# NousResearch/hermes-agent · LM Studio remote context length and model URL fixes

## Open now

- 2 issues, 4 PRs open on GitHub.
- #47200: \[Bug\]: fail to detect context length from remote LMStudio instances
- #65481: Support models_url in custom_providers to decouple model discovery from inference base URL
- PR #47244: fix(agent): query LMStudio native API for context_length on remote instances
- PR #47698: fix(agent): fall back to max_context_length in LM Studio probe
- PR #59094: \[codex\] fix LM Studio context metadata fallback
- PR #65550: feat(providers): support custom models_url

These issues and pull requests address failures to detect context length from remote LM Studio instances and add support for a configurable models_url to decouple model discovery from the inference base URL.

## TL;DR

- 6 member(s): 2 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evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 `0.29`: 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

- #47200: \[Bug\]: fail to detect context length from remote LMStudio instances
- #65481: Support models_url in custom_providers to decouple model discovery from inference base URL

## Prior & competing PRs

- **#47244: fix(agent): query LMStudio native API for context_length on remote instances**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/model_metadata.py`, `tests/agent/test_model_metadata_local_ctx.py`
- **#47698: fix(agent): fall back to max_context_length in LM Studio probe**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `01ad0aacaf4f5f8a23c72ed14e36d642b930853d`
  - files: `agent/model_metadata.py`
- **#59094: \[codex\] fix LM Studio context metadata fallback**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#47244`
  - files: `agent/model_metadata.py`, `tests/agent/test_model_metadata_local_ctx.py`
- **#65550: feat(providers): support custom models_url**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `cli-config.yaml.example`, `hermes_cli/config.py`, `hermes_cli/main.py`, `hermes_cli/model_setup_flows.py`, `hermes_cli/model_switch.py`, `hermes_cli/models.py`, `hermes_cli/providers.py`, `tests/hermes_cli/test_custom_provider_model_switch.py`, `tests/hermes_cli/test_model_switch_custom_providers.py`, `tests/hermes_cli/test_model_validation.py`, `tests/hermes_cli/test_provider_config_validation.py`, `tests/hermes_cli/test_user_providers_model_switch.py`, `website/docs/integrations/providers.md`

## Fix status

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