feat(search): add semantic similar session matching via Voyage AI embeddings

Adds vector-based similar session discovery using the existing Voyage AI
embedding infrastructure and pgvector cosine similarity search.

- New AISessionEmbedding model with vector(1024) column
- session_embedding_service: generate + upsert embeddings, find similar sessions
- Embeddings generated on session create (from problem_summary/domain) and
  updated on resolve (adds resolution_summary)
- GET /ai-sessions/{id}/similar endpoint returns top-N similar sessions
- Migration a7c9e3b1f402 creates ai_session_embeddings table

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/alembic/versions/a7c9e3b1f402_add_ai_session_embeddings_table.py

@@ -0,0 +1,83 @@
+"""add ai_session_embeddings table for similar-session matching
+
+Revision ID: a7c9e3b1f402
+Revises: dbf67047d4c8
+Create Date: 2026-03-20
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+
+# revision identifiers, used by Alembic.
+revision: str = "a7c9e3b1f402"
+down_revision: Union[str, None] = "dbf67047d4c8"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # pgvector extension should already exist from migration 042
+    op.execute("CREATE EXTENSION IF NOT EXISTS vector")
+
+    op.create_table(
+        "ai_session_embeddings",
+        sa.Column(
+            "id",
+            postgresql.UUID(as_uuid=True),
+            primary_key=True,
+            server_default=sa.text("gen_random_uuid()"),
+        ),
+        sa.Column(
+            "session_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("ai_sessions.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column(
+            "account_id",
+            postgresql.UUID(as_uuid=True),
+            sa.ForeignKey("accounts.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("chunk_text", sa.Text(), nullable=False),
+        sa.Column(
+            "embedding_model",
+            sa.String(50),
+            nullable=False,
+            server_default="voyage-3.5",
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+        ),
+    )
+
+    # Add vector column via raw SQL (pgvector type not in SA dialect)
+    op.execute(
+        "ALTER TABLE ai_session_embeddings ADD COLUMN embedding vector(1024)"
+    )
+
+    op.create_index(
+        "ix_ai_session_embeddings_session_id",
+        "ai_session_embeddings",
+        ["session_id"],
+        unique=True,
+    )
+    op.create_index(
+        "ix_ai_session_embeddings_account_id",
+        "ai_session_embeddings",
+        ["account_id"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("ai_session_embeddings")