Port pattern from zed-industries/zed#62729: request ungated Codex model catalog (clean-room)

The ChatGPT Codex models endpoint interprets client_version as a Codex
CLI compatibility version and filters out any model whose
minimal_client_version is newer than the value sent. Hermes hardcoded
client_version=1.0.0 at both catalog request sites, so model visibility
was accidentally coupled to a version scheme Hermes doesn't follow —
future models gated behind a higher minimal version would silently
vanish from the account catalog.

The backend accepts the exact sentinel 0.0.0 as an ungated request
returning the complete account catalog (verified live: 0.0.0 and
current versions return identical model sets today, while omitting the
parameter is HTTP 400 and out-of-sequence values like 0.0.1 return no
models). Both request sites (hermes_cli/codex_models.py and the
context-length probe in agent/model_metadata.py) now share one
CODEX_UNGATED_CLIENT_VERSION constant.

Clean-room port of the observed behavior in zed-industries/zed#62729;
no GPL code translated.

hermes_cli/codex_models.py

@@ -155,10 +155,8 @@ def _fetch_models_from_api(access_token: str) -> List[str]:
         acct_id = _extract_chatgpt_account_id(access_token)
         if acct_id:
             headers["ChatGPT-Account-Id"] = acct_id
-        resp = httpx.get(
-            "https://chatgpt.com/backend-api/codex/models?client_version=1.0.0",
-            headers=headers,
-            timeout=10)
+        from agent.model_metadata import CODEX_MODELS_CATALOG_URL
+        resp = httpx.get(CODEX_MODELS_CATALOG_URL, headers=headers, timeout=10)
         if resp.status_code != 200:
             return []
         data = resp.json()