JustEnough.
All evidence cases
DeepSWE v1.1repositoryPython

Add session bundle recording and replay to IPython

Add `.ipybundle` recording, validation, and replay APIs for IPython sessions.

ipython-session-bundle-replay

Normalized profile

What this task asks for

Add `.ipybundle` recording, validation, and replay APIs for IPython sessions. Expose `%session_bundle` controls and matching `InteractiveShell` methods for starting, stopping, and inspecting recording. Store bundles as ZIP archives containing `metadata.json` and `events.jsonl`. Record contiguous cell events with code, execution state, streams, display results, and structured errors. Advance execution history only when replay uses `store_history=True`. Validate bundle schemas in strict or non-strict mode and expose validation paths and errors. Apply ordered literal redactions throughout `events.jsonl` and enforce overwrite behavior for existing bundles.

Intent

  • feature implementation
  • configuration tuning
  • data transformation
  • test and validation

Work surfaces

  • CLI
  • serialization
  • validation layer
  • library API

Technology

  • IPython

Expected artifacts

  • repository patch

What makes it difficult

  • changes span multiple components or interfaces

Published evidence

Model × harness outcomes

Counts are tied to these exact configurations. Harnesses are not treated as equivalent across benchmarks.

Models
13
Configurations
41
Trials
164

Showing 41 of 41 configurations

ModelHarnessEffortResultPasses
claude-fable-5vertex_aimini-swe-agentpublished configurationlowNo passes0/4
claude-fable-5vertex_aimini-swe-agentpublished configurationmediumMixed1/4
claude-fable-5vertex_aimini-swe-agentpublished configurationhighMixed2/4
claude-fable-5vertex_aimini-swe-agentpublished configurationxhighMixed3/4
claude-fable-5vertex_aimini-swe-agentpublished configurationmaxMixed3/4
claude-opus-4-8anthropicmini-swe-agentpublished configurationlowNo passes0/4
claude-opus-4-8anthropicmini-swe-agentpublished configurationmediumNo passes0/4
claude-opus-4-8anthropicmini-swe-agentpublished configurationhighMixed3/4
claude-opus-4-8anthropicmini-swe-agentpublished configurationxhighMixed2/4
claude-opus-4-8anthropicmini-swe-agentpublished configurationmaxMixed3/4
claude-sonnet-4-6anthropicmini-swe-agentpublished configurationhighNo passes0/4
claude-sonnet-5anthropicmini-swe-agentpublished configurationlowMixed1/4
claude-sonnet-5anthropicmini-swe-agentpublished configurationmediumMixed2/4
claude-sonnet-5anthropicmini-swe-agentpublished configurationhighMixed2/4
claude-sonnet-5anthropicmini-swe-agentpublished configurationxhighMixed2/4
claude-sonnet-5anthropicmini-swe-agentpublished configurationmaxAll passed4/4
gemini-3-1-pro-previewvertex_aimini-swe-agentpublished configurationhighMixed3/4
gemini-3-5-flashvertex_aimini-swe-agentpublished configurationmediumAll passed4/4
glm-5-2zaimini-swe-agentpublished configurationhighMixed1/4
glm-5-2zaimini-swe-agentpublished configurationmaxMixed3/4
gpt-5-4openaimini-swe-agentpublished configurationxhighNo passes0/4
gpt-5-5openaimini-swe-agentpublished configurationlowAll passed4/4
gpt-5-5openaimini-swe-agentpublished configurationmediumMixed3/4
gpt-5-5openaimini-swe-agentpublished configurationhighMixed2/4
gpt-5-5openaimini-swe-agentpublished configurationxhighMixed1/4
gpt-5-6-lunaopenaimini-swe-agentpublished configurationlowNo passes0/4
gpt-5-6-lunaopenaimini-swe-agentpublished configurationmediumMixed2/4
gpt-5-6-lunaopenaimini-swe-agentpublished configurationhighMixed3/4
gpt-5-6-lunaopenaimini-swe-agentpublished configurationxhighMixed3/4
gpt-5-6-lunaopenaimini-swe-agentpublished configurationmaxMixed2/4
gpt-5-6-solopenaimini-swe-agentpublished configurationlowAll passed4/4
gpt-5-6-solopenaimini-swe-agentpublished configurationmediumAll passed4/4
gpt-5-6-solopenaimini-swe-agentpublished configurationhighMixed3/4
gpt-5-6-solopenaimini-swe-agentpublished configurationxhighAll passed4/4
gpt-5-6-solopenaimini-swe-agentpublished configurationmaxAll passed4/4
gpt-5-6-terraopenaimini-swe-agentpublished configurationlowMixed3/4
gpt-5-6-terraopenaimini-swe-agentpublished configurationmediumAll passed4/4
gpt-5-6-terraopenaimini-swe-agentpublished configurationhighMixed1/4
gpt-5-6-terraopenaimini-swe-agentpublished configurationxhighAll passed4/4
gpt-5-6-terraopenaimini-swe-agentpublished configurationmaxMixed3/4
kimi-k2-7-codeopenroutermini-swe-agentpublished configurationdefaultNo passes0/4