feat: add agent selector to UI and support direct agent assignment

- Added an agent selector (Auto, Claude, Gemini) to the Start Next Task button.
- Updated the backend to pass query parameters as environment variables to scripts.
- Modified the executor pool to skip classification when a specific agent is requested.
- Added --agent flag to claudomator start command.
- Updated tests to cover the new functionality.

1 files changed, 17 insertions, 0 deletions

diff --git a/internal/api/server_test.go b/internal/api/server_test.go
index c90e3b3..2209a69 100644
--- a/internal/api/server_test.go
+++ b/internal/api/server_test.go
@@ -384,6 +384,23 @@ func TestRunTask_TimedOutTask_Returns202(t *testing.T) {
 	}
 }
 
+func TestRunTask_WithAgentParam(t *testing.T) {
+	srv, store := testServer(t)
+	createTaskWithState(t, store, "run-agent-param", task.StatePending)
+
+	// Request run with agent=gemini.
+	req := httptest.NewRequest("POST", "/api/tasks/run-agent-param/run?agent=gemini", nil)
+	w := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(w, req)
+
+	if w.Code != http.StatusAccepted {
+		t.Fatalf("status: want 202, got %d; body: %s", w.Code, w.Body.String())
+	}
+
+	// Wait for the task to complete via the mock runner.
+	pollState(t, store, "run-agent-param", task.StateReady, 2*time.Second)
+}
+
 func TestRunTask_CompletedTask_Returns409(t *testing.T) {
 	srv, store := testServer(t)
 	createTaskWithState(t, store, "run-completed", task.StateCompleted)