feat(provider): send Anthropic Messages to /ai/v1 - #4615
Conversation
Anthropic-protocol Veryfront Cloud models now use the same vendor-neutral base as OpenAI-protocol models, <api>/ai/v1, and send Messages requests to /ai/v1/messages. Eval still recognises the earlier /ai/anthropic/v1 prefix in recorded failures.
|
You have reached your Codex usage limits for security reviews. Please try again later. |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
|
Warning Review limit reachedNext included review available in 12 minutes. View limit detailsLimit details: You’ve used the included review currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (8)
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 |
📦 Client bundle boundary
A server module in a client graph aborts hydration in the browser. New leaks fail CI; known leaks are tracked in |
|
|
Review: 82/100 — Good, one doc fix needed before mergeClean, tightly-scoped routing change with matching test updates across all three affected suites. Holding the merge note is the right call given the dependency on the not-yet-live Strengths
Concerns
Action item to unblock a clean merge: update the CHANGELOG's existing Anthropic-route entry to reflect Generated by Claude Code |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b9b00ad19f
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
You have reached your Codex usage limits for security reviews. Please try again later. |
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
|
@codex review |
|
Codex Review: Didn't find any major issues. More of your lovely PRs please. Reviewed commit: ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
|
You have reached your Codex usage limits for security reviews. Please try again later. |
|
@codex review |
|
Codex Review: Didn't find any major issues. Another round soon, please! Reviewed commit: ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
|
kwakayama
left a comment
kwakayama
left a comment
There was a problem hiding this comment.
Score: 97/100
Verdict: APPROVE
Reviewed SHA: f0a9f48
Actionable findings: 0
Reviewed the Anthropic base path and /messages composition, provider-qualified model rewriting, vendor-route opt-out, and eval classification compatibility. Exact-head CI checks are green; formatting and lint passed locally. Targeted local tests were blocked by the repository runtime guard rejecting installed Deno 2.9.4.
2 participants
Refs veryfront/veryfront-issue-inbox#1904.
What changes
The platform now serves every protocol under one prefix. OpenAI requests go to
/ai/v1/chat/completionsand/ai/v1/responses, and Anthropic Messages to/ai/v1/messages./ai/anthropic/v1is deprecated.src/provider/veryfront-cloud/shared.tsgives Anthropic-protocol Veryfront Cloud models the base<api>/ai/v1, the same base as OpenAI-protocol models. The Anthropic client appends/messages, so requests go to<api>/ai/v1/messages. Request bodies still name the model as<provider>/<model>. TheVERYFRONT_CLOUD_GATEWAY_ROUTES=vendoropt-out is unchanged.src/eval/model-access.tstreats/ai/v1/messagesas a gateway route through the/ai/v1/prefix. It keeps recognising/ai/anthropic/v1/, which failures recorded by earlier releases can still carry.docs/guides/configuration.mdanddocs/architecture/27-agent-message-stream-dataflow.md.Tests
<api>/ai/v1and<api>/ai/v1/messagesfor Anthropic-protocol models./ai/v1/messages,/ai/v1/messages/count_tokens, and the earlier prefix.deno task typecheck,fmt:check,lint,docs:validateanddocs:api-reference:checkpass.test:fileonsrc/provider,src/evalandtests/integration/provider: 56 passed, 0 failed.