common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(kimi): don't send Anthropic thinking to api.kimi.com/coding (#13826)

Browse Source 
Kimi's /coding endpoint speaks the Anthropic Messages protocol but has
its own thinking semantics: when thinking.enabled is sent, Kimi validates
the history and requires every prior assistant tool-call message to carry
OpenAI-style reasoning_content. The Anthropic path never populates that
field, and convert_messages_to_anthropic strips Anthropic thinking blocks
on third-party endpoints — so after one tool-calling turn the next request
fails with:

  HTTP 400: thinking is enabled but reasoning_content is missing in
  assistant tool call message at index N

Kimi on chat_completions handles thinking via extra_body in
ChatCompletionsTransport (#13503). On the Anthropic route, drop the
parameter entirely and let Kimi drive reasoning server-side.

build_anthropic_kwargs now gates the reasoning_config -> thinking block
on not _is_kimi_coding_endpoint(base_url).

Tests: 8 new parametric tests cover /coding, /coding/v1, /coding/anthropic,
/coding/ (trailing slash), explicit disabled, other third-party endpoints
still getting thinking (MiniMax), native Anthropic unaffected, and the
non-/coding Kimi root route.
This commit is contained in:
Teknium
2026-04-21 21:19:14 -07:00
committed by GitHub
parent 7b79e0f4c9
commit 410f33a728
2 changed files with 130 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
agent/anthropic_adapter.py
View File

@@ -1426,11 +1426,25 @@ def build_anthropic_kwargs(
# MiniMax Anthropic-compat endpoints support thinking (manual mode only,
# not adaptive). Haiku does NOT support extended thinking — skip entirely.
#
# Kimi's /coding endpoint speaks the Anthropic Messages protocol but has
# its own thinking semantics: when ``thinking.enabled`` is sent, Kimi
# validates the message history and requires every prior assistant
# tool-call message to carry OpenAI-style ``reasoning_content``. The
# Anthropic path never populates that field, and
# ``convert_messages_to_anthropic`` strips all Anthropic thinking blocks
# on third-party endpoints — so the request fails with HTTP 400
# "thinking is enabled but reasoning_content is missing in assistant
# tool call message at index N". Kimi's reasoning is driven server-side
# on the /coding route, so skip Anthropic's thinking parameter entirely
# for that host. (Kimi on chat_completions enables thinking via
# extra_body in the ChatCompletionsTransport — see #13503.)
#
# On 4.7+ the `thinking.display` field defaults to "omitted", which
# silently hides reasoning text that Hermes surfaces in its CLI. We
# request "summarized" so the reasoning blocks stay populated — matching
# 4.6 behavior and preserving the activity-feed UX during long tool runs.
if reasoning_config and isinstance(reasoning_config, dict):
_is_kimi_coding = _is_kimi_coding_endpoint(base_url)
if reasoning_config and isinstance(reasoning_config, dict) and not _is_kimi_coding:
if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
effort = str(reasoning_config.get("effort", "medium")).lower()
budget = THINKING_BUDGET.get(effort, 8000)