feat(rag): 新增 ImpactRAG 索引/检索服务（含 index_dir）

src/genesis/rag/impact_rag.py

@@ -0,0 +1,64 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import List, Tuple
+
+from genesis.rag.embeddings import Embedder
+from genesis.rag.store import RagStore
+
+_CHUNK = 800
+_TEXT_EXTS = {
+    ".java", ".py", ".js", ".ts", ".go", ".kt", ".scala", ".xml", ".yml",
+    ".yaml", ".md", ".txt", ".json", ".csv", ".sql", ".html", ".css", ".sh",
+}
+
+
+def _split(text: str, size: int = _CHUNK) -> List[str]:
+    paras = [p.strip() for p in text.split("\n") if p.strip()]
+    out, buf = [], ""
+    for p in paras:
+        if len(buf) + len(p) > size and buf:
+            out.append(buf)
+            buf = p
+        else:
+            buf = (buf + "\n" + p).strip()
+    if buf:
+        out.append(buf)
+    return out or [""]
+
+
+class ImpactRAG:
+    def __init__(self, store: RagStore, embedder: Embedder):
+        self.store = store
+        self.embedder = embedder
+
+    def index(self, scope: str, sources: List[Tuple[str, str]]) -> None:
+        chunks = []
+        for name, text in sources:
+            for piece in _split(text):
+                chunks.append(f"[{name}]\n{piece}")
+        embs = self.embedder.embed(chunks)
+        self.store.add(scope, chunks, embs)
+
+    def index_dir(self, scope: str, root: str) -> int:
+        """D1：索引目录内文本源文件（既有系统源码）。返回索引的片段数。"""
+        root_path = Path(root)
+        sources: List[Tuple[str, str]] = []
+        if root_path.is_dir():
+            for p in root_path.rglob("*"):
+                if p.is_file() and p.suffix.lower() in _TEXT_EXTS:
+                    try:
+                        text = p.read_text(encoding="utf-8", errors="ignore")
+                    except Exception:
+                        continue
+                    if text.strip():
+                        sources.append((str(p.relative_to(root_path)), text))
+        if sources:
+            self.index(scope, sources)
+        return len(sources)
+
+    def retrieve(self, scope: str, query: str, k: int = 5) -> List[str]:
+        if not query.strip():
+            return []
+        qv = self.embedder.embed([query])[0]
+        return self.store.search(scope, qv, k)

tests/test_impact_rag.py

@@ -0,0 +1,35 @@
+from genesis.rag.embeddings import FakeEmbedder
+from genesis.rag.store import RagStore
+from genesis.rag.impact_rag import ImpactRAG
+
+
+def test_retrieve_returns_relevant_chunk():
+    store = RagStore(":memory:")
+    try:
+        rag = ImpactRAG(store, FakeEmbedder())
+        sources = [
+            ("OrderController.java", "public class OrderController { 创建订单 }"),
+            ("UserAuth.java", "public class UserAuth { 用户登录认证 }"),
+        ]
+        rag.index("p1", sources)
+        res = rag.retrieve("p1", "OrderController 的影响范围", k=1)
+        assert res and "OrderController" in res[0]
+    finally:
+        store.close()
+
+
+def test_index_dir_reads_text_files(tmp_path):
+    (tmp_path / "src").mkdir()
+    (tmp_path / "src" / "OrderController.java").write_text(
+        "public class OrderController { 创建订单 }", encoding="utf-8"
+    )
+    (tmp_path / "src" / "binary.bin").write_bytes(b"\x00\x01")
+    store = RagStore(":memory:")
+    try:
+        rag = ImpactRAG(store, FakeEmbedder())
+        n = rag.index_dir("p1", str(tmp_path / "src"))
+        assert n == 1
+        res = rag.retrieve("p1", "OrderController 的影响范围", k=1)
+        assert res and "OrderController" in res[0]
+    finally:
+        store.close()