compaction: engine hook, failure policy, persistence (OPE-27 2/4)

Minimal engine footprint: a checkpoint at each iteration top (between tool
turns and before a new turn), the usage signal captured per round-trip
(context_tokens; chars/4 estimate when never reported), and
_outbound_messages consulting the boundary. The summarizer runs off-loop
through the normal provider router, so the Settings model pin is just an
id.

Failure policy per spec: retry once in both modes; attended sessions get
the Retry / Trim-oldest-10% prompt (via the ask_user plumbing, gated by an
is_attended callback the WS surface wires); unattended runs auto-trim and
continue — never parked on internal bookkeeping. Raw context-overflow 400s
from the main model route into the same policy, progress-guarded so a
still-overflowing model terminates in the error path.

CompactionState persists on the session record (new sqlite column, same
defensive parse as grants), so reloads keep the compacted view. A
persisted compacted notice + a new COMPACTED event mark the spot for
the GUI divider (rendered in commit 3).

coworker/server/app.py

@@ -1677,6 +1677,9 @@ def create_app(manager: SessionManager) -> FastAPI:
             )
             await ws.close()
             return
+        # Auto-compaction failure prompt (OPE-27): only an ATTENDED session may be asked
+        # Retry/Trim — unattended runs auto-trim (the policy in engine._compact_now).
+        engine.is_attended = lambda: _visibility() == VIS_INLINE
         await ws.send_json(
             {
                 "type": "ready",