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

GPT-5, GPT-5-mini support

Browse Source 
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
This commit is contained in:
Fahad
2025-08-08 08:51:34 +05:00
parent 9a4791cb06
commit 1a8ec2e12f
30 changed files with 792 additions and 483 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
config.py
View File

@@ -75,10 +75,10 @@ DEFAULT_CONSENSUS_MAX_INSTANCES_PER_COMBINATION = 2
#
# IMPORTANT: This limit ONLY applies to the Claude CLI ↔ MCP Server transport boundary.
# It does NOT limit internal MCP Server operations like system prompts, file embeddings,
# conversation history, or content sent to external models (Gemini/O3/OpenRouter).
# conversation history, or content sent to external models (Gemini/OpenAI/OpenRouter).
#
# MCP Protocol Architecture:
# Claude CLI ←→ MCP Server ←→ External Model (Gemini/O3/etc.)
# Claude CLI ←→ MCP Server ←→ External Model (Gemini/OpenAI/etc.)
# ↑ ↑
# │ │
# MCP transport Internal processing