Open
Conversation
Contributor
WalkthroughAdds OpenRouter as a supported LLM provider across the LLM hint flow: updates provider types, configures ChatOpenAI for OpenRouter (baseURL and API key handling), adjusts model/temperature resolution, and adds corresponding unit, e2e, and seeding changes. Changes
sequenceDiagram
rect rgba(60,130,200,0.5)
Client->>API_Route: POST /api/llm-hint (provider: "openrouter", model, temp)
end
rect rgba(120,200,80,0.5)
API_Route->>GetChatModel: resolve provider & api key (env or account)
GetChatModel->>Env: read OPENROUTER_API_KEY / account-scoped key
GetChatModel-->>API_Route: ChatOpenAI client configured (baseURL=https://openrouter.ai/api/v1)
end
rect rgba(200,90,140,0.5)
API_Route->>OpenRouter_API: send request via ChatOpenAI client
OpenRouter_API-->>API_Route: LLM response
API_Route-->>Client: LLM hint response
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ 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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
tests/unit/llm-hint.test.ts (1)
717-781: Add one test for OpenRouter default model fallback.Please add a case where
provider: "openrouter"andmodelis omitted, then assertmodel: "openai/gpt-4o-mini"is used. That protects the new defaulting logic from regressions.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@tests/unit/llm-hint.test.ts` around lines 717 - 781, Add a new test inside the "OpenRouter Provider" describe block that sets mockTestResult.extra_data.llm!.provider = "openrouter" but leaves model undefined, then POST to the API via the existing POST(request) helper and assert response.status === 200 and that mockChatOpenAI was called with an objectContaining({ model: "openai/gpt-4o-mini", apiKey: process.env.OPENROUTER_API_KEY (or account-specific env if you set mockTestResult.extra_data.llm!.account), configuration: { baseURL: "https://openrouter.ai/api/v1" } }); use the same pattern as the other OpenRouter tests and refer to POST, mockTestResult, and mockChatOpenAI so the test verifies the default model fallback.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@app/api/llm-hint/route.ts`:
- Around line 188-200: The temperature fallback currently uses the || operator
which treats 0 as falsy and overrides explicit 0; update each provider branch
("openai", "azure", "anthropic", "openrouter") to use the nullish coalescing
operator (??) for the temperature assignment (e.g., replace temperature || 0.85
with temperature ?? 0.85) in the constructors (e.g., ChatOpenAI / AzureOpenAI /
ChatAnthropic or whichever classes are used in those branches) so an explicit 0
is preserved.
---
Nitpick comments:
In `@tests/unit/llm-hint.test.ts`:
- Around line 717-781: Add a new test inside the "OpenRouter Provider" describe
block that sets mockTestResult.extra_data.llm!.provider = "openrouter" but
leaves model undefined, then POST to the API via the existing POST(request)
helper and assert response.status === 200 and that mockChatOpenAI was called
with an objectContaining({ model: "openai/gpt-4o-mini", apiKey:
process.env.OPENROUTER_API_KEY (or account-specific env if you set
mockTestResult.extra_data.llm!.account), configuration: { baseURL:
"https://openrouter.ai/api/v1" } }); use the same pattern as the other
OpenRouter tests and refer to POST, mockTestResult, and mockChatOpenAI so the
test verifies the default model fallback.
ℹ️ Review info
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
app/api/llm-hint/route.tsscripts/DatabaseSeedingUtils.tstests/e2e/llm-hint.test.tsxtests/unit/llm-hint.test.tsutils/supabase/DatabaseTypes.d.ts
|
The latest updates on your projects. Learn more about Argos notifications ↗︎ Awaiting the start of a new Argos build… |
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
app/api/llm-hint/route.ts (1)
188-200: OpenRouter integration is correct — optional attribution headers can enhance tracking.The implementation correctly uses
ChatOpenAIwith baseURL override, which is the standard approach for OpenAI-compatible APIs. API key handling and error messaging match established patterns.OpenRouter supports optional
HTTP-RefererandX-Titleheaders for attribution and analytics. These are entirely optional and won't affect functionality, but can improve tracking in the OpenRouter dashboard if desired.🔧 Optional: Add attribution headers
return new ChatOpenAI({ model, apiKey: process.env[key_env_name], - configuration: { baseURL: "https://openrouter.ai/api/v1" }, + configuration: { + baseURL: "https://openrouter.ai/api/v1", + defaultHeaders: { + "HTTP-Referer": process.env.OPENROUTER_REFERER || "https://pawtograder.com", + "X-Title": "Pawtograder Feedbot" + } + }, temperature: temperature ?? 0.85, maxTokens: maxTokens, maxRetries: maxRetries || 2 });🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/api/llm-hint/route.ts` around lines 188 - 200, Add optional attribution headers to the OpenRouter client construction: when provider === "openrouter" and creating the ChatOpenAI instance, extend the configuration object passed to ChatOpenAI (currently configuration: { baseURL: "https://openrouter.ai/api/v1" }) to include a headers map with optional "HTTP-Referer" and "X-Title" values (e.g., taken from environment variables or request context); update key_env_name usage remains the same and ensure these headers are only added when present so behavior is unchanged if they are not set.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@app/api/llm-hint/route.ts`:
- Around line 188-200: Add optional attribution headers to the OpenRouter client
construction: when provider === "openrouter" and creating the ChatOpenAI
instance, extend the configuration object passed to ChatOpenAI (currently
configuration: { baseURL: "https://openrouter.ai/api/v1" }) to include a headers
map with optional "HTTP-Referer" and "X-Title" values (e.g., taken from
environment variables or request context); update key_env_name usage remains the
same and ensure these headers are only added when present so behavior is
unchanged if they are not set.
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.
Summary by CodeRabbit
New Features
Behavior
Tests