torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: remove MAX_OUTPUT_TOKENS configuration

Browse Source 
Remove the hardcoded 32,768 token output limit to allow Gemini to use
its default/dynamic output token allocation. This provides more
flexibility for responses without artificial constraints.

- Remove MAX_OUTPUT_TOKENS constant from config
- Remove max_tokens parameter from ToolRequest base model
- Clean up all references in server.py and tools/base.py
- Remove test_output_tokens.py as it's no longer needed
- Update imports to remove MAX_OUTPUT_TOKENS references

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Fahad
2025-06-09 08:15:45 +04:00
parent 9bcc78c430
commit e7dcc681d3
5 changed files with 4 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
config.py
View File

@@ -10,7 +10,6 @@ __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