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
This commit is contained in:
2026-07-04 19:05:32 +00:00
parent af778ef327
commit 3573ac8d79
4 changed files with 74 additions and 10 deletions
+30 -4
View File
@@ -26,7 +26,8 @@ import time
from datetime import datetime, timezone
from lyra import (
config, era, feeds, logbus, memory, narrative, poker, profile, self_state, summary, thoughts,
config, era, feeds, logbus, memory, narrative, notify, poker, profile, self_state,
summary, thoughts,
)
from lyra.llm import Backend
from lyra.summary import SUMMARIZE_AFTER
@@ -34,6 +35,17 @@ from lyra.summary import SUMMARIZE_AFTER
# A drive at/above this has built up enough to act on.
THRESHOLD = 0.6
# Wall-clock ceiling for a single pass. Every consolidation/introspection call is
# individually bounded (llm.complete's default timeout), but this caps the whole
# pass: once exceeded, remaining stages are skipped and Brian is pinged — so a slow
# or wedged MI50 can never grind for hours unattended. The host watchdog (A) is the
# independent fallback if this ever fails to fire.
DREAM_CYCLE_BUDGET_SEC = 20 * 60
def _over_budget(deadline: float) -> bool:
return time.monotonic() > deadline
# How much backlog saturates each pressure (the drive reaches ~1.0 at this level).
CONTINUITY_FULL = 4 # ripe (summary-needing) sessions
COHERENCE_FULL = 10 # gists not yet folded into the profile
@@ -96,9 +108,12 @@ def dream_cycle(backend: Backend | None = None, force: bool = False) -> dict:
logbus.log("error", "daily digest failed", error=str(exc)[:160])
actions: list[str] = []
# Cap the whole pass: skip any stage we reach after the deadline (checked
# between stages; each call is already individually bounded).
deadline = time.monotonic() + DREAM_CYCLE_BUDGET_SEC
# --- continuity: compact raw sessions into gists ---
if force or drives["continuity"] >= THRESHOLD:
if (force or drives["continuity"] >= THRESHOLD) and not _over_budget(deadline):
report = summary.summarize_all(backend=backend)
actions.append(f"consolidated {report['summarized']} sessions")
drives["continuity"] = 0.0
@@ -108,7 +123,7 @@ def dream_cycle(backend: Backend | None = None, force: bool = False) -> dict:
drives["coherence"] = _clamp(profile_lag / COHERENCE_FULL)
# --- coherence: fold gists up into profile / eras / narrative ---
if force or drives["coherence"] >= THRESHOLD:
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)
@@ -124,7 +139,7 @@ def dream_cycle(backend: Backend | None = None, force: bool = False) -> dict:
logbus.log("error", "villain merge scan failed", error=str(exc)[:200])
# --- curiosity: reflect and evolve the self, then advance the thought loop ---
if force or drives["curiosity"] >= THRESHOLD:
if (force or drives["curiosity"] >= THRESHOLD) and not _over_budget(deadline):
# reflect()/think() self-resolve to the *introspection* backend (her voice),
# which can differ from the consolidation backend above — don't pass `backend`.
self_state.reflect(source="dream") # writes state + journal itself
@@ -139,6 +154,17 @@ def dream_cycle(backend: Backend | None = None, force: bool = False) -> dict:
logbus.log("error", "thought loop failed", error=str(exc)[:200])
drives["curiosity"] = CURIOSITY_FLOOR
if _over_budget(deadline):
logbus.log("error", "dream cycle over budget — stopped early",
budget_min=DREAM_CYCLE_BUDGET_SEC // 60, done=actions)
actions.append("stopped early (over budget)")
notify.push(
"Lyra — dream cycle over budget",
f"A dream pass ran past {DREAM_CYCLE_BUDGET_SEC // 60} min and stopped early. "
"The MI50 backend may be slow or wedged — worth a look.",
tags="warning",
)
if not actions:
actions.append("rested (nothing past threshold)")