fix(agent): use standard MiniMax-M2.7 for auxiliary model instead of highspeed

MiniMax-M2.7-highspeed is the same model running on faster hardware at 2x the price ($0.60/$2.40 per M tokens vs $0.30/$1.20). For auxiliary tasks like summarization and compression where throughput is not critical, the standard variant is the correct default. Closes #4082
2026-04-30 16:01:49 +08:00 · 2026-03-31 10:55:54 +10:00
1 changed files with 2 additions and 2 deletions
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -56,8 +56,8 @@ logger = logging.getLogger(__name__)
 _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
    "zai": "glm-4.5-flash",
    "kimi-coding": "kimi-k2-turbo-preview",
-    "minimax": "MiniMax-M2.7-highspeed",
+    "minimax": "MiniMax-M2.7",
-    "minimax-cn": "MiniMax-M2.7-highspeed",
+    "minimax-cn": "MiniMax-M2.7",
    "anthropic": "claude-haiku-4-5-20251001",
    "ai-gateway": "google/gemini-3-flash",
    "opencode-zen": "gemini-3-flash",