fix(model-catalog): fall through to raw.github when Vercel 403s; swap step-3.5-flash for step-3.7-flash on OpenRouter+Nous

The docs site (Vercel) serves /docs/api/model-catalog.json behind a bot
mitigation rule that returns HTTP 403 + x-vercel-mitigated: challenge for
non-browser User-Agents — including urllib (what the CLI uses) and curl.
When that happens, get_catalog() falls back to the stale disk cache and
new model releases (Opus 4.8, etc.) never reach the /model picker even
though they're already in OPENROUTER_MODELS and the live OpenRouter API.

Adds a fallback URL chain: when the primary catalog URL fails, walk
DEFAULT_CATALOG_FALLBACK_URLS — currently the raw.githubusercontent.com
copy of the same file. GitHub raw doesn't bot-gate, so the manifest stays
reachable through Vercel firewall hiccups. Per-provider override URLs
keep their direct-fetch semantics (operators configure those specifically,
no implicit fallback).

Also swaps stepfun/step-3.5-flash for stepfun/step-3.7-flash in the
OpenRouter + Nous Portal curated picker lists. Native stepfun provider
configuration (api.stepfun.ai) is left alone — that depends on what
stepfun.ai itself serves, not what OpenRouter routes.

Test plan: 5 new TestFallbackChain tests cover primary-success,
primary-failure-fallback-success, all-fail, primary==fallback-dedup, and
end-to-end get_catalog routing through the new helper. Existing 23 tests
in test_model_catalog.py still pass (28 total). Wider tests/hermes_cli/
sweep: 5701/5701 pass.

hermes_cli/model_catalog.py

@@ -64,6 +64,15 @@ logger = logging.getLogger(__name__)
 DEFAULT_CATALOG_URL = (
     "https://hermes-agent.nousresearch.com/docs/api/model-catalog.json"
 )
+# Fallback fetch chain. The Docusaurus site is served through Vercel, which
+# occasionally returns HTTP 403 + x-vercel-mitigated: challenge for non-
+# browser clients (urllib, curl). When that happens the disk cache goes
+# stale and new model releases never reach the picker. The raw GitHub URL
+# is the same manifest published from the same repo and is not bot-gated,
+# so we fall through to it whenever the primary URL fails.
+DEFAULT_CATALOG_FALLBACK_URLS: tuple[str, ...] = (
+    "https://raw.githubusercontent.com/NousResearch/hermes-agent/main/website/static/api/model-catalog.json",
+)
 DEFAULT_TTL_HOURS = 24
 DEFAULT_FETCH_TIMEOUT = 8.0
 SUPPORTED_SCHEMA_VERSION = 1
@@ -139,6 +148,31 @@ def _fetch_manifest(url: str, timeout: float) -> dict[str, Any] | None:
     return data
 
 
+def _fetch_manifest_with_fallback(
+    primary_url: str,
+    timeout: float,
+    fallback_urls: tuple[str, ...] = DEFAULT_CATALOG_FALLBACK_URLS,
+) -> dict[str, Any] | None:
+    """Try ``primary_url`` first, then walk ``fallback_urls``.
+
+    Returns the first manifest that fetches and validates, or None when
+    every URL fails. Skips fallback URLs identical to the primary so an
+    operator who configured the catalog URL to point at the raw GitHub
+    copy doesn't double-fetch.
+    """
+    data = _fetch_manifest(primary_url, timeout)
+    if data is not None:
+        return data
+    for url in fallback_urls:
+        if not url or url == primary_url:
+            continue
+        data = _fetch_manifest(url, timeout)
+        if data is not None:
+            logger.info("model catalog primary URL failed; using fallback %s", url)
+            return data
+    return None
+
+
 def _validate_manifest(data: Any) -> bool:
     """Return True when ``data`` matches the minimum manifest shape."""
     if not isinstance(data, dict):
@@ -235,7 +269,7 @@ def get_catalog(*, force_refresh: bool = False) -> dict[str, Any]:
         return disk_data
 
     # Need to (re)fetch. If it fails, fall back to any stale disk copy.
-    fetched = _fetch_manifest(cfg["url"], DEFAULT_FETCH_TIMEOUT)
+    fetched = _fetch_manifest_with_fallback(cfg["url"], DEFAULT_FETCH_TIMEOUT)
     if fetched is not None:
         _write_disk_cache(fetched)
         new_disk_data, new_mtime = _read_disk_cache()

hermes_cli/models.py

@@ -53,7 +53,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("google/gemini-3.1-pro-preview",          ""),
     ("google/gemini-3.1-flash-lite-preview",   ""),
     ("qwen/qwen3.6-35b-a3b",                   ""),
-    ("stepfun/step-3.5-flash",                 ""),
+    ("stepfun/step-3.7-flash",                 ""),
     ("minimax/minimax-m2.7",                   ""),
     ("z-ai/glm-5.1",                           ""),
     ("x-ai/grok-4.20",                         ""),
@@ -160,7 +160,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "google/gemini-3.1-pro-preview",
         "google/gemini-3.1-flash-lite-preview",
         "qwen/qwen3.6-35b-a3b",
-        "stepfun/step-3.5-flash",
+        "stepfun/step-3.7-flash",
         "minimax/minimax-m2.7",
         "z-ai/glm-5.1",
         "x-ai/grok-4.3",