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/crdt_state.rs

@@ -3,7 +3,7 @@
 /// The CRDT document is the primary source of truth for pipeline item
 /// metadata (stage, name, agent, etc.).  CRDT ops are persisted to SQLite so
 /// state survives restarts.  The filesystem `.huskies/work/` directories are
-/// no longer written to — all state lives in the CRDT and DB content store.
+/// still updated as a secondary output for backwards compatibility.
 ///
 /// Stage transitions detected by `write_item()` are broadcast as [`CrdtEvent`]s
 /// so subscribers (auto-assign, WebSocket, notifications) can react without