ModelCallScenario
Agents scenarios · Implementation: mlsysim/engine/scenario_definitions/agents.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
One call of prompt_tokens (+ instruction_tokens) in and output_tokens out at floors.
Notes
Equation: Compose mlsysim.solvers.ModelCallModel.
Assumptions: The stated fields are inputs to mlsysim.solvers.ModelCallModel; its documented validity regime, units, and modeling choices apply unchanged.
Excludes: This scenario adds no measurement, empirical calibration, or mechanisms beyond mlsysim.solvers.ModelCallModel.
References
Derivation: this scenario binds its input fields to the referenced implementation contracts: mlsysim.solvers.ModelCallModel. The methods below identify any additional arithmetic.
Examples
>>> from mlsysim import Scenarios
>>> case = Scenarios.CodingAgentFirstTurnCall
>>> type(case.result).__name__
'ModelCallResult'Attributes
| Name | Description |
|---|---|
| deadline | |
| floors | |
| instruction_tokens | |
| output_tokens | |
| prompt_tokens | |
| result | Evaluate this scenario through mlsysim.solvers.ModelCallModel.solve. Equation: pass |
| shared_prefix_tokens | |
| stage_success |
floors
Type: DecodeScenario.
Declared default: required.
prompt_tokens
Type: int.
Declared default: required.
output_tokens
Type: int.
Declared default: required.
instruction_tokens
Type: int.
Declared default: 0.
deadline
Type: Optional[Quantity].
Declared default: None.
stage_success
Type: Optional[Dict[str, float]].
Declared default: None.
result
engine.scenario_types.ModelCallScenario.result
Evaluate this scenario through mlsysim.solvers.ModelCallModel.solve. Equation: pass the stated fields to that implementation; its contract defines the calculation and feasibility tests. Units: each returned field follows the referenced result schema; no independent equation is evaluated by this wrapper.