Commit Graph

17 Commits

Author SHA1 Message Date
Fahad
514c9c58fc feat: grok-4.1 support https://github.com/BeehiveInnovations/pal-mcp-server/issues/339 2025-12-11 20:08:17 +00:00
Fahad
7c36b9255a refactor: moved registries into a separate module and code cleanup
fix: refactored dial provider to follow the same pattern
2025-10-07 12:59:09 +04:00
Fahad
02d13da897 refactor: new base class for model registry / loading 2025-10-07 12:31:34 +04:00
Fahad
2a706d5720 feat: all native providers now read from catalog files like OpenRouter / Custom configs. Allows for greater control over the capabilities 2025-10-07 12:17:47 +04:00
Fahad
06d7701cc3 refactor: removed subclass override when the base class should be resolving the model name
refactor: always disable "stream"
2025-10-04 10:35:32 +04:00
Fahad
6cab9e56fc feat: added intelligence_score to the model capabilities schema; a 1-20 number that can be specified to influence the sort order of models presented to the CLI in auto selection mode
fix: model definition re-introduced into the schema but intelligently and only a summary is generated per tool. Required to ensure CLI calls and uses the correct model
fix: removed `model` param from some tools where this wasn't needed
fix: fixed adherence to `*_ALLOWED_MODELS` by advertising only the allowed models to the CLI
fix: removed duplicates across providers when passing canonical names back to the CLI; the first enabled provider wins
2025-10-02 21:43:44 +04:00
Fahad
693b84db2b refactor: cleanup provider base class; cleanup shared responsibilities; cleanup public contract
docs: document provider base class
refactor: cleanup custom provider, it should only deal with `is_custom` model configurations
fix: make sure openrouter provider does not load `is_custom` models
fix: listmodels tool cleanup
2025-10-02 12:59:45 +04:00
Fahad
a254ff2220 refactor: removed method from provider, should use model capabilities instead
refactor: cleanup temperature factory method
2025-10-02 11:08:56 +04:00
Fahad
1dc25f6c3d refactor: renaming to reflect underlying type
docs: updated to reflect new modules
2025-10-02 09:07:40 +04:00
Fahad
182aa627df refactor: code cleanup 2025-10-02 08:09:44 +04:00
Fahad
7f37efcbfe Grok-4 support 2025-08-08 09:39:07 +05:00
Fahad
1a8ec2e12f GPT-5, GPT-5-mini support
Improvements to model name resolution
Improved instructions for multi-step workflows when continuation is available
Improved instructions for chat tool
Improved preferred model resolution, moved code from registry -> each provider
Updated tests
2025-08-08 08:51:34 +05:00
Fahad
ce6c1fd7ea Quick test mode for simulation tests
Fixed o4-mini name, OpenAI removed o4-mini-high
Add max_output_tokens property to ModelCapabilities
2025-06-23 18:33:47 +04:00
Fahad
498ea88293 Use ModelCapabilities consistently instead of dictionaries
Moved aliases as part of SUPPORTED_MODELS instead of shorthand, more in line with how custom_models are declared
Further refactoring to cleanup some code
2025-06-23 16:58:59 +04:00
Fahad
9079d06941 Fix for: https://github.com/BeehiveInnovations/zen-mcp-server/issues/101
Fix for: https://github.com/BeehiveInnovations/zen-mcp-server/issues/102

- Removed centralized MODEL_CAPABILITIES_DESC from config.py
- Added model descriptions to individual provider SUPPORTED_MODELS
- Updated _get_available_models() to use ModelProviderRegistry for API key filtering
- Added comprehensive test suite validating bug reproduction and fix
2025-06-21 15:07:52 +04:00
Fahad
dad1e2d74e Proper fix for model discovery per provider 2025-06-18 07:16:10 +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