agent-loop: Skald adapters behind the crate traits (phase 1)

New skald-core::loop_adapters module — implements the agent-loop trait
surface over existing infrastructure, unused by the current loop (wired
in phase 2):

- SqliteHistory: HistoryStore over chat_sessions_stack/chat_history/
  chat_llm_tools/chat_summaries, no schema change; CallState maps 1:1 on
  the existing status strings; wire call ids synthesized as tc_{id}
- SkaldSelector: ModelSelector over LlmManager with the agent's strength
  captured per-turn (D14); DtlMode → ToolRendering mapping (D15)
- SkaldActivationSource + SkaldToolActivator: DTL catalog + persistence
  (activated_tools, anchored at the triggering message) behind the
  crate's protocol traits; unifies the grants/persistence split
- ApprovalGate: port of run_approval_gate (pre-approved, engine, fs
  fast-path, auto-deny, AwaitingHuman + block on human); a closed human
  channel maps to the new GateDecision::Suspend in agent-loop
- SkaldToolSet + CoreToolBridge/McpToolBridge: core-api and MCP tools
  run inside the crate's kernel (execution bridged, execute_cmd keeps
  its teardown; D7 MarkInterrupted for shell)
- agent-loop: re-export async_trait at root; EventSink::new made public

17 adapter tests green (temp-DB integration); full workspace suite green
(pre-existing honcho-client doc-test failure untouched: missing dev-deps).

crates/agent-loop/src/events.rs

@@ -123,7 +123,10 @@ pub struct EventSink {
 }
 
 impl EventSink {
-    pub(crate) fn new(conversation: ConversationId, tx: broadcast::Sender<Event<LoopEvent>>) -> Self {
+    /// Wrap a bus sender for one conversation. Public so hosts can build
+    /// sinks in their own tests and adapters; the kernel builds them via the
+    /// manager.
+    pub fn new(conversation: ConversationId, tx: broadcast::Sender<Event<LoopEvent>>) -> Self {
         Self { conversation, tx }
     }