Sven Lito 3b4fd88d7e fix: resolve temperature handling issues for O3/custom models (#245) ...

- Fix consensus tool hardcoded temperature=0.2 bypassing model capabilities
- Add intelligent temperature inference for unknown custom models
- Support multi-model collaboration (O3, Gemini, Claude, Mistral, DeepSeek)
- Only OpenAI O-series and DeepSeek reasoner models reject temperature
- Most reasoning models (Gemini Pro, Claude, Mistral) DO support temperature
- Comprehensive logging for temperature decisions and user guidance

Resolves: https://github.com/BeehiveInnovations/zen-mcp-server/issues/245

2025-08-23 18:43:51 +07:00

..

shared

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

simple

fix: https://github.com/BeehiveInnovations/zen-mcp-server/issues/251 added handling for safety_feedback from Gemini. FinishReason.STOP can be a hidden safety block from gemini or issued when it chooses not to respond.

2025-08-23 14:03:46 +04:00

workflow

feat: refactored and improved codereview in line with precommit. Reviews are now either external (default) or internal. Takes away anxiety and loss of tokens when Claude incorrectly decides to be 'confident' about its own changes and bungle things up.

2025-08-21 14:04:32 +04:00

__init__.py

New tool! "challenge" with confidence and stop Claude from agreeing with you blindly and undoing the _correct_ strategy because you were wrong

2025-06-29 15:50:45 +04:00

analyze.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

challenge.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

chat.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

codereview.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

consensus.py

fix: resolve temperature handling issues for O3/custom models (#245)

2025-08-23 18:43:51 +07:00

debug.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

docgen.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

listmodels.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

models.py

Generic naming to work with Gemini CLI / Claude Code

2025-06-27 23:41:20 +04:00

planner.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

precommit.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

refactor.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

secaudit.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

testgen.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

thinkdeep.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

tracer.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00

version.py

feat: refactored and tweaked model descriptions / schema to use fewer tokens at launch (average reduction per field description: 60-80%) without sacrificing tool effectiveness

2025-08-22 09:23:59 +04:00