ling/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-28 06:51:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(run_agent): prevent reasoning_content regression in DeepSeek/Kimi tool-call replay

Browse Source 
PR #15478 fixed missing reasoning_content for DeepSeek API but introduced
a regression: tool-call messages with genuine 'reasoning' field were
overwritten by empty-string fallback before promotion.

Re-order _copy_reasoning_content_for_api steps:
  1. Preserve explicit reasoning_content
  2. Promote 'reasoning' field (MOVED UP)
  3. DeepSeek/Kimi tool-call empty-string fallback (MOVED DOWN)
  4. Non-thinking provider cleanup

Fixes #15812, relates #15749, #15478.
This commit is contained in:
FocusFlow Dev
2026-04-26 12:16:32 +08:00
committed by Teknium
parent 15937a6b46
commit 63bf7a29b6
1 changed files with 11 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
run_agent.py
View File

@@ -7868,7 +7868,17 @@ class AIAgent:
api_msg["reasoning_content"] = existing
return
# 2. DeepSeek / Kimi thinking mode: tool-call turns that lack
# 2. Healthy session: promote 'reasoning' field to 'reasoning_content'
# for providers that use the internal 'reasoning' key.
# This must happen BEFORE the DeepSeek/Kimi tool-call check so that
# genuine reasoning content is not overwritten by the empty-string
# fallback (#15812 regression in PR #15478).
normalized_reasoning = source_msg.get("reasoning")
if isinstance(normalized_reasoning, str) and normalized_reasoning:
api_msg["reasoning_content"] = normalized_reasoning
return
# 3. DeepSeek / Kimi thinking mode: tool-call turns that lack
# reasoning_content are "poisoned history" — a prior provider (MiniMax,
# etc.) left them empty. DeepSeek returns HTTP 400 if reasoning_content
# is absent on replay; inject "" to satisfy the provider's requirement
@@ -7884,13 +7894,6 @@ class AIAgent:
api_msg["reasoning_content"] = ""
return
# 3. Healthy session: promote 'reasoning' field to 'reasoning_content'
# for providers that use the internal 'reasoning' key.
normalized_reasoning = source_msg.get("reasoning")
if isinstance(normalized_reasoning, str) and normalized_reasoning:
api_msg["reasoning_content"] = normalized_reasoning
return
# 4. DeepSeek / Kimi thinking mode: all assistant messages need
# reasoning_content. Inject "" to satisfy the provider's requirement
# when no explicit reasoning content is present.