From 1192f29450f1dc440d44b094817977f00475643c Mon Sep 17 00:00:00 2001
From: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Date: Wed, 8 Jul 2026 17:27:52 +0530
Subject: [PATCH] fix: Z.AI endpoint persist failure must not break URL
 resolution

Review findings (hermes-pr-review Phase 2, 3-angle):
- _save_auth_store() does real filesystem I/O (mkdir, O_EXCL create, fsync,
  atomic replace) and can raise on disk-full/permissions/lock-timeout. The
  persist ran bare in the success path, so a persist failure aborted
  _resolve_zai_base_url() after detection had already succeeded. Wrap the
  persist in try/except: log a warning and still return the detected URL
  (worst case: next start re-probes).
- Readability: stage the payload in a local detected_endpoint instead of
  writing through the stale pre-lock 'state' dict, which is no longer what
  gets persisted.
---
 hermes_cli/auth.py | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/hermes_cli/auth.py b/hermes_cli/auth.py
index 103c151e675..5cf6d50186a 100644
--- a/hermes_cli/auth.py
+++ b/hermes_cli/auth.py
@@ -701,23 +701,29 @@ def _resolve_zai_base_url(api_key: str, default_url: str, env_override: str) ->
     if detected and detected.get("base_url"):
         # Persist the detection result keyed on the API key hash.
         key_hash = hashlib.sha256(api_key.encode()).hexdigest()[:16]
-        state["detected_endpoint"] = {
+        detected_endpoint = {
             "base_url": detected["base_url"],
             "endpoint_id": detected.get("id", ""),
             "model": detected.get("model", ""),
             "label": detected.get("label", ""),
             "key_hash": key_hash,
         }
-        with _auth_store_lock():
-            # Reload auth_store under lock to avoid overwriting concurrent changes
-            auth_store = _load_auth_store()
-            state_under_lock = _load_provider_state(auth_store, "zai") or {}
-            state_under_lock["detected_endpoint"] = state["detected_endpoint"]
-            # set_active=False: this runs from credential-pool env seeding
-            # (agent/credential_pool.py) for ANY user with a Z.AI key in env,
-            # and caching a probe result must not flip their active provider.
-            _store_provider_state(auth_store, "zai", state_under_lock, set_active=False)
-            _save_auth_store(auth_store)
+        # Persist failure (disk full, permissions, lock timeout) must not
+        # break resolution — detection already succeeded; worst case the
+        # next start re-probes.
+        try:
+            with _auth_store_lock():
+                # Reload auth_store under lock to avoid overwriting concurrent changes
+                auth_store = _load_auth_store()
+                state_under_lock = _load_provider_state(auth_store, "zai") or {}
+                state_under_lock["detected_endpoint"] = detected_endpoint
+                # set_active=False: this runs from credential-pool env seeding
+                # (agent/credential_pool.py) for ANY user with a Z.AI key in env,
+                # and caching a probe result must not flip their active provider.
+                _store_provider_state(auth_store, "zai", state_under_lock, set_active=False)
+                _save_auth_store(auth_store)
+        except Exception as exc:
+            logger.warning("Z.AI: could not persist detected endpoint (%s); will re-probe next start", exc)
         logger.info("Z.AI: auto-detected endpoint %s (%s)", detected["label"], detected["base_url"])
         return detected["base_url"]