- GROK.md: full agent instructions optimized for Grok 4.3 high-effort mode - GPT55.md: agent instructions for GPT-5.5 (o3-level reasoning, stateless) - docs/handoff_template.md: mandatory cross-session handoff artifact template - .env.grok43: Grok 4.3 environment config additions (do not commit secrets) - AGENTS.md: prepend Grok 4.3 multi-agent/Arena mode addendum block
25 lines
882 B
Text
25 lines
882 B
Text
# Grok 4.3 environment configuration for CORE
|
|
# -----------------------------------------------
|
|
# Copy relevant variables into your .env (which is gitignored).
|
|
# Do NOT commit actual API keys — this file is for reference only.
|
|
#
|
|
# Required for Grok 4.3 via xAI API or Grok Build CLI:
|
|
|
|
# Model selection
|
|
GROK_MODEL=grok-4.3
|
|
|
|
# Always use high effort for algebra/field/cognition work.
|
|
# Acceptable values: high | medium | low
|
|
# Default in xAI API is low — override it here.
|
|
GROK_REASONING_EFFORT=high
|
|
|
|
# Context budget — leave ~200k headroom under the 1M cap for tool outputs
|
|
# and intermediate reasoning.
|
|
GROK_CONTEXT_BUDGET=800000
|
|
|
|
# API key — fill in your actual key in .env, never here
|
|
# XAI_API_KEY=xai-...
|
|
|
|
# Optional: Grok Build CLI config
|
|
# GROK_BUILD_ARENA_MODE=true # enable parallel subagent mode
|
|
# GROK_BUILD_MAX_AGENTS=4 # limit parallelism to 4 subagents
|