feat(models): add MiniMax-M3 to native minimax providers + 1M context (#36214)

Add MiniMax-M3 to the minimax, minimax-oauth, and minimax-cn curated
lists (these are hardcoded — the native Anthropic-format endpoint has no
/v1/models listing and the providers aren't in _MODELS_DEV_PREFERRED, so
new models don't auto-pull). Add a DEFAULT_CONTEXT_LENGTHS key
'minimax-m3' -> 1,000,000 so M3 resolves to its 1M context on every
surface (native ID + OpenRouter/Nous slug) via longest-key-first
substring match, while the M2.x series stays at 204,800.

agent/model_metadata.py

@@ -200,8 +200,12 @@ DEFAULT_CONTEXT_LENGTHS = {
     "qwen3-coder-plus": 1000000,  # 1M context
     "qwen3-coder": 262144,        # 256K context
     "qwen": 131072,
-    # MiniMax — official docs: 204,800 context for all models
-    # https://platform.minimax.io/docs/api-reference/text-anthropic-api
+    # MiniMax — M3 is 1M context (max output 512K); M2.x series is 204,800.
+    # Keys use substring matching (longest-first), so "minimax-m3" wins over
+    # the generic "minimax" catch-all for the M3 slug on every surface
+    # (native MiniMax-M3, OpenRouter/Nous minimax/minimax-m3).
+    # https://platform.minimax.io/docs/api-reference/text-chat-openai
+    "minimax-m3": 1000000,
     "minimax": 204800,
     # GLM
     "glm": 202752,

hermes_cli/models.py

@@ -295,16 +295,19 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "kimi-k2-0905-preview",
     ],
     "minimax": [
+        "MiniMax-M3",
         "MiniMax-M2.7",
         "MiniMax-M2.5",
         "MiniMax-M2.1",
         "MiniMax-M2",
     ],
     "minimax-oauth": [
+        "MiniMax-M3",
         "MiniMax-M2.7",
         "MiniMax-M2.7-highspeed",
     ],
     "minimax-cn": [
+        "MiniMax-M3",
         "MiniMax-M2.7",
         "MiniMax-M2.5",
         "MiniMax-M2.1",