From 3c3ae7428dca9693dfea59f5756bf8602225cbde Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Mon, 3 Aug 2026 15:04:31 -0700
Subject: [PATCH] feat(models): add qwen3.8-max to Nous portal + OpenRouter
 catalogs, replacing qwen3.7-max

Qwen3.8 Max is live on both OpenRouter and the Nous portal
(qwen/qwen3.8-max, 1M context, 131K max output). Per the
newest-max-replaces-last-max convention, it takes qwen3.7-max's slot
in both curated lists.

- hermes_cli/models.py: OPENROUTER_MODELS + _PROVIDER_MODELS[nous]
  swap qwen/qwen3.7-max -> qwen/qwen3.8-max
- agent/model_metadata.py: DEFAULT_CONTEXT_LENGTHS entry for
  qwen3.8-max at 1,000,000 (verified against OpenRouter live
  metadata and Nous /v1/models 2026-08-03)
- tests/test_empty_model_fallback.py: swap incidental catalog fixture
  to the surviving slug
- website/static/api/model-catalog.json: regenerated

Pricing snapshot skipped: both routes bill via official_models_api
(live pricing), verified with resolve_billing_route. Reasoning
timeout floor already covered by the qwen3 prefix (180s).
---
 agent/model_metadata.py               | 1 +
 hermes_cli/models.py                  | 4 ++--
 tests/test_empty_model_fallback.py    | 8 ++++----
 website/static/api/model-catalog.json | 6 +++---
 4 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/agent/model_metadata.py b/agent/model_metadata.py
index b1701c32e89fb..c147ef126b1a8 100644
--- a/agent/model_metadata.py
+++ b/agent/model_metadata.py
@@ -472,6 +472,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "llama": 131072,
     # 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)
     "qwen3.6-plus": 1048576,      # 1M context (DashScope/Alibaba & OpenRouter)
     "qwen3.7-plus": 1048576,      # 1M context (DashScope/Alibaba)
     "qwen3-coder-plus": 1000000,  # 1M context
diff --git a/hermes_cli/models.py b/hermes_cli/models.py
index 75597f4602a3a..e2e6c967f9d22 100644
--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -72,7 +72,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("deepseek/deepseek-v4-flash",             ""),
     ("deepseek/deepseek-v4-flash-0731",        "dated snapshot of v4-flash"),
     # Qwen
-    ("qwen/qwen3.7-max",                       ""),
+    ("qwen/qwen3.8-max",                       ""),
     # MoonshotAI
     ("moonshotai/kimi-k3",                     "recommended"),
     # MiniMax
@@ -244,7 +244,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "deepseek/deepseek-v4-flash",
         "deepseek/deepseek-v4-flash-0731",
         # Qwen
-        "qwen/qwen3.7-max",
+        "qwen/qwen3.8-max",
         # MoonshotAI
         "moonshotai/kimi-k3",
         # MiniMax
diff --git a/tests/test_empty_model_fallback.py b/tests/test_empty_model_fallback.py
index 7a0ec903df9f9..3d7f8505ec62c 100644
--- a/tests/test_empty_model_fallback.py
+++ b/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/qwen3.7-max",
+            return_value="qwen/qwen3.8-max",
         ):
             assert (
                 models_mod.get_preferred_silent_default_model("nous")
-                == "qwen/qwen3.7-max"
+                == "qwen/qwen3.8-max"
             )
-            # nous catalog carries qwen3.7-max, so the full resolver follows.
+            # nous catalog carries qwen3.8-max, so the full resolver follows.
             assert (
                 models_mod.get_default_model_for_provider("nous")
-                == "qwen/qwen3.7-max"
+                == "qwen/qwen3.8-max"
             )
 
 
diff --git a/website/static/api/model-catalog.json b/website/static/api/model-catalog.json
index 549edb0423051..946ea073cbef7 100644
--- a/website/static/api/model-catalog.json
+++ b/website/static/api/model-catalog.json
@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "updated_at": "2026-07-31T15:41:39Z",
+  "updated_at": "2026-08-03T22:03:15Z",
   "metadata": {
     "source": "hermes-agent repo",
     "docs": "https://hermes-agent.nousresearch.com/docs/reference/model-catalog"
@@ -101,7 +101,7 @@
           "description": "dated snapshot of v4-flash"
         },
         {
-          "id": "qwen/qwen3.7-max",
+          "id": "qwen/qwen3.8-max",
           "description": ""
         },
         {
@@ -238,7 +238,7 @@
           "id": "deepseek/deepseek-v4-flash-0731"
         },
         {
-          "id": "qwen/qwen3.7-max"
+          "id": "qwen/qwen3.8-max"
         },
         {
           "id": "moonshotai/kimi-k3"