What does this PR do?

When a provider returns an overloaded message (e.g. Z.AI code 1305: "temporarily overloaded, please try again later"), the "try again" substring matched _RATE_LIMIT_PATTERNS, causing it to be classified as rate_limit with should_rotate_credential=True. This exhausted the credential pool for what is actually a server-side capacity issue.

Related Issue

Fixes #14038

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ✅ Tests (adding or improving test coverage)
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

• agent/error_classifier.py: Added overloaded error classification distinct from rate_limit
• tests/agent/test_error_classifier.py: Tests for overloaded classification (121 passed in full suite)

How to Test

1. Run:

   python -m pytest -o 'addopts=' tests/agent/test_error_classifier.py -v

2. Confirm result: 121 passed.

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform: macOS 15 (Darwin 24.6.0)

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A

Screenshots / Logs

python -m pytest -o 'addopts=' tests/agent/test_error_classifier.py -v
# 121 passed