repowiserepowise
Sign in
krsatyam36/xyz-local
OverviewDocsArchitectureKnowledge GraphFilesCode HealthRefactoring

People & History

CommitsContributorsDecisions
ChatPro
Stats
repowiserepowise
ExplorePricingDocs
Sign inIndex repoIndex your repo free
repowisekrsatyam36/xyz-local
XY
XY

krsatyam36 / xyz-local

pythonmain454242c3.4K linessynced 1mo ago

Code health

5.2out of 10Fair

This codebase scores 5.2 out of 10 on defect risk, which we rate fair. It also scores maintainability 6.6 and static performance risk 9.8 out of 10. The three are scored separately and never blended into one number. The files you change most are the weak spot: 3 of 20 files are git hotspots, and they average 2.4.

Full health report →
Lines of code
3.4K
Files
20
Symbols
195
Modules
10
Languages
5

Recent activity

All commits →

Commits

No commits indexed yet.

Decisions

  • Known typo-squatting / malicious package names. NOTE: do not put legitimate package names here — entproposed
  • Context window. Ollama defaults to only 2048 tokens, which is far too small for an agent loop (a sinproposed
  • Fallback: parse tool calls out of streamed text if API didn't return them nativelyproposed
  • Longest marker is "<tool_request" (13). Hold back this many trailing chars while streaming so a markproposed
  • Load config from file then apply environment overridesproposed
  • Set context window to 8192 instead of Ollama defaultproposed

Needs attention

31 open
  • medium severity. ProposedKnown typo-squatting / malicious package names. NOTE: do not put legitimate package names here — entAuto-proposed decision awaiting review
  • medium severity. ProposedContext window. Ollama defaults to only 2048 tokens, which is far too small for an agent loop (a sinAuto-proposed decision awaiting review
  • medium severity. ProposedFallback: parse tool calls out of streamed text if API didn't return them nativelyAuto-proposed decision awaiting review
  • medium severity. ProposedLongest marker is "<tool_request" (13). Hold back this many trailing chars while streaming so a markAuto-proposed decision awaiting review
  • medium severity. ProposedLoad config from file then apply environment overridesAuto-proposed decision awaiting review

Where the risk concentrates

All 3 hotspots →

Ranked by prior bug fixes and change frequency, mined from full git history rather than from the code alone.

FileChurnPrior fixesMaintainersCommits 90d
agent.pysrc/xyz_local92.3th12bus factor 119
tools.pysrc/xyz_local84.6th12bus factor 117
main.pysrc/xyz_local76.9th1214

Composition

Open the graph →
python 65%markdown 15%yaml 10%dockerfile 5%toml 5%

Explore this codebase

  • Docs0 pages across 10 modules→
  • ChatAsk this codebase a question and get an answer with its sources→
  • Files20 files with per-file docs, health and history→
  • ArchitectureDependency graph, layers, and 1 entry points→
  • Code healthPer-file scores, 96 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→