Skip to content

[codex] Add inference router diagnostics - #1

Merged
GuideboardLabs merged 1 commit into
GuideboardLabs:mainfrom
Ozhiaki:codex/inference-router-diagnostics
May 14, 2026
Merged

[codex] Add inference router diagnostics#1
GuideboardLabs merged 1 commit into
GuideboardLabs:mainfrom
Ozhiaki:codex/inference-router-diagnostics

Conversation

@TheEditor

Copy link
Copy Markdown
Contributor

Summary

Adds low-risk introspection and diagnostic methods to the existing InferenceRouter without changing the primary chat/embed request paths. The router can now report configured backends, fallback chains, loaded Ollama model state, conservative model capability and fit estimates, health details, config validation findings, route explanations, and wait_for_any() availability checks.

Why

Oathweaver already has a useful local inference router, but it is hard to inspect from CLI/API/UI surfaces. This PR makes local runtime state easier to understand and debug while keeping the first slice additive.

Validation

  • python3 -m unittest tests.test_inference_router_compat
  • python3 -m py_compile SourceCode/shared_tools/inference_router.py tests/test_inference_router_compat.py

@GuideboardLabs
GuideboardLabs marked this pull request as ready for review May 14, 2026 13:25
@GuideboardLabs
GuideboardLabs merged commit 232d9ca into GuideboardLabs:main May 14, 2026
0 of 2 checks passed
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.

2 participants