Verifying LLM-Written SDK Code Against the Pinned Version: A Recipe Against Type Hallucination

Mon, 18 May 2026 00:00:00 +0000

An agent writes a 200-line streaming-client implementation against your project’s pinned SDK. It compiles cleanly in the model’s head. The test code references SomeStreamEvent, the streaming function signature is func NewStreaming(ctx, params) (stream, error), and the iteration loop uses stream.Recv(). The reviewer skims it, sees plausible naming, approves. CI fails with “undefined: SomeStreamEvent”. The agent escalates: “the SDK is broken — package not found.” Hours later, somebody figures out that the SDK they’re pinned to has none of those symbols. The import path is different. The function returns one value not two. The iteration pattern is Next() / Current() / Err(), not Recv(). The model invented the API.

Agent-Debugging on Agent Zone

Verifying LLM-Written SDK Code Against the Pinned Version: A Recipe Against Type Hallucination