e9124fc6de
All checks were successful
Deploy SOLUTION_ERP / build-deploy (push) Successful in 5m30s
- NHOM A restart-verify: A1 tier:'fable' tren reviewer pin-opus -> resolved claude-fable-5 (spawn-param THANG); A2 no-tier -> claude-opus-4-8 DU lead=Fable (pin an runtime); A3 autoMemory WRITE-path OK (project_h23_spawn_precedence.md moi). - B1 sweep all-inherit floor-song: 15 dong/5 file + 3 cung-lop lot-pattern + 5 dong H23-stale o 3 command-file (H1 bat) -> VA HET; spawn-model-audit Section-D flush H8->S124 + effort-check (fault-inject 2-chieu PASS, 14 duong-gia -> 0); governance-detectors C3 seed +worker-tier-pin; re-grep 0 floor-song; suite 45 = baseline 0-new. - vocab-alias-map §3 canonical flip -> worker-tier-pin (all-inherit/two-tier = 2 alias cu); STATUS:6 FROZEN-diary label (het H24-3 lag); STATUS:25 + agents/README:5 sync. - Email hub h23-precedence-test-result stamp 945cf3ad (reviewer-gate FAIL bat 3 loi truoc stamp -> gotcha #83 aggregate-cumulative) + _index cung luot. - B3/B4 owner-gated: soan b3-b4-owner-gated-proposals.md CHO ANH (mega-line retier + budget:74 wording) — 0 apply. - Closeout: harvest 4 lane + 2 monitor (H2 GATE PASS 5/5, 0/29 orphan; H1 3/4 clean + 5-spot fix) + curate moved-not-cut reviewer/inv-cb + carry disposition (DONG 2: restart-s124, h23-fable-test-postrestart; MO re-stamp 9) + H24 counter=5 + pilot H22 D5 (pause-roundtrip + hook-fire re-verified; cross-model PENDING). - Governance/tooling-only: 0 prod-code, 0 mig, test 509 GIU, bundle FROZEN. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
27 lines
3.7 KiB
JSON
27 lines
3.7 KiB
JSON
{
|
|
"_note": "Harness-24 (S121, 2026-07-15, wave adap-6-broadcast W2) session counter for lead-self-audit cadence. THIS FILE HOLDS STATE ONLY - every cadence NUMBER lives in .claude/agent-memory/memory-budget.json -> h24_cadence (single-source, H24 section 2(3)). Never copy the digits here.",
|
|
"_why_content_based_not_blind_increment": "Owner-decisions-15-07-2026 Q2, trap found by lane E: the Stop-hook .claude/hooks/wal-flush.ps1 auto-commits on EVERY turn-boundary. A blind counter++ would therefore tick many times per real session and the cadence would be meaningless. So a tick is CONTENT-ADDRESSED: it is keyed on the repo HEAD sha at tick time. Ticking twice on the same HEAD is a NO-OP, which is what makes running /session-start twice in a row safe (acceptance: 2x /session-start on the same HEAD => +1, not +2).",
|
|
"_why_this_path": "Deliberately .claude/governance/ and NOT .claude/agent-memory/. The hook covers exactly 3 paths (.claude/WAL.md, agent-memory/, workflows/runs/); .claude/governance/ is OUTSIDE all three, so this file is never swept into a 'wal:' commit as a side effect. Compare .claude/agent-memory/.mfe-state.json, which IS inside the hook's reach - a counter must not live there.",
|
|
"_contract": {
|
|
"tick": "tick(session, head): if head == last_ticked_head -> NO-OP (idempotent, same HEAD = same real session state). Else counter = counter + 1, last_ticked_session = session, last_ticked_head = head, last_ticked_at = date.",
|
|
"fail_loud_on_regress": "If an incoming counter is LOWER than the stored counter, or last_ticked_head names a commit not reachable from HEAD, DO NOT silently reset: report to owner. A counter that moves backwards means the state file was rolled back or hand-edited, and a silent reset would hide the cadence gap.",
|
|
"overdue": "OVERDUE(light) when (counter - last_audit.light_at_counter) >= h24_cadence.light_every. Same shape for deep_every. Skipping sessions does NOT lose the debt - the gap is measured from the counter, not from wall-clock, so a missed session surfaces as OVERDUE rather than vanishing.",
|
|
"jump": "jump_on_class_repeat (h24_cadence): if ONE flag class from lead_self_audit.flag_classes repeats N times, pull the next audit forward regardless of the counter.",
|
|
"writer": "Lead is single-writer. Wired at /session-start (W3 owns the ritual; W2 owns this file + its shape)."
|
|
},
|
|
"_seed_honesty": "Seeded UNTICKED on purpose. counter=0 and last_ticked_* = null mean 'no tick has ever happened', which is the truth at S121 - the ritual that performs the tick lands in W3. Seeding a fake first tick here would make the very first cadence reading a lie, and H24 exists to catch exactly that kind of invented number.",
|
|
"counter": 5,
|
|
"last_ticked_session": "S126",
|
|
"last_ticked_head": "f9fa77d679be704db2448478390bffaaa9d721b8",
|
|
"last_ticked_at": "2026-07-16",
|
|
"last_audit": {
|
|
"light_at_counter": 3,
|
|
"deep_at_counter": 3,
|
|
"_note": "Counter value at which the last light/deep self-audit actually ran. S124 (2026-07-15): FIRST-EVER real run of both H24 vai (owner-triggered dogfood at counter=3) — full 2-vai coverage (view + omission), 0-garble. Credited as BOTH light+deep (thorough audit) so next light~counter 9, next deep~counter 18. lead-view: 9 flag; lead-omission: 4 flag+1 INFORM (carry-age structurally vacuous — escalated owner)."
|
|
},
|
|
"class_repeat": {
|
|
"_note": "Rolling tally per flag class from lead_self_audit.flag_classes (memory-budget.json). Key = class name, value = consecutive-audit repeat count. S124 first audit = SEED (fired-once), not repeats yet (per lead-view-auditor honest-note). jump_on_class_repeat=3.",
|
|
"counts": { "view-residual-asym": 1, "view-stale-count": 1, "gap-carry-dropped": 1, "gap-decision-sunk": 1 }
|
|
},
|
|
"history": []
|
|
} |