fix(ask-ai): correct eval Ask-AI domain and claude-code Opus model id#57
fix(ask-ai): correct eval Ask-AI domain and claude-code Opus model id#57tristantelleb wants to merge 2 commits into
Conversation
Two fixes surfaced while verifying Mintlify Ask AI against the live docs: - tests/evals/mintlify_client.py: the Ask-AI assistant domain defaulted to "docs.edenai.co", which 404s. The Mintlify project domain is "edenai" — the eval suite could not reach Ask AI until this was corrected. - v3/integrations/claude-code.mdx: replaced the invalid model id "anthropic/claude-opus-4.7" (a dotted id not present in /v3/models) and the stale "anthropic/claude-opus-4-7" with "anthropic/claude-opus-4-8" (current, valid, hyphenated) so every Opus reference on the page is consistent. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
|
Warning Review limit reached
More reviews will be available in 59 minutes and 10 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 refill rate. 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, the refill rate gradually slows as usage increases. The highest same-day bursts are limited more strictly. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✨ 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 |
1 participant
Summary
Two small fixes surfaced while verifying that Mintlify Ask AI reflects the latest docs.
1. Eval pipeline couldn't reach Ask AI (
tests/evals/mintlify_client.py)ask_mintlify()defaulteddomain="docs.edenai.co", which the Mintlify assistant API returns 404 for. The project's actual domain isedenai(verified: onlyedenaireturns 200;docs.edenai.co,edenai.mintlify.app,www.edenai.coall 404). Without this,pytest tests/evals/fails for everyone on the first request.2. Invalid / stale Opus model id (
v3/integrations/claude-code.mdx)The page used
anthropic/claude-opus-4.7— a dotted id that isn't in the/v3/modelscatalog (Eden AI uses hyphens), so a request copied from the docs would fail with "model not found". It also mixed in a stale hyphenatedanthropic/claude-opus-4-7. Both are nowanthropic/claude-opus-4-8(current, valid), making every Opus reference on the page consistent.Verification
edenai.anthropic/claude-opus-4-8confirmed present inGET https://api.edenai.run/v3/models.🤖 Generated with Claude Code