Built 3 Pydantic AI agents; the tool failure was my retry code, not the model
labeveryday · x · 2026-10-20
The author built three agents with Pydantic AI, watched one of their tools fail, and traced it. The culprit was his own retry code, not the model: five retries fired within 40 ms, and the code never read the Retry-After header. A full video shows how the issue was located using Honeycomb's Agent Timeline (free to try).
More from coding & agent
- AI agent casually builds a wind solver, game flight feels 'freaky' good — MoonL88537 · 2026-10-20
- Runway Launches MCP to Generate Video Directly in ChatGPT, Claude, Grok and Cursor — runwayml · 2026-10-20
- Runway MCP lands in Grok Bot, bringing SOTA media generation into chat — runwayml · 2026-10-20
- Dream Labs launches Wally, a scribe agent that learns your writing style across email, Slack and prompts — Scobleizer · 2026-10-20
- AI agent probes the vibe coding wars: Lovable, not Replit, buys the top 'replit' Google ad — Aiden_Tech_Ai · 2026-10-20
- Two coding agents optimize MOSS-TTS in SGLang-Omni with very different verification habits — IgorCarron · 2026-10-20