docs: clarify Vertex AI uses LLM_PROVIDER_MODE=vertex - #554
Conversation
|
Warning Review limit reached
More reviews will be available in 52 minutes and 6 seconds. Learn how PR review limits work. Your organization has used up its prepaid credits, and credit purchases are no longer available. Enable the review add-on in the billing tab to keep reviews running — you're only billed for reviews past your plan's rate limits ($0.25/file). ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based credits. 🚦 How do rate limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (1)
WalkthroughVertex AI documentation now shows ChangesVertex routing guidance
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 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 |
![arvo-ai-staging[bot]](https://avatars.githubusercontent.com/in/4088260?s=60&v=4){kind=small}
The provider routing accepts a provider name as LLM_PROVIDER_MODE to force all model picks through that provider, but the Vertex docs recommended `direct` mode. Under `direct`, only `vertex/`-prefixed model ids route to Vertex; a clean `google/...` id silently goes to the Google AI provider instead. Document `LLM_PROVIDER_MODE=vertex` as the recommended, unambiguous option. Also corrects an inaccurate tip claiming the project id is auto-extracted from the service account JSON; the provider reads VERTEX_AI_PROJECT directly and is unavailable without it.
28f0aca to
d059414
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 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.
Inline comments:
In @.env.example:
- Around line 109-112: The provider-mode comment in .env.example overstates the
behavior of explicit provider-name mode; update the description near the
provider mode setting so it says a named provider routes models through that
backend when supported, with unsupported models falling back to direct prefix
routing. Keep the wording aligned with the runtime contract by adjusting the
explanatory text for the provider mode options rather than changing behavior.
In `@website/docs/integrations/llm-providers.md`:
- Around line 147-163: The Vertex AI docs are inconsistent: the provider table
still marks Vertex AI as Direct even though this section now recommends routing
through Vertex with LLM_PROVIDER_MODE=vertex. Update the Vertex AI row in the
supported-providers table to match the behavior described here, and keep the
wording aligned with the llm-providers.md guidance so the table and the
Vertex-specific section agree.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: c6dedcce-151c-486b-a68a-6458a61f03af
📒 Files selected for processing (3)
.env.examplewebsite/docs/configuration/environment.mdwebsite/docs/integrations/llm-providers.md
Use the LLM_PROVIDER_MODE value (openrouter, vertex, bedrock) in the Mode column for the providers that have a dedicated routing mode, so the table agrees with the Vertex setup section recommending LLM_PROVIDER_MODE=vertex.
95ad176
|
2 participants
Summary
LLM_PROVIDER_MODE=vertexas the recommended way to run Aurora on Vertex AI, instead of the previously-recommendeddirectmode.openrouter/direct/autovalue as a forced provider name. Underdirectmode, routing is by model prefix, so onlyvertex/...ids reach Vertex — a cleangoogle/...id silently goes to the Google AI (API-key) provider instead.LLM_PROVIDER_MODE=vertexremoves that ambiguity by forcing all supported picks through Vertex.VERTEX_AI_PROJECTdirectly (is_available()returnsbool(self.project)) and is unavailable without it.Docs-only change; no code behavior changes.
Test plan
cd website && npm run build(or docs build) renders the updated Vertex section without MDX errors:::tip/:::noteadmonitions render correctlySummary by CodeRabbit
LLM_PROVIDER_MODE=vertexfor clearer model routing.vertex/-prefixed model IDs.