LLM call logging, plan persistence API, quote-to-feedback UX, requirement input improvements

- Add llm_call_log table and per-call timing/token tracking in agent loop
- New GET /workflows/{id}/plan endpoint to restore plan from snapshots on page load
- New GET /workflows/{id}/llm-calls endpoint + WS LlmCallLog broadcast
- Parse Usage from LLM API response (prompt_tokens, completion_tokens)
- Detailed mode toggle in execution log showing LLM call cards with phase/tokens/latency
- Quote-to-feedback: hover quote buttons on plan steps and log entries, multi-quote chips in comment input
- Requirement input: larger textarea, multi-line display with pre-wrap and scroll

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

src/llm.rs

@@ -67,9 +67,20 @@ pub struct ToolCallFunction {
     pub arguments: String,
 }
 
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Usage {
+    #[serde(default)]
+    pub prompt_tokens: u32,
+    #[serde(default)]
+    pub completion_tokens: u32,
+    #[serde(default)]
+    pub total_tokens: u32,
+}
+
 #[derive(Debug, Deserialize)]
 pub struct ChatResponse {
     pub choices: Vec<ChatChoice>,
+    pub usage: Option<Usage>,
 }
 
 #[derive(Debug, Deserialize)]