feat: web switch for her inner voice (Dolphin/3090 | Qwen-32B/MI50 | Off)

Her introspection (reflect/think) voice is now switchable live from the web
settings, read each cycle by the dream loop — so Brian can flip it off the 3090
before gaming without touching config or restarting.

- memory: runtime key/value settings table + get_setting/set_setting.
- self_state: INTROSPECTION_MODES (dolphin=local/dolphin3:8b, mi50=Qwen-32B,
  off=paused) + introspection_target()/set_introspection_mode(); default "dolphin".
  reflect() resolves from the live setting and SKIPS entirely when off.
- thoughts.think(): same resolution + skip-when-off.
- server: GET/POST /settings/introspection.
- index.html: "Inner Voice (introspection)" selector in Settings, applies instantly.
- tests: routing (dolphin/mi50), off-skip for think + reflect. Suite 77, ruff clean.

Default = Dolphin on the 3090 (richer voice). Flip to MI50 or Off in Settings
before gaming — that was the GPU-contention culprit.

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

lyra/memory.py

@@ -95,6 +95,12 @@ CREATE TABLE IF NOT EXISTS journal (
 );
 CREATE INDEX IF NOT EXISTS idx_journal_created ON journal(created_at);
 
+-- Small runtime key/value settings (UI-tunable, read live by the dream loop).
+CREATE TABLE IF NOT EXISTS settings (
+    key TEXT PRIMARY KEY,
+    value TEXT
+);
+
 -- 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).
@@ -639,6 +645,22 @@ def backfill_journal_embeddings(limit: int | None = None) -> int:
     return n
 
 
+def get_setting(key: str, default: str | None = None) -> str | None:
+    """A runtime setting value (UI-tunable), or `default` if unset."""
+    r = _connection().execute("SELECT value FROM settings WHERE key = ?", (key,)).fetchone()
+    return r["value"] if r else default
+
+
+def set_setting(key: str, value: str) -> None:
+    conn = _connection()
+    with conn:
+        conn.execute(
+            "INSERT INTO settings (key, value) VALUES (?, ?) "
+            "ON CONFLICT(key) DO UPDATE SET value = excluded.value",
+            (key, str(value)),
+        )
+
+
 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:

lyra/self_state.py

@@ -136,6 +136,36 @@ Respond with ONLY a JSON object — the same shape as the draft, plus "self_crit
 }"""
 
 
+# Her introspection (reflect/think) voice — switchable live from the web settings.
+# "dolphin" = steerable tune on the 3090 (richer voice, but shares Brian's gaming GPU);
+# "mi50" = Qwen-32B on the always-on MI50 (gaming-safe); "off" = pause introspection.
+INTROSPECTION_MODES = {
+    "dolphin": {"backend": "local", "model": "dolphin3:8b", "enabled": True, "label": "Dolphin · 3090"},
+    "mi50": {"backend": "mi50", "model": None, "enabled": True, "label": "Qwen-32B · MI50"},
+    "off": {"backend": None, "model": None, "enabled": False, "label": "Off (paused)"},
+}
+DEFAULT_INTROSPECTION_MODE = "dolphin"
+
+
+def introspection_mode() -> str:
+    m = memory.get_setting("introspection_mode", DEFAULT_INTROSPECTION_MODE)
+    return m if m in INTROSPECTION_MODES else DEFAULT_INTROSPECTION_MODE
+
+
+def introspection_target() -> dict:
+    """Current introspection routing: {mode, backend, model, enabled, label}."""
+    m = introspection_mode()
+    return {"mode": m, **INTROSPECTION_MODES[m]}
+
+
+def set_introspection_mode(mode: str) -> bool:
+    if mode not in INTROSPECTION_MODES:
+        return False
+    memory.set_setting("introspection_mode", mode)
+    logbus.log("info", "introspection mode set", mode=mode)
+    return True
+
+
 def load() -> dict:
     """Current self-state, or a copy of the default (not persisted until reflect).
 
@@ -240,9 +270,14 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     produces (reflections, the critique, and any deliberate journal note) is also
     appended to her permanent journal, tagged with `source`.
     """
-    cfg = config.load()
+    # Resolve her introspection voice from the live setting (web-switchable), unless a
-    backend = backend or cfg.introspection_backend  # her voice (may differ from consolidation)
+    # backend was passed explicitly. If introspection is switched off, skip entirely.
-    model = model or cfg.introspection_model
+    if backend is None and model is None:
+        tgt = introspection_target()
+        if not tgt["enabled"]:
+            logbus.log("info", "reflection skipped — introspection off")
+            return load()
+        backend, model = tgt["backend"], tgt["model"]
     state = load()
     state.setdefault("reflections", [])
     state.setdefault("metacognition", [])

lyra/thoughts.py

@@ -477,8 +477,14 @@ def think(backend: Backend | None = None, force_mode: str | None = None,
     """Advance the thought loop by one step. Returns a small report, or None on a
     parse miss. `force_mode` ('new'|'continue'|'respond') is mainly for tests."""
     cfg = config.load()
-    backend = backend or cfg.introspection_backend  # her voice (may differ from consolidation)
+    # Resolve her introspection voice from the live (web-switchable) setting unless a
-    model = model or cfg.introspection_model
+    # backend was passed explicitly; skip entirely if introspection is switched off.
+    if backend is None and model is None:
+        tgt = self_state.introspection_target()
+        if not tgt["enabled"]:
+            logbus.log("info", "thought skipped — introspection off")
+            return None
+        backend, model = tgt["backend"], tgt["model"]
     mode, thread = _pick("new" if force_mode == "react" else force_mode)
     state = self_state.load()
     react_item = None

lyra/web/server.py

@@ -243,6 +243,21 @@ def create_app() -> FastAPI:
     async def journal_data(limit: int = 300) -> dict:
         return {"entries": memory.list_journal(limit=limit)}
 
+    @app.get("/settings/introspection")
+    async def get_introspection() -> dict:
+        """Current introspection (her inner voice) routing + the available options."""
+        tgt = self_state.introspection_target()
+        return {"mode": tgt["mode"],
+                "options": [{"key": k, "label": v["label"]}
+                            for k, v in self_state.INTROSPECTION_MODES.items()]}
+
+    @app.post("/settings/introspection")
+    async def set_introspection(request: Request) -> dict:
+        """Switch her inner voice: dolphin (3090) | mi50 (gaming-safe) | off."""
+        b = await request.json()
+        ok = await asyncio.to_thread(self_state.set_introspection_mode, b.get("mode", ""))
+        return {"ok": ok, "mode": self_state.introspection_target()["mode"]}
+
     @app.get("/thoughts")
     async def thoughts_page() -> FileResponse:
         """Lyra's thought loop — threads she's been turning over, and a place to reply."""

lyra/web/static/index.html

@@ -169,6 +169,17 @@
           </select>
         </div>
 
+        <div class="settings-section" style="margin-top: 24px;">
+          <h4>Inner Voice (introspection)</h4>
+          <p class="settings-desc">Which model runs her reflections & thoughts (her dream loop).
+            Dolphin is richer but shares the 3090 — switch to MI50 or Off before gaming.</p>
+          <select id="introspectionMode">
+            <option value="dolphin">Dolphin · 3090 (richer voice)</option>
+            <option value="mi50">Qwen-32B · MI50 (gaming-safe)</option>
+            <option value="off">Off (pause her thinking)</option>
+          </select>
+        </div>
+
         <div class="settings-section" style="margin-top: 24px;">
           <h4>Session Management</h4>
           <p class="settings-desc">Manage your saved chat sessions:</p>
@@ -979,10 +990,31 @@
         }
       }
 
+      // Inner-voice (introspection) switch — applies instantly, read live by the dream loop.
+      const introspectionSel = document.getElementById("introspectionMode");
+      async function loadIntrospection() {
+        try {
+          const r = await fetch("/settings/introspection", { cache: "no-store" });
+          const d = await r.json();
+          if (d.mode) introspectionSel.value = d.mode;
+        } catch (e) {}
+      }
+      if (introspectionSel) {
+        introspectionSel.addEventListener("change", async () => {
+          try {
+            await fetch("/settings/introspection", {
+              method: "POST", headers: { "Content-Type": "application/json" },
+              body: JSON.stringify({ mode: introspectionSel.value })
+            });
+          } catch (e) {}
+        });
+      }
+
       // Show modal and load session list
       settingsBtn.addEventListener("click", () => {
         settingsModal.classList.add("show");
         loadSessionList(); // Refresh session list when opening settings
+        loadIntrospection(); // reflect the current inner-voice setting
       });
 
       // Sidebar "Settings" from another page navigates here with ?settings=1.

tests/test_reflect.py

@@ -99,6 +99,14 @@ def test_consolidation_rebuilds_narrative_from_reflections(lyra, monkeypatch):
     assert "steady" in out["relationship"]
 
 
+def test_reflect_skipped_when_introspection_off(lyra):
+    calls = lyra
+    from lyra import self_state
+    self_state.set_introspection_mode("off")
+    self_state.reflect()
+    assert calls == []          # paused -> no draft/examine LLM calls at all
+
+
 def test_consolidation_skips_with_too_few_reflections(lyra):
     from lyra import memory, self_state
     st = self_state.load()

tests/test_thoughts.py

@@ -275,10 +275,10 @@ def test_ping_salience_floor_is_optional(lyra, monkeypatch):
     assert th.maybe_ping(1, "hey", 0.8) is True
 
 
-def test_think_routes_to_introspection_backend(lyra, monkeypatch):
+def test_think_routes_to_selected_voice(lyra, monkeypatch):
+    from lyra import self_state
     _, th, box = lyra
-    monkeypatch.setenv("INTROSPECTION_BACKEND", "local")
+    self_state.set_introspection_mode("dolphin")
-    monkeypatch.setenv("INTROSPECTION_MODEL", "dolphin3:8b")
     seen = {}
 
     def cap(messages, backend="local", model=None):
@@ -290,6 +290,19 @@ def test_think_routes_to_introspection_backend(lyra, monkeypatch):
     th.think(force_mode="new")
     assert seen["backend"] == "local" and seen["model"] == "dolphin3:8b"
 
+    self_state.set_introspection_mode("mi50")     # gaming-safe: Qwen-32B on the MI50
+    th.think(force_mode="new")
+    assert seen["backend"] == "mi50" and seen["model"] is None
+
+
+def test_think_skipped_when_introspection_off(lyra):
+    from lyra import self_state
+    _, th, box = lyra
+    self_state.set_introspection_mode("off")
+    _gen(box, content="should not be generated")
+    assert th.think(force_mode="new") is None      # paused -> no thought, no LLM call
+    assert th.list_threads() == []
+
 
 def test_no_ping_without_ntfy(lyra, monkeypatch):
     _, th, _ = lyra