Releases: langchain-ai/deepagents
langchain-runloop==0.0.3
Changes since langchain-runloop==0.0.2
release(sdk): bump partner packages (daytona 0.0.3, modal 0.0.2, runloop 0.0.3) (#1689)
release(sdk): bump deepagents to 0.4.7 (#1688)
feat(infra): add fireworks as eval provider (#1684)
release(sdk): bump deepagents to 0.4.6 (#1677)
chore: bump lock file (#1674)
chore(sdk): expand eval matrix and fix model name access for groq (#1623)
release(deepagents): 0.4.5 (#1622)
chore(sdk): expand eval model matrix to 28 models across 7 providers (#1617)
chore: standardize makefile type targets/ add type CI check (#1581)
test: add standard tests for runloop and modal (#1537)
release(deepagents): 0.4.4 (#1519)
release(deepagents): 0.4.3 (#1465)
fix(sdk): guard timeout forwarding for older backend packages (#1461)
chore(deepagents): bump min version for langchain-anthropic (#1431)
feat(sdk): add per-command timeout override to execute() (#1154)
chore: auto-generate makefile help from target annotations (#1417)
chore: revert SDK version following yank (#1407)
chore: enable type checking for all other packages (#1365)
release(sdk): 0.4.2 (#1312)
chore: rollback uv workspace migration, restore per-package lockfiles (#1278)
chore: migrate to uv workspace (#1264)
chore(deps): bump the uv group across 2 directories with 1 update (#1245)
chore: rename master to main (#984)
release(sdk): 0.4.0 (#1236)
release(deepagents): 0.4 (#1234)
Thanks to our contributors: Sydney Runkle (@sydney-runkle), Eugene Yurtsev (@eyurtsev), Mason Daugherty (@mdrxy)
langchain-modal==0.0.2
Changes since langchain-modal==0.0.1
release(sdk): bump partner packages (daytona 0.0.3, modal 0.0.2, runloop 0.0.3) (#1689)
release(sdk): bump deepagents to 0.4.7 (#1688)
feat(infra): add fireworks as eval provider (#1684)
release(sdk): bump deepagents to 0.4.6 (#1677)
chore: bump lock file (#1674)
chore(sdk): expand eval matrix and fix model name access for groq (#1623)
release(deepagents): 0.4.5 (#1622)
chore(sdk): expand eval model matrix to 28 models across 7 providers (#1617)
chore: standardize makefile type targets/ add type CI check (#1581)
test: add standard tests for runloop and modal (#1537)
release(deepagents): 0.4.4 (#1519)
release(deepagents): 0.4.3 (#1465)
fix(sdk): guard timeout forwarding for older backend packages (#1461)
chore(deepagents): bump min version for langchain-anthropic (#1431)
feat(sdk): add per-command timeout override to execute() (#1154)
chore: auto-generate makefile help from target annotations (#1417)
chore: revert SDK version following yank (#1407)
chore: enable type checking for all other packages (#1365)
release(sdk): 0.4.2 (#1312)
chore: rollback uv workspace migration, restore per-package lockfiles (#1278)
chore: migrate to uv workspace (#1264)
chore(deps): bump the uv group across 2 directories with 1 update (#1245)
chore: rename master to main (#984)
release(sdk): 0.4.0 (#1236)
release(deepagents): 0.4 (#1234)
Thanks to our contributors: Sydney Runkle (@sydney-runkle), Eugene Yurtsev (@eyurtsev), Mason Daugherty (@mdrxy)
langchain-daytona==0.0.3
Changes since langchain-daytona==0.0.2
release(sdk): bump partner packages (daytona 0.0.3, modal 0.0.2, runloop 0.0.3) (#1689)
release(sdk): bump deepagents to 0.4.7 (#1688)
feat(infra): add fireworks as eval provider (#1684)
release(sdk): bump deepagents to 0.4.6 (#1677)
chore: bump lock file (#1674)
chore(sdk): expand eval matrix and fix model name access for groq (#1623)
release(deepagents): 0.4.5 (#1622)
chore(sdk): expand eval model matrix to 28 models across 7 providers (#1617)
chore: standardize makefile type targets/ add type CI check (#1581)
chore(deps): bump the pip-dependencies group across 8 directories with 17 updates (#1564)
chore(deps): bump the pip-dependencies group across 8 directories with 19 updates (#1491)
release(deepagents): 0.4.4 (#1519)
release(deepagents): 0.4.3 (#1465)
fix(sdk): guard timeout forwarding for older backend packages (#1461)
chore(deepagents): bump min version for langchain-anthropic (#1431)
feat(sdk): add per-command timeout override to execute() (#1154)
chore: auto-generate makefile help from target annotations (#1417)
chore: revert SDK version following yank (#1407)
chore(daytona): add integration test suite to daytona (#1397)
chore: enable type checking for all other packages (#1365)
release(sdk): 0.4.2 (#1312)
chore: rollback uv workspace migration, restore per-package lockfiles (#1278)
chore: migrate to uv workspace (#1264)
chore(deps): bump the pip-dependencies group across 8 directories with 9 updates (#1252)
chore(deps): bump cryptography from 46.0.4 to 46.0.5 in /libs/partners/daytona (#1243)
chore: rename master to main (#984)
release(sdk): 0.4.0 (#1236)
release(deepagents): 0.4 (#1234)
chore(deps): bump the pip-dependencies group across 8 directories with 27 updates (#1230)
Thanks to our contributors: Sydney Runkle (@sydney-runkle), Eugene Yurtsev (@eyurtsev), Mason Daugherty (@mdrxy)
deepagents==0.4.7
Changes since deepagents==0.4.6
release(sdk): bump deepagents to 0.4.7 (#1688)
fix(deepagents): restore full routed path in write/edit results (#1681)
feat(infra): add fireworks as eval provider (#1684)
Thanks to our contributors: Naga Karumuri (@naga-k)
deepagents==0.4.6
Changes since deepagents==0.4.5
release(sdk): bump deepagents to 0.4.6 (#1677)
chore: bump lock file (#1674)
fix(sdk): extract text from all content blocks for large tool result eviction (#1673)
fix(sdk): enforce path boundaries in CompositeBackend routing (#1659)
refactor(sdk): split eval assertions into correctness and efficiency tiers (#1670)
test(sdk): remove an ambiguous eval test (#1661)
chore(sdk): add tool usage evals (#1637)
test(deepagents): fix one more file operation test (#1653)
test(sdk): update eval test to be a bit less ambiguous (#1643)
docs(sdk): middleware module docstring (#1620)
chore(sdk): expand eval matrix and fix model name access for groq (#1623)
Thanks to our contributors: DoTA (@dotuananh0712), Brace Sproul (@bracesproul), Eugene Yurtsev (@eyurtsev), Mason Daugherty (@mdrxy)
deepagents-cli==0.0.29
Features
--model-paramsflag on/modelcommand (#1679) (9b6433d)--shell-allow-list all(#1695) (4aec7b3)- Hook dispatch for external tool integration (#1553) (cdb2230)
- Detect deceptive unicode in tool args and URLs (#1694) (d4c8544)
- MCP tool loading with auto-discovery (#801) (df0908e)
Bug Fixes
Thanks to our contributors: jcuypers, Eugene Yurtsev (@eyurtsev)
deepagents-cli==0.0.28
Features
- Add video support to multimodal inputs (#1521) (f9b49b7)
- Add NVIDIA api key support and default model (#1577) (9ce2660)
- Fuzzy search for slash command autocomplete (#1660) (5f6e9c0)
- Tab autocomplete in model selector (#1669) (28bd0aa)
Bug Fixes
- Backspace at cursor position 0 exits mode even with text (#1666) (dfa4c1f)
- Skip auto-approve toggle when modal screen is open (#1668) (6597f0b)
- Truncate model name in status bar on narrow terminals (#1665) (0e24a04)
Thanks to our contributors: Arthur Drozdov (@arthur-drozdov), Soumili Nandi (@soumilinandi), Mason Daugherty (@mdrxy)
deepagents-cli==0.0.27
Features
- Add background PyPI update check (#1648) (2e7a5e7)
- Add install script (#1649) (68f6ef9)
- Add fuzzy search to model switcher (#1266) (a6bbb18)
- Add model usage stats display (#1587) (a1208db)
- Add substring matching to command history navigation (#1301) (e276d5a)
Bug Fixes
- Allow Esc to exit command/bash input mode (#1644) (906da72)
- Make
!bash commands interruptible viaEsc/Ctrl+C(#1638) (0c414d1) - Make escape reject pending HITL approval first (#1645) (5d7be0c)
- Show cwd on startup (#1209) (23032dd)
- Terminate active subprocesses on app quit (#1646) (5f2e614)
- Use first-class OpenRouter attribution kwargs (#1635) (9c1ed93)
Thanks to our contributors: Ninad Kale (@1Ninad), Ananya Narayan (@an-ny89), Peter Kolcza (@peterkolcza), Mason Daugherty (@mdrxy)
deepagents==0.4.5
Changes since deepagents==0.4.4
release(deepagents): 0.4.5 (#1622)
chore(sdk): expand eval model matrix to 28 models across 7 providers (#1617)
chore: remove unnecessary @pytest.mark.asyncio decorators (#1616)
chore(sdk): update evals to use chat model instance (#1614)
fix(sdk): make evals more robust across model output variations (#1608)
fix(infra): streamline evals workflow and summary (#1602)
docs(sdk): improve docstrings around summarization conditions (#1597)
chore(sdk): add json report to evals (#1594)
chore(sdk,cli): switch claude-sonnet-4-5-20250929 -> claude-sonnet-4-6 (#1590)
feat(cli): /compact command (#1579)
chore: standardize makefile type targets/ add type CI check (#1581)
ci(sdk): skip some evals (#1580)
docs(sdk): rename 'prompt' to 'system_prompt' in subagent keys (#1578)
docs(sdk): docstring fixes for summarization.py (#1568)
chore(sdk): remove unused base_path alias in skills.py (#1543)
chore(deps): bump the pip-dependencies group across 8 directories with 17 updates (#1564)
fix(sdk,cli,deps): support timeout=0 for sandbox execute() (#1558)
fix: Potential fixes for 2 code quality findings (#1534)
fix: Variable defined multiple times (#1536)
feat(cli,sdk): compaction hook (#1420)
chore(deps): bump the pip-dependencies group across 8 directories with 19 updates (#1491)
Thanks to our contributors: Adem Boukhris (@AdemBoukhris457), alexpap (@AlexPapadakis), Eugene Yurtsev (@eyurtsev)
deepagents-cli==0.0.26
Features
- Compaction hook (#1420) (e87cdad)
- Add
--profile-overrideCLI flag (#1605) (1984099) - Add model profile overrides to config (#1603) (d3d6899)
- Show summarization status and notification (#919) (2e3cb74)
Bug Fixes
- Fix image path pasting qualms (#1560) (8caaf3e)
- Load
.agentsskill alias directories at interactive startup (#1556) (af0a759) - Coerce execute timeout to int before formatting tool display (#1588) (04b8c72), closes #1586
- Add missing flags to help screen (#1619) (6067749)
- Align compaction messaging across
/compactandcompact_conversation(#1583) (d455a6b) - Apply profile overrides in
/compact(#1612) (a9dc2c5) - Disambiguate
/tokensvs/compacttoken reporting (#1618) (51c3347) - Make LangSmith URL lookups non-blocking (#1595) (572eaee)
- Only exit input mode on backspace, not text clear (#1479) (da0965e)
- Retry langsmith project url lookup until project exists (#1562) (e137a63)
- Show model info in
/tokensbefore first usage (#1607) (7b01ae7) - Support
timeout=0for sandboxexecute()(#1558) (ed14443) - Unreachable
exceptblock (#1535) (0e17e35)
Performance Improvements
- Optimize thread resume path with prefetch and batched hydration (#1561) (068d112)
- Parallelize detection scripts for faster first-turn (#1541) (dad8b6e)
- Speed up
/threadsfirst-open (#1481) (b248b15)
Thanks to our contributors: Jihyun kim (@Taylor0819), Mohammad Mohtashim (@keenborder786), Adem Boukhris (@AdemBoukhris457), John Kennedy (@jkennedyvz), Eugene Yurtsev (@eyurtsev), Mason Daugherty (@mdrxy)