2187 lines
102 KiB
JSON
2187 lines
102 KiB
JSON
{
|
||
"schema": 1,
|
||
"kind": "official-first-audit-public-source-ledger",
|
||
"recordedAt": "2026-11-06T14:09:15.016711+00:00",
|
||
"sourceHead": "4da2550becdf4750320cedd5ee30a7e38baba2f9",
|
||
"officialSdkCommit": "c6fc264689d384d5caec150fafa1a9567c4a3f56",
|
||
"acquired": [
|
||
{
|
||
"id": "deepseek-create",
|
||
"requestedUrl": "https://api-docs.deepseek.com/api/create-chat-completion",
|
||
"observedAt": "2026-11-06T13:05:31.918033+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://api-docs.deepseek.com/api/create-chat-completion/",
|
||
"contentType": "text/html",
|
||
"contentLength": "129498",
|
||
"bytes": 129498,
|
||
"completeByReadLimit": true,
|
||
"sha256": "b43ca950bd04ae7f6f537b42e6cb729f543d942dcd848ec43ad4e9bfe059fe1f",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/deepseek-create.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/deepseek-create.text",
|
||
"reviewScope": [
|
||
"max_tokens",
|
||
"reasoning_effort",
|
||
"thinking",
|
||
"usage"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 193,
|
||
"text": "(Beta) Used for the thinking mode in the Chat Prefix Completion feature as the input for the CoT in the last assistant message. When using this feature, the prefix parameter must be set to true.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 287,
|
||
"text": "thinking",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 291,
|
||
"text": "Controls the switch between thinking and non-thinking mode. When thinking is omitted or null, the mode follows reasoning_effort; if reasoning_effort is also omitted, thinking is enabled. When this object is provided, type is required and takes precedence over reasoning_effort for selecting the mode.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 297,
|
||
"text": "If set to enabled, then use thinking mode. If set to disabled, then use non-thinking model.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 299,
|
||
"text": "reasoning_effort string",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 303,
|
||
"text": "Controls the thinking mode toggle and the thinking effort. none disables thinking mode; low / high / max enable thinking mode. The default effort is high. For compatibility with existing software, minimal is accepted and mapped to low, and medium / xhigh are accepted and mapped to high.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 305,
|
||
"text": "max_tokens integernullable",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 311,
|
||
"text": "The value must be between 1 and 384K (393216). When not set, the default is 8K in non-thinking mode, 64K in thinking mode (128K with reasoning_effort set to max). Please refer to the Models & Pricing page for details.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 319,
|
||
"text": "Important: When using JSON Output, you must also instruct the model to produce JSON yourself via a system or user message. If the model's output cannot be recognized as JSON, the API replaces the non-JSON content with spaces (U+0020). As a result, the message content may contain only spaces (appearing empty), even when finish_reason is stop. Also note that the message content may be partially cut off if finish_reason=\"length\", which indicates the generation exceeded max_tokens or the conversatio",
|
||
"snippetComplete": false
|
||
},
|
||
{
|
||
"line": 362,
|
||
"text": "include_usage boolean",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 364,
|
||
"text": "If set to true, all chunks in the stream will include a usage field, whose value is null on every chunk except the last one. If omitted or set to false, the usage field is absent from all chunks except the last one.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 366,
|
||
"text": "Either way, the last chunk before the data: [DONE] message carries the token usage statistics for the entire request in its usage field. Note that no separate usage-only chunk is emitted: the statistics ride on the last content chunk, whose choices array always contains exactly one element that carries no new content and a non-null finish_reason.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 376,
|
||
"text": "We generally recommend altering this or top_p but not both. Has no effect in thinking mode.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 386,
|
||
"text": "deepseek-flash: In thinking mode, the default is 1.0 and values below 0.95 are treated as 0.95. In non-thinking mode, it is fixed at 1.0 and the value you pass is ignored.",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "deepseek-thinking",
|
||
"requestedUrl": "https://api-docs.deepseek.com/guides/thinking_mode",
|
||
"observedAt": "2026-11-06T13:05:31.918033+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://api-docs.deepseek.com/guides/thinking_mode/",
|
||
"contentType": "text/html",
|
||
"contentLength": "117778",
|
||
"bytes": 117778,
|
||
"completeByReadLimit": true,
|
||
"sha256": "42151b5f86827bff663a61693080a61cdbf99074dee94af756c9fce855baa7cd",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/deepseek-thinking.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/deepseek-thinking.text",
|
||
"reviewScope": [
|
||
"reasoning_content",
|
||
"reasoning_effort",
|
||
"thinking mode",
|
||
"all previous"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 3,
|
||
"text": "Thinking Mode | DeepSeek API Docs",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 22,
|
||
"text": "Thinking Mode",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 34,
|
||
"text": "Thinking Mode",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 40,
|
||
"text": "Thinking Mode",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 42,
|
||
"text": "The DeepSeek model supports the thinking mode: before outputting the final answer, the model will first output a chain-of-thought reasoning to improve the accuracy of the final response.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 44,
|
||
"text": "Thinking Mode Toggle and Effort Control",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 47,
|
||
"text": "Thinking Mode Toggle(1){\"thinking\": {\"type\": \"enabled/disabled\"}}{\"reasoning\": {\"effort\": \"none/low/high/max\"}}(none disables thinking mode)",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 48,
|
||
"text": "Thinking Effort Control(2){\"reasoning_effort\": \"low/high/max\"}{\"output_config\": {\"effort\": \"low/high/max\"}}",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 50,
|
||
"text": "(1) Thinking mode is enabled by default, with the default effort being high",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 63,
|
||
"text": "response = client.chat.completions.create( model=\"deepseek-flash\", # ... reasoning_effort=\"high\", extra_body={\"thinking\": {\"type\": \"enabled\"}},)",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 67,
|
||
"text": "Thinking mode does not support the temperature, presence_penalty, or frequency_penalty parameters. Please note that, for compatibility with existing software, setting these parameters will not trigger an error but will also have no effect.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 71,
|
||
"text": "deepseek-flash: only takes effect in thinking mode, where the effective range is 0.95–1.0; values below 0.95 are treated as 0.95. In non-thinking mode it is fixed at 1.0 and your value is ignored.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 73,
|
||
"text": "deepseek-v4-pro: in thinking mode your value is ignored (fixed at 0.95 when tool calling is enabled, otherwise 1.0); in non-thinking mode it takes effect. Setting tool_choice to none disables tool calling even when tools is provided.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 75,
|
||
"text": "In thinking mode, the chain-of-thought content is returned via the reasoning_content parameter, at the same level as content. In subsequent requests, whether reasoning_content should be passed back and whether it will be concatenated into the context depends on whether the request carries the tools parameter:",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "deepseek-cache",
|
||
"requestedUrl": "https://api-docs.deepseek.com/guides/kv_cache",
|
||
"observedAt": "2026-11-06T13:05:31.918033+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://api-docs.deepseek.com/guides/kv_cache/",
|
||
"contentType": "text/html",
|
||
"contentLength": "35850",
|
||
"bytes": 35850,
|
||
"completeByReadLimit": true,
|
||
"sha256": "061c0c7055ceb96d0a522ae1829ff5f7126ff08f26af217643e371abb740a081",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/deepseek-cache.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/deepseek-cache.text",
|
||
"reviewScope": [
|
||
"prefix",
|
||
"best-effort",
|
||
"prompt_cache_hit_tokens",
|
||
"prompt_cache_miss_tokens"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 24,
|
||
"text": "Chat Prefix Completion (Beta)",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 44,
|
||
"text": "Each user request will trigger the construction of a hard disk cache. If subsequent requests have overlapping prefixes with previous requests, the overlapping part will only be fetched from the cache, which counts as a \"cache hit.\"",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 48,
|
||
"text": "A cache hit requires that the corresponding prefix has already been \"persisted\" (written to the disk cache). Due to the Sliding Window Attention mechanism, the storage and matching of cached prefixes differs from before. Each cached prefix is an independent, complete unit. A subsequent request can only hit the cache if it fully matches a cache prefix unit.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 50,
|
||
"text": "When cache prefixes are persisted:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 52,
|
||
"text": "Persistence at request boundaries: Each request will produce two cache prefix units at the end position of the user input and the end position of the model output. A subsequent request can hit the cache if it fully matches them.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 54,
|
||
"text": "Common prefix detection persistence: When the system detects a common prefix across multiple requests, it will persist that common prefix as an independent cache prefix unit. A subsequent request can hit the cache if it fully reuses that cache prefix unit.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 56,
|
||
"text": "Persistence at fixed token intervals: For long inputs or long outputs, the system will carve out cache prefix units at fixed token intervals, to avoid long prefixes from being completely uncacheable due to never reaching an end position.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 58,
|
||
"text": "Example 1: A user's first-round request is A + B, and the second-round request is A + B + C. The second request can fully match the cache prefix unit A + B, hitting the cache for A + B. See Example 1 below.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 60,
|
||
"text": "Example 2: A user's first-round request is A + B, and the second-round request is A + C. The second request cannot hit the cache, because A + C does not fully match the first round's cache prefix unit (A + B). However, at this point the system will detect that the two requests share a common prefix A, and persist A as a cache prefix unit. When a third-round request A + D arrives, it can fully match the cache prefix unit A, hitting the cache for A. See Example 2 below.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 72,
|
||
"text": "In this example, the second request can fully reuse the cache prefix unit from the first request, which will count as a \"cache hit.\"",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 88,
|
||
"text": "In the above example, the first two requests will not hit the cache. After the first two requests are completed, the system will identify the system message + <financial report content> in the user message as a cache prefix unit and persist it. In the third request, since it fully matches the previously persisted cache prefix unit, it can hit the cache.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 94,
|
||
"text": "prompt_cache_hit_tokens: The number of tokens in the input of this request that resulted in a cache hit.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 96,
|
||
"text": "prompt_cache_miss_tokens: The number of tokens in the input of this request that did not result in a cache hit.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 100,
|
||
"text": "The hard disk cache only matches the prefix part of the user's input. The output is still generated through computation and inference, and it is influenced by parameters such as temperature, introducing randomness.",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "qwen-compatible",
|
||
"requestedUrl": "https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope",
|
||
"observedAt": "2026-11-06T13:07:38.225266+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope",
|
||
"contentType": "text/html;charset=UTF-8",
|
||
"contentLength": null,
|
||
"bytes": 167084,
|
||
"completeByReadLimit": true,
|
||
"sha256": "0b58c3f79d2e330af6457a5c98cd347397ab8db4cd09c7d50e0cb41d6daf6c1a",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/qwen-compatible.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/qwen-compatible.text",
|
||
"reviewScope": [
|
||
"enable_thinking",
|
||
"thinking_budget",
|
||
"compatible-mode",
|
||
"model",
|
||
"usage"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 3,
|
||
"text": " 如何通过OpenAI接口调用千问模型-大模型服务平台百炼(Model Studio)-阿里云帮助中心",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 55,
|
||
"text": "北京:https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 56,
|
||
"text": "弗吉尼亚:https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 57,
|
||
"text": "新加坡:https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 58,
|
||
"text": "日本(东京):https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 62,
|
||
"text": "北京:POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 63,
|
||
"text": "弗吉尼亚:POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 64,
|
||
"text": "新加坡:POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 65,
|
||
"text": "日本(东京):POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 122,
|
||
"text": " # 新加坡和北京地域的API Key不同。获取API Key:https://help.aliyun.com/zh/model-studio/get-api-key",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 125,
|
||
"text": " base_url=\"https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1\",",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 128,
|
||
"text": " model=\"qwen3.8-max\", # 此处以qwen-plus为例,可按需更换模型名称。模型列表:https://help.aliyun.com/zh/model-studio/getting-started/models",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 132,
|
||
"text": " print(completion.model_dump_json())",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 155,
|
||
"text": " \"model\": \"qwen3.8-max\",",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "zai-chat",
|
||
"requestedUrl": "https://docs.z.ai/api-reference/llm/chat-completion",
|
||
"observedAt": "2026-11-06T13:07:38.865783+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://docs.z.ai/api-reference/llm/chat-completion",
|
||
"contentType": "text/markdown; charset=utf-8",
|
||
"contentLength": null,
|
||
"bytes": 42735,
|
||
"completeByReadLimit": true,
|
||
"sha256": "5e608d3c82b283ed8dac0b7991187b625e378ca706a060f0eaa40ddf90d1e110",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/zai-chat.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/zai-chat.body",
|
||
"reviewScope": [
|
||
"thinking",
|
||
"max_tokens",
|
||
"tool_choice",
|
||
"stream",
|
||
"usage"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 7,
|
||
"text": "> Create a chat completion model that generates AI replies for given conversation messages. It supports multimodal inputs (text, images, audio, video, file), offers configurable parameters (like temperature, max tokens, tool use), and supports both streaming and non-streaming output modes.",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 38,
|
||
"text": " max tokens, tool use), and supports both streaming and non-streaming",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 63,
|
||
"text": " stream: false",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 64,
|
||
"text": " Stream Example:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 75,
|
||
"text": " stream: true",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 76,
|
||
"text": " Thinking Example:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 86,
|
||
"text": " thinking:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 88,
|
||
"text": " stream: true",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 103,
|
||
"text": " stream: true",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 165,
|
||
"text": " tool_choice: auto",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 345,
|
||
"text": " stream:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 354,
|
||
"text": " standard Event Stream. When the Event Stream ends, a `data: [DONE]`",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 356,
|
||
"text": " thinking:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 357,
|
||
"text": " $ref: '#/components/schemas/ChatThinking'",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "moonshot-chat",
|
||
"requestedUrl": "https://platform.moonshot.cn/docs/api/chat",
|
||
"observedAt": "2026-11-06T13:07:38.880185+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://platform.kimi.com/docs/api/chat",
|
||
"contentType": "text/markdown; charset=utf-8",
|
||
"contentLength": null,
|
||
"bytes": 62409,
|
||
"completeByReadLimit": true,
|
||
"sha256": "db19cb0b1047af8a9b534f0e67d0cedb529265527986ed31c873d09697558409",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/moonshot-chat.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/moonshot-chat.body",
|
||
"reviewScope": [
|
||
"prompt_cache_options",
|
||
"cache_write_tokens",
|
||
"cached_tokens",
|
||
"uncached_tokens"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 208,
|
||
"text": "> \"cache_write_tokens\": 256",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 229,
|
||
"text": "> data: {\"id\":\"chatcmpl-6adb0ef5ba679679914a2719\",\"object\":\"chat.completion.chunk\",\"created\":1792741109,\"model\":\"kimi-k3.1-pro\",\"choices\":[],\"usage\":{\"prompt_tokens\":309,\"completion_tokens\":101,\"total_tokens\":410,\"completion_tokens_details\":{\"reasoning_tokens\":71},\"prompt_tokens_details\":{\"cache_write_tokens\":256}}}",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 240,
|
||
"text": "> Cache Write 适用于 `kimi-k3.1-pro`、`kimi-k3.1-pro-highspeed` 和 `kimi-k3`。Kimi API 会对重复的请求前缀自动启用上下文缓存,命中部分以更低价格计费且响应更快。通过 `prompt_cache_options` 可以控制缓存写入行为:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 244,
|
||
"text": "> | `prompt_cache_options` | object | 上下文缓存写入选项。不传时默认开启缓存写入(`5m` 档) |",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 245,
|
||
"text": "> | `prompt_cache_options.mode` | `\"implicit\"` | 缓存写入模式,仅支持 `implicit`:自动将请求前缀写入缓存 |",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 246,
|
||
"text": "> | `prompt_cache_options.ttl` | `\"5m\"` \\| `\"1h\"` | 缓存写入的有效期,仅支持 `5m`、`1h` 两档(默认 `5m`),两档缓存相互独立 |",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 252,
|
||
"text": "> \"prompt_cache_options\": { \"mode\": \"implicit\", \"ttl\": \"1h\" }",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 270,
|
||
"text": "> | `usage.prompt_tokens_details.cached_tokens` | 命中缓存的 Token 数量(缓存读取) |",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 271,
|
||
"text": "> | `usage.prompt_tokens_details.cache_write_tokens` | 本次写入缓存的 Token 数量(缓存写入) |",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 273,
|
||
"text": "> `cached_tokens`、`cache_write_tokens` 与未缓存部分互斥,三者之和等于 `prompt_tokens`,即未缓存部分 = `prompt_tokens` − `cached_tokens` − `cache_write_tokens`。",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 483,
|
||
"text": "> data: {\"id\":\"chatcmpl-6adb0efa76cd871ffe47cb4d\",\"object\":\"chat.completion.chunk\",\"created\":1792741114,\"model\":\"kimi-k3.1-pro\",\"choices\":[],\"usage\":{\"prompt_tokens\":90,\"completion_tokens\":1139,\"total_tokens\":1229,\"completion_tokens_details\":{\"reasoning_tokens\":620},\"prompt_tokens_details\":{\"cache_write_tokens\":0}}}",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 863,
|
||
"text": " cached_tokens:",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 869,
|
||
"text": " 输入 Token 的分类明细。cached_tokens、cache_write_tokens 与未缓存部分互斥,三者之和等于",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 872,
|
||
"text": " cached_tokens:",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "bedrock-converse",
|
||
"requestedUrl": "https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html",
|
||
"observedAt": "2026-11-06T13:07:40.021384+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html",
|
||
"contentType": "text/markdown",
|
||
"contentLength": "33273",
|
||
"bytes": 33273,
|
||
"completeByReadLimit": true,
|
||
"sha256": "85ac5b5807d42802d888781df64c6ee6ee44c5b5261ced83691b6022cb21a59a",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/bedrock-converse.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/bedrock-converse.body",
|
||
"reviewScope": [
|
||
"Request Syntax",
|
||
"inferenceConfig",
|
||
"additionalModelRequestFields",
|
||
"cacheReadInputTokens",
|
||
"cacheWriteInputTokens"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 12,
|
||
"text": "You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the `promptVariables` field. You can append more messages to the prompt by using the `messages` field. If you use a prompt from Prompt management, you can't include the following fields in the request: `additionalModelRequestFields`, `inferenceConfig`, `system`, or `toolConfig`. Instead, these fields must be defined through Prompt management. For more info",
|
||
"snippetComplete": false
|
||
},
|
||
{
|
||
"line": 25,
|
||
"text": "## Request Syntax",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 33,
|
||
"text": " \"additionalModelRequestFields\": {{JSON value}},",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 40,
|
||
"text": " \"inferenceConfig\": { ",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 106,
|
||
"text": " ** [additionalModelRequestFields](#API_runtime_Converse_RequestSyntax) ** <a name=\"bedrock-runtime_Converse-request-additionalModelRequestFields\"></a>",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 107,
|
||
"text": "Additional inference parameters that the model supports, beyond the base set of inference parameters that `Converse` and `ConverseStream` support in the `inferenceConfig` field. For more information, see [Model parameters](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html). ",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 126,
|
||
"text": " ** [inferenceConfig](#API_runtime_Converse_RequestSyntax) ** <a name=\"bedrock-runtime_Converse-request-inferenceConfig\"></a>",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 127,
|
||
"text": "Inference parameters to pass to the model. `Converse` and `ConverseStream` support a base set of inference parameters. If you need to pass additional parameters that the model supports, use the `additionalModelRequestFields` request field. ",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 128,
|
||
"text": "Type: [InferenceConfiguration](API_runtime_InferenceConfiguration.md) object ",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 431,
|
||
"text": " \"cacheReadInputTokens\": number,",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 432,
|
||
"text": " \"cacheWriteInputTokens\": number,",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 553,
|
||
"text": " \"inferenceConfig\": {",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 598,
|
||
"text": "In the following example, the request passess a field (`top_k`) that the `Converse` field doesn't support. You pass the additional field in the `additionalModelRequestFields` field. The example also shows how to set the paths for the additional fields sent in the response from the model. ",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 619,
|
||
"text": " \"inferenceConfig\": {",
|
||
"snippetComplete": true
|
||
}
|
||
],
|
||
"notEvidenceOf": [
|
||
"live provider acceptance",
|
||
"all vendor features implemented",
|
||
"full website review"
|
||
]
|
||
},
|
||
{
|
||
"id": "azure-endpoints",
|
||
"requestedUrl": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/switching-endpoints",
|
||
"observedAt": "2026-11-06T13:07:40.454248+00:00",
|
||
"readLimitBytes": 3500000,
|
||
"status": 200,
|
||
"finalUrl": "https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/switching-endpoints",
|
||
"contentType": "text/markdown; charset=utf-8",
|
||
"contentLength": "6356",
|
||
"bytes": 6356,
|
||
"completeByReadLimit": true,
|
||
"sha256": "10920c1be8f3c1ac6d8f3a49f2ad292e2831905042ba95c38e4c0974befb13be",
|
||
"bodyPath": ".qa/official-first-system-audit-2026-11-06/official-public/azure-endpoints.body",
|
||
"attemptLedger": ".qa/official-first-system-audit-2026-11-06/official-public/attempts.json",
|
||
"authority": "vendor-owned-public-source",
|
||
"readStatus": "targeted-sections-reviewed",
|
||
"reviewPath": ".qa/official-first-system-audit-2026-11-06/official-public/azure-endpoints.body",
|
||
"reviewScope": [
|
||
"base_url",
|
||
"api_key",
|
||
"token_provider",
|
||
"deployment",
|
||
"v1/"
|
||
],
|
||
"reviewAnchors": [
|
||
{
|
||
"line": 65,
|
||
"text": "| ```python<br>import os<br>from openai import OpenAI<br><br>client = OpenAI(<br> api_key=os.getenv(\"OPENAI_API_KEY\")<br>)<br><br><br><br>``` | ```python<br>import os<br>from openai import OpenAI<br> <br>client = OpenAI(<br> api_key=os.getenv(\"AZURE_OPENAI_API_KEY\"), <br> base_url = \"https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/\"<br>)<br>``` |",
|
||
"snippetComplete": true
|
||
},
|
||
{
|
||
"line": 71,
|
||
"text": "| ```python<br>import os<br>from openai import OpenAI<br><br>client = OpenAI(<br> api_key=os.getenv(\"OPENAI_API_KEY\")<br>)<br><br><br><br><br><br><br><br><br>``` | ```python<br>from azure.identity import DefaultAzureCredential, get_bearer_token_provider<br>from openai import OpenAI<br><br>token_provider = get_bearer_token_provider(<br> DefaultAzureCredential(), \"https://ai.azure.com/.default\"<br>)<br><br>client = OpenAI(<br> 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<br>response = client.responses.create( <br> model=\"gpt-4.1-nano\", # Replace with your model deployment name <br> input=\"This is a test.\"<br>)<br><br>chat_completion = client.chat.completions.create(<br> model=\"gpt-4o\",<br> messages=\"<messages>\"<br>)<br><br>embedding = client.embeddings.create(<br> model=\"text-embedding-3-large\",<br> input=\"<input>\"<br>)<br>``` | ```python<br>response = client.responses.create( <br> model=\"gpt-4.1-nano\", # Replace with your mo",
|
||
"snippetComplete": false
|
||
},
|
||
{
|
||
"line": 91,
|
||
"text": "| ```python<br>inputs = [\"A\", \"B\", \"C\"] <br><br>embedding = client.embeddings.create(<br> input=inputs,<br> model=\"text-embedding-3-large\"<br>)<br><br><br>``` | ```python<br>inputs = [\"A\", \"B\", \"C\"] #max array size=2048<br><br>embedding = client.embeddings.create(<br> input=inputs,<br> model=\"text-embedding-3-large\" # This must match the custom deployment name you chose for your model.<br> # engine=\"text-embedding-ada-002\"<br>)<br><br>``` |",
|
||
"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 <key>` 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": "<urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>",
|
||
"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": "<urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>",
|
||
"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": "<urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>",
|
||
"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": "<urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>",
|
||
"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": "<urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>",
|
||
"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": "<urlopen error [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应,连接尝试失败。>",
|
||
"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"
|
||
]
|
||
}
|