feat: transcription & AI - Whisper, summaries, task extraction (#39)

Part 4/4 of audio recording feature stack.

## Changes
- OpenAI Whisper transcription (gpt-4o-mini-transcribe)
- Auto-generate 3-7 word summaries (GPT-4o-mini)
- Extract actionable tasks from transcripts
- TranscriptionSection UI component
- SettingsPanel for OpenAI key management
- Secure API key storage in authStore
- 25MB file size limit handling

## Stack
- PR 1/4: Foundation
- PR 2/4: Recording service
- PR 3/4: Recording UI
- **PR 4/4: Transcription & AI** ← You are here

## Review notes
Completes the feature. Focus on AI prompts, error handling, and API key security.

Author: lucasheriques

src/main/index.ts

@@ -13,7 +13,7 @@ import { registerAgentIpc, type TaskController } from "./services/agent.js";
 import { registerFsIpc } from "./services/fs.js";
 import { registerOsIpc } from "./services/os.js";
 import { registerPosthogIpc } from "./services/posthog.js";
-import { registerRecordingIpc } from "./services/recording-notranscribe.js";
+import { registerRecordingIpc } from "./services/recording.js";
 
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);