
AI & Machine Learning17 min
OpenAI Agents SDK 0.23: Tool Error Redaction Tested
I ran openai-agents 0.22.3 and 0.23.1 with a scripted model. The default tool error message no longer sends exception text to the model or to trace spans.
Tag
81 posts
Page 1 of 7

AI & Machine Learning17 min
I ran openai-agents 0.22.3 and 0.23.1 with a scripted model. The default tool error message no longer sends exception text to the model or to trace spans.

AI & Machine Learning16 min
AG-UI 1.0 migration, tested: what a 1.0.1 client does with 0.x streams, the multimodal tool result that crashed a 0.x client, and a protocolVersion fix.

AI & Machine Learning35 min
ADK 2.0 Workflow retries are jittered, unmatched routes raise no error, and timeouts can't stop blocking code. Tested: google-adk 2.10.0, Python 3.10-3.13.

AI & Machine Learning14 min
The ratified MCP Tasks extension needs three new methods. The official Python SDK v2.2.0 still doesn't implement them. Here's a tested server that does.

AI & Machine Learning14 min
The Agent2Agent (A2A) protocol reached v1.0 with 150+ backers and nearly 24,000 GitHub stars. Learn how it differs from MCP and build a working Python agent.
LLM & Integration10 min
Build smarter apps with the OpenAI API: chat completions, vision, embeddings, function calling, and assistants. Patterns, runnable code, and real cost tips.
Backend Development14 min
Python best practices for 2026: pyproject.toml, uv, Ruff, type hints, pytest, free-threaded 3.14, structured logging, and security patterns for clean, fast, shippable code.
Backend Development13 min
Hands-on 2026 tutorial: build a tiny, secure Distroless Python container for a FastAPI app using uv 0.11.8, multi-stage builds, and a non-root runtime user.
AI & Machine Learning16 min
A practical, working PyTorch guide for 2026. Tensors, autograd, training loops, transfer learning, torch.compile, and deployment — all with code that runs on the current PyTorch 2.x release.
AI & Machine Learning19 min
TensorFlow 2 zero to production: tensors, Keras Sequential and Functional, tf.data, GradientTape, distributed training, TF Serving and TF Lite — all in Colab.
AI & Machine Learning10 min
Deep learning fundamentals, practical: feedforward, CNN, RNN, Transformer. Training, optimization, regularization — with a runnable PyTorch neural network.
Python async for AI: asyncio.gather, semaphores, streaming, and the patterns that cut latency for LLM and inference pipelines handling parallel requests.