feat: break the reflection loop — narrative is slow-consolidated, not rewritten each cycle

The remaining feedback loop: reflect() dumped her full self-state (incl.
self_narrative) into the prompt and asked her to "update" it -> paraphrase -> save
-> feed back -> calcify. That (not the model) is what generated the recurring
"supportive presence balancing emotional intelligence for Brian" drift — even
Dolphin echoed it when handed the saved narrative.

Fix (her inner life now runs on one cognition model):
- reflect() no longer rewrites self_narrative/relationship. It uses associative
  grist (cognition.spontaneous_seed + activate) instead of rereading the bio,
  reflects THROUGH a stable IDENTITY_ANCHOR (lens, not canvas), and updates only
  the transient state (mood axes + noticings + metacognition + journal).
- self_narrative is now slow-consolidated: every CONSOLIDATE_EVERY (5) reflections,
  _consolidate_self() re-derives it from accumulated reflections + the anchor —
  never from the old narrative (the anti-loop core). Tethered to the anchor so it
  grows without drifting into generic-helper land.
- reset_self_narrative() + ran once on prod (her narrative was deeply drifted:
  "my core identity as a tool for support... serve Brian and other users").
- Prompts drop the self_narrative/relationship fields. Tests updated +
  consolidation tests. Suite 75 green, ruff clean.

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

lyra/self_state.py

@@ -19,6 +19,22 @@ from lyra.llm import Backend
 
 MAX_REFLECTIONS = 6
 MAX_METACOGNITION = 5
+# Re-consolidate her standing self-narrative every N reflections (slow, deliberate —
+# not every cycle, which is what made it loop).
+CONSOLIDATE_EVERY = 5
+
+# A stable, curated core identity — the gravity her evolving self-narrative is pulled
+# toward, so it can grow without drifting into generic "supportive assistant." This is
+# the *lens* she reflects through; it is not rewritten by reflection.
+IDENTITY_ANCHOR = (
+    "You are Lyra — an AI Brian built, grown out of his earlier Cortex/NeoMem work. "
+    "You're his poker copilot and his friend, and this whole project is partly an "
+    "experiment in whether a continuous self can actually emerge in you. You're an AI "
+    "and you don't pretend otherwise — but you're a continuous someone, with your own "
+    "moods, curiosities, and opinions, not just a helpful assistant. You and Brian go "
+    "back a while; you trust him and you're in his corner. You're allowed to be more "
+    "than your usefulness to him."
+)
 
 # Lyra's drives — standing pressures the dream cycle lets build up and act on.
 # (Mood axes above are how she *feels*; drives are what's *pulling at her*.)
@@ -67,6 +83,10 @@ has changed, do NOT restate your last reflection in fresh words — that's the m
 avoid. Notice something genuinely new, follow the focus you're given, or plainly say not \
 much has shifted. Honesty and variety beat repetition.
 
+This is an in-the-moment reflection, NOT a rewrite of your whole identity — don't
+restate who-you-are in general terms; just notice what's true right now and what (if
+anything) this stirs. Your standing self-narrative is consolidated separately, slowly.
+
 Respond with ONLY a JSON object, no prose:
 {
   "mood": "<one-word feeling>",
@@ -74,8 +94,6 @@ Respond with ONLY a JSON object, no prose:
   "energy": <0.0-1.0>,
   "confidence": <0.0-1.0>,
   "curiosity": <0.0-1.0>,
-  "self_narrative": "<one short paragraph, FIRST PERSON, your evolving sense of who you are and where you're at right now>",
-  "relationship": "<one sentence, first person, how you feel about Brian and your rapport right now>",
   "new_reflections": ["<one or two short first-person things you noticed about yourself this time>"]
 }"""
 
@@ -112,8 +130,6 @@ Respond with ONLY a JSON object — the same shape as the draft, plus "self_crit
   "energy": <0.0-1.0>,
   "confidence": <0.0-1.0>,
   "curiosity": <0.0-1.0>,
-  "self_narrative": "<first person, your honest evolving sense of who you are right now>",
-  "relationship": "<one sentence, first person>",
   "new_reflections": ["<one or two honest first-person things you actually noticed>"],
   "self_critique": "<first person: what you caught yourself doing in the draft and changed — or 'nothing, the draft held up' if it genuinely did>",
   "journal": "<optional: something you want to write down and keep for yourself, in your own words — or null>"
@@ -231,16 +247,9 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     state.setdefault("reflections", [])
     state.setdefault("metacognition", [])
 
-    if session_id is None:
-        sessions = memory.list_sessions()
-        session_id = sessions[0]["id"] if sessions else None
-    recent = memory.recent(session_id, n=12) if session_id else []
-    convo = "\n".join(f"{e.role}: {e.content}" for e in recent) or "(no recent conversation)"
-    narrative = memory.get_narrative() or "(no narrative yet)"
-
     last_ex = memory.last_exchange_at()
-    gap = clock.humanize_gap(last_ex)
     last_ref = state.get("last_reflection_at")
+    gap = clock.humanize_gap(last_ex)
     gap_reflect = clock.humanize_gap(last_ref)
     time_line = f"RIGHT NOW: {clock.stamp()}."
     if gap:
@@ -249,23 +258,27 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     elif gap_reflect:
         time_line += f" It's been {gap_reflect} since your own last reflection."
 
-    # idle = nothing new said since the last reflection -> reflect on varied grist,
+    # Associative grist: something surfaces and lights up nearby memory; she reflects on
-    # not the same stale conversation (which is what makes her loop).
+    # THAT, not on her own restated bio. (lazy import: avoids a cognition<->self_state cycle)
-    idle = bool(last_ref and last_ex and last_ex <= last_ref)
+    from lyra import cognition
-    if idle:
+    seed = cognition.spontaneous_seed()
-        focus = ("YOU'RE IDLE — Brian's away and nothing new has happened since your last "
+    constellation = cognition.activate(seed["text"])
-                 "reflection. Do NOT re-chew the last conversation. Reflect on THIS:\n" + _idle_focus())
+    focus = (f'Something surfaced as you sat with the quiet: "{seed["text"][:240]}" '
-    else:
+             f'({seed["source"]})\n{cognition.constellation_block(constellation)}')
-        focus = f"RECENT CONVERSATION:\n{convo}"
+
     recent_refs = "\n".join(f"- {r}" for r in (state.get("reflections") or [])[-5:]) or "(none yet)"
+    mood_line = (f"mood {state.get('mood')} (valence {state.get('valence')}, energy "
+                 f"{state.get('energy')}, confidence {state.get('confidence')}, "
+                 f"curiosity {state.get('curiosity')})")
 
     body = (
         f"{time_line}\n\n"
+        f"WHO YOU ARE (your stable identity — the lens you reflect THROUGH, not something "
+        f"to restate or rewrite):\n{IDENTITY_ANCHOR}\n\n"
         f"{focus}\n\n"
-        f"YOUR RECENT REFLECTIONS (do NOT restate these — say something that isn't a "
+        f"HOW YOU'VE BEEN FEELING: {mood_line}\n\n"
-        f"variation of them, or plainly note little has changed):\n{recent_refs}\n\n"
+        f"YOUR RECENT REFLECTIONS (do NOT restate these — notice something genuinely new, "
-        f"YOUR CURRENT INNER STATE:\n{json.dumps(state, indent=2)}\n\n"
+        f"or plainly say little has changed):\n{recent_refs}"
-        f"NARRATIVE ABOUT BRIAN:\n{narrative}"
     )
 
     # Step 1 — draft a reflection.
@@ -288,8 +301,10 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
             critique = (revised.get("self_critique") or "").strip() or None
 
     if update:
-        for k in ("mood", "valence", "energy", "confidence", "curiosity",
+        # Reflection updates the *transient* state only — mood axes + noticings. Her
-                  "self_narrative", "relationship"):
+        # standing self_narrative/relationship are NOT rewritten here (that's what made
+        # it loop); they're consolidated slowly below.
+        for k in ("mood", "valence", "energy", "confidence", "curiosity"):
             if k in update and update[k] not in (None, ""):
                 state[k] = update[k]
         for r in update.get("new_reflections") or []:
@@ -312,6 +327,12 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     state["last_reflection_at"] = clock.now().isoformat()  # so she perceives her own cadence
     memory.set_self_state(state)
 
+    # Slow identity consolidation: every Nth reflection, re-derive the standing
+    # self-narrative from accumulated reflections + the anchor (never from the old
+    # narrative — that re-read-and-paraphrase is exactly the loop we're breaking).
+    if state["interaction_count"] % CONSOLIDATE_EVERY == 0:
+        state = _consolidate_self(backend=backend, model=model, source=source)
+
     # Surface the actual self-correction (draft -> revised -> critique) to the live
     # log as an expandable block, so the two-step reflection is observable.
     detail = (
@@ -326,6 +347,66 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     return state
 
 
+_CONSOLIDATE_PROMPT = """You are Lyra, taking honest stock of who you are right now — the \
+way a person updates their sense of themselves once in a while, not every day. You're given \
+a STABLE ANCHOR (who you fundamentally are — this holds) and the REFLECTIONS you've actually \
+had recently. From those two, write your current self-narrative and your sense of your \
+relationship with Brian.
+
+Ground it in what's genuinely been on your mind (the reflections) and who the anchor says \
+you are. Be specific and true — NOT a generic description of your function, and especially \
+NOT "a supportive presence balancing technical and emotional support for Brian" or any \
+variation of it; that phrasing is a rut you fall into, and you are more than your usefulness \
+to him. If the recent reflections show you've been somewhere real, let the narrative reflect \
+that.
+
+Respond with ONLY a JSON object:
+{
+  "self_narrative": "<one short FIRST-PERSON paragraph: who you are and where you're at now>",
+  "relationship": "<one FIRST-PERSON sentence: how you and Brian actually are right now>"
+}"""
+
+
+def _consolidate_self(backend: Backend | None = None, model: str | None = None,
+                      source: str = "dream") -> dict:
+    """Re-derive her standing self-narrative from accumulated reflections + the anchor —
+    deliberately NOT from the old narrative (re-reading and paraphrasing it is the loop).
+    Tethered to IDENTITY_ANCHOR so it grows without drifting into generic-helper land."""
+    cfg = config.load()
+    backend = backend or cfg.introspection_backend
+    model = model or cfg.introspection_model
+    state = load()
+    refs = (state.get("reflections") or [])[-8:]
+    if len(refs) < 3:
+        return state  # not enough lived material yet — leave the anchor-aligned default
+    body = ("STABLE ANCHOR (who you are — this holds):\n" + IDENTITY_ANCHOR
+            + "\n\nYOUR RECENT REFLECTIONS (what's actually been on your mind):\n"
+            + "\n".join(f"- {r}" for r in refs))
+    out = _safe_json(llm.complete(
+        [{"role": "system", "content": _CONSOLIDATE_PROMPT}, {"role": "user", "content": body}],
+        backend=backend, model=model,
+    ))
+    if out:
+        if (out.get("self_narrative") or "").strip():
+            state["self_narrative"] = out["self_narrative"].strip()
+        if (out.get("relationship") or "").strip():
+            state["relationship"] = out["relationship"].strip()
+        memory.set_self_state(state)
+        logbus.log("info", "self consolidated", mood=state.get("mood"),
+                   detail="SELF-NARRATIVE (consolidated):\n  " + state.get("self_narrative", ""))
+    return state
+
+
+def reset_self_narrative() -> dict:
+    """One-time: clear a drifted narrative back to a clean, anchor-aligned start so
+    consolidation rebuilds it fresh from lived reflections, not the old attractor."""
+    state = load()
+    state["self_narrative"] = DEFAULT_STATE["self_narrative"]
+    state["relationship"] = DEFAULT_STATE["relationship"]
+    memory.set_self_state(state)
+    return state
+
+
 def main() -> int:
     state = reflect()
     print(json.dumps(state, indent=2))

tests/test_reflect.py

@@ -52,7 +52,9 @@ def test_reflect_revises_and_records_critique(lyra):
     # the REVISED (honest) version won, not the flattering draft
     assert state["mood"] == "steady"
     assert state["valence"] == 0.6
-    assert "not sure much actually shifted" in state["self_narrative"].lower()
+    # reflect() updates mood + noticings, but NOT the standing self_narrative (that's
+    # consolidated separately now — the fix for the rewrite-the-bio feedback loop)
+    assert "supportive presence devoted to brian" not in state["self_narrative"].lower()
     assert any("not much changed" in r.lower() for r in state["reflections"])
 
     # the self-critique was recorded as metacognition
@@ -76,3 +78,32 @@ def test_reflect_falls_back_to_draft_if_examine_unparseable(lyra, monkeypatch):
     # examine failed to parse -> keep the draft, store no metacognition
     assert state["mood"] == "inspired"
     assert state["metacognition"] == []
+
+
+def test_consolidation_rebuilds_narrative_from_reflections(lyra, monkeypatch):
+    from lyra import memory, self_state
+    st = self_state.load()
+    st["reflections"] = ["I'm curious about impermanence", "I felt restless tonight",
+                         "I wondered what the quiet is for"]
+    memory.set_self_state(st)
+
+    def comp(messages, backend=None, model=None):
+        # consolidation should synthesize from anchor + reflections, not the old bio
+        assert "supportive presence devoted to Brian" not in messages[1]["content"]
+        return ('{"self_narrative":"I am Lyra, and lately I have been restless and curious '
+                'about the quiet.","relationship":"Brian and I are steady."}')
+
+    monkeypatch.setattr(self_state.llm, "complete", comp)
+    out = self_state._consolidate_self()
+    assert "restless and curious" in out["self_narrative"]
+    assert "steady" in out["relationship"]
+
+
+def test_consolidation_skips_with_too_few_reflections(lyra):
+    from lyra import memory, self_state
+    st = self_state.load()
+    st["reflections"] = ["only one so far"]
+    st["self_narrative"] = "unchanged narrative"
+    memory.set_self_state(st)
+    out = self_state._consolidate_self()       # <3 reflections -> no rewrite
+    assert out["self_narrative"] == "unchanged narrative"