feat: dream-cycle time budget + default per-call timeout (guard C)

Belt-and-suspenders so no dream pass can run unchecked for hours:
- llm.complete() now always bounds the OpenAI/mi50 request: default 300s +
  max_retries=0 instead of the SDK's 600s x2 (~30 min). One change bounds every
  consolidation/introspection call (profile/era/narrative/reflect/think), not
  just summaries. Live chat (chat_call*) is a separate path, unaffected.
- dream_cycle() enforces a 20-min wall-clock budget, checked between stages;
  once past it, remaining stages are skipped, it logs 'stopped early (over
  budget)', and notify.push() pings Brian. Paired with the host watchdog (A) as
  an independent fallback.

Tests: default timeout/max_retries threaded into complete(); an over-budget pass
skips later stages + pings. 178 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

@@ -77,3 +77,31 @@ def test_dream_cycle_consolidates_and_persists(lyra):
     state2 = dream.dream_cycle(force=False)
     assert state2["dream"]["cycle_count"] == 2
     assert state2["drives"]["continuity"] == 0.0
+
+
+def test_dream_cycle_stops_when_over_budget(lyra, monkeypatch):
+    memory = lyra
+    from lyra import dream, notify
+
+    for k in range(7):
+        _seed(memory, f"s{k}", 4)
+
+    # Go over budget right after the first heavy stage: first check passes
+    # (summarize runs), every check after trips.
+    checks = {"n": 0}
+
+    def fake_over(deadline):
+        checks["n"] += 1
+        return checks["n"] > 1
+    monkeypatch.setattr(dream, "_over_budget", fake_over)
+
+    pings: list = []
+    monkeypatch.setattr(notify, "push",
+                        lambda title, message, **k: pings.append((title, message)) or True)
+
+    state = dream.dream_cycle(force=True)
+    acts = state["dream"]["last_actions"]
+
+    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"

tests/test_llm_bounds.py

@@ -55,9 +55,12 @@ def test_cloud_threads_max_tokens_and_timeout(fake_openai):
     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.
+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
+    # unless asked, though.
     llm.complete([{"role": "user", "content": "hi"}], backend="mi50")
 
     assert "max_tokens" not in fake_openai["create"]
-    assert "timeout" not in fake_openai["client"]
+    assert fake_openai["client"]["timeout"] == 300
+    assert fake_openai["client"]["max_retries"] == 0