fix(agent): don't treat custom:<name> pools as cross-provider mismatch (#45289)

Custom endpoints carry two naming conventions for the same provider: the
agent's provider attribute is the generic 'custom' label while the pool
is keyed 'custom:<normalized-name>'. The defensive guard in
recover_with_credential_pool compared them literally, logged
'Credential pool provider mismatch: pool=custom:<name>, agent=custom',
and skipped recovery — so 401 refresh and 429 rotation never ran for
ANY custom-provider user (seen in the field on a Fireworks setup whose
dead key burned full retry cycles every turn with the skip warning on
each one).

Accept the pair only when the agent's CURRENT base_url resolves to the
same pool key via get_custom_provider_pool_key, preserving the guard's
original purpose (#33088/#33163): a fallback provider or a different
custom endpoint still skips pool mutation.
This commit is contained in:
Teknium
2026-06-13 02:01:09 -07:00
committed by GitHub
parent bdd3868b57
commit 3803e5fc28
2 changed files with 130 additions and 6 deletions
+27 -6
View File
@@ -618,12 +618,33 @@ def recover_with_credential_pool(
current_provider = (getattr(agent, "provider", "") or "").strip().lower()
pool_provider = (getattr(pool, "provider", "") or "").strip().lower()
if current_provider and pool_provider and current_provider != pool_provider:
_ra().logger.warning(
"Credential pool provider mismatch: pool=%s, agent=%s"
"skipping pool mutation to avoid cross-provider contamination",
pool_provider, current_provider,
)
return False, has_retried_429
# Custom endpoints use two naming conventions for the SAME provider:
# the agent carries the generic ``custom`` label while the pool is
# keyed ``custom:<name>`` (see CUSTOM_POOL_PREFIX). A literal string
# compare treats them as a mismatch and skips recovery for every
# custom-provider user — 401s/429s then burn the full retry cycle
# with no rotation or refresh. Accept the pair as matching only when
# the agent's CURRENT base_url actually resolves to this pool key,
# so a fallback provider (or a different custom endpoint) still
# triggers the guard.
_custom_match = False
if current_provider == "custom" and pool_provider.startswith("custom:"):
try:
from agent.credential_pool import get_custom_provider_pool_key
_agent_base = (getattr(agent, "base_url", "") or "").strip()
_custom_match = bool(_agent_base) and (
(get_custom_provider_pool_key(_agent_base) or "").strip().lower()
== pool_provider
)
except Exception:
_custom_match = False
if not _custom_match:
_ra().logger.warning(
"Credential pool provider mismatch: pool=%s, agent=%s"
"skipping pool mutation to avoid cross-provider contamination",
pool_provider, current_provider,
)
return False, has_retried_429
effective_reason = classified_reason
if effective_reason is None: