Sanitize leaked tool-call markup in commentary channel

NousResearch/hermes-agent · cluster 125458 · agent

Data as of

3 open items. Fix attempted, not merged.

The short answer

1open issue
2open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
1 issue and 2 PRs.

These items address a bug where tool-call tokens or markup leak through the commentary channel and reach users as junk text. The work involves detecting and stripping that unwanted echo, including cases where structured tool_calls are also present.

Open issues1

  • Issue#125458Codex commentary-channel tool-call leak is not sanitized when structured tool_calls are also present (junk tokens reach users)

Open PRs2

  • PR#125472fix(agent): sanitize leaked tool-call markup in Codex commentary text
  • PR#125482fix(codex): drop the commentary-channel tool-call echo beside the real call
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

Subsystem
agent
Closed issues
0
Attempts
0 PRs closed without merging

For your agent

The same facts, typed.