Kimi K2 HTTP 400 thinking/reasoning_effort conflict fixes
Cluster 16875. Data as of
Nothing open on GitHub. Fix merged in #18271 on 1 May 2026. Check it covers your case.
The short answer
- Known?
- Yes. 4 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #18271. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #18271. That is separate from the fix event. - Still open
- Nothing open on GitHub.
Multiple bug reports and fix attempts addressing HTTP 400 errors when OpenCode Go sends both 'thinking' and 'reasoning_effort' parameters simultaneously to Kimi K2 models. Also includes adjacent work on Moonshot schema cleanup and minor catalog/routing changes for Kimi and related models.
Open issues0
Open PRs0
Fixes on record
-
#18271 fix(moonshot): strip null-type anyOf branches + null/empty enum values (salvages #18177)
files:
agent/moonshot_schema.py,scripts/release.py,tests/agent/test_moonshot_schema.py
2 PRs closed without merging
From the close comments: closed without comment 1 · merged via another change 1
Closed issues · 1
- Closed#16875[Bug]: HTTP 400 error when using kimi-k2.6 model via OpenCode Go in Hermes Agent
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.50: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Merged PRs
- #18271
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 1 May 2026