{"id":"src_reidosAHay-vJROI8wSJB","slug":"claude-platform-releases","name":"Claude Platform","type":"scrape","url":"https://platform.claude.com/docs/en/release-notes/overview","orgId":"org_HXldkKAl-bZUWW6lNnELP","productId":"prod_BE0qCzI8J0bhXsJUbEhdR","productSlug":"claude-platform","org":{"id":"org_HXldkKAl-bZUWW6lNnELP","slug":"anthropic","name":"Anthropic"},"isPrimary":false,"isHidden":false,"discovery":"curated","metadata":"{\"noFeedFound\":true,\"sourceActor\":{\"nextAlarmAt\":null,\"lastAlarmAt\":\"2026-10-08T12:57:51.959Z\",\"managed\":false},\"markdownUrl\":\"https://platform.claude.com/docs/en/release-notes/overview.md\"}","notice":null,"kind":"platform","stars":null,"starsFetchedAt":null,"releaseCount":598,"releasesLast30Days":30,"avgReleasesPerWeek":8.9,"latestVersion":null,"latestDate":"2026-10-08T00:00:00.000Z","changelogUrl":null,"hasChangelogFile":false,"lastFetchedAt":"2026-10-06T13:03:47.781Z","lastPolledAt":"2026-09-17T15:04:57.295Z","changeDetectedAt":null,"trackingSince":"2024-05-10T00:00:00.000Z","releases":[{"id":"rel_SDGR7dKm5FQtvL2xodEPd","version":null,"type":"feature","title":"Compliance API now returns chats from unified Claude experience","summary":"Compliance API chat endpoints now also return chats from the unified Claude experience, in beta for Claude Enterprise organizations, using the existing Compliance Access Key.","titleGenerated":"Claude Platform Compliance API returns chats from unified Claude experience","titleShort":"Compliance API covers unified Claude chats","breaking":"none","importance":3,"content":"The Compliance API chat endpoints now also return chats from the unified Claude experience, in beta for Claude Enterprise organizations, with your existing Compliance Access Key.","publishedAt":"2026-10-08T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.264Z","url":"https://platform.claude.com/docs/en/release-notes/overview#compliance-api-now-returns-chats-from-unified-claude-experie","media":[],"coverageCount":0},{"id":"rel_gMa7-iwVsXI741L1RipmZ","version":null,"type":"feature","title":"Claude Managed Agents: web_fetch now restricted to URLs in prior context","summary":"The web_fetch tool in Claude Managed Agents now fetches only URLs that have already appeared in the session, via user messages, web_search results, or previously fetched pages; URLs appearing only in Claude's output, system prompt, attached documents, or tool outputs return a url_not_in_prior_context error. The restriction is intended to reduce data exfiltration risk.","titleGenerated":"Claude Managed Agents restricts web_fetch to URLs already in session context","titleShort":"web_fetch now limited to URLs seen in session context","breaking":"major","importance":4,"content":"The `web_fetch` tool in Claude Managed Agents now fetches only URLs that have already appeared in the session (in user messages, web_search results, or previously fetched pages). URLs appearing only in Claude's output, system prompt, attached documents, or tool outputs return `url_not_in_prior_context` error. This reduces data exfiltration risk.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.580Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-managed-agents-web-fetch-now-restricted-to-urls-in-pr","media":[],"coverageCount":0},{"id":"rel_FfZPx9ngV3JO58l2mJlVD","version":null,"type":"feature","title":"Claude Managed Agents: web tools now respect allowed_hosts in limited networking","summary":"In Claude Managed Agents, cloud environments with limited networking now apply allowed_hosts to the web_search and web_fetch tools: web_fetch returns a url_not_allowed error for non-matching hosts, web_search omits their results, and neither tool returns results when allowed_hosts lists no hosts.","titleGenerated":"Claude Managed Agents web tools now respect allowed_hosts in limited networking","titleShort":"Web tools enforce allowed_hosts under limited networking","breaking":"major","importance":3,"content":"In Claude Managed Agents, cloud environments with `limited` networking now apply `allowed_hosts` to `web_search` and `web_fetch` tools. `web_fetch` calls for URLs on hosts not matching `allowed_hosts` return `url_not_allowed` error. `web_search` omits results from such hosts. When `allowed_hosts` lists no hosts, neither tool returns results.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.580Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-managed-agents-web-tools-now-respect-allowed-hosts-in","media":[],"coverageCount":0},{"id":"rel_p6unnXU1_SAGZsa-4LmOO","version":null,"type":"feature","title":"Prompt cache reads pricing reduced for Claude Sonnet 5.5","summary":"Prompt cache reads on Claude Sonnet 5.5 drop from $0.20 to $0.10 USD per million tokens, now 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged.","titleGenerated":"Claude Sonnet 5.5 prompt cache reads halved to $0.10 per million tokens","titleShort":"Prompt cache reads halved to $0.10 per million tokens","breaking":"none","importance":4,"content":"Lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens (0.05x the base input price instead of 0.1x). Cache writes and all other prices unchanged.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.264Z","url":"https://platform.claude.com/docs/en/release-notes/overview#prompt-cache-reads-pricing-reduced-for-claude-sonnet-5-5","media":[],"coverageCount":0},{"id":"rel_cgvtOWBpFnlY9QbgcuTNJ","version":null,"type":"feature","title":"Claude Haiku 5.5 launched with 1M token context and adaptive thinking","summary":"Claude Haiku 5.5 (claude-haiku-5-5) is tuned for high-volume, latency-sensitive work with a 1M token context window, 128k max output tokens, and adaptive thinking with an effort parameter. It is available on Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.","titleGenerated":"Claude Haiku 5.5 launches with 1M token context and adaptive thinking","titleShort":"Claude Haiku 5.5: 1M context, adaptive thinking","breaking":"none","importance":5,"content":"Launched Claude Haiku 5.5 (`claude-haiku-5-5`), tuned for high-volume and latency-sensitive work. Features include 1M token context window, 128k max output tokens, and adaptive thinking with effort parameter. Available on Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.264Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-haiku-5-5-launched-with-1m-token-context-and-adaptive","media":[],"coverageCount":0},{"id":"rel_E34fpXRavRePJrW1RZ4AU","version":null,"type":"feature","title":"Browser and computer use SDK toolsets now available in beta","summary":"Python and TypeScript SDKs now include beta classes for the browser use and computer use tools; subclass one and write a method per tool against your own browser or desktop automation, while the SDK runs the tool loop, URL and file policies, and approval callback.","titleGenerated":"Claude Platform beta adds browser and computer use SDK toolsets","titleShort":"Browser and computer use toolsets land in SDKs","breaking":"none","importance":3,"content":"Python and TypeScript SDKs now include classes in beta for the browser use tool and computer use tool. Subclass one and write one method per tool against your own browser or desktop automation. SDK runs the tool loop, URL and file policies, and approval callback.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.264Z","url":"https://platform.claude.com/docs/en/release-notes/overview#browser-and-computer-use-sdk-toolsets-now-available-in-beta","media":[],"coverageCount":0},{"id":"rel_2dy-rRbh8LQDR6tR2Ay5i","version":null,"type":"feature","title":"Claude Max and Team plans now include monthly API credits","summary":"Claude Max and Team plans now include monthly API credits, claimable through the API credits for subscribers feature.","titleGenerated":"Claude Max and Team plans now include monthly API credits","titleShort":"Max and Team plans get monthly API credits","breaking":"none","importance":3,"content":"Claude Max and Team plans now include monthly API credits. Users can claim them through the API credits for subscribers feature.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.264Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-max-and-team-plans-now-include-monthly-api-credits","media":[],"coverageCount":0},{"id":"rel_5IpQ6SEMuf3tgNyigKB3D","version":null,"type":"feature","title":"Models API now reports server tools capabilities","summary":"Added capabilities.server_tools to the Models API, so GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts web search and code execution tools. capabilities.server_tools.code_execution indicates code execution tool support.","titleGenerated":"Claude Platform Models API now reports server tools capabilities","titleShort":"Models API reports server tools capabilities per model","breaking":"none","importance":3,"content":"Added `capabilities.server_tools` to the Models API. `GET /v1/models` and `GET /v1/models/{model_id}` now report whether each model accepts web search and code execution tools. `capabilities.server_tools.code_execution` indicates code execution tool support.","publishedAt":"2026-10-06T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:09.580Z","url":"https://platform.claude.com/docs/en/release-notes/overview#models-api-now-reports-server-tools-capabilities","media":[],"coverageCount":0},{"id":"rel_zNi3h_2__g7LdlHx2dC5T","version":null,"type":"feature","title":"Models API: capabilities.thinking.types.disabled","summary":"Added capabilities.thinking.types.disabled to the Models API, so GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: \"disabled\"}.","titleGenerated":"Claude Models API reports whether models accept thinking disabled","titleShort":"Models API now reports thinking-disabled support","breaking":"none","importance":2,"content":"Added `capabilities.thinking.types.disabled` to the Models API. `GET /v1/models` and `GET /v1/models/{model_id}` now report whether each model accepts `thinking: {type: \"disabled\"}`, which turns thinking off.","publishedAt":"2026-10-05T00:00:00.000Z","fetchedAt":"2026-10-07T01:06:47.780Z","url":"https://platform.claude.com/docs/en/release-notes/overview#models-api-capabilities-thinking-types-disabled","media":[],"coverageCount":0},{"id":"rel_L4S7MkNkL30fPiNOH7FdH","version":null,"type":"feature","title":"Models API: model line field added","summary":"Added a `line` field to the Models API. `GET /v1/models` and `GET /v1/models/{model_id}` now return the model line each model belongs to (e.g., Claude...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"Added a `line` field to the Models API. `GET /v1/models` and `GET /v1/models/{model_id}` now return the model line each model belongs to (e.g., Claude Opus 4.5 and Claude Opus 4.6 both report `opus`). Use `line` to group models without parsing their IDs. `line` is `null` for models that belong to no line.","publishedAt":"2026-10-01T00:00:00.000Z","fetchedAt":"2026-10-06T13:03:44.453Z","url":"https://platform.claude.com/docs/en/release-notes/overview#models-api-model-line-field-added","media":[],"coverageCount":0},{"id":"rel_9R2gTeUiKk3UCYXaK7v_z","version":null,"type":"feature","title":"Claude Sonnet 4.5 deprecation announced","summary":"Claude Sonnet 4.5 (claude-sonnet-4-5-20250929) is deprecated with retirement scheduled for November 30, 2026. Users are recommended to migrate to Claude Sonnet 5.5.","titleGenerated":"Anthropic deprecates Claude Sonnet 4.5, retirement set for November 30, 2026","titleShort":"Claude Sonnet 4.5 deprecated; retire Nov 30, 2026","breaking":"minor","importance":4,"content":"Claude Sonnet 4.5 (`claude-sonnet-4-5-20250929`) is deprecated with retirement scheduled for November 30, 2026. Users are recommended to migrate to Claude Sonnet 5.5. See [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).","publishedAt":"2026-09-30T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.868Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-sonnet-4-5-deprecation-announced","media":[],"coverageCount":0},{"id":"rel_g0f71kC67icmArn_JYIkv","version":null,"type":"feature","title":"Claude Sonnet 5.5 launched","summary":"Claude Sonnet 5.5 (claude-sonnet-5-5) is available on the Claude API, Amazon Bedrock, AWS, Google Cloud, and Microsoft Foundry with a 1M token context window and 128k max output tokens. Code written for Claude Sonnet 5 may break in five ways: disabling up-front thinking now requires thinking: {\"type\": \"between_tools\"} instead of \"disabled\" at effort high or below, forced tool use returns a 400 error, the computer_20251124 computer use tool isn't accepted on Claude API and Google Cloud, and the advisor tool rejects Opus 4.8, 4.7, and Sonnet 5 as advisors.","titleGenerated":"Claude Sonnet 5.5 launches with 1M context and five breaking API changes","titleShort":"Sonnet 5.5 ships; five ways Sonnet 5 code breaks","breaking":"major","importance":4,"content":"Claude Sonnet 5.5 (`claude-sonnet-5-5`) is now available on the Claude API, Amazon Bedrock, AWS, Google Cloud, and Microsoft Foundry. The model supports a 1M token context window and 128k max output tokens. Code written for Claude Sonnet 5 may break on Claude Sonnet 5.5 in five ways: turning off up-front thinking requires `thinking: {\"type\": \"between_tools\"}` instead of `\"disabled\"` at effort `high` or below; forced tool use (`tool_choice` types `any` and `tool`) returns a 400 error; thinking blocks are tied to the model and conversation; the earlier `computer_20251124` computer use tool isn't accepted on Claude API and Google Cloud; the advisor tool rejects Claude Opus 4.8, 4.7, and Sonnet 5 as advisors. Thinking blocks produced by Sonnet 5.5 work only in the account that produced them or linked accounts. See [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5) and [migration guide](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide).","publishedAt":"2026-09-28T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.868Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-sonnet-5-5-launched","media":[],"coverageCount":0},{"id":"rel_1PUrf3EkTDtQXssVC3azL","version":null,"type":"feature","title":"Compliance API updates and refusal billing changes","summary":"Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook, and billing has resumed for refusals arriving before any output when stop_details.category is \"bio\", \"frontier_llm\", or \"reasoning_extraction\". The Compliance API Activity Feed no longer returns file names, project document names, or artifact titles.","titleGenerated":"Claude Platform Compliance API exits beta, resumes refusal billing","titleShort":"Compliance API exits beta; refusal billing resumes","breaking":"major","importance":3,"content":"Resuming billing for refusals that arrive before any output when `stop_details.category` is `\"bio\"`, `\"frontier_llm\"`, or `\"reasoning_extraction\"`. The Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook. The Compliance API Activity Feed no longer returns file names, project document names, or artifact titles.","publishedAt":"2026-09-24T00:00:00.000Z","fetchedAt":"2026-10-02T11:46:01.701Z","url":"https://platform.claude.com/docs/en/release-notes/overview#compliance-api-updates-and-refusal-billing-changes","media":[],"coverageCount":0},{"id":"rel_d6ctpe8AEIcd36ETVkLxa","version":null,"type":"feature","title":"Refusal billing changes and Compliance API updates","summary":"Billing for refusals before any output resumes for stop_details.category values \"bio\", \"frontier_llm\", and \"reasoning_extraction\", while mid-stream refusals were already billed. Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook, and Activity Feed no longer returns file names, project document names, or artifact titles — filename and title are now empty or omitted, requiring a Compliance Access Key with read:compliance_user_data scope to look up names by ID.","titleGenerated":"Claude Platform resumes refusal billing and ends Compliance API data exposure","titleShort":"Refusal billing resumes; Activity Feed drops file titles","breaking":"major","importance":4,"content":"Billing for refusals before any output resumes for `stop_details.category` values `\"bio\"`, `\"frontier_llm\"`, and `\"reasoning_extraction\"`. Mid-stream refusals were already billed. Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook. Activity Feed no longer returns file names, project document names, or artifact titles; `filename` and `title` fields are now empty or omitted. Use a Compliance Access Key with `read:compliance_user_data` scope to look up names by ID.","publishedAt":"2026-09-24T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.868Z","url":"https://platform.claude.com/docs/en/release-notes/overview#refusal-billing-changes-and-compliance-api-updates","media":[],"coverageCount":0},{"id":"rel_m27GSHS-2hFI70Vh82Fbq","version":null,"type":"feature","title":"Cache diagnostics out of beta","summary":"Cache diagnostics is out of beta on the Claude API and no longer requires the cache-diagnosis-2026-04-07 beta header; include the diagnostics object on a Messages request to opt in. Responses from POST /v1/messages now always include the diagnostics field, which is null when the request did not include the diagnostics object.","titleGenerated":"Claude Platform cache diagnostics exits beta with new always-on diagnostics field","titleShort":"Cache diagnostics out of beta; diagnostics field always returned","breaking":"none","importance":3,"content":"Cache diagnostics is out of beta on the Claude API and no longer requires the `cache-diagnosis-2026-04-07` beta header. Include the `diagnostics` object on a Messages request to opt in. Responses from `POST /v1/messages` now always include the `diagnostics` field, which is `null` when the request did not include the `diagnostics` object.","publishedAt":"2026-09-23T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.868Z","url":"https://platform.claude.com/docs/en/release-notes/overview#cache-diagnostics-out-of-beta","media":[],"coverageCount":0},{"id":"rel_KFYP_BzxXt2GK7j_Lhx0L","version":null,"type":"feature","title":"Claude Opus 5.5 launched","summary":"Claude Opus 5.5 (claude-opus-5-5) ships with a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking at $4 / $20 per MTok, down from Opus 5's $5 / $25, across Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry. Thinking can no longer be disabled and tool_choice types any and tool now return 400 errors; computer use requires computer_toolset_20260801, and mid-conversation system messages can define tools via the inline-tools-2026-09-15 beta header.","titleGenerated":"Anthropic launches Claude Opus 5.5 with 1M context and always-on adaptive thinking","titleShort":"Opus 5.5: 1M context, always-on thinking, $4/$20 pricing","breaking":"major","importance":5,"content":"Claude Opus 5.5 (`claude-opus-5-5`) is available for long-running agentic coding and knowledge work with a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking at $4 / $20 USD per MTok (vs $5 / $25 for Opus 5). Available on Claude API, Amazon Bedrock, AWS, Google Cloud, and Microsoft Foundry. Thinking cannot be disabled: `thinking: {\"type\": \"disabled\"}` and `thinking: {\"type\": \"enabled\", ...}` return 400 errors. `tool_choice` types `any` and `tool` also return 400 errors; use `auto` with strict tool use. Computer use requires `computer_toolset_20260801` on Claude API and Google Cloud; earlier `computer_20251124` tool returns 400 error. Fast mode (research preview) is available. Tools can now be defined inside mid-conversation system messages (beta, `inline-tools-2026-09-15` header). See [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5) and [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).","publishedAt":"2026-09-22T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.868Z","url":"https://platform.claude.com/docs/en/release-notes/overview#claude-opus-5-5-launched","media":[],"coverageCount":0},{"id":"rel_FMZ5Ha_F4BKLXtArgsj87","version":null,"type":"feature","title":"Mid-conversation tools: inline tool definitions and MCP toolsets","summary":"With the inline-tools-2026-09-15 beta header, tools can be defined inside a mid-conversation system message via a tool_addition block carrying the tool's full definition, so a tool can be added, have its schema changed, or be moved to a newer server version without editing tools or invalidating the prompt cache. The same header covers adding and removing tools by reference, and the MCP connector's mcp-client-2026-09-15 header allows an MCP toolset definition with each server's fetched tool list recorded in an mcp_tool_listing block.","titleGenerated":"Claude API beta adds inline tool definitions in mid-conversation messages","titleShort":"Tools defs inline in mid-conversation; MCP toolsets via reference","breaking":"none","importance":3,"content":"Tools can now be defined inside a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), in beta on the Claude API with the `inline-tools-2026-09-15` beta header. A `tool_addition` block can carry the tool's full definition (`tool: {\"type\": \"tool_definition\", \"definition\": {...}}`), allowing you to add a tool, change its schema, or move a server tool to a newer version without editing `tools` or invalidating the prompt cache. The same header covers adding and removing tools by reference. With the MCP connector's `mcp-client-2026-09-15` beta header, the definition can be an MCP toolset, and a response records each server's fetched tool list in an `mcp_tool_listing` block.","publishedAt":"2026-09-22T00:00:00.000Z","fetchedAt":"2026-09-24T13:18:55.753Z","url":"https://platform.claude.com/docs/en/release-notes/overview#mid-conversation-tools-inline-tool-definitions-and-mcp-tools","media":[],"coverageCount":0},{"id":"rel_mgGyBqfZXLrXoDWlMcWgx","version":null,"type":"feature","title":"Compliance API local sessions now include Claude in Chrome","summary":"Compliance API local session endpoints now return transcripts of Claude in Chrome sessions, identified by a product_surface value of claude_in_chrome. The capability is in beta for Claude Enterprise organizations and uses the existing Compliance Access Key and read:compliance_user_data scope.","titleGenerated":"Claude Platform Compliance API local sessions now include Claude in Chrome","titleShort":"Compliance API spans Claude in Chrome sessions","breaking":"none","importance":3,"content":"The Compliance API local session endpoints now return transcripts of Claude in Chrome sessions (`product_surface` value `claude_in_chrome`), in beta for Claude Enterprise organizations, with existing Compliance Access Key and `read:compliance_user_data` scope.","publishedAt":"2026-09-18T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.904Z","url":"https://platform.claude.com/docs/en/release-notes/overview#compliance-api-local-sessions-now-include-claude-in-chrome","media":[],"coverageCount":0},{"id":"rel_VmFeFueHVuiR217xy9tR9","version":null,"type":"feature","title":"Cache diagnostics response field always included","summary":"Responses to requests sending the `cache-diagnosis-2026-04-07` beta header now always include the `diagnostics` field, which is null when the request did not include the diagnostics object; previously the field was omitted in that case.","titleGenerated":"Claude Platform cache diagnostics responses always include diagnostics field","titleShort":"Cache diagnostics field now always present, null when unused","breaking":"minor","importance":2,"content":"For cache diagnostics, responses to requests sending the `cache-diagnosis-2026-04-07` beta header now always include the `diagnostics` field, which is `null` when the request did not include the `diagnostics` object. Previously the field was omitted in that case.","publishedAt":"2026-09-18T00:00:00.000Z","fetchedAt":"2026-10-02T11:38:13.904Z","url":"https://platform.claude.com/docs/en/release-notes/overview#cache-diagnostics-response-field-always-included","media":[],"coverageCount":0},{"id":"rel_cTZffEnyGLpDpQHKP0Pv5","version":null,"type":"feature","title":"Compliance API: Claude in Chrome sessions support","summary":"The Compliance API local session endpoints now return transcripts of Claude in Chrome sessions (`product_surface` value `claude_in_chrome`), in beta f...","titleGenerated":null,"titleShort":null,"breaking":"unknown","importance":null,"content":"The Compliance API local session endpoints now return transcripts of Claude in Chrome sessions (`product_surface` value `claude_in_chrome`), in beta for Claude Enterprise organizations. Uses existing Compliance Access Key and `read:compliance_user_data` scope.","publishedAt":"2026-09-18T00:00:00.000Z","fetchedAt":"2026-09-22T13:51:54.181Z","url":"https://platform.claude.com/docs/en/release-notes/overview#compliance-api-claude-in-chrome-sessions-support","media":[],"coverageCount":0}],"pagination":{"nextCursor":"2026-09-18T00:00:00.000Z|2026-09-22T13:51:54.181Z|rel_cTZffEnyGLpDpQHKP0Pv5","limit":20},"summaries":{"rolling":{"windowDays":90,"summary":"Claude Platform shipped a major model refresh and expanded its agentic capabilities. Opus 4.7 arrived with improved reasoning and broke API compatibility, requiring migration from earlier versions; Sonnet 4.6 landed as a faster balanced option with extended thinking and 1M context now generally available at standard pricing. The platform grew its agent-building toolkit with Managed Agents (fully sandboxed autonomous operation), an advisor tool (pairing fast executors with high-intelligence guidance), and the `ant` CLI for streamlined local development. Automatic caching simplified request optimization, the compaction API enabled effectively infinite conversations through server-side summarization, and capability discovery moved into the Models API itself.","releaseCount":15,"generatedAt":"2026-04-16T14:57:46.787Z"},"monthly":[{"year":2026,"month":3,"summary":"Extended output and expanded context reached general availability this month. The 1M token context window graduated to standard pricing for Claude Opus 4.6 and Sonnet 4.6, with the media limit per request raised to 600 images or PDFs. The max_tokens cap on Batches API grew to 300k for longer single-turn outputs, while a new display field for extended thinking lets developers omit thinking blocks for faster streaming. The Models API gained capability fields exposing max_input_tokens, max_tokens, and a capabilities object for runtime model discovery. The 1M context beta for Sonnet 4.5 and 4 retires April 30, after which requests exceeding 200k tokens will error on those models.","releaseCount":4,"generatedAt":"2026-04-10T13:55:29.604Z"}]}}