2233admin / AxisAgentic
pythonmain0aa54b143.9K linessynced 2d ago
Code health
7.6out of 10Good
This codebase scores 7.6 out of 10 on defect risk, which we rate good. It also scores maintainability 7.3 and static performance risk 9.9 out of 10. The three are scored separately and never blended into one number.
- Lines of code
- 43.9K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Maintain rollback markers as internal runtime messages hidden from visible conversationproposed · 2d ago
- Use recovery prompt for tool-call format errors in assistant responsesproposed · 2d ago
- Map conversation stages to stable orchestrator actions via enumproposed · 2d ago
- Use independent table answers and judge model flow for WideSearchproposed · 2d ago
- Use multiple benchmark-specific evaluation approaches rather than a single universal methodproposed · 2d ago
- Provide an interactive dashboard via Streamlit for log directoriesproposed · 2d ago
Needs attention
70 open- medium severity. ProposedMaintain rollback markers as internal runtime messages hidden from visible conversationAuto-proposed decision awaiting review
- medium severity. ProposedUse recovery prompt for tool-call format errors in assistant responsesAuto-proposed decision awaiting review
- medium severity. ProposedMap conversation stages to stable orchestrator actions via enumAuto-proposed decision awaiting review
- medium severity. ProposedUse independent table answers and judge model flow for WideSearchAuto-proposed decision awaiting review
- medium severity. ProposedUse multiple benchmark-specific evaluation approaches rather than a single universal methodAuto-proposed decision awaiting review
Composition
Open the graphpython 80%markdown 12%yaml 8%toml 0%shell 0%
Explore this codebase
- Docs265 pages across 33 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files208 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 1 entry points
- Code healthPer-file scores, 741 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