langchain-ai / langchain
pythonmaster0727992320.5K linessynced 4h ago
Code health
6.3out of 10Fair
This codebase scores 6.3 out of 10 on defect risk, which we rate fair. It also scores maintainability 7.4 and static performance risk 10.0 out of 10. The three are scored separately and never blended into one number. The files you change most are the weak spot: 115 of 2,730 files are git hotspots, and they average 3.5.
- Lines of code
- 320.5K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Add an earlier PyPI dependency validation guard for release PRsactive · 4h ago
- avoid eager pydantic.v1 import in @deprecatedproposed · 4h ago
- Remove shielded decorator and early-exit for non-end event handlersproposed · 4h ago
- Unify mypy version and configuration across the monorepoproposed · 4h ago
- Use asyncio.get_running_loop() in async contextsproposed · 4h ago
- Make BaseCallbackManager.remove_handler robust to constructor-only handlersproposed · 4h ago
Needs attention
63 open- high severity. Stale decisionAdd an earlier PyPI dependency validation guard for release PRsActive decision drifting from the code it governs
- medium severity. Proposedavoid eager `pydantic.v1` import in `@deprecated`Auto-proposed decision awaiting review
- medium severity. ProposedRemove shielded decorator and early-exit for non-end event handlersAuto-proposed decision awaiting review
- medium severity. ProposedUnify mypy version and configuration across the monorepoAuto-proposed decision awaiting review
- medium severity. ProposedUse asyncio.get_running_loop() in async contextsAuto-proposed decision awaiting review
Where the risk concentrates
All 115 hotspotsRanked by prior bug fixes and change frequency, mined from full git history rather than from the code alone.
| File | Churn | Prior fixes | Maintainers | Commits 90d |
|---|---|---|---|---|
| _profiles.pylibs/partners/openrouter/langchain_openrouter/data | 100.0th | 1 | 3 | 55 |
| chat_models.pylibs/partners/anthropic/langchain_anthropic | 99.9th | 18bug magnet | 39 | 15 |
| test_chat_models.pylibs/partners/anthropic/tests/unit_tests | 99.9th | 19bug magnet | 26 | 22 |
| base.pylibs/partners/openai/langchain_openai/chat_models | 99.8th | 25bug magnet | 74 | 19 |
| test_base.pylibs/partners/openai/tests/unit_tests/chat_models | 99.8th | 20bug magnet | 33 | 19 |
Composition
Open the graphpython 93%yaml 2%json 2%markdown 1%toml 1%Other 2%
Explore this codebase
- Docs2,052 pages across 24 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files2,730 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 6 entry points
- Code healthPer-file scores, 5,373 open findings, coverage and refactoring targets
- Knowledge graphEntities, communities, and the paths between them
- Change couplingFiles that keep changing together, mined from commit history
- CommitsChange-risk ranked history with agent provenance
- ContributorsBus factor, per-file maintainers, and the human/agent split
- StatsSize class, origin, lifetime churn, rhythm and records
- CostsWhat indexing this snapshot cost, by model and by run