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/onboard/wizard.rs

@@ -274,8 +274,9 @@ fn memory_config_defaults_for_backend(backend: &str) -> MemoryConfig {
         embedding_provider: "none".to_string(),
         embedding_model: "text-embedding-3-small".to_string(),
         embedding_dimensions: 1536,
-        vector_weight: 0.7,
-        keyword_weight: 0.3,
+        vector_weight: 0.4,
+        keyword_weight: 0.6,
+        min_relevance_score: 0.4,
         embedding_cache_size: if profile.uses_sqlite_hygiene {
             10000
         } else {