Skip to content

fix: use agent context_window_size across all channels instead of hardcoded limits #344

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
nap-liu wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: use agent context_window_size across all channels instead of hardcoded limits #344

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions backend/app/api/feishu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1497,11 +1497,11 @@ async def _call_agent_llm(
return f"⚠️ {agent.name} 未配置 LLM 模型，请在管理后台设置。"

# Build conversation messages (without system prompt — call_llm adds it)
# NOTE: history is already truncated to ctx_size by the SQL .limit() in
# each caller, so no further slicing is needed here.
messages: list[dict] = []
from app.models.agent import DEFAULT_CONTEXT_WINDOW_SIZE
ctx_size = agent.context_window_size or DEFAULT_CONTEXT_WINDOW_SIZE
if history:
messages.extend(history[-ctx_size:])
messages.extend(history)
messages.append({"role": "user", "content": user_text})

# Use actual user_id so the system prompt knows who it's chatting with
Expand Down