[polakamtejas]

What

An episode now records itself in the run index, as a runner records the runs it accepts:

• Before Task.run: a RunRecord with runner episode, status RUNNING, the task, its version and the instance id. It's written before the first await, so start() still returns with the run listed.
• After teardown: mark_terminal with COMPLETED, FAILED and the error, or CANCELED and the abandon reason.
• EpisodeSpec.start(run_group_id=...): files the run in that run group (overrides.metadata.run_group_id), the key the explorer groups a task's runs by. Without it, each run is its own group.

Why

The explorer's run lists read only the run index (agent_env.runner.store). An episode called Task.run directly, so its runs never appeared there: training episodes were reachable only by instance id. That holds for every trainer that plays through the Episode API, the OpenEnv-based helpers included. With a run group, a trainer can show a group of rollouts together, with their mean score.

The terminal status is written after teardown, as the cancelled record already is. A scored episode still answers result(teardown=False) at once (#393), and its run turns COMPLETED once its teardown is done.

Known limit

An episode in a trainer process that dies stays RUNNING in the index. LocalRunner marks its own interrupted runs failed on restart, and nothing does that for episodes yet.

Tests

• New: run_test.py::test_an_episode_is_in_the_run_index_running_then_ended_in_the_group_it_was_started_in. It checks running with its group, then completed, cancelled with the reason, and failed with the error.
• Affected suites: tst/unit/task, runner, explorer, openenv and training pass, 532 of 532, on five runs. One run right after uv sync had a single failure that didn't recur, likely a timing flake; the log didn't keep which test.
• End to end: Tinker training on a local bundle wrote its episodes here with run groups, and the explorer's task page listed them grouped by training step. The Tinker PR stacked on this one uses run_group_id.

🤖 Generated with Claude Code

Confidence Score: 5/5

The PR appears safe to merge; the missing-seed finding is fixed and no new actionable issues remain.

Summary

Episodes now appear in the run index, with optional run groups and a final status written after teardown.

• Episodes appear in run lists with a status and optional grouping.
• The explorer explains when another process owns a run.

Diagram

%%{init: {'theme': 'neutral'}}%%
flowchart LR
  A["EpisodeSpec.start"] --> B["Save RUNNING record and metadata"]
  B --> C["Task.run"]
  C --> D["Release proxies and tear down"]
  D --> E["Save final run status"]
  B --> F["Explorer run groups"]
  E --> F

Loading

_{Reviews (3) · Last reviewed commit: "fix(episode): keep an episode's seed in ..." · Reviewed by Greptile}