Files
webber/webber-api/docs/mistral-instructions.md
jpmschweitzerandClaude Opus 4.5 3b58fa4f8b
Build and Push API / release (push) Successful in 3s
Build and Push API / build (push) Successful in 2m27s
refactor: reorganize into monorepo with separate subprojects
Structure webber into three independent subprojects:
- webber-api/: FastAPI backend server with all agent code
- webber-cli/: Standalone CLI client (renamed from cli/ to webber_cli/)
- webber-sandbox/: Test project for functional testing

Key changes:
- Each subproject has its own .venv (Python 3.12+)
- Added sandbox.sh for managing test project templates
- Created sandbox-templates/ with calculator-cli and empty starter
- Updated CI/CD for prefixed tags (api/v*, cli/v*)
- Added comprehensive AGENTS.md with operational instructions
- Added gitignore filtering to glob and grep tools
- Created pyproject.toml for each subproject

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 10:37:47 +01:00

708 B

Background

Research with Gemini identified key issues with mistral-nemo and tool calling:

  • "Pre-computation Hallucination" - model answers before using tools
  • High default temperature (0.7-0.8) causes wandering
  • Model is "chatty and confident" - needs explicit constraints

Key Recommendations from Gemini Research

  1. Temperature 0.0 for tool-calling agents (deterministic, follows schema)
  2. Chain of Thought (CoT) - force step-by-step reasoning
  3. Negative constraints - tell model what NOT to do (Nemo responds better)
  4. Explicit tool descriptions - verbose docstrings with "never estimate yourself"
  5. "Strictly tool-based assistant" pattern - NO internal knowledge claim