Kjell Tore Guttormsen
abc3083c1e
/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 the02243c6red-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>
6.2 KiB
6.2 KiB
Voyage JSONL stats — schema audit (v4.1 input)
Purpose: Field-allowlist input for v4.1 OTel exporter (Step 11). Lists every field every voyage stats JSONL writer emits today, plus the additive fields v4.1 introduces. Load-bearing for Step 11 (field-allowlist) and Step 8 (stats plumbing).
PII-flag:
command_excerptfromhooks/scripts/post-bash-stats.mjsslices the first 120 chars of an arbitrary Bash command — may contain operator paths, branch names, or fragments of secrets that survived the secrets-hook. CWE-212 (Improper Cross-boundary Removal of Sensitive Data). The OTel exporter MUST NOT export this field unless the operator explicitly opts in viaVOYAGE_EXPORT_INCLUDE_COMMAND_EXCERPT=1(deferred to v4.2 — v4.1 hard-excludes).Additive v4.1 fields:
profile,phase_models,parallel_agents,external_research_enabled,profile_source. All are forward-compat: existing v4.0 consumers ignore unknown keys, v4.1 consumers get richer signal.
Field table per JSONL writer
| schema_id | fields | writer_path | line_ref | v4.1 additive | PII |
|---|---|---|---|---|---|
| trekbrief-stats | ts, task, slug, mode, interview_turns, review_iterations, brief_quality, research_topics, auto_research, auto_result, intent_approved, project_dir, order_id, order_claimed_at, order_reason | commands/trekbrief.md (orchestrator-emit Phase 7; order_* added by lib/stats/stats-append.mjs) | trekbrief.md:961-976 | profile, phase_models, profile_source | none |
| trekresearch-stats | ts, question, mode, scope, engine, slug, project_dir, brief_path, dimensions, dimensions_baseline, dimensions_baseline_preserved, effort, conv_turns, empty_turns, unique_sources, agents_local, agents_external, gemini_used, confidence, contradictions, open_questions | commands/trekresearch.md (orchestrator-emit Stats tracking) | trekresearch.md:634-676 | profile, phase_models, parallel_agents, external_research_enabled, profile_source | none |
| trekplan-stats | ts, task, mode, slug, brief_path, project_dir, codebase_size, codebase_files, agents_deployed, deep_dives, research_briefs_used, research_scout_used, critic_verdict, guardian_verdict, outcome | commands/trekplan.md (orchestrator-emit Phase 12) | trekplan.md:805-826 | profile, phase_models, parallel_agents, profile_source | none |
| trekexecute-stats (Phase 9 record) | ts, plan, plan_type, mode, result, steps_total, steps_passed, steps_failed, steps_skipped, failed_at_step | lib/stats/stats-append.mjs (trekexecute.md Phase 9) | trekexecute.md:2263-2285 | profile, phase_models, profile_source | none |
| trekexecute-stats (autonomy events) | ts, event, known_event, payload | lib/stats/event-emit.mjs emit() |
event-emit.mjs:78-99 | payload.profile, payload.phase_models, payload.profile_source | none |
| trekexecute-stats (PostToolUse Bash) | ts, session_id, command_excerpt, duration_ms, success | hooks/scripts/post-bash-stats.mjs (Bash PostToolUse) | post-bash-stats.mjs:42-54 | none (hook is plugin-level, not profile-aware) | command_excerpt (CWE-212) |
| trekreview-stats | ts, slug, verdict, counts (BLOCKER/MAJOR/MINOR/SUGGESTION), reviewed_files_count, mode, duration_ms | commands/trekreview.md (orchestrator-emit Phase 8) | trekreview.md:255 | profile, phase_models, profile_source | none |
| trekcontinue-stats | ts, project, next_session_label, status | commands/trekcontinue.md (orchestrator-emit Phase 5) | trekcontinue.md:289 | profile, profile_source | none |
| token-usage | ts, session_id, scope, model, tokens_input, tokens_output, tokens_cache_creation, tokens_cache_read, cost_usd, is_estimate, price_table_version | lib/stats/token-usage.mjs captureTokenUsage (via hooks/scripts/otel-export.mjs Stop hook, opt-in VOYAGE_TOKEN_METER) |
token-usage.mjs:buildRecord | n/a (SKAL-2 schema) | session_id (stripped at export) |
Field-allowlist input for Step 11
The OTel exporter (Step 11 lib/exporters/field-allowlist.mjs) MUST inline the
following static const arrays (NOT load from this file at runtime — Step 11
explicit constraint: INLINE static const, IKKE runtime fra tests/fixtures):
EXPORT_ALLOWLIST (numeric/bool/short-string fields safe for OTel metric labels):
ts, slug, mode, brief_quality, auto_research, auto_result,
codebase_size, codebase_files, agents_deployed, deep_dives,
agents_local, agents_external, gemini_used, dimensions, confidence,
contradictions, open_questions, interview_turns, review_iterations,
research_topics, research_briefs_used, research_scout_used,
critic_verdict, guardian_verdict, outcome, plan_type, result,
steps_total, steps_passed, steps_failed, steps_skipped, failed_at_step,
verdict, reviewed_files_count, duration_ms, status, next_session_label,
event, known_event, success, scope,
profile, profile_source, parallel_agents, external_research_enabled,
model, tokens_input, tokens_output, tokens_cache_creation, tokens_cache_read,
cost_usd, is_estimate, price_table_version
EXPORT_DENYLIST (PII or high-cardinality, never export):
task, question, project_dir, project, plan, brief_path, command_excerpt, payload, counts, phase_models, session_id,
order_id, order_claimed_at, order_reason
Notes:
taskandquestionmay contain user-content prose → high-cardinality + PII risk.project_dirand paths leak filesystem layout.command_excerptper CWE-212 above.phase_modelsis a structured object (6 keys) — too high-cardinality for label; profile name (profile) is the safe summary. v4.2 may revisit if operators ask.counts(review BLOCKER/MAJOR/MINOR/SUGGESTION) is a nested object — Step 11 exporter flattens tovoyage_review_counts_blocker/_major/_minor/_suggestionmetrics rather than a label.session_idis a UUID — high-cardinality, not useful as a label, log-only.
Cross-reference
- Step 8 (stats plumbing) — adds
profile+phase_models+profile_sourceto all 6 orchestrator-emit sites listed above. - Step 11 (field-allowlist) — codifies the EXPORT_ALLOWLIST/DENYLIST arrays above
as inline static consts in
lib/exporters/field-allowlist.mjs. - Step 9 (Prometheus textfile) — emits one metric line per allowlist-numeric field per JSONL writer; PII-flagged fields are dropped at format-layer, not export-layer.