feat(models): OpenRouter, Nous Portal, and Alibaba Token Plan pickers carry Qwen3.8-Max-0902

Alibaba shipped qwen3.8-max-0902 (alias qwen3.8-max-2026-09-02), the upgraded
snapshot of Qwen3.8-Max: 1M context / 131K output, $2 in / $6 out. Both
aggregators now serve it and dropped the bare slug from their catalogs
(verified 2026-09-02: OpenRouter /v1/models + a 200 completion echoing the
slug; Nous Portal /v1/models).

- OPENROUTER_MODELS (feeds the nous list too): qwen/qwen3.8-max -> qwen/qwen3.8-max-0902
- _ALIBABA_TOKEN_PLAN_MODELS: qwen3.8-max-preview -> qwen3.8-max-0902
- test_empty_model_fallback fixture follows the nous catalog slug
- model-catalog.json regenerated

No new metadata: DEFAULT_CONTEXT_LENGTHS substring-matches qwen3.8-max (1M),
reasoning floor prefix fires (180s), both aggregator routes bill via
official_models_api. alibaba/alibaba-cn/opencode-go/setup.py left unchanged
(out of scope).

hermes_cli/models_catalog_static.py

@@ -36,7 +36,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
         "openai/gpt-5.5", "openai/gpt-5.5-pro", "openai/gpt-5.4-mini", "google/gemini-3.1-pro-preview",
         "google/gemini-3.8-flash", "google/gemini-3.7-flash", "x-ai/grok-4.6", "deepseek/deepseek-v4-pro",
         "deepseek/deepseek-v4-pro-0813", "deepseek/deepseek-v4-flash", "deepseek/deepseek-v4-flash-0731",
-        "qwen/qwen3.8-max", "qwen/qwen3.8-flash", "moonshotai/kimi-k3", "minimax/minimax-m3", "z-ai/glm-5.3",
+        "qwen/qwen3.8-max-0902", "qwen/qwen3.8-flash", "moonshotai/kimi-k3", "minimax/minimax-m3", "z-ai/glm-5.3",
         "z-ai/glm-5.3-flash", "z-ai/glm-5.2", "xiaomi/mimo-v2.5-pro", "tencent/hy4-preview", "tencent/hy3",
         "stepfun/step-3.7-flash", "nvidia/nemotron-3-super-120b-a12b", "meta/muse-spark-1.2",
         "meta/muse-spark-1.2-contributor", "meta/muse-spark-1.3", "meta/muse-spark-1.3-contributor", "sakana/fugu-ultra",
@@ -146,7 +146,7 @@ _ALIBABA_CODING_PLAN_MODELS = [
 ]
 # Verified against a live Token Plan subscription (key tier ``sk-sp-...``).
 _ALIBABA_TOKEN_PLAN_MODELS = [
-    "qwen3.8-max-preview", "qwen3.7-max", "qwen3.7-plus", "qwen3.6-plus", "qwen3.6-flash", "deepseek-v4-pro",
+    "qwen3.8-max-0902", "qwen3.7-max", "qwen3.7-plus", "qwen3.6-plus", "qwen3.6-flash", "deepseek-v4-pro",
     "deepseek-v4-flash", "deepseek-v3.2", "kimi-k2.7-code", "kimi-k2.6", "kimi-k2.5", "glm-5.2", "glm-5.1", "glm-5",
 ]
 _XAI_MODELS = _xai_curated_models()

tests/test_empty_model_fallback.py

@@ -27,16 +27,16 @@ class TestGetDefaultModelForProvider:
 
         with patch(
             "hermes_cli.model_catalog.get_default_model_from_cache",
-            return_value="qwen/qwen3.8-max",
+            return_value="qwen/qwen3.8-max-0902",
         ):
             assert (
                 models_mod.get_preferred_silent_default_model("nous")
-                == "qwen/qwen3.8-max"
+                == "qwen/qwen3.8-max-0902"
             )
-            # nous catalog carries qwen3.8-max, so the full resolver follows.
+            # nous catalog carries qwen3.8-max-0902, so the full resolver follows.
             assert (
                 models_mod.get_default_model_for_provider("nous")
-                == "qwen/qwen3.8-max"
+                == "qwen/qwen3.8-max-0902"
             )
 
 

website/static/api/model-catalog.json

@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "updated_at": "2026-09-04T22:47:22Z",
+  "updated_at": "2026-09-05T06:42:02Z",
   "metadata": {
     "source": "hermes-agent repo",
     "docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog"
@@ -137,7 +137,7 @@
           "description": "dated snapshot of v4-flash"
         },
         {
-          "id": "qwen/qwen3.8-max",
+          "id": "qwen/qwen3.8-max-0902",
           "description": ""
         },
         {
@@ -341,7 +341,7 @@
           "id": "deepseek/deepseek-v4-flash-0731"
         },
         {
-          "id": "qwen/qwen3.8-max"
+          "id": "qwen/qwen3.8-max-0902"
         },
         {
           "id": "qwen/qwen3.8-flash"