Tag
6 posts tagged.
Measured on @openai/agents 0.18.0: the built-in client-side tool_search loader matches paths against tool names by exact string equality, and a miss returns zero tools with no error and no warning. The failure arrives one turn later as an error that blames the model.
Measured on @voltagent/core 2.11.0: the first agent call lazily starts three setInterval timers that are never unref'd, so your Node process stays alive forever. Two of them poll 20 times a second. Here is the reproduction, the cause and the fix.
Measured on ai 7.0.118 and zod 4.6.5: a .refine() on a tool input schema is stripped before the schema reaches the model, with no warning. z.string().startsWith('acct_') arrives as a pattern; the same rule written as a refinement arrives as nothing.
On ai 7.0.116, generateText and streamText run exactly one step by default. Pass tools without stopWhen and the model calls a tool, your tool runs, and you get an empty string with no error. The same package defaults ToolLoopAgent to twenty. Measured on the wire, with the bundle lines that cause it.
On ai 7.0.114, whatever your tool execute function throws is serialised and sent to the model provider in a tool_result block marked is_error. The documented toModelOutput hook is skipped on that path. Measured first-party with a local capture server, no API key.
Wire AbortController from the browser into the Claude stream and your tools, cancel a run even after a reload, and clean up partial side effects safely.
