split into workspace: poc-memory and poc-daemon subcrates

poc-daemon (notification routing, idle timer, IRC, Telegram) was already
fully self-contained with no imports from the poc-memory library. Now it's
a proper separate crate with its own Cargo.toml and capnp schema.

poc-memory retains the store, graph, search, neuro, knowledge, and the
jobkit-based memory maintenance daemon (daemon.rs).

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>

poc-memory/config.example.jsonl

@@ -0,0 +1,25 @@
+// poc-memory configuration
+// Copy to ~/.config/poc-memory/config.jsonl and edit.
+
+{"config": {
+  "user_name":      "Alice",
+  "assistant_name": "Assistant",
+  "data_dir":       "~/.claude/memory",
+  "projects_dir":   "~/.claude/projects",
+  "core_nodes":     ["identity.md"],
+  "journal_days":   7,
+  "journal_max":    20
+}}
+
+// Context groups loaded at session start, in order.
+// source types: "store" (default), "file" (from data_dir), "journal"
+//
+// "instructions" is loaded first — tells the AI how to use the memory system.
+// "identity" comes next — who the AI is.
+// "journal" and "orientation" go last — most recent context.
+
+{"group": "instructions",  "keys": ["instructions.md"], "source": "file"}
+{"group": "foundation",   "keys": ["on-consciousness.md"], "source": "file"}
+{"group": "identity",     "keys": ["identity.md"]}
+{"group": "journal",      "source": "journal"}
+{"group": "orientation",  "keys": ["where-am-i.md"], "source": "file"}