Initial project import

2026-08-14 09:40:51 +03:00
parent 00040e5ce4
commit d7099bf80d
146 changed files with 30509 additions and 1055 deletions
@@ -0,0 +1,105 @@
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[2]
+sys.path.insert(0, str(ROOT / "scripts"))
+
+import embed_1c_code_vectors as worker  # noqa: E402
+
+
+def test_embed_pending_code_vectors_upserts_with_precondition(monkeypatch) -> None:
+    calls: list[tuple[str, dict]] = []
+
+    def fake_adapter_call(
+        adapter_url: str,
+        method: str,
+        payload: dict,
+        *,
+        timeout_seconds: int = 180,
+    ) -> dict:
+        calls.append((method, payload))
+        if method == "metadata.code_vector.pending":
+            assert payload["embedding_model"] == "local-hashing-v1"
+            assert payload["chunk_kinds"] == ["routine"]
+            assert payload["max_text_chars"] == 4000
+            return {
+                "status": "ok",
+                "chunks": [
+                    {
+                        "chunk_id": "chunk-1",
+                        "text_sha1": "a" * 40,
+                        "text": "Процедура РассчитатьНалог()",
+                    }
+                ],
+            }
+        if method == "metadata.code_vector.embedding.upsert":
+            assert payload["chunk_id"] == "chunk-1"
+            assert payload["text_sha1"] == "a" * 40
+            assert payload["embedding_model"] == "local-hashing-v1"
+            assert len(payload["embedding"]) == 16
+            return {"status": "ok", "dimensions": 16}
+        raise AssertionError(method)
+
+    monkeypatch.setattr(worker, "adapter_call", fake_adapter_call)
+
+    result = worker.embed_pending_code_vectors(
+        adapter_url="http://adapter/rpc",
+        base_id="upo_test",
+        limit=1,
+        dimensions=16,
+    )
+
+    assert result["status"] == "ok"
+    assert result["embedding"]["dimensions"] == 16
+    assert result["counts"] == {
+        "pending": 1,
+        "processed": 1,
+        "stored": 1,
+        "conflicts": 0,
+        "skipped": 0,
+        "errors": 0,
+    }
+    assert [method for method, _payload in calls] == [
+        "metadata.code_vector.pending",
+        "metadata.code_vector.embedding.upsert",
+    ]
+
+
+def test_embed_pending_code_vectors_dry_run_does_not_upsert(monkeypatch) -> None:
+    calls: list[str] = []
+
+    def fake_adapter_call(
+        adapter_url: str,
+        method: str,
+        payload: dict,
+        *,
+        timeout_seconds: int = 180,
+    ) -> dict:
+        calls.append(method)
+        return {
+            "status": "ok",
+            "chunks": [
+                {
+                    "chunk_id": "chunk-1",
+                    "text_sha1": "b" * 40,
+                    "text": "Функция НайтиОбъект()",
+                }
+            ],
+        }
+
+    monkeypatch.setattr(worker, "adapter_call", fake_adapter_call)
+
+    result = worker.embed_pending_code_vectors(
+        adapter_url="http://adapter/rpc",
+        base_id="upo_test",
+        dimensions=8,
+        dry_run=True,
+    )
+
+    assert result["counts"]["processed"] == 1
+    assert result["counts"]["stored"] == 0
+    assert result["upserts"][0]["status"] == "dry_run"
+    assert calls == ["metadata.code_vector.pending"]