# NousResearch/hermes-agent · Kimi thinking/reasoning parameter handling fixes

## Open now

- Nothing open on GitHub.

Multiple issues and fixes addressing how thinking, reasoning_effort, and related parameters are sent (or incorrectly blocked) for Kimi and Kimi-coding Anthropic endpoints. The work spans guard clause scoping, parameter forwarding, and adaptive thinking behavior.

## TL;DR

- 5 member(s): 0 open issue(s), 2 closed issue(s), 0 open PR(s), 1 merged PR(s), 2 PR(s) closed without merging.
- A fix was merged to main in PR #67391. Verify it addresses your case.
- **Recommended:** read PR #67391 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## 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evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 `0.34`: 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.

## Closed / duplicate issues

- #18823: Kimi Coding: reasoning_config ignored due to _is_kimi_coding guard — thinking parameter never sent
- #56727: Kimi /coding endpoint thinking is incorrectly blocked (was PR #49143)

## Prior & competing PRs

- **#67391: fix(anthropic): preserve signed thinking blocks on Kimi-family replay (#66948 salvage)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`; implication `superseded`
  - files: `agent/anthropic_adapter.py`, `contributors/emails/[redacted:email]`, `tests/agent/test_anthropic_kimi_signed_thinking_replay.py`
- **#18898: Enable thinking/reasoning for kimi-for-coding via anthropic_messages**. closed without merge
  - maintainer direction: category `silent_close`; implication `active`
- **#56730: fix(anthropic): scope Kimi thinking guard to /coding endpoint only**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#67228`, `#13848`, `#67391`, `#67228`, `#67228`, `#56727`

## Fix status

- Merged to main in PR #67391 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-07-19`.
- Subsystem: `agent`