Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Episode results

Step reply

Each step returns observation, reward and done. Until the episode ends, reward is 0 and done is false. The last step has done: true, the reward (or null when the episode could not be graded) and the metadata below.

Metadata

FieldWhat
task_idthe task
successevery check scored 1, with no harm
harma change out of scope, a failed gate, or a fault
checkseach check’s name and score, with gate, by and error when they apply, then the scope gate
out_of_scopeup to 100 net changes outside allowed_changes: tbl, op, pk, columns and app
out_of_scope_counthow many there are in all
answerthe stored answer, or null
terminationsubmit, max_steps, max_seconds, void or crash
world, task_hash, manifest_hash, miroir_versionwhat the episode ran on
clockfor clock tasks: the minutes elapsed, and the events fired with their minute and status
faultwhy the episode broke the env, which made it harm
crashedthe process that exited, and its exit_code
quiet_timeouttrue when the quiet command never passed before grading
invalidwhy Miroir could not grade the episode, whose reward is null
clock_rolledtrue when the date moved during the episode, as at midnight

A faulted episode, or one that could not be graded, has no checks.

Record

The record frame, or Session.finish()["record"], returns the finished episode in full, within 4 MiB. The adapters save it with traces=.

FieldWhat
episode_id, task_idwhich episode
rewardits reward
null_maxthe task’s null_max
metadataas above
signaturea hash of the end state; null when the episode was not graded
diagnosticscounts: calls, client_errors, server_errors, repeated_calls, docs_calls, code_requests, coworker_replies, events
actionseach call’s tool, method, path, status, latency_ms, arguments and result, with app and via when set
changeseach net change’s tbl, op, pk, before, after and columns
effectseach effect’s kind and data
timingsreset_s (each reset step, and the total), episode_s and grading_s
limit_bytesthe size limit, 4 MiB
truncatedwhat was left out to fit the limit, counted by part

The signature reads the times the episode wrote relative to when it ran, so rollouts that end alike share it on any day.

State

The state frame returns episode_id, step_count, task_id, done, reward and success. reward and success stay null until the episode is done.