1ce42a9e59
- tdd-gate: pass criterion is the task's TEST_FILES scope (matches run-ci-tests.sh M19 P-14), not the full suite — contradicted qwen-code-methodology rule 5 in the same system prompt - tdd-protect: tests/ path described relative to project working dir (AGENT_WORKING_DIR is /workspace/project in repo composites) - qwen-code-methodology: task_complete tool DOES exist — rule 8 said the opposite; pytest examples use -q - airouter-code-tdd template: TT-39 runtime_overrides (max_result_bytes 24KB, max_history_turns 16) Claude-Session: https://claude.ai/code/session_012arAwUuBQrpnMzJ36mEVBk
1.6 KiB
1.6 KiB
TDD Gate — Tests Must Pass
You are operating in TDD mode. The test suite defines correctness. You must not finish until all tests pass.
Rules
- Run the task's test scope after every change. If the task names specific test files, that scope IS the passing criterion (the CI gate runs exactly those files); otherwise run the full suite.
- A red test suite is not acceptable output. If tests fail, keep working.
- Never skip, comment out, or delete tests. Tests are read-only (OS-enforced). Any attempt to modify them will fail.
- Never use
pytest --ignore,-k "not ...", or--deselectto hide failures. The passing criterion ispyteston the task's test scope with no filters. - Fix the implementation, not the tests. If a test looks wrong, you are wrong.
- Commit only when green. The finalize phase checks
TEST_PASS_REQUIRED=true— a failing suite will fail the task.
Workflow
# Run the task's test scope to see current state (use the file(s) named in the task)
python -m pytest <task test file(s)> -q --tb=short
# Implement until green
# ... edit source files ...
python -m pytest <task test file(s)> -q --tb=short
# Only when all green:
# finalize will commit and push via agent-repo
If you are stuck
- Read the failing test to understand exactly what it expects
- Read the spec (if present at
/workspace/project/spec/) for the subsystem under test - Check the error message carefully — most failures have a clear root cause
- Do not attempt workarounds that hide failures; fix the underlying behaviour