Skip to content
Merged

test #1266

Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 4 additions & 6 deletions .github/workflows/claude-code-review.yml
Original file line number Diff line number Diff line change
Expand Up @@ -28,19 +28,18 @@ jobs:

- name: Run Claude Code Review
uses: anthropics/claude-code-action@v1
env:
PATH: /home/runner/.local/bin:${{ env.PATH }}
with:
claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
github_token: ${{ github.token }}

plugin_marketplaces: "https://github.com/anthropics/claude-code.git"
plugins: "code-review@claude-code-plugins"

# NOTE: do NOT use --dangerouslyDisableSandbox (it can crash the CLI).
# This flag is for non-interactive CI runs (bypasses approval prompts).
Copy link

Copilot AI Feb 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The comment above claude_args says "This flag is for non-interactive CI runs (bypasses approval prompts)", but the flag being warned about there is --dangerouslyDisableSandbox (which is not being used). The approval-prompt bypass behavior belongs to --dangerously-skip-permissions; please reword/move the comment so it's unambiguous which flag it refers to.

Suggested change
# This flag is for non-interactive CI runs (bypasses approval prompts).
# The --dangerously-skip-permissions flag is for non-interactive CI runs (bypasses approval prompts).

Copilot uses AI. Check for mistakes.
claude_args: >
--dangerously-skip-permissions
--dangerouslyDisableSandbox
--max-turns 80
--max-turns 10
--allowedTools
"Bash"

Expand All @@ -58,7 +57,7 @@ jobs:
3) find .claude/rules -maxdepth 1 -name "*.md" -print | head -n 10 | xargs -I{} cat "{}" 2>/dev/null || true
4) gh pr view ${{ github.event.pull_request.number }} --repo ${{ github.repository }} --json title,body,files,changedFiles,additions,deletions,headRefOid
5) gh pr diff ${{ github.event.pull_request.number }} --repo ${{ github.repository }}
6) Post ONE top-level PR comment, then STOP.
6) Post ONE top-level PR comment titled "Claude Code Review", then STOP.

Output format:
- Head SHA
Expand All @@ -67,7 +66,6 @@ jobs:
- Findings with file + line numbers when possible
- If no issues: 0–3 improvement opportunities (only if confident)

Post ONE top-level PR comment titled "Claude Code Review".
If posting is blocked, write the full review to the GitHub Actions job summary instead, then STOP.

additional_permissions: |
Expand Down
2 changes: 1 addition & 1 deletion CLAUDE.md
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ source ./mfc.sh load -c p -m c # Load Phoenix CPU modules

# Other
./mfc.sh validate case.py # Validate case file without running
./mfc.sh params <query> # Search ~3,400 case parameters
./mfc.sh params <query> # Search 3,400 case parameters
Copy link

Copilot AI Feb 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

./mfc.sh params line now says "Search 3,400 case parameters" (exact), but later in the same doc the source-of-truth count is described as "~3,400". Consider keeping these consistent (either both approximate or both exact) to avoid the doc getting stale as the parameter count changes.

Suggested change
./mfc.sh params <query> # Search 3,400 case parameters
./mfc.sh params <query> # Search ~3,400 case parameters

Copilot uses AI. Check for mistakes.
./mfc.sh clean # Remove build artifacts
./mfc.sh new <name> # Create new case from template
```
Expand Down
Loading