feat(rag): feed whole matched documents to the LLM — no context truncation (A7 revised)

tests/e2e/mock_llm.py

@@ -26,6 +26,11 @@ Implements just enough of the aipi surface:
   - system prompt containing ``<tuning>`` (phase 15, steering notes) ->
     the composed answer ends with `` (tuning: <first note line>)`` —
     makes prompt injection observable in the UI deterministically.
+  - user message containing ``show the end of your notes`` (phase 24,
+    whole-document context) -> the answer quotes the **last 160 chars of
+    the document context** — a tail echo, byte-stable across runs, so a
+    sentinel placed at the *end* of a document appears in the rendered
+    answer iff the whole document was in the prompt.
 
   ``max_tokens`` is honored deterministically (token ≈ whitespace word),
   like a real endpoint: an answer longer than the cap is truncated. This
@@ -104,6 +109,13 @@ THINKING_TRIGGER = "think out loud"
 SLOW_PRETOKEN_TRIGGER = "think out loud then hesitate"
 PRE_CONTENT_PAUSE_S = 4.0
 
+#: Phase 24 (whole-document-context story): a user message containing this
+#: substring (case-insensitive) gets an answer quoting the TAIL of the
+#: document context (see the module docstring). Verified 2026-08-24: no
+#: existing E2E question or fixture file contains the phrase, so every
+#: other suite is unaffected.
+END_OF_NOTES_TRIGGER = "show the end of your notes"
+
 
 def long_answer() -> str:
     """~900-word deterministic walkthrough (phase 11): numbered steps plus
@@ -151,6 +163,16 @@ def compose_answer(body: dict[str, Any]) -> str:
             "kubernetes, backups, or deploying a new service — I know those inside out. "
             "You've got this!"
         )
+    elif END_OF_NOTES_TRIGGER in user.lower():
+        # Whole-document-context story (phase 24): echo the tail of the
+        # context. Byte-stable across runs — a sentinel on the document's
+        # last line appears in the answer iff the whole document was in
+        # the prompt. (The tail includes the closing </documents> —
+        # harmless for the E2E sentinel assertions.)
+        answer = (
+            f"…and the very end of my notes reads: “{_context(body)[-160:]}” "
+            "(Deterministic mock answer for E2E.)"
+        )
     else:
         ctx = _context(body)
         snippet = ctx[:220].replace("\n", " ").strip()