@eminent337/aery-ai 0.67.68 → 0.67.70

package/README.md

@@ -1,4 +1,4 @@
-# @mariozechner/pi-ai
+# @eminent337/aery-ai
 
 Unified LLM API with automatic model discovery, provider configuration, token and cost tracking, and simple context persistence and hand-off to other models mid-session.
 
@@ -72,15 +72,15 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 ## Installation
 
 ```bash
-npm install @mariozechner/pi-ai
+npm install @eminent337/aery-ai
 ```
 
-TypeBox exports are re-exported from `@mariozechner/pi-ai`: `Type`, `Static`, and `TSchema`.
+TypeBox exports are re-exported from `@eminent337/aery-ai`: `Type`, `Static`, and `TSchema`.
 
 ## Quick Start
 
 ```typescript
-import { Type, getModel, stream, complete, Context, Tool, StringEnum } from '@mariozechner/pi-ai';
+import { Type, getModel, stream, complete, Context, Tool, StringEnum } from '@eminent337/aery-ai';
 
 // Fully typed with auto-complete support for both providers and models
 const model = getModel('openai', 'gpt-4o-mini');
@@ -206,7 +206,7 @@ Tools enable LLMs to interact with external systems. This library uses TypeBox s
 ### Defining Tools
 
 ```typescript
-import { Type, Tool, StringEnum } from '@mariozechner/pi-ai';
+import { Type, Tool, StringEnum } from '@eminent337/aery-ai';
 
 // Define tool parameters with TypeBox
 const weatherTool: Tool = {
@@ -332,7 +332,7 @@ When using `agentLoop`, tool arguments are automatically validated against your
 When implementing your own tool execution loop with `stream()` or `complete()`, use `validateToolCall` to validate arguments before passing them to your tools:
 
 ```typescript
-import { stream, validateToolCall, Tool } from '@mariozechner/pi-ai';
+import { stream, validateToolCall, Tool } from '@eminent337/aery-ai';
 
 const tools: Tool[] = [weatherTool, calculatorTool];
 const s = stream(model, { messages, tools });
@@ -386,7 +386,7 @@ Models with vision capabilities can process images. You can check if a model sup
 
 ```typescript
 import { readFileSync } from 'fs';
-import { getModel, complete } from '@mariozechner/pi-ai';
+import { getModel, complete } from '@eminent337/aery-ai';
 
 const model = getModel('openai', 'gpt-4o-mini');
 
@@ -423,7 +423,7 @@ Many models support thinking/reasoning capabilities where they can show their in
 ### Unified Interface (streamSimple/completeSimple)
 
 ```typescript
-import { getModel, streamSimple, completeSimple } from '@mariozechner/pi-ai';
+import { getModel, streamSimple, completeSimple } from '@eminent337/aery-ai';
 
 // Many models across providers support thinking/reasoning
 const model = getModel('anthropic', 'claude-sonnet-4-20250514');
@@ -461,7 +461,7 @@ for (const block of response.content) {
 For fine-grained control, use the provider-specific options:
 
 ```typescript
-import { getModel, complete } from '@mariozechner/pi-ai';
+import { getModel, complete } from '@eminent337/aery-ai';
 
 // OpenAI Reasoning (o1, o3, gpt-5)
 const openaiModel = getModel('openai', 'gpt-5-mini');
@@ -550,7 +550,7 @@ if (message.stopReason === 'error' || message.stopReason === 'aborted') {
 The abort signal allows you to cancel in-progress requests. Aborted requests have `stopReason === 'aborted'`:
 
 ```typescript
-import { getModel, stream } from '@mariozechner/pi-ai';
+import { getModel, stream } from '@eminent337/aery-ai';
 
 const model = getModel('openai', 'gpt-4o-mini');
 const controller = new AbortController();
@@ -649,7 +649,7 @@ import {
   fauxToolCall,
   registerFauxProvider,
   stream,
-} from '@mariozechner/pi-ai';
+} from '@eminent337/aery-ai';
 
 const registration = registerFauxProvider({
   tokensPerSecond: 50 // optional
@@ -734,7 +734,7 @@ A **provider** offers models through a specific API. For example:
 ### Querying Providers and Models
 
 ```typescript
-import { getProviders, getModels, getModel } from '@mariozechner/pi-ai';
+import { getProviders, getModels, getModel } from '@eminent337/aery-ai';
 
 // Get all available providers
 const providers = getProviders();
@@ -760,7 +760,7 @@ console.log(`Using ${model.name} via ${model.api} API`);
 You can create custom models for local inference servers or custom endpoints:
 
 ```typescript
-import { Model, stream } from '@mariozechner/pi-ai';
+import { Model, stream } from '@eminent337/aery-ai';
 
 // Example: Ollama using OpenAI-compatible API
 const ollamaModel: Model<'openai-completions'> = {
@@ -878,7 +878,7 @@ If `compat` is not set, the library falls back to URL-based detection. If `compa
 Models are typed by their API, which keeps the model metadata accurate. Provider-specific option types are enforced when you call the provider functions directly. The generic `stream` and `complete` functions accept `StreamOptions` with additional provider fields.
 
 ```typescript
-import { streamAnthropic, type AnthropicOptions } from '@mariozechner/pi-ai';
+import { streamAnthropic, type AnthropicOptions } from '@eminent337/aery-ai';
 
 // TypeScript knows this is an Anthropic model
 const claude = getModel('anthropic', 'claude-sonnet-4-20250514');
@@ -907,7 +907,7 @@ When messages from one provider are sent to a different provider, the library au
 ### Example: Multi-Provider Conversation
 
 ```typescript
-import { getModel, complete, Context } from '@mariozechner/pi-ai';
+import { getModel, complete, Context } from '@eminent337/aery-ai';
 
 // Start with Claude
 const claude = getModel('anthropic', 'claude-sonnet-4-20250514');
@@ -952,7 +952,7 @@ This enables flexible workflows where you can:
 The `Context` object can be easily serialized and deserialized using standard JSON methods, making it simple to persist conversations, implement chat history, or transfer contexts between services:
 
 ```typescript
-import { Context, getModel, complete } from '@mariozechner/pi-ai';
+import { Context, getModel, complete } from '@eminent337/aery-ai';
 
 // Create and use a context
 const context: Context = {
@@ -989,7 +989,7 @@ const continuation = await complete(newModel, restored);
 The library supports browser environments. You must pass the API key explicitly since environment variables are not available in browsers:
 
 ```typescript
-import { getModel, complete } from '@mariozechner/pi-ai';
+import { getModel, complete } from '@eminent337/aery-ai';
 
 // API key must be passed explicitly in browser
 const model = getModel('anthropic', 'claude-3-5-haiku-20241022');
@@ -1006,7 +1006,7 @@ const response = await complete(model, {
 ### Browser Compatibility Notes
 
 - Amazon Bedrock (`bedrock-converse-stream`) is not supported in browser environments.
-- OAuth login flows are not supported in browser environments. Use the `@mariozechner/pi-ai/oauth` entry point in Node.js.
+- OAuth login flows are not supported in browser environments. Use the `@eminent337/aery-ai/oauth` entry point in Node.js.
 - In browser builds, Bedrock can still appear in model lists. Calls to Bedrock models fail at runtime.
 - Use a server-side proxy or backend service if you need Bedrock or OAuth-based auth from a web app.
 
@@ -1070,7 +1070,7 @@ This only affects direct API calls to `api.anthropic.com` and `api.openai.com`.
 ### Checking Environment Variables
 
 ```typescript
-import { getEnvApiKey } from '@mariozechner/pi-ai';
+import { getEnvApiKey } from '@eminent337/aery-ai';
 
 // Check if an API key is set in environment variables
 const key = getEnvApiKey('openai');  // checks OPENAI_API_KEY
@@ -1111,7 +1111,7 @@ export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
 ```
 
 ```typescript
-import { getModel, complete } from '@mariozechner/pi-ai';
+import { getModel, complete } from '@eminent337/aery-ai';
 
 (async () => {
   const model = getModel('google-vertex', 'gemini-2.5-flash');
@@ -1134,16 +1134,16 @@ Official docs: [Application Default Credentials](https://cloud.google.com/docs/a
 The quickest way to authenticate:
 
 ```bash
-npx @mariozechner/pi-ai login              # interactive provider selection
-npx @mariozechner/pi-ai login anthropic    # login to specific provider
-npx @mariozechner/pi-ai list               # list available providers
+npx @eminent337/aery-ai login              # interactive provider selection
+npx @eminent337/aery-ai login anthropic    # login to specific provider
+npx @eminent337/aery-ai list               # list available providers
 ```
 
 Credentials are saved to `auth.json` in the current directory.
 
 ### Programmatic OAuth
 
-The library provides login and token refresh functions via the `@mariozechner/pi-ai/oauth` entry point. Credential storage is the caller's responsibility.
+The library provides login and token refresh functions via the `@eminent337/aery-ai/oauth` entry point. Credential storage is the caller's responsibility.
 
 ```typescript
 import {
@@ -1161,13 +1161,13 @@ import {
   // Types
   type OAuthProvider,  // 'anthropic' | 'openai-codex' | 'github-copilot' | 'google-gemini-cli' | 'google-antigravity'
   type OAuthCredentials,
-} from '@mariozechner/pi-ai/oauth';
+} from '@eminent337/aery-ai/oauth';
 ```
 
 ### Login Flow Example
 
 ```typescript
-import { loginGitHubCopilot } from '@mariozechner/pi-ai/oauth';
+import { loginGitHubCopilot } from '@eminent337/aery-ai/oauth';
 import { writeFileSync } from 'fs';
 
 const credentials = await loginGitHubCopilot({
@@ -1191,8 +1191,8 @@ writeFileSync('auth.json', JSON.stringify(auth, null, 2));
 Use `getOAuthApiKey()` to get an API key, automatically refreshing if expired:
 
 ```typescript
-import { getModel, complete } from '@mariozechner/pi-ai';
-import { getOAuthApiKey } from '@mariozechner/pi-ai/oauth';
+import { getModel, complete } from '@eminent337/aery-ai';
+import { getOAuthApiKey } from '@eminent337/aery-ai/oauth';
 import { readFileSync, writeFileSync } from 'fs';
 
 // Load your stored credentials
@@ -1251,7 +1251,7 @@ Create a new provider file (for example `amazon-bedrock.ts`) that exports:
 - Register the API with `registerApiProvider()`
 - Add a package subpath export in `package.json` for the provider module (`./dist/providers/<provider>.js`)
 - Add lazy loader wrappers in `src/providers/register-builtins.ts`, do not statically import provider implementation modules there
-- Add any root-level `export type` re-exports in `src/index.ts` that should remain available from `@mariozechner/pi-ai`
+- Add any root-level `export type` re-exports in `src/index.ts` that should remain available from `@eminent337/aery-ai`
 - Add credential detection in `env-api-keys.ts` for the new provider
 - Ensure `streamSimple` handles auth lookup via `getEnvApiKey()` or provider-specific auth
 

package/dist/providers/anthropic.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"anthropic.d.ts","sourceRoot":"","sources":["../../src/providers/anthropic.ts"],"names":[],"mappings":"AAAA,OAAO,SAAS,MAAM,mBAAmB,CAAC;AAS1C,OAAO,KAAK,EAQX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAMb,MAAM,aAAa,CAAC;AAkIrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAEhE,MAAM,WAAW,gBAAiB,SAAQ,aAAa;IACtD;;;;OAIG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B;;;OAGG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAC9B;;;;;;;;;OASG;IACH,MAAM,CAAC,EAAE,eAAe,CAAC;IACzB;;;;;;;;;;OAUG;IACH,eAAe,CAAC,EAAE,wBAAwB,CAAC;IAC3C,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B,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;AAYD,eAAO,MAAM,eAAe,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CA2PlF,CAAC;AA4CF,eAAO,MAAM,qBAAqB,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CAuC3F,CAAC","sourcesContent":["import Anthropic from \"@anthropic-ai/sdk\";\nimport type {\n\tCacheControlEphemeral,\n\tContentBlockParam,\n\tMessageCreateParamsStreaming,\n\tMessageParam,\n} from \"@anthropic-ai/sdk/resources/messages.js\";\nimport { getEnvApiKey } from \"../env-api-keys.js\";\nimport { calculateCost } from \"../models.js\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tImageContent,\n\tMessage,\n\tModel,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingContent,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.js\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.js\";\nimport { headersToRecord } from \"../utils/headers.js\";\nimport { parseStreamingJson } from \"../utils/json-parse.js\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.js\";\n\nimport { buildCopilotDynamicHeaders, hasCopilotVisionInput } from \"./github-copilot-headers.js\";\nimport { adjustMaxTokensForThinking, buildBaseOptions } from \"./simple-options.js\";\nimport { transformMessages } from \"./transform-messages.js\";\n\n/**\n * Resolve cache retention preference.\n * Defaults to \"short\" and uses PI_CACHE_RETENTION for backward compatibility.\n */\nfunction resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {\n\tif (cacheRetention) {\n\t\treturn cacheRetention;\n\t}\n\tif (typeof process !== \"undefined\" && process.env.PI_CACHE_RETENTION === \"long\") {\n\t\treturn \"long\";\n\t}\n\treturn \"short\";\n}\n\nfunction getCacheControl(\n\tbaseUrl: string,\n\tcacheRetention?: CacheRetention,\n): { retention: CacheRetention; cacheControl?: CacheControlEphemeral } {\n\tconst retention = resolveCacheRetention(cacheRetention);\n\tif (retention === \"none\") {\n\t\treturn { retention };\n\t}\n\tconst ttl = retention === \"long\" && baseUrl.includes(\"api.anthropic.com\") ? \"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://aery.dev/data/prompts-2.1.11.md\n// To update: https://github.com/eminent337/aery\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\nexport interface AnthropicOptions extends StreamOptions {\n\t/**\n\t * Enable extended thinking.\n\t * For Opus 4.6 and Sonnet 4.6: uses adaptive thinking (model decides when/how much to think).\n\t * For older models: uses budget-based thinking with thinkingBudgetTokens.\n\t */\n\tthinkingEnabled?: boolean;\n\t/**\n\t * Token budget for extended thinking (older models only).\n\t * Ignored for Opus 4.6 and Sonnet 4.6, which use adaptive thinking.\n\t */\n\tthinkingBudgetTokens?: number;\n\t/**\n\t * Effort level for adaptive thinking (Opus 4.6+ and Sonnet 4.6).\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)\n\t * - \"high\": Always thinks, deep reasoning (default)\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 */\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 (default here).\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 */\n\tthinkingDisplay?: AnthropicThinkingDisplay;\n\tinterleavedThinking?: boolean;\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: (Record<string, string> | undefined)[]): Record<string, string> {\n\tconst merged: Record<string, string> = {};\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\nexport const streamAnthropic: 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 ?? getEnvApiKey(model.provider) ?? \"\";\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 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\toptions?.headers,\n\t\t\t\t\tcopilotDynamicHeaders,\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 { data: anthropicStream, response } = await client.messages\n\t\t\t\t.stream({ ...params, stream: true }, { signal: options?.signal })\n\t\t\t\t.withResponse();\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 anthropicStream) {\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\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\toutput.stopReason = mapStopReason(event.delta.stop_reason);\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 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(\"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 * Check if a model supports adaptive thinking (Opus 4.6+, Sonnet 4.6)\n */\nfunction supportsAdaptiveThinking(modelId: string): boolean {\n\t// Adaptive-thinking model IDs (with or without date suffix)\n\treturn (\n\t\tmodelId.includes(\"opus-4-6\") ||\n\t\tmodelId.includes(\"opus-4.6\") ||\n\t\tmodelId.includes(\"opus-4-7\") ||\n\t\tmodelId.includes(\"opus-4.7\") ||\n\t\tmodelId.includes(\"sonnet-4-6\") ||\n\t\tmodelId.includes(\"sonnet-4.6\")\n\t);\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 supports \"xhigh\".\n */\nfunction mapThinkingLevelToEffort(level: SimpleStreamOptions[\"reasoning\"], modelId: string): AnthropicEffort {\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\t\treturn \"low\";\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\tcase \"xhigh\":\n\t\t\tif (modelId.includes(\"opus-4-6\") || modelId.includes(\"opus-4.6\")) {\n\t\t\t\treturn \"max\";\n\t\t\t}\n\t\t\tif (modelId.includes(\"opus-4-7\") || modelId.includes(\"opus-4.7\")) {\n\t\t\t\treturn \"xhigh\";\n\t\t\t}\n\t\t\treturn \"high\";\n\t\tdefault:\n\t\t\treturn \"high\";\n\t}\n}\n\nexport const streamSimpleAnthropic: StreamFunction<\"anthropic-messages\", SimpleStreamOptions> = (\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst apiKey = options?.apiKey || getEnvApiKey(model.provider);\n\tif (!apiKey) {\n\t\tthrow new Error(`No API key for provider: ${model.provider}`);\n\t}\n\n\tconst base = buildBaseOptions(model, options, apiKey);\n\tif (!options?.reasoning) {\n\t\treturn streamAnthropic(model, context, { ...base, thinkingEnabled: false } satisfies AnthropicOptions);\n\t}\n\n\t// For Opus 4.6 and Sonnet 4.6: use adaptive thinking with effort level\n\t// For older models: use budget-based thinking\n\tif (supportsAdaptiveThinking(model.id)) {\n\t\tconst effort = mapThinkingLevelToEffort(options.reasoning, model.id);\n\t\treturn streamAnthropic(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\tconst adjusted = adjustMaxTokensForThinking(\n\t\tbase.maxTokens || 0,\n\t\tmodel.maxTokens,\n\t\toptions.reasoning,\n\t\toptions.thinkingBudgets,\n\t);\n\n\treturn streamAnthropic(model, context, {\n\t\t...base,\n\t\tmaxTokens: adjusted.maxTokens,\n\t\tthinkingEnabled: true,\n\t\tthinkingBudgetTokens: adjusted.thinkingBudget,\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,\n\tinterleavedThinking: boolean,\n\toptionsHeaders?: Record<string, string>,\n\tdynamicHeaders?: Record<string, string>,\n): { client: Anthropic; isOAuthToken: boolean } {\n\t// Adaptive thinking models (Opus 4.6, Sonnet 4.6) have interleaved thinking built-in.\n\t// The beta header is deprecated on Opus 4.6 and redundant on Sonnet 4.6, so skip it.\n\tconst needsInterleavedBeta = interleavedThinking && !supportsAdaptiveThinking(model.id);\n\n\t// Copilot: Bearer auth, selective betas (no fine-grained-tool-streaming)\n\tif (model.provider === \"github-copilot\") {\n\t\tconst betaFeatures: string[] = [];\n\t\tif (needsInterleavedBeta) {\n\t\t\tbetaFeatures.push(\"interleaved-thinking-2025-05-14\");\n\t\t}\n\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...(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\tconst betaFeatures = [\"fine-grained-tool-streaming-2025-05-14\"];\n\tif (needsInterleavedBeta) {\n\t\tbetaFeatures.push(\"interleaved-thinking-2025-05-14\");\n\t}\n\n\t// OAuth: Bearer auth, Claude Code identity headers\n\tif (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 auth\n\tconst client = new Anthropic({\n\t\tapiKey,\n\t\tbaseURL: model.baseUrl,\n\t\tdangerouslyAllowBrowser: true,\n\t\tdefaultHeaders: mergeHeaders(\n\t\t\t{\n\t\t\t\taccept: \"application/json\",\n\t\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t\t\"anthropic-beta\": betaFeatures.join(\",\"),\n\t\t\t},\n\t\t\tmodel.headers,\n\t\t\toptionsHeaders,\n\t\t),\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.baseUrl, options?.cacheRetention);\n\tconst params: MessageCreateParamsStreaming = {\n\t\tmodel: model.id,\n\t\tmessages: convertMessages(context.messages, model, isOAuthToken, cacheControl),\n\t\tmax_tokens: options?.maxTokens || (model.maxTokens / 3) | 0,\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 (adaptive or budget-based).\n\tif (options?.temperature !== undefined && !options?.thinkingEnabled) {\n\t\tparams.temperature = options.temperature;\n\t}\n\n\tif (context.tools) {\n\t\tparams.tools = convertTools(context.tools, isOAuthToken, cacheControl);\n\t}\n\n\t// Configure thinking mode: adaptive (Opus 4.6+ and Sonnet 4.6),\n\t// budget-based (older models), 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 (supportsAdaptiveThinking(model.id)) {\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) {\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): 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 block without <thinking> tags to avoid API rejection\n\t\t\t\t\t// and prevent Claude from mimicking the tags in responses\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\ttype: \"text\",\n\t\t\t\t\t\t\ttext: sanitizeSurrogates(block.thinking),\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 convertTools(\n\ttools: Tool[],\n\tisOAuthToken: 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\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(reason: Anthropic.Messages.StopReason | string): StopReason {\n\tswitch (reason) {\n\t\tcase \"end_turn\":\n\t\t\treturn \"stop\";\n\t\tcase \"max_tokens\":\n\t\t\treturn \"length\";\n\t\tcase \"tool_use\":\n\t\t\treturn \"toolUse\";\n\t\tcase \"refusal\":\n\t\t\treturn \"error\";\n\t\tcase \"pause_turn\": // Stop is good enough -> resubmit\n\t\t\treturn \"stop\";\n\t\tcase \"stop_sequence\":\n\t\t\treturn \"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 \"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.d.ts","sourceRoot":"","sources":["../../src/providers/anthropic.ts"],"names":[],"mappings":"AAAA,OAAO,SAAS,MAAM,mBAAmB,CAAC;AAU1C,OAAO,KAAK,EAQX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAMb,MAAM,aAAa,CAAC;AAkIrB,MAAM,MAAM,eAAe,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,GAAG,OAAO,GAAG,KAAK,CAAC;AAE1E,MAAM,MAAM,wBAAwB,GAAG,YAAY,GAAG,SAAS,CAAC;AAEhE,MAAM,WAAW,gBAAiB,SAAQ,aAAa;IACtD;;;;OAIG;IACH,eAAe,CAAC,EAAE,OAAO,CAAC;IAC1B;;;OAGG;IACH,oBAAoB,CAAC,EAAE,MAAM,CAAC;IAC9B;;;;;;;;;OASG;IACH,MAAM,CAAC,EAAE,eAAe,CAAC;IACzB;;;;;;;;;;OAUG;IACH,eAAe,CAAC,EAAE,wBAAwB,CAAC;IAC3C,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B,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;AAsLD,eAAO,MAAM,eAAe,EAAE,cAAc,CAAC,oBAAoB,EAAE,gBAAgB,CA2PlF,CAAC;AA4CF,eAAO,MAAM,qBAAqB,EAAE,cAAc,CAAC,oBAAoB,EAAE,mBAAmB,CAuC3F,CAAC","sourcesContent":["import Anthropic from \"@anthropic-ai/sdk\";\nimport type {\n\tCacheControlEphemeral,\n\tContentBlockParam,\n\tMessageCreateParamsStreaming,\n\tMessageParam,\n\tRawMessageStreamEvent,\n} from \"@anthropic-ai/sdk/resources/messages.js\";\nimport { getEnvApiKey } from \"../env-api-keys.js\";\nimport { calculateCost } from \"../models.js\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tImageContent,\n\tMessage,\n\tModel,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingContent,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.js\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.js\";\nimport { headersToRecord } from \"../utils/headers.js\";\nimport { parseJsonWithRepair, parseStreamingJson } from \"../utils/json-parse.js\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.js\";\n\nimport { buildCopilotDynamicHeaders, hasCopilotVisionInput } from \"./github-copilot-headers.js\";\nimport { adjustMaxTokensForThinking, buildBaseOptions } from \"./simple-options.js\";\nimport { transformMessages } from \"./transform-messages.js\";\n\n/**\n * Resolve cache retention preference.\n * Defaults to \"short\" and uses PI_CACHE_RETENTION for backward compatibility.\n */\nfunction resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {\n\tif (cacheRetention) {\n\t\treturn cacheRetention;\n\t}\n\tif (typeof process !== \"undefined\" && process.env.PI_CACHE_RETENTION === \"long\") {\n\t\treturn \"long\";\n\t}\n\treturn \"short\";\n}\n\nfunction getCacheControl(\n\tbaseUrl: string,\n\tcacheRetention?: CacheRetention,\n): { retention: CacheRetention; cacheControl?: CacheControlEphemeral } {\n\tconst retention = resolveCacheRetention(cacheRetention);\n\tif (retention === \"none\") {\n\t\treturn { retention };\n\t}\n\tconst ttl = retention === \"long\" && baseUrl.includes(\"api.anthropic.com\") ? \"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://aery.dev/data/prompts-2.1.11.md\n// To update: https://github.com/eminent337/aery\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\nexport interface AnthropicOptions extends StreamOptions {\n\t/**\n\t * Enable extended thinking.\n\t * For Opus 4.6 and Sonnet 4.6: uses adaptive thinking (model decides when/how much to think).\n\t * For older models: uses budget-based thinking with thinkingBudgetTokens.\n\t */\n\tthinkingEnabled?: boolean;\n\t/**\n\t * Token budget for extended thinking (older models only).\n\t * Ignored for Opus 4.6 and Sonnet 4.6, which use adaptive thinking.\n\t */\n\tthinkingBudgetTokens?: number;\n\t/**\n\t * Effort level for adaptive thinking (Opus 4.6+ and Sonnet 4.6).\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)\n\t * - \"high\": Always thinks, deep reasoning (default)\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 */\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 (default here).\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 */\n\tthinkingDisplay?: AnthropicThinkingDisplay;\n\tinterleavedThinking?: boolean;\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: (Record<string, string> | undefined)[]): Record<string, string> {\n\tconst merged: Record<string, string> = {};\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\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\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\tfor await (const sse of iterateSseMessages(response.body, signal)) {\n\t\tif (!sse.event || sse.event === \"ping\") {\n\t\t\tcontinue;\n\t\t}\n\n\t\tif (sse.event === \"error\") {\n\t\t\tthrow new Error(sse.data);\n\t\t}\n\n\t\ttry {\n\t\t\tyield parseJsonWithRepair<RawMessageStreamEvent>(sse.data);\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\nexport const streamAnthropic: 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 ?? getEnvApiKey(model.provider) ?? \"\";\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 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\toptions?.headers,\n\t\t\t\t\tcopilotDynamicHeaders,\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 response = await client.messages\n\t\t\t\t.create({ ...params, stream: true }, { signal: options?.signal })\n\t\t\t\t.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\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\toutput.stopReason = mapStopReason(event.delta.stop_reason);\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 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(\"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 * Check if a model supports adaptive thinking (Opus 4.6+, Sonnet 4.6)\n */\nfunction supportsAdaptiveThinking(modelId: string): boolean {\n\t// Adaptive-thinking model IDs (with or without date suffix)\n\treturn (\n\t\tmodelId.includes(\"opus-4-6\") ||\n\t\tmodelId.includes(\"opus-4.6\") ||\n\t\tmodelId.includes(\"opus-4-7\") ||\n\t\tmodelId.includes(\"opus-4.7\") ||\n\t\tmodelId.includes(\"sonnet-4-6\") ||\n\t\tmodelId.includes(\"sonnet-4.6\")\n\t);\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 supports \"xhigh\".\n */\nfunction mapThinkingLevelToEffort(level: SimpleStreamOptions[\"reasoning\"], modelId: string): AnthropicEffort {\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\t\treturn \"low\";\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\tcase \"xhigh\":\n\t\t\tif (modelId.includes(\"opus-4-6\") || modelId.includes(\"opus-4.6\")) {\n\t\t\t\treturn \"max\";\n\t\t\t}\n\t\t\tif (modelId.includes(\"opus-4-7\") || modelId.includes(\"opus-4.7\")) {\n\t\t\t\treturn \"xhigh\";\n\t\t\t}\n\t\t\treturn \"high\";\n\t\tdefault:\n\t\t\treturn \"high\";\n\t}\n}\n\nexport const streamSimpleAnthropic: StreamFunction<\"anthropic-messages\", SimpleStreamOptions> = (\n\tmodel: Model<\"anthropic-messages\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst apiKey = options?.apiKey || getEnvApiKey(model.provider);\n\tif (!apiKey) {\n\t\tthrow new Error(`No API key for provider: ${model.provider}`);\n\t}\n\n\tconst base = buildBaseOptions(model, options, apiKey);\n\tif (!options?.reasoning) {\n\t\treturn streamAnthropic(model, context, { ...base, thinkingEnabled: false } satisfies AnthropicOptions);\n\t}\n\n\t// For Opus 4.6 and Sonnet 4.6: use adaptive thinking with effort level\n\t// For older models: use budget-based thinking\n\tif (supportsAdaptiveThinking(model.id)) {\n\t\tconst effort = mapThinkingLevelToEffort(options.reasoning, model.id);\n\t\treturn streamAnthropic(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\tconst adjusted = adjustMaxTokensForThinking(\n\t\tbase.maxTokens || 0,\n\t\tmodel.maxTokens,\n\t\toptions.reasoning,\n\t\toptions.thinkingBudgets,\n\t);\n\n\treturn streamAnthropic(model, context, {\n\t\t...base,\n\t\tmaxTokens: adjusted.maxTokens,\n\t\tthinkingEnabled: true,\n\t\tthinkingBudgetTokens: adjusted.thinkingBudget,\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,\n\tinterleavedThinking: boolean,\n\toptionsHeaders?: Record<string, string>,\n\tdynamicHeaders?: Record<string, string>,\n): { client: Anthropic; isOAuthToken: boolean } {\n\t// Adaptive thinking models (Opus 4.6, Sonnet 4.6) have interleaved thinking built-in.\n\t// The beta header is deprecated on Opus 4.6 and redundant on Sonnet 4.6, so skip it.\n\tconst needsInterleavedBeta = interleavedThinking && !supportsAdaptiveThinking(model.id);\n\n\t// Copilot: Bearer auth, selective betas (no fine-grained-tool-streaming)\n\tif (model.provider === \"github-copilot\") {\n\t\tconst betaFeatures: string[] = [];\n\t\tif (needsInterleavedBeta) {\n\t\t\tbetaFeatures.push(\"interleaved-thinking-2025-05-14\");\n\t\t}\n\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...(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\tconst betaFeatures: string[] = [];\n\tif (needsInterleavedBeta) {\n\t\tbetaFeatures.push(\"interleaved-thinking-2025-05-14\");\n\t}\n\n\t// OAuth: Bearer auth, Claude Code identity headers\n\tif (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 auth\n\tconst client = new Anthropic({\n\t\tapiKey,\n\t\tbaseURL: model.baseUrl,\n\t\tdangerouslyAllowBrowser: true,\n\t\tdefaultHeaders: mergeHeaders(\n\t\t\t{\n\t\t\t\taccept: \"application/json\",\n\t\t\t\t\"anthropic-dangerous-direct-browser-access\": \"true\",\n\t\t\t\t...(betaFeatures.length > 0 ? { \"anthropic-beta\": betaFeatures.join(\",\") } : {}),\n\t\t\t},\n\t\t\tmodel.headers,\n\t\t\toptionsHeaders,\n\t\t),\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.baseUrl, options?.cacheRetention);\n\tconst params: MessageCreateParamsStreaming = {\n\t\tmodel: model.id,\n\t\tmessages: convertMessages(context.messages, model, isOAuthToken, cacheControl),\n\t\tmax_tokens: options?.maxTokens || (model.maxTokens / 3) | 0,\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 (adaptive or budget-based).\n\tif (options?.temperature !== undefined && !options?.thinkingEnabled) {\n\t\tparams.temperature = options.temperature;\n\t}\n\n\tif (context.tools) {\n\t\tparams.tools = convertTools(context.tools, isOAuthToken, cacheControl);\n\t}\n\n\t// Configure thinking mode: adaptive (Opus 4.6+ and Sonnet 4.6),\n\t// budget-based (older models), 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 (supportsAdaptiveThinking(model.id)) {\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) {\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): 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 block without <thinking> tags to avoid API rejection\n\t\t\t\t\t// and prevent Claude from mimicking the tags in responses\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\ttype: \"text\",\n\t\t\t\t\t\t\ttext: sanitizeSurrogates(block.thinking),\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 convertTools(\n\ttools: Tool[],\n\tisOAuthToken: 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\teager_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(reason: Anthropic.Messages.StopReason | string): StopReason {\n\tswitch (reason) {\n\t\tcase \"end_turn\":\n\t\t\treturn \"stop\";\n\t\tcase \"max_tokens\":\n\t\t\treturn \"length\";\n\t\tcase \"tool_use\":\n\t\t\treturn \"toolUse\";\n\t\tcase \"refusal\":\n\t\t\treturn \"error\";\n\t\tcase \"pause_turn\": // Stop is good enough -> resubmit\n\t\t\treturn \"stop\";\n\t\tcase \"stop_sequence\":\n\t\t\treturn \"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 \"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/providers/anthropic.js

@@ -3,7 +3,7 @@ import { getEnvApiKey } from "../env-api-keys.js";
 import { calculateCost } from "../models.js";
 import { AssistantMessageEventStream } from "../utils/event-stream.js";
 import { headersToRecord } from "../utils/headers.js";
-import { parseStreamingJson } from "../utils/json-parse.js";
+import { parseJsonWithRepair, parseStreamingJson } from "../utils/json-parse.js";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.js";
 import { adjustMaxTokensForThinking, buildBaseOptions } from "./simple-options.js";
@@ -113,6 +113,137 @@ function mergeHeaders(...headerSources) {
     }
     return merged;
 }
+function flushSseEvent(state) {
+    if (!state.event && state.data.length === 0) {
+        return null;
+    }
+    const event = {
+        event: state.event,
+        data: state.data.join("\n"),
+        raw: [...state.raw],
+    };
+    state.event = null;
+    state.data = [];
+    state.raw = [];
+    return event;
+}
+function decodeSseLine(line, state) {
+    if (line === "") {
+        return flushSseEvent(state);
+    }
+    state.raw.push(line);
+    if (line.startsWith(":")) {
+        return null;
+    }
+    const delimiterIndex = line.indexOf(":");
+    const fieldName = delimiterIndex === -1 ? line : line.slice(0, delimiterIndex);
+    let value = delimiterIndex === -1 ? "" : line.slice(delimiterIndex + 1);
+    if (value.startsWith(" ")) {
+        value = value.slice(1);
+    }
+    if (fieldName === "event") {
+        state.event = value;
+    }
+    else if (fieldName === "data") {
+        state.data.push(value);
+    }
+    return null;
+}
+function nextLineBreakIndex(text) {
+    const carriageReturnIndex = text.indexOf("\r");
+    const newlineIndex = text.indexOf("\n");
+    if (carriageReturnIndex === -1) {
+        return newlineIndex;
+    }
+    if (newlineIndex === -1) {
+        return carriageReturnIndex;
+    }
+    return Math.min(carriageReturnIndex, newlineIndex);
+}
+function consumeLine(text) {
+    const lineBreakIndex = nextLineBreakIndex(text);
+    if (lineBreakIndex === -1) {
+        return null;
+    }
+    let nextIndex = lineBreakIndex + 1;
+    if (text[lineBreakIndex] === "\r" && text[nextIndex] === "\n") {
+        nextIndex += 1;
+    }
+    return {
+        line: text.slice(0, lineBreakIndex),
+        rest: text.slice(nextIndex),
+    };
+}
+async function* iterateSseMessages(body, signal) {
+    const reader = body.getReader();
+    const decoder = new TextDecoder();
+    const state = { event: null, data: [], raw: [] };
+    let buffer = "";
+    try {
+        while (true) {
+            if (signal?.aborted) {
+                throw new Error("Request was aborted");
+            }
+            const { value, done } = await reader.read();
+            if (done) {
+                break;
+            }
+            buffer += decoder.decode(value, { stream: true });
+            let consumed = consumeLine(buffer);
+            while (consumed) {
+                buffer = consumed.rest;
+                const event = decodeSseLine(consumed.line, state);
+                if (event) {
+                    yield event;
+                }
+                consumed = consumeLine(buffer);
+            }
+        }
+        buffer += decoder.decode();
+        let consumed = consumeLine(buffer);
+        while (consumed) {
+            buffer = consumed.rest;
+            const event = decodeSseLine(consumed.line, state);
+            if (event) {
+                yield event;
+            }
+            consumed = consumeLine(buffer);
+        }
+        if (buffer.length > 0) {
+            const event = decodeSseLine(buffer, state);
+            if (event) {
+                yield event;
+            }
+        }
+        const trailingEvent = flushSseEvent(state);
+        if (trailingEvent) {
+            yield trailingEvent;
+        }
+    }
+    finally {
+        reader.releaseLock();
+    }
+}
+async function* iterateAnthropicEvents(response, signal) {
+    if (!response.body) {
+        throw new Error("Attempted to iterate over an Anthropic response with no body");
+    }
+    for await (const sse of iterateSseMessages(response.body, signal)) {
+        if (!sse.event || sse.event === "ping") {
+            continue;
+        }
+        if (sse.event === "error") {
+            throw new Error(sse.data);
+        }
+        try {
+            yield parseJsonWithRepair(sse.data);
+        }
+        catch (error) {
+            const message = error instanceof Error ? error.message : String(error);
+            throw new Error(`Could not parse Anthropic SSE event ${sse.event}: ${message}; data=${sse.data}; raw=${sse.raw.join("\\n")}`);
+        }
+    }
+}
 export const streamAnthropic = (model, context, options) => {
     const stream = new AssistantMessageEventStream();
     (async () => {
@@ -159,13 +290,13 @@ export const streamAnthropic = (model, context, options) => {
             if (nextParams !== undefined) {
                 params = nextParams;
             }
-            const { data: anthropicStream, response } = await client.messages
-                .stream({ ...params, stream: true }, { signal: options?.signal })
-                .withResponse();
+            const response = await client.messages
+                .create({ ...params, stream: true }, { signal: options?.signal })
+                .asResponse();
             await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
             stream.push({ type: "start", partial: output });
             const blocks = output.content;
-            for await (const event of anthropicStream) {
+            for await (const event of iterateAnthropicEvents(response, options?.signal)) {
                 if (event.type === "message_start") {
                     output.responseId = event.message.id;
                     // Capture initial token usage from message_start event
@@ -448,7 +579,7 @@ function createClient(model, apiKey, interleavedThinking, optionsHeaders, dynami
         });
         return { client, isOAuthToken: false };
     }
-    const betaFeatures = ["fine-grained-tool-streaming-2025-05-14"];
+    const betaFeatures = [];
     if (needsInterleavedBeta) {
         betaFeatures.push("interleaved-thinking-2025-05-14");
     }
@@ -462,7 +593,7 @@ function createClient(model, apiKey, interleavedThinking, optionsHeaders, dynami
             defaultHeaders: mergeHeaders({
                 accept: "application/json",
                 "anthropic-dangerous-direct-browser-access": "true",
-                "anthropic-beta": `claude-code-20250219,oauth-2025-04-20,${betaFeatures.join(",")}`,
+                "anthropic-beta": ["claude-code-20250219", "oauth-2025-04-20", ...betaFeatures].join(","),
                 "user-agent": `claude-cli/${claudeCodeVersion}`,
                 "x-app": "cli",
             }, model.headers, optionsHeaders),
@@ -477,7 +608,7 @@ function createClient(model, apiKey, interleavedThinking, optionsHeaders, dynami
         defaultHeaders: mergeHeaders({
             accept: "application/json",
             "anthropic-dangerous-direct-browser-access": "true",
-            "anthropic-beta": betaFeatures.join(","),
+            ...(betaFeatures.length > 0 ? { "anthropic-beta": betaFeatures.join(",") } : {}),
         }, model.headers, optionsHeaders),
     });
     return { client, isOAuthToken: false };
@@ -741,6 +872,7 @@ function convertTools(tools, isOAuthToken, cacheControl) {
         return {
             name: isOAuthToken ? toClaudeCodeName(tool.name) : tool.name,
             description: tool.description,
+            eager_input_streaming: true,
             input_schema: {
                 type: "object",
                 properties: schema.properties ?? {},