# NousResearch/hermes-agent · Ollama/local provider hang and timeout issues

## Open now

- 5 issues, 4 PRs open on GitHub.
- #17913: OmniRoute compatibility: local custom providers can stall indefinitely on streamed chat completions
- #25629: \[Bug\]: Hermes Agent + Ollama Local — Hangs indefinitely with tool definitions
- #26339: \[Bug\] Connection reset by peer (errno 104) with Ollama local endpoint — 76KB payload rejected
- #26489: Hermes hangs when provider=custom + LiteLLM proxy + Ollama (no chat completion call after probing 404s)
- #56994: Requests to local Ollama models hang indefinitely with full CLI toolset (works via raw ollama run and cloud providers)
- PR #18703: fix(agent): keep local stream timeouts finite
- PR #18716: fix(agent): scale stream timeouts by max_tokens output budget
- PR #25638: fix(ollama): skip local num_ctx probe for explicit chat completions
- PR #26347: fix(cli): honor legacy minimal toolset config

Multiple bug reports and fixes related to indefinite hangs, stream timeouts, and connection issues when using local providers like Ollama, particularly with tool definitions and custom proxy setups. Associated fixes address stream timeout scaling, context probing behavior, and toolset configuration.

## TL;DR

- 9 member(s): 5 open issue(s), 0 closed issue(s), 4 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evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.15`: 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

- #17913: OmniRoute compatibility: local custom providers can stall indefinitely on streamed chat completions
- #25629: \[Bug\]: Hermes Agent + Ollama Local — Hangs indefinitely with tool definitions
- #26339: \[Bug\] Connection reset by peer (errno 104) with Ollama local endpoint — 76KB payload rejected
- #26489: Hermes hangs when provider=custom + LiteLLM proxy + Ollama (no chat completion call after probing 404s)
- #56994: Requests to local Ollama models hang indefinitely with full CLI toolset (works via raw ollama run and cloud providers)

## Prior & competing PRs

- **#18703: fix(agent): keep local stream timeouts finite**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `615ad97928f042d401b83142fd7d9daf50f48915`, `0430e71ec971d673a6d2a32fd54c1847683a16d2`
  - files: `run_agent.py`, `tests/agent/test_local_stream_timeout.py`
- **#18716: fix(agent): scale stream timeouts by max_tokens output budget**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `run_agent.py`, `tests/agent/test_stream_timeout_max_tokens.py`
- **#25638: fix(ollama): skip local num_ctx probe for explicit chat completions**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `9f408989c`
  - files: `run_agent.py`, `tests/run_agent/test_run_agent.py`
- **#26347: fix(cli): honor legacy minimal toolset config**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `hermes_cli/tools_config.py`, `tests/hermes_cli/test_tools_config.py`

## Fix status

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