/trekexecute no longer builds steps itself. Each plan step is built by one
fresh helper (new agent step-implementer: opus, effort high, no Agent tool)
and judged by one controller (a general helper on opus) that reads the
diff from a recorded start_sha and gives two verdicts, spec and quality.
Fix rounds go up, maximum 5: three fixes by a fresh helper, then back to
the plan, then to the operator. No cheaper-model ladder.
Proof is a command, never the model's word:
- lib/verification/red-proof.mjs: the step's test must fail at the start
point and pass at the result (exit 0/1/2; 2 is never green). Reproduces
the 02243c6 red-first measurement (6 of 55) through the shim fixture.
- lib/verification/test-integrity.mjs: the floor guard on the diff
(removed asserts, skipped/deleted tests, muted checks, stubs, loosened
thresholds). Over the last 150 commits: 149 clean, 1 real finding.
- lib/verification/done-line.mjs: DONE step N only when the test command
exits 0.
Test first is required from plan_version 1.8. The test lock (K8) is used
through its CLI and reported as not-locked while it is missing. A run
stops only on a closed list of four classes; every other call goes into a
decision log with its cost if wrong. Without a passing run-the-thing
criterion the result is not verified end to end, never green.
Handover 5 gains optional per-step start_sha, report_path, red_proof,
test_lock, fix_rounds (0-5) and run-level decisions and end_to_end; old
progress files still validate and resume.
No isolation on the helper: measured, a worktree-isolated subagent
branches from the default branch (02f320f), not the executor's HEAD
(2c89a6b), so it would miss the earlier steps.
Borrowings credited in commands/trekexecute.md ## Credits (Superpowers,
ai-native-sdlc, Kiro, GitHub Spec Kit, agent-skills, Cherny).
Tests: 1411 -> 1457 (1455 pass, 0 fail, 2 skipped).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/trekexecute writes run status stopped (dirty-tree stop, entry-condition stop, escalation) and step status blocked (Step 0 sandbox sentinel); the validator rejected the first and warned on the second. Both are real states lib/util/session-orders.mjs already reads (ENDED_BAD), so the validator learns them. The step-status list is exported as PROGRESS_STEP_STATUSES (was an inline literal) so tests check prose against it instead of keeping a copy. docs/HANDOVER-CONTRACTS.md Handover 5 rows updated.
Red: 3 of 4 new tests fail on the pre-fix code (stopped run status, PROGRESS_STEP_STATUSES export, blocked step status). Regression guard (green on arrival): every run status but completed stays resumable.
progress-validator 16/16. Suite 1368 (1366/0/2).
Voyage order 20261005T104513Z-1250514346, plan step 1/5.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
