Menü
Invokes the test-runner subagent and emits the run_tests workflow sentinel. Used by Workflow Step 6.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Conduct a decision-tree interview with the user to lock in requirements, motivation, scope, and non-goals before planning.
Stage 3 of three-stage planning pipeline. Produce a file-level implementation plan via detail-planner/detail-reviewer loop, then get user approval. Inputs are confirmed intent (<session-id>-intent.md) and outline (<session-id>-outline.md) from prior stages.
Edit source code for the current task. Delegates editing and lint/typecheck/self-repair to a subagent.
Plan and write test cases with high reasoning effort. Test iteration runs in a subagent to minimize confirmations.
Explore the codebase to understand existing patterns, constraints, and relevant files before planning.
Investigate git history, docs/history.md, and GitHub issue/PR timeline since the relevant issue opened, to surface changes that may invalidate the issue's premises.
| name | run-tests |
| description | Invokes the test-runner subagent and emits the run_tests workflow sentinel. Used by Workflow Step 6. |
| tools | Agent, Bash |
| model | sonnet |
| user-invocable | false |
Run the project test suite via the test-runner subagent and emit the workflow sentinel.
When a hook blocks a sanctioned command, a fallback path is taken, or any unexpected outcome occurs, report via supervisor-report — see rules/supervisor-reporting.md.
RNT-1. Resolve merge-base (fallback chain):
git fetch origin main --no-tags 2>/dev/null, then merge_base=$(git merge-base origin/main HEAD).origin/main absent: merge_base=$(git merge-base main HEAD).main absent (shallow clone / detached): merge_base=HEAD~1; emit warning [run-tests] merge-base fallback: HEAD~1 (no main ref).HEAD~1 unavailable (root commit): emit [run-tests] cannot resolve merge-base; skipping selection and treat as empty selection (go to step RNT-5 empty-selection policy).RNT-2. Tier 1 — mechanical stem match.
tier1_tests=$(bin/select-tests.sh "$merge_base")
Filename stem substring match only. No frontmatter reading.
RNT-3. Tier 2 — LLM semantic match.
For each tests/*.sh not in tier1_tests and not under tests/_archive/:
# Tests: and # Tags: lines (single-line, within head -n 10).git diff --name-only "$merge_base"...HEAD and diff body.# Tests: path overlaps a changed file, OR # Tags: token semantically matches a changed subsystem.RNT-4. Tier 3 — default skip.
All remaining tests are skipped unless RUN_ALL_TESTS=1 or --all is passed explicitly.
RNT-5. Empty-selection policy (no silent --all fallback).
If Tier 1 + Tier 2 = 0 tests:
[run-tests] docs-only change; skipping tests and skip.[run-tests] no tests matched; user judgment required and ask the user: skip / --all (explicit opt-in) / specify tests. Never auto-fallback to --all — that recreates the #673 hang.RNT-6. Run tests.
Pass the final list as positional args to tests/run-all.sh. Use tests/run-all.sh --all only when the user explicitly opts in. Never pass auto-detect.
RNT-7. Invoke test-runner subagent with the resolved command and working directory. Return structured YAML.
RNT-8. Parse the YAML block returned by the agent.
RNT-9. Emit sentinel as a separate Bash call:
status: pass → echo "<<WORKFLOW_MARK_STEP_run_tests_complete>>"status: fail | timeout | runner-error → echo "<<WORKFLOW_MARK_STEP_run_tests_pending>>"RNT-10. If status is not pass, surface: summary / failing_tests / log_tail.
auto-detect.--all to tests/run-all.sh.--all fallback.