client = OpenAI( base_url = \"https://YOUR-RESOURCE-NAME.openai.azure.com/openai",
+ "snippetComplete": false
+ },
+ {
+ "line": 75,
+ "text": "OpenAI uses the `model` keyword argument to specify what model to use. Azure OpenAI has the concept of unique model [deployments](create-resource?pivots=web-portal#deploy-a-model). When you use Azure OpenAI, `model` should refer to the underlying deployment name you chose when you deployed the model.",
+ "snippetComplete": true
+ },
+ {
+ "line": 79,
+ "text": "When you access the model via the API in Azure OpenAI, you need to refer to the deployment name rather than the underlying model name in API calls, which is one of the [key differences](switching-endpoints) between OpenAI and Azure OpenAI. OpenAI only requires the model name. Azure OpenAI always requires deployment name, even when using the model parameter. In our docs, we often have examples where deployment names are represented as identical to model names to help indicate which model works wi",
+ "snippetComplete": false
+ },
+ {
+ "line": 83,
+ "text": "| ```python response = client.responses.create( model=\"gpt-4.1-nano\", # Replace with your model deployment name input=\"This is a test.\" )
embedding = client.embeddings.create( input=inputs, model=\"text-embedding-3-large\" # This must match the custom deployment name you chose for your model. # engine=\"text-embedding-ada-002\" )
``` |",
+ "snippetComplete": true
+ }
+ ],
+ "notEvidenceOf": [
+ "live provider acceptance",
+ "all vendor features implemented",
+ "full website review"
+ ]
+ },
+ {
+ "id": "openai-sdk-commit",
+ "requestedUrl": "https://api.github.com/repos/openai/openai-python/commits/main",
+ "observedAt": "2026-11-06T13:30:56.222Z",
+ "credentials": false,
+ "totalTimeoutMs": 18000,
+ "status": 200,
+ "finalUrl": "https://api.github.com/repos/openai/openai-python/commits/main",
+ "contentType": "application/json; charset=utf-8",
+ "bytes": 95778,
+ "sha256": "bbdefbc797ccb444f22af75122532ebee5052c648ffb47b28e1415744eb6f49a",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-commit.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-attempts.json",
+ "authority": "vendor-owned-public-source",
+ "readStatus": "source-identity-only",
+ "reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-commit.body",
+ "reviewScope": [],
+ "reviewAnchors": [],
+ "notEvidenceOf": [
+ "live provider acceptance",
+ "all vendor features implemented",
+ "full website review"
+ ]
+ },
+ {
+ "id": "openai-sdk-tools",
+ "requestedUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/responses/tool_param.py",
+ "observedAt": "2026-11-06T13:30:57.740Z",
+ "credentials": false,
+ "totalTimeoutMs": 18000,
+ "status": 200,
+ "finalUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/responses/tool_param.py",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 16632,
+ "sha256": "8b5ddf4bf72fa3704808626189c91969dce7d2039967e30036dc46d698455af8",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-tools.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-attempts.json",
+ "authority": "vendor-owned-public-source",
+ "readStatus": "targeted-sections-reviewed",
+ "reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-tools.body",
+ "reviewScope": [
+ "ToolParam",
+ "WebSearch",
+ "Computer",
+ "Mcp",
+ "Shell",
+ "ApplyPatch",
+ "ImageGeneration"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 9,
+ "text": "from .custom_tool_param import CustomToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 10,
+ "text": "from .computer_tool_param import ComputerToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 11,
+ "text": "from .function_tool_param import FunctionToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 12,
+ "text": "from .namespace_tool_param import NamespaceToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 14,
+ "text": " Filters as _compat_WebSearchToolFilters,",
+ "snippetComplete": true
+ },
+ {
+ "line": 15,
+ "text": " UserLocation as _compat_WebSearchToolUserLocation,",
+ "snippetComplete": true
+ },
+ {
+ "line": 16,
+ "text": " WebSearchToolParam,",
+ "snippetComplete": true
+ },
+ {
+ "line": 17,
+ "text": " WebSearchToolParam as _compat_WebSearchTool,",
+ "snippetComplete": true
+ },
+ {
+ "line": 19,
+ "text": "from .apply_patch_tool_param import ApplyPatchToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 20,
+ "text": "from .file_search_tool_param import FileSearchToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 21,
+ "text": "from .tool_search_tool_param import ToolSearchToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 22,
+ "text": "from .function_shell_tool_param import FunctionShellToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 23,
+ "text": "from .web_search_preview_tool_param import WebSearchPreviewToolParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 24,
+ "text": "from .computer_use_preview_tool_param import ComputerUsePreviewToolParam",
+ "snippetComplete": true
+ }
+ ],
+ "notEvidenceOf": [
+ "live provider acceptance",
+ "all vendor features implemented",
+ "full website review"
+ ]
+ },
+ {
+ "id": "openai-sdk-responses",
+ "requestedUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/responses/response_create_params.py",
+ "observedAt": "2026-11-06T13:30:57.738Z",
+ "credentials": false,
+ "totalTimeoutMs": 18000,
+ "status": 200,
+ "finalUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/responses/response_create_params.py",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 21917,
+ "sha256": "dbce54c51a1d1b3764616fe5d723acf4af219a3ca3f3c8199abec60b3d59b4b7",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-responses.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-attempts.json",
+ "authority": "vendor-owned-public-source",
+ "readStatus": "targeted-sections-reviewed",
+ "reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-responses.body",
+ "reviewScope": [
+ "max_output_tokens:",
+ "reasoning:",
+ "text:",
+ "prompt_cache_options:",
+ "stream_options:",
+ "tool_choice:",
+ "background:",
+ "conversation:"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 50,
+ "text": " background: Optional[bool]",
+ "snippetComplete": true
+ },
+ {
+ "line": 59,
+ "text": " conversation: Optional[Conversation]",
+ "snippetComplete": true
+ },
+ {
+ "line": 112,
+ "text": " max_output_tokens: Optional[int]",
+ "snippetComplete": true
+ },
+ {
+ "line": 173,
+ "text": " prompt_cache_options: PromptCacheOptions",
+ "snippetComplete": true
+ },
+ {
+ "line": 207,
+ "text": " reasoning: Optional[Reasoning]",
+ "snippetComplete": true
+ },
+ {
+ "line": 260,
+ "text": " stream_options: Optional[StreamOptions]",
+ "snippetComplete": true
+ },
+ {
+ "line": 271,
+ "text": " text: ResponseTextConfigParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 280,
+ "text": " tool_choice: ToolChoice",
+ "snippetComplete": true
+ },
+ {
+ "line": 373,
+ "text": "Conversation: TypeAlias = Union[str, ResponseConversationParamParam]",
+ "snippetComplete": true
+ }
+ ],
+ "notEvidenceOf": [
+ "live provider acceptance",
+ "all vendor features implemented",
+ "full website review"
+ ]
+ },
+ {
+ "id": "openai-sdk-chat",
+ "requestedUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/chat/completion_create_params.py",
+ "observedAt": "2026-11-06T13:30:57.739Z",
+ "credentials": false,
+ "totalTimeoutMs": 18000,
+ "status": 200,
+ "finalUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/chat/completion_create_params.py",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 27619,
+ "sha256": "a27e422737a8998c1a35b3d0e004828281839e5449fcdbf3d1eb66f8821b8023",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-chat.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-attempts.json",
+ "authority": "vendor-owned-public-source",
+ "readStatus": "targeted-sections-reviewed",
+ "reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-chat.body",
+ "reviewScope": [
+ "max_completion_tokens:",
+ "max_tokens:",
+ "prompt_cache_options:",
+ "stream_options:",
+ "tool_choice:",
+ "response_format:",
+ "n:"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 189,
+ "text": " max_completion_tokens: Optional[int]",
+ "snippetComplete": true
+ },
+ {
+ "line": 196,
+ "text": " max_tokens: Optional[int]",
+ "snippetComplete": true
+ },
+ {
+ "line": 231,
+ "text": " moderation: Optional[Moderation]",
+ "snippetComplete": true
+ },
+ {
+ "line": 234,
+ "text": " n: Optional[int]",
+ "snippetComplete": true
+ },
+ {
+ "line": 248,
+ "text": " prediction: Optional[ChatCompletionPredictionContentParam]",
+ "snippetComplete": true
+ },
+ {
+ "line": 271,
+ "text": " prompt_cache_options: PromptCacheOptions",
+ "snippetComplete": true
+ },
+ {
+ "line": 285,
+ "text": " prompt_cache_retention: Optional[Literal[\"in_memory\", \"24h\"]]",
+ "snippetComplete": true
+ },
+ {
+ "line": 316,
+ "text": " response_format: ResponseFormat",
+ "snippetComplete": true
+ },
+ {
+ "line": 390,
+ "text": " stream_options: Optional[ChatCompletionStreamOptionsParam]",
+ "snippetComplete": true
+ },
+ {
+ "line": 401,
+ "text": " tool_choice: ChatCompletionToolChoiceOptionParam",
+ "snippetComplete": true
+ },
+ {
+ "line": 476,
+ "text": " description: str",
+ "snippetComplete": true
+ },
+ {
+ "line": 568,
+ "text": " region: str",
+ "snippetComplete": true
+ },
+ {
+ "line": 600,
+ "text": " user_location: Optional[WebSearchOptionsUserLocation]",
+ "snippetComplete": true
+ }
+ ],
+ "notEvidenceOf": [
+ "live provider acceptance",
+ "all vendor features implemented",
+ "full website review"
+ ]
+ },
+ {
+ "id": "openai-sdk-model",
+ "requestedUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/model.py",
+ "observedAt": "2026-11-06T13:30:57.740Z",
+ "credentials": false,
+ "totalTimeoutMs": 18000,
+ "status": 200,
+ "finalUrl": "https://raw.githubusercontent.com/openai/openai-python/c6fc264689d384d5caec150fafa1a9567c4a3f56/src/openai/types/model.py",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 753,
+ "sha256": "435fe8bb27b95b31d2606fef1a2dc455c443498d4f6668cdf8513b0268d58ddc",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-model.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-attempts.json",
+ "authority": "vendor-owned-public-source",
+ "readStatus": "targeted-sections-reviewed",
+ "reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-sdk-model.body",
+ "reviewScope": [
+ "class Model",
+ "^ id:",
+ "^ created:",
+ "^ owned_by:",
+ "shutdown_date"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 11,
+ "text": "class Model(BaseModel):",
+ "snippetComplete": true
+ },
+ {
+ "line": 14,
+ "text": " id: str",
+ "snippetComplete": true
+ },
+ {
+ "line": 17,
+ "text": " created: int",
+ "snippetComplete": true
+ },
+ {
+ "line": 23,
+ "text": " owned_by: str",
+ "snippetComplete": true
+ },
+ {
+ "line": 26,
+ "text": " shutdown_date: Optional[str] = None",
+ "snippetComplete": true
+ }
+ ],
+ "notEvidenceOf": [
+ "live provider acceptance",
+ "all vendor features implemented",
+ "full website review"
+ ]
+ },
+ {
+ "id": "claude-manage-claude__authentication",
+ "requestedUrl": "https://platform.claude.com/docs/en/manage-claude/authentication",
+ "finalUrl": "https://platform.claude.com/docs/en/manage-claude/authentication",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/manage-claude__authentication.md",
+ "sha256": "ebcf0f67d9388089131cba530cf59f006db668b5ec4e7bd11d1fcd20761c0489",
+ "bytes": 28077,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "Authorization",
+ "x-api-key",
+ "2026-10-21"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 11,
+ "text": "| [API key](https://platform.claude.com/docs/en/manage-claude/authentication#api-keys) | Static `sk-ant-api...` secret sent as a bearer token in the `Authorization` header | Local development, prototyping, scripts, and servers where you control secret storage |",
+ "snippetComplete": true
+ },
+ {
+ "line": 19,
+ "text": "API keys are static secrets that you generate in the Claude Console and send on every request as a bearer token in the `Authorization` header.",
+ "snippetComplete": true
+ },
+ {
+ "line": 40,
+ "text": "* **Use the key:** Send it as `Authorization: Bearer ` on direct HTTP requests, or set the `ANTHROPIC_API_KEY` environment variable and the [client SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) picks it up automatically.",
+ "snippetComplete": true
+ },
+ {
+ "line": 44,
+ "text": "Authorization: Bearer YOUR_API_KEY",
+ "snippetComplete": true
+ },
+ {
+ "line": 45,
+ "text": "anthropic-version: 2026-10-21",
+ "snippetComplete": true
+ },
+ {
+ "line": 49,
+ "text": "You can also send the key in the legacy `x-api-key: YOUR_API_KEY` header in place of `Authorization`.",
+ "snippetComplete": true
+ },
+ {
+ "line": 56,
+ "text": " -H \"x-api-key: $ANTHROPIC_API_KEY\" \\",
+ "snippetComplete": true
+ },
+ {
+ "line": 57,
+ "text": " -H \"anthropic-version: 2026-10-21\" \\",
+ "snippetComplete": true
+ },
+ {
+ "line": 134,
+ "text": " -H \"x-api-key: $ANTHROPIC_API_KEY\" \\",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__handling-stop-reasons",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__handling-stop-reasons.md",
+ "sha256": "7945fdb1e7f8b4374277a0e34c0d3d633e23c9e6691f5891565230eded7dc73d",
+ "bytes": 124582,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "pause_turn",
+ "max_tokens",
+ "end_turn",
+ "stop_reason"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 4,
+ "text": "description: Learn what each stop_reason value means and how to handle truncation, tool use, paused turns, and refusals in your application.",
+ "snippetComplete": true
+ },
+ {
+ "line": 7,
+ "text": "Every Messages API response includes a [`stop_reason`](https://platform.claude.com/docs/en/api/messages/create#message.stop_reason) field that tells you why Claude stopped generating. Check this field to decide whether to use the response as-is, continue the conversation, retry, or fall back to another model.",
+ "snippetComplete": true
+ },
+ {
+ "line": 15,
+ "text": "| [`end_turn`](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#end-turn) | Claude completed its response naturally. | Use the response. |",
+ "snippetComplete": true
+ },
+ {
+ "line": 16,
+ "text": "| [`max_tokens`](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#max-tokens) | The response reached your `max_tokens` limit. | Raise `max_tokens` or [continue the response](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#ensuring-complete-responses). |",
+ "snippetComplete": true
+ },
+ {
+ "line": 19,
+ "text": "| [`pause_turn`](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#pause-turn) | A server-tool loop reached its iteration limit. | Send the assistant content back to continue. |",
+ "snippetComplete": true
+ },
+ {
+ "line": 25,
+ "text": "The `stop_reason` field is part of every successful Messages API response. Unlike errors, which indicate failures in processing your request, `stop_reason` tells you why Claude completed its response generation.",
+ "snippetComplete": true
+ },
+ {
+ "line": 38,
+ "text": " \"stop_reason\": \"end_turn\",",
+ "snippetComplete": true
+ },
+ {
+ "line": 62,
+ "text": " \"max_tokens\": 1024,",
+ "snippetComplete": true
+ },
+ {
+ "line": 79,
+ "text": " max_tokens=1024,",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__working-with-messages",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/working-with-messages",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/working-with-messages",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__working-with-messages.md",
+ "sha256": "ecc2b6b3000d5728deda9c60c7ab580b0c5e76b51824a7952c003ddc031ead35",
+ "bytes": 35403,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "max_tokens",
+ "stateless",
+ "content",
+ "tool"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 59,
+ "text": " -H \"content-type: application/json\" \\",
+ "snippetComplete": true
+ },
+ {
+ "line": 62,
+ "text": " \"max_tokens\": 1024,",
+ "snippetComplete": true
+ },
+ {
+ "line": 64,
+ "text": " {\"role\": \"user\", \"content\": \"Hello, Claude\"}",
+ "snippetComplete": true
+ },
+ {
+ "line": 73,
+ "text": " --message '{role: user, content: \"Hello, Claude\"}'",
+ "snippetComplete": true
+ },
+ {
+ "line": 79,
+ "text": " max_tokens=1024,",
+ "snippetComplete": true
+ },
+ {
+ "line": 80,
+ "text": " messages=[{\"role\": \"user\", \"content\": \"Hello, Claude\"}],",
+ "snippetComplete": true
+ },
+ {
+ "line": 90,
+ "text": " max_tokens: 1024,",
+ "snippetComplete": true
+ },
+ {
+ "line": 91,
+ "text": " messages: [{ role: \"user\", content: \"Hello, Claude\" }]",
+ "snippetComplete": true
+ },
+ {
+ "line": 103,
+ "text": " Messages = [new UserMessageParam { Content = \"Hello, Claude\" }]",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__streaming",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/streaming",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/streaming",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__streaming.md",
+ "sha256": "a19a4c84f18e82fa11c71969960078ba9a338dabc4cdaff987f7858e9fd0428b",
+ "bytes": 55157,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "message_start",
+ "content_block",
+ "message_stop",
+ "error"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 322,
+ "text": "Each server-sent event includes a named event type and associated JSON data. Each event uses an SSE event name (for example, `event: message_stop`), and includes the matching event `type` in its data.",
+ "snippetComplete": true
+ },
+ {
+ "line": 326,
+ "text": "1. `message_start`: contains a `Message` object with empty `content`. Under the [`thinking-binding-controls-2026-08-01`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) beta header, this `Message` object also carries the `input_transformations` array. After a mid-stream [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), the final `message_delta` event carries the array again with th",
+ "snippetComplete": false
+ },
+ {
+ "line": 327,
+ "text": "2. A series of content blocks, each of which has a `content_block_start`, one or more `content_block_delta` events, and a `content_block_stop` event. Each content block has an `index` that corresponds to its index in the final Message `content` array. One exception: during [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) responses, a `fallback` content block arrives at each model boundary as a `content_block_start` and `cont",
+ "snippetComplete": false
+ },
+ {
+ "line": 329,
+ "text": "4. A final `message_stop` event.",
+ "snippetComplete": true
+ },
+ {
+ "line": 339,
+ "text": "### Error events",
+ "snippetComplete": true
+ },
+ {
+ "line": 341,
+ "text": "The API might occasionally send [errors](https://platform.claude.com/docs/en/api/errors) in the event stream. For example, during periods of high usage, you might receive an `overloaded_error`, which would normally correspond to an HTTP 529 in a non-streaming context:",
+ "snippetComplete": true
+ },
+ {
+ "line": 343,
+ "text": "```sse Example error",
+ "snippetComplete": true
+ },
+ {
+ "line": 344,
+ "text": "event: error",
+ "snippetComplete": true
+ },
+ {
+ "line": 345,
+ "text": "data: {\"type\": \"error\", \"error\": {\"type\": \"overloaded_error\", \"message\": \"Overloaded\"}}",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__extended-thinking",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/extended-thinking",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/extended-thinking",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__extended-thinking.md",
+ "sha256": "8af431a97d34d39e959593ebe26298cde6b764f168a44ed2d16ea74544da81e0",
+ "bytes": 23929,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "thinking",
+ "budget_tokens",
+ "adaptive"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 2,
+ "text": "title: Extended thinking",
+ "snippetComplete": true
+ },
+ {
+ "line": 3,
+ "text": "url: https://platform.claude.com/docs/en/build-with-claude/extended-thinking",
+ "snippetComplete": true
+ },
+ {
+ "line": 4,
+ "text": "description: Configure manual extended thinking with a fixed budget_tokens budget on Claude models that support it, and migrate to adaptive thinking.",
+ "snippetComplete": true
+ },
+ {
+ "line": 24,
+ "text": " Extended thinking is a legacy feature.",
+ "snippetComplete": true
+ },
+ {
+ "line": 26,
+ "text": " Extended thinking (`thinking.type: \"enabled\"` with `budget_tokens`) is deprecated. Claude 4.7 and later models do not support it and reject requests that use it, returning a 400 error.",
+ "snippetComplete": true
+ },
+ {
+ "line": 28,
+ "text": " * Recommended alternative: [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost)",
+ "snippetComplete": true
+ },
+ {
+ "line": 29,
+ "text": " * Migration guide: [Migrating to adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#migrating-to-adaptive-thinking)",
+ "snippetComplete": true
+ },
+ {
+ "line": 32,
+ "text": "Extended thinking in manual mode gives you direct control over how much Claude thinks. You set a thinking token budget on each request with `thinking: {type: \"enabled\", budget_tokens: N}`, and Claude thinks against that budget before it starts its final answer. Manual mode remains useful when your workload requires predictable latency or precise control over thinking costs. This page covers how to set and tune the budget, how manual mode interacts with interleaved thinking and prompt caching, an",
+ "snippetComplete": false
+ },
+ {
+ "line": 34,
+ "text": "To learn how thinking itself works, including thinking blocks and the response shape, the `display` parameter, streaming, thinking with tool use, and encryption, see the [thinking overview](https://platform.claude.com/docs/en/build-with-claude/thinking).",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__thinking-steering-and-cost",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__thinking-steering-and-cost.md",
+ "sha256": "28b1226b41557efa8d43e3eb28aa038c70b96866939bf1e7cbfd976d82482854",
+ "bytes": 41398,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "thinking",
+ "tool",
+ "effort",
+ "cache",
+ "model"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 2,
+ "text": "title: Steering thinking",
+ "snippetComplete": true
+ },
+ {
+ "line": 3,
+ "text": "url: https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost",
+ "snippetComplete": true
+ },
+ {
+ "line": 4,
+ "text": "description: Steer how often and how deeply Claude thinks with effort levels, system prompt guidance, and per-message steering, and understand thinking's cost and pricing.",
+ "snippetComplete": true
+ },
+ {
+ "line": 11,
+ "text": "Claude’s thinking is adaptive: the model evaluates each request and determines whether to think and how much. You set an intent, optionally specify the effort, and the model allocates reasoning where reasoning is likely to help.",
+ "snippetComplete": true
+ },
+ {
+ "line": 13,
+ "text": "This makes thinking a strong fit for workloads that mix trivial and complex requests, and for long-horizon agentic workflows where the right amount of reasoning varies from step to step.",
+ "snippetComplete": true
+ },
+ {
+ "line": 15,
+ "text": "To learn how to turn thinking on and how to read thinking output, see the [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) overview. This page covers how Claude determines when to think, how to steer thinking, and the caching, cost, and pricing mechanics that follow from it.",
+ "snippetComplete": true
+ },
+ {
+ "line": 19,
+ "text": "Thinking is optional for the model. On each request, Claude evaluates the complexity of the input and determines whether deeper reasoning would improve the answer. A simple factual question might get a direct response with no thinking block at all; a multistep math problem or a tricky debugging task triggers deeper reasoning.",
+ "snippetComplete": true
+ },
+ {
+ "line": 21,
+ "text": "This determination occurs for each request. The same conversation can contain turns with and without thinking, and a turn where Claude skips thinking contains no thinking block. Don’t build application logic that assumes every assistant turn starts with one.",
+ "snippetComplete": true
+ },
+ {
+ "line": 23,
+ "text": "The primary control over this determination is the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) parameter, which acts as soft guidance for how often and how deeply Claude uses thinking; see [Effort levels](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#effort-levels) on this page for what each level does.",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__thinking",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__thinking.md",
+ "sha256": "ff24b4c309610835c57611e4f5b6f8870b27950a8d4548bfae680c9eec1dfb42",
+ "bytes": 87672,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "Configuring thinking",
+ "Claude Opus 5.5",
+ "Claude Sonnet 5.5",
+ "Claude Haiku 5.5",
+ "between_tools"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 79,
+ "text": "## Configuring thinking",
+ "snippetComplete": true
+ },
+ {
+ "line": 83,
+ "text": "| Model | No `thinking` field | `\"adaptive\"` | `\"enabled\"` with `budget_tokens` | `\"between_tools\"` | `\"disabled\"` |",
+ "snippetComplete": true
+ },
+ {
+ "line": 85,
+ "text": "| Claude Opus 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | 400 error |",
+ "snippetComplete": true
+ },
+ {
+ "line": 86,
+ "text": "| Claude Sonnet 5.5 | Adaptive thinking | Adaptive thinking | 400 error | Up-front thinking off at `high` effort or below | 400 error |",
+ "snippetComplete": true
+ },
+ {
+ "line": 87,
+ "text": "| Claude Haiku 5.5 | Adaptive thinking | Adaptive thinking | 400 error | 400 error | Thinking off at `high` effort or below |",
+ "snippetComplete": true
+ },
+ {
+ "line": 493,
+ "text": "Claude Sonnet 5.5 also has thinking on by default, and it rejects `thinking: {type: \"disabled\"}` with a 400 error. To turn off up-front thinking, send `thinking: {type: \"between_tools\"}` instead. It’s the lowest thinking setting on Claude Sonnet 5.5, and it’s accepted at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. The model still returns its [progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-up",
+ "snippetComplete": false
+ },
+ {
+ "line": 495,
+ "text": "Claude Haiku 5.5 also has thinking on by default and accepts `thinking: {type: \"disabled\"}` at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. At `xhigh` or `max` effort, that combination returns a 400 error. To get less thinking, lower the effort level first. With thinking off, the model can skip a tool call it needs when you also request JSON output. A [per-message `output_config.effort`](https://platform.claude.com/docs/en/build-with-claude/effort#chang",
+ "snippetComplete": false
+ },
+ {
+ "line": 497,
+ "text": "Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, and Claude Mythos Preview reject `thinking: {type: \"disabled\"}`. Thinking can’t be turned off on these models.",
+ "snippetComplete": true
+ },
+ {
+ "line": 499,
+ "text": "To check whether a model accepts `\"disabled\"` or `\"between_tools\"` before you send a request, read its `capabilities.thinking.types.disabled.supported` or `capabilities.thinking.types.between_tools.supported` value from the Models API. [Using the Models API](https://platform.claude.com/docs/en/models/overview#using-the-models-api) describes both fields.",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__thinking-tool-workflows",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking-tool-workflows",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking-tool-workflows",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__thinking-tool-workflows.md",
+ "sha256": "7ef354e2d61ba79d65b0ce70ffa2687b8d9ffd4e03fc77ba43d3011a071f1257",
+ "bytes": 31431,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "thinking",
+ "tool",
+ "effort",
+ "cache",
+ "model"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 2,
+ "text": "title: Thinking in tool and multi-turn workflows",
+ "snippetComplete": true
+ },
+ {
+ "line": 3,
+ "text": "url: https://platform.claude.com/docs/en/build-with-claude/thinking-tool-workflows",
+ "snippetComplete": true
+ },
+ {
+ "line": 4,
+ "text": "description: Walk through a complete two-turn tool-use round trip that preserves thinking blocks correctly, and see how interleaved thinking changes the flow.",
+ "snippetComplete": true
+ },
+ {
+ "line": 11,
+ "text": "This page walks through a complete two-turn tool-use round trip with thinking enabled: Claude thinks, requests a tool call, receives the result, and finishes its answer, with the thinking blocks handled correctly at every step. The full rules live on the [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) page, in [Thinking with tool use](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use) and [Preserving thinking blocks](https://platform",
+ "snippetComplete": false
+ },
+ {
+ "line": 15,
+ "text": "Each link leads to the full statement on the Thinking page:",
+ "snippetComplete": true
+ },
+ {
+ "line": 17,
+ "text": "* [Limit tool choice to `auto` or `none` in manual mode](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use): `tool_choice` options that force tool use return an error with manual extended thinking (`thinking: {type: \"enabled\"}`). Adaptive thinking supports forced tool use, except on Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1, which return a 400 error. Where forced tool use is accepted, it skips thinking: the response starts wit",
+ "snippetComplete": false
+ },
+ {
+ "line": 18,
+ "text": "* [Keep one thinking configuration per assistant turn](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-with-tool-use): a tool-use loop is one assistant turn, so change the configuration only between turns.",
+ "snippetComplete": true
+ },
+ {
+ "line": 19,
+ "text": "* [Pass thinking blocks back complete and unmodified](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks): when you return a tool result, the thinking blocks from the assistant message must come back with it.",
+ "snippetComplete": true
+ },
+ {
+ "line": 20,
+ "text": "* [Echo the assistant message exactly as received](https://platform.claude.com/docs/en/build-with-claude/thinking#preserving-thinking-blocks): rebuilding the message or filtering out `redacted_thinking` blocks triggers a 400 error.",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__thinking-troubleshooting",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__thinking-troubleshooting.md",
+ "sha256": "1589613c37232b5e38c9042084b7e0aa3faa6e4692093199ae72fcd0078cc060",
+ "bytes": 23671,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "thinking",
+ "tool",
+ "effort",
+ "cache",
+ "model"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 2,
+ "text": "title: Troubleshooting thinking",
+ "snippetComplete": true
+ },
+ {
+ "line": 3,
+ "text": "url: https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting",
+ "snippetComplete": true
+ },
+ {
+ "line": 4,
+ "text": "description: \"Diagnose and fix the most common thinking failures: configuration 400 errors, empty or missing thinking blocks, max_tokens stops, and cache misses.\"",
+ "snippetComplete": true
+ },
+ {
+ "line": 11,
+ "text": "This page covers the most common failures when configuring thinking or round-tripping thinking blocks (sending returned thinking blocks back in later requests). The first section maps each model to its supported thinking configurations and the ones it rejects; the sections after it each start from a symptom you observe, so you can match an error message or unexpected response directly to its cause and fix. To learn how thinking works, see the [Thinking](https://platform.claude.com/docs/en/build-",
+ "snippetComplete": false
+ },
+ {
+ "line": 13,
+ "text": "## Thinking support, defaults, and rejected configurations by model",
+ "snippetComplete": true
+ },
+ {
+ "line": 15,
+ "text": "Most thinking configuration errors are a mismatch between the `thinking.type` value in the request and what the model supports. On most models, thinking runs as `thinking: {type: \"adaptive\"}`, and many have it on by default. Some earlier models instead use [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking), a legacy manual mode configured as `thinking: {type: \"enabled\", budget_tokens: N}`.",
+ "snippetComplete": true
+ },
+ {
+ "line": 17,
+ "text": "Extended thinking (`thinking.type: \"enabled\"` with `budget_tokens`) is deprecated on the Claude 4.6 models (requests using it still succeed). Claude 4.7 and later models do not support it and reject requests that use it, returning a 400 error. On Claude 4.5 and earlier models that support thinking, extended thinking is the only available thinking mode. Claude Mythos Preview supports both modes. Where both modes are available, use [adaptive thinking](https://platform.claude.com/docs/en/build-with",
+ "snippetComplete": false
+ },
+ {
+ "line": 19,
+ "text": "The table lists what each model supports, what it defaults to, and which `thinking.type` values it rejects with a 400 error; any value not listed as rejected is accepted. Only Claude Sonnet 5.5 accepts `\"between_tools\"`, and it takes that value in place of `\"disabled\"`.",
+ "snippetComplete": true
+ },
+ {
+ "line": 21,
+ "text": "| Model | Thinking types | Default | Rejected with 400 |",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-build-with-claude__prompt-caching",
+ "requestedUrl": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching",
+ "finalUrl": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/build-with-claude__prompt-caching.md",
+ "sha256": "ff35232788f3f7fbd0f9aae002351567a9ea8e68e5b749069d96dab52882747d",
+ "bytes": 164465,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "cache_control",
+ "ephemeral",
+ "TTL",
+ "tools",
+ "cache_creation"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 4,
+ "text": "description: Cache prompt prefixes with `cache_control` to cut costs and latency, using automatic caching or explicit breakpoints with 5-minute or 1-hour TTLs.",
+ "snippetComplete": true
+ },
+ {
+ "line": 8,
+ "text": " note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements). Your prompts and Claude's outputs are not stored. KV cache representations and cryptographic hashes are held in memory for the cache TTL and promptly deleted after expiry.",
+ "snippetComplete": true
+ },
+ {
+ "line": 39,
+ "text": "* **Messages API**: Opt in with `cache_control`, at the top level or on blocks.",
+ "snippetComplete": true
+ },
+ {
+ "line": 46,
+ "text": "* **[Automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching):** Add a single `cache_control` field at the top level of your request. The system automatically applies the cache breakpoint to the last cacheable block and moves it forward as conversations grow. Best for multi-turn conversations where the growing message history should be cached automatically.",
+ "snippetComplete": true
+ },
+ {
+ "line": 47,
+ "text": "* **[Explicit cache breakpoints](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#explicit-cache-breakpoints):** Place `cache_control` directly on individual content blocks for fine-grained control over exactly what gets cached.",
+ "snippetComplete": true
+ },
+ {
+ "line": 60,
+ "text": " \"cache_control\": {\"type\": \"ephemeral\"},",
+ "snippetComplete": true
+ },
+ {
+ "line": 75,
+ "text": " cache_control:",
+ "snippetComplete": true
+ },
+ {
+ "line": 76,
+ "text": " type: ephemeral",
+ "snippetComplete": true
+ },
+ {
+ "line": 92,
+ "text": " cache_control={\"type\": \"ephemeral\"},",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ },
+ {
+ "id": "claude-models__overview",
+ "requestedUrl": "https://platform.claude.com/docs/en/models/overview",
+ "finalUrl": "https://platform.claude.com/docs/en/models/overview",
+ "authority": "vendor-owned-reused-export",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/claude-extracted/models__overview.md",
+ "sha256": "04ced1978ad32f6015dfd82c4b4a89812f673411d4d0bd10aedb2957431d9907",
+ "bytes": 22885,
+ "readStatus": "targeted-sections-reviewed-not-full-article-review",
+ "reviewScope": [
+ "Claude API ID",
+ "Context window",
+ "Max output",
+ "128K",
+ "thinking",
+ "between_tools",
+ "server_tool"
+ ],
+ "reviewAnchors": [
+ {
+ "line": 33,
+ "text": "| Claude API ID | `claude-fable-5-1` | `claude-opus-5-5` | `claude-sonnet-5-5` | `claude-haiku-5-5` ",
+ "snippetComplete": false
+ },
+ {
+ "line": 34,
+ "text": "| [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) | Adaptive (always on) | Adaptive (always on) | Adaptive | Adaptive ",
+ "snippetComplete": false
+ },
+ {
+ "line": 36,
+ "text": "| [Context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) | 1M tokens | 1M tokens | 1M tokens | 1M tokens ",
+ "snippetComplete": false
+ },
+ {
+ "line": 37,
+ "text": "| Max output | 128K tokens | 128K tokens | 128K tokens | 128K tokens ",
+ "snippetComplete": false
+ },
+ {
+ "line": 48,
+ "text": "* **Comparative latency:** Relative to the current lineup. Actual latency depends on prompt length, output length, and thinking effort.",
+ "snippetComplete": true
+ },
+ {
+ "line": 50,
+ "text": "* **Claude API ID:** Every Claude model ID is a pinned snapshot, including the dateless IDs used from the 4.6 generation on.",
+ "snippetComplete": true
+ },
+ {
+ "line": 51,
+ "text": "* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual thinking.type “enabled” + budget\\_tokens mode on earlier models; it is deprecated on Claude Opus 4.6 and Claude Sonnet 4.6 and not accepted on later models.",
+ "snippetComplete": true
+ },
+ {
+ "line": 53,
+ "text": "* **Context window:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.",
+ "snippetComplete": true
+ },
+ {
+ "line": 54,
+ "text": "* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.",
+ "snippetComplete": true
+ }
+ ],
+ "acquisition": "reused existing prefix export; not a new direct page request",
+ "completeArticleToNextArticle": true,
+ "exportComplete": false,
+ "exportSha256": "76854bfc5b7d670bc96b8fe8074a7709bf7dc1ad04826cf083ada4e6137a427d"
+ }
+ ],
+ "unavailable": [
+ {
+ "id": "google-generate",
+ "requestedUrl": "https://ai.google.dev/api/generate-content",
+ "observedAt": "2026-11-06T13:05:31.918033+00:00",
+ "readLimitBytes": 3500000,
+ "error": "",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "google-models",
+ "requestedUrl": "https://ai.google.dev/api/models",
+ "observedAt": "2026-11-06T13:05:32.410991+00:00",
+ "readLimitBytes": 3500000,
+ "error": "",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "google-thinking",
+ "requestedUrl": "https://ai.google.dev/gemini-api/docs/thinking",
+ "observedAt": "2026-11-06T13:05:32.418990+00:00",
+ "readLimitBytes": 3500000,
+ "error": "",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "google-cache",
+ "requestedUrl": "https://ai.google.dev/gemini-api/docs/caching",
+ "observedAt": "2026-11-06T13:05:32.564211+00:00",
+ "readLimitBytes": 3500000,
+ "error": "",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "mistral-api",
+ "requestedUrl": "https://docs.mistral.ai/api/",
+ "observedAt": "2026-11-06T13:07:38.708231+00:00",
+ "readLimitBytes": 3500000,
+ "error": "",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "xai-models",
+ "requestedUrl": "https://docs.x.ai/developers/models",
+ "observedAt": "2026-11-06T13:07:38.770680+00:00",
+ "readLimitBytes": 3500000,
+ "error": "",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "openai-cache-node",
+ "requestedUrl": "https://developers.openai.com/api/docs/guides/prompt-caching",
+ "observedAt": "2026-11-06T13:10:14.887Z",
+ "totalTimeoutMs": 18000,
+ "transport": {
+ "schemaVersion": 1,
+ "implementation": "undici-7.30.1",
+ "autoSelectFamily": true,
+ "familyAttemptTimeoutMs": 250,
+ "connectTimeoutMs": 0,
+ "httpProxyConfigured": false,
+ "httpsProxyConfigured": false,
+ "noProxyConfigured": false
+ },
+ "requestHasCredentials": false,
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "finalUrl": "https://developers.openai.com/api/docs/guides/prompt-caching",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 59,
+ "completeByReadLimit": true,
+ "sha256": "530e3fa63f9dc60d51db98efe35f21485c02052b90bb1620074a86f44036915d",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-cache-node.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/node-attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "openai-responses-node",
+ "requestedUrl": "https://developers.openai.com/api/reference/resources/responses/methods/create",
+ "observedAt": "2026-11-06T13:10:15.341Z",
+ "totalTimeoutMs": 18000,
+ "transport": {
+ "schemaVersion": 1,
+ "implementation": "undici-7.30.1",
+ "autoSelectFamily": true,
+ "familyAttemptTimeoutMs": 250,
+ "connectTimeoutMs": 0,
+ "httpProxyConfigured": false,
+ "httpsProxyConfigured": false,
+ "noProxyConfigured": false
+ },
+ "requestHasCredentials": false,
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "finalUrl": "https://developers.openai.com/api/reference/resources/responses/methods/create",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 59,
+ "completeByReadLimit": true,
+ "sha256": "c4522a7bca682ff16dc4de67983c8597e7284f49eadf12ceb4ada62c219eed3d",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/openai-responses-node.body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/node-attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "google-discovery",
+ "requestedUrl": "https://generativelanguage.googleapis.com/$discovery/rest?version=v1beta",
+ "observedAt": "2026-11-06T13:10:15.342Z",
+ "totalTimeoutMs": 18000,
+ "transport": {
+ "schemaVersion": 1,
+ "implementation": "undici-7.30.1",
+ "autoSelectFamily": true,
+ "familyAttemptTimeoutMs": 250,
+ "connectTimeoutMs": 0,
+ "httpProxyConfigured": false,
+ "httpsProxyConfigured": false,
+ "noProxyConfigured": false
+ },
+ "requestHasCredentials": false,
+ "readLimitBytes": 1800000,
+ "error": {
+ "name": "TimeoutError",
+ "message": "The operation was aborted due to timeout"
+ },
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/node-attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "google-generate-node",
+ "requestedUrl": "https://ai.google.dev/api/generate-content",
+ "observedAt": "2026-11-06T13:10:15.342Z",
+ "totalTimeoutMs": 18000,
+ "transport": {
+ "schemaVersion": 1,
+ "implementation": "undici-7.30.1",
+ "autoSelectFamily": true,
+ "familyAttemptTimeoutMs": 250,
+ "connectTimeoutMs": 0,
+ "httpProxyConfigured": false,
+ "httpsProxyConfigured": false,
+ "noProxyConfigured": false
+ },
+ "requestHasCredentials": false,
+ "readLimitBytes": 1800000,
+ "error": {
+ "name": "TimeoutError",
+ "message": "The operation was aborted due to timeout"
+ },
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/node-attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "mistral-index-node",
+ "requestedUrl": "https://docs.mistral.ai/llms.txt",
+ "observedAt": "2026-11-06T13:10:15.343Z",
+ "totalTimeoutMs": 18000,
+ "transport": {
+ "schemaVersion": 1,
+ "implementation": "undici-7.30.1",
+ "autoSelectFamily": true,
+ "familyAttemptTimeoutMs": 250,
+ "connectTimeoutMs": 0,
+ "httpProxyConfigured": false,
+ "httpsProxyConfigured": false,
+ "noProxyConfigured": false
+ },
+ "requestHasCredentials": false,
+ "readLimitBytes": 1800000,
+ "error": {
+ "name": "TimeoutError",
+ "message": "The operation was aborted due to timeout"
+ },
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/node-attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "id": "xai-index-node",
+ "requestedUrl": "https://docs.x.ai/llms.txt",
+ "observedAt": "2026-11-06T13:10:15.343Z",
+ "totalTimeoutMs": 18000,
+ "transport": {
+ "schemaVersion": 1,
+ "implementation": "undici-7.30.1",
+ "autoSelectFamily": true,
+ "familyAttemptTimeoutMs": 250,
+ "connectTimeoutMs": 0,
+ "httpProxyConfigured": false,
+ "httpsProxyConfigured": false,
+ "noProxyConfigured": false
+ },
+ "requestHasCredentials": false,
+ "readLimitBytes": 1800000,
+ "error": {
+ "name": "TimeoutError",
+ "message": "The operation was aborted due to timeout"
+ },
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/node-attempts.json",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "requestedUrl": "https://developers.openai.com/llms.txt",
+ "observedAt": "2026-11-06T13:04:04.019436+00:00",
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "error": "HTTP Error 403: Forbidden",
+ "finalUrl": "https://developers.openai.com/llms.txt",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 59,
+ "sha256": "3a5870f906018336f1f547ad755e370754f7ce79f444f0cb2a7979d30966c1fb",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/openai-attempt-1.error-body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/openai-first-attempts.json",
+ "id": "openai-first-attempts-1",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "requestedUrl": "https://developers.openai.com/api/docs/guides/prompt-caching.md",
+ "observedAt": "2026-11-06T13:04:04.020437+00:00",
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "error": "HTTP Error 403: Forbidden",
+ "finalUrl": "https://developers.openai.com/api/docs/guides/prompt-caching.md",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 59,
+ "sha256": "422abe50929fc3a165de851179b8432c7003ec89b85d495d313e4fd09ef56b61",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/openai-attempt-2.error-body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/openai-first-attempts.json",
+ "id": "openai-first-attempts-2",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "requestedUrl": "https://developers.openai.com/api/docs/guides/reasoning.md",
+ "observedAt": "2026-11-06T13:04:04.020437+00:00",
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "error": "HTTP Error 403: Forbidden",
+ "finalUrl": "https://developers.openai.com/api/docs/guides/reasoning.md",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 59,
+ "sha256": "4e0849b85e841fcbed1f848b58db441822f65dbf3a3660c036bab6981b63a845",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/openai-attempt-3.error-body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/openai-first-attempts.json",
+ "id": "openai-first-attempts-3",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "requestedUrl": "https://platform.openai.com/docs/api-reference/responses/create",
+ "observedAt": "2026-11-06T13:04:04.020437+00:00",
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "error": "HTTP Error 403: Forbidden",
+ "finalUrl": "https://platform.openai.com/docs/api-reference/responses/create",
+ "contentType": "text/html; charset=UTF-8",
+ "bytes": 5660,
+ "sha256": "02fb68a392f7539657f390047853c6dd1c9071a66ee568354245d4ea21cc2018",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/openai-attempt-4.error-body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/openai-first-attempts.json",
+ "id": "openai-first-attempts-4",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ },
+ {
+ "requestedUrl": "https://developers.openai.com/api/docs/guides/text.md",
+ "observedAt": "2026-11-06T13:04:04.497667+00:00",
+ "readLimitBytes": 1800000,
+ "status": 403,
+ "error": "HTTP Error 403: Forbidden",
+ "finalUrl": "https://developers.openai.com/api/docs/guides/text.md",
+ "contentType": "text/plain; charset=utf-8",
+ "bytes": 59,
+ "sha256": "af001f5caf9d2fff94894166c9ec84a2849e4cb8dab47b77781d7e9bb5768f1c",
+ "bodyPath": ".qa/official-first-system-audit-2026-11-06/openai-attempt-5.error-body",
+ "attemptLedger": ".qa/official-first-system-audit-2026-11-06/openai-first-attempts.json",
+ "id": "openai-first-attempts-5",
+ "readStatus": "unavailable-not-API-contract-evidence"
+ }
+ ],
+ "reused": [
+ {
+ "path": "docs/claude-official-capacity-2026-11-06.json",
+ "sha256": "44c980b97c3058658cb461031977c92fe53a015cb78f3b2aae584e5d50bad353",
+ "scope": "four exact current Claude IDs; synchronous 128000 output / 1000000 context; prior source verification, not live capacity validation"
+ },
+ {
+ "path": "docs/newapi-documentation-review-2026-11-06.json",
+ "sha256": "b3d3c36a494563ed7ceb993dae7a1f9b346b543877843108e035c0a26b5d1601",
+ "scope": "305 article bodies / 201 embedded schemas already reviewed; reused without new full crawl",
+ "sourceManifestSha256": "4cb416511da1aa6f14171024729a4c8f891f589250ed4c676da5f26cd85b56e6",
+ "repositoryCommit": "d254f1842dc3d08d60f2269e2c9d4c9876a3dfbc",
+ "authority": "gateway-and-compatibility-reference-not-provider-authority"
+ }
+ ],
+ "limits": [
+ "targeted contract review, not all official websites or every global provider",
+ "SDK schema is an official contract source, not acquired current web guides or live provider acceptance",
+ "403/timeout pages are acquisition failures, not API model failures",
+ "official capacity does not authenticate a proxy backend or establish its effective limit"
+ ]
+}
diff --git a/docs/official-first-system-audit-2026-11-06.json b/docs/official-first-system-audit-2026-11-06.json
new file mode 100644
index 00000000..89b78dcb
--- /dev/null
+++ b/docs/official-first-system-audit-2026-11-06.json
@@ -0,0 +1,1982 @@
+{
+ "schema": 1,
+ "kind": "official-first-complete-system-key-path-audit",
+ "recordedAt": "2026-11-06T14:09:15.016711+00:00",
+ "sourceHead": "4da2550becdf4750320cedd5ee30a7e38baba2f9",
+ "branch": "feat/task-agreement-1.25",
+ "scope": "inventory and all major-layer key-path audit, not manual line-by-line review of every file",
+ "production": {
+ "freshHealthEvidence": ".qa/official-first-system-audit-2026-11-06/formal-health-readonly.json",
+ "freshHealthSha256": "456fdd09327c95232c00cc054824419d06517dcf3b24312e8a7fbc5b4e6440b0",
+ "observedHealth": [
+ {
+ "route": "/api/health",
+ "status": 200,
+ "observedAt": "2026-11-06T13:08:18.279628+00:00",
+ "body": {
+ "app": "agent-workbench",
+ "version": "1.25.12",
+ "pid": 71628,
+ "ready": true,
+ "uptimeMs": 43891093
+ },
+ "sha256": "d7df430a07e4daf2aeea5f26d5ea77b8554f45849d90cf835df2dac2de656901"
+ }
+ ],
+ "priorDeployedSource": "6867cd5a3094c133b09a7c50384ae844ef34c038",
+ "retentionScope": "prior F deployment evidence reused; health is not fresh data/credential retention verification"
+ },
+ "pendingSourceFixes": [
+ {
+ "commit": "ae5123c5",
+ "change": "catalog existing-model metadata refresh",
+ "deployed": false
+ },
+ {
+ "commit": "341f5f69",
+ "change": "diagnostic follows actual output token wire fields",
+ "deployed": false
+ },
+ {
+ "commit": "2bd7b24a",
+ "change": "exact official Claude capacity fallback",
+ "deployed": false
+ }
+ ],
+ "thisAudit": {
+ "productSourceChanges": 0,
+ "realModelRequests": 0,
+ "realCredentialsRead": 0,
+ "productionWrites": 0,
+ "releaseOrRestart": false,
+ "publicDocumentationRequests": true,
+ "ownedLocalUiFixture": true,
+ "offlineNumberedObservations": 21,
+ "separateCorrections": [
+ "O18-C"
+ ],
+ "sourceInventoryVerified": 715,
+ "inventory": {
+ "src": {
+ "files": 272,
+ "lines": 31738
+ },
+ "tests": {
+ "files": 171,
+ "lines": 20981
+ },
+ "scripts": {
+ "files": 272,
+ "lines": 24917
+ }
+ }
+ },
+ "validationBoundary": {
+ "offlineProbes": "21 observations and one correction; success means reproduction completed, not product correctness",
+ "ui": [
+ "owned1280 settings and persistence; owned390 actual controls/full form",
+ "seven prior build inputs and thirty compiled outputs verified unchanged",
+ "not current production Electron acceptance"
+ ],
+ "priorTargetedChecks": [
+ "126/126 New API repairs",
+ "67/67 Claude capacity repair"
+ ],
+ "priorFailures": "original regression/environment/network failures remain; not rerun or relabelled as pass"
+ },
+ "sourcesPath": "docs/official-first-sources-2026-11-06.json",
+ "sourcesSha256": "d230cfa36f12653757c9fb73d238dcbf0790d8587e3a66dffcb83765c5caaf59",
+ "evidenceSeal": {
+ "manifestPath": ".qa/official-first-system-audit-2026-11-06/MANIFEST.json",
+ "summaryPath": "docs/official-first-audit-evidence-2026-11-06.json",
+ "scope": "immutable raw audit files plus four final report/data inputs; mutable commit/push receipts kept separately"
+ },
+ "observations": [
+ {
+ "id": "O01",
+ "title": "Responses effort control deletes sibling summary",
+ "category": "defect",
+ "expected": {
+ "reasoning": {
+ "effort": "high",
+ "summary": "auto"
+ }
+ },
+ "observed": {
+ "reasoning": {
+ "effort": "high"
+ },
+ "text": {
+ "verbosity": "medium"
+ }
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O02",
+ "title": "Messages effort/mode controls delete format/display",
+ "category": "defect",
+ "expected": {
+ "preserve": [
+ "output_config.format",
+ "thinking.display"
+ ]
+ },
+ "observed": {
+ "effortChange": {
+ "output_config": {
+ "effort": "max"
+ },
+ "thinking": {
+ "type": "adaptive",
+ "display": "summarized"
+ }
+ },
+ "modeChange": {
+ "output_config": {
+ "effort": "high",
+ "format": {
+ "type": "json_schema",
+ "schema": {
+ "type": "object"
+ }
+ }
+ },
+ "thinking": {
+ "type": "adaptive"
+ }
+ }
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O03",
+ "title": "Metadata-absent Opus 5.5 still offers rejected manual/disabled modes",
+ "category": "defect",
+ "expected": {
+ "officialModes": [
+ "adaptive"
+ ],
+ "manualEnabled": "official 400",
+ "disabled": "official 400"
+ },
+ "observed": {
+ "offered": [
+ "disabled",
+ "enabled",
+ "adaptive"
+ ],
+ "generated": {
+ "thinking": {
+ "type": "enabled",
+ "budget_tokens": 1024
+ }
+ }
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O04",
+ "title": "Catalog loses between_tools and empty supported-mode list falls back to all modes",
+ "category": "defect",
+ "expected": {
+ "sonnetModes": [
+ "adaptive",
+ "between_tools"
+ ],
+ "explicitNegativeModes": []
+ },
+ "observed": {
+ "sonnetCatalog": {
+ "id": "claude-sonnet-5-5",
+ "name": "claude-sonnet-5-5",
+ "owner": "",
+ "lifecycle": null,
+ "contextLimit": 1000000,
+ "maxOutputTokens": 128000,
+ "capabilityDeclarations": {
+ "text": "unknown",
+ "tools": "unknown",
+ "streaming": "unknown",
+ "vision": "unknown",
+ "audio": "unknown"
+ },
+ "features": {
+ "thinking": "supported",
+ "effort": "unknown",
+ "pdf_input": "unknown",
+ "structured_outputs": "unknown",
+ "server_tools": "unknown",
+ "code_execution": "unknown",
+ "batch": "unknown",
+ "citations": "unknown",
+ "context_management": "unknown"
+ },
+ "efforts": [],
+ "modes": [
+ "adaptive"
+ ],
+ "parameters": [],
+ "metadataSource": "upstream-model-list"
+ },
+ "negativeProfile": {
+ "id": "anthropic",
+ "label": "Claude Messages 兼容",
+ "source": "按品牌、型号与协议匹配,可手动更改",
+ "efforts": [
+ "low",
+ "medium",
+ "high",
+ "xhigh",
+ "max"
+ ],
+ "modes": [
+ "disabled",
+ "enabled",
+ "adaptive"
+ ],
+ "thinking": true
+ }
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O05",
+ "title": "Feature table says structured parameters rejected while open wire forwards them",
+ "category": "display_drift",
+ "expected": "Describe forwarding separately from structured-output validation support",
+ "observed": {
+ "row": {
+ "name": "结构化输出约束",
+ "upstream": "待确认",
+ "local": "尚未接入,参数保存时明确拒绝"
+ },
+ "forwarded": {
+ "type": "json_object"
+ }
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O06",
+ "title": "Messages block/tool cache controls are dropped; top-level control survives",
+ "category": "missing_adapter_capability",
+ "expected": "Retain official block/tool fields via an explicit native content/tool representation",
+ "observed": {
+ "system": [
+ {
+ "type": "text",
+ "text": "stable audit prefix"
+ }
+ ],
+ "tools": [
+ {
+ "name": "audit_tool",
+ "description": "No execution",
+ "input_schema": {
+ "type": "object"
+ }
+ }
+ ],
+ "topLevel": {
+ "type": "ephemeral"
+ }
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O07",
+ "title": "Kimi cache-write usage preserved raw but absent from normalized usage",
+ "category": "missing_adapter_capability",
+ "expected": "Normalized cache read/write/uncached fields with provider provenance",
+ "observed": {
+ "prompt_tokens": 1000,
+ "completion_tokens": 100,
+ "total_tokens": 1100,
+ "prompt_tokens_details": {
+ "cached_tokens": 600
+ },
+ "raw": {
+ "prompt_tokens": 1000,
+ "completion_tokens": 100,
+ "total_tokens": 1100,
+ "prompt_tokens_details": {
+ "cached_tokens": 600,
+ "cache_write_tokens": 300,
+ "uncached_tokens": 100
+ }
+ },
+ "protocol": "chat-completions"
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O08",
+ "title": "Automatic pool selects declared unsupported member in unrestricted mode",
+ "category": "selection_defect",
+ "expected": "Automatic ranking prefers capable member while explicit manual selection remains unrestricted",
+ "observed": {
+ "first": "incapable",
+ "requirements": [
+ "tools"
+ ],
+ "declarations": [
+ {
+ "id": "incapable",
+ "tools": "unsupported"
+ },
+ {
+ "id": "capable",
+ "tools": "supported"
+ }
+ ]
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O09",
+ "title": "Affinity is Run-scoped, not session/task-scoped",
+ "category": "missing_routing_capability",
+ "expected": "Explicit conversational affinity strategy for cross-Run continuations",
+ "observed": {
+ "runA": "incapable",
+ "runAAgain": "incapable",
+ "nextRun": "capable",
+ "affinityKey": "runId"
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O10",
+ "title": "Unlimited attempt persistence conflicts with advertised retention and lacks full ledger view",
+ "category": "display_and_storage_gap",
+ "expected": {
+ "actualRetention": "unlimited",
+ "fullLedger": "paginated"
+ },
+ "observed": {
+ "persisted": 1001,
+ "view": 100,
+ "advertisedRetention": 1000
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O11",
+ "title": "Native server-tool blocks and pause continuation not implemented",
+ "category": "missing_adapter_capability",
+ "expected": "Typed native output and continuation handling, distinct from truncated/incomplete tools",
+ "observed": [
+ {
+ "id": "server-tool",
+ "accepted": false,
+ "diagnostic": {
+ "kind": "protocol",
+ "source": "model_connection",
+ "origin": "local",
+ "stage": "model_request",
+ "title": "模型响应未通过完整性核对",
+ "message": "Messages 包含未接入或不完整的内容块:server_tool_use。",
+ "retryable": false,
+ "occurredAt": "2026-11-06T13:21:14.809Z"
+ },
+ "message": "Messages 包含未接入或不完整的内容块:server_tool_use。"
+ },
+ {
+ "id": "pause-turn",
+ "accepted": false,
+ "diagnostic": {
+ "kind": "protocol",
+ "source": "model_connection",
+ "origin": "local",
+ "stage": "model_request",
+ "title": "模型响应未通过完整性核对",
+ "message": "Messages 未完整结束或停止原因为上下文上限、暂停或未知;原响应未用于执行工具。",
+ "retryable": false,
+ "occurredAt": "2026-11-06T13:21:14.810Z"
+ },
+ "message": "Messages 未完整结束或停止原因为上下文上限、暂停或未知;原响应未用于执行工具。"
+ }
+ ],
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O12",
+ "title": "Gemini-style entries parse but native nextPageToken does not",
+ "category": "missing_native_protocol",
+ "expected": "Native list/endpoint/pagination/generate/stream/auth contract",
+ "observed": {
+ "entries": [
+ {
+ "id": "models/audit-gemini",
+ "name": "models/audit-gemini",
+ "owner": "",
+ "lifecycle": null,
+ "contextLimit": 1000000,
+ "maxOutputTokens": 65536,
+ "capabilityDeclarations": {
+ "text": "unknown",
+ "tools": "unknown",
+ "streaming": "unknown",
+ "vision": "unknown",
+ "audio": "unknown"
+ },
+ "features": {
+ "thinking": "unknown",
+ "effort": "unknown",
+ "pdf_input": "unknown",
+ "structured_outputs": "unknown",
+ "server_tools": "unknown",
+ "code_execution": "unknown",
+ "batch": "unknown",
+ "citations": "unknown",
+ "context_management": "unknown"
+ },
+ "efforts": [],
+ "modes": [],
+ "parameters": [],
+ "metadataSource": "upstream-model-list"
+ }
+ ],
+ "hasMore": false,
+ "cursor": ""
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-contract-observations.json",
+ "evidenceSha256": "f2a8c574aabcda2a6c0e7d2290a462dd6fca8673b10ecab56d0a32dbf808b4c0"
+ },
+ {
+ "id": "O13",
+ "category": "missing_mcp_schema_support",
+ "title": "Ordinary union and 65-property schemas rejected regardless of open mode",
+ "observed": [
+ {
+ "id": "anyOf",
+ "accepted": false,
+ "message": "工具schema超出当前支持的有界JSON Schema范围。"
+ },
+ {
+ "id": "65-properties",
+ "accepted": false,
+ "message": "工具schema属性范围无效。"
+ }
+ ],
+ "expected": "Support vendor/standard schemas without arbitrary work-size caps; unsupported schema must remain explicit until implemented.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-harness-observations.json",
+ "evidenceSha256": "16ecdcefb2ea46b5f810e247a473c0a17a73a56cbaedd2b939ebff7c6c76e8e6"
+ },
+ {
+ "id": "O14",
+ "category": "remaining_hard_cap",
+ "title": "Open-mode MCP task still blocked after 30 operations",
+ "observed": "当前任务已达到30次MCP操作上限。",
+ "expected": "0/unlimited in unrestricted mode; keep each invocation identity and unknown outcome handling.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-harness-observations.json",
+ "evidenceSha256": "16ecdcefb2ea46b5f810e247a473c0a17a73a56cbaedd2b939ebff7c6c76e8e6"
+ },
+ {
+ "id": "O15",
+ "category": "remaining_hard_cap",
+ "title": "Open-mode checkpoint still blocks after 2000 tool references",
+ "observed": "当前任务超过恢复包2000项工具引用的上限,请缩小任务范围。",
+ "expected": "Paged/streamed verified checkpoints with unlimited default, not a request to shrink the task.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-harness-observations.json",
+ "evidenceSha256": "16ecdcefb2ea46b5f810e247a473c0a17a73a56cbaedd2b939ebff7c6c76e8e6"
+ },
+ {
+ "id": "O16",
+ "category": "instruction_drift",
+ "title": "MCP model-facing instruction always asks confirmation although full policy automatically approves",
+ "observed": {
+ "description": "请求用户确认后调用本次目录的已启用MCP工具。先核对固定程序/实际握手/schema,不自动重试;完整结果按工件读取。",
+ "fullModePolicy": {
+ "approve": true,
+ "mode": "full",
+ "source": "full-access-policy"
+ }
+ },
+ "expected": "Model-facing description derived from active approval mode; do not imply an extra manual confirmation.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-harness-observations.json",
+ "evidenceSha256": "16ecdcefb2ea46b5f810e247a473c0a17a73a56cbaedd2b939ebff7c6c76e8e6"
+ },
+ {
+ "id": "O17",
+ "category": "silent_parameter_rewrite",
+ "title": "Chat streaming replaces explicit stream_options",
+ "expected": {
+ "include_usage": false,
+ "include_obfuscation": false
+ },
+ "observed": {
+ "include_usage": true
+ },
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-forwarding-observations.json",
+ "evidenceSha256": "ef657bbe3d07c6c5a85227da29ccde24208f1fcd7e68fcf95f2706aa871c94a9"
+ },
+ {
+ "id": "O18",
+ "category": "incomplete_response_selection",
+ "title": "Multiple choices remain raw; harness consumes only first choice",
+ "observed": {
+ "acceptedRawChoices": 2,
+ "canonicalChoice": 0
+ },
+ "expected": "Explicit candidate-selection contract and complete raw retention; never apply multiple alternatives blindly.",
+ "sourceInference": "Provider and Chat stream choose index 0; this probe establishes acceptance, not a live stream/UI run.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-forwarding-observations.json",
+ "evidenceSha256": "ef657bbe3d07c6c5a85227da29ccde24208f1fcd7e68fcf95f2706aa871c94a9"
+ },
+ {
+ "id": "O19",
+ "category": "cache_observation_gap",
+ "title": "Prompt prefix observation excludes native parameters that may affect supplier cache",
+ "observed": {
+ "schemaVersion": 2,
+ "method": "ordered-wire-prompt-fields-utf8",
+ "upstreamCache": "unknown",
+ "variants": [
+ {
+ "connectionId": null,
+ "protocol": "chat-completions",
+ "model": "audit-only-model",
+ "toolsSha256": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945",
+ "toolBytes": 2,
+ "toolNames": [],
+ "promptBytes": 100,
+ "previousPromptBytes": 100,
+ "commonPrefixBytes": 100,
+ "reason": "same_prompt",
+ "blocks": [
+ {
+ "path": "model",
+ "role": null,
+ "sha256": "bc9b64afd40848b6216a18919080b26718cc5875166afe314b32309c95e83e69",
+ "bytes": 18
+ },
+ {
+ "path": "tools",
+ "role": null,
+ "sha256": "4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945",
+ "bytes": 2
+ },
+ {
+ "path": "system",
+ "role": null,
+ "sha256": "74234e98afe7498fb5daf1f36ac2d78acc339464f950703b8c019892f982b90b",
+ "bytes": 4
+ },
+ {
+ "path": "messages[0]",
+ "role": "user",
+ "sha256": "684dfefce8cea4319a87556ed5340b6d2b9f530c31cc5637ea07de5524cc62bd",
+ "bytes": 33
+ }
+ ],
+ "firstChange": null,
+ "tools": []
+ }
+ ]
+ },
+ "expected": "Keep ordered prompt observation distinct from actual supplier cache; add a vendor-specific cache-relevant parameter fingerprint.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-forwarding-observations.json",
+ "evidenceSha256": "ef657bbe3d07c6c5a85227da29ccde24208f1fcd7e68fcf95f2706aa871c94a9"
+ },
+ {
+ "id": "O18-C",
+ "corrects": "O18.sourceInference",
+ "kind": "correction",
+ "originalEvidence": "offline-forwarding-observations.json",
+ "originalPreserved": true,
+ "finding": "Nonstreaming accepts multiple raw choices and Provider consumes choices[0]; Chat streaming rejects every choice.index other than 0 locally.",
+ "observed": {
+ "streamedSecondChoiceRejected": true,
+ "diagnostic": "当前只接入单个Chat候选流。",
+ "streamTerminal": false,
+ "capturedBytes": 247
+ },
+ "limitation": "Synthetic in-memory SSE; no live supplier, HTTP request, UI assertion, or alternative execution.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-correction-observations.json",
+ "evidenceSha256": "8fd84fb828a72e1ca145d33b908e2e090467dce744dabf2a21d6a14f8a2669a7"
+ },
+ {
+ "id": "O20",
+ "category": "policy_display_drift",
+ "title": "Identity policy says require-match while unrestricted execution records and continues",
+ "observed": {
+ "configuredPolicy": "require-match",
+ "executionMode": "unrestricted",
+ "reportedIdentity": "mismatch",
+ "requestStatus": "completed",
+ "consumptionOutcome": "completed",
+ "mockFetchCalls": 1
+ },
+ "sourceInterpretation": "ModelIdentityDetails displays pause for require-match regardless of executionMode; production UI was not changed or exercised by this probe.",
+ "expected": "Expose requested and effective policy accurately, and preserve the unrestricted default; do not reintroduce compulsory identity interception.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-correction-observations.json",
+ "evidenceSha256": "8fd84fb828a72e1ca145d33b908e2e090467dce744dabf2a21d6a14f8a2669a7"
+ },
+ {
+ "id": "O21",
+ "category": "fixed-load-count-cap",
+ "title": "Saved-credential metadata with 102 entries is marked unavailable even in unrestricted mode",
+ "observed": [
+ {
+ "entries": 101,
+ "blocked": false,
+ "loadedEntries": 101,
+ "originalMetaEntries": 101
+ },
+ {
+ "entries": 102,
+ "blocked": true,
+ "loadedEntries": 0,
+ "originalMetaEntries": 102
+ }
+ ],
+ "limitation": "Only synthetic metadata count gate; no encryption/decryption, valid saved payload restore, real Key or real vault read; original meta is not deleted.",
+ "expected": "Saved-credential metadata should load by supported version and record validity, not a fixed connection-count cap.",
+ "evidencePath": ".qa/official-first-system-audit-2026-11-06/offline-credential-scope-observations.json",
+ "evidenceSha256": "fb9cba4aaadf9ab1bb4cc4f143f9b9ecf32cff0636a2c9aa78e786f92fd0cec1"
+ }
+ ],
+ "capabilities": [
+ {
+ "id": "C01",
+ "name": "模型发现、多连接、多模型池",
+ "implementation": "implemented-partial",
+ "validation": "local-and-recorded-live",
+ "deployment": "1.25.12; refresh repair source-only",
+ "issues": [
+ "I04",
+ "I13",
+ "I15",
+ "I29"
+ ]
+ },
+ {
+ "id": "C02",
+ "name": "原生参数与推理选择",
+ "implementation": "implemented-with-defects",
+ "validation": "offline-and-owned-web-observed",
+ "deployment": "1.25.12; current controls still defective",
+ "issues": [
+ "I01",
+ "I02",
+ "I03",
+ "I08"
+ ]
+ },
+ {
+ "id": "C03",
+ "name": "官方容量、默认本地透传",
+ "implementation": "implemented-partial",
+ "validation": "67 prior targeted plus current audit",
+ "deployment": "passthrough deployed; official fallback source-only",
+ "issues": [
+ "I29"
+ ]
+ },
+ {
+ "id": "C04",
+ "name": "官方认证/版本/云平台",
+ "implementation": "implemented-bearer-and-x-api-key-only",
+ "validation": "local-contract-not-global-live",
+ "deployment": "1.25.12 for current subset",
+ "issues": [
+ "I14",
+ "I16",
+ "I17"
+ ]
+ },
+ {
+ "id": "C05",
+ "name": "JSON/SSE、原错与unknown用量",
+ "implementation": "implemented-with-coverage-gaps",
+ "validation": "historical-live-and-current-offline",
+ "deployment": "1.25.12; wire diagnostic repair source-only",
+ "issues": [
+ "I02",
+ "I10",
+ "I18",
+ "I21",
+ "I28",
+ "I29"
+ ]
+ },
+ {
+ "id": "C06",
+ "name": "ask/auto/full持久权限与开放执行",
+ "implementation": "implemented-with-residual-caps",
+ "validation": "historical-runtime-and-current-offline",
+ "deployment": "1.25.12",
+ "issues": [
+ "I05",
+ "I06",
+ "I07",
+ "I08",
+ "I33"
+ ]
+ },
+ {
+ "id": "C07",
+ "name": "型号声明/响应身份记录",
+ "implementation": "implemented-not-weight-authentication",
+ "validation": "historical-live-and-current-mock",
+ "deployment": "1.25.12",
+ "issues": [
+ "I08"
+ ]
+ },
+ {
+ "id": "C08",
+ "name": "自动适配与会话连续性",
+ "implementation": "implemented-run-routing-only",
+ "validation": "offline-observed",
+ "deployment": "1.25.12",
+ "issues": [
+ "I04",
+ "I11",
+ "I15"
+ ]
+ },
+ {
+ "id": "C09",
+ "name": "原生多模态/文件",
+ "implementation": "basic-png-image-only",
+ "validation": "prior-owned-vision-ui",
+ "deployment": "1.25.12 for basic image",
+ "issues": [
+ "I20"
+ ]
+ },
+ {
+ "id": "C10",
+ "name": "原生服务端工具/续接/候选/后台",
+ "implementation": "not-implemented-completely",
+ "validation": "rejection-observed-and-source",
+ "deployment": "not deployed as workflow",
+ "issues": [
+ "I18",
+ "I19",
+ "I21",
+ "I37"
+ ]
+ },
+ {
+ "id": "C11",
+ "name": "文件读写/改动集/自动应用/Git回滚",
+ "implementation": "implemented",
+ "validation": "historical-Node-React-Python-delivery-and-local-QA",
+ "deployment": "1.25.12",
+ "issues": []
+ },
+ {
+ "id": "C12",
+ "name": "环境诊断/依赖/Node/Python检查",
+ "implementation": "implemented",
+ "validation": "AH/local-and-historical-AD-AE",
+ "deployment": "1.25.12 including AH/AI",
+ "issues": []
+ },
+ {
+ "id": "C13",
+ "name": "命令执行/完整日志/停止/Git证据",
+ "implementation": "implemented-pipes",
+ "validation": "AI/local-and-historical-live",
+ "deployment": "1.25.12",
+ "issues": [
+ "I22"
+ ]
+ },
+ {
+ "id": "C14",
+ "name": "要求证据/单轮观察/终态报告",
+ "implementation": "implemented",
+ "validation": "historical-A-B-AI-QA",
+ "deployment": "1.25.12",
+ "issues": [
+ "I24",
+ "I35"
+ ]
+ },
+ {
+ "id": "C15",
+ "name": "工具目录/原请求前缀/重复读取观察",
+ "implementation": "implemented-observation-not-benefit",
+ "validation": "historical-C-D-and-current-offline",
+ "deployment": "1.25.12",
+ "issues": [
+ "I12",
+ "I35"
+ ]
+ },
+ {
+ "id": "C16",
+ "name": "缓存控制/归一统计/会话缓存",
+ "implementation": "implemented-partial",
+ "validation": "one-live-cache-observation-and-offline",
+ "deployment": "1.25.12 subset",
+ "issues": [
+ "I09",
+ "I10",
+ "I11",
+ "I12",
+ "I35"
+ ]
+ },
+ {
+ "id": "C17",
+ "name": "可关闭提醒与实际回读",
+ "implementation": "implemented-default-off",
+ "validation": "D-owned-HTTP-web-desktop-release",
+ "deployment": "1.25.10 onward",
+ "issues": [
+ "I35"
+ ]
+ },
+ {
+ "id": "C18",
+ "name": "来源经验草稿/采用撤销/完整修订",
+ "implementation": "implemented-semantic-benefit-unknown",
+ "validation": "E-owned-and-release-QA",
+ "deployment": "1.25.11 onward",
+ "issues": [
+ "I35"
+ ]
+ },
+ {
+ "id": "C19",
+ "name": "Worker角色/模型绑定/真实质量回收",
+ "implementation": "implemented-partial",
+ "validation": "F-owned-and-release-QA",
+ "deployment": "1.25.12",
+ "issues": [
+ "I24",
+ "I25",
+ "I35"
+ ]
+ },
+ {
+ "id": "C20",
+ "name": "Skills/MCP生态",
+ "implementation": "implemented-local-subset",
+ "validation": "historical-QA-and-current-offline",
+ "deployment": "1.25.12",
+ "issues": [
+ "I05",
+ "I06",
+ "I08",
+ "I25"
+ ]
+ },
+ {
+ "id": "C21",
+ "name": "内置浏览器/页面预览/DOM动作",
+ "implementation": "implemented-fixed-action-set",
+ "validation": "historical-web-desktop-and-current-owned-form",
+ "deployment": "1.25.12",
+ "issues": [
+ "I23"
+ ]
+ },
+ {
+ "id": "C22",
+ "name": "Windows桌面桥/本机加密凭据",
+ "implementation": "implemented-not-general-OS-control",
+ "validation": "historical-DPAPI-and-install-QA-not-real-key-read",
+ "deployment": "1.25.12",
+ "issues": [
+ "I23",
+ "I38"
+ ]
+ },
+ {
+ "id": "C23",
+ "name": "DeepSeek Harness/外部完整引擎",
+ "implementation": "DeepSeek-bridge-implemented-others-missing",
+ "validation": "fixed-SDK-owned-and-historical-live",
+ "deployment": "1.25.12 bridge; full Codex/Claude Code not implemented",
+ "issues": []
+ },
+ {
+ "id": "C24",
+ "name": "原版Purge加载与对照",
+ "implementation": "mechanism-implemented-benefit-unknown",
+ "validation": "historical-AG-four-groups-not-comparable",
+ "deployment": "1.25.12 default-off option",
+ "issues": [
+ "I36"
+ ]
+ },
+ {
+ "id": "C25",
+ "name": "REA来源分析与证据工件",
+ "implementation": "implemented-static-job-adapter",
+ "validation": "historical-source-and-owned-QA",
+ "deployment": "1.25.12",
+ "issues": []
+ },
+ {
+ "id": "C26",
+ "name": "Companion手机查看/批准/停止",
+ "implementation": "implemented-real-current-device-unverified",
+ "validation": "historical-owned-contracts",
+ "deployment": "1.25.12",
+ "issues": [
+ "I32",
+ "I33"
+ ]
+ },
+ {
+ "id": "C27",
+ "name": "Mnemo及跨产品协作",
+ "implementation": "read-only-contract-feedback-only",
+ "validation": "synthetic-original-package-review",
+ "deployment": "native export/inbound delegation missing",
+ "issues": [
+ "I31"
+ ]
+ },
+ {
+ "id": "C28",
+ "name": "SQLite事件/工件/恢复检查点",
+ "implementation": "implemented-with-caps-and-scale-risk",
+ "validation": "historical-recovery-and-current-offline/source",
+ "deployment": "1.25.12",
+ "issues": [
+ "I07",
+ "I13",
+ "I26"
+ ]
+ },
+ {
+ "id": "C29",
+ "name": "源码打包/独立程序/安装回退",
+ "implementation": "implemented-source-data-separated",
+ "validation": "historical-F-release-and-retention",
+ "deployment": "1.25.12; three later source repairs pending",
+ "issues": [
+ "I27",
+ "I28",
+ "I29"
+ ]
+ },
+ {
+ "id": "C30",
+ "name": "Orven三配色/任务与模型中心界面",
+ "implementation": "implemented-with-copy-and-controls-drift",
+ "validation": "historical-release plus owned1280/390",
+ "deployment": "1.25.12 for brand; no new production UI audit",
+ "issues": [
+ "I03",
+ "I08",
+ "I30"
+ ]
+ }
+ ],
+ "issues": [
+ {
+ "id": "I01",
+ "title": "推理快捷编辑丢失嵌套原生字段",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-defect",
+ "impact": "修改 effort 或 thinking 会删除 summary、output_config.format、thinking.display,用户请求未如实保留。",
+ "nextChange": "只修改目标键;删除目标值也不删除同对象其他字段;明确默认重置的范围。",
+ "acceptance": "三协议往返、JSON/快捷控件/保存/重新打开,非目标字段逐项保持。",
+ "observations": [
+ "O01",
+ "O02"
+ ],
+ "references": [
+ {
+ "path": "src/shared/contracts/model-parameter-profiles.mjs",
+ "line": 54,
+ "sha256": "1264a90ba612b721ea639206cd6d8f595309c7bda38f80c45bb13c78af4a2d1f",
+ "match": " else next[effortField] = effortField === 'reasoning_effort' ? effort : { effort };"
+ },
+ {
+ "path": "src/shared/contracts/model-parameter-profiles.mjs",
+ "line": 57,
+ "sha256": "1264a90ba612b721ea639206cd6d8f595309c7bda38f80c45bb13c78af4a2d1f",
+ "match": " else if (field === 'budget') next.thinking = { type: 'enabled', budget_tokens: value };"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I02",
+ "title": "Chat 流式覆盖用户 stream_options",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-defect",
+ "impact": "include_usage=false 与其他上游 stream_options 被整对象替换。",
+ "nextChange": "透传显式原生设置;默认建议与用户值分开,不隐式覆盖。",
+ "acceptance": "实际本机 HTTP wire 与用户对象一致,缺失字段才按明确策略补充。",
+ "observations": [
+ "O17"
+ ],
+ "references": [
+ {
+ "path": "src/shared/contracts/model-request.mjs",
+ "line": 22,
+ "sha256": "5606dc2c245e3461c35613773c0d1b47718acd28a6fe4abd07406bbe80af2e11",
+ "match": " ...(stream ? { stream_options: { include_usage: true } } : {}) };"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I03",
+ "title": "Claude 型号推理能力与官方未对齐",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-defect",
+ "impact": "Opus5.5 仍能生成官方拒绝的 enabled/disabled;between_tools 未解析;全否定目录又回退全部选项。",
+ "nextChange": "以精确型号、协议、官方版本解析模式/effort/条件,区分未知与明确不支持。",
+ "acceptance": "官方新旧型号矩阵、目录全否定和缺失情况通过;UI/保存/wire 一致;兼容显式覆盖仍可用。",
+ "observations": [
+ "O03",
+ "O04"
+ ],
+ "references": [
+ {
+ "path": "src/shared/contracts/model-catalog.mjs",
+ "line": 38,
+ "sha256": "abb7b41982d072ecdb8c8d7c2feb67228eeb03c751c3f10b8557ac12b25022e1",
+ "match": " const modes = ['disabled', 'enabled', 'adaptive'].filter(value => supported(caps.thinking?.types?.[value]) === 'supported');"
+ },
+ {
+ "path": "src/shared/contracts/model-parameter-profiles.mjs",
+ "line": 27,
+ "sha256": "1264a90ba612b721ea639206cd6d8f595309c7bda38f80c45bb13c78af4a2d1f",
+ "match": " modes: metadata?.features?.thinking === 'unsupported' ? [] : metadata?.modes?.length ? metadata.modes : ['disabled', 'enabled', ...(protocol === 'anthropic-messages' ? ['adaptive'] : [])],"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I04",
+ "title": "自动模型池可选明确不支持工具的成员",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-selection-defect",
+ "impact": "需要工程工具时,自动模式仍可把请求发给明确不支持工具的模型。",
+ "nextChange": "自动候选按能力与任务排序,显式手选/强制尝试与自动适配分别记录,不恢复全局拒发。",
+ "acceptance": "自动选择工具支持成员;未知有明确策略;用户手选仍可透传;记录选择依据。",
+ "observations": [
+ "O08"
+ ],
+ "references": [
+ {
+ "path": "src/core/models/model-hub.mjs",
+ "line": 321,
+ "sha256": "630c276a445641e3abaf920957e01d6ffd1b50f8264c0227ee55d29073d9dbb9",
+ "match": " const eligible = routing.members.filter(value => unrestricted(this.store) || capabilityRejections(value, requirements, value.credentialRevision).length === 0);"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I05",
+ "title": "开放模式仍有每任务 30 次 MCP 操作上限",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-execution-cap",
+ "impact": "长工程在已有开放权限下仍被固定次数挡住。",
+ "nextChange": "移除开放模式次数门槛,完整账本用游标/分页;保留每次真实身份、结果和停止。",
+ "acceptance": "同任务第31次及更长序列可执行且无旧记录丢失;停止/重启 unknown 保留。",
+ "observations": [
+ "O14"
+ ],
+ "references": [
+ {
+ "path": "src/core/tools/mcp-registry.mjs",
+ "line": 121,
+ "sha256": "6e91279f20aa08850478f29155702f6f6b41d576ea7d58204d84a66d7b4ec360",
+ "match": " if (this.jobs(session).filter(job => job.taskId === session.taskId).length >= 30) throw mcpError('当前任务已达到30次MCP操作上限。');"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I06",
+ "title": "MCP JSON Schema 子集拒绝常见合法工具",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-adapter-gap",
+ "impact": "anyOf 和65属性等普通 schema 无法接入,与开放工具能力目标不符。",
+ "nextChange": "支持官方/服务器声明的 JSON Schema 或按协议原样转交;不用固定属性数假冒模型能力。",
+ "acceptance": "union/ref/嵌套/65以上属性工具真实握手后可选择;错误与原 schema 可核对。",
+ "observations": [
+ "O13"
+ ],
+ "references": [
+ {
+ "path": "src/core/tools/mcp-contract.mjs",
+ "line": 24,
+ "sha256": "9f534148fcbf1e6c016b9b6da70d9af2046ffa910dc4710b8a085c90c8c99dab",
+ "match": " if (!plain(value) || ++nodes > 256 || depth > 8 || Object.keys(value).some(key => !keywords.has(key))) throw mcpError('工具schema超出当前支持的有界JSON Schema范围。', 400);"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I07",
+ "title": "检查点仍受 30/2000/64MiB 固定上限",
+ "priority": "P0",
+ "statusAtAudit": "confirmed-execution-cap",
+ "impact": "工具引用2000项、检查点30个或结果64MiB可阻断开放工程恢复。",
+ "nextChange": "采用分段索引、流式校验与分页恢复,去掉开放模式固定额度。",
+ "acceptance": "跨各旧边界建立和恢复检查点,旧工具/结果原 SHA 与归属完整。",
+ "observations": [
+ "O15"
+ ],
+ "references": [
+ {
+ "path": "src/core/tasks/task-checkpoint-manager.mjs",
+ "line": 15,
+ "sha256": "2f50f9de2e6b8c90376028ed2814eb795633e1ea917ab944a977299220ad820f",
+ "match": "export const TASK_CHECKPOINT_LIMITS = Object.freeze({ checkpoints: 30, tools: 2000, resultBytes: 64 * 1024 * 1024 });"
+ }
+ ],
+ "dependsOn": [],
+ "fixedInThisAudit": false
+ },
+ {
+ "id": "I08",
+ "title": "能力/权限说明与实际行为不一致",
+ "priority": "P1",
+ "statusAtAudit": "confirmed-display-drift",
+ "impact": "结构化参数被说成拒绝、MCP仍提示确认、require-match显示暂停但开放模式继续。",
+ "nextChange": "展示声明能力、本地实现、实际权限/身份策略与可选覆盖;同步模型提示。",
+ "acceptance": "ask/auto/full 与完整参数/身份原件在网页和桌面一致;不恢复强制拦截。",
+ "observations": [
+ "O05",
+ "O16",
+ "O20"
+ ],
+ "references": [
+ {
+ "path": "src/shared/contracts/model-parameter-profiles.mjs",
+ "line": 81,
+ "sha256": "1264a90ba612b721ea639206cd6d8f595309c7bda38f80c45bb13c78af4a2d1f",
+ "match": " { name: '结构化输出约束', upstream: states[connection.upstreamModel?.features?.structured_outputs ?? 'unknown'], local: '尚未接入,参数保存时明确拒绝' },"
+ },
+ {
+ "path": "src/core/tools/mcp-contract.mjs",
+ "line": 74,
+ "sha256": "9f534148fcbf1e6c016b9b6da70d9af2046ffa910dc4710b8a085c90c8c99dab",
+ "match": "export const mcpToolDefinitions = [{ type: 'function', function: { name: 'call_registered_mcp', description: '请求用户确认后调用本次目录的已启用MCP工具。先核对固定程序/实际握手/schema,不自动重试;完整结果按工件读取。',"
+ },
+ {
+ "path": "src/client/ModelIdentityDetails.tsx",
+ "line": 13,
+ "sha256": "3e8bd9f735e21cc62abf217fc5f184c04014ea246d45115c42a95616248ac40b",
+ "match": "