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_provider_smoke.py

@@ -0,0 +1,26 @@
+from app.ports.model_providers import ModelProviderError, ProviderErrorKind
+from app.tools.provider_smoke import failed_probe
+
+
+def test_failed_probe_only_exposes_sanitized_provider_fields() -> None:
+    error = ModelProviderError(
+        operation="embedding.create",
+        kind=ProviderErrorKind.AUTHENTICATION,
+        status_code=401,
+        provider_code="invalid_api_key",
+        request_id="req-safe-1",
+    )
+
+    result = failed_probe("embedding", error)
+
+    assert result.error_kind == "authentication"
+    assert result.status_code == 401
+    assert result.request_id == "req-safe-1"
+    assert "invalid_api_key" not in repr(result)
+
+
+def test_unexpected_error_is_reduced_to_fixed_category() -> None:
+    result = failed_probe("chat", RuntimeError("sensitive content"))
+
+    assert result.error_kind == "internal_contract_error"
+    assert "sensitive content" not in repr(result)