feat: cloud-first consolidation routing + graceful backend fallback

Nail down which backend each LLM path uses, and make the dream cycle resilient to
a backend being down (the MI50 outage left profile/era/narrative — pinned to mi50
with no fallback — aborting every dream cycle).

- Consolidation (summaries + profile/era/narrative) -> cloud via SUMMARY_BACKEND=
  cloud (.env, not committed). Matches the documented lesson that the MI50 is too
  slow/hot for bulk consolidation; nothing background touches the card now.
- llm.complete_with_fallback(): try the primary backend, fall back to cloud on
  error (re-raise if already cloud / no key). Wired into reflect + think so the
  introspection voice (3090/dolphin) survives the gaming PC being powered off.
- dream coherence stage is now fault-isolated: a rebuild failure logs + continues
  instead of sinking the whole pass (reflection still runs).
- .env: removed stale INTROSPECTION_BACKEND=mi50 (live routing is the web-switchable
  introspection_mode DB setting = dolphin/3090; the var only fed a dead fallback).

Verified: forced cycle runs consolidation on cloud, introspection on the 3090,
completes with zero MI50 calls. 206 pass, ruff clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015yrEb5qpPGv2FjyxrB7LLk

lyra/dream.py

@@ -124,11 +124,18 @@ def dream_cycle(backend: Backend | None = None, force: bool = False) -> dict:
 
     # --- coherence: fold gists up into profile / eras / narrative ---
     if (force or drives["coherence"] >= THRESHOLD) and not _over_budget(deadline):
+        # A backend hiccup here must not sink the whole pass (reflection still
+        # deserves to run); log it and move on, leaving coherence unrelieved so a
+        # later cycle retries.
+        try:
             profile.rebuild_profile(backend=backend)
             era.rebuild_eras(backend=backend)
             narrative.rebuild_narrative(backend=backend)
             actions.append("integrated knowledge (profile/eras/narrative)")
             drives["coherence"] = 0.0
+        except Exception as exc:
+            logbus.log("error", "coherence stage failed", error=str(exc)[:200])
+            actions.append("coherence stage failed")
         # Off-hot-path villain identity housekeeping: propose likely same-person
         # merges for Brian to confirm on the Players page. Never sinks the cycle.
         try:

lyra/llm.py

@@ -92,6 +92,26 @@ def complete(messages: list[Message], backend: Backend = "local", model: str | N
     return out
 
 
+def complete_with_fallback(messages: list[Message], backend: Backend, model: str | None = None,
+                           *, fallback: Backend = "cloud",
+                           max_tokens: int | None = None, timeout: float | None = None) -> str:
+    """`complete()` but if the primary backend errors (e.g. a local GPU that's
+    powered off or down), retry once on `fallback` (cloud) instead of failing.
+    Lets local/GPU-routed work (introspection, consolidation) degrade gracefully.
+    Re-raises if the primary is already the fallback or no cloud key is configured."""
+    try:
+        return complete(messages, backend=backend, model=model,
+                        max_tokens=max_tokens, timeout=timeout)
+    except Exception as exc:
+        can_fallback = backend != fallback and (fallback != "cloud" or load().openai_api_key)
+        if not can_fallback:
+            raise
+        logbus.log("info", "llm fell back", primary=backend, to=fallback, error=str(exc)[:80])
+        # Drop the primary's model on fallback — let the fallback pick its own default.
+        return complete(messages, backend=fallback, model=None,
+                        max_tokens=max_tokens, timeout=timeout)
+
+
 def chat_call(
     messages: list, backend: Backend = "cloud", model: str | None = None,
     tools: list | None = None,

lyra/self_state.py

@@ -317,7 +317,7 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     )
 
     # Step 1 — draft a reflection.
-    draft = _safe_json(llm.complete(
+    draft = _safe_json(llm.complete_with_fallback(
         [{"role": "system", "content": _REFLECT_PROMPT}, {"role": "user", "content": body}],
         backend=backend, model=model,
     ))
@@ -326,7 +326,7 @@ def reflect(backend: Backend | None = None, session_id: str | None = None,
     update, critique, revised = draft, None, None
     if draft:
         examine_body = body + "\n\nYOUR DRAFT REFLECTION:\n" + json.dumps(draft, indent=2)
-        revised = _safe_json(llm.complete(
+        revised = _safe_json(llm.complete_with_fallback(
             [{"role": "system", "content": _EXAMINE_PROMPT},
              {"role": "user", "content": examine_body}],
             backend=backend, model=model,
@@ -417,7 +417,7 @@ def _consolidate_self(backend: Backend | None = None, model: str | None = None,
     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(
+    out = _safe_json(llm.complete_with_fallback(
         [{"role": "system", "content": _CONSOLIDATE_PROMPT}, {"role": "user", "content": body}],
         backend=backend, model=model,
     ))

lyra/thoughts.py

@@ -414,7 +414,7 @@ def _compose_reachout(title: str, content: str, backend, model) -> str:
     """Auto-write her a short personal text about a genuinely salient thought she didn't
     explicitly flag — so the good ones reach Brian, in her voice, not as a thought-dump."""
     try:
-        out = llm.complete(
+        out = llm.complete_with_fallback(
             [{"role": "system", "content": _REACHOUT_PROMPT},
              {"role": "user", "content": f'Thought "{title}": {content}'}],
             backend=backend, model=model,
@@ -612,7 +612,7 @@ def think(backend: Backend | None = None, force_mode: str | None = None,
         )
 
     body = f"{time_line}\n\n{inner}{norestate}\n\n{task}"
-    out = _safe_json(llm.complete(
+    out = _safe_json(llm.complete_with_fallback(
         [{"role": "system", "content": _THINK_PROMPT}, {"role": "user", "content": body}],
         backend=backend, model=model,
     ))

tests/test_dream.py

@@ -105,3 +105,22 @@ def test_dream_cycle_stops_when_over_budget(lyra, monkeypatch):
     assert any("stopped early" in a for a in acts)   # bailed
     assert not any("reflected" in a for a in acts)   # later stage skipped
     assert pings, "expected an over-budget ntfy push"
+
+
+def test_coherence_failure_does_not_sink_the_cycle(lyra, monkeypatch):
+    memory = lyra
+    from lyra import dream, profile
+
+    for k in range(3):
+        _seed(memory, f"s{k}", 4)
+
+    # A backend hiccup in the consolidation rebuild must not abort the whole pass
+    # (this is what broke the cycle when the MI50 was down).
+    monkeypatch.setattr(profile, "rebuild_profile",
+                        lambda *a, **k: (_ for _ in ()).throw(RuntimeError("backend down")))
+
+    state = dream.dream_cycle(force=True)
+    acts = state["dream"]["last_actions"]
+
+    assert any("coherence" in a and "fail" in a for a in acts)  # logged, not fatal
+    assert any("reflected" in a for a in acts)                  # cycle still reached reflection

tests/test_llm_bounds.py

@@ -55,6 +55,50 @@ def test_cloud_threads_max_tokens_and_timeout(fake_openai):
     assert fake_openai["client"]["max_retries"] == 0
 
 
+def test_fallback_uses_primary_when_it_succeeds(monkeypatch):
+    seen = []
+    monkeypatch.setattr(llm, "complete",
+                        lambda messages, backend="local", model=None, **k:
+                        seen.append(backend) or f"{backend}-ok")
+    out = llm.complete_with_fallback([{"role": "user", "content": "x"}],
+                                     backend="local", model="dolphin3:8b")
+    assert out == "local-ok"
+    assert seen == ["local"]  # no fallback when the primary works
+
+
+def test_fallback_to_cloud_when_primary_errors(monkeypatch):
+    monkeypatch.setattr(llm, "load", lambda: types.SimpleNamespace(openai_api_key="sk"))
+    seen = []
+
+    def fake(messages, backend="local", model=None, **k):
+        seen.append(backend)
+        if backend == "local":
+            raise RuntimeError("3090 is powered off")
+        return "cloud-ok"
+    monkeypatch.setattr(llm, "complete", fake)
+
+    out = llm.complete_with_fallback([{"role": "user", "content": "x"}],
+                                     backend="local", model="dolphin3:8b")
+    assert out == "cloud-ok"
+    assert seen == ["local", "cloud"]
+
+
+def test_fallback_reraises_when_primary_is_already_cloud(monkeypatch):
+    monkeypatch.setattr(llm, "load", lambda: types.SimpleNamespace(openai_api_key="sk"))
+    monkeypatch.setattr(llm, "complete",
+                        lambda *a, **k: (_ for _ in ()).throw(RuntimeError("boom")))
+    with pytest.raises(RuntimeError):
+        llm.complete_with_fallback([{"role": "user", "content": "x"}], backend="cloud")
+
+
+def test_fallback_reraises_without_openai_key(monkeypatch):
+    monkeypatch.setattr(llm, "load", lambda: types.SimpleNamespace(openai_api_key=""))
+    monkeypatch.setattr(llm, "complete",
+                        lambda *a, **k: (_ for _ in ()).throw(RuntimeError("down")))
+    with pytest.raises(RuntimeError):
+        llm.complete_with_fallback([{"role": "user", "content": "x"}], backend="local")
+
+
 def test_default_bounds_calls_even_without_explicit_timeout(fake_openai):
     # No cap / timeout passed -> still bounded: 300s default + no SDK retries, so
     # no call can silently inherit the SDK's 600s x2 (~30 min). No length cap

tests/test_reflect.py

@@ -28,7 +28,7 @@ def lyra(tmp_path, monkeypatch):
 
     calls = []
 
-    def fake_complete(messages, backend=None, model=None):
+    def fake_complete(messages, backend=None, model=None, **_):
         calls.append(messages)
         # the examine step's system prompt is the one asking for self_critique
         is_examine = "self_critique" in messages[0]["content"]
@@ -69,7 +69,7 @@ def test_reflect_revises_and_records_critique(lyra):
 def test_reflect_falls_back_to_draft_if_examine_unparseable(lyra, monkeypatch):
     from lyra import llm, self_state
 
-    def only_draft(messages, backend=None, model=None):
+    def only_draft(messages, backend=None, model=None, **_):
         return DRAFT if "self_critique" not in messages[0]["content"] else "not json at all"
 
     monkeypatch.setattr(llm, "complete", only_draft)
@@ -87,7 +87,7 @@ def test_consolidation_rebuilds_narrative_from_reflections(lyra, monkeypatch):
                          "I wondered what the quiet is for"]
     memory.set_self_state(st)
 
-    def comp(messages, backend=None, model=None):
+    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 '

tests/test_thoughts.py

@@ -31,7 +31,7 @@ def lyra(tmp_path, monkeypatch):
     # Canned LLM: tests set `box["next"]` to the dict think() should "generate".
     box = {"next": {}}
     monkeypatch.setattr(thoughts.llm, "complete",
-                        lambda messages, backend=None, model=None: json.dumps(box["next"]))
+                        lambda messages, backend=None, model=None, **_: json.dumps(box["next"]))
     # Keep the loop offline + silent by default: no feed fetch, no push.
     monkeypatch.setattr(thoughts.feeds, "next_item", lambda **k: None)
     monkeypatch.setattr(thoughts.notify, "push", lambda **k: False)
@@ -342,7 +342,7 @@ def test_think_routes_to_selected_voice(lyra, monkeypatch):
     self_state.set_introspection_mode("dolphin")
     seen = {}
 
-    def cap(messages, backend="local", model=None):
+    def cap(messages, backend="local", model=None, **_):
         seen["backend"], seen["model"] = backend, model
         return json.dumps(box["next"])