Gemini 4 Argon pattern: server-side background execution for minutes-long reasoning runs
rseroter · x · 2026-10-14
A developer shares the key architectural pattern for building with Gemini 4 Argon: server-side background execution. Frontier reasoning models can spend minutes generating tens of thousands of tokens on tasks like legacy code migrations, formal proofs, and transaction simulations, so long runs shouldn't block a synchronous request.
Key points:
- Set background=True via the Interactions API and poll interaction.status client-side
- Example in the screenshot: a full proof of the prime number theorem with maxoutputtokens: 262144 and thinkinglevel: high, stitching text across server-side continuation hops
- A migration checklist highlights 1M token output; Antigravity users can install the gemini-api-dev skill and run /gemini-api-dev migrate to auto-migrate apps
Related event: Gemini 4 Argon Server-side Background Execution Enables 260K-token Runs(2 posts)→
More from coding & agent
- Google DeepMind team: AI agents boost ML engineering but can't run autonomous R&D end-to-end — HaydnBelfield · 2026-10-14
- Harness Launches a $149 Command Center to Run All Your AI Agents — dee_hw · 2026-10-14
- Dev runs Codex as a shell tool inside Claude for code review, skipping tmux hassles — abhi9u · 2026-10-14
- Using AI agents turns out to be accidental management training — dr_alphalyrae · 2026-10-14
- Rerunning the single-task experiment across all ipython harness versions produced the benchmark plot — yb2698 · 2026-10-14
- Small-model agent harnesses are fragile to environment noise — open-source ipython harness released — yb2698 · 2026-10-14