langchain-ai / langchain
pythonmastercdca311316.8K linessynced 5h ago
Code health
6.4out of 10Fair
This codebase scores 6.4 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: 111 of 2,723 files are git hotspots, and they average 3.5.
- Lines of code
- 316.8K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Prevent async task garbage collection for retry logging/callback tasksproposed · 5h ago
- Make ModelProfile forward-compatible with missing fields and schema drift warningsproposed · 5h ago
- Use lc_versions for package-version trace metadataproposed · 5h ago
- Preserve reasoning blocks alongside tool_call in v3 streamproposed · 5h ago
- preserve usage token details in v3 streaming eventsproposed · 5h ago
- fix indexing num_skipped count with within-batch deduplicationproposed · 5h ago
Needs attention
66 open- high severity. Stale decisionAdd an earlier guard for release dependency publishabilityActive decision drifting from the code it governs
- medium severity. ProposedPrevent async task garbage collection for retry logging/callback tasksAuto-proposed decision awaiting review
- medium severity. ProposedMake ModelProfile forward-compatible with missing fields and schema drift warningsAuto-proposed decision awaiting review
- medium severity. ProposedUse lc_versions for package-version trace metadataAuto-proposed decision awaiting review
- medium severity. ProposedPreserve reasoning blocks alongside tool_call in v3 streamAuto-proposed decision awaiting review
Where the risk concentrates
All 111 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 | 52 |
| chat_models.pylibs/partners/anthropic/langchain_anthropic | 99.9th | 19bug magnet | 22 | 11 |
| test_chat_models.pylibs/partners/anthropic/tests/unit_tests | 99.9th | 20bug magnet | 21 | 17 |
| base.pylibs/partners/openai/langchain_openai/chat_models | 99.8th | 24bug magnet | 40 | 13 |
| test_base.pylibs/partners/openai/tests/unit_tests/chat_models | 99.8th | 17bug magnet | 26 | 15 |
Composition
Open the graphpython 93%yaml 2%json 2%markdown 1%toml 1%Other 2%
Explore this codebase
- Docs2,046 pages across 108 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files2,723 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 6 entry points
- Code healthPer-file scores, 5,228 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