deepagents==0.4.3

langchain-ai/deepagentsdeepagents==0.4.3Feb 20, 2026by github-actions[bot]

AI Summary

This significant release adds per-command timeout overrides, enables type checking across the codebase, and introduces a comprehensive evaluation framework. The release also addresses multiple security vulnerabilities related to path traversal.

Key Highlights

Add per-command timeout override to execute() method
Enable type checking and resolve most linting issues
Add evaluation tests for skills and agent memory
Fix path traversal vulnerabilities in glob operations
Improve Memory prompt guidelines

New Features

Per-command timeout override to execute()
Type checking enabled in deepagents
Evaluation framework with tests
Path hardening for security
Base agent prompt implementation

Full Release Notes

Changes since deepagents==0.4.2
release(deepagents): 0.4.3 (#1465)
fix(sdk): guard timeout forwarding for older backend packages (#1461)
fix(sdk): correct imports and mock inheritance in filesystem middleware tests (#1464)
fix(sdk): warn on virtual mode (#1462)
chore(sdk): add more eval test cases (#1452)
test(deepagents): add evaluation tests for skills (#1429)
fix(deepagents): Fix Memory prompt guidelines that could lead to wrong actions (#1448)
test(sdk): add smoke test for system prompt with memory and skills (#1430)
chore(deepagents): bump min version for langchain-anthropic (#1431)
feat(deepagents): add evaluation tests for agent memory (#1415)
chore(sdk): adapt integration tests to evals framework (#1426)
feat(sdk): add per-command `timeout` override to `execute()` (#1154)
chore: auto-generate makefile help from target annotations (#1417)
chore(sdk): add more evals (#1404)
chore(sdk): minor updates to system message (#1367)
chore(sdk): add model parameterization to evals (#1408)
chore: revert SDK version following yank (#1407)
chore(sdk): add simple eval scaffolding (#1400)
refactor(sdk): add logging to silent path skips, rename `validate_path` (#1370)
fix(cli,sdk): harden path hardening (#918)
chore(sdk): add smoke tests for system message (#1363)
feat(sdk): enable type checking in deepagents and resolve most linting issues (#991)
chore(sdk): move some integration tests into unit tests (#1330)
revert(sdk): reimplement skill loading via `skill` tool calling (#1328)
fix(sdk): missing `_validate_path()` on `Glob` tool's `path` parameter allows directory traversal (#1320)
fix: Path Traversal via Unsanitized Glob Pattern in glob_info() Bypasses Virtual Mode Sandbox (#1322)
feat(sdk): add base agent prompt (#1314)

---

Thanks to our contributors: @MuriloAndre2000, @vtrivedy, @sydney-runkle, @app/corridor-security, @app/copilot-swe-agent, @ccurme, @eyurtsev, @mdrxy