Fahad
86728a1442
WIP
2025-06-15 15:32:41 +04:00
Fahad
9b8ea72280
Fixed for git actions
2025-06-15 14:14:15 +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
6304b7af6b
Native support for xAI Grok3
...
Model shorthand mapping related fixes
Comprehensive auto-mode related tests
2025-06-15 12:21:44 +04:00
Fahad
4becd70a82
Perform prompt size checks only at the MCP boundary
...
New test to confirm history build-up and system prompt does not affect prompt size checks
Also check for large prompts in focus_on
Fixed .env.example incorrectly did not comment out CUSTOM_API causing the run-server script to think at least one key exists
2025-06-15 10:37:08 +04:00
Fahad
3b03783ea7
Instructions on how to add a new tool
2025-06-15 09:42:28 +04:00
Fahad
44db8c9e63
Updated to reflect actual prompt
2025-06-15 09:37:56 +04:00
Fahad
3c56694d3f
Formatting
2025-06-15 09:34:37 +04:00
Fahad
f4395a796c
Typo
2025-06-15 09:33:48 +04:00
Fahad
81ab4da60c
Typo
2025-06-15 09:33:18 +04:00
Fahad
77faea24e1
Typo
2025-06-15 09:30:55 +04:00
Fahad
8364170881
Merge remote-tracking branch 'origin/main'
2025-06-15 09:25:58 +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
318b5c7ae7
Easier access to logs at startup
...
Updated documentation
2025-06-15 07:09:44 +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
Beehive Innovations
be907a7b29
Merge pull request #39 from NikolaiUgelvik/fix-openrouter-auto-mode
...
Fix auto mode when only OpenRouter is configured
2025-06-14 21:37:17 +04:00
Nikolai Ugelvik
0eeea3dd67
Apply black formatting to test_openrouter_provider.py
2025-06-14 19:33:20 +02:00
Nikolai Ugelvik
be2612752a
Fix auto mode when only OpenRouter is configured
...
The get_available_models method in ModelProviderRegistry was only checking
for providers with SUPPORTED_MODELS attribute, which OpenRouter doesn't have.
This caused auto mode to fail with "No models available" error when only
OpenRouter API key was configured.
Added special handling for OpenRouter provider to check its _registry
for available models, ensuring auto mode works correctly with OpenRouter.
Added comprehensive tests to verify:
- Auto mode works with only OpenRouter configured
- Model restrictions are respected
- Graceful handling when no providers are available
- No crashes when OpenRouter lacks _registry attribute
2025-06-14 19:21:14 +02:00
Fahad
70f1356e3e
Improved trigger words to enforce large prompts are passed in as a file reference
2025-06-14 21:03:17 +04:00
Fahad
4cacd2dad9
Fixed trigger word
2025-06-14 20:14:40 +04:00
Fahad
6b05096ba0
testgen grounding
2025-06-14 20:10:59 +04:00
Fahad
b2489409eb
Move o3-pro test into its own
2025-06-14 19:53:33 +04:00
Beehive Innovations
9f973b90e5
Merge pull request #36 from lox/add-o3-pro-support
...
feat: Add o3-pro model support
2025-06-14 19:44:14 +04:00
Fahad
68a75a7791
Updated lint instructions for PRs
2025-06-14 19:37:53 +04:00
Fahad
a8fd7f3d24
Bump
2025-06-14 19:32:11 +04:00
Fahad
f1ad06c529
Fixed lint, tests after recent fix
...
Updated readme
2025-06-14 19:31:31 +04:00
Fahad
b41b874e31
Fixed model name mapping for openrouter
2025-06-14 19:19:59 +04:00
Fahad
b405aaf8bd
some justifications
2025-06-14 19:01:53 +04:00
Fahad
a4f9e22256
Renamed version tool
2025-06-14 18:54:53 +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
ec5fee4409
Bump
2025-06-14 16:48:21 +04:00
Fahad
698c1611d2
Lint fix
2025-06-14 16:47:59 +04:00
Fahad
d0d0a171dc
Ensure duplicate file references are gracefully handled
...
Improved prompt to encourage immediate action
2025-06-14 16:37:02 +04:00
Fahad
ec707e021a
Fix for path translation within docker
2025-06-14 16:00:54 +04:00
Fahad
acbfa1c94e
Improved prompt for next steps
2025-06-14 15:51:04 +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
Lachlan Donald
40aa1eaeb6
Format test_auto_mode.py with black
...
Fix code formatting to comply with black style requirements.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-06-14 21:09:47 +10:00
Fahad
7d33aafcab
Configurable conversation limit now set to 10 exchanges. This helps when you want to manually continue a thread of thought across different models manually.
2025-06-14 14:00:13 +04:00
Fahad
bc3f98a291
Make conversation timeout configuration (so that you're able to resume a discussion manually with another model with a gap of several hours in case you stepped away)
2025-06-14 13:27:19 +04:00
Beehive Innovations
a569e316af
Update README.md
2025-06-14 12:41:15 +04:00
Fahad
710a2ab0eb
Surface important public notice
2025-06-14 11:48:57 +04:00
Fahad
7481af5c8f
Surface important public notice
2025-06-14 11:47:29 +04:00
Fahad
4a3767921a
Surface important public notice
2025-06-14 11:46:32 +04:00
Fahad
002203f0da
Surface important public notice
2025-06-14 11:45:45 +04:00
Fahad
b17fe06d27
bump
2025-06-14 11:34:28 +04:00
Fahad
e0a05b86f1
Add encouraging message about powerful models to schema in case it's not on Opus 4 or above
...
OPENROUTER_ALLOWED_MODELS environment variable support to further limit the models to allow from within Claude. This will put a limit on top of even the ones listed in custom_models.json
2025-06-14 11:34:17 +04:00
Fahad
21037c2d81
Refactored prompts for better maintainability
2025-06-14 11:09:13 +04:00
Fahad
94b2a4d407
Bump
2025-06-14 10:57:08 +04:00
Fahad
23353734cd
Support for allowed model restrictions per provider
...
Tool escalation added to `analyze` to a graceful switch over to codereview is made when absolutely necessary
2025-06-14 10:56:53 +04:00
