# NousResearch/hermes-agent · Kanban task creation: max_runtime_seconds=0 handling and null placeholders

## Open now

- 1 issue, 2 PRs open on GitHub.
- #38366: \[Bug\] max_runtime_seconds=0 on a kanban task silently kills workers — no validation
- PR #38373: fix(kanban): treat max_runtime_seconds=0 as no limit instead of instant timeout
- PR #142168: fix(kanban): OpenAI models answer null instead of placeholders in kanban_create (#38366)

Most members concern kanban behavior around max_runtime_seconds=0, with one bug report about missing validation and one pull request treating 0 as no limit. A third member covers a different kanban_create issue involving OpenAI models returning null instead of placeholders, so the group is only partly one theme.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 0 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.67`: the share of member 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.

## Open related issues

- #38366: \[Bug\] max_runtime_seconds=0 on a kanban task silently kills workers — no validation

## Prior & competing PRs

- **#38373: fix(kanban): treat max_runtime_seconds=0 as no limit instead of instant timeout**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `hermes_cli/kanban_db.py`, `tests/hermes_cli/test_kanban_db.py`
- **#142168: fix(kanban): OpenAI models answer null instead of placeholders in kanban_create (#38366)**. open
  - maintainer direction: category `silent_close`; implication `active`
  - files: `agent/openai_schema.py`, `agent/transports/chat_completions.py`, `tests/agent/test_openai_schema.py`, `tests/agent/transports/test_chat_completions.py`, `tests/tools/test_kanban_tools.py`, `tools/kanban_tools_schemas.py`

## Fix status

- No merged fix on record.
- Subsystem: `agent`