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_vector/models/__init__.py

@@ -0,0 +1 @@
+from . import embedding

custom_addons/encoach_vector/models/embedding.py

@@ -0,0 +1,121 @@
+"""Odoo model for storing vector embeddings via pgvector."""
+
+import json
+import logging
+from odoo import api, models, fields
+
+_logger = logging.getLogger(__name__)
+
+VECTOR_DIM = 384  # all-MiniLM-L6-v2 output dimension
+
+
+class EncoachEmbedding(models.Model):
+    _name = 'encoach.embedding'
+    _description = 'Vector Embedding'
+    _order = 'create_date desc'
+
+    content_type = fields.Selection([
+        ('course', 'Course'),
+        ('resource', 'Resource'),
+        ('question', 'Question'),
+        ('module', 'Module'),
+        ('topic', 'Topic'),
+        ('feedback', 'Feedback'),
+        ('generation_log', 'Generation Log'),
+    ], required=True, index=True)
+    content_id = fields.Integer(required=True, index=True)
+    content_text = fields.Text()
+    metadata_json = fields.Text(default='{}')
+
+    _content_unique = models.Constraint(
+        'UNIQUE(content_type, content_id)',
+        'Each content item can only have one embedding.',
+    )
+
+    @api.model
+    def _auto_init(self):
+        res = super()._auto_init()
+        cr = self.env.cr
+        cr.execute("SELECT 1 FROM pg_extension WHERE extname = 'vector'")
+        if not cr.fetchone():
+            try:
+                cr.execute("CREATE EXTENSION IF NOT EXISTS vector")
+                _logger.info("pgvector extension created")
+            except Exception:
+                _logger.warning(
+                    "Could not create pgvector extension — run "
+                    "'CREATE EXTENSION vector' as a superuser",
+                    exc_info=True,
+                )
+                return res
+
+        cr.execute("""
+            SELECT column_name FROM information_schema.columns
+            WHERE table_name = 'encoach_embedding' AND column_name = 'embedding'
+        """)
+        if not cr.fetchone():
+            cr.execute(
+                f"ALTER TABLE encoach_embedding ADD COLUMN embedding vector({VECTOR_DIM})"
+            )
+            cr.execute(
+                "CREATE INDEX IF NOT EXISTS encoach_embedding_vec_idx "
+                "ON encoach_embedding USING ivfflat (embedding vector_cosine_ops) "
+                "WITH (lists = 100)"
+            )
+            _logger.info("Vector column and index created on encoach_embedding")
+        return res
+
+    def set_embedding(self, vector):
+        """Store a vector embedding for this record."""
+        self.ensure_one()
+        vec_str = '[' + ','.join(str(v) for v in vector) + ']'
+        self.env.cr.execute(
+            "UPDATE encoach_embedding SET embedding = %s WHERE id = %s",
+            (vec_str, self.id),
+        )
+
+    @api.model
+    def cron_reindex(self):
+        """Cron entry point for periodic re-indexing."""
+        from odoo.addons.encoach_vector.services.indexer import index_all
+        return index_all(self.env)
+
+    @api.model
+    def similarity_search(self, query_vector, *, content_type=None, limit=10):
+        """Find similar embeddings using cosine distance."""
+        vec_str = '[' + ','.join(str(v) for v in query_vector) + ']'
+        where = "WHERE embedding IS NOT NULL"
+        params = [vec_str, limit]
+        if content_type:
+            where += " AND content_type = %s"
+            params = [vec_str, content_type, limit]
+
+        query = f"""
+            SELECT id, content_type, content_id, content_text, metadata_json,
+                   1 - (embedding <=> %s::vector) AS similarity
+            FROM encoach_embedding
+            {where}
+            ORDER BY embedding <=> %s::vector
+            LIMIT %s
+        """
+        if content_type:
+            self.env.cr.execute(query, (vec_str, content_type, vec_str, limit))
+        else:
+            self.env.cr.execute(query, (vec_str, vec_str, limit))
+
+        results = []
+        for row in self.env.cr.dictfetchall():
+            metadata = {}
+            try:
+                metadata = json.loads(row['metadata_json'] or '{}')
+            except (json.JSONDecodeError, TypeError):
+                pass
+            results.append({
+                'id': row['id'],
+                'content_type': row['content_type'],
+                'content_id': row['content_id'],
+                'text': row['content_text'],
+                'metadata': metadata,
+                'similarity': round(row['similarity'], 4),
+            })
+        return results