Implement tool approval, fix tool definition refresh, and wire embeddings

This commit addresses three critical issues from code review:

1. Tool approval enforcement: Tools declaring requires_approval() (shell,
   http, file write/patch, build_software) now gate execution. Adds
   PendingApproval struct, session-scoped auto-approved tools set, and
   approval flow with yes/no/always commands.

2. Tool definition refresh: Tool definitions now refresh each iteration
   in both chat and job loops, so newly built tools become visible
   immediately within the same session.

3. Worker tool call handling: Changed respond() to respond_with_tools()
   when select_tools returns empty, properly executing tool calls instead
   of formatting them as text.

Also includes prior work from the plan:
- Wire embeddings provider (OpenAI + NEAR AI) to workspace
- Load workspace system prompt (identity files) into LLM context
- Route heartbeat notifications through channel manager
- Enable auto-context compaction when threshold exceeded
- Refactor to config structs (AgentDeps, WorkerDeps, LlmCallRecord)
- Fix clippy warnings (saturating_sub, too_many_arguments)

Co-Authored-By: Claude Opus 4.5 <[email protected]>

src/channels/cli/render.rs

@@ -89,11 +89,7 @@ fn render_messages(frame: &mut Frame, app: &AppState, area: Rect) {
     // Calculate scroll - show most recent messages
     let visible_height = area.height.saturating_sub(2) as usize; // Account for borders
     let total_lines = lines.len();
-    let scroll_offset = if total_lines > visible_height {
-        total_lines - visible_height
-    } else {
-        0
-    };
+    let scroll_offset = total_lines.saturating_sub(visible_height);
 
     let text = Text::from(lines);
     let messages = Paragraph::new(text)