feat(models): qwen3.8-flash now selectable on OpenRouter and Nous portal

Live on both providers (verified 2026-08-28 against openrouter.ai/api/v1/models
and inference-api.nousresearch.com/v1/models) but absent from both curated
picker lists. Adds the entry directly below qwen3.8-max per newest-first
family ordering, an explicit 1M DEFAULT_CONTEXT_LENGTHS entry (new family
slug would otherwise fall through to the generic qwen 131072 catch-all —
same class as #69881), and regenerates model-catalog.json.

Scoped rollout: only the named providers touched. Pricing snapshot skipped
(both routes bill via official_models_api live pricing). Reasoning floor
already fires via the qwen3 prefix entry (180s, verified).

agent/model_metadata.py

@@ -504,6 +504,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     # Qwen — specific model families before the catch-all.
     # Official docs: https://help.aliyun.com/zh/model-studio/developer-reference/
     "qwen3.8-max": 1_000_000,     # 1M context (OpenRouter & Nous portal, verified 2026-08-03)
+    "qwen3.8-flash": 1_000_000,   # 1M context (OpenRouter & Nous portal, verified 2026-08-28)
     "qwen3.6-plus": 1048576,      # 1M context (DashScope/Alibaba & OpenRouter)
     "qwen3.7-plus": 1048576,      # 1M context (DashScope/Alibaba)
     "qwen3-coder-plus": 1000000,  # 1M context

hermes_cli/models.py

@@ -111,6 +111,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("deepseek/deepseek-v4-flash-0731",        "dated snapshot of v4-flash"),
     # Qwen
     ("qwen/qwen3.8-max",                       ""),
+    ("qwen/qwen3.8-flash",                     ""),
     # MoonshotAI
     ("moonshotai/kimi-k3",                     "recommended"),
     # MiniMax
@@ -291,6 +292,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "deepseek/deepseek-v4-flash-0731",
         # Qwen
         "qwen/qwen3.8-max",
+        "qwen/qwen3.8-flash",
         # MoonshotAI
         "moonshotai/kimi-k3",
         # MiniMax

website/static/api/model-catalog.json

@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "updated_at": "2026-08-27T11:03:10Z",
+  "updated_at": "2026-08-28T07:53:26Z",
   "metadata": {
     "source": "hermes-agent repo",
     "docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog"
@@ -108,6 +108,10 @@
           "id": "qwen/qwen3.8-max",
           "description": ""
         },
+        {
+          "id": "qwen/qwen3.8-flash",
+          "description": ""
+        },
         {
           "id": "moonshotai/kimi-k3",
           "description": "recommended"
@@ -267,6 +271,9 @@
         {
           "id": "qwen/qwen3.8-max"
         },
+        {
+          "id": "qwen/qwen3.8-flash"
+        },
         {
           "id": "moonshotai/kimi-k3"
         },