integration-direct: route to MiniMax M3 max-effort instead of Anthropic OAuth

Integration runs were burning the personal Anthropic 5-hour window
(429 storm + window drain, 2026-09-02). New env-only context
minimax-m3-max/v1 pins ANTHROPIC_MODEL=MiniMax-M3[1m], maxes the
thinking budget, and sets the 1M auto-compact window; layered on
minimax/v1 for base URL + apiKeyHelper auth.

Claude-Session: https://claude.ai/code/session_019tJk7P8tZzJ24PvtgoGhLN

harnesses/composites/integration-direct/v1/harness.yaml

@@ -5,7 +5,11 @@ description: "Integration harness — cherry-picks from agent fork and pushes di
 
 layers:
   - context: integration/v1
-  - context: anthropic-cloud-paul-oauth/v1
+  # MiniMax M3 (bulk coding-plan subscription) instead of the Anthropic
+  # personal-subscription OAuth — integration runs are frequent/mechanical
+  # and were draining the interactive 5-hour window (2026-09-02).
+  - context: minimax/v1
+  - context: minimax-m3-max/v1
   - context: gitea-ssh/v1
   - context: agent-repo/v1
   - context: direct-push/v1

harnesses/contexts/minimax-m3-max/v1/harness.yaml

@@ -0,0 +1,19 @@
+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: [claude-code]
+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.
+# - MAX_THINKING_TOKENS maxes the extended-thinking budget; the MiniMax
+#   /anthropic layer translates thinking budget to M3 reasoning effort.
+# - 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"
+  MAX_THINKING_TOKENS: "32000"
+  CLAUDE_CODE_AUTO_COMPACT_WINDOW: "1000000"