Skip to content

fix(proxy): add OpenAI-compatible model discovery - #1114

Open
Gout999 wants to merge 1 commit into
TencentCloud:feat/server_teamfrom
Gout999:agent/fix-proxy-model-list-1098
Open

fix(proxy): add OpenAI-compatible model discovery#1114
Gout999 wants to merge 1 commit into
TencentCloud:feat/server_teamfrom
Gout999:agent/fix-proxy-model-list-1098

Conversation

@Gout999

@Gout999 Gout999 commented Aug 21, 2026

Copy link
Copy Markdown

Addresses #1098.

Summary

  • Add OpenAI-compatible GET /models and GET /v1/models endpoints.
  • Add the same model-listing paths under /<agent>/<spaceId>/, which covers Hermes custom-provider probes such as /hermes/default/models.
  • Expose the configured public modelName alias when present, fall back to the configured model ID, and return an empty list when no pricing table is configured.
  • Document the endpoint in both MemoryProxy READMEs.

Validation

  • npm exec vitest run src/__tests__/server-models.test.ts — 2 passed.
  • git diff --check — passed.
  • The package-wide npm run typecheck still reports existing errors in unrelated files (anthropicHandler.ts, codexHandler.ts, config.ts, and the cost-guard alias); it is not reported as a pass here.

Signed-off-by: Gout999 <gout999@users.noreply.github.com>
@Maxwell-Code07

Copy link
Copy Markdown
Collaborator

Thank you so much for your attention and contribution! We will arrange an internal review for this PR shortly, and all feedback will be shared right here in the discussion.

@Gout999
Gout999 marked this pull request as ready for review August 23, 2026 13:44
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