Fahad
dfed6f0cbd
New tool: "tracer" helps with static analysis / call-flow generation. Does NOT use external models. Used as a quick prompt generator to aid in call-flow / dependency-chart generation. Can be used as an input into another tool / model for extended analysis and deeper thought.
...
Faster docker restarts
2025-06-15 18:42:10 +04:00
Fahad
86728a1442
WIP
2025-06-15 15:32:41 +04:00
Fahad
3bc7956239
Implement TracePath tool for static call path analysis
...
Add comprehensive TracePath tool that predicts and explains full call paths
and control flow without executing code. Features include:
**Core Functionality:**
- Static call path prediction with confidence levels (🟢 🟡 🔴 )
- Multi-language support (Python, JavaScript, TypeScript, C#, Java)
- Value-driven flow analysis based on parameter combinations
- Side effects identification (database, network, filesystem)
- Polymorphism and dynamic dispatch analysis
- Entry point parsing for multiple syntax patterns
**Technical Implementation:**
- Hybrid AI-first architecture (Phase 1: pure AI, Phase 2: AST enhancement)
- Export formats: Markdown, JSON, PlantUML
- Confidence threshold filtering for speculative branches
- Integration with existing tool ecosystem and conversation threading
- Comprehensive error handling and token management
**Files Added:**
- tools/tracepath.py - Main tool implementation
- systemprompts/tracepath_prompt.py - System prompt for analysis
- tests/test_tracepath.py - Comprehensive unit tests (32 tests)
**Files Modified:**
- server.py - Tool registration
- tools/__init__.py - Tool exports
- systemprompts/__init__.py - Prompt exports
**Quality Assurance:**
- All 449 unit tests pass including 32 new TracePath tests
- Full linting and formatting compliance
- Follows established project patterns and conventions
- Multi-model validation with O3 and Gemini Pro insights
**Usage Examples:**
- "Use zen tracepath to analyze BookingManager::finalizeInvoice(invoiceId: 123)"
- "Trace payment.process_payment() with confidence levels and side effects"
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-06-15 14:07:23 +04:00
Fahad
c7835e7eef
Easier access to logs at startup with -f on the run script
...
Improved prompt for immediate action
Additional logging of tool names
Updated documentation
Context aware decomposition system prompt
New script to run code quality checks
2025-06-15 09:25:52 +04:00
Fahad
99fab3e83d
Docs added to show how a new provider is added
...
Docs added to show how a new tool is created
All tools should add numbers to code for models to be able to reference if needed
Enabled line numbering for code for all tools to use
Additional tests to validate line numbering is not added to git diffs
2025-06-15 07:02:27 +04:00
Fahad
b5004b91fc
Major new addition: refactor tool
...
Supports decomposing large components and files, finding codesmells, finding modernizing opportunities as well as code organization opportunities. Fix this mega-classes today!
Line numbers added to embedded code for better references from model -> claude
2025-06-15 06:00:01 +04:00
Fahad
6b05096ba0
testgen grounding
2025-06-14 20:10:59 +04:00
Fahad
442decba70
Improved model response handling to handle additional response statuses in future
...
Improved testgen; encourages follow-ups with less work in between and less token generation to avoid surpassing the 25K barrier
Improved coderevew tool to request a focused code review instead where a single-pass code review is too large or complex
2025-06-14 18:43:56 +04:00
Fahad
4086306c58
New tool: testgen
...
Generates unit tests and encourages model to auto-detect framework and testing style from existing sample (if available)
2025-06-14 15:41:47 +04:00
Fahad
21037c2d81
Refactored prompts for better maintainability
2025-06-14 11:09:13 +04:00
