Skip to content

types

diapason.learning.spec_search.diagnose.types

Data types for the diagnose phase.

Lightweight dataclasses used as return types by diagnostic tools and as internal data carriers. These are NOT pydantic models — they don't need validation or JSON schema generation.

See spec §5.2 for the tool return type rationale.

BenchmarkTask dataclass

One task from the personal benchmark.

ComparisonResult dataclass

Structured comparison between student and teacher outputs.

DiagnosticTool dataclass

A tool exposed to the teacher in the diagnose phase.

Unlike BaseTool, these are not registered in ToolRegistry. They are lightweight wrappers: a name, description, JSON schema for parameters, and a callable that implements the tool.

to_openai_function()

Convert to OpenAI function-calling format.

StudentRun dataclass

Result of re-executing the local student on a benchmark task.

TeacherRun dataclass

Result of the teacher running itself on a benchmark task.

ToolCallRecord dataclass

One teacher tool call, persisted to the JSONL log.

to_jsonl_dict()

Serialize to a JSON-safe dict for JSONL output.

ToolMeta dataclass

Metadata about a tool in the ToolRegistry.

TraceMeta dataclass

Lightweight summary of a trace for browsing.