feat(context): token-based compaction, persistent sessions, and LLM consolidation (#3574)

Comprehensive long-running context upgrades:

- Token-based compaction: replace message-count trigger with token
  estimation (~4 chars/token). Compaction fires when estimated tokens
  exceed max_context_tokens (default 32K) OR message count exceeds
  max_history_messages. Cuts at user-turn boundaries only.

- Persistent sessions: JSONL append-only session files per channel
  sender in {workspace}/sessions/. Sessions survive daemon restarts.
  Hydrates in-memory history from disk on startup.

- LLM-driven memory consolidation: two-phase extraction after each
  conversation turn. Phase 1 writes a timestamped history entry (Daily).
  Phase 2 extracts new facts/preferences to Core memory (if any).
  Replaces raw message auto-save with semantic extraction.

- New config fields: agent.max_context_tokens (32000),
  channels_config.session_persistence (true).

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/memory/mod.rs

@@ -1,6 +1,7 @@
 pub mod backend;
 pub mod chunker;
 pub mod cli;
+pub mod consolidation;
 pub mod embeddings;
 pub mod hygiene;
 pub mod lucid;