feat(executor): per-task agent MCP server + token registry (Phase 2)

Adds the agent-facing MCP transport foundation: a Registry that mints a
per-task bearer token bound to a freshly built MCP server exposing the four
agent tools (ask_user, report_summary, spawn_subtask, record_progress), and
an HTTP handler (StreamableHTTP) that resolves the token to that server. The
server never trusts an agent-supplied task ID — context comes from the token.

The default storeChannel now buffers summary and question signals under a
mutex (an MCP tool call lands on an HTTP-handler goroutine mid-run), exposing
ReportedSummary/PendingQuestion. The pool flushes the buffered summary onto
the execution after the run, replacing the runner's direct exec.Summary write
and keeping the read race-free.

ask_user follows the record-and-resume model: it buffers the question, returns
ErrAgentBlocked, and the tool tells the agent to end its turn; the run blocks
and resumes later via claude --resume (no live slot held).

Tests cover registry lifecycle, in-memory tool dispatch, and HTTP end-to-end
with bearer auth (valid token dispatches; invalid token rejected).

Not yet wired into the runners or mounted on the API server — next increment.

https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39

1 files changed, 3 insertions, 3 deletions

diff --git a/internal/executor/local_test.go b/internal/executor/local_test.go
index 8aa8791..ffe87f9 100644
--- a/internal/executor/local_test.go
+++ b/internal/executor/local_test.go
@@ -72,7 +72,7 @@ func TestLocalRunner_Run_WritesStreamJSON(t *testing.T) {
 	}
 	exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
 
-	if err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID, exec)); err != nil {
+	if err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID)); err != nil {
 		t.Fatalf("Run: %v", err)
 	}
 
@@ -121,7 +121,7 @@ func TestLocalRunner_Run_NoClient_Errors(t *testing.T) {
 	r := &LocalRunner{LogDir: t.TempDir()}
 	tt := &task.Task{ID: "x", Agent: task.AgentConfig{Instructions: "hi"}}
 	exec := &storage.Execution{ID: "exec-x"}
-	err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID, exec))
+	err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID))
 	if err == nil || !strings.Contains(err.Error(), "no LLM client") {
 		t.Errorf("expected 'no LLM client' error, got %v", err)
 	}
@@ -134,7 +134,7 @@ func TestLocalRunner_Run_EmptyInstructions_Errors(t *testing.T) {
 	}
 	tt := &task.Task{ID: "x", Agent: task.AgentConfig{}}
 	exec := &storage.Execution{ID: "exec-x"}
-	err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID, exec))
+	err := r.Run(context.Background(), tt, exec, newStoreChannel(nil, tt.ID))
 	if err == nil || !strings.Contains(err.Error(), "empty instructions") {
 		t.Errorf("expected empty-instructions error, got %v", err)
 	}