@hyperspaceng/neural-ai 0.70.3 → 0.70.7

package/dist/providers/amazon-bedrock.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"amazon-bedrock.d.ts","sourceRoot":"","sources":["../../src/providers/amazon-bedrock.ts"],"names":[],"mappings":"AAwBA,OAAO,KAAK,EAMX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAEb,eAAe,EAEf,aAAa,EAIb,MAAM,aAAa,CAAC;AAOrB,MAAM,MAAM,sBAAsB,GAAG,YAAY,GAAG,SAAS,CAAC;AAE9D,MAAM,WAAW,cAAe,SAAQ,aAAa;IACpD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IAEtE,SAAS,CAAC,EAAE,aAAa,CAAC;IAE1B,eAAe,CAAC,EAAE,eAAe,CAAC;IAElC,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;;;;;;OASG;IACH,eAAe,CAAC,EAAE,sBAAsB,CAAC;IACzC;;;sGAGkG;IAClG,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACzC;;;;yGAIqG;IACrG,WAAW,CAAC,EAAE,MAAM,CAAC;CACrB;AAID,eAAO,MAAM,aAAa,EAAE,cAAc,CAAC,yBAAyB,EAAE,cAAc,CAgMnF,CAAC;AAgCF,eAAO,MAAM,mBAAmB,EAAE,cAAc,CAAC,yBAAyB,EAAE,mBAAmB,CA0C9F,CAAC","sourcesContent":["import {\n\tBedrockRuntimeClient,\n\ttype BedrockRuntimeClientConfig,\n\tBedrockRuntimeServiceException,\n\tStopReason as BedrockStopReason,\n\ttype Tool as BedrockTool,\n\tCachePointType,\n\tCacheTTL,\n\ttype ContentBlock,\n\ttype ContentBlockDeltaEvent,\n\ttype ContentBlockStartEvent,\n\ttype ContentBlockStopEvent,\n\tConversationRole,\n\tConverseStreamCommand,\n\ttype ConverseStreamMetadataEvent,\n\tImageFormat,\n\ttype Message,\n\ttype SystemContentBlock,\n\ttype ToolChoice,\n\ttype ToolConfiguration,\n\tToolResultStatus,\n} from \"@aws-sdk/client-bedrock-runtime\";\nimport type { DocumentType } from \"@smithy/types\";\nimport { calculateCost } from \"../models.js\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tModel,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingBudgets,\n\tThinkingContent,\n\tThinkingLevel,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.js\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.js\";\nimport { parseStreamingJson } from \"../utils/json-parse.js\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.js\";\nimport { adjustMaxTokensForThinking, buildBaseOptions, clampReasoning } from \"./simple-options.js\";\nimport { transformMessages } from \"./transform-messages.js\";\n\nexport type BedrockThinkingDisplay = \"summarized\" | \"omitted\";\n\nexport interface BedrockOptions extends StreamOptions {\n\tregion?: string;\n\tprofile?: string;\n\ttoolChoice?: \"auto\" | \"any\" | \"none\" | { type: \"tool\"; name: string };\n\t/* See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-reasoning.html for supported models. */\n\treasoning?: ThinkingLevel;\n\t/* Custom token budgets per thinking level. Overrides default budgets. */\n\tthinkingBudgets?: ThinkingBudgets;\n\t/* Only supported by Claude 4.x models, see https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-extended-thinking.html#claude-messages-extended-thinking-tool-use-interleaved */\n\tinterleavedThinking?: boolean;\n\t/**\n\t * Controls how Claude's thinking content is returned in responses.\n\t * - \"summarized\": Thinking blocks contain summarized thinking text (default here).\n\t * - \"omitted\": Thinking content is redacted but the signature still travels back\n\t *   for multi-turn continuity, reducing time-to-first-text-token.\n\t *\n\t * Note: Anthropic's API default for Claude Opus 4.7 and Mythos Preview is\n\t * \"omitted\". We default to \"summarized\" here to keep behavior consistent with\n\t * older Claude 4 models. Only applies to Claude models on Bedrock.\n\t */\n\tthinkingDisplay?: BedrockThinkingDisplay;\n\t/** Key-value pairs attached to the inference request for cost allocation tagging.\n\t * Keys: max 64 chars, no `aws:` prefix. Values: max 256 chars. Max 50 pairs.\n\t * Tags appear in AWS Cost Explorer split cost allocation data.\n\t * @see https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html */\n\trequestMetadata?: Record<string, string>;\n\t/** Bearer token for Bedrock API key authentication.\n\t * When set, bypasses SigV4 signing and sends Authorization: Bearer <token> instead.\n\t * Requires `bedrock:CallWithBearerToken` IAM permission on the token's identity.\n\t * Set via AWS_BEARER_TOKEN_BEDROCK env var or pass directly.\n\t * @see https://docs.aws.amazon.com/service-authorization/latest/reference/list_amazonbedrock.html */\n\tbearerToken?: string;\n}\n\ntype Block = (TextContent | ThinkingContent | ToolCall) & { index?: number; partialJson?: string };\n\nexport const streamBedrock: StreamFunction<\"bedrock-converse-stream\", BedrockOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions: BedrockOptions = {},\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: \"bedrock-converse-stream\" 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\tconst blocks = output.content as Block[];\n\n\t\tconst config: BedrockRuntimeClientConfig = {\n\t\t\tprofile: options.profile,\n\t\t};\n\t\tconst configuredRegion = getConfiguredBedrockRegion(options);\n\t\tconst hasConfiguredProfile = hasConfiguredBedrockProfile();\n\t\tconst endpointRegion = getStandardBedrockEndpointRegion(model.baseUrl);\n\t\tconst useExplicitEndpoint = shouldUseExplicitBedrockEndpoint(\n\t\t\tmodel.baseUrl,\n\t\t\tconfiguredRegion,\n\t\t\thasConfiguredProfile,\n\t\t);\n\n\t\t// Only pin standard AWS Bedrock runtime endpoints when no region/profile is configured.\n\t\t// This preserves custom endpoints (VPC/proxy) from #3402 without forcing built-in\n\t\t// catalog defaults such as us-east-1 to override AWS_REGION/AWS_PROFILE.\n\t\tif (useExplicitEndpoint) {\n\t\t\tconfig.endpoint = model.baseUrl;\n\t\t}\n\n\t\t// Resolve bearer token for Bedrock API key auth.\n\t\tconst bearerToken = options.bearerToken || process.env.AWS_BEARER_TOKEN_BEDROCK || undefined;\n\t\tconst useBearerToken = bearerToken !== undefined && process.env.AWS_BEDROCK_SKIP_AUTH !== \"1\";\n\n\t\t// in Node.js/Bun environment only\n\t\tif (typeof process !== \"undefined\" && (process.versions?.node || process.versions?.bun)) {\n\t\t\t// Region resolution: explicit option > env vars > SDK default chain.\n\t\t\t// When AWS_PROFILE is set, we leave region undefined so the SDK can\n\t\t\t// resovle it from aws profile configs. Otherwise fall back to us-east-1.\n\t\t\tif (configuredRegion) {\n\t\t\t\tconfig.region = configuredRegion;\n\t\t\t} else if (endpointRegion && useExplicitEndpoint) {\n\t\t\t\tconfig.region = endpointRegion;\n\t\t\t} else if (!hasConfiguredProfile) {\n\t\t\t\tconfig.region = \"us-east-1\";\n\t\t\t}\n\n\t\t\t// Support proxies that don't need authentication\n\t\t\tif (process.env.AWS_BEDROCK_SKIP_AUTH === \"1\") {\n\t\t\t\tconfig.credentials = {\n\t\t\t\t\taccessKeyId: \"dummy-access-key\",\n\t\t\t\t\tsecretAccessKey: \"dummy-secret-key\",\n\t\t\t\t};\n\t\t\t}\n\n\t\t\tif (\n\t\t\t\tprocess.env.HTTP_PROXY ||\n\t\t\t\tprocess.env.HTTPS_PROXY ||\n\t\t\t\tprocess.env.NO_PROXY ||\n\t\t\t\tprocess.env.http_proxy ||\n\t\t\t\tprocess.env.https_proxy ||\n\t\t\t\tprocess.env.no_proxy\n\t\t\t) {\n\t\t\t\tconst nodeHttpHandler = await import(\"@smithy/node-http-handler\");\n\t\t\t\tconst proxyAgent = await import(\"proxy-agent\");\n\n\t\t\t\tconst agent = new proxyAgent.ProxyAgent();\n\n\t\t\t\t// Bedrock runtime uses NodeHttp2Handler by default since v3.798.0, which is based\n\t\t\t\t// on `http2` module and has no support for http agent.\n\t\t\t\t// Use NodeHttpHandler to support http agent.\n\t\t\t\tconfig.requestHandler = new nodeHttpHandler.NodeHttpHandler({\n\t\t\t\t\thttpAgent: agent,\n\t\t\t\t\thttpsAgent: agent,\n\t\t\t\t});\n\t\t\t} else if (process.env.AWS_BEDROCK_FORCE_HTTP1 === \"1\") {\n\t\t\t\t// Some custom endpoints require HTTP/1.1 instead of HTTP/2\n\t\t\t\tconst nodeHttpHandler = await import(\"@smithy/node-http-handler\");\n\t\t\t\tconfig.requestHandler = new nodeHttpHandler.NodeHttpHandler();\n\t\t\t}\n\t\t} else {\n\t\t\t// Non-Node environment (browser): fall back to us-east-1 since\n\t\t\t// there's no config file resolution available.\n\t\t\tconfig.region =\n\t\t\t\tconfiguredRegion || (endpointRegion && useExplicitEndpoint ? endpointRegion : undefined) || \"us-east-1\";\n\t\t}\n\n\t\tif (useBearerToken) {\n\t\t\tconfig.token = { token: bearerToken };\n\t\t\tconfig.authSchemePreference = [\"httpBearerAuth\"];\n\t\t}\n\n\t\ttry {\n\t\t\tconst client = new BedrockRuntimeClient(config);\n\t\t\tconst cacheRetention = resolveCacheRetention(options.cacheRetention);\n\t\t\tlet commandInput = {\n\t\t\t\tmodelId: model.id,\n\t\t\t\tmessages: convertMessages(context, model, cacheRetention),\n\t\t\t\tsystem: buildSystemPrompt(context.systemPrompt, model, cacheRetention),\n\t\t\t\tinferenceConfig: {\n\t\t\t\t\t...(options.maxTokens !== undefined && { maxTokens: options.maxTokens }),\n\t\t\t\t\t...(options.temperature !== undefined && { temperature: options.temperature }),\n\t\t\t\t},\n\t\t\t\ttoolConfig: convertToolConfig(context.tools, options.toolChoice),\n\t\t\t\tadditionalModelRequestFields: buildAdditionalModelRequestFields(model, options),\n\t\t\t\t...(options.requestMetadata !== undefined && { requestMetadata: options.requestMetadata }),\n\t\t\t};\n\t\t\tconst nextCommandInput = await options?.onPayload?.(commandInput, model);\n\t\t\tif (nextCommandInput !== undefined) {\n\t\t\t\tcommandInput = nextCommandInput as typeof commandInput;\n\t\t\t}\n\t\t\tconst command = new ConverseStreamCommand(commandInput);\n\n\t\t\tconst response = await client.send(command, { abortSignal: options.signal });\n\t\t\tif (response.$metadata.httpStatusCode !== undefined) {\n\t\t\t\tconst responseHeaders: Record<string, string> = {};\n\t\t\t\tif (response.$metadata.requestId) {\n\t\t\t\t\tresponseHeaders[\"x-amzn-requestid\"] = response.$metadata.requestId;\n\t\t\t\t}\n\t\t\t\tawait options?.onResponse?.({ status: response.$metadata.httpStatusCode, headers: responseHeaders }, model);\n\t\t\t}\n\n\t\t\tfor await (const item of response.stream!) {\n\t\t\t\tif (item.messageStart) {\n\t\t\t\t\tif (item.messageStart.role !== ConversationRole.ASSISTANT) {\n\t\t\t\t\t\tthrow new Error(\"Unexpected assistant message start but got user message start instead\");\n\t\t\t\t\t}\n\t\t\t\t\tstream.push({ type: \"start\", partial: output });\n\t\t\t\t} else if (item.contentBlockStart) {\n\t\t\t\t\thandleContentBlockStart(item.contentBlockStart, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockDelta) {\n\t\t\t\t\thandleContentBlockDelta(item.contentBlockDelta, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockStop) {\n\t\t\t\t\thandleContentBlockStop(item.contentBlockStop, blocks, output, stream);\n\t\t\t\t} else if (item.messageStop) {\n\t\t\t\t\toutput.stopReason = mapStopReason(item.messageStop.stopReason);\n\t\t\t\t} else if (item.metadata) {\n\t\t\t\t\thandleMetadata(item.metadata, model, output);\n\t\t\t\t} else if (item.internalServerException) {\n\t\t\t\t\tthrow item.internalServerException;\n\t\t\t\t} else if (item.modelStreamErrorException) {\n\t\t\t\t\tthrow item.modelStreamErrorException;\n\t\t\t\t} else if (item.validationException) {\n\t\t\t\t\tthrow item.validationException;\n\t\t\t\t} else if (item.throttlingException) {\n\t\t\t\t\tthrow item.throttlingException;\n\t\t\t\t} else if (item.serviceUnavailableException) {\n\t\t\t\t\tthrow item.serviceUnavailableException;\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 === \"error\" || output.stopReason === \"aborted\") {\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 Block).index;\n\t\t\t\t// partialJson is only a streaming scratch buffer; never persist it.\n\t\t\t\tdelete (block as Block).partialJson;\n\t\t\t}\n\t\t\toutput.stopReason = options.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = formatBedrockError(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 * Human-readable prefixes for Bedrock SDK exception names.\n * The downstream retry logic in agent-session matches patterns like\n * `server.?error` and `service.?unavailable`, so we preserve the legacy\n * prefix format rather than using the raw SDK exception name.\n */\nconst BEDROCK_ERROR_PREFIXES: Record<string, string> = {\n\tInternalServerException: \"Internal server error\",\n\tModelStreamErrorException: \"Model stream error\",\n\tValidationException: \"Validation error\",\n\tThrottlingException: \"Throttling error\",\n\tServiceUnavailableException: \"Service unavailable\",\n};\n\n/**\n * Format a Bedrock error with a human-readable prefix.\n * AWS SDK exceptions (both from `client.send()` and from stream event items)\n * extend BedrockRuntimeServiceException. We map the `.name` to a stable\n * human-readable prefix so downstream consumers (retry logic, context-overflow\n * detection) can distinguish error categories via simple string matching.\n */\nfunction formatBedrockError(error: unknown): string {\n\tconst message = error instanceof Error ? error.message : JSON.stringify(error);\n\tif (error instanceof BedrockRuntimeServiceException) {\n\t\tconst prefix = BEDROCK_ERROR_PREFIXES[error.name] ?? error.name;\n\t\treturn `${prefix}: ${message}`;\n\t}\n\treturn message;\n}\n\nexport const streamSimpleBedrock: StreamFunction<\"bedrock-converse-stream\", SimpleStreamOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst base = buildBaseOptions(model, options, undefined);\n\tif (!options?.reasoning) {\n\t\treturn streamBedrock(model, context, { ...base, reasoning: undefined } satisfies BedrockOptions);\n\t}\n\n\tif (model.id.includes(\"anthropic.claude\") || model.id.includes(\"anthropic/claude\")) {\n\t\tif (supportsAdaptiveThinking(model.id)) {\n\t\t\treturn streamBedrock(model, context, {\n\t\t\t\t...base,\n\t\t\t\treasoning: options.reasoning,\n\t\t\t\tthinkingBudgets: options.thinkingBudgets,\n\t\t\t} satisfies BedrockOptions);\n\t\t}\n\n\t\tconst adjusted = adjustMaxTokensForThinking(\n\t\t\tbase.maxTokens || 0,\n\t\t\tmodel.maxTokens,\n\t\t\toptions.reasoning,\n\t\t\toptions.thinkingBudgets,\n\t\t);\n\n\t\treturn streamBedrock(model, context, {\n\t\t\t...base,\n\t\t\tmaxTokens: adjusted.maxTokens,\n\t\t\treasoning: options.reasoning,\n\t\t\tthinkingBudgets: {\n\t\t\t\t...(options.thinkingBudgets || {}),\n\t\t\t\t[clampReasoning(options.reasoning)!]: adjusted.thinkingBudget,\n\t\t\t},\n\t\t} satisfies BedrockOptions);\n\t}\n\n\treturn streamBedrock(model, context, {\n\t\t...base,\n\t\treasoning: options.reasoning,\n\t\tthinkingBudgets: options.thinkingBudgets,\n\t} satisfies BedrockOptions);\n};\n\nfunction handleContentBlockStart(\n\tevent: ContentBlockStartEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = event.contentBlockIndex!;\n\tconst start = event.start;\n\n\tif (start?.toolUse) {\n\t\tconst block: Block = {\n\t\t\ttype: \"toolCall\",\n\t\t\tid: start.toolUse.toolUseId || \"\",\n\t\t\tname: start.toolUse.name || \"\",\n\t\t\targuments: {},\n\t\t\tpartialJson: \"\",\n\t\t\tindex,\n\t\t};\n\t\toutput.content.push(block);\n\t\tstream.push({ type: \"toolcall_start\", contentIndex: blocks.length - 1, partial: output });\n\t}\n}\n\nfunction handleContentBlockDelta(\n\tevent: ContentBlockDeltaEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst contentBlockIndex = event.contentBlockIndex!;\n\tconst delta = event.delta;\n\tlet index = blocks.findIndex((b) => b.index === contentBlockIndex);\n\tlet block = blocks[index];\n\n\tif (delta?.text !== undefined) {\n\t\t// If no text block exists yet, create one, as `handleContentBlockStart` is not sent for text blocks\n\t\tif (!block) {\n\t\t\tconst newBlock: Block = { type: \"text\", text: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tindex = blocks.length - 1;\n\t\t\tblock = blocks[index];\n\t\t\tstream.push({ type: \"text_start\", contentIndex: index, partial: output });\n\t\t}\n\t\tif (block.type === \"text\") {\n\t\t\tblock.text += delta.text;\n\t\t\tstream.push({ type: \"text_delta\", contentIndex: index, delta: delta.text, partial: output });\n\t\t}\n\t} else if (delta?.toolUse && block?.type === \"toolCall\") {\n\t\tblock.partialJson = (block.partialJson || \"\") + (delta.toolUse.input || \"\");\n\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\tstream.push({ type: \"toolcall_delta\", contentIndex: index, delta: delta.toolUse.input || \"\", partial: output });\n\t} else if (delta?.reasoningContent) {\n\t\tlet thinkingBlock = block;\n\t\tlet thinkingIndex = index;\n\n\t\tif (!thinkingBlock) {\n\t\t\tconst newBlock: Block = { type: \"thinking\", thinking: \"\", thinkingSignature: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tthinkingIndex = blocks.length - 1;\n\t\t\tthinkingBlock = blocks[thinkingIndex];\n\t\t\tstream.push({ type: \"thinking_start\", contentIndex: thinkingIndex, partial: output });\n\t\t}\n\n\t\tif (thinkingBlock?.type === \"thinking\") {\n\t\t\tif (delta.reasoningContent.text) {\n\t\t\t\tthinkingBlock.thinking += delta.reasoningContent.text;\n\t\t\t\tstream.push({\n\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\tcontentIndex: thinkingIndex,\n\t\t\t\t\tdelta: delta.reasoningContent.text,\n\t\t\t\t\tpartial: output,\n\t\t\t\t});\n\t\t\t}\n\t\t\tif (delta.reasoningContent.signature) {\n\t\t\t\tthinkingBlock.thinkingSignature =\n\t\t\t\t\t(thinkingBlock.thinkingSignature || \"\") + delta.reasoningContent.signature;\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunction handleMetadata(\n\tevent: ConverseStreamMetadataEvent,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toutput: AssistantMessage,\n): void {\n\tif (event.usage) {\n\t\toutput.usage.input = event.usage.inputTokens || 0;\n\t\toutput.usage.output = event.usage.outputTokens || 0;\n\t\toutput.usage.cacheRead = event.usage.cacheReadInputTokens || 0;\n\t\toutput.usage.cacheWrite = event.usage.cacheWriteInputTokens || 0;\n\t\toutput.usage.totalTokens = event.usage.totalTokens || output.usage.input + output.usage.output;\n\t\tcalculateCost(model, output.usage);\n\t}\n}\n\nfunction handleContentBlockStop(\n\tevent: ContentBlockStopEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = blocks.findIndex((b) => b.index === event.contentBlockIndex);\n\tconst block = blocks[index];\n\tif (!block) return;\n\tdelete (block as Block).index;\n\n\tswitch (block.type) {\n\t\tcase \"text\":\n\t\t\tstream.push({ type: \"text_end\", contentIndex: index, content: block.text, partial: output });\n\t\t\tbreak;\n\t\tcase \"thinking\":\n\t\t\tstream.push({ type: \"thinking_end\", contentIndex: index, content: block.thinking, partial: output });\n\t\t\tbreak;\n\t\tcase \"toolCall\":\n\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t// Finalize in-place and strip the scratch buffer so replay only\n\t\t\t// carries parsed arguments.\n\t\t\tdelete (block as Block).partialJson;\n\t\t\tstream.push({ type: \"toolcall_end\", contentIndex: index, toolCall: block, partial: output });\n\t\t\tbreak;\n\t}\n}\n\n/**\n * Check if the model supports adaptive thinking (Opus 4.6+, Sonnet 4.6).\n */\nfunction supportsAdaptiveThinking(modelId: string): boolean {\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\nfunction mapThinkingLevelToEffort(\n\tlevel: SimpleStreamOptions[\"reasoning\"],\n\tmodelId: string,\n): \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\" {\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\tcase \"low\":\n\t\t\treturn \"low\";\n\t\tcase \"medium\":\n\t\t\treturn \"medium\";\n\t\tcase \"high\":\n\t\t\treturn \"high\";\n\t\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\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\n/**\n * Check if the model supports prompt caching.\n * Supported: Claude 3.5 Haiku, Claude 3.7 Sonnet, Claude 4.x models\n *\n * For base models and system-defined inference profiles the model ID / ARN\n * contains the model name, so we can decide locally.\n *\n * For application inference profiles (whose ARNs don't contain the model name),\n * set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.  Amazon Nova models\n * have automatic caching and don't need explicit cache points.\n */\nfunction supportsPromptCaching(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst id = model.id.toLowerCase();\n\tif (!id.includes(\"claude\")) {\n\t\t// Application inference profiles don't contain the model name in the ARN.\n\t\t// Allow users to force cache points via environment variable.\n\t\tif (typeof process !== \"undefined\" && process.env.AWS_BEDROCK_FORCE_CACHE === \"1\") return true;\n\t\treturn false;\n\t}\n\t// Claude 4.x models (opus-4, sonnet-4, haiku-4)\n\tif (id.includes(\"-4-\") || id.includes(\"-4.\")) return true;\n\t// Claude 3.7 Sonnet\n\tif (id.includes(\"claude-3-7-sonnet\")) return true;\n\t// Claude 3.5 Haiku\n\tif (id.includes(\"claude-3-5-haiku\")) return true;\n\treturn false;\n}\n\n/**\n * Check if the model supports thinking signatures in reasoningContent.\n * Only Anthropic Claude models support the signature field.\n * Other models (OpenAI, Qwen, Minimax, Moonshot, etc.) reject it with:\n * \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n */\nfunction supportsThinkingSignature(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst id = model.id.toLowerCase();\n\treturn id.includes(\"anthropic.claude\") || id.includes(\"anthropic/claude\");\n}\n\nfunction buildSystemPrompt(\n\tsystemPrompt: string | undefined,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n): SystemContentBlock[] | undefined {\n\tif (!systemPrompt) return undefined;\n\n\tconst blocks: SystemContentBlock[] = [{ text: sanitizeSurrogates(systemPrompt) }];\n\n\t// Add cache point for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model)) {\n\t\tblocks.push({\n\t\t\tcachePoint: { type: CachePointType.DEFAULT, ...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}) },\n\t\t});\n\t}\n\n\treturn blocks;\n}\n\nfunction normalizeToolCallId(id: string): string {\n\tconst sanitized = id.replace(/[^a-zA-Z0-9_-]/g, \"_\");\n\treturn sanitized.length > 64 ? sanitized.slice(0, 64) : sanitized;\n}\n\nfunction convertMessages(\n\tcontext: Context,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n): Message[] {\n\tconst result: Message[] = [];\n\tconst transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);\n\n\tfor (let i = 0; i < transformedMessages.length; i++) {\n\t\tconst m = transformedMessages[i];\n\n\t\tswitch (m.role) {\n\t\t\tcase \"user\":\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent:\n\t\t\t\t\t\ttypeof m.content === \"string\"\n\t\t\t\t\t\t\t? [{ text: sanitizeSurrogates(m.content) }]\n\t\t\t\t\t\t\t: m.content.map((c) => {\n\t\t\t\t\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\t\t\t\t\tcase \"text\":\n\t\t\t\t\t\t\t\t\t\t\treturn { text: sanitizeSurrogates(c.text) };\n\t\t\t\t\t\t\t\t\t\tcase \"image\":\n\t\t\t\t\t\t\t\t\t\t\treturn { image: createImageBlock(c.mimeType, c.data) };\n\t\t\t\t\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\t\t\t\t\tthrow new Error(\"Unknown user content type\");\n\t\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t\t}),\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\tcase \"assistant\": {\n\t\t\t\t// Skip assistant messages with empty content (e.g., from aborted requests)\n\t\t\t\t// Bedrock rejects messages with empty content arrays\n\t\t\t\tif (m.content.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tconst contentBlocks: ContentBlock[] = [];\n\t\t\t\tfor (const c of m.content) {\n\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\tcase \"text\":\n\t\t\t\t\t\t\t// Skip empty text blocks\n\t\t\t\t\t\t\tif (c.text.trim().length === 0) continue;\n\t\t\t\t\t\t\tcontentBlocks.push({ text: sanitizeSurrogates(c.text) });\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tcase \"toolCall\":\n\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\ttoolUse: { toolUseId: c.id, name: c.name, input: c.arguments },\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tcase \"thinking\":\n\t\t\t\t\t\t\t// Skip empty thinking blocks\n\t\t\t\t\t\t\tif (c.thinking.trim().length === 0) continue;\n\t\t\t\t\t\t\t// Only Anthropic models support the signature field in reasoningText.\n\t\t\t\t\t\t\t// For other models, we omit the signature to avoid errors like:\n\t\t\t\t\t\t\t// \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n\t\t\t\t\t\t\tif (supportsThinkingSignature(model)) {\n\t\t\t\t\t\t\t\t// Signatures arrive after thinking deltas. If a partial or externally\n\t\t\t\t\t\t\t\t// persisted message lacks a signature, Bedrock rejects the replayed\n\t\t\t\t\t\t\t\t// reasoning block. Fall back to plain text, matching Anthropic.\n\t\t\t\t\t\t\t\tif (!c.thinkingSignature || c.thinkingSignature.trim().length === 0) {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({ text: sanitizeSurrogates(c.thinking) });\n\t\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\t\treasoningText: {\n\t\t\t\t\t\t\t\t\t\t\t\ttext: sanitizeSurrogates(c.thinking),\n\t\t\t\t\t\t\t\t\t\t\t\tsignature: c.thinkingSignature,\n\t\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\treasoningText: { text: sanitizeSurrogates(c.thinking) },\n\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\tthrow new Error(\"Unknown assistant content type\");\n\t\t\t\t\t}\n\t\t\t\t}\n\t\t\t\t// Skip if all content blocks were filtered out\n\t\t\t\tif (contentBlocks.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.ASSISTANT,\n\t\t\t\t\tcontent: contentBlocks,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tcase \"toolResult\": {\n\t\t\t\t// Collect all consecutive toolResult messages into a single user message\n\t\t\t\t// Bedrock requires all tool results to be in one message\n\t\t\t\tconst toolResults: ContentBlock.ToolResultMember[] = [];\n\n\t\t\t\t// Add current tool result with all content blocks combined\n\t\t\t\ttoolResults.push({\n\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\ttoolUseId: m.toolCallId,\n\t\t\t\t\t\tcontent: m.content.map((c) =>\n\t\t\t\t\t\t\tc.type === \"image\"\n\t\t\t\t\t\t\t\t? { image: createImageBlock(c.mimeType, c.data) }\n\t\t\t\t\t\t\t\t: { text: sanitizeSurrogates(c.text) },\n\t\t\t\t\t\t),\n\t\t\t\t\t\tstatus: m.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t},\n\t\t\t\t});\n\n\t\t\t\t// Look ahead for consecutive toolResult messages\n\t\t\t\tlet j = i + 1;\n\t\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\t\tconst nextMsg = transformedMessages[j] as ToolResultMessage;\n\t\t\t\t\ttoolResults.push({\n\t\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\t\ttoolUseId: nextMsg.toolCallId,\n\t\t\t\t\t\t\tcontent: nextMsg.content.map((c) =>\n\t\t\t\t\t\t\t\tc.type === \"image\"\n\t\t\t\t\t\t\t\t\t? { image: createImageBlock(c.mimeType, c.data) }\n\t\t\t\t\t\t\t\t\t: { text: sanitizeSurrogates(c.text) },\n\t\t\t\t\t\t\t),\n\t\t\t\t\t\t\tstatus: nextMsg.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t\t},\n\t\t\t\t\t});\n\t\t\t\t\tj++;\n\t\t\t\t}\n\n\t\t\t\t// Skip the messages we've already processed\n\t\t\t\ti = j - 1;\n\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent: toolResults,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tdefault:\n\t\t\t\tthrow new Error(\"Unknown message role\");\n\t\t}\n\t}\n\n\t// Add cache point to the last user message for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model) && result.length > 0) {\n\t\tconst lastMessage = result[result.length - 1];\n\t\tif (lastMessage.role === ConversationRole.USER && lastMessage.content) {\n\t\t\t(lastMessage.content as ContentBlock[]).push({\n\t\t\t\tcachePoint: {\n\t\t\t\t\ttype: CachePointType.DEFAULT,\n\t\t\t\t\t...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}),\n\t\t\t\t},\n\t\t\t});\n\t\t}\n\t}\n\n\treturn result;\n}\n\nfunction convertToolConfig(\n\ttools: Tool[] | undefined,\n\ttoolChoice: BedrockOptions[\"toolChoice\"],\n): ToolConfiguration | undefined {\n\tif (!tools?.length || toolChoice === \"none\") return undefined;\n\n\tconst bedrockTools: BedrockTool[] = tools.map((tool) => ({\n\t\ttoolSpec: {\n\t\t\tname: tool.name,\n\t\t\tdescription: tool.description,\n\t\t\tinputSchema: { json: tool.parameters as unknown as DocumentType },\n\t\t},\n\t}));\n\n\tlet bedrockToolChoice: ToolChoice | undefined;\n\tswitch (toolChoice) {\n\t\tcase \"auto\":\n\t\t\tbedrockToolChoice = { auto: {} };\n\t\t\tbreak;\n\t\tcase \"any\":\n\t\t\tbedrockToolChoice = { any: {} };\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tif (toolChoice?.type === \"tool\") {\n\t\t\t\tbedrockToolChoice = { tool: { name: toolChoice.name } };\n\t\t\t}\n\t}\n\n\treturn { tools: bedrockTools, toolChoice: bedrockToolChoice };\n}\n\nfunction mapStopReason(reason: string | undefined): StopReason {\n\tswitch (reason) {\n\t\tcase BedrockStopReason.END_TURN:\n\t\tcase BedrockStopReason.STOP_SEQUENCE:\n\t\t\treturn \"stop\";\n\t\tcase BedrockStopReason.MAX_TOKENS:\n\t\tcase BedrockStopReason.MODEL_CONTEXT_WINDOW_EXCEEDED:\n\t\t\treturn \"length\";\n\t\tcase BedrockStopReason.TOOL_USE:\n\t\t\treturn \"toolUse\";\n\t\tdefault:\n\t\t\treturn \"error\";\n\t}\n}\n\nfunction getConfiguredBedrockRegion(options: BedrockOptions): string | undefined {\n\tif (typeof process === \"undefined\") {\n\t\treturn options.region;\n\t}\n\n\treturn options.region || process.env.AWS_REGION || process.env.AWS_DEFAULT_REGION || undefined;\n}\n\nfunction hasConfiguredBedrockProfile(): boolean {\n\tif (typeof process === \"undefined\") {\n\t\treturn false;\n\t}\n\n\treturn Boolean(process.env.AWS_PROFILE);\n}\n\nfunction getStandardBedrockEndpointRegion(baseUrl: string | undefined): string | undefined {\n\tif (!baseUrl) {\n\t\treturn undefined;\n\t}\n\n\ttry {\n\t\tconst { hostname } = new URL(baseUrl);\n\t\tconst match = hostname.toLowerCase().match(/^bedrock-runtime(?:-fips)?\\.([a-z0-9-]+)\\.amazonaws\\.com(?:\\.cn)?$/);\n\t\treturn match?.[1];\n\t} catch {\n\t\treturn undefined;\n\t}\n}\n\nfunction shouldUseExplicitBedrockEndpoint(\n\tbaseUrl: string,\n\tconfiguredRegion: string | undefined,\n\thasConfiguredProfile: boolean,\n): boolean {\n\tconst endpointRegion = getStandardBedrockEndpointRegion(baseUrl);\n\tif (!endpointRegion) {\n\t\treturn true;\n\t}\n\n\treturn !configuredRegion && !hasConfiguredProfile;\n}\n\nfunction isGovCloudBedrockTarget(model: Model<\"bedrock-converse-stream\">, options: BedrockOptions): boolean {\n\tconst region = getConfiguredBedrockRegion(options);\n\tif (region?.toLowerCase().startsWith(\"us-gov-\")) {\n\t\treturn true;\n\t}\n\n\tconst modelId = model.id.toLowerCase();\n\treturn modelId.startsWith(\"us-gov.\") || modelId.startsWith(\"arn:aws-us-gov:\");\n}\n\nfunction buildAdditionalModelRequestFields(\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toptions: BedrockOptions,\n): Record<string, any> | undefined {\n\tif (!options.reasoning || !model.reasoning) {\n\t\treturn undefined;\n\t}\n\n\tif (model.id.includes(\"anthropic.claude\") || model.id.includes(\"anthropic/claude\")) {\n\t\t// GovCloud Bedrock currently rejects the Claude thinking.display field.\n\t\t// Omit it there until the GovCloud Converse schema catches up.\n\t\tconst display = isGovCloudBedrockTarget(model, options) ? undefined : (options.thinkingDisplay ?? \"summarized\");\n\t\tconst result: Record<string, any> = supportsAdaptiveThinking(model.id)\n\t\t\t? {\n\t\t\t\t\tthinking: { type: \"adaptive\", ...(display !== undefined ? { display } : {}) },\n\t\t\t\t\toutput_config: { effort: mapThinkingLevelToEffort(options.reasoning, model.id) },\n\t\t\t\t}\n\t\t\t: (() => {\n\t\t\t\t\tconst defaultBudgets: Record<ThinkingLevel, number> = {\n\t\t\t\t\t\tminimal: 1024,\n\t\t\t\t\t\tlow: 2048,\n\t\t\t\t\t\tmedium: 8192,\n\t\t\t\t\t\thigh: 16384,\n\t\t\t\t\t\txhigh: 16384, // Claude doesn't support xhigh, clamp to high\n\t\t\t\t\t};\n\n\t\t\t\t\t// Custom budgets override defaults (xhigh not in ThinkingBudgets, use high)\n\t\t\t\t\tconst level = options.reasoning === \"xhigh\" ? \"high\" : options.reasoning;\n\t\t\t\t\tconst budget = options.thinkingBudgets?.[level] ?? defaultBudgets[options.reasoning];\n\n\t\t\t\t\treturn {\n\t\t\t\t\t\tthinking: {\n\t\t\t\t\t\t\ttype: \"enabled\",\n\t\t\t\t\t\t\tbudget_tokens: budget,\n\t\t\t\t\t\t\t...(display !== undefined ? { display } : {}),\n\t\t\t\t\t\t},\n\t\t\t\t\t};\n\t\t\t\t})();\n\n\t\tif (!supportsAdaptiveThinking(model.id) && (options.interleavedThinking ?? true)) {\n\t\t\tresult.anthropic_beta = [\"interleaved-thinking-2025-05-14\"];\n\t\t}\n\n\t\treturn result;\n\t}\n\n\treturn undefined;\n}\n\nfunction createImageBlock(mimeType: string, data: string) {\n\tlet format: ImageFormat;\n\tswitch (mimeType) {\n\t\tcase \"image/jpeg\":\n\t\tcase \"image/jpg\":\n\t\t\tformat = ImageFormat.JPEG;\n\t\t\tbreak;\n\t\tcase \"image/png\":\n\t\t\tformat = ImageFormat.PNG;\n\t\t\tbreak;\n\t\tcase \"image/gif\":\n\t\t\tformat = ImageFormat.GIF;\n\t\t\tbreak;\n\t\tcase \"image/webp\":\n\t\t\tformat = ImageFormat.WEBP;\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tthrow new Error(`Unknown image type: ${mimeType}`);\n\t}\n\n\tconst binaryString = atob(data);\n\tconst bytes = new Uint8Array(binaryString.length);\n\tfor (let i = 0; i < binaryString.length; i++) {\n\t\tbytes[i] = binaryString.charCodeAt(i);\n\t}\n\n\treturn { source: { bytes }, format };\n}\n"]}
+{"version":3,"file":"amazon-bedrock.d.ts","sourceRoot":"","sources":["../../src/providers/amazon-bedrock.ts"],"names":[],"mappings":"AAwBA,OAAO,KAAK,EAMX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAEb,eAAe,EAEf,aAAa,EAIb,MAAM,aAAa,CAAC;AAOrB,MAAM,MAAM,sBAAsB,GAAG,YAAY,GAAG,SAAS,CAAC;AAE9D,MAAM,WAAW,cAAe,SAAQ,aAAa;IACpD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IAEtE,SAAS,CAAC,EAAE,aAAa,CAAC;IAE1B,eAAe,CAAC,EAAE,eAAe,CAAC;IAElC,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;;;;;;OASG;IACH,eAAe,CAAC,EAAE,sBAAsB,CAAC;IACzC;;;sGAGkG;IAClG,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACzC;;;;yGAIqG;IACrG,WAAW,CAAC,EAAE,MAAM,CAAC;CACrB;AAID,eAAO,MAAM,aAAa,EAAE,cAAc,CAAC,yBAAyB,EAAE,cAAc,CAgMnF,CAAC;AAgCF,eAAO,MAAM,mBAAmB,EAAE,cAAc,CAAC,yBAAyB,EAAE,mBAAmB,CA0C9F,CAAC","sourcesContent":["import {\n\tBedrockRuntimeClient,\n\ttype BedrockRuntimeClientConfig,\n\tBedrockRuntimeServiceException,\n\tStopReason as BedrockStopReason,\n\ttype Tool as BedrockTool,\n\tCachePointType,\n\tCacheTTL,\n\ttype ContentBlock,\n\ttype ContentBlockDeltaEvent,\n\ttype ContentBlockStartEvent,\n\ttype ContentBlockStopEvent,\n\tConversationRole,\n\tConverseStreamCommand,\n\ttype ConverseStreamMetadataEvent,\n\tImageFormat,\n\ttype Message,\n\ttype SystemContentBlock,\n\ttype ToolChoice,\n\ttype ToolConfiguration,\n\tToolResultStatus,\n} from \"@aws-sdk/client-bedrock-runtime\";\nimport type { DocumentType } from \"@smithy/types\";\nimport { calculateCost } from \"../models.js\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tModel,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingBudgets,\n\tThinkingContent,\n\tThinkingLevel,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.js\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.js\";\nimport { parseStreamingJson } from \"../utils/json-parse.js\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.js\";\nimport { adjustMaxTokensForThinking, buildBaseOptions, clampReasoning } from \"./simple-options.js\";\nimport { transformMessages } from \"./transform-messages.js\";\n\nexport type BedrockThinkingDisplay = \"summarized\" | \"omitted\";\n\nexport interface BedrockOptions extends StreamOptions {\n\tregion?: string;\n\tprofile?: string;\n\ttoolChoice?: \"auto\" | \"any\" | \"none\" | { type: \"tool\"; name: string };\n\t/* See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-reasoning.html for supported models. */\n\treasoning?: ThinkingLevel;\n\t/* Custom token budgets per thinking level. Overrides default budgets. */\n\tthinkingBudgets?: ThinkingBudgets;\n\t/* Only supported by Claude 4.x models, see https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-extended-thinking.html#claude-messages-extended-thinking-tool-use-interleaved */\n\tinterleavedThinking?: boolean;\n\t/**\n\t * Controls how Claude's thinking content is returned in responses.\n\t * - \"summarized\": Thinking blocks contain summarized thinking text (default here).\n\t * - \"omitted\": Thinking content is redacted but the signature still travels back\n\t *   for multi-turn continuity, reducing time-to-first-text-token.\n\t *\n\t * Note: Anthropic's API default for Claude Opus 4.7 and Mythos Preview is\n\t * \"omitted\". We default to \"summarized\" here to keep behavior consistent with\n\t * older Claude 4 models. Only applies to Claude models on Bedrock.\n\t */\n\tthinkingDisplay?: BedrockThinkingDisplay;\n\t/** Key-value pairs attached to the inference request for cost allocation tagging.\n\t * Keys: max 64 chars, no `aws:` prefix. Values: max 256 chars. Max 50 pairs.\n\t * Tags appear in AWS Cost Explorer split cost allocation data.\n\t * @see https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html */\n\trequestMetadata?: Record<string, string>;\n\t/** Bearer token for Bedrock API key authentication.\n\t * When set, bypasses SigV4 signing and sends Authorization: Bearer <token> instead.\n\t * Requires `bedrock:CallWithBearerToken` IAM permission on the token's identity.\n\t * Set via AWS_BEARER_TOKEN_BEDROCK env var or pass directly.\n\t * @see https://docs.aws.amazon.com/service-authorization/latest/reference/list_amazonbedrock.html */\n\tbearerToken?: string;\n}\n\ntype Block = (TextContent | ThinkingContent | ToolCall) & { index?: number; partialJson?: string };\n\nexport const streamBedrock: StreamFunction<\"bedrock-converse-stream\", BedrockOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions: BedrockOptions = {},\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: \"bedrock-converse-stream\" 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\tconst blocks = output.content as Block[];\n\n\t\tconst config: BedrockRuntimeClientConfig = {\n\t\t\tprofile: options.profile,\n\t\t};\n\t\tconst configuredRegion = getConfiguredBedrockRegion(options);\n\t\tconst hasConfiguredProfile = hasConfiguredBedrockProfile();\n\t\tconst endpointRegion = getStandardBedrockEndpointRegion(model.baseUrl);\n\t\tconst useExplicitEndpoint = shouldUseExplicitBedrockEndpoint(\n\t\t\tmodel.baseUrl,\n\t\t\tconfiguredRegion,\n\t\t\thasConfiguredProfile,\n\t\t);\n\n\t\t// Only pin standard AWS Bedrock runtime endpoints when no region/profile is configured.\n\t\t// This preserves custom endpoints (VPC/proxy) from #3402 without forcing built-in\n\t\t// catalog defaults such as us-east-1 to override AWS_REGION/AWS_PROFILE.\n\t\tif (useExplicitEndpoint) {\n\t\t\tconfig.endpoint = model.baseUrl;\n\t\t}\n\n\t\t// Resolve bearer token for Bedrock API key auth.\n\t\tconst bearerToken = options.bearerToken || process.env.AWS_BEARER_TOKEN_BEDROCK || undefined;\n\t\tconst useBearerToken = bearerToken !== undefined && process.env.AWS_BEDROCK_SKIP_AUTH !== \"1\";\n\n\t\t// in Node.js/Bun environment only\n\t\tif (typeof process !== \"undefined\" && (process.versions?.node || process.versions?.bun)) {\n\t\t\t// Region resolution: explicit option > env vars > SDK default chain.\n\t\t\t// When AWS_PROFILE is set, we leave region undefined so the SDK can\n\t\t\t// resovle it from aws profile configs. Otherwise fall back to us-east-1.\n\t\t\tif (configuredRegion) {\n\t\t\t\tconfig.region = configuredRegion;\n\t\t\t} else if (endpointRegion && useExplicitEndpoint) {\n\t\t\t\tconfig.region = endpointRegion;\n\t\t\t} else if (!hasConfiguredProfile) {\n\t\t\t\tconfig.region = \"us-east-1\";\n\t\t\t}\n\n\t\t\t// Support proxies that don't need authentication\n\t\t\tif (process.env.AWS_BEDROCK_SKIP_AUTH === \"1\") {\n\t\t\t\tconfig.credentials = {\n\t\t\t\t\taccessKeyId: \"dummy-access-key\",\n\t\t\t\t\tsecretAccessKey: \"dummy-secret-key\",\n\t\t\t\t};\n\t\t\t}\n\n\t\t\tif (\n\t\t\t\tprocess.env.HTTP_PROXY ||\n\t\t\t\tprocess.env.HTTPS_PROXY ||\n\t\t\t\tprocess.env.NO_PROXY ||\n\t\t\t\tprocess.env.http_proxy ||\n\t\t\t\tprocess.env.https_proxy ||\n\t\t\t\tprocess.env.no_proxy\n\t\t\t) {\n\t\t\t\tconst nodeHttpHandler = await import(\"@smithy/node-http-handler\");\n\t\t\t\tconst proxyAgent = await import(\"proxy-agent\");\n\n\t\t\t\tconst agent = new proxyAgent.ProxyAgent();\n\n\t\t\t\t// Bedrock runtime uses NodeHttp2Handler by default since v3.798.0, which is based\n\t\t\t\t// on `http2` module and has no support for http agent.\n\t\t\t\t// Use NodeHttpHandler to support http agent.\n\t\t\t\tconfig.requestHandler = new nodeHttpHandler.NodeHttpHandler({\n\t\t\t\t\thttpAgent: agent,\n\t\t\t\t\thttpsAgent: agent,\n\t\t\t\t});\n\t\t\t} else if (process.env.AWS_BEDROCK_FORCE_HTTP1 === \"1\") {\n\t\t\t\t// Some custom endpoints require HTTP/1.1 instead of HTTP/2\n\t\t\t\tconst nodeHttpHandler = await import(\"@smithy/node-http-handler\");\n\t\t\t\tconfig.requestHandler = new nodeHttpHandler.NodeHttpHandler();\n\t\t\t}\n\t\t} else {\n\t\t\t// Non-Node environment (browser): fall back to us-east-1 since\n\t\t\t// there's no config file resolution available.\n\t\t\tconfig.region =\n\t\t\t\tconfiguredRegion || (endpointRegion && useExplicitEndpoint ? endpointRegion : undefined) || \"us-east-1\";\n\t\t}\n\n\t\tif (useBearerToken) {\n\t\t\tconfig.token = { token: bearerToken };\n\t\t\tconfig.authSchemePreference = [\"httpBearerAuth\"];\n\t\t}\n\n\t\ttry {\n\t\t\tconst client = new BedrockRuntimeClient(config);\n\t\t\tconst cacheRetention = resolveCacheRetention(options.cacheRetention);\n\t\t\tlet commandInput = {\n\t\t\t\tmodelId: model.id,\n\t\t\t\tmessages: convertMessages(context, model, cacheRetention),\n\t\t\t\tsystem: buildSystemPrompt(context.systemPrompt, model, cacheRetention),\n\t\t\t\tinferenceConfig: {\n\t\t\t\t\t...(options.maxTokens !== undefined && { maxTokens: options.maxTokens }),\n\t\t\t\t\t...(options.temperature !== undefined && { temperature: options.temperature }),\n\t\t\t\t},\n\t\t\t\ttoolConfig: convertToolConfig(context.tools, options.toolChoice),\n\t\t\t\tadditionalModelRequestFields: buildAdditionalModelRequestFields(model, options),\n\t\t\t\t...(options.requestMetadata !== undefined && { requestMetadata: options.requestMetadata }),\n\t\t\t};\n\t\t\tconst nextCommandInput = await options?.onPayload?.(commandInput, model);\n\t\t\tif (nextCommandInput !== undefined) {\n\t\t\t\tcommandInput = nextCommandInput as typeof commandInput;\n\t\t\t}\n\t\t\tconst command = new ConverseStreamCommand(commandInput);\n\n\t\t\tconst response = await client.send(command, { abortSignal: options.signal });\n\t\t\tif (response.$metadata.httpStatusCode !== undefined) {\n\t\t\t\tconst responseHeaders: Record<string, string> = {};\n\t\t\t\tif (response.$metadata.requestId) {\n\t\t\t\t\tresponseHeaders[\"x-amzn-requestid\"] = response.$metadata.requestId;\n\t\t\t\t}\n\t\t\t\tawait options?.onResponse?.({ status: response.$metadata.httpStatusCode, headers: responseHeaders }, model);\n\t\t\t}\n\n\t\t\tfor await (const item of response.stream!) {\n\t\t\t\tif (item.messageStart) {\n\t\t\t\t\tif (item.messageStart.role !== ConversationRole.ASSISTANT) {\n\t\t\t\t\t\tthrow new Error(\"Unexpected assistant message start but got user message start instead\");\n\t\t\t\t\t}\n\t\t\t\t\tstream.push({ type: \"start\", partial: output });\n\t\t\t\t} else if (item.contentBlockStart) {\n\t\t\t\t\thandleContentBlockStart(item.contentBlockStart, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockDelta) {\n\t\t\t\t\thandleContentBlockDelta(item.contentBlockDelta, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockStop) {\n\t\t\t\t\thandleContentBlockStop(item.contentBlockStop, blocks, output, stream);\n\t\t\t\t} else if (item.messageStop) {\n\t\t\t\t\toutput.stopReason = mapStopReason(item.messageStop.stopReason);\n\t\t\t\t} else if (item.metadata) {\n\t\t\t\t\thandleMetadata(item.metadata, model, output);\n\t\t\t\t} else if (item.internalServerException) {\n\t\t\t\t\tthrow item.internalServerException;\n\t\t\t\t} else if (item.modelStreamErrorException) {\n\t\t\t\t\tthrow item.modelStreamErrorException;\n\t\t\t\t} else if (item.validationException) {\n\t\t\t\t\tthrow item.validationException;\n\t\t\t\t} else if (item.throttlingException) {\n\t\t\t\t\tthrow item.throttlingException;\n\t\t\t\t} else if (item.serviceUnavailableException) {\n\t\t\t\t\tthrow item.serviceUnavailableException;\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 === \"error\" || output.stopReason === \"aborted\") {\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 Block).index;\n\t\t\t\t// partialJson is only a streaming scratch buffer; never persist it.\n\t\t\t\tdelete (block as Block).partialJson;\n\t\t\t}\n\t\t\toutput.stopReason = options.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = formatBedrockError(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 * Human-readable prefixes for Bedrock SDK exception names.\n * The downstream retry logic in agent-session matches patterns like\n * `server.?error` and `service.?unavailable`, so we preserve the legacy\n * prefix format rather than using the raw SDK exception name.\n */\nconst BEDROCK_ERROR_PREFIXES: Record<string, string> = {\n\tInternalServerException: \"Internal server error\",\n\tModelStreamErrorException: \"Model stream error\",\n\tValidationException: \"Validation error\",\n\tThrottlingException: \"Throttling error\",\n\tServiceUnavailableException: \"Service unavailable\",\n};\n\n/**\n * Format a Bedrock error with a human-readable prefix.\n * AWS SDK exceptions (both from `client.send()` and from stream event items)\n * extend BedrockRuntimeServiceException. We map the `.name` to a stable\n * human-readable prefix so downstream consumers (retry logic, context-overflow\n * detection) can distinguish error categories via simple string matching.\n */\nfunction formatBedrockError(error: unknown): string {\n\tconst message = error instanceof Error ? error.message : JSON.stringify(error);\n\tif (error instanceof BedrockRuntimeServiceException) {\n\t\tconst prefix = BEDROCK_ERROR_PREFIXES[error.name] ?? error.name;\n\t\treturn `${prefix}: ${message}`;\n\t}\n\treturn message;\n}\n\nexport const streamSimpleBedrock: StreamFunction<\"bedrock-converse-stream\", SimpleStreamOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst base = buildBaseOptions(model, options, undefined);\n\tif (!options?.reasoning) {\n\t\treturn streamBedrock(model, context, { ...base, reasoning: undefined } satisfies BedrockOptions);\n\t}\n\n\tif (isAnthropicClaudeModel(model)) {\n\t\tif (supportsAdaptiveThinking(model.id, model.name)) {\n\t\t\treturn streamBedrock(model, context, {\n\t\t\t\t...base,\n\t\t\t\treasoning: options.reasoning,\n\t\t\t\tthinkingBudgets: options.thinkingBudgets,\n\t\t\t} satisfies BedrockOptions);\n\t\t}\n\n\t\tconst adjusted = adjustMaxTokensForThinking(\n\t\t\tbase.maxTokens || 0,\n\t\t\tmodel.maxTokens,\n\t\t\toptions.reasoning,\n\t\t\toptions.thinkingBudgets,\n\t\t);\n\n\t\treturn streamBedrock(model, context, {\n\t\t\t...base,\n\t\t\tmaxTokens: adjusted.maxTokens,\n\t\t\treasoning: options.reasoning,\n\t\t\tthinkingBudgets: {\n\t\t\t\t...(options.thinkingBudgets || {}),\n\t\t\t\t[clampReasoning(options.reasoning)!]: adjusted.thinkingBudget,\n\t\t\t},\n\t\t} satisfies BedrockOptions);\n\t}\n\n\treturn streamBedrock(model, context, {\n\t\t...base,\n\t\treasoning: options.reasoning,\n\t\tthinkingBudgets: options.thinkingBudgets,\n\t} satisfies BedrockOptions);\n};\n\nfunction handleContentBlockStart(\n\tevent: ContentBlockStartEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = event.contentBlockIndex!;\n\tconst start = event.start;\n\n\tif (start?.toolUse) {\n\t\tconst block: Block = {\n\t\t\ttype: \"toolCall\",\n\t\t\tid: start.toolUse.toolUseId || \"\",\n\t\t\tname: start.toolUse.name || \"\",\n\t\t\targuments: {},\n\t\t\tpartialJson: \"\",\n\t\t\tindex,\n\t\t};\n\t\toutput.content.push(block);\n\t\tstream.push({ type: \"toolcall_start\", contentIndex: blocks.length - 1, partial: output });\n\t}\n}\n\nfunction handleContentBlockDelta(\n\tevent: ContentBlockDeltaEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst contentBlockIndex = event.contentBlockIndex!;\n\tconst delta = event.delta;\n\tlet index = blocks.findIndex((b) => b.index === contentBlockIndex);\n\tlet block = blocks[index];\n\n\tif (delta?.text !== undefined) {\n\t\t// If no text block exists yet, create one, as `handleContentBlockStart` is not sent for text blocks\n\t\tif (!block) {\n\t\t\tconst newBlock: Block = { type: \"text\", text: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tindex = blocks.length - 1;\n\t\t\tblock = blocks[index];\n\t\t\tstream.push({ type: \"text_start\", contentIndex: index, partial: output });\n\t\t}\n\t\tif (block.type === \"text\") {\n\t\t\tblock.text += delta.text;\n\t\t\tstream.push({ type: \"text_delta\", contentIndex: index, delta: delta.text, partial: output });\n\t\t}\n\t} else if (delta?.toolUse && block?.type === \"toolCall\") {\n\t\tblock.partialJson = (block.partialJson || \"\") + (delta.toolUse.input || \"\");\n\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\tstream.push({ type: \"toolcall_delta\", contentIndex: index, delta: delta.toolUse.input || \"\", partial: output });\n\t} else if (delta?.reasoningContent) {\n\t\tlet thinkingBlock = block;\n\t\tlet thinkingIndex = index;\n\n\t\tif (!thinkingBlock) {\n\t\t\tconst newBlock: Block = { type: \"thinking\", thinking: \"\", thinkingSignature: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tthinkingIndex = blocks.length - 1;\n\t\t\tthinkingBlock = blocks[thinkingIndex];\n\t\t\tstream.push({ type: \"thinking_start\", contentIndex: thinkingIndex, partial: output });\n\t\t}\n\n\t\tif (thinkingBlock?.type === \"thinking\") {\n\t\t\tif (delta.reasoningContent.text) {\n\t\t\t\tthinkingBlock.thinking += delta.reasoningContent.text;\n\t\t\t\tstream.push({\n\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\tcontentIndex: thinkingIndex,\n\t\t\t\t\tdelta: delta.reasoningContent.text,\n\t\t\t\t\tpartial: output,\n\t\t\t\t});\n\t\t\t}\n\t\t\tif (delta.reasoningContent.signature) {\n\t\t\t\tthinkingBlock.thinkingSignature =\n\t\t\t\t\t(thinkingBlock.thinkingSignature || \"\") + delta.reasoningContent.signature;\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunction handleMetadata(\n\tevent: ConverseStreamMetadataEvent,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toutput: AssistantMessage,\n): void {\n\tif (event.usage) {\n\t\toutput.usage.input = event.usage.inputTokens || 0;\n\t\toutput.usage.output = event.usage.outputTokens || 0;\n\t\toutput.usage.cacheRead = event.usage.cacheReadInputTokens || 0;\n\t\toutput.usage.cacheWrite = event.usage.cacheWriteInputTokens || 0;\n\t\toutput.usage.totalTokens = event.usage.totalTokens || output.usage.input + output.usage.output;\n\t\tcalculateCost(model, output.usage);\n\t}\n}\n\nfunction handleContentBlockStop(\n\tevent: ContentBlockStopEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = blocks.findIndex((b) => b.index === event.contentBlockIndex);\n\tconst block = blocks[index];\n\tif (!block) return;\n\tdelete (block as Block).index;\n\n\tswitch (block.type) {\n\t\tcase \"text\":\n\t\t\tstream.push({ type: \"text_end\", contentIndex: index, content: block.text, partial: output });\n\t\t\tbreak;\n\t\tcase \"thinking\":\n\t\t\tstream.push({ type: \"thinking_end\", contentIndex: index, content: block.thinking, partial: output });\n\t\t\tbreak;\n\t\tcase \"toolCall\":\n\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t// Finalize in-place and strip the scratch buffer so replay only\n\t\t\t// carries parsed arguments.\n\t\t\tdelete (block as Block).partialJson;\n\t\t\tstream.push({ type: \"toolcall_end\", contentIndex: index, toolCall: block, partial: output });\n\t\t\tbreak;\n\t}\n}\n\n/**\n * Check if the model supports adaptive thinking (Opus 4.6+, Sonnet 4.6).\n * Checks both model ID and model name to support application inference profiles\n * whose ARNs don't contain the model name.\n */\nfunction getModelMatchCandidates(modelId: string, modelName?: string): string[] {\n\tconst values = modelName ? [modelId, modelName] : [modelId];\n\treturn values.flatMap((value) => {\n\t\tconst lower = value.toLowerCase();\n\t\treturn [lower, lower.replace(/[\\s_.:]+/g, \"-\")];\n\t});\n}\n\nfunction supportsAdaptiveThinking(modelId: string, modelName?: string): boolean {\n\tconst candidates = getModelMatchCandidates(modelId, modelName);\n\treturn candidates.some((s) => s.includes(\"opus-4-6\") || s.includes(\"opus-4-7\") || s.includes(\"sonnet-4-6\"));\n}\n\nfunction mapThinkingLevelToEffort(\n\tlevel: SimpleStreamOptions[\"reasoning\"],\n\tmodelId: string,\n\tmodelName?: string,\n): \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\" {\n\tconst candidates = getModelMatchCandidates(modelId, modelName);\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\tcase \"low\":\n\t\t\treturn \"low\";\n\t\tcase \"medium\":\n\t\t\treturn \"medium\";\n\t\tcase \"high\":\n\t\t\treturn \"high\";\n\t\tcase \"xhigh\":\n\t\t\tif (candidates.some((s) => s.includes(\"opus-4-6\"))) {\n\t\t\t\treturn \"max\";\n\t\t\t}\n\t\t\tif (candidates.some((s) => s.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\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\n/**\n * Check if the model is an Anthropic Claude model on Bedrock.\n * Checks both model ID and model name to support application inference profiles\n * whose ARNs don't contain the model name.\n */\nfunction isAnthropicClaudeModel(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst id = model.id.toLowerCase();\n\tconst name = model.name?.toLowerCase() ?? \"\";\n\treturn (\n\t\tid.includes(\"anthropic.claude\") ||\n\t\tid.includes(\"anthropic/claude\") ||\n\t\tname.includes(\"anthropic.claude\") ||\n\t\tname.includes(\"anthropic/claude\") ||\n\t\tname.includes(\"claude\")\n\t);\n}\n\n/**\n * Check if the model supports prompt caching.\n * Supported: Claude 3.5 Haiku, Claude 3.7 Sonnet, Claude 4.x models\n *\n * For base models and system-defined inference profiles the model ID / ARN\n * contains the model name, so we can decide locally.\n *\n * For application inference profiles (whose ARNs don't contain the model name),\n * also checks model.name which is user-controlled via models.json or registerProvider.\n * As a last resort, set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.\n * Amazon Nova models have automatic caching and don't need explicit cache points.\n */\nfunction supportsPromptCaching(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst candidates = getModelMatchCandidates(model.id, model.name);\n\n\tconst hasClaudeRef = candidates.some((s) => s.includes(\"claude\"));\n\tif (!hasClaudeRef) {\n\t\t// Application inference profiles don't contain the model name in the ARN.\n\t\t// Allow users to force cache points via environment variable.\n\t\tif (typeof process !== \"undefined\" && process.env.AWS_BEDROCK_FORCE_CACHE === \"1\") return true;\n\t\treturn false;\n\t}\n\t// Claude 4.x models (opus-4, sonnet-4, haiku-4)\n\tif (candidates.some((s) => s.includes(\"-4-\"))) return true;\n\t// Claude 3.7 Sonnet\n\tif (candidates.some((s) => s.includes(\"claude-3-7-sonnet\"))) return true;\n\t// Claude 3.5 Haiku\n\tif (candidates.some((s) => s.includes(\"claude-3-5-haiku\"))) return true;\n\treturn false;\n}\n\n/**\n * Check if the model supports thinking signatures in reasoningContent.\n * Only Anthropic Claude models support the signature field.\n * Other models (OpenAI, Qwen, Minimax, Moonshot, etc.) reject it with:\n * \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n *\n * Checks both model ID and model name to support application inference profiles.\n */\nfunction supportsThinkingSignature(model: Model<\"bedrock-converse-stream\">): boolean {\n\treturn isAnthropicClaudeModel(model);\n}\n\nfunction buildSystemPrompt(\n\tsystemPrompt: string | undefined,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n): SystemContentBlock[] | undefined {\n\tif (!systemPrompt) return undefined;\n\n\tconst blocks: SystemContentBlock[] = [{ text: sanitizeSurrogates(systemPrompt) }];\n\n\t// Add cache point for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model)) {\n\t\tblocks.push({\n\t\t\tcachePoint: { type: CachePointType.DEFAULT, ...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}) },\n\t\t});\n\t}\n\n\treturn blocks;\n}\n\nfunction normalizeToolCallId(id: string): string {\n\tconst sanitized = id.replace(/[^a-zA-Z0-9_-]/g, \"_\");\n\treturn sanitized.length > 64 ? sanitized.slice(0, 64) : sanitized;\n}\n\nfunction convertMessages(\n\tcontext: Context,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n): Message[] {\n\tconst result: Message[] = [];\n\tconst transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);\n\n\tfor (let i = 0; i < transformedMessages.length; i++) {\n\t\tconst m = transformedMessages[i];\n\n\t\tswitch (m.role) {\n\t\t\tcase \"user\":\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent:\n\t\t\t\t\t\ttypeof m.content === \"string\"\n\t\t\t\t\t\t\t? [{ text: sanitizeSurrogates(m.content) }]\n\t\t\t\t\t\t\t: m.content.map((c) => {\n\t\t\t\t\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\t\t\t\t\tcase \"text\":\n\t\t\t\t\t\t\t\t\t\t\treturn { text: sanitizeSurrogates(c.text) };\n\t\t\t\t\t\t\t\t\t\tcase \"image\":\n\t\t\t\t\t\t\t\t\t\t\treturn { image: createImageBlock(c.mimeType, c.data) };\n\t\t\t\t\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\t\t\t\t\tthrow new Error(\"Unknown user content type\");\n\t\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t\t}),\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\tcase \"assistant\": {\n\t\t\t\t// Skip assistant messages with empty content (e.g., from aborted requests)\n\t\t\t\t// Bedrock rejects messages with empty content arrays\n\t\t\t\tif (m.content.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tconst contentBlocks: ContentBlock[] = [];\n\t\t\t\tfor (const c of m.content) {\n\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\tcase \"text\":\n\t\t\t\t\t\t\t// Skip empty text blocks\n\t\t\t\t\t\t\tif (c.text.trim().length === 0) continue;\n\t\t\t\t\t\t\tcontentBlocks.push({ text: sanitizeSurrogates(c.text) });\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tcase \"toolCall\":\n\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\ttoolUse: { toolUseId: c.id, name: c.name, input: c.arguments },\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tcase \"thinking\":\n\t\t\t\t\t\t\t// Skip empty thinking blocks\n\t\t\t\t\t\t\tif (c.thinking.trim().length === 0) continue;\n\t\t\t\t\t\t\t// Only Anthropic models support the signature field in reasoningText.\n\t\t\t\t\t\t\t// For other models, we omit the signature to avoid errors like:\n\t\t\t\t\t\t\t// \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n\t\t\t\t\t\t\tif (supportsThinkingSignature(model)) {\n\t\t\t\t\t\t\t\t// Signatures arrive after thinking deltas. If a partial or externally\n\t\t\t\t\t\t\t\t// persisted message lacks a signature, Bedrock rejects the replayed\n\t\t\t\t\t\t\t\t// reasoning block. Fall back to plain text, matching Anthropic.\n\t\t\t\t\t\t\t\tif (!c.thinkingSignature || c.thinkingSignature.trim().length === 0) {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({ text: sanitizeSurrogates(c.thinking) });\n\t\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\t\treasoningText: {\n\t\t\t\t\t\t\t\t\t\t\t\ttext: sanitizeSurrogates(c.thinking),\n\t\t\t\t\t\t\t\t\t\t\t\tsignature: c.thinkingSignature,\n\t\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\treasoningText: { text: sanitizeSurrogates(c.thinking) },\n\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\tthrow new Error(\"Unknown assistant content type\");\n\t\t\t\t\t}\n\t\t\t\t}\n\t\t\t\t// Skip if all content blocks were filtered out\n\t\t\t\tif (contentBlocks.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.ASSISTANT,\n\t\t\t\t\tcontent: contentBlocks,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tcase \"toolResult\": {\n\t\t\t\t// Collect all consecutive toolResult messages into a single user message\n\t\t\t\t// Bedrock requires all tool results to be in one message\n\t\t\t\tconst toolResults: ContentBlock.ToolResultMember[] = [];\n\n\t\t\t\t// Add current tool result with all content blocks combined\n\t\t\t\ttoolResults.push({\n\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\ttoolUseId: m.toolCallId,\n\t\t\t\t\t\tcontent: m.content.map((c) =>\n\t\t\t\t\t\t\tc.type === \"image\"\n\t\t\t\t\t\t\t\t? { image: createImageBlock(c.mimeType, c.data) }\n\t\t\t\t\t\t\t\t: { text: sanitizeSurrogates(c.text) },\n\t\t\t\t\t\t),\n\t\t\t\t\t\tstatus: m.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t},\n\t\t\t\t});\n\n\t\t\t\t// Look ahead for consecutive toolResult messages\n\t\t\t\tlet j = i + 1;\n\t\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\t\tconst nextMsg = transformedMessages[j] as ToolResultMessage;\n\t\t\t\t\ttoolResults.push({\n\t\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\t\ttoolUseId: nextMsg.toolCallId,\n\t\t\t\t\t\t\tcontent: nextMsg.content.map((c) =>\n\t\t\t\t\t\t\t\tc.type === \"image\"\n\t\t\t\t\t\t\t\t\t? { image: createImageBlock(c.mimeType, c.data) }\n\t\t\t\t\t\t\t\t\t: { text: sanitizeSurrogates(c.text) },\n\t\t\t\t\t\t\t),\n\t\t\t\t\t\t\tstatus: nextMsg.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t\t},\n\t\t\t\t\t});\n\t\t\t\t\tj++;\n\t\t\t\t}\n\n\t\t\t\t// Skip the messages we've already processed\n\t\t\t\ti = j - 1;\n\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent: toolResults,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tdefault:\n\t\t\t\tthrow new Error(\"Unknown message role\");\n\t\t}\n\t}\n\n\t// Add cache point to the last user message for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model) && result.length > 0) {\n\t\tconst lastMessage = result[result.length - 1];\n\t\tif (lastMessage.role === ConversationRole.USER && lastMessage.content) {\n\t\t\t(lastMessage.content as ContentBlock[]).push({\n\t\t\t\tcachePoint: {\n\t\t\t\t\ttype: CachePointType.DEFAULT,\n\t\t\t\t\t...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}),\n\t\t\t\t},\n\t\t\t});\n\t\t}\n\t}\n\n\treturn result;\n}\n\nfunction convertToolConfig(\n\ttools: Tool[] | undefined,\n\ttoolChoice: BedrockOptions[\"toolChoice\"],\n): ToolConfiguration | undefined {\n\tif (!tools?.length || toolChoice === \"none\") return undefined;\n\n\tconst bedrockTools: BedrockTool[] = tools.map((tool) => ({\n\t\ttoolSpec: {\n\t\t\tname: tool.name,\n\t\t\tdescription: tool.description,\n\t\t\tinputSchema: { json: tool.parameters as unknown as DocumentType },\n\t\t},\n\t}));\n\n\tlet bedrockToolChoice: ToolChoice | undefined;\n\tswitch (toolChoice) {\n\t\tcase \"auto\":\n\t\t\tbedrockToolChoice = { auto: {} };\n\t\t\tbreak;\n\t\tcase \"any\":\n\t\t\tbedrockToolChoice = { any: {} };\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tif (toolChoice?.type === \"tool\") {\n\t\t\t\tbedrockToolChoice = { tool: { name: toolChoice.name } };\n\t\t\t}\n\t}\n\n\treturn { tools: bedrockTools, toolChoice: bedrockToolChoice };\n}\n\nfunction mapStopReason(reason: string | undefined): StopReason {\n\tswitch (reason) {\n\t\tcase BedrockStopReason.END_TURN:\n\t\tcase BedrockStopReason.STOP_SEQUENCE:\n\t\t\treturn \"stop\";\n\t\tcase BedrockStopReason.MAX_TOKENS:\n\t\tcase BedrockStopReason.MODEL_CONTEXT_WINDOW_EXCEEDED:\n\t\t\treturn \"length\";\n\t\tcase BedrockStopReason.TOOL_USE:\n\t\t\treturn \"toolUse\";\n\t\tdefault:\n\t\t\treturn \"error\";\n\t}\n}\n\nfunction getConfiguredBedrockRegion(options: BedrockOptions): string | undefined {\n\tif (typeof process === \"undefined\") {\n\t\treturn options.region;\n\t}\n\n\treturn options.region || process.env.AWS_REGION || process.env.AWS_DEFAULT_REGION || undefined;\n}\n\nfunction hasConfiguredBedrockProfile(): boolean {\n\tif (typeof process === \"undefined\") {\n\t\treturn false;\n\t}\n\n\treturn Boolean(process.env.AWS_PROFILE);\n}\n\nfunction getStandardBedrockEndpointRegion(baseUrl: string | undefined): string | undefined {\n\tif (!baseUrl) {\n\t\treturn undefined;\n\t}\n\n\ttry {\n\t\tconst { hostname } = new URL(baseUrl);\n\t\tconst match = hostname.toLowerCase().match(/^bedrock-runtime(?:-fips)?\\.([a-z0-9-]+)\\.amazonaws\\.com(?:\\.cn)?$/);\n\t\treturn match?.[1];\n\t} catch {\n\t\treturn undefined;\n\t}\n}\n\nfunction shouldUseExplicitBedrockEndpoint(\n\tbaseUrl: string,\n\tconfiguredRegion: string | undefined,\n\thasConfiguredProfile: boolean,\n): boolean {\n\tconst endpointRegion = getStandardBedrockEndpointRegion(baseUrl);\n\tif (!endpointRegion) {\n\t\treturn true;\n\t}\n\n\treturn !configuredRegion && !hasConfiguredProfile;\n}\n\nfunction isGovCloudBedrockTarget(model: Model<\"bedrock-converse-stream\">, options: BedrockOptions): boolean {\n\tconst region = getConfiguredBedrockRegion(options);\n\tif (region?.toLowerCase().startsWith(\"us-gov-\")) {\n\t\treturn true;\n\t}\n\n\tconst modelId = model.id.toLowerCase();\n\treturn modelId.startsWith(\"us-gov.\") || modelId.startsWith(\"arn:aws-us-gov:\");\n}\n\nfunction buildAdditionalModelRequestFields(\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toptions: BedrockOptions,\n): Record<string, any> | undefined {\n\tif (!options.reasoning || !model.reasoning) {\n\t\treturn undefined;\n\t}\n\n\tif (isAnthropicClaudeModel(model)) {\n\t\t// GovCloud Bedrock currently rejects the Claude thinking.display field.\n\t\t// Omit it there until the GovCloud Converse schema catches up.\n\t\tconst display = isGovCloudBedrockTarget(model, options) ? undefined : (options.thinkingDisplay ?? \"summarized\");\n\t\tconst result: Record<string, any> = supportsAdaptiveThinking(model.id, model.name)\n\t\t\t? {\n\t\t\t\t\tthinking: { type: \"adaptive\", ...(display !== undefined ? { display } : {}) },\n\t\t\t\t\toutput_config: { effort: mapThinkingLevelToEffort(options.reasoning, model.id, model.name) },\n\t\t\t\t}\n\t\t\t: (() => {\n\t\t\t\t\tconst defaultBudgets: Record<ThinkingLevel, number> = {\n\t\t\t\t\t\tminimal: 1024,\n\t\t\t\t\t\tlow: 2048,\n\t\t\t\t\t\tmedium: 8192,\n\t\t\t\t\t\thigh: 16384,\n\t\t\t\t\t\txhigh: 16384, // Claude doesn't support xhigh, clamp to high\n\t\t\t\t\t};\n\n\t\t\t\t\t// Custom budgets override defaults (xhigh not in ThinkingBudgets, use high)\n\t\t\t\t\tconst level = options.reasoning === \"xhigh\" ? \"high\" : options.reasoning;\n\t\t\t\t\tconst budget = options.thinkingBudgets?.[level] ?? defaultBudgets[options.reasoning];\n\n\t\t\t\t\treturn {\n\t\t\t\t\t\tthinking: {\n\t\t\t\t\t\t\ttype: \"enabled\",\n\t\t\t\t\t\t\tbudget_tokens: budget,\n\t\t\t\t\t\t\t...(display !== undefined ? { display } : {}),\n\t\t\t\t\t\t},\n\t\t\t\t\t};\n\t\t\t\t})();\n\n\t\tif (!supportsAdaptiveThinking(model.id, model.name) && (options.interleavedThinking ?? true)) {\n\t\t\tresult.anthropic_beta = [\"interleaved-thinking-2025-05-14\"];\n\t\t}\n\n\t\treturn result;\n\t}\n\n\treturn undefined;\n}\n\nfunction createImageBlock(mimeType: string, data: string) {\n\tlet format: ImageFormat;\n\tswitch (mimeType) {\n\t\tcase \"image/jpeg\":\n\t\tcase \"image/jpg\":\n\t\t\tformat = ImageFormat.JPEG;\n\t\t\tbreak;\n\t\tcase \"image/png\":\n\t\t\tformat = ImageFormat.PNG;\n\t\t\tbreak;\n\t\tcase \"image/gif\":\n\t\t\tformat = ImageFormat.GIF;\n\t\t\tbreak;\n\t\tcase \"image/webp\":\n\t\t\tformat = ImageFormat.WEBP;\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tthrow new Error(`Unknown image type: ${mimeType}`);\n\t}\n\n\tconst binaryString = atob(data);\n\tconst bytes = new Uint8Array(binaryString.length);\n\tfor (let i = 0; i < binaryString.length; i++) {\n\t\tbytes[i] = binaryString.charCodeAt(i);\n\t}\n\n\treturn { source: { bytes }, format };\n}\n"]}

package/dist/providers/amazon-bedrock.js

@@ -218,8 +218,8 @@ export const streamSimpleBedrock = (model, context, options) => {
     if (!options?.reasoning) {
         return streamBedrock(model, context, { ...base, reasoning: undefined });
     }
-    if (model.id.includes("anthropic.claude") || model.id.includes("anthropic/claude")) {
-        if (supportsAdaptiveThinking(model.id)) {
+    if (isAnthropicClaudeModel(model)) {
+        if (supportsAdaptiveThinking(model.id, model.name)) {
             return streamBedrock(model, context, {
                 ...base,
                 reasoning: options.reasoning,
@@ -344,16 +344,22 @@ function handleContentBlockStop(event, blocks, output, stream) {
 }
 /**
  * Check if the model supports adaptive thinking (Opus 4.6+, Sonnet 4.6).
+ * Checks both model ID and model name to support application inference profiles
+ * whose ARNs don't contain the model name.
  */
-function supportsAdaptiveThinking(modelId) {
-    return (modelId.includes("opus-4-6") ||
-        modelId.includes("opus-4.6") ||
-        modelId.includes("opus-4-7") ||
-        modelId.includes("opus-4.7") ||
-        modelId.includes("sonnet-4-6") ||
-        modelId.includes("sonnet-4.6"));
+function getModelMatchCandidates(modelId, modelName) {
+    const values = modelName ? [modelId, modelName] : [modelId];
+    return values.flatMap((value) => {
+        const lower = value.toLowerCase();
+        return [lower, lower.replace(/[\s_.:]+/g, "-")];
+    });
+}
+function supportsAdaptiveThinking(modelId, modelName) {
+    const candidates = getModelMatchCandidates(modelId, modelName);
+    return candidates.some((s) => s.includes("opus-4-6") || s.includes("opus-4-7") || s.includes("sonnet-4-6"));
 }
-function mapThinkingLevelToEffort(level, modelId) {
+function mapThinkingLevelToEffort(level, modelId, modelName) {
+    const candidates = getModelMatchCandidates(modelId, modelName);
     switch (level) {
         case "minimal":
         case "low":
@@ -363,10 +369,10 @@ function mapThinkingLevelToEffort(level, modelId) {
         case "high":
             return "high";
         case "xhigh":
-            if (modelId.includes("opus-4-6") || modelId.includes("opus-4.6")) {
+            if (candidates.some((s) => s.includes("opus-4-6"))) {
                 return "max";
             }
-            if (modelId.includes("opus-4-7") || modelId.includes("opus-4.7")) {
+            if (candidates.some((s) => s.includes("opus-4-7"))) {
                 return "xhigh";
             }
             return "high";
@@ -387,6 +393,20 @@ function resolveCacheRetention(cacheRetention) {
     }
     return "short";
 }
+/**
+ * Check if the model is an Anthropic Claude model on Bedrock.
+ * Checks both model ID and model name to support application inference profiles
+ * whose ARNs don't contain the model name.
+ */
+function isAnthropicClaudeModel(model) {
+    const id = model.id.toLowerCase();
+    const name = model.name?.toLowerCase() ?? "";
+    return (id.includes("anthropic.claude") ||
+        id.includes("anthropic/claude") ||
+        name.includes("anthropic.claude") ||
+        name.includes("anthropic/claude") ||
+        name.includes("claude"));
+}
 /**
  * Check if the model supports prompt caching.
  * Supported: Claude 3.5 Haiku, Claude 3.7 Sonnet, Claude 4.x models
@@ -395,12 +415,14 @@ function resolveCacheRetention(cacheRetention) {
  * contains the model name, so we can decide locally.
  *
  * For application inference profiles (whose ARNs don't contain the model name),
- * set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.  Amazon Nova models
- * have automatic caching and don't need explicit cache points.
+ * also checks model.name which is user-controlled via models.json or registerProvider.
+ * As a last resort, set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.
+ * Amazon Nova models have automatic caching and don't need explicit cache points.
  */
 function supportsPromptCaching(model) {
-    const id = model.id.toLowerCase();
-    if (!id.includes("claude")) {
+    const candidates = getModelMatchCandidates(model.id, model.name);
+    const hasClaudeRef = candidates.some((s) => s.includes("claude"));
+    if (!hasClaudeRef) {
         // Application inference profiles don't contain the model name in the ARN.
         // Allow users to force cache points via environment variable.
         if (typeof process !== "undefined" && process.env.AWS_BEDROCK_FORCE_CACHE === "1")
@@ -408,13 +430,13 @@ function supportsPromptCaching(model) {
         return false;
     }
     // Claude 4.x models (opus-4, sonnet-4, haiku-4)
-    if (id.includes("-4-") || id.includes("-4."))
+    if (candidates.some((s) => s.includes("-4-")))
         return true;
     // Claude 3.7 Sonnet
-    if (id.includes("claude-3-7-sonnet"))
+    if (candidates.some((s) => s.includes("claude-3-7-sonnet")))
         return true;
     // Claude 3.5 Haiku
-    if (id.includes("claude-3-5-haiku"))
+    if (candidates.some((s) => s.includes("claude-3-5-haiku")))
         return true;
     return false;
 }
@@ -423,10 +445,11 @@ function supportsPromptCaching(model) {
  * Only Anthropic Claude models support the signature field.
  * Other models (OpenAI, Qwen, Minimax, Moonshot, etc.) reject it with:
  * "This model doesn't support the reasoningContent.reasoningText.signature field"
+ *
+ * Checks both model ID and model name to support application inference profiles.
  */
 function supportsThinkingSignature(model) {
-    const id = model.id.toLowerCase();
-    return id.includes("anthropic.claude") || id.includes("anthropic/claude");
+    return isAnthropicClaudeModel(model);
 }
 function buildSystemPrompt(systemPrompt, model, cacheRetention) {
     if (!systemPrompt)
@@ -672,14 +695,14 @@ function buildAdditionalModelRequestFields(model, options) {
     if (!options.reasoning || !model.reasoning) {
         return undefined;
     }
-    if (model.id.includes("anthropic.claude") || model.id.includes("anthropic/claude")) {
+    if (isAnthropicClaudeModel(model)) {
         // GovCloud Bedrock currently rejects the Claude thinking.display field.
         // Omit it there until the GovCloud Converse schema catches up.
         const display = isGovCloudBedrockTarget(model, options) ? undefined : (options.thinkingDisplay ?? "summarized");
-        const result = supportsAdaptiveThinking(model.id)
+        const result = supportsAdaptiveThinking(model.id, model.name)
             ? {
                 thinking: { type: "adaptive", ...(display !== undefined ? { display } : {}) },
-                output_config: { effort: mapThinkingLevelToEffort(options.reasoning, model.id) },
+                output_config: { effort: mapThinkingLevelToEffort(options.reasoning, model.id, model.name) },
             }
             : (() => {
                 const defaultBudgets = {
@@ -700,7 +723,7 @@ function buildAdditionalModelRequestFields(model, options) {
                     },
                 };
             })();
-        if (!supportsAdaptiveThinking(model.id) && (options.interleavedThinking ?? true)) {
+        if (!supportsAdaptiveThinking(model.id, model.name) && (options.interleavedThinking ?? true)) {
             result.anthropic_beta = ["interleaved-thinking-2025-05-14"];
         }
         return result;