fix(ci): drop ineffective/diagnostic claude.yml inputs, root cause found

[BigSimmo]

Summary

• Root cause found. show_full_output: true (added in fix(ci): target enableAllProjectMcpServers via settings, add diagnostics #1366) revealed the real error on every @claude run: "Failed to authenticate. API Error: 401 OAuth access token is invalid." The CLAUDE_CODE_OAUTH_TOKEN repository secret is stale/invalid.
• fix(ci): disable project MCP auto-load for the Claude Code Action #1359 and fix(ci): target enableAllProjectMcpServers via settings, add diagnostics #1366 both targeted project MCP auto-load (this repo's .mcp.json "railway" server). That was never the actual cause — the earlier logs (with show_full_output off) only showed the SDK client starting up, which I mistook for successful authentication. Real auth only happens on the first API call, which has been failing with 401 the whole time.
• This PR drops claude_args: --strict-mcp-config (proved to have zero observable effect — likely because this action runs the Agent SDK's query() in-process rather than a claude CLI subprocess, so arbitrary CLI-style args may not translate) and show_full_output: true (no longer needed once root-caused; leaving it on would keep printing full agent tool-call output to Actions logs unnecessarily).
• Keeps settings: '{"enableAllProjectMcpServers": false}' — a CI runner has no legitimate use for project MCP servers regardless of whether it was the actual bug.
• No workflow change fixes an invalid token. The CLAUDE_CODE_OAUTH_TOKEN secret itself needs to be regenerated (claude setup-token locally) and updated on the repo — that's a manual step outside this PR.

Verification

• npm run check:github-actions — pin/policy check passes.
• Verification not run: unit suite — workflow YAML only, no application code.
• Live verification: three throwaway-PR @claude tests were run across this debugging session (all failed with the same 401 until show_full_output exposed why). No live test possible for this PR specifically until it merges (GitHub loads issue_comment workflow definitions from the default branch, not the PR head) — and even once merged, @claude will still fail until the secret is regenerated.

Risk and rollout

• Risk: low — removes two additive inputs, keeps one; no permissions/trigger/pinned-SHA changes.
• Rollback: revert this commit.
• Provider or production effects: None beyond the @claude Actions workflow itself.

Notes

• Third and (hopefully) final iteration in this chain: fix(ci): disable project MCP auto-load for the Claude Code Action #1359 → fix(ci): target enableAllProjectMcpServers via settings, add diagnostics #1366 → this PR. Once merged, @claude still needs a fresh CLAUDE_CODE_OAUTH_TOKEN before it will actually work.

---

Generated by Claude Code

[supabase]

This pull request has been ignored for the connected project sjrfecxgysukkwxsowpy because there are no changes detected in supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.

---

Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 21 minutes

Your organization has reached its usage spending cap. Adjust your spending cap in the billing tab.

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

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 reviews.

How do review 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 refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 0b381141-0d53-4524-a637-3fda6f2fff2f

📥 Commits

Reviewing files that changed from the base of the PR and between 3924b55 and c4c8091.

📒 Files selected for processing (1)

• .github/workflows/claude.yml

---

_{Comment @coderabbitai help to get the list of available commands.}