Tool failure outcomes lost or misrepresented in summaries

NousResearch/hermes-agent · cluster 131244

Data as of

Nothing open on GitHub. Fix merged in #132141. Check it covers your case.

The short answer

0open issues
0open PRs
5items grouped
Known?
Yes. 5 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #132141. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #132166. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items concern a bug where errors or refusals from tool operations (such as write_file) are incorrectly summarized as successes, and proposed fixes to preserve accurate failure outcomes in templated tool-result stubs and agent summaries.

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.

  • #132141 Compaction stubs keep a tool call's FAILED outcome (#131244, salvage #131312)

    merged to main

    files: agent/context_compressor.py, tests/agent/test_context_compressor.py

  • #132166 Compaction no longer stubs a refused write_file as written (#131244, salvage #131247)

    merged to main

    files: agent/context_compressor.py, tests/agent/test_context_compressor.py

2 PRs closed without merging

From the close comments: merged via another change 2

  • #131247 fix(agent): preserve failed mutation outcomes in summaries · merged via another change → f6c78be, 8519e94, #132166, #132141, #131244
  • #131312 fix(compression): keep the outcome in templated tool-result stubs · merged via another change → d6e740b, #132141
Closed issues · 1
  • Closed#131244Compaction summarizes a REFUSED write_file (and a rejected patch) as a success — the post-compaction agent then reports a write that never happened
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.40: 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
#132141, #132166
Closed issues
1
Attempts
2 PRs closed without merging
Fix link checked
3 Oct 2026

For your agent

The same facts, typed.