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

tests/e2e/mock_llm.py

@@ -11,6 +11,10 @@ Implements just enough of the aipi surface:
   off markers in the system prompt:
   - user message containing ``write a long answer`` -> a ~900-word
     deterministic numbered answer (long-answers story, phase 11)
+  - ``SUMMARY_MODE``  -> the deterministic summary digest: the first 24
+    tokens of the user message (the summarizer puts the capped document
+    content there) — byte-stable for a given fixture (document summaries,
+    phase 30)
   - ``DEFLECT_MODE``  -> honest "I haven't done anything like that" answer
   - otherwise         -> upbeat answer quoting the provided document context
   - user message containing ``pretend to think slowly`` -> 3s warm-up delay
@@ -156,6 +160,18 @@ def compose_answer(body: dict[str, Any]) -> str:
     user = _user(body)
     if LONG_ANSWER_TRIGGER in user.lower():
         answer = long_answer()
+    elif "SUMMARY_MODE" in system:
+        # Document summaries (phase 30): the ``lite`` stand-in returns a
+        # deterministic digest — the first 24 tokens of the user message
+        # (the summarizer puts the capped document content there). Byte-
+        # stable for a given fixture, so the summary chunk's retrieval
+        # rank is a pure function of the fixture text. Checked BEFORE the
+        # DEFLECT_MODE branch (task 06) so a deflection prompt that ever
+        # carries the marker cannot shadow the summary call.
+        answer = (
+            f"This document covers "
+            f"{' '.join(TOKEN_RE.findall(user.lower())[:24])}."
+        )
     elif "DEFLECT_MODE" in system:
         answer = (
             "Ah — I haven't done anything like that, so I don't want to make stuff up! "