Commit Graph

67 Commits

Author SHA1 Message Date
Lachlan Donald
69ec38d1af Add o3-pro model support and extend test coverage
- Added o3-pro model configuration to custom_models.json with 200K context
- Updated OpenAI provider to support o3-pro with fixed temperature constraint
- Extended simulator tests to include o3-pro validation scenarios

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-06-14 15:49:19 +10:00
Fahad
746380eb7f Renamed setup script to avoid confusion (https://github.com/BeehiveInnovations/zen-mcp-server/issues/35)
Further fixes to tests
Pass O3 simulation test when keys are not set, along with a notice
Updated docs on testing, simulation tests / contributing
Support for OpenAI o4-mini and o4-mini-high
2025-06-14 09:28:20 +04:00
Fahad
eb388ab2f2 Categorize tools into 'model capabilities categories' to help determine which type of model to pick when in auto mode
Encourage Claude to pick the best model for the job automatically in auto mode
Lots of new tests to ensure automatic model picking works reliably based on user preference or when a matching model is not found or ambiguous
Improved error reporting when bogus model is requested and is not configured or available
2025-06-14 02:17:06 +04:00
Fahad
8ac5bbb5af Fixed workspace path mapping
Refactoring
Improved system prompts, more generalized
Home folder protection and detection
Retry logic for gemini
2025-06-14 00:26:59 +04:00
Fahad
048ebf90bf Cleanup 2025-06-13 16:05:21 +04:00
Fahad
6739182c20 Differentiate custom from openrouter models
Split readme into multiple docs
2025-06-13 15:59:48 +04:00
Fahad
f44ca326ef Breaking change: openrouter_models.json -> custom_models.json
* Support for Custom URLs and custom models, including locally hosted models such as ollama
* Support for native + openrouter + local models (i.e. dozens of models) means you can start delegating sub-tasks to particular models or work to local models such as localizations or other boring work etc.
* Several tests added
* precommit to also include untracked (new) files
* Logfile auto rollover
* Improved logging
2025-06-13 15:22:09 +04:00
Fahad
b16f85979b Use consistent terminology 2025-06-13 09:06:12 +04:00
Fahad
2cdb92460b WIP
- OpenRouter model configuration registry
- Model definition file for users to be able to control
- Additional tests
- Update instructions
2025-06-13 06:33:12 +04:00
Fahad
cd1105b741 WIP
- OpenRouter model configuration registry
- Model definition file for users to be able to control
- Update instructions
2025-06-13 05:52:26 +04:00
Fahad
a19055b76a WIP
- OpenRouter model configuration registry
- Model definition file for users to be able to control
- Update instructions
2025-06-13 05:52:16 +04:00
Fahad
52b45f2b03 WIP - OpenRouter support and related refactoring 2025-06-12 22:17:11 +04:00
Fahad
3aedb16101 Use the new Gemini 2.5 Flash
Updated to support Thinking Tokens as a ratio of the max allowed
Updated tests
Updated README
2025-06-12 20:46:54 +04:00
Fahad
79af2654b9 Use the new flash model
Updated tests
2025-06-12 13:44:09 +04:00
Fahad
fb66825bf6 Rebranding, refactoring, renaming, cleanup, updated docs 2025-06-12 10:40:43 +04:00
Fahad
9a55ca8898 WIP lots of new tests and validation scenarios
Simulation tests to confirm threading and history traversal
Chain of communication and branching validation tests from live simulation
Temperature enforcement per model
2025-06-12 09:35:05 +04:00
Fahad
2a067a7f4e WIP major refactor and features 2025-06-12 07:14:59 +04:00