Files
my-pal-mcp-server/config.py
Fahad 5cd4908e32 fix: increase output token limit to prevent response truncation
- Add MAX_OUTPUT_TOKENS constant set to 32,768 (Gemini 2.5 Pro's limit)
- Update all tools and chat handler to use MAX_OUTPUT_TOKENS
- Add comprehensive tests for output token configuration
- Update README with configuration details and system prompt docs

This fixes the issue where Gemini responses were being cut off at 8192 tokens,
causing Claude to repeatedly ask for the same analysis.

Fixes #1

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-06-09 05:22:22 +04:00

69 lines
1.6 KiB
Python

"""
Configuration and constants for Gemini MCP Server
"""
# Version and metadata
__version__ = "2.4.0"
__updated__ = "2025-06-08"
__author__ = "Fahad Gilani"
# Model configuration
DEFAULT_MODEL = "gemini-2.5-pro-preview-06-05"
MAX_CONTEXT_TOKENS = 1_000_000 # 1M tokens for Gemini Pro
MAX_OUTPUT_TOKENS = 32_768 # Maximum output tokens for Gemini 2.5 Pro
# Temperature defaults for different tool types
TEMPERATURE_ANALYTICAL = 0.2 # For code review, debugging
TEMPERATURE_BALANCED = 0.5 # For general chat
TEMPERATURE_CREATIVE = 0.7 # For architecture, deep thinking
# Tool trigger phrases for natural language matching
TOOL_TRIGGERS = {
"think_deeper": [
"think deeper",
"ultrathink",
"extend my analysis",
"reason through",
"explore alternatives",
"challenge my thinking",
"deep think",
"extended thinking",
"validate my approach",
"find edge cases",
],
"review_code": [
"review",
"check for issues",
"find bugs",
"security check",
"code quality",
"audit",
"code review",
"check this code",
"review for",
"find vulnerabilities",
],
"debug_issue": [
"debug",
"error",
"failing",
"root cause",
"trace",
"why doesn't",
"not working",
"diagnose",
"troubleshoot",
"investigate this error",
],
"analyze": [
"analyze",
"examine",
"look at",
"check",
"inspect",
"understand",
"analyze file",
"analyze these files",
],
}