Claude/fix mcp oauth connections xot j6 - #5
Merged
Merged
Conversation
- Add path-aware RFC 9728/8414 discovery routes (/.well-known/ oauth-protected-resource/api/mcp + authorization-server) to fix the 404 that aborted OAuth in modern Claude/Cursor/Codex/VS Code builds - Centralize discovery metadata + CORS in mcp-oauth.server.ts - /api/mcp now sends CORS, an OPTIONS handler, and exposes the WWW-Authenticate challenge so web connectors can discover OAuth - CLI: super-agent connect/login/status/logout/setup + a local stdio<->HTTP bridge that injects and refreshes the OAuth token - Document the OAuth + CLI flow on /connect and /docs/mcp with ready-to-paste connection prompts https://claude.ai/code/session_01QjRrzVxTXxMAwWsU65Avaf
The old get_methodology dumped the full 7-pillar rubric and review_skill echoed every check + literal fix string, so a model internalised the evaluator after one call and never needed us again. - Evaluation logic (signals, weights, thresholds) is now server-private - get_methodology returns only dimension names + how-to-use, never the rubric - review_skill returns overall_score, per-dimension score + coarse band, and rotating, file-specific outcome directives — no per-check pass/fail, no detector strings - Stronger engine: graded multi-signal scoring with per-type weighting (soul→identity, playbook→procedure, guardrail→guardrails) and weighted deficit ranking so actions target what most moves this file's score - Realign overview / server instructions / docs to the proprietary framing https://claude.ai/code/session_01QjRrzVxTXxMAwWsU65Avaf
6 tasks
criptogus
pushed a commit
that referenced
this pull request
May 28, 2026
…equest Infra/API follow-ups from operator feedback: - review_skills_batch: score up to 10 files in one parallel call, aligned to input order with a single shared feedback_request — far lower round-trip latency than N review_skill calls (feedback #8). - In-process result cache keyed by content_hash + options. Identical re-submissions skip both the deterministic scoring and the LLM semantic pass, cutting ~15-30s to ~0 on iterative loops; responses carry `cached` (#9). Core review logic extracted into computeReview(), shared by single + batch. - dry_run preview for upload_packages and request_primitive: validates the file (type inference + prompt-injection guard) or echoes the would-be request WITHOUT auth, persistence, or model budget, so agents can test the publish flow before connecting OAuth. The MCP write-tool auth gate now lets a dry_run call through anonymously (#5/#6). https://claude.ai/code/session_01EntkmBiYh381pKqvvSFBkg
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
2 participants
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.
What does this PR add?
Type
version)Checklist (for content PRs)
slugand the type's folderbun run validate:contentpasses locallyNotes for reviewers