mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-02 12:13:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

fix(delegation): budget subagent summaries against parent context headroom

Browse source 
Batch delegation returned each subagent's full final_response verbatim
into the parent's context. A fan-out of N children could dump 60k+ tokens
at once, blowing the parent's context window and — on rate-limited
providers — triggering a compression/429 death spiral (429 misread as
context-too-large -> window step-down -> retry loop -> conversation dies).

Cap each summary against the parent's *remaining* context headroom split
across the batch (not a magic char count). When trimming, mirror the
web_extract convention: spill the full text to cache/delegation (mounted
into remote backends via credential_files._CACHE_DIRS) and return a
head+tail window (75/25, line-snapped) plus a footer with the exact
read_file offset to page the omitted middle. Both the subagent's opening
AND its closing (outcomes / files-changed / issues, which live at the end)
survive in-context, and nothing is lost — the parent can read_file the
full version on any backend.

delegation.max_summary_chars (default 24000) is a static ceiling layered
on top as belt-and-suspenders for models that ignore 'be concise'; 0
disables it. Child prompt tightened to lead with outcomes / bullets.

Co-authored-by: rc-int <rcint@klaith.com>
This commit is contained in:
teknium1 2026-06-30 01:30:47 -07:00 • committed by Teknium
parent 3b2bb30c5d
commit 35a0803a3b
5 changed files with 341 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
scripts/release.py
View file

@ -79,6 +79,7 @@ AUTHOR_MAP = {
"15205536+595650661@users.noreply.github.com": "595650661", # PR #37851 salvage (classify MiniMax new_sensitive content filter → content_policy_blocked; #32421)
"benbenwyb@gmail.com": "benbenlijie", # PR #47205 salvage (named custom-provider extra_body + Z.AI Coding overload adaptive backoff; #50663)
"dana@added-value.co.il": "Danamove", # PR #46726 salvage (kill venv-resident pythonw gateway before recreating venv on Windows; #47036/#47557/#47910)
"rcint@klaith.com": "rc-int", # PR #9126 salvage / co-author (cap subagent summary size vs parent context overflow)
"145739220+wgu9@users.noreply.github.com": "wgu9", # PR #51468 salvage (WSL/no-systemd orphan gateway tracking, #51325)
"165020384+uperLu@users.noreply.github.com": "uperLu", # PR #50958 salvage (rename plugins/cron → plugins/cron_providers; #50872)
"277269729+yusekiotacode@users.noreply.github.com": "yusekiotacode", # PR #48706 salvage (anthropic OAuth login token endpoint → platform.claude.com; #45250/#49821)