feat(executor): add DAG auto-cascade-fail + role-typed subtask spawning (Phase 6)

Two prerequisites for safe parallel evaluator fan-out (later phase):

1. Auto-cascade-fail: previously, a failed task's dependents just sat
   PENDING/QUEUED forever (or until something eventually tried to dispatch
   them and discovered the dependency was dead). Pool.cascadeFail now fires
   right after a task lands in a terminal failure state (FAILED/TIMED_OUT/
   CANCELLED/BUDGET_EXCEEDED, from handleRunResult, the budget-gate reject
   path, and the checkDepsReady dependency-failure path), recursively
   cancelling every not-yet-run dependent (PENDING/QUEUED only -- RUNNING and
   terminal states are left alone) with a message referencing the upstream
   failure. A visited-set guards recursion, which turned out to be
   load-bearing rather than defense-in-depth: task creation does not prevent
   dependency cycles anywhere in this codebase.

   Correction to an earlier assumption: internal/executor's
   waitForDependencies is dead code, never called. The live mechanism is
   checkDepsReady, invoked synchronously in execute() with a self-requeue via
   time.AfterFunc. Added a freshness re-check (GetTask, bail if no longer
   QUEUED) at the top of that block so a task cascade-cancelled while sitting
   in the requeue loop stops silently instead of hitting an invalid
   CANCELLED->CANCELLED transition or, worse, still getting dispatched.

2. storeChannel.SpawnSubtask hardcoded Agent.Type: "claude" on every spawned
   child regardless of what role it should play -- a hard blocker for a
   Planner/Builder task spawning role-typed evaluator subtasks. SubtaskSpec
   (internal/agentchannel) gains a Role field; when set, the child task gets
   Agent.Role instead of a hardcoded Type, so Phase 5's role-resolution picks
   provider/model from that role's escalation ladder. spec.Role == "" (every
   existing caller) preserves today's exact behavior byte-for-byte -- proven
   by an explicit regression test, not just new-feature coverage. Threaded
   the new `role` parameter through both spawn_subtask transports: the native
   tool-use loop (internal/agentloop/tools.go) and the MCP tool exposed to
   ContainerRunner-driven claude/gemini agents (internal/executor/agentmcp.go).

go build/vet/test -race -count=1 all pass, full suite (20 packages).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs

1 files changed, 38 insertions, 0 deletions

diff --git a/internal/executor/nativerunner_test.go b/internal/executor/nativerunner_test.go
index ab0317c..b081b8e 100644
--- a/internal/executor/nativerunner_test.go
+++ b/internal/executor/nativerunner_test.go
@@ -199,6 +199,44 @@ func TestNativeRunner_Run_ToolLoop_ReportSummaryAndSpawn(t *testing.T) {
 	}
 }
 
+// TestNativeRunner_Run_ToolLoop_SpawnSubtask_RolePassthrough is an
+// end-to-end-ish test (fake LLM server, real agentloop.Loop/tools.go
+// dispatch, real storeChannel) proving a spawn_subtask tool call carrying a
+// "role" argument reaches SubtaskSpec.Role correctly through
+// internal/agentloop/tools.go's dispatchTool, and from there through
+// storeChannel.SpawnSubtask into the created child task's Agent.Role.
+func TestNativeRunner_Run_ToolLoop_SpawnSubtask_RolePassthrough(t *testing.T) {
+	srv := fakeChatServer(t, []fakeTurn{
+		{toolCalls: []llm.ToolCall{toolCall("c1", "spawn_subtask", `{"name":"eval","instructions":"evaluate","role":"evaluator_quality"}`)}},
+		{content: "finished"},
+	})
+	defer srv.Close()
+
+	r := newLocalRunner(t, srv)
+	tt := localTask()
+	store := &fakeChannelStore{}
+	ch := newStoreChannel(store, tt.ID)
+	exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
+
+	if err := r.Run(context.Background(), tt, exec, ch); err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+
+	if len(store.createdTasks) != 1 {
+		t.Fatalf("expected 1 spawned subtask, got %d", len(store.createdTasks))
+	}
+	child := store.createdTasks[0]
+	if child.Agent.Role != "evaluator_quality" {
+		t.Errorf("Agent.Role: want evaluator_quality, got %q", child.Agent.Role)
+	}
+	if child.Agent.Type != "" {
+		t.Errorf("Agent.Type: want empty for role-typed subtask, got %q", child.Agent.Type)
+	}
+	if child.Agent.Instructions != "evaluate" {
+		t.Errorf("Agent.Instructions: want evaluate, got %q", child.Agent.Instructions)
+	}
+}
+
 func TestNativeRunner_Run_RecordProgress(t *testing.T) {
 	srv := fakeChatServer(t, []fakeTurn{
 		{toolCalls: []llm.ToolCall{toolCall("c1", "record_progress", `{"message":"halfway there"}`)}},