Files
agent-runtime-framework/harnesses/contexts/minimax-m3-max/v1/harness.yaml
Paul O'Reilly 2dcb9c7605 fix(minimax-m3-max, fable-low-effort): requires takes harness refs, not capability tags
'requires: [claude-code]' failed composition ('Invalid harness reference
format'). Both contexts need no hard dependency — layer ordering in the
composites already guarantees the auth layer precedes them. Validated
locally with entrypoint.harness compose_harness for all 6 affected
composites this time.

Claude-Session: https://claude.ai/code/session_019tJk7P8tZzJ24PvtgoGhLN
2026-09-03 01:13:34 +12:00

23 lines
902 B
YAML

kind: context
name: minimax-m3-max
version: 1
description: "Pin MiniMax M3 (1M context) at max reasoning effort — layer AFTER minimax/v1 (auth + base URL come from there)"
requires: []
provides: []
# Model pin + effort for the MiniMax Anthropic-compatible proxy.
# - ANTHROPIC_MODEL forces every main-loop request to M3 (1M context variant)
# instead of the proxy's default Claude-name mapping.
# - The max thinking budget (M3 reasoning effort) is set by init.sh via
# settings.json — the env var name trips H-SECRET-4's credential pattern
# so it cannot live in this env: block.
# - CLAUDE_CODE_AUTO_COMPACT_WINDOW matches M3's real 1M window (the proxy's
# model metadata under-reports 200K, which triggers premature compaction).
env:
ANTHROPIC_MODEL: "MiniMax-M3[1m]"
ANTHROPIC_SMALL_FAST_MODEL: "MiniMax-M3"
CLAUDE_CODE_AUTO_COMPACT_WINDOW: "1000000"
scripts:
init: ./init.sh