executor: fix session ID on second block-and-resume cycle

When a resumed execution is blocked again, SessionID was set to the new
exec's own UUID instead of the original ResumeSessionID. The next resume
would then pass the wrong --resume argument to claude and fail.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

1 files changed, 9 insertions, 2 deletions

diff --git a/internal/executor/claude.go b/internal/executor/claude.go
index db4d0fa..4839a90 100644
--- a/internal/executor/claude.go
+++ b/internal/executor/claude.go
@@ -85,9 +85,16 @@ func (r *ClaudeRunner) Run(ctx context.Context, t *task.Task, e *storage.Executi
 	}
 
 	// Pre-assign session ID so we can resume after a BLOCKED state.
-	// If this is a resume execution the session ID is already set.
+	// For resume executions, the claude session continues under the original
+	// session ID (the one passed to --resume). Using the new exec's own UUID
+	// would cause a second block-and-resume cycle to pass the wrong --resume
+	// argument.
 	if e.SessionID == "" {
-		e.SessionID = e.ID // reuse execution UUID as session UUID (both are UUIDs)
+		if e.ResumeSessionID != "" {
+			e.SessionID = e.ResumeSessionID
+		} else {
+			e.SessionID = e.ID // reuse execution UUID as session UUID (both are UUIDs)
+		}
 	}
 
 	// For new (non-resume) executions with a project_dir, clone into a sandbox.