eduevidence 5.2.0 → 6.2.0
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.
- package/CONTRIBUTING.md +105 -0
- package/README.md +142 -75
- package/README.zh-CN.md +73 -30
- package/SKILL.md +397 -131
- package/agents/openai.yaml +4 -0
- package/assets/readme/controlled-execution.svg +34 -0
- package/assets/readme/landing-tour.gif +0 -0
- package/assets/readme/logo.png +0 -0
- package/assets/readme/research-workflow.svg +56 -0
- package/assets/readme/studio-graph.png +0 -0
- package/assets/readme/studio-overview.png +0 -0
- package/assets/readme/studio-reports.png +0 -0
- package/assets/readme/studio-tour.gif +0 -0
- package/autoevolve/config.yaml +17 -0
- package/autoevolve/program.md +25 -0
- package/autoevolve/protected.manifest.yaml +34 -0
- package/benchmarks/adversarial/cases.jsonl +7 -0
- package/benchmarks/evidence-library.json +5268 -0
- package/benchmarks/partitions.json +8 -0
- package/bin/eduevidence.js +2 -1
- package/docs/architecture.md +496 -0
- package/docs/autoresearch-evolution-plan.md +2903 -0
- package/docs/autoresearch-implementation-status.md +101 -0
- package/docs/demo-storyboard.md +20 -0
- package/docs/demo-workplace-ai.md +92 -0
- package/docs/demo.md +32 -0
- package/docs/install-guide.md +150 -0
- package/docs/orchestration-role-model.md +1254 -0
- package/docs/release-closeout/README.md +17 -0
- package/docs/release-closeout/frontend-acceptance.md +23 -0
- package/docs/release-closeout/issues.md +19 -0
- package/docs/release-closeout/verification.md +28 -0
- package/docs/release-contract.md +108 -0
- package/docs/research-studio-guide.zh-CN.md +166 -0
- package/docs/sciverse-api.md +125 -0
- package/eduevidence_cli.py +29 -13
- package/engine/_resources.py +13 -0
- package/engine/autoevolve/__init__.py +3 -0
- package/engine/autoevolve/agent_view.py +167 -0
- package/engine/autoevolve/core.py +357 -0
- package/engine/autoevolve/events.py +11 -0
- package/engine/autoevolve/git_workspace.py +77 -0
- package/engine/autoevolve/projection.py +23 -0
- package/engine/autoevolve/runner.py +413 -0
- package/engine/autoevolve/trust.py +146 -0
- package/engine/autoresearch/__init__.py +6 -0
- package/engine/autoresearch/commit.py +132 -0
- package/engine/autoresearch/contracts.py +126 -0
- package/engine/autoresearch/controller.py +207 -0
- package/engine/autoresearch/events.py +12 -0
- package/engine/autoresearch/gap_priority.py +168 -0
- package/engine/autoresearch/projection.py +30 -0
- package/engine/autoresearch/research_memory.py +59 -0
- package/engine/autoresearch/saturation.py +91 -0
- package/engine/briefs.py +2 -1
- package/engine/capabilities.py +1 -0
- package/engine/contracts.py +3 -1
- package/engine/decision_policy.py +96 -0
- package/engine/evidence_graph.py +14 -10
- package/engine/evidencecore.py +7 -5
- package/engine/gaps.py +132 -73
- package/engine/ids.py +2 -0
- package/engine/judge_pack.py +65 -0
- package/engine/library.py +6 -2
- package/engine/library_builtin.py +3 -1
- package/engine/living.py +36 -5
- package/engine/meta_synthesis.py +3 -1
- package/engine/migration.py +88 -3
- package/engine/orchestration.py +460 -0
- package/engine/paths.py +2 -0
- package/engine/pilot.py +36 -33
- package/engine/project.py +2 -2
- package/engine/research_service.py +113 -0
- package/engine/studio_read_model.py +400 -0
- package/engine/taxonomy.py +211 -0
- package/engine/tribunal.py +44 -33
- package/engine/update.py +1 -0
- package/engine/versions.py +1 -1
- package/engine/worker_result.py +109 -0
- package/engine/workflows.py +70 -0
- package/examples/ai-coding-assistant-evidence/EduEvidence_Report.html +2934 -0
- package/examples/ai-coding-assistant-evidence/artifact_manifest.json +15 -0
- package/examples/ai-coding-assistant-evidence/citation_check.json +79 -0
- package/examples/ai-coding-assistant-evidence/claims.jsonl +12 -0
- package/examples/ai-coding-assistant-evidence/evaluation.json +35 -0
- package/examples/ai-coding-assistant-evidence/evidence.jsonl +12 -0
- package/examples/ai-coding-assistant-evidence/final_verdict.json +107 -0
- package/examples/ai-coding-assistant-evidence/frame.json +48 -0
- package/examples/ai-coding-assistant-evidence/gate_report.json +101 -0
- package/examples/ai-coding-assistant-evidence/intervention.json +51 -0
- package/examples/ai-coding-assistant-evidence/methodology.json +36 -0
- package/examples/ai-coding-assistant-evidence/raw_verdict.json +86 -0
- package/examples/ai-coding-assistant-evidence/report_spec.json +230 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_academic.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_claude.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_datalab-dark.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_datalab.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_presentation.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/report_academic.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/report_claude.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/report_datalab-dark.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/report_datalab.html +2934 -0
- package/examples/ai-coding-assistant-evidence/reports-5themes/report_presentation.html +2934 -0
- package/examples/ai-coding-assistant-evidence/result.json +1457 -0
- package/examples/ai-coding-assistant-evidence/result.zh.json +1457 -0
- package/examples/ai-coding-assistant-evidence/skeptic.json +72 -0
- package/examples/ai-coding-assistant-evidence/sources.jsonl +8 -0
- package/examples/ai-coding-assistant-evidence/verdict.json +107 -0
- package/examples/spaced-retrieval-practice/applicability.json +14 -0
- package/examples/spaced-retrieval-practice/artifact_manifest.json +15 -0
- package/examples/spaced-retrieval-practice/claims.jsonl +3 -0
- package/examples/spaced-retrieval-practice/evidence.jsonl +6 -0
- package/examples/spaced-retrieval-practice/final_verdict.json +93 -0
- package/examples/spaced-retrieval-practice/frame.json +58 -0
- package/examples/spaced-retrieval-practice/gate_report.json +101 -0
- package/examples/spaced-retrieval-practice/methodology.json +78 -0
- package/examples/spaced-retrieval-practice/report_spec.json +212 -0
- package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_academic.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_claude.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_datalab-dark.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_datalab.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_presentation.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/report_academic.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/report_claude.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/report_datalab-dark.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/report_datalab.html +2728 -0
- package/examples/spaced-retrieval-practice/reports-5themes/report_presentation.html +2728 -0
- package/examples/spaced-retrieval-practice/result.json +942 -0
- package/examples/spaced-retrieval-practice/result.zh.json +942 -0
- package/examples/spaced-retrieval-practice/skeptic.json +70 -0
- package/examples/spaced-retrieval-practice/sources.jsonl +7 -0
- package/examples/spaced-retrieval-practice/verdict.json +93 -0
- package/examples/workplace-ai-assistant/artifact_manifest.json +15 -0
- package/examples/workplace-ai-assistant/claims.jsonl +4 -0
- package/examples/workplace-ai-assistant/evaluation.json +19 -0
- package/examples/workplace-ai-assistant/evidence.jsonl +4 -0
- package/examples/workplace-ai-assistant/evidence_graph.json +444 -0
- package/examples/workplace-ai-assistant/final_verdict.json +78 -0
- package/examples/workplace-ai-assistant/frame.json +41 -0
- package/examples/workplace-ai-assistant/gate_report.json +101 -0
- package/examples/workplace-ai-assistant/intervention.json +27 -0
- package/examples/workplace-ai-assistant/legacy-link-check.json +16 -0
- package/examples/workplace-ai-assistant/methodology.json +60 -0
- package/examples/workplace-ai-assistant/report_spec.json +224 -0
- package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_academic.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_claude.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_datalab-dark.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_datalab.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_presentation.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/report_academic.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/report_claude.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/report_datalab-dark.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/report_datalab.html +2814 -0
- package/examples/workplace-ai-assistant/reports-5themes/report_presentation.html +2814 -0
- package/examples/workplace-ai-assistant/result.json +615 -0
- package/examples/workplace-ai-assistant/result.zh.json +615 -0
- package/examples/workplace-ai-assistant/search_log.json +19 -0
- package/examples/workplace-ai-assistant/skeptic.json +72 -0
- package/examples/workplace-ai-assistant/sources.jsonl +3 -0
- package/examples/workplace-ai-assistant/validation_result.json +9 -0
- package/examples/workplace-ai-assistant/verdict.json +78 -0
- package/install.sh +7 -7
- package/integrations/agent_mcp.py +2 -2
- package/integrations/orchestration_dispatch.py +146 -0
- package/package.json +46 -3
- package/pyproject.toml +14 -22
- package/references/autoresearch.md +30 -0
- package/references/evaluation-policy.md +24 -0
- package/references/orchestration.md +22 -0
- package/references/report-copy-style.md +67 -0
- package/references/retrieval-compliance.md +75 -0
- package/references/retrieval-protocol.md +20 -0
- package/references/scientific-invariants.md +19 -0
- package/retrieval/audit.py +178 -0
- package/retrieval/fetch.py +96 -0
- package/retrieval/sciverse.py +398 -0
- package/retrieval/search.py +47 -7
- package/schemas/applicability.schema.json +94 -0
- package/schemas/chart-spec.schema.json +10 -3
- package/schemas/evidence.schema.json +316 -43
- package/schemas/fetch-result.schema.json +2 -1
- package/schemas/intervention.schema.json +106 -21
- package/schemas/report-result.schema.json +12 -4
- package/schemas/report-spec.schema.json +98 -100
- package/schemas/skeptic.schema.json +86 -0
- package/schemas/source.schema.json +21 -2
- package/schemas/v2/finding.schema.json +5 -1
- package/schemas/v2/methodology-audit.schema.json +5 -1
- package/schemas/v2/outcome.schema.json +28 -5
- package/schemas/v2/project.schema.json +2 -2
- package/schemas/v2/run.schema.json +1 -1
- package/schemas/v2/study.schema.json +5 -1
- package/schemas/vNext/autoevolve-session.schema.json +34 -0
- package/schemas/vNext/eval-snapshot.schema.json +77 -0
- package/schemas/vNext/execution-plan.schema.json +50 -0
- package/schemas/vNext/gap-priority.schema.json +54 -0
- package/schemas/vNext/negative-search-record.schema.json +68 -0
- package/schemas/vNext/research-iteration.schema.json +87 -0
- package/schemas/vNext/research-strategy.schema.json +62 -0
- package/schemas/vNext/skill-experiment.schema.json +90 -0
- package/schemas/vNext/task-spec.schema.json +156 -0
- package/schemas/vNext/worker-result.schema.json +60 -0
- package/schemas/verdict.schema.json +164 -28
- package/scripts/benchmark_judge.py +2 -2
- package/scripts/benchmark_v3.py +26 -43
- package/scripts/build_esl_artifacts.py +4 -4
- package/scripts/build_evidence_library.py +2 -2
- package/scripts/build_gh_pages.py +98 -0
- package/scripts/build_readme_diagrams.py +72 -0
- package/scripts/build_report_variants.py +101 -0
- package/scripts/build_result.py +74 -9
- package/scripts/check_autoresearch_invariants.py +95 -0
- package/scripts/check_package_parity.py +85 -0
- package/scripts/check_protocol_alignment.py +375 -0
- package/scripts/check_versioned_schemas.py +254 -0
- package/scripts/claim_audit.py +13 -8
- package/scripts/compute_confidence.py +10 -0
- package/scripts/daily_evolve.py +30 -0
- package/scripts/dashboard_server.py +130 -101
- package/scripts/did_regression.py +17 -32
- package/scripts/enrich_projects_human_and_lieflat.py +1 -1
- package/scripts/evidence_score.py +5 -2
- package/scripts/generate_metrics.py +4 -3
- package/scripts/generate_new_projects.py +5 -5
- package/scripts/orchestrator.py +286 -36
- package/scripts/pre_verdict_gate.py +224 -26
- package/scripts/quickstart.py +18 -2
- package/scripts/rebake_all_5themes.py +1 -2
- package/scripts/research_auto_cli.py +475 -0
- package/scripts/run_workspace.py +24 -8
- package/scripts/search_provenance.py +64 -0
- package/scripts/serve_web.py +9 -10
- package/scripts/skill_lint.py +1 -1
- package/scripts/skill_payload.py +81 -0
- package/scripts/test_adversarial_empirical.py +26 -19
- package/scripts/validate_schema.py +46 -2
- package/scripts/vnext_cli.py +133 -0
- package/setup.py +12 -0
- package/skill/agents/evaluation-designer.md +20 -4
- package/skill/agents/evidence-analyst.md +19 -3
- package/skill/agents/evidence-judge.md +50 -2
- package/skill/agents/evidence-retriever.md +20 -3
- package/skill/agents/intervention-designer.md +20 -4
- package/skill/agents/method-reviewer.md +18 -2
- package/skill/agents/{education-planner.md → research-planner.md} +19 -3
- package/skill/agents/skeptic.md +18 -2
- package/skill/roles/registry.yaml +45 -0
- package/skill/sub-skills/aihot-trend-analysis/SKILL.md +28 -9
- package/skill/sub-skills/contradiction-analysis/SKILL.md +31 -11
- package/skill/sub-skills/data-analysis/SKILL.md +34 -15
- package/skill/sub-skills/ethics-review/SKILL.md +33 -10
- package/skill/sub-skills/evidence-extraction/SKILL.md +29 -11
- package/skill/sub-skills/evidence-review/SKILL.md +31 -12
- package/skill/sub-skills/gap-analysis/SKILL.md +31 -9
- package/skill/sub-skills/literature-review/SKILL.md +35 -14
- package/skill/sub-skills/methodology-audit/SKILL.md +29 -12
- package/skill/sub-skills/report-generation/SKILL.md +40 -6
- package/skill/sub-skills/research-planning/SKILL.md +41 -14
- package/skill/sub-skills/study-design/SKILL.md +30 -9
- package/skill/task-briefs/adjudicate.md +32 -7
- package/skill/task-briefs/applicability.md +38 -0
- package/skill/task-briefs/audit.md +32 -7
- package/skill/task-briefs/challenge.md +34 -5
- package/skill/task-briefs/evaluate.md +30 -5
- package/skill/task-briefs/extract.md +31 -8
- package/skill/task-briefs/frame.md +39 -10
- package/skill/task-briefs/intervene.md +32 -6
- package/skill/task-briefs/present.md +32 -8
- package/skill/task-briefs/projection.md +37 -0
- package/skill/task-briefs/retrieve.md +36 -6
- package/skill/workflows/decision-and-pilot.md +85 -0
- package/skill/workflows/evaluate-and-update.md +93 -0
- package/skill/workflows/evidence-review.md +117 -0
- package/visualization/eduevidence-report/assets/base.css +2 -2
- package/visualization/eduevidence-report/assets/reader.css +752 -0
- package/visualization/eduevidence-report/assets/reader.js +132 -0
- package/visualization/eduevidence-report/references/chart-selection-catalog.md +109 -0
- package/visualization/eduevidence-report/references/lieflat-composition.md +3 -1
- package/visualization/eduevidence-report/scripts/build_figures.py +25 -3
- package/visualization/eduevidence-report/scripts/build_infographics.py +5 -1
- package/visualization/eduevidence-report/scripts/build_report.py +561 -121
- package/visualization/eduevidence-report/scripts/charts_data.py +2 -0
- package/visualization/eduevidence-report/scripts/lieflat_engine.py +371 -136
- package/visualization/eduevidence-report/scripts/zh_labels.py +80 -1
- package/visualization/eduevidence-report/themes/academic.css +1 -1
- package/visualization/eduevidence-report/themes/claude.css +1 -1
- package/visualization/eduevidence-report/themes/datalab-dark.css +2 -2
- package/visualization/eduevidence-report/themes/datalab.css +2 -2
- package/visualization/eduevidence-report/themes/presentation.css +2 -2
- package/web/README.md +18 -0
- package/web/architecture.html +14885 -0
- package/web/index.html +53 -0
- package/web/studio/THIRD_PARTY_LICENSES.txt +146 -0
- package/web/studio/assets/index-B8tkF44Q.css +1 -0
- package/web/studio/assets/index-CQ6Keoyc.js +230 -0
- package/web/studio/config.json +1 -0
- package/web/studio/index.html +14 -0
- package/engine/__pycache__/__init__.cpython-312.pyc +0 -0
- package/engine/__pycache__/analysis.cpython-312.pyc +0 -0
- package/engine/__pycache__/bias.cpython-312.pyc +0 -0
- package/engine/__pycache__/briefs.cpython-312.pyc +0 -0
- package/engine/__pycache__/capabilities.cpython-312.pyc +0 -0
- package/engine/__pycache__/citation_check.cpython-312.pyc +0 -0
- package/engine/__pycache__/contracts.cpython-312.pyc +0 -0
- package/engine/__pycache__/datasets.cpython-312.pyc +0 -0
- package/engine/__pycache__/events.cpython-312.pyc +0 -0
- package/engine/__pycache__/evidence_graph.cpython-312.pyc +0 -0
- package/engine/__pycache__/evidence_review.cpython-312.pyc +0 -0
- package/engine/__pycache__/evidencecore.cpython-312.pyc +0 -0
- package/engine/__pycache__/gap_lens.cpython-312.pyc +0 -0
- package/engine/__pycache__/gaps.cpython-312.pyc +0 -0
- package/engine/__pycache__/graph_store.cpython-312.pyc +0 -0
- package/engine/__pycache__/graph_validate.cpython-312.pyc +0 -0
- package/engine/__pycache__/ids.cpython-312.pyc +0 -0
- package/engine/__pycache__/library.cpython-312.pyc +0 -0
- package/engine/__pycache__/library_builtin.cpython-312.pyc +0 -0
- package/engine/__pycache__/living.cpython-312.pyc +0 -0
- package/engine/__pycache__/log.cpython-312.pyc +0 -0
- package/engine/__pycache__/meta_analysis.cpython-312.pyc +0 -0
- package/engine/__pycache__/meta_synthesis.cpython-312.pyc +0 -0
- package/engine/__pycache__/migration.cpython-312.pyc +0 -0
- package/engine/__pycache__/mode_router.cpython-312.pyc +0 -0
- package/engine/__pycache__/paths.cpython-312.pyc +0 -0
- package/engine/__pycache__/pilot.cpython-312.pyc +0 -0
- package/engine/__pycache__/planner.cpython-312.pyc +0 -0
- package/engine/__pycache__/project.cpython-312.pyc +0 -0
- package/engine/__pycache__/projections.cpython-312.pyc +0 -0
- package/engine/__pycache__/robustness.cpython-312.pyc +0 -0
- package/engine/__pycache__/run.cpython-312.pyc +0 -0
- package/engine/__pycache__/semantics.cpython-312.pyc +0 -0
- package/engine/__pycache__/study_design.cpython-312.pyc +0 -0
- package/engine/__pycache__/synthesis.cpython-312.pyc +0 -0
- package/engine/__pycache__/tribunal.cpython-312.pyc +0 -0
- package/engine/__pycache__/update.cpython-312.pyc +0 -0
- package/engine/__pycache__/versions.cpython-312.pyc +0 -0
- package/integrations/__pycache__/__init__.cpython-312.pyc +0 -0
- package/integrations/__pycache__/agent_mcp.cpython-312.pyc +0 -0
- package/integrations/__pycache__/smart_web_fetch.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/__init__.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/corpus_store.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/dedupe.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/failures.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/fetch.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/search.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/source.cpython-312.pyc +0 -0
- package/retrieval/__pycache__/validate.cpython-312.pyc +0 -0
- package/scripts/__pycache__/__init__.cpython-312.pyc +0 -0
- package/scripts/__pycache__/benchmark.cpython-312.pyc +0 -0
- package/scripts/__pycache__/benchmark_evaluator.cpython-312.pyc +0 -0
- package/scripts/__pycache__/benchmark_judge.cpython-312.pyc +0 -0
- package/scripts/__pycache__/benchmark_routing.cpython-312.pyc +0 -0
- package/scripts/__pycache__/benchmark_v2.cpython-312.pyc +0 -0
- package/scripts/__pycache__/benchmark_v3.cpython-312.pyc +0 -0
- package/scripts/__pycache__/build_result.cpython-312.pyc +0 -0
- package/scripts/__pycache__/claim_audit.cpython-312.pyc +0 -0
- package/scripts/__pycache__/complexity_gate.cpython-312.pyc +0 -0
- package/scripts/__pycache__/compute_confidence.cpython-312.pyc +0 -0
- package/scripts/__pycache__/dashboard_server.cpython-312.pyc +0 -0
- package/scripts/__pycache__/did_regression.cpython-312.pyc +0 -0
- package/scripts/__pycache__/effect_calculator.cpython-312.pyc +0 -0
- package/scripts/__pycache__/evidence_matrix.cpython-312.pyc +0 -0
- package/scripts/__pycache__/evidence_score.cpython-312.pyc +0 -0
- package/scripts/__pycache__/evidence_semantics.cpython-312.pyc +0 -0
- package/scripts/__pycache__/fetch_benchmark.cpython-312.pyc +0 -0
- package/scripts/__pycache__/lint_report_layout.cpython-312.pyc +0 -0
- package/scripts/__pycache__/orchestrator.cpython-312.pyc +0 -0
- package/scripts/__pycache__/pre_verdict_gate.cpython-312.pyc +0 -0
- package/scripts/__pycache__/recompute_demo_quality.cpython-312.pyc +0 -0
- package/scripts/__pycache__/render_report.cpython-312.pyc +0 -0
- package/scripts/__pycache__/render_report_html.cpython-312.pyc +0 -0
- package/scripts/__pycache__/run_workspace.cpython-312.pyc +0 -0
- package/scripts/__pycache__/skill_lint.cpython-312.pyc +0 -0
- package/scripts/__pycache__/startup_probe.cpython-312.pyc +0 -0
- package/scripts/__pycache__/sync_killer_demo_report.cpython-312.pyc +0 -0
- package/scripts/__pycache__/test_adversarial_empirical.cpython-312-pytest-9.0.2.pyc +0 -0
- package/scripts/__pycache__/test_adversarial_empirical.cpython-312-pytest-9.1.1.pyc +0 -0
- package/scripts/__pycache__/validate_schema.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/adapter_contract.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/build_artifact_manifest.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/build_charts.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/build_figures.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/build_infographics.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/build_report.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/charts_data.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/lieflat_engine.cpython-312.pyc +0 -0
- package/visualization/eduevidence-report/scripts/__pycache__/zh_labels.cpython-312.pyc +0 -0
|
@@ -2,129 +2,127 @@
|
|
|
2
2
|
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
3
|
"$id": "https://github.com/37chengshan/eduevidence/schemas/report-spec.schema.json",
|
|
4
4
|
"title": "ReportSpec",
|
|
5
|
-
"description": "
|
|
5
|
+
"description": "Build record emitted next to every rendered report by visualization/eduevidence-report/scripts/build_report.py. It records which theme was baked, which charts the gallery selected or suppressed (with reasons), the integrity-gate result, and the chapter outline. It is a projection record, never a research fact store. Legacy packs that predate this contract carry a smaller shape (mode/title/theme/sections) which is accepted for compatibility.",
|
|
6
6
|
"type": "object",
|
|
7
7
|
"additionalProperties": false,
|
|
8
|
-
"required": [
|
|
9
|
-
"title",
|
|
10
|
-
"theme",
|
|
11
|
-
"sections"
|
|
12
|
-
],
|
|
8
|
+
"required": [],
|
|
13
9
|
"properties": {
|
|
14
|
-
"
|
|
10
|
+
"generated_by": {
|
|
15
11
|
"type": "string"
|
|
16
12
|
},
|
|
17
|
-
"
|
|
18
|
-
"type": "string"
|
|
19
|
-
"enum": [
|
|
20
|
-
"claude",
|
|
21
|
-
"academic",
|
|
22
|
-
"datalab",
|
|
23
|
-
"datalab-dark",
|
|
24
|
-
"presentation"
|
|
25
|
-
]
|
|
13
|
+
"source": {
|
|
14
|
+
"type": "string"
|
|
26
15
|
},
|
|
27
|
-
"
|
|
28
|
-
"type": "string"
|
|
29
|
-
"enum": [
|
|
30
|
-
"research",
|
|
31
|
-
"demo"
|
|
32
|
-
],
|
|
33
|
-
"default": "research"
|
|
16
|
+
"question": {
|
|
17
|
+
"type": "string"
|
|
34
18
|
},
|
|
35
|
-
"
|
|
36
|
-
"type": "string"
|
|
37
|
-
"format": "date-time"
|
|
19
|
+
"theme_selected": {
|
|
20
|
+
"type": "string"
|
|
38
21
|
},
|
|
39
|
-
"
|
|
22
|
+
"theme_display": {
|
|
23
|
+
"type": "string"
|
|
24
|
+
},
|
|
25
|
+
"theme_available": {
|
|
40
26
|
"type": "array",
|
|
41
27
|
"items": {
|
|
42
|
-
"type": "
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
"enum": [
|
|
62
|
-
"ReportShell",
|
|
63
|
-
"Section",
|
|
64
|
-
"DecisionCard",
|
|
65
|
-
"ConfidenceBadge",
|
|
66
|
-
"OutcomeSummary",
|
|
67
|
-
"InteractiveChart",
|
|
68
|
-
"AcademicFigure",
|
|
69
|
-
"InfographicBlock",
|
|
70
|
-
"EvidenceMatrix",
|
|
71
|
-
"EvidenceRow",
|
|
72
|
-
"TribunalView",
|
|
73
|
-
"MethodologyPanel",
|
|
74
|
-
"ConflictCard",
|
|
75
|
-
"ClaimTrace",
|
|
76
|
-
"ApplicabilityCard",
|
|
77
|
-
"InterventionTimeline",
|
|
78
|
-
"EvaluationFlow",
|
|
79
|
-
"BenchmarkPanel",
|
|
80
|
-
"SourceList",
|
|
81
|
-
"ProvenancePanel",
|
|
82
|
-
"Footnote"
|
|
83
|
-
]
|
|
84
|
-
},
|
|
85
|
-
"data_ref": {
|
|
86
|
-
"type": "string",
|
|
87
|
-
"description": "Pointer into result.json (e.g. 'decision', 'evidence', 'sources')."
|
|
88
|
-
},
|
|
89
|
-
"props": {
|
|
90
|
-
"type": "object",
|
|
91
|
-
"additionalProperties": true,
|
|
92
|
-
"description": "Component props (theme-agnostic)."
|
|
93
|
-
}
|
|
94
|
-
}
|
|
28
|
+
"type": "string"
|
|
29
|
+
}
|
|
30
|
+
},
|
|
31
|
+
"theme_selection": {
|
|
32
|
+
"type": "string"
|
|
33
|
+
},
|
|
34
|
+
"lang_default": {
|
|
35
|
+
"type": "string"
|
|
36
|
+
},
|
|
37
|
+
"lang_switchable": {
|
|
38
|
+
"type": "array",
|
|
39
|
+
"items": {
|
|
40
|
+
"type": "string"
|
|
41
|
+
}
|
|
42
|
+
},
|
|
43
|
+
"report_pages": {
|
|
44
|
+
"type": "array",
|
|
45
|
+
"items": {
|
|
46
|
+
"type": "string"
|
|
95
47
|
}
|
|
96
48
|
},
|
|
49
|
+
"full_report_outline": {
|
|
50
|
+
"type": "object",
|
|
51
|
+
"additionalProperties": true,
|
|
52
|
+
"description": "Chapter plan actually rendered, plus the source it was resolved from (result.report_outline, or safe_fallback)."
|
|
53
|
+
},
|
|
54
|
+
"visualization_decisions": {
|
|
55
|
+
"type": "object",
|
|
56
|
+
"additionalProperties": true
|
|
57
|
+
},
|
|
58
|
+
"lieflat_gallery": {
|
|
59
|
+
"type": "object",
|
|
60
|
+
"additionalProperties": true,
|
|
61
|
+
"description": "Selected / suppressed / rejected gallery entries with reasons, and the layout_source (visual_layout or deterministic_fallback)."
|
|
62
|
+
},
|
|
97
63
|
"charts": {
|
|
98
64
|
"type": "array",
|
|
99
|
-
"description": "Chart declarations (see chart-spec.schema.json).",
|
|
100
65
|
"items": {
|
|
101
66
|
"$ref": "chart-spec.schema.json"
|
|
67
|
+
},
|
|
68
|
+
"description": "Chart records; each one must satisfy schemas/chart-spec.schema.json."
|
|
69
|
+
},
|
|
70
|
+
"infographics": {
|
|
71
|
+
"type": "array",
|
|
72
|
+
"items": {
|
|
73
|
+
"type": "object",
|
|
74
|
+
"additionalProperties": true
|
|
75
|
+
}
|
|
76
|
+
},
|
|
77
|
+
"academic_figures": {
|
|
78
|
+
"type": "array",
|
|
79
|
+
"items": {
|
|
80
|
+
"type": "object",
|
|
81
|
+
"additionalProperties": true
|
|
102
82
|
}
|
|
103
83
|
},
|
|
84
|
+
"integrity_gate": {
|
|
85
|
+
"type": "object",
|
|
86
|
+
"additionalProperties": true
|
|
87
|
+
},
|
|
88
|
+
"mode": {
|
|
89
|
+
"type": "string"
|
|
90
|
+
},
|
|
91
|
+
"title": {
|
|
92
|
+
"type": "string"
|
|
93
|
+
},
|
|
94
|
+
"theme": {
|
|
95
|
+
"type": "string"
|
|
96
|
+
},
|
|
97
|
+
"sections": {
|
|
98
|
+
"type": "array"
|
|
99
|
+
},
|
|
100
|
+
"generated_at": {
|
|
101
|
+
"type": "string"
|
|
102
|
+
},
|
|
104
103
|
"integrity": {
|
|
105
104
|
"type": "object",
|
|
106
|
-
"additionalProperties":
|
|
107
|
-
"description": "Scientific Integrity Gate result (v5 方案 §27).",
|
|
108
|
-
"properties": {
|
|
109
|
-
"status": {
|
|
110
|
-
"type": "string",
|
|
111
|
-
"enum": [
|
|
112
|
-
"VALID",
|
|
113
|
-
"REPORT_INVALID"
|
|
114
|
-
]
|
|
115
|
-
},
|
|
116
|
-
"checks": {
|
|
117
|
-
"type": "array",
|
|
118
|
-
"items": {
|
|
119
|
-
"type": "string"
|
|
120
|
-
}
|
|
121
|
-
}
|
|
122
|
-
}
|
|
105
|
+
"additionalProperties": true
|
|
123
106
|
},
|
|
124
107
|
"extensions": {
|
|
125
108
|
"type": "object",
|
|
126
|
-
"description": "结构化扩展字段的统一容器(P1-01)。未列入本 schema 的字段必须放在这里,禁止在顶层新增属性。",
|
|
127
109
|
"additionalProperties": true
|
|
128
110
|
}
|
|
129
|
-
}
|
|
111
|
+
},
|
|
112
|
+
"anyOf": [
|
|
113
|
+
{
|
|
114
|
+
"required": [
|
|
115
|
+
"theme_selected",
|
|
116
|
+
"integrity_gate"
|
|
117
|
+
]
|
|
118
|
+
},
|
|
119
|
+
{
|
|
120
|
+
"required": [
|
|
121
|
+
"mode",
|
|
122
|
+
"title",
|
|
123
|
+
"theme",
|
|
124
|
+
"sections"
|
|
125
|
+
]
|
|
126
|
+
}
|
|
127
|
+
]
|
|
130
128
|
}
|
|
@@ -0,0 +1,86 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
|
+
"$id": "https://github.com/37chengshan/eduevidence/schemas/skeptic.schema.json",
|
|
4
|
+
"title": "SkepticFindings",
|
|
5
|
+
"description": "Counter-evidence record produced by the Challenge stage (skill/task-briefs/challenge.md, skill/agents/skeptic.md). The nine checks are mandatory: an empty or partial record used to pass the Pre-Verdict Gate, which made the counter-evidence gate cosmetic.",
|
|
6
|
+
"type": "object",
|
|
7
|
+
"additionalProperties": false,
|
|
8
|
+
"required": [
|
|
9
|
+
"search_performed",
|
|
10
|
+
"skeptic_findings",
|
|
11
|
+
"contradictory_evidence_found"
|
|
12
|
+
],
|
|
13
|
+
"properties": {
|
|
14
|
+
"search_performed": {
|
|
15
|
+
"type": "boolean",
|
|
16
|
+
"const": true
|
|
17
|
+
},
|
|
18
|
+
"method": {
|
|
19
|
+
"type": "string"
|
|
20
|
+
},
|
|
21
|
+
"skeptic_findings": {
|
|
22
|
+
"type": "array",
|
|
23
|
+
"minItems": 9,
|
|
24
|
+
"items": {
|
|
25
|
+
"type": "object",
|
|
26
|
+
"additionalProperties": false,
|
|
27
|
+
"required": [
|
|
28
|
+
"check",
|
|
29
|
+
"status",
|
|
30
|
+
"detail"
|
|
31
|
+
],
|
|
32
|
+
"properties": {
|
|
33
|
+
"check": {
|
|
34
|
+
"type": "string",
|
|
35
|
+
"enum": [
|
|
36
|
+
"1_null_result",
|
|
37
|
+
"2_negative_result",
|
|
38
|
+
"3_contradictory_evidence",
|
|
39
|
+
"4_alternative_explanation",
|
|
40
|
+
"5_measurement_mismatch",
|
|
41
|
+
"6_sampling_bias",
|
|
42
|
+
"7_novelty_effect",
|
|
43
|
+
"8_ai_dependency",
|
|
44
|
+
"9_scope_overreach"
|
|
45
|
+
],
|
|
46
|
+
"description": "The fixed check this finding reports on."
|
|
47
|
+
},
|
|
48
|
+
"status": {
|
|
49
|
+
"type": "string",
|
|
50
|
+
"enum": [
|
|
51
|
+
"found",
|
|
52
|
+
"not_found"
|
|
53
|
+
]
|
|
54
|
+
},
|
|
55
|
+
"detail": {
|
|
56
|
+
"type": "string",
|
|
57
|
+
"minLength": 8,
|
|
58
|
+
"description": "What was looked for and what was found; an empty note is not a check."
|
|
59
|
+
},
|
|
60
|
+
"related_evidence_ids": {
|
|
61
|
+
"type": "array",
|
|
62
|
+
"items": {
|
|
63
|
+
"type": "string"
|
|
64
|
+
}
|
|
65
|
+
}
|
|
66
|
+
}
|
|
67
|
+
}
|
|
68
|
+
},
|
|
69
|
+
"contradictory_evidence_found": {
|
|
70
|
+
"type": "boolean"
|
|
71
|
+
},
|
|
72
|
+
"no_contradictory_evidence_statement": {
|
|
73
|
+
"type": "string"
|
|
74
|
+
},
|
|
75
|
+
"threats_to_validity": {
|
|
76
|
+
"type": "array",
|
|
77
|
+
"items": {
|
|
78
|
+
"type": "string"
|
|
79
|
+
}
|
|
80
|
+
},
|
|
81
|
+
"extensions": {
|
|
82
|
+
"type": "object",
|
|
83
|
+
"additionalProperties": true
|
|
84
|
+
}
|
|
85
|
+
}
|
|
86
|
+
}
|
|
@@ -212,7 +212,8 @@
|
|
|
212
212
|
"markdown_new",
|
|
213
213
|
"defuddle",
|
|
214
214
|
"raw_html",
|
|
215
|
-
"pdf_parser"
|
|
215
|
+
"pdf_parser",
|
|
216
|
+
"sciverse_content"
|
|
216
217
|
]
|
|
217
218
|
},
|
|
218
219
|
"fetch_status": {
|
|
@@ -304,8 +305,26 @@
|
|
|
304
305
|
}
|
|
305
306
|
}
|
|
306
307
|
}
|
|
308
|
+
},
|
|
309
|
+
"extensions": {
|
|
310
|
+
"type": "object",
|
|
311
|
+
"additionalProperties": true,
|
|
312
|
+
"description": "Structured extension container. Provider-specific locators live here - e.g. sciverse: {doc_id, offset, next_offset, more} - so the closed fetch contract can carry them without new top-level fields."
|
|
313
|
+
},
|
|
314
|
+
"doc_id": {
|
|
315
|
+
"type": "string",
|
|
316
|
+
"description": "Full-text artifact id (Sciverse)."
|
|
317
|
+
},
|
|
318
|
+
"chunk_id": {
|
|
319
|
+
"type": "string",
|
|
320
|
+
"description": "Retrieved chunk id (Sciverse)."
|
|
321
|
+
},
|
|
322
|
+
"offset": {
|
|
323
|
+
"type": "integer",
|
|
324
|
+
"minimum": 0,
|
|
325
|
+
"description": "Unicode code-point offset of the fetched slice (Sciverse /content)."
|
|
307
326
|
}
|
|
308
327
|
}
|
|
309
328
|
}
|
|
310
329
|
}
|
|
311
|
-
}
|
|
330
|
+
}
|
|
@@ -11,7 +11,11 @@
|
|
|
11
11
|
],
|
|
12
12
|
"properties": {
|
|
13
13
|
"finding_id": { "type": "string", "pattern": "^FND-" },
|
|
14
|
-
"study_id": {
|
|
14
|
+
"study_id": {
|
|
15
|
+
"type": "string",
|
|
16
|
+
"pattern": "^(ST-|STU-|STUDY-)",
|
|
17
|
+
"description": "Owning Study. ST- preserves the placeholder prefix used by some legacy/curated packs; migration never renames ids."
|
|
18
|
+
},
|
|
15
19
|
"finding_type": {
|
|
16
20
|
"type": "string",
|
|
17
21
|
"enum": [
|
|
@@ -13,7 +13,11 @@
|
|
|
13
13
|
],
|
|
14
14
|
"properties": {
|
|
15
15
|
"audit_id": { "type": "string", "pattern": "^AUD-" },
|
|
16
|
-
"study_id": {
|
|
16
|
+
"study_id": {
|
|
17
|
+
"type": "string",
|
|
18
|
+
"pattern": "^(ST-|STU-|STUDY-)",
|
|
19
|
+
"description": "Audited Study. ST- preserves the placeholder prefix used by some legacy/curated packs; migration never renames ids."
|
|
20
|
+
},
|
|
17
21
|
"policy_version": { "type": "string", "minLength": 1 },
|
|
18
22
|
"design_quality": { "type": "integer", "minimum": 0, "maximum": 2 },
|
|
19
23
|
"sample_quality": { "type": "integer", "minimum": 0, "maximum": 2 },
|
|
@@ -5,14 +5,37 @@
|
|
|
5
5
|
"description": "A measurable education outcome from the Outcome Taxonomy: learning / task performance / process / risk.",
|
|
6
6
|
"type": "object",
|
|
7
7
|
"additionalProperties": false,
|
|
8
|
-
"required": [
|
|
8
|
+
"required": [
|
|
9
|
+
"outcome_id",
|
|
10
|
+
"name",
|
|
11
|
+
"outcome_type",
|
|
12
|
+
"extensions"
|
|
13
|
+
],
|
|
9
14
|
"properties": {
|
|
10
|
-
"outcome_id": {
|
|
11
|
-
|
|
15
|
+
"outcome_id": {
|
|
16
|
+
"type": "string",
|
|
17
|
+
"pattern": "^OUT-"
|
|
18
|
+
},
|
|
19
|
+
"name": {
|
|
20
|
+
"type": "string",
|
|
21
|
+
"minLength": 1
|
|
22
|
+
},
|
|
12
23
|
"outcome_type": {
|
|
13
24
|
"type": "string",
|
|
14
|
-
"enum": [
|
|
25
|
+
"enum": [
|
|
26
|
+
"learning",
|
|
27
|
+
"task_performance",
|
|
28
|
+
"process",
|
|
29
|
+
"risk",
|
|
30
|
+
"effectiveness",
|
|
31
|
+
"cost",
|
|
32
|
+
"equity",
|
|
33
|
+
"feasibility"
|
|
34
|
+
],
|
|
35
|
+
"description": "Outcome category bucket. The education domain declares learning / task_performance / process / risk; the policy domain declares effectiveness / cost / equity / feasibility / risk. domains/<id>/outcome_taxonomy.json is the authority and scripts/check_protocol_alignment.py fails if this enum drifts from it."
|
|
15
36
|
},
|
|
16
|
-
"extensions": {
|
|
37
|
+
"extensions": {
|
|
38
|
+
"type": "object"
|
|
39
|
+
}
|
|
17
40
|
}
|
|
18
41
|
}
|
|
@@ -13,9 +13,9 @@
|
|
|
13
13
|
"properties": {
|
|
14
14
|
"project_id": { "type": "string", "pattern": "^PRJ-" },
|
|
15
15
|
"title": { "type": "string", "minLength": 1 },
|
|
16
|
-
"domain": { "type": "string", "enum": ["education"] },
|
|
16
|
+
"domain": { "type": "string", "enum": ["education", "policy"] },
|
|
17
17
|
"question": { "type": "string", "minLength": 1 },
|
|
18
|
-
"research_mode": { "type": "string", "enum": ["evidence_review", "full_research_cycle"] },
|
|
18
|
+
"research_mode": { "type": "string", "enum": ["evidence_review", "decision_and_pilot", "evaluate_and_update", "full_research_cycle"] },
|
|
19
19
|
"decision_target": {
|
|
20
20
|
"type": "string",
|
|
21
21
|
"enum": ["evidence_review", "teaching_decision", "teaching_pilot", "evaluation_plan", "research_cycle"]
|
|
@@ -15,7 +15,7 @@
|
|
|
15
15
|
"project_id": { "type": "string", "pattern": "^PRJ-" },
|
|
16
16
|
"purpose": { "type": "string", "minLength": 1 },
|
|
17
17
|
"started_at": { "type": "string", "format": "date-time" },
|
|
18
|
-
"status": { "type": "string", "enum": ["running", "completed", "failed", "aborted"] },
|
|
18
|
+
"status": { "type": "string", "enum": ["queued", "running", "waiting_for_user", "waiting_for_user_data", "waiting_for_executor", "waiting_for_tool", "waiting_for_review", "blocked_scientific_gate", "blocked_contract_error", "completed", "failed_recoverable", "failed_terminal", "cancelled", "failed", "aborted"] },
|
|
19
19
|
"graph_revision_before": { "type": "integer", "minimum": 0 },
|
|
20
20
|
"graph_revision_after": { "type": ["integer", "null"], "minimum": 0 },
|
|
21
21
|
"capabilities": {
|
|
@@ -10,7 +10,11 @@
|
|
|
10
10
|
"independence_key", "identity_status", "extensions"
|
|
11
11
|
],
|
|
12
12
|
"properties": {
|
|
13
|
-
"study_id": {
|
|
13
|
+
"study_id": {
|
|
14
|
+
"type": "string",
|
|
15
|
+
"pattern": "^(ST-|STU-|STUDY-)",
|
|
16
|
+
"description": "Study identity. ST- is the placeholder prefix some legacy/curated packs used before STU-/STUDY-; migration preserves original ids rather than renaming them."
|
|
17
|
+
},
|
|
14
18
|
"source_ids": {
|
|
15
19
|
"type": "array",
|
|
16
20
|
"items": { "type": "string", "pattern": "^(SRC-|S-)" },
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
|
+
"$id": "https://github.com/37chengshan/eduevidence/schemas/vNext/autoevolve-session.schema.json",
|
|
4
|
+
"title": "AutoevolveSessionReport",
|
|
5
|
+
"description": "Daily self-evolution session report (engine/autoevolve/runner.py -> state_root/daily-report.json). Records one bounded branch-only session: how many experiments ran, their promotion statuses, the stopping reason, cost and wall time, and whether runner-owned isolation was verified. Automatic KEEP requires verified OS isolation; evaluator self-attestation is ignored.",
|
|
6
|
+
"type": "object",
|
|
7
|
+
"additionalProperties": false,
|
|
8
|
+
"required": [
|
|
9
|
+
"run_tag", "branch", "experiments", "statuses", "cost", "wall_minutes",
|
|
10
|
+
"plateau", "stop_reason", "promotion", "holdout_isolation_verified", "mutation_view"
|
|
11
|
+
],
|
|
12
|
+
"properties": {
|
|
13
|
+
"run_tag": {"type": "string", "minLength": 1, "description": "Session tag; also the SkillExperiment.session_id of every experiment in this session."},
|
|
14
|
+
"branch": {"type": "string", "minLength": 1, "description": "Branch the session ran on. Promotion is branch-only."},
|
|
15
|
+
"experiments": {"type": "integer", "minimum": 0, "description": "Number of experiments attempted."},
|
|
16
|
+
"statuses": {"type": "array", "items": {"enum": ["created", "KEEP", "REJECT", "RETEST", "HUMAN_REVIEW", "CRASH", "INVALID"]}, "description": "Per-experiment promotion verdict, in attempt order."},
|
|
17
|
+
"best_experiment_id": {"type": ["string", "null"]},
|
|
18
|
+
"best_candidate_commit": {"type": ["string", "null"]},
|
|
19
|
+
"cost": {"type": "number", "minimum": 0, "description": "Cumulative session cost in USD, as reported by the agent and evaluator."},
|
|
20
|
+
"wall_minutes": {"type": "number", "minimum": 0},
|
|
21
|
+
"plateau": {"type": "boolean"},
|
|
22
|
+
"stop_reason": {"type": "string", "minLength": 1, "description": "Why the loop stopped (for example budget_exhausted, plateau, completed)."},
|
|
23
|
+
"promotion": {"const": "branch_only", "description": "Daily mode never promotes directly; KEEP only marks a candidate branch."},
|
|
24
|
+
"branch_push_requested": {"type": "boolean"},
|
|
25
|
+
"branch_pushed": {"type": "boolean"},
|
|
26
|
+
"mutation_view": {"type": "string", "minLength": 1, "description": "Isolation actually used for the mutation view."},
|
|
27
|
+
"holdout_isolation_verified": {"type": "boolean", "description": "Runner-owned OS isolation verification. Automatic KEEP requires true."},
|
|
28
|
+
"isolation_provider": {"type": "string"},
|
|
29
|
+
"isolation_reason": {"type": "string"},
|
|
30
|
+
"eval_suite_hash": {"type": "string", "description": "Trusted evaluation suite hash captured before the session; a mid-session change invalidates the experiment."},
|
|
31
|
+
"security_note": {"type": "string"},
|
|
32
|
+
"candidate_artifacts": {"type": "string", "description": "Where candidate artifacts live; local session state is never auto-pushed."}
|
|
33
|
+
}
|
|
34
|
+
}
|
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
|
+
"title": "EvalSnapshot",
|
|
4
|
+
"description": "The measurement record for one self-evolution candidate (engine/autoevolve/core.py). Carries gate outcomes, science/research scores, robustness, cost, latency, repeats and the trusted eval-suite hash. Runner-owned snapshots ignore evaluator self-attestation; a mid-session suite-hash change invalidates the experiment.",
|
|
5
|
+
"type": "object",
|
|
6
|
+
"required": [
|
|
7
|
+
"eval_id",
|
|
8
|
+
"hard_gates_passed",
|
|
9
|
+
"science_score",
|
|
10
|
+
"research_score",
|
|
11
|
+
"robustness",
|
|
12
|
+
"cost",
|
|
13
|
+
"latency",
|
|
14
|
+
"complexity",
|
|
15
|
+
"repeats",
|
|
16
|
+
"noise_floor",
|
|
17
|
+
"dev_passed",
|
|
18
|
+
"holdout_passed",
|
|
19
|
+
"adversarial_passed",
|
|
20
|
+
"holdout_isolation_verified",
|
|
21
|
+
"eval_suite_hash"
|
|
22
|
+
],
|
|
23
|
+
"properties": {
|
|
24
|
+
"eval_id": {
|
|
25
|
+
"type": "string"
|
|
26
|
+
},
|
|
27
|
+
"hard_gates_passed": {
|
|
28
|
+
"type": "boolean"
|
|
29
|
+
},
|
|
30
|
+
"science_score": {
|
|
31
|
+
"type": "number"
|
|
32
|
+
},
|
|
33
|
+
"research_score": {
|
|
34
|
+
"type": "number"
|
|
35
|
+
},
|
|
36
|
+
"robustness": {
|
|
37
|
+
"type": "number"
|
|
38
|
+
},
|
|
39
|
+
"cost": {
|
|
40
|
+
"type": "number",
|
|
41
|
+
"minimum": 0
|
|
42
|
+
},
|
|
43
|
+
"latency": {
|
|
44
|
+
"type": "number",
|
|
45
|
+
"minimum": 0
|
|
46
|
+
},
|
|
47
|
+
"complexity": {
|
|
48
|
+
"type": "number",
|
|
49
|
+
"minimum": 0
|
|
50
|
+
},
|
|
51
|
+
"repeats": {
|
|
52
|
+
"type": "integer",
|
|
53
|
+
"minimum": 1
|
|
54
|
+
},
|
|
55
|
+
"noise_floor": {
|
|
56
|
+
"type": "number",
|
|
57
|
+
"minimum": 0
|
|
58
|
+
},
|
|
59
|
+
"dev_passed": {
|
|
60
|
+
"type": "boolean"
|
|
61
|
+
},
|
|
62
|
+
"holdout_passed": {
|
|
63
|
+
"type": "boolean"
|
|
64
|
+
},
|
|
65
|
+
"adversarial_passed": {
|
|
66
|
+
"type": "boolean"
|
|
67
|
+
},
|
|
68
|
+
"holdout_isolation_verified": {
|
|
69
|
+
"type": "boolean"
|
|
70
|
+
},
|
|
71
|
+
"eval_suite_hash": {
|
|
72
|
+
"type": "string",
|
|
73
|
+
"minLength": 1
|
|
74
|
+
}
|
|
75
|
+
},
|
|
76
|
+
"additionalProperties": false
|
|
77
|
+
}
|
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
{
|
|
2
|
+
"$schema": "http://json-schema.org/draft-07/schema#",
|
|
3
|
+
"title": "ExecutionPlan",
|
|
4
|
+
"description": "The plan for one research run (engine/orchestration.py ExecutionPlanner.plan). Complexity level, the ordered TaskSpecs, the maximum parallel workers and the parallel groups; S delegates zero tasks, M and L are capped by policy. scripts/check_autoresearch_invariants.py enforces those caps.",
|
|
5
|
+
"type": "object",
|
|
6
|
+
"required": [
|
|
7
|
+
"complexity",
|
|
8
|
+
"tasks",
|
|
9
|
+
"max_parallel_workers",
|
|
10
|
+
"parallel_groups",
|
|
11
|
+
"plan_id"
|
|
12
|
+
],
|
|
13
|
+
"properties": {
|
|
14
|
+
"complexity": {
|
|
15
|
+
"enum": [
|
|
16
|
+
"S",
|
|
17
|
+
"M",
|
|
18
|
+
"L"
|
|
19
|
+
]
|
|
20
|
+
},
|
|
21
|
+
"tasks": {
|
|
22
|
+
"type": "array",
|
|
23
|
+
"items": {
|
|
24
|
+
"$ref": "task-spec.schema.json"
|
|
25
|
+
}
|
|
26
|
+
},
|
|
27
|
+
"max_parallel_workers": {
|
|
28
|
+
"type": "integer",
|
|
29
|
+
"minimum": 0,
|
|
30
|
+
"maximum": 6
|
|
31
|
+
},
|
|
32
|
+
"parallel_groups": {
|
|
33
|
+
"type": "array",
|
|
34
|
+
"items": {
|
|
35
|
+
"type": "array",
|
|
36
|
+
"minItems": 1,
|
|
37
|
+
"items": {
|
|
38
|
+
"type": "string"
|
|
39
|
+
}
|
|
40
|
+
}
|
|
41
|
+
},
|
|
42
|
+
"plan_id": {
|
|
43
|
+
"type": [
|
|
44
|
+
"string",
|
|
45
|
+
"null"
|
|
46
|
+
]
|
|
47
|
+
}
|
|
48
|
+
},
|
|
49
|
+
"additionalProperties": false
|
|
50
|
+
}
|