coder-eval 0.12.11__tar.gz → 0.12.12__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/agents.md +126 -96
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.env.example +18 -21
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/pr-checks.yml +21 -24
- {coder_eval-0.12.11 → coder_eval-0.12.12}/CHANGELOG.md +143 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/PKG-INFO +1 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/action.yml +1 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/REPORT_SCHEMA.md +27 -3
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/TASK_DEFINITION_GUIDE.md +15 -10
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/USER_GUIDE.md +1 -1
- coder_eval-0.12.12/docs/agents/DELEGATE.md +210 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/agents/HARNESS_PARITY.md +20 -24
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/default.yaml +2 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/.claude-plugin/plugin.json +1 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/pyproject.toml +2 -2
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/__init__.py +1 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/__init__.py +1 -1
- coder_eval-0.12.12/src/coder_eval/agents/delegate/package.json +9 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/delegate_agent.py +486 -254
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/categorization.py +17 -6
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/agent_config.py +27 -11
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/results.py +4 -2
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/overrides.py +18 -4
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/reports/html.py +24 -3
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/reports/markdown.py +53 -7
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/result_metrics.py +24 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/run_record.py +7 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/delegate/hello_date_delegate.yaml +1 -1
- coder_eval-0.12.12/tests/_fixtures/golden_streams/delegate_fixtures.py +274 -0
- coder_eval-0.12.12/tests/_fixtures/golden_streams/expected/delegate_a_tool_call.json +101 -0
- coder_eval-0.12.12/tests/_fixtures/golden_streams/expected/delegate_b_max_turns_cut.json +112 -0
- coder_eval-0.12.12/tests/_fixtures/golden_streams/expected/delegate_c_error_frame_crash.json +92 -0
- coder_eval-0.12.12/tests/_fixtures/golden_streams/expected/delegate_d_orphaned_tool.json +92 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/run_full.md +10 -9
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/run_minimal.md +2 -2
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_golden_master.py +22 -4
- coder_eval-0.12.12/tests/test_delegate_agent.py +1123 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_delegate_agent_config.py +16 -4
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_delegate_agent_live.py +18 -16
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_merge_characterization.py +1 -1
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_overrides_engine.py +32 -2
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reports.py +65 -4
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_retry_logic_comprehensive.py +16 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_record.py +30 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timing_identity_contract.py +5 -3
- {coder_eval-0.12.11 → coder_eval-0.12.12}/uv.lock +115 -78
- coder_eval-0.12.11/docs/agents/DELEGATE.md +0 -192
- coder_eval-0.12.11/src/coder_eval/agents/delegate/delegate_host.mjs +0 -175
- coder_eval-0.12.11/src/coder_eval/agents/delegate/package.json +0 -9
- coder_eval-0.12.11/tests/test_delegate_agent.py +0 -651
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/commands/coder-eval-code-review-full.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/commands/coder-eval-code-review-wf.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/commands/coder-eval-code-review.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/commands/coder-eval-create-plan.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/commands/coder-eval-implement-plan.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/commands/coder-eval-review.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/harness-candidates.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/contracts.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/isolation.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/lint-rules.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/orchestration.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/permissions.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/persistence.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/reporting.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/notes/timing.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/shared/axes.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/shared/multi-model-review.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/shared/review-rubric.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/shared/run-layout.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/workflows/cr-axis.js +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude/workflows/cr-parent.js +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.claude-plugin/marketplace.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/CODEOWNERS +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/ISSUE_TEMPLATE/adopter.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/ISSUE_TEMPLATE/bug_report.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/ISSUE_TEMPLATE/config.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/actionlint.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/code_review.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/dependabot.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/pages-stub/index.html +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/scripts/diagnose_delegate_token_claims.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/scripts/harbor_e2e.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/scripts/release_notes.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/claude-pr-review.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/codeql.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/conventional-commits.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/docker-publish.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/docs.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/harbor-e2e.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/publish-testpypi.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/release.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.github/workflows/verify-published-action.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.gitignore +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.pre-commit-config.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/.python-version +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/ADOPTERS.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/CLAUDE.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/CODE_OF_CONDUCT.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/CONTRIBUTING.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/LICENSE +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/Makefile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/NOTICE +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/SECURITY.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/comparison.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docker/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docker/Dockerfile.runtime +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docker/coder_eval_entrypoint.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docker/coder_eval_runtime_entrypoint.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/AB_EXPERIMENTS.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/CI_GATE.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/DATASETS.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/DIALOG_MODE.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/DOCKER_ISOLATION.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/EXTENDING.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/PLUGIN.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/agents/ANTIGRAVITY.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/agents/CLAUDE_CODE.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/agents/CODEX.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/agents/OPENCODE.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/agents/PI.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/assets/hero.gif +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/comparison.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/index.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/llms.txt +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/01-first-evaluation.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/02-ci-pipeline.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/03-evalboard-local.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/04-writing-a-task.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/05-comparing-models.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/06-use-docker-isolation.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/07-plugin-in-claude-code.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/docs/tutorials/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/.gitignore +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/__tests__/harness-badge.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/__tests__/harness-selector.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/__tests__/search-box.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/__tests__/skeleton.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/col-help.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/collapsible-rail.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/harness-badge.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/harness-selector.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/scroll-table.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/search-box.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/skeleton.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/unit-toggle.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_components/version-list.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_lib/__tests__/source-param.test.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_lib/source-param.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/__tests__/efficiency-charts.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/__tests__/harness-legend.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/__tests__/harness-series.test.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/daily-chart.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/efficiency-charts.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/harness-legend.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/harness-series.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/tag-rail.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/turn-budget-chart.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/wall-clock-chart.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/_overview/window-summary.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/api/download/route.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/api/file/route.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/api/refresh/__tests__/route.test.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/api/refresh/route.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/error.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/globals.css +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/icon.png +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/layout.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/loading.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/page.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/path-to-ga/__tests__/task-table.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/path-to-ga/page.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/path-to-ga/task-table.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/scribe/page.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/scribe/run-table.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/trends/__tests__/trends-view.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/trends/actions.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/trends/page.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/trends/trends-view.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/watchlist/__tests__/watchlist-view.test.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/watchlist/page.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/app/watchlist/watchlist-view.tsx +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/next-env.d.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/next.config.mjs +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/package.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/pnpm-lock.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/postcss.config.mjs +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/public/harness/antigravity.png +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/public/harness/claude-code.png +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/public/harness/codex.png +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/public/harness/pi.png +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/public/uipath.png +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/tailwind.config.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/tsconfig.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/vitest.config.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/evalboard/vitest.setup.ts +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/early-stop-ab.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/model-comparison.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/permissions-smoke.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/plugin-comparison.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/prompt-mutations-example.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/experiments/smoke_variants.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/litellm/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/litellm/cost_logger.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/litellm/litellm-config.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/litellm/start-litellm.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/mkdocs.yml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/osv-scanner.toml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/cli-setup.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/criteria.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/repo-layout.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/run-layout.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/task-rubric.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/templates/activation-rows.jsonl +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/reference/templates/activation.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/skills/analyze/SKILL.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/skills/check-skill/SKILL.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/skills/ci/SKILL.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/skills/init/SKILL.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/skills/lint-tasks/SKILL.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/plugins/coder-eval/skills/task/SKILL.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/check_commit_msg.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/corpus/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/corpus/antigravity.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/corpus/claude-code.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/corpus/codex.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/corpus/opencode.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/corpus/pi.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/scripts/timing/decompose_run.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/.gitattributes +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/_logging.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/_skills.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/antigravity_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/claude_code_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/codex_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/delegate/.gitignore +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/noop_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/opencode_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/pi_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/registry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/agents/watchdog.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/analysis.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/argv_match.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/console.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/evaluate_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/evaluate_target.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/execute_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/export_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/harbor_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/plan_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/report_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/run_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/run_helpers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/run_task_internal_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/cli/utils.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/_classification_aggregate.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/agent_judge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/base.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/classification_match.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/cli_called.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/command_executed.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/commands_efficiency.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/file_check.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/file_contains.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/file_exists.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/file_matches_regex.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/json_check.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/llm_judge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/reference_comparison.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/run_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/skill_triggered.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/system_one_judge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/criteria/uipath_eval.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/durations.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/budget.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/categories.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/checker_misuse.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/executor.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/judge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/reference.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/retry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/errors/timeout.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/checker.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_anthropic.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_bedrock.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_context.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_litellm.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_persistence.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_system_one.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/judge_usage.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/sub_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/summaries.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/system_one_scoring.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/evaluation/verdict_tool.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/formatting.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/fs_permissions.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/agent_paths.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/atif_emit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/atif_hydrate.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/atif_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/experiment_packager.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/packager.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/portability.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/harbor/reward.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/invocation_log.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/isolation/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/isolation/docker_runner.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/isolation/eval_material.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/litellm_cost.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/logging_config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/cli_match.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/container_context.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/container_paths.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/criteria.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/enums.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/experiment.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/judge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/judge_defaults.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/limits.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/merge_strategy.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/mutations.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/routing.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/sandbox.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/system_one.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/tasks.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/telemetry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/models/templates.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/batch.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/config_merge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/early_stop.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/evaluation.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/experiment.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/regrade.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/run_limits.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/run_summary_rebuild.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestration/task_loader.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/orchestrator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/path_utils.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/plugins.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/pricing.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/py.typed +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/reports/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/reports/experiment.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/reports/helpers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/reports/junit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/resources/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/resources/default_ignore_patterns.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/resources/tags.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/sandbox.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/ast_similarity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/complexity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/quality.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/signature_similarity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/similarity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/scoring/token_similarity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/simulation/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/simulation/termination.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/simulation/user_simulator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/simulation/utterance.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/stats.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/streaming/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/streaming/callbacks.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/streaming/collector.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/streaming/events.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/streaming/renderers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/streaming/wire.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/telemetry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/timing.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/src/coder_eval/utils.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agentless_smoke_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/antigravity_hello_world.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/antigravity_hello_world_docker.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/claude_hello_world.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/claude_hello_world_docker.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/claude_parallel_single_gen.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/claude_subagent_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_disallowed_tools_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_hello_world.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_parallel_commands.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_parallel_single_gen.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_skills_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_string_utils.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/codex_subagent_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/subagent_bash_long_input.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/agents/subagent_merge_sort.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/anti_cheat_reference/anti_cheat_reference.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/anti_cheat_reference/reference/solution.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/byod_smoke_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dataset_example.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/datasets/sentiment.jsonl +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/delegate/fizzbuzz_delegate.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dockerfile_build_example/dockerfile_build_example.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dockerfile_build_example/environment/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dockerfile_build_example/environment/Dockerfile.workdir +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dockerfile_build_example/environment/input.txt +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dockerfile_build_example/working_dir_auto_example.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/dockerfile_build_example/working_dir_concrete_example.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/early_stop_decision_budget_exceeded.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/early_stop_weighted_high_weight_kills_run.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/early_stop_weighted_low_weight_absorbed.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/fibonacci_with_template.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/hello_date.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/inline_starter_example.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/internal/session_resumption.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/mock_path_dirs_smoke.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/mock_path_dirs_template_dir/mock-cli-bins/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/mock_path_dirs_template_dir/mock-cli-bins/mocks/echo_args +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/mock_path_dirs_template_dir/mock-cli-bins/mocks/fixtures/config.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/mock_path_dirs_template_dir/mock-cli-bins/mocks/say_hello +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/mock_path_dirs_template_dir/task.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/opencode_smoke_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/pi_smoke_test.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/python_cli_simulated_judged/echo_simulated_judged.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/record_cli_responses.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/run_limits/max_turns_cap.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/run_limits/turn_timeout.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/3d-scan-calc/3d-scan-calc.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/3d-scan-calc/environment/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/3d-scan-calc/environment/material_density_table.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/3d-scan-calc/environment/scan_data.stl +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/3d-scan-calc/verifier/test.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/3d-scan-calc/verifier/test_outputs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/court-form-filling/court-form-filling.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/court-form-filling/environment/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/court-form-filling/environment/sc100-blank.pdf +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/court-form-filling/verifier/test.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/court-form-filling/verifier/test_outputs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/dialogue-parser/dialogue-parser.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/dialogue-parser/environment/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/dialogue-parser/environment/script.txt +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/dialogue-parser/verifier/test.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/samples/skillsbench/dialogue-parser/verifier/test_outputs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/sentiment_classification.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_agent_judge.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_budget_exceeded.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_cost_budget_exceeded.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_llm_judge.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_negative_path.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_system_one_judge.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_task_timeout.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/smoke_variants.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/test_sandbox.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tasks/token_check.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/templates/byod_smoke_test/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/templates/fibonacci-starter/README.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/templates/fibonacci-starter/src/main.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/templates/fibonacci-starter/tests/test_main.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_bracket_clock.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_container_contract.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/_scrub.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/antigravity_fixtures.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/claude_fixtures.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/codex_fixtures.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/antigravity_a_single_text_turn.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/antigravity_b_tool_call_resolved.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/antigravity_c_thinking_and_tool_same_generation.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/antigravity_d_orphaned_tool.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/antigravity_e_multi_generation.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_a_single_text_turn.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_b_tool_use_result.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_c_multi_emission_delta.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_d_subagent_terminal.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_e_model_usage_and_backfill.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_f_orphaned_tool.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_g_crash_format_placeholder.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_h1_timeout_process_error.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_h2_process_error_crash.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/claude_i_in_loop_deadline_break.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_a_agent_message_only.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_b_command_execution.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_c_reasoning_placeholder.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_d_cross_flush_is_error.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_e_orphan_tool.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_f_collab_fallback.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_g_items_rebuild.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/codex_h_no_turn_completed_crash.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/opencode_a_single_text_turn.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/opencode_b_tool_call_resolved.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/opencode_c_multi_step_tiling.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/opencode_d_orphaned_tool.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/opencode_e_error_after_generation.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/pi_a_single_text_turn.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/pi_b_tool_call_resolved.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/pi_c_multi_turn_tiling.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/pi_d_orphaned_tool.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/pi_e_error_after_generation.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/expected/pi_f_duplicate_turn_end.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/opencode_fixtures.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/golden_streams/pi_fixtures.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/environment/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/environment/docker-compose.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/environment/task.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/instruction.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/task.toml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/tests/reference/greeting.txt +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/tests/task.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/expected/tests/test.sh +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/source_task/environment/Dockerfile +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/source_task/reference/greeting.txt +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/harbor_export_golden/source_task/task.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/live_criteria.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/_snapshot.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/experiment_2variant.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/experiment_3variant.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/report_snapshots/experiment_replicates.md +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_fixtures/timing_union_cases.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/_path_helpers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/conftest.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/atif/known_good_trajectory.json +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/byoa_demo_plugin/byoa_demo.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/byoa_demo_plugin/pyproject.toml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/mock_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/pi_happy_stream.jsonl +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/tasks/test_task_informational_criterion.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/tasks/test_task_multiple_criteria.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/tasks/test_task_pass.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/fixtures/text_stub_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/harbor_e2e/fixtures/docker_baseline.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/harbor_e2e/fixtures/llm_judge.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/harbor_e2e/fixtures/template_sources.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/harbor_e2e/fixtures/trajectory_criteria.yaml +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/action_docs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/agent_roster_parity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/dead_config_fields.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/doc_env_parity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/doc_examples.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/doc_indexes.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/doc_schema_parity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/generated.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/live_verdict_contract.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/plugin_manifest_parity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/plugin_reference.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/pricing_mirror.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/prose_budget.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/pyright_config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/__init__.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/_layers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/_model_ctor.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/base.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce014_merge_strategy_declared.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce015_create_subprocess_limit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce016_no_computed_tokenusage_kwargs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce017_models_lazy_agent_imports.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce018_no_final_status_name_denylist.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce019_telemetry_non_fatal.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce020_no_sdk_typed_base_agent_fields.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce021_guarded_evaluationresult_parse.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce022_dialog_loop_statement_cap.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce024_discriminated_unions.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce032_criteria_path_seam.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce037_no_dead_private_helper.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce038_acquire_inside_try.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce039_config_error_escalates.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce043_no_command_output_truncation.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce046_env_info_spreads_super.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce048_no_in_process_typer_command_call.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce049_no_score_or_zero.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce050_no_union_getattr_probe.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce051_no_driver_override.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce052_process_lethal_must_be_container_gated.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce053_run_record_filename_literal.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce054_env_info_key_round_trip.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce056_no_container_env_literal.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce057_sidecar_shim_stdlib_only.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce058_no_timing_literal.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce059_generation_window_is_two_reads.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce060_message_id_declared.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce061_window_via_close_window.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce063_no_busy_ms_in_agents.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce064_turn_bracket_on_the_clock.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/ce066_no_report_imports_in_core.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_agent_timing_access.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_blocking_io_in_async.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_cli_imports_in_core.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_silent_except.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_submodule_model_imports.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_top_level_run_limits_access.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_transcript_regex_in_eval.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/no_type_name_string_dispatch.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/open_explicit_encoding.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/read_text_explicit_encoding.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/register_criterion_required.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/subprocess_run_explicit_encoding.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/rules/yaml_models_forbid_extras.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/runner.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/violation.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/lint/workflow_outputs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_action_inputs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_action_version_pin.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_config_no_timing_fields.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_config_optional_type.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_config_registry_dispatch.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_config_sdk_decoupling.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_judge_criterion.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_telemetry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_telemetry_advanced.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agent_timeout.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_agentless.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_antigravity_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_atif_emit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_atif_hydrate.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_atif_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_byoa_plugin.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_byoa_plugin_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_byod_feature.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_check_all_async.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_checker_logging.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_classification_match.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_claude_settings_enforcement_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cleanup_preservation_guard.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_backend_flag.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_called_criterion.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_empty_glob.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_match_parity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_sdk_options.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_set_overrides.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_telemetry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cli_type_flag.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_code_review_bugs.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_codex_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_codex_agent_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_codex_agent_unit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_codex_token_mapping.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_command_executed.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_command_statistics.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_command_telemetry_result_data.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_commands_efficiency.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_config_lineage.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_config_merge_engine.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_config_precedence.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_container_context.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_continuous_scoring.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_cost_accounting_paths.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_criterion_result_round_trip.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_custom_lint.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_dataset_expansion.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_debug_logging.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_delegate_agent_registration.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_detached_grading_boundaries.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_detached_grading_guards.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_build_failure.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_litellm_env.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_runner_container_death.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_runner_mounts.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_runner_stream_limit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_wildcard_env.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_docker_workdir_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_driver_resolver.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_durations.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_early_stop.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_error_handling.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_eval_material.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_evaluate_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_evaluate_format_harbor.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_evaluate_target.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_evaluator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_event_collector.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_execute_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_execute_evaluate_loop.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_execute_format_harbor.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_experiment_cli.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_experiment_loader.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_experiment_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_experiment_reports.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_experiment_resolver.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_experiment_runner.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_file_check.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_file_contains_scoring.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_formatting.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_git_clone_failure.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_glob_paths_in_file_criteria.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_e2e_fixtures.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_experiment_packager.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_export_golden.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_packager.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_portability.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_harbor_reward.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_heartbeat_watchdog.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_ignore_patterns_negation.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_image_from_dockerfiles.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_image_skew_refusal.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_integration.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_json_check.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_anthropic.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_bedrock.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_burn_in_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_context_builder.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_litellm.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_persistence.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_judge_system_one.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_lint_no_top_level_run_limits.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_lint_runner.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_litellm_config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_litellm_cost.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_litellm_cost_logger.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_litellm_judge_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_litellm_route.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_llm_judge_criterion.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_log_tail_buffer.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_logging.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_logging_isolation.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_merge_strategy_annotations.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_merge_unification.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_mutations.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_new_criteria.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_node_env_config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_opencode_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_optional_dependencies.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_orchestrator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_orchestrator_error_log_tail.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_orchestrator_telemetry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_parallel.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_path_utils.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pi_agent.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pi_agent_config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pi_smoke_task.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_plan_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_plugin_processing.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_plugins.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_post_run.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pr_review_workflow.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pre_run.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_preservation_mode.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pricing_mirror.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_pricing_registry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_prose_budget.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_prose_budget_commands.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reference_comparison_scoring.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reference_evaluator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reference_missing_file.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reference_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reference_permissions.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_registry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_regrade.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_release_notes.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_replicate_stats.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_report_command.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reports_html.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reports_junit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_reports_package.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_resolve_task_files.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_result_metrics.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_resume.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_route_seam_exhaustiveness.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_routing.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_command_junit.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_command_stdout.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_helpers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_limits_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_limits_orchestrator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_limits_resolver.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_metrics.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_summary_rebuild.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_run_task_internal.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_runtime_tool_versions.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_adopt.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_layer_builder.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_optional.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_record_cli.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_security.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_symlink_preservation.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_templates.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sandbox_venv_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_scorers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_scoring_quality.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sdk_option_classification.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_seed_from_prior_result.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_simulation_config.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_simulation_integration.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_simulation_termination.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_simulation_trials.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_skill_triggered.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_stats.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_stats_nonfinite.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_agent_integration.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_batch.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_callbacks.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_cli.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_events.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_orchestrator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_renderers.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_streaming_wire.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_sub_agent_runner.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_success_criterion_union.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_suite_rollup.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_summaries.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_system_one_judge.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_system_one_judge_live.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_tags.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_task_definition_unknown_fields.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_teardown_interrupt.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_telemetry.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_template_env_expansion.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_threshold_enforcement.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timeout_batch.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timeout_categorization.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timeout_exceptions.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timeout_models.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timeout_orchestrator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timing_close_window.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_timing_union_parity.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_token_usage.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_uipath_eval.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_ungraded_reporting.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_user_simulator.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_utils.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_utterance_extraction.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_variant_prompt_file.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_verdict_tool.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_verify_published_workflow.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_watchdog.py +0 -0
- {coder_eval-0.12.11 → coder_eval-0.12.12}/tests/test_yaml_migration.py +0 -0
|
@@ -558,7 +558,7 @@ shell-aware `parameters["command"]` extraction in `criteria/command_executed.py`
|
|
|
558
558
|
to raw-JSON matching — so the same task scores differently per harness. Unknown names pass
|
|
559
559
|
through unchanged.
|
|
560
560
|
|
|
561
|
-
|
|
561
|
+
Four cases are worth knowing:
|
|
562
562
|
|
|
563
563
|
- **OpenCode's tool set varies by MODEL within the one harness.** A live 174-task run
|
|
564
564
|
showed DeepSeek using `write`/`edit` 199 times and `apply_patch` 0, while GPT-5.6 used
|
|
@@ -571,6 +571,11 @@ Three cases are worth knowing:
|
|
|
571
571
|
- **Pi's search tool is `find`** (glob-by-pattern), not `glob`; there is no `glob` tool in
|
|
572
572
|
its built-in set, so mapping `find` to the canonical `Glob` is what keeps
|
|
573
573
|
`command_executed` and `commands_efficiency` comparable.
|
|
574
|
+
- **Delegate's host maps most names itself, but not `LoadSkill`.** `delegate-stdio` reports
|
|
575
|
+
`ReadFile` as `Read` and `ExecuteSkillApi` as `Skill`, so `DelegateAgent` maps only
|
|
576
|
+
`LoadSkill {name}` to `Skill {skill}`; without it `skill_triggered` never sees a Delegate skill
|
|
577
|
+
load. The rename is keyed by the host's name: keyed by `Skill`, it would also turn
|
|
578
|
+
ExecuteSkillApi's `name`, an API call, into a skill engagement.
|
|
574
579
|
|
|
575
580
|
Antigravity additionally strips the result payload out of a tool call's arguments: the
|
|
576
581
|
harness folds result fields into the same `args` dict at DONE. Beyond a static key list,
|
|
@@ -801,89 +806,117 @@ release adding an unclassified field fails loudly instead of silently passing th
|
|
|
801
806
|
|
|
802
807
|
## Delegate agent
|
|
803
808
|
|
|
804
|
-
`DelegateAgent` drives UiPath Autopilot's Delegate agent
|
|
805
|
-
|
|
806
|
-
|
|
807
|
-
|
|
808
|
-
|
|
809
|
-
`
|
|
810
|
-
|
|
811
|
-
|
|
812
|
-
|
|
813
|
-
|
|
814
|
-
|
|
815
|
-
|
|
816
|
-
|
|
817
|
-
|
|
818
|
-
|
|
819
|
-
|
|
820
|
-
|
|
821
|
-
|
|
822
|
-
|
|
823
|
-
|
|
824
|
-
|
|
825
|
-
|
|
826
|
-
|
|
827
|
-
|
|
828
|
-
|
|
829
|
-
|
|
830
|
-
|
|
831
|
-
|
|
832
|
-
the
|
|
833
|
-
|
|
834
|
-
|
|
835
|
-
|
|
836
|
-
`
|
|
837
|
-
|
|
838
|
-
`
|
|
839
|
-
|
|
840
|
-
|
|
841
|
-
|
|
842
|
-
|
|
843
|
-
|
|
844
|
-
|
|
845
|
-
|
|
846
|
-
|
|
847
|
-
|
|
848
|
-
|
|
849
|
-
|
|
850
|
-
|
|
851
|
-
|
|
852
|
-
|
|
853
|
-
|
|
854
|
-
|
|
855
|
-
|
|
856
|
-
|
|
857
|
-
|
|
858
|
-
|
|
859
|
-
|
|
860
|
-
|
|
861
|
-
|
|
862
|
-
|
|
863
|
-
`
|
|
864
|
-
|
|
865
|
-
|
|
866
|
-
|
|
867
|
-
|
|
868
|
-
|
|
869
|
-
|
|
870
|
-
|
|
871
|
-
|
|
872
|
-
|
|
873
|
-
|
|
874
|
-
`
|
|
875
|
-
|
|
876
|
-
|
|
877
|
-
|
|
878
|
-
|
|
879
|
-
|
|
880
|
-
|
|
881
|
-
|
|
882
|
-
|
|
883
|
-
|
|
884
|
-
(
|
|
885
|
-
`
|
|
886
|
-
|
|
809
|
+
`DelegateAgent` drives UiPath Autopilot's Delegate agent: reasoning in the UiPath backend, tools run
|
|
810
|
+
locally. It spawns the host from the public `@uipath/delegate-stdio` npm package
|
|
811
|
+
(`dist/delegate_stdio.mjs`), which pulls in `@uipath/delegate-sdk` and the interop binaries. The
|
|
812
|
+
package README is the wire-protocol SSOT. `agents/delegate/package.json` sets the floor at `1.203.0`, the
|
|
813
|
+
first release with the `auth` init option and the `usage` frame (UiPath/Autopilot#6656). The other frame
|
|
814
|
+
shapes were confirmed against a live `1.202.1` transcript; the frame builders in
|
|
815
|
+
`tests/_fixtures/golden_streams/delegate_fixtures.py` replay those shapes. (An earlier first-party
|
|
816
|
+
`delegate_host.mjs` wrapper is gone; see git history.)
|
|
817
|
+
|
|
818
|
+
**Auth goes to the host as the `auth` init option, not through its env.** `_env` reads the
|
|
819
|
+
`DELEGATE_*` name first, then the bare `AUTH_TOKEN` / `TENANT_ID` / `ORG_ID` / `ORG_SLUG` /
|
|
820
|
+
`TENANT_SLUG`. `DELEGATE_BACKEND_URL` → `backendUrl`, `DELEGATE_ENV` → `env`. We do not adopt the
|
|
821
|
+
host's own names (`ORG_LOGICAL_NAME`, `BACKEND_URL`, …): bare names collide with other tooling, and CI
|
|
822
|
+
secrets use the `DELEGATE_*` names. `_HOST_ENV_REMOVED` strips the host's names and the token from the
|
|
823
|
+
host env, because the agent's shells inherit it (token leak to code under test) and a stray
|
|
824
|
+
`BACKEND_URL` would reroute the host. A refresh source still writes the fresh token into the host's
|
|
825
|
+
own `process.env.AUTH_TOKEN`. `_INIT_CONFIG_ERROR_HINT` names our variables beside the host's message,
|
|
826
|
+
which names the host's own. `env=<slug>` without org/tenant
|
|
827
|
+
slugs fails init.
|
|
828
|
+
|
|
829
|
+
**`LLMGW_*` leaves the host env only when a token file is set.** Without a token file, the host's
|
|
830
|
+
`selectTokenSource` uses that S2S pair to refresh, so stripping it always would end refresh after an
|
|
831
|
+
hour. `_strip_redundant_gateway_creds` mirrors the host's lookup exactly
|
|
832
|
+
(`DELEGATE_AUTH_TOKEN_FILE ?? AUTH_TOKEN_FILE`, path-delimiter split, blanks ignored).
|
|
833
|
+
|
|
834
|
+
**Effort rides `sdk_options.effort`** — the same key as Claude Code, so one `-D` drives both.
|
|
835
|
+
`get_sdk_options()` returns the whole `init` dict (so the reports show Model and Effort), with
|
|
836
|
+
credentials redacted: `auth` → its field names, `backendUrl` → its host (`None` when `urlparse` cannot
|
|
837
|
+
parse the URL: the orchestrator reads it while it persists `task.json`, so a raise there would lose
|
|
838
|
+
the file and hide the original error). It is persisted in
|
|
839
|
+
`task.json`.
|
|
840
|
+
|
|
841
|
+
**`enableSkills` must be sent explicitly**: the host default is `false`, so `bundledSkillsPath` alone
|
|
842
|
+
loads nothing. `_resolve_bundled_skills_path` maps `<plugin.path>/skills` (first plugin wins), not the
|
|
843
|
+
shared `agents/_skills.py` resolver: the SDK wants ONE parent directory, not a list of skill dirs.
|
|
844
|
+
|
|
845
|
+
**`max_turns` stays client-side.** The host's `maxSteps` does not stop the turn (live: `maxSteps: 2`
|
|
846
|
+
ran 7 steps). The adapter counts calls from the event stream and abandons the host when call N+1
|
|
847
|
+
opens; `len(turnUsages)` from the `result` then replaces the estimate as `num_turns`.
|
|
848
|
+
|
|
849
|
+
**A cut turn keeps the usage of its finished calls.** A turn cut by `max_turns` or a stop gets no
|
|
850
|
+
`result`, so the adapter sums the per-round-trip `usage` frames; the `result`'s total replaces the sum
|
|
851
|
+
when it arrives. Ordering (from SDK/backend source, not a live transcript): call N's `usage` frame
|
|
852
|
+
always precedes the `tool_result` that opens call N+1. The frame is NOT a call boundary — it arrives
|
|
853
|
+
before its call's tools run — so the cap stays on "the previous call's tools have all returned". The
|
|
854
|
+
adapter warns when a cut turn had finished calls but no usage.
|
|
855
|
+
|
|
856
|
+
**One `AssistantMessage` per `communicate()`.** `isStepStart` and `turnUsages` would allow a
|
|
857
|
+
per-round-trip split; today `isStepStart` only merges streamed deltas. `close_window` opens the one
|
|
858
|
+
window at turn start, so head and tail measure ~0.
|
|
859
|
+
|
|
860
|
+
**Known host failures are recategorized** in `_describe_host_error` / `_crash_on_host_error`, ported
|
|
861
|
+
from the out-of-tree `delegate-sdk` adapter that drove the same host and backend:
|
|
862
|
+
|
|
863
|
+
- **Cloudflare WAF block page** (`<title>Continue with UiPath Platform</title>` or "not available in
|
|
864
|
+
your country"): a WAF rule matched shell-like text in the request, not a geo/auth block. A retry
|
|
865
|
+
is blocked again, so the reason carries "content filter" (`AGENT_INVALID_OUTPUT`). Two markers,
|
|
866
|
+
because the host truncates near 50 KB and the country sentence sits after ~48 KB of CSS.
|
|
867
|
+
- **SSE connect timeout**: no response headers, so the backend never started the turn. Rewritten to
|
|
868
|
+
"connection" (`AGENT_API_ERROR`, retried) with "timeout" removed, which would be `AGENT_TIMEOUT`
|
|
869
|
+
(not retried).
|
|
870
|
+
- **Session conflict** ("A reply is already being generated", 409): `_session_id` is dropped so the
|
|
871
|
+
retry starts a new conversation, but only while no turn of that conversation has finished
|
|
872
|
+
(`_conversation_has_history`). On a later turn a new conversation would continue the task without
|
|
873
|
+
the earlier turns, and the row would still be graded as one trajectory. So the retry keeps the
|
|
874
|
+
session. The 409 is short-lived: the backend cancels the reply when the killed host's stream
|
|
875
|
+
disconnects, then releases its turn claim, so the 5 s and 10 s `AGENT_CRASH` retries usually
|
|
876
|
+
succeed. A claim it fails to release expires after `TURN_CLAIM_TTL_SECONDS` (900 s), and the task
|
|
877
|
+
ends as an error. A `session_id` pinned in config counts as history, and dropping it would not
|
|
878
|
+
help anyway: each respawn sends it in `init`, and the SDK falls back to it when `send` carries no
|
|
879
|
+
`sessionId` (`sessionId || this.options.sessionId` in the SDK's `sendMessage`).
|
|
880
|
+
|
|
881
|
+
Not ported: stall-timeout+resend and the S2S token-file refresher. Port them when the need shows.
|
|
882
|
+
|
|
883
|
+
**No crash reason carries the stderr tail.** Categorization matches substrings of the reason, and the
|
|
884
|
+
tail holds incidental text (the sandbox path, so the task id). In build 13599116 "guardrail" in a task
|
|
885
|
+
path turned a transient error into non-retryable `AGENT_INVALID_OUTPUT`. `_log_stderr_tail` logs the
|
|
886
|
+
tail at WARNING instead.
|
|
887
|
+
|
|
888
|
+
**Only an init error that a retry cannot fix is non-retryable.** `AgentConfigError` only on
|
|
889
|
+
`_INIT_CONFIG_ERROR_MARKERS` (auth missing/rejected, missing slugs, unknown env) or on a whole-word
|
|
890
|
+
401/403. A bare `"401"` substring also matched ports and GUIDs, such as `127.0.0.1:54013`, and ended a
|
|
891
|
+
transient failure with no retry. Any other init error and the 60 s init deadline raise a retryable
|
|
892
|
+
`AgentCrashError`. The shared categorizer matches status codes as whole words too
|
|
893
|
+
(`errors/categorization.py::_mentions_status`): the `AgentCrashError` goes through `categorize_error`,
|
|
894
|
+
whose raw `"401"` substring made the same port and GUID cases a non-retryable auth error. A mid-run
|
|
895
|
+
respawn keeps the same classification: it once made every `AgentConfigError` retryable, so an expired
|
|
896
|
+
token ended the task at `start()` but was retried later.
|
|
897
|
+
|
|
898
|
+
**Clear the process handle on every path that leaves the host dead or dying** — EOF, `error` frame,
|
|
899
|
+
timeout (pre-check AND mid-`wait_for`), stop, `max_turns`. A shipped bug left it set after a mid-read
|
|
900
|
+
timeout, so the next turn reused a host with a `send` in flight
|
|
901
|
+
(`test_timeout_elapsing_mid_read_still_raises_turn_timeout_error` pins it). `_force_kill_host` clears
|
|
902
|
+
the handle before its reap. The adapter never reuses a host after a failed `send`, so no late event
|
|
903
|
+
leaks into the retry.
|
|
904
|
+
|
|
905
|
+
**Registered unconditionally**, like `codex`/`antigravity`; its extra is empty. Node and
|
|
906
|
+
`@uipath/delegate-stdio` are the real prerequisite, resolved lazily in `start()`.
|
|
907
|
+
|
|
908
|
+
**Host resolution: `DELEGATE_STDIO_PATH`, then local installs, then a global one.** Local means
|
|
909
|
+
the cwd, its ancestors and `agents/delegate/`; a local install wins, as in Node. A global install
|
|
910
|
+
is found through the package's `delegate-stdio` bin shim on `PATH`, not `npm root -g`, so the
|
|
911
|
+
resolver runs no npm subprocess. On POSIX the shim is a symlink to the bundle. On Windows it is a
|
|
912
|
+
`.cmd` file beside the prefix's `node_modules`. We never execute the `.cmd`: that would make
|
|
913
|
+
`cmd.exe` parse the arguments again. The home probe and `DELEGATE_SDK_NODE_MODULES` are gone. The
|
|
914
|
+
global search covers "install once, run from anywhere", and the root override only repeated the
|
|
915
|
+
path override. The explicit path stays for CI: a source build has no install root, and an install
|
|
916
|
+
in a temporary directory for each run keeps the runs on a shared host on their own versions.
|
|
917
|
+
|
|
918
|
+
**Windows path length**: an install root that pushes the interop binary path past 260 characters makes
|
|
919
|
+
the spawn fail with `ENOENT`. The docs tell users to install into a short path.
|
|
887
920
|
|
|
888
921
|
### Delegate agent pricing
|
|
889
922
|
|
|
@@ -913,16 +946,13 @@ un-mirrored gap, with the same caveat comment). The two tables can price the SAM
|
|
|
913
946
|
differently until someone reconciles them — a known, pre-existing state, not something this port
|
|
914
947
|
introduced or should silently "fix" by picking one number over the other.
|
|
915
948
|
|
|
916
|
-
### Delegate agent golden-master
|
|
949
|
+
### Delegate agent golden-master coverage
|
|
917
950
|
|
|
918
|
-
`
|
|
919
|
-
|
|
920
|
-
|
|
921
|
-
|
|
922
|
-
|
|
923
|
-
|
|
924
|
-
|
|
925
|
-
|
|
926
|
-
which IS a real, unexempted case: the ms-exact four-bucket identity depends only on this agent's own
|
|
927
|
-
`close_window`/`_finalize_turn` code (a single window per turn, opened at `_TurnState.__init__` and
|
|
928
|
-
closed at finalize), never on the SDK's field names, so there is nothing unverified for it to guess at.
|
|
951
|
+
`tests/_fixtures/golden_streams/delegate_fixtures.py` scripts the host's stdout frames for four
|
|
952
|
+
scenarios: a tool call, a `max_turns` cut, an `error`-frame crash and an orphaned tool. The `event`,
|
|
953
|
+
`result` and `error` frames mirror the live `1.202.1` transcript. The `usage` frame and the `result`
|
|
954
|
+
fields new in `1.203.0` follow the host source of UiPath/Autopilot#6656 (`src/usage.ts` and
|
|
955
|
+
`handleSend`): every usage object carries all four buckets with `input_tokens` exclusive of cache,
|
|
956
|
+
the frames flush before each event and before the `result` or `error`, and `result.usage` is the sum
|
|
957
|
+
of `turnUsages`. No live `1.203.0` transcript has been compared yet. If one differs, change the
|
|
958
|
+
builders and regenerate the snapshots with `GOLDEN_REGEN=1`.
|
|
@@ -89,36 +89,33 @@ LOG_TO_FILE=false # Set to true to enable file logging
|
|
|
89
89
|
# CODER_EVAL_REMEDIATE_HOME_PLUGINS=0
|
|
90
90
|
|
|
91
91
|
# Delegate agent settings (UiPath Autopilot's Delegate agent, requires Node.js
|
|
92
|
-
# on PATH plus `npm install @uipath/delegate-
|
|
93
|
-
#
|
|
92
|
+
# on PATH plus `npm install -g @uipath/delegate-stdio`, a release that accepts the
|
|
93
|
+
# `auth` init option). coder_eval finds the install itself. See docs/agents/DELEGATE.md.
|
|
94
94
|
#
|
|
95
|
-
#
|
|
96
|
-
#
|
|
97
|
-
# DELEGATE_SDK_NODE_MODULES="/path/to/install/root"
|
|
98
|
-
# DELEGATE_SDK_PATH="/path/to/node_modules/@uipath/delegate-sdk/dist/index.mjs"
|
|
99
|
-
#
|
|
100
|
-
# DELEGATE_ENV — cloud environment slug (alpha/staging/production/localhost),
|
|
101
|
-
# used to derive the backend URL from the auth record's org/tenant slugs.
|
|
95
|
+
# DELEGATE_ENV — cloud environment slug (alpha/staging/production),
|
|
96
|
+
# used to derive the backend URL from the org/tenant slugs.
|
|
102
97
|
# DELEGATE_ENV="alpha"
|
|
103
98
|
#
|
|
104
99
|
# DELEGATE_BACKEND_URL — pin the full agent-service URL directly instead
|
|
105
100
|
# (wins over DELEGATE_ENV when both are set).
|
|
106
101
|
# DELEGATE_BACKEND_URL="https://cloud.uipath.com/<org>/<tenant>/delegate_"
|
|
107
102
|
#
|
|
108
|
-
# Auth: either the token set below, or a prior `delegate-
|
|
109
|
-
#
|
|
110
|
-
# by coder_eval).
|
|
111
|
-
#
|
|
112
|
-
#
|
|
113
|
-
#
|
|
114
|
-
#
|
|
115
|
-
#
|
|
116
|
-
#
|
|
103
|
+
# Auth: either the token set below, or a prior `delegate-cli login`
|
|
104
|
+
# that wrote ~/.aria/sdk-auth.json (read by the Node host itself, not
|
|
105
|
+
# by coder_eval). coder_eval sends these values to the host as its `auth`
|
|
106
|
+
# init option, so the token stays out of the environment that the agent's
|
|
107
|
+
# shell tools inherit. Each var also accepts the bare spelling (AUTH_TOKEN,
|
|
108
|
+
# TENANT_ID, ORG_ID, ORG_SLUG, TENANT_SLUG) as a fallback -- prefer the
|
|
109
|
+
# DELEGATE_ spelling in a shared environment, since the bare names collide
|
|
110
|
+
# with what other tooling (npm, Vault, Terraform) commonly exports.
|
|
111
|
+
# DELEGATE_AUTH_TOKEN="..."
|
|
112
|
+
# DELEGATE_TENANT_ID="..."
|
|
113
|
+
# DELEGATE_ORG_ID="..."
|
|
117
114
|
# With DELEGATE_ENV (not DELEGATE_BACKEND_URL) also set these two -- the
|
|
118
115
|
# human-readable org/tenant names, not the GUIDs above -- or init fails with
|
|
119
|
-
# "
|
|
120
|
-
#
|
|
121
|
-
#
|
|
116
|
+
# 'env="alpha" requires org/tenant slugs'. See docs/agents/DELEGATE.md.
|
|
117
|
+
# DELEGATE_ORG_SLUG="..."
|
|
118
|
+
# DELEGATE_TENANT_SLUG="..."
|
|
122
119
|
|
|
123
120
|
# Usage Telemetry (anonymous; on by default).
|
|
124
121
|
# Disable entirely:
|
|
@@ -1175,8 +1175,8 @@ jobs:
|
|
|
1175
1175
|
retention-days: 7
|
|
1176
1176
|
|
|
1177
1177
|
delegate-live-tests:
|
|
1178
|
-
# Live Delegate e2e: spawns the real Node host
|
|
1179
|
-
#
|
|
1178
|
+
# Live Delegate e2e: spawns the real Node host from the public
|
|
1179
|
+
# @uipath/delegate-stdio package against a real UiPath backend. Runs on
|
|
1180
1180
|
# every PR/push like the other live-test jobs (codex-live-tests, byoa-live-tests)
|
|
1181
1181
|
# now that the DELEGATE_ROPC_* secrets are provisioned; the presence-check gate
|
|
1182
1182
|
# below skips cleanly ONLY on a fork PR (no secrets available there) and fails
|
|
@@ -1187,10 +1187,10 @@ jobs:
|
|
|
1187
1187
|
# and implemented in coder_eval_uipath/eval_runner/scripts/ci/refresh-auth.sh —
|
|
1188
1188
|
# rather than a long-lived AUTH_TOKEN secret, since a minted token's ~1h TTL
|
|
1189
1189
|
# would make a static secret stale between runs. A dedicated bot user's
|
|
1190
|
-
# username/password is the durable credential; the
|
|
1191
|
-
#
|
|
1192
|
-
# docs/agents/DELEGATE.md), so no
|
|
1193
|
-
# is needed here.
|
|
1190
|
+
# username/password is the durable credential; the agent sends the minted
|
|
1191
|
+
# token (DELEGATE_AUTH_TOKEN, with DELEGATE_TENANT_ID / DELEGATE_ORG_ID) to the
|
|
1192
|
+
# host as its `auth` init option (see docs/agents/DELEGATE.md), so no
|
|
1193
|
+
# sdk-auth.json or client-secret refresh chain is needed here.
|
|
1194
1194
|
name: Delegate Live E2E (ROPC)
|
|
1195
1195
|
runs-on: uipath-ubuntu-24.04
|
|
1196
1196
|
timeout-minutes: 15
|
|
@@ -1260,7 +1260,7 @@ jobs:
|
|
|
1260
1260
|
if: steps.gate.outputs.present == 'true'
|
|
1261
1261
|
run: uv sync --frozen --extra dev
|
|
1262
1262
|
|
|
1263
|
-
- name: Install @uipath/delegate-
|
|
1263
|
+
- name: Install @uipath/delegate-stdio (public npm, no token needed)
|
|
1264
1264
|
if: steps.gate.outputs.present == 'true'
|
|
1265
1265
|
working-directory: src/coder_eval/agents/delegate
|
|
1266
1266
|
# --safe-chain-skip-minimum-package-age (not a growing exclusion-list entry
|
|
@@ -1372,17 +1372,15 @@ jobs:
|
|
|
1372
1372
|
- name: Run fizzbuzz delegate task (assert PASS)
|
|
1373
1373
|
if: steps.gate.outputs.present == 'true'
|
|
1374
1374
|
env:
|
|
1375
|
-
DELEGATE_SDK_NODE_MODULES: ${{ github.workspace }}/src/coder_eval/agents/delegate
|
|
1376
1375
|
DELEGATE_ENV: ${{ github.event.inputs.delegate_uipath_env || 'alpha' }}
|
|
1377
|
-
|
|
1378
|
-
|
|
1379
|
-
|
|
1380
|
-
#
|
|
1381
|
-
#
|
|
1382
|
-
#
|
|
1383
|
-
|
|
1384
|
-
|
|
1385
|
-
TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
|
|
1376
|
+
DELEGATE_AUTH_TOKEN: ${{ steps.ropc.outputs.access_token }}
|
|
1377
|
+
DELEGATE_TENANT_ID: ${{ secrets.DELEGATE_TENANT_ID }}
|
|
1378
|
+
DELEGATE_ORG_ID: ${{ secrets.DELEGATE_ORG_ID }}
|
|
1379
|
+
# Needed alongside the GUIDs above whenever DELEGATE_ENV (rather than
|
|
1380
|
+
# DELEGATE_BACKEND_URL) resolves the backend; the agent sends all five to
|
|
1381
|
+
# the host as its `auth` init option (see .claude/notes/agents.md § Delegate agent).
|
|
1382
|
+
DELEGATE_ORG_SLUG: ${{ secrets.DELEGATE_ORG_SLUG }}
|
|
1383
|
+
DELEGATE_TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
|
|
1386
1384
|
run: .venv/bin/coder-eval run tasks/delegate/fizzbuzz_delegate.yaml --run-dir runs/delegate-live
|
|
1387
1385
|
|
|
1388
1386
|
- name: Verify Delegate live run PASSED
|
|
@@ -1405,17 +1403,16 @@ jobs:
|
|
|
1405
1403
|
- name: Run Delegate live unit tests (assert PASS)
|
|
1406
1404
|
if: steps.gate.outputs.present == 'true'
|
|
1407
1405
|
env:
|
|
1408
|
-
DELEGATE_SDK_NODE_MODULES: ${{ github.workspace }}/src/coder_eval/agents/delegate
|
|
1409
1406
|
DELEGATE_ENV: ${{ github.event.inputs.delegate_uipath_env || 'alpha' }}
|
|
1410
|
-
|
|
1411
|
-
|
|
1412
|
-
|
|
1413
|
-
|
|
1414
|
-
|
|
1407
|
+
DELEGATE_AUTH_TOKEN: ${{ steps.ropc.outputs.access_token }}
|
|
1408
|
+
DELEGATE_TENANT_ID: ${{ secrets.DELEGATE_TENANT_ID }}
|
|
1409
|
+
DELEGATE_ORG_ID: ${{ secrets.DELEGATE_ORG_ID }}
|
|
1410
|
+
DELEGATE_ORG_SLUG: ${{ secrets.DELEGATE_ORG_SLUG }}
|
|
1411
|
+
DELEGATE_TENANT_SLUG: ${{ secrets.DELEGATE_TENANT_SLUG }}
|
|
1415
1412
|
run: |
|
|
1416
1413
|
mkdir -p tmp
|
|
1417
1414
|
.venv/bin/pytest tests/test_delegate_agent_live.py \
|
|
1418
|
-
-m live -n0 -v --tb=short --strict-markers -ra \
|
|
1415
|
+
-m live -n0 -v --tb=short --strict-markers -ra --log-level=DEBUG \
|
|
1419
1416
|
--junit-xml=tmp/junit-delegate-live.xml
|
|
1420
1417
|
|
|
1421
1418
|
- name: Assert Delegate live tests actually ran (not silently skipped)
|
|
@@ -2,6 +2,149 @@
|
|
|
2
2
|
|
|
3
3
|
<!-- version list -->
|
|
4
4
|
|
|
5
|
+
## v0.12.12 (2026-10-06)
|
|
6
|
+
|
|
7
|
+
### Bug Fixes
|
|
8
|
+
|
|
9
|
+
- **delegate**: Categorize WAF blocks, SSE connect timeouts and session conflicts
|
|
10
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
11
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
12
|
+
|
|
13
|
+
- **delegate**: Keep a non-retryable init error terminal on a respawn
|
|
14
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
15
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
16
|
+
|
|
17
|
+
- **delegate**: Keep the conversation on a session conflict after a finished turn
|
|
18
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
19
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
20
|
+
|
|
21
|
+
- **delegate**: Keep the LLMGW_* secret out of agent shells when a token file is set
|
|
22
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
23
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
24
|
+
|
|
25
|
+
- **delegate**: Keep the usage of the calls under a max_turns cut
|
|
26
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
27
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
28
|
+
|
|
29
|
+
- **delegate**: Keep tool rows whose result has no open call
|
|
30
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
31
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
32
|
+
|
|
33
|
+
- **delegate**: Let the init keys coder_eval owns win over sdk_options
|
|
34
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
35
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
36
|
+
|
|
37
|
+
- **delegate**: Make crash retry independent of the stderr tail
|
|
38
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
39
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
40
|
+
|
|
41
|
+
- **delegate**: Match an init 401/403 as a whole word
|
|
42
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
43
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
44
|
+
|
|
45
|
+
- **delegate**: Record an interrupted tool as an error, not a success
|
|
46
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
47
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
48
|
+
|
|
49
|
+
- **delegate**: Record no host for a DELEGATE_BACKEND_URL that does not parse
|
|
50
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
51
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
52
|
+
|
|
53
|
+
- **delegate**: Record the SDK's LoadSkill call as the canonical Skill call
|
|
54
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
55
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
56
|
+
|
|
57
|
+
- **delegate**: Reject an sdk_options.effort that is not a string
|
|
58
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
59
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
60
|
+
|
|
61
|
+
- **deps**: Bump multidict 6.7.1 -> 6.9.1 for CVE-2026-104874
|
|
62
|
+
([#218](https://github.com/UiPath/coder_eval/pull/218),
|
|
63
|
+
[`2fc1ae0`](https://github.com/UiPath/coder_eval/commit/2fc1ae0bc5013da6f9d4f4215d756b27f69c0d80))
|
|
64
|
+
|
|
65
|
+
- **errors**: Match an HTTP status code in an error message as a whole word
|
|
66
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
67
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
68
|
+
|
|
69
|
+
### Chores
|
|
70
|
+
|
|
71
|
+
- **delegate**: Require @uipath/delegate-stdio 1.203.0
|
|
72
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
73
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
74
|
+
|
|
75
|
+
### Continuous Integration
|
|
76
|
+
|
|
77
|
+
- **delegate**: Add temporary shell probes to the Delegate live job
|
|
78
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
79
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
80
|
+
|
|
81
|
+
- **delegate**: Remove the temporary shell probes
|
|
82
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
83
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
84
|
+
|
|
85
|
+
- **delegate**: Replace the shell probes with an auth/host A/B/C probe
|
|
86
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
87
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
88
|
+
|
|
89
|
+
### Documentation
|
|
90
|
+
|
|
91
|
+
- Say that the sdk_options keys and record depend on the agent type
|
|
92
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
93
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
94
|
+
|
|
95
|
+
- **delegate**: Describe the host env scrub as defense in depth
|
|
96
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
97
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
98
|
+
|
|
99
|
+
- **notes**: Shorten the Delegate agent section
|
|
100
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
101
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
102
|
+
|
|
103
|
+
### Features
|
|
104
|
+
|
|
105
|
+
- **delegate**: Drive the public @uipath/delegate-stdio host
|
|
106
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
107
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
108
|
+
|
|
109
|
+
- **delegate**: Drive the public @uipath/delegate-stdio host [PILOT-7854]
|
|
110
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
111
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
112
|
+
|
|
113
|
+
- **delegate**: Find a global delegate-stdio install; rename DELEGATE_SDK_PATH to
|
|
114
|
+
DELEGATE_STDIO_PATH ([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
115
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
116
|
+
|
|
117
|
+
- **delegate**: Read the delegate-stdio host's own env var names; route effort through sdk_options
|
|
118
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
119
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
120
|
+
|
|
121
|
+
- **delegate**: Send auth to the host as an init option; read the DELEGATE_* names again
|
|
122
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
123
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
124
|
+
|
|
125
|
+
- **reports**: Report agent wall and grading separately from end-to-end latency
|
|
126
|
+
([#213](https://github.com/UiPath/coder_eval/pull/213),
|
|
127
|
+
[`b806791`](https://github.com/UiPath/coder_eval/commit/b806791cd4ebd5e3e026d20ee5acac925b750106))
|
|
128
|
+
|
|
129
|
+
### Testing
|
|
130
|
+
|
|
131
|
+
- **delegate**: Show the host's results when the live shell check fails
|
|
132
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
133
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
134
|
+
|
|
135
|
+
- **golden**: Add Delegate golden-master scenarios
|
|
136
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
137
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
138
|
+
|
|
139
|
+
- **golden**: Give the Delegate golden-coverage exemption a true reason
|
|
140
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
141
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
142
|
+
|
|
143
|
+
- **overrides**: Pin the sdk_options guard on the registry, not its contents
|
|
144
|
+
([#207](https://github.com/UiPath/coder_eval/pull/207),
|
|
145
|
+
[`abc24e8`](https://github.com/UiPath/coder_eval/commit/abc24e8d518cacd09dac36b43f63fb0bb3d3fc21))
|
|
146
|
+
|
|
147
|
+
|
|
5
148
|
## v0.12.11 (2026-10-05)
|
|
6
149
|
|
|
7
150
|
### Bug Fixes
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: coder-eval
|
|
3
|
-
Version: 0.12.
|
|
3
|
+
Version: 0.12.12
|
|
4
4
|
Summary: Evaluate, benchmark, and A/B-test AI coding agents (Claude Code, Codex, Gemini/Antigravity, OpenCode, Pi, Delegate) with sandboxed, reproducible YAML task suites.
|
|
5
5
|
Project-URL: Homepage, https://coder-eval.com
|
|
6
6
|
Project-URL: Repository, https://github.com/UiPath/coder_eval
|
|
@@ -25,7 +25,7 @@ inputs:
|
|
|
25
25
|
version:
|
|
26
26
|
description: coder-eval version to install from PyPI, or "local" to install from the action checkout
|
|
27
27
|
required: false
|
|
28
|
-
default: "0.12.
|
|
28
|
+
default: "0.12.12" # <-- kept in sync with releases by release.yml
|
|
29
29
|
extras:
|
|
30
30
|
description: >-
|
|
31
31
|
Comma-separated coder-eval extras (`codex`, `antigravity,litellm`), composed
|