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>

web/src/ws.ts

@@ -34,12 +34,18 @@ export interface WsProjectUpdate {
   name: string
 }
 
+export interface WsLlmCallLog {
+  type: 'LlmCallLog'
+  workflow_id: string
+  entry: import('./types').LlmCallLogEntry
+}
+
 export interface WsError {
   type: 'Error'
   message: string
 }
 
-export type WsMessage = WsPlanUpdate | WsStepStatusUpdate | WsWorkflowStatusUpdate | WsRequirementUpdate | WsReportReady | WsProjectUpdate | WsError
+export type WsMessage = WsPlanUpdate | WsStepStatusUpdate | WsWorkflowStatusUpdate | WsRequirementUpdate | WsReportReady | WsProjectUpdate | WsLlmCallLog | WsError
 
 export type WsHandler = (msg: WsMessage) => void