feat(engine): Phase 6 — bridge adapters for main crate integration

Strategy C parallel deployment: when ENGINE_V2=true env var is set,
user messages route through the engine instead of the existing agentic
loop. All existing behavior is unchanged when the flag is off.

Bridge module (src/bridge/):
- LlmBridgeAdapter: wraps LlmProvider as engine LlmBackend, converts
  ThreadMessage↔ChatMessage, ActionDef↔ToolDefinition, depth-based
  model routing (primary vs cheap_llm)
- EffectBridgeAdapter: wraps ToolRegistry+SafetyLayer as EffectExecutor,
  routes tool calls through existing execute_tool_with_safety pipeline
- InMemoryStore: HashMap-backed Store impl (no DB tables needed yet)
- EngineRouter: is_engine_v2_enabled() + handle_with_engine() that
  builds engine from Agent deps and processes messages end-to-end

Integration touchpoint (4 lines in agent_loop.rs):
  After hook processing, before session resolution, check ENGINE_V2
  flag and route UserInput through the engine path.

Accessor visibility widened: llm(), cheap_llm(), safety(), tools()
changed from pub(super) to pub(crate) for bridge access.

85 engine tests + main crate clippy clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

src/lib.rs

@@ -42,6 +42,7 @@ pub mod agent;
 pub mod app;
 pub mod boot_screen;
 pub mod bootstrap;
+pub mod bridge;
 pub mod channels;
 pub mod cli;
 pub mod config;