mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-31 19:16:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

feat(gateway): session activity watchdog, stall notify, compress timeout (#72424)

Browse source 
Three mechanisms to detect and notify when gateway sessions stall silently:

1. Mid-turn activity heartbeats stamped to SessionDB so hermes sessions list
   and hermes status show progress during long turns without new message rows.

2. Stall watchdog: when a busy session has pending inbound and the shared
   activity clock is idle past agent.session_stall_timeout (default 300),
   log a WARNING and notify the user once to try /new. Notify-only; does
   not kill the turn.

3. Compaction timeout: fenceless compress_context callers get a progress-aware
   host budget (compression.context_timeout_seconds default 120 idle,
   compression.context_total_ceiling_seconds default 600 ceiling). On timeout,
   cancel via commit fence, skip compaction without dropping messages, and
   continue the turn.

Closes #72016 (slices 1-3; slice 4 cumulative SSE stream-retry deadline
remains a follow-up).

Cherry-picked from PR #72424 by @fangliquanflq.
This commit is contained in:
fangliquanflq 2026-07-27 23:16:24 +05:00 • committed by kshitij
parent 5fde131eb2
commit cfb206fe2e
24 changed files with 2638 additions and 107 deletions
Download patch file Download diff file Expand all files Collapse all files

6
website/docs/user-guide/configuration.md
View file

@ -754,6 +754,8 @@ compression:
hygiene_timeout_seconds: 30 # Max seconds of NO summary-model output before hygiene compression is cut off
hygiene_total_ceiling_seconds: 600 # Absolute cap on the hygiene wait even while tokens are still streaming
hygiene_failure_cooldown_seconds: 300 # Skip repeated failed hygiene attempts for this session
context_timeout_seconds: 120 # Inactivity budget for in-agent compress_context (loop /compress / preflight) — see below
context_total_ceiling_seconds: 600 # Absolute cap on in-agent compress_context wait even while tokens are still streaming
proactive_prune_tokens: 0 # Opt-in tokens trigger for the no-LLM tool-result prune (0 = off; see below)
proactive_prune_min_result_chars: 8000 # Prune's summarize pass only touches tool results larger than this (clamped >= 200)
proactive_prune_min_reclaim_tokens: 4096 # Prune only commits when it reclaims at least this many tokens (0 = commit any)
@ -780,6 +782,10 @@ Older configs with `compression.summary_model`, `compression.summary_provider`,
`hygiene_failure_cooldown_seconds` controls that per-session cooldown after a hygiene compression timeout or abort. During the cooldown, the gateway skips repeated hygiene attempts for the same oversized session so every incoming message does not block on the same broken auxiliary backend. `/compress`, `/reset`, or a healthy later turn can still recover the session.
`context_timeout_seconds` (default `120`) is the same **inactivity budget** for in-agent `compress_context` — the conversation loop, preflight compaction, and manual `/compress` — so a hung summary model cannot stall a session indefinitely. Streamed summary tokens extend the wait; only a silent worker is cut off. On timeout Hermes skips compaction, keeps the existing messages, and warns the user. Set to `0` to disable. Gateway session hygiene keeps its own `hygiene_timeout_seconds` path and is not double-wrapped.
`context_total_ceiling_seconds` (default `600`) bounds the in-agent wait even while tokens are still moving. It is clamped to at least `context_timeout_seconds`.
`protect_first_n` controls how many **non-system** head messages are pinned across every compaction. Default `3` — the opening user/assistant exchange survives every summarizer pass so the original goal stays visible. On long-running rolling-compaction sessions where the opening turn is no longer relevant, set `protect_first_n: 0` to pin nothing but the system prompt + summary + tail. The system prompt itself is always preserved regardless of this setting.
`threshold_tokens` sets an optional **absolute token cap** for the compression trigger. When set, compression fires at the lower of the ratio-based `threshold` and this absolute count — so compression never fires later than the user's preferred token number regardless of which model is active. This solves the problem where switching between models with different context windows (e.g. 1M → 400K) shifts the absolute trigger point. The cap is clamped to the model's context length, so setting it higher than the model supports is safe — the ratio-based threshold is used instead. Default `null` (disabled — ratio-based threshold only). The cap survives model switches and fallback activations.