Skip to content

AGENTS.md

Latest commit

 

History

History
236 lines (172 loc) · 11.1 KB

AGENTS.md

File metadata and controls

236 lines (172 loc) · 11.1 KB

AGENTS.md — opencode-warcraft

Commands

# Build (warcraft-core first, then opencode-warcraft plugin)
bun run build

# Run all workspace tests + smoke E2E (~2,500 tests)
bun run test

# Run a single test file
bun test packages/warcraft-core/src/feature/feature-service.test.ts

# Run one package's tests only
bun run test --filter warcraft-core
bun run test --filter opencode-warcraft

# Type-check both packages + Biome lint
bun run lint

# Auto-fix formatting
bun run format

# Check formatting without writing (CI mode)
bun run format:check

# Full pre-release gate (install → build → test → lint → format:check)
bun run release:check

# Regenerate skill registry after adding/editing skills/*.md
bun run generate-skills          # run from packages/opencode-warcraft/

# E2E lanes (optional; host lane requires git + br CLI)
bun run test:e2e:host

Architecture

  • Monorepo: Bun workspaces with two packages
    • packages/warcraft-core — domain logic: services, stores, types, state machine, utilities
    • packages/opencode-warcraft — OpenCode plugin: agents, tools, hooks, skills, MCP, DI container
  • DI: Composition root in packages/opencode-warcraft/src/container.ts wires all services and tools
  • Storage: Pluggable via beadsMode — filesystem JSON files (docs/<feature>/) or beads-backed (br CLI + .beads/)
  • Agents (6): Khadgar (hybrid), Mimiron (planner), Saurfang (orchestrator), Brann (researcher), Mekkatorque (worker), Algalon (reviewer)
  • Tools (16): across feature, plan, task, execute, context, status, agents-md, doctor, skill, hashline-edit domains
  • Data flow: feature_create → plan_write → plan_approve (SHA-256) → tasks_sync → warcraft_execute → task() call → worker → task_update → status
  • hashline-edit: Vendored in packages/opencode-warcraft/src/tools/hashline-edit/. Uses xxHash32 LINE#HASH tags. Path-validated (absolute + project root containment). Available to Mekkatorque workers only.

Code Style

Formatting (Biome)

  • 2-space indent, single quotes, semicolons always, trailing commas always, 120-char line width
  • Config: biome.json at repo root
  • Run bun run format to auto-fix; CI checks with bun run format:check

Imports

  • ESM only — local imports MUST use .js extension: import { Foo } from './foo.js';
  • Type-only imports — use import type for types: import type { FeatureJson } from '../types.js';
  • Separate value and type imports on different lines when both are needed from the same module
  • Node builtins use bare specifiers: import * as fs from 'fs';

Naming Conventions

Kind Convention Example
Types / Classes PascalCase FeatureService, TaskStatus, OperationOutcome
Functions / Variables camelCase createStores, sanitizeName, beadsMode
Constants UPPER_SNAKE_CASE ALLOWED_TRANSITIONS, DEFAULT_AGENT_MODELS
Files kebab-case feature-service.ts, bead-gateway.ts
Test files Co-located *.test.ts feature-service.test.ts next to feature-service.ts

Types and Interfaces

  • Prefer interface for object shapes, type for unions/intersections/aliases
  • Explicit return types on all public/exported functions
  • Use discriminated unions for result types (e.g., OperationOutcome with severity: 'ok' | 'degraded' | 'fatal')
  • No any — prefer unknown with type narrowing; any is linter-allowed but discouraged

Error Handling

  • Services return OperationOutcome<T> (ok/degraded/fatal) with Diagnostic entries — never throw for expected failures
  • Stores may throw — services catch and wrap into outcomes
  • Tools return JSON strings via toolSuccess(data) or toolError(message, hints?, options?) — never raw strings
  • State machine violations throw InvalidTransitionError with from and to fields
  • Beads layer uses Result<T> discriminated union ({ success: true, value } | { success: false, error })

Patterns

  • async/await over raw promises; no .then() chains
  • Constructor injection for dependencies (services take stores/factories as params)
  • Store factory pattern: createStores(root, beadsMode) returns { featureStore, taskStore, planStore }
  • spyOn for mocking in tests — no test framework beyond bun:test
  • Atomic file writes via writeJsonLockedSync / patchJsonLockedSync in filesystem stores

Testing

// Standard test structure
import { afterEach, beforeEach, describe, expect, it } from 'bun:test';

describe('FeatureService', () => {
  let testRoot: string;

  beforeEach(() => {
    testRoot = fs.mkdtempSync(path.join(os.tmpdir(), 'warcraft-test-'));
  });

  afterEach(() => {
    fs.rmSync(testRoot, { recursive: true, force: true });
  });

  it('creates feature at canonical path', () => {
    const stores = createStores(testRoot, 'off');
    const service = new FeatureService(testRoot, stores.featureStore, 'off');
    const outcome = service.create('my-feature');
    expect(outcome.severity).toBe('ok');
  });
});
  • Test temp dirs with fs.mkdtempSync + cleanup in afterEach
  • Stub stores with partial overrides: createFeatureStoreStub(feature, { list: () => [] })
  • E2E helpers in packages/opencode-warcraft/src/e2e/helpers/test-env.ts
  • Use isUsable(outcome) guard before accessing outcome.value

Package Boundaries

  • Shared logic → warcraft-core: services, stores, types, utilities, state machine
  • Plugin wiring → opencode-warcraft: agents, tools, hooks, skills, MCP, prompt assembly
  • Export new public APIs via warcraft-core/src/index.ts; consume in plugin via warcraft-core workspace dependency
  • Keep warcraft-core plugin-agnostic — no OpenCode imports

GitNexus — Code Intelligence

This project is indexed by GitNexus as opencode-warcraft (2503 symbols, 6920 relationships, 201 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.

If any GitNexus tool warns the index is stale, run npx gitnexus analyze in terminal first.

Always Do

  • MUST run impact analysis before editing any symbol. Before modifying a function, class, or method, run gitnexus_impact({target: "symbolName", direction: "upstream"}) and report the blast radius (direct callers, affected processes, risk level) to the user.
  • MUST run gitnexus_detect_changes() before committing to verify your changes only affect expected symbols and execution flows.
  • MUST warn the user if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.
  • When exploring unfamiliar code, use gitnexus_query({query: "concept"}) to find execution flows instead of grepping. It returns process-grouped results ranked by relevance.
  • When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use gitnexus_context({name: "symbolName"}).

When Debugging

  1. gitnexus_query({query: "<error or symptom>"}) — find execution flows related to the issue
  2. gitnexus_context({name: "<suspect function>"}) — see all callers, callees, and process participation
  3. READ gitnexus://repo/opencode-warcraft/process/{processName} — trace the full execution flow step by step
  4. For regressions: gitnexus_detect_changes({scope: "compare", base_ref: "main"}) — see what your branch changed

When Refactoring

  • Renaming: MUST use gitnexus_rename({symbol_name: "old", new_name: "new", dry_run: true}) first. Review the preview — graph edits are safe, text_search edits need manual review. Then run with dry_run: false.
  • Extracting/Splitting: MUST run gitnexus_context({name: "target"}) to see all incoming/outgoing refs, then gitnexus_impact({target: "target", direction: "upstream"}) to find all external callers before moving code.
  • After any refactor: run gitnexus_detect_changes({scope: "all"}) to verify only expected files changed.

Never Do

  • NEVER edit a function, class, or method without first running gitnexus_impact on it.
  • NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.
  • NEVER rename symbols with find-and-replace — use gitnexus_rename which understands the call graph.
  • NEVER commit changes without running gitnexus_detect_changes() to check affected scope.

Tools Quick Reference

Tool When to use Command
query Find code by concept gitnexus_query({query: "auth validation"})
context 360-degree view of one symbol gitnexus_context({name: "validateUser"})
impact Blast radius before editing gitnexus_impact({target: "X", direction: "upstream"})
detect_changes Pre-commit scope check gitnexus_detect_changes({scope: "staged"})
rename Safe multi-file rename gitnexus_rename({symbol_name: "old", new_name: "new", dry_run: true})
cypher Custom graph queries gitnexus_cypher({query: "MATCH ..."})

Impact Risk Levels

Depth Meaning Action
d=1 WILL BREAK — direct callers/importers MUST update these
d=2 LIKELY AFFECTED — indirect deps Should test
d=3 MAY NEED TESTING — transitive Test if critical path

Resources

Resource Use for
gitnexus://repo/opencode-warcraft/context Codebase overview, check index freshness
gitnexus://repo/opencode-warcraft/clusters All functional areas
gitnexus://repo/opencode-warcraft/processes All execution flows
gitnexus://repo/opencode-warcraft/process/{name} Step-by-step execution trace

Self-Check Before Finishing

Before completing any code modification task, verify:

  1. gitnexus_impact was run for all modified symbols
  2. No HIGH/CRITICAL risk warnings were ignored
  3. gitnexus_detect_changes() confirms changes match expected scope
  4. All d=1 (WILL BREAK) dependents were updated

Keeping the Index Fresh

After committing code changes, the GitNexus index becomes stale. Re-run analyze to update it:

npx gitnexus analyze

If the index previously included embeddings, preserve them by adding --embeddings:

npx gitnexus analyze --embeddings

To check whether embeddings exist, inspect .gitnexus/meta.json — the stats.embeddings field shows the count (0 means no embeddings). Running analyze without --embeddings will delete any previously generated embeddings.

Claude Code users: A PostToolUse hook handles this automatically after git commit and git merge.

CLI

Task Read this skill file
Understand architecture / "How does X work?" .claude/skills/gitnexus/gitnexus-exploring/SKILL.md
Blast radius / "What breaks if I change X?" .claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md
Trace bugs / "Why is X failing?" .claude/skills/gitnexus/gitnexus-debugging/SKILL.md
Rename / extract / split / refactor .claude/skills/gitnexus/gitnexus-refactoring/SKILL.md
Tools, resources, schema reference .claude/skills/gitnexus/gitnexus-guide/SKILL.md
Index, status, clean, wiki CLI commands .claude/skills/gitnexus/gitnexus-cli/SKILL.md