// AI Platform Drift

Compliance API now retrieves local Cowork and Claude Code session transcripts

Claude Platform release notes · published 2026-08-17 00:11 UTC
WORTH KNOWING VERIFY_ONLY APISECURITY
WHAT CHANGEDThree new Compliance API endpoints launched August 11, 2026 in beta for Enterprise organizations: GET /v1/compliance/apps/sessions/local lists all local sessions, GET /v1/compliance/apps/sessions/local/{session_id} retrieves session metadata, and GET /v1/compliance/apps/sessions/local/{session_id}/messages returns the full transcript. These cover Cowork and Claude Code sessions running on user machines. Authentication uses existing Compliance Access Keys with read:compliance_user_data scope.
WHY IT MATTERSYour compliance tooling can now audit conversations that happen in desktop applications, not just API calls. If you already pull compliance data for governance or retention, these sessions were previously invisible and are now retrievable through the same authentication mechanism.
WHAT TO DOIf you run compliance exports or audits, add these three endpoints to your retrieval jobs. Test with GET /v1/compliance/apps/sessions/local using your existing Compliance Access Key to confirm scope and verify the transcript format matches your storage schema.
Model-reported confidence 85% (not measured accuracy) Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
 https://platform.claude.com/docs/en/release-notes/overview#april-14-2026
 Tue, 14 Apr 2026 00:00:00 GMT
 
-We announced the deprecation of the Claude Sonnet 4 model (claude-sonnet-4-20250514) and the Claude Opus 4 model (claude-opus-4-20250514), with retirement on the Claude API scheduled for June 15, 2026. We recommend migrating to Claude Sonnet 4.6 and Claude Opus 4.8 respectively. Read more in model deprecations.
+We announced the deprecation of the Claude Sonnet 4 model (claude-sonnet-4-20250514) and the Claude Opus 4 model (claude-opus-4-20250514), with retirement on the Claude API scheduled for June 15, 2026. We recommend migrating to Claude Sonnet 4.6 and Claude Opus 4.8 respectively. Read more in Model deprecations.
 
 ## Claude Platform release notes — April 16, 2026
 https://platform.claude.com/docs/en/release-notes/overview#april-16-2026
@@
 
 Some customers might encounter 429 (rate_limit_error) errors following a sharp increase in API usage due to acceleration limits on the API. Previously, 529 (overloaded_error) errors would occur in similar scenarios.
 
+## Claude Platform release notes — August 11, 2026
+https://platform.claude.com/docs/en/release-notes/overview#august-11-2026
+Tue, 11 Aug 2026 00:00:00 GMT
+
+The Compliance API now returns transcripts of Cowork and Claude Code sessions that run on your users' machines, in beta for Claude Enterprise organizations. GET /v1/compliance/apps/sessions/local lists sessions across your organization, GET /v1/compliance/apps/sessions/local/{session_id} retrieves one session's metadata, and GET /v1/compliance/apps/sessions/local/{session_id}/messages returns its transcript, all with your existing Compliance Access Key and the read:compliance_user_data scope. See Retrieve local sessions.
+
 ## Claude Platform release notes — August 12, 2025
 https://platform.claude.com/docs/en/release-notes/overview#august-12-2025
 Tue, 12 Aug 2025 00:00:00 GMT
@@
 Wed, 05 Aug 2026 00:00:00 GMT
 
 Inference hooks are now in beta for Claude Enterprise organizations. Point Claude at your organization's AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server's allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance Activity Feed. See Inference hooks.
-We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805). All requests to this model will now return an error. We recommend upgrading to Claude Opus 5. Researchers can request ongoing access through the External Researcher Access Program.
+We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805). All requests to this model on the Claude API will now return an error. We recommend upgrading to Claude Opus 5. Researchers can request ongoing access through the External Researcher Access Program.
 
+## Claude Platform release notes — August 7, 2026
+https://platform.claude.com/docs/en/release-notes/overview#august-7-2026
+Fri, 07 Aug 2026 00:00:00 GMT
+
+You can now set a budget on a Claude Managed Agents session: a hard cap on the session's spend, priced at public list rates. A session that reaches its budget pauses with the budget_reached stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments accept the same budget and apply it to each session they start. See Session budgets.
+You can now give a Claude Managed Agents session an advisor: a model at least as capable as the agent's own that the session's primary thread can consult mid-turn for strategic guidance. Configure it as a {"type": "advisor"} entry in the agent's multiagent roster, naming the model to consult. See Give the session an advisor.
+You can now control where model inference runs for a Claude Managed Agents agent. Set inference_geo inside the model object when you create the agent, or override it for a single session. See Data residency for the available geos and pricing.
+Claude Managed Agents sessions can now load skills from a GitHub repository. When a session mounts a repository, any skills in its root .claude/skills directory are discovered automatically at session start and available to the agent for that session.
+
 ## Claude Platform release notes — August 8, 2025
 https://platform.claude.com/docs/en/release-notes/overview#august-8-2025
 Fri, 08 Aug 2025 00:00:00 GMT
@@
 Thu, 19 Feb 2026 00:00:00 GMT
 
 We've launched automatic caching for the Messages API. Add a single cache_control field to your request body and the system automatically caches the last cacheable block, moving the cache point forward as conversations grow. No manual breakpoint management required. Works alongside existing block-level cache control for fine-grained optimization. Available on the Claude API and Microsoft Foundry (preview). Learn more in Prompt caching.
-We've retired the Claude Sonnet 3.7 model (claude-3-7-sonnet-20250219) and the Claude Haiku 3.5 model (claude-3-5-haiku-20241022). All requests to these models will now return an error. We recommend upgrading to Claude Sonnet 4.6 and Claude Haiku 4.5 respectively. Researchers can request ongoing access through the External Researcher Access Program.
+We've retired the Claude Sonnet 3.7 model (claude-3-7-sonnet-20250219) and the Claude Haiku 3.5 model (claude-3-5-haiku-20241022). All requests to Claude Sonnet 3.7 will now return an error. Requests to Claude Haiku 3.5 on the Claude API will now return an error; it remains available on Amazon Bedrock and Google Cloud. We recommend upgrading to Claude Sonnet 4.6 and Claude Haiku 4.5 respectively. Researchers can request ongoing access through the External Researcher Access Program.
 We announced the deprecation of the Claude Haiku 3 model (claude-3-haiku-20240307), with retirement scheduled for April 20, 2026. We recommend migrating to Claude Haiku 4.5. Read more in Model deprecations.
 
 ## Claude Platform release notes — February 24th, 2025
@@
 https://platform.claude.com/docs/en/release-notes/overview#june-15-2026
 Mon, 15 Jun 2026 00:00:00 GMT
 
-We've retired the Claude Sonnet 4 model (claude-sonnet-4-20250514) and the Claude Opus 4 model (claude-opus-4-20250514). All requests to these models will now return an error. We recommend upgrading to Claude Sonnet 4.6 and Claude Opus 4.8 respectively. Researchers can request ongoing access through the External Researcher Access Program.
+We've retired the Claude Sonnet 4 model (claude-sonnet-4-20250514) and the Claude Opus 4 model (claude-opus-4-20250514). All requests to these models on the Claude API will now return an error. We recommend upgrading to Claude Sonnet 4.6 and Claude Opus 4.8 respectively. Researchers can request ongoing access through the External Researcher Access Program.
 
 ## Claude Platform release notes — June 18, 2026
 https://platform.claude.com/docs/en/release-notes/overview#june-18-2026
@@
 https://platform.claude.com/docs/en/release-notes/overview#june-5-2026
 Fri, 05 Jun 2026 00:00:00 GMT
 
-We announced the deprecation of the Claude Opus 4.1 model (claude-opus-4-1-20250805), with retirement on the Claude API scheduled for August 5, 2026. We recommend migrating to Claude Opus 4.8. Read more in model deprecations.
+We announced the deprecation of the Claude Opus 4.1 model (claude-opus-4-1-20250805), with retirement on the Claude API scheduled for August 5, 2026. We recommend migrating to Claude Opus 4.8. Read more in Model deprecations.
 
 ## Claude Platform release notes — June 9, 2026
 https://platform.claude.com/docs/en/release-notes/overview#june-9-2026
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.45
triage reasoningMultiple new API capabilities, features, and endpoints added; model availability clarified across platforms.
signalsnew API endpoints added (Compliance API for local sessions) · new feature: Claude Managed Agents session budgets with hard spend caps · new feature: Claude Managed Agents advisor model capability · new feature: data residency control (inference_geo) for agents · new feature: GitHub repository skill loading for agents · model retirement clarification (Claude Haiku 3.5 remains on Bedrock/GCP) · multiple new release notes entries (Aug 7, Aug 11, 2026)
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)