-
-
Notifications
You must be signed in to change notification settings - Fork 80.7k
Live model switch mid-attempt terminates the run instead of retrying against the new model #101676
Copy link
Copy link
Open
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:fix-shape-clearClawSweeper found a clear likely implementation shape for this issue.ClawSweeper found a clear likely implementation shape for this issue.clawsweeper:queueable-fixClawSweeper marked this issue as an existing queue_fix_pr work candidate.ClawSweeper marked this issue as an existing queue_fix_pr work candidate.clawsweeper:source-reproClawSweeper found a high-confidence source-level issue reproduction.ClawSweeper found a high-confidence source-level issue reproduction.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.Auth, provider routing, model choice, or SecretRef resolution may break.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦞 diamond lobsterVery strong issue quality with high-confidence source-level or clear reproduction.Very strong issue quality with high-confidence source-level or clear reproduction.no-staleExclude from stale automationExclude from stale automation
Description
Metadata
Metadata
Assignees
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:fix-shape-clearClawSweeper found a clear likely implementation shape for this issue.ClawSweeper found a clear likely implementation shape for this issue.clawsweeper:queueable-fixClawSweeper marked this issue as an existing queue_fix_pr work candidate.ClawSweeper marked this issue as an existing queue_fix_pr work candidate.clawsweeper:source-reproClawSweeper found a high-confidence source-level issue reproduction.ClawSweeper found a high-confidence source-level issue reproduction.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.Auth, provider routing, model choice, or SecretRef resolution may break.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦞 diamond lobsterVery strong issue quality with high-confidence source-level or clear reproduction.Very strong issue quality with high-confidence source-level or clear reproduction.no-staleExclude from stale automationExclude from stale automation
Type
Fields
Priority
None yet
OpenClaw 2026.6.11 (e085fa1)
Symptom
A model-switch request that arrives while a turn is actively in-flight causes a hard failure instead of retrying the same turn against the newly-selected model.
Evidence
Suggested fix
When a live model-switch is requested mid-attempt, treat it like a fallback candidate: retry the in-flight turn against the new model rather than surfacing it as a terminal error. Current behavior looks like it hits the fallback-decision path (
model_fallback_decision) but bails becausefallbackConfigured=false, when really this should be an intentional retry path, not a fallback-config-dependent one.Impact
Any mid-turn model switch (session_status model override,
/model, cron job override, etc.) issued while a turn is running currently kills that turn outright instead of completing it on the new model.