Clean up project documentation and constitution for post-MVP maturity
- CLAUDE.md: replace 32-line per-feature tech changelog with consolidated tech stack, add project structure and data/storage sections, remove stale Recent Changes - README.md: rewrite for current feature set, fix bestiary description (import-based, not bundled), remove placeholder license section - Constitution v2.2.0: remove unused Agent Boundary principle (MAJOR), add README and CLAUDE.md sync rules to Development Workflow (MINOR) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1,14 +1,17 @@
|
||||
<!--
|
||||
Sync Impact Report
|
||||
───────────────────
|
||||
Version change: 1.0.2 → 1.0.3 (PATCH — add merge-gate rule)
|
||||
Version change: 1.0.3 → 2.2.0 (MAJOR+MINOR — remove Agent Boundary, add README/CLAUDE.md sync rules)
|
||||
Modified sections:
|
||||
- Development Workflow: added automated-checks merge gate
|
||||
- Core Principles: removed III (Agent Boundary), renumbered IV→III, V→IV, VI→V, VII→VI
|
||||
- Layered Architecture: removed Agent layer (4→3 layers)
|
||||
- Clarification-First: reworded "the agent" → "Claude Code"
|
||||
- Development Workflow: removed agent-assisted reference
|
||||
Templates requiring updates:
|
||||
- .specify/templates/plan-template.md ✅ no update needed
|
||||
- .specify/templates/spec-template.md ✅ no update needed
|
||||
- .specify/templates/plan-template.md ⚠️ update Constitution Check if it references Agent Boundary
|
||||
- .specify/templates/spec-template.md ⚠️ update Constitution Check if it references Agent Boundary
|
||||
- .specify/templates/tasks-template.md ✅ no update needed
|
||||
Follow-up TODOs: none
|
||||
Follow-up TODOs: review templates for stale Agent Boundary references
|
||||
-->
|
||||
# Encounter Console Constitution
|
||||
|
||||
@@ -29,7 +32,7 @@ be injected at the boundary, never sourced inside the domain layer.
|
||||
|
||||
### II. Layered Architecture
|
||||
|
||||
The codebase MUST be organized into four layers with strict
|
||||
The codebase MUST be organized into three layers with strict
|
||||
dependency direction:
|
||||
|
||||
1. **Domain** — pure types, state transitions, validation rules.
|
||||
@@ -39,34 +42,21 @@ dependency direction:
|
||||
interfaces that Adapters implement. May import Domain only.
|
||||
3. **Adapters** — I/O, persistence, UI rendering, external APIs.
|
||||
May import Application and Domain.
|
||||
4. **Agent** — AI-assisted features (suggestions, analysis).
|
||||
May import Application and Domain as read-only consumers.
|
||||
|
||||
A module in an inner layer MUST NOT import from an outer layer.
|
||||
|
||||
### III. Agent Boundary
|
||||
|
||||
The agent layer MAY read domain events and current state. The agent
|
||||
MAY produce suggestions, annotations, or recommendations. The agent
|
||||
MUST NOT mutate domain state directly. All agent-originated changes
|
||||
MUST flow through the Application layer as explicit user-confirmed
|
||||
commands.
|
||||
|
||||
- Agent output MUST be clearly labeled as suggestions.
|
||||
- No silent or automatic application of agent recommendations.
|
||||
|
||||
### IV. Clarification-First
|
||||
### III. Clarification-First
|
||||
|
||||
Before making any non-trivial assumption during specification,
|
||||
planning, or implementation, the agent MUST surface a clarification
|
||||
planning, or implementation, Claude Code MUST surface a clarification
|
||||
question to the user. "Non-trivial" means any decision that would
|
||||
alter observable behavior, data model shape, or public API surface.
|
||||
The agent MUST also ask when multiple valid interpretations exist,
|
||||
Claude Code MUST also ask when multiple valid interpretations exist,
|
||||
when a choice would affect architectural layering, or when scope
|
||||
would expand beyond the current spec. The agent MUST NOT silently
|
||||
would expand beyond the current spec. Claude Code MUST NOT silently
|
||||
choose among valid alternatives.
|
||||
|
||||
### V. Escalation Gates
|
||||
### IV. Escalation Gates
|
||||
|
||||
Any feature, requirement, or scope change not present in the current
|
||||
spec MUST be rejected at implementation time until the spec is
|
||||
@@ -77,7 +67,7 @@ explicitly updated. The workflow is:
|
||||
3. Update the spec via `/speckit.specify` or `/speckit.clarify`.
|
||||
4. Only then proceed with implementation.
|
||||
|
||||
### VI. MVP Baseline Language
|
||||
### V. MVP Baseline Language
|
||||
|
||||
Constraints in this constitution and in specs MUST use MVP baseline
|
||||
language ("MVP baseline does not include X") rather than permanent
|
||||
@@ -86,7 +76,7 @@ add capabilities in future iterations without constitutional
|
||||
amendment. The current MVP baseline is local-first and single-user;
|
||||
this is a starting scope, not a permanent restriction.
|
||||
|
||||
### VII. No Gameplay Rules in Constitution
|
||||
### VI. No Gameplay Rules in Constitution
|
||||
|
||||
This constitution MUST NOT contain concrete gameplay mechanics,
|
||||
rule-system specifics, or encounter resolution logic. Such details
|
||||
@@ -96,9 +86,9 @@ architecture, and quality — not product behavior.
|
||||
## Scope Constraints
|
||||
|
||||
- The Encounter Console's primary focus is initiative tracking and
|
||||
encounter state management. Adjacent capabilities (e.g., richer
|
||||
game-engine features) are not in the MVP baseline but may be
|
||||
added via spec updates in future iterations.
|
||||
encounter state management. Adjacent capabilities (e.g., bestiary
|
||||
integration, richer game-engine features) may be added via spec
|
||||
updates.
|
||||
- Technology choices, UI framework, and storage mechanism are
|
||||
spec-level decisions, not constitutional mandates.
|
||||
- Testing strategy (unit, integration, contract) is determined per
|
||||
@@ -117,8 +107,14 @@ architecture, and quality — not product behavior.
|
||||
- Commits SHOULD be atomic and map to individual tasks where
|
||||
practical.
|
||||
- Layer boundary compliance MUST be verified by automated import
|
||||
rules or architectural tests. Agent-assisted or manual review MAY
|
||||
supplement but not replace automated checks.
|
||||
rules or architectural tests.
|
||||
- When a feature adds, removes, or changes user-facing capabilities
|
||||
described in README.md, the README MUST be updated in the same
|
||||
change. Features that materially alter what the product does or
|
||||
how it is set up SHOULD also be reflected in the README.
|
||||
- When a feature changes the tech stack, project structure, or
|
||||
architectural patterns documented in CLAUDE.md, the CLAUDE.md
|
||||
MUST be updated in the same change.
|
||||
|
||||
## Governance
|
||||
|
||||
@@ -142,4 +138,4 @@ MUST comply with its principles.
|
||||
**Compliance review**: Every spec and plan MUST include a
|
||||
Constitution Check section validating adherence to all principles.
|
||||
|
||||
**Version**: 1.0.3 | **Ratified**: 2026-03-03 | **Last Amended**: 2026-03-03
|
||||
**Version**: 2.2.0 | **Ratified**: 2026-03-03 | **Last Amended**: 2026-03-10
|
||||
|
||||
Reference in New Issue
Block a user