types
diapason.core.types
¶
Canonical data types shared across all Diapason primitives.
Conversation
dataclass
¶
Message
dataclass
¶
A single chat message (OpenAI-compatible structure).
text
property
¶
Return message content as text, treating None as empty.
ModelSpec
dataclass
¶
Metadata describing a language model.
Quantization
¶
Bases: str, Enum
Model quantization formats.
Role
¶
Bases: str, Enum
Chat message roles (OpenAI-compatible).
RoutingContext
dataclass
¶
Context describing a query for model routing decisions.
StepType
¶
Bases: str, Enum
Types of steps within an agent trace.
TelemetryRecord
dataclass
¶
Single telemetry observation recorded after an inference call.
ToolCall
dataclass
¶
A single tool invocation request embedded in an assistant message.
ToolResult
dataclass
¶
Result returned by a tool invocation.
Trace
dataclass
¶
Complete trace of an agent handling a query.
A trace captures the full sequence of steps an agent took to handle a query — which model was selected, what memory was retrieved, which tools were called, and the final response. Traces are the primary input to the learning system: by analyzing which decisions led to good outcomes, the system can improve routing, tool selection, and memory strategies.
add_step(step)
¶
Append a step and update running totals.
TraceStep
dataclass
¶
A single step within an agent trace.
Each step records what the agent did (route, retrieve, generate, tool_call, respond), its inputs and outputs, and timing.