Skip to content

feat: single-file analysis, flexible model selection#1

Merged
bsbodden merged 2 commits into
integrallis:mainfrom
abrookins:feature/llm-pass-key-fallthrough-models
Oct 27, 2025
Merged

feat: single-file analysis, flexible model selection#1
bsbodden merged 2 commits into
integrallis:mainfrom
abrookins:feature/llm-pass-key-fallthrough-models

Conversation

@abrookins

Copy link
Copy Markdown
Contributor

Description

  • Pass provider API key to LiteLLM via AnalysisConfig.get_litellm_config()
  • Remove forced fallback to Claude for unknown models so requests fall through to provider
  • Add support for GPT-5 and GPT-5-mini aliases
  • Support analyzing a single Python file path (in addition to directories)
  • Docs and CHANGELOG updated

Type of Change

  • New feature
  • Bug fix
  • Breaking change
  • Documentation update

Coverage notes:

  • I think the core modules are at 100%

Checklist

  • Tests written for changes
  • Code follows style guidelines
  • Self-review completed
  • Documentation updated (README single-file usage)
  • CHANGELOG updated
  • MFCQI score maintained or improved (≥0.753)

MFCQI Score

  • src/mfcqi analyzed (metrics-only): 0.872

Notes

  • Lint: ruff check --fix applied; ruff format run

mfcqi allows configuring an LLM vendor with key, so we should send
the key to LiteLLM if we have it -- otherwise, the user will need
to set an env var.

Meanwhile, the fixed choice of models is limited. Include the latest
GPT-5 models, but also, allow users to specify any model, and we'll
pass it through to the vendor. This way, mfcqi doesn't have to change
every time a new model comes out.
@abrookins
abrookins force-pushed the feature/llm-pass-key-fallthrough-models branch from 2e7d3e0 to 7f777db Compare October 23, 2025 23:50
@abrookins abrookins changed the title feat: single-file analysis; pass API key to LiteLLM; allow model fall-through; add gpt-5(-mini) feat: single-file analysis, flexible model selection Oct 23, 2025
@bsbodden
bsbodden self-requested a review October 24, 2025 01:08
Allow analyzing a single file instead of assigning zero
to every metric.
@abrookins
abrookins force-pushed the feature/llm-pass-key-fallthrough-models branch from 7f777db to ad45b9e Compare October 24, 2025 16:47
@bsbodden bsbodden self-assigned this Oct 24, 2025
@codecov-commenter

Copy link
Copy Markdown

Welcome to Codecov 🎉

Once you merge this PR into your default branch, you're all set! Codecov will compare coverage reports and display results in all future pull requests.

Thanks for integrating Codecov - We've got you covered ☂️

@bsbodden bsbodden left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! Thanks!

@bsbodden
bsbodden merged commit b32e609 into integrallis:main Oct 27, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants