Complex tasks in Claude Code can take a while. Run a few in parallel across different repos and it gets hard to track which ones are done and which ones need input. Claude Code supports hooks - shell commands that run in response to events. Hook into the Stop and Notification events to send a Slack message when a task completes or when Claude needs attention. The notification script Using PEP 723 inline metadata to keep everything in one file: ...
TIL: Inline dependencies in Python scripts
When sharing a Python script as a gist, you’d typically include a requirements.txt or a pyproject.toml with uv.lock. Multiple files for one script. Turns out there’s a cleaner way. PEP 723 lets you embed dependencies and Python version requirements directly in the script: # /// script # requires-python = ">=3.11" # dependencies = [ # "requests", # "rich", # ] # /// import requests from rich import print response = requests.get("https://api.github.com/zen") print(f"[bold green]{response.text}[/bold green]") Run it with uv: ...
Validating LLM Outputs in Go
The Problem LLMs hallucinate. They return wrong types, invalid values, and malformed data. A rating meant to be 1-5 comes back as 10. An email field contains “not provided”. A required field is missing entirely. In Python, Pydantic is the standard solution - define a model, validate the output, catch errors before they crash your app. But what about Go? godantic brings Pydantic-style validation to Go. Full JSON schema generation for LLM APIs. This post shows common patterns for validating LLM outputs in Go. ...
Detecting event loop blocking in asyncio
If you’re writing async Python, you’ve probably blocked the event loop without knowing it. Your code runs. Your tests pass. But in production, p90 latencies spike and timeouts appear seemingly at random. The culprit? Synchronous code hiding inside your async def functions. Python’s asyncio is cooperative. When you await something, you’re yielding control back to the event loop so other tasks can run. But if you call synchronous code, even accidentally, the entire event loop freezes. Every other coroutine waits. Every concurrent request hangs. Every other user gets blocked. ...
The OpenAI Compatibility Paradox
The promise of a standardized interface for LLMs via OpenAI-compatible endpoints is compelling. In theory, it allows for a plug-and-play architecture where switching models is as trivial as changing a base_url. In practice, this compatibility is often an illusion. I’ve spent the past year building a multi-provider LLM backend, and the pattern is always the same: things work for basic text generation, then break the moment you need production-critical features. ...
Streaming Partial JSON from LLMs in Go
The Problem LLMs stream JSON token by token. Your structured output arrives as: {"project": {"name": "Mo {"project": {"name": "Mobile App", "status": "in_prog {"project": {"name": "Mobile App", "status": "in_progress"}, "tasks": [{"title": "UI Redes ... Standard encoding/json fails on every chunk except the last: json.Unmarshal([]byte(`{"project": {"name": "Mo`), &result) // error: unexpected end of JSON input This was recently highlighted by swyx as a #1 or #2 performance issue in AI applications. You’re forced to wait for the complete response before showing anything to users - negating the entire point of streaming with json mode or structured output. ...
Jina 🤝 Linkerd
Let’s discuss today about a way to debug your Executors & Flows using Linkerd service mesh. What is a Service Mesh? From Linkerd docs A service mesh is a tool for adding observability, security, and reliability features to “cloud native” applications by transparently inserting this functionality at the platform layer rather than the application layer. Few of the commonly used service meshes are Linkerd, Istio, Consul etc. Why Linkerd? Significantly lighter than competitors. Basic request tracing with no additional config. Telemetry & monitoring exposing Golden metrics. The simplicity of its usage is mind-blowing. Just annotate the K8S Deployment, and you’re done. How does Linkerd work? While this majorly underestimates the magic Linkerd brings, here are the major components. Feel free to go through the architecture in official docs. ...
Jina ❤️ Serverless
What is Jina? From the Docs Jina is a framework that empowers anyone to build cross-modal and multi-modal applications on the cloud. What is serverless? From Wikipedia Serverless computing is a cloud computing execution model in which the cloud provider allocates machine resources on demand, taking care of the servers on behalf of their customers. Also, “Serverless” is a misnomer in the sense that servers are still used by cloud service providers to execute code for developers. However, developers of serverless applications are not concerned with capacity planning, configuration, management, maintenance, fault tolerance, or scaling of containers, VMs, or physical servers. ...