Skip to content

PR 07: Add sample experiment API examples#126

Closed
cm2435 wants to merge 4 commits into
codex/episode-sample-pr06-builtin-environmentsfrom
codex/episode-sample-pr07-examples-vertical
Closed

PR 07: Add sample experiment API examples#126
cm2435 wants to merge 4 commits into
codex/episode-sample-pr06-builtin-environmentsfrom
codex/episode-sample-pr07-examples-vertical

Conversation

@cm2435

@cm2435 cm2435 commented May 26, 2026

Copy link
Copy Markdown
Contributor

Review Guide

Stack position: PR 07, base codex/episode-sample-pr06-builtin-environments, head codex/episode-sample-pr07-examples-vertical.

Implements RFC Docs

  • 04-ecosystem/03-examples.md: public examples and vertical calling flows.
  • 02-core-authoring-api.md: practical Environment, Experiment, and sampler usage.
  • 03b-implementation-churn.md: CLI/examples move toward sample/experiment vocabulary.
  • 09-implementation-plan/08-pr-07-examples-vertical.md.

Why This PR Exists

This PR shows the user-side API in real scripts. It moves examples away from definition persistence and launch calls toward Python composition with environments, experiments, and experiment.submit(...).

What Actually Changes

  • Adds example scripts under examples/experiment_api for:
    • MiniF2F single environment.
    • Mixed environments.
    • Streaming SWE with candidate_pool_size > k.
    • Curriculum sampler.
    • Row-dependent runtime configuration.
  • Moves the MiniF2F llama.cpp getting-started flow to examples/getting_started/01_minif2f_local_llamacpp/submit.py.
  • Replaces persist_benchmark / launch_run in that getting-started example with MiniF2FEnvironment, Experiment, and experiment.submit(...).
  • Keeps run.py as a compatibility delegator to submit.py.
  • Updates CLI catalogue so ergon examples launch minif2f-local-llamacpp points at submit.py.
  • Adds stable print_submission_summary(...) output with experiment_id, sampler_invocation_id, batch_id, and sample_ids.

Gotchas / Review Risks

  • Some simple examples print result.model_dump_json(...), while getting-started normalizes experiment_id; review vocabulary consistency here.
  • The curriculum sampler sorts candidates but does not itself slice to k. That matches the public sampler design, but only if the service enforces selected count correctly.
  • Some examples import underscored builtin helper functions for default sandbox/evaluator setup. That may be okay as example scaffolding, but it is a review point.
  • ERGON_REPO_ROOT is strict in the getting-started path.

Cleaned Later

  • run.py remains as a shim for now.
  • Read APIs, CLI inspection, dashboard pages, and definition deletion happen in later PRs.
  • Architecture allowances are expanded as this stack adds example/import paths.

Validation Notes

Review the example tests and smoke-facing getting-started script. At the time of agent review, this PR had Python lint/type passing, while frontend and smoke checks were still failing from stack-level issues.

@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

Screenshots pushed to screenshots/pr-126.

swebench-verified/de45f6c0-02fc-42fd-afdd-cbd2533e905d-activity-stack.png
swebench-verified/de45f6c0-02fc-42fd-afdd-cbd2533e905d-happy.png
swebench-verified/de45f6c0-02fc-42fd-afdd-cbd2533e905d-visual-debugger-full.png
swebench-verified/dec677d9-a2b5-49fd-8385-3454f32f0f82-activity-stack.png
swebench-verified/dec677d9-a2b5-49fd-8385-3454f32f0f82-happy.png
swebench-verified/dec677d9-a2b5-49fd-8385-3454f32f0f82-visual-debugger-full.png
swebench-verified/eebf4490-52ff-4fc2-8e4e-4762050a3b7b-activity-stack.png
swebench-verified/eebf4490-52ff-4fc2-8e4e-4762050a3b7b-sad.png
swebench-verified/eebf4490-52ff-4fc2-8e4e-4762050a3b7b-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

Screenshots pushed to screenshots/pr-126.

minif2f/107fe0cf-3df3-4532-889c-5010d111a371-activity-stack.png
minif2f/107fe0cf-3df3-4532-889c-5010d111a371-happy.png
minif2f/107fe0cf-3df3-4532-889c-5010d111a371-visual-debugger-full.png
minif2f/3c72c403-8f75-41f1-acc5-a14e13d75514-activity-stack.png
minif2f/3c72c403-8f75-41f1-acc5-a14e13d75514-happy.png
minif2f/3c72c403-8f75-41f1-acc5-a14e13d75514-visual-debugger-full.png
minif2f/c4b2d28c-aa79-4bc9-bd04-6acf757c821f-activity-stack.png
minif2f/c4b2d28c-aa79-4bc9-bd04-6acf757c821f-sad.png
minif2f/c4b2d28c-aa79-4bc9-bd04-6acf757c821f-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

Screenshots pushed to screenshots/pr-126.

researchrubrics/31576674-25e9-4a0b-a70c-2cf0cad41a2e-activity-stack.png
researchrubrics/31576674-25e9-4a0b-a70c-2cf0cad41a2e-sad.png
researchrubrics/31576674-25e9-4a0b-a70c-2cf0cad41a2e-visual-debugger-full.png
researchrubrics/3857eadf-c84e-427b-a277-6744f6e17eeb-activity-stack.png
researchrubrics/3857eadf-c84e-427b-a277-6744f6e17eeb-happy.png
researchrubrics/3857eadf-c84e-427b-a277-6744f6e17eeb-visual-debugger-full.png
researchrubrics/da0219a8-996f-434b-b08f-c9a60c904407-activity-stack.png
researchrubrics/da0219a8-996f-434b-b08f-c9a60c904407-happy.png
researchrubrics/da0219a8-996f-434b-b08f-c9a60c904407-visual-debugger-full.png

@cm2435
cm2435 force-pushed the codex/episode-sample-pr06-builtin-environments branch from 525ec9e to 620b8b1 Compare May 26, 2026 23:11
@cm2435
cm2435 force-pushed the codex/episode-sample-pr07-examples-vertical branch from 0431edd to a8b2c7d Compare May 26, 2026 23:13
@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

Screenshots pushed to screenshots/pr-126.

swebench-verified/221ad835-a6e4-42ff-88f3-c605abd3e5ba-activity-stack.png
swebench-verified/221ad835-a6e4-42ff-88f3-c605abd3e5ba-sad.png
swebench-verified/221ad835-a6e4-42ff-88f3-c605abd3e5ba-visual-debugger-full.png
swebench-verified/60121a46-330d-4178-9660-c4f55ff36bce-activity-stack.png
swebench-verified/60121a46-330d-4178-9660-c4f55ff36bce-happy.png
swebench-verified/60121a46-330d-4178-9660-c4f55ff36bce-visual-debugger-full.png
swebench-verified/e9572d01-45d7-46a7-90c0-5a8375caa243-activity-stack.png
swebench-verified/e9572d01-45d7-46a7-90c0-5a8375caa243-happy.png
swebench-verified/e9572d01-45d7-46a7-90c0-5a8375caa243-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

Screenshots pushed to screenshots/pr-126.

researchrubrics/342bceee-f252-4a21-8771-fe3818060fb0-activity-stack.png
researchrubrics/342bceee-f252-4a21-8771-fe3818060fb0-happy.png
researchrubrics/342bceee-f252-4a21-8771-fe3818060fb0-visual-debugger-full.png
researchrubrics/54d3fb0e-f5f8-47b3-b76f-5be2b67b0d91-activity-stack.png
researchrubrics/54d3fb0e-f5f8-47b3-b76f-5be2b67b0d91-happy.png
researchrubrics/54d3fb0e-f5f8-47b3-b76f-5be2b67b0d91-visual-debugger-full.png
researchrubrics/b195662e-b148-42a9-ab94-ebf823037065-activity-stack.png
researchrubrics/b195662e-b148-42a9-ab94-ebf823037065-sad.png
researchrubrics/b195662e-b148-42a9-ab94-ebf823037065-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

Screenshots pushed to screenshots/pr-126.

minif2f/04addcae-9177-4872-ba1f-a1c5d211ef90-activity-stack.png
minif2f/04addcae-9177-4872-ba1f-a1c5d211ef90-sad.png
minif2f/04addcae-9177-4872-ba1f-a1c5d211ef90-visual-debugger-full.png
minif2f/1bf16420-cdfb-45c2-b89f-9e0d0c251289-activity-stack.png
minif2f/1bf16420-cdfb-45c2-b89f-9e0d0c251289-happy.png
minif2f/1bf16420-cdfb-45c2-b89f-9e0d0c251289-visual-debugger-full.png
minif2f/9a673a08-938f-4e2c-9a2e-b903eef352a2-activity-stack.png
minif2f/9a673a08-938f-4e2c-9a2e-b903eef352a2-happy.png
minif2f/9a673a08-938f-4e2c-9a2e-b903eef352a2-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

Screenshots pushed to screenshots/pr-126.

researchrubrics/9b8214a4-3922-4995-850a-073cfbf98326-activity-stack.png
researchrubrics/9b8214a4-3922-4995-850a-073cfbf98326-happy.png
researchrubrics/9b8214a4-3922-4995-850a-073cfbf98326-visual-debugger-full.png
researchrubrics/9e44f93d-0990-4339-838b-a287935d28c2-activity-stack.png
researchrubrics/9e44f93d-0990-4339-838b-a287935d28c2-happy.png
researchrubrics/9e44f93d-0990-4339-838b-a287935d28c2-visual-debugger-full.png
researchrubrics/eefc347b-db15-4ab7-9c9f-5d506cabdf78-activity-stack.png
researchrubrics/eefc347b-db15-4ab7-9c9f-5d506cabdf78-sad.png
researchrubrics/eefc347b-db15-4ab7-9c9f-5d506cabdf78-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

Screenshots pushed to screenshots/pr-126.

swebench-verified/2f3c6032-fb1c-4bf3-85b1-6a5295f3d640-activity-stack.png
swebench-verified/2f3c6032-fb1c-4bf3-85b1-6a5295f3d640-happy.png
swebench-verified/2f3c6032-fb1c-4bf3-85b1-6a5295f3d640-visual-debugger-full.png
swebench-verified/888400a9-7cb5-45d5-94f2-103c1dcfb02f-activity-stack.png
swebench-verified/888400a9-7cb5-45d5-94f2-103c1dcfb02f-sad.png
swebench-verified/888400a9-7cb5-45d5-94f2-103c1dcfb02f-visual-debugger-full.png
swebench-verified/bb919f2e-682f-4659-b08d-8fee2df3c183-activity-stack.png
swebench-verified/bb919f2e-682f-4659-b08d-8fee2df3c183-happy.png
swebench-verified/bb919f2e-682f-4659-b08d-8fee2df3c183-visual-debugger-full.png

@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

Screenshots pushed to screenshots/pr-126.

minif2f/22c43aea-7db9-443f-ac48-60a411712566-activity-stack.png
minif2f/22c43aea-7db9-443f-ac48-60a411712566-happy.png
minif2f/22c43aea-7db9-443f-ac48-60a411712566-visual-debugger-full.png
minif2f/63721bd1-627a-4d99-b54e-447b02738935-activity-stack.png
minif2f/63721bd1-627a-4d99-b54e-447b02738935-sad.png
minif2f/63721bd1-627a-4d99-b54e-447b02738935-visual-debugger-full.png
minif2f/c6cb735d-16e6-404f-9ed2-a1165534a4ce-activity-stack.png
minif2f/c6cb735d-16e6-404f-9ed2-a1165534a4ce-happy.png
minif2f/c6cb735d-16e6-404f-9ed2-a1165534a4ce-visual-debugger-full.png

@cm2435
cm2435 force-pushed the codex/episode-sample-pr06-builtin-environments branch from 620b8b1 to 4c959b2 Compare May 27, 2026 14:00
@cm2435
cm2435 force-pushed the codex/episode-sample-pr07-examples-vertical branch from 35596c3 to 6477e05 Compare May 27, 2026 14:00
@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

1 similar comment
@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@cm2435
cm2435 force-pushed the codex/episode-sample-pr06-builtin-environments branch from 4c959b2 to 77f8226 Compare May 27, 2026 14:44
@cm2435
cm2435 force-pushed the codex/episode-sample-pr07-examples-vertical branch from 6477e05 to 9603f8e Compare May 27, 2026 14:44
@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

1 similar comment
@github-actions

Copy link
Copy Markdown

E2E smoke — researchrubrics

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — minif2f

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@github-actions

Copy link
Copy Markdown

E2E smoke — swebench-verified

No PNG screenshots were uploaded for this leg. See screenshots/pr-126 for the uploaded placeholder.

@cm2435

cm2435 commented Jun 7, 2026

Copy link
Copy Markdown
Contributor Author

Closed after landing the cumulative episode/sample stack snapshot through PR132 directly onto dev in merge commit 1c22130. This PR's changes are included in dev.

@cm2435 cm2435 closed this Jun 7, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant