shivamg5080 / mcp-qa-pdf
pythonmain36966013.2K linessynced 1mo ago
Code health
9.2out of 10Excellent
This codebase scores 9.2 out of 10 on defect risk, which we rate excellent. It also scores maintainability 9.7 and static performance risk 10.0 out of 10. The three are scored separately and never blended into one number.
- Lines of code
- 3.2K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Keys we ask ChromaDB to include in query results. We always need documents (chunk text / matched…proposed · 1mo ago
- Maximum tokens requested from the Anthropic API. Kept small because the server returns concise…proposed · 1mo ago
- Fall back to the whole-page text when no paragraph boundaries were found.proposed · 1mo ago
- Imported lazily so that simply importing this module does not trigger the heavy…proposed · 1mo ago
- Embedding batch size kept modest to avoid surprising memory spikes on large pages while still…proposed · 1mo ago
- Cite contributing contexts with page info when availableproposed · 1mo ago
Needs attention
29 open- medium severity. ProposedKeys we ask ChromaDB to include in query results. We always need documents (chunk text / matched…Auto-proposed decision awaiting review
- medium severity. ProposedMaximum tokens requested from the Anthropic API. Kept small because the server returns concise…Auto-proposed decision awaiting review
- medium severity. ProposedFall back to the whole-page text when no paragraph boundaries were found.Auto-proposed decision awaiting review
- medium severity. ProposedImported lazily so that simply importing this module does not trigger the heavy…Auto-proposed decision awaiting review
- medium severity. ProposedEmbedding batch size kept modest to avoid surprising memory spikes on large pages while still…Auto-proposed decision awaiting review
Composition
Open the graphpython 56%json 22%markdown 19%toml 4%
Explore this codebase
- Docs0 pages across 13 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files27 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 1 entry points
- Code healthPer-file scores, 21 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