The SQLite database contains integral project content (273 tickets,
dependencies, sprint planning). Remove from .gitignore and check in.
WAL/SHM journal files remain ignored as transient.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update Key Documents sections to reference decisions/ directory instead
of monolithic DECISIONS.md. Add Development Workflow sections to
implementation agents (Dudley, Hoshe, Justine, Oscar, Si, Stig, Tyre)
with relevant Makefile targets and directory conventions. Streamline
decision references to point to specific domain files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Agent personality files and skill definitions updated to reference decisions/
domain files instead of monolithic DECISIONS.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds DevOps procedures document and updates CLAUDE.md/README.md to reference
decisions/ domain files and Makefile-based workflow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three-agent analysis (Si, Qatux, Tyre) evaluating approaches to scale
DECISIONS.md. All independently recommended hybrid domain-split markdown
+ SQLite index. Tyre sharpened scope: 7 domains not 11, 2 tables not 3,
pre-commit hook for sync drift prevention (Phase 2).
Also adds D-031 to Round 18 in discussions index.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add decisions_sync.py that parses decisions/*.md markdown headings,
extracts metadata (type, domain, status, round, date), and upserts
into SQLite. Two-pass approach: decisions first, then cross-references
to avoid FK violations on forward references.
Schema adds decisions table (52 rows) and decision_refs table (29 rows)
with cascading deletes. Makefile gains decisions-sync, decisions-coverage,
decisions-active, and decisions-orphan targets. Sync runs as part of
make setup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace monolithic 474-line DECISIONS.md with 7 domain files under
decisions/: architecture, perception, content, scope, process,
questions, rejected. Each file owns its decisions with cross-reference
hyperlinks. Root DECISIONS.md becomes a redirect with domain index.
Reduces per-agent context load by ~70-80% (80-150 lines vs 474).
Taxonomy: architecture (D-008..D-031), perception (D-011..D-019),
content (D-023..D-029), scope (D-001..D-027), process (D-004..D-022),
questions (Q-001..Q-011), rejected (R-001..R-010).
Restores D-002 original text (was a tombstone referencing D-005).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Create client/, server/, tooling/, tests/, .config/ (tracked) and
.cache/ (gitignored). Update CLAUDE.md project structure to reflect
the new layout including workshops directory.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
10 ticks = 1 game-minute, 4 day phases (Morning/Afternoon/Evening/Night),
diegetic time display on insert HUD. Unblocks daily routine pipeline (#88)
and all time-dependent systems. Workshop consensus from Tyre and Gestalt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
7 agents across 2 rounds stress-tested the 232-ticket v0.1 plan against
concept proof, fun delivery, completeness, and testability. Key outcomes:
D-030 testability architecture confirmed, 15 priority promotions, 41 new
tickets (273 total), replay ceiling estimated at 10-12 playthroughs.
Reorganized workshops into per-workshop directories.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Complete the set of whitelistable wrapper scripts so all SQLite
access goes through db/connectors/sqlite-* (query, exec, init, seed).
Update the ticket skill to reference wrappers instead of calling
sqlite_connector.py directly, making permissions allowlisting clean.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add D-023 through D-029 context (content architecture, NPC generation,
social sites, simulation tiers, vertical slice, dialogue, population
ratios) to all 18 agent briefings. Core workshop participants get
detailed action items; specialist/infrastructure agents get relevant
implications. Mellanie activated from standby for content authoring.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Full team workshop (8 agents, 3 rounds) producing 7 decisions:
D-023 three-tier content model, D-024 NPC 10-axis generation,
D-025 social site atomic unit, D-026 timestamp-based sim tiers,
D-027 smuggler+detective vertical slice (supersedes D-006),
D-028 tagged line pool dialogue, D-029 population 30/50/20 split.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pre-workshop planning document for Round 17. Proposes three-tier
content model, life-sim substrate, NPC generation axes, simulation
tiers, DLC architecture, and 20 open questions for team discussion.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Instructs Qatux to always use project-relative paths in documents,
since the project is worked on across multiple systems.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove misplaced ROUND-16-STATUS.md from root (duplicate of
round-16-session-notes.md). Convert all macOS absolute paths to
project-relative paths across round-16 docs and design reference.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Round 15: README.md Steam page placeholder (Miri + Mellanie)
- Created README.md with game description for Steam page
- Placeholder structure with lorem ipsum for undetermined content
Round 16: Faction development (Miri, Paula, Gestalt)
- Full development of six factions with lore, politics, mechanics
- 3D reputation system (Trust × Usefulness × Exposure)
- Mechanical grounding with "First 30 Minutes" test
- v0.1 recommendation: Commission + Severance
- Session flagged for team input
Process changes (D-022):
- Retired DISCUSSION.md, work directly in round files
- Qatux mandatory in all team interactions
- Updated CLAUDE.md and agent personas
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Full team worldbuilding round establishing the original SF setting.
Miri's foundation brief covers: dual-tier gate network (Founder
Gates + Span Gates), the Interstitium and Builders, neural lattice
with four enhancement tiers, two-tier death with sleeve economics,
six factions, the Meridian information network, and infrastructure-
as-mystery as the core hook.
Team reactions from Gore (Threshold concept, "cost of knowing"
thesis), Ozzie (delivery via system manipulation, water cooler
moments), Nigel (character-as-lens replayability, Unbound as secret
weapon), Paula (interpersonal relationships layer, post-hard-death
dialogue, faction conversation signatures), and Gestalt (clean
mechanical mappings, imprint-as-save proposal, v0.1 scope cut).
Key consensus: Severance dual-naming, stable topology with shuffled
politics, single Gyre seed in v0.1, interpersonal relationships as
next design priority. Unstated design principle: the player should
eventually realize the loading screen was the most important thing
in the game.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Miri now flags concepts that drift too close to specific franchises
(Hamilton, Banks, Reynolds, Simmons, Morgan) and proposes original
alternatives. "Inspired by" means structural dynamics, not surface
details.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Full team debate on engine paradigms, leading to Godot client +
Rust simulation via subprocess/IPC (D-020). Includes Tyre/Troblum
sidequest, IP pivot to original setting, and serialization format
selection. Updated discussions index.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
D-020: Godot 4 client + Rust/bevy_ecs simulation server via
subprocess/IPC. MessagePack serialization. Kill switch at week 8.
Q-001 resolved. Rejected alternatives R-004 through R-010 (pure
Bevy, pure Godot, GDExtension, C++ GDExtension, Fyrox, custom
framework, protobuf).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reflect D-020 engine decision in project description (Godot 4 +
Rust/bevy_ecs via subprocess/IPC). Update connector usage examples
to reference the new whitelistable wrapper scripts instead of
calling python3 directly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pivot to original IP means Miri no longer guards Hamilton canon.
New role: designs and maintains the original SF setting, ensures
internal consistency, grounds features in worldbuilding. Updated
agent file, agents README, and team roster.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tyre's architecture evaluation (eval-godot-rust-bridge.md) and
Troblum's risk assessment (risk-godot-rust-bridge.md) for the
Godot 4 client + Rust simulation server approach. These reports
informed the D-020 engine decision and the shift from GDExtension
to subprocess/IPC.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Thin bash wrappers around sqlite_connector.py and qdrant_connector.py
that can be whitelisted in Claude Code permissions. Covers sqlite-query,
sqlite-exec, qdrant-search, qdrant-index, qdrant-health, qdrant-count.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Set up Commonwealth game project with complete agent team (18 agents),
discussion archives (12 rounds), briefing system, ticketing database,
Qdrant document search, and skill definitions. Establishes the
documentation and tooling foundation for engine selection and
implementation phases.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
