fix(fallback): attach credential pool after provider switch

When automatic fallback activates a provider that differs from the
primary, try_activate_fallback() cleared the primary's pool (to avoid
cross-provider base_url contamination, #33163) but never loaded the
fallback provider's own pool. The fallback then ran with no pool, so
rate_limit/billing/auth recovery couldn't rotate its credentials.

After clearing a mismatched pool, load_pool(fb_provider) and attach it
when it has credentials, so provider-specific rotation continues to
work on the fallback target.
This commit is contained in:
herbalizer404 2026-06-27 04:07:59 -07:00 committed by Teknium
parent 635841d210
commit 3fe16e3cd5
2 changed files with 76 additions and 13 deletions

View file

@ -1210,14 +1210,16 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
agent._transport_cache.clear()
agent._fallback_activated = True
# Clear the credential pool when the fallback provider doesn't match
# the pool's provider. The pool was seeded for the primary provider;
# leaving it attached means downstream recovery (rate_limit / billing /
# auth) calls ``_swap_credential`` with a primary entry which overwrites
# the agent's ``base_url`` back to the primary's endpoint — every
# fallback request then 404s against the wrong host. See #33163.
# Rebind the credential pool to the fallback provider when the provider
# changes. Keeping the primary pool attached would make downstream
# recovery (rate_limit / billing / auth) mutate the wrong credential
# set and can overwrite the fallback's base_url back to the primary
# endpoint. See #33163.
#
# When the fallback shares the pool's provider (e.g. both openrouter
# entries with different routing) the pool is preserved.
# entries with different routing) the pool is preserved. When the
# providers differ, load the fallback provider's own pool if one exists
# so provider-specific rotation continues to work after the switch.
_existing_pool = getattr(agent, "_credential_pool", None)
if _existing_pool is not None:
_pool_provider = (getattr(_existing_pool, "provider", "") or "").strip().lower()
@ -1228,6 +1230,22 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
fb_provider, fb_model, _pool_provider,
)
agent._credential_pool = None
if getattr(agent, "_credential_pool", None) is None:
try:
from agent.credential_pool import load_pool
fallback_pool = load_pool(fb_provider)
if fallback_pool and fallback_pool.has_credentials():
agent._credential_pool = fallback_pool
logger.info(
"Fallback to %s/%s: attached fallback credential pool",
fb_provider, fb_model,
)
except Exception as exc:
logger.debug(
"Fallback to %s/%s: could not attach credential pool: %s",
fb_provider, fb_model, exc,
)
# Honor per-provider / per-model request_timeout_seconds for the
# fallback target (same knob the primary client uses). None = use