cogency.types

Classes

AgentState

dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2)


AgentState(self, /, *args, **kwargs)

Context

Agent operational context.


Context(
  self,
  current_input: str,
  messages: List[Dict[str, str]] = None,
  tool_results: Optional[List[Dict[str, Any]]] = None,
  max_history: Optional[int] = None
)

ExecutionTrace

Lean trace engine - just stores entries with serialization safety.


ExecutionTrace(self)

ReasoningDecision

Structured decision from reasoning - NO JSON CEREMONY.


ReasoningDecision(
  self,
  should_respond: bool,
  response_text: Optional[str] = None,
  tool_calls: Optional[List[Dict[str, Any]]] = None,
  task_complete: bool = False
) -> None

Functions

format_full_debug

Format full debug trace (dev mode).


format_full_debug(trace: cogency.types.ExecutionTrace) -> str

format_trace

Format full trace with icons.


format_trace(trace: cogency.types.ExecutionTrace) -> str

summarize_trace

Generate clean summary from trace entries.


summarize_trace(trace: cogency.types.ExecutionTrace) -> str