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):
-        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
+        # 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,
     ))