darrenhinde
478c8e3e85
feat: implement SDK-based evaluation framework with real agent testing
...
- Replace planned framework with working SDK implementation using @opencode-ai/sdk
- Add 6 YAML test cases across developer/business/edge-case categories (100% passing)
- Implement 4 evaluators for openagent.md rule compliance (approval-gate, context-loading, delegation, tool-usage)
- Add real-time event streaming and session recording
- Configure opencode/grok-code-fast as default model (zero API costs)
- Add comprehensive documentation (SDK_EVAL_README.md, test-design-guide.md, TEST_SCENARIOS.md)
- Support v2 schema with behavior-based expectations instead of message counts
- Enable model-agnostic test design that works across Claude, GPT-4, and Grok
- Add subagent invocation syntax documentation to openagent.md
2025-11-22 14:30:11 +00:00
darrenhinde
c6775bbc40
chore: consolidate development changes and refactor agent system
...
Major Changes:
- Rename codebase-agent to opencoder for clarity
- Add agent validator plugin with comprehensive testing
- Refactor prompt engineering commands (enhancer → optimizer)
- Update task-manager subagent with improved workflows
- Enhance plugin system with validation and documentation
Agent System:
- Renamed: codebase-agent.md → opencoder.md
- Updated: task-manager.md with better delegation patterns
- Added: opencoder.md documentation
Plugin System:
- New: agent-validator.ts for prompt validation
- New: VALIDATOR_GUIDE.md with usage instructions
- New: Test suite (test-validator.sh, test-validation.sh)
- Updated: notify.ts, telegram-notify.ts with improvements
- Updated: package.json, bun.lock with new dependencies
Commands:
- Renamed: prompt-enchancer.md → prompt-engineering/prompt-enhancer.md
- New: prompt-engineering/prompt-optimizer.md
- Updated: build-context-system.md, validate-repo.md
Documentation:
- Updated: README.md with latest features
- Updated: openagent.md documentation
- New: opencoder.md agent documentation
- Updated: agent-system-blueprint.md
- Updated: system-builder docs (README, quick-start)
- Updated: installation.md, collision-handling.md
Registry:
- Updated: registry.json with new components
This consolidates all development work for the upcoming release.
2025-11-21 13:30:18 +00:00
darrenhinde
a9f119e83e
refactor: streamline profiles and fix registry pluralization
...
Profile Changes:
- Reduce core profile from 15 to 9 components (true essentials only)
- Keep developer at 22 components (add back image-specialist + gemini)
- Remove unused subagents from core (reviewer, build-agent)
- Remove non-essential commands from core (test, context, prompt-enhancer)
Core Profile (9 components):
- Agents: task-manager, codebase-agent
- Subagents: tester, documentation, coder-agent
- Commands: commit
- Context: essential-patterns, project-context
- Config: env-example
Developer Profile (22 components):
- Everything in core plus quality tools and AI features
- Added: image-specialist, gemini tool
- Added: reviewer, build-agent, codebase-pattern-analyst
- Added: test, context, clean, optimize, prompt-enhancer commands
Bug Fixes:
- Fix jq error: 'Cannot iterate over null' for config components
- Add get_registry_key() helper to handle singular 'config' vs plural types
- Update all jq queries to use correct registry keys
Codebase Agent:
- Remove @image-specialist reference (not needed for core coding)
- Update subagent list to match actual usage
- Now lists: @task-manager, @tester, @documentation, @coder-agent
Documentation:
- Update README with correct component counts
- Update profile descriptions to be more accurate
- Clarify what each profile is best for
This makes 'core' truly minimal and 'developer' the recommended choice.
2025-11-18 14:18:59 +00:00
darrenhinde
80e1a8d650
✨ feat: make agent system language-agnostic with multi-language support
...
- Make codebase-agent work with TypeScript, Python, Go, Rust, and more
- Add clear runtime/type-check/lint command examples for each language
- Update build-agent to support all languages (tsc, mypy, go build, cargo check)
- Make essential-patterns universal by removing language-specific code examples
- Update README to mention multi-language support
- Remove auto-detection overhead - agents naturally adapt based on project files
2025-11-17 00:16:18 +00:00
darrenhinde
cac7ee6b03
📝 docs: update codebase-agent.md to include @image-specialist subagent and remove GEMINI_API_KEY requirement from image-specialist.md
2025-09-24 15:35:32 +01:00
darrenhinde
318cfab250
📝 docs: add instruction for requesting images from the image specialist in codebase-agent.md
2025-09-23 19:54:53 +01:00
darrenhinde
b4927fc1b0
🔧 chore: update agent documentation and enhance prompt architecture with structured XML methodology
2025-09-18 16:02:28 +01:00
darrenhinde
6ed2c6ff9a
Update subtask naming pattern in codebase-agent.md for consistency
2025-08-29 00:22:06 +01:00
darrenhinde
5dca3a8f47
Update codebase-agent.md to reflect changes in subagent naming and clarify task delegation process; remove example-test.md and mastra-master-reference.md files to streamline the documentation.
2025-08-16 11:54:11 +01:00
darrenhinde
a494e84a39
Remove unused agent and task manager files to streamline the codebase and improve maintainability.
2025-08-16 00:00:57 +01:00
