@daniel156161/prism 0.2.100 → 0.2.105

package/node_modules/@earendil-works/pi-agent-core/dist/types.js.map

@@ -1 +1 @@
-{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"","sourcesContent":["import type {\n\tApi,\n\tAssistantMessage,\n\tAssistantMessageEvent,\n\tAssistantMessageEventStream,\n\tContext,\n\tImageContent,\n\tMessage,\n\tModel,\n\tSimpleStreamOptions,\n\tTextContent,\n\tTool,\n\tToolResultMessage,\n\tUsage,\n} from \"@earendil-works/pi-ai\";\nimport type { Static, TSchema } from \"typebox\";\n\n/**\n * Stream function used by the agent loop. `Models.streamSimple` satisfies\n * this shape.\n *\n * Contract:\n * - Must not throw or return a rejected promise for request/model/runtime failures.\n * - Must return an AssistantMessageEventStream.\n * - Failures must be encoded in the returned stream via protocol events and a\n *   final AssistantMessage with stopReason \"error\" or \"aborted\" and errorMessage.\n */\nexport type StreamFn = (\n\tmodel: Model<Api>,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n) => AssistantMessageEventStream | Promise<AssistantMessageEventStream>;\n\n/**\n * Configuration for how tool calls from a single assistant message are executed.\n *\n * - \"sequential\": each tool call is prepared, executed, and finalized before the next one starts.\n * - \"parallel\": tool calls are prepared sequentially, then allowed tools execute concurrently.\n *   `tool_execution_end` is emitted in tool completion order after each tool is finalized,\n *   while tool-result message artifacts are emitted later in assistant source order.\n */\nexport type ToolExecutionMode = \"sequential\" | \"parallel\";\n\n/**\n * Controls how many queued user messages are injected when the agent loop reaches a queue drain point.\n *\n * - \"all\": drain and inject every queued message at that point.\n * - \"one-at-a-time\": drain and inject only the oldest queued message, leaving the rest queued for later drain points.\n */\nexport type QueueMode = \"all\" | \"one-at-a-time\";\n\n/** A single tool call content block emitted by an assistant message. */\nexport type AgentToolCall = Extract<AssistantMessage[\"content\"][number], { type: \"toolCall\" }>;\n\n/**\n * Result returned from `beforeToolCall`.\n *\n * Returning `{ block: true }` prevents the tool from executing. The loop emits an error tool result instead.\n * `reason` becomes the text shown in that error result. If omitted, a default blocked message is used.\n */\nexport interface BeforeToolCallResult {\n\tblock?: boolean;\n\treason?: string;\n\t/**\n\t * Hint that the agent should stop after the current tool batch when this call is blocked.\n\t * Early termination only happens when every finalized tool result in the batch sets this to true.\n\t */\n\tterminate?: boolean;\n}\n\n/**\n * Partial override returned from `afterToolCall`.\n *\n * Merge semantics are field-by-field:\n * - `content`: if provided, replaces the tool result content array in full\n * - `details`: if provided, replaces the tool result details value in full\n * - `isError`: if provided, replaces the tool result error flag\n * - `usage`: if provided, replaces the tool result usage\n * - `terminate`: if provided, replaces the early-termination hint\n *\n * Omitted fields keep the original executed tool result values.\n * There is no deep merge for `content`, `details`, or `usage`.\n */\nexport interface AfterToolCallResult {\n\tcontent?: (TextContent | ImageContent)[];\n\tdetails?: unknown;\n\tisError?: boolean;\n\t/** Usage from the final tool execution itself, if available. Not used for main LLM context accounting. */\n\tusage?: Usage;\n\t/**\n\t * Hint that the agent should stop after the current tool batch.\n\t * Early termination only happens when every finalized tool result in the batch sets this to true.\n\t */\n\tterminate?: boolean;\n}\n\n/** Context passed to `beforeToolCall`. */\nexport interface BeforeToolCallContext {\n\t/** The assistant message that requested the tool call. */\n\tassistantMessage: AssistantMessage;\n\t/** The raw tool call block from `assistantMessage.content`. */\n\ttoolCall: AgentToolCall;\n\t/** Validated tool arguments for the target tool schema. */\n\targs: unknown;\n\t/** Current agent context at the time the tool call is prepared. */\n\tcontext: AgentContext;\n}\n\n/** Context passed to `afterToolCall`. */\nexport interface AfterToolCallContext {\n\t/** The assistant message that requested the tool call. */\n\tassistantMessage: AssistantMessage;\n\t/** The raw tool call block from `assistantMessage.content`. */\n\ttoolCall: AgentToolCall;\n\t/** Validated tool arguments for the target tool schema. */\n\targs: unknown;\n\t/** The executed tool result before any `afterToolCall` overrides are applied. */\n\tresult: AgentToolResult<any>;\n\t/** Whether the executed tool result is currently treated as an error. */\n\tisError: boolean;\n\t/** Current agent context at the time the tool call is finalized. */\n\tcontext: AgentContext;\n}\n\n/** Context passed to `shouldStopAfterTurn`. */\nexport interface ShouldStopAfterTurnContext {\n\t/** The assistant message that completed the turn. */\n\tmessage: AssistantMessage;\n\t/** Tool result messages passed to the preceding `turn_end` event. */\n\ttoolResults: ToolResultMessage[];\n\t/** Current agent context after the turn's assistant message and tool results have been appended. */\n\tcontext: AgentContext;\n\t/** Messages that this loop invocation will return if it exits at this point. Prompt runs include the initial prompt messages; continuation runs do not include pre-existing context messages. */\n\tnewMessages: AgentMessage[];\n}\n\n/** Replacement runtime state used by the agent loop before starting another provider request. */\nexport interface AgentLoopTurnUpdate {\n\t/** Context for the next provider request. */\n\tcontext?: AgentContext;\n\t/** Model for the next provider request. */\n\tmodel?: Model<any>;\n\t/** Thinking level for the next provider request. */\n\tthinkingLevel?: ThinkingLevel;\n}\n\nexport interface PrepareNextTurnContext extends ShouldStopAfterTurnContext {}\n\nexport interface AgentLoopConfig extends SimpleStreamOptions {\n\tmodel: Model<any>;\n\n\t/**\n\t * Converts AgentMessage[] to LLM-compatible Message[] before each LLM call.\n\t *\n\t * Each AgentMessage must be converted to a UserMessage, AssistantMessage, or ToolResultMessage\n\t * that the LLM can understand. AgentMessages that cannot be converted (e.g., UI-only notifications,\n\t * status messages) should be filtered out.\n\t *\n\t * Contract: must not throw or reject. Return a safe fallback value instead.\n\t * Throwing interrupts the low-level agent loop without producing a normal event sequence.\n\t *\n\t * @example\n\t * ```typescript\n\t * convertToLlm: (messages) => messages.flatMap(m => {\n\t *   if (m.role === \"custom\") {\n\t *     // Convert custom message to user message\n\t *     return [{ role: \"user\", content: m.content, timestamp: m.timestamp }];\n\t *   }\n\t *   if (m.role === \"notification\") {\n\t *     // Filter out UI-only messages\n\t *     return [];\n\t *   }\n\t *   // Pass through standard LLM messages\n\t *   return [m];\n\t * })\n\t * ```\n\t */\n\tconvertToLlm: (messages: AgentMessage[]) => Message[] | Promise<Message[]>;\n\n\t/**\n\t * Optional transform applied to the context before `convertToLlm`.\n\t *\n\t * Use this for operations that work at the AgentMessage level:\n\t * - Context window management (pruning old messages)\n\t * - Injecting context from external sources\n\t *\n\t * Contract: must not throw or reject. Return the original messages or another\n\t * safe fallback value instead.\n\t *\n\t * @example\n\t * ```typescript\n\t * transformContext: async (messages) => {\n\t *   if (estimateTokens(messages) > MAX_TOKENS) {\n\t *     return pruneOldMessages(messages);\n\t *   }\n\t *   return messages;\n\t * }\n\t * ```\n\t */\n\ttransformContext?: (messages: AgentMessage[], signal?: AbortSignal) => Promise<AgentMessage[]>;\n\n\t/**\n\t * Resolves an API key dynamically for each LLM call.\n\t *\n\t * Useful for short-lived OAuth tokens (e.g., GitHub Copilot) that may expire\n\t * during long-running tool execution phases.\n\t *\n\t * Contract: must not throw or reject. Return undefined when no key is available.\n\t */\n\tgetApiKey?: (provider: string) => Promise<string | undefined> | string | undefined;\n\n\t/**\n\t * Called after each turn fully completes and `turn_end` has been emitted.\n\t *\n\t * If it returns true, the loop emits `agent_end` and exits before polling steering or follow-up queues,\n\t * without starting another LLM call. The current assistant response and any tool executions finish normally.\n\t *\n\t * Use this to request a graceful stop after the current turn, e.g. before context gets too full.\n\t *\n\t * Contract: must not throw or reject. Throwing interrupts the low-level agent loop without producing a normal event sequence.\n\t */\n\tshouldStopAfterTurn?: (context: ShouldStopAfterTurnContext) => boolean | Promise<boolean>;\n\n\t/**\n\t * Called after `turn_end` and before the loop decides whether another provider request should start.\n\t * Return replacement context/model/thinking state to affect the next turn in this run.\n\t * Return undefined to keep using the current context/config.\n\t */\n\tprepareNextTurn?: (\n\t\tcontext: PrepareNextTurnContext,\n\t) => AgentLoopTurnUpdate | undefined | Promise<AgentLoopTurnUpdate | undefined>;\n\n\t/**\n\t * Returns steering messages to inject into the conversation mid-run.\n\t *\n\t * Called after the current assistant turn finishes executing its tool calls, unless `shouldStopAfterTurn` exits first.\n\t * If messages are returned, they are added to the context before the next LLM call.\n\t * Tool calls from the current assistant message are not skipped.\n\t *\n\t * Use this for \"steering\" the agent while it's working.\n\t *\n\t * Contract: must not throw or reject. Return [] when no steering messages are available.\n\t */\n\tgetSteeringMessages?: () => Promise<AgentMessage[]>;\n\n\t/**\n\t * Returns follow-up messages to process after the agent would otherwise stop.\n\t *\n\t * Called when the agent has no more tool calls and no steering messages.\n\t * If messages are returned, they're added to the context and the agent\n\t * continues with another turn.\n\t *\n\t * Use this for follow-up messages that should wait until the agent finishes.\n\t *\n\t * Contract: must not throw or reject. Return [] when no follow-up messages are available.\n\t */\n\tgetFollowUpMessages?: () => Promise<AgentMessage[]>;\n\n\t/**\n\t * Tool execution mode.\n\t * - \"sequential\": execute tool calls one by one\n\t * - \"parallel\": preflight tool calls sequentially, then execute allowed tools concurrently;\n\t *   emit `tool_execution_end` in tool completion order after each tool is finalized,\n\t *   then emit tool-result message artifacts later in assistant source order\n\t *\n\t * Default: \"parallel\"\n\t */\n\ttoolExecution?: ToolExecutionMode;\n\n\t/**\n\t * Called before a tool is executed, after arguments have been validated.\n\t *\n\t * Return `{ block: true }` to prevent execution. The loop emits an error tool result instead.\n\t * A blocked result can also set `terminate: true` to participate in the batch early-termination rule.\n\t * The hook receives the agent abort signal and is responsible for honoring it.\n\t */\n\tbeforeToolCall?: (context: BeforeToolCallContext, signal?: AbortSignal) => Promise<BeforeToolCallResult | undefined>;\n\n\t/**\n\t * Called after a tool finishes executing, before `tool_execution_end` and tool-result message events are emitted.\n\t *\n\t * Return an `AfterToolCallResult` to override parts of the executed tool result:\n\t * - `content` replaces the full content array\n\t * - `details` replaces the full details payload\n\t * - `isError` replaces the error flag\n\t * - `usage` replaces the tool result usage\n\t * - `terminate` replaces the early-termination hint\n\t *\n\t * Any omitted fields keep their original values. No deep merge is performed.\n\t * The hook receives the agent abort signal and is responsible for honoring it.\n\t */\n\tafterToolCall?: (context: AfterToolCallContext, signal?: AbortSignal) => Promise<AfterToolCallResult | undefined>;\n}\n\n/**\n * Thinking/reasoning level for models that support it.\n * Note: \"xhigh\" and \"max\" are only supported by selected model families. Use model\n * thinking-level metadata from @earendil-works/pi-ai to detect support for a concrete model.\n */\nexport type ThinkingLevel = \"off\" | \"minimal\" | \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\";\n\n/**\n * Extensible interface for custom app messages.\n * Apps can extend via declaration merging:\n *\n * @example\n * ```typescript\n * declare module \"@mariozechner/agent\" {\n *   interface CustomAgentMessages {\n *     artifact: ArtifactMessage;\n *     notification: NotificationMessage;\n *   }\n * }\n * ```\n */\nexport interface CustomAgentMessages {\n\t// Empty by default - apps extend via declaration merging\n}\n\n/**\n * AgentMessage: Union of LLM messages + custom messages.\n * This abstraction allows apps to add custom message types while maintaining\n * type safety and compatibility with the base LLM messages.\n */\nexport type AgentMessage = Message | CustomAgentMessages[keyof CustomAgentMessages];\n\n/**\n * Public agent state.\n *\n * `tools` and `messages` use accessor properties so implementations can copy\n * assigned arrays before storing them.\n */\nexport interface AgentState {\n\t/** System prompt sent with each model request. */\n\tsystemPrompt: string;\n\t/** Active model used for future turns. */\n\tmodel: Model<any>;\n\t/** Requested reasoning level for future turns. */\n\tthinkingLevel: ThinkingLevel;\n\t/** Available tools. Assigning a new array copies the top-level array. */\n\tset tools(tools: AgentTool<any>[]);\n\tget tools(): AgentTool<any>[];\n\t/** Conversation transcript. Assigning a new array copies the top-level array. */\n\tset messages(messages: AgentMessage[]);\n\tget messages(): AgentMessage[];\n\t/**\n\t * True while the agent is processing a prompt or continuation.\n\t *\n\t * This remains true until awaited `agent_end` listeners settle.\n\t */\n\treadonly isStreaming: boolean;\n\t/** Partial assistant message for the current streamed response, if any. */\n\treadonly streamingMessage?: AgentMessage;\n\t/** Tool call ids currently executing. */\n\treadonly pendingToolCalls: ReadonlySet<string>;\n\t/** Error message from the most recent failed or aborted assistant turn, if any. */\n\treadonly errorMessage?: string;\n}\n\n/** Final or partial result produced by a tool. */\nexport interface AgentToolResult<T> {\n\t/** Text or image content returned to the model. */\n\tcontent: (TextContent | ImageContent)[];\n\t/** Arbitrary structured details for logs or UI rendering. */\n\tdetails: T;\n\t/** Usage from the final tool execution itself, if available. Not used for main LLM context accounting. */\n\tusage?: Usage;\n\t/** Names of tools introduced by this result and available from this transcript point onward. */\n\taddedToolNames?: string[];\n\t/**\n\t * Hint that the agent should stop after the current tool batch.\n\t * Early termination only happens when every finalized tool result in the batch sets this to true.\n\t */\n\tterminate?: boolean;\n}\n\n/**\n * Callback used by tools to stream partial execution updates.\n *\n * The callback is scoped to the current `execute()` invocation. Calls made after\n * the tool promise settles are ignored.\n */\nexport type AgentToolUpdateCallback<T = any> = (partialResult: AgentToolResult<T>) => void;\n\n/** Tool definition used by the agent runtime. */\nexport interface AgentTool<TParameters extends TSchema = TSchema, TDetails = any> extends Tool<TParameters> {\n\t/** Human-readable label for UI display. */\n\tlabel: string;\n\t/**\n\t * Optional compatibility shim for raw tool-call arguments before schema validation.\n\t * Must return an object that matches `TParameters`.\n\t */\n\tprepareArguments?: (args: unknown) => Static<TParameters>;\n\t/** Execute the tool call. Throw on failure instead of encoding errors in `content`. */\n\texecute: (\n\t\ttoolCallId: string,\n\t\tparams: Static<TParameters>,\n\t\tsignal?: AbortSignal,\n\t\tonUpdate?: AgentToolUpdateCallback<TDetails>,\n\t) => Promise<AgentToolResult<TDetails>>;\n\t/**\n\t * Per-tool execution mode override.\n\t * - \"sequential\": this tool must execute one at a time with other tool calls.\n\t * - \"parallel\": this tool can execute concurrently with other tool calls.\n\t *\n\t * If omitted, the default execution mode applies.\n\t */\n\texecutionMode?: ToolExecutionMode;\n}\n\n/** Context snapshot passed into the low-level agent loop. */\nexport interface AgentContext {\n\t/** System prompt included with the request. */\n\tsystemPrompt: string;\n\t/** Transcript visible to the model. */\n\tmessages: AgentMessage[];\n\t/** Tools available for this run. */\n\ttools?: AgentTool<any>[];\n}\n\n/**\n * Events emitted by the Agent for UI updates.\n *\n * `agent_end` is the last event emitted for a run, but awaited `Agent.subscribe()`\n * listeners for that event are still part of run settlement. The agent becomes\n * idle only after those listeners finish.\n */\nexport type AgentEvent =\n\t// Agent lifecycle\n\t| { type: \"agent_start\" }\n\t| { type: \"agent_end\"; messages: AgentMessage[] }\n\t// Turn lifecycle - a turn is one assistant response + any tool calls/results\n\t| { type: \"turn_start\" }\n\t| { type: \"turn_end\"; message: AgentMessage; toolResults: ToolResultMessage[] }\n\t// Message lifecycle - emitted for user, assistant, and toolResult messages\n\t| { type: \"message_start\"; message: AgentMessage }\n\t// Only emitted for assistant messages during streaming\n\t| { type: \"message_update\"; message: AgentMessage; assistantMessageEvent: AssistantMessageEvent }\n\t| { type: \"message_end\"; message: AgentMessage }\n\t// Tool execution lifecycle\n\t| { type: \"tool_execution_start\"; toolCallId: string; toolName: string; args: any }\n\t| { type: \"tool_execution_update\"; toolCallId: string; toolName: string; args: any; partialResult: any }\n\t| { type: \"tool_execution_end\"; toolCallId: string; toolName: string; result: any; isError: boolean };\n"]}
+{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"","sourcesContent":["import type {\n\tApi,\n\tAssistantMessage,\n\tAssistantMessageEvent,\n\tAssistantMessageEventStream,\n\tContext,\n\tImageContent,\n\tMessage,\n\tModel,\n\tSimpleStreamOptions,\n\tTextContent,\n\tTool,\n\tToolResultMessage,\n\tUsage,\n} from \"@earendil-works/pi-ai\";\nimport type { Static, TSchema } from \"typebox\";\n\n/**\n * Stream function used by the agent loop. `Models.streamSimple` satisfies\n * this shape.\n *\n * Contract:\n * - Must not throw or return a rejected promise for request/model/runtime failures.\n * - Must return an AssistantMessageEventStream.\n * - Failures must be encoded in the returned stream via protocol events and a\n *   final AssistantMessage with stopReason \"error\" or \"aborted\" and errorMessage.\n */\nexport type StreamFn = (\n\tmodel: Model<Api>,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n) => AssistantMessageEventStream | Promise<AssistantMessageEventStream>;\n\n/**\n * Configuration for how tool calls from a single assistant message are executed.\n *\n * - \"sequential\": each tool call is prepared, executed, and finalized before the next one starts.\n * - \"parallel\": tool calls are prepared sequentially, then allowed tools execute concurrently.\n *   `tool_execution_end` is emitted in tool completion order after each tool is finalized,\n *   while tool-result message artifacts are emitted later in assistant source order.\n */\nexport type ToolExecutionMode = \"sequential\" | \"parallel\";\n\n/**\n * Controls how many queued user messages are injected when the agent loop reaches a queue drain point.\n *\n * - \"all\": drain and inject every queued message at that point.\n * - \"one-at-a-time\": drain and inject only the oldest queued message, leaving the rest queued for later drain points.\n */\nexport type QueueMode = \"all\" | \"one-at-a-time\";\n\n/** A single tool call content block emitted by an assistant message. */\nexport type AgentToolCall = Extract<AssistantMessage[\"content\"][number], { type: \"toolCall\" }>;\n\n/**\n * Result returned from `beforeToolCall`.\n *\n * Returning `{ block: true }` prevents the tool from executing. The loop emits an error tool result instead.\n * `reason` becomes the text shown in that error result. If omitted, a default blocked message is used.\n */\nexport interface BeforeToolCallResult {\n\tblock?: boolean;\n\treason?: string;\n\t/**\n\t * Hint that the agent should stop after the current tool batch when this call is blocked.\n\t * Early termination only happens when every finalized tool result in the batch sets this to true.\n\t */\n\tterminate?: boolean;\n}\n\n/**\n * Partial override returned from `afterToolCall`.\n *\n * Merge semantics are field-by-field:\n * - `content`: if provided, replaces the tool result content array in full\n * - `details`: if provided, replaces the tool result details value in full\n * - `isError`: if provided, replaces the tool result error flag\n * - `usage`: if provided, replaces the tool result usage\n * - `terminate`: if provided, replaces the early-termination hint\n *\n * Omitted fields keep the original executed tool result values.\n * There is no deep merge for `content`, `details`, or `usage`.\n */\nexport interface AfterToolCallResult {\n\tcontent?: (TextContent | ImageContent)[];\n\tdetails?: unknown;\n\tisError?: boolean;\n\t/** Usage from the final tool execution itself, if available. Not used for main LLM context accounting. */\n\tusage?: Usage;\n\t/**\n\t * Hint that the agent should stop after the current tool batch.\n\t * Early termination only happens when every finalized tool result in the batch sets this to true.\n\t */\n\tterminate?: boolean;\n}\n\n/** Context passed to `beforeToolCall`. */\nexport interface BeforeToolCallContext {\n\t/** The assistant message that requested the tool call. */\n\tassistantMessage: AssistantMessage;\n\t/** The raw tool call block from `assistantMessage.content`. */\n\ttoolCall: AgentToolCall;\n\t/** Validated tool arguments for the target tool schema. */\n\targs: unknown;\n\t/** Current agent context at the time the tool call is prepared. */\n\tcontext: AgentContext;\n}\n\n/** Context passed to `afterToolCall`. */\nexport interface AfterToolCallContext {\n\t/** The assistant message that requested the tool call. */\n\tassistantMessage: AssistantMessage;\n\t/** The raw tool call block from `assistantMessage.content`. */\n\ttoolCall: AgentToolCall;\n\t/** Validated tool arguments for the target tool schema. */\n\targs: unknown;\n\t/** The executed tool result before any `afterToolCall` overrides are applied. */\n\tresult: AgentToolResult<any>;\n\t/** Whether the executed tool result is currently treated as an error. */\n\tisError: boolean;\n\t/** Current agent context at the time the tool call is finalized. */\n\tcontext: AgentContext;\n}\n\n/** Context passed to `shouldStopAfterTurn`. */\nexport interface ShouldStopAfterTurnContext {\n\t/** The assistant message that completed the turn. */\n\tmessage: AssistantMessage;\n\t/** Tool result messages passed to the preceding `turn_end` event. */\n\ttoolResults: ToolResultMessage[];\n\t/** Current agent context after the turn's assistant message and tool results have been appended. */\n\tcontext: AgentContext;\n\t/** Messages that this loop invocation will return if it exits at this point. Prompt runs include the initial prompt messages; continuation runs do not include pre-existing context messages. */\n\tnewMessages: AgentMessage[];\n}\n\n/** Replacement runtime state used by the agent loop before starting another provider request. */\nexport interface AgentLoopTurnUpdate {\n\t/** Context for the next provider request. */\n\tcontext?: AgentContext;\n\t/** Model for the next provider request. */\n\tmodel?: Model<any>;\n\t/** Thinking level for the next provider request. */\n\tthinkingLevel?: ThinkingLevel;\n}\n\nexport interface PrepareNextTurnContext extends ShouldStopAfterTurnContext {}\n\nexport interface AgentLoopConfig extends SimpleStreamOptions {\n\tmodel: Model<any>;\n\n\t/**\n\t * Converts AgentMessage[] to LLM-compatible Message[] before each LLM call.\n\t *\n\t * Each AgentMessage must be converted to a UserMessage, AssistantMessage, or ToolResultMessage\n\t * that the LLM can understand. AgentMessages that cannot be converted (e.g., UI-only notifications,\n\t * status messages) should be filtered out.\n\t *\n\t * Contract: must not throw or reject. Return a safe fallback value instead.\n\t * Throwing interrupts the low-level agent loop without producing a normal event sequence.\n\t *\n\t * @example\n\t * ```typescript\n\t * convertToLlm: (messages) => messages.flatMap(m => {\n\t *   if (m.role === \"custom\") {\n\t *     // Convert custom message to user message\n\t *     return [{ role: \"user\", content: m.content, timestamp: m.timestamp }];\n\t *   }\n\t *   if (m.role === \"notification\") {\n\t *     // Filter out UI-only messages\n\t *     return [];\n\t *   }\n\t *   // Pass through standard LLM messages\n\t *   return [m];\n\t * })\n\t * ```\n\t */\n\tconvertToLlm: (messages: AgentMessage[]) => Message[] | Promise<Message[]>;\n\n\t/**\n\t * Optional transform applied to the context before `convertToLlm`.\n\t *\n\t * Use this for operations that work at the AgentMessage level:\n\t * - Context window management (pruning old messages)\n\t * - Injecting context from external sources\n\t *\n\t * Contract: must not throw or reject. Return the original messages or another\n\t * safe fallback value instead.\n\t *\n\t * @example\n\t * ```typescript\n\t * transformContext: async (messages) => {\n\t *   if (estimateTokens(messages) > MAX_TOKENS) {\n\t *     return pruneOldMessages(messages);\n\t *   }\n\t *   return messages;\n\t * }\n\t * ```\n\t */\n\ttransformContext?: (messages: AgentMessage[], signal?: AbortSignal) => Promise<AgentMessage[]>;\n\n\t/**\n\t * Resolves an API key dynamically for each LLM call.\n\t *\n\t * Useful for short-lived OAuth tokens (e.g., GitHub Copilot) that may expire\n\t * during long-running tool execution phases.\n\t *\n\t * Contract: must not throw or reject. Return undefined when no key is available.\n\t */\n\tgetApiKey?: (provider: string) => Promise<string | undefined> | string | undefined;\n\n\t/**\n\t * Called after each turn fully completes and `turn_end` has been emitted.\n\t *\n\t * If it returns true, the loop emits `agent_end` and exits before polling steering or follow-up queues,\n\t * without starting another LLM call. The current assistant response and any tool executions finish normally.\n\t * This callback sees the completed-turn context and runs before `prepareNextTurn`.\n\t *\n\t * Use this to request a graceful stop after the current turn, e.g. before context gets too full.\n\t *\n\t * Contract: must not throw or reject. Throwing interrupts the low-level agent loop without producing a normal event sequence.\n\t */\n\tshouldStopAfterTurn?: (context: ShouldStopAfterTurnContext) => boolean | Promise<boolean>;\n\n\t/**\n\t * Called after `turn_end` when the loop will continue, immediately before the next turn starts.\n\t * Return replacement context/model/thinking state to affect that turn.\n\t * Return undefined to keep using the current context/config.\n\t */\n\tprepareNextTurn?: (\n\t\tcontext: PrepareNextTurnContext,\n\t) => AgentLoopTurnUpdate | undefined | Promise<AgentLoopTurnUpdate | undefined>;\n\n\t/**\n\t * Returns steering messages to inject into the conversation mid-run.\n\t *\n\t * Called after the current assistant turn finishes executing its tool calls, unless `shouldStopAfterTurn` exits first.\n\t * If messages are returned, they are added to the context before the next LLM call.\n\t * Tool calls from the current assistant message are not skipped.\n\t *\n\t * Use this for \"steering\" the agent while it's working.\n\t *\n\t * Contract: must not throw or reject. Return [] when no steering messages are available.\n\t */\n\tgetSteeringMessages?: () => Promise<AgentMessage[]>;\n\n\t/**\n\t * Returns follow-up messages to process after the agent would otherwise stop.\n\t *\n\t * Called when the agent has no more tool calls and no steering messages.\n\t * If messages are returned, they're added to the context and the agent\n\t * continues with another turn.\n\t *\n\t * Use this for follow-up messages that should wait until the agent finishes.\n\t *\n\t * Contract: must not throw or reject. Return [] when no follow-up messages are available.\n\t */\n\tgetFollowUpMessages?: () => Promise<AgentMessage[]>;\n\n\t/**\n\t * Tool execution mode.\n\t * - \"sequential\": execute tool calls one by one\n\t * - \"parallel\": preflight tool calls sequentially, then execute allowed tools concurrently;\n\t *   emit `tool_execution_end` in tool completion order after each tool is finalized,\n\t *   then emit tool-result message artifacts later in assistant source order\n\t *\n\t * Default: \"parallel\"\n\t */\n\ttoolExecution?: ToolExecutionMode;\n\n\t/**\n\t * Called before a tool is executed, after arguments have been validated.\n\t *\n\t * Return `{ block: true }` to prevent execution. The loop emits an error tool result instead.\n\t * A blocked result can also set `terminate: true` to participate in the batch early-termination rule.\n\t * The hook receives the agent abort signal and is responsible for honoring it.\n\t */\n\tbeforeToolCall?: (context: BeforeToolCallContext, signal?: AbortSignal) => Promise<BeforeToolCallResult | undefined>;\n\n\t/**\n\t * Called after a tool finishes executing, before `tool_execution_end` and tool-result message events are emitted.\n\t *\n\t * Return an `AfterToolCallResult` to override parts of the executed tool result:\n\t * - `content` replaces the full content array\n\t * - `details` replaces the full details payload\n\t * - `isError` replaces the error flag\n\t * - `usage` replaces the tool result usage\n\t * - `terminate` replaces the early-termination hint\n\t *\n\t * Any omitted fields keep their original values. No deep merge is performed.\n\t * The hook receives the agent abort signal and is responsible for honoring it.\n\t */\n\tafterToolCall?: (context: AfterToolCallContext, signal?: AbortSignal) => Promise<AfterToolCallResult | undefined>;\n}\n\n/**\n * Thinking/reasoning level for models that support it.\n * Note: \"xhigh\" and \"max\" are only supported by selected model families. Use model\n * thinking-level metadata from @earendil-works/pi-ai to detect support for a concrete model.\n */\nexport type ThinkingLevel = \"off\" | \"minimal\" | \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\";\n\n/**\n * Extensible interface for custom app messages.\n * Apps can extend via declaration merging:\n *\n * @example\n * ```typescript\n * declare module \"@mariozechner/agent\" {\n *   interface CustomAgentMessages {\n *     artifact: ArtifactMessage;\n *     notification: NotificationMessage;\n *   }\n * }\n * ```\n */\nexport interface CustomAgentMessages {\n\t// Empty by default - apps extend via declaration merging\n}\n\n/**\n * AgentMessage: Union of LLM messages + custom messages.\n * This abstraction allows apps to add custom message types while maintaining\n * type safety and compatibility with the base LLM messages.\n */\nexport type AgentMessage = Message | CustomAgentMessages[keyof CustomAgentMessages];\n\n/**\n * Public agent state.\n *\n * `tools` and `messages` use accessor properties so implementations can copy\n * assigned arrays before storing them.\n */\nexport interface AgentState {\n\t/** System prompt sent with each model request. */\n\tsystemPrompt: string;\n\t/** Active model used for future turns. */\n\tmodel: Model<any>;\n\t/** Requested reasoning level for future turns. */\n\tthinkingLevel: ThinkingLevel;\n\t/** Available tools. Assigning a new array copies the top-level array. */\n\tset tools(tools: AgentTool<any>[]);\n\tget tools(): AgentTool<any>[];\n\t/** Conversation transcript. Assigning a new array copies the top-level array. */\n\tset messages(messages: AgentMessage[]);\n\tget messages(): AgentMessage[];\n\t/**\n\t * True while the agent is processing a prompt or continuation.\n\t *\n\t * This remains true until awaited `agent_end` listeners settle.\n\t */\n\treadonly isStreaming: boolean;\n\t/** Partial assistant message for the current streamed response, if any. */\n\treadonly streamingMessage?: AgentMessage;\n\t/** Tool call ids currently executing. */\n\treadonly pendingToolCalls: ReadonlySet<string>;\n\t/** Error message from the most recent failed or aborted assistant turn, if any. */\n\treadonly errorMessage?: string;\n}\n\n/** Final or partial result produced by a tool. */\nexport interface AgentToolResult<T> {\n\t/** Text or image content returned to the model. */\n\tcontent: (TextContent | ImageContent)[];\n\t/** Arbitrary structured details for logs or UI rendering. */\n\tdetails: T;\n\t/** Usage from the final tool execution itself, if available. Not used for main LLM context accounting. */\n\tusage?: Usage;\n\t/** Names of tools introduced by this result and available from this transcript point onward. */\n\taddedToolNames?: string[];\n\t/**\n\t * Hint that the agent should stop after the current tool batch.\n\t * Early termination only happens when every finalized tool result in the batch sets this to true.\n\t */\n\tterminate?: boolean;\n}\n\n/**\n * Callback used by tools to stream partial execution updates.\n *\n * The callback is scoped to the current `execute()` invocation. Calls made after\n * the tool promise settles are ignored.\n */\nexport type AgentToolUpdateCallback<T = any> = (partialResult: AgentToolResult<T>) => void;\n\n/** Tool definition used by the agent runtime. */\nexport interface AgentTool<TParameters extends TSchema = TSchema, TDetails = any> extends Tool<TParameters> {\n\t/** Human-readable label for UI display. */\n\tlabel: string;\n\t/**\n\t * Optional compatibility shim for raw tool-call arguments before schema validation.\n\t * Must return an object that matches `TParameters`.\n\t */\n\tprepareArguments?: (args: unknown) => Static<TParameters>;\n\t/** Execute the tool call. Throw on failure instead of encoding errors in `content`. */\n\texecute: (\n\t\ttoolCallId: string,\n\t\tparams: Static<TParameters>,\n\t\tsignal?: AbortSignal,\n\t\tonUpdate?: AgentToolUpdateCallback<TDetails>,\n\t) => Promise<AgentToolResult<TDetails>>;\n\t/**\n\t * Per-tool execution mode override.\n\t * - \"sequential\": this tool must execute one at a time with other tool calls.\n\t * - \"parallel\": this tool can execute concurrently with other tool calls.\n\t *\n\t * If omitted, the default execution mode applies.\n\t */\n\texecutionMode?: ToolExecutionMode;\n}\n\n/** Context snapshot passed into the low-level agent loop. */\nexport interface AgentContext {\n\t/** System prompt included with the request. */\n\tsystemPrompt: string;\n\t/** Transcript visible to the model. */\n\tmessages: AgentMessage[];\n\t/** Tools available for this run. */\n\ttools?: AgentTool<any>[];\n}\n\n/**\n * Events emitted by the Agent for UI updates.\n *\n * `agent_end` is the last event emitted for a run, but awaited `Agent.subscribe()`\n * listeners for that event are still part of run settlement. The agent becomes\n * idle only after those listeners finish.\n */\nexport type AgentEvent =\n\t// Agent lifecycle\n\t| { type: \"agent_start\" }\n\t| { type: \"agent_end\"; messages: AgentMessage[] }\n\t// Turn lifecycle - a turn is one assistant response + any tool calls/results\n\t| { type: \"turn_start\" }\n\t| { type: \"turn_end\"; message: AgentMessage; toolResults: ToolResultMessage[] }\n\t// Message lifecycle - emitted for user, assistant, and toolResult messages\n\t| { type: \"message_start\"; message: AgentMessage }\n\t// Only emitted for assistant messages during streaming\n\t| { type: \"message_update\"; message: AgentMessage; assistantMessageEvent: AssistantMessageEvent }\n\t| { type: \"message_end\"; message: AgentMessage }\n\t// Tool execution lifecycle\n\t| { type: \"tool_execution_start\"; toolCallId: string; toolName: string; args: any }\n\t| { type: \"tool_execution_update\"; toolCallId: string; toolName: string; args: any; partialResult: any }\n\t| { type: \"tool_execution_end\"; toolCallId: string; toolName: string; result: any; isError: boolean };\n"]}

package/node_modules/@earendil-works/pi-agent-core/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@earendil-works/pi-agent-core",
-	"version": "0.84.2",
+	"version": "0.84.4",
 	"description": "General-purpose agent with transport abstraction, state management, and attachment support",
 	"type": "module",
 	"main": "./dist/index.js",
@@ -35,8 +35,8 @@
 		"prepublishOnly": "npm run build"
 	},
 	"dependencies": {
-		"@earendil-works/pi-ai": "^0.84.2",
-		"@earendil-works/pi-telemetry": "^0.84.2",
+		"@earendil-works/pi-ai": "^0.84.4",
+		"@earendil-works/pi-telemetry": "^0.84.4",
 		"diff": "8.0.4",
 		"ignore": "7.0.5",
 		"typebox": "1.3.7",
@@ -60,7 +60,7 @@
 		"node": ">=22.19.0"
 	},
 	"devDependencies": {
-		"@types/node": "24.12.4",
+		"@types/node": "22.19.19",
 		"@vitest/coverage-v8": "4.1.9",
 		"typescript": "5.9.3",
 		"vitest": "4.1.9"

package/node_modules/@earendil-works/pi-ai/README.md

@@ -794,7 +794,7 @@ Many models support thinking/reasoning capabilities where they can show their in
 const model = models.getModel('anthropic', 'claude-sonnet-4-5')!;
 // or models.getModel('openai', 'gpt-5-mini');
 // or models.getModel('google', 'gemini-2.5-flash');
-// or models.getModel('xai', 'grok-4.5');
+// or models.getModel('xai', 'grok-4.6');
 
 // Check if model supports reasoning
 if (model.reasoning) {
@@ -1183,8 +1183,10 @@ interface OpenAICompletionsCompat {
   requiresThinkingAsText?: boolean;  // Whether thinking blocks must be converted to text (default: false)
   requiresReasoningContentOnAssistantMessages?: boolean; // Whether all replayed assistant messages must include empty reasoning_content when reasoning is enabled (default: auto-detected for DeepSeek)
   thinkingFormat?: 'openai' | 'openrouter' | 'deepseek' | 'together' | 'baseten' | 'zai' | 'qwen' | 'chat-template' | 'qwen-chat-template' | 'string-thinking' | 'ant-ling'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'deepseek' uses thinking: { type } plus reasoning_effort when supported, 'together' uses reasoning: { enabled } plus reasoning_effort when supported, 'baseten' uses configurable chat_template_args plus reasoning_effort when supported, 'zai' uses thinking: { type }, 'qwen' uses enable_thinking, 'chat-template' uses configurable chat_template_kwargs, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking and preserve_thinking, 'string-thinking' uses top-level thinking, 'ant-ling' uses reasoning: { effort } only for mapped efforts (default: openai)
-  chatTemplateKwargs?: Record<string, string | number | boolean | null | { '$var': 'thinking.enabled' | 'thinking.effort'; omitWhenOff?: boolean }>; // chat_template_kwargs values; use $var for pi-controlled thinking values
-  chatTemplateArgs?: Record<string, string | number | boolean | null | { '$var': 'thinking.enabled' | 'thinking.effort'; omitWhenOff?: boolean }>; // chat_template_args values for thinkingFormat: 'baseten'; use $var for pi-controlled thinking values
+  chatTemplateKwargs?: Record<string, string | number | boolean | null | { '$var': 'thinking.enabled' | 'thinking.effort' | 'thinking.budget'; omitWhenOff?: boolean }>; // chat_template_kwargs values; use $var for pi-controlled thinking values
+  chatTemplateArgs?: Record<string, string | number | boolean | null | { '$var': 'thinking.enabled' | 'thinking.effort' | 'thinking.budget'; omitWhenOff?: boolean }>; // chat_template_args values for thinkingFormat: 'baseten'; use $var for pi-controlled thinking values
+  thinkingTokenBudgetField?: 'thinking_token_budget' | 'thinking_budget' | 'thinking_budget_tokens'; // Top-level field that caps reasoning tokens from thinkingBudgets (vLLM / Qwen / llama.cpp). Off by default.
+  supportsThinkingTokenBudget?: boolean; // Alias for thinkingTokenBudgetField: 'thinking_token_budget' (vLLM). Prefer thinkingTokenBudgetField. Default: false.
   cacheControlFormat?: 'anthropic';  // Anthropic-style cache_control on system prompt, last tool, and last user/assistant text content
   openRouterRouting?: OpenRouterRouting; // OpenRouter routing preferences (default: {})
   vercelGatewayRouting?: VercelGatewayRouting; // Vercel AI Gateway routing preferences (default: {})

package/node_modules/@earendil-works/pi-ai/dist/api/anthropic-messages.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"anthropic-messages.d.ts","sourceRoot":"","sources":["../../src/api/anthropic-messages.ts"],"names":[],"mappings":"AAAA,OAAO,SAAS,MAAM,mBAAmB,CAAC;AAU1C,OAAO,KAAK,EAWX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAMb,MAAM,aAAa,CAAC;AAwIrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAkChE,MAAM,WAAW,gBAAiB,SAAQ,aAAa;IACtD;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B;;;;OAIG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAC9B;;;;;;;;;;;OAWG;IACH,MAAM,CAAC,EAAE,eAAe,CAAC;IACzB;;;;;;;;;;;OAWG;IACH,eAAe,CAAC,EAAE,wBAAwB,CAAC;IAC3C;;;;;OAKG;IACH,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IACtE;;;;OAIG;IACH,MAAM,CAAC,EAAE,SAAS,CAAC;CACnB;AA+OD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CA+RzE,CAAC;AA2BF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CAwClF,CAAC","sourcesContent":["import Anthropic from \"@anthropic-ai/sdk\";\nimport type {\n\tCacheControlEphemeral,\n\tContentBlockParam,\n\tMessageCreateParamsStreaming,\n\tMessageParam,\n\tRawMessageStreamEvent,\n\tRefusalStopDetails,\n} from \"@anthropic-ai/sdk/resources/messages.js\";\nimport { calculateCost } from \"../models.ts\";\nimport type {\n\tAnthropicMessagesCompat,\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tImageContent,\n\tMessage,\n\tModel,\n\tProviderEnv,\n\tProviderHeaders,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingContent,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.ts\";\nimport { splitDeferredTools } from \"../utils/deferred-tools.ts\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { headersToRecord } from \"../utils/headers.ts\";\nimport { parseJsonWithRepair, parseStreamingJson } from \"../utils/json-parse.ts\";\nimport { getPiUserAgent } from \"../utils/pi-user-agent.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { retryProviderRequest } from \"../utils/provider-retry.ts\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.ts\";\n\nimport { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling } from \"./constrained-sampling.ts\";\nimport { buildCopilotDynamicHeaders, hasCopilotVisionInput } from \"./github-copilot-headers.ts\";\nimport { adjustMaxTokensForThinking, buildBaseOptions, clampMaxTokensToContext } from \"./simple-options.ts\";\nimport { transformMessages } from \"./transform-messages.ts\";\n\n/**\n * Resolve cache retention preference.\n * Defaults to \"short\" and uses PI_CACHE_RETENTION for backward compatibility.\n */\nfunction resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {\n\tif (cacheRetention) {\n\t\treturn cacheRetention;\n\t}\n\tif (getProviderEnvValue(\"PI_CACHE_RETENTION\", env) === \"long\") {\n\t\treturn \"long\";\n\t}\n\treturn \"short\";\n}\n\nfunction getCacheControl(\n\tmodel: Model<\"anthropic-messages\">,\n\tcacheRetention?: CacheRetention,\n\tenv?: ProviderEnv,\n): { retention: CacheRetention; cacheControl?: CacheControlEphemeral } {\n\tconst retention = resolveCacheRetention(cacheRetention, env);\n\tif (retention === \"none\") {\n\t\treturn { retention };\n\t}\n\tconst ttl = retention === \"long\" && getAnthropicCompat(model).supportsLongCacheRetention ? \"1h\" : undefined;\n\treturn {\n\t\tretention,\n\t\tcacheControl: { type: \"ephemeral\", ...(ttl && { ttl }) },\n\t};\n}\n\n// Stealth mode: Mimic Claude Code's tool naming exactly\nconst claudeCodeVersion = \"2.1.75\";\n\n// Claude Code 2.x tool names (canonical casing)\n// Source: https://cchistory.mariozechner.at/data/prompts-2.1.11.md\n// To update: https://github.com/badlogic/cchistory\nconst claudeCodeTools = [\n\t\"Read\",\n\t\"Write\",\n\t\"Edit\",\n\t\"Bash\",\n\t\"Grep\",\n\t\"Glob\",\n\t\"AskUserQuestion\",\n\t\"EnterPlanMode\",\n\t\"ExitPlanMode\",\n\t\"KillShell\",\n\t\"NotebookEdit\",\n\t\"Skill\",\n\t\"Task\",\n\t\"TaskOutput\",\n\t\"TodoWrite\",\n\t\"WebFetch\",\n\t\"WebSearch\",\n];\n\nconst ccToolLookup = new Map(claudeCodeTools.map((t) => [t.toLowerCase(), t]));\n\n// Convert tool name to CC canonical casing if it matches (case-insensitive)\nconst toClaudeCodeName = (name: string) => ccToolLookup.get(name.toLowerCase()) ?? name;\nconst fromClaudeCodeName = (name: string, tools?: Tool[]) => {\n\tif (tools && tools.length > 0) {\n\t\tconst lowerName = name.toLowerCase();\n\t\tconst matchedTool = tools.find((tool) => tool.name.toLowerCase() === lowerName);\n\t\tif (matchedTool) return matchedTool.name;\n\t}\n\treturn name;\n};\n\n/**\n * Convert content blocks to Anthropic API format\n */\nfunction convertContentBlocks(content: (TextContent | ImageContent)[]):\n\t| string\n\t| Array<\n\t\t\t| { type: \"text\"; text: string }\n\t\t\t| {\n\t\t\t\t\ttype: \"image\";\n\t\t\t\t\tsource: {\n\t\t\t\t\t\ttype: \"base64\";\n\t\t\t\t\t\tmedia_type: \"image/jpeg\" | \"image/png\" | \"image/gif\" | \"image/webp\";\n\t\t\t\t\t\tdata: string;\n\t\t\t\t\t};\n\t\t\t  }\n\t  > {\n\t// If only text blocks, return as concatenated string for simplicity\n\tconst hasImages = content.some((c) => c.type === \"image\");\n\tif (!hasImages) {\n\t\treturn sanitizeSurrogates(content.map((c) => (c as TextContent).text).join(\"\\n\"));\n\t}\n\n\t// If we have images, convert to content block array\n\tconst blocks = content.map((block) => {\n\t\tif (block.type === \"text\") {\n\t\t\treturn {\n\t\t\t\ttype: \"text\" as const,\n\t\t\t\ttext: sanitizeSurrogates(block.text),\n\t\t\t};\n\t\t}\n\t\treturn {\n\t\t\ttype: \"image\" as const,\n\t\t\tsource: {\n\t\t\t\ttype: \"base64\" as const,\n\t\t\t\tmedia_type: block.mimeType as \"image/jpeg\" | \"image/png\" | \"image/gif\" | \"image/webp\",\n\t\t\t\tdata: block.data,\n\t\t\t},\n\t\t};\n\t});\n\n\t// If only images (no text), add placeholder text block\n\tconst hasText = blocks.some((b) => b.type === \"text\");\n\tif (!hasText) {\n\t\tblocks.unshift({\n\t\t\ttype: \"text\" as const,\n\t\t\ttext: \"(see attached image)\",\n\t\t});\n\t}\n\n\treturn blocks;\n}\n\nexport type AnthropicEffort = \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\";\n\nexport type AnthropicThinkingDisplay = \"summarized\" | \"omitted\";\n\nconst FINE_GRAINED_TOOL_STREAMING_BETA = \"fine-grained-tool-streaming-2025-05-14\";\nconst INTERLEAVED_THINKING_BETA = \"interleaved-thinking-2025-05-14\";\n\nfunction getAnthropicCompat(\n\tmodel: Model<\"anthropic-messages\">,\n): Required<Omit<AnthropicMessagesCompat, \"forceAdaptiveThinking\">> {\n\treturn {\n\t\tsupportsEagerToolInputStreaming: model.compat?.supportsEagerToolInputStreaming ?? true,\n\t\tsupportsLongCacheRetention: model.compat?.supportsLongCacheRetention ?? true,\n\t\tsendSessionAffinityHeaders: model.compat?.sendSessionAffinityHeaders ?? false,\n\t\tsupportsCacheControlOnTools: model.compat?.supportsCacheControlOnTools ?? true,\n\t\tsupportsTemperature: model.compat?.supportsTemperature ?? true,\n\t\tallowEmptySignature: model.compat?.allowEmptySignature ?? false,\n\t\tsupportsStrictTools: model.compat?.supportsStrictTools ?? false,\n\t\tsupportsToolReferences: model.compat?.supportsToolReferences ?? defaultSupportsToolReferences(model),\n\t};\n}\n\n/**\n * Default for `supportsToolReferences`: first-party Anthropic models except\n * Haiku (rejects client-side tool_reference blocks) and models that predate\n * tool search (Claude 3.x, Opus/Sonnet 4.0, Opus 4.1).\n */\nfunction defaultSupportsToolReferences(model: Model<\"anthropic-messages\">): boolean {\n\tif (model.provider !== \"anthropic\" || model.id.includes(\"haiku\")) return false;\n\tconst version = model.id.match(/^claude-(?:opus|sonnet|fable)-(\\d+)(?:-(\\d+))?(?:-|$)/);\n\tif (!version) return false;\n\tconst major = Number(version[1]);\n\tconst minor = version[2] && version[2].length < 8 ? Number(version[2]) : 0;\n\treturn major > 4 || (major === 4 && minor >= 5);\n}\n\nexport interface AnthropicOptions extends StreamOptions {\n\t/**\n\t * Enable extended thinking.\n\t * For adaptive thinking models: the model decides when/how much to think.\n\t * For older models: uses budget-based thinking with thinkingBudgetTokens.\n\t * Default: undefined (thinking is omitted unless `streamSimple()` maps\n\t * a simple reasoning level to this option, or callers set it explicitly).\n\t */\n\tthinkingEnabled?: boolean;\n\t/**\n\t * Token budget for extended thinking (older models only).\n\t * Ignored for adaptive thinking models.\n\t * Default: 1024 when `thinkingEnabled` is true and no budget is provided.\n\t */\n\tthinkingBudgetTokens?: number;\n\t/**\n\t * Effort level for adaptive thinking models.\n\t * Controls how much thinking Claude allocates:\n\t * - \"max\": Always thinks with no constraints (Opus 4.6 only)\n\t * - \"xhigh\": Highest reasoning level (Opus 4.7+, Fable 5)\n\t * - \"high\": Always thinks, deep reasoning\n\t * - \"medium\": Moderate thinking, may skip for simple queries\n\t * - \"low\": Minimal thinking, skips for simple tasks\n\t * Ignored for older models.\n\t * Default: omitted unless `streamSimple()` maps a simple reasoning\n\t * level to this option.\n\t */\n\teffort?: AnthropicEffort;\n\t/**\n\t * Controls how thinking content is returned in API responses.\n\t * - \"summarized\": Thinking blocks contain summarized thinking text.\n\t * - \"omitted\": Thinking blocks return an empty thinking field; the encrypted\n\t *   signature still travels back for multi-turn continuity. Use for faster\n\t *   time-to-first-text-token when your UI does not surface thinking.\n\t *\n\t * Note: Anthropic's API default for Claude Opus 4.7 and Claude Mythos Preview\n\t * is \"omitted\". We default to \"summarized\" here to keep behavior consistent\n\t * with older Claude 4 models. Set this explicitly to \"omitted\" to opt in.\n\t * Default: \"summarized\" when thinking is enabled.\n\t */\n\tthinkingDisplay?: AnthropicThinkingDisplay;\n\t/**\n\t * Whether to request the interleaved thinking beta header for non-adaptive\n\t * thinking models. Adaptive thinking models have interleaved thinking built in,\n\t * so the header is skipped for them regardless of this setting.\n\t * Default: true.\n\t */\n\tinterleavedThinking?: boolean;\n\t/**\n\t * Anthropic tool choice behavior. String values map to Anthropic's built-in\n\t * choices; `{ type: \"tool\", name }` forces a specific tool.\n\t * Default: omitted (Anthropic default behavior, currently equivalent to auto).\n\t */\n\ttoolChoice?: \"auto\" | \"any\" | \"none\" | { type: \"tool\"; name: string };\n\t/**\n\t * Pre-built Anthropic client instance. When provided, skips internal client\n\t * construction entirely. Use this to inject alternative SDK clients such as\n\t * `AnthropicVertex` that shares the same messaging API.\n\t */\n\tclient?: Anthropic;\n}\n\nfunction mergeHeaders(...headerSources: (ProviderHeaders | undefined)[]): ProviderHeaders {\n\tconst merged: ProviderHeaders = {};\n\tfor (const headers of headerSources) {\n\t\tif (headers) {\n\t\t\tObject.assign(merged, headers);\n\t\t}\n\t}\n\treturn merged;\n}\n\nfunction mergeClientHeaders(\n\tmodel: Model<\"anthropic-messages\">,\n\t...headerSources: (ProviderHeaders | undefined)[]\n): ProviderHeaders {\n\tconst merged = mergeHeaders(...headerSources);\n\tif (model.provider === \"kimi-coding\") {\n\t\tfor (const name of Object.keys(merged)) {\n\t\t\tif (name.toLowerCase() === \"user-agent\") delete merged[name];\n\t\t}\n\t\tmerged[\"User-Agent\"] = getPiUserAgent();\n\t}\n\treturn merged;\n}\n\nfunction hasHeader(headers: ProviderHeaders | undefined, name: string): boolean {\n\tif (!headers) return false;\n\tconst expected = name.toLowerCase();\n\tfor (const [key, value] of Object.entries(headers)) {\n\t\tif (key.toLowerCase() === expected && value !== null && value.trim().length > 0) return true;\n\t}\n\treturn false;\n}\n\nfunction assertRequestAuth(provider: string, apiKey: string | undefined, headers: ProviderHeaders | undefined): void {\n\tif (apiKey) return;\n\tif (\n\t\thasHeader(headers, \"authorization\") ||\n\t\thasHeader(headers, \"x-api-key\") ||\n\t\thasHeader(headers, \"cf-aig-authorization\")\n\t) {\n\t\treturn;\n\t}\n\tthrow new Error(`No API key for provider: ${provider}`);\n}\n\ninterface ServerSentEvent {\n\tevent: string | null;\n\tdata: string;\n\traw: string[];\n}\n\ninterface SseDecoderState {\n\tevent: string | null;\n\tdata: string[];\n\traw: string[];\n}\n\nconst ANTHROPIC_MESSAGE_EVENTS: ReadonlySet<string> = new Set([\n\t\"message_start\",\n\t\"message_delta\",\n\t\"message_stop\",\n\t\"content_block_start\",\n\t\"content_block_delta\",\n\t\"content_block_stop\",\n]);\n\nfunction flushSseEvent(state: SseDecoderState): ServerSentEvent | null {\n\tif (!state.event && state.data.length === 0) {\n\t\treturn null;\n\t}\n\n\tconst event: ServerSentEvent = {\n\t\tevent: state.event,\n\t\tdata: state.data.join(\"\\n\"),\n\t\traw: [...state.raw],\n\t};\n\tstate.event = null;\n\tstate.data = [];\n\tstate.raw = [];\n\treturn event;\n}\n\nfunction decodeSseLine(line: string, state: SseDecoderState): ServerSentEvent | null {\n\tif (line === \"\") {\n\t\treturn flushSseEvent(state);\n\t}\n\n\tstate.raw.push(line);\n\tif (line.startsWith(\":\")) {\n\t\treturn null;\n\t}\n\n\tconst delimiterIndex = line.indexOf(\":\");\n\tconst fieldName = delimiterIndex === -1 ? line : line.slice(0, delimiterIndex);\n\tlet value = delimiterIndex === -1 ? \"\" : line.slice(delimiterIndex + 1);\n\tif (value.startsWith(\" \")) {\n\t\tvalue = value.slice(1);\n\t}\n\n\tif (fieldName === \"event\") {\n\t\tstate.event = value;\n\t} else if (fieldName === \"data\") {\n\t\tstate.data.push(value);\n\t}\n\n\treturn null;\n}\n\nfunction nextLineBreakIndex(text: string): number {\n\tconst carriageReturnIndex = text.indexOf(\"\\r\");\n\tconst newlineIndex = text.indexOf(\"\\n\");\n\tif (carriageReturnIndex === -1) {\n\t\treturn newlineIndex;\n\t}\n\tif (newlineIndex === -1) {\n\t\treturn carriageReturnIndex;\n\t}\n\treturn Math.min(carriageReturnIndex, newlineIndex);\n}\n\nfunction consumeLine(text: string): { line: string; rest: string } | null {\n\tconst lineBreakIndex = nextLineBreakIndex(text);\n\tif (lineBreakIndex === -1) {\n\t\treturn null;\n\t}\n\n\tlet nextIndex = lineBreakIndex + 1;\n\tif (text[lineBreakIndex] === \"\\r\" && text[nextIndex] === \"\\n\") {\n\t\tnextIndex += 1;\n\t}\n\n\treturn {\n\t\tline: text.slice(0, lineBreakIndex),\n\t\trest: text.slice(nextIndex),\n\t};\n}\n\nasync function* iterateSseMessages(\n\tbody: ReadableStream<Uint8Array>,\n\tsignal?: AbortSignal,\n): AsyncGenerator<ServerSentEvent> {\n\tconst reader = body.getReader();\n\tconst decoder = new TextDecoder();\n\tconst state: SseDecoderState = { event: null, data: [], raw: [] };\n\tlet buffer = \"\";\n\n\ttry {\n\t\twhile (true) {\n\t\t\tif (signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tconst { value, done } = await reader.read();\n\t\t\tif (done) {\n\t\t\t\tbreak;\n\t\t\t}\n\n\t\t\tbuffer += decoder.decode(value, { stream: true });\n\t\t\tlet consumed = consumeLine(buffer);\n\t\t\twhile (consumed) {\n\t\t\t\tbuffer = consumed.rest;\n\t\t\t\tconst event = decodeSseLine(consumed.line, state);\n\t\t\t\tif (event) {\n\t\t\t\t\tyield event;\n\t\t\t\t}\n\t\t\t\tconsumed = consumeLine(buffer);\n\t\t\t}\n\t\t}\n\n\t\tbuffer += decoder.decode();\n\t\tlet consumed = consumeLine(buffer);\n\t\twhile (consumed) {\n\t\t\tbuffer = consumed.rest;\n\t\t\tconst event = decodeSseLine(consumed.line, state);\n\t\t\tif (event) {\n\t\t\t\tyield event;\n\t\t\t}\n\t\t\tconsumed = consumeLine(buffer);\n\t\t}\n\n\t\tif (buffer.length > 0) {\n\t\t\tconst event = decodeSseLine(buffer, state);\n\t\t\tif (event) {\n\t\t\t\tyield event;\n\t\t\t}\n\t\t}\n\n\t\tconst trailingEvent = flushSseEvent(state);\n\t\tif (trailingEvent) {\n\t\t\tyield trailingEvent;\n\t\t}\n\t} finally {\n\t\treader.releaseLock();\n\t}\n}\n\nasync function* iterateAnthropicEvents(\n\tresponse: Response,\n\tsignal?: AbortSignal,\n): AsyncGenerator<RawMessageStreamEvent> {\n\tif (!response.body) {\n\t\tthrow new Error(\"Attempted to iterate over an Anthropic response with no body\");\n\t}\n\n\tlet sawMessageStart = false;\n\tlet sawMessageEnd = false;\n\n\tfor await (const sse of iterateSseMessages(response.body, signal)) {\n\t\tif (sse.event === \"error\") {\n\t\t\tthrow new Error(sse.data);\n\t\t}\n\n\t\tif (!ANTHROPIC_MESSAGE_EVENTS.has(sse.event ?? \"\")) {\n\t\t\tcontinue;\n\t\t}\n\n\t\ttry {\n\t\t\tconst event = parseJsonWithRepair<RawMessageStreamEvent>(sse.data);\n\t\t\tif (event.type === \"message_start\") {\n\t\t\t\tsawMessageStart = true;\n\t\t\t} else if (event.type === \"message_stop\") {\n\t\t\t\tsawMessageEnd = true;\n\t\t\t}\n\t\t\tyield event;\n\t\t} catch (error) {\n\t\t\tconst message = error instanceof Error ? error.message : String(error);\n\t\t\tthrow new Error(\n\t\t\t\t`Could not parse Anthropic SSE event ${sse.event}: ${message}; data=${sse.data}; raw=${sse.raw.join(\"\\\\n\")}`,\n\t\t\t);\n\t\t}\n\t}\n\n\tif (sawMessageStart && !sawMessageEnd) {\n\t\tthrow new Error(\"Anthropic stream ended before message_stop\");\n\t}\n}\n\nexport const stream: StreamFunction<\"anthropic-messages\", AnthropicOptions> = (\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\toptions?: AnthropicOptions,\n): AssistantMessageEventStream => {\n\tconst stream = new AssistantMessageEventStream();\n\n\t(async () => {\n\t\tconst output: AssistantMessage = {\n\t\t\trole: \"assistant\",\n\t\t\tcontent: [],\n\t\t\tapi: model.api as Api,\n\t\t\tprovider: model.provider,\n\t\t\tmodel: model.id,\n\t\t\tusage: {\n\t\t\t\tinput: 0,\n\t\t\t\toutput: 0,\n\t\t\t\tcacheRead: 0,\n\t\t\t\tcacheWrite: 0,\n\t\t\t\ttotalTokens: 0,\n\t\t\t\tcost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },\n\t\t\t},\n\t\t\tstopReason: \"pending\",\n\t\t\ttimestamp: Date.now(),\n\t\t};\n\n\t\ttry {\n\t\t\tlet client: Anthropic;\n\t\t\tlet isOAuth: boolean;\n\n\t\t\tif (options?.client) {\n\t\t\t\tclient = options.client;\n\t\t\t\tisOAuth = false;\n\t\t\t} else {\n\t\t\t\tconst apiKey = options?.apiKey;\n\t\t\t\tassertRequestAuth(model.provider, apiKey, options?.headers);\n\n\t\t\t\tlet copilotDynamicHeaders: Record<string, string> | undefined;\n\t\t\t\tif (model.provider === \"github-copilot\") {\n\t\t\t\t\tconst hasImages = hasCopilotVisionInput(context.messages);\n\t\t\t\t\tcopilotDynamicHeaders = buildCopilotDynamicHeaders({\n\t\t\t\t\t\tmessages: context.messages,\n\t\t\t\t\t\thasImages,\n\t\t\t\t\t});\n\t\t\t\t}\n\n\t\t\t\tconst cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);\n\t\t\t\tconst cacheSessionId = cacheRetention === \"none\" ? undefined : options?.sessionId;\n\n\t\t\t\tconst created = createClient(\n\t\t\t\t\tmodel,\n\t\t\t\t\tapiKey,\n\t\t\t\t\toptions?.interleavedThinking ?? true,\n\t\t\t\t\tshouldUseFineGrainedToolStreamingBeta(model, context),\n\t\t\t\t\toptions?.headers,\n\t\t\t\t\toptions?.fetch,\n\t\t\t\t\tcopilotDynamicHeaders,\n\t\t\t\t\tcacheSessionId,\n\t\t\t\t);\n\t\t\t\tclient = created.client;\n\t\t\t\tisOAuth = created.isOAuthToken;\n\t\t\t}\n\t\t\tlet params = buildParams(model, context, isOAuth, options);\n\t\t\tconst nextParams = await options?.onPayload?.(params, model);\n\t\t\tif (nextParams !== undefined) {\n\t\t\t\tparams = nextParams as MessageCreateParamsStreaming;\n\t\t\t}\n\t\t\tconst requestOptions = {\n\t\t\t\t...(options?.signal ? { signal: options.signal } : {}),\n\t\t\t\t...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),\n\t\t\t\tmaxRetries: 0,\n\t\t\t};\n\t\t\tconst response = await retryProviderRequest(\n\t\t\t\t() => client.messages.create({ ...params, stream: true }, requestOptions).asResponse(),\n\t\t\t\t{\n\t\t\t\t\tmaxRetries: options?.maxRetries,\n\t\t\t\t\tmaxRetryDelayMs: options?.maxRetryDelayMs,\n\t\t\t\t\tsignal: options?.signal,\n\t\t\t\t},\n\t\t\t);\n\t\t\tawait options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);\n\t\t\tstream.push({ type: \"start\", partial: output });\n\n\t\t\ttype Block = (ThinkingContent | TextContent | (ToolCall & { partialJson: string })) & { index: number };\n\t\t\tconst blocks = output.content as Block[];\n\n\t\t\tfor await (const event of iterateAnthropicEvents(response, options?.signal)) {\n\t\t\t\tif (event.type === \"message_start\") {\n\t\t\t\t\toutput.responseId = event.message.id;\n\t\t\t\t\t// Capture initial token usage from message_start event\n\t\t\t\t\t// This ensures we have input token counts even if the stream is aborted early\n\t\t\t\t\toutput.usage.input = event.message.usage.input_tokens || 0;\n\t\t\t\t\toutput.usage.output = event.message.usage.output_tokens || 0;\n\t\t\t\t\toutput.usage.cacheRead = event.message.usage.cache_read_input_tokens || 0;\n\t\t\t\t\toutput.usage.cacheWrite = event.message.usage.cache_creation_input_tokens || 0;\n\t\t\t\t\toutput.usage.cacheWrite1h = event.message.usage.cache_creation?.ephemeral_1h_input_tokens || 0;\n\t\t\t\t\t// Anthropic doesn't provide total_tokens, compute from components\n\t\t\t\t\toutput.usage.totalTokens =\n\t\t\t\t\t\toutput.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;\n\t\t\t\t\tcalculateCost(model, output.usage);\n\t\t\t\t} else if (event.type === \"content_block_start\") {\n\t\t\t\t\tif (event.content_block.type === \"text\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\t\ttext: event.content_block.text ?? \"\",\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"text_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t} else if (event.content_block.type === \"thinking\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\tthinking: event.content_block.thinking ?? \"\",\n\t\t\t\t\t\t\tthinkingSignature: event.content_block.signature ?? \"\",\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"thinking_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t} else if (event.content_block.type === \"redacted_thinking\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\tthinking: \"[Reasoning redacted]\",\n\t\t\t\t\t\t\tthinkingSignature: event.content_block.data,\n\t\t\t\t\t\t\tredacted: true,\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"thinking_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t} else if (event.content_block.type === \"tool_use\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"toolCall\",\n\t\t\t\t\t\t\tid: event.content_block.id,\n\t\t\t\t\t\t\tname: isOAuth\n\t\t\t\t\t\t\t\t? fromClaudeCodeName(event.content_block.name, context.tools)\n\t\t\t\t\t\t\t\t: event.content_block.name,\n\t\t\t\t\t\t\targuments: (event.content_block.input as Record<string, any>) ?? {},\n\t\t\t\t\t\t\tpartialJson: \"\",\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"toolcall_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t}\n\t\t\t\t} else if (event.type === \"content_block_delta\") {\n\t\t\t\t\tif (event.delta.type === \"text_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"text\") {\n\t\t\t\t\t\t\tblock.text += event.delta.text;\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"text_delta\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tdelta: event.delta.text,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t} else if (event.delta.type === \"thinking_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"thinking\") {\n\t\t\t\t\t\t\tblock.thinking += event.delta.thinking;\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tdelta: event.delta.thinking,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t} else if (event.delta.type === \"input_json_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"toolCall\") {\n\t\t\t\t\t\t\tblock.partialJson += event.delta.partial_json;\n\t\t\t\t\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"toolcall_delta\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tdelta: event.delta.partial_json,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t} else if (event.delta.type === \"signature_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"thinking\") {\n\t\t\t\t\t\t\tblock.thinkingSignature = block.thinkingSignature || \"\";\n\t\t\t\t\t\t\tblock.thinkingSignature += event.delta.signature;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t} else if (event.type === \"content_block_stop\") {\n\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\tif (block) {\n\t\t\t\t\t\tdelete (block as any).index;\n\t\t\t\t\t\tif (block.type === \"text\") {\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"text_end\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tcontent: block.text,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t} else if (block.type === \"thinking\") {\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"thinking_end\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tcontent: block.thinking,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t} else if (block.type === \"toolCall\") {\n\t\t\t\t\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t\t\t\t\t// Finalize in-place and strip the scratch buffer so replay only\n\t\t\t\t\t\t\t// carries parsed arguments.\n\t\t\t\t\t\t\tdelete (block as { partialJson?: string }).partialJson;\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"toolcall_end\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\ttoolCall: block,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t} else if (event.type === \"message_delta\") {\n\t\t\t\t\tif (event.delta.stop_reason) {\n\t\t\t\t\t\toutput.rawStopReason = event.delta.stop_reason;\n\t\t\t\t\t\tconst stopReasonResult = mapStopReason(event.delta.stop_reason, event.delta.stop_details);\n\t\t\t\t\t\toutput.stopReason = stopReasonResult.stopReason;\n\t\t\t\t\t\tif (stopReasonResult.errorMessage) {\n\t\t\t\t\t\t\toutput.errorMessage = stopReasonResult.errorMessage;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\t// Only update usage fields if present (not null).\n\t\t\t\t\t// Preserves input_tokens from message_start when proxies omit it in message_delta.\n\t\t\t\t\tif (event.usage) {\n\t\t\t\t\t\tif (event.usage.input_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.input = event.usage.input_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tif (event.usage.output_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.output = event.usage.output_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tif (event.usage.cache_read_input_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.cacheRead = event.usage.cache_read_input_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tif (event.usage.cache_creation_input_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.cacheWrite = event.usage.cache_creation_input_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\t// Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the\n\t\t\t\t\t\t// final message_delta usage (a subset of output_tokens). SDK 0.91.1 omits the field from\n\t\t\t\t\t\t// its Usage type, so read it through a narrow cast. Verified against the live API.\n\t\t\t\t\t\tconst thinkingTokens = (event.usage as { output_tokens_details?: { thinking_tokens?: number } })\n\t\t\t\t\t\t\t.output_tokens_details?.thinking_tokens;\n\t\t\t\t\t\tif (thinkingTokens != null) {\n\t\t\t\t\t\t\toutput.usage.reasoning = thinkingTokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\t// Anthropic doesn't provide total_tokens, compute from components\n\t\t\t\t\toutput.usage.totalTokens =\n\t\t\t\t\t\toutput.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;\n\t\t\t\t\tcalculateCost(model, output.usage);\n\t\t\t\t}\n\t\t\t}\n\n\t\t\tif (options?.signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tif (output.stopReason === \"pending\") {\n\t\t\t\tthrow new Error(\"Anthropic stream ended without a stop reason\");\n\t\t\t}\n\t\t\tif (output.stopReason === \"aborted\" || output.stopReason === \"error\") {\n\t\t\t\tthrow new Error(output.errorMessage || \"An unknown error occurred\");\n\t\t\t}\n\n\t\t\tstream.push({ type: \"done\", reason: output.stopReason, message: output });\n\t\t\tstream.end();\n\t\t} catch (error) {\n\t\t\tfor (const block of output.content) {\n\t\t\t\tdelete (block as { index?: number }).index;\n\t\t\t\t// partialJson is only a streaming scratch buffer; never persist it.\n\t\t\t\tdelete (block as { partialJson?: string }).partialJson;\n\t\t\t}\n\t\t\toutput.stopReason = options?.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = error instanceof Error ? error.message : JSON.stringify(error);\n\t\t\tstream.push({ type: \"error\", reason: output.stopReason, error: output });\n\t\t\tstream.end();\n\t\t}\n\t})();\n\n\treturn stream;\n};\n\n/**\n * Map ThinkingLevel to Anthropic effort levels for adaptive thinking.\n * Note: effort \"max\" is available on all adaptive-thinking Claude models, while native\n * \"xhigh\" is only available on Opus 4.7/4.8, Sonnet 5, and Fable 5.\n */\nfunction mapThinkingLevelToEffort(\n\tmodel: Model<\"anthropic-messages\">,\n\tlevel: SimpleStreamOptions[\"reasoning\"],\n): AnthropicEffort {\n\tconst mapped = level ? model.thinkingLevelMap?.[level] : undefined;\n\tif (typeof mapped === \"string\") return mapped as AnthropicEffort;\n\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\tcase \"low\":\n\t\t\treturn \"low\";\n\t\tcase \"medium\":\n\t\t\treturn \"medium\";\n\t\tcase \"high\":\n\t\t\treturn \"high\";\n\t\tdefault:\n\t\t\treturn \"high\";\n\t}\n}\n\nexport const streamSimple: StreamFunction<\"anthropic-messages\", SimpleStreamOptions> = (\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tassertRequestAuth(model.provider, options?.apiKey, options?.headers);\n\n\tconst base = buildBaseOptions(model, context, options, options?.apiKey);\n\tif (!options?.reasoning) {\n\t\treturn stream(model, context, { ...base, thinkingEnabled: false } satisfies AnthropicOptions);\n\t}\n\n\t// For models with adaptive thinking: use an effort level.\n\t// For older models: use budget-based thinking.\n\tif (model.compat?.forceAdaptiveThinking === true) {\n\t\tconst effort = mapThinkingLevelToEffort(model, options.reasoning);\n\t\treturn stream(model, context, {\n\t\t\t...base,\n\t\t\tthinkingEnabled: true,\n\t\t\teffort,\n\t\t} satisfies AnthropicOptions);\n\t}\n\n\t// Undefined means the caller did not request an output cap; let the helper use the model cap.\n\t// Do not coerce to 0 here, or the thinking budget would become the entire max_tokens value.\n\tconst adjusted = adjustMaxTokensForThinking(\n\t\tbase.maxTokens,\n\t\tmodel.maxTokens,\n\t\toptions.reasoning,\n\t\toptions.thinkingBudgets,\n\t);\n\n\tconst maxTokens = clampMaxTokensToContext(model, context, adjusted.maxTokens);\n\n\treturn stream(model, context, {\n\t\t...base,\n\t\tmaxTokens,\n\t\tthinkingEnabled: true,\n\t\tthinkingBudgetTokens: Math.min(adjusted.thinkingBudget, Math.max(0, maxTokens - 1024)),\n\t} satisfies AnthropicOptions);\n};\n\nfunction isOAuthToken(apiKey: string): boolean {\n\treturn apiKey.includes(\"sk-ant-oat\");\n}\n\nfunction createClient(\n\tmodel: Model<\"anthropic-messages\">,\n\tapiKey: string | undefined,\n\tinterleavedThinking: boolean,\n\tuseFineGrainedToolStreamingBeta: boolean,\n\toptionsHeaders?: ProviderHeaders,\n\tfetch?: typeof globalThis.fetch,\n\tdynamicHeaders?: Record<string, string>,\n\tsessionId?: string,\n): { client: Anthropic; isOAuthToken: boolean } {\n\t// Adaptive thinking models have interleaved thinking built in, so skip the beta header.\n\tconst needsInterleavedBeta = interleavedThinking && model.compat?.forceAdaptiveThinking !== true;\n\tconst betaFeatures: string[] = [];\n\tif (useFineGrainedToolStreamingBeta) {\n\t\tbetaFeatures.push(FINE_GRAINED_TOOL_STREAMING_BETA);\n\t}\n\tif (needsInterleavedBeta) {\n\t\tbetaFeatures.push(INTERLEAVED_THINKING_BETA);\n\t}\n\n\t// Copilot: Bearer auth, selective betas.\n\tif (model.provider === \"github-copilot\") {\n\t\tconst client = new Anthropic({\n\t\t\tapiKey: null,\n\t\t\tauthToken: apiKey ?? null,\n\t\t\tbaseURL: model.baseUrl,\n\t\t\tdangerouslyAllowBrowser: true,\n\t\t\tfetch,\n\t\t\tdefaultHeaders: mergeClientHeaders(\n\t\t\t\tmodel,\n\t\t\t\t{\n\t\t\t\t\taccept: \"application/json\",\n\t\t\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t\t\t...(betaFeatures.length > 0 ? { \"anthropic-beta\": betaFeatures.join(\",\") } : {}),\n\t\t\t\t},\n\t\t\t\tmodel.headers,\n\t\t\t\tdynamicHeaders,\n\t\t\t\toptionsHeaders,\n\t\t\t),\n\t\t});\n\n\t\treturn { client, isOAuthToken: false };\n\t}\n\n\t// OAuth: Bearer auth, Claude Code identity headers\n\tif (apiKey && isOAuthToken(apiKey)) {\n\t\tconst client = new Anthropic({\n\t\t\tapiKey: null,\n\t\t\tauthToken: apiKey,\n\t\t\tbaseURL: model.baseUrl,\n\t\t\tdangerouslyAllowBrowser: true,\n\t\t\tfetch,\n\t\t\tdefaultHeaders: mergeClientHeaders(\n\t\t\t\tmodel,\n\t\t\t\t{\n\t\t\t\t\taccept: \"application/json\",\n\t\t\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t\t\t\"anthropic-beta\": [\"claude-code-20250219\", \"oauth-2025-04-20\", ...betaFeatures].join(\",\"),\n\t\t\t\t\t\"user-agent\": `claude-cli/${claudeCodeVersion}`,\n\t\t\t\t\t\"x-app\": \"cli\",\n\t\t\t\t},\n\t\t\t\tmodel.headers,\n\t\t\t\toptionsHeaders,\n\t\t\t),\n\t\t});\n\n\t\treturn { client, isOAuthToken: true };\n\t}\n\n\t// API key or header-owned auth.\n\tconst sessionAffinityHeaders: ProviderHeaders =\n\t\tsessionId && getAnthropicCompat(model).sendSessionAffinityHeaders ? { \"x-session-affinity\": sessionId } : {};\n\tconst defaultHeaders = mergeClientHeaders(\n\t\tmodel,\n\t\t{\n\t\t\taccept: \"application/json\",\n\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t...(betaFeatures.length > 0 ? { \"anthropic-beta\": betaFeatures.join(\",\") } : {}),\n\t\t},\n\t\tsessionAffinityHeaders,\n\t\tmodel.headers,\n\t\toptionsHeaders,\n\t);\n\tconst client = new Anthropic({\n\t\tapiKey: apiKey ?? null,\n\t\tauthToken: null,\n\t\tbaseURL: model.baseUrl,\n\t\tdangerouslyAllowBrowser: true,\n\t\tfetch,\n\t\tdefaultHeaders,\n\t});\n\n\treturn { client, isOAuthToken: false };\n}\n\nfunction buildParams(\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\tisOAuthToken: boolean,\n\toptions?: AnthropicOptions,\n): MessageCreateParamsStreaming {\n\tconst { cacheControl } = getCacheControl(model, options?.cacheRetention, options?.env);\n\tconst compat = getAnthropicCompat(model);\n\tconst transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);\n\tconst normalizeToolName = isOAuthToken ? toClaudeCodeName : (name: string) => name;\n\tconst toolPlacement = splitDeferredTools(\n\t\t{ ...context, messages: transformedMessages },\n\t\tcompat.supportsToolReferences,\n\t\tnormalizeToolName,\n\t);\n\tlet immediateTools = toolPlacement.immediate;\n\tlet deferredTools = [...toolPlacement.deferred.values()];\n\tif (immediateTools.length === 0 && deferredTools.length > 0) {\n\t\timmediateTools = deferredTools;\n\t\tdeferredTools = [];\n\t}\n\tconst deferredToolNames = new Set(deferredTools.map((tool) => normalizeToolName(tool.name)));\n\tconst params: MessageCreateParamsStreaming = {\n\t\tmodel: model.id,\n\t\tmessages: convertMessages(\n\t\t\ttransformedMessages,\n\t\t\tisOAuthToken,\n\t\t\tcacheControl,\n\t\t\tcompat.allowEmptySignature,\n\t\t\tdeferredToolNames,\n\t\t\tnormalizeToolName,\n\t\t),\n\t\tmax_tokens: options?.maxTokens ?? model.maxTokens,\n\t\tstream: true,\n\t};\n\n\t// For OAuth tokens, we MUST include Claude Code identity\n\tif (isOAuthToken) {\n\t\tparams.system = [\n\t\t\t{\n\t\t\t\ttype: \"text\",\n\t\t\t\ttext: \"You are Claude Code, Anthropic's official CLI for Claude.\",\n\t\t\t\t...(cacheControl ? { cache_control: cacheControl } : {}),\n\t\t\t},\n\t\t];\n\t\tif (context.systemPrompt) {\n\t\t\tparams.system.push({\n\t\t\t\ttype: \"text\",\n\t\t\t\ttext: sanitizeSurrogates(context.systemPrompt),\n\t\t\t\t...(cacheControl ? { cache_control: cacheControl } : {}),\n\t\t\t});\n\t\t}\n\t} else if (context.systemPrompt) {\n\t\t// Add cache control to system prompt for non-OAuth tokens\n\t\tparams.system = [\n\t\t\t{\n\t\t\t\ttype: \"text\",\n\t\t\t\ttext: sanitizeSurrogates(context.systemPrompt),\n\t\t\t\t...(cacheControl ? { cache_control: cacheControl } : {}),\n\t\t\t},\n\t\t];\n\t}\n\n\t// Temperature is incompatible with extended thinking and unsupported on Claude Opus 4.7+.\n\tif (options?.temperature !== undefined && !options?.thinkingEnabled && compat.supportsTemperature) {\n\t\tparams.temperature = options.temperature;\n\t}\n\n\tif (immediateTools.length > 0 || deferredTools.length > 0) {\n\t\tparams.tools = [\n\t\t\t...convertTools(\n\t\t\t\timmediateTools,\n\t\t\t\tisOAuthToken,\n\t\t\t\tcompat.supportsEagerToolInputStreaming,\n\t\t\t\tcompat.supportsStrictTools,\n\t\t\t\tcompat.supportsCacheControlOnTools ? cacheControl : undefined,\n\t\t\t),\n\t\t\t...convertTools(\n\t\t\t\tdeferredTools,\n\t\t\t\tisOAuthToken,\n\t\t\t\tcompat.supportsEagerToolInputStreaming,\n\t\t\t\tcompat.supportsStrictTools,\n\t\t\t\tundefined,\n\t\t\t\ttrue,\n\t\t\t),\n\t\t];\n\t}\n\n\t// Configure thinking mode: adaptive, budget-based, or explicitly disabled.\n\tif (model.reasoning) {\n\t\tif (options?.thinkingEnabled) {\n\t\t\t// Default to \"summarized\" so Opus 4.7 and Mythos Preview behave like\n\t\t\t// older Claude 4 models (whose API default is also \"summarized\").\n\t\t\tconst display: AnthropicThinkingDisplay = options.thinkingDisplay ?? \"summarized\";\n\t\t\tif (model.compat?.forceAdaptiveThinking === true) {\n\t\t\t\t// Adaptive thinking: Claude decides when and how much to think.\n\t\t\t\tparams.thinking = { type: \"adaptive\", display };\n\t\t\t\tif (options.effort) {\n\t\t\t\t\t// The Anthropic SDK types can lag newly supported effort values such as \"xhigh\".\n\t\t\t\t\tparams.output_config =\n\t\t\t\t\t\toptions.effort === \"xhigh\"\n\t\t\t\t\t\t\t? ({ effort: options.effort } as unknown as NonNullable<\n\t\t\t\t\t\t\t\t\tMessageCreateParamsStreaming[\"output_config\"]\n\t\t\t\t\t\t\t\t>)\n\t\t\t\t\t\t\t: { effort: options.effort };\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\t// Budget-based thinking for older models\n\t\t\t\tparams.thinking = {\n\t\t\t\t\ttype: \"enabled\",\n\t\t\t\t\tbudget_tokens: options.thinkingBudgetTokens || 1024,\n\t\t\t\t\tdisplay,\n\t\t\t\t};\n\t\t\t}\n\t\t} else if (options?.thinkingEnabled === false && model.thinkingLevelMap?.off !== null) {\n\t\t\tparams.thinking = { type: \"disabled\" };\n\t\t}\n\t}\n\n\tif (options?.metadata) {\n\t\tconst userId = options.metadata.user_id;\n\t\tif (typeof userId === \"string\") {\n\t\t\tparams.metadata = { user_id: userId };\n\t\t}\n\t}\n\n\tif (options?.toolChoice) {\n\t\tif (typeof options.toolChoice === \"string\") {\n\t\t\tparams.tool_choice = { type: options.toolChoice };\n\t\t} else {\n\t\t\tparams.tool_choice = options.toolChoice;\n\t\t}\n\t}\n\n\treturn params;\n}\n\n// Normalize tool call IDs to match Anthropic's required pattern and length\nfunction normalizeToolCallId(id: string): string {\n\treturn id.replace(/[^a-zA-Z0-9_-]/g, \"_\").slice(0, 64);\n}\n\nfunction convertToolResult(\n\tmsg: ToolResultMessage,\n\tisOAuthToken: boolean,\n\tdeferredToolNames: ReadonlySet<string>,\n\tloadedToolNames: Set<string>,\n\tnormalizeToolName: (name: string) => string,\n): { toolResult: ContentBlockParam; siblingContent: ContentBlockParam[] } {\n\tconst references: Array<{ type: \"tool_reference\"; tool_name: string }> = [];\n\tfor (const name of msg.addedToolNames ?? []) {\n\t\tconst normalizedName = normalizeToolName(name);\n\t\tif (!deferredToolNames.has(normalizedName) || loadedToolNames.has(normalizedName)) continue;\n\t\tloadedToolNames.add(normalizedName);\n\t\treferences.push({\n\t\t\ttype: \"tool_reference\",\n\t\t\ttool_name: isOAuthToken ? toClaudeCodeName(name) : name,\n\t\t});\n\t}\n\tconst convertedContent = convertContentBlocks(msg.content);\n\t// Anthropic rejects tool references mixed with ordinary tool-result content.\n\treturn {\n\t\ttoolResult: {\n\t\t\ttype: \"tool_result\",\n\t\t\ttool_use_id: msg.toolCallId,\n\t\t\tcontent: references.length > 0 ? references : convertedContent,\n\t\t\tis_error: msg.isError,\n\t\t},\n\t\tsiblingContent:\n\t\t\treferences.length === 0\n\t\t\t\t? []\n\t\t\t\t: typeof convertedContent === \"string\"\n\t\t\t\t\t? [{ type: \"text\", text: convertedContent }]\n\t\t\t\t\t: convertedContent,\n\t};\n}\n\nfunction convertMessages(\n\ttransformedMessages: Message[],\n\tisOAuthToken: boolean,\n\tcacheControl?: CacheControlEphemeral,\n\tallowEmptySignature = false,\n\tdeferredToolNames: ReadonlySet<string> = new Set(),\n\tnormalizeToolName: (name: string) => string = (name) => name,\n): MessageParam[] {\n\tconst params: MessageParam[] = [];\n\tconst loadedToolNames = new Set<string>();\n\n\tfor (let i = 0; i < transformedMessages.length; i++) {\n\t\tconst msg = transformedMessages[i];\n\n\t\tif (msg.role === \"user\") {\n\t\t\tif (typeof msg.content === \"string\") {\n\t\t\t\tif (msg.content.trim().length > 0) {\n\t\t\t\t\tparams.push({\n\t\t\t\t\t\trole: \"user\",\n\t\t\t\t\t\tcontent: sanitizeSurrogates(msg.content),\n\t\t\t\t\t});\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\tconst blocks: ContentBlockParam[] = msg.content.map((item) => {\n\t\t\t\t\tif (item.type === \"text\") {\n\t\t\t\t\t\treturn {\n\t\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\t\ttext: sanitizeSurrogates(item.text),\n\t\t\t\t\t\t};\n\t\t\t\t\t} else {\n\t\t\t\t\t\treturn {\n\t\t\t\t\t\t\ttype: \"image\",\n\t\t\t\t\t\t\tsource: {\n\t\t\t\t\t\t\t\ttype: \"base64\",\n\t\t\t\t\t\t\t\tmedia_type: item.mimeType as \"image/jpeg\" | \"image/png\" | \"image/gif\" | \"image/webp\",\n\t\t\t\t\t\t\t\tdata: item.data,\n\t\t\t\t\t\t\t},\n\t\t\t\t\t\t};\n\t\t\t\t\t}\n\t\t\t\t});\n\t\t\t\tconst filteredBlocks = blocks.filter((b) => {\n\t\t\t\t\tif (b.type === \"text\") {\n\t\t\t\t\t\treturn b.text.trim().length > 0;\n\t\t\t\t\t}\n\t\t\t\t\treturn true;\n\t\t\t\t});\n\t\t\t\tif (filteredBlocks.length === 0) continue;\n\t\t\t\tparams.push({\n\t\t\t\t\trole: \"user\",\n\t\t\t\t\tcontent: filteredBlocks,\n\t\t\t\t});\n\t\t\t}\n\t\t} else if (msg.role === \"assistant\") {\n\t\t\tconst blocks: ContentBlockParam[] = [];\n\n\t\t\tfor (const block of msg.content) {\n\t\t\t\tif (block.type === \"text\") {\n\t\t\t\t\tif (block.text.trim().length === 0) continue;\n\t\t\t\t\tblocks.push({\n\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\ttext: sanitizeSurrogates(block.text),\n\t\t\t\t\t});\n\t\t\t\t} else if (block.type === \"thinking\") {\n\t\t\t\t\t// Redacted thinking: pass the opaque payload back as redacted_thinking\n\t\t\t\t\tif (block.redacted) {\n\t\t\t\t\t\tblocks.push({\n\t\t\t\t\t\t\ttype: \"redacted_thinking\",\n\t\t\t\t\t\t\tdata: block.thinkingSignature!,\n\t\t\t\t\t\t});\n\t\t\t\t\t\tcontinue;\n\t\t\t\t\t}\n\t\t\t\t\tconst thinkingSignature = block.thinkingSignature;\n\t\t\t\t\tconst hasThinkingSignature = !!thinkingSignature && thinkingSignature.trim().length > 0;\n\t\t\t\t\tif (block.thinking.trim().length === 0 && !hasThinkingSignature) continue;\n\t\t\t\t\t// If thinking signature is missing/empty (e.g., from aborted stream),\n\t\t\t\t\t// convert to plain text for Anthropic. Some compatible providers emit\n\t\t\t\t\t// and accept empty signatures, so let marked models preserve the block.\n\t\t\t\t\tif (!hasThinkingSignature) {\n\t\t\t\t\t\tblocks.push(\n\t\t\t\t\t\t\tallowEmptySignature\n\t\t\t\t\t\t\t\t? {\n\t\t\t\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\t\t\t\tthinking: sanitizeSurrogates(block.thinking),\n\t\t\t\t\t\t\t\t\t\tsignature: \"\",\n\t\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t\t: {\n\t\t\t\t\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\t\t\t\t\ttext: sanitizeSurrogates(block.thinking),\n\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t);\n\t\t\t\t\t} else {\n\t\t\t\t\t\tblocks.push({\n\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\tthinking: sanitizeSurrogates(block.thinking),\n\t\t\t\t\t\t\tsignature: thinkingSignature,\n\t\t\t\t\t\t});\n\t\t\t\t\t}\n\t\t\t\t} else if (block.type === \"toolCall\") {\n\t\t\t\t\tblocks.push({\n\t\t\t\t\t\ttype: \"tool_use\",\n\t\t\t\t\t\tid: block.id,\n\t\t\t\t\t\tname: isOAuthToken ? toClaudeCodeName(block.name) : block.name,\n\t\t\t\t\t\tinput: block.arguments ?? {},\n\t\t\t\t\t});\n\t\t\t\t}\n\t\t\t}\n\t\t\tif (blocks.length === 0) continue;\n\t\t\tparams.push({\n\t\t\t\trole: \"assistant\",\n\t\t\t\tcontent: blocks,\n\t\t\t});\n\t\t} else if (msg.role === \"toolResult\") {\n\t\t\t// Collect all consecutive toolResult messages, needed for z.ai Anthropic endpoint.\n\t\t\tconst toolResults: ContentBlockParam[] = [];\n\t\t\tconst siblingContent: ContentBlockParam[] = [];\n\t\t\tlet j = i;\n\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\tconst converted = convertToolResult(\n\t\t\t\t\ttransformedMessages[j] as ToolResultMessage,\n\t\t\t\t\tisOAuthToken,\n\t\t\t\t\tdeferredToolNames,\n\t\t\t\t\tloadedToolNames,\n\t\t\t\t\tnormalizeToolName,\n\t\t\t\t);\n\t\t\t\ttoolResults.push(converted.toolResult);\n\t\t\t\tsiblingContent.push(...converted.siblingContent);\n\t\t\t\tj++;\n\t\t\t}\n\n\t\t\t// Skip the messages we've already processed.\n\t\t\ti = j - 1;\n\n\t\t\t// Displaced reference-bearing results must follow every tool_result block.\n\t\t\tparams.push({\n\t\t\t\trole: \"user\",\n\t\t\t\tcontent: [...toolResults, ...siblingContent],\n\t\t\t});\n\t\t}\n\t}\n\n\t// Add cache_control to the last user message to cache conversation history\n\tif (cacheControl && params.length > 0) {\n\t\tconst lastMessage = params[params.length - 1];\n\t\tif (lastMessage.role === \"user\") {\n\t\t\tif (Array.isArray(lastMessage.content)) {\n\t\t\t\tconst lastBlock = lastMessage.content[lastMessage.content.length - 1];\n\t\t\t\tif (\n\t\t\t\t\tlastBlock &&\n\t\t\t\t\t(lastBlock.type === \"text\" || lastBlock.type === \"image\" || lastBlock.type === \"tool_result\")\n\t\t\t\t) {\n\t\t\t\t\t(lastBlock as any).cache_control = cacheControl;\n\t\t\t\t}\n\t\t\t} else if (typeof lastMessage.content === \"string\") {\n\t\t\t\tlastMessage.content = [\n\t\t\t\t\t{\n\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\ttext: lastMessage.content,\n\t\t\t\t\t\tcache_control: cacheControl,\n\t\t\t\t\t},\n\t\t\t\t] as any;\n\t\t\t}\n\t\t}\n\t}\n\n\treturn params;\n}\n\nfunction shouldUseFineGrainedToolStreamingBeta(model: Model<\"anthropic-messages\">, context: Context): boolean {\n\treturn !!context.tools?.length && !getAnthropicCompat(model).supportsEagerToolInputStreaming;\n}\n\nfunction convertTools(\n\ttools: Tool[],\n\tisOAuthToken: boolean,\n\tsupportsEagerToolInputStreaming: boolean,\n\tsupportsStrictTools: boolean,\n\tcacheControl?: CacheControlEphemeral,\n\tdeferLoading = false,\n): Anthropic.Messages.Tool[] {\n\tif (!tools) return [];\n\n\treturn tools.map((tool, index) => {\n\t\tconst strict = resolveJsonSchemaStrictSampling(tool, supportsStrictTools);\n\t\tconst parameters = getJsonSchemaToolParameters(tool, strict);\n\t\tconst schema = parameters as { properties?: unknown; required?: string[] };\n\t\tconst legacyInputSchema = {\n\t\t\ttype: \"object\" as const,\n\t\t\tproperties: schema.properties ?? {},\n\t\t\trequired: schema.required ?? [],\n\t\t};\n\t\tconst inputSchema =\n\t\t\tstrict === true\n\t\t\t\t? {\n\t\t\t\t\t\t...(parameters as Record<string, unknown>),\n\t\t\t\t\t\t...legacyInputSchema,\n\t\t\t\t\t}\n\t\t\t\t: legacyInputSchema;\n\n\t\treturn {\n\t\t\tname: isOAuthToken ? toClaudeCodeName(tool.name) : tool.name,\n\t\t\tdescription: tool.description,\n\t\t\t...(supportsEagerToolInputStreaming ? { eager_input_streaming: true } : {}),\n\t\t\t...(strict === true ? { strict: true } : {}),\n\t\t\tinput_schema: inputSchema,\n\t\t\t...(deferLoading ? { defer_loading: true } : {}),\n\t\t\t...(cacheControl && index === tools.length - 1 ? { cache_control: cacheControl } : {}),\n\t\t};\n\t});\n}\n\nfunction mapStopReason(\n\treason: Anthropic.Messages.StopReason | string,\n\tstopDetails?: RefusalStopDetails | null,\n): { stopReason: StopReason; errorMessage?: string } {\n\tswitch (reason) {\n\t\tcase \"end_turn\":\n\t\t\treturn { stopReason: \"stop\" };\n\t\tcase \"max_tokens\":\n\t\t\treturn { stopReason: \"length\" };\n\t\tcase \"tool_use\":\n\t\t\treturn { stopReason: \"toolUse\" };\n\t\tcase \"refusal\":\n\t\t\treturn {\n\t\t\t\tstopReason: \"error\",\n\t\t\t\terrorMessage: stopDetails?.explanation || `The model refused to complete the request`,\n\t\t\t};\n\t\tcase \"pause_turn\": // Stop is good enough -> resubmit\n\t\t\treturn { stopReason: \"stop\" };\n\t\tcase \"stop_sequence\":\n\t\t\treturn { stopReason: \"stop\" }; // We don't supply stop sequences, so this should never happen\n\t\tcase \"sensitive\": // Content flagged by safety filters (not yet in SDK types)\n\t\t\treturn { stopReason: \"error\", errorMessage: \"Provider stopped with: sensitive\" };\n\t\tdefault:\n\t\t\t// Handle unknown stop reasons gracefully (API may add new values)\n\t\t\tthrow new Error(`Unhandled stop reason: ${reason}`);\n\t}\n}\n"]}
+{"version":3,"file":"anthropic-messages.d.ts","sourceRoot":"","sources":["../../src/api/anthropic-messages.ts"],"names":[],"mappings":"AAAA,OAAO,SAAS,MAAM,mBAAmB,CAAC;AAU1C,OAAO,KAAK,EAWX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAMb,MAAM,aAAa,CAAC;AAwIrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AA2ChE,MAAM,WAAW,gBAAiB,SAAQ,aAAa;IACtD;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B;;;;OAIG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAC9B;;;;;;;;;;;OAWG;IACH,MAAM,CAAC,EAAE,eAAe,CAAC;IACzB;;;;;;;;;;;OAWG;IACH,eAAe,CAAC,EAAE,wBAAwB,CAAC;IAC3C;;;;;OAKG;IACH,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IACtE;;;;OAIG;IACH,MAAM,CAAC,EAAE,SAAS,CAAC;CACnB;AAqOD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CAySzE,CAAC;AA2BF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CA8ClF,CAAC","sourcesContent":["import Anthropic from \"@anthropic-ai/sdk\";\nimport type {\n\tCacheControlEphemeral,\n\tContentBlockParam,\n\tMessageCreateParamsStreaming,\n\tMessageParam,\n\tRawMessageStreamEvent,\n\tRefusalStopDetails,\n} from \"@anthropic-ai/sdk/resources/messages.js\";\nimport { calculateCost } from \"../models.ts\";\nimport type {\n\tAnthropicMessagesCompat,\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tImageContent,\n\tMessage,\n\tModel,\n\tProviderEnv,\n\tProviderHeaders,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingContent,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.ts\";\nimport { splitDeferredTools } from \"../utils/deferred-tools.ts\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { headersToRecord } from \"../utils/headers.ts\";\nimport { parseJsonWithRepair, parseStreamingJson } from \"../utils/json-parse.ts\";\nimport { getPiUserAgent } from \"../utils/pi-user-agent.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { retryProviderRequest } from \"../utils/provider-retry.ts\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.ts\";\n\nimport { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling } from \"./constrained-sampling.ts\";\nimport { buildCopilotDynamicHeaders, hasCopilotVisionInput } from \"./github-copilot-headers.ts\";\nimport { adjustMaxTokensForThinking, buildBaseOptions, clampMaxTokensToContext } from \"./simple-options.ts\";\nimport { transformMessages } from \"./transform-messages.ts\";\n\n/**\n * Resolve cache retention preference.\n * Defaults to \"short\" and uses PI_CACHE_RETENTION for backward compatibility.\n */\nfunction resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {\n\tif (cacheRetention) {\n\t\treturn cacheRetention;\n\t}\n\tif (getProviderEnvValue(\"PI_CACHE_RETENTION\", env) === \"long\") {\n\t\treturn \"long\";\n\t}\n\treturn \"short\";\n}\n\nfunction getCacheControl(\n\tmodel: Model<\"anthropic-messages\">,\n\tcacheRetention?: CacheRetention,\n\tenv?: ProviderEnv,\n): { retention: CacheRetention; cacheControl?: CacheControlEphemeral } {\n\tconst retention = resolveCacheRetention(cacheRetention, env);\n\tif (retention === \"none\") {\n\t\treturn { retention };\n\t}\n\tconst ttl = retention === \"long\" && getAnthropicCompat(model).supportsLongCacheRetention ? \"1h\" : undefined;\n\treturn {\n\t\tretention,\n\t\tcacheControl: { type: \"ephemeral\", ...(ttl && { ttl }) },\n\t};\n}\n\n// Stealth mode: Mimic Claude Code's tool naming exactly\nconst claudeCodeVersion = \"2.1.75\";\n\n// Claude Code 2.x tool names (canonical casing)\n// Source: https://cchistory.mariozechner.at/data/prompts-2.1.11.md\n// To update: https://github.com/badlogic/cchistory\nconst claudeCodeTools = [\n\t\"Read\",\n\t\"Write\",\n\t\"Edit\",\n\t\"Bash\",\n\t\"Grep\",\n\t\"Glob\",\n\t\"AskUserQuestion\",\n\t\"EnterPlanMode\",\n\t\"ExitPlanMode\",\n\t\"KillShell\",\n\t\"NotebookEdit\",\n\t\"Skill\",\n\t\"Task\",\n\t\"TaskOutput\",\n\t\"TodoWrite\",\n\t\"WebFetch\",\n\t\"WebSearch\",\n];\n\nconst ccToolLookup = new Map(claudeCodeTools.map((t) => [t.toLowerCase(), t]));\n\n// Convert tool name to CC canonical casing if it matches (case-insensitive)\nconst toClaudeCodeName = (name: string) => ccToolLookup.get(name.toLowerCase()) ?? name;\nconst fromClaudeCodeName = (name: string, tools?: Tool[]) => {\n\tif (tools && tools.length > 0) {\n\t\tconst lowerName = name.toLowerCase();\n\t\tconst matchedTool = tools.find((tool) => tool.name.toLowerCase() === lowerName);\n\t\tif (matchedTool) return matchedTool.name;\n\t}\n\treturn name;\n};\n\n/**\n * Convert content blocks to Anthropic API format\n */\nfunction convertContentBlocks(content: (TextContent | ImageContent)[]):\n\t| string\n\t| Array<\n\t\t\t| { type: \"text\"; text: string }\n\t\t\t| {\n\t\t\t\t\ttype: \"image\";\n\t\t\t\t\tsource: {\n\t\t\t\t\t\ttype: \"base64\";\n\t\t\t\t\t\tmedia_type: \"image/jpeg\" | \"image/png\" | \"image/gif\" | \"image/webp\";\n\t\t\t\t\t\tdata: string;\n\t\t\t\t\t};\n\t\t\t  }\n\t  > {\n\t// If only text blocks, return as concatenated string for simplicity\n\tconst hasImages = content.some((c) => c.type === \"image\");\n\tif (!hasImages) {\n\t\treturn sanitizeSurrogates(content.map((c) => (c as TextContent).text).join(\"\\n\"));\n\t}\n\n\t// If we have images, convert to content block array\n\tconst blocks = content.map((block) => {\n\t\tif (block.type === \"text\") {\n\t\t\treturn {\n\t\t\t\ttype: \"text\" as const,\n\t\t\t\ttext: sanitizeSurrogates(block.text),\n\t\t\t};\n\t\t}\n\t\treturn {\n\t\t\ttype: \"image\" as const,\n\t\t\tsource: {\n\t\t\t\ttype: \"base64\" as const,\n\t\t\t\tmedia_type: block.mimeType as \"image/jpeg\" | \"image/png\" | \"image/gif\" | \"image/webp\",\n\t\t\t\tdata: block.data,\n\t\t\t},\n\t\t};\n\t});\n\n\t// If only images (no text), add placeholder text block\n\tconst hasText = blocks.some((b) => b.type === \"text\");\n\tif (!hasText) {\n\t\tblocks.unshift({\n\t\t\ttype: \"text\" as const,\n\t\t\ttext: \"(see attached image)\",\n\t\t});\n\t}\n\n\treturn blocks;\n}\n\nexport type AnthropicEffort = \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\";\n\nexport type AnthropicThinkingDisplay = \"summarized\" | \"omitted\";\n\ntype MessageCreateParamsStreamingWithFallbacks = MessageCreateParamsStreaming & {\n\tfallbacks?: readonly { model: string }[];\n};\n\nconst FINE_GRAINED_TOOL_STREAMING_BETA = \"fine-grained-tool-streaming-2025-05-14\";\nconst INTERLEAVED_THINKING_BETA = \"interleaved-thinking-2025-05-14\";\nconst SERVER_SIDE_FALLBACK_BETA = \"server-side-fallback-2026-07-01\";\n\nfunction shouldUseServerSideFallbackBeta(model: Model<\"anthropic-messages\">): boolean {\n\treturn (model.compat?.allowedFallbackModels?.length ?? 0) > 0;\n}\n\nfunction getAnthropicCompat(\n\tmodel: Model<\"anthropic-messages\">,\n): Required<Omit<AnthropicMessagesCompat, \"forceAdaptiveThinking\" | \"allowedFallbackModels\">> {\n\treturn {\n\t\tsupportsEagerToolInputStreaming: model.compat?.supportsEagerToolInputStreaming ?? true,\n\t\tsupportsLongCacheRetention: model.compat?.supportsLongCacheRetention ?? true,\n\t\tsendSessionAffinityHeaders: model.compat?.sendSessionAffinityHeaders ?? false,\n\t\tsupportsCacheControlOnTools: model.compat?.supportsCacheControlOnTools ?? true,\n\t\tsupportsTemperature: model.compat?.supportsTemperature ?? true,\n\t\tallowEmptySignature: model.compat?.allowEmptySignature ?? false,\n\t\tsupportsStrictTools: model.compat?.supportsStrictTools ?? false,\n\t\tsupportsToolReferences: model.compat?.supportsToolReferences ?? defaultSupportsToolReferences(model),\n\t};\n}\n\n/**\n * Default for `supportsToolReferences`: first-party Anthropic models except\n * Haiku (rejects client-side tool_reference blocks) and models that predate\n * tool search (Claude 3.x, Opus/Sonnet 4.0, Opus 4.1).\n */\nfunction defaultSupportsToolReferences(model: Model<\"anthropic-messages\">): boolean {\n\tif (model.provider !== \"anthropic\" || model.id.includes(\"haiku\")) return false;\n\tconst version = model.id.match(/^claude-(?:opus|sonnet|fable)-(\\d+)(?:-(\\d+))?(?:-|$)/);\n\tif (!version) return false;\n\tconst major = Number(version[1]);\n\tconst minor = version[2] && version[2].length < 8 ? Number(version[2]) : 0;\n\treturn major > 4 || (major === 4 && minor >= 5);\n}\n\nexport interface AnthropicOptions extends StreamOptions {\n\t/**\n\t * Enable extended thinking.\n\t * For adaptive thinking models: the model decides when/how much to think.\n\t * For older models: uses budget-based thinking with thinkingBudgetTokens.\n\t * Default: undefined (thinking is omitted unless `streamSimple()` maps\n\t * a simple reasoning level to this option, or callers set it explicitly).\n\t */\n\tthinkingEnabled?: boolean;\n\t/**\n\t * Token budget for extended thinking (older models only).\n\t * Ignored for adaptive thinking models.\n\t * Default: 1024 when `thinkingEnabled` is true and no budget is provided.\n\t */\n\tthinkingBudgetTokens?: number;\n\t/**\n\t * Effort level for adaptive thinking models.\n\t * Controls how much thinking Claude allocates:\n\t * - \"max\": Always thinks with no constraints (Opus 4.6 only)\n\t * - \"xhigh\": Highest reasoning level (Opus 4.7+, Fable 5)\n\t * - \"high\": Always thinks, deep reasoning\n\t * - \"medium\": Moderate thinking, may skip for simple queries\n\t * - \"low\": Minimal thinking, skips for simple tasks\n\t * Ignored for older models.\n\t * Default: omitted unless `streamSimple()` maps a simple reasoning\n\t * level to this option.\n\t */\n\teffort?: AnthropicEffort;\n\t/**\n\t * Controls how thinking content is returned in API responses.\n\t * - \"summarized\": Thinking blocks contain summarized thinking text.\n\t * - \"omitted\": Thinking blocks return an empty thinking field; the encrypted\n\t *   signature still travels back for multi-turn continuity. Use for faster\n\t *   time-to-first-text-token when your UI does not surface thinking.\n\t *\n\t * Note: Anthropic's API default for Claude Opus 4.7 and Claude Mythos Preview\n\t * is \"omitted\". We default to \"summarized\" here to keep behavior consistent\n\t * with older Claude 4 models. Set this explicitly to \"omitted\" to opt in.\n\t * Default: \"summarized\" when thinking is enabled.\n\t */\n\tthinkingDisplay?: AnthropicThinkingDisplay;\n\t/**\n\t * Whether to request the interleaved thinking beta header for non-adaptive\n\t * thinking models. Adaptive thinking models have interleaved thinking built in,\n\t * so the header is skipped for them regardless of this setting.\n\t * Default: true.\n\t */\n\tinterleavedThinking?: boolean;\n\t/**\n\t * Anthropic tool choice behavior. String values map to Anthropic's built-in\n\t * choices; `{ type: \"tool\", name }` forces a specific tool.\n\t * Default: omitted (Anthropic default behavior, currently equivalent to auto).\n\t */\n\ttoolChoice?: \"auto\" | \"any\" | \"none\" | { type: \"tool\"; name: string };\n\t/**\n\t * Pre-built Anthropic client instance. When provided, skips internal client\n\t * construction entirely. Use this to inject alternative SDK clients such as\n\t * `AnthropicVertex` that shares the same messaging API.\n\t */\n\tclient?: Anthropic;\n}\n\nfunction mergeHeaders(...headerSources: (ProviderHeaders | undefined)[]): ProviderHeaders {\n\tconst merged: ProviderHeaders = {};\n\tfor (const headers of headerSources) {\n\t\tif (headers) {\n\t\t\tObject.assign(merged, headers);\n\t\t}\n\t}\n\treturn merged;\n}\n\nfunction mergeClientHeaders(...headerSources: (ProviderHeaders | undefined)[]): ProviderHeaders {\n\treturn mergeHeaders({ \"User-Agent\": getPiUserAgent() }, ...headerSources);\n}\n\nfunction hasHeader(headers: ProviderHeaders | undefined, name: string): boolean {\n\tif (!headers) return false;\n\tconst expected = name.toLowerCase();\n\tfor (const [key, value] of Object.entries(headers)) {\n\t\tif (key.toLowerCase() === expected && value !== null && value.trim().length > 0) return true;\n\t}\n\treturn false;\n}\n\nfunction assertRequestAuth(provider: string, apiKey: string | undefined, headers: ProviderHeaders | undefined): void {\n\tif (apiKey) return;\n\tif (\n\t\thasHeader(headers, \"authorization\") ||\n\t\thasHeader(headers, \"x-api-key\") ||\n\t\thasHeader(headers, \"cf-aig-authorization\")\n\t) {\n\t\treturn;\n\t}\n\tthrow new Error(`No API key for provider: ${provider}`);\n}\n\ninterface ServerSentEvent {\n\tevent: string | null;\n\tdata: string;\n\traw: string[];\n}\n\ninterface SseDecoderState {\n\tevent: string | null;\n\tdata: string[];\n\traw: string[];\n}\n\nconst ANTHROPIC_MESSAGE_EVENTS: ReadonlySet<string> = new Set([\n\t\"message_start\",\n\t\"message_delta\",\n\t\"message_stop\",\n\t\"content_block_start\",\n\t\"content_block_delta\",\n\t\"content_block_stop\",\n]);\n\nfunction flushSseEvent(state: SseDecoderState): ServerSentEvent | null {\n\tif (!state.event && state.data.length === 0) {\n\t\treturn null;\n\t}\n\n\tconst event: ServerSentEvent = {\n\t\tevent: state.event,\n\t\tdata: state.data.join(\"\\n\"),\n\t\traw: [...state.raw],\n\t};\n\tstate.event = null;\n\tstate.data = [];\n\tstate.raw = [];\n\treturn event;\n}\n\nfunction decodeSseLine(line: string, state: SseDecoderState): ServerSentEvent | null {\n\tif (line === \"\") {\n\t\treturn flushSseEvent(state);\n\t}\n\n\tstate.raw.push(line);\n\tif (line.startsWith(\":\")) {\n\t\treturn null;\n\t}\n\n\tconst delimiterIndex = line.indexOf(\":\");\n\tconst fieldName = delimiterIndex === -1 ? line : line.slice(0, delimiterIndex);\n\tlet value = delimiterIndex === -1 ? \"\" : line.slice(delimiterIndex + 1);\n\tif (value.startsWith(\" \")) {\n\t\tvalue = value.slice(1);\n\t}\n\n\tif (fieldName === \"event\") {\n\t\tstate.event = value;\n\t} else if (fieldName === \"data\") {\n\t\tstate.data.push(value);\n\t}\n\n\treturn null;\n}\n\nfunction nextLineBreakIndex(text: string): number {\n\tconst carriageReturnIndex = text.indexOf(\"\\r\");\n\tconst newlineIndex = text.indexOf(\"\\n\");\n\tif (carriageReturnIndex === -1) {\n\t\treturn newlineIndex;\n\t}\n\tif (newlineIndex === -1) {\n\t\treturn carriageReturnIndex;\n\t}\n\treturn Math.min(carriageReturnIndex, newlineIndex);\n}\n\nfunction consumeLine(text: string): { line: string; rest: string } | null {\n\tconst lineBreakIndex = nextLineBreakIndex(text);\n\tif (lineBreakIndex === -1) {\n\t\treturn null;\n\t}\n\n\tlet nextIndex = lineBreakIndex + 1;\n\tif (text[lineBreakIndex] === \"\\r\" && text[nextIndex] === \"\\n\") {\n\t\tnextIndex += 1;\n\t}\n\n\treturn {\n\t\tline: text.slice(0, lineBreakIndex),\n\t\trest: text.slice(nextIndex),\n\t};\n}\n\nasync function* iterateSseMessages(\n\tbody: ReadableStream<Uint8Array>,\n\tsignal?: AbortSignal,\n): AsyncGenerator<ServerSentEvent> {\n\tconst reader = body.getReader();\n\tconst decoder = new TextDecoder();\n\tconst state: SseDecoderState = { event: null, data: [], raw: [] };\n\tlet buffer = \"\";\n\n\ttry {\n\t\twhile (true) {\n\t\t\tif (signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tconst { value, done } = await reader.read();\n\t\t\tif (done) {\n\t\t\t\tbreak;\n\t\t\t}\n\n\t\t\tbuffer += decoder.decode(value, { stream: true });\n\t\t\tlet consumed = consumeLine(buffer);\n\t\t\twhile (consumed) {\n\t\t\t\tbuffer = consumed.rest;\n\t\t\t\tconst event = decodeSseLine(consumed.line, state);\n\t\t\t\tif (event) {\n\t\t\t\t\tyield event;\n\t\t\t\t}\n\t\t\t\tconsumed = consumeLine(buffer);\n\t\t\t}\n\t\t}\n\n\t\tbuffer += decoder.decode();\n\t\tlet consumed = consumeLine(buffer);\n\t\twhile (consumed) {\n\t\t\tbuffer = consumed.rest;\n\t\t\tconst event = decodeSseLine(consumed.line, state);\n\t\t\tif (event) {\n\t\t\t\tyield event;\n\t\t\t}\n\t\t\tconsumed = consumeLine(buffer);\n\t\t}\n\n\t\tif (buffer.length > 0) {\n\t\t\tconst event = decodeSseLine(buffer, state);\n\t\t\tif (event) {\n\t\t\t\tyield event;\n\t\t\t}\n\t\t}\n\n\t\tconst trailingEvent = flushSseEvent(state);\n\t\tif (trailingEvent) {\n\t\t\tyield trailingEvent;\n\t\t}\n\t} finally {\n\t\treader.releaseLock();\n\t}\n}\n\nasync function* iterateAnthropicEvents(\n\tresponse: Response,\n\tsignal?: AbortSignal,\n): AsyncGenerator<RawMessageStreamEvent> {\n\tif (!response.body) {\n\t\tthrow new Error(\"Attempted to iterate over an Anthropic response with no body\");\n\t}\n\n\tlet sawMessageStart = false;\n\tlet sawMessageEnd = false;\n\n\tfor await (const sse of iterateSseMessages(response.body, signal)) {\n\t\tif (sse.event === \"error\") {\n\t\t\tthrow new Error(sse.data);\n\t\t}\n\n\t\tif (!ANTHROPIC_MESSAGE_EVENTS.has(sse.event ?? \"\")) {\n\t\t\tcontinue;\n\t\t}\n\n\t\ttry {\n\t\t\tconst event = parseJsonWithRepair<RawMessageStreamEvent>(sse.data);\n\t\t\tif (event.type === \"message_start\") {\n\t\t\t\tsawMessageStart = true;\n\t\t\t} else if (event.type === \"message_stop\") {\n\t\t\t\tsawMessageEnd = true;\n\t\t\t}\n\t\t\tyield event;\n\t\t} catch (error) {\n\t\t\tconst message = error instanceof Error ? error.message : String(error);\n\t\t\tthrow new Error(\n\t\t\t\t`Could not parse Anthropic SSE event ${sse.event}: ${message}; data=${sse.data}; raw=${sse.raw.join(\"\\\\n\")}`,\n\t\t\t);\n\t\t}\n\t}\n\n\tif (sawMessageStart && !sawMessageEnd) {\n\t\tthrow new Error(\"Anthropic stream ended before message_stop\");\n\t}\n}\n\nexport const stream: StreamFunction<\"anthropic-messages\", AnthropicOptions> = (\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\toptions?: AnthropicOptions,\n): AssistantMessageEventStream => {\n\tconst stream = new AssistantMessageEventStream();\n\n\t(async () => {\n\t\tconst output: AssistantMessage = {\n\t\t\trole: \"assistant\",\n\t\t\tcontent: [],\n\t\t\tapi: model.api as Api,\n\t\t\tprovider: model.provider,\n\t\t\tmodel: model.id,\n\t\t\tusage: {\n\t\t\t\tinput: 0,\n\t\t\t\toutput: 0,\n\t\t\t\tcacheRead: 0,\n\t\t\t\tcacheWrite: 0,\n\t\t\t\ttotalTokens: 0,\n\t\t\t\tcost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },\n\t\t\t},\n\t\t\tstopReason: \"pending\",\n\t\t\ttimestamp: Date.now(),\n\t\t};\n\n\t\ttry {\n\t\t\tlet client: Anthropic;\n\t\t\tlet isOAuth: boolean;\n\t\t\tlet usageModel = model;\n\n\t\t\tif (options?.client) {\n\t\t\t\tclient = options.client;\n\t\t\t\tisOAuth = false;\n\t\t\t} else {\n\t\t\t\tconst apiKey = options?.apiKey;\n\t\t\t\tassertRequestAuth(model.provider, apiKey, options?.headers);\n\n\t\t\t\tlet copilotDynamicHeaders: Record<string, string> | undefined;\n\t\t\t\tif (model.provider === \"github-copilot\") {\n\t\t\t\t\tconst hasImages = hasCopilotVisionInput(context.messages);\n\t\t\t\t\tcopilotDynamicHeaders = buildCopilotDynamicHeaders({\n\t\t\t\t\t\tmessages: context.messages,\n\t\t\t\t\t\thasImages,\n\t\t\t\t\t});\n\t\t\t\t}\n\n\t\t\t\tconst cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);\n\t\t\t\tconst cacheSessionId = cacheRetention === \"none\" ? undefined : options?.sessionId;\n\n\t\t\t\tconst created = createClient(\n\t\t\t\t\tmodel,\n\t\t\t\t\tapiKey,\n\t\t\t\t\toptions?.interleavedThinking ?? true,\n\t\t\t\t\tshouldUseFineGrainedToolStreamingBeta(model, context),\n\t\t\t\t\tshouldUseServerSideFallbackBeta(model),\n\t\t\t\t\toptions?.headers,\n\t\t\t\t\toptions?.fetch,\n\t\t\t\t\tcopilotDynamicHeaders,\n\t\t\t\t\tcacheSessionId,\n\t\t\t\t);\n\t\t\t\tclient = created.client;\n\t\t\t\tisOAuth = created.isOAuthToken;\n\t\t\t}\n\t\t\tlet params = buildParams(model, context, isOAuth, options);\n\t\t\tconst nextParams = await options?.onPayload?.(params, model);\n\t\t\tif (nextParams !== undefined) {\n\t\t\t\tparams = nextParams as MessageCreateParamsStreaming;\n\t\t\t}\n\t\t\tconst requestOptions = {\n\t\t\t\t...(options?.signal ? { signal: options.signal } : {}),\n\t\t\t\t...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),\n\t\t\t\tmaxRetries: 0,\n\t\t\t};\n\t\t\tconst response = await retryProviderRequest(\n\t\t\t\t() => client.messages.create({ ...params, stream: true }, requestOptions).asResponse(),\n\t\t\t\t{\n\t\t\t\t\tmaxRetries: options?.maxRetries,\n\t\t\t\t\tmaxRetryDelayMs: options?.maxRetryDelayMs,\n\t\t\t\t\tsignal: options?.signal,\n\t\t\t\t},\n\t\t\t);\n\t\t\tawait options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);\n\t\t\tstream.push({ type: \"start\", partial: output });\n\n\t\t\ttype Block = (ThinkingContent | TextContent | (ToolCall & { partialJson: string })) & { index: number };\n\t\t\tconst blocks = output.content as Block[];\n\n\t\t\tfor await (const event of iterateAnthropicEvents(response, options?.signal)) {\n\t\t\t\tif (event.type === \"message_start\") {\n\t\t\t\t\toutput.responseId = event.message.id;\n\t\t\t\t\toutput.model = event.message.model;\n\t\t\t\t\tconst fallbackCost =\n\t\t\t\t\t\toutput.model === model.id\n\t\t\t\t\t\t\t? undefined\n\t\t\t\t\t\t\t: model.compat?.allowedFallbackModels?.find(\n\t\t\t\t\t\t\t\t\t(fallback) => fallback.provider === model.provider && fallback.model === output.model,\n\t\t\t\t\t\t\t\t)?.cost;\n\t\t\t\t\tusageModel = fallbackCost ? { ...model, id: output.model, cost: fallbackCost } : model;\n\t\t\t\t\t// Capture initial token usage from message_start event\n\t\t\t\t\t// This ensures we have input token counts even if the stream is aborted early\n\t\t\t\t\toutput.usage.input = event.message.usage.input_tokens || 0;\n\t\t\t\t\toutput.usage.output = event.message.usage.output_tokens || 0;\n\t\t\t\t\toutput.usage.cacheRead = event.message.usage.cache_read_input_tokens || 0;\n\t\t\t\t\toutput.usage.cacheWrite = event.message.usage.cache_creation_input_tokens || 0;\n\t\t\t\t\toutput.usage.cacheWrite1h = event.message.usage.cache_creation?.ephemeral_1h_input_tokens || 0;\n\t\t\t\t\t// Anthropic doesn't provide total_tokens, compute from components\n\t\t\t\t\toutput.usage.totalTokens =\n\t\t\t\t\t\toutput.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;\n\t\t\t\t\tcalculateCost(usageModel, output.usage);\n\t\t\t\t} else if (event.type === \"content_block_start\") {\n\t\t\t\t\tif (event.content_block.type === \"text\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\t\ttext: event.content_block.text ?? \"\",\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"text_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t} else if (event.content_block.type === \"thinking\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\tthinking: event.content_block.thinking ?? \"\",\n\t\t\t\t\t\t\tthinkingSignature: event.content_block.signature ?? \"\",\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"thinking_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t} else if (event.content_block.type === \"redacted_thinking\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\tthinking: \"[Reasoning redacted]\",\n\t\t\t\t\t\t\tthinkingSignature: event.content_block.data,\n\t\t\t\t\t\t\tredacted: true,\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"thinking_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t} else if (event.content_block.type === \"tool_use\") {\n\t\t\t\t\t\tconst block: Block = {\n\t\t\t\t\t\t\ttype: \"toolCall\",\n\t\t\t\t\t\t\tid: event.content_block.id,\n\t\t\t\t\t\t\tname: isOAuth\n\t\t\t\t\t\t\t\t? fromClaudeCodeName(event.content_block.name, context.tools)\n\t\t\t\t\t\t\t\t: event.content_block.name,\n\t\t\t\t\t\t\targuments: (event.content_block.input as Record<string, any>) ?? {},\n\t\t\t\t\t\t\tpartialJson: \"\",\n\t\t\t\t\t\t\tindex: event.index,\n\t\t\t\t\t\t};\n\t\t\t\t\t\toutput.content.push(block);\n\t\t\t\t\t\tstream.push({ type: \"toolcall_start\", contentIndex: output.content.length - 1, partial: output });\n\t\t\t\t\t}\n\t\t\t\t} else if (event.type === \"content_block_delta\") {\n\t\t\t\t\tif (event.delta.type === \"text_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"text\") {\n\t\t\t\t\t\t\tblock.text += event.delta.text;\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"text_delta\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tdelta: event.delta.text,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t} else if (event.delta.type === \"thinking_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"thinking\") {\n\t\t\t\t\t\t\tblock.thinking += event.delta.thinking;\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tdelta: event.delta.thinking,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t} else if (event.delta.type === \"input_json_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"toolCall\") {\n\t\t\t\t\t\t\tblock.partialJson += event.delta.partial_json;\n\t\t\t\t\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"toolcall_delta\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tdelta: event.delta.partial_json,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t} else if (event.delta.type === \"signature_delta\") {\n\t\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\t\tif (block && block.type === \"thinking\") {\n\t\t\t\t\t\t\tblock.thinkingSignature = block.thinkingSignature || \"\";\n\t\t\t\t\t\t\tblock.thinkingSignature += event.delta.signature;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t} else if (event.type === \"content_block_stop\") {\n\t\t\t\t\tconst index = blocks.findIndex((b) => b.index === event.index);\n\t\t\t\t\tconst block = blocks[index];\n\t\t\t\t\tif (block) {\n\t\t\t\t\t\tdelete (block as any).index;\n\t\t\t\t\t\tif (block.type === \"text\") {\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"text_end\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tcontent: block.text,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t} else if (block.type === \"thinking\") {\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"thinking_end\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\tcontent: block.thinking,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t} else if (block.type === \"toolCall\") {\n\t\t\t\t\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t\t\t\t\t// Finalize in-place and strip the scratch buffer so replay only\n\t\t\t\t\t\t\t// carries parsed arguments.\n\t\t\t\t\t\t\tdelete (block as { partialJson?: string }).partialJson;\n\t\t\t\t\t\t\tstream.push({\n\t\t\t\t\t\t\t\ttype: \"toolcall_end\",\n\t\t\t\t\t\t\t\tcontentIndex: index,\n\t\t\t\t\t\t\t\ttoolCall: block,\n\t\t\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t} else if (event.type === \"message_delta\") {\n\t\t\t\t\tif (event.delta.stop_reason) {\n\t\t\t\t\t\toutput.rawStopReason = event.delta.stop_reason;\n\t\t\t\t\t\tconst stopReasonResult = mapStopReason(event.delta.stop_reason, event.delta.stop_details);\n\t\t\t\t\t\toutput.stopReason = stopReasonResult.stopReason;\n\t\t\t\t\t\tif (stopReasonResult.errorMessage) {\n\t\t\t\t\t\t\toutput.errorMessage = stopReasonResult.errorMessage;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\t// Only update usage fields if present (not null).\n\t\t\t\t\t// Preserves input_tokens from message_start when proxies omit it in message_delta.\n\t\t\t\t\tif (event.usage) {\n\t\t\t\t\t\tif (event.usage.input_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.input = event.usage.input_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tif (event.usage.output_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.output = event.usage.output_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tif (event.usage.cache_read_input_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.cacheRead = event.usage.cache_read_input_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tif (event.usage.cache_creation_input_tokens != null) {\n\t\t\t\t\t\t\toutput.usage.cacheWrite = event.usage.cache_creation_input_tokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t\t// Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the\n\t\t\t\t\t\t// final message_delta usage (a subset of output_tokens). SDK 0.91.1 omits the field from\n\t\t\t\t\t\t// its Usage type, so read it through a narrow cast. Verified against the live API.\n\t\t\t\t\t\tconst thinkingTokens = (event.usage as { output_tokens_details?: { thinking_tokens?: number } })\n\t\t\t\t\t\t\t.output_tokens_details?.thinking_tokens;\n\t\t\t\t\t\tif (thinkingTokens != null) {\n\t\t\t\t\t\t\toutput.usage.reasoning = thinkingTokens;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\t// Anthropic doesn't provide total_tokens, compute from components\n\t\t\t\t\toutput.usage.totalTokens =\n\t\t\t\t\t\toutput.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;\n\t\t\t\t\tcalculateCost(usageModel, output.usage);\n\t\t\t\t}\n\t\t\t}\n\n\t\t\tif (options?.signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tif (output.stopReason === \"pending\") {\n\t\t\t\tthrow new Error(\"Anthropic stream ended without a stop reason\");\n\t\t\t}\n\t\t\tif (output.stopReason === \"aborted\" || output.stopReason === \"error\") {\n\t\t\t\tthrow new Error(output.errorMessage || \"An unknown error occurred\");\n\t\t\t}\n\n\t\t\tstream.push({ type: \"done\", reason: output.stopReason, message: output });\n\t\t\tstream.end();\n\t\t} catch (error) {\n\t\t\tfor (const block of output.content) {\n\t\t\t\tdelete (block as { index?: number }).index;\n\t\t\t\t// partialJson is only a streaming scratch buffer; never persist it.\n\t\t\t\tdelete (block as { partialJson?: string }).partialJson;\n\t\t\t}\n\t\t\toutput.stopReason = options?.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = error instanceof Error ? error.message : JSON.stringify(error);\n\t\t\tstream.push({ type: \"error\", reason: output.stopReason, error: output });\n\t\t\tstream.end();\n\t\t}\n\t})();\n\n\treturn stream;\n};\n\n/**\n * Map ThinkingLevel to Anthropic effort levels for adaptive thinking.\n * Note: effort \"max\" is available on all adaptive-thinking Claude models, while native\n * \"xhigh\" is only available on Opus 4.7/4.8, Sonnet 5, and Fable 5.\n */\nfunction mapThinkingLevelToEffort(\n\tmodel: Model<\"anthropic-messages\">,\n\tlevel: SimpleStreamOptions[\"reasoning\"],\n): AnthropicEffort {\n\tconst mapped = level ? model.thinkingLevelMap?.[level] : undefined;\n\tif (typeof mapped === \"string\") return mapped as AnthropicEffort;\n\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\tcase \"low\":\n\t\t\treturn \"low\";\n\t\tcase \"medium\":\n\t\t\treturn \"medium\";\n\t\tcase \"high\":\n\t\t\treturn \"high\";\n\t\tdefault:\n\t\t\treturn \"high\";\n\t}\n}\n\nexport const streamSimple: StreamFunction<\"anthropic-messages\", SimpleStreamOptions> = (\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tassertRequestAuth(model.provider, options?.apiKey, options?.headers);\n\n\tconst base = {\n\t\t...buildBaseOptions(model, context, options, options?.apiKey),\n\t\ttoolChoice: options?.toolChoice,\n\t} satisfies AnthropicOptions;\n\tif (!options?.reasoning) {\n\t\treturn stream(model, context, {\n\t\t\t...base,\n\t\t\tthinkingEnabled: false,\n\t\t} satisfies AnthropicOptions);\n\t}\n\n\t// For models with adaptive thinking: use an effort level.\n\t// For older models: use budget-based thinking.\n\tif (model.compat?.forceAdaptiveThinking === true) {\n\t\tconst effort = mapThinkingLevelToEffort(model, options.reasoning);\n\t\treturn stream(model, context, {\n\t\t\t...base,\n\t\t\tthinkingEnabled: true,\n\t\t\teffort,\n\t\t} satisfies AnthropicOptions);\n\t}\n\n\t// Undefined means the caller did not request an output cap; let the helper use the model cap.\n\t// Do not coerce to 0 here, or the thinking budget would become the entire max_tokens value.\n\tconst adjusted = adjustMaxTokensForThinking(\n\t\tbase.maxTokens,\n\t\tmodel.maxTokens,\n\t\toptions.reasoning,\n\t\toptions.thinkingBudgets,\n\t);\n\n\tconst maxTokens = clampMaxTokensToContext(model, context, adjusted.maxTokens);\n\n\treturn stream(model, context, {\n\t\t...base,\n\t\tmaxTokens,\n\t\tthinkingEnabled: true,\n\t\tthinkingBudgetTokens: Math.min(adjusted.thinkingBudget, Math.max(0, maxTokens - 1024)),\n\t} satisfies AnthropicOptions);\n};\n\nfunction isOAuthToken(apiKey: string): boolean {\n\treturn apiKey.includes(\"sk-ant-oat\");\n}\n\nfunction createClient(\n\tmodel: Model<\"anthropic-messages\">,\n\tapiKey: string | undefined,\n\tinterleavedThinking: boolean,\n\tuseFineGrainedToolStreamingBeta: boolean,\n\tuseServerSideFallbackBeta: boolean,\n\toptionsHeaders?: ProviderHeaders,\n\tfetch?: typeof globalThis.fetch,\n\tdynamicHeaders?: Record<string, string>,\n\tsessionId?: string,\n): { client: Anthropic; isOAuthToken: boolean } {\n\t// Adaptive thinking models have interleaved thinking built in, so skip the beta header.\n\tconst needsInterleavedBeta = interleavedThinking && model.compat?.forceAdaptiveThinking !== true;\n\tconst betaFeatures: string[] = [];\n\tif (useFineGrainedToolStreamingBeta) {\n\t\tbetaFeatures.push(FINE_GRAINED_TOOL_STREAMING_BETA);\n\t}\n\tif (needsInterleavedBeta) {\n\t\tbetaFeatures.push(INTERLEAVED_THINKING_BETA);\n\t}\n\tif (useServerSideFallbackBeta) {\n\t\tbetaFeatures.push(SERVER_SIDE_FALLBACK_BETA);\n\t}\n\n\t// Copilot: Bearer auth, selective betas.\n\tif (model.provider === \"github-copilot\") {\n\t\tconst client = new Anthropic({\n\t\t\tapiKey: null,\n\t\t\tauthToken: apiKey ?? null,\n\t\t\tbaseURL: model.baseUrl,\n\t\t\tdangerouslyAllowBrowser: true,\n\t\t\tfetch,\n\t\t\tdefaultHeaders: mergeClientHeaders(\n\t\t\t\t{\n\t\t\t\t\taccept: \"application/json\",\n\t\t\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t\t\t...(betaFeatures.length > 0 ? { \"anthropic-beta\": betaFeatures.join(\",\") } : {}),\n\t\t\t\t},\n\t\t\t\tmodel.headers,\n\t\t\t\tdynamicHeaders,\n\t\t\t\toptionsHeaders,\n\t\t\t),\n\t\t});\n\n\t\treturn { client, isOAuthToken: false };\n\t}\n\n\t// OAuth: Bearer auth, Claude Code identity headers\n\tif (apiKey && isOAuthToken(apiKey)) {\n\t\tconst client = new Anthropic({\n\t\t\tapiKey: null,\n\t\t\tauthToken: apiKey,\n\t\t\tbaseURL: model.baseUrl,\n\t\t\tdangerouslyAllowBrowser: true,\n\t\t\tfetch,\n\t\t\tdefaultHeaders: mergeClientHeaders(\n\t\t\t\t{\n\t\t\t\t\taccept: \"application/json\",\n\t\t\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t\t\t\"anthropic-beta\": [\"claude-code-20250219\", \"oauth-2025-04-20\", ...betaFeatures].join(\",\"),\n\t\t\t\t\t\"user-agent\": `claude-cli/${claudeCodeVersion}`,\n\t\t\t\t\t\"x-app\": \"cli\",\n\t\t\t\t},\n\t\t\t\tmodel.headers,\n\t\t\t\toptionsHeaders,\n\t\t\t),\n\t\t});\n\n\t\treturn { client, isOAuthToken: true };\n\t}\n\n\t// API key or header-owned auth.\n\tconst sessionAffinityHeaders: ProviderHeaders =\n\t\tsessionId && getAnthropicCompat(model).sendSessionAffinityHeaders ? { \"x-session-affinity\": sessionId } : {};\n\tconst defaultHeaders = mergeClientHeaders(\n\t\t{\n\t\t\taccept: \"application/json\",\n\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t...(betaFeatures.length > 0 ? { \"anthropic-beta\": betaFeatures.join(\",\") } : {}),\n\t\t},\n\t\tsessionAffinityHeaders,\n\t\tmodel.headers,\n\t\toptionsHeaders,\n\t);\n\tconst client = new Anthropic({\n\t\tapiKey: apiKey ?? null,\n\t\tauthToken: null,\n\t\tbaseURL: model.baseUrl,\n\t\tdangerouslyAllowBrowser: true,\n\t\tfetch,\n\t\tdefaultHeaders,\n\t});\n\n\treturn { client, isOAuthToken: false };\n}\n\nfunction buildParams(\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\tisOAuthToken: boolean,\n\toptions?: AnthropicOptions,\n): MessageCreateParamsStreamingWithFallbacks {\n\tconst { cacheControl } = getCacheControl(model, options?.cacheRetention, options?.env);\n\tconst compat = getAnthropicCompat(model);\n\tconst transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);\n\tconst normalizeToolName = isOAuthToken ? toClaudeCodeName : (name: string) => name;\n\tconst toolPlacement = splitDeferredTools(\n\t\t{ ...context, messages: transformedMessages },\n\t\tcompat.supportsToolReferences,\n\t\tnormalizeToolName,\n\t);\n\tlet immediateTools = toolPlacement.immediate;\n\tlet deferredTools = [...toolPlacement.deferred.values()];\n\tif (immediateTools.length === 0 && deferredTools.length > 0) {\n\t\timmediateTools = deferredTools;\n\t\tdeferredTools = [];\n\t}\n\tconst deferredToolNames = new Set(deferredTools.map((tool) => normalizeToolName(tool.name)));\n\tconst params: MessageCreateParamsStreamingWithFallbacks = {\n\t\tmodel: model.id,\n\t\tmessages: convertMessages(\n\t\t\ttransformedMessages,\n\t\t\tisOAuthToken,\n\t\t\tcacheControl,\n\t\t\tcompat.allowEmptySignature,\n\t\t\tdeferredToolNames,\n\t\t\tnormalizeToolName,\n\t\t),\n\t\tmax_tokens: options?.maxTokens ?? model.maxTokens,\n\t\tstream: true,\n\t};\n\n\t// For OAuth tokens, we MUST include Claude Code identity\n\tif (isOAuthToken) {\n\t\tparams.system = [\n\t\t\t{\n\t\t\t\ttype: \"text\",\n\t\t\t\ttext: \"You are Claude Code, Anthropic's official CLI for Claude.\",\n\t\t\t\t...(cacheControl ? { cache_control: cacheControl } : {}),\n\t\t\t},\n\t\t];\n\t\tif (context.systemPrompt) {\n\t\t\tparams.system.push({\n\t\t\t\ttype: \"text\",\n\t\t\t\ttext: sanitizeSurrogates(context.systemPrompt),\n\t\t\t\t...(cacheControl ? { cache_control: cacheControl } : {}),\n\t\t\t});\n\t\t}\n\t} else if (context.systemPrompt) {\n\t\t// Add cache control to system prompt for non-OAuth tokens\n\t\tparams.system = [\n\t\t\t{\n\t\t\t\ttype: \"text\",\n\t\t\t\ttext: sanitizeSurrogates(context.systemPrompt),\n\t\t\t\t...(cacheControl ? { cache_control: cacheControl } : {}),\n\t\t\t},\n\t\t];\n\t}\n\n\t// Temperature is incompatible with extended thinking and unsupported on Claude Opus 4.7+.\n\tif (options?.temperature !== undefined && !options?.thinkingEnabled && compat.supportsTemperature) {\n\t\tparams.temperature = options.temperature;\n\t}\n\n\tif (immediateTools.length > 0 || deferredTools.length > 0) {\n\t\tparams.tools = [\n\t\t\t...convertTools(\n\t\t\t\timmediateTools,\n\t\t\t\tisOAuthToken,\n\t\t\t\tcompat.supportsEagerToolInputStreaming,\n\t\t\t\tcompat.supportsStrictTools,\n\t\t\t\tcompat.supportsCacheControlOnTools ? cacheControl : undefined,\n\t\t\t),\n\t\t\t...convertTools(\n\t\t\t\tdeferredTools,\n\t\t\t\tisOAuthToken,\n\t\t\t\tcompat.supportsEagerToolInputStreaming,\n\t\t\t\tcompat.supportsStrictTools,\n\t\t\t\tundefined,\n\t\t\t\ttrue,\n\t\t\t),\n\t\t];\n\t}\n\n\t// Configure thinking mode: adaptive, budget-based, or explicitly disabled.\n\tif (model.reasoning) {\n\t\tif (options?.thinkingEnabled) {\n\t\t\t// Default to \"summarized\" so Opus 4.7 and Mythos Preview behave like\n\t\t\t// older Claude 4 models (whose API default is also \"summarized\").\n\t\t\tconst display: AnthropicThinkingDisplay = options.thinkingDisplay ?? \"summarized\";\n\t\t\tif (model.compat?.forceAdaptiveThinking === true) {\n\t\t\t\t// Adaptive thinking: Claude decides when and how much to think.\n\t\t\t\tparams.thinking = { type: \"adaptive\", display };\n\t\t\t\tif (options.effort) {\n\t\t\t\t\t// The Anthropic SDK types can lag newly supported effort values such as \"xhigh\".\n\t\t\t\t\tparams.output_config =\n\t\t\t\t\t\toptions.effort === \"xhigh\"\n\t\t\t\t\t\t\t? ({ effort: options.effort } as unknown as NonNullable<\n\t\t\t\t\t\t\t\t\tMessageCreateParamsStreaming[\"output_config\"]\n\t\t\t\t\t\t\t\t>)\n\t\t\t\t\t\t\t: { effort: options.effort };\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\t// Budget-based thinking for older models\n\t\t\t\tparams.thinking = {\n\t\t\t\t\ttype: \"enabled\",\n\t\t\t\t\tbudget_tokens: options.thinkingBudgetTokens || 1024,\n\t\t\t\t\tdisplay,\n\t\t\t\t};\n\t\t\t}\n\t\t} else if (options?.thinkingEnabled === false && model.thinkingLevelMap?.off !== null) {\n\t\t\tparams.thinking = { type: \"disabled\" };\n\t\t}\n\t}\n\n\tif (options?.metadata) {\n\t\tconst userId = options.metadata.user_id;\n\t\tif (typeof userId === \"string\") {\n\t\t\tparams.metadata = { user_id: userId };\n\t\t}\n\t}\n\n\tif (options?.toolChoice) {\n\t\tif (typeof options.toolChoice === \"string\") {\n\t\t\tparams.tool_choice = { type: options.toolChoice };\n\t\t} else {\n\t\t\tparams.tool_choice = options.toolChoice;\n\t\t}\n\t}\n\n\tconst allowedFallbackModels = model.compat?.allowedFallbackModels;\n\tif (allowedFallbackModels && allowedFallbackModels.length > 0) {\n\t\tparams.fallbacks = allowedFallbackModels.map((fallback) => ({ model: fallback.model }));\n\t}\n\n\treturn params;\n}\n\n// Normalize tool call IDs to match Anthropic's required pattern and length\nfunction normalizeToolCallId(id: string): string {\n\treturn id.replace(/[^a-zA-Z0-9_-]/g, \"_\").slice(0, 64);\n}\n\nfunction convertToolResult(\n\tmsg: ToolResultMessage,\n\tisOAuthToken: boolean,\n\tdeferredToolNames: ReadonlySet<string>,\n\tloadedToolNames: Set<string>,\n\tnormalizeToolName: (name: string) => string,\n): { toolResult: ContentBlockParam; siblingContent: ContentBlockParam[] } {\n\tconst references: Array<{ type: \"tool_reference\"; tool_name: string }> = [];\n\tfor (const name of msg.addedToolNames ?? []) {\n\t\tconst normalizedName = normalizeToolName(name);\n\t\tif (!deferredToolNames.has(normalizedName) || loadedToolNames.has(normalizedName)) continue;\n\t\tloadedToolNames.add(normalizedName);\n\t\treferences.push({\n\t\t\ttype: \"tool_reference\",\n\t\t\ttool_name: isOAuthToken ? toClaudeCodeName(name) : name,\n\t\t});\n\t}\n\tconst convertedContent = convertContentBlocks(msg.content);\n\t// Anthropic rejects tool references mixed with ordinary tool-result content.\n\treturn {\n\t\ttoolResult: {\n\t\t\ttype: \"tool_result\",\n\t\t\ttool_use_id: msg.toolCallId,\n\t\t\tcontent: references.length > 0 ? references : convertedContent,\n\t\t\tis_error: msg.isError,\n\t\t},\n\t\tsiblingContent:\n\t\t\treferences.length === 0\n\t\t\t\t? []\n\t\t\t\t: typeof convertedContent === \"string\"\n\t\t\t\t\t? [{ type: \"text\", text: convertedContent }]\n\t\t\t\t\t: convertedContent,\n\t};\n}\n\nfunction convertMessages(\n\ttransformedMessages: Message[],\n\tisOAuthToken: boolean,\n\tcacheControl?: CacheControlEphemeral,\n\tallowEmptySignature = false,\n\tdeferredToolNames: ReadonlySet<string> = new Set(),\n\tnormalizeToolName: (name: string) => string = (name) => name,\n): MessageParam[] {\n\tconst params: MessageParam[] = [];\n\tconst loadedToolNames = new Set<string>();\n\n\tfor (let i = 0; i < transformedMessages.length; i++) {\n\t\tconst msg = transformedMessages[i];\n\n\t\tif (msg.role === \"user\") {\n\t\t\tif (typeof msg.content === \"string\") {\n\t\t\t\tif (msg.content.trim().length > 0) {\n\t\t\t\t\tparams.push({\n\t\t\t\t\t\trole: \"user\",\n\t\t\t\t\t\tcontent: sanitizeSurrogates(msg.content),\n\t\t\t\t\t});\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\tconst blocks: ContentBlockParam[] = msg.content.map((item) => {\n\t\t\t\t\tif (item.type === \"text\") {\n\t\t\t\t\t\treturn {\n\t\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\t\ttext: sanitizeSurrogates(item.text),\n\t\t\t\t\t\t};\n\t\t\t\t\t} else {\n\t\t\t\t\t\treturn {\n\t\t\t\t\t\t\ttype: \"image\",\n\t\t\t\t\t\t\tsource: {\n\t\t\t\t\t\t\t\ttype: \"base64\",\n\t\t\t\t\t\t\t\tmedia_type: item.mimeType as \"image/jpeg\" | \"image/png\" | \"image/gif\" | \"image/webp\",\n\t\t\t\t\t\t\t\tdata: item.data,\n\t\t\t\t\t\t\t},\n\t\t\t\t\t\t};\n\t\t\t\t\t}\n\t\t\t\t});\n\t\t\t\tconst filteredBlocks = blocks.filter((b) => {\n\t\t\t\t\tif (b.type === \"text\") {\n\t\t\t\t\t\treturn b.text.trim().length > 0;\n\t\t\t\t\t}\n\t\t\t\t\treturn true;\n\t\t\t\t});\n\t\t\t\tif (filteredBlocks.length === 0) continue;\n\t\t\t\tparams.push({\n\t\t\t\t\trole: \"user\",\n\t\t\t\t\tcontent: filteredBlocks,\n\t\t\t\t});\n\t\t\t}\n\t\t} else if (msg.role === \"assistant\") {\n\t\t\tconst blocks: ContentBlockParam[] = [];\n\n\t\t\tfor (const block of msg.content) {\n\t\t\t\tif (block.type === \"text\") {\n\t\t\t\t\tif (block.text.trim().length === 0) continue;\n\t\t\t\t\tblocks.push({\n\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\ttext: sanitizeSurrogates(block.text),\n\t\t\t\t\t});\n\t\t\t\t} else if (block.type === \"thinking\") {\n\t\t\t\t\t// Redacted thinking: pass the opaque payload back as redacted_thinking\n\t\t\t\t\tif (block.redacted) {\n\t\t\t\t\t\tblocks.push({\n\t\t\t\t\t\t\ttype: \"redacted_thinking\",\n\t\t\t\t\t\t\tdata: block.thinkingSignature!,\n\t\t\t\t\t\t});\n\t\t\t\t\t\tcontinue;\n\t\t\t\t\t}\n\t\t\t\t\tconst thinkingSignature = block.thinkingSignature;\n\t\t\t\t\tconst hasThinkingSignature = !!thinkingSignature && thinkingSignature.trim().length > 0;\n\t\t\t\t\tif (block.thinking.trim().length === 0 && !hasThinkingSignature) continue;\n\t\t\t\t\t// If thinking signature is missing/empty (e.g., from aborted stream),\n\t\t\t\t\t// convert to plain text for Anthropic. Some compatible providers emit\n\t\t\t\t\t// and accept empty signatures, so let marked models preserve the block.\n\t\t\t\t\tif (!hasThinkingSignature) {\n\t\t\t\t\t\tblocks.push(\n\t\t\t\t\t\t\tallowEmptySignature\n\t\t\t\t\t\t\t\t? {\n\t\t\t\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\t\t\t\tthinking: sanitizeSurrogates(block.thinking),\n\t\t\t\t\t\t\t\t\t\tsignature: \"\",\n\t\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t\t: {\n\t\t\t\t\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\t\t\t\t\ttext: sanitizeSurrogates(block.thinking),\n\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t);\n\t\t\t\t\t} else {\n\t\t\t\t\t\tblocks.push({\n\t\t\t\t\t\t\ttype: \"thinking\",\n\t\t\t\t\t\t\tthinking: sanitizeSurrogates(block.thinking),\n\t\t\t\t\t\t\tsignature: thinkingSignature,\n\t\t\t\t\t\t});\n\t\t\t\t\t}\n\t\t\t\t} else if (block.type === \"toolCall\") {\n\t\t\t\t\tblocks.push({\n\t\t\t\t\t\ttype: \"tool_use\",\n\t\t\t\t\t\tid: block.id,\n\t\t\t\t\t\tname: isOAuthToken ? toClaudeCodeName(block.name) : block.name,\n\t\t\t\t\t\tinput: block.arguments ?? {},\n\t\t\t\t\t});\n\t\t\t\t}\n\t\t\t}\n\t\t\tif (blocks.length === 0) continue;\n\t\t\tparams.push({\n\t\t\t\trole: \"assistant\",\n\t\t\t\tcontent: blocks,\n\t\t\t});\n\t\t} else if (msg.role === \"toolResult\") {\n\t\t\t// Collect all consecutive toolResult messages, needed for z.ai Anthropic endpoint.\n\t\t\tconst toolResults: ContentBlockParam[] = [];\n\t\t\tconst siblingContent: ContentBlockParam[] = [];\n\t\t\tlet j = i;\n\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\tconst converted = convertToolResult(\n\t\t\t\t\ttransformedMessages[j] as ToolResultMessage,\n\t\t\t\t\tisOAuthToken,\n\t\t\t\t\tdeferredToolNames,\n\t\t\t\t\tloadedToolNames,\n\t\t\t\t\tnormalizeToolName,\n\t\t\t\t);\n\t\t\t\ttoolResults.push(converted.toolResult);\n\t\t\t\tsiblingContent.push(...converted.siblingContent);\n\t\t\t\tj++;\n\t\t\t}\n\n\t\t\t// Skip the messages we've already processed.\n\t\t\ti = j - 1;\n\n\t\t\t// Displaced reference-bearing results must follow every tool_result block.\n\t\t\tparams.push({\n\t\t\t\trole: \"user\",\n\t\t\t\tcontent: [...toolResults, ...siblingContent],\n\t\t\t});\n\t\t}\n\t}\n\n\t// Add cache_control to the last user message to cache conversation history\n\tif (cacheControl && params.length > 0) {\n\t\tconst lastMessage = params[params.length - 1];\n\t\tif (lastMessage.role === \"user\") {\n\t\t\tif (Array.isArray(lastMessage.content)) {\n\t\t\t\tconst lastBlock = lastMessage.content[lastMessage.content.length - 1];\n\t\t\t\tif (\n\t\t\t\t\tlastBlock &&\n\t\t\t\t\t(lastBlock.type === \"text\" || lastBlock.type === \"image\" || lastBlock.type === \"tool_result\")\n\t\t\t\t) {\n\t\t\t\t\t(lastBlock as any).cache_control = cacheControl;\n\t\t\t\t}\n\t\t\t} else if (typeof lastMessage.content === \"string\") {\n\t\t\t\tlastMessage.content = [\n\t\t\t\t\t{\n\t\t\t\t\t\ttype: \"text\",\n\t\t\t\t\t\ttext: lastMessage.content,\n\t\t\t\t\t\tcache_control: cacheControl,\n\t\t\t\t\t},\n\t\t\t\t] as any;\n\t\t\t}\n\t\t}\n\t}\n\n\treturn params;\n}\n\nfunction shouldUseFineGrainedToolStreamingBeta(model: Model<\"anthropic-messages\">, context: Context): boolean {\n\treturn !!context.tools?.length && !getAnthropicCompat(model).supportsEagerToolInputStreaming;\n}\n\nfunction convertTools(\n\ttools: Tool[],\n\tisOAuthToken: boolean,\n\tsupportsEagerToolInputStreaming: boolean,\n\tsupportsStrictTools: boolean,\n\tcacheControl?: CacheControlEphemeral,\n\tdeferLoading = false,\n): Anthropic.Messages.Tool[] {\n\tif (!tools) return [];\n\n\treturn tools.map((tool, index) => {\n\t\tconst strict = resolveJsonSchemaStrictSampling(tool, supportsStrictTools);\n\t\tconst parameters = getJsonSchemaToolParameters(tool, strict);\n\t\tconst schema = parameters as { properties?: unknown; required?: string[] };\n\t\tconst legacyInputSchema = {\n\t\t\ttype: \"object\" as const,\n\t\t\tproperties: schema.properties ?? {},\n\t\t\trequired: schema.required ?? [],\n\t\t};\n\t\tconst inputSchema =\n\t\t\tstrict === true\n\t\t\t\t? {\n\t\t\t\t\t\t...(parameters as Record<string, unknown>),\n\t\t\t\t\t\t...legacyInputSchema,\n\t\t\t\t\t}\n\t\t\t\t: legacyInputSchema;\n\n\t\treturn {\n\t\t\tname: isOAuthToken ? toClaudeCodeName(tool.name) : tool.name,\n\t\t\tdescription: tool.description,\n\t\t\t...(supportsEagerToolInputStreaming ? { eager_input_streaming: true } : {}),\n\t\t\t...(strict === true ? { strict: true } : {}),\n\t\t\tinput_schema: inputSchema,\n\t\t\t...(deferLoading ? { defer_loading: true } : {}),\n\t\t\t...(cacheControl && index === tools.length - 1 ? { cache_control: cacheControl } : {}),\n\t\t};\n\t});\n}\n\nfunction mapStopReason(\n\treason: Anthropic.Messages.StopReason | string,\n\tstopDetails?: RefusalStopDetails | null,\n): { stopReason: StopReason; errorMessage?: string } {\n\tswitch (reason) {\n\t\tcase \"end_turn\":\n\t\t\treturn { stopReason: \"stop\" };\n\t\tcase \"max_tokens\":\n\t\t\treturn { stopReason: \"length\" };\n\t\tcase \"tool_use\":\n\t\t\treturn { stopReason: \"toolUse\" };\n\t\tcase \"refusal\":\n\t\t\treturn {\n\t\t\t\tstopReason: \"error\",\n\t\t\t\terrorMessage: stopDetails?.explanation || `The model refused to complete the request`,\n\t\t\t};\n\t\tcase \"pause_turn\": // Stop is good enough -> resubmit\n\t\t\treturn { stopReason: \"stop\" };\n\t\tcase \"stop_sequence\":\n\t\t\treturn { stopReason: \"stop\" }; // We don't supply stop sequences, so this should never happen\n\t\tcase \"sensitive\": // Content flagged by safety filters (not yet in SDK types)\n\t\t\treturn { stopReason: \"error\", errorMessage: \"Provider stopped with: sensitive\" };\n\t\tdefault:\n\t\t\t// Handle unknown stop reasons gracefully (API may add new values)\n\t\t\tthrow new Error(`Unhandled stop reason: ${reason}`);\n\t}\n}\n"]}

package/node_modules/@earendil-works/pi-ai/dist/api/anthropic-messages.js

@@ -110,6 +110,10 @@ function convertContentBlocks(content) {
 }
 const FINE_GRAINED_TOOL_STREAMING_BETA = "fine-grained-tool-streaming-2025-05-14";
 const INTERLEAVED_THINKING_BETA = "interleaved-thinking-2025-05-14";
+const SERVER_SIDE_FALLBACK_BETA = "server-side-fallback-2026-07-01";
+function shouldUseServerSideFallbackBeta(model) {
+    return (model.compat?.allowedFallbackModels?.length ?? 0) > 0;
+}
 function getAnthropicCompat(model) {
     return {
         supportsEagerToolInputStreaming: model.compat?.supportsEagerToolInputStreaming ?? true,
@@ -146,16 +150,8 @@ function mergeHeaders(...headerSources) {
     }
     return merged;
 }
-function mergeClientHeaders(model, ...headerSources) {
-    const merged = mergeHeaders(...headerSources);
-    if (model.provider === "kimi-coding") {
-        for (const name of Object.keys(merged)) {
-            if (name.toLowerCase() === "user-agent")
-                delete merged[name];
-        }
-        merged["User-Agent"] = getPiUserAgent();
-    }
-    return merged;
+function mergeClientHeaders(...headerSources) {
+    return mergeHeaders({ "User-Agent": getPiUserAgent() }, ...headerSources);
 }
 function hasHeader(headers, name) {
     if (!headers)
@@ -351,6 +347,7 @@ export const stream = (model, context, options) => {
         try {
             let client;
             let isOAuth;
+            let usageModel = model;
             if (options?.client) {
                 client = options.client;
                 isOAuth = false;
@@ -368,7 +365,7 @@ export const stream = (model, context, options) => {
                 }
                 const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
                 const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
-                const created = createClient(model, apiKey, options?.interleavedThinking ?? true, shouldUseFineGrainedToolStreamingBeta(model, context), options?.headers, options?.fetch, copilotDynamicHeaders, cacheSessionId);
+                const created = createClient(model, apiKey, options?.interleavedThinking ?? true, shouldUseFineGrainedToolStreamingBeta(model, context), shouldUseServerSideFallbackBeta(model), options?.headers, options?.fetch, copilotDynamicHeaders, cacheSessionId);
                 client = created.client;
                 isOAuth = created.isOAuthToken;
             }
@@ -393,6 +390,11 @@ export const stream = (model, context, options) => {
             for await (const event of iterateAnthropicEvents(response, options?.signal)) {
                 if (event.type === "message_start") {
                     output.responseId = event.message.id;
+                    output.model = event.message.model;
+                    const fallbackCost = output.model === model.id
+                        ? undefined
+                        : model.compat?.allowedFallbackModels?.find((fallback) => fallback.provider === model.provider && fallback.model === output.model)?.cost;
+                    usageModel = fallbackCost ? { ...model, id: output.model, cost: fallbackCost } : model;
                     // Capture initial token usage from message_start event
                     // This ensures we have input token counts even if the stream is aborted early
                     output.usage.input = event.message.usage.input_tokens || 0;
@@ -403,7 +405,7 @@ export const stream = (model, context, options) => {
                     // Anthropic doesn't provide total_tokens, compute from components
                     output.usage.totalTokens =
                         output.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;
-                    calculateCost(model, output.usage);
+                    calculateCost(usageModel, output.usage);
                 }
                 else if (event.type === "content_block_start") {
                     if (event.content_block.type === "text") {
@@ -572,7 +574,7 @@ export const stream = (model, context, options) => {
                     // Anthropic doesn't provide total_tokens, compute from components
                     output.usage.totalTokens =
                         output.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;
-                    calculateCost(model, output.usage);
+                    calculateCost(usageModel, output.usage);
                 }
             }
             if (options?.signal?.aborted) {
@@ -624,9 +626,15 @@ function mapThinkingLevelToEffort(model, level) {
 }
 export const streamSimple = (model, context, options) => {
     assertRequestAuth(model.provider, options?.apiKey, options?.headers);
-    const base = buildBaseOptions(model, context, options, options?.apiKey);
+    const base = {
+        ...buildBaseOptions(model, context, options, options?.apiKey),
+        toolChoice: options?.toolChoice,
+    };
     if (!options?.reasoning) {
-        return stream(model, context, { ...base, thinkingEnabled: false });
+        return stream(model, context, {
+            ...base,
+            thinkingEnabled: false,
+        });
     }
     // For models with adaptive thinking: use an effort level.
     // For older models: use budget-based thinking.
@@ -652,7 +660,7 @@ export const streamSimple = (model, context, options) => {
 function isOAuthToken(apiKey) {
     return apiKey.includes("sk-ant-oat");
 }
-function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStreamingBeta, optionsHeaders, fetch, dynamicHeaders, sessionId) {
+function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStreamingBeta, useServerSideFallbackBeta, optionsHeaders, fetch, dynamicHeaders, sessionId) {
     // Adaptive thinking models have interleaved thinking built in, so skip the beta header.
     const needsInterleavedBeta = interleavedThinking && model.compat?.forceAdaptiveThinking !== true;
     const betaFeatures = [];
@@ -662,6 +670,9 @@ function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStre
     if (needsInterleavedBeta) {
         betaFeatures.push(INTERLEAVED_THINKING_BETA);
     }
+    if (useServerSideFallbackBeta) {
+        betaFeatures.push(SERVER_SIDE_FALLBACK_BETA);
+    }
     // Copilot: Bearer auth, selective betas.
     if (model.provider === "github-copilot") {
         const client = new Anthropic({
@@ -670,7 +681,7 @@ function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStre
             baseURL: model.baseUrl,
             dangerouslyAllowBrowser: true,
             fetch,
-            defaultHeaders: mergeClientHeaders(model, {
+            defaultHeaders: mergeClientHeaders({
                 accept: "application/json",
                 "anthropic-dangerous-direct-browser-access": "true",
                 ...(betaFeatures.length > 0 ? { "anthropic-beta": betaFeatures.join(",") } : {}),
@@ -686,7 +697,7 @@ function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStre
             baseURL: model.baseUrl,
             dangerouslyAllowBrowser: true,
             fetch,
-            defaultHeaders: mergeClientHeaders(model, {
+            defaultHeaders: mergeClientHeaders({
                 accept: "application/json",
                 "anthropic-dangerous-direct-browser-access": "true",
                 "anthropic-beta": ["claude-code-20250219", "oauth-2025-04-20", ...betaFeatures].join(","),
@@ -698,7 +709,7 @@ function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStre
     }
     // API key or header-owned auth.
     const sessionAffinityHeaders = sessionId && getAnthropicCompat(model).sendSessionAffinityHeaders ? { "x-session-affinity": sessionId } : {};
-    const defaultHeaders = mergeClientHeaders(model, {
+    const defaultHeaders = mergeClientHeaders({
         accept: "application/json",
         "anthropic-dangerous-direct-browser-access": "true",
         ...(betaFeatures.length > 0 ? { "anthropic-beta": betaFeatures.join(",") } : {}),
@@ -813,6 +824,10 @@ function buildParams(model, context, isOAuthToken, options) {
             params.tool_choice = options.toolChoice;
         }
     }
+    const allowedFallbackModels = model.compat?.allowedFallbackModels;
+    if (allowedFallbackModels && allowedFallbackModels.length > 0) {
+        params.fallbacks = allowedFallbackModels.map((fallback) => ({ model: fallback.model }));
+    }
     return params;
 }
 // Normalize tool call IDs to match Anthropic's required pattern and length