feat(story-62): add permission request prompts to web UI

When Claude Code requires user approval before executing a tool (file
writes, commits, etc.) the agent sends a permission_request message
over the WebSocket.  The web UI now intercepts that message, surfaces a
modal dialog showing the tool name and input, and lets the user approve
or deny.  The decision is sent back as a permission_response, allowing
the agent to continue or adjust its approach.

Backend changes:
- claude_code.rs: parse "permission_request" NDJSON events from the PTY,
  block the PTY thread via a sync channel, and write the user's decision
  back to the PTY stdin as a JSON permission_response.
- chat.rs: thread an optional UnboundedSender<PermissionReqMsg> through
  to the provider.
- ws.rs: create a permission-request channel, forward requests to the
  client, collect responses via a pending-perms map, and interleave all
  of this with the active chat session using tokio::select!.

Frontend changes:
- client.ts: add permission_request to WsResponse, permission_response
  to WsRequest, onPermissionRequest handler to ChatWebSocket.connect(),
  and sendPermissionResponse() method.
- types.ts: mirror the same type additions.
- Chat.tsx: add permissionRequest state, wire onPermissionRequest
  callback, and render an approval modal with tool name, input context,
  Approve and Deny buttons.

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

.story_kit/work/2_current/62_story_allow_frontend_ui_to_accept_permissions_requests.md

@@ -0,0 +1,26 @@
+---
+name: Agent Permission Prompts in Web UI
+test_plan: pending
+---
+
+# Story 62: Agent Permission Prompts in Web UI
+
+## User Story
+
+As a user interacting with an agent through the web UI, I want to be prompted for permission approvals (e.g. file writes, commits) so that the agent can complete tasks that require elevated permissions without getting blocked.
+
+Right now, the web UI does not have any way of the user allowing permissions requests, so dev processes are basically blocked. 
+
+## Acceptance Criteria
+
+- [ ] When an agent action requires permission (e.g. writing to a file, committing), the web UI surfaces a prompt to the user
+- [ ] The user can approve or deny the permission request from the UI
+- [ ] On approval, the agent continues with the requested action
+- [ ] On denial, the agent receives the denial and adjusts its approach
+- [ ] Permission prompts display enough context (file path, action type) for the user to make an informed decision
+
+
+## Out of Scope
+
+- Bulk/blanket permission grants (e.g. "allow all writes to this directory")
+- Persisting permission decisions across sessions