feat(rag): steering notes — tune how Brain answers, stored in Postgres and injected into every system prompt

tests/e2e/mock_llm.py

@@ -15,6 +15,9 @@ Implements just enough of the aipi surface:
   - otherwise         -> upbeat answer quoting the provided document context
   - user message containing ``pretend to think slowly`` -> 3s warm-up delay
     (used by the loading-feedback story).
+  - 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.
 
   ``max_tokens`` is honored deterministically (token ≈ whitespace word),
   like a real endpoint: an answer longer than the cap is truncated. This
@@ -89,25 +92,54 @@ def long_answer() -> str:
     return "\n".join(lines)
 
 
+#: First numbered note line of a ``<tuning>`` section (phase 15).
+_TUNING_BLOCK_RE = re.compile(r"<tuning>\n(.*?)\n</tuning>", re.S)
+_NOTE_LINE_RE = re.compile(r"^\d+\.\s*(.+)$")
+
+
+def first_tuning_note(system: str) -> str | None:
+    """The first steering note in the system prompt, or ``None``.
+
+    The prompt numbers notes 1..N oldest-first (see
+    ``app.rag.prompts.build_steering_section``); the mock echoes the first
+    one into its answer so prompt injection is observable in the UI.
+    """
+    block = _TUNING_BLOCK_RE.search(system)
+    if not block:
+        return None
+    for line in block.group(1).splitlines():
+        m = _NOTE_LINE_RE.match(line.strip())
+        if m:
+            return m.group(1).strip()
+    return None
+
+
 def compose_answer(body: dict[str, Any]) -> str:
     system = _system(body)
     user = _user(body)
     if LONG_ANSWER_TRIGGER in user.lower():
-        return long_answer()
-    if "DEFLECT_MODE" in system:
-        return (
+        answer = long_answer()
+    elif "DEFLECT_MODE" in system:
+        answer = (
             "Ah — I haven't done anything like that, so I don't want to make stuff up! "
             "You're thinking bigger than my notes for a second. Try asking about "
             "kubernetes, backups, or deploying a new service — I know those inside out. "
             "You've got this!"
         )
-    ctx = _context(body)
-    snippet = ctx[:220].replace("\n", " ").strip()
-    return (
-        f"Great question — you've absolutely got this! Here's what my notes say about "
-        f"“{user.strip()[:80]}”: {snippet}… That's the gist from the docs; happy to "
-        "dig into any of it. (Deterministic mock answer for E2E.)"
-    )
+    else:
+        ctx = _context(body)
+        snippet = ctx[:220].replace("\n", " ").strip()
+        answer = (
+            f"Great question — you've absolutely got this! Here's what my notes say about "
+            f"“{user.strip()[:80]}”: {snippet}… That's the gist from the docs; happy to "
+            "dig into any of it. (Deterministic mock answer for E2E.)"
+        )
+    # Steering (phase 15): when the system prompt carries <tuning>, the
+    # answer ends with the first note — deterministically observable.
+    note = first_tuning_note(system)
+    if note:
+        answer = f"{answer} (tuning: {note})"
+    return answer
 
 
 @app.post("/__shutdown__")