     readonly location?: string
     readonly project?: string
-    readonly providerOptions?: GeminiProviderOptionsInput
   }
 
 const fromRequest = Effect.fn("GoogleVertex.fromRequest")(function* (request: LLMRequest) {
@@ -93,7 +93,10 @@ const configuredRoute = (input: Config, modelID: string | ModelID) => {
   const apiKey = GoogleVertexShared.apiKey(input)
   const endpointModel = String(modelID).startsWith("endpoints/")
   if (apiKey !== undefined && endpointModel)
-    throw new Error("Google Vertex tuned models do not support Express Mode API keys")
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "Google Vertex tuned models do not support Express Mode API keys",
+    })
   const location = GoogleVertexShared.location(inputLocation, "us-central1")
   const project = GoogleVertexShared.project(inputProject)
   const endpoint =
@@ -121,16 +124,22 @@ export const provider = {
   id,
   configure,
 }
-export const model: ProviderPackage.Definition<Settings, GeminiProviderOptionsInput>["model"] = (modelID, settings) => {
-  if (settings.apiKey !== undefined && settings.accessToken !== undefined)
-    throw new Error("Google Vertex apiKey cannot be combined with accessToken or auth")
+export const model: ProviderPackage.Definition<Settings, GeminiProviderOptionsInput>["model"] = (
+  modelID,
+  { accessToken, apiKey, baseURL, body, headers, location, project, ...providerOptions },
+) => {
+  if (apiKey !== undefined && accessToken !== undefined)
+    throw new ProviderConfigurationError({
+      provider: id,
+      message: "Google Vertex apiKey cannot be combined with accessToken or auth",
+    })
   return configure({
-    ...(settings.apiKey === undefined ? { accessToken: settings.accessToken } : { apiKey: settings.apiKey }),
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    location: settings.location,
-    project: settings.project,
-    providerOptions: settings.providerOptions,
+    ...(apiKey === undefined ? { accessToken: accessToken } : { apiKey: apiKey }),
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    location,
+    project,
+    providerOptions,
   }).model(modelID)
 }

packages/ai/src/providers/google.ts

@@ -20,11 +20,11 @@ export type Config = RouteDefaultsInput &
     readonly providerOptions?: Gemini.ProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: Gemini.ProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  Gemini.ProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const auth = (options: ProviderAuthOption<"optional">) => {
   if ("auth" in options && options.auth) return options.auth
@@ -57,13 +57,16 @@ export const configure = (input: Config = {}) => {
 }
 
 export const provider = configure()
-export const model: ProviderPackage.Definition<Settings, Gemini.ProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, Gemini.ProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export const image = provider.image

packages/ai/src/providers/groq.ts

@@ -26,11 +26,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ProviderOptions
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: ProviderOptions
-}
+export type Settings = ProviderPackage.Settings &
+  ProviderOptions & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const Options = Schema.Struct({
   includeReasoning: Schema.optional(Schema.Boolean),
@@ -103,13 +103,16 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, ProviderOptions>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, ProviderOptions>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as Groq from "./groq.js"

packages/ai/src/providers/index.ts

@@ -1,3 +1,4 @@
+export * as Alibaba from "./alibaba.js"
 export * as Anthropic from "./anthropic.js"
 export * as AnthropicCompatible from "./anthropic-compatible.js"
 export * as AmazonBedrock from "./amazon-bedrock.js"

packages/ai/src/providers/meta.ts

@@ -79,11 +79,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: ProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  ProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const responsesRoute = Route.make({
   id: "meta-responses",
@@ -169,13 +169,13 @@ export const chatModel: ProviderPackage.Definition<Settings, OpenResponsesProvid
 export const messagesModel: ProviderPackage.Definition<Settings, MessagesOptionsInput>["model"] = (modelID, settings) =>
   fromSettings(settings).messages(modelID)
 
-function fromSettings(settings: Settings) {
+function fromSettings({ apiKey, baseURL, body, headers, ...providerOptions }: Settings) {
   return configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   })
 }
 

packages/ai/src/providers/minimax.ts

@@ -40,11 +40,11 @@ export type Config = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ProviderOptionsInput
   }
 
-export interface Settings<Options = MessagesOptionsInput> extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: Options
-}
+export type Settings<Options = MessagesOptionsInput> = ProviderPackage.Settings &
+  Options & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const ChatOptions = Schema.Struct({
   thinking: Schema.optional(Schema.Struct({ type: Schema.String })),
@@ -127,14 +127,14 @@ export const provider = configure()
 
 export const model: ProviderPackage.Definition<Settings<MessagesOptionsInput>, MessagesOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export const messages = provider.messages

packages/ai/src/providers/minimax/chat.ts

@@ -3,11 +3,14 @@ import { MiniMax } from "../minimax.js"
 
 export type Settings = MiniMax.Settings<MiniMax.ChatOptionsInput>
 
-export const model: ProviderPackage.Definition<Settings, MiniMax.ChatOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, MiniMax.ChatOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   MiniMax.configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).chat(modelID)

packages/ai/src/providers/minimax/responses.ts

@@ -5,12 +5,12 @@ export type Settings = MiniMax.Settings<MiniMax.ResponsesOptionsInput>
 
 export const model: ProviderPackage.Definition<Settings, MiniMax.ResponsesOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   MiniMax.configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).responses(modelID)

packages/ai/src/providers/mistral.ts

@@ -14,11 +14,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ProviderOptions
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: ProviderOptions
-}
+export type Settings = ProviderPackage.Settings &
+  ProviderOptions & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = MistralChat.route
 export const routes = [route]
@@ -39,13 +39,16 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, ProviderOptions>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, ProviderOptions>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as Mistral from "./mistral.js"

packages/ai/src/providers/moonshot.ts

@@ -42,11 +42,11 @@ export type Config = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ChatOptionsInput | MessagesOptionsInput | ResponsesOptionsInput
   }
 
-export interface Settings<Options = ChatOptionsInput> extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: Options
-}
+export type Settings<Options = ChatOptionsInput> = ProviderPackage.Settings &
+  Options & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const ChatOptions = Schema.Struct({
   reasoningEffort: Schema.optional(Schema.String),
@@ -133,13 +133,16 @@ export const chat = provider.chat
 export const messages = provider.messages
 export const responses = provider.responses
 
-export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as Moonshot from "./moonshot.js"

packages/ai/src/providers/moonshot/messages.ts

@@ -5,12 +5,12 @@ export type Settings = Moonshot.Settings<Moonshot.MessagesOptionsInput>
 
 export const model: ProviderPackage.Definition<Settings, Moonshot.MessagesOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   Moonshot.configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).messages(modelID)

packages/ai/src/providers/moonshot/responses.ts

@@ -5,12 +5,12 @@ export type Settings = Moonshot.Settings<Moonshot.ResponsesOptionsInput>
 
 export const model: ProviderPackage.Definition<Settings, Moonshot.ResponsesOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   Moonshot.configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).responses(modelID)

packages/ai/src/providers/openai-compatible-responses.ts

@@ -16,12 +16,12 @@ export type Config = RouteDefaultsInput &
     readonly providerOptions?: OpenResponsesProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL: string
-  readonly provider?: string
-  readonly providerOptions?: OpenResponsesProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenResponsesProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL: string
+    readonly provider?: string
+  }
 
 export const routes = [OpenAICompatibleResponses.route]
 
@@ -48,13 +48,13 @@ export const provider = {
 
 export const model: ProviderPackage.Definition<Settings, OpenResponsesProviderOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, provider, ...providerOptions },
 ) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    provider: settings.provider,
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    provider,
+    providerOptions,
   }).model(modelID)

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

@@ -14,12 +14,12 @@ type GenericModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL: string
-  readonly provider?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL: string
+    readonly provider?: string
+  }
 
 export const routes = [OpenAICompatibleChat.route]
 
@@ -45,14 +45,17 @@ export const provider = {
   configure,
 }
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, provider, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    provider: settings.provider,
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    provider,
+    providerOptions,
   }).model(modelID)
 
 export * as OpenAICompatible from "./openai-compatible.js"

packages/ai/src/providers/openai.ts

@@ -57,14 +57,14 @@ export const imageGeneration = (options: ImageGenerationOptions = {}) =>
     },
   })
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly organization?: string
-  readonly project?: string
-  readonly queryParams?: Readonly<Record<string, string>>
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+    readonly organization?: string
+    readonly project?: string
+    readonly queryParams?: Readonly<Record<string, string>>
+  }
 
 const auth = (options: ProviderAuthOption<"optional">) => AuthOptions.bearer(options, "OPENAI_API_KEY")
 
@@ -116,19 +116,28 @@ export const configure = (input: Config = {}) => {
 
 export const provider = configure()
 
-const config = (settings: Settings): Config => {
+const config = ({
+  apiKey,
+  baseURL,
+  body,
+  headers: given,
+  organization,
+  project,
+  queryParams,
+  ...providerOptions
+}: Settings): Config => {
   const headers = {
-    ...(settings.organization === undefined ? {} : { "OpenAI-Organization": settings.organization }),
-    ...(settings.project === undefined ? {} : { "OpenAI-Project": settings.project }),
-    ...settings.headers,
+    ...(organization === undefined ? {} : { "OpenAI-Organization": organization }),
+    ...(project === undefined ? {} : { "OpenAI-Project": project }),
+    ...given,
   }
   return {
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
+    apiKey,
+    baseURL,
     headers: Object.keys(headers).length === 0 ? undefined : headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
-    queryParams: settings.queryParams === undefined ? undefined : { ...settings.queryParams },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
+    queryParams: queryParams === undefined ? undefined : { ...queryParams },
   }
 }
 

packages/ai/src/providers/openrouter.ts

@@ -77,11 +77,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenRouterProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenRouterProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenRouterProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const OpenRouterBody = Schema.StructWithRest(Schema.Struct(OpenAIChat.bodyFields), [
   Schema.Record(Schema.String, Schema.Any),
@@ -191,12 +191,12 @@ export const configure = (input: LanguageModelOptions = {}) => {
 export const provider = configure()
 export const model: ProviderPackage.Definition<Settings, OpenRouterProviderOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)

packages/ai/src/providers/togetherai.ts

@@ -15,11 +15,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: OpenAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: OpenAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  OpenAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export const route = Route.make({
   id: "togetherai-chat",
@@ -52,11 +52,14 @@ export const configure = (input: LanguageModelOptions = {}) => {
 
 export const provider = configure()
 
-export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers === undefined ? undefined : { ...settings.headers },
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers: headers === undefined ? undefined : { ...headers },
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)

packages/ai/src/providers/xai.ts

@@ -20,11 +20,11 @@ export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: XAIProviderOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: XAIProviderOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  XAIProviderOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export type { XAIImageOptions } from "../protocols/xai-images.js"
 
@@ -41,6 +41,10 @@ const responsesRoute = Route.make({
     id: "openai-responses",
     name: "xAI Responses",
     rotateAfterMs: RESPONSES_WEBSOCKET_ROTATE_AFTER_MS,
+    // xAI continues a chain only from stored responses: with `store: false` (the route default) `previous_response_id`
+    // fails with "Response with id=… not found", so those steps are sent in full over the reused connection. It also
+    // rejects `instructions` next to `previous_response_id` and keeps the instructions of the response it continues.
+    continuation: ({ instructions: _instructions, ...request }) => (request.store === false ? undefined : request),
   }),
   defaults: { providerOptions: { store: false, include: ["reasoning.encrypted_content"] } },
 })
@@ -106,13 +110,13 @@ export const model: ProviderPackage.Definition<
   Settings,
   XAIProviderOptionsInput,
   typeof responsesRoute.compact
->["model"] = (modelID, settings) =>
+>["model"] = (modelID, { apiKey, baseURL, body, headers, ...providerOptions }) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 export const responses = provider.responses
 export const chat = provider.chat

packages/ai/src/providers/zai-coding-plan.ts

@@ -23,11 +23,11 @@ export type Config = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ChatOptionsInput | MessagesOptionsInput | ResponsesOptionsInput
   }
 
-export interface Settings<Options = ChatOptionsInput> extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: Options
-}
+export type Settings<Options = ChatOptionsInput> = ProviderPackage.Settings &
+  Options & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 const chatRoute = Route.make({
   id: "zai-coding-chat",
@@ -80,13 +80,16 @@ export const chat = provider.chat
 export const messages = provider.messages
 export const responses = provider.responses
 
-export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as ZAICodingPlan from "./zai-coding-plan.js"

packages/ai/src/providers/zai-coding-plan/messages.ts

@@ -5,12 +5,12 @@ export type Settings = ZAICodingPlan.Settings<ZAICodingPlan.MessagesOptionsInput
 
 export const model: ProviderPackage.Definition<Settings, ZAICodingPlan.MessagesOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   ZAICodingPlan.configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).messages(modelID)

packages/ai/src/providers/zai-coding-plan/responses.ts

@@ -5,12 +5,12 @@ export type Settings = ZAICodingPlan.Settings<ZAICodingPlan.ResponsesOptionsInpu
 
 export const model: ProviderPackage.Definition<Settings, ZAICodingPlan.ResponsesOptionsInput>["model"] = (
   modelID,
-  settings,
+  { apiKey, baseURL, body, headers, ...providerOptions },
 ) =>
   ZAICodingPlan.configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).responses(modelID)

packages/ai/src/providers/zai.ts

@@ -17,11 +17,11 @@ export type Config = Omit<RouteDefaultsInput, "providerOptions"> &
     readonly providerOptions?: ChatOptionsInput
   }
 
-export interface Settings extends ProviderPackage.Settings {
-  readonly apiKey?: string
-  readonly baseURL?: string
-  readonly providerOptions?: ChatOptionsInput
-}
+export type Settings = ProviderPackage.Settings &
+  ChatOptionsInput & {
+    readonly apiKey?: string
+    readonly baseURL?: string
+  }
 
 export type { ZAIImageOptions } from "../protocols/zai-images.js"
 
@@ -70,13 +70,16 @@ export const provider = configure()
 export const image = provider.image
 export const chat = provider.chat
 
-export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (modelID, settings) =>
+export const model: ProviderPackage.Definition<Settings, ChatOptionsInput>["model"] = (
+  modelID,
+  { apiKey, baseURL, body, headers, ...providerOptions },
+) =>
   configure({
-    apiKey: settings.apiKey,
-    baseURL: settings.baseURL,
-    headers: settings.headers,
-    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.providerOptions,
+    apiKey,
+    baseURL,
+    headers,
+    http: body === undefined ? undefined : { body: { ...body } },
+    providerOptions,
   }).model(modelID)
 
 export * as ZAI from "./zai.js"

packages/ai/src/route/client.ts

@@ -23,6 +23,7 @@ import {
   LanguageModel,
   LLMEvent,
   InvalidProviderOutputError,
+  ProviderConfigurationError,
   ProviderID,
   mergeGenerationOptions,
   mergeHttpOptions,
@@ -128,7 +129,10 @@ const makeRouteLanguageModel = <Options extends ProviderOptions, Compact extends
   const provider = route.provider ?? ("provider" in mapped ? mapped.provider : undefined)
   if (!provider) throw new Error(`Route.model(${route.id}) requires a provider`)
   if (!endpointBaseURL(route.endpoint))
-    throw new Error(`Route.model(${route.id}) requires an endpoint baseURL — configure it on the route first`)
+    throw new ProviderConfigurationError({
+      provider: ProviderID.make(provider),
+      message: `Route.model(${route.id}) requires an endpoint baseURL — configure it on the route first`,
+    })
   return LanguageModel.make<Options, Compact>({
     ...mapped,
     provider,

packages/ai/src/route/transport/websocket.ts

@@ -115,8 +115,11 @@ const waitOpen = (ws: globalThis.WebSocket, input: WebSocketRequest) => {
     }
     const onAbort = () => {
       cleanup()
-      if (ws.readyState !== globalThis.WebSocket.CLOSED && ws.readyState !== globalThis.WebSocket.CLOSING)
-        ws.close(1000)
+      if (ws.readyState === globalThis.WebSocket.CLOSED || ws.readyState === globalThis.WebSocket.CLOSING) return
+      // Node's ws reports an aborted handshake as an error event on the next tick; with no listener left
+      // after cleanup, EventEmitter would throw it as an uncaught exception.
+      ws.addEventListener("error", () => {}, { once: true })
+      ws.close(1000)
     }
     const onOpen = () => {
       cleanup()

packages/ai/src/schema/errors.ts

@@ -50,6 +50,19 @@ export class UnsupportedOperationError extends Schema.TaggedError<UnsupportedOpe
   route: Schema.optional(RouteID),
 }) {}
 
+/**
+ * Provider settings that are missing, conflicting, or unsupported, such as
+ * Azure without `resourceName` or `baseURL`. Thrown synchronously while a
+ * provider facade or package entrypoint configures a model, before any
+ * request exists, so it is not an `AIError` reason.
+ */
+export class ProviderConfigurationError extends Schema.TaggedError<ProviderConfigurationError>(
+  "AI.Error.ProviderConfiguration",
+)("ProviderConfiguration", {
+  provider: ProviderID,
+  message: Schema.String,
+}) {}
+
 export class NoRouteError extends Schema.TaggedError<NoRouteError>("AI.Error.NoRoute")("NoRoute", {
   ...ReasonFields,
   route: RouteID,

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

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-chat",
+      "provider:alibaba",
+      "protocol:alibaba-chat",
+      "region:ap-southeast-1",
+      "thinking",
+      "usage"
+    ],
+    "name": "alibaba-chat/qwen-3-7-plus-streams-thinking-disabled",
+    "recordedAt": "2026-09-08T03:10:42.782Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_completion_tokens\":4096,\"enable_thinking\":false}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=utf-8"
+        },
+        "body": "data: {\"model\":\"qwen3.7-plus\",\"id\":\"chatcmpl-047bcb67-b193-9a4f-9d77-ea0325be6d7c\",\"created\":1788837041,\"object\":\"chat.completion.chunk\",\"usage\":null,\"choices\":[{\"logprobs\":null,\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\"},\"finish_reason\":null}]}\n\ndata: {\"model\":\"qwen3.7-plus\",\"id\":\"chatcmpl-047bcb67-b193-9a4f-9d77-ea0325be6d7c\",\"choices\":[{\"delta\":{\"content\":\"3\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837041,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.7-plus\",\"id\":\"chatcmpl-047bcb67-b193-9a4f-9d77-ea0325be6d7c\",\"choices\":[{\"delta\":{\"content\":\"7887\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837041,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.7-plus\",\"id\":\"chatcmpl-047bcb67-b193-9a4f-9d77-ea0325be6d7c\",\"choices\":[{\"delta\":{\"content\":\"\"},\"index\":0,\"finish_reason\":\"stop\",\"logprobs\":null}],\"created\":1788837041,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"choices\":[],\"created\":1788837041,\"id\":\"chatcmpl-047bcb67-b193-9a4f-9d77-ea0325be6d7c\",\"model\":\"qwen3.7-plus\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":5,\"prompt_tokens\":32,\"prompt_tokens_details\":{\"cached_tokens\":0,\"text_tokens\":32},\"total_tokens\":37}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-chat",
+      "provider:alibaba",
+      "protocol:alibaba-chat",
+      "region:ap-southeast-1",
+      "tool",
+      "tool-choice"
+    ],
+    "name": "alibaba-chat/qwen-3-8-max-obeys-named-tool-choice",
+    "recordedAt": "2026-09-08T03:10:56.576Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":\"Find the current weather in Paris.\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get weather in a city\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"]}}}],\"tool_choice\":{\"type\":\"function\",\"function\":{\"name\":\"get_weather\"}},\"stream\":true,\"stream_options\":{\"include_usage\":true},\"reasoning_effort\":\"none\",\"max_completion_tokens\":4096}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=utf-8"
+        },
+        "body": "data: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null,\"choices\":[{\"logprobs\":null,\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"tool_calls\":[{\"index\":0,\"id\":\"call_4eb823cb28d141c8befbb331\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"\"}}]},\"finish_reason\":null}]}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{\"content\":\"\",\"tool_calls\":[{\"index\":0,\"id\":\"\",\"type\":\"function\",\"function\":{\"arguments\":\"\"}}]},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{\"content\":\"\",\"tool_calls\":[{\"type\":\"function\",\"index\":0,\"function\":{\"arguments\":\"{\\\"city\\\": \\\"Paris\"}}]},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{\"content\":\"\",\"tool_calls\":[{\"type\":\"function\",\"index\":0,\"function\":{\"arguments\":\"\\\"\"}}]},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{\"content\":\"\",\"tool_calls\":[{\"type\":\"function\",\"index\":0,\"function\":{\"arguments\":\"}\"}}]},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{\"content\":\"\",\"tool_calls\":[{\"type\":\"function\",\"index\":0,\"function\":{\"arguments\":\"\"}}]},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{\"tool_calls\":[{\"function\":{\"arguments\":\"\"},\"index\":0,\"id\":null,\"type\":\"function\"}],\"content\":\"\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"choices\":[{\"delta\":{},\"index\":0,\"finish_reason\":\"stop\",\"logprobs\":null}],\"created\":1788837055,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"choices\":[],\"created\":1788837055,\"id\":\"chatcmpl-681dfa5a-ae08-98da-ba0d-4b1d0d364b6b\",\"model\":\"qwen3.8-max\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":19,\"prompt_tokens\":288,\"prompt_tokens_details\":{\"cached_tokens\":0,\"text_tokens\":288},\"total_tokens\":307}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/alibaba-chat/qwen-3-8-max-returns-a-json-object.json

@@ -0,0 +1,34 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-chat",
+      "provider:alibaba",
+      "protocol:alibaba-chat",
+      "region:ap-southeast-1",
+      "structured-output"
+    ],
+    "name": "alibaba-chat/qwen-3-8-max-returns-a-json-object",
+    "recordedAt": "2026-09-08T03:11:29.462Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":\"Return a JSON object with one key \\\"city\\\" set to the capital city of France.\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"reasoning_effort\":\"none\",\"max_completion_tokens\":1024,\"response_format\":{\"type\":\"json_object\"}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=utf-8"
+        },
+        "body": "data: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-de34af77-7b1e-9999-a48f-e564c03d4b6b\",\"created\":1788837088,\"object\":\"chat.completion.chunk\",\"usage\":null,\"choices\":[{\"logprobs\":null,\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\"},\"finish_reason\":null}]}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-de34af77-7b1e-9999-a48f-e564c03d4b6b\",\"choices\":[{\"delta\":{\"content\":\"{\\\"\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837088,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-de34af77-7b1e-9999-a48f-e564c03d4b6b\",\"choices\":[{\"delta\":{\"content\":\"city\\\":\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837088,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-de34af77-7b1e-9999-a48f-e564c03d4b6b\",\"choices\":[{\"delta\":{\"content\":\" \\\"Paris\\\"}\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788837088,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-de34af77-7b1e-9999-a48f-e564c03d4b6b\",\"choices\":[{\"delta\":{\"content\":\"\"},\"index\":0,\"finish_reason\":\"stop\",\"logprobs\":null}],\"created\":1788837088,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"choices\":[],\"created\":1788837088,\"id\":\"chatcmpl-de34af77-7b1e-9999-a48f-e564c03d4b6b\",\"model\":\"qwen3.8-max\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":6,\"prompt_tokens\":32,\"prompt_tokens_details\":{\"cached_tokens\":0,\"text_tokens\":32},\"total_tokens\":38}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/alibaba-chat/qwen-3-8-max-streams-none-effort.json

@@ -0,0 +1,36 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-chat",
+      "provider:alibaba",
+      "protocol:alibaba-chat",
+      "region:ap-southeast-1",
+      "text",
+      "reasoning",
+      "usage"
+    ],
+    "name": "alibaba-chat/qwen-3-8-max-streams-none-effort",
+    "recordedAt": "2026-09-08T03:09:27.584Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"reasoning_effort\":\"none\",\"max_completion_tokens\":4096}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=utf-8"
+        },
+        "body": "data: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-d8fbc8fe-4d5a-9dc9-84c6-ed0c7b9dd3bb\",\"created\":1788836967,\"object\":\"chat.completion.chunk\",\"usage\":null,\"choices\":[{\"logprobs\":null,\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\"},\"finish_reason\":null}]}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-d8fbc8fe-4d5a-9dc9-84c6-ed0c7b9dd3bb\",\"choices\":[{\"delta\":{\"content\":\"3\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788836967,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-d8fbc8fe-4d5a-9dc9-84c6-ed0c7b9dd3bb\",\"choices\":[{\"delta\":{\"content\":\"78\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788836967,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-d8fbc8fe-4d5a-9dc9-84c6-ed0c7b9dd3bb\",\"choices\":[{\"delta\":{\"content\":\"87\"},\"index\":0,\"finish_reason\":null,\"logprobs\":null}],\"created\":1788836967,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"model\":\"qwen3.8-max\",\"id\":\"chatcmpl-d8fbc8fe-4d5a-9dc9-84c6-ed0c7b9dd3bb\",\"choices\":[{\"delta\":{\"content\":\"\"},\"index\":0,\"finish_reason\":\"stop\",\"logprobs\":null}],\"created\":1788836967,\"object\":\"chat.completion.chunk\",\"usage\":null}\n\ndata: {\"choices\":[],\"created\":1788836967,\"id\":\"chatcmpl-d8fbc8fe-4d5a-9dc9-84c6-ed0c7b9dd3bb\",\"model\":\"qwen3.8-max\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":5,\"prompt_tokens\":32,\"prompt_tokens_details\":{\"cached_tokens\":0,\"text_tokens\":32},\"total_tokens\":37}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-messages",
+      "provider:alibaba",
+      "protocol:alibaba-messages",
+      "region:ap-southeast-1",
+      "thinking",
+      "usage"
+    ],
+    "name": "alibaba-messages/qwen-3-7-plus-streams-thinking-disabled",
+    "recordedAt": "2026-09-08T03:10:57.819Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.7-plus\",\"id\":\"msg_c4d58b4f-a61d-9d0c-a9e4-cb45d34b1120\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":20,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"3\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"7887\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":5,\"cache_creation_input_tokens\":0,\"input_tokens\":32,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,34 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-messages",
+      "provider:alibaba",
+      "protocol:alibaba-messages",
+      "region:ap-southeast-1",
+      "structured-output"
+    ],
+    "name": "alibaba-messages/qwen-3-8-max-follows-a-json-schema",
+    "recordedAt": "2026-09-08T03:11:30.530Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object with one key \\\"city\\\" set to the capital city of France.\"}]}],\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"disabled\"},\"output_config\":{\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_16e067c1-984b-94d3-9abb-11792d794271\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":18,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"{\\\"\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"city\\\":\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\" \\\"Paris\\\"}\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":6,\"cache_creation_input_tokens\":0,\"input_tokens\":32,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-messages",
+      "provider:alibaba",
+      "protocol:alibaba-messages",
+      "region:ap-southeast-1",
+      "tool",
+      "tool-choice"
+    ],
+    "name": "alibaba-messages/qwen-3-8-max-obeys-named-tool-choice",
+    "recordedAt": "2026-09-08T03:11:06.590Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Find the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"]}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_0e8f1abf-f2bc-9a86-a6a7-14804ac17eac\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":45,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"name\":\"get_weather\",\"input\":{},\"id\":\"toolu_cf9cab33261f4709ae096d8a\",\"type\":\"tool_use\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"{\\\"city\\\": \\\"Paris\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"\\\"\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"}\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":19,\"cache_creation_input_tokens\":0,\"input_tokens\":288,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,36 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-messages",
+      "provider:alibaba",
+      "protocol:alibaba-messages",
+      "region:ap-southeast-1",
+      "text",
+      "reasoning",
+      "usage"
+    ],
+    "name": "alibaba-messages/qwen-3-8-max-streams-max-effort",
+    "recordedAt": "2026-09-08T03:12:36.479Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"max\"}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_7952446b-0176-9526-ad7d-b1f0184bc106\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":20,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"thinking\",\"signature\":\"\",\"thinking\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"We\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" need answer user\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"'s simple multiplication with\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" only final integer.\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Need compute 1\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"73*2\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"19. \"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"173*\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"200=\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"3460\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"0; 1\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"73*1\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"9=32\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"87 (\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"173*\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"20=3\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"460-\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"173=\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"3287\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"); sum=3\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"7887\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\". Final only integer\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"signature_delta\",\"signature\":\"\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":1}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"37\"},\"type\":\"content_block_delta\",\"index\":1}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"887\"},\"type\":\"content_block_delta\",\"index\":1}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":1}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":92,\"cache_creation_input_tokens\":0,\"input_tokens\":81,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,36 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-messages",
+      "provider:alibaba",
+      "protocol:alibaba-messages",
+      "region:ap-southeast-1",
+      "text",
+      "reasoning",
+      "usage"
+    ],
+    "name": "alibaba-messages/qwen-3-8-max-streams-xhigh-effort",
+    "recordedAt": "2026-09-08T03:10:04.633Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"xhigh\"}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_a57b8563-71fb-9248-a31e-c49d6ba38717\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":20,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"thinking\",\"signature\":\"\",\"thinking\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"We\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" need answer simple multiplication\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\". We\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" already call\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\". Need compute \"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"173*\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"219.\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" 173\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"*200\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"=346\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"00; *\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"19=3\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"287;\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" sum 37\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"88\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"7. Final only\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" integer. Ensure\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" no extra.\\n\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"signature_delta\",\"signature\":\"\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":1}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"378\"},\"type\":\"content_block_delta\",\"index\":1}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"87\"},\"type\":\"content_block_delta\",\"index\":1}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":1}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":69,\"cache_creation_input_tokens\":0,\"input_tokens\":81,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+      }
+    }
+  ]
+}

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

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-responses",
+      "provider:alibaba",
+      "protocol:alibaba-responses",
+      "region:ap-southeast-1",
+      "thinking",
+      "usage"
+    ],
+    "name": "alibaba-responses/qwen-3-7-plus-streams-thinking-disabled",
+    "recordedAt": "2026-09-08T03:11:07.495Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/responses",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.7-plus\",\"input\":[{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"max_output_tokens\":4096,\"enable_thinking\":false,\"stream\":true}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=UTF-8"
+        },
+        "body": "id:1\nevent:response.created\n:HTTP_STATUS/200\ndata:{\"sequence_number\":0,\"type\":\"response.created\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"created_at\":1788837067,\"store\":true,\"tools\":[],\"output\":[],\"top_p\":1.0,\"completed_at\":1788837067,\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.7-plus\",\"service_tier\":\"default\",\"id\":\"resp_493607bf-baef-9ced-9e36-2e2a583b6177\",\"max_output_tokens\":4096,\"object\":\"response\",\"status\":\"queued\"}}\n\nid:2\nevent:response.in_progress\n:HTTP_STATUS/200\ndata:{\"sequence_number\":1,\"type\":\"response.in_progress\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"created_at\":1788837067,\"store\":true,\"tools\":[],\"output\":[],\"top_p\":1.0,\"completed_at\":1788837067,\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.7-plus\",\"service_tier\":\"default\",\"id\":\"resp_493607bf-baef-9ced-9e36-2e2a583b6177\",\"max_output_tokens\":4096,\"object\":\"response\",\"status\":\"in_progress\"}}\n\nid:3\nevent:response.output_item.added\n:HTTP_STATUS/200\ndata:{\"sequence_number\":2,\"item\":{\"id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"status\":\"in_progress\"},\"output_index\":0,\"type\":\"response.output_item.added\"}\n\nid:4\nevent:response.content_part.added\n:HTTP_STATUS/200\ndata:{\"sequence_number\":3,\"output_index\":0,\"type\":\"response.content_part.added\",\"content_index\":0,\"item_id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"part\":{\"type\":\"output_text\",\"annotations\":[],\"text\":\"\"}}\n\nid:5\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":4,\"content_index\":0,\"item_id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"delta\":\"3\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:6\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":5,\"content_index\":0,\"item_id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"delta\":\"7887\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:7\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":6,\"content_index\":0,\"item_id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"delta\":\"\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:8\nevent:response.output_text.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":7,\"content_index\":0,\"item_id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"text\":\"37887\",\"output_index\":0,\"type\":\"response.output_text.done\",\"logprobs\":[]}\n\nid:9\nevent:response.content_part.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":8,\"output_index\":0,\"type\":\"response.content_part.done\",\"content_index\":0,\"item_id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"part\":{\"type\":\"output_text\",\"annotations\":[],\"text\":\"37887\"}}\n\nid:10\nevent:response.output_item.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":9,\"item\":{\"id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"text\":\"37887\"}],\"status\":\"completed\"},\"output_index\":0,\"type\":\"response.output_item.done\"}\n\nid:11\nevent:response.completed\n:HTTP_STATUS/200\ndata:{\"sequence_number\":10,\"type\":\"response.completed\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"usage\":{\"total_tokens\":73,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens\":5,\"input_tokens\":68,\"output_tokens_details\":{\"reasoning_tokens\":0},\"x_details\":[{\"total_tokens\":73,\"x_billing_type\":\"response_api\",\"output_tokens\":5,\"input_tokens\":68,\"prompt_tokens_details\":{\"cached_tokens\":0}}]},\"created_at\":1788837067,\"store\":true,\"tools\":[],\"output\":[{\"id\":\"msg_509c6dec-e527-41b5-a9c9-7f02fecb7a3f\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"text\":\"37887\"}],\"status\":\"completed\"}],\"top_p\":1.0,\"completed_at\":1788837067,\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.7-plus\",\"service_tier\":\"default\",\"id\":\"resp_493607bf-baef-9ced-9e36-2e2a583b6177\",\"max_output_tokens\":4096,\"object\":\"response\",\"status\":\"completed\"}}\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/alibaba-responses/qwen-3-8-max-continues-a-stored-response.json

@@ -0,0 +1,53 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:alibaba-responses",
+      "provider:alibaba",
+      "protocol:alibaba-responses",
+      "region:ap-southeast-1",
+      "continuation",
+      "storage"
+    ],
+    "name": "alibaba-responses/qwen-3-8-max-continues-a-stored-response",
+    "recordedAt": "2026-09-08T03:12:42.429Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/responses",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"input\":[{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Remember the password word apricot. Reply OK.\"}]}],\"store\":true,\"reasoning\":{\"effort\":\"none\"},\"max_output_tokens\":1024,\"stream\":true}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=UTF-8"
+        },
+        "body": "id:1\nevent:response.created\n:HTTP_STATUS/200\ndata:{\"sequence_number\":0,\"type\":\"response.created\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"reasoning\":{\"effort\":\"none\"},\"created_at\":1788837161,\"store\":true,\"tools\":[],\"output\":[],\"top_p\":1.0,\"completed_at\":1788837161,\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.8-max\",\"service_tier\":\"default\",\"id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"max_output_tokens\":1024,\"object\":\"response\",\"status\":\"queued\"}}\n\nid:2\nevent:response.in_progress\n:HTTP_STATUS/200\ndata:{\"sequence_number\":1,\"type\":\"response.in_progress\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"reasoning\":{\"effort\":\"none\"},\"created_at\":1788837161,\"store\":true,\"tools\":[],\"output\":[],\"top_p\":1.0,\"completed_at\":1788837161,\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.8-max\",\"service_tier\":\"default\",\"id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"max_output_tokens\":1024,\"object\":\"response\",\"status\":\"in_progress\"}}\n\nid:3\nevent:response.output_item.added\n:HTTP_STATUS/200\ndata:{\"sequence_number\":2,\"item\":{\"id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"status\":\"in_progress\"},\"output_index\":0,\"type\":\"response.output_item.added\"}\n\nid:4\nevent:response.content_part.added\n:HTTP_STATUS/200\ndata:{\"sequence_number\":3,\"output_index\":0,\"type\":\"response.content_part.added\",\"content_index\":0,\"item_id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"part\":{\"type\":\"output_text\",\"annotations\":[],\"text\":\"\"}}\n\nid:5\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":4,\"content_index\":0,\"item_id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"delta\":\"OK\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:6\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":5,\"content_index\":0,\"item_id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"delta\":\".\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:7\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":6,\"content_index\":0,\"item_id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"delta\":\"\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:8\nevent:response.output_text.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":7,\"content_index\":0,\"item_id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"text\":\"OK.\",\"output_index\":0,\"type\":\"response.output_text.done\",\"logprobs\":[]}\n\nid:9\nevent:response.content_part.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":8,\"output_index\":0,\"type\":\"response.content_part.done\",\"content_index\":0,\"item_id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"part\":{\"type\":\"output_text\",\"annotations\":[],\"text\":\"OK.\"}}\n\nid:10\nevent:response.output_item.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":9,\"item\":{\"id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"text\":\"OK.\"}],\"status\":\"completed\"},\"output_index\":0,\"type\":\"response.output_item.done\"}\n\nid:11\nevent:response.completed\n:HTTP_STATUS/200\ndata:{\"sequence_number\":10,\"type\":\"response.completed\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"reasoning\":{\"effort\":\"none\"},\"usage\":{\"total_tokens\":60,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens\":2,\"input_tokens\":58,\"output_tokens_details\":{\"reasoning_tokens\":0},\"x_details\":[{\"total_tokens\":60,\"x_billing_type\":\"response_api\",\"output_tokens\":2,\"input_tokens\":58,\"prompt_tokens_details\":{\"cached_tokens\":0}}]},\"created_at\":1788837161,\"store\":true,\"tools\":[],\"output\":[{\"id\":\"msg_a908ad8e-6220-444b-880c-02aecbaf8fac\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"text\":\"OK.\"}],\"status\":\"completed\"}],\"top_p\":1.0,\"completed_at\":1788837161,\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.8-max\",\"service_tier\":\"default\",\"id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"max_output_tokens\":1024,\"object\":\"response\",\"status\":\"completed\"}}\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/responses",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"qwen3.8-max\",\"input\":[{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What word did I ask you to remember? Reply with only the word.\"}]}],\"store\":true,\"reasoning\":{\"effort\":\"none\"},\"max_output_tokens\":1024,\"previous_response_id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"stream\":true}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=UTF-8"
+        },
+        "body": "id:1\nevent:response.created\n:HTTP_STATUS/200\ndata:{\"sequence_number\":0,\"type\":\"response.created\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"reasoning\":{\"effort\":\"none\"},\"created_at\":1788837162,\"store\":true,\"tools\":[],\"output\":[],\"top_p\":1.0,\"completed_at\":1788837162,\"previous_response_id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.8-max\",\"service_tier\":\"default\",\"id\":\"resp_1d81d34c-d3ec-9f98-ab59-5d4641d4217a\",\"max_output_tokens\":1024,\"object\":\"response\",\"status\":\"queued\"}}\n\nid:2\nevent:response.in_progress\n:HTTP_STATUS/200\ndata:{\"sequence_number\":1,\"type\":\"response.in_progress\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"reasoning\":{\"effort\":\"none\"},\"created_at\":1788837162,\"store\":true,\"tools\":[],\"output\":[],\"top_p\":1.0,\"completed_at\":1788837162,\"previous_response_id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.8-max\",\"service_tier\":\"default\",\"id\":\"resp_1d81d34c-d3ec-9f98-ab59-5d4641d4217a\",\"max_output_tokens\":1024,\"object\":\"response\",\"status\":\"in_progress\"}}\n\nid:3\nevent:response.output_item.added\n:HTTP_STATUS/200\ndata:{\"sequence_number\":2,\"item\":{\"id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"status\":\"in_progress\"},\"output_index\":0,\"type\":\"response.output_item.added\"}\n\nid:4\nevent:response.content_part.added\n:HTTP_STATUS/200\ndata:{\"sequence_number\":3,\"output_index\":0,\"type\":\"response.content_part.added\",\"content_index\":0,\"item_id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"part\":{\"type\":\"output_text\",\"annotations\":[],\"text\":\"\"}}\n\nid:5\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":4,\"content_index\":0,\"item_id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"delta\":\"ap\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:6\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":5,\"content_index\":0,\"item_id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"delta\":\"ricot\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:7\nevent:response.output_text.delta\n:HTTP_STATUS/200\ndata:{\"sequence_number\":6,\"content_index\":0,\"item_id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"delta\":\"\",\"output_index\":0,\"type\":\"response.output_text.delta\",\"logprobs\":[]}\n\nid:8\nevent:response.output_text.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":7,\"content_index\":0,\"item_id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"text\":\"apricot\",\"output_index\":0,\"type\":\"response.output_text.done\",\"logprobs\":[]}\n\nid:9\nevent:response.content_part.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":8,\"output_index\":0,\"type\":\"response.content_part.done\",\"content_index\":0,\"item_id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"part\":{\"type\":\"output_text\",\"annotations\":[],\"text\":\"apricot\"}}\n\nid:10\nevent:response.output_item.done\n:HTTP_STATUS/200\ndata:{\"sequence_number\":9,\"item\":{\"id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"text\":\"apricot\"}],\"status\":\"completed\"},\"output_index\":0,\"type\":\"response.output_item.done\"}\n\nid:11\nevent:response.completed\n:HTTP_STATUS/200\ndata:{\"sequence_number\":10,\"type\":\"response.completed\",\"response\":{\"top_logprobs\":0,\"metadata\":{},\"presence_penalty\":0.0,\"reasoning\":{\"effort\":\"none\"},\"usage\":{\"total_tokens\":92,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens\":3,\"input_tokens\":89,\"output_tokens_details\":{\"reasoning_tokens\":0},\"x_details\":[{\"total_tokens\":92,\"x_billing_type\":\"response_api\",\"output_tokens\":3,\"input_tokens\":89,\"prompt_tokens_details\":{\"cached_tokens\":0}}]},\"created_at\":1788837162,\"store\":true,\"tools\":[],\"output\":[{\"id\":\"msg_7bc50c33-8fbd-4b10-91fc-4f2533bb2091\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"text\":\"apricot\"}],\"status\":\"completed\"}],\"top_p\":1.0,\"completed_at\":1788837162,\"previous_response_id\":\"resp_97f8cd28-c7ab-9d51-9c14-4fc531decdc8\",\"frequency_penalty\":0.0,\"parallel_tool_calls\":true,\"background\":false,\"temperature\":1.0,\"tool_choice\":\"auto\",\"model\":\"qwen3.8-max\",\"service_tier\":\"default\",\"id\":\"resp_1d81d34c-d3ec-9f98-ab59-5d4641d4217a\",\"max_output_tokens\":1024,\"object\":\"response\",\"status\":\"completed\"}}\n\n"
+      }
+    }
+  ]
+}