AppendOnlyContextScenario
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.
A trajectory that appends each turn to its prompt and resends the whole history.
Notes
Equation: Compose mlsysim.solvers.AppendOnlyContextModel.
Assumptions: The stated fields are inputs to mlsysim.solvers.AppendOnlyContextModel; its documented validity regime, units, and modeling choices apply unchanged.
Excludes: This scenario adds no measurement, empirical calibration, or mechanisms beyond mlsysim.solvers.AppendOnlyContextModel.
References
Derivation: this scenario binds its input fields to the referenced implementation contracts: mlsysim.solvers.AppendOnlyContextModel. The methods below identify any additional arithmetic.
Examples
>>> from mlsysim import Scenarios
>>> case = Scenarios.AppendOnlyRepairContext
>>> type(case.result).__name__
'AppendOnlyContextResult'Attributes
| Name | Description |
|---|---|
| context_window | |
| initial_tokens | |
| result | Evaluate this scenario through mlsysim.solvers.AppendOnlyContextModel.solve. |
| tokens_per_turn | |
| turns |
initial_tokens
Type: Quantity.
Declared default: required.
tokens_per_turn
Type: Quantity.
Declared default: required.
turns
Type: int.
Declared default: required.
context_window
Type: Quantity.
Declared default: required.
result
engine.scenario_types.AppendOnlyContextScenario.result
Evaluate this scenario through mlsysim.solvers.AppendOnlyContextModel.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.