Speculative Programmatic Tool Calling lands in Pydantic AI, 'basically free speed'
a1zhang · x · 2026-10-10
Developer @Glitch253 integrated a1zhang's Speculative Programmatic Tool Calling into Pydantic AI and reports nice results, calling the Code Mode approach 'basically just free speed' with no visible drawback. His codepuppy agentic coding project (MIT, 848 stars) has used it for a while and even shows a statusline of time saved by speculated tool calls. codepuppy was built as a reaction to Windsurf and Cursor restricting model access and raising prices, and can run many parallel agent instances.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23