In this configuration:<\/p>\n
The security-gate group runs gate.py before every code_execution or write_file call. If the script returns {“decision”: “deny”, “reason”: “…”}, the tool call is skipped and the rejection reason is passed into the model\u2019s context.The auto-format group runs auto_lint.py after every tool finishes to enforce code styling.Hooks also support http type handlers that POST directly to an external endpoint.<\/p>\n
For complete HTTP hook definitions and failure handling semantics, refer to the hooks documentation<\/a>.<\/p>\n Teams are already using hooks to build production-grade validation pipelines. For example, AI-native investment bank Offdeal uses post_tool_execution hooks to run automated image verification inside the remote sandbox.<\/p>\n “OffDeal is an AI-native investment bank, and Archie is the AI analyst our bankers use every day. A requirement for banker-ready decks is company logos: buyer tables, sponsor columns, tombstone grids, often 30+ logos in a single deck, every one of which must be the right company, the appropriate size and aspect ratio, contain the name, have a transparent background, and have a high contrast when placed on a white slide.<\/p>\n Before agent hooks, we couldn\u2019t do this on Gemini\u2019s managed agents: the sandbox is remote, so our validation code had nowhere to run. With hooks, a post_tool_execution hook triggers our pipeline inside the sandbox the moment Archie writes its company list, fetching candidates, enforcing pixel-level quality checks, verifying each logo with Gemini vision, and publishing a manifest of approved files that are the only images allowed into the deck.”<\/p>\n – Alston Lin, Founder & CTO of OffDeal<\/p>\n Cost control and automation featuresFree tier availability<\/p>\n Managed agents are now available on free tier projects<\/a>. Developers can experiment with agentic workflows using an API key from a project without active billing<\/a>.<\/p>\n Budget controls<\/p>\n Because managed agents execute multi-turn autonomous loops, complex tasks can consume significant token budgets. To prevent runaway tasks, you can pass max_total_tokens inside agent_config to cap total consumption (input + output + thinking).<\/p>\n