Runs and transcripts¶
One run's details, transcript, workspace, logs and telemetry.
runs ¶
Runs: details, transcripts, workspace files, logs, GPU telemetry, cancel, retry and re-grade.
Transcript ¶
Bases: list[dict[str, Any]]
A run's transcript: every event LLMDyno's proxy recorded between the agent and the model, in order. The list holds the raw events ("request", "block_start", "delta", "response"); the methods give the usual views.
turns ¶
turns() -> list[Any]
One dict per model call: the new messages sent ("messages": tool results, the user prompt), the reply's blocks (thinking, text, tool calls), why it stopped, token usage, time to first token, time and cost.
tool_calls ¶
tool_calls() -> list[Any]
Every tool call the agent made: {"seq", "id", "name", "args" (parsed), "result" (what the tool returned)}.
usage ¶
usage() -> dict[str, Any]
Totals over the run: model calls, input / cached / output / reasoning tokens, cost and model time.
to_pandas ¶
to_pandas()
One row per model call (turns()) as a pandas DataFrame, with usage spread into columns.
Run ¶
Run(data: dict[str, Any] | str)
Bases: Handle
One benchmark run: a profile × harness × benchmark × iteration, with its scores, transcript and workspace.
status
property
¶
status: str
queued, running, grading, done, failed, cancelled or skipped (fetched fresh).
transcript ¶
transcript(start: int = 0, limit: int = 20000) -> Transcript
Everything the agent and the model said, as a Transcript (turns(), tool_calls(), thinking(), usage()).
requests ¶
requests() -> list[Any]
Each model request through LLMDyno's proxy: tokens, timings, time to first token, cost, finish reason.
files ¶
files(home: bool = False) -> list[Any]
Files the agent left in its workspace (home=True: the agent's home folder, with its config and sessions): [{"path", "size", "mtime"}].
read_file ¶
read_file(path: str, home: bool = False) -> str
A workspace file's text (or a note when it is binary or larger than 2 MB).
log ¶
log(stage: int = 1, stream: str = 'stdout') -> str
The harness's output for one stage (stream "stdout" or "stderr"); the last 400 kB.
server_log ¶
server_log() -> str
The llama-server log of the plan's local model (empty for cloud runs).
gpu ¶
gpu(max_points: int = 600) -> list[Any]
GPU telemetry samples taken while the run was going (utilisation, VRAM, power, temperature).
download ¶
download(path: Union[str, Path, None] = None) -> Path
Save the run's workspace as a zip (default: