feat(ai): add Cerebras + Cloudflare providers; harden pipeline#9
Merged
Conversation
- Cerebras and Cloudflare Workers AI BYOK providers (CF: account id folded into the run URL, token + account treated as one pair) - NVIDIA key verify was a no-op: GET /v1/models is public and returns 200 for any key; probe chat/completions with max_tokens=1 instead - degrade to plain requests when a 200 stream carries no SSE data instead of failing the whole fallback chain - count Cloudflare as bundled when either half of the user pair is missing, matching resolve()'s fallback to the bundled pair - strip unterminated <think> blocks; remember Mistral OCR model swap across pages; redact nvapi-/gsk_/hf_/cfut_ tokens in logs - password keyboard on key fields; fix NVIDIA default-model hint - route only image/* mimes to bitmap decode; drop dead MAX_PDF_PAGES - evict completed verification jobs; raise OpenAI-compat read timeout to 90s to match the executor's attempt budget Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cerebras + Cloudflare Workers AI BYOK providers, plus fixes from the AI pipeline audit.
Feature
Audit fixes
GET /v1/modelsis public and returns 200 for any key (live-verified); now probeschat/completionswithmax_tokens=1(401/403 on bad keys)resolve()'s pair fallback<think>blocks; remember Mistral OCR model swap across pages; redactnvapi-/gsk_/hf_/cfut_tokens in logsimage/*mimes to bitmap decode (video/mp4 now gets the unsupported-type error); drop deadMAX_PDF_PAGES:app:compileDebugKotlinpasses.🤖 Generated with Claude Code