vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 17:40:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(agents): improve fallback failure observability

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-27 12:49:30 +01:00
parent 63eaf8ea51
commit 0e586bb48a
14 changed files with 166 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/concepts/model-failover.md
View File

@@ -203,7 +203,7 @@ Defaults:
## Model fallback
If all profiles for a provider fail, OpenClaw moves to the next model in `agents.defaults.model.fallbacks`. This applies to auth failures, rate limits, and timeouts that exhausted profile rotation (other errors do not advance fallback).
If all profiles for a provider fail, OpenClaw moves to the next model in `agents.defaults.model.fallbacks`. This applies to auth failures, rate limits, and timeouts that exhausted profile rotation (other errors do not advance fallback). Provider errors that do not expose enough detail are still labeled precisely in fallback state: `empty_response` means the provider returned no usable message or status, `no_error_details` means the provider explicitly returned `Unknown error (no error details in response)`, and `unclassified` means OpenClaw preserved the raw preview but no classifier matched it yet.
Overloaded and rate-limit errors are handled more aggressively than billing cooldowns. By default, OpenClaw allows one same-provider auth-profile retry, then switches to the next configured model fallback without waiting. Provider-busy signals such as `ModelNotReadyException` land in that overloaded bucket. Tune this with `auth.cooldowns.overloadedProfileRotations`, `auth.cooldowns.overloadedBackoffMs`, and `auth.cooldowns.rateLimitedProfileRotations`.
@@ -302,6 +302,8 @@ The persisted fallback override closes that window, and the narrow rollback keep
- optional status/code
- human-readable error summary
Structured `model_fallback_decision` logs also include flat `fallbackStep*` fields when a candidate fails, is skipped, or a later fallback succeeds. These fields make the attempted transition explicit (`fallbackStepFromModel`, `fallbackStepToModel`, `fallbackStepFromFailureReason`, `fallbackStepFromFailureDetail`, `fallbackStepFinalOutcome`) so log and diagnostic exporters can reconstruct the primary failure even when the terminal fallback also fails.
When every candidate fails, OpenClaw throws `FallbackSummaryError`. The outer reply runner can use that to build a more specific message such as "all models are temporarily rate-limited" and include the soonest cooldown expiry when one is known.
That cooldown summary is model-aware: