NousResearch/hermes-agent

Skip redundant SDK transform for chat-completions payloads

Cluster 111723. Data as of

Nothing open on GitHub. Fix merged in #112231 on 16 Sep 2026. Check it covers your case.

The short answer

0open issues
0open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #112231. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #112231. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items address a performance concern where chat-completions requests pass through an OpenAI SDK client-side transform that consumes significant CPU time (reportedly up to 97% of client time on long conversations) despite producing a byte-identical body. The work involves routing bulk chat-completions payloads to bypass that transform.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #112231 perf(agent): chat-completions requests skip the SDK client-side transform of the conversation body (#111723, salvage #102036, #106755)

    merged to main

    files: agent/auxiliary_client.py, agent/chat_completion_helpers.py, agent/codex_runtime.py, agent/sdk_transform_bypass.py, tests/agent/test_chat_sdk_transform_bypass.py, tests/agent/test_codex_sdk_transform_bypass.py

1 PR closed without merging

From the close comments: merged via another change 1

  • #102036 perf(agent): keep bulk chat-completions payloads out of the SDK request transform · merged via another change → 1e39c93, #112231
Closed issues · 1
  • Closed#111723[Perf bug]: the default chat-completions path still pays the OpenAI SDK client-side request transform on every call — up to 97 % of client time on long conversations for a byte-identical body
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Merged PRs
#112231
Closed issues
1
Attempts
1 PR closed without merging
Fix link checked
16 Sep 2026

For your agent

The same facts, typed.