deepagents-code==0.1.65

Features

• Added Python extension support, including discovery, configuration and loading, runtime hosting, and trust and inspection UX (#5631, #5632, #5633, #5634)
• Added a /summarization-model command and model picker for configuring the summarization model (#5884, #5932)
• Added support for optional extra uninstall commands (#5875)
• Added an option to show visible reasoning (#5887)

Bug Fixes

• Improved model and task reliability by retrying interrupted model streams, recovering stale pending work before compaction, and isolating parallel task failures (#5905, #5909, #5954)
• Improved server restart handling by waiting for graph readiness before continuing (#5947)
• Capped MCP tool names for provider compatibility (#5953)
• Fixed Auto approval gate path expansion handling and now records Auto classifier deadline misses as traced errors (#5941, #5944)
• Completed ASCII UI fallbacks and hid inactive F2 tool hints (#5930, #5939)
• Isolated debug logs by thread (#5921)
• Updated rubric grader model changes to apply without a restart (#5885)

---

Internal maintainers: Alexander Olsen (@aolsenjazz), Mason Daugherty (@mdrxy)

Released by: Mason Daugherty (@mdrxy)

Git log since deepagents-code==0.1.64

This commit history includes changes to this package. Commits are listed newest first.

• a233ded release(deepagents-code): 0.1.65 (#5929)
• 0ac6ee4 docs(code): remove streaming retry design (#5957)
• 0eb8e57 fix(code): cap MCP tool names for provider compatibility (#5953)
• e0a474f fix(code): isolate parallel task failures (#5954)
• 46dea07 fix(code): guard path expansion in the Auto approval gate (#5941)
• 9a643c7 fix(code): record Auto classifier deadline as a traced error (#5944)
• 358bc33 fix(code): wait for graph readiness after server restart (#5947)
• f90d4fe feat(code): open summarization model picker (#5932)
• fd7ba1a fix(code): hide inactive F2 tool hint (#5939)
• e9a1623 fix(code): complete ASCII UI fallbacks (#5930)
• 77b0f01 chore(deps): raise dependency minimums for all (#5936)
• 457ac43 feat(code): optionally show visible reasoning (#5887)
• 4f34c51 feat(code): add /summarization-model (#5884)
• 213f0c8 fix(code): recover stale pending work before compaction (#5909)
• d36f226 feat(code): add optional extra uninstall commands (#5875)
• cf8cbcd docs(code): remove managed configuration from README (#5931)
• 4358cce fix(code): isolate debug logs by thread (#5921)
• dfcd941 fix(code): retry interrupted model streams (#5905)
• 428e760 fix(code): update rubric grader model without restart (#5885)