Restructure Hydrotech Beam project — KB-integrated layout

New project structure with knowledge base integration:
- kb/ with components, materials, fea, dev generations
- models/ for reference NX files (golden copies)
- studies/ for self-contained optimization campaigns
- deliverables/ for final outputs
- DECISIONS.md decision log (6 decisions tracked)
- BREAKDOWN.md (moved from 1_breakdown/)
- Gen 001 created from intake + technical breakdown

KB extension file: atomizer/shared/skills/knowledge-base-atomizer-ext.md

Refs: DEC-HB-004, DEC-HB-005, DEC-HB-006

projects/hydrotech-beam/DECISIONS.md

@@ -0,0 +1,47 @@
+# DECISIONS.md — Hydrotech Beam
+
+Numbered decision log. Check here before proposing anything that contradicts a prior decision.
+
+---
+
+## DEC-HB-001: Single-objective formulation
+- **Date:** 2026-02-08
+- **By:** Technical Lead 🔧
+- **Decision:** Minimize mass as sole objective. Tip displacement (≤ 10 mm) and von Mises stress (≤ 130 MPa) as hard constraints.
+- **Rationale:** Mass is Antoine's clear priority. Displacement and stress are pass/fail limits, not competing objectives to trade off. Single-objective converges faster and is appropriate for 4 design variables.
+- **Status:** Proposed — awaiting CEO confirmation
+
+## DEC-HB-002: Two-phase optimization strategy
+- **Date:** 2026-02-08
+- **By:** Technical Lead 🔧
+- **Decision:** Phase 1 = Latin Hypercube DoE (40–50 trials) to map landscape. Phase 2 = TPE via Optuna (60–100 trials) to converge.
+- **Rationale:** DoE first catches model failures, maps feasibility, reveals sensitivities. TPE handles mixed integer/continuous natively and is sample-efficient.
+- **Status:** Proposed — awaiting CEO confirmation
+
+## DEC-HB-003: Integer handling for hole_count
+- **Date:** 2026-02-08
+- **By:** Technical Lead 🔧
+- **Decision:** Treat `hole_count` as true integer throughout (not continuous + rounding).
+- **Rationale:** Only 11 levels (5–15). NX model must rebuild with integer count anyway. TPE handles mixed types natively.
+- **Status:** Proposed — awaiting CEO confirmation
+
+## DEC-HB-004: Project structure — KB-integrated layout
+- **Date:** 2026-02-09
+- **By:** Manager 🎯 + CEO
+- **Decision:** Projects use KB-integrated structure with `models/`, `kb/`, `studies/`, `deliverables/`. Knowledge base follows accumulation principle from shared KB skill. Studies are self-contained with own model copy and introspection.
+- **Rationale:** Centralizes project knowledge, supports multiple studies per project, enables CDR compilation from KB, keeps everything in Gitea.
+- **Status:** Approved
+
+## DEC-HB-005: No Notion — Gitea + .md as source of truth
+- **Date:** 2026-02-09
+- **By:** CEO
+- **Decision:** All project documentation lives as .md files in the Atomizer Gitea repo. No external project management tools.
+- **Rationale:** CEO preference. Efficient, version-controlled, browseable on Gitea, accessible to all agents.
+- **Status:** Approved
+
+## DEC-HB-006: KB skill — extension pattern, no fork
+- **Date:** 2026-02-09
+- **By:** Manager 🎯 + CEO
+- **Decision:** Use Mario's shared knowledge-base skill as-is. Atomizer maintains an extension file (`knowledge-base-atomizer-ext.md`) for agent-specific workflows. No fork of the shared repo.
+- **Rationale:** Avoids merge conflicts, gets upstream improvements automatically, clean separation between general toolbox and Atomizer playbook.
+- **Status:** Approved

projects/hydrotech-beam/README.md

@@ -0,0 +1,72 @@
+# Hydrotech Beam — Structural Optimization
+
+**Client:** Hydrotech (internal test fixture)
+**Channel:** #project-hydrotech-beam
+**Created:** 2026-02-08
+**Status:** Technical Breakdown Complete — Awaiting Gap Resolution
+
+---
+
+## Objective
+
+Optimize a sandwich I-beam with lightening holes: minimize mass while meeting stiffness and strength constraints.
+
+## Key Numbers
+
+| Metric | Baseline | Target |
+|--------|----------|--------|
+| Mass | ~974 kg | Minimize |
+| Tip displacement | ~22 mm | ≤ 10 mm |
+| Von Mises stress | TBD | ≤ 130 MPa |
+
+## Design Variables
+
+| Variable | Range | Type |
+|----------|-------|------|
+| Half-core thickness | 10–40 mm | Continuous |
+| Face thickness | 10–40 mm | Continuous |
+| Hole diameter | 150–450 mm | Continuous |
+| Hole count | 5–15 | Integer |
+
+## Approach
+
+Two-phase optimization:
+1. **DoE** (LHS, 40–50 trials) — map the landscape
+2. **TPE** (Bayesian, 60–100 trials) — converge to optimum
+
+Total budget: ~100–150 NX evaluations, est. 2–5 hours compute.
+
+## Project Structure
+
+```
+hydrotech-beam/
+├── README.md              ← You are here
+├── CONTEXT.md             # Intake requirements
+├── BREAKDOWN.md           # Technical analysis
+├── DECISIONS.md           # Decision log
+├── models/                # Reference NX models (golden copies)
+├── kb/                    # Living knowledge base
+│   ├── components/        # Per-component knowledge
+│   ├── materials/         # Material data
+│   ├── fea/               # FEA model knowledge
+│   └── dev/               # Generation documents
+├── images/                # Screenshots, plots, renders
+├── studies/               # Optimization campaigns
+│   └── 01_doe_landscape/  # (first study — pending)
+└── deliverables/          # Final reports and recommendations
+```
+
+## Key Documents
+
+- [CONTEXT.md](CONTEXT.md) — Full intake data
+- [BREAKDOWN.md](BREAKDOWN.md) — Tech Lead's technical analysis
+- [DECISIONS.md](DECISIONS.md) — All project decisions
+- [kb/_index.md](kb/_index.md) — Knowledge base overview
+
+## Team
+
+| Role | Agent | Status |
+|------|-------|--------|
+| Manager | 🎯 Manager | Coordinating |
+| Technical Lead | 🔧 Tech Lead | Breakdown complete |
+| CEO | Antoine | Gap resolution pending |

projects/hydrotech-beam/kb/_history.md

@@ -0,0 +1,22 @@
+# Knowledge Base History — Hydrotech Beam
+
+All modifications tracked by generation.
+
+---
+
+## Gen 001 — 2026-02-09 — Initial KB
+
+**Source:** Project intake (CONTEXT.md) + Technical Lead breakdown (BREAKDOWN.md)
+**Author:** Manager 🎯
+
+**Created:**
+- `components/sandwich-beam.md` — initial component file from intake data
+- `materials/steel-aisi.md` — material placeholder
+- `fea/models/sol101-static.md` — FEA model placeholder from breakdown
+- `dev/gen-001.md` — generation document
+
+**Key findings from breakdown:**
+- Baseline FAILS displacement constraint (22 mm vs 10 mm limit)
+- Feasible region may be narrow — stiffness and mass compete
+- Sandwich effect (core thickness) is the primary stiffness lever
+- 9 gaps identified requiring CEO input before proceeding

projects/hydrotech-beam/kb/_index.md

@@ -0,0 +1,47 @@
+# Knowledge Base — Hydrotech Beam
+
+**Project:** Hydrotech Beam Structural Optimization
+**Generation:** 001
+**Last updated:** 2026-02-09
+
+---
+
+## Overview
+
+Sandwich I-beam optimization for a test fixture. Steel construction with lightening holes in the web. Goal: reduce mass from ~974 kg while meeting displacement (≤ 10 mm) and stress (≤ 130 MPa) constraints.
+
+## Components
+
+| Component | File | Status |
+|-----------|------|--------|
+| Sandwich Beam | [sandwich-beam.md](components/sandwich-beam.md) | Initial |
+
+## Materials
+
+| Material | File | Status |
+|----------|------|--------|
+| Steel (AISI) | [steel-aisi.md](materials/steel-aisi.md) | Initial |
+
+## FEA
+
+| Model | File | Status |
+|-------|------|--------|
+| Static Analysis (SOL 101) | [fea/models/sol101-static.md](fea/models/sol101-static.md) | Pending gap resolution |
+
+## Generations
+
+| Gen | Date | Summary |
+|-----|------|---------|
+| 001 | 2026-02-09 | Initial KB from intake + technical breakdown |
+
+## Open Tasks
+
+- ❓ G1: Beam length and support conditions
+- ❓ G2: Loading definition (point? distributed? self-weight?)
+- ❓ G3: Displacement measurement location and DOF
+- ❓ G4: Stress constraint scope (whole model? exclude supports?)
+- ❓ G5: Geometric feasibility of hole patterns at extremes
+- ❓ G6: Result sensors in Beam_sim1.sim
+- ❓ G7: NX parametric rebuild reliability across full range
+- ❓ G8: Mesh type, density, convergence status
+- ❓ G9: 130 MPa stress limit basis (yield? safety factor?)

projects/hydrotech-beam/kb/components/sandwich-beam.md

@@ -0,0 +1,52 @@
+# Sandwich Beam
+
+**Type:** Primary structural component
+**Material:** Steel (AISI) — see [steel-aisi.md](../materials/steel-aisi.md)
+**Status:** Baseline documented, optimization pending
+
+---
+
+## Description
+
+Sandwich I-beam serving as primary load-bearing member in a test fixture assembly. Cross-section features a core layer flanked by face sheets on top and bottom flanges. Web contains a pattern of lightening holes (circular cutouts) to reduce mass.
+
+## Specifications
+
+| Parameter | Value | Units | Source |
+|-----------|-------|-------|--------|
+| Mass (baseline) | ~974 | kg | NX expression `p173` |
+| Tip displacement (baseline) | ~22 | mm | SOL 101 result |
+| Half-core thickness | 20 (baseline) | mm | DV range: 10–40 |
+| Face thickness | 20 (baseline) | mm | DV range: 10–40 |
+| Hole diameter | 300 (baseline) | mm | DV range: 150–450 |
+| Hole count | 10 (baseline) | — | DV range: 5–15 (integer) |
+| Beam length | ❓ TBD | mm | Gap G1 |
+| Support conditions | ❓ TBD | — | Gap G1 |
+
+## Structural Behavior
+
+*From Technical Breakdown (Gen 001):*
+
+The beam is **bending-dominated**:
+
+| Behavior | Governing Parameters | Notes |
+|----------|---------------------|-------|
+| Bending stiffness (EI) | Face thickness, core thickness | Faces carry bending stress, core carries shear. Stiffness scales ~quadratically with distance from neutral axis |
+| Mass | All four variables | Core and face add material; holes remove material from web |
+| Stress concentrations | Hole diameter, hole spacing | Larger holes → higher SCF at edges. Closely spaced holes can interact |
+| Shear capacity | Core thickness, hole count, diameter | Holes reduce shear-carrying area |
+
+## Design Variable Interactions
+
+1. **Core × Face** — classic sandwich interaction. Optimal stiffness balances core depth (lever arm) vs face material (bending resistance)
+2. **Hole diameter × Hole count** — both remove web material. Large + many could leave insufficient ligament width
+3. **Face × Hole diameter** — thicker faces reduce nominal stress, allowing larger holes
+4. **Core × Hole diameter** — core thickness determines web height, constrains max feasible hole diameter
+
+## Key Risk
+
+> ⚠️ Baseline FAILS displacement constraint (22 mm vs 10 mm target). Optimizer must increase stiffness by >50% while reducing mass. Feasible region may be tight.
+
+## History
+
+- **Gen 001** (2026-02-09): Initial documentation from intake + technical breakdown

projects/hydrotech-beam/kb/dev/gen-001.md

@@ -0,0 +1,58 @@
+# Gen 001 — Project Intake + Technical Breakdown
+
+**Date:** 2026-02-09
+**Sources:** CEO intake in #project-hydrotech-beam, Technical Lead analysis
+**Author:** Manager 🎯
+
+---
+
+## What Happened
+
+1. Antoine submitted the Hydrotech beam optimization request via #project-hydrotech-beam
+2. Manager created project folder and CONTEXT.md from intake data
+3. Technical Lead produced a full technical breakdown (BREAKDOWN.md)
+4. Manager and CEO agreed on project structure (KB-integrated layout)
+
+## Key Findings
+
+### From Intake
+- Sandwich I-beam, steel, with lightening holes in web
+- 4 design variables (3 continuous + 1 integer)
+- Current design: ~974 kg, ~22 mm tip displacement
+- Targets: minimize mass, displacement ≤ 10 mm, stress ≤ 130 MPa
+
+### From Technical Breakdown
+- **Critical:** Baseline already violates displacement constraint (22 mm vs 10 mm)
+- Single-objective formulation recommended (minimize mass, constrain the rest)
+- Two-phase approach: DoE (40–50 trials) then TPE (60–100 trials)
+- Significant variable interactions expected (sandwich theory, hole interactions)
+- 9 gaps identified needing CEO input
+- Overall risk: MEDIUM-HIGH (feasible region may be tight or empty)
+
+## KB Entries Created
+
+- `components/sandwich-beam.md` — component file with specs, behavior, interactions
+- `materials/steel-aisi.md` — placeholder, needs NX model data
+- `fea/models/sol101-static.md` — solver setup, pending gap resolution
+
+## Decisions Made
+
+- DEC-HB-004: KB-integrated project structure (Approved)
+- DEC-HB-005: No Notion, Gitea + .md only (Approved)
+- DEC-HB-006: KB skill extension pattern, no fork (Approved)
+
+## Open Items
+
+9 gaps pending CEO input (see [_index.md](../_index.md)):
+- G1–G2: Geometry and loading (most critical)
+- G3–G4: Result extraction specifics
+- G5: Geometric feasibility at extremes
+- G6–G8: NX model details
+- G9: Stress allowable basis
+
+## Next Steps
+
+1. Resolve gaps G1–G9 with Antoine
+2. Upload reference models to `models/`
+3. Begin NX model introspection
+4. Set up first study (DoE)

projects/hydrotech-beam/kb/fea/models/sol101-static.md

@@ -0,0 +1,46 @@
+# SOL 101 — Static Analysis
+
+**Simulation:** Beam_sim1.sim
+**Solver:** NX Nastran SOL 101 (Linear Static)
+**Status:** Pending gap resolution
+
+---
+
+## Setup
+
+| Item | Value | Notes |
+|------|-------|-------|
+| Solution type | SOL 101 (Linear Static) | Appropriate for this problem |
+| Element type | ❓ TBD | Gap G8: CQUAD4/CQUAD8 (shell) or CTETRA/CHEXA (solid)? |
+| Mesh density | ❓ TBD | Gap G8: convergence checked? |
+| Loading | ❓ TBD | Gap G2: point load? distributed? self-weight? |
+| BCs | ❓ TBD | Gap G1: cantilever? simply-supported? |
+
+## Result Extraction
+
+| Output | Method | Expression/Sensor | Status |
+|--------|--------|-------------------|--------|
+| Mass | NX expression | `p173` | ✅ Known |
+| Tip displacement | ❓ Sensor or .f06 parse | TBD | Gap G3, G6 |
+| Von Mises stress | ❓ Sensor or .f06 parse | TBD | Gap G4, G6 |
+
+## Solver Considerations
+
+*From Technical Breakdown:*
+
+- **Linear assumption:** 22 mm displacement on likely 2+ m beam → L/δ probably OK. Verify.
+- **Mesh sensitivity:** Stress at hole edges is mesh-dependent. Need convergence check (Gap G8).
+- **Mesh morphing vs remesh:** Parametric NX models typically remesh on update. Need to confirm behavior across DV range (Gap G7).
+- **Runtime estimate:** Single beam, ~10K–100K DOF → probably seconds to low minutes per evaluation.
+
+## Validation Checklist
+
+- [ ] Baseline mass matches NX expression `p173`
+- [ ] Baseline displacement matches reported ~22 mm
+- [ ] Mesh convergence verified at baseline
+- [ ] Mesh quality acceptable at DV range extremes
+- [ ] Model rebuilds cleanly at all 4 corners of design space
+
+## History
+
+- **Gen 001** (2026-02-09): Initial documentation from technical breakdown. All solver details pending gap resolution.

projects/hydrotech-beam/kb/materials/steel-aisi.md

@@ -0,0 +1,26 @@
+# Steel (AISI)
+
+**Status:** Placeholder — needs full material card details
+
+---
+
+## Properties
+
+| Property | Value | Units | Source |
+|----------|-------|-------|--------|
+| Standard | AISI | — | Intake |
+| Grade | ❓ TBD | — | Need from NX model |
+| Yield strength | ❓ TBD | MPa | — |
+| E (Young's modulus) | ❓ TBD | GPa | — |
+| Density | ❓ TBD | kg/m³ | — |
+| Poisson's ratio | ❓ TBD | — | — |
+
+## Notes
+
+- Stress allowable of 130 MPa was given as constraint — need to confirm basis (Gap G9)
+- If yield is ~250 MPa, then 130 MPa implies SF ≈ 1.9 — conservative
+- Material card should be extracted from NX model during introspection
+
+## History
+
+- **Gen 001** (2026-02-09): Placeholder from intake — "Steel (AISI)" is all we have

projects/hydrotech-beam/models/README.md

@@ -0,0 +1,23 @@
+# Reference Models — Hydrotech Beam
+
+Golden copies of the NX model files. **Do not modify these directly.**
+
+Studies should copy these to their own `model/` folder and modify there.
+
+## Files
+
+| File | Description | Status |
+|------|-------------|--------|
+| `Beam.prt` | NX CAD part — sandwich I-beam with lightening holes | ⏳ Pending upload |
+| `Beam_fem1.fem` | FEM mesh file | ⏳ Pending upload |
+| `Beam_fem1_i.prt` | Idealized part for FEM | ⏳ Pending upload |
+| `Beam_sim1.sim` | Simulation file — SOL 101 static | ⏳ Pending upload |
+
+## Key Expression
+
+- `p173` — beam mass (kg)
+
+## Notes
+
+- Model files will be added once Syncthing/file transfer is set up
+- Verify model rebuild across full design variable range before optimization