feat(zai): add GLM-5V-Turbo support for coding plan (#9907)

- Add glm-5v-turbo to OpenRouter, Nous, and native Z.AI model lists
- Add glm-5v context length entry (200K tokens) to model metadata
- Update Z.AI endpoint probe to try multiple candidate models per
  endpoint (glm-5.1, glm-5v-turbo, glm-4.7) — fixes detection for
  newer coding plan accounts that lack older models
- Add zai to _PROVIDER_VISION_MODELS so auxiliary vision tasks
  (vision_analyze, browser screenshots) route through 5v

Fixes #9888

agent/auxiliary_client.py

@@ -112,6 +112,7 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
 # "exotic provider" branch checks this before falling back to the main model.
 _PROVIDER_VISION_MODELS: Dict[str, str] = {
     "xiaomi": "mimo-v2-omni",
+    "zai": "glm-5v-turbo",
 }
 
 # OpenRouter app attribution headers

hermes_cli/auth.py

@@ -383,13 +383,16 @@ def _resolve_api_key_provider_secret(
 # Z.AI has separate billing for general vs coding plans, and global vs China
 # endpoints.  A key that works on one may return "Insufficient balance" on
 # another.  We probe at setup time and store the working endpoint.
+# Each entry lists candidate models to try in order — newer coding plan accounts
+# may only have access to recent models (glm-5.1, glm-5v-turbo) while older
+# ones still use glm-4.7.
 
 ZAI_ENDPOINTS = [
-    # (id, base_url, default_model, label)
-    ("global",        "https://api.z.ai/api/paas/v4",        "glm-5",   "Global"),
-    ("cn",            "https://open.bigmodel.cn/api/paas/v4", "glm-5",   "China"),
-    ("coding-global", "https://api.z.ai/api/coding/paas/v4",  "glm-4.7", "Global (Coding Plan)"),
-    ("coding-cn",     "https://open.bigmodel.cn/api/coding/paas/v4", "glm-4.7", "China (Coding Plan)"),
+    # (id, base_url, probe_models, label)
+    ("global",        "https://api.z.ai/api/paas/v4",        ["glm-5"],   "Global"),
+    ("cn",            "https://open.bigmodel.cn/api/paas/v4", ["glm-5"],   "China"),
+    ("coding-global", "https://api.z.ai/api/coding/paas/v4",  ["glm-5.1", "glm-5v-turbo", "glm-4.7"], "Global (Coding Plan)"),
+    ("coding-cn",     "https://open.bigmodel.cn/api/coding/paas/v4", ["glm-5.1", "glm-5v-turbo", "glm-4.7"], "China (Coding Plan)"),
 ]
 
 
@@ -397,35 +400,37 @@ def detect_zai_endpoint(api_key: str, timeout: float = 8.0) -> Optional[Dict[str
     """Probe z.ai endpoints to find one that accepts this API key.
 
     Returns {"id": ..., "base_url": ..., "model": ..., "label": ...} for the
-    first working endpoint, or None if all fail.
+    first working endpoint, or None if all fail.  For endpoints with multiple
+    candidate models, tries each in order and returns the first that succeeds.
     """
-    for ep_id, base_url, model, label in ZAI_ENDPOINTS:
-        try:
-            resp = httpx.post(
-                f"{base_url}/chat/completions",
-                headers={
-                    "Authorization": f"Bearer {api_key}",
-                    "Content-Type": "application/json",
-                },
-                json={
-                    "model": model,
-                    "stream": False,
-                    "max_tokens": 1,
-                    "messages": [{"role": "user", "content": "ping"}],
-                },
-                timeout=timeout,
-            )
-            if resp.status_code == 200:
-                logger.debug("Z.AI endpoint probe: %s (%s) OK", ep_id, base_url)
-                return {
-                    "id": ep_id,
-                    "base_url": base_url,
-                    "model": model,
-                    "label": label,
-                }
-            logger.debug("Z.AI endpoint probe: %s returned %s", ep_id, resp.status_code)
-        except Exception as exc:
-            logger.debug("Z.AI endpoint probe: %s failed: %s", ep_id, exc)
+    for ep_id, base_url, probe_models, label in ZAI_ENDPOINTS:
+        for model in probe_models:
+            try:
+                resp = httpx.post(
+                    f"{base_url}/chat/completions",
+                    headers={
+                        "Authorization": f"Bearer {api_key}",
+                        "Content-Type": "application/json",
+                    },
+                    json={
+                        "model": model,
+                        "stream": False,
+                        "max_tokens": 1,
+                        "messages": [{"role": "user", "content": "ping"}],
+                    },
+                    timeout=timeout,
+                )
+                if resp.status_code == 200:
+                    logger.debug("Z.AI endpoint probe: %s (%s) model=%s OK", ep_id, base_url, model)
+                    return {
+                        "id": ep_id,
+                        "base_url": base_url,
+                        "model": model,
+                        "label": label,
+                    }
+                logger.debug("Z.AI endpoint probe: %s model=%s returned %s", ep_id, model, resp.status_code)
+            except Exception as exc:
+                logger.debug("Z.AI endpoint probe: %s model=%s failed: %s", ep_id, model, exc)
     return None
 
 

hermes_cli/models.py

@@ -44,6 +44,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("minimax/minimax-m2.7",            ""),
     ("minimax/minimax-m2.5",            ""),
     ("z-ai/glm-5.1",                    ""),
+    ("z-ai/glm-5v-turbo",               ""),
     ("z-ai/glm-5-turbo",                ""),
     ("moonshotai/kimi-k2.5",            ""),
     ("x-ai/grok-4.20",                  ""),
@@ -89,6 +90,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "minimax/minimax-m2.7",
         "minimax/minimax-m2.5",
         "z-ai/glm-5.1",
+        "z-ai/glm-5v-turbo",
         "z-ai/glm-5-turbo",
         "moonshotai/kimi-k2.5",
         "x-ai/grok-4.20-beta",
@@ -134,6 +136,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
     "zai": [
         "glm-5.1",
         "glm-5",
+        "glm-5v-turbo",
         "glm-5-turbo",
         "glm-4.7",
         "glm-4.5",