feat: Generation Page AI workflows + AI/Vector modules + exam session fixes

Generation Page (complete rebuild):
- Full production-parity exam generation wizard with 4 IELTS modules
- Reading: AI passage gen, 5 exercise types (MCQ, Fill, Write, T/F, Match)
- Listening: 4 section types, AI context gen, TTS audio gen (ElevenLabs)
- Writing: Task 1/2, AI instruction gen, word limits, marks
- Speaking: 3 parts, AI script gen, avatar video gen (7 avatars)
- Per-module config: timer, CEFR difficulty, access, approval, rubrics
- Exam submission workflow (draft/published)

Exam Structures:
- New encoach.exam.structure model + CRUD controller
- ExamStructuresPage wired to real API

AI Module (encoach_ai):
- OpenAI service, ElevenLabs TTS, AWS Polly, ELAI avatars
- AI settings model with Odoo config parameters
- 7 generation endpoints (passage, exercises, instructions, scripts, context)

Vector Module (encoach_vector):
- pgvector integration for RAG-based content search
- Embedding service with sentence-transformers

Exam Session Fixes:
- Fixed ExamSession.tsx field mapping (question_type→type, exam_title→title)
- Fixed submit payload to include attempt_id and answers
- Fixed normalizeType to handle null/undefined

Tested: 12/12 API tests passed, browser-verified with real OpenAI calls
Made-with: Cursor

custom_addons/encoach_ai/services/elevenlabs_service.py

@@ -0,0 +1,103 @@
+"""ElevenLabs text-to-speech service."""
+
+import logging
+import time
+
+_logger = logging.getLogger(__name__)
+
+try:
+    import requests as _requests
+except ImportError:
+    _requests = None
+
+ELEVENLABS_BASE = "https://api.elevenlabs.io/v1"
+
+DEFAULT_VOICES = {
+    "female_british": "21m00Tcm4TlvDq8ikWAM",  # Rachel
+    "male_british": "VR6AewLTigWG4xSOukaG",     # Arnold
+    "female_american": "EXAVITQu4vr4xnSDxMaL",  # Bella
+    "male_american": "TxGEqnHWrfWFTfGW9XjX",    # Josh
+}
+
+
+class ElevenLabsService:
+    """ElevenLabs TTS — higher quality multilingual voices."""
+
+    def __init__(self, env):
+        self.env = env
+        self._get_param = env["ir.config_parameter"].sudo().get_param
+
+    def _get_key(self):
+        key = self._get_param("encoach_ai.elevenlabs_api_key", "")
+        if not key:
+            import os
+            key = os.environ.get("ELEVENLABS_API_KEY", "")
+        if not key:
+            raise RuntimeError("ElevenLabs API key not configured — set in AI Settings")
+        return key
+
+    def _log(self, action, latency, status="success", error=None):
+        try:
+            self.env["encoach.ai.log"].sudo().create({
+                "service": "elevenlabs",
+                "action": action,
+                "latency_ms": latency,
+                "status": status,
+                "error_message": error,
+            })
+        except Exception:
+            pass
+
+    def synthesize(self, text, *, voice_id=None, voice_key="female_british",
+                   model=None, output_format="mp3_44100_128"):
+        """Convert text to speech using ElevenLabs.
+
+        Returns:
+            dict with 'audio' (bytes), 'content_type', 'voice_id', 'characters'
+        """
+        if not _requests:
+            raise RuntimeError("requests package not installed")
+        key = self._get_key()
+        voice_id = voice_id or DEFAULT_VOICES.get(voice_key, list(DEFAULT_VOICES.values())[0])
+        model = model or self._get_param("encoach_ai.elevenlabs_model", "eleven_multilingual_v2")
+
+        url = f"{ELEVENLABS_BASE}/text-to-speech/{voice_id}"
+        t0 = time.time()
+        try:
+            resp = _requests.post(
+                url,
+                json={
+                    "text": text,
+                    "model_id": model,
+                    "voice_settings": {"stability": 0.5, "similarity_boost": 0.75},
+                },
+                headers={"xi-api-key": key, "Accept": "audio/mpeg"},
+                params={"output_format": output_format},
+                timeout=60,
+            )
+            resp.raise_for_status()
+            latency = int((time.time() - t0) * 1000)
+            self._log("synthesize", latency)
+            return {
+                "audio": resp.content,
+                "content_type": "audio/mpeg",
+                "voice_id": voice_id,
+                "characters": len(text),
+            }
+        except Exception as exc:
+            self._log("synthesize", int((time.time() - t0) * 1000), "error", str(exc))
+            raise
+
+    def list_voices(self):
+        """List available ElevenLabs voices."""
+        key = self._get_key()
+        resp = _requests.get(
+            f"{ELEVENLABS_BASE}/voices",
+            headers={"xi-api-key": key},
+            timeout=15,
+        )
+        resp.raise_for_status()
+        return [
+            {"voice_id": v["voice_id"], "name": v["name"], "labels": v.get("labels", {})}
+            for v in resp.json().get("voices", [])
+        ]