# NousResearch/hermes-agent · Grok 4.7 reasoning effort support on xAI

## Open now

- 1 issue, 3 PRs open on GitHub.
- #121796: xAI: grok-4.7 gets no reasoning.effort (allowlist stops at grok-4.6), so the setting is silently ignored
- PR #118414: fix(xai): send reasoning effort and priority tier for grok-4.7
- PR #121814: fix(agent): send Grok 4.7 reasoning effort on xAI Responses
- PR #138170: feat(xai): support Grok 4.7 on the Responses API

These items cover adding day-zero support for Grok 4.7 on the xAI provider and addressing a gap where reasoning.effort was silently ignored for that model due to an incomplete allowlist. Multiple fixes target sending reasoning.effort correctly for Grok 4.7.

## TL;DR

- 6 member(s): 1 open issue(s), 0 closed issue(s), 3 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.33`: 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

- #121796: xAI: grok-4.7 gets no reasoning.effort (allowlist stops at grok-4.6), so the setting is silently ignored

## Prior & competing PRs

- **#118413: feat(xai): Grok 4.7 day-zero support on the direct xAI provider**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#118414`, `#118414`
- **#118414: fix(xai): send reasoning effort and priority tier for grok-4.7**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#118414`
  - files: `agent/model_metadata.py`, `agent/transports/codex.py`, `hermes_cli/models.py`, `tests/agent/transports/test_codex_transport.py`, `tests/hermes_cli/test_fast_command.py`
- **#121814: fix(agent): send Grok 4.7 reasoning effort on xAI Responses**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `7cc3fb8cb5`, `#118414`
  - files: `agent/model_metadata.py`, `agent/transports/codex.py`, `tests/agent/transports/test_codex_transport.py`
- **#122545: fix(xai): send reasoning.effort for grok-4.7**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#121796`
- **#138170: feat(xai): support Grok 4.7 on the Responses API**. open
  - maintainer direction: category `silent_close`; implication `active`
  - files: `agent/chat_completion_helpers.py`, `agent/codex_responses_adapter.py`, `agent/conversation_compression.py`, `agent/model_metadata.py`, `agent/native_compaction.py`, `agent/reasoning_effort.py`, `agent/reasoning_timeouts.py`, `agent/transports/codex.py`, `agent/usage_pricing.py`, `hermes_cli/model_setup_flows.py`, `hermes_cli/models.py`, `hermes_cli/models_catalog_static.py`, `plugins/model-providers/xai/__init__.py`, `providers/base.py`, `tests/agent/test_model_metadata.py`, `tests/agent/test_native_compaction.py`, `tests/agent/test_usage_pricing.py`, `tests/agent/test_xai_responses_compact.py`, `tests/agent/transports/test_codex_transport.py`, `tests/hermes_cli/test_fast_command.py` (+5 more)

## Fix status

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