Pydantic AI adds long-decode support for Gemini 4 Argon, auto-following continuation tokens past the 32K limit
m4rkmc · x · 2026-10-14
Pydantic AI now supports long decode for Gemini 4 Argon. A single Argon request caps at 32K output tokens (64K streamed); Pydantic AI lets you set a larger output budget and automatically follows Google's continuation token, delivering one agent run as one combined response — no manual chunking required.
More from coding & agent
- AI software factories: faster coding doesn't mean faster software delivery — Pavan_Belagatti · 2026-10-14
- Naming "Context Inertia": agents fixate on wrong ideas instead of backtracking — dbreunig · 2026-10-14
- GPT-6 Astra + Blender MCP produces a 489MB all-3D hotel website concept — sidahuj · 2026-10-14
- LeanLLM brings a unified LiteLLM-style LLM client to the Lean 4 ecosystem — hargup13 · 2026-10-14
- Gemini 4 Argon builds a Jupiter/Moog combo synth in one HTML file, under 30 minutes — GCWebDesigner · 2026-10-14
- ViteConf 2026 lineup revealed: Evan You on developer tooling in the agentic era — cnakazawa · 2026-10-14