# NousResearch/hermes-agent · Azure Foundry GPT-6 Luna/Sol Responses API routing

## Open now

- 1 issue, 2 PRs open on GitHub.
- #120263: \[Bug\] Azure Foundry gpt-6-luna requires Responses API when function tools and reasoning are enabled
- PR #139489: fix(azure-foundry): route gpt-6 to Responses and honour a caller's explicit api_mode
- PR #142809: GPT-6 behind Azure Foundry or a custom gateway no longer 400s on max_tokens or temperature (port cline#15137, salvage #135527 #67846)

A bug report and two related fix attempts addressing the need to route Azure Foundry GPT-6 Luna and Sol models to the Responses API when function tools and reasoning are enabled.

## TL;DR

- 5 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 2 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.40`: 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

- #120263: \[Bug\] Azure Foundry gpt-6-luna requires Responses API when function tools and reasoning are enabled

## Prior & competing PRs

- **#120327: fix(azure-foundry): route GPT-6 Luna/Sol to Responses API**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`
- **#124105: fix(azure-foundry): route GPT-6 Luna/Sol to the Responses API**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `0e427d788d2`, `0e427d788d2`, `#120327`, `#120263`, `#120327`, `#120327`, `#120327`, `#120327`, `#120263`
- **#139489: fix(azure-foundry): route gpt-6 to Responses and honour a caller's explicit api_mode**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/auxiliary_client.py`, `hermes_cli/models_catalog_static.py`, `tests/agent/test_auxiliary_client_azure_foundry.py`, `tests/hermes_cli/test_model_validation.py`
- **#142809: GPT-6 behind Azure Foundry or a custom gateway no longer 400s on max_tokens or temperature (port cline#15137, salvage #135527 #67846)**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/auxiliary_client.py`, `contributors/emails/[redacted:email]`, `hermes_cli/models_catalog_static.py`, `tests/agent/test_unsupported_temperature_retry.py`, `tests/hermes_cli/test_model_validation.py`, `tests/test_model_forces_max_completion_tokens.py`, `utils.py`, `website/docs/guides/azure-foundry.md`

## Fix status

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