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/driver/mod.rs

@@ -60,6 +60,15 @@ pub struct CompletionRequest {
     pub stop: Vec<String>,
     /// Enable streaming
     pub stream: bool,
+    /// Enable extended thinking/reasoning
+    #[serde(default)]
+    pub thinking_enabled: bool,
+    /// Reasoning effort level (for providers that support it)
+    #[serde(default)]
+    pub reasoning_effort: Option<String>,
+    /// Enable plan mode
+    #[serde(default)]
+    pub plan_mode: bool,
 }
 
 impl Default for CompletionRequest {
@@ -73,27 +82,16 @@ impl Default for CompletionRequest {
             temperature: Some(0.7),
             stop: Vec::new(),
             stream: false,
+            thinking_enabled: false,
+            reasoning_effort: None,
+            plan_mode: false,
         }
     }
 }
 
-/// Tool definition for LLM
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct ToolDefinition {
-    pub name: String,
-    pub description: String,
-    pub input_schema: serde_json::Value,
-}
-
-impl ToolDefinition {
-    pub fn new(name: impl Into<String>, description: impl Into<String>, schema: serde_json::Value) -> Self {
-        Self {
-            name: name.into(),
-            description: description.into(),
-            input_schema: schema,
-        }
-    }
-}
+/// Tool definition for LLM function calling.
+/// Re-exported from `zclaw_types::tool::ToolDefinition` (canonical definition).
+pub use zclaw_types::tool::ToolDefinition;
 
 /// Completion response
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -110,7 +108,8 @@ pub struct CompletionResponse {
     pub stop_reason: StopReason,
 }
 
-/// Content block in response
+/// LLM driver response content block (subset of canonical zclaw_types::ContentBlock).
+/// Used internally by Anthropic/OpenAI/Gemini/Local drivers for API response parsing.
 #[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ContentBlock {