mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-27 17:58:07 +00:00
32fd9d65cf
The gateway's pre-agent session-hygiene compression killed the summary
call at a fixed 30s wall-clock deadline (compression.hygiene_timeout_seconds),
regardless of whether the summary model was hung or merely slow. A reasoning
model happily streaming a large summary was cut off mid-generation, the user
got '⚠️ Context compression timed out after 30.0s', and a 300s failure
cooldown left the session oversized — a doom loop for slow-but-healthy
auxiliary models.
Timeouts are now liveness-based instead of wall-clock-based:
- agent/auxiliary_client.py: new thread-local aux_progress_hook. When
installed (only by context compression today), the primary call_llm
attempt streams (stream=True) and aggregates chunks back into a complete
response, ticking the hook per chunk. The configured timeout then acts
per stream read (idle) instead of as a total budget. Providers that
reject streaming fall back to the plain non-streaming call; auth/payment/
rate-limit/transport errors propagate unchanged into the existing
recovery chains. Codex Responses (per SSE event) and Anthropic Messages
(per stream event, via the new create_anthropic_message on_stream_event
callback) tick the same hook from inside their wire adapters.
- agent/conversation_compression.py: CompressionCommitFence gains
touch_progress()/seconds_since_progress(); compress_context() installs
fence.touch_progress as the progress hook around the compress call.
- gateway/run.py: the hygiene wait loop treats hygiene_timeout_seconds as
an INACTIVITY budget — while the fence reports fresh progress the wait
extends, bounded by the new compression.hygiene_total_ceiling_seconds
(default 600s, clamped >= the idle budget) so a degenerate trickle
stream still dies. The timeout warning now says the summary model
produced no output, which is the only case that still triggers it.
- config/docs: hygiene_total_ceiling_seconds added to DEFAULT_CONFIG and
configuration.md; hygiene_timeout_seconds documented as inactivity-based.
Tests: tests/agent/test_aux_progress_streaming.py (hook plumbing, stream
aggregation incl. tool-call deltas and reasoning deltas, rejection
fallback, ceiling kill, fence progress surface); two new gateway tests
prove a slow-but-streaming worker survives past the fixed timeout
(sabotage-verified: fails with the old fixed deadline) and a
forever-trickling worker is still cut off at the ceiling.
|
||
|---|---|---|
| .. | ||
| assets | ||
| builtin_hooks | ||
| platforms | ||
| relay | ||
| __init__.py | ||
| authz_mixin.py | ||
| cgroup_cleanup.py | ||
| channel_directory.py | ||
| code_skew.py | ||
| config.py | ||
| cwd_placeholder.py | ||
| dead_targets.py | ||
| delivery.py | ||
| delivery_ledger.py | ||
| display_config.py | ||
| drain_control.py | ||
| hooks.py | ||
| kanban_watchers.py | ||
| memory_monitor.py | ||
| message_timestamps.py | ||
| mirror.py | ||
| pairing.py | ||
| platform_registry.py | ||
| profile_routing.py | ||
| readiness.py | ||
| response_filters.py | ||
| restart.py | ||
| restart_loop_guard.py | ||
| rich_sent_store.py | ||
| run.py | ||
| runtime_footer.py | ||
| scale_to_zero.py | ||
| session.py | ||
| session_context.py | ||
| shutdown_forensics.py | ||
| shutdown_watchdog.py | ||
| slash_access.py | ||
| slash_commands.py | ||
| status.py | ||
| status_phrases.py | ||
| sticker_cache.py | ||
| stream_consumer.py | ||
| stream_dispatch.py | ||
| stream_events.py | ||
| systemd_notify.py | ||
| turn_lease.py | ||
| wake.py | ||
| whatsapp_identity.py | ||