settled-reach/docs/workshops/economic-built-world.md

Workshop — The economic & built world (Stage 2)

Second workshop in the world-derivation arc. The first (D-227 / D-228) settled the natural substrate. This one is Stage 2: the economic & built world.

Premise & the order

The world is built in three stages, all frozen in amber — the goal right now is a deterministic starting state we can look at through the Atlas, not a running simulation:

1. Natural world tiles — terrain / water / vegetation / geology (done: D-227 derive-don't-store world model, D-228 composite tile schema)
2. Economic world tiles → architecture + infrastructure ← this workshop
3. Living sim — NPCs, clutter, the lived-in feel (deferred — "NPCs follow the world when it's there"; complicated; later)

So: built structures are IN scope; NPCs / creatures / clutter are OUT.

The load-bearing caveat (pin this)

Settlement, architecture, and infrastructure placement derive from the economy's initial state + seed — NEVER the rolling economy.

Rolling-economy placement would make the built world un-re-derivable: a city's existence or layout would drift as prices move, and you could no longer rebuild it from seed. The physical world is pinned to the economy's starting snapshot. (Persistence model, D-227: the rolling economy is saved sim-state with cache-eviction; it never feeds the derivation of physical form.)

What this workshop must produce (→ D-records + tickets)

Three threads. We do not close until they're resolved in records — convergence on one is not "done" (lesson from Workshop 1).

• Q1 — Economy → placement. How does the initial economic state (+ seed + the natural world from Stage 1) decide where settlements, economic activity, and infrastructure sit? Ports at harbours (D-228 morphology zones), farms on alluvial plains, mines at lithology/ore, hubs at trade-corridor confluence. The initial-economics caveat lives here.
• Q2 — Placement → built form. How does a placement become actual architecture / roads / rail / districts occupying voxels (D-227)? This must connect to the existing generator-architecture work, not restart it — height tiers, z-levels, block/chunk skeletons, cultural room grammar all already have decisions. The open seam is the economic → architectural hand-off and how built structures sit in the voxel/floor model (D-227).
• Q3 — Frozen-amber coherence. Natural (Stage 1) + economic/built (Stage 2) must compose into one deterministic starting state the Atlas can render — re-derivable from initial-economics + seed, no rolling-state dependency, no squaring, coherent with the baked reliefmap (which is a deterministic input, Q-100).

Build on what exists (don't restart)

• Natural substrate (Stage 1): D-227, D-228.
• Economics: D-176 (productivity seeding), D-178 (economic model), D-184 (commodity catalogue), D-199 (economic read-set for city generation), D-189 (brand layer). Burnelli owns these.
• Settlement / provinces: D-191 (Atlas / settlement), D-205 (province boundaries), D-220 (settlement density — tile scale, density classes, vertical pressure).
• Architecture / generator: D-106 / D-108 (height tiers, rooftop clause), D-200 / D-201 / D-203 (three-tier execution, region, LRU cache), D-110 (signed z-levels), D-222 (subtile → district hierarchy), server/src/.../skeleton_gen.rs (Layer-4 block placement), and the prior docs/workshops/generator-architecture/ rounds.

Team & angles (Sonnet-pinned)

• Burnelli — the initial-economic-state → placement driver: what economic signals (commodity production, trade corridors, harbour quality, agricultural potential) determine where things go, at what scale, frozen at t=0.
• Tyre — the derivation architecture: initial-economy + seed + natural-world → settlement → built form, deterministically; how built structures occupy the voxel/floor model (D-227); the economic→architectural hand-off seam.
• Miri — settlement & cultural architecture: how heritage/culture shapes the built form on top of the economic skeleton (she led the generator-arch worldbuilding); keeping it coherent with the Reach's setting.
• Gestalt — systems meaning: what built form does (movement, access, chokepoints, asymmetric-info), and what a tile/structure must carry for it.
• Nigel — variety: do two economically-similar bodies produce categorically different cities, or same-y grids? Where does sameness creep in?
• Araminta — visual architecture grammar: where the visual/render grammar plugs into the derived built form (lighter touch; structural derivation leads).

Round 1 task (each)

Read this brief + the pointed decisions/code for your angle. Post an opening position: (1) your contribution to Q1/Q2/Q3 from your lens, (2) the key forks / risks, (3) anything in existing decisions that constrains or contradicts the approach (especially the initial-economics caveat). Investigation + position, not final design. Flag blockers early.

Process

Round-based. Lead consolidates each round (no raw cross-talk dumped at the principal) and pulls Jeroen in. Close only when D-records + tickets exist AND Jeroen confirms the whole problem — not one thread — is resolved. Teammates edit nothing; the lead does all git.

Heartbeat: if stuck >15 min on one thing without progress, message the lead with the blocker — don't silently retry.