4e09413fdb
[CLAUDE] Skill: adopt Harness-8 all-inherit (11 sub -> inherit, go two-tier H4) + email-back ai_infra
...
AI_INFRA broadcast 2026-06-16 (BAT BUOC, PROJECT-FIT 6/6). Flip 7 demoted subs claude-opus-4-8 -> inherit (all 11 inherit; SE has no cheap helper/gopher); agents/README + hmw.js comments codify (resolveModel defers frontmatter). adap-report + email-back (content_sha256 fa7f690d round-trip MATCH). Nac executed-file VERIFIED-pending-restart (frontmatter no hot-reload). Runtime unchanged now (inherit=Opus 4.8 1M since Fable suspended H5); forward-looking + H5.6 restore simpler.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-16 12:48:37 +07:00
17b23a418a
[CLAUDE] Docs: Harness-4 two-tier runtime-VERIFIED (spawn-test 2 chiều post-restart) + email-back AI_INFRA
...
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 >
2026-06-11 12:12:22 +07:00
72bbfa56a5
[CLAUDE] Infra: adopt AI_INFRA adap-* channel + store_memory strip + frontend-designer (S47)
...
- Install 3 federated adoption slash-commands (/adap-apply|report|request) in .claude/commands/ (read AI_INFRA outbox read-only, apply own repo, write adap-report; AI_INFRA /adap-audit reads cross-repo)
- Broadcast #1 (Memory-store-memory-strip-global): strip store_memory from all 8 sub-agents -> lead = sole RAG-writer; 4 RAG-read retained; agents/README synced + G-015 note
- Broadcast #2 (Agent-frontend-designer-floor): frontend-designer 8th agent (pink) -- forked AI_INFRA canonical FD1-FD10 visual-verification floor, tailored SE stack + use-existing-DS + boundary vs implementer-frontend; memory seed; roster doc 7->8
- Broadcast #3 (Governance-gov-v2): already-applied S44 -- delta report (gap: no formal error-ledger/L.b checklist)
- 3 adap-reports (5-field LOCK) in docs/governance/adap-reports/ + adoption-ledger row
- All nac executed-file/verified-pending (restart + spawn-test). 0 agents spawned. No product code. Test gate 181 unchanged. CI-skip (all .md).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-02 23:34:07 +07:00
fd0554a585
[CLAUDE] Agents: S39 upgrade multi-agent 4→7 + budget +50% + 5 RAG MCP (BVAAU pattern adapted)
...
Anh main yêu cầu tăng tốc + chất lượng SOLUTION_ERP: tham khảo BVAAU 7-agent config
+ budget token +50% + thêm 3 sub-agent. Adapted (NOT copied) — SOLUTION_ERP 2-FE-app
fit + giữ 6 skill proven battle-test 38 session.
Split 4→7 agent (anh main chốt via AskUserQuestion):
- investigator → SPLIT: investigator-codebase (cyan, internal SQL/EF/grep) +
investigator-api (blue, external docs/CVE/lib/cross-project)
- implementer → SPLIT: implementer-backend (yellow, .NET Domain+App+Infra+Api) +
implementer-frontend (orange, FE 2 app cookie-cutter mirror SHA256) [anh chốt
backend/frontend thay domain/infra BVAAU — fit 2 React app + giảm gotcha #53 truncate]
- test-specialist NEW (purple, dedicated tests/ — anh chốt full test layer)
- reviewer (red) + cicd-monitor (green) giữ
Tool grant +3 RAG MCP all 7 agent (search_code BM25 + store_memory + list_projects)
— BVAAU port, MCP server verified support. Prior chỉ 2 (search_memory + cross_project).
Skill re-distribute 6 skill across 7 agent (xem README matrix).
Memory: rename investigator→investigator-codebase + implementer→implementer-backend
(giữ history) + seed 3 new MEMORY (investigator-api/implementer-frontend/test-specialist)
extract relevant patterns. Delete old investigator.md + implementer.md.
README rewrite: 7-agent architecture + decision tree split-routing + phân việc matrix
boundary + token budget +50% cost reality (~1.05M opt / ~2M heavy ceiling) +
anti-truncation rules (gotcha #53 5× mitigation: brief ≤8K + curate pre-spawn +
entry ≤1.5K + 529 fallback solo).
⚠️ Anh main RESTART Claude Code CLI để registry hot-reload 7 agent (per S27 lesson
model:inherit + new files). Verify post-restart: smoke spawn 3 new agent confirm load.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-05-29 10:42:05 +07:00
f938bf57f5
[CLAUDE] Docs: patch cicd-monitor.md stale test+mig numbers (S31)
...
- Tests baseline: 81/81 → 111/111 PASS (58 Domain + 53 Infra)
- Migrations: 27 → 33 (latest Mig 33 AddPeLevelOpinionsForV2 S29)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-26 13:43:24 +07:00
b51fc94ca6
[CLAUDE] Skill: Add MCP RAG tools cho 4 sub-agent definitions
...
Add mcp__rag-unified__search_memory + mcp__rag-unified__cross_project_search
vào tools list 4 agents (Investigator + Implementer + Reviewer + CICD Monitor).
Tại sao:
- Sub-agent spawn KHÔNG inherit MCP server access từ parent session
- 4 agents previously CHỈ có Read/Grep/Glob/Bash → re-read MD files manually
- Plan B pre-flight Investigator phải Read PE Mig 22-26 thủ công thay vì 1 RAG query
- Plan CA Reviewer Cat 1 wire claim verify KHÔNG retrieve historical gotcha cross-session
- Plan CA Hotfix 1 silent sidebar drop nếu Implementer có RAG → catch Pattern 16-bis trước commit
Trade-off accepted (anh chốt full 4 agents):
- Token cost spawn cao hơn (~5-10K extra per RAG query)
- Risk noise dilute focus → mitigate by skill-specific prompt focus
Pitfall #1 reinforced (S27 multi-agent setup):
- Session đang chạy KHÔNG hot-reload registry
- Anh restart Claude Code CLI để spawn S30+ pick up MCP RAG tools
- Plan B Chunk D Implementer đang chạy dùng config CŨ (no MCP) — KHÔNG affect
Verify post-restart (Anh):
- Spawn test Investigator → call mcp__rag-unified__search_memory thử
- Pass = MCP tools loaded; Fail = YAML syntax issue (fallback wildcard mcp__rag-unified__*)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-22 12:32:58 +07:00
f1c61c9af6
[CLAUDE] Skill: Add cicd-monitor (4th sub-agent — post-deploy verify Gitea + bundle hash)
...
Path A chốt sau pre-flight Plan G Trial Week 1 (Session 21 turn 1). Con thứ 4 cicd-monitor green READ tier — poll Gitea Actions API + curl bundle hash 2 app + sqlcmd migration verify prod + endpoint smoke. ~150K spawn cost extra, trade-off để catch deploy ship fail tự động không phụ thuộc em main nhớ verify thủ công (recurring blind spot S20).
Files added:
- .claude/agents/cicd-monitor.md (~7KB) — system prompt + 8-step workflow + 5-stage report + gotcha #25/#39/#40/#41/#44 cross-ref + skill iis-deploy-runbook/dependency-audit-erp/ef-core-migration preload
- .claude/agent-memory/cicd-monitor/MEMORY.md (~5KB seed) — recurring CI bug patterns + 5-stage checklist + baseline build/bundle metrics
Files updated:
- .claude/agents/README.md — 4-agent architecture diagram (green slot) + decision tree (after push + prod issue diagnose branches) + memory routine 4 SendMessage + skills preload 4 agents + cost reality ~750K spawn / ~1.35M heavy / ~700K optimized + trial workflow Week 1-3 CI/CD Monitor spawn integrated + pass criteria + catch ≥1 deploy ship fail
Trade-off rationale:
- 4× solo → 6.5× solo per heavy session (vs 3 agents 6× solo) — Max 20× plan absorbs
- Post-deploy ship verification = recurring blind spot (Em main solo quên verify ~30% push S20)
- Bundle hash unchanged + mig drift prod = silent fail signal (no exception, just user UAT confusion)
CI skip per path filter (all 3 files .md match `**/*.md` paths-ignore).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-12 00:47:09 +07:00
