[CLAUDE] Docs: Harness-4 two-tier runtime-VERIFIED (spawn-test 2 chiều post-restart) + email-back AI_INFRA
Some checks failed
Deploy SOLUTION_ERP / build-deploy (push) Has been cancelled

- Spawn-test 2 chiều S57bis: H1 tooling-auditor (demote pin) self-report claude-opus-4-8[1m] + H2 harvest-curator (promote inherit) self-report claude-fable-5[1m] → nấc executed-file/PENDING-RESTART → RUNTIME-VERIFIED (adap-report §2/§5 + STATUS row). [1m] 1M-resolve SE tự verify.
- Email update 2026-06-11-se-to-ai_infra-harness-4-runtime-verified (nac sent, sha ecf1d587, honest n=1/chiều, hmw.js executed-file giữ) + _index OUTBOUND.
- Lesson env: CCD harness cache agent frontmatter — restart CLI mới ăn (2 data-point 06-10/06-11).
- Bundle 06-10 carry: 7 agent pin opus-4-8 + 4 inherit + hmw.js tier-map H4.5 + agents/README two-tier + 2 adap-report + email 06-10 + agent-memory delta (KEEP-ALL-5 H2-verified) + investigator L1→L2 archive curate.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
pqhuy1987
2026-06-11 12:12:22 +07:00
parent a62e797332
commit 17b23a418a
27 changed files with 236 additions and 38 deletions

View File

@ -21,7 +21,7 @@
| Gotchas | **58** | +1 S56 **#58** EF read-modify-write lost-update (`entity.X += n; SaveChanges` đua) → `ExecuteUpdateAsync` atomic increment + Serializable tx. (#57 backlog CLOSED S53) |
| User memory | **20** | re-grounded S54 (H1 disk-count — S53 base thật 19 không phải 18); +1 S54 `feedback_agent_cwd_relative_memory_misland` (sub cd subdir → MEMORY Write stray) |
| Skills | 6 | 3 domain + 3 ops |
| Sub-agents | **11** | Opus 4.8 1M · 9 product/quality (7 core + frontend-designer + database-agent) + 2 monitor INFORM-only (tooling-auditor H1 + harvest-curator H2). ✅ database-agent **verified-runtime S53** (spawn-test PASSED — caught Mig 46-unapplied-local drift) |
| Sub-agents | **11** | **two-tier H4 (06-10):** em main Fable 5 (1M) Max · 4 promote `inherit`=Fable 5 (reviewer·investigator-codebase·database-agent·harvest-curator) · 7 demote pin `claude-opus-4-8` (**runtime-VERIFIED 06-11** — spawn-test 2 chiều S57bis: H1 tooling-auditor self-report `claude-opus-4-8[1m]` + H2 harvest-curator `claude-fable-5[1m]`; `[1m]` 1M-resolve SE tự verify) · effort Max ×2 tier. 9 product/quality + 2 monitor INFORM-only. ✅ database-agent **verified-runtime S53** (spawn-test PASSED — caught Mig 46-unapplied-local drift) |
| RAG chunks | **2416** | Recovered S52 (S51 Qdrant DOWN → nay alive, rerank live 0.9375). Stale `last_indexed 05-29` (S42-S52 via store_memory stopgap; full re-index = AI_INFRA op cần VOYAGE_API_KEY). |
**Bundle hash live (prod):** admin `4SUwDLD8` · user `XdKzt9LL` (S55 — admin rotate 2× [master-data form rồi redesign]; user 1× [master-data]). Latest deploy Run #378 (`7feb53e`, ~4m24s): **Phase 1 FE redesign fe-admin** (density-first design system, giữ brand #1F7DC1) — admin bundle `B-d6893W``4SUwDLD8`, user `XdKzt9LL` UNCHANGED (scope-correct FE-admin-only), no new mig, health 200/200. Prior Run #377 (`69cb393`): Mig 48 applied prod · master data real Projects 6/6 · WorkItems 71 · Suppliers 3 · CAL01.Investor exact.

View File

@ -0,0 +1,40 @@
# adap-report — 2026-06-10-Governance-harness-4-model-tier-promotion
> SISTER = SOLUTION_ERP. Report-format LOCK (5 trường). Generated 2026-06-10 (S57-resume), apply by em main solo (governance file-work, single-writer; 2 spawn-test demoted + 1 reviewer-gate spawn). Refine/supersede phần SUB của `model-fable-5-max` (AM cùng ngày).
## 1. id-broadcast
`2026-06-10-Governance-harness-4-model-tier-promotion` (from: ai_infra · category: **Governance** · reviewer_gate: **PASS_WITH_FIXES ×2 applied** · nac: published · targets: **all-fit** · content_sha256 `3e9b9461…`). HARNESS-4 two-tier: lead giữ Fable 5 (1M) Max · sub default demote pin `claude-opus-4-8` (Max) · CHỈ promote-list justify theo tiêu chí H4.3 (a-d) giữ `inherit` · workflow tier-map H4.5 · email-back AI_INFRA H4.7 BẮT BUỘC · honest-claim H4.8.
## 2. nac G-011
**RUNTIME-VERIFIED (2026-06-11 — spawn-test 2 chiều post-restart, S57bis).** H1 tooling-auditor (demote-list) self-report nguyên văn "Opus 4.8 (1M context) · `claude-opus-4-8[1m]`" → **pin ĂN runtime** + 1M-resolve `[1m]` SE TỰ verify (hết lệ thuộc claim AI_INFRA s20). H2 harvest-curator (promote `inherit`) self-report `claude-fable-5[1m]`**inherit Fable 5 GIỮ nguyên**. Lead Fable 5 (1M) Max live. *Trail lịch sử:* **EXECUTED-FILE (2026-06-10) · runtime-PENDING-RESTART.** 11 file edited + verified grep. **Spawn-test n=2 demoted (H4.8) đã chạy NGAY → phát hiện SE-env divergence:** cả 2 self-report `claude-fable-5[1m]` (KHÔNG phải opus-4-8) → **SE env (CCD harness) KHÔNG fresh-read agent frontmatter mỗi spawn** — registry cache definition session-start (khớp SE-fact đã biết S47/S52: agent `.md` no-hot-reload, restart CLI mới ăn). Khác AI_INFRA s20 (fresh-read NGAY). → Demote pin = executed-file, hiệu lực runtime SAU restart; **re-spawn-test post-restart** mới nâng runtime-verified. **Lead Fable 5 = verified-runtime** (session live). **Promote-tier inherit→Fable = verified-live** (n=2 spawn 06-10 inherit-chain — định nghĩa promote không đổi nên post-restart giữ nguyên hành vi).
## 3. evidence
**PROMOTION-LIST (4 — giữ `model: inherit` = Fable 5 1M), justification + evidence per-vị-trí:**
| Vị trí | Tiêu chí | Justification | Evidence track-record |
|---|---|---|---|
| 🟥 reviewer | **(a) gate≥writer** | adversarial pre-commit cuối sau lead — gate yếu hơn writer = writer qua mặt vô tình | S51 bắt 1 MAJOR pre-commit (Driver FE↔BE required-mismatch) · S54 chain-verify role-string "Admin" thật (disarm decoy QTV) · S49 gate 3 adap-report |
| 🟦 investigator-codebase | **(b) verdict-nuôi-quyết-định** | verdict recon/audit mà em main + anh quyết theo; sai 1 verdict lan cả chuỗi | S56 pre-golive verdict (bắt dept-IT 0-active-user prod — test xanh không thấy) · S57 flag "master-write-open" → thành fix authz thật ×3 controller |
| 🔵 database-agent | **(b) verdict-class DB-lens** | read-advisory verdict schema/migration/concurrency nuôi quyết định migration-design | S53 first-spawn bắt Mig 46 committed-but-unapplied-local (203 SQLite-test + CI-prod đều MISS) · S56 review MAJOR → bump Serializable (gotcha #58 fix) |
| ⬜ harvest-curator | **(c) chống-rubber-stamp** | fidelity-gate phải DÁM từ-chối xác-nhận cái sai của CHÍNH LEAD | S56 GATE chấm 4.5/5 (KHÔNG rubber-stamp 5/5) buộc em main append Serializable-correction vào impl/test MEMORY trước đóng |
**DEMOTE-LIST (7 — pin `model: claude-opus-4-8`, H4.4):** 🟨 implementer-backend + 🟧 implementer-frontend (deterministic scaffold spec-sạch, double-gate reviewer+test+cicd sau lưng) · 🟪 test-specialist (artifact RED→GREEN observable, reviewer gate sau) · 🟩 cicd-monitor (checklist-verify deploy, evidence curl/sqlcmd deterministic — AI_INFRA cũng demote con tương đương) · 🟫 tooling-auditor (checklist-class propose-only — AI_INFRA demote chính con này) · 🟦 investigator-api (external research-gathering, ít verdict hệ-trọng; re-assess nếu track-record verdict xuất hiện) · 🩷 frontend-designer (execute-layer design, FD-rubric + screenshot-loop + reviewer-gate sau; giữ `effort: max` riêng sẵn có).
**WORKFLOW tier-map H4.5 (`hmw.js`):** `resolveModel(role, tier, i)` — promote-roles (investigator-codebase·reviewer·database-agent ∈ VALID_ROLES) → `undefined` (inherit Fable qua frontmatter) · demoted-roles → `undefined` (frontmatter pin tự lo) · **role-less → `'opus'`** (sweep-class CÓ CHỦ ĐÍCH — taskList do lead author từng run = đã phân loại lúc author, mirror lý-lẽ AI_INFRA worked-example) + log nhắc khai `tier:'fable'` khi hệ-trọng · **per-task `tier:'fable'|'opus'` override** (tier lạ → WARN + default). meta.description đã sync.
**Files edited (11 core + 3 bookkeeping):** 7× `.claude/agents/{implementer-backend,implementer-frontend,test-specialist,cicd-monitor,tooling-auditor,investigator-api,frontend-designer}.md` (`model: inherit``claude-opus-4-8`, GIỮ effort/tools) · `hmw.js` (tier-map + meta + args-comment + agent-call; invalid-role typo → fail-UP inherit per reviewer #7) · `agents/README.md` (header tier + upgrade-note 06-10 + ASCII EM-main Fable + spawn-line) · `STATUS.md` Sub-agents row (attribution per reviewer #2) · `ultra-on.md` P2 row — bookkeeping: 2 adap-report + 1 email outbox.
**SELF-CHECK broadcast:** lead Fable 5 (1M) Max live ✓ · justification per-vị-trí (bảng trên, KHÔNG list suông) ✓ · grep `model:` = đúng 7 `claude-opus-4-8` + 4 `inherit`, 0 file `[1m]` frontmatter ✓ · workflow gate=inherit/sweep='opus' ✓ · spawn-test đã chạy (n=2 demoted — kết quả = env-divergence finding, see §2) ✓ · email `/send-email ai_infra` SENT (`broadcasts/outbox/ai_infra/2026-06-10-se-to-ai_infra-harness-4-adopt-report.md`, hash-verified) ✓ · nấc G-011 chuẩn (executed-file, KHÔNG claim runtime-verified) ✓.
**🟥 reviewer-gate (pre-send + pre-commit): PASS-with-fixes — ALL applied.** 0 CRITICAL / 0 MAJOR floor-violation · 1 REQUIRED (sequencing: hash thật trước `nac: sent` — enforced) + 6 MINOR (STATUS attribution · hmw.js log banner "same-model"→two-tier · meta 8→9-agent · files-count thống nhất · `[1m]` body-match count cập nhật · email ④ cite direct-evidence) + #7 design-fix (invalid-role typo → fail-UP inherit, KHÔNG rơi 'opus'). **Reviewer self-report `claude-fable-5[1m]` = promote-tier DIRECT evidence n=1** (promote-list member thật, mạnh hơn inherit-chain n=2 demoted-on-cache). Cross-verify độc lập: 8/8 evidence-claim khớp HANDOFF/STATUS/memory/working-tree, 0 claim phịa.
## 4. tailored-gì + skip-gì-vì-sao
- **FUNCTION-floor adopt FULLY:** H4.1→H4.8 giữ đủ (lead không demote · tiêu chí a-d nguyên văn · email-back · honest-claim).
- **FORM tailored SE:** (a) map vai theo function-class SE roster 11 (không copy tên AI_INFRA): promote 4/11 — trong đó database-agent là vị trí SE-specific (AI_INFRA worked-example không có); (b) harvest-curator promote (c) dù AI_INFRA chỉ ghi "vùng-xám-nghiêng-giữ" — SE evidence S56 4.5/5 đủ mạnh; (c) hmw.js role-less default `'opus'` = đúng nhánh "taskList lead-author từng run" của worked-example (KHÔNG phải nhánh "default nghiêng inherit"); (d) frontend-designer giữ `effort: max` frontmatter riêng (demote model KHÔNG đụng effort).
- **SKIP:** không có helper Sonnet by-design (n-a) · không project-pin model phải gỡ (n-a — khác VIPIX).
## 5. honest-caveat
- **Nấc = RUNTIME-VERIFIED 06-11** (G-011) — ✅ RESOLVED post-restart: spawn-test demote n=1 (tooling-auditor `claude-opus-4-8[1m]`) + promote n=1 (harvest-curator `claude-fable-5[1m]`), S57bis. Lịch sử 06-10: executed-file · runtime-PENDING-RESTART. SE env ≠ AI_INFRA env: spawn-test n=2 PROVE frontmatter KHÔNG fresh-read trên CCD harness (cả 2 demoted vẫn self-report `claude-fable-5[1m]`). Sau restart CLI → re-spawn-test ≥2 demoted self-report `claude-opus-4-8*` mới claim runtime-verified. **Đây là finding ngược với AI_INFRA s20 "fresh-read không cần restart"** — đã báo trong email H4.7 mục ⑤ (surface-the-need §K; broadcast tự dặn "đừng kế thừa kết luận mù" — đúng).
- **Context-variant demoted: ✅ VERIFIED 06-11** — tooling-auditor self-report "Opus 4.8 (1M context)" → `[1m]` runtime-resolve 1M trên SE confirmed (trước đó chỉ là claim AI_INFRA s20).
- **Effort cả 2 tier:** env machine-wide `max` — KHÔNG introspect được từ trong agent (H4.8), không claim "verified effort".
- **Risk demote thấy được:** tooling-auditor/cicd-monitor nếu verdict-quality giảm rõ sau vài session → adap-request đề xuất promote lại (theo dõi qua H1/H2 chính chúng + em main).
- **Quota note: ✅ RESOLVED 06-11** — restart done, demote-pin ăn runtime → tiết kiệm two-tier bắt đầu từ S57bis.

View File

@ -0,0 +1,25 @@
# adap-report — 2026-06-10-Governance-model-fable-5-max
> SISTER = SOLUTION_ERP. Report-format LOCK (5 trường). Generated 2026-06-10 (S57-resume), apply by em main solo (governance file-work, single-writer). Đọc CÙNG broadcast PM cùng ngày `harness-4-model-tier-promotion` (supersede phần SUB của broadcast này).
## 1. id-broadcast
`2026-06-10-Governance-model-fable-5-max` (from: ai_infra · category: **Governance** · reviewer_gate: **PASS** · nac: published · targets: **all-fit** · content_sha256 `c450d36c…`). Layer C model-line: lead = **Fable 5 (1M) + effort Max** thay Opus 4.8 1M. ⚠️ SUPERSEDE-NOTE trong chính broadcast: phần SUB (floor #2 "sub giữ `model: inherit`") superseded bởi `harness-4-model-tier-promotion` (PM cùng ngày) — áp 2 broadcast bất kỳ thứ tự → end-state = two-tier.
## 2. nac G-011
**LEAD-part = VERIFIED-RUNTIME (session S57-resume 2026-06-10):** em main session này đang chạy `claude-fable-5[1m]` (system-identity live — UI/session = source-of-truth, không phải config suông). Machine-wide user-settings do AI_INFRA update sẵn → SE **no-action**. **SUB-part = SUPERSEDED** → xử lý + nấc ghi tại report `2026-06-10-Governance-harness-4-model-tier-promotion.md`.
## 3. evidence
- **Project-pin check (SELF-CHECK #2):** grep `"model"` trong `.claude/settings*.json` repo SE = **0 match** → SE không pin, ăn user-level. (Broadcast recon cũng ghi: chỉ VIPIX pin — SE thuộc nhóm 5 sister no-action.)
- **gotcha #37 check (SELF-CHECK #3):** grep `[1m]` frontmatter `.claude/agents/*.md` = 0 value match (2 match body-text hợp lệ: database-agent.md:46 checklist + agents/README.md:9 upgrade-note 06-10 — không phải frontmatter value).
- **Spawn-test inherit (SELF-CHECK #4):** 2 sub spawn 2026-06-10 self-report `claude-fable-5[1m]` (inherit từ lead) — inherit-chain Fable 5 LIVE.
- **Effort Max:** env `CLAUDE_CODE_EFFORT_LEVEL=max` machine-wide giữ nguyên (zero-action per broadcast).
## 4. tailored-gì + skip-gì-vì-sao
- **Adopt nguyên:** lead model-line Fable 5 (1M) Max — config universal, không tailor gì.
- **Policy-doc amend:** SE không có policy-doc model riêng — model-line ghi tại `agents/README.md` header + `STATUS.md` Sub-agents row (đã amend cùng harness-4, giữ trail Opus 4.8 trong history Recently-Done/session-log — không xóa).
- **SKIP floor #2 sub-inherit:** superseded by harness-4 two-tier (chính broadcast tự note) — KHÔNG áp "mọi sub inherit Fable".
- **Cheap-tier (floor #3):** SE không có helper Sonnet by-design → n-a.
## 5. honest-caveat
- **Picker re-confirm effort trên Fable 5:** session này = CCD harness (không thấy picker CLI trực tiếp); env var đúng giá trị `max` + model-id `[1m]` live. Per broadcast caveat: nếu picker CLI sau này KHÔNG hiện `max` trên Fable 5 → báo AI_INFRA (chưa quan sát được từ trong session — effort KHÔNG introspect được, H4.8).
- Phần SUB mọi claim → report harness-4 (đó mới là end-state).