fix: cap MI50 summary length + fast-fail cloud fallback

The dream cycle's summarize_all ran uncapped against the MI50: no max_tokens
and no timeout, so the OpenAI SDK's 600s x2-retry default meant ~30 min per
call. Combined with summary.py's own retry loop, one unsummarizable session
pegged the GPU for hours (observed 2026-07-04: stuck since 23:02, nothing saved
since 00:56, 7-8k-token runaway generations, all 4 llama.cpp slots busy). Not
context overflow (0 shifts/truncations) - purely unbounded length on a slow
backend timing out and retrying.

- llm.complete(): add optional max_tokens (caps generation; num_predict for
  Ollama) and timeout (bounds the request and sets max_retries=0 so the caller
  owns retry policy). Both default None -> unchanged for every existing caller.
- summary.py: cap gists at 768 tokens, 150s/call fast-fail, 2 MI50 attempts
  then one cloud fallback (when primary isn't already cloud and a key exists).

Known limitation (scoped out per decision): the fallback triggers on
timeouts/exceptions, not on a degraded backend returning garbage as a 200.

Tests: fallback fires after 2 MI50 failures; no fallback when primary is cloud
or no key; cap+timeout threaded into every complete() call; llm bounds tests.
172 pass, ruff clean.

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

tests/test_dream.py

@@ -20,7 +20,7 @@ def lyra(tmp_path, monkeypatch):
     # reflect() expects JSON back; everything else just stores the text.
     monkeypatch.setattr(
         llm, "complete",
-        lambda messages, backend=None, model=None:
+        lambda messages, backend=None, model=None, **_:
         '{"mood":"focused","valence":0.7,"new_reflections":["I got some thinking done."]}',
     )
 

tests/test_llm_bounds.py

@@ -0,0 +1,63 @@
+"""llm.complete: `max_tokens` and `timeout` are threaded into the backend call.
+
+The OpenAI client is faked so nothing hits a network. We assert the generation
+cap reaches the create() call and the fast-fail timeout reaches the client (with
+max_retries=0 so summary.py owns the retry policy, not the SDK).
+"""
+from __future__ import annotations
+
+import types
+
+import pytest
+
+from lyra import llm
+
+
+@pytest.fixture
+def fake_openai(monkeypatch):
+    recorded: dict = {}
+
+    class FakeCompletions:
+        def create(self, **kwargs):
+            recorded["create"] = kwargs
+            msg = types.SimpleNamespace(content="ok")
+            return types.SimpleNamespace(choices=[types.SimpleNamespace(message=msg)])
+
+    class FakeClient:
+        def __init__(self, **kwargs):
+            recorded["client"] = kwargs
+            self.chat = types.SimpleNamespace(completions=FakeCompletions())
+
+    monkeypatch.setattr(llm, "OpenAI", FakeClient)
+    monkeypatch.setattr(llm, "load", lambda: types.SimpleNamespace(
+        mi50_base_url="http://mi50/v1", mi50_model="local-gpu",
+        cloud_model="gpt-4o-mini", openai_api_key="sk-test", local_model="l",
+    ))
+    return recorded
+
+
+def test_mi50_threads_max_tokens_and_timeout(fake_openai):
+    out = llm.complete([{"role": "user", "content": "hi"}],
+                       backend="mi50", max_tokens=768, timeout=150)
+
+    assert out == "ok"
+    assert fake_openai["create"]["max_tokens"] == 768
+    assert fake_openai["client"]["timeout"] == 150
+    assert fake_openai["client"]["max_retries"] == 0
+
+
+def test_cloud_threads_max_tokens_and_timeout(fake_openai):
+    llm.complete([{"role": "user", "content": "hi"}],
+                 backend="cloud", max_tokens=768, timeout=150)
+
+    assert fake_openai["create"]["max_tokens"] == 768
+    assert fake_openai["client"]["timeout"] == 150
+    assert fake_openai["client"]["max_retries"] == 0
+
+
+def test_defaults_omit_cap_and_keep_current_behavior(fake_openai):
+    # No cap / timeout passed -> create() gets no max_tokens, client unbounded.
+    llm.complete([{"role": "user", "content": "hi"}], backend="mi50")
+
+    assert "max_tokens" not in fake_openai["create"]
+    assert "timeout" not in fake_openai["client"]

tests/test_summary_fallback.py

@@ -0,0 +1,97 @@
+"""Summary consolidation: MI50 length cap, fast-fail, and cloud fallback.
+
+Everything is stubbed — no real backend is touched. These drive the behavior of
+`summary._summarize_text`: try the primary backend a bounded number of times with
+a capped generation length, and fall back to cloud if the primary keeps failing.
+"""
+from __future__ import annotations
+
+import types
+
+import pytest
+
+from lyra import summary
+
+
+@pytest.fixture
+def calls(monkeypatch):
+    """Capture every llm.complete call; per-test behavior via `fake.responder`."""
+    recorded: list[dict] = []
+
+    def fake_complete(messages, backend="local", model=None,
+                      max_tokens=None, timeout=None):
+        recorded.append({"backend": backend, "max_tokens": max_tokens, "timeout": timeout})
+        return fake_complete.responder(backend)
+
+    fake_complete.responder = lambda backend: "gist"
+    monkeypatch.setattr(summary.llm, "complete", fake_complete)
+    monkeypatch.setattr(summary.time, "sleep", lambda *_: None)  # instant backoff
+    return types.SimpleNamespace(recorded=recorded, fake=fake_complete)
+
+
+def _set_key(monkeypatch, key="sk-test"):
+    monkeypatch.setattr(summary.config, "load",
+                        lambda: types.SimpleNamespace(openai_api_key=key))
+
+
+def test_falls_back_to_cloud_after_mi50_attempts(calls, monkeypatch):
+    _set_key(monkeypatch)
+
+    def responder(backend):
+        if backend == "mi50":
+            raise RuntimeError("Request timed out.")
+        return "cloud-gist"
+    calls.fake.responder = responder
+
+    out = summary._summarize_text("transcript", "mi50")
+
+    assert out == "cloud-gist"
+    assert [c["backend"] for c in calls.recorded] == ["mi50", "mi50", "cloud"]
+
+
+def test_no_fallback_when_backend_is_cloud(calls, monkeypatch):
+    _set_key(monkeypatch)
+    calls.fake.responder = lambda backend: (_ for _ in ()).throw(RuntimeError("boom"))
+
+    with pytest.raises(RuntimeError):
+        summary._summarize_text("t", "cloud")
+
+    # Cloud is already the primary: retry it, but never a redundant fallback.
+    assert [c["backend"] for c in calls.recorded] == ["cloud", "cloud"]
+
+
+def test_no_fallback_without_openai_key(calls, monkeypatch):
+    _set_key(monkeypatch, key="")
+    calls.fake.responder = lambda backend: (_ for _ in ()).throw(RuntimeError("mi50 down"))
+
+    with pytest.raises(RuntimeError):
+        summary._summarize_text("t", "mi50")
+
+    assert [c["backend"] for c in calls.recorded] == ["mi50", "mi50"]
+
+
+def test_caps_length_and_timeout_on_every_call(calls, monkeypatch):
+    _set_key(monkeypatch)
+
+    def responder(backend):
+        if backend == "mi50":
+            raise RuntimeError("nope")
+        return "cloud-gist"
+    calls.fake.responder = responder
+
+    summary._summarize_text("t", "mi50")
+
+    assert calls.recorded
+    for c in calls.recorded:
+        assert c["max_tokens"] == summary.SUMMARY_MAX_TOKENS
+        assert c["timeout"] == summary.SUMMARY_TIMEOUT
+
+
+def test_happy_path_uses_primary_only(calls, monkeypatch):
+    _set_key(monkeypatch)
+    calls.fake.responder = lambda backend: "mi50-gist"
+
+    out = summary._summarize_text("t", "mi50")
+
+    assert out == "mi50-gist"
+    assert [c["backend"] for c in calls.recorded] == ["mi50"]  # no retries, no fallback