8000 chore: Update triaging agent's model and event based prompt by copybara-service[bot] · Pull Request #1479 · google/adk-python · GitHub
[go: up one dir, main page]
Skip to content

chore: Update triaging agent's model and event based prompt #1479

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

chore: Update triaging agent's model and event based prompt #1479

Show file tree
Hide file tree
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: 5 additions & 1 deletion contributing/samples/adk_triaging_agent/agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
import os

from google.adk import Agent
from google.genai import types
import requests

GITHUB_TOKEN = os.getenv("GITHUB_TOKEN")
Expand Down Expand Up @@ -115,7 +116,7 @@ def add_label_to_issue(issue_number: str, label: str):
)

root_agent = Agent(
model="gemini-2.5-pro-preview-05-06",
model="gemini-2.5-pro",
name="adk_triaging_assistant",
description="Triage ADK issues.",
instruction=f"""
Expand All @@ -142,4 +143,7 @@ def add_label_to_issue(issue_number: str, label: str):
list_issues,
add_label_to_issue,
],
generate_content_config=types.GenerateContentConfig(
temperature=0.0,
),
)
3 changes: 2 additions & 1 deletion contributing/samples/adk_triaging_agent/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,8 @@ async def run_agent_prompt(session: Session, prompt_text: str):
f" \"{specific_issue['body']}\"\n\nBased on the rules, recommend an"
" appropriate label and its justification."
" Then, use the 'add_label_to_issue' tool to apply the label "
"directly to this issue."
"directly to this issue. Only label this issue, do not process"
" any other issues!"
f" The issue number is {specific_issue['number']}."
)
await run_agent_prompt(session_11, prompt)
Expand Down
0