1 files changed, 94 insertions, 0 deletions
diff --git a/internal/executor/executor.go b/internal/executor/executor.go
index 981a3ad..ed38d7d 100644
--- a/internal/executor/executor.go
+++ b/internal/executor/executor.go
@@ -45,6 +45,9 @@ type Store interface {
 	// if none is active. Used by execute() to resolve tier 0 of a role-typed
 	// task's escalation ladder.
 	GetActiveRoleConfig(role string) (*storage.RoleConfigRow, error)
+	// ListDependents returns tasks that directly depend on taskID. Used by
+	// cascadeFail to proactively cancel a failed task's downstream subtree.
+	ListDependents(taskID string) ([]*task.Task, error)
 }
 
 // LogPather is an optional interface runners can implement to provide the log
@@ -524,6 +527,16 @@ func (p *Pool) handleRunResult(ctx context.Context, t *task.Task, exec *storage.
 		}
 	}
 
+	// Proactively cancel the downstream dependency subtree the moment this
+	// task lands in a terminal failure state, so tasks depending on it (e.g.
+	// evaluator subtasks fanned out from a Builder) don't sit around waiting
+	// on a dependency that will never complete. BLOCKED/READY/COMPLETED are
+	// intentionally excluded — those aren't terminal failures.
+	switch exec.Status {
+	case "FAILED", "TIMED_OUT", "CANCELLED", "BUDGET_EXCEEDED":
+		p.cascadeFail(t.ID, exec.ErrorMsg)
+	}
+
 	summary := exec.Summary
 	if summary == "" && exec.StdoutPath != "" {
 		summary = extractSummary(exec.StdoutPath)
@@ -550,6 +563,75 @@ func (p *Pool) handleRunResult(ctx context.Context, t *task.Task, exec *storage.
 	p.resultCh <- &Result{TaskID: t.ID, Execution: exec, Err: err}
 }
 
+// cascadeCancellableStates are the task states a dependent task can safely be
+// preempted from: it hasn't started running yet. RUNNING, terminal states,
+// and BLOCKED (subtask delegation) are all left untouched — cascadeFail only
+// preempts work that hasn't started.
+var cascadeCancellableStates = map[task.State]bool{
+	task.StatePending: true,
+	task.StateQueued:  true,
+}
+
+// cascadeFail proactively cancels the downstream dependency subtree rooted at
+// taskID. It is called right after a task is marked into a terminal failure
+// state (FAILED/TIMED_OUT/CANCELLED/BUDGET_EXCEEDED): every direct dependent
+// still waiting to run (PENDING or QUEUED) is recorded as CANCELLED with a
+// message referencing the upstream failure, and the same cancellation is
+// applied recursively to that dependent's own dependents — so a multi-level
+// chain (A fails, B depends on A, C depends on B) cascades all the way down,
+// not just one hop. Dependents that are already RUNNING or in a terminal
+// state are left alone.
+//
+// This exists so a fan-out pattern (e.g. a Builder task with several
+// Evaluator subtasks depending on it) doesn't leave those subtasks sitting
+// around forever — or worse, waiting on a dependency that will never
+// complete — when the upstream task fails. Without this, a dependent only
+// discovers its dependency failed the next time something tries to dispatch
+// it (see checkDepsReady), which may be never for a task nobody has
+// submitted to the pool yet.
+func (p *Pool) cascadeFail(taskID string, reason string) {
+	p.cascadeFailFrom(taskID, reason, make(map[string]bool))
+}
+
+// cascadeFailFrom does the actual work for cascadeFail, threading a visited
+// set through the recursion so a pathological dependency cycle can't cause
+// infinite recursion.
+func (p *Pool) cascadeFailFrom(taskID string, reason string, visited map[string]bool) {
+	if visited[taskID] {
+		return
+	}
+	visited[taskID] = true
+
+	dependents, err := p.store.ListDependents(taskID)
+	if err != nil {
+		p.logger.Error("cascadeFail: list dependents", "taskID", taskID, "error", err)
+		return
+	}
+	for _, dep := range dependents {
+		if !cascadeCancellableStates[dep.State] {
+			continue // already running, already terminal, or blocked — leave it alone
+		}
+		msg := fmt.Sprintf("upstream dependency %s failed: %s", taskID, reason)
+		now := time.Now().UTC()
+		exec := &storage.Execution{
+			ID:        uuid.New().String(),
+			TaskID:    dep.ID,
+			StartTime: now,
+			EndTime:   now,
+			Status:    "CANCELLED",
+			ErrorMsg:  msg,
+		}
+		if createErr := p.store.CreateExecution(exec); createErr != nil {
+			p.logger.Error("cascadeFail: create execution", "taskID", dep.ID, "error", createErr)
+		}
+		if stateErr := p.store.UpdateTaskState(dep.ID, task.StateCancelled); stateErr != nil {
+			p.logger.Error("cascadeFail: update task state", "taskID", dep.ID, "error", stateErr)
+			continue // couldn't actually cancel it — don't cascade further from here
+		}
+		p.logger.Info("cascade-cancelled dependent task", "taskID", dep.ID, "upstream", taskID)
+		p.cascadeFailFrom(dep.ID, msg, visited)
+	}
+}
 
 // ActiveCount returns the number of currently running tasks.
 func (p *Pool) ActiveCount() int {
@@ -839,6 +921,7 @@ func (p *Pool) execute(ctx context.Context, t *task.Task) {
 				if err := p.store.UpdateTaskState(t.ID, task.StateBudgetExceeded); err != nil {
 					p.logger.Error("failed to update task state", "taskID", t.ID, "state", task.StateBudgetExceeded, "error", err)
 				}
+				p.cascadeFail(t.ID, exec.ErrorMsg)
 				p.resultCh <- &Result{TaskID: t.ID, Execution: exec, Err: fmt.Errorf("budget cap reached for %s", agentType)}
 				return
 			}
@@ -849,6 +932,16 @@ func (p *Pool) execute(ctx context.Context, t *task.Task) {
 	// if a dependent task holds the slot while waiting for its dependency to run,
 	// the dependency can never start (maxPerAgent=1).
 	if len(t.DependsOn) > 0 {
+		// cascadeFail (triggered when some ancestor of t failed) may already
+		// have cancelled t out from under it while it sat in the AfterFunc
+		// requeue loop below — re-check the fresh state so we don't try (and
+		// fail, since CANCELLED has no valid self-transition) to re-apply a
+		// terminal transition, and — more importantly — so a cascade-cancelled
+		// task never actually gets dispatched to a runner.
+		if fresh, ferr := p.store.GetTask(t.ID); ferr == nil && fresh.State != task.StateQueued {
+			p.logger.Info("skipping dispatch: task no longer queued (likely cascade-cancelled)", "taskID", t.ID, "state", fresh.State)
+			return
+		}
 		ready, depErr := p.checkDepsReady(t)
 		if depErr != nil {
 			// A dependency hit a terminal failure — cancel this task immediately.
@@ -867,6 +960,7 @@ func (p *Pool) execute(ctx context.Context, t *task.Task) {
 			if err := p.store.UpdateTaskState(t.ID, task.StateCancelled); err != nil {
 				p.logger.Error("failed to update task state", "taskID", t.ID, "state", task.StateCancelled, "error", err)
 			}
+			p.cascadeFail(t.ID, depErr.Error())
 			p.resultCh <- &Result{TaskID: t.ID, Execution: exec, Err: depErr}
 			return
 		}