Make the first RAG slice executable without risking production data

The Stage 1 foundation now proves provider contracts with mocks and validates PostgreSQL/pgvector ingestion, approval binding, retrieval, reranking, and idempotency using only synthetic data. Live Bailian validation remains gated on rotating the exposed key.

Constraint: The key shown in chat is compromised and cannot be used or committed

Rejected: Mark Stage 1 complete from mock and offline results | real three-model smoke is still required

Confidence: high

Scope-risk: moderate

Reversibility: clean

Directive: Do not enable real-data ingestion until Stage 3 cloud approval and outbound manifest controls are enforced end to end

Tested: make verify; 41 pytest tests; strict mypy; Ruff; Compose config; pinned image build; empty-volume migration; role denial; two idempotent 20-vector seeds; database restart persistence

Not-tested: Live Bailian calls require a newly rotated key; React product UI is not implemented

backend/tests/unit/test_seed_demo.py

@@ -0,0 +1,54 @@
+from pathlib import Path
+
+import pytest
+
+from app.adapters.fake import FakeEmbeddingProvider
+from app.core.config import Settings
+from app.tools.seed_demo import (
+    embed_in_batches,
+    embedding_profile_hash,
+    load_documents,
+    prepare_chunks,
+)
+
+PROJECT_ROOT = Path(__file__).resolve().parents[3]
+DOCUMENTS_PATH = PROJECT_ROOT / "data" / "samples" / "public" / "demo_documents.jsonl"
+
+
+@pytest.mark.asyncio
+async def test_seed_preparation_batches_and_hash_binds_twenty_documents() -> None:
+    documents = load_documents(DOCUMENTS_PATH)
+    settings = Settings()
+    provider = FakeEmbeddingProvider()
+    texts = [
+        f"标题：{item.title}\n地区：{item.region}\n矿种：{item.mineral}\n正文：{item.content}"
+        for item in documents
+    ]
+
+    vectors, model = await embed_in_batches(provider, texts)
+    chunks = prepare_chunks(
+        documents,
+        vectors,
+        profile_hash=embedding_profile_hash(settings, "fake"),
+        embedding_model=model,
+    )
+
+    assert len(chunks) == 20
+    assert all(len(item.vector) == 1024 for item in chunks)
+    assert all(item.embedding_text == item.embedding_prefix + item.cloud_text for item in chunks)
+    assert len({item.chunk_id for item in chunks}) == 20
+    assert all(len(item.outbound_manifest_sha256) == 64 for item in chunks)
+
+
+def test_seed_rejects_fixture_not_explicitly_marked_synthetic(tmp_path: Path) -> None:
+    path = tmp_path / "documents.jsonl"
+    path.write_text(
+        '{"doc_id":"x","title":"x","content":"x","region":"x",'
+        '"mineral":"x","page_no":1,"source_type":"unknown",'
+        '"review_state":"LOCAL_PARSED_PENDING_CLOUD_REVIEW",'
+        '"cloud_policy_id":"synthetic-demo-v1"}\n',
+        encoding="utf-8",
+    )
+
+    with pytest.raises(ValueError, match="non_synthetic_document"):
+        load_documents(path)