fix(credential_pool): add Nous OAuth cross-process auth-store sync

Concurrent Hermes processes (e.g. cron jobs) refreshing a Nous OAuth token
via resolve_nous_runtime_credentials() write the rotated tokens to auth.json.
The calling process's pool entry becomes stale, and the next refresh against
the already-rotated token triggers a 'refresh token reuse' revocation on
the Nous Portal.

_sync_nous_entry_from_auth_store() reads auth.json under the same lock used
by resolve_nous_runtime_credentials, and adopts the newer token pair before
refreshing the pool entry. This complements #15111 (which preserved the
obtained_at timestamps through seeding).

Partial salvage of #10160 by @konsisumer — only the agent/credential_pool.py
changes + the 3 Nous-specific regression tests. The PR also touched 10
unrelated files (Dockerfile, tips.py, various tool tests) which were
dropped as scope creep.

Regression tests:
- test_sync_nous_entry_from_auth_store_adopts_newer_tokens
- test_sync_nous_entry_noop_when_tokens_match
- test_nous_exhausted_entry_recovers_via_auth_store_sync
This commit is contained in:
konsisumer
2026-04-24 05:18:53 -07:00
committed by Teknium
parent cd221080ec
commit 785d168d50
2 changed files with 258 additions and 0 deletions

View File

@@ -455,6 +455,61 @@ class CredentialPool:
logger.debug("Failed to sync from credentials file: %s", exc)
return entry
def _sync_nous_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
"""Sync a Nous pool entry from auth.json if tokens differ.
Nous OAuth refresh tokens are single-use. When another process
(e.g. a concurrent cron) refreshes the token via
``resolve_nous_runtime_credentials``, it writes fresh tokens to
auth.json under ``_auth_store_lock``. The pool entry's tokens
become stale. This method detects that and adopts the newer pair,
avoiding a "refresh token reuse" revocation on the Nous Portal.
"""
if self.provider != "nous" or entry.source != "device_code":
return entry
try:
with _auth_store_lock():
auth_store = _load_auth_store()
state = _load_provider_state(auth_store, "nous")
if not state:
return entry
store_refresh = state.get("refresh_token", "")
store_access = state.get("access_token", "")
if store_refresh and store_refresh != entry.refresh_token:
logger.debug(
"Pool entry %s: syncing tokens from auth.json (Nous refresh token changed)",
entry.id,
)
field_updates: Dict[str, Any] = {
"access_token": store_access,
"refresh_token": store_refresh,
"last_status": None,
"last_status_at": None,
"last_error_code": None,
}
if state.get("expires_at"):
field_updates["expires_at"] = state["expires_at"]
if state.get("agent_key"):
field_updates["agent_key"] = state["agent_key"]
if state.get("agent_key_expires_at"):
field_updates["agent_key_expires_at"] = state["agent_key_expires_at"]
if state.get("inference_base_url"):
field_updates["inference_base_url"] = state["inference_base_url"]
extra_updates = dict(entry.extra)
for extra_key in ("obtained_at", "expires_in", "agent_key_id",
"agent_key_expires_in", "agent_key_reused",
"agent_key_obtained_at"):
val = state.get(extra_key)
if val is not None:
extra_updates[extra_key] = val
updated = replace(entry, extra=extra_updates, **field_updates)
self._replace_entry(entry, updated)
self._persist()
return updated
except Exception as exc:
logger.debug("Failed to sync Nous entry from auth.json: %s", exc)
return entry
def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
"""Write refreshed pool entry tokens back to auth.json providers.
@@ -561,6 +616,9 @@ class CredentialPool:
last_refresh=refreshed.get("last_refresh"),
)
elif self.provider == "nous":
synced = self._sync_nous_entry_from_auth_store(entry)
if synced is not entry:
entry = synced
nous_state = {
"access_token": entry.access_token,
"refresh_token": entry.refresh_token,
@@ -635,6 +693,26 @@ class CredentialPool:
# Credentials file had a valid (non-expired) token — use it directly
logger.debug("Credentials file has valid token, using without refresh")
return synced
# For nous: another process may have consumed the refresh token
# between our proactive sync and the HTTP call. Re-sync from
# auth.json and adopt the fresh tokens if available.
if self.provider == "nous":
synced = self._sync_nous_entry_from_auth_store(entry)
if synced.refresh_token != entry.refresh_token:
logger.debug("Nous refresh failed but auth.json has newer tokens — adopting")
updated = replace(
synced,
last_status=STATUS_OK,
last_status_at=None,
last_error_code=None,
last_error_reason=None,
last_error_message=None,
last_error_reset_at=None,
)
self._replace_entry(synced, updated)
self._persist()
self._sync_device_code_entry_to_auth_store(updated)
return updated
self._mark_exhausted(entry, None)
return None
@@ -698,6 +776,17 @@ class CredentialPool:
if synced is not entry:
entry = synced
cleared_any = True
# For nous entries, sync from auth.json before status checks.
# Another process may have successfully refreshed via
# resolve_nous_runtime_credentials(), making this entry's
# exhausted status stale.
if (self.provider == "nous"
and entry.source == "device_code"
and entry.last_status == STATUS_EXHAUSTED):
synced = self._sync_nous_entry_from_auth_store(entry)
if synced is not entry:
entry = synced
cleared_any = True
if entry.last_status == STATUS_EXHAUSTED:
exhausted_until = _exhausted_until(entry)
if exhausted_until is not None and now < exhausted_until: