hermes-agent/website/docs
Teknium 32fd9d65cf feat(compression): progress-aware timeouts — stop punishing slow summary models
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.
2026-07-25 12:26:28 -07:00
..
developer-guide fix(api-server): expose model options inventory 2026-07-24 11:20:07 -07:00
getting-started Reapply "Merge pull request #30179 from NousResearch/feat/iron-proxy" 2026-07-24 09:49:00 -07:00
guides rip out brew + pip/PyPI wheel support (#68217) 2026-07-22 16:51:01 -04:00
integrations rip out brew + pip/PyPI wheel support (#68217) 2026-07-22 16:51:01 -04:00
reference docs(acp): document HERMES_ACP_SKIP_CONFIGURED_MCP for ACP hosts 2026-07-24 15:51:20 -07:00
user-guide feat(compression): progress-aware timeouts — stop punishing slow summary models 2026-07-25 12:26:28 -07:00
index.mdx feat(docs): clarify platform support 2026-06-26 11:37:56 -07:00
user-stories.mdx docs(website): add User Stories and Use Cases collage page (#18282) 2026-04-30 23:56:59 -07:00