feat: async research tool - runs in background, returns immediately

The research tool now spawns the scout agent in a background tokio task
and returns immediately with a research_id placeholder. This allows the
agent to continue working while research runs (30-120 seconds).

Key changes:
- New PendingResearchManager for tracking async research tasks
- research tool returns immediately with placeholder containing research_id
- research_status tool to check progress of pending research
- Auto-injection of completed research at natural break points:
  - Start of each tool iteration (before LLM call)
  - Before prompting user in interactive mode
- /research CLI command to list all research tasks
- Updated system prompt to explain async behavior

The agent can:
- Continue with other work while research runs
- Check status with research_status tool
- Yield turn to user if results are critical before continuing

crates/g3-cli/src/interactive.rs

@@ -210,6 +210,14 @@ pub async fn run_interactive<W: UiWriter>(
         // Display context window progress bar before each prompt
         display_context_progress(&agent, &output);
 
+        // Check for completed research and inject into context
+        // This happens before prompting the user for input
+        let injected_count = agent.inject_completed_research();
+        if injected_count > 0 {
+            println!("📋 {} research result(s) ready - injected into context", injected_count);
+            println!();
+        }
+
         // Build prompt
         let prompt = build_prompt(in_multiline, agent_name, &active_project);