Code
How cheaper-inference/omniroute is laid out, and where to start for common changes.
There is no import map for this report yet.
Where to start reading
- Repository root
- Repository root
- Likely public API
- Likely public API
- Likely start-up file
- Likely start-up file
- Suggested starting pointAI
- Suggested starting pointAI
Find files for a task
AIAdd a new AI provider integration
- Register provider metadata and free tier info in the models registry
- Add provider credentials validation in the A2A authentication layer
- Define provider health checks and quota rules in assessment domain
- Add provider-specific routing rules or constraints if needed
Add a new dashboard feature or widget
- Define UI state in the appropriate store if needed
- Add internationalization keys for the new feature
- Integrate the component into the home page or relevant dashboard page
Implement a new security or authorization policy
- Define the policy logic in the authorization classification module
- Add assertion or validation in the auth middleware
- If prompt-based, add detection patterns to the injection guard
Optimize token compression for a new model family
- Analyze compression effectiveness in compression hooks
- Register compression rules in the model-to-provider registry
- Test compression estimation in preview handler
Change the public API
Trace runtime behavior
Add or update tests
Change build or automation
RepoPilot lists up to 500 files, so a file missing here may still exist.
- Files marked “likely” are guessed from their names.
- Some entry points named in the manifest are build output or are missing from the file list, so their source is not shown.
- The file list is newer than the written guide, so descriptions and suggested changes may describe older code.