fix(litellm): fall back to /v1/models if /v1/model/info is forbidden#855
Closed
richard-guan-dev wants to merge 3 commits into
Closed
fix(litellm): fall back to /v1/models if /v1/model/info is forbidden#855richard-guan-dev wants to merge 3 commits into
richard-guan-dev wants to merge 3 commits into
Conversation
richard-guan-dev
requested review from
JamesRobert20,
edelauna,
hannesrudolph,
navedmerchant and
taltas
as code owners
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthrough
ChangesLiteLLM Model Fetching Fallback
Estimated code review effort: 3 (Moderate) | ~25 minutes Sequence Diagram(s)sequenceDiagram
participant Caller
participant getLiteLLMModels
participant ModelInfoEndpoint as /v1/model/info
participant ModelsEndpoint as /v1/models
Caller->>getLiteLLMModels: request models
getLiteLLMModels->>ModelInfoEndpoint: GET model info
alt success
ModelInfoEndpoint-->>getLiteLLMModels: model_name/model_info response
getLiteLLMModels->>getLiteLLMModels: parse non-fallback branch
getLiteLLMModels-->>Caller: return model map
else HTTP 403
ModelInfoEndpoint-->>getLiteLLMModels: error
getLiteLLMModels->>ModelsEndpoint: GET fallback models
alt fallback success
ModelsEndpoint-->>getLiteLLMModels: id-based response
getLiteLLMModels->>getLiteLLMModels: parse fallback branch
getLiteLLMModels-->>Caller: return model map
else fallback failure
ModelsEndpoint-->>getLiteLLMModels: error
getLiteLLMModels-->>Caller: reject with original error
end
else non-403 error
ModelInfoEndpoint-->>getLiteLLMModels: error
getLiteLLMModels-->>Caller: reject immediately
end
Suggested labels: Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
src/api/providers/fetchers/litellm.ts (1)
35-48: 🩺 Stability & Availability | 🔵 Trivial | ⚡ Quick winFallback triggers on any error and swallows the fallback failure.
Two related concerns in the retry block:
- The
catch (infoError)fires the fallback for any failure (network error, timeout, 500, etc.), not just the 403 this PR targets. A transient/v1/model/infoerror will now silently return degraded models (default capabilities, no pricing) instead of surfacing the failure. Consider gating the fallback on a 403 status.fallbackErroris caught but never logged beforethrow infoError, so when/v1/modelsalso fails there's no visibility into why the fallback failed.♻️ Suggested narrowing + logging
} catch (infoError: any) { + // Only fall back for authorization failures (e.g. virtual keys blocked on /v1/model/info) + if (infoError?.response?.status !== 403) { + throw infoError + } console.warn( `[getLiteLLMModels] Failed to fetch /v1/model/info, attempting fallback to /v1/models:`, infoError.message, ) const fallbackUrlObj = new URL(baseUrl) fallbackUrlObj.pathname = fallbackUrlObj.pathname.replace(/\/+$/, "").replace(/\/+/g, "/") + "/v1/models" const fallbackUrl = fallbackUrlObj.href try { response = await axios.get(fallbackUrl, { headers, timeout: 5000 }) isFallback = true } catch (fallbackError: any) { + console.warn(`[getLiteLLMModels] Fallback to /v1/models also failed:`, fallbackError.message) throw infoError } }🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/api/providers/fetchers/litellm.ts` around lines 35 - 48, Narrow the LiteLLM fallback in getLiteLLMModels so it only runs for the intended 403 case from /v1/model/info, rather than for every infoError; inspect the error status before building fallbackUrl and calling axios.get. Also, in the fallback catch block, log fallbackError with the existing console.warn/console.error context before rethrowing so failures in /v1/models are visible instead of silently bubbling as infoError.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@src/api/providers/fetchers/litellm.ts`:
- Around line 35-48: Narrow the LiteLLM fallback in getLiteLLMModels so it only
runs for the intended 403 case from /v1/model/info, rather than for every
infoError; inspect the error status before building fallbackUrl and calling
axios.get. Also, in the fallback catch block, log fallbackError with the
existing console.warn/console.error context before rethrowing so failures in
/v1/models are visible instead of silently bubbling as infoError.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 943030f3-1bcd-4ead-8f07-2ff00e593448
📒 Files selected for processing (2)
src/api/providers/fetchers/__tests__/litellm.spec.tssrc/api/providers/fetchers/litellm.ts
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
On LiteLLM instances using virtual keys, the metadata endpoint
/v1/model/infois restricted and returns a 403 Forbidden error. This PR adds a fallback mechanism that queries the standard/v1/modelsendpoint instead to list available models, parsing the simpler payload correctly.Summary by CodeRabbit