Add agent memory: linked note store, MCP server, recall hook, and graph UI

The distilled knowledge layer over the raw log/transcript history, inspired by
TencentDB-Agent-Memory's memory-hub model, adapted to handler's invariants
(state lives only in the database; workers stay stateless and disposable):

- memory_notes + memory_links tables (migration 0014) with a portable DAL:
  scoped listing/search (project + global), idempotent linking, and a one-read
  graph. Deleting an agent nulls attribution but keeps its notes; deleting a
  project removes its notes and edges, leaving global knowledge intact.
- /memory API routes: reads on the normal token, note/link authoring on the
  admin token, plus GET /memory/graph for the dashboard.
- Bundled handler-memory MCP server (python -m handler.mcpserver), a
  dependency-free stdio JSON-RPC implementation injected into every launch's
  --mcp-config ahead of the DB connectors and allowlisted in generated
  settings, exposing memory_search / memory_get / memory_save / memory_link.
  Identity and DATABASE_URL arrive via the spawn env, same as hooks.
- SessionStart recall hook: injects the most recent notes in scope as
  additional context at session start, best-effort, never blocking.
- Memory page in the web UI: a hand-rolled force-directed SVG graph of the
  note web (colored by kind, hover highlights, click-through details), plus
  note/link authoring — the app's first visualization, no chart dependency.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WYqkoYPX8NAo1V2KyXr1pk

tests/test_control_spawn.py

@@ -79,11 +79,17 @@ def test_spawn_creates_agent_settings_and_run(env, fake_launch):
     with get_engine().begin() as conn:
         assert repo.get_agent_by_name(conn, "proj", "api")["id"] == agent["id"]
 
-    # settings.json wires all four hook events AND the headless permission allowlist
+    # settings.json wires all five hook events AND the headless permission allowlist
     # (claude -p auto-denies anything that would prompt; the allowlist is what lets
     # normal work proceed — the hooks stay the hard gate).
     settings = json.loads((root / ".claude" / "settings.json").read_text())
-    assert set(settings["hooks"]) == {"Stop", "SessionEnd", "PreToolUse", "Notification"}
+    assert set(settings["hooks"]) == {
+        "Stop",
+        "SessionEnd",
+        "SessionStart",
+        "PreToolUse",
+        "Notification",
+    }
     pre = settings["hooks"]["PreToolUse"][0]
     assert pre["matcher"] == "AskUserQuestion|Bash"
     assert "handler.hooks pre_tool_use" in pre["hooks"][0]["command"]