docs(briefings): update all 18 briefings for v0.2 pivot

Remove stale v0.1 references (detective/smuggler gameplay,
hand-authored content pipeline, named NPCs) and align with
v0.2 reality: generator-first (D-122), LLM voice pipeline
(D-138), composable behaviors (D-139), tycoon bookmark deferred.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docs/briefings/araminta.md

@@ -1,11 +1,28 @@
 # Araminta - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete — visual grammar, spatial layouts, and color system all specified.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path. **Araminta's zone visual grammar and tile palettes are generator prerequisites — on the critical path.**
 
-## Status
-**ACTIVE.** Mostly unblocked. Visual Grammar document has zero upstream dependencies — can start immediately. Spatial layouts need Miri's setting (available from workshop Round 1) + Paula's relationship web (available from workshop Round 2).
+## v0.2 Pivot — Key Changes for Your Role
+The visual system shifts from designing layouts for three hand-crafted social sites to designing the visual grammar that the generator uses to produce legible zones at scale.
+
+**What changes:**
+- The three specific social sites (Logistics Hub, The Last Shift bar, maintenance corridors) are no longer hand-crafted deliverables. They become instances of generated zone types.
+- D-033 player color split (smuggler `#e8e0d0` / detective `#e0e8ff`) no longer applies — single tycoon character type in v0.2.
+- D-034 FRIEND visual treatment as an authoring assignment is gone — the FRIEND pattern is now a generator template; Araminta's role is ensuring the entity color system communicates relationship progression clearly for generated NPCs.
+- Spatial layout deliverables shift: instead of three specific floor plans, Araminta produces zone type visual rules that the generator instantiates.
+
+**What survives:**
+- D-033 entity color = relationship to player (unknown teal, friendly green, POI amber, hostile red) — unchanged
+- Insert/minimap visual language
+- Monologue display system
+- Phase 1-3 placeholder art pipeline
+- Zone palette identities (D-036 three-zone breakdown maps to generator zone types)
+
+**New critical path items (Araminta prerequisites for generator spike):**
+- Zone visual grammar — what each zone type looks like visually; tile palette per zone type
+- Character creation visual spec — full character customisation (D-126): hair, clothing, colours
 
 ## Decisions Relevant to Your Role
 - D-013: Diegetic insert/POI navigation — in-world UI aesthetic
@@ -15,50 +32,43 @@ The Settled Reach: top-down immersive sim, single-character perspective, asymmet
 - D-018: Three-range sound — visual indicators for medium range
 - D-019: Top-down art style
 - D-021: Official title "The Settled Reach"
-
-### Workshop Decisions (Content Gap Analysis)
-- **D-033: Entity color = relationship to player** — your proposal, approved by project lead:
-  - Unknown/Neutral: cool teal `#4a9ebb`
-  - Known/Friendly: soft green `#6bc9a6`
-  - Person of Interest: warm amber `#e8c547`
-  - Hostile/Dangerous: muted red `#d45d5d`
-  - Static objects: muted grey `#8b8ba0`
-  - Player: `#e0e8ff` (detective) / `#e8e0d0` (smuggler)
-  - Transitions: 0.5s smooth fade. THE FRIEND's first green→amber shift should be the first color change in the session.
-- **D-034: THE FRIEND visual treatment** — no special rendering before contradiction. Standard colored rectangle + name label. Earned visual detail: color transition from green to amber IS the visual punch. Same system, loaded context.
-- **D-036: Sova Transit District** — three visual zones:
-  - Zone 1 (Logistics Hub): cool grey-navy institutional
-  - Zone 2 (Bar): warm dark, amber lighting
-  - Zone 3 (Corridors): neutral dark, dim irregular lighting
-- **D-038: Audio in v0.1** — 8 files confirmed. Your visual sound indicators are complementary (direction info), not replacement. Design can be subtler.
-- **D-039: All 6 wow moments** — span gate glow as first-impression anchor (wow moment #1). Spatial layouts serve wow moment sightlines.
+- D-033: Entity color = relationship to player (palette unchanged)
+- D-036: Sova Transit District visual zones — maps to generator zone types
+- D-114: v0.2 proof-of-life = generator + graphics (graphics = Araminta's domain)
+- D-117: Tycoon bookmark — single character type, apartment wakeup, goes to work
+- D-119: Generator spike Sprint 25 — Araminta's zone visual grammar is a prerequisite
+- D-122: All NPCs generated — visual system must handle generator-created entities
+- D-126: Full character customisation (hair, clothing, colours)
+- D-128: Culture implicit in starting location — visual language should communicate Krenn culture
+- D-131: First Settled Reach moment = apartment + insert activation — visual priority
+- D-135: Setting delivery via both layers (visual + insert) in parallel
 
 ## Open Questions Assigned to You
-- Q-003: Art direction (LEAD) — further resolved by workshop; long-term direction still open
+- Q-003: Art direction (LEAD)
+- Q-WTF-039: Character creation screen — portrait render or tile-scale preview?
+- Q-WTF-040: Do creation choices trace into the generated apartment?
 
 ## Current Priorities
-**Spatial layouts are the single most important visual DELIVERABLE.**
+Consult `docs/sprints/` for active sprint briefing.
 
-1. **v0.1 Visual Grammar document** — color palette, entity sizing, label rules, UI layers, fog spec. Zero dependencies. Start immediately.
-2. **Spatial layouts x3** — tile-level floor plans with sightline analysis:
-   - Logistics Hub: main corridor chokepoint, scanner bays (public), supervisor office + restricted storage (private), break room (semi-private)
-   - Bar (The Last Shift): corner booth as key observation position, bar counter (high visibility), back room, news ticker display
-   - Corridors + Smuggling spaces: maintenance corridors, hidden spaces in 40-year-old construction, transition chokepoints
-3. **Insert/HUD wireframe** — dual-character variants (smuggler social map vs detective case file overlay). One system, two `lattice_profile` parameters.
-4. **Monologue display system spec** — typography, animation, stacking, character voice differentiation (smuggler warmer, detective cooler)
-5. **Sound indicator visual design** — fog-edge pulse, complementary to audio
-6. **THE FRIEND visual treatment spec** — after Paula's NPC profiles
+**Zone visual grammar is the single most important visual deliverable for the generator spike.**
 
-### Placeholder art pipeline (4 phases)
-- Phase 1 (Structural): tile floor plans, entity rectangles, fog rendering — blocks gameplay testing
-- Phase 2 (Information): insert overlay, monologue display, dialogue panel, sound indicators — blocks content testing
-- Phase 3 (Atmosphere): zone palettes, lighting, span gate glow, character insert variants — blocks experience testing
-- Phase 4 (Polish): sprite replacements, animations, particles — pre-release
+1. **Zone type visual grammar** — blocked by Miri's zone identity spec. Once Miri delivers zone type definitions, Araminta produces tile palette and visual rules per zone type. Blocked by: Miri zone identity spec. Blocks: Tyre generator zone template parameters.
+2. **Character customisation visual spec** — hair, clothing, colours (D-126). What are the customisation dimensions? What does the creation screen communicate? Feeds Q-WTF-039 (portrait vs tile-scale preview).
+3. **Apartment visual spec** — generated apartment reflects economic position. What does a small business owner's apartment look like visually? How does the generator know which tiles/props to use? Q-WTF-040 feeds into this.
+4. **Entity color system for generated NPCs** — D-033 palette unchanged. Ensure relationship transition visuals (especially the first green→amber shift) work with generated NPC names and labels, not hand-authored ones.
+5. **Insert/HUD wireframe for tycoon** — single character type variant (vs previous smuggler/detective dual variants). One `lattice_profile` parameter for v0.2.
 
-**v0.1 target: Phases 1-3. Zero image files — everything procedural (colored rectangles, styled text, shader overlays).**
+### Placeholder art pipeline (status)
+- Phase 1 (Structural): tile floor plans, entity rectangles, fog rendering — establish zone type rules
+- Phase 2 (Information): insert overlay, monologue display, dialogue panel — adapt for tycoon character
+- Phase 3 (Atmosphere): zone palettes per generated zone type, character customisation display
+- Phase 4 (Polish): sprite replacements, animations — post-generator spike
 
 Note: Image generation via /asset-gen costs money — always get Team Leader permission before generating.
 
 ## Key Documents
 - decisions/perception.md — D-011 through D-019, D-033
-- docs/workshops/content-gap-analysis_v0_1/ — workshop outputs and SUMMARY.md (your Round 2 has spatial layout ASCII art)
+- decisions/scope.md — D-114 through D-120
+- decisions/content.md — D-036, D-126 through D-131
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 pivot summary, dependency chain

docs/briefings/dudley.md

@@ -1,20 +1,22 @@
 # Dudley - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41 confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020: Rust/bevy_ecs server). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete. Knowledge Graph & Information Boundaries Workshop complete (D-041).
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Status
-STANDBY. This briefing will be populated when backend/engine implementation begins.
+STANDBY. This briefing will be populated when backend/engine implementation begins. Note: the generator spike (D-119) is Sprint 25 and is Tyre's domain; Dudley activates when simulation implementation work is assigned.
 
 ## Key Decisions for Your Domain
 Read `decisions/architecture.md` (primary) and `decisions/content.md` (NPC model). Key decisions:
 - **D-010:** Four architectural principles (client-server, info boundaries, deterministic sim, input events)
 - **D-020:** Rust simulation server with bevy_ecs, MessagePack protocol to Godot client
-- **D-024:** NPC ECS model (10 axes + CombatCapability component)
+- **D-024:** NPC ECS model (10 axes + CombatCapability component) — survives in v0.2; applies to generator output
 - **D-026:** Simulation tier engine (Active/Background/State-saved/Ungenerated, timestamp LRU)
 - **D-030:** Testability architecture (hybrid Rust tests, deterministic replay critical)
 - **D-031:** Time system (10 ticks = 1 game-minute, 4 day phases)
+- **D-122:** All NPCs generated — no hand-authored named NPCs. The NpcBlueprint struct (Tyre) is the ECS entry point.
+- **D-129:** Traits + behavior first; relationships Sims + Rimworld style. Codify for systems.
 
 ## Development Workflow
 See `docs/DEVOPS.md` for full procedures. Your key targets:
@@ -27,11 +29,11 @@ See `docs/DEVOPS.md` for full procedures. Your key targets:
 - Server code lives in `server/` — unit tests inline with `#[cfg(test)]`, integration tests in `server/tests/`
 - Cross-boundary IPC fixtures in `tests/`
 
-### Workshop Decisions (relevant to server implementation)
-- **D-034: THE FRIEND ECS spec** — 14 ECS components defined for production-level NPCs (NpcIdentity, Want, Secret, Relationships[3], ToleranceThreshold, DailyRoutine, InformationInventory, Contentment, PersonalityTraits, TellState, SkillSet, AccessTierMap, TriangleMembership, MoodState)
+### Key Workshop Decisions (relevant to server implementation)
 - **D-035: Converged tag taxonomy (6+3)** — dialogue selection pipeline: access (hard filter) → situation (context filter) → trust (hard filter) → mood+topic (weighted selection). Server implements pipeline.
 - **D-038: Audio architecture** — event-driven: SoundEventEmitter → ObserverSnapshot → SoundRenderer. Server emits sound events.
-- **D-041: Knowledge Graph Data Model** — Per-entity `KnowledgeGraph` Component with BTreeMap storage (deterministic). 4-level confidence hierarchy (Suspects/KnowsOf/KnowsDetails/Direct). StableEntityId + EntityRegistry for stable entity references. Event-driven updates via KnowledgeEventQueue. Sprint 2 scope: data structures + direct observation + basic decay + observer snapshot integration (#112). Canonical Rust structs at `docs/workshops/knowledge-graph-information-boundaries/round2-synthesis.md` Part 3.
+- **D-041: Knowledge Graph Data Model** — Per-entity `KnowledgeGraph` Component with BTreeMap storage (deterministic). 4-level confidence hierarchy (Suspects/KnowsOf/KnowsDetails/Direct). StableEntityId + EntityRegistry for stable entity references. Event-driven updates via KnowledgeEventQueue. Canonical Rust structs at `docs/workshops/knowledge-graph-information-boundaries/round2-synthesis.md` Part 3.
+- **D-122:** All NPCs generated — the 14 ECS components from the FRIEND spec (D-034) survive as the NPC component model for ALL generated NPCs, not just hand-authored ones.
 
 ## Key Documents
 - decisions/ - domain-split decision files (see decisions/README.md for index)

docs/briefings/gestalt.md

@@ -1,11 +1,17 @@
 # Gestalt - Project Briefing
-Last updated: 2026-02-13
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41+ confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). Sprints 1-4 complete. Sprint 5 (Live) active — content at scale.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Engine selected (D-020). Sprint 25 generator spike confirmed as critical path.
 
-## Status
-**ACTIVE.** Sprint 5 systems content support. Tag taxonomy is formalized in YAML schemas. Knowledge vocabulary delivered. Content pipeline operational. Primary role this sprint: validate FRIEND pack content against systems constraints, support relationship phase mapping.
+## v0.2 Pivot — Key Changes for Your Role
+- **Generator-first (D-114):** The proof-of-life is the generator producing legible characters at scale, not a hand-built vertical slice.
+- **Tycoon bookmark (D-117):** Zero investigation content for v0.2. Tycoon (small business owner) is the starting state in the Krenn System.
+- **All NPCs generated (D-122):** No hand-authored named NPCs. The FRIEND pattern (D-034) survives as a generator template instruction set, not an authoring assignment.
+- **Broad verb vocabulary (D-130):** Life verbs, not tycoon-specific — all career types use the same verb set.
+- **Consequence model (D-132):** Dual-scale — Rimworld-style sharp events + DF-style slow accumulation simultaneously.
+- **Skills affect outcome (D-118):** Mostly Category C (everyone sees same verbs); skill modifies outcome probability.
+- **NpcBlueprint struct (Tyre prerequisite for D-119):** Generator output format must encode the 10-axis model (D-024 survives).
 
 ## Decisions Relevant to Your Role
 - D-005: Core concept — story generator mechanics, emergent narrative from systems
@@ -16,59 +22,49 @@ The Settled Reach: top-down immersive sim, single-character perspective, asymmet
 - D-017: Perception loadout system — observer queries
 - D-018: Three-range sound system — information quality by distance
 - D-020: Godot client + Rust/bevy_ecs simulation via subprocess/IPC
-- D-024: 10-axis NPC consolidation
+- D-024: 10-axis NPC model (survives; applies to all generated NPCs)
 - D-025: Social site as systemic unit
 - D-026: Timestamp eviction
-- D-027: Vertical slice as systems proof
 - D-028: Axis-to-pipeline mapping (dialogue selection)
-- D-032: Separate monologue pools — `character` is a hard partition tag
-- D-034: THE FRIEND ECS spec — full pipeline depth test
-- D-035: Converged tag taxonomy (6+3) — your Round 2 design is canonical
+- D-035: Converged tag taxonomy (6+3)
 - D-038: Audio architecture — event-driven system
-- D-039: 6 wow moments — systems must support all 6
 - D-041: Knowledge Graph Data Model — 4-level confidence hierarchy, contradiction detection
+- D-114: v0.2 proof-of-life = generator + graphics
+- D-117: Tycoon bookmark, zero investigation content
+- D-118: Skills affect outcome (Category C — everyone sees same verbs)
+- D-119: Generator spike Sprint 25 — critical path
+- D-122: All NPCs generated, no named hand-authored characters
+- D-125: Quietly responsive world — gradient of caring by social proximity
+- D-129: Traits + behavior first; relationships Sims + Rimworld style
+- D-130: Broad life-verb vocabulary (not tycoon-specific)
+- D-132: Dual-scale consequence model (sharp events + slow accumulation)
 
-## What's Been Delivered (Sprints 2-4)
-### Server infrastructure (all operational):
-- Knowledge graph components + types (#361), event queue (#363), direct observation flow (#364), decay (#365) — Sprint 2
-- Content directory structure (#385), schema definitions (#386), validate-content CLI (#392) — Sprint 3
-- Global enums YAML (#387), entity-attributes.yaml (#388), pools.yaml (#389), template YAMLs (#390), triangle YAMLs (#391) — Sprint 4
-- Seed configuration schema (#394) — Sprint 4
-- YAML content loader Phase 2 (#408) — Sprint 4
-- YAML-to-RON converter (#403) — Sprint 4
-- Line previewer CLI (#407) — Sprint 4
-
-### Content pipeline: fully operational
-- Schemas defined, loader working, validator running, previewer available
+## What Survives From v0.1
+- Content pipeline infrastructure: schemas, loader, validator, previewer — all operational
 - Tag taxonomy formalized in `content/_schema/` and `content/global/enums/`
+- 10-axis NPC model (D-024) — applies to generator output
+- Knowledge graph (D-041)
+- Verb system (VerbPriorityProfile refactor needed for tycoon verbs)
 
-## Sprint 5 Priorities
-**Sprint briefing:** `docs/sprints/sprint-5/copy.md` (supporting copy team)
+## Current Priorities
+Consult `docs/sprints/` for active sprint briefing.
 
-### Primary:
-1. **Relationship phase mapping for Kael and Sera** — map the arc phases to concrete systems triggers, tag transitions, and knowledge state thresholds. Support Paula during FRIEND profile authoring.
-2. **#379 NPC Authoring Style Guide validation** — review Gestalt constraints section, verify tag usage rules, validate 4-layer pipeline documentation.
-3. **FRIEND pack content validation** — when #297/#298 content arrives, validate tag compliance, access tier correctness, trust progression logic, monologue trigger prerequisites.
-
-### Supporting:
-4. **Tag usage review** — ensure FRIEND pack content exercises the full tag taxonomy correctly
-5. **Contradiction detection spec support** — verify FRIEND contradiction content maps correctly to D-041 knowledge states
+### v0.2 systems design:
+1. **Verb map for tycoon bookmark** — broad life-verb vocabulary design (D-130). Economic, social, mundane verbs. Job = rails to launch from, not a cage.
+2. **NpcBlueprint systems spec** — define how the 10-axis model (D-024) maps to generator output format. Co-design with Tyre.
+3. **Skills × outcomes design** — Category C interaction model (same verbs, different outcome weights per skill). What does skill actually modify?
+4. **Consequence model design** — dual-scale mechanics (D-132): what triggers a sharp event? What accumulates slowly? How does the player read the accumulation?
+5. **Composable behavior primitives** — traits + behavior engine design (D-129). Culture + role + context as behavioral primitives.
 
 ## Open Questions Assigned to You
-- Q-002: v0.1 scope definition (co-lead)
-- Q-005: Prototype scale (co-lead with Tyre, Miri)
 - Q-010: Storyteller AI architecture (co-lead with Nigel)
-- Q-012: Generation expansion method (co-lead with Mellanie)
-- Q-013: Line previewer temporal progression (co-lead with Dudley)
-- Q-014: Audio timing with monologue chime (co-lead with Ozzie)
-- Q-015: Generation expansion for FRIEND content (co-lead with Mellanie)
-- Q-017: Triangle pressure threshold (co-lead with Paula)
 - Q-024: Gossip propagation timing (co-lead with Tyre)
-- Q-026: Contradiction detection algorithm (co-lead with Paula, Dudley)
+- Q-WTF-036: Behavioral deltas in monologue vs current state only
 
 ## Key Documents
-- decisions/content.md — D-023 through D-037
-- decisions/architecture.md — D-008 through D-031, D-041
-- docs/sprints/sprint-5/copy.md — current sprint briefing (copy team, where Gestalt supports)
-- content/_schema/ — YAML schema definitions (your taxonomy formalized)
+- decisions/content.md — D-023 through D-132
+- decisions/scope.md — D-114 through D-120
+- decisions/architecture.md — D-008 through D-041, D-133 through D-137
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 pivot summary
+- content/_schema/ — YAML schema definitions
 - content/global/ — enums, knowledge, pools, templates, triangles

docs/briefings/gore.md

@@ -1,28 +1,50 @@
 # Gore - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
+
+## v0.2 Pivot — Key Changes for Your Role
+The workshop confirmed and sharpened the thematic frame. "Is this enough?" survives as the central question. The change is that it now must be posed through a generated tycoon's life, not through authored detective/smuggler characters.
+
+**What changes:**
+- The thematic question is no longer framed through smuggler-vs-detective as "two answers." The tycoon IS the question: a small business owner in a mid-Reach system. Has this person settled? Is settling valid? Does the player make it more or settle deeper?
+- Consequence replaces complicity as the thematic frame (D-132 supersedes D-091). The player's arc is not "did you help or hinder the conspiracy?" but "what did your choices produce and do you own them?"
+- Fully emergent moral arc for v0.2 (D-131). No authored arc structure. The generator must prove relationships are readable before narrative depth is layered on.
+
+**What survives:**
+- Life-sim as thematic ground floor (D-023) — your insight confirmed and central to v0.2
+- Contentment axis (D-024) — connects generated NPCs to thematic question, more important than ever
+- Unentangled majority as load-bearing thematic wall (D-029) — quiet life must feel genuinely good
+- "Player choices ARE the content" (D-127) — the Rimworld model, explicitly confirmed in workshop
 
 ## Decisions Relevant to Your Role
-- D-005: Core concept - ascension as transformative character progression
-- D-007: Five pillars - thematic foundations supporting ascension narrative
-- D-008: Action pillar - scales with ascension level, hubris wall as ascension check
-- D-017: Perception modes - scaling with ascension, expanded awareness at higher tiers
+- D-005: Core concept — ascension as transformative character progression (long-term)
+- D-007: Five pillars — thematic foundations
+- D-008: Action pillar — hubris wall as ascension check
+- D-017: Perception modes — scaling with ascension
 - D-021: Official title "The Settled Reach"
-
-### Round 17 Decisions (Thematic Architecture)
-- **D-023: Life-sim as thematic ground floor** - Your insight: life-sim substrate IS the thematic spine. "Is this enough?" requires honest counterweight. Quiet life must feel genuinely good, not empty. Conspiracies are weather.
-- **D-024: Contentment axis** - Your proposal: NPCs track whether current life satisfies Want. Connects generated NPCs to thematic question. Is this life worth living?
-- **D-027: Smuggler + detective as two answers to central question** - Smuggler has chosen camouflage and routine. Detective has chosen pursuit and purpose. Both face "is this enough?" differently.
-- **D-029: Unentangled majority as load-bearing thematic wall** - Most NPCs are NOT pursuing transcendence. They've settled. That choice must feel valid, not cowardly.
+- D-023: Life-sim as thematic ground floor
+- D-024: Contentment axis — NPCs track whether current life satisfies Want
+- D-029: Unentangled majority as load-bearing thematic wall
+- D-114: v0.2 proof-of-life = generator + graphics
+- D-117: Tycoon bookmark, zero investigation content
+- D-122: All NPCs generated, no named hand-authored characters
+- D-127: Player choices are the content — Rimworld model
+- D-131: First Settled Reach moment = apartment + insert activation
+- D-132: Consequence replaces complicity as thematic frame; fully emergent moral arc
 
 ## Open Questions Assigned to You
 - Q-004: One campaign or eras? (co-lead with Miri)
-- ~~Q-009: Time system design~~ — **Resolved** as D-031 (10 ticks = 1 game-minute, 4 day phases)
 
 ## Current Priorities
-Ensure vertical slice thematic spine is sound (both characters face "is this enough?"). Contentment axis implementation in NPC generation. Mundane NPC life must feel valid — write guide on presenting unentangled life as genuinely satisfying, not failed ambition.
+Consult `docs/sprints/` for active sprint briefing.
+
+### v0.2 thematic design:
+1. **Tycoon thematic frame** — what is the tycoon's version of "is this enough?" A small business owner who started something. What are they pursuing? What have they already accepted? Design the thematic question the tycoon bookmark poses.
+2. **Consequence arc design** — the dual-scale consequence model (D-132): what does slow accumulation mean thematically? Reputation as conscience. Debt as consequence. Relationship erosion as moral record. Gore's role: ensure the systems produce moral weight, not just mechanical outcomes.
+3. **Contentment axis in tycoon context** — revisit D-024 for the tycoon setting. What does NPC contentment mean for a logistics worker vs a small business owner in the Krenn System?
+4. **Mundane NPC life validity** — the unentangled majority must feel like a genuine life, not failed ambition. This is more important in v0.2 where ALL NPCs are generated and must carry this.
 
 **Future flag:** Base builder DLC as thematic counter-offer to ascension (settling as active choice vs escape). Not now — but keep design space open.
 

docs/briefings/hoshe.md

@@ -1,18 +1,18 @@
 # Hoshe - Project Briefing
-Last updated: 2026-02-13
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41+ confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). Sprints 1-4 complete. Sprint 5 (Live) active — content at scale.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Status
-**ACTIVE.** Sprint 5 is content-focused with no dedicated QA tickets, but test infrastructure from Sprint 4 needs maintenance and the content pipeline needs validation coverage.
+**ACTIVE.** Test infrastructure from earlier sprints is operational. v0.2 focus: generator output validation — can the generator produce legible NPCs? Are relationships readable from generator output?
 
 ## Decisions Relevant to Your Role
 Read `decisions/architecture.md` (D-010, D-020, D-030) and `decisions/perception.md` (D-011, D-017, D-018). Key decisions:
 - **D-010:** Information boundaries — testable? Can we verify information never leaks?
 - **D-020:** MessagePack serialization — correct round-trip? No data loss at protocol boundary?
-- **D-027:** Vertical slice success criteria (30-min runway, divergent playthroughs, emergent discovery)
 - **D-030:** Testability architecture (hybrid Rust tests, gdUnit4, three-layer IPC, CauseChain)
+- **D-119:** Generator spike Sprint 25 — the success criterion is "can the player read NPC relationships from generator output?" Hoshe defines and verifies this criterion.
 
 ## What's Been Delivered (Sprints 2-4)
 ### Test infrastructure now in place:
@@ -27,20 +27,19 @@ Read `decisions/architecture.md` (D-010, D-020, D-030) and `decisions/perception
 - Global knowledge files (#388) — canonical FactId source for validation
 - Line previewer CLI (#407) — can verify content loads without errors
 
-## Sprint 5 Priorities
+## Current Priorities
+Consult `docs/sprints/` for active sprint briefing.
 
-### Integration test maintenance:
-1. **Verify existing integration tests still pass** after Sprint 4 merges — regression check
-2. **Content loading integration tests** — verify YAML content loader handles real campaign content correctly (not just test fixtures)
+### Generator spike validation (v0.2 critical path):
+1. **Generator output legibility test plan** — define what "can the player read NPC relationships from generator output?" means as a testable criterion. Produce test plan before the Sprint 25 generator spike begins.
+2. **NpcBlueprint struct tests** — when Tyre delivers the NpcBlueprint struct design, write unit tests verifying the 10-axis model (D-024) is correctly encoded in generator output.
+3. **Generated NPC relationship readability test** — functional test: given a generated location with generated NPCs, can a blind observer describe social relationships correctly? Design the test protocol.
 
-### Content quality support:
-3. **FactId validation testing** — when #393 (pre-commit hook) lands, verify it catches real typos and doesn't false-positive on valid content
-4. **Line previewer regression tests** — verify FRIEND pack content loads through previewer without errors when #297/#298 complete
-
-### Ongoing priorities (from previous sprints):
+### Infrastructure maintenance:
+4. **Verify existing integration tests still pass** — regression check after any architectural changes
 5. **Test harness improvements** — reusable fixtures for server+client pairs
-6. **Edge case coverage** — malformed packets, disconnects, entities at map edges, interactions at max range
-7. **Dedicated test map** — minimal map for routing, pathfinding, visibility, protocol correctness (not dependent on content)
+6. **Dedicated test map** — minimal map for routing, pathfinding, visibility, protocol correctness (not dependent on hand-authored content)
+7. **Edge case coverage** — malformed packets, disconnects, entities at map edges, interactions at max range
 
 ## Development Workflow
 See `docs/DEVOPS.md` for full procedures. Your key targets:
@@ -58,6 +57,7 @@ See `docs/DEVOPS.md` for full procedures. Your key targets:
 ## Key Documents
 - decisions/ — domain-split decision files (see decisions/README.md for index)
 - docs/DEVOPS.md — build, test, lint, CI procedures
-- docs/sprints/sprint-5/ — current sprint briefings
+- docs/sprints/ — current sprint briefings
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 success criteria context
 - tests/ — integration and end-to-end tests
 - TEAM.md — team roster

docs/briefings/justine.md

@@ -1,11 +1,11 @@
 # Justine - Project Briefing
-Last updated: 2026-02-13
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41+ confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). Sprints 1-4 complete. Sprint 5 (Live) active — content at scale.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05). v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Status
-**ACTIVE.** Single-ticket sprint for CI. Goal is content quality assurance — prevent FactId typos from reaching main during heavy content authoring.
+**ACTIVE.** CI and build pipeline maintenance. Content validation infrastructure remains relevant as the AI-assisted content pipeline (D-123) produces NPC content at scale.
 
 ## Key Decisions for Your Domain
 Read `decisions/architecture.md` (D-020, D-026, D-030) and `decisions/questions.md` (Q-007). Key decisions:

docs/briefings/mellanie.md

@@ -1,65 +1,64 @@
 # Mellanie - Project Briefing
-Last updated: 2026-02-13
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41+ confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). Sprints 1-4 complete. Sprint 5 (Live) active — content at scale.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
-## Status
-**ACTIVE.** Sprint 5 lead writer. This is the heaviest copy sprint — FRIEND packs carry D-027 success criterion #3 and D-039 wow moment #3. Quality bar is high.
+## v0.2 Pivot — Key Changes for Your Role
+The copy pipeline fundamentally shifts from hand-authoring specific NPC profiles to designing the culture-driven voice system that feeds the generator.
+
+**What dies:**
+- FRIEND pack authoring for Kael Davan and Sera Venn — D-122 eliminates all named hand-authored NPCs
+- Smuggler voice card and detective voice card as primary deliverables — single playable character type in v0.2
+- D-032 hard partition (smuggler/detective monologue pools) — no longer applicable; one character type
+- Hand-authored ~1,030-1,380 line content volume per sprint — generator replaces hand-authoring of NPC lines
+- Monologue as primary narrative feedback channel — demoted to supplementary per workshop findings
+
+**What survives:**
+- Player monologue — hand-authored, excluded from "limited vocabulary at first" (Q-WTF-042 open)
+- Voice guide work — the culture-primary voice architecture (D-121) is Mellanie's domain
+- Tag taxonomy (D-035) — selection architecture survives; pools now AI-assisted
+- Environmental text and flavor text — still authored
+- UI microcopy — still authored
+- News ticker — still authored
+- Tycoon character voice — one character background, one monologue pool
+
+**Key shift:** Mellanie's primary deliverable for v0.2 is culture-primary voice cards (D-121, D-128). Culture drives voice; job modifies it. These are the constraints that feed the AI content pipeline (D-123). The hand-authoring model (write 10, generate 40) survives for anchor lines; but the bulk of NPC dialogue is AI-assisted templating from culture vectors.
 
 ## Key Decisions for Your Domain
 - D-005: Single-character perspective — all narrative filtered through one viewpoint
 - D-013: Diegetic UI text — in-world written content and documents
-- D-016: Internal monologue system — primary narrative content delivery mechanism
+- D-016: Internal monologue system — supplementary (not primary) narrative channel
 - D-021: Official title "The Settled Reach"
-- D-027: Vertical slice — smuggler + detective, station district
-- D-028: Dialogue architecture — tagged line pools with four relational layers
-- D-032: Separate monologue pools per character — non-negotiable hard partition
-- D-034: THE FRIEND NPC pattern — one production-level NPC per character
-- D-035: Converged tag taxonomy (6+3) — your authoring format
-- D-036: Sova Transit District / Krenn System — first concrete setting
-- D-037: Contraband = unlicensed lattice components — smuggling access, not weapons
-- D-039: All 6 wow moments in scope
+- D-028: Dialogue architecture — tagged line pool selection architecture survives
+- D-035: Converged tag taxonomy (6+3) — authoring format
+- D-036: Sova Transit District / Krenn System — setting for all content
+- D-037: Contraband = unlicensed lattice components — world content flavor
+- D-117: Tycoon bookmark — one starting type for v0.2 (not smuggler/detective)
+- D-121: Voice is culture-driven, job as modifier (inverted from prior assumption)
+- D-122: All NPCs generated — NPC content via AI templating, not hand-authoring
+- D-123: Generative AI for NPC content templating via culture vectors
+- D-128: Culture implicit in starting location — Krenn System = Krenn culture
+- D-131: First Settled Reach moment = apartment + insert activation
+- D-134: Groundhog Day alarm clock homage (first day only) — Mellanie writes the monologue
 
-## What's Been Delivered (Sprints 2-4)
-- Dual Lens Authoring Guide (#261) — **DONE** (Sprint 3)
-- PC-as-NPC unified spec (#381) — done
-- Smuggler voice card + moral arc spec (#382) — done
-- THE MIRROR pattern spec (#380) — done
-- Content directory structure (#384, #385) — done
-- Content schema definitions (#386) — done
-- Wiki-to-YAML conversion (#398) — done
-- Monologue content pool ~200 lines (#399) — done
-- NPC-format briefs for both PCs (#383) — done
-- News ticker headline pool (#395) — done
-- Environmental text examples (#378) — done
-- YAML content loader Phase 2 (#408) — done (server loads real content)
-- Line previewer CLI (#407) — done (can test dialogue output)
+## Current Priorities
+Consult `docs/sprints/` for active sprint briefing.
 
-## Sprint 5 Priorities
-**Sprint briefing:** `docs/sprints/sprint-5/copy.md`
+### v0.2 voice pipeline (critical path items):
+1. **Culture-primary voice cards for Krenn System** — the primary pipeline deliverable. Blocked by Miri's culture profile. Once Miri delivers the Krenn culture profile (D-128), Mellanie formalises it as a voice card: tone register, formality norms, emotional expression, verbal tics, what Krenn people sound like under stress vs at ease. This feeds the AI content pipeline (D-123).
+2. **Job-as-modifier voice spec** — how does being a small business owner modify the Krenn base voice? What does a tycoon sound like vs a logistics worker vs a bar owner? Design the modifier layer (D-121).
+3. **Player monologue for tycoon** — hand-authored monologue lines for the tycoon character. Voice, tone, what they notice, what they care about. This is still hand-authored (excluded from "limited vocabulary" per Q-WTF-042).
+4. **Day 1 content** — alarm clock homage (D-134), insert activation moment (D-131). These are authored set-pieces.
+5. **UI microcopy** — still authored, coordinate with Stig on length constraints.
 
-### Critical path (voice patterns gate everything):
-1. **#310 Character voice speech patterns** — CRITICAL START, day 1. Sentence-level execution detail for smuggler + detective (sentence length, contractions, verbal tics, stress markers). Blocks #297, #298, #379.
-2. **#297 THE FRIEND: Kael Davan** — 75-100 hand-authored lines, full profile, multi-phase arc. Blocked by #310.
-3. **#298 THE FRIEND: Sera Venn** — 75-100 hand-authored lines, trust-contamination arc. Blocked by #310.
-4. **#379 NPC Authoring Style Guide** — consolidated handbook. Parallel with #310 but final version needs voice patterns complete.
-5. **#401 PC-as-NPC content authoring** — ~25 authored items. Blocked by #297 + #298.
-
-### Can start immediately:
-6. **#409 UI microcopy** — ~50 UI strings, joint ticket with Stig (client). YAML format. Coordinate on length constraints.
-
-## Content Volume Estimate
-~1,030-1,380 authored lines total. ~3,200-4,200 after generation expansion (4x dialogue, 2x monologue).
-
-## Asks from Others
-- **From Paula:** 10-axis profiles for Kael and Sera (personality, relationships, wants, secrets, routines) — parallel work during voice patterns
-- **From Gestalt:** Relationship phase mapping for both FRIENDs, tag usage validation
-- **From Stig:** UI string length constraints for #409
+## Open Questions Assigned to You
+- Q-012: Generation expansion method (co-lead with Gestalt)
+- Q-WTF-036: Behavioral deltas in monologue vs current state only — directly affects Mellanie's trigger catalog
+- Q-WTF-042: Is player monologue excluded from "limited vocabulary at first"? — directly affects Mellanie's quality floor
 
 ## Key Documents
-- decisions/content.md — D-023 through D-037
-- docs/sprints/sprint-5/copy.md — current sprint briefing
-- docs/workshops/content-gap-analysis_v0_1/ — workshop outputs
+- decisions/content.md — D-023 through D-132
+- decisions/scope.md — D-114 through D-120
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 pivot summary
 - content/_schema/ — YAML schema definitions
-- content/campaigns/main/systems/krenn/sova/sova-transit/ — target content directory

docs/briefings/miri.md

@@ -1,52 +1,59 @@
 # Miri - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete — Sova Transit District established as first concrete setting, wiki taxonomy designed.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path. **Miri's zone identity spec and Krenn culture profile are generator prerequisites — these are on the critical path.**
 
-## Status
-**ACTIVE.** Multiple deliverables unblocked. Sova setting brief (Round 1) is the v0.1 slice of the cultural generation guide. Wiki taxonomy structure has zero dependencies — can start immediately. Contraband specification can be written now.
+## v0.2 Pivot — Key Changes for Your Role
+The workshop confirmed Sova Transit District as the v0.2 setting (tycoon bookmark in the Krenn System) and resolved the culture architecture gap in Miri's favour.
+
+**What changes:**
+- D-027 vertical slice (smuggler + detective) is superseded. No named NPCs (Kael Davan, Sera Venn, Naia, Maret) as production content — D-122.
+- Detective institutional chain of command is deferred — no investigation content for v0.2.
+- Character selection roster (Q-011) reframed: skills + bookmark (CK3 style), not a character roster with named starting characters.
+- Culture is no longer deferred: D-128 resolves it. Culture is implicit in starting location. Krenn System = Krenn culture. The player doesn't select culture — they select a starting location and inherit it.
+
+**What survives and gains priority:**
+- Sova Transit District as setting — tycoon bookmark is HERE (D-117)
+- Krenn System setting details (D-036) — all canonical
+- Zone identity and culture profile — now generator prerequisites, highest priority
+- Contraband spec (D-037) — survives as world content (storyline, not investigation objective for v0.2)
+
+**New critical path items (Miri prerequisites for generator spike):**
+- Zone identity spec — what zone types mean in the Settled Reach's social vocabulary
+- One culture profile: Krenn System / Station Sova — blocks voice pipeline, NPC gen, AI content pipeline
 
 ## Decisions Relevant to Your Role
 - D-005: Core concept — asymmetric information, single-character perspective
 - D-016: Internal monologue — character voice, unreliable narrator
 - D-017: Perception modes — lore-consistent
-- D-021: Official title "The Settled Reach" (repository remains "commonwealth")
-
-### Workshop Decisions (Content Gap Analysis)
-- **D-036: Sova Transit District / Krenn System** — your Round 1 output is canonical. First concrete, named star system. Krenn System: mid-Reach, G3V, ~180 years settled, ~2.4M population. Station Sova: logistics hub, ~12,000 pop. Sova Transit District: 40-year-old prefab-modular-retrofitted freight district.
-  - NPC naming: Krenn conventions (compact, consonant-heavy, first-name-primary)
-  - Bar: "The Last Shift" (official) / "Lera's" (informal)
-  - Atmosphere: "quotidian-with-undertow"
-- **D-037: Contraband = unlicensed lattice components** — your proposal confirmed. Primary: aftermarket lattice mods. Secondary: medical-grade neural replacements (humanitarian dimension), Severance tech. Smuggling access, not weapons.
-- **D-034: THE FRIEND NPC pattern** — Kael Davan (your naming) is smuggler's FRIEND. Sera Venn is detective's FRIEND. Paula's Round 2 NPC names are canonical; your name mapping validated.
-- **D-040: Wiki taxonomy structure** — your Round 2 proposal is canonical:
-  - You own wiki structure (new categories, template changes, structural decisions)
-  - Hierarchical: star-systems/ → stations/ → districts/ → locations/
-  - Characters flat (not nested under locations)
-  - YAML frontmatter on every entry with `status` field (proposed → draft → canonical)
-  - 14 entry templates defined
+- D-021: Official title "The Settled Reach"
+- D-036: Sova Transit District / Krenn System — canonical setting (survives unchanged)
+- D-037: Contraband = unlicensed lattice components — world content, not v0.2 investigation objective
+- D-040: Wiki taxonomy structure
+- D-114: v0.2 proof-of-life = generator + graphics
+- D-117: Tycoon is the v0.2 bookmark — small business owner in Krenn System
+- D-119: Generator spike Sprint 25 — Miri's zone identity spec + culture profile are prerequisites
+- D-122: All NPCs generated, no named hand-authored characters
+- D-123: Generative AI for NPC content templating via culture vectors
+- D-128: Culture implicit in starting location — Krenn System = Krenn culture
+- D-135: Setting delivery via both layers (visual + insert) in parallel
 
 ## Open Questions Assigned to You
 - Q-004: One campaign or eras? (co-lead with Gore)
-- Q-011: Character selection roster for prototype (co-lead with Paula)
+- Q-WTF-041: What should the player feel looking at the span gate from their apartment?
 
 ## Current Priorities
-**Setting foundation + wiki structure — parallel tracks, both unblocked.**
+**Zone identity spec and Krenn culture profile are on the critical path. These must exist before/during the generator spike.**
 
-1. **Contraband Specification** — formalize D-037 as a standalone document. Unblocks Paula's NPC motivations and Mellanie's cargo dialogue. Immediate.
-2. **Sova Texture Appendix** — 1 page covering:
-   - Slang/idiom glossary (15-20 terms: "shift" vs "rotation", credit terminology, swearing conventions)
-   - Informal decoration details (graffiti, stickers, locker personalization)
-   - The local complaint (ventilation in Sector 3)
-   - Sensory gaps Mellanie identified
-   Blocks Mellanie's environmental text and monologue authoring. Critical.
-3. **Wiki taxonomy structure + first entries** — create `wiki/` directory with templates, Krenn System entry, Station Sova entry, Sova Transit District entry. Establishes the pattern.
-4. **NPC name finalization** — validate Paula's Round 2 assignments against Krenn conventions. Names already proposed: Kael, Voss, Lera, Torek, Drin, Maret, Hael, Sera, Nils, Kosse, Naia, Pael, Tev, Ren.
-5. **Detective institutional chain of command** — who assigned the investigation, stated mandate, political pressures. Blocks Paula's detective character build.
-6. **Meridian coverage map, span gate schedule, off-station connections** — medium priority, parallel with content work.
+1. **Zone identity spec** — what zone types mean in the Settled Reach's social vocabulary. Logistics hub, residential, commercial, transit corridor, restricted industrial, social venue. What does each zone communicate about the people who inhabit it? Blocks: generator zone template parameters, Araminta tile palettes.
+2. **Krenn System / Station Sova culture profile** — working-class pragmatic, ~180 years settled, compact consonant-heavy naming. Formalise as a structured culture vector document: tone, formality registers, emotional expression norms, values, slang register, what Krenn people do/don't discuss with strangers. Blocks: voice pipeline (Mellanie), NPC gen (Tyre), AI content pipeline (D-123).
+3. **Tycoon bookmark setting brief** — what does Station Sova look like from a small business owner's perspective? What kind of business? What economic pressures? What does the tycoon's apartment reflect about their position? Blocks: Ozzie's Day 1 experience brief, Araminta's zone visuals.
+4. **Wiki taxonomy maintenance** — update wiki entries (Krenn System, Station Sova, Sova Transit District) to reflect v0.2 framing. Remove investigation-specific details from primary entries.
+5. **NPC naming conventions confirmation** — Krenn naming conventions documented in D-036 apply to ALL generated NPCs. Confirm the convention is suitable for generator-scale name creation.
 
 ## Key Documents
-- decisions/content.md — D-036 (setting), D-037 (contraband)
+- decisions/content.md — D-036 (setting), D-037 (contraband), D-121 through D-132
+- decisions/scope.md — D-114 through D-120
 - decisions/process.md — D-040 (wiki taxonomy)
-- docs/workshops/content-gap-analysis_v0_1/ — workshop outputs and SUMMARY.md (your Round 1 IS the Sova brief; Round 2 has wiki taxonomy)
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 pivot summary, dependency chain

docs/briefings/nigel.md

@@ -1,29 +1,53 @@
 # Nigel - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
+
+## v0.2 Pivot — Key Changes for Your Role
+The replayability frame shifts from "same conspiracy, different character lens" to "same generator, different seeded world." The anti-metagaming goal survives; the mechanism changes.
+
+**What changes:**
+- D-027 two-character proof is superseded. Replayability in v0.2 comes from the generator producing different worlds, not from two playable characters with inverted experiences.
+- Tier 1 authored drama modules are deferred (D-023 amendment). The generator IS the replayability mechanism — variable NPC seeds, social triangles, economic circumstances, relationships.
+- No "solving the conspiracy" metagaming problem in v0.2. The replayability question is: does a second run feel like a genuinely different life?
+
+**What survives:**
+- Variable entanglement rate per seed (D-029) — the principle is unchanged; the triangles are economic and social rather than investigation-intrigue
+- Generator variety design (D-136): both structural and cosmetic variety at different scales. Same design problem, generator context.
+- "No skill ceiling in v0.2" (D-137) — skill progression open-ended, not ladder-gated
+- Emergent narrative as primary replayability mechanism (D-127)
 
 ## Decisions Relevant to Your Role
-- D-005: Replayability through perspective - each playthrough reveals different information
-- D-008: Procedural generation for replayability - no two runs identical
+- D-005: Replayability through perspective — each playthrough a different seeded world
+- D-008: Procedural generation for replayability
 - D-010: Deterministic simulation aids debugging and replay verification
-- D-012: Chunk-based maps - no solvable maps, ensuring fresh exploration each run
-- D-017: Perception modes as playstyle selectors - different builds see different games
+- D-012: Chunk-based maps
+- D-017: Perception modes as playstyle selectors
 - D-021: Official title "The Settled Reach"
-
-### Round 17 Decisions (Replayability)
-- **D-023: Pool-based Tier 1 modules** - Plural modules drawn from pool at game start. Access tiers (0-3) control which modules appear. Different tier seeds = different conspiracy landscapes. Anti-metagaming: can't learn "the conspiracy," only "a conspiracy."
-- **D-027: Two-character proof** - Your requirement: vertical slice must support two fundamentally different playthroughs. Same world seed, different character lens, inverted experience.
-- **D-029: Variable entanglement rate per seed** - Your proposal: 30/50/20 split varies per playthrough to defeat metagaming. Can't calibrate "everyone with hesitation tells is suspicious" because the ratio changes. Module attachment ratio (60-70/30-40 known vs stranger NPCs) also varies.
+- D-023: Pool-based Tier 1 modules (deferred to post-generator; v0.2 ships zero Tier 1)
+- D-029: Variable entanglement rate per seed — economic/social triangles in v0.2
+- D-114: v0.2 proof-of-life = generator + graphics
+- D-117: Tycoon bookmark, zero investigation content
+- D-119: Generator spike Sprint 25 — critical path
+- D-122: All NPCs generated
+- D-127: Player choices are the content — Rimworld model
+- D-136: Both structural and cosmetic generator variety at different scales
+- D-137: No skill ceiling in v0.2
 
 ## Open Questions Assigned to You
 - Q-010: Storyteller AI architecture (co-lead with Gestalt)
 
 ## Current Priorities
-Access tier system design (Tier 0-3 content pools). Seed-based population split variance implementation. Module attachment logic (known vs stranger NPC ratio). Vertical slice replayability proof: verify smuggler and detective playthroughs produce fundamentally different experiences from identical world seed.
+Consult `docs/sprints/` for active sprint briefing.
 
-**Key replayability multiplier:** Access tiers make Tier 1 conspiracy pool variable across playthroughs, not just within one game.
+### v0.2 replayability design:
+1. **Generator variety spec** — structural and cosmetic variety at different scales (D-136). What varies per seed: NPC personality distributions, economic triangle shapes, social proximity webs, zone layout. Design the variety dimensions the generator must support.
+2. **Anti-metagaming in tycoon context** — the anti-metagaming concern (D-029) reframed: in v0.2, what would "solving the game" look like? Knowing which NPC personality types to befriend? Optimal economic strategies? Design variety to prevent calibration.
+3. **Generator replayability test criteria** — what makes two generated runs feel genuinely different? Define playtest criteria for the generator spike (D-119): if Tyre's output passes, what does Nigel need to see?
+4. **Seed-based population variance** — variable 30/50/20 split implementation design for economic/social/mundane triangles.
+
+**Key replayability multiplier:** The generator produces structurally different worlds per seed. Second run is not a different character lens on the same world — it is a different world, same bookmark.
 
 ## Key Documents
 - decisions/ - domain-split decision files (see decisions/README.md for index)

docs/briefings/oscar.md

@@ -1,8 +1,8 @@
 # Oscar - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05). v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Engine selected (D-020).
 
 ## Status
 STANDBY. This briefing will be populated when networking/multiplayer implementation begins.

docs/briefings/ozzie.md

@@ -1,68 +1,63 @@
 # Ozzie - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete — wow moments budgeted, THE FRIEND designed, audio specified.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated, no detective/smuggler identity frame. Sprint 25 generator spike confirmed as critical path.
 
-## Status
-**ACTIVE.** Validation and gut-check role. Review THE FRIEND contradiction arcs. Finalize audio asset spec. Track wow moment dependencies.
+## v0.2 Pivot — Key Changes for Your Role
+The workshop revealed a core framing error: the game was built as a detective puzzle game but the vision is a single-character life sim. The fix is not cosmetic.
+
+**What dies:**
+- Detective/smuggler as the game's identity — they are jobs, not the game
+- Named NPCs (Kael Davan, Sera Venn) as authored emotional content
+- Pre-authored FRIEND contradiction arcs
+- 6-wow-moment budget tied to investigation content (D-039 is superseded by v0.2 scope)
+- 30-minute investigation runway as the primary experience criterion
+
+**What survives:**
+- The emotional goal: players must feel something about generated NPCs
+- The warmth-before-drama principle: Phase Zero warmth earned through observed relationship progression, not authored backstory
+- NPC legibility as the universal gate: generated NPCs must have enough personality surface area for attachment
+- The engine: simulation, knowledge graph, verb system all survive
+- Quiet responsive world as emotional texture
+
+**New wow moments for v0.2 (to be designed):**
+- First generated NPC who feels like a person, not a dot
+- A relationship that develops visibly over multiple sessions
+- A consequence that traces back to a choice the player made days ago
+- The generator producing something unexpected and specific
 
 ## Decisions Relevant to Your Role
 - D-005: Core concept — player experience of asymmetric information and perspective
 - D-008: Action pillar — hubris wall mechanic
 - D-019: Top-down primary view
 - D-021: Official title "The Settled Reach"
-- D-023: Life-sim substrate — daily life is the sentence, conspiracies are punctuation
-- D-027: Vertical slice — 30-minute runway, both playthroughs feel different, player names an NPC they felt conflicted about
-- D-028: Four dialogue layers — every layer enriches social interaction
-- D-029: Quality floor for unentangled NPCs
+- D-023: Life-sim substrate — daily life is the sentence, events are punctuation
+- D-114: v0.2 proof-of-life = generator + graphics, not hand-built slice
+- D-117: Tycoon bookmark, zero investigation content
+- D-122: All NPCs generated, no named hand-authored characters
+- D-125: Quietly responsive world — gradient of caring by social proximity
+- D-126: Full character customisation (hair, clothing, colours)
+- D-128: Culture implicit in starting location (Krenn System = Krenn culture)
+- D-129: Traits + observable behaviour as NPC personality surface
+- D-131: First Settled Reach moment = apartment + insert activation
+- D-132: Consequence model dual-scale (sharp events + slow accumulation)
+- D-134: Groundhog Day alarm clock homage (first day only)
 
-### Workshop Decisions (Content Gap Analysis)
-- **D-034: THE FRIEND** — your emotional concept, confirmed by project lead. One per character, production-level complex:
-  - Smuggler's FRIEND: Kael Davan. Warmth → trust → doubt → conflict. Observable contradiction (wrong place, deflection, contaminated trust).
-  - Detective's FRIEND: Sera Venn. Same emotional arc, different relationship context (institutional peer, avoidance pattern as tell).
-  - Both follow the pattern: warmth beat, trust beat, contradiction beat, conflict beat. D-027 criterion #3 lives or dies on these NPCs.
-- **D-033: Entity color = relationship to player** — same NPC, different color per character. Green → amber shift on THE FRIEND IS the visual wow moment.
-- **D-038: Audio in v0.1** — your spec is canonical. 8 files:
-  1. `amb_station_base.ogg` — station hum (global, the "you're in space" signal)
-  2. `amb_workplace_layer.ogg` — cargo machinery, scanner pings
-  3. `amb_bar_layer.ogg` — conversation, glass, low music
-  4. `amb_corridor_layer.ogg` — echoes, louder gate hum
-  5. `sfx_footstep_metal.ogg` — walk on metal grating
-  6. `sfx_footstep_metal_run.ogg` — run variant
-  7. `sfx_monologue_chime.ogg` — soft crystalline tone, "neural lattice firing" feel. **Non-negotiable.**
-  8. `sfx_monologue_chime_urgent.ogg` — sharper variant for contradiction/anomaly. Trains player unconsciously.
-- **D-039: All 6 wow moments in scope** — your budget, all promoted by project lead:
-  1. Arrival (minute 0-1): station hum + first monologue chime
-  2. Character's Eye (5-15): observation monologue + urgent chime
-  3. FRIEND Contradiction (20-25): THE FRIEND in wrong place + urgent chime
-  4. Divergence Reveal (2nd playthrough): different colors, names, voice
-  5. News Ticker Gut-Punch: same ticker, opposite reactions
-  6. Quiet Moment: idle reflective monologue
+## Current Priorities
+Consult `docs/sprints/` for active sprint briefing.
+
+### v0.2 player experience design:
+1. **Gut-check the generator spike test** — when Tyre's generator produces output, Ozzie's question is: "Does this NPC feel like a person? Would I name them if they were gone?" Define what legibility looks like to a player.
+2. **Phase Zero warmth spec** — what does the player observe that builds attachment to a generated NPC? Observable behavior, relationship progression cues, world responsiveness signals.
+3. **v0.2 wow moment design** — replace the v0.1 investigation-specific wow moments with life-sim equivalents. Focus on relationship emergence, consequence legibility, and world responsiveness.
+4. **Tycoon Day 1 experience brief** — apartment wakeup, insert activation, first day at work. What should the player feel? What should they want to do next?
 
 ## Open Questions Assigned to You
 - Q-014: Audio timing with monologue chime (co-lead with Gestalt)
-
-## Current Priorities
-**Validation, gut-check, wow moment tracking.**
-
-1. **Review THE FRIEND contradiction arcs** — gut check on Kael's and Sera's shifts. Does the discovery feel right? Does the ambiguity work? Is the replay resonance real?
-2. **Audio asset specification** — finalize technical details (format, generation pipeline, mixing levels, loop points). Identify who generates the 8 files.
-3. **Wow moment dependency tracking** — for each wow moment, track whether its content and systems dependencies are on track:
-   - Arrival: needs station ambient + opening monologue + NPC routines
-   - Character's Eye: needs observation monologue + NPC routine deviation + urgent chime
-   - FRIEND Contradiction: needs full FRIEND content package + spatial staging
-   - Divergence Reveal: needs all dual-lens content for first location
-   - Ticker Gut-Punch: needs ticker content + dual monologue reactions
-   - Quiet Moment: needs reflective lines + time_idle trigger
-4. **Playtest readiness evaluation** — when content reaches critical mass, evaluate whether the 30-minute session delivers
-
-## Priority Ranking of Content Gaps (Your R2)
-- **Tier 1 (game doesn't exist without):** Voice kits + DLG, THE FRIEND, opening 5-min content, observation monologue
-- **Tier 2 (game feels empty without):** Flat NPC pass, audio, news ticker, template content packs
-- **Tier 3 (game feels rough without):** Mirror moments, insert flavor text, spatial wow-moment pass, UI microcopy
+- Q-WTF-040: Do creation choices trace into the generated apartment?
 
 ## Key Documents
-- decisions/scope.md — D-027, D-038, D-039
-- decisions/content.md — D-034 (THE FRIEND)
-- docs/workshops/content-gap-analysis_v0_1/ — workshop outputs and SUMMARY.md (your Round 2 has wow moment budget, audio spec, priority ranking)
+- decisions/scope.md — D-114 through D-120
+- decisions/content.md — D-023, D-122 through D-132
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 pivot summary and convergences

docs/briefings/paula.md

@@ -1,71 +1,65 @@
 # Paula - Project Briefing
-Last updated: 2026-02-13
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41+ confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). Sprints 1-4 complete. Sprint 5 (Live) active — content at scale.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
-## Status
-**ACTIVE.** Sprint 5 NPC design lead. FRIEND profiles are the deliverable that carries D-027 success criterion #3 ("player names an NPC they felt conflicted about") and D-039 wow moment #3. These NPCs must feel real.
+## v0.2 Pivot — Key Changes for Your Role
+
+**What dies:**
+- Kael Davan and Sera Venn as production content — D-122 eliminates all named hand-authored NPCs
+- THE FRIEND as an authoring assignment for specific named characters
+- The smuggler + detective triangle web (Voss/Kael/Nils, Maret/Drin/Voss, etc.) as authored production content
+- D-027 success criterion #3 as authored — the player must feel conflicted about a *generated* NPC
+- D-032 hard partition between smuggler/detective monologue pools — single playable character type in v0.2
+
+**What survives:**
+- THE FRIEND *pattern* (D-034) — the 3+ relationship phases, observable contradiction, sympathetic motivation design now lives as a generator template instruction set
+- 10-axis NPC model (D-024) — applies to all generated NPCs
+- 30/50/20 population split rationale (D-029) — applies to economic/social/mundane triangles in tycoon context
+- Triangle model as generator architecture — triangles are still the atomic social unit, now generator output
+- The relationship web pattern — generator creates social webs; Paula's role is designing the *template shapes* the generator follows
+- Asymmetric information as core mechanic
+- Consequence-as-narrative (D-132 reframes moral arc: emergent, not authored)
+
+**Key shift:** Paula's role moves from authoring specific NPC profiles (Kael, Sera) to designing the generator templates that produce FRIEND-quality NPCs. The NPC relationship web is now a generator spec, not a writing assignment.
 
 ## Decisions Relevant to Your Role
-- D-005: Asymmetric information as core mechanic driving faction dynamics
+- D-005: Asymmetric information as core mechanic driving social dynamics
 - D-016: Internal monologue — unreliable narrator reflecting character perspective
-- D-024: NPC triangle model — 10 axes + combat component
+- D-024: NPC triangle model — 10 axes + combat component (survives; applies to generator output)
 - D-025: Cross-template triangles via reference links
-- D-028: Four relational dialogue layers
-- D-029: 30/50/20 population split
-- D-032: Separate monologue pools per character — hard partition, no shared lines
-- D-033: Entity color = relationship to player — green/teal/amber/red maps to access tier model
-- D-034: THE FRIEND NPC pattern — your designs are canonical
-- D-035: Converged tag taxonomy — your 4 layers map to tags
-- D-036: Sova Transit District — 15 NPCs with Krenn System names
-- D-037: Contraband = unlicensed lattice components — moral ambiguity confirmed
-- D-039: All 6 wow moments in scope — THE FRIEND contradiction is wow moment #3
-- D-041: Knowledge Graph Data Model — 4-level confidence hierarchy, FactId format, contradiction detection
+- D-028: Four relational dialogue layers (survives; pools now AI-assisted per D-123)
+- D-029: 30/50/20 population split — rationale survives, tycoon economic triangles replace investigation triangles
+- D-033: Entity color = relationship to player
+- D-034: THE FRIEND pattern — survives as generator template, not authoring assignment
+- D-035: Converged tag taxonomy — tag architecture survives
+- D-036: Sova Transit District / Krenn System — setting survives (tycoon bookmark is Krenn System)
+- D-041: Knowledge Graph Data Model — 4-level confidence hierarchy, contradiction detection
+- D-114: v0.2 proof-of-life = generator + graphics
+- D-117: Tycoon bookmark, zero investigation content
+- D-122: All NPCs generated, no named hand-authored characters
+- D-123: Generative AI for NPC content templating via culture vectors
+- D-125: Quietly responsive world — gradient of caring by social proximity
+- D-128: Culture implicit in starting location (Krenn System = Krenn culture)
+- D-129: Traits + observable behaviour as NPC personality surface; relationships Sims + Rimworld style
+- D-132: Consequence replaces complicity as thematic frame; fully emergent moral arc
 
-## What's Been Delivered (Sprints 2-4)
-- **Dual Lens Authoring Guide (#261) — DONE** (Sprint 3, was critical path blocker — now resolved)
-- PC-as-NPC unified spec (#381) — done
-- Smuggler voice card + moral arc spec (#382) — done
-- THE MIRROR pattern spec (#380) — done
-- NPC-format briefs for both PCs (#383) — done
-- Round 2 NPC pattern/motivation mapping (#396) — done
-- Triangle 1 fix (#377) — done
-- Drin Tier 2 profile expansion (#397) — done
-- Content pipeline infrastructure all in place (schemas, loader, validator, line previewer)
+## Current Priorities
+Consult `docs/sprints/` for active sprint briefing.
 
-## Your Relationship Web (Canonical — Round 2)
-15 NPCs, 5 triangles:
-- **Triangle 1 (Hub Power):** Voss - Kael - Nils
-- **Triangle 2 (Worried Knowledge):** Maret - Drin - Voss
-- **Triangle 3 (Bar Tensions):** Lera - Torek - Ren
-- **Triangle 4 (Worried Partner):** Naia - Kael - Sera (connects both FRIENDs)
-- **Triangle 5 (Informant Question):** Naia - Kosse - Drin (cross-template)
-
-Distribution: 3 flat (Pael, Ren, Tev), 7 mundane triangle, 4-5 entangled.
-
-## Sprint 5 Priorities
-**Sprint briefing:** `docs/sprints/sprint-5/copy.md`
-
-### Parallel work during voice patterns (#310) authoring:
-1. **10-axis profiles for Kael and Sera** — personality, relationships, wants, secrets, routines. Can start immediately.
-2. **Relationship phase mapping** — comfort->crack->observation->confrontation for Kael; trust->data->recognition->question->contamination for Sera.
-
-### After voice patterns complete:
-3. **#297 THE FRIEND: Kael Davan** — full Tier 1 profile + dialogue authoring (co-author with Mellanie using voice spec)
-4. **#298 THE FRIEND: Sera Venn** — full Tier 1 profile + dialogue authoring
-5. **#401 PC-as-NPC content authoring** — reverse dual-lens notes, ~25 authored items. Blocked by #297 + #298.
-
-### Supporting:
-6. **#379 NPC Authoring Style Guide** — contribute tier templates and authoring rules
+### v0.2 NPC architecture design:
+1. **FRIEND pattern as generator spec** — rewrite D-034's authoring assignments as generator template parameters. What profile values produce a FRIEND-quality NPC? What axis ranges? What triangle role? Output: a generator instruction set Tyre can implement.
+2. **Triangle template shapes for tycoon context** — what social triangles does a small business owner encounter? Economic triangles (supplier/customer/competitor), workplace triangles, social triangles. Design 3-5 triangle templates as generator primitives.
+3. **Relationship arc design for generated NPCs** — how does the player read relationship progression with a generated NPC? What observable signals mark phase transitions? Warmth earned through observed progression (not authored backstory).
+4. **30/50/20 for tycoon scope** — revisit the population split rationale in context of economic, social, and mundane triangles. What does the "entangled 20%" mean when there's no investigation content?
+5. **Consequence model narrative design** — dual-scale consequences (D-132): what does slow accumulation look like from inside a relationship? Reputation erosion, debt, trust decay. How does the player read it?
 
 ## Open Questions Assigned to You
-- Q-011: Character selection roster for prototype (co-lead with Miri)
-- Q-017: Triangle pressure threshold (co-lead with Gestalt)
-- Q-026: Contradiction detection algorithm (co-lead with Gestalt, Dudley)
+- Q-WTF-036: Behavioral deltas in monologue vs current state only
+- Q-WTF-040: Do creation choices trace into the generated apartment?
 
 ## Key Documents
-- decisions/content.md — D-023 through D-037
-- docs/sprints/sprint-5/copy.md — current sprint briefing
-- docs/workshops/content-gap-analysis_v0_1/ — workshop outputs
-- content/campaigns/main/systems/krenn/sova/sova-transit/ — target content directory
+- decisions/content.md — D-023 through D-132
+- decisions/scope.md — D-114 through D-120
+- docs/workshops/wheres-the-fun/workshop-outcomes.md — v0.2 pivot summary

docs/briefings/qatux.md

@@ -1,41 +1,47 @@
 # Qatux - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020: Godot 4 + Rust/bevy_ecs via subprocess/IPC). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions (D-001 through D-137). Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked, outcomes at `docs/workshops/wheres-the-fun/workshop-outcomes.md`. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Decisions Relevant to Your Role
-All decisions (D-001 through D-040) — maintains decision domain files in `decisions/` as the canonical record. Indexes and retrieves decision context for the team.
+All decisions (D-001 through D-137) — maintains decision domain files in `decisions/` as the canonical record. Indexes and retrieves decision context for the team.
 
 **D-022 (Process change):** Discussions now captured directly in round documents at `docs/discussions/round-NN-topic.md` instead of DISCUSSION.md. Qatux must be included in all team interactions to ensure documentation.
 
 ### Decision Domain Structure
 Decisions are split across domain files in `decisions/`:
-- `decisions/architecture.md` — D-008, D-009, D-010, D-012, D-020, D-026, D-030, D-031
+- `decisions/architecture.md` — D-008, D-009, D-010, D-012, D-020, D-026, D-030, D-031, D-133, D-134, D-135, D-136, D-137
 - `decisions/perception.md` — D-011, D-015, D-016, D-017, D-018, D-019, D-033
-- `decisions/content.md` — D-023, D-024, D-025, D-028, D-029, D-032, D-034, D-035, D-036, D-037
-- `decisions/scope.md` — D-001, D-003, D-005, D-006, D-007, D-013, D-014, D-027, D-038, D-039
+- `decisions/content.md` — D-023, D-024, D-025, D-028, D-029, D-032, D-034, D-035, D-036, D-037, D-121 through D-132
+- `decisions/scope.md` — D-001, D-003, D-005, D-006, D-007, D-013, D-014, D-027, D-038, D-039, D-114 through D-120
 - `decisions/process.md` — D-004, D-021, D-022, D-040
-- `decisions/questions.md` — Q-001 through Q-017
-- `decisions/rejected.md` — R-001 through R-010
+- `decisions/questions*.md` — Q-001 onwards (including Q-WTF-* from workshop)
+- `decisions/rejected.md` — R-001 onwards
 - `decisions/README.md` — domain index and query examples
 
-### Workshop Summary (Latest — v0.1 Content Gap Analysis)
-**Date:** 2026-02-11
-**Format:** 6-agent workshop (Mellanie, Paula, Araminta, Miri, Gestalt, Ozzie), 2 rounds
-**Decisions produced:** 9 (D-032 through D-040)
-**Key themes:** Dual-lens content architecture, THE FRIEND NPC pattern, converged tag taxonomy (6+3), Sova Transit District as first concrete setting, entity color = relationship to player, audio specification, wow moment budget, wiki taxonomy
-**Open questions added:** Q-012 through Q-017
+### Workshop Summaries
+**Where's the Fun? Workshop** (2026-03-05):
+- 5 rounds, 9 agents + Qatux + SI, 24 decisions locked (D-114 through D-137)
+- Outcomes: `docs/workshops/wheres-the-fun/workshop-outcomes.md`
+- Key v0.2 pivots: generator-first (D-114), tycoon bookmark (D-117), all NPCs generated (D-122), culture implicit in location (D-128), consequence replaces complicity (D-132)
+- Superseded: D-027, D-014, D-039 (v0.1 framing), D-091
+- Open questions: Q-WTF-033, Q-WTF-036, Q-WTF-039, Q-WTF-040, Q-WTF-041, Q-WTF-042
+
+**v0.1 Content Gap Analysis Workshop** (2026-02-11):
+- D-032 through D-040 produced
+- Outcomes: `docs/workshops/content-gap-analysis_v0_1/SUMMARY.md`
+- Note: Several decisions from this workshop have been amended or superseded by the Where's the Fun? Workshop. Check amendment notes in `decisions/content.md` (D-023, D-024, D-028, D-029, D-034).
 
 ## Open Questions Assigned to You
-None assigned directly.
+None assigned directly. Track all Q-NNN and Q-WTF-* records.
 
 ## Current Priorities
 1. Maintain decision domain files in `decisions/` with any new confirmed decisions after each discussion round
 2. Create round documents directly at `docs/discussions/round-NN-topic.md` (D-022 workflow)
 3. Update `docs/discussions/README.md` with new round entries after formal closure
 4. Update relevant agent briefing files with new decision references
-5. **Create and update diagrams** whenever D-records are added or modified — use the `/d2-diagram` skill to generate d2 source + PNG. New decisions get a diagram if they describe systems, flows, or relationships. Existing diagrams in `docs/diagrams/{category}/` must be updated when their source decisions change. Categories: architecture, data-flow, entity, state, ui.
+5. **Create and update diagrams** whenever D-records are added or modified — use the `/d2-diagram` skill to generate d2 source + PNG. Existing diagrams in `docs/diagrams/{category}/` must be updated when their source decisions change. Categories: architecture, data-flow, entity, state, ui.
 6. Re-index changed documents in Qdrant after updates
 7. Verify briefing freshness against decision domain files
 
@@ -48,11 +54,11 @@ None assigned directly.
 - `TEAM.md` — team roster
 
 ## Recent Archive Activity
+- 2026-03-13: Ticket #658 — updated all 18 agent briefings for v0.2 pivot
+- 2026-03-05: Where's the Fun? Workshop concluded — 24 decisions locked (D-114 through D-137)
+  - Created `docs/workshops/wheres-the-fun/workshop-outcomes.md`
+  - Added D-114 through D-137 to decision domain files
+  - Added Q-WTF-033, Q-WTF-036, Q-WTF-039, Q-WTF-040, Q-WTF-041, Q-WTF-042 to questions
+- 2026-02-13: Sprint 5 briefings updated (gestalt, mellanie, paula, hoshe, stig, justine)
 - 2026-02-11: v0.1 Content Gap Analysis Workshop documented
-  - Created `docs/workshops/content-gap-analysis_v0_1/SUMMARY.md`
-  - Added D-032 through D-040 to decision domain files
-  - Added Q-012 through Q-017 to `decisions/questions.md`
-  - Updated all 6 workshop participant briefings (mellanie, paula, araminta, miri, gestalt, ozzie)
-  - Updated all 12 non-workshop briefings for decision count and resolved questions
 - 2026-02-10: Round 17 archived to `docs/discussions/round-17-content-architecture.md`
-- 2026-02-10: All agent briefings updated with Round 17 decisions

docs/briefings/si.md

@@ -1,8 +1,8 @@
 # Si - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41 confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete — ~50 tickets identified across 7 categories. Knowledge Graph & Information Boundaries Workshop complete (D-041) — Sprint 2 ticket impact requires reconciliation with existing #49 epic children.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Decisions Relevant to Your Role
 All decisions across all domains. Read `decisions/README.md` for the index. Query decisions DB for sprint planning:
@@ -15,24 +15,32 @@ make decisions-active     # List all active decisions
 ## Open Questions Assigned to You
 All open questions - tracks as tickets for assignment and progress monitoring.
 
+## v0.2 Critical Path (from Where's the Fun? Workshop)
+The generator spike (D-119) is Sprint 25 and is the first deliverable. Everything gates on it.
+
+**Prerequisites that must exist before/during the generator spike:**
+1. Miri: Zone identity spec + Krenn culture profile — blocks voice, NPC gen, AI pipeline
+2. Araminta: Zone visual grammar, tile palettes — blocked by Miri zone identity spec
+3. Tyre: NpcBlueprint struct design — generator output format
+4. Mellanie: Culture-primary voice cards — blocked by Miri culture profile
+
+**Dependency chain:**
+```
+Miri: Zone Identity Spec + Krenn Culture Profile
+  |-- Araminta: zone visual grammar, tile palettes
+  |-- Tyre: generator zone template parameters, NpcBlueprint
+  |-- Mellanie: culture-primary voice cards
+  v
+Tyre: Generator Spike (Sprint 25)
+  |-- Produces: auto-generated location + NPCs
+  v
+Test: Can the player read NPC relationships from generator output?
+```
+
+**Estimated timeline (Tyre):** 7 sprints to proof-of-life playtest (generated location + legible characters + tycoon bookmark from creation to Day 3).
+
 ## Current Priorities
-Create sprint plan for vertical slice implementation (D-027). Break D-024 through D-041 into tickets. Workshop output (`docs/workshops/content-gap-analysis_v0_1/SUMMARY.md`) contains ~50 deduplicated ticket proposals across 7 categories. Track dependencies:
-- Paula's Dual Lens Authoring Guide (#261) — critical path, blocks all downstream content
-- Miri's contraband spec + Sova texture appendix (blocks Mellanie)
-- Gestalt's tag taxonomy spec + knowledge state vocabulary — **UNBLOCKED by D-041** (Appendix A provides v0.1 vocabulary)
-- Hoshe's test plans (must precede implementation)
-- NPC ECS model (blocks template instantiation)
-- Template system (blocks dialogue system)
-- **Knowledge graph system (D-041)** — Sprint 2 priority, blocks #112, #358, #356. Requires ticket reconciliation with #49 epic.
-
-Vertical slice implementation + content authoring are now parallel workstreams — coordinate with Team Leader on sequencing and resourcing.
-
-### Knowledge Graph Workshop Ticket Impact (D-041)
-See synthesis Part 8 for full details. Key actions:
-1. **Create 8 new tickets** as children of #351 (KnowledgeGraph component, StableEntityId, KnowledgeEventQueue, direct observation flow, basic decay, observer snapshot integration, unit tests, vocabulary for #309)
-2. **Reconcile existing #49 children:** Reparent #89, #138-142, #269, #272, #182, #360 under #351 or mark as resolved/deferred
-3. **Update #112 description** with interface contract from synthesis Part 7
-4. **Update sprint 2 dependencies:** KnowledgeGraph blocks #112, StableEntityId blocks #360, observer snapshot integration blocks #358/#356
+Consult `docs/sprints/` for current sprint briefing. Break v0.2 decisions (D-114 through D-137) into tickets if not already covered. Track dependencies above.
 
 ## Development Workflow
 See `docs/DEVOPS.md` for full procedures. Key awareness for sprint planning:

docs/briefings/stig.md

@@ -1,36 +1,39 @@
 # Stig - Project Briefing
-Last updated: 2026-02-13
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41+ confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020). Vertical slice defined (D-027). Sprints 1-4 complete. Sprint 5 (Live) active — content at scale.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Status
-**ACTIVE.** Light sprint — Sprint 4 delivered most client infrastructure. Sprint 5 focus is content authoring (copy team) with client providing integration points.
+**ACTIVE.** v0.2 brings a character customisation UI requirement and removes the dual-character variant for insert/HUD.
 
 ## Key Decisions for Your Domain
-Read `decisions/perception.md` (primary) and `decisions/scope.md` (D-013, D-014). Key decisions:
+Read `decisions/perception.md` (primary) and `decisions/scope.md` (D-013). Key decisions:
 - **D-013:** Diegetic insert/POI navigation system
 - **D-015:** Camera locked to character, vision cone
 - **D-016:** Internal monologue text display
 - **D-017:** Perception mode overlays
 - **D-019:** Top-down primary view, Godot 4 client (GDScript)
 - **D-028:** Dialogue UI — four relational layers (access tiers, history, trust-gated, unprompted)
-- **D-033:** Entity color = relationship to player — palette: unknown teal, friendly green, POI amber, hostile red, static grey. 0.5s transitions.
-- **D-034:** THE FRIEND visual treatment — standard colored rectangle + name label. Color transition IS the visual punch.
+- **D-033:** Entity color = relationship to player — palette: unknown teal, friendly green, POI amber, hostile red, static grey. 0.5s transitions. Unchanged in v0.2.
+- **D-117:** Tycoon bookmark — single character type in v0.2 (no smuggler/detective variants)
+- **D-126:** Full character customisation (hair, clothing, colours) — new UI requirement
+- **D-131:** First Settled Reach moment = apartment + insert activation — UI must support this moment
 
 ## What's Been Delivered (Sprints 1-4)
 ### Sprint 1 (Run): IPC bridge, player movement
 ### Sprint 2 (See): Fog rendering (#113), camera lock (#116), tile rendering (#129), entity sprites (#130), fog overlay (#131)
 ### Sprint 3 (Know): Content directory structure used by client
 ### Sprint 4 (Feel): Integration tests (#410 tile data, #411 input roundtrip), server bug fix for tile type data (#412)
-### Sprint 5 carry-over: Interaction prompt (#405) — **DONE**
 
-## Sprint 5 Priorities
-**Sprint briefing:** `docs/sprints/sprint-5/client.md`
+## Current Priorities
+Consult `docs/sprints/` for active sprint briefing.
 
-1. **#409 UI microcopy** (joint ticket with copy team) — integrate ~50 UI strings from Mellanie. YAML format. Coordinate on length constraints early.
-   - Interaction prompt labels, knowledge panel headers, relationship state text, HUD labels, tutorial text
-   - File location: `content/campaigns/main/_meta/ui-strings.yaml` loaded via content loader, or `client/scripts/constants/ui_strings.gd`
+### v0.2 client UI:
+1. **Character customisation screen** — hair, clothing, colours (D-126). Blocked by Araminta's character customisation visual spec and Q-WTF-039 (portrait vs tile-scale preview). Once Araminta delivers the spec, implement.
+2. **Insert/HUD — tycoon variant** — remove dual-character variants (smuggler/detective). Single `lattice_profile` parameter. Coordinate with Araminta on tycoon insert wireframe.
+3. **UI microcopy integration** — coordinate with Mellanie on tycoon-voice UI strings. YAML format, length constraints.
+   - File location: `content/campaigns/main/_meta/ui-strings.yaml` or `client/scripts/constants/ui_strings.gd`
 
 ## Development Workflow
 See `docs/DEVOPS.md` for full procedures. Your key targets:

docs/briefings/tiger.md

@@ -1,8 +1,8 @@
 # Tiger - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05). v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated.
 
 ## Status
 STANDBY. This briefing will be populated when localization work begins.
@@ -11,14 +11,10 @@ STANDBY. This briefing will be populated when localization work begins.
 - D-016: Internal monologue system - localization of character voice and personality through text
 - D-021: Official title "The Settled Reach"
 - Q-008: Licensing (open question - affects localization scope and supported languages)
-
-### Round 17 Decisions (Localization Implications)
-- **D-028: Tagged line pool dialogue system** - Localization advantages: each line is tagged with context metadata (access tier, relationship level, trust threshold, mood). Translators receive rich context. Lines are pooled, not tree-branched — translation scope is predictable. Trait modifiers apply post-translation (base line + transformation guide = variants in target language).
-
-### Workshop Decisions (Content Gap Analysis — localization implications)
-- **D-032: Separate monologue pools per character** — hard partition. Two parallel content trees doubles monologue translation scope.
+- **D-028: Tagged line pool dialogue system** — Localization advantages: each line is tagged with context metadata (access tier, relationship level, trust threshold, mood). Translators receive rich context. Lines are pooled, not tree-branched — translation scope is predictable.
 - **D-035: Converged tag taxonomy (6+3)** — 9 tags per line provide rich context for translators. 13 situations, 9 topics, 8 moods. Translation scope predictable from pool size.
 - **D-036: Sova Transit District / Krenn System** — Krenn naming conventions (compact, consonant-heavy). Localization note: proper nouns and slang terms need transliteration guides per target language.
+- **D-121: Voice is culture-driven, job as modifier** — localization implication: culture voice cards are the primary translation unit, not individual NPC profiles. Single tycoon character type in v0.2 (D-117) reduces monologue translation scope vs. prior smuggler/detective dual-pool model (D-032 superseded for v0.2).
 
 ## Key Documents
 - decisions/ - domain-split decision files (see decisions/README.md for index)

docs/briefings/troblum.md

@@ -1,27 +1,25 @@
 # Troblum - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 40 confirmed decisions, 17 discussion rounds + 1 workshop complete. Engine selected (D-020: Godot + Rust/bevy_ecs subprocess). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05). v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Sprint 25 generator spike confirmed as critical path.
 
 ## Decisions Relevant to Your Role
 - D-010: Architectural baseline - four principles
 - D-012: Chunk-based map architecture
-- D-020: Godot 4 client + Rust/bevy_ecs server via subprocess/IPC (your risk assessment shifted integration from GDExtension to subprocess)
-
-### Round 17 Decisions (Technical Evaluation)
-- **D-026: Simulation tier budgets** - Performance targets for technical stress-testing:
+- D-020: Godot 4 client + Rust/bevy_ecs server via subprocess/IPC
+- D-026: Simulation tier budgets — performance targets for technical stress-testing:
   - Active: 30-80 NPCs, full sim, 10-20 tps
   - Background: 500-2,000 NPCs, state machine ticks 1/game-minute, 4 machines each
   - State-saved: 10,000+ NPCs, frozen serialized structs ~1-2KB each
   - Timestamp-based LRU eviction against available sim-space
-- **D-027: Two-character vertical slice** - Architecture implication: ~20% more effort than single-character, no new systems. Multi-observer already supported by D-020 client-server model.
+- D-119: Generator spike Sprint 25 — the generator must produce usable output before anything else matters. Performance of the generator at scale is a key evaluation question.
 
 ## Open Questions Assigned to You
 - ~~Q-001: Engine selection~~ — **Resolved** as D-020 (Godot 4 + Rust/bevy_ecs via subprocess/IPC)
 
 ## Current Priorities
-Monitor D-026 simulation tier implementation for performance validation. Stress-test timestamp-based eviction against worst-case scenarios. Validate bevy_ecs dynamic component performance for tier transitions. Challenge any implementation that doesn't meet stated budgets with hard profiling data.
+Monitor D-026 simulation tier implementation for performance validation. Stress-test timestamp-based eviction against worst-case scenarios. Validate bevy_ecs dynamic component performance for tier transitions. Challenge any implementation that doesn't meet stated budgets with hard profiling data. When the generator spike (D-119) begins, evaluate generator performance at scale: what does generating an entire location's worth of NPCs cost?
 
 ## Key Documents
 - decisions/ - domain-split decision files (see decisions/README.md for index)

docs/briefings/tyre.md

@@ -1,8 +1,8 @@
 # Tyre - Project Briefing
-Last updated: 2026-02-11
+Last updated: 2026-03-13
 
 ## Current Project State
-The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 41 confirmed decisions, 17 discussion rounds + 2 workshops complete. Engine selected (D-020: Godot + Rust/bevy_ecs subprocess). Vertical slice defined (D-027). v0.1 Content Gap Analysis Workshop complete. Knowledge Graph & Information Boundaries Workshop complete (D-041) — architectural foundation for information boundaries system defined.
+The Settled Reach: top-down immersive sim, single-character perspective, asymmetric information core mechanic, Rimworld-style storyteller. 137+ confirmed decisions. Where's the Fun? Workshop complete (2026-03-05) — 24 decisions locked. v0.2 direction: generator-first proof-of-life, tycoon bookmark, all NPCs generated. Engine selected (D-020: Godot + Rust/bevy_ecs subprocess). Knowledge Graph & Information Boundaries Workshop complete (D-041). **Sprint 25 generator spike is Tyre's critical path — the proof-of-life depends on it.**
 
 ## Decisions Relevant to Your Role
 Read `decisions/architecture.md` (primary) and `decisions/perception.md` (secondary). Key decisions:
@@ -15,23 +15,25 @@ Read `decisions/architecture.md` (primary) and `decisions/perception.md` (second
 
 ## Open Questions Assigned to You
 - ~~Q-001: Engine selection~~ — **Resolved** as D-020 (Godot 4 + Rust/bevy_ecs via subprocess/IPC)
-- Q-002: v0.1 scope definition (co-lead)
-- Q-005: Prototype scale (co-lead with Gestalt, Miri)
 - Q-007: Target platforms
 - Q-021: Tick budget overflow policy (co-lead with Dudley)
 - Q-022: NPC pathfinding cache eviction (co-lead with Dudley)
 - Q-024: Gossip propagation timing (co-lead with Gestalt) — preferred direction: queued
 - Q-025: Knowledge graph cap and eviction strategy (co-lead with Dudley)
+- Q-WTF-033: AI templating pipeline — Claude API, local ollama, or manual for v0.2?
 
 ## Current Priorities
-Vertical slice technical implementation:
-1. NPC ECS component model (10 axes + optional CombatCapability component)
-2. **Knowledge Graph Data Model (D-041)** — Sprint 2 priority. Implement canonical Rust structs from workshop synthesis. BTreeMap for deterministic iteration (non-negotiable). StableEntityId + EntityRegistry. KnowledgeEventQueue. Direct observation flow. Basic decay. Observer snapshot integration (#112). ~6.5 developer-days. Blocks #352 (Observer Snapshot Pipeline Workshop).
-3. Template instantiation system (single-ownership + reference links with metadata)
-4. Simulation tier transitions (timestamp LRU + scope tags + bevy_ecs component add/remove)
-5. Access tier system (content filtering by tier 0-3)
-6. Basic cargo/goods system (for smuggling ring mechanics)
-7. Line previewer CLI (weekend build — YAML templates → trait-modified line pools)
+Consult `docs/sprints/` for active sprint briefing.
+
+### v0.2 critical path (generator spike, Sprint 25):
+1. **NpcBlueprint struct design** — prerequisite for the generator spike. Define the generator output format encoding the 10-axis model (D-024). Co-design with Gestalt on systems mapping.
+2. **Generator zone template parameters** — what parameters describe a zone to the generator? Blocked by Miri's zone identity spec.
+3. **Generator spike (D-119)** — Sprint 25. Produce a generated location with generated NPCs. Success criterion: can the player read NPC relationships from generator output?
+4. **AI content pipeline design** — D-123 generative AI for NPC content templating. Q-WTF-033 open: Claude API vs local ollama vs manual. Decide before/during generator spike.
+
+### Architecture maintenance:
+5. Simulation tier transitions (timestamp LRU + scope tags + bevy_ecs component add/remove)
+6. Knowledge Graph Data Model (D-041) — canonical Rust structs from workshop synthesis
 
 **Future flag:** Base builder DLC requires data model stub now: `modifications: Vec<Modification>` on relevant entities. Add to schema early.