Cairn
NousResearch/hermes-agent

Consent guard fixes for headless clarify mode

Cluster 107068 · agent. Data as of

2 open items. Fix attempted, not merged.

The short answer

1open issue
1open PR
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. 1 PR closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
1 issue and 1 PR.

These members address a bug where headless/no-user auto-decide in the clarify flow could silently select authorization- or consent-semantic options without human approval. The fixes apply fail-closed behavior and decline consent-semantic choices in headless mode.

Open issues1

  • Issue#107068[Bug]: single-query clarify auto-decide can pick authorization-semantic Recommended option - silent self-authorization bypasses human-consent intent

Open PRs1

  • PR#107279fix(clarify): fail-closed consent guard on no-user auto-decide (#107068)

1 PR closed without merging

From the close comments: other 1

  • #107265 fix(clarify): decline consent-semantic options in headless mode · other → #107279, #107068
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
1 PR closed without merging

For your agent

The same facts, typed.

cluster/107068.json
cluster/107068.md