fix(agent): use config max_tool_iterations, add memory relevance filtering, rebalance search weights

Three fixes for conversation quality issues:

1. loop_.rs and channels now read max_tool_iterations from AgentConfig
   instead of using a hardcoded constant of 10, making it configurable.

2. Memory recall now filters entries below a configurable
   min_relevance_score threshold (default 0.4), preventing unrelated
   memories from bleeding into conversation context.

3. Default hybrid search weights rebalanced from 70/30 vector/keyword
   to 40/60, reducing cross-topic semantic bleed.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/agent/agent.rs

@@ -271,7 +271,10 @@ impl Agent {
             .memory(memory)
             .observer(observer)
             .tool_dispatcher(tool_dispatcher)
-            .memory_loader(Box::new(DefaultMemoryLoader::default()))
+            .memory_loader(Box::new(DefaultMemoryLoader::new(
+                5,
+                config.memory.min_relevance_score,
+            )))
             .prompt_builder(SystemPromptBuilder::with_defaults())
             .config(config.agent.clone())
             .model_name(model_name)