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, 4 insertions, 4 deletions

diff --git a/internal/executor/claude_test.go b/internal/executor/claude_test.go
index 0e76260..414f6cf 100644
--- a/internal/executor/claude_test.go
+++ b/internal/executor/claude_test.go
@@ -259,7 +259,7 @@ func TestClaudeRunner_Run_ResumeSetsSessionIDFromResumeSession(t *testing.T) {
 	}
 
 	// Run completes successfully (binary is "true").
-	_ = r.Run(context.Background(), tk, exec, newStoreChannel(nil, tk.ID, exec))
+	_ = r.Run(context.Background(), tk, exec, newStoreChannel(nil, tk.ID))
 
 	// SessionID must be the original session (ResumeSessionID), not the new
 	// exec's own ID. If it were exec.ID, a second blocked-then-resumed cycle
@@ -284,7 +284,7 @@ func TestClaudeRunner_Run_InaccessibleWorkingDir_ReturnsError(t *testing.T) {
 	}
 	exec := &storage.Execution{ID: "test-exec"}
 
-	err := r.Run(context.Background(), tk, exec, newStoreChannel(nil, tk.ID, exec))
+	err := r.Run(context.Background(), tk, exec, newStoreChannel(nil, tk.ID))
 
 	if err == nil {
 		t.Fatal("expected error for inaccessible working_dir, got nil")
@@ -732,7 +732,7 @@ func TestClaudeRunner_Run_ResumeUsesStoredSandboxDir(t *testing.T) {
 		SandboxDir:      sandboxDir,
 	}
 
-	_ = r.Run(context.Background(), tk, exec, newStoreChannel(nil, tk.ID, exec))
+	_ = r.Run(context.Background(), tk, exec, newStoreChannel(nil, tk.ID))
 
 	got, err := os.ReadFile(cwdFile)
 	if err != nil {
@@ -778,7 +778,7 @@ func TestClaudeRunner_Run_StaleSandboxDir_ClonesAfresh(t *testing.T) {
 		SandboxDir:      staleSandbox,
 	}
 
-	if err := r.Run(context.Background(), tk, e, newStoreChannel(nil, tk.ID, e)); err != nil {
+	if err := r.Run(context.Background(), tk, e, newStoreChannel(nil, tk.ID)); err != nil {
 		t.Fatalf("Run with stale sandbox: %v", err)
 	}