feat: behind-the-scenes 👍/👎 rating system (fine-tune data collection)

Brian can rate Lyra's outputs as he uses her; each rating is stored as a
(context, content, rating) triple — the shape a future fine-tune / preference
dataset wants, collected passively during real use.

- memory: ratings table + add_rating (upsert: one row per item, re-rating
  replaces), list_ratings, rating_counts
- server: POST /rate, GET /ratings/counts, GET /ratings/export (JSONL download)
- chat UI: subtle 👍/👎 on each assistant reply, captures the prompting message
  as context
- journal/reflection UI: 👍/👎 on each thought
- tests: counts + upsert-replace behavior

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/memory.py

@@ -92,6 +92,21 @@ CREATE TABLE IF NOT EXISTS journal (
     source TEXT
 );
 CREATE INDEX IF NOT EXISTS idx_journal_created ON journal(created_at);
+
+-- Brian's behind-the-scenes feedback on Lyra's outputs (chat replies, reflections,
+-- journal/metacognition). Stored as (context, content, rating) — the shape a future
+-- fine-tune / preference dataset wants. One row per rated item (re-rating updates it).
+CREATE TABLE IF NOT EXISTS ratings (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    created_at TEXT NOT NULL,
+    kind TEXT NOT NULL,        -- chat | reflection | metacognition | journal
+    rating INTEGER NOT NULL,   -- +1 (good / want more) or -1 (off / want less)
+    content TEXT NOT NULL,     -- the rated output
+    context TEXT,              -- what prompted it (e.g. the user message for a chat reply)
+    ref TEXT,                  -- optional source id (journal id, session id, ...)
+    note TEXT
+);
+CREATE INDEX IF NOT EXISTS idx_ratings_created ON ratings(created_at);
 """
 
 _conn: sqlite3.Connection | None = None
@@ -542,6 +557,41 @@ def add_journal_entry(kind: str, content: str, source: str | None = None) -> int
     return int(cur.lastrowid)
 
 
+def add_rating(kind: str, rating: int, content: str, context: str | None = None,
+               ref: str | None = None, note: str | None = None) -> int:
+    """Record (or replace) Brian's feedback on one Lyra output. One row per item:
+    re-rating the same content updates it. Returns row id."""
+    now = datetime.now(timezone.utc).isoformat()
+    conn = _connection()
+    with conn:
+        conn.execute("DELETE FROM ratings WHERE kind = ? AND content = ?", (kind, content))
+        cur = conn.execute(
+            "INSERT INTO ratings (created_at, kind, rating, content, context, ref, note) "
+            "VALUES (?, ?, ?, ?, ?, ?, ?)",
+            (now, kind, 1 if rating >= 0 else -1, content, context,
+             str(ref) if ref is not None else None, note),
+        )
+    return int(cur.lastrowid)
+
+
+def list_ratings(limit: int | None = None) -> list[dict]:
+    conn = _connection()
+    sql = "SELECT id, created_at, kind, rating, content, context, ref, note FROM ratings ORDER BY id DESC"
+    if limit is not None:
+        sql += f" LIMIT {int(limit)}"
+    return [dict(r) for r in conn.execute(sql).fetchall()]
+
+
+def rating_counts() -> dict:
+    conn = _connection()
+    r = conn.execute(
+        "SELECT COUNT(*) AS total, "
+        "COALESCE(SUM(CASE WHEN rating > 0 THEN 1 ELSE 0 END), 0) AS up, "
+        "COALESCE(SUM(CASE WHEN rating < 0 THEN 1 ELSE 0 END), 0) AS down FROM ratings"
+    ).fetchone()
+    return {"total": r["total"], "up": r["up"], "down": r["down"]}
+
+
 def list_journal(limit: int | None = None, kinds: tuple[str, ...] | None = None) -> list[dict]:
     """Journal entries, newest first. Optionally filter by kind."""
     conn = _connection()

lyra/web/server.py

@@ -142,6 +142,32 @@ def create_app() -> FastAPI:
     async def journal_data(limit: int = 300) -> dict:
         return {"entries": memory.list_journal(limit=limit)}
 
+    @app.post("/rate")
+    async def rate(request: Request) -> dict:
+        """Record Brian's 👍/👎 on a Lyra output (chat reply, reflection, journal)."""
+        b = await request.json()
+        rating = int(b.get("rating", 0))
+        content = (b.get("content") or "").strip()
+        if not content or rating == 0:
+            return {"ok": False}
+        memory.add_rating(
+            kind=b.get("kind") or "chat", rating=rating, content=content,
+            context=(b.get("context") or None), ref=b.get("ref"), note=b.get("note"),
+        )
+        logbus.log("info", "rating", kind=b.get("kind"), rating=1 if rating >= 0 else -1)
+        return {"ok": True, "counts": memory.rating_counts()}
+
+    @app.get("/ratings/counts")
+    async def ratings_counts() -> dict:
+        return memory.rating_counts()
+
+    @app.get("/ratings/export")
+    async def ratings_export() -> Response:
+        """All ratings as JSONL — the seed for a future fine-tune / preference set."""
+        lines = "\n".join(json.dumps(r) for r in memory.list_ratings())
+        return Response(content=lines + ("\n" if lines else ""), media_type="application/x-ndjson",
+                        headers={"Content-Disposition": 'attachment; filename="lyra_ratings.jsonl"'})
+
     @app.get("/hand/{hand_id}")
     async def hand_page(hand_id: int) -> FileResponse:
         """Replayable hand-history viewer."""

lyra/web/static/index.html

@@ -354,12 +354,46 @@
     return out.join("\n");
   }
 
+	function addRateBar(div) {
+	  const bar = document.createElement("div");
+	  bar.className = "rate-bar";
+	  const up = document.createElement("button");
+	  up.className = "rate-btn"; up.textContent = "👍"; up.title = "Good — more like this";
+	  const down = document.createElement("button");
+	  down.className = "rate-btn"; down.textContent = "👎"; down.title = "Off — less like this";
+	  up.addEventListener("click", () => rateMessage(div, 1, up, down));
+	  down.addEventListener("click", () => rateMessage(div, -1, up, down));
+	  bar.appendChild(up); bar.appendChild(down);
+	  div.appendChild(bar);
+	}
+
+	function rateMessage(div, value, up, down) {
+	  // context = the nearest preceding user message
+	  let ctx = "", p = div.previousElementSibling;
+	  while (p) {
+	    if (p.classList && p.classList.contains("user")) { ctx = p.textContent; break; }
+	    p = p.previousElementSibling;
+	  }
+	  fetch(`${RELAY_BASE}/rate`, {
+	    method: "POST", headers: { "Content-Type": "application/json" },
+	    body: JSON.stringify({ kind: "chat", rating: value, content: div.dataset.raw || "", context: ctx, session_id: currentSession })
+	  }).catch(() => {});
+	  up.classList.toggle("rated", value === 1);
+	  down.classList.toggle("rated", value === -1);
+	}
+
 	function addMessage(role, text, autoScroll = true) {
 	  const messagesEl = document.getElementById("messages");
 
 	  const msgDiv = document.createElement("div");
 	  msgDiv.className = `msg ${role}`;
-	  if (role === "assistant") { msgDiv.innerHTML = renderMarkdown(text); } else { msgDiv.textContent = text; }
+	  if (role === "assistant") {
+	    msgDiv.innerHTML = renderMarkdown(text);
+	    msgDiv.dataset.raw = text;
+	    addRateBar(msgDiv);
+	  } else {
+	    msgDiv.textContent = text;
+	  }
 	  messagesEl.appendChild(msgDiv);
 
 	  // Auto-scroll to bottom if enabled

lyra/web/static/journal.html

@@ -52,6 +52,12 @@
     .time { color: var(--fade); font-size: .72rem; }
     .src  { color: var(--fade); font-size: .68rem; opacity: .7; }
     .text { font-size: .98rem; line-height: 1.55; }
+    .jrate { display: flex; gap: 8px; margin-top: 6px; opacity: .35; }
+    .entry:hover .jrate { opacity: .85; }
+    .jr { background: none; border: none; cursor: pointer; font-size: .85rem; padding: 2px 5px;
+          border-radius: 5px; filter: grayscale(.6); -webkit-tap-highlight-color: transparent; }
+    .jr:hover { filter: none; background: rgba(255,122,0,.12); }
+    .jr.rated { filter: none; background: rgba(255,122,0,.25); opacity: 1; }
     .empty { color: var(--fade); text-align: center; padding: 44px 16px; }
     .hidden { display: none !important; }
   </style>
@@ -115,12 +121,29 @@
               ${e.source ? `<span class="src">via ${esc(e.source)}</span>` : ''}
             </div>
             <div class="text">${esc(e.content)}</div>
+            <div class="jrate">
+              <button class="jr" data-id="${e.id}" data-val="1">👍</button>
+              <button class="jr" data-id="${e.id}" data-val="-1">👎</button>
+            </div>
           </div>
         </div>`;
       }
       root.innerHTML = html;
     }
 
+    // 👍/👎 on a thought -> /rate (fine-tune signal)
+    root.addEventListener('click', (ev) => {
+      const b = ev.target.closest('.jr'); if (!b) return;
+      const e = entries.find(x => String(x.id) === b.dataset.id); if (!e) return;
+      fetch('/rate', {
+        method: 'POST', headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ kind: e.kind, rating: Number(b.dataset.val), content: e.content, ref: e.id })
+      }).catch(() => {});
+      const bar = b.parentElement;
+      bar.querySelectorAll('.jr').forEach(x => x.classList.remove('rated'));
+      b.classList.add('rated');
+    });
+
     async function load(){
       try {
         const r = await fetch('/journal/data', { cache: 'no-store' });

lyra/web/static/style.css

@@ -994,3 +994,14 @@ select:hover {
   border-radius: 6px; padding: 10px 12px; margin: 8px 0; overflow-x: auto;
 }
 .msg.assistant pre code { background: none; padding: 0; font-size: 0.85em; }
+
+/* Behind-the-scenes 👍/👎 feedback (fine-tune signal) — subtle until hovered. */
+.rate-bar { display: flex; gap: 6px; margin-top: 7px; opacity: 0.3; transition: opacity .15s; }
+.msg.assistant:hover .rate-bar { opacity: 0.85; }
+.rate-btn {
+  background: none; border: none; cursor: pointer; font-size: 0.85rem;
+  padding: 2px 5px; border-radius: 5px; line-height: 1; filter: grayscale(0.6);
+  -webkit-tap-highlight-color: transparent;
+}
+.rate-btn:hover { filter: none; background: rgba(255,122,0,0.12); }
+.rate-btn.rated { filter: none; background: rgba(255,122,0,0.25); opacity: 1; }

tests/test_ratings.py

@@ -0,0 +1,28 @@
+"""Behind-the-scenes feedback storage (fine-tune signal)."""
+from __future__ import annotations
+
+import importlib
+
+import pytest
+
+
+@pytest.fixture
+def memory(tmp_path, monkeypatch):
+    monkeypatch.setenv("LYRA_DB_PATH", str(tmp_path / "t.db"))
+    from lyra import llm
+    monkeypatch.setattr(llm, "embed", lambda texts: [[0.1, 0.2, 0.3] for _ in texts])
+    import lyra.memory as m
+    importlib.reload(m)
+    return m
+
+
+def test_rating_counts_and_upsert(memory):
+    memory.add_rating("chat", 1, "good reply", context="hey")
+    memory.add_rating("reflection", -1, "repetitive thought")
+    assert memory.rating_counts() == {"total": 2, "up": 1, "down": 1}
+    assert any(r["context"] == "hey" for r in memory.list_ratings())
+
+    # re-rating the same content replaces the row (no duplicate; flips the rating)
+    memory.add_rating("chat", -1, "good reply")
+    assert memory.rating_counts() == {"total": 2, "up": 0, "down": 2}
+    assert any(r["content"] == "good reply" and r["rating"] == -1 for r in memory.list_ratings())