mitzen

Let's say you would like to ensure that you pipeline operates in a sequential manner - lockBehaviour  option- sequential in a sense that if user A trigger pipeline at 12:00 and then another user B trigger pipeline at 12:01, user B will have to wait until user A completes.  If user a cancel it, User B will have to wait until the cancellation completes. This can take a while before next pipeline start executing.  There are 2 option available - sequential and runLatest. stages: - stage: A   lockBehavior: sequential   jobs:   - job: Job     steps:     - script: Hey! If we do not specify, lockBehaviour is runLatest. Potential issue :- Queued runs waiting on a check can eventually time out, so B could fail if it waits too long behind other runs. Only runs targeting the same protected resource (for example, the same environment, repository, agent pool, service connection) compete for the lock.

With Azure Devops future uncertain - find myself hardly read or keep up to date with it. Well just in case, I do, there is always this link here to goto  :) https://learn.microsoft.com/en-us/azure/devops/release-notes/2026/sprint-280-update

In gcp agentic platform mcp server is an abtraction that allows your agent to call a actual MCP hosted elsewhere.  It is not to create and deploy an MCP server. You can of course do that via Google Cloud run.  Typically you can use the following code in your agentic runtime to call this MCP server  import os from google.adk.integrations.agent_registry import AgentRegistry from google.auth import default from google.adk.agents import Agent from google.adk.models import Gemini from google.genai import types _ , project_id = default() LOCATION = os.environ.setdefault( "GOOGLE_CLOUD_LOCATION" , "us-central1" ) MCP_SERVER_NAME = os.environ.get( "MCP_SERVER_NAME" , "agentregistry-00000000-0000-0000-bd07-35253020786b" ) os.environ[ "GOOGLE_GENAI_USE_VERTEXAI" ] = "True" registry = AgentRegistry(project_id=project_id, location=LOCATION) mcp_toolset = registry.get_mcp_toolset(     f "projects/project-id/locations/us-cen...

 This is an example of how we can deployment agent runtime agent with environment variables. The key settings here is the "env_vars".  import asyncio from urllib import response from google . adk . agents import Agent from google . adk . runners import Runner from google . adk . sessions import InMemorySessionService from google . genai import types from google . adk . agents . callback_context import CallbackContext from google . adk . models . llm_request import LlmRequest from vertexai import types as vertex_types from google . genai import types import vertexai import agentplatform from agentplatform import types   # check below: this is my assumption from agentplatform . frameworks import AdkApp # 1. Define the callback function def inspect_llm_input ( callback_context : CallbackContext , llm_request : LlmRequest ):     """Callback triggered directly before ADK sends payload to the LLM."""     print ( ...

When you're calling your agentic app, you ran into this error  raise ClientError(status_code, response_json, response) google.genai.errors.ClientError: 404 NOT_FOUND. {'error': {'code': 404, 'message': 'Not Found. However, the operation was successful.', 'status': 'NOT_FOUND'}} And then you try to see what is wrong. This can lead into a whole rabbit whole. Took me 2 hours to resolve this.  This happens to me because I enabled gateway agent on my agent. So an operation that will generally be fine, has raise this error.  I had to disabled that be redeploy my runtime and removing gateway from it.

So what happens after you have deployed your agent to agentic platform, you should have code to call it. How can we do that? import asyncio import agentplatform client = agentplatform .Client(     project = "project-your-project-id" ,     location = "us-central1" , ) async def main ():     runtime = client .runtimes.get(         name = "projects/your-project-id/locations/us-central1/ reasoningEngines/2026277059566764032"     )     print ( runtime )     runtime .operation_schemas()     session = await runtime .async_create_session( user_id = "user_123" )     async for event in runtime .async_stream_query(         user_id = "user_123" ,         message = "What is my account balance including pending charges for user_123?" ,     ):         print ( event ) asyncio . run ( main ()) It is even documente...

GCP serverless model are model like gemini-2.5-flash, gemini-3.5-flash that are generally avaiable. This include Claude Sonnet or Haiku 5.5.  If you ever wanted  your agent to use these model, all you need to do is the following code.  banking_agent = Agent (     name = "account_assistant" ,     model = "gemini-2.5-flash" ,     instruction = "You are a helpful customer support agent. Answer questions concisely." ,     tools = [ get_user_account_balance ],     before_model_callback = inspect_llm_input ) And that's is all. Can you believe it. Deploy it and then go to the playground to test it out.  The full code base is here :- import asyncio from urllib import response from google . adk . agents import Agent from google . adk . runners import Runner from google . adk . sessions import InMemorySessionService from google . genai import types from google . adk . agents . callback_context import Callba...

We can use the following python to perform deployment. Also notice that this is more configurable compare to glcoud command line.  So we will be deploying an agent to google agent runtime and it will use an gateway. This gateway is an ingress (client-to-agent)  and it is called my-first-gateway. If you have another setup client-to-everywhere else (egress) setup would be slightly different. import asyncio from urllib import response from google . adk . agents import Agent from google . adk . runners import Runner from google . adk . sessions import InMemorySessionService from google . genai import types from google . adk . agents . callback_context import CallbackContext from google . adk . models . llm_request import LlmRequest from vertexai import types as vertex_types from google . genai import types import vertexai # Ensure this matches your actual GCP Project ID, not a placeholder vertexai . init ( project = "project-project-id" , location = ...

GLM OCR is pretty lightweight and fit for purpose when i tried it out on invoice images.  Here is the code for setting up and running it locally.  """ Extract line items from an invoice image using a local model served at http://localhost:8888/v1, called through LiteLLM. Setup:     pip install litellm pydantic     export LOCAL_API_KEY="your-local-server-key" Usage:     python extract_invoice_local.py invoice.jpg """ import base64 import json import mimetypes import os import re import sys from typing import Optional import litellm from pydantic import BaseModel # Same settings as your LiteLlm config --------------------------------------- MODEL = "openai/ggml-org/GLM-OCR-GGUF" API_BASE = "http://localhost:8888/v1" API_KEY = "sk-unsloth-4d0a1b198bd177a2a72ee1954585342a"   # keep the key out of source code TEMPERATURE = 0.0 # Ask the server to constrain output to the schema (llama.cpp-based server...