core.response_result

Structured return type for FFAI response generation.

class ResponseResult(response, resolved_prompt='', usage=None, cost_usd=0.0, model='', duration_ms=0.0, status='success', condition_trace=None, condition_error=None, parsed=None, parsing_errors=None)[source]

Bases: object

Structured result from an FFAI response generation call.

Replaces side-channel attributes (last_usage, last_cost_usd, last_resolved_prompt) with a single typed return value.

Parameters:

response (Any)
resolved_prompt (str)
usage (TokenUsage | None)
cost_usd (float)
model (str)
duration_ms (float)
status (str)
condition_trace (str | None)
condition_error (str | None)
parsed (Any)
parsing_errors (list[str] | None)

response

The cleaned AI response (str, dict, list, etc.).

Type:: Any

resolved_prompt

The fully interpolated prompt sent to the model.

Type:: str

usage

Token usage from the API call, if available.

Type:: ffai.core.usage.TokenUsage | None

cost_usd

Estimated cost in USD for this call.

Type:: float

model

Model identifier used for this call.

Type:: str

duration_ms

Wall-clock duration of the LLM call in milliseconds.

Type:: float

status

Execution status – “success”, “skipped”, or “failed”.

Type:: str

condition_trace

The resolved condition expression (when condition is used).

Type:: str | None

condition_error

Error message if condition evaluation failed.

Type:: str | None

parsed

Validated Pydantic model instance (when response_model is used).

Type:: Any

parsing_errors

Validation error strings if structured output parsing failed.

Type:: list[str] | None

response: Any

resolved_prompt: str = ''

usage: TokenUsage | None = None

cost_usd: float = 0.0

model: str = ''

duration_ms: float = 0.0

status: str = 'success'

condition_trace: str | None = None

condition_error: str | None = None

parsed: Any = None

parsing_errors: list[str] | None = None

Classes