google / adk-python
pythonmainf4fd7d5418.6K linessynced 22h ago
Code health
7.2out of 10Good
This codebase scores 7.2 out of 10 on defect risk, which we rate good. It also scores maintainability 8.3 and static performance risk 9.9 out of 10. The three are scored separately and never blended into one number. The files you change most are the weak spot: 238 of 2,369 files are git hotspots, and they average 4.9.
- Lines of code
- 418.6K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Retain latest user input across transfer_to_agent when include_contents='none'proposed · 22h ago
- Use a Unicode-aware tokenizer for ROUGE-1 matchingproposed · 22h ago
- Use typing.Optional in cleanup_unused_files tool annotationsproposed · 22h ago
- Treat RetryConfig(max_attempts=0) as no retriesproposed · 22h ago
- Add Pydantic serializers to make session event state JSON-serializableproposed · 22h ago
- docs(tools): encourage using mode='single_turn' in AgentTool and document manual artifacts configurationproposed · 22h ago
Needs attention
44 open- medium severity. ProposedRetain latest user input across transfer_to_agent when include_contents='none'Auto-proposed decision awaiting review
- medium severity. ProposedUse a Unicode-aware tokenizer for ROUGE-1 matchingAuto-proposed decision awaiting review
- medium severity. ProposedUse typing.Optional in cleanup_unused_files tool annotationsAuto-proposed decision awaiting review
- medium severity. ProposedTreat RetryConfig(max_attempts=0) as no retriesAuto-proposed decision awaiting review
- medium severity. ProposedAdd Pydantic serializers to make session event state JSON-serializableAuto-proposed decision awaiting review
Where the risk concentrates
All 238 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 |
|---|---|---|---|---|
| test_bigquery_agent_analytics_plugin.pytests/unittests/plugins | 99.9th | 5bug magnet | 5 | 18 |
| test_artifact_service.pytests/unittests/artifacts | 99.9th | 10bug magnet | 6 | 11 |
| test_remote_a2a_agent.pytests/unittests/agents | 99.8th | 6bug magnet | 5 | 9 |
| bigquery_agent_analytics_plugin.pysrc/google/adk/plugins | 99.8th | 5bug magnet | 4 | 14 |
| test_request_confirmation.pytests/unittests/flows/llm_flows | 99.7th | 4bug magnet | 5 | 7 |
Composition
Open the graphpython 74%markdown 11%json 7%javascript 4%yaml 2%Other 1%
Explore this codebase
- Docs2,736 pages across 9 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files2,369 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 61 entry points
- Code healthPer-file scores, 8,641 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