@earendil-works/pi-ai 0.80.5 → 0.80.7

package/README.md

@@ -730,7 +730,7 @@ if (model.reasoning) {
 const response = await models.completeSimple(model, {
   messages: [{ role: 'user', content: 'Solve: 2x + 5 = 13', timestamp: Date.now() }]
 }, {
-  reasoning: 'medium'  // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh'
+  reasoning: 'medium'  // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max'
 });
 
 // Access thinking and text blocks
@@ -743,6 +743,8 @@ for (const block of response.content) {
 }
 ```
 
+`xhigh` and `max` are model-specific, opt-in levels. Use `getSupportedThinkingLevels(model)` to determine whether a concrete model exposes either level; models such as GPT-5.6 can expose both.
+
 ### Provider-Specific Options (stream/complete)
 
 `models.stream()`/`complete()` accept the owning API's full option set. Use `hasApi()` to narrow a dynamically looked-up model to its API for full option typing:
@@ -999,7 +1001,7 @@ Custom models can carry `headers` (e.g. proxies behind bot detection) and `compa
 
 Some OpenAI-compatible servers do not understand the `developer` role used for reasoning-capable models. For those providers, set `compat.supportsDeveloperRole` to `false` so the system prompt is sent as a `system` message instead. If the server also does not support `reasoning_effort`, set `compat.supportsReasoningEffort` to `false` too. This commonly applies to Ollama, vLLM, SGLang, and similar OpenAI-compatible servers.
 
-Use model-level `thinkingLevelMap` to describe model-specific thinking controls. Keys are pi thinking levels (`off`, `minimal`, `low`, `medium`, `high`, `xhigh`). Missing keys use provider defaults, string values are sent to the provider, and `null` marks a level unsupported.
+Use model-level `thinkingLevelMap` to describe model-specific thinking controls. Keys are pi thinking levels (`off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`). Missing standard levels through `high` use provider defaults; `xhigh` and `max` are opt-in and require a non-null map entry. String values are sent to the provider, `null` marks a level unsupported, and maps may skip levels.
 
 ```typescript
 const ollamaReasoningModel: Model<'openai-completions'> = {
@@ -1068,7 +1070,8 @@ interface OpenAICompletionsCompat {
   supportsReasoningEffort?: boolean; // Whether provider supports `reasoning_effort` (default: true)
   supportsUsageInStreaming?: boolean; // Whether provider supports `stream_options: { include_usage: true }` (default: true)
   supportsStrictMode?: boolean;      // Whether provider supports `strict` in tool definitions (default: true)
-  sendSessionAffinityHeaders?: boolean; // Whether to send `session_id`, `x-client-request-id`, and `x-session-affinity` from `sessionId` when caching is enabled (default: false)
+  sendSessionAffinityHeaders?: boolean; // Send session-affinity data from `sessionId` (default: false)
+  sessionAffinityFormat?: 'openai' | 'openai-nosession' | 'openrouter'; // Format for session affinity: 'openai' uses `prompt_cache_key`, `session_id`, `x-client-request-id`, and `x-session-affinity`; 'openai-nosession' uses `prompt_cache_key`, `x-client-request-id`, and `x-session-affinity`; 'openrouter' uses `x-session-id` (default: auto-detected)
   maxTokensField?: 'max_completion_tokens' | 'max_tokens';  // Which field name to use (default: max_completion_tokens)
   requiresToolResultName?: boolean;  // Whether tool results require the `name` field (default: false)
   requiresAssistantAfterToolResult?: boolean; // Whether tool results must be followed by an assistant message (default: false)
@@ -1083,7 +1086,7 @@ interface OpenAICompletionsCompat {
 
 interface OpenAIResponsesCompat {
   supportsDeveloperRole?: boolean;   // Whether provider supports `developer` role vs `system` (default: true)
-  sendSessionIdHeader?: boolean;     // Whether to send `session_id` from `sessionId` when caching is enabled (default: true)
+  sessionAffinityFormat?: 'openai' | 'openai-nosession' | 'openrouter'; // Session-affinity header format: 'openai' sends `session_id` and `x-client-request-id`; 'openai-nosession' sends `x-client-request-id`; 'openrouter' sends `x-session-id`. Does not affect the `prompt_cache_key` body param (default: auto-detected)
   supportsLongCacheRetention?: boolean; // Whether provider supports `prompt_cache_retention: "24h"` (default: true)
 }
 ```

package/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;AAoIrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAkBhE,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;AAiOD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CAiRzE,CAAC;AA0BF,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 { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { headersToRecord } from \"../utils/headers.ts\";\nimport { parseJsonWithRepair, parseStreamingJson } from \"../utils/json-parse.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.ts\";\n\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};\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 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: \"stop\",\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\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: options?.maxRetries ?? 0,\n\t\t\t};\n\t\t\tconst response = await client.messages.create({ ...params, stream: true }, requestOptions).asResponse();\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: \"\",\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: \"\",\n\t\t\t\t\t\t\tthinkingSignature: \"\",\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\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.input_tokens != null) {\n\t\t\t\t\t\toutput.usage.input = event.usage.input_tokens;\n\t\t\t\t\t}\n\t\t\t\t\tif (event.usage.output_tokens != null) {\n\t\t\t\t\t\toutput.usage.output = event.usage.output_tokens;\n\t\t\t\t\t}\n\t\t\t\t\tif (event.usage.cache_read_input_tokens != null) {\n\t\t\t\t\t\toutput.usage.cacheRead = event.usage.cache_read_input_tokens;\n\t\t\t\t\t}\n\t\t\t\t\tif (event.usage.cache_creation_input_tokens != null) {\n\t\t\t\t\t\toutput.usage.cacheWrite = event.usage.cache_creation_input_tokens;\n\t\t\t\t\t}\n\t\t\t\t\t// Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the\n\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// its Usage type, so read it through a narrow cast. Verified against the live API.\n\t\t\t\t\tconst thinkingTokens = (event.usage as { output_tokens_details?: { thinking_tokens?: number } })\n\t\t\t\t\t\t.output_tokens_details?.thinking_tokens;\n\t\t\t\t\tif (thinkingTokens != null) {\n\t\t\t\t\t\toutput.usage.reasoning = thinkingTokens;\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 === \"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 only valid on Opus 4.6, while Opus 4.7+ and Fable 5 support \"xhigh\".\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\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\tdefaultHeaders: mergeHeaders(\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\tdefaultHeaders: mergeHeaders(\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 = mergeHeaders(\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\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 params: MessageCreateParamsStreaming = {\n\t\tmodel: model.id,\n\t\tmessages: convertMessages(context.messages, model, isOAuthToken, cacheControl, compat.allowEmptySignature),\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 (context.tools && context.tools.length > 0) {\n\t\tparams.tools = convertTools(\n\t\t\tcontext.tools,\n\t\t\tisOAuthToken,\n\t\t\tcompat.supportsEagerToolInputStreaming,\n\t\t\tcompat.supportsCacheControlOnTools ? cacheControl : undefined,\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 convertMessages(\n\tmessages: Message[],\n\tmodel: Model<\"anthropic-messages\">,\n\tisOAuthToken: boolean,\n\tcacheControl?: CacheControlEphemeral,\n\tallowEmptySignature = false,\n): MessageParam[] {\n\tconst params: MessageParam[] = [];\n\n\t// Transform messages for cross-provider compatibility\n\tconst transformedMessages = transformMessages(messages, model, normalizeToolCallId);\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\tif (block.thinking.trim().length === 0) 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 (!block.thinkingSignature || block.thinkingSignature.trim().length === 0) {\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: block.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\n\t\t\t// Add the current tool result\n\t\t\ttoolResults.push({\n\t\t\t\ttype: \"tool_result\",\n\t\t\t\ttool_use_id: msg.toolCallId,\n\t\t\t\tcontent: convertContentBlocks(msg.content),\n\t\t\t\tis_error: msg.isError,\n\t\t\t});\n\n\t\t\t// Look ahead for consecutive toolResult messages\n\t\t\tlet j = i + 1;\n\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\tconst nextMsg = transformedMessages[j] as ToolResultMessage; // We know it's a toolResult\n\t\t\t\ttoolResults.push({\n\t\t\t\t\ttype: \"tool_result\",\n\t\t\t\t\ttool_use_id: nextMsg.toolCallId,\n\t\t\t\t\tcontent: convertContentBlocks(nextMsg.content),\n\t\t\t\t\tis_error: nextMsg.isError,\n\t\t\t\t});\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// Add a single user message with all tool results\n\t\t\tparams.push({\n\t\t\t\trole: \"user\",\n\t\t\t\tcontent: toolResults,\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\tcacheControl?: CacheControlEphemeral,\n): Anthropic.Messages.Tool[] {\n\tif (!tools) return [];\n\n\treturn tools.map((tool, index) => {\n\t\tconst schema = tool.parameters as { properties?: unknown; required?: string[] };\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\tinput_schema: {\n\t\t\t\ttype: \"object\",\n\t\t\t\tproperties: schema.properties ?? {},\n\t\t\t\trequired: schema.required ?? [],\n\t\t\t},\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\" };\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;AAqIrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAiChE,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;AAiOD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CAmRzE,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 { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.ts\";\n\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\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 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: \"stop\",\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\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: options?.maxRetries ?? 0,\n\t\t\t};\n\t\t\tconst response = await client.messages.create({ ...params, stream: true }, requestOptions).asResponse();\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: \"\",\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: \"\",\n\t\t\t\t\t\t\tthinkingSignature: \"\",\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\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 === \"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\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\tdefaultHeaders: mergeHeaders(\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\tdefaultHeaders: mergeHeaders(\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 = mergeHeaders(\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\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.supportsCacheControlOnTools ? cacheControl : undefined,\n\t\t\t),\n\t\t\t...convertTools(deferredTools, isOAuthToken, compat.supportsEagerToolInputStreaming, undefined, true),\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\tcacheControl?: CacheControlEphemeral,\n\tdeferLoading = false,\n): Anthropic.Messages.Tool[] {\n\tif (!tools) return [];\n\n\treturn tools.map((tool, index) => {\n\t\tconst schema = tool.parameters as { properties?: unknown; required?: string[] };\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\tinput_schema: {\n\t\t\t\ttype: \"object\",\n\t\t\t\tproperties: schema.properties ?? {},\n\t\t\t\trequired: schema.required ?? [],\n\t\t\t},\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\" };\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/dist/api/anthropic-messages.js

@@ -1,5 +1,6 @@
 import Anthropic from "@anthropic-ai/sdk";
 import { calculateCost } from "../models.js";
+import { splitDeferredTools } from "../utils/deferred-tools.js";
 import { AssistantMessageEventStream } from "../utils/event-stream.js";
 import { headersToRecord } from "../utils/headers.js";
 import { parseJsonWithRepair, parseStreamingJson } from "../utils/json-parse.js";
@@ -114,8 +115,24 @@ function getAnthropicCompat(model) {
         supportsCacheControlOnTools: model.compat?.supportsCacheControlOnTools ?? true,
         supportsTemperature: model.compat?.supportsTemperature ?? true,
         allowEmptySignature: model.compat?.allowEmptySignature ?? false,
+        supportsToolReferences: model.compat?.supportsToolReferences ?? defaultSupportsToolReferences(model),
     };
 }
+/**
+ * Default for `supportsToolReferences`: first-party Anthropic models except
+ * Haiku (rejects client-side tool_reference blocks) and models that predate
+ * tool search (Claude 3.x, Opus/Sonnet 4.0, Opus 4.1).
+ */
+function defaultSupportsToolReferences(model) {
+    if (model.provider !== "anthropic" || model.id.includes("haiku"))
+        return false;
+    const version = model.id.match(/^claude-(?:opus|sonnet|fable)-(\d+)(?:-(\d+))?(?:-|$)/);
+    if (!version)
+        return false;
+    const major = Number(version[1]);
+    const minor = version[2] && version[2].length < 8 ? Number(version[2]) : 0;
+    return major > 4 || (major === 4 && minor >= 5);
+}
 function mergeHeaders(...headerSources) {
     const merged = {};
     for (const headers of headerSources) {
@@ -510,25 +527,27 @@ export const stream = (model, context, options) => {
                     }
                     // Only update usage fields if present (not null).
                     // Preserves input_tokens from message_start when proxies omit it in message_delta.
-                    if (event.usage.input_tokens != null) {
-                        output.usage.input = event.usage.input_tokens;
-                    }
-                    if (event.usage.output_tokens != null) {
-                        output.usage.output = event.usage.output_tokens;
-                    }
-                    if (event.usage.cache_read_input_tokens != null) {
-                        output.usage.cacheRead = event.usage.cache_read_input_tokens;
-                    }
-                    if (event.usage.cache_creation_input_tokens != null) {
-                        output.usage.cacheWrite = event.usage.cache_creation_input_tokens;
-                    }
-                    // Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the
-                    // final message_delta usage (a subset of output_tokens). SDK 0.91.1 omits the field from
-                    // its Usage type, so read it through a narrow cast. Verified against the live API.
-                    const thinkingTokens = event.usage
-                        .output_tokens_details?.thinking_tokens;
-                    if (thinkingTokens != null) {
-                        output.usage.reasoning = thinkingTokens;
+                    if (event.usage) {
+                        if (event.usage.input_tokens != null) {
+                            output.usage.input = event.usage.input_tokens;
+                        }
+                        if (event.usage.output_tokens != null) {
+                            output.usage.output = event.usage.output_tokens;
+                        }
+                        if (event.usage.cache_read_input_tokens != null) {
+                            output.usage.cacheRead = event.usage.cache_read_input_tokens;
+                        }
+                        if (event.usage.cache_creation_input_tokens != null) {
+                            output.usage.cacheWrite = event.usage.cache_creation_input_tokens;
+                        }
+                        // Anthropic reports reasoning tokens in `output_tokens_details.thinking_tokens` on the
+                        // final message_delta usage (a subset of output_tokens). SDK 0.91.1 omits the field from
+                        // its Usage type, so read it through a narrow cast. Verified against the live API.
+                        const thinkingTokens = event.usage
+                            .output_tokens_details?.thinking_tokens;
+                        if (thinkingTokens != null) {
+                            output.usage.reasoning = thinkingTokens;
+                        }
                     }
                     // Anthropic doesn't provide total_tokens, compute from components
                     output.usage.totalTokens =
@@ -561,7 +580,8 @@ export const stream = (model, context, options) => {
 };
 /**
  * Map ThinkingLevel to Anthropic effort levels for adaptive thinking.
- * Note: effort "max" is only valid on Opus 4.6, while Opus 4.7+ and Fable 5 support "xhigh".
+ * Note: effort "max" is available on all adaptive-thinking Claude models, while native
+ * "xhigh" is only available on Opus 4.7/4.8, Sonnet 5, and Fable 5.
  */
 function mapThinkingLevelToEffort(model, level) {
     const mapped = level ? model.thinkingLevelMap?.[level] : undefined;
@@ -670,9 +690,19 @@ function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStre
 function buildParams(model, context, isOAuthToken, options) {
     const { cacheControl } = getCacheControl(model, options?.cacheRetention, options?.env);
     const compat = getAnthropicCompat(model);
+    const transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);
+    const normalizeToolName = isOAuthToken ? toClaudeCodeName : (name) => name;
+    const toolPlacement = splitDeferredTools({ ...context, messages: transformedMessages }, compat.supportsToolReferences, normalizeToolName);
+    let immediateTools = toolPlacement.immediate;
+    let deferredTools = [...toolPlacement.deferred.values()];
+    if (immediateTools.length === 0 && deferredTools.length > 0) {
+        immediateTools = deferredTools;
+        deferredTools = [];
+    }
+    const deferredToolNames = new Set(deferredTools.map((tool) => normalizeToolName(tool.name)));
     const params = {
         model: model.id,
-        messages: convertMessages(context.messages, model, isOAuthToken, cacheControl, compat.allowEmptySignature),
+        messages: convertMessages(transformedMessages, isOAuthToken, cacheControl, compat.allowEmptySignature, deferredToolNames, normalizeToolName),
         max_tokens: options?.maxTokens ?? model.maxTokens,
         stream: true,
     };
@@ -707,8 +737,11 @@ function buildParams(model, context, isOAuthToken, options) {
     if (options?.temperature !== undefined && !options?.thinkingEnabled && compat.supportsTemperature) {
         params.temperature = options.temperature;
     }
-    if (context.tools && context.tools.length > 0) {
-        params.tools = convertTools(context.tools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsCacheControlOnTools ? cacheControl : undefined);
+    if (immediateTools.length > 0 || deferredTools.length > 0) {
+        params.tools = [
+            ...convertTools(immediateTools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsCacheControlOnTools ? cacheControl : undefined),
+            ...convertTools(deferredTools, isOAuthToken, compat.supportsEagerToolInputStreaming, undefined, true),
+        ];
     }
     // Configure thinking mode: adaptive, budget-based, or explicitly disabled.
     if (model.reasoning) {
@@ -760,10 +793,37 @@ function buildParams(model, context, isOAuthToken, options) {
 function normalizeToolCallId(id) {
     return id.replace(/[^a-zA-Z0-9_-]/g, "_").slice(0, 64);
 }
-function convertMessages(messages, model, isOAuthToken, cacheControl, allowEmptySignature = false) {
+function convertToolResult(msg, isOAuthToken, deferredToolNames, loadedToolNames, normalizeToolName) {
+    const references = [];
+    for (const name of msg.addedToolNames ?? []) {
+        const normalizedName = normalizeToolName(name);
+        if (!deferredToolNames.has(normalizedName) || loadedToolNames.has(normalizedName))
+            continue;
+        loadedToolNames.add(normalizedName);
+        references.push({
+            type: "tool_reference",
+            tool_name: isOAuthToken ? toClaudeCodeName(name) : name,
+        });
+    }
+    const convertedContent = convertContentBlocks(msg.content);
+    // Anthropic rejects tool references mixed with ordinary tool-result content.
+    return {
+        toolResult: {
+            type: "tool_result",
+            tool_use_id: msg.toolCallId,
+            content: references.length > 0 ? references : convertedContent,
+            is_error: msg.isError,
+        },
+        siblingContent: references.length === 0
+            ? []
+            : typeof convertedContent === "string"
+                ? [{ type: "text", text: convertedContent }]
+                : convertedContent,
+    };
+}
+function convertMessages(transformedMessages, isOAuthToken, cacheControl, allowEmptySignature = false, deferredToolNames = new Set(), normalizeToolName = (name) => name) {
     const params = [];
-    // Transform messages for cross-provider compatibility
-    const transformedMessages = transformMessages(messages, model, normalizeToolCallId);
+    const loadedToolNames = new Set();
     for (let i = 0; i < transformedMessages.length; i++) {
         const msg = transformedMessages[i];
         if (msg.role === "user") {
@@ -828,12 +888,14 @@ function convertMessages(messages, model, isOAuthToken, cacheControl, allowEmpty
                         });
                         continue;
                     }
-                    if (block.thinking.trim().length === 0)
+                    const thinkingSignature = block.thinkingSignature;
+                    const hasThinkingSignature = !!thinkingSignature && thinkingSignature.trim().length > 0;
+                    if (block.thinking.trim().length === 0 && !hasThinkingSignature)
                         continue;
                     // If thinking signature is missing/empty (e.g., from aborted stream),
                     // convert to plain text for Anthropic. Some compatible providers emit
                     // and accept empty signatures, so let marked models preserve the block.
-                    if (!block.thinkingSignature || block.thinkingSignature.trim().length === 0) {
+                    if (!hasThinkingSignature) {
                         blocks.push(allowEmptySignature
                             ? {
                                 type: "thinking",
@@ -849,7 +911,7 @@ function convertMessages(messages, model, isOAuthToken, cacheControl, allowEmpty
                         blocks.push({
                             type: "thinking",
                             thinking: sanitizeSurrogates(block.thinking),
-                            signature: block.thinkingSignature,
+                            signature: thinkingSignature,
                         });
                     }
                 }
@@ -870,33 +932,22 @@ function convertMessages(messages, model, isOAuthToken, cacheControl, allowEmpty
             });
         }
         else if (msg.role === "toolResult") {
-            // Collect all consecutive toolResult messages, needed for z.ai Anthropic endpoint
+            // Collect all consecutive toolResult messages, needed for z.ai Anthropic endpoint.
             const toolResults = [];
-            // Add the current tool result
-            toolResults.push({
-                type: "tool_result",
-                tool_use_id: msg.toolCallId,
-                content: convertContentBlocks(msg.content),
-                is_error: msg.isError,
-            });
-            // Look ahead for consecutive toolResult messages
-            let j = i + 1;
+            const siblingContent = [];
+            let j = i;
             while (j < transformedMessages.length && transformedMessages[j].role === "toolResult") {
-                const nextMsg = transformedMessages[j]; // We know it's a toolResult
-                toolResults.push({
-                    type: "tool_result",
-                    tool_use_id: nextMsg.toolCallId,
-                    content: convertContentBlocks(nextMsg.content),
-                    is_error: nextMsg.isError,
-                });
+                const converted = convertToolResult(transformedMessages[j], isOAuthToken, deferredToolNames, loadedToolNames, normalizeToolName);
+                toolResults.push(converted.toolResult);
+                siblingContent.push(...converted.siblingContent);
                 j++;
             }
-            // Skip the messages we've already processed
+            // Skip the messages we've already processed.
             i = j - 1;
-            // Add a single user message with all tool results
+            // Displaced reference-bearing results must follow every tool_result block.
             params.push({
                 role: "user",
-                content: toolResults,
+                content: [...toolResults, ...siblingContent],
             });
         }
     }
@@ -927,7 +978,7 @@ function convertMessages(messages, model, isOAuthToken, cacheControl, allowEmpty
 function shouldUseFineGrainedToolStreamingBeta(model, context) {
     return !!context.tools?.length && !getAnthropicCompat(model).supportsEagerToolInputStreaming;
 }
-function convertTools(tools, isOAuthToken, supportsEagerToolInputStreaming, cacheControl) {
+function convertTools(tools, isOAuthToken, supportsEagerToolInputStreaming, cacheControl, deferLoading = false) {
     if (!tools)
         return [];
     return tools.map((tool, index) => {
@@ -941,6 +992,7 @@ function convertTools(tools, isOAuthToken, supportsEagerToolInputStreaming, cach
                 properties: schema.properties ?? {},
                 required: schema.required ?? [],
             },
+            ...(deferLoading ? { defer_loading: true } : {}),
             ...(cacheControl && index === tools.length - 1 ? { cache_control: cacheControl } : {}),
         };
     });