NousResearch/hermes-agent

Unachievable goals misclassified as done in kanban

Cluster 100954. Data as of 2026-10-25 11:21 UTC

Nothing open on GitHub. Fix merged in #101278 on 2 Sep 2026. Check it covers your case.

open issues

open PRs

items grouped

Known?: Yes. 3 related items grouped here, 1 issue already closed.
Fix event: A fix was merged to main in PR #101278. Check it covers your case. No release data is tracked.
Tracker: The maintainers' tracker marks this resolved, deciding PR #101278. That is separate from the fix event.
Still open: Nothing open on GitHub.

Next step: read #101278, then check it covers your case.

Read #101278 Pick up a Lab task

A bug causes the goal_judge to return a 'done' verdict for genuinely unachievable goals instead of marking them as blocked. The members address detecting and correctly routing unachievable goals to a blocked state rather than silently completing them.

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.

#101278 fix(kanban): unachievable goals land in blocked, not done (#100954, salvage #101108)

merged to main

files: contributors/emails/[email protected], hermes_cli/goals.py, hermes_cli/kanban.py, hermes_cli/loops.py, tests/hermes_cli/test_goals.py, tests/hermes_cli/test_kanban_goal_mode.py, tests/hermes_cli/test_loops.py, tools/kanban_tools.py, website/docs/user-guide/features/goals.md, website/docs/user-guide/features/kanban.md, website/docs/user-guide/features/loops.md

1 PR closed without merging

From the close comments: merged via another change 1

#101108 fix(kanban): judge unachievable goals as blocked, never done · merged via another change → 5c6cbbc, #101278

Closed issues · 1

Closed#100954goal_judge's "genuinely unachievable" branch still returns verdict=done, so an impossible goal completes silently instead of blocking (kanban_complete gate can't tell the two apart)

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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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: #101278
Closed issues: 1
Attempts: 1 PR closed without merging
Fix link checked: 2 Sep 2026

For your agent

The same facts, typed.

cluster/100954.json
cluster/100954.md