- Add Pause icon with amber color for paused accounts
- Show styled "PAUSED" badge instead of plain error text
- Distinguish paused state from other errors visually
- Check isAccountPaused() before readAuthData() in fetchAccountQuota()
- Return "Account is paused" instead of confusing "Auth file not found"
- Improves UX by explaining why quota fetch fails for paused accounts
CLIProxyAPI's watcher uses filepath.Walk() which recursively scans
all subdirectories of auth/. Moving paused tokens to auth/paused/
subdirectory didn't hide them from CLIProxyAPI, causing token refresh
loops where paused tokens were immediately recreated.
Solution: Use auth-paused/ as a sibling directory instead of auth/paused/
subdirectory. This places paused tokens completely outside CLIProxyAPI's
scan path, preventing token discovery and refresh.
Path change:
- Before: ~/.ccs/cliproxy/auth/paused/
- After: ~/.ccs/cliproxy/auth-paused/
Address PR review feedback:
- Wrap fs.renameSync() in try-catch for pauseAccount/resumeAccount
- Wrap fs.mkdirSync() in try-catch for paused directory creation
- Add idempotent checks (skip if already paused/active)
- Rely on syncRegistryWithTokenFiles() for recovery on failure
Follows same error handling pattern as removeAccount().
Pausing an account now physically moves the token file to auth/paused/
subdirectory, preventing CLIProxyAPI from discovering and using it.
Resume moves the file back to auth/ directory.
Changes:
- Add getPausedDir() helper for paused tokens location
- Update pauseAccount() to move token to paused/ subdir
- Update resumeAccount() to move token back to auth/
- Update syncRegistryWithTokenFiles() to check both directories
- Update removeAccount() to clean up from both directories
- Update getAccountTokenPath() to return correct path based on state
Fixes#337
- Add more allowed bash patterns: gh issue view, gh api, git commands
- Add base tools: Edit, LS for better flexibility
- Update prompt to write pr_review.md in working dir (not /tmp/)
- Add step to Read before Write to avoid security block
- Add explicit rules about avoiding shell operators (||, &&, <<)
- Allow rm pr_review.md for cleanup
Previous run had 9 tool rejections wasting ~5000 tokens due to:
- gh issue view not allowed (only gh pr view was)
- /tmp/ outside working directory
- Write without Read blocked
- Complex shell operators blocked
express-rate-limit was imported in auth-middleware.ts but only the
@types/express-rate-limit package was declared in devDependencies.
This caused "Cannot find module 'express-rate-limit'" error when
running `ccs config` after installing v7.20.0 globally.
Closes#333
- Pass verbose flag through fetchQuotaWithDedup to fetchAccountQuota
- Change verbose logging from console.log to console.error (stderr)
- Keep quotaPercent optional (semantically correct for cases without quota)
- Use /api/provider/agy endpoint for proper model routing
- Set ANTHROPIC_DEFAULT_*_MODEL to route Haiku/Sonnet/Opus correctly
- Disable telemetry, error reporting, bug command
- Set max output/thinking tokens
- Change calculateAverageQuota() to return null instead of 100 when no model data
- Update callers to use null coalescing (?? 0) for health check thresholds
- Display "N/A (fetch unavailable)" for null quota values
- Add --verbose flag to quota-related functions for troubleshooting
- Add debug logging: token refresh status, API response, errors
Add `--list-backups` and `--restore` options to the ccs persist command
for backup management. Enables users to list and restore settings.json
backups. Updated CLAUDE.md to document persist command.
Resolves#248
Co-authored-by: Leynier Gutiérrez González <leynier41@gmail.com>
Add backup management functionality to the persist command:
- List available backups with timestamps and dates
- Restore from most recent or specific backup
- Improved error handling for corrupted settings.json
- Updated CLAUDE.md to document the persist command and the exception to the non-invasive constraint
Add Bash(echo *) and Bash(cat *) patterns to allow heredocs and pipes.
This gives the AI reviewer flexibility to use any method for posting
multi-line review comments while remaining safe (shell-operator aware).
Changed pattern from `Bash(gh pr comment:*)` to `Bash(gh pr comment *)`
to match space-separated args. Updated prompt to discourage heredocs
and pipes which don't match the pattern, causing 6+ retry attempts.
Root cause: When the bot posts a review comment, GitHub fires an
issue_comment event that joins the same concurrency group and cancels
the in-progress run BEFORE job `if` conditions are evaluated.
Solution: Non-actionable triggers (bot comments, comments without
/review) get a unique per-run group via format('skip-{0}', github.run_id),
while legitimate triggers share the PR-based group for proper
cancellation of outdated reviews.
- Add `synchronize` event to trigger on new commits pushed to PR
- Add `reopened` event to trigger when PR is reopened
- Update documentation comments to reflect new behavior
- Keep cancel-in-progress to prevent stale reviews
Fixes issue where AI review only ran on PR creation, requiring
manual /review comment for subsequent commits.
- Fix React side effect: move navigate() to useEffect in LoginPage
- Remove misplaced express-rate-limit from ui/package.json
- Add bcrypt hash format validation before bcrypt.compare
kaitranntt