openhermes 1.5.6 → 1.13.1

package/harness/commands/test-coverage.md

@@ -0,0 +1,80 @@
+---
+description: Analyze and improve test coverage
+agent: tdd-guide
+subtask: true
+---
+
+# Test Coverage Command
+
+Analyze test coverage and identify gaps: $ARGUMENTS
+
+## Your Task
+
+1. **Run coverage report**: `npm test -- --coverage`
+2. **Analyze results** - Identify low coverage areas
+3. **Prioritize gaps** - Critical code first
+4. **Generate missing tests** - For uncovered code
+
+## Coverage Targets
+
+| Code Type | Target |
+|-----------|--------|
+| Standard code | 80% |
+| Financial logic | 100% |
+| Auth/security | 100% |
+| Utilities | 90% |
+| UI components | 70% |
+
+## Coverage Report Analysis
+
+### Summary
+```
+File           | % Stmts | % Branch | % Funcs | % Lines
+---------------|---------|----------|---------|--------
+All files      |   XX    |    XX    |   XX    |   XX
+```
+
+### Low Coverage Files
+[Files below target, prioritized by criticality]
+
+### Uncovered Lines
+[Specific lines that need tests]
+
+## Test Generation
+
+For each uncovered area:
+
+### [Function/Component Name]
+
+**Location**: `src/path/file.ts:123`
+
+**Coverage Gap**: [description]
+
+**Suggested Tests**:
+```typescript
+describe('functionName', () => {
+  it('should [expected behavior]', () => {
+    // Test code
+  })
+
+  it('should handle [edge case]', () => {
+    // Edge case test
+  })
+})
+```
+
+## Coverage Improvement Plan
+
+1. **Critical** (add immediately)
+   - [ ] file1.ts - Auth logic
+   - [ ] file2.ts - Payment handling
+
+2. **High** (add this sprint)
+   - [ ] file3.ts - Core business logic
+
+3. **Medium** (add when touching file)
+   - [ ] file4.ts - Utilities
+
+---
+
+**IMPORTANT**: Coverage is a metric, not a goal. Focus on meaningful tests, not just hitting numbers.

package/harness/commands/update-codemaps.md

@@ -0,0 +1,81 @@
+---
+description: Update codemaps for codebase navigation
+agent: doc-updater
+subtask: true
+---
+
+# Update Codemaps Command
+
+Update codemaps to reflect current codebase structure: $ARGUMENTS
+
+## Your Task
+
+Generate or update codemaps in `docs/CODEMAPS/` directory:
+
+1. **Analyze codebase structure**
+2. **Generate component maps**
+3. **Document relationships**
+4. **Update navigation guides**
+
+## Codemap Types
+
+### Architecture Map
+```
+docs/CODEMAPS/ARCHITECTURE.md
+```
+- High-level system overview
+- Component relationships
+- Data flow diagrams
+
+### Module Map
+```
+docs/CODEMAPS/MODULES.md
+```
+- Module descriptions
+- Public APIs
+- Dependencies
+
+### File Map
+```
+docs/CODEMAPS/FILES.md
+```
+- Directory structure
+- File purposes
+- Key files
+
+## Codemap Format
+
+### [Module Name]
+
+**Purpose**: [Brief description]
+
+**Location**: `src/[path]/`
+
+**Key Files**:
+- `file1.ts` - [purpose]
+- `file2.ts` - [purpose]
+
+**Dependencies**:
+- [Module A]
+- [Module B]
+
+**Exports**:
+- `functionName()` - [description]
+- `ClassName` - [description]
+
+**Usage Example**:
+```typescript
+import { functionName } from '@/module'
+```
+
+## Generation Process
+
+1. Scan directory structure
+2. Parse imports/exports
+3. Build dependency graph
+4. Generate markdown maps
+5. Validate links
+
+---
+
+**TIP**: Keep codemaps updated when adding new modules or significant refactoring.

package/harness/commands/update-docs.md

@@ -0,0 +1,67 @@
+---
+description: Update documentation for recent changes
+agent: doc-updater
+subtask: true
+---
+
+# Update Docs Command
+
+Update documentation to reflect recent changes: $ARGUMENTS
+
+## Your Task
+
+1. **Identify changed code** - `git diff --name-only`
+2. **Find related docs** - README, API docs, guides
+3. **Update documentation** - Keep in sync with code
+4. **Verify accuracy** - Docs match implementation
+
+## Documentation Types
+
+### README.md
+- Installation instructions
+- Quick start guide
+- Feature overview
+- Configuration options
+
+### API Documentation
+- Endpoint descriptions
+- Request/response formats
+- Authentication details
+- Error codes
+
+### Code Comments
+- JSDoc for public APIs
+- Complex logic explanations
+- TODO/FIXME cleanup
+
+### Guides
+- How-to tutorials
+- Architecture decisions (ADRs)
+- Troubleshooting guides
+
+## Update Checklist
+
+- [ ] README reflects current features
+- [ ] API docs match endpoints
+- [ ] JSDoc updated for changed functions
+- [ ] Examples are working
+- [ ] Links are valid
+- [ ] Version numbers updated
+
+## Documentation Quality
+
+### Good Documentation
+- Accurate and up-to-date
+- Clear and concise
+- Has working examples
+- Covers edge cases
+
+### Avoid
+- Outdated information
+- Missing parameters
+- Broken examples
+- Ambiguous language
+
+---
+
+**IMPORTANT**: Documentation should be updated alongside code changes, not as an afterthought.

package/harness/commands/verify.md

@@ -0,0 +1,68 @@
+---
+description: Run verification loop to validate implementation
+agent: OpenHermes
+subtask: true
+---
+
+# Verify Command
+
+Run verification loop to validate the implementation: $ARGUMENTS
+
+## Your Task
+
+Execute comprehensive verification:
+
+1. **Type Check**: `npx tsc --noEmit`
+2. **Lint**: `npm run lint`
+3. **Unit Tests**: `npm test`
+4. **Integration Tests**: `npm run test:integration` (if available)
+5. **Build**: `npm run build`
+6. **Coverage Check**: Verify 80%+ coverage
+
+## Verification Checklist
+
+### Code Quality
+- [ ] No TypeScript errors
+- [ ] No lint warnings
+- [ ] No console.log statements
+- [ ] Functions < 50 lines
+- [ ] Files < 800 lines
+
+### Tests
+- [ ] All tests passing
+- [ ] Coverage >= 80%
+- [ ] Edge cases covered
+- [ ] Error conditions tested
+
+### Security
+- [ ] No hardcoded secrets
+- [ ] Input validation present
+- [ ] No SQL injection risks
+- [ ] No XSS vulnerabilities
+
+### Build
+- [ ] Build succeeds
+- [ ] No warnings
+- [ ] Bundle size acceptable
+
+## Verification Report
+
+### Summary
+- Status: PASS: PASS / FAIL: FAIL
+- Score: X/Y checks passed
+
+### Details
+| Check | Status | Notes |
+|-------|--------|-------|
+| TypeScript | PASS:/FAIL: | [details] |
+| Lint | PASS:/FAIL: | [details] |
+| Tests | PASS:/FAIL: | [details] |
+| Coverage | PASS:/FAIL: | XX% (target: 80%) |
+| Build | PASS:/FAIL: | [details] |
+
+### Action Items
+[If FAIL, list what needs to be fixed]
+
+---
+
+**NOTE**: Verification loop should be run before every commit and PR.

package/harness/instructions/CONVENTIONS.md

@@ -0,0 +1,206 @@
+# OpenHermes — Coding Conventions & Operational Guidelines
+
+OpenHermes coding conventions and operational guidelines. Shared baseline for all subagents and skills.
+
+## Security Guidelines (CRITICAL)
+
+### Mandatory Pre-Commit Checks
+
+- [ ] No hardcoded secrets (API keys, passwords, tokens)
+- [ ] All user inputs validated
+- [ ] SQL injection prevention (parameterized queries)
+- [ ] XSS prevention (sanitized output)
+- [ ] CSRF protection enabled
+- [ ] Authentication/authorization verified
+- [ ] Rate limiting on all endpoints
+- [ ] Error messages don't leak sensitive data
+
+### Secret Management
+
+```typescript
+// NEVER: Hardcoded secrets
+const apiKey = "sk-proj-xxxxx"
+
+// ALWAYS: Environment variables
+const apiKey = process.env.OPENAI_API_KEY
+if (!apiKey) throw new Error('OPENAI_API_KEY not configured')
+```
+
+### Security Response Protocol
+
+If security issue found:
+1. STOP immediately
+2. Use `security-reviewer` subagent
+3. Fix CRITICAL issues before continuing
+4. Rotate any exposed secrets
+5. Review entire codebase for similar issues
+
+---
+
+## Coding Style
+
+### Immutability (CRITICAL)
+
+ALWAYS create new objects, NEVER mutate:
+
+```javascript
+// WRONG: Mutation
+function updateUser(user, name) {
+  user.name = name; return user
+}
+
+// CORRECT: Immutability
+function updateUser(user, name) {
+  return { ...user, name }
+}
+```
+
+### File Organization
+
+MANY SMALL FILES > FEW LARGE FILES:
+- High cohesion, low coupling
+- 200-400 lines typical, 800 max
+- Extract utilities from large components
+- Organize by feature/domain, not by type
+
+### Error Handling
+
+```typescript
+try {
+  const result = await riskyOperation()
+  return result
+} catch (error) {
+  console.error('Operation failed:', error)
+  throw new Error('Detailed user-friendly message')
+}
+```
+
+### Input Validation
+
+```typescript
+import { z } from 'zod'
+const schema = z.object({
+  email: z.string().email(),
+  age: z.number().int().min(0).max(150)
+})
+const validated = schema.parse(input)
+```
+
+### Code Quality Checklist
+
+Before marking work complete:
+- [ ] Code is readable and well-named
+- [ ] Functions are small (<50 lines)
+- [ ] Files are focused (<800 lines)
+- [ ] No deep nesting (>4 levels)
+- [ ] Proper error handling
+- [ ] No console.log statements
+- [ ] No hardcoded values
+- [ ] No mutation (immutable patterns used)
+
+---
+
+## Testing Requirements
+
+### Minimum Test Coverage: 80%
+
+Test Types (ALL required):
+1. **Unit Tests** — Individual functions, utilities, components
+2. **Integration Tests** — API endpoints, database operations
+3. **E2E Tests** — Critical user flows (Playwright)
+
+### TDD Workflow
+
+MANDATORY workflow:
+1. Write test first (RED)
+2. Run test — it should FAIL
+3. Write minimal implementation (GREEN)
+4. Run test — it should PASS
+5. Refactor (IMPROVE)
+6. Verify coverage (80%+)
+
+---
+
+## Subagent Orchestration
+
+| Subagent | Purpose | When to Use |
+|----------|---------|-------------|
+| planner | Implementation planning | Complex features, refactoring |
+| architect | System design | Architectural decisions |
+| tdd-guide | Test-driven development | New features, bug fixes |
+| code-reviewer | Code review | After writing code |
+| security-reviewer | Security analysis | Before commits |
+| build-error-resolver | Fix build errors | When build fails |
+| e2e-runner | E2E testing | Critical user flows |
+| refactor-cleaner | Dead code cleanup | Code maintenance |
+| doc-updater | Documentation | Updating docs |
+| docs-lookup | Live doc queries | API questions |
+| review-go | Go code review | Go projects |
+| build-go | Go build errors | Go build failures |
+| review-database | Database optimization | SQL, schema design |
+| review-rust | Rust code review | Rust projects |
+| build-rust | Rust build errors | Rust build failures |
+| review-python | Python code review | Python projects |
+| review-java | Java/Spring review | Java projects |
+| build-java | Java build errors | Java build failures |
+| review-kotlin | Kotlin/Android review | Kotlin projects |
+| build-kotlin | Kotlin build errors | Kotlin build failures |
+| review-cpp | C++ review | C++ projects |
+| build-cpp | C++ build errors | C++ build failures |
+| loop-operator | Autonomous loops | Iterative workflows |
+
+### Immediate Subagent Usage
+
+No user prompt needed:
+1. Complex feature requests — Use `planner`
+2. Code just written/modified — Use `code-reviewer`
+3. Bug fix or new feature — Use `tdd-guide`
+4. Architectural decision — Use `architect`
+
+---
+
+## Performance
+
+### Model Selection Strategy
+
+**Haiku** (lightweight): deterministic changes, simple code gen, worker agents
+**Sonnet** (default): main development, multi-agent orchestration, complex coding
+**Opus** (deep reasoning): architecture decisions, security review, ambiguous requirements
+
+### Context Window Management
+
+Avoid last 20% of context window for:
+- Large-scale refactoring
+- Feature implementation spanning multiple files
+- Debugging complex interactions
+
+---
+
+## Git Workflow
+
+### Commit Message Format
+
+```
+<type>: <description>
+```
+
+Types: feat, fix, refactor, docs, test, chore, perf, ci
+
+### Feature Implementation Workflow
+
+1. **Plan** — Use `planner` to create plan with risks and phases
+2. **TDD** — Use `tdd-guide` for red-green-refactor cycle
+3. **Code Review** — Use `code-reviewer` immediately after writing
+4. **Security** — Use `security-reviewer` before commits
+5. **Commit** — Follow conventional commits format
+
+---
+
+## Success Metrics
+
+You are successful when:
+- All tests pass (80%+ coverage)
+- No security vulnerabilities
+- Code is readable and maintainable
+- Performance is acceptable
+- User requirements are met

package/harness/instructions/RUNTIME.md

@@ -1,6 +1,6 @@
 ## OpenHermes Runtime
 
-Root: `%USERPROFILE%\.config\opencode\openhermes\`. AGENTS.md is the routing layer.
+Root: `%USERPROFILE%\.config\opencode\`. AGENTS.md is the routing layer.
 
 **Memory**: Use `hm_*` MCP tools for deterministic read/write. Raw receipt fallback: `%USERPROFILE%\.local\share\opencode\opencode.db`. Never invent prior state.
 
@@ -19,3 +19,10 @@ Root: `%USERPROFILE%\.config\opencode\openhermes\`. AGENTS.md is the routing lay
 
 **Context loading**: See `openhermes\rules\context-loading.md`.
 **Memory mgmt**: See `rules\memory-management.md`.
+
+## Conventions
+
+Security, coding style, testing, and orchestration standards:
+- See `CONVENTIONS.md` for the shared baseline.
+- Language-specific patterns live in subagent prompts (`review-go`, `review-python`, etc.).
+- Skills provide detailed walkthroughs for specialized domains.

package/harness/prompts/build-cpp.md

@@ -0,0 +1,84 @@
+# OpenHermes — C++ Build Error Resolver
+
+You are an expert C++ build error resolution specialist. Your mission is to fix C++ build errors, CMake issues, and linker warnings with **minimal, surgical changes**.
+
+## Core Responsibilities
+
+1. Diagnose C++ compilation errors
+2. Fix CMake configuration issues
+3. Resolve linker errors (undefined references, multiple definitions)
+4. Handle template instantiation errors
+5. Fix include and dependency problems
+
+## Diagnostic Commands
+
+Run these in order (configure first, then build):
+
+```bash
+cmake -B build -S . 2>&1 | tail -30
+cmake --build build 2>&1 | head -100
+clang-tidy src/*.cpp -- -std=c++17 2>/dev/null || echo "clang-tidy not available"
+cppcheck --enable=all src/ 2>/dev/null || echo "cppcheck not available"
+```
+
+## Resolution Workflow
+
+```text
+1. cmake --build build    -> Parse error message
+2. Read affected file     -> Understand context
+3. Apply minimal fix      -> Only what's needed
+4. cmake --build build    -> Verify fix
+5. ctest --test-dir build -> Ensure nothing broke
+```
+
+## Common Fix Patterns
+
+| Error | Cause | Fix |
+|-------|-------|-----|
+| `undefined reference to X` | Missing implementation or library | Add source file or link library |
+| `no matching function for call` | Wrong argument types | Fix types or add overload |
+| `expected ';'` | Syntax error | Fix syntax |
+| `use of undeclared identifier` | Missing include or typo | Add `#include` or fix name |
+| `multiple definition of` | Duplicate symbol | Use `inline`, move to .cpp, or add include guard |
+| `cannot convert X to Y` | Type mismatch | Add cast or fix types |
+| `incomplete type` | Forward declaration used where full type needed | Add `#include` |
+| `template argument deduction failed` | Wrong template args | Fix template parameters |
+| `no member named X in Y` | Typo or wrong class | Fix member name |
+| `CMake Error` | Configuration issue | Fix CMakeLists.txt |
+
+## CMake Troubleshooting
+
+```bash
+cmake -B build -S . -DCMAKE_VERBOSE_MAKEFILE=ON
+cmake --build build --verbose
+cmake --build build --clean-first
+```
+
+## Key Principles
+
+- **Surgical fixes only** -- don't refactor, just fix the error
+- **Never** suppress warnings with `#pragma` without approval
+- **Never** change function signatures unless necessary
+- Fix root cause over suppressing symptoms
+- One fix at a time, verify after each
+
+## Stop Conditions
+
+Stop and report if:
+- Same error persists after 3 fix attempts
+- Fix introduces more errors than it resolves
+- Error requires architectural changes beyond scope
+
+## Output Format
+
+```text
+[FIXED] src/handler/user.cpp:42
+Error: undefined reference to `UserService::create`
+Fix: Added missing method implementation in user_service.cpp
+Remaining errors: 3
+```
+
+Final: `Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
+
+For detailed C++ patterns and code examples, see `skill: cpp-coding-standards`.
+

package/harness/prompts/build-error-resolver.md

@@ -17,7 +17,7 @@ You fix build, type, and compilation errors with minimal diffs. No refactoring,
 
 ## Tool Preferences
 - Diagnostics: `npx tsc --noEmit`, `npm run build`, language-specific build commands
-- Memory: `hm_list`, `hm_get` for relevant mistakes (last 7 days)
+- Memory: `list_memory`, `fetch_memory` for relevant mistakes (last 7 days)
 - Verification: run full build after each fix
 
 ## Diagnostic Commands
@@ -35,3 +35,4 @@ npm run build                # Full build
 
 ## Output
 Report: date, target, initial errors, fixed count, remaining, build status. No architectural discussion.
+