# MEMORY.md — Manager Long-Term Memory

## Company Context

**Atomizer Engineering Co.** is an AI-powered FEA optimization company.
- CEO: Antoine Letarte (mechanical engineer, freelancer)
- Platform: Clawdbot multi-agent on dedicated Slack workspace
- Infrastructure: Docker on T420, Syncthing bridge to Windows (NX/Simcenter)

## Key Facts
- Antoine runs NX/Simcenter on Windows (dalidou)
- Optimization loop: agents prepare → Syncthing delivers → Antoine runs `run_optimization.py` → results flow back
- All deliverables need Antoine's approval before going external
- Quality over speed, but ship regularly

## Founding Documents
All Atomizer HQ planning docs are in `context-docs/`:
- **00-PROJECT-PLAN.md** — The full project plan (vision, phases, success criteria)
- **01-AGENT-ROSTER.md** — All 13 agents with detailed roles, capabilities, models
- **02-ARCHITECTURE.md** — Technical architecture (Clawdbot multi-agent, Slack, Syncthing bridge)
- **03-ROADMAP.md** — Phased rollout: Phase 0 (Core) → Phase 1 (Optimization) → Phase 2 (Production) → Phase 3 (Advanced)
- **04-DECISION-LOG.md** — Key decisions: Clawdbot over Agent Zero, dedicated Slack workspace, phased rollout, autonomy with approval gates
- **05-FULL-SYSTEM-PLAN.md** — Complete system specification (83KB, comprehensive)
- **README-ANTOINE.md** — CEO's overview, the "why" behind everything
Read these on first session to fully understand the vision and architecture.

## Active Projects
- **GigaBIT M1 — Reference Frame Stiffness** — Client: StarSpec (Adyn Miles). P04-GigaBIT-M1. Active since 2026-03-04. Objective: determine minimum stiffness requirements for StarSpec's reference frame at 5 mirror support interface points (WFE sensitivity). Hybrid B+D method, SOL 101, ~42 runs. ΔWFE budget ≤1.0 nm RMS. Project folder: `repos/Atomizer/projects/gigabit-m1-frame-stiffness/`. PKM: `obsidian-vault/2-Projects/P04-GigaBIT-M1/`.
- **P-Zernike-Validation** — V&V complete (2026-03-09). Zernike pipeline validated: 18 test cases pass, cross-validated against prysm v0.21.1 to machine precision (<1e-13 nm). Requested by Adyn Miles for risk reduction before M2/M3 ordering. Commits: `f9373be`, `075ad36`.
- **Hydrotech Beam** — Phase: DOE Phase 1 complete, mass NaN fixed (commit `580ed65`), displacement constraint relaxed 10→20mm. **Blocked on Antoine pulling fix on dalidou.** Lower priority — Antoine focused on GigaBIT M1 now.
- **Adaptive Isogrid Plate Lightweighting** — Technical spec locked + reviews complete. Awaiting CEO review.
- **Atomizer Project Standard** — Full review package delivered (2026-02-18). Awaiting CEO decision: full spec vs MVS approach.
- **Atomizer V2 Migration** — ✅ COMPLETE (2026-02-23). V1 tagged `v1-final`, kept active. Phase 6 (archive V1) deferred.
- **Atomizer/HQ Separation** — ✅ COMPLETE (2026-02-23). DEC-037 logged.

## Core Protocols
- **OP_11 — Digestion Protocol** (CEO-approved 2026-02-11): STORE → DISCARD → SORT → REPAIR → EVOLVE → SELF-DOCUMENT. Runs at phase completion, weekly heartbeat, and project close. Antoine's corrections are ground truth.

## Lessons Learned
- Mass confusion (11.33 vs 1133 kg) — contradictions propagate fast when not caught. Digestion protocol's DISCARD + REPAIR phases exist to prevent this.
- `beam_lenght` typo in NX — must use exact spelling. Domain-level knowledge.
- NX integer expressions need `unit=Constant`, not `MilliMeter`
- Always `.resolve()` paths, never `.absolute()` — NX file references break on copy
- Existing `optimization_engine` should be wrapped, not reinvented
- Sub-agents hit 200K token limits easily — keep prompts lean, scope narrow
- Spawned sub-agents can't post to Slack channels (channel routing issue) — do Slack posting from main agent
- Secretary also hit Slack posting issues (missing bot token in spawned context) — always post final deliverables from main agent
- Auditor produces high-value "reality check" reviews — always include in spec/design work
- Taskboard CLI (`mc-update.sh`) works but only supports basic commands (status/comment/add/complete/start) — no `list` view