refactor(crates): kernel/generation module split + DeerFlow optimizations + middleware + dead code cleanup

- Split zclaw-kernel/kernel.rs (1486 lines) into 9 domain modules
- Split zclaw-kernel/generation.rs (1080 lines) into 3 modules
- Add DeerFlow-inspired middleware: DanglingTool, SubagentLimit, ToolError, ToolOutputGuard
- Add PromptBuilder for structured system prompt assembly
- Add FactStore (zclaw-memory) for persistent fact extraction
- Add task builtin tool for agent task management
- Driver improvements: Anthropic/OpenAI extended thinking, Gemini safety settings
- Replace let _ = with proper log::warn! across SaaS handlers
- Remove unused dependency (url) from zclaw-hands

crates/zclaw-runtime/src/middleware/memory.rs

@@ -60,34 +60,39 @@ impl AgentMiddleware for MemoryMiddleware {
     fn priority(&self) -> i32 { 150 }
 
     async fn before_completion(&self, ctx: &mut MiddlewareContext) -> Result<MiddlewareDecision> {
-        // Skip memory injection for very short queries.
-        // Short queries (e.g., "1+6", "hi", "好") don't benefit from memory context.
-        // Worse, the retriever's scope-based fallback may return high-importance but
-        // irrelevant old memories, causing the model to think about past conversations
-        // instead of answering the current question.
-        // Use char count (not byte count) so CJK queries are handled correctly:
-        // a single Chinese char is 3 UTF-8 bytes but 1 meaningful character.
-        let query = ctx.user_input.trim();
-        if query.chars().count() < 2 {
-            tracing::debug!(
-                "[MemoryMiddleware] Skipping enhancement for short query ({:?}): no memory context needed",
-                query
-            );
-            return Ok(MiddlewareDecision::Continue);
-        }
+        tracing::debug!(
+            "[MemoryMiddleware] before_completion for query: {:?}",
+            ctx.user_input.chars().take(50).collect::<String>()
+        );
 
-        match self.growth.enhance_prompt(
-            &ctx.agent_id,
-            &ctx.system_prompt,
-            &ctx.user_input,
-        ).await {
+        // Retrieve relevant memories and inject into system prompt.
+        // The SqliteStorage retriever now uses FTS5-only matching — if FTS5 finds
+        // no relevant results, no memories are returned (no scope-based fallback).
+        // This prevents irrelevant high-importance memories from leaking into
+        // unrelated conversations.
+        let base = &ctx.system_prompt;
+        match self.growth.enhance_prompt(&ctx.agent_id, base, &ctx.user_input).await {
             Ok(enhanced) => {
-                ctx.system_prompt = enhanced;
+                if enhanced != *base {
+                    tracing::info!(
+                        "[MemoryMiddleware] Injected memories into system prompt for agent {}",
+                        ctx.agent_id
+                    );
+                    ctx.system_prompt = enhanced;
+                } else {
+                    tracing::debug!(
+                        "[MemoryMiddleware] No relevant memories found for query: {:?}",
+                        ctx.user_input.chars().take(50).collect::<String>()
+                    );
+                }
                 Ok(MiddlewareDecision::Continue)
             }
             Err(e) => {
-                // Non-fatal: memory retrieval failure should not block the loop
-                tracing::warn!("[MemoryMiddleware] Prompt enhancement failed: {}", e);
+                // Non-fatal: retrieval failure should not block the conversation
+                tracing::warn!(
+                    "[MemoryMiddleware] Memory retrieval failed (non-fatal): {}",
+                    e
+                );
                 Ok(MiddlewareDecision::Continue)
             }
         }