Add DocGen tool with comprehensive documentation generation capabilities (#109)
* WIP: new workflow architecture * WIP: further improvements and cleanup * WIP: cleanup and docks, replace old tool with new * WIP: cleanup and docks, replace old tool with new * WIP: new planner implementation using workflow * WIP: precommit tool working as a workflow instead of a basic tool Support for passing False to use_assistant_model to skip external models completely and use Claude only * WIP: precommit workflow version swapped with old * WIP: codereview * WIP: replaced codereview * WIP: replaced codereview * WIP: replaced refactor * WIP: workflow for thinkdeep * WIP: ensure files get embedded correctly * WIP: thinkdeep replaced with workflow version * WIP: improved messaging when an external model's response is received * WIP: analyze tool swapped * WIP: updated tests * Extract only the content when building history * Use "relevant_files" for workflow tools only * WIP: updated tests * Extract only the content when building history * Use "relevant_files" for workflow tools only * WIP: fixed get_completion_next_steps_message missing param * Fixed tests Request for files consistently * Fixed tests Request for files consistently * Fixed tests * New testgen workflow tool Updated docs * Swap testgen workflow * Fix CI test failures by excluding API-dependent tests - Update GitHub Actions workflow to exclude simulation tests that require API keys - Fix collaboration tests to properly mock workflow tool expert analysis calls - Update test assertions to handle new workflow tool response format - Ensure unit tests run without external API dependencies in CI 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * WIP - Update tests to match new tools * WIP - Update tests to match new tools * WIP - Update tests to match new tools * Should help with https://github.com/BeehiveInnovations/zen-mcp-server/issues/97 Clear python cache when running script: https://github.com/BeehiveInnovations/zen-mcp-server/issues/96 Improved retry error logging Cleanup * WIP - chat tool using new architecture and improved code sharing * Removed todo * Removed todo * Cleanup old name * Tweak wordings * Tweak wordings Migrate old tests * Support for Flash 2.0 and Flash Lite 2.0 * Support for Flash 2.0 and Flash Lite 2.0 * Support for Flash 2.0 and Flash Lite 2.0 Fixed test * Improved consensus to use the workflow base class * Improved consensus to use the workflow base class * Allow images * Allow images * Replaced old consensus tool * Cleanup tests * Tests for prompt size * New tool: docgen Tests for prompt size Fixes: https://github.com/BeehiveInnovations/zen-mcp-server/issues/107 Use available token size limits: https://github.com/BeehiveInnovations/zen-mcp-server/issues/105 * Improved docgen prompt Exclude TestGen from pytest inclusion * Updated errors * Lint * DocGen instructed not to fix bugs, surface them and stick to d * WIP * Stop claude from being lazy and only documenting a small handful * More style rules --------- Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Beehive Innovations
committed by
GitHub
GitHub
parent
0655590a51
commit
c960bcb720
@@ -1,10 +1,13 @@
|
||||
"""Base model provider interface and data classes."""
|
||||
|
||||
import logging
|
||||
from abc import ABC, abstractmethod
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Enum
|
||||
from typing import Any, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ProviderType(Enum):
|
||||
"""Supported model provider types."""
|
||||
@@ -228,6 +231,46 @@ class ModelProvider(ABC):
|
||||
"""Validate if the model name is supported by this provider."""
|
||||
pass
|
||||
|
||||
def get_effective_temperature(self, model_name: str, requested_temperature: float) -> Optional[float]:
|
||||
"""Get the effective temperature to use for a model given a requested temperature.
|
||||
|
||||
This method handles:
|
||||
- Models that don't support temperature (returns None)
|
||||
- Fixed temperature models (returns the fixed value)
|
||||
- Clamping to min/max range for models with constraints
|
||||
|
||||
Args:
|
||||
model_name: The model to get temperature for
|
||||
requested_temperature: The temperature requested by the user/tool
|
||||
|
||||
Returns:
|
||||
The effective temperature to use, or None if temperature shouldn't be passed
|
||||
"""
|
||||
try:
|
||||
capabilities = self.get_capabilities(model_name)
|
||||
|
||||
# Check if model supports temperature at all
|
||||
if hasattr(capabilities, "supports_temperature") and not capabilities.supports_temperature:
|
||||
return None
|
||||
|
||||
# Get temperature range
|
||||
min_temp, max_temp = capabilities.temperature_range
|
||||
|
||||
# Clamp to valid range
|
||||
if requested_temperature < min_temp:
|
||||
logger.debug(f"Clamping temperature from {requested_temperature} to {min_temp} for model {model_name}")
|
||||
return min_temp
|
||||
elif requested_temperature > max_temp:
|
||||
logger.debug(f"Clamping temperature from {requested_temperature} to {max_temp} for model {model_name}")
|
||||
return max_temp
|
||||
else:
|
||||
return requested_temperature
|
||||
|
||||
except Exception as e:
|
||||
logger.debug(f"Could not determine effective temperature for {model_name}: {e}")
|
||||
# If we can't get capabilities, return the requested temperature
|
||||
return requested_temperature
|
||||
|
||||
def validate_parameters(self, model_name: str, temperature: float, **kwargs) -> None:
|
||||
"""Validate model parameters against capabilities.
|
||||
|
||||
|
||||
@@ -19,6 +19,22 @@ class GeminiModelProvider(ModelProvider):
|
||||
|
||||
# Model configurations
|
||||
SUPPORTED_MODELS = {
|
||||
"gemini-2.0-flash": {
|
||||
"context_window": 1_048_576, # 1M tokens
|
||||
"supports_extended_thinking": True, # Experimental thinking mode
|
||||
"max_thinking_tokens": 24576, # Same as 2.5 flash for consistency
|
||||
"supports_images": True, # Vision capability
|
||||
"max_image_size_mb": 20.0, # Conservative 20MB limit for reliability
|
||||
"description": "Gemini 2.0 Flash (1M context) - Latest fast model with experimental thinking, supports audio/video input",
|
||||
},
|
||||
"gemini-2.0-flash-lite": {
|
||||
"context_window": 1_048_576, # 1M tokens
|
||||
"supports_extended_thinking": False, # Not supported per user request
|
||||
"max_thinking_tokens": 0, # No thinking support
|
||||
"supports_images": False, # Does not support images
|
||||
"max_image_size_mb": 0.0, # No image support
|
||||
"description": "Gemini 2.0 Flash Lite (1M context) - Lightweight fast model, text-only",
|
||||
},
|
||||
"gemini-2.5-flash": {
|
||||
"context_window": 1_048_576, # 1M tokens
|
||||
"supports_extended_thinking": True,
|
||||
@@ -37,6 +53,10 @@ class GeminiModelProvider(ModelProvider):
|
||||
},
|
||||
# Shorthands
|
||||
"flash": "gemini-2.5-flash",
|
||||
"flash-2.0": "gemini-2.0-flash",
|
||||
"flash2": "gemini-2.0-flash",
|
||||
"flashlite": "gemini-2.0-flash-lite",
|
||||
"flash-lite": "gemini-2.0-flash-lite",
|
||||
"pro": "gemini-2.5-pro",
|
||||
}
|
||||
|
||||
|
||||
@@ -409,8 +409,13 @@ class OpenAICompatibleProvider(ModelProvider):
|
||||
if not self.validate_model_name(model_name):
|
||||
raise ValueError(f"Model '{model_name}' not in allowed models list. Allowed models: {self.allowed_models}")
|
||||
|
||||
# Validate parameters
|
||||
self.validate_parameters(model_name, temperature)
|
||||
# Get effective temperature for this model
|
||||
effective_temperature = self.get_effective_temperature(model_name, temperature)
|
||||
|
||||
# Only validate if temperature is not None (meaning the model supports it)
|
||||
if effective_temperature is not None:
|
||||
# Validate parameters with the effective temperature
|
||||
self.validate_parameters(model_name, effective_temperature)
|
||||
|
||||
# Prepare messages
|
||||
messages = []
|
||||
@@ -452,20 +457,13 @@ class OpenAICompatibleProvider(ModelProvider):
|
||||
# Check model capabilities once to determine parameter support
|
||||
resolved_model = self._resolve_model_name(model_name)
|
||||
|
||||
# Get model capabilities once to avoid duplicate calls
|
||||
try:
|
||||
capabilities = self.get_capabilities(model_name)
|
||||
# Defensive check for supports_temperature field (backward compatibility)
|
||||
supports_temperature = getattr(capabilities, "supports_temperature", True)
|
||||
except Exception as e:
|
||||
# If capability check fails, fall back to conservative behavior
|
||||
# Default to including temperature for most models (backward compatibility)
|
||||
logging.debug(f"Failed to check temperature support for {model_name}: {e}")
|
||||
# Use the effective temperature we calculated earlier
|
||||
if effective_temperature is not None:
|
||||
completion_params["temperature"] = effective_temperature
|
||||
supports_temperature = True
|
||||
|
||||
# Add temperature parameter if supported
|
||||
if supports_temperature:
|
||||
completion_params["temperature"] = temperature
|
||||
else:
|
||||
# Model doesn't support temperature
|
||||
supports_temperature = False
|
||||
|
||||
# Add max tokens if specified and model supports it
|
||||
# O3/O4 models that don't support temperature also don't support max_tokens
|
||||
|
||||
@@ -327,7 +327,11 @@ class ModelProviderRegistry:
|
||||
return xai_models[0]
|
||||
elif gemini_available and any("flash" in m for m in gemini_models):
|
||||
# Find the flash model (handles full names)
|
||||
return next(m for m in gemini_models if "flash" in m)
|
||||
# Prefer 2.5 over 2.0 for backward compatibility
|
||||
flash_models = [m for m in gemini_models if "flash" in m]
|
||||
# Sort to ensure 2.5 comes before 2.0
|
||||
flash_models_sorted = sorted(flash_models, reverse=True)
|
||||
return flash_models_sorted[0]
|
||||
elif gemini_available and gemini_models:
|
||||
# Fall back to any available Gemini model
|
||||
return gemini_models[0]
|
||||
@@ -353,7 +357,10 @@ class ModelProviderRegistry:
|
||||
elif xai_available and xai_models:
|
||||
return xai_models[0]
|
||||
elif gemini_available and any("flash" in m for m in gemini_models):
|
||||
return next(m for m in gemini_models if "flash" in m)
|
||||
# Prefer 2.5 over 2.0 for backward compatibility
|
||||
flash_models = [m for m in gemini_models if "flash" in m]
|
||||
flash_models_sorted = sorted(flash_models, reverse=True)
|
||||
return flash_models_sorted[0]
|
||||
elif gemini_available and gemini_models:
|
||||
return gemini_models[0]
|
||||
elif openrouter_available:
|
||||
|
||||
Reference in New Issue
Block a user