feat(rag): lite-model document summaries — non-markdown docs summarized at import, summary chunk retrieves and resolves to the full source doc

tests/fakes.py

@@ -2,6 +2,7 @@
 from __future__ import annotations
 
 from app.config import Settings
+from app.rag.llm import LLMError
 
 
 class FakeEmbedder:
@@ -9,7 +10,11 @@ class FakeEmbedder:
     ``Embedder`` protocol in :mod:`app.rag.importer`).
 
     Returns deterministic vectors of *dim* dimensions; records every call
-    so tests can assert batching behaviour.
+    so tests can assert batching behaviour. ``chat`` is the deterministic
+    ``lite``-model stand-in (phase 30): it returns
+    ``"Summary of <first token of the user content>"`` and raises
+    :class:`LLMError` when the content contains the sentinel word
+    ``SUMMARY-BLOWUP`` (drives the importer's fail-soft summary path).
     """
 
     def __init__(self, dim: int = 768) -> None:
@@ -17,8 +22,19 @@ class FakeEmbedder:
         self.settings = Settings(_env_file=None)  # pyright: ignore[reportCallIssue]
         self.embed_batches = 0
         self.calls: list[list[str]] = []
+        self.chat_calls: list[list[dict[str, str]]] = []
 
     async def embed(self, texts: list[str]) -> list[list[float]]:
         self.calls.append(list(texts))
         self.embed_batches += 1
         return [[0.01 * (i % 97) for i in range(self.dim)] for _ in texts]
+
+    async def chat(
+        self, messages: list[dict[str, str]], model: str | None = None
+    ) -> str:
+        self.chat_calls.append(list(messages))
+        user = next((m["content"] for m in messages if m.get("role") == "user"), "")
+        if "SUMMARY-BLOWUP" in user:
+            raise LLMError("simulated lite-model failure (SUMMARY-BLOWUP sentinel)")
+        first = user.split()
+        return "Summary of " + (first[0] if first else "<empty>")