Skip to content

fix: resolve delegation providers from custom_providers#1012

Closed
stablegenius49 wants to merge 1 commit intoNousResearch:mainfrom
stablegenius49:pr-factory/issue-1011-custom-delegation
Closed

fix: resolve delegation providers from custom_providers#1012
stablegenius49 wants to merge 1 commit intoNousResearch:mainfrom
stablegenius49:pr-factory/issue-1011-custom-delegation

Conversation

@stablegenius49
Copy link
Contributor

@stablegenius49 stablegenius49 commented Mar 12, 2026

Summary

  • resolve named custom providers from config.yaml custom_providers during runtime provider selection
  • allow delegation config to reference either the raw custom provider name (for example "local") or the menu-key form ("custom:local")
  • add regression coverage for saved custom-provider credentials and env-key fallback

Testing

  • python3 -m pytest -q -o addopts='' tests/test_runtime_provider_resolution.py
  • python3 -m pytest -q -o addopts='' tests/test_api_key_providers.py::TestRuntimeProviderResolution

Closes #1011.

teknium1 added a commit that referenced this pull request Mar 14, 2026
Follow up on salvaged PR #1012.
Prevents raw custom-provider names from intercepting built-in provider ids,
and keeps the regression coverage focused on current-main behavior.
teknium1 added a commit that referenced this pull request Mar 14, 2026
Salvaged PR #1012 onto current main with the contributor commit preserved plus a small follow-up for builtin-provider shadowing and stale test cleanup.
@teknium1
Copy link
Contributor

Merged via PR #1328. Your substantive runtime-provider fix was cherry-picked onto current main with authorship preserved, plus a small follow-up for builtin-provider shadowing and stale test cleanup. Thanks for the contribution.

@teknium1 teknium1 closed this Mar 14, 2026
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.

[Bug]: agent delegation to custom inference provider does not work

3 participants