Gemini API runs multi-hop continuations server-side with polling, step aggregation and thinking levels
clmt · x · 2026-10-14
How Gemini API interactions work for long-running agent tasks
- Server-side continuation hops: the Gemini API manages multi-hop token continuations on Google infrastructure, so your client connection doesn't hang.
- Polling: your backend polls client.interactions.get(id=...) until the status leaves inprogress.
- Step aggregation: each hop appends a modeloutput step to interaction.steps; join the text across steps when done.
- Thinking budget control: thinkinglevel: low for quick queries, medium (default) for balanced tasks, high for hard math and system-level refactoring.
Related event: Gemini 4 Argon Server-side Background Execution Enables 260K-token Runs(2 posts)→
More from coding & agent
- Consultancy ships free playbook for a product design harness that keeps coding agents on-brand — thisiskp_ · 2026-10-14
- Reward-Rate Policy Gradient: Teaching Agentic RL to Pay for Execution Time — sherryyangML · 2026-10-14
- tldraw plugin runs embeddable canvases inside ChatGPT, with app logic drawn as statecharts — max__drake · 2026-10-14
- MazeBench record: Schema with GPT-6 Astra hits 33%, beating top-50 human median — patience_cave · 2026-10-14
- Perplexity Computer decompiles a Windows-only keyboard app with Ghidra and ports it to native Linux Rust — AravSrinivas · 2026-10-14
- CMU Paper: Most Wrong Actions by System One Models Follow Correct Reading of State — CarnegieMellonU · 2026-10-14