timestamp sanitization, CoT logging, reasoning field fix, persistent queue

- store/types.rs: sanitize timestamps on capnp load — old records had
  raw offsets instead of unix epoch, breaking sort-by-timestamp queries
- agents/api.rs: drain reasoning tokens from UI channel into LLM logs
  so we can see Qwen's chain-of-thought in agent output
- agents/daemon.rs: persistent task queue (pending-tasks.jsonl) —
  tasks survive daemon restarts. Push before spawn, remove on completion,
  recover on startup.
- api/openai.rs: only send reasoning field when explicitly configured,
  not on every request (fixes vllm warning)
- api/mod.rs: add 600s total request timeout as backstop for hung
  connections
- Cargo.toml: enable tokio-console feature for task introspection

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

poc-agent/src/api/mod.rs

@@ -39,6 +39,7 @@ impl ApiClient {
     pub fn new(base_url: &str, api_key: &str, model: &str) -> Self {
         let client = Client::builder()
             .connect_timeout(Duration::from_secs(30))
+            .timeout(Duration::from_secs(600))
             .build()
             .expect("failed to build HTTP client");
 

poc-agent/src/api/openai.rs

@@ -30,10 +30,14 @@ pub async fn stream(
         max_tokens: Some(16384),
         temperature: Some(0.6),
         stream: Some(true),
-        reasoning: Some(ReasoningConfig {
-            enabled: reasoning_effort != "none",
-            effort: Some(reasoning_effort.to_string()),
-        }),
+        reasoning: if reasoning_effort != "none" && reasoning_effort != "default" {
+            Some(ReasoningConfig {
+                enabled: true,
+                effort: Some(reasoning_effort.to_string()),
+            })
+        } else {
+            None
+        },
         chat_template_kwargs: None,
     };