ling/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-28 06:51:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
- 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
This commit is contained in:
Teknium
2026-04-14 16:26:01 -07:00
committed by GitHub
parent 1e5e1e822b
commit 6448e1da23
3 changed files with 42 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
hermes_cli/auth.py
View File

@@ -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