mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-25 17:18:11 +00:00
850f576f3d
Extends the fanout enum with 'every_n:<N>' (N >= 2): advisors run on the
first iteration of each user turn and every Nth tool iteration after it;
off-cadence iterations REUSE the cached guidance from the last on-cadence
run via the same cache mechanism the user_turn fanout uses, so the
aggregator still gets advice on every step. The cadence counter is scoped
per user turn (resets on a new user message) and only advances when the
advisory state actually changes, so streaming retries never consume a
cadence slot. Mapping form {mode: every_n, n: N} normalizes to the
canonical string. Unknown/degenerate values fall back to per_iteration.
Addresses issue #63393 (advisor fan-out multiplies turn latency/cost by
the tool-iteration count). Redesigned from PR #63448: the submitted shape
skipped references entirely on off-cadence iterations (aggregator ran
advice-less); this version keeps the last advice in play, credited for
the idea and cadence framing.
Config-gated, default-off (default fanout remains per_iteration).
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
|
||
|---|---|---|
| .. | ||
| features | ||
| messaging | ||
| secrets | ||
| skills | ||
| _category_.json | ||
| checkpoints-and-rollback.md | ||
| cli.md | ||
| configuration.md | ||
| configuring-models.md | ||
| desktop.md | ||
| docker.md | ||
| git-worktrees.md | ||
| managed-scope.md | ||
| multi-profile-gateways.md | ||
| profile-distributions.md | ||
| profiles.md | ||
| security.md | ||
| sessions.md | ||
| tui.md | ||
| windows-native.md | ||
| windows-wsl-quickstart.md | ||