[CLAUDE] Docs: S94 nâng cap lead 220K→380K (anh-directed) + re-tier STATUS/HANDOFF mega-line

- Cap lead_tokens 220K→380K (memory-budget.json canonical; SE-override, lead KHÔNG còn AI_INFRA-parity, subs giữ 60K/50K). Mark H-15 v4-delta RC-pqhuy1987-29-06-2026-23-25-50. Flush 3 derived echo (ACTIVE-MARKS · session-start §2.1.6 · engine §G adopt-delta).
- Re-tier mega-line (fix Read-25K/call OOM + token-cost): STATUS 389→89 dòng (mega-line 59.6K→7.1K char) · HANDOFF 732→12 dòng. Live 332KB→34KB (−90%). Session ≤S90 → docs/_archive/STATUS-HANDOFF-tier-S94 (0 byte-loss: new+archive = orig + 995B pointer).
- Verify: detector 27=baseline (0 broken-pointer mới) · canonical mig59/test434/gotcha76/table88 intact · MFE live-read 380K · conservation spot-check PASS.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.claude/agent-memory/memory-budget.json

@@ -78,9 +78,9 @@
     "_note": "Harness-15-v2 (S82, 2026-06-21): UPDATED by delta broadcast 2026-06-20-Governance-harness-15-v2-hot-feed-update (supersedes_scope = tier-1-sizing + L2/L3-caps ONLY; rest of H15 unchanged). TWO CHANGES vs S81: (1) Tier-1 = HOT-FEED LARGE per-role (was flat 12K -- too thin, caused lead to forget work across sessions); (2) L2/L3 caps REMOVED (on-demand, no artificial tier-limit, bounded only by model context window). Still the SECOND governor (token) ORTHOGONAL to the BYTE governor (tiers/archive_gate above) -- keep BOTH (B(e)); byte measures file-size-on-disk, token measures context-loaded; VN text ~3.0-3.5 byte/tok so byte/4 = upper bound => real headroom LARGER. Budget = MINIMUM-to-USE floor (FILL Tier-1 with real work-state up to the number; under-fill ONLY when high-value content exhausted; NEVER garbage-stuff -- token-saving = forgetting work).",
     "role_boundary_note": "v2 §6 ROLE BOUNDARY (🔴): the budget numbers (Tier-1 per-role cap + per-bucket allocation) are ANH's (project-owner / chu-du-an) RIGHT to set -- NOT the AI-lead's. em-main's job is exactly two parts: (1) EXECUTE the config faithfully (load Tier-1 to the number, no-truncate, pull each bucket to target) + (2) REPORT %-composition at session-start (§2.1.6) and session-end (§L.b(c)) so anh decides. em-main self-measures + proposes numbers; em-main does NOT auto-tune them down. This corrects the S81 'LEAD-AUTHORITY' framing which conflated AI-lead with project-owner.",
     "tier1_hotfeed_tokens": {
-      "_note": "Tier-1 always-loaded HOT-FEED, PER-ROLE (v3 S83 2026-06-22: FULL AI_INFRA parity, owner-set). FILL with the 4 work buckets: (1) WIP work-state, (2) recurring-bugs/anti-patterns/gotcha (value_protect, kept regardless of age), (3) backlog, (4) pending-decisions. anh-set: lead 220K / mem-sub 60K / wf-sub 50K = EXACT AI_INFRA parity. This SUPERSEDES the S82 'SE numbers are SMALLER (lead 60K; subs stay 20K/16K because the byte-cap binds first)' self-justification -- that was the AI under-shrinking, forbidden by role_boundary_note + mark RC-...01-58-01 (token-saving = forgetting work). KEY CORRECTION on subs: the sub MEMORY.md byte-cap (30720B ~9.3K tok) is ONLY ONE SLICE of a sub's Tier-1 -- the SPAWN PROMPT (relevant gotchas + state + full task-context + related docs/memory, written by em-main) fills the REST up to the token budget. So 60K/50K is NOT 'unusable headroom'; it is the target em-main fills via a RICH spawn prompt (see spawn_fill_directive). %-print at the two session ends shows the REAL composition.",
+      "_note": "Tier-1 always-loaded HOT-FEED, PER-ROLE (v3 S83 2026-06-22: FULL AI_INFRA parity, owner-set). FILL with the 4 work buckets: (1) WIP work-state, (2) recurring-bugs/anti-patterns/gotcha (value_protect, kept regardless of age), (3) backlog, (4) pending-decisions. anh-set: lead 380K (S94 2026-06-29 owner-override, SE-SPECIFIC -- diverged from AI_INFRA-parity to fit the full ~368K read-set) / mem-sub 60K / wf-sub 50K (subs STILL AI_INFRA parity). This SUPERSEDES the S82 'SE numbers are SMALLER (lead 60K; subs stay 20K/16K because the byte-cap binds first)' self-justification -- that was the AI under-shrinking, forbidden by role_boundary_note + mark RC-...01-58-01 (token-saving = forgetting work). KEY CORRECTION on subs: the sub MEMORY.md byte-cap (30720B ~9.3K tok) is ONLY ONE SLICE of a sub's Tier-1 -- the SPAWN PROMPT (relevant gotchas + state + full task-context + related docs/memory, written by em-main) fills the REST up to the token budget. So 60K/50K is NOT 'unusable headroom'; it is the target em-main fills via a RICH spawn prompt (see spawn_fill_directive). %-print at the two session ends shows the REAL composition.",
-      "lead_tokens": 220000,
+      "lead_tokens": 380000,
-      "lead_note": "ANH-SET 220K (S83 2026-06-22 owner-directive, full AI_INFRA parity; raised from the 200K interim earlier in S83 and the 60K S82 self-shrink). DO NOT auto-reduce (role_boundary_note + mark RC-...01-58-01). Hot-feed = STATUS full current-state + 4-bucket work-state block + ACTIVE-MARKS + recent-3-session HANDOFF + active roadmap (migration-todos) + roster-slice + task-relevant gotchas + active-task files + task-relevant docs/code -- read GENEROUSLY ('dau phien nap them tier1_lead cho du'), NOT 'on-demand-deferred', but HIGHEST-VALUE distilled only, NEVER garbage-stuff. Opus 4.8 1M window => 220K is ~22% of window, ample. anh-adjustable (owner authority).",
+      "lead_note": "ANH-SET 380K (S94 2026-06-29 owner-directive RC-pqhuy1987-29-06-2026-23-25-50 -- raised 220K->380K so the FULL canonical read-set ~368K fits; SE-SPECIFIC override, NO LONGER AI_INFRA-parity for lead, sub caps unchanged). History: 220K (S83 full-parity) <- 200K interim <- 60K S82 self-shrink. DO NOT auto-reduce (role_boundary_note + mark RC-...01-58-01). Hot-feed = STATUS full current-state + 4-bucket work-state block + ACTIVE-MARKS + recent-3-session HANDOFF + active roadmap (migration-todos) + roster-slice + task-relevant gotchas + active-task files + task-relevant docs/code -- read GENEROUSLY ('dau phien nap them tier1_lead cho du'), NOT 'on-demand-deferred', but HIGHEST-VALUE distilled only, NEVER garbage-stuff. Opus 4.8 1M window => 380K is ~38% of window. CAVEAT: at ~368K loaded the hot-feed is ~97% full => near-zero headroom + HIGHER context-rot (honest_caveat trade-off accepted by owner). TOOLING NOTE: the 380K BUDGET cap is ORTHOGONAL to the harness Read-tool 25K/call cap -- STATUS/HANDOFF mega-lines STILL cannot be fully Read until re-tiered (mega-line not line-paginatable); cap raise alone does NOT unblock the Read. anh-adjustable (owner authority).",
       "memory_sub_tokens": 60000,
       "memory_sub_note": "memory-bearing sub (agent-chinh), anh-set 60K (S83 full parity): own MEMORY.md (<=30720B ~9.3K tok auto-inject) + archive _INDEX map + work-state slice + THE RICH SPAWN PROMPT em-main writes (relevant gotchas + current state + full task-context + related docs/memory) = fills toward 60K. The byte-cap on MEMORY.md is NOT the binding limit on the sub's Tier-1; the spawn prompt is. em-main MUST write a context-rich brief, NOT a thin 8K brief (that old anti-truncation heuristic guarded RETURN-truncation #53, mitigated by lean memoryDelta RETURN -- not by starving INPUT).",
       "workflow_sub_tokens": 50000,

.claude/commands/session-start.md

@@ -111,7 +111,7 @@ Em main xác nhận **lead model resolve được** đầu session. Lead SE = **
 
 > Floor H15-v2 (🔴 [`harness-11-engine.md §G.4`](../../docs/governance/harness-11-engine.md)): Tầng-1 = HOT-FEED LỚN → cần "kính soi" để anh thấy phần luôn-nạp đang chứa gì, bucket nào mỏng, còn trống bao nhiêu → anh quyết điều-chỉnh. 🔴 **Ranh-giới vai-trò:** con-số = **quyền anh (chủ-dự-án)**; em-main chỉ THỰC-THI-đúng-số + BÁO-% (KHÔNG tự-tinh-chỉnh con-số).
 
-- **In ở Phase 3 REPORT (đầu phiên):** ước-lượng composition Tầng-1 theo **% / 4 bucket** (tỉ-lệ đủ, KHÔNG cần đo chính-xác): (1) WIP work-state · (2) lỗi-lặp/anti-pattern/gotcha · (3) tồn-đọng · (4) quyết-định-chờ. + **Headroom** = phần còn-trống so cap role (`memory-budget.json:token_governor.tier1_hotfeed_tokens` — lead 220K · mem-sub (agent-ký-ức) 60K · wf-sub (agent-workflow) 50K; **v3 S83 full AI_INFRA parity**, canonical = budget.json → đọc số sống ở đó, đừng tin echo này khi anh đổi cap).
+- **In ở Phase 3 REPORT (đầu phiên):** ước-lượng composition Tầng-1 theo **% / 4 bucket** (tỉ-lệ đủ, KHÔNG cần đo chính-xác): (1) WIP work-state · (2) lỗi-lặp/anti-pattern/gotcha · (3) tồn-đọng · (4) quyết-định-chờ. + **Headroom** = phần còn-trống so cap role (`memory-budget.json:token_governor.tier1_hotfeed_tokens` — lead **380K** (v4 S94 owner-override, SE-specific — fit full read-set ~368K; subs giữ parity) · mem-sub (agent-ký-ức) 60K · wf-sub (agent-workflow) 50K; canonical = budget.json → đọc số sống ở đó, đừng tin echo này khi anh đổi cap).
 - 🔴 **Headroom > 0 mà CÒN nội-dung giá-trị-cao chưa nạp = under-fill (SAI)** → nạp tiếp tới khi đầy hoặc cạn nội-dung giá-trị-cao. Headroom = cờ-báo, KHÔNG phải đích-tiết-kiệm; **nạp-đầy ≠ nhồi-rác** (giá-trị-thấp KHÔNG vào Tầng-1).
 - **Light/hỏi-đáp → gọn 1 dòng; feature/bug/governance → in đủ 4-bucket %.** Đối-xứng `session-end §L.b(c)` (% cuối phiên + Headroom).
 - **🧪 MFE opt-in (Harness-16 §H — memory-fidelity-EVAL, KHÁC H6.7 memoryDelta-routing):** lệnh kèm tham-số `eval` → chạy thêm baseline `powershell.exe -ExecutionPolicy Bypass -File scripts/mfe-eval.ps1` = LEAD coverage-FIT (must-remember vs cap, token-RANGE) + age-band (flag-not-cut) + Goodhart-anchor (strikes/RCA) + SUB per-role coverage (đo-thật, prose-only→N/A). KHÔNG `eval` = bỏ qua (tương-thích-ngược). MFE **READS** budget single-source, KHÔNG ghi. Light → skip; governance/audit → nên chạy.

.claude/governance/ACTIVE-MARKS.md

@@ -15,7 +15,7 @@
 | `RC-pqhuy1987-20-06-2026-10-29-09` | `rules.md §6.6` + `engine §E.4` (≙ §F4.2) | Quyết-định kiến-trúc/chức-năng = tiêu-chí KHÁCH-QUAN (điểm-đau · khối-lượng · chất-lượng) **KHÔNG quy-mô-đội**; "overkill/quá-mức-solo-dev/cảm-tính" = **BÁC**; thẩm-quyền cần-vs-thừa = AI_INFRA cross-project; AI = neo lý-tính | **pain:** lập-luận "quá mức solo-dev" đã khiến 1 dự-án từ-chối chức-năng chống-lách-engine (sự-cố thật) — SE = solo-dev, đúng đối-tượng · **volume:** 6 dự-án federated + SE 11-agent cần neo nhất-quán · **quality:** quyết-định-cảm-tính trôi chất-lượng âm-thầm; neo-lý-tính giữ rigor | null | 🔖 **Active-High** (anh-confirm S79 · P4 DACI report-before-stamp) |
 | `RC-pqhuy1987-20-06-2026-10-29-10` | `engine §E` (≙ §P) | Codify **User-Mark + chữ-ký RC** (Harness-12/13) — chữ-ký quyết-định governance + 4 cấp + no-cảm-tính deterministic + report-before-stamp | **pain:** quyết-định governance bị quên / giảm-bằng-cảm-tính (không chữ-ký+tier) · **volume:** SE tích-lũy Harness 1-14 cần audit-trail nhất-quán · **quality:** RC-sig = minh-oan + tranh-luận-bằng-bằng-chứng + trách-nhiệm-2-chiều | null | 🔖 **Active-High** (anh-confirm S79 · P4 dogfood: invest-wf→review-wf→báo-cáo→confirm→stamp) |
 | `RC-pqhuy1987-20-06-2026-10-29-11` | `rules.md §6.6 DM-time/age` (≙ §F4.2-ext / H-14) | **Mở-rộng mark-1** — time/age/recency-decay = **false-proxy** (cùng-họ team-size); kiến-trúc KHÔNG dựa cũ / lâu-chưa-dùng / auto-decay; trần budget=(dung-lượng÷tốc-độ-thay-mới) KHÔNG núm-decay-tuổi, drift=đường-nền-cuộn KHÔNG cửa-sổ-tuổi; **additive** (mark-1 GIỮ) | **pain:** cap∝chunk_count = Goodhart-vanity + age-window drift = alarm-spam (sự-cố thật H-14); SE memory-budget từng dễ mắc "giảm-theo-độ-cũ" · **volume:** 6 dự-án áp budget/drift/eval + SE L1/L2/L3 + archive-gate · **quality:** age-decay cắt memory-tốt = false-economy (DM-004 Goodhart §6.6) | null (additive) | 🔖 **Active-High** (anh-confirm S79 via `/user-mark-active-high` · P4 DACI · supersedes:null) |
-| `RC-pqhuy1987-20-06-2026-23-07-37` | `harness-11-engine.md §G` + `memory-budget.json` + `rules.md §6.6` (≙ AI_INFRA H-15) | **H-15 memory-budget per-agent (token-based):** token-governor (**v3 §G.5 S83:** Tầng-1 hot-feed per-role **lead 220K/mem-sub 60K/wf-sub 50K** full AI_INFRA parity (sửa self-shrink S82) + **spawn-fill-to-budget** (sub Tầng-1 = MEMORY.md byte-cap + spawn-prompt giàu, `spawn_fill_directive`); **v2 §G.4 S82:** L2/L3 **bỏ-trần** on-demand + báo-% 2-đầu-phiên; con-số = **quyền CHỦ-DỰ-ÁN/anh** + AI thực-thi-đúng-số + báo-%) + **value-gated archival** (giữ recurring-bug/anti-pattern/gotcha bất-kể tuổi) + fill-L1-full (budget = sàn-tận-dụng KHÔNG trần-tiết-kiệm) + work-state-block @session-start + %-print 2-đầu-phiên + 2-governor (byte⟂token) | **pain:** tiết-kiệm-token → quên-việc/rơi-trạng-thái giữa phiên (sự-cố thật — Tầng-1 mỏng = lead quên việc nhiều phiên, bằng-chứng v2); SE keep-floor age-based có thể archive gotcha cũ ra khỏi L1 — value-gate FLAG đã bắt thật (test-specialist gotcha#/guard) · **volume:** 11-agent × (SÀN 30K + Tầng-1 hot-feed per-role lead 220K/mem-sub 60K/wf-sub 50K, v3 §G.5 full-parity) always-load/spawn + L2 archive ~240KB (cicd 194KB) cần value-protect · **quality:** quên-việc → làm-lại → tốn-hơn (Goodhart); giữ hard-won lessons | null (additive — mark `…11` GIỮ; H-15 mở-rộng value-axis xuống tầng-bộ-nhớ) | 🔖 **Active-High** (anh-confirm S81 · **v2-delta anh-confirm S82** `RC-pqhuy1987-21-06-2026-01-58-01` — hot-feed-lớn/bỏ-trần/anh-authority · **v3-delta anh-directed S83** `RC-pqhuy1987-22-06-2026-16-35-37` — full-parity 220/60/50 + spawn-fill-to-budget, P4 DACI report-before-stamp ✓) |
+| `RC-pqhuy1987-20-06-2026-23-07-37` | `harness-11-engine.md §G` + `memory-budget.json` + `rules.md §6.6` (≙ AI_INFRA H-15) | **H-15 memory-budget per-agent (token-based):** token-governor (**v3 §G.5 S83:** Tầng-1 hot-feed per-role **lead 380K (v4 §G.5 S94 owner-override, SE-specific để chứa full read-set ~368K — lead KHÔNG còn AI_INFRA-parity)/mem-sub 60K/wf-sub 50K** (subs giữ parity) + **spawn-fill-to-budget** (sub Tầng-1 = MEMORY.md byte-cap + spawn-prompt giàu, `spawn_fill_directive`); **v2 §G.4 S82:** L2/L3 **bỏ-trần** on-demand + báo-% 2-đầu-phiên; con-số = **quyền CHỦ-DỰ-ÁN/anh** + AI thực-thi-đúng-số + báo-%) + **value-gated archival** (giữ recurring-bug/anti-pattern/gotcha bất-kể tuổi) + fill-L1-full (budget = sàn-tận-dụng KHÔNG trần-tiết-kiệm) + work-state-block @session-start + %-print 2-đầu-phiên + 2-governor (byte⟂token) | **pain:** tiết-kiệm-token → quên-việc/rơi-trạng-thái giữa phiên (sự-cố thật — Tầng-1 mỏng = lead quên việc nhiều phiên, bằng-chứng v2); SE keep-floor age-based có thể archive gotcha cũ ra khỏi L1 — value-gate FLAG đã bắt thật (test-specialist gotcha#/guard) · **volume:** 11-agent × (SÀN 30K + Tầng-1 hot-feed per-role lead 220K/mem-sub 60K/wf-sub 50K, v3 §G.5 full-parity) always-load/spawn + L2 archive ~240KB (cicd 194KB) cần value-protect · **quality:** quên-việc → làm-lại → tốn-hơn (Goodhart); giữ hard-won lessons | null (additive — mark `…11` GIỮ; H-15 mở-rộng value-axis xuống tầng-bộ-nhớ) | 🔖 **Active-High** (anh-confirm S81 · **v2-delta anh-confirm S82** `RC-pqhuy1987-21-06-2026-01-58-01` — hot-feed-lớn/bỏ-trần/anh-authority · **v3-delta anh-directed S83** `RC-pqhuy1987-22-06-2026-16-35-37` — full-parity 220/60/50 + spawn-fill-to-budget · **v4-delta anh-directed S94** `RC-pqhuy1987-29-06-2026-23-25-50` — lead 220K→**380K** SE-override để chứa full read-set ~368K (⚠️ ~97% fill = context-rot trade-off owner-accepted; trần budget ⟂ harness Read-25K/call → mega-line STATUS/HANDOFF VẪN cần re-tier mới Read-trọn), P4 DACI report-before-stamp ✓) |
 
 ## 🟢 ACTIVE (follow + nhắc-lại xuyên-suốt — HIỆN @session)
 _(trống)_

docs/governance/harness-11-engine.md

@@ -167,6 +167,8 @@ SE đã có RAG golden-set harness (KHÔNG phải gap): `eval/golden-set-solutio
 >
 > **Adopt-delta S83 (2026-06-22)** — **anh owner-directive trực-tiếp** (KHÔNG broadcast): full AI_INFRA parity (lead 220K · mem-sub 60K · wf-sub 50K) + **spawn-fill-to-budget** (sub Tầng-1 = MEMORY.md byte-cap + spawn-prompt giàu) → **§G.5**. Sửa self-shrink S82. Mark H-15 v3-delta (`ACTIVE-MARKS.md`).
 >
+> **Adopt-delta S94 (2026-06-29)** — **anh owner-directive trực-tiếp** (KHÔNG broadcast): lead **220K→380K** (SE-specific override để chứa full canonical read-set ~368K; lead KHÔNG còn AI_INFRA-parity, subs giữ 60K/50K). ⚠️ ~97% fill = context-rot trade-off **owner-accepted** (honest_caveat §5); trần budget ⟂ harness **Read-25K/call** — mega-line STATUS/HANDOFF VẪN cần re-tier mới Read-trọn (cap raise KHÔNG unblock Read). §G.5 body giữ S83-record (no-retrofit), số sống = `budget.json` live-read. Mark H-15 v4-delta `RC-pqhuy1987-29-06-2026-23-25-50` (`ACTIVE-MARKS.md`).
+>
 > 🔑 **Cốt-lõi:** ngân-sách bộ-nhớ = **mức TẬN-DỤNG-TỐI-THIỂU phải đạt, KHÔNG phải trần để dè-xẻn.** Tiết-kiệm-token = **quên-việc** (rơi trạng-thái giữa phiên) = KHÔNG tiết-kiệm thật (làm-lại tốn HƠN — cùng họ Goodhart §F.4/§6.6). Khoảng-trống quan-sát hay rơi đúng vào **chính LEAD** (lead tự-nạp kiến-trúc/luật nhưng bỏ quên trạng-thái-công-việc) → §G.2(c) vá đúng chỗ đó.
 
 ### G.1 — Mô-hình = SÀN cố-định + 3 tầng được-quản-lý (A1/A2/A3)