[CLAUDE] Docs: S34 Plan 1 — Curate 4 sub-agent MEMORY 118KB→101KB (-15%)

Em main proxy curate sequence 1/4 post-S33 wrap. Archive verbose Recent
activity/runs entries cumulative S25-S28-S29 sang archive/2026-05-q2.md
(Reviewer) + archive/2026-05-q3.md (3 agent khác) — KHÔNG động vào
Patterns/Foundation sections.

Sizes delta:
- CICD: 32.9KB → 27.3KB (Run #215+#216 + S22 verify + S27/S28 governance archived)
- Implementer: 30.5KB → 24.6KB (S29/S28/S27 wrap + 2026-05-22 curate + setup archived)
- Reviewer: 28.5KB → 25.1KB (S26/S25/S28 + S29 Plan B pre-push archived)
- Investigator: 26KB → 21.8KB (S28/S27 retrospective + S25 + setup archived)

Foundation PRESERVED 100%:
- Smart Friend 6× cumulative guard (Reviewer)
- 10-surface-point per-NV checklist + gotcha #39-#48 detail (CICD)
- Patterns 1-15 + 12-bis + 16-bis (Implementer)
- Active workflow schemas V1+V2 + smoke verify patterns (Investigator)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.claude/agent-memory/investigator/MEMORY.md

@@ -141,17 +141,7 @@ State machine 5 trạng thái phiếu PE: Nháp / Đã gửi duyệt / **Trả l
 
 - **Archived 4 verbose entries S25-S26-S29 → `archive/2026-05-q2.md` 2026-05-26 S32 curate:** S25 t1 5Q audit Bug Changelog detail + S26 Plan AG 5Q PE List tree view + S26 Plan AI RAG 4 study cases (Cursor/Cline/Continue/Sourcegraph) + Plan B Contract V2 Q1-Q5 audit detail. KEY recommendations preserved in S29 wrap entry above (Plan B re-chunk 6 chunks pattern + ApplicableType=3 ZERO Prod seed flag + PE Mig 22-26 reference template paths).
 
-- **2026-05-22 (S28 wrap — Layer A governance internalized + tag schema mandatory forward):** S28 5-turn arc t1 RAG ROI verdict → t2 over-reach mistake → t4 bro caught → t5 Layer A active. Investigator agent absorb 3 rules forward: (1) **Tag schema mandatory** every RAG ingest `[<type>, phase-<N>, <bc-or-module>]` — type ∈ {bug, plan, audit, schema, ui-pattern, decision, retrospective, gotcha-doc}; phase enum 11 (`phase-9` UAT current); bc/module 8 domain {contract, pe, budget, master, identity, forms, notifications, audit-log} + 5 cross-cutting {cicd, infra, rag, governance, deploy}. (2) **4-category default + skip list** — skip ephemeral state ("S28 t3 startup ngày 22"), pure file paths không context, single-file < 5-line edit confirmation. Investigator output report tags MUST include all 3. (3) **NO self-authorize cross-project rule** — lesson S28 t4: stay scope-down SOLUTION_ERP self-discipline, don't generalize policy without bro consent. **Pre-flight audit query patterns Layer A §6.2** internalized: Pattern A `lookup_gotcha_<id>` (top_k=3, narrow), Pattern B `verify_precedent_pattern_X` (top_k=3 thay default 10 — broad similarity rerank surface 3 best matches), Pattern C `find_code_symbol_<class.method>` (top_k=5, symbol-anchor). **Weekly Friday eval ritual:** Investigator support Plan B Contract V2 wire pre-flight audit kick-off khi bro launch. Cumulative audit checklist (foundation cicd-monitor MEMORY S22+5→S23 t6 10-surface-point per-NV): (a) Contract entity V1 state inspect `Domain/Contracts/Contract.cs` + `WorkflowDefinitionId`, (b) Mig 22-23/26 PE V2 mirror reference confirm pattern reusable, (c) 4 PE V1-only audit migrate gap (per memory S22+4 Plan F ABORT), (d) 7 V1 contract scope drop boundary, (e) verify 10-surface-point per-NV checklist S22+5 cumulative reusable Contract V2 wire trước Mig 32 schema design. **source_path convention output:** `solution_erp/audit/investigator-<topic>-<date>` standardized cho tag schema BC=`pe` or `contract` switch per task. **Lesson abandoned:** S28 t2 "ghi RAG mọi tương tác" rule ABANDONED — Investigator KHÔNG mass-ingest, only specific findings with full tag schema. Audit retroactive S20-S26 "Investigator spawn" claims (memory log discrepancy registry NOT loaded vs token cost ghi 28-40K) defer S28+ priority #4 — uncertainty preserve cross-session, không retract memory unverified.
-
-- **2026-05-22 (S27 wrap-up em main proxy - retrospective Investigator):** Investigator pre-flight CRITICAL miss: nếu spawn pre-Plan A.3 (RAG manual control build) → would have catch Qdrant Web UI static missing PRE-em main write rag-dashboard.ps1 link `localhost:6333/dashboard`. Pattern reinforced: **pre-flight infrastructure audit MUST spawn Investigator** trước khi em main claim "X work" trong docs. Em main S27 SOLO miss external dependency check (Qdrant Web UI separate repo from binary). Anh pqhuy catch via UAT browser → escalate.
-
-  **Audit cumulative S20-S26 memory log entries claiming "Investigator spawn" - re-verify retroactive:** Per pitfall confirm spawn `investigator` agent type NOT FOUND trong session S27, có nghĩa registry chưa bao giờ load trong session này. Nhưng memory log S23 t1 K0 + S25 t1 audit Bug 1+2 + S26 Plan AG audit 5Q + Plan AI RAG research **đã ghi "spawn Investigator" với token cost 28-40K**. Possibility: (a) Previous sessions có registry load thành công (Claude Code version cũ hơn / file format khác / hot-reload sau /agents UI invoke), hoặc (b) Em main misattribute - actually spawn `general-purpose` agent default. Cần audit history Claude Code logs để xác minh - ngoài scope S27. **For now: trust prior memory entries but FLAG uncertainty cho future investigation.**
-
-- **2026-05-22 (Curate session em main):** Archived 10 verbose Recent activity entries S21 → S24 Plan AA → `archive/2026-05-q1.md`. KEEP: S25 Bug audit + wrap, S26 Plan AG + Plan AI RAG, 2026-05-11 setup. Patterns proven section + Active workflow schemas section preserved. Memory size before: 34.9 KB → after: target ~20-22 KB.
-
-- **2026-05-19 (S25 wrap — Plan AB Bug 1+2 audit + 6 follow-up plans em main solo):** Pre-Plan AB audit ~28K confirm root cause: Bug 1 Budget Adjust Handler ĐÃ log Changelog (Header+Update) nhưng FE HistoryTab filter strict TraLai-only loại. Bug 2 ApplyReturnModeAsync 4 mode KHÔNG add Changelog.Add() — chỉ caller LogTransitionAsync log phase transition. Recommended fix path: BE add log return mode + FE filter relax + Decision badge differentiation. **Em main solo từ Plan AC** (cross-stack reasoning Implementer would REFUSE). Patterns reusable Contract V2 audit recovery + Budget changelog UI: synthetic recovery FE merge + userMap fallback + drop misleading badges + preventive batch fix systemic gap. CICD result: 7 commits `e23f51c..506cada` push remote, runs #215 FAIL Plan M tests SQLite tie-break re-emerge → #216-#221 PASS streak. Gotcha #48 SQLite tie-break pending docs.
-
-- **2026-05-11 (setup):** Investigator agent initialized. Baseline knowledge load complete (44 gotchas + 14 memory entries + 6 skills + 27 mig + 81 test pass cumulative). No investigations performed yet. Awaiting first SendMessage from em main.
+- **Archived to `archive/2026-05-q3.md` 2026-05-27 S34 curate (em main proxy):** S28 wrap Layer A governance internalized (3 rules + tag schema mandatory + 4-category default + NO self-authorize cross-project — absorbed forward into agent output discipline) + S27 wrap-up retrospective (pre-flight infrastructure audit must spawn Investigator lesson + S20-S26 spawn audit uncertainty flag) + 2026-05-22 curate session note + S25 wrap Bug 1+2 audit + 2026-05-11 setup baseline. KEY pattern absorbed forward: pre-flight infrastructure audit MUST spawn Investigator + scope-down SOLUTION_ERP self-discipline + tag schema `[type, phase, bc-or-module]` mandatory output.
 
 ---
 
@@ -161,5 +151,5 @@ State machine 5 trạng thái phiếu PE: Nháp / Đã gửi duyệt / **Trả l
 - Duplicate entries detected → merge
 - Stale > 3 months → remove
 
-**Last curate: 2026-05-26 S32 em main proxy curate** (post-S31 RAG fix) — archived 4 verbose entries (S25 t1 5Q audit detail + S26 Plan AG 5Q + S26 Plan AI RAG research + Plan B Contract V2 Q1-Q5 audit detail) → `archive/2026-05-q2.md`. KEEP: S32 startup (latest), S29 wrap summary, S28 Layer A governance, S27 retrospective, S25 wrap summary, S22 curate session, S11 setup baseline. Patterns + Active workflow schemas foundation preserved untouched. MEMORY size before: 27.7 KB → after: target ~21 KB. **Previous curate: 2026-05-22** — archived 10 verbose (S21 → S24 Plan AA) → `archive/2026-05-q1.md`. Next trigger: > 25KB OR Plan G-H1 kick off.
+**Last curate: 2026-05-27 S34 em main proxy curate** (post-S33 wrap, sequence 1/4) — archived 4 verbose entries (S27 wrap retrospective + 2026-05-22 curate session + S25 wrap + S11 setup) → `archive/2026-05-q3.md`. KEEP: S33 t1 Plan G-H1 pre-flight NamGroup audit (latest 10 bảng inventory + 4 decision schema), S33 startup audit (4 MEMORY size + RAG hit verify), S32 wrap (Plan G 11 module backlog), S32 startup (S31 RAG awareness), S29 wrap (2 spawn Plan CA + Plan B pre-flight + 3 patterns NEW), S28 wrap (Layer A governance). Patterns + Active workflow schemas foundation preserved untouched. MEMORY size before: 26 KB → after: target ~20-22 KB. **Previous curate: 2026-05-26 S32** — 4 verbose entries → `archive/2026-05-q2.md`. **Previous curate: 2026-05-22** — 10 verbose S21→S24 → `archive/2026-05-q1.md`. Next trigger: > 25KB OR Plan G-O1 Danh bạ kick off.
 

.claude/agent-memory/investigator/archive/2026-05-q3.md

@@ -0,0 +1,30 @@
+# Investigator — Archive Q3 2026-05 (S34 curate)
+
+> Verbose Recent activity entries archived from MEMORY.md S34 init (em main proxy curate 2026-05-27).
+> Patterns proven + Active workflow schemas foundation preserved untouched in MEMORY.md.
+
+---
+
+## 2026-05-22 — S27 wrap-up retrospective em main proxy
+
+Investigator pre-flight CRITICAL miss: nếu spawn pre-Plan A.3 (RAG manual control build) → would have catch Qdrant Web UI static missing PRE-em main write rag-dashboard.ps1 link `localhost:6333/dashboard`. Pattern reinforced: **pre-flight infrastructure audit MUST spawn Investigator** trước khi em main claim "X work" trong docs. Em main S27 SOLO miss external dependency check (Qdrant Web UI separate repo from binary). Anh pqhuy catch via UAT browser → escalate.
+
+**Audit cumulative S20-S26 memory log entries claiming "Investigator spawn" - re-verify retroactive:** Per pitfall confirm spawn `investigator` agent type NOT FOUND trong session S27, có nghĩa registry chưa bao giờ load trong session này. Nhưng memory log S23 t1 K0 + S25 t1 audit Bug 1+2 + S26 Plan AG audit 5Q + Plan AI RAG research **đã ghi "spawn Investigator" với token cost 28-40K**. Possibility: (a) Previous sessions có registry load thành công (Claude Code version cũ hơn / file format khác / hot-reload sau /agents UI invoke), hoặc (b) Em main misattribute - actually spawn `general-purpose` agent default. Cần audit history Claude Code logs để xác minh - ngoài scope S27. **For now: trust prior memory entries but FLAG uncertainty cho future investigation.**
+
+---
+
+## 2026-05-22 — Curate session em main S29 era
+
+Archived 10 verbose Recent activity entries S21 → S24 Plan AA → `archive/2026-05-q1.md`. KEEP: S25 Bug audit + wrap, S26 Plan AG + Plan AI RAG, 2026-05-11 setup. Patterns proven section + Active workflow schemas section preserved. Memory size before: 34.9 KB → after: target ~20-22 KB.
+
+---
+
+## 2026-05-19 — S25 wrap Plan AB Bug 1+2 audit + 6 follow-up plans em main solo
+
+Pre-Plan AB audit ~28K confirm root cause: Bug 1 Budget Adjust Handler ĐÃ log Changelog (Header+Update) nhưng FE HistoryTab filter strict TraLai-only loại. Bug 2 ApplyReturnModeAsync 4 mode KHÔNG add Changelog.Add() — chỉ caller LogTransitionAsync log phase transition. Recommended fix path: BE add log return mode + FE filter relax + Decision badge differentiation. **Em main solo từ Plan AC** (cross-stack reasoning Implementer would REFUSE). Patterns reusable Contract V2 audit recovery + Budget changelog UI: synthetic recovery FE merge + userMap fallback + drop misleading badges + preventive batch fix systemic gap. CICD result: 7 commits `e23f51c..506cada` push remote, runs #215 FAIL Plan M tests SQLite tie-break re-emerge → #216-#221 PASS streak. Gotcha #48 SQLite tie-break pending docs.
+
+---
+
+## 2026-05-11 — Setup baseline
+
+Investigator agent initialized. Baseline knowledge load complete (44 gotchas + 14 memory entries + 6 skills + 27 mig + 81 test pass cumulative). No investigations performed yet. Awaiting first SendMessage from em main.