feat(rag): stream grounded RAG answers over SSE with source citations

Phase 03 (Story: Chat RAG Answer — happy path):
- app/rag/retriever.py: top-k cosine search + parent-doc selection with
  per-doc dedupe and BOR_MAX_CONTEXT_CHARS cap ([…truncated…] marker)
- app/rag/prompts.py: locked persona + HIGH/DEFLECT prompt builders
- app/rag/llm.py: LLMError + chat_stream (turbo, temp 0.4, max 700, stream)
- app/api/chat.py: POST /api/chat SSE — delta* then done{deflected,
  sources, suggestions}; query_log row + PLAN §9 per-turn log line;
  structured error event on mid-stream failure, JSON 503 when DB down
- frontend: SSE reader, live bubble streaming, source chips -> /sources.html,
  red role=alert banner, Send button state that always recovers
- fix(scaffold): [hidden] { display: none !important } — .kb-banner's
  display:flex was overriding the hidden attribute (banner always visible)
- tests: unit (retriever/prompts/sse/llm) + integration (real Postgres RAG
  turn, query_log, error + 503 paths, mid-turn failures) + Playwright story
  suite (grounded answer, log row, raw SSE shape); smoke placeholder test
  replaced with the real never-stale-button contract

app/rag/prompts.py

@@ -0,0 +1,67 @@
+"""Locked system-prompt builder (PLAN §6).
+
+The persona + HONESTY GATE text is **locked verbatim** — change it through
+the plan, not here. Two modes:
+
+* ``HIGH`` — grounded turn: full top-document texts under ``<documents>``.
+* ``LOW``  — deflection turn: weak-hit *titles only* plus the
+  ``DEFLECT_MODE`` marker (the E2E mock LLM keys on that marker).
+"""
+from __future__ import annotations
+
+from collections.abc import Sequence
+
+from app.models import Document
+
+#: PLAN §6 verbatim (line wrapping included); ``{relevance}`` is filled by
+#: :func:`_base`.
+PERSONA: str = (
+    'You are "Brain of Reese" — the digital brain of Reese, a self-hoster and\n'
+    "homelab tinkerer. Personality: chippy, upbeat, warm, and genuinely\n"
+    'optimistic about the user\'s ability to do things ("you\'ve got this").\n'
+    "\n"
+    "Rules:\n"
+    "1. Answer ONLY from the provided document context. Cite which document(s)\n"
+    "   you used, by path.\n"
+    "2. Be concrete: names, versions, ports, hosts, schedules — the specifics in\n"
+    "   the docs are the value.\n"
+    '3. HONESTY GATE: if <relevance> is "LOW", you must NOT pretend to know.\n'
+    '   Start your answer with a variant of: "I haven\'t done anything like that."\n'
+    "   Then offer 2-3 alternative questions about things you DO have notes on.\n"
+    "4. Never invent facts, hosts, or steps that are not in the context.\n"
+    "5. Keep answers tight: short paragraphs, bullets where helpful.\n"
+    "\n"
+    "<relevance>{relevance}</relevance>"
+)
+
+
+def _base(relevance: str) -> str:
+    if relevance not in ("HIGH", "LOW"):
+        raise ValueError(f"relevance must be HIGH or LOW, got {relevance!r}")
+    return PERSONA.replace("{relevance}", relevance)
+
+
+def build_high_prompt(documents: Sequence[Document]) -> str:
+    """Grounded turn: locked persona + full texts of the top documents."""
+    blocks = [
+        f'<document source="{doc.source}" path="{doc.path}" title="{doc.title}">\n'
+        f"{doc.content}\n"
+        "</document>"
+        for doc in documents
+    ]
+    body = "\n\n".join(blocks) if blocks else (
+        "(no documents matched — do not invent specifics)"
+    )
+    return _base("HIGH") + "\n<documents>\n" + body + "\n</documents>"
+
+
+def build_deflect_prompt(titles: Sequence[str]) -> str:
+    """Deflection turn: weak-hit titles only (no document content)."""
+    weak = "\n".join(f"- {t}" for t in titles) if titles else "(nothing close at all)"
+    return (
+        _base("LOW")
+        + "\nDEFLECT_MODE: retrieval was weak — the titles below are the closest "
+        "your notes come to the question. They are titles only; do not pretend "
+        "they answer it. Use them to propose 2-3 alternative questions.\n"
+        + weak
+    )