feat(antigravity): conductor-level credits fallback for Claude models

Move credits handling from executor-level retry to conductor-level
orchestration. When all free-tier auths are exhausted (429/503), the
conductor discovers auths with available Google One AI credits and
retries with enabledCreditTypes injected via context flag.

Key changes:
- Add AntigravityCreditsHint system for tracking per-auth credits state
- Conductor tries credits fallback after all auths fail (Execute/Stream/Count)
- Executor injects enabledCreditTypes only when conductor sets context flag
- Credits fallback respects provider scope (requires antigravity in providers)
- Add context cancellation check in credits fallback to avoid wasted requests
- Remove executor-level attemptCreditsFallback and preferCredits machinery
- Restructure 429 decision logic (parse details first, keyword fallback)
- Expand shouldAbort to cover INVALID_ARGUMENT/FAILED_PRECONDITION/500+UNKNOWN
- Support human-readable retry delay parsing (e.g. "1h43m56s")
This commit is contained in:
sususu98
2026-04-23 13:44:20 +08:00
parent a188159632
commit 14d46a0a5d
9 changed files with 989 additions and 694 deletions
+1 -1
View File
@@ -98,7 +98,7 @@ disable-cooling: false
quota-exceeded:
switch-project: true # Whether to automatically switch to another project when a quota is exceeded
switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded
antigravity-credits: true # Whether to retry Antigravity quota_exhausted 429s once with enabledCreditTypes=["GOOGLE_ONE_AI"]
antigravity-credits: true # Whether to use credits as last-resort fallback when all free-tier auths are exhausted for Claude models
# Routing strategy for selecting credentials when multiple match.
routing: