fix: merge_agent_work blocks until complete instead of requiring polling

The mergemaster agent was burning all 30 turns polling get_merge_status
every 2 seconds while the merge pipeline takes ~2 minutes. It would
exhaust turns, exit, restart, and repeat — never seeing the result.

merge_agent_work now blocks with a 10-second internal poll loop and
returns the final result directly. The agent calls it once and gets
the answer. No more polling turns wasted.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

server/src/http/mcp/qa_tools.rs

@@ -46,10 +46,12 @@ pub(super) async fn tool_approve_qa(args: &Value, ctx: &AppContext) -> Result<St
 
     let project_root = ctx.agents.get_project_root(&ctx.state)?;
 
-    // Clear review_hold in content store + CRDT before moving.
-    if let Some(contents) = crate::db::read_content(story_id) {
-        let updated = crate::io::story_metadata::clear_front_matter_field_in_content(&contents, "review_hold");
-        crate::db::write_item_with_content(story_id, "3_qa", &updated);
+    // Clear review_hold before moving
+    let qa_path = project_root
+        .join(".huskies/work/3_qa")
+        .join(format!("{story_id}.md"));
+    if qa_path.exists() {
+        let _ = crate::io::story_metadata::clear_front_matter_field(&qa_path, "review_hold");
     }
 
     // Move story from work/3_qa/ to work/4_merge/