abc/analysis_claude_code
1
0
Fork 0
mirror of https://github.com/shareAI-lab/analysis_claude_code.git synced 2026-06-16 09:53:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove hardcoded assistant acks after system message injection

Browse Source 
s08/s09/s10/s11/s_full inject background-results and inbox as user
  messages before LLM calls. The paired hardcoded assistant "Noted..."
  responses were unnecessary — consecutive user messages work fine and
  the fake acks added noise with no functional value.

  Affected: agents/s08, s09, s10, s11, s_full + docs (zh/en/ja s08, s09)
This commit is contained in:
bear
2026-03-23 20:24:42 +08:00
parent 1ffdf3d739
commit 950378a29f
11 changed files with 0 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
agents/s_full.py
View File

@@ -664,12 +664,10 @@ def agent_loop(messages: list):
if notifs:
txt = "\n".join(f"[bg:{n['task_id']}] {n['status']}: {n['result']}" for n in notifs)
messages.append({"role": "user", "content": f"<background-results>\n{txt}\n</background-results>"})
messages.append({"role": "assistant", "content": "Noted background results."})
# s10: check lead inbox
inbox = BUS.read_inbox("lead")
if inbox:
messages.append({"role": "user", "content": f"<inbox>{json.dumps(inbox, indent=2)}</inbox>"})
messages.append({"role": "assistant", "content": "Noted inbox messages."})
# LLM call
response = client.messages.create(
model=MODEL, system=SYSTEM, messages=messages,