Resume crashed agent workflows without repeating tool calls with PydanticAI
KhuyenTran16 · x · 2026-10-08
Covers PydanticAI's AgentRunResult: it stores the agent's output together with the run context, so a failed agent workflow can resume from where it stopped instead of redoing successful tool calls.
- Pain point: a full retry after a mid-workflow crash repeats completed tool calls, wasting time, raising API costs, and potentially re-running actions that should happen only once.
- Bonus: it also makes it easier to recover, debug, and audit agent runs.
Related event: PydanticAI tip: resume crashed agent workflows without re-running tools(2 posts)→
More from coding & agent
- LlamaIndex explains why Markdown is its default parsing output (HTML for merged headers) — llama_index · 2026-10-09
- 3 engineers, $1M and 1.5T tokens: Compound V2 rebuilds Office suite for AI agents — peterjliu · 2026-10-09
- While waiting for his AI coding limit to reset, a dev went back to hand-writing Go — haydendevs · 2026-10-09
- Orchestrator rebuilds its agent terminal: 13ms typing lag, 5x faster output — julianweisser · 2026-10-09
- Dev releases free 'AI Software Factory' ebook on agentic SDLC — Pavan_Belagatti · 2026-10-09
- Infisical Launches Agent Vault to Give AI Coding Agents API Access Without Real Credentials — ycombinator · 2026-10-09