@hassangameryt/freeflow 0.7.3 → 0.9.0
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/.agents/plugins/marketplace.json +2 -2
- package/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +2 -2
- package/.codex-plugin/plugin.json +3 -3
- package/.cursor-plugin/plugin.json +1 -1
- package/NOTICE +14 -0
- package/README.md +101 -159
- package/capabilities/cognitive-routing/SKILL.md +47 -210
- package/capabilities/cognitive-routing/references/coordinator.md +163 -0
- package/capabilities/cognitive-routing/references/worker.md +38 -0
- package/capabilities/compaction/SKILL.md +49 -0
- package/capabilities/compaction/references/summary-format.md +250 -0
- package/capabilities/messaging/SKILL.md +49 -0
- package/capabilities/task-memory/SKILL.md +87 -0
- package/command-surface.json +8 -52
- package/gemini-extension.json +1 -1
- package/hooks/claude/hooks.json +13 -3
- package/hooks/codex/hooks.json +2 -1
- package/hooks/shared/runtime-context.mjs +73 -83
- package/licenses/Apache-2.0.txt +55 -0
- package/package.json +42 -12
- package/pi-extension/README.md +41 -0
- package/pi-extension/dist/ask-user/ask.js +108 -0
- package/pi-extension/dist/ask-user/form.js +250 -0
- package/pi-extension/dist/ask-user/questions.js +66 -0
- package/pi-extension/dist/ask-user/tool.js +124 -0
- package/pi-extension/dist/cognitive-routing/assembler.js +417 -0
- package/pi-extension/dist/cognitive-routing/bootstrap.js +90 -0
- package/pi-extension/dist/{cognitive-routing-v2 → cognitive-routing}/config.js +8 -6
- package/pi-extension/dist/cognitive-routing/economics.js +45 -0
- package/pi-extension/dist/cognitive-routing/event-schema.js +388 -0
- package/pi-extension/dist/{session-sources/events.js → cognitive-routing/event-store.js} +107 -41
- package/pi-extension/dist/cognitive-routing/gate.js +256 -0
- package/pi-extension/dist/cognitive-routing/handlers.js +901 -0
- package/pi-extension/dist/cognitive-routing/handoffs.js +350 -0
- package/pi-extension/dist/cognitive-routing/model-control.js +476 -0
- package/pi-extension/dist/cognitive-routing/projection.js +520 -0
- package/pi-extension/dist/cognitive-routing/provenance.js +83 -0
- package/pi-extension/dist/{cognitive-routing-v2 → cognitive-routing}/render.js +15 -15
- package/pi-extension/dist/cognitive-routing/runtime.js +398 -0
- package/pi-extension/dist/{cognitive-routing-v2 → cognitive-routing}/schemas.js +47 -11
- package/pi-extension/dist/cognitive-routing/session.js +223 -0
- package/pi-extension/dist/{session-sources → cognitive-routing}/sources.js +126 -87
- package/pi-extension/dist/{cognitive-routing-v2 → cognitive-routing}/state.js +55 -386
- package/pi-extension/dist/cognitive-routing/status.js +81 -0
- package/pi-extension/dist/cognitive-routing/tools.js +74 -0
- package/pi-extension/dist/{cognitive-routing-v2 → cognitive-routing}/types.js +14 -11
- package/pi-extension/dist/compaction/carry.js +205 -0
- package/pi-extension/dist/compaction/config.js +24 -0
- package/pi-extension/dist/compaction/controller.js +494 -0
- package/pi-extension/dist/compaction/harness.js +93 -0
- package/pi-extension/dist/compaction/results.js +159 -0
- package/pi-extension/dist/compaction/thresholds.js +35 -0
- package/pi-extension/dist/compaction/tool.js +57 -0
- package/pi-extension/dist/host/branch.js +13 -0
- package/pi-extension/dist/host/canonical.js +12 -0
- package/pi-extension/dist/host/catalog.js +62 -0
- package/pi-extension/dist/host/config-validation.js +233 -0
- package/pi-extension/dist/host/config.js +361 -0
- package/pi-extension/dist/host/inbound.js +142 -0
- package/pi-extension/dist/host/projection-tags.js +60 -0
- package/pi-extension/dist/host/prompts.js +93 -0
- package/pi-extension/dist/{session-sources → host}/read-only-session.js +117 -1
- package/pi-extension/dist/{runtime → host}/request-history.js +125 -39
- package/pi-extension/dist/host/rows.js +25 -0
- package/pi-extension/dist/host/runtime-state.js +204 -0
- package/pi-extension/dist/host/section-keeper.js +85 -0
- package/pi-extension/dist/host/settings/freeflow-command.js +2323 -0
- package/pi-extension/dist/{settings/settings-tui.js → host/settings/settings-view.js} +205 -73
- package/pi-extension/dist/host/staging.js +28 -0
- package/pi-extension/dist/host/status.js +115 -0
- package/pi-extension/dist/index.js +1004 -188
- package/pi-extension/dist/messaging/config.js +27 -0
- package/pi-extension/dist/messaging/messaging.js +398 -0
- package/pi-extension/dist/messaging/registry.js +57 -0
- package/pi-extension/dist/messaging/render.js +90 -0
- package/pi-extension/dist/messaging/tools.js +109 -0
- package/pi-extension/dist/messaging/transport.js +101 -0
- package/pi-extension/dist/provider-support/cache/anchor.js +21 -0
- package/pi-extension/dist/provider-support/cache/anthropic.js +102 -0
- package/pi-extension/dist/provider-support/cache/health.js +73 -0
- package/pi-extension/dist/provider-support/cache/index.js +58 -0
- package/pi-extension/dist/provider-support/cache/keepalive.js +222 -0
- package/pi-extension/dist/provider-support/cache/monitor.js +17 -0
- package/pi-extension/dist/provider-support/cache/openai-responses.js +48 -0
- package/pi-extension/dist/provider-support/effort.js +13 -0
- package/pi-extension/dist/provider-support/index.js +44 -3
- package/pi-extension/dist/provider-support/{astra → openai}/adapter.js +46 -29
- package/pi-extension/dist/provider-support/{astra → openai}/history.js +10 -8
- package/pi-extension/dist/provider-support/{astra → openai}/index.js +8 -4
- package/pi-extension/dist/provider-support/{astra → openai}/session-state.js +29 -38
- package/pi-extension/dist/provider-support/routes.js +17 -0
- package/pi-extension/dist/task-memory/config.js +49 -0
- package/pi-extension/dist/task-memory/registry.js +119 -0
- package/pi-extension/dist/task-memory/render.js +107 -0
- package/pi-extension/dist/task-memory/runtime.js +994 -0
- package/pi-extension/dist/task-memory/tool.js +233 -0
- package/pi-extension/dist/tool-execution/apply-patch/grammar.js +23 -0
- package/pi-extension/dist/tool-execution/apply-patch/match.js +38 -0
- package/pi-extension/dist/tool-execution/apply-patch/parser.js +177 -0
- package/pi-extension/dist/tool-execution/apply-patch/plan.js +201 -0
- package/pi-extension/dist/tool-execution/apply-patch/tool.js +84 -0
- package/pi-extension/dist/tool-execution/background.js +430 -0
- package/pi-extension/dist/tool-execution/bash-guard.js +23 -0
- package/pi-extension/dist/tool-execution/config.js +33 -0
- package/pi-extension/dist/tool-execution/edit-messages.js +120 -0
- package/pi-extension/dist/tool-execution/file-state.js +138 -0
- package/pi-extension/dist/tool-execution/file-tracking.js +163 -0
- package/pi-extension/dist/tool-execution/guidance-notices.js +124 -0
- package/pi-extension/dist/tool-execution/prompt.js +54 -0
- package/pi-extension/dist/tool-execution/skill-reads.js +143 -0
- package/pi-extension/dist/tool-execution/tools.js +16 -0
- package/pi-extension/freeflow/README.md +9 -0
- package/runtime/prompts/cognitive-routing.md +4 -4
- package/runtime/prompts/core.md +29 -72
- package/runtime/prompts/interaction-contract.md +18 -8
- package/runtime/prompts/tool-execution.md +25 -0
- package/runtime/prompts/working-method.md +25 -0
- package/skills/deliver-work/SKILL.md +76 -0
- package/skills/deliver-work/references/branch-closeout.md +134 -0
- package/skills/deliver-work/references/commit.md +83 -0
- package/skills/deliver-work/references/launch.md +94 -0
- package/skills/deliver-work/references/release.md +85 -0
- package/skills/deliver-work/scripts/commit-state.mjs +139 -0
- package/skills/deliver-work/scripts/delivery-state.mjs +107 -0
- package/skills/deliver-work/scripts/lib/git-state.mjs +178 -0
- package/skills/deliver-work/scripts/push-route.mjs +122 -0
- package/skills/deliver-work/scripts/release-preflight.mjs +177 -0
- package/skills/discuss-work/SKILL.md +148 -0
- package/skills/{discuss → discuss-work}/references/discussion-continuity.md +13 -50
- package/skills/discuss-work/references/learning-action.md +36 -0
- package/skills/discuss-work/scripts/choices.mjs +101 -0
- package/skills/discuss-work/scripts/lib/choices.mjs +159 -0
- package/skills/evaluate-behavior/SKILL.md +107 -0
- package/skills/evaluate-behavior/references/authoring.md +381 -0
- package/skills/evaluate-behavior/references/coding-tasks.md +145 -0
- package/skills/evaluate-behavior/references/conversations-pipelines-judges.md +177 -0
- package/skills/evaluate-behavior/references/design-and-measurement.md +273 -0
- package/skills/evaluate-behavior/references/running-and-evidence.md +245 -0
- package/skills/evaluate-behavior/scripts/claude-guard.mjs +76 -0
- package/skills/evaluate-behavior/scripts/guard-rules.mjs +309 -0
- package/skills/evaluate-behavior/scripts/lib/agreement.mjs +90 -0
- package/skills/evaluate-behavior/scripts/lib/arms.mjs +55 -0
- package/skills/evaluate-behavior/scripts/lib/budget.mjs +87 -0
- package/skills/evaluate-behavior/scripts/lib/build-source.mjs +287 -0
- package/skills/evaluate-behavior/scripts/lib/clear.mjs +74 -0
- package/skills/evaluate-behavior/scripts/lib/container.mjs +395 -0
- package/skills/evaluate-behavior/scripts/lib/decision.mjs +418 -0
- package/skills/evaluate-behavior/scripts/lib/definitions.mjs +1072 -0
- package/skills/evaluate-behavior/scripts/lib/freeflow.mjs +103 -0
- package/skills/evaluate-behavior/scripts/lib/grade-command.mjs +591 -0
- package/skills/evaluate-behavior/scripts/lib/grade-comparison.mjs +90 -0
- package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/grade-interaction.mjs +19 -18
- package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/grade-support.mjs +32 -5
- package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/grade-workspace.mjs +28 -12
- package/skills/evaluate-behavior/scripts/lib/grade.mjs +101 -0
- package/skills/evaluate-behavior/scripts/lib/hooks.mjs +98 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/confinement.mjs +196 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/constraints.mjs +111 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/index.mjs +48 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/isolation.mjs +74 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/launch.mjs +123 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/model-call.mjs +73 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/recorder.mjs +178 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/session.mjs +494 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/claude-code/skills.mjs +81 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/index.mjs +31 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/names.mjs +3 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/pi/confinement.mjs +173 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/pi/host.mjs +148 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/pi/index.mjs +70 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/pi/isolation.mjs +81 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/pi/model-call.mjs +79 -0
- package/skills/evaluate-behavior/scripts/lib/hosts/pi/process.mjs +241 -0
- package/skills/{evaluate-skill/scripts/lib → evaluate-behavior/scripts/lib/hosts/pi}/rpc.mjs +144 -26
- package/skills/evaluate-behavior/scripts/lib/identity.mjs +82 -0
- package/skills/evaluate-behavior/scripts/lib/judge.mjs +688 -0
- package/skills/evaluate-behavior/scripts/lib/metrics.mjs +332 -0
- package/skills/evaluate-behavior/scripts/lib/model-call.mjs +17 -0
- package/skills/evaluate-behavior/scripts/lib/participants.mjs +616 -0
- package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/process.mjs +22 -0
- package/skills/evaluate-behavior/scripts/lib/queue.mjs +54 -0
- package/skills/evaluate-behavior/scripts/lib/reference.mjs +343 -0
- package/skills/evaluate-behavior/scripts/lib/reuse.mjs +277 -0
- package/skills/evaluate-behavior/scripts/lib/review.mjs +933 -0
- package/skills/evaluate-behavior/scripts/lib/runner.mjs +732 -0
- package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/sandbox.mjs +121 -14
- package/skills/evaluate-behavior/scripts/lib/scan-shell.mjs +457 -0
- package/skills/evaluate-behavior/scripts/lib/scan.mjs +479 -0
- package/skills/evaluate-behavior/scripts/lib/seal.mjs +91 -0
- package/skills/evaluate-behavior/scripts/lib/shell.mjs +560 -0
- package/skills/evaluate-behavior/scripts/lib/source-override.mjs +64 -0
- package/skills/evaluate-behavior/scripts/lib/subject-file.mjs +88 -0
- package/skills/{evaluate-skill/scripts/lib/pi.mjs → evaluate-behavior/scripts/lib/subject.mjs} +239 -262
- package/skills/evaluate-behavior/scripts/lib/task-copy.mjs +124 -0
- package/skills/evaluate-behavior/scripts/lib/trials.mjs +524 -0
- package/skills/evaluate-behavior/scripts/lib/validity.mjs +68 -0
- package/skills/evaluate-behavior/scripts/lib/view-html.mjs +454 -0
- package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/view.mjs +218 -11
- package/skills/evaluate-behavior/scripts/pi-command-tool.mjs +159 -0
- package/skills/evaluate-behavior/scripts/pi-container-route.mjs +23 -0
- package/skills/evaluate-behavior/scripts/pi-guard.mjs +77 -0
- package/skills/evaluate-behavior/scripts/pi-login-refresh.mjs +31 -0
- package/skills/evaluate-behavior/scripts/skill-eval.mjs +586 -0
- package/skills/execute-work/SKILL.md +96 -72
- package/skills/execute-work/references/code-practices.md +27 -49
- package/skills/execute-work/references/design.md +271 -0
- package/skills/execute-work/references/diagnose.md +117 -0
- package/skills/execute-work/references/migration.md +108 -0
- package/skills/execute-work/references/simplify.md +65 -0
- package/skills/execute-work/scripts/self-review.mjs +422 -0
- package/skills/execute-work/scripts/touch-map.mjs +290 -0
- package/skills/review-work/SKILL.md +94 -64
- package/skills/review-work/references/adjudication.md +94 -0
- package/skills/review-work/references/artifact.md +198 -0
- package/skills/review-work/references/evals-and-judges.md +66 -0
- package/skills/review-work/references/work.md +177 -0
- package/skills/review-work/scripts/check-brief.mjs +128 -0
- package/skills/review-work/scripts/review-packet.mjs +233 -0
- package/skills/setup-freeflow/SKILL.md +69 -16
- package/skills/track-work/SKILL.md +135 -151
- package/skills/track-work/references/handoff.md +190 -0
- package/skills/track-work/references/projects.md +51 -0
- package/skills/track-work/references/working-record-format.md +201 -344
- package/skills/track-work/scripts/lib/document.mjs +79 -19
- package/skills/track-work/scripts/lib/format.mjs +18 -1
- package/skills/track-work/scripts/lib/recover.mjs +254 -0
- package/skills/track-work/scripts/lib/registry.mjs +656 -0
- package/skills/track-work/scripts/lib/search.mjs +40 -0
- package/skills/track-work/scripts/lib/store.mjs +53 -21
- package/skills/track-work/scripts/lib/transitions.mjs +79 -4
- package/skills/track-work/scripts/lib/views.mjs +50 -1
- package/skills/track-work/scripts/working-record.mjs +263 -22
- package/skills/verify-work/SKILL.md +64 -47
- package/skills/verify-work/references/feature-map.md +120 -0
- package/skills/verify-work/references/runtime-evidence.md +203 -0
- package/skills/verify-work/references/test-design.md +27 -6
- package/skills/verify-work/scripts/test-changes.mjs +246 -0
- package/skills/write-docs/SKILL.md +171 -0
- package/skills/write-docs/references/documentation-shapes.md +184 -0
- package/skills/write-docs/references/spec-and-plan-shapes.md +308 -0
- package/skills/write-docs/scripts/artifact-check.mjs +148 -0
- package/skills/write-docs/scripts/docs-check.mjs +229 -0
- package/skills/write-docs/scripts/plan-lint.mjs +123 -0
- package/skills/write-skill/SKILL.md +165 -165
- package/skills/write-skill/references/activation-and-wording.md +143 -0
- package/skills/write-skill/references/placement-and-dependencies.md +154 -0
- package/skills/write-skill/scripts/lib/compare.mjs +701 -0
- package/skills/write-skill/scripts/lib/similarity.mjs +56 -0
- package/skills/write-skill/scripts/lib/skill-author.mjs +197 -3
- package/skills/write-skill/scripts/skill-author.mjs +67 -8
- package/capabilities/context-virtualization/SKILL.md +0 -103
- package/capabilities/conversation-history/SKILL.md +0 -53
- package/hooks/tests/check-host-adapters.test.mjs +0 -82
- package/hooks/tests/check-runtime-context-hook.sh +0 -212
- package/pi-extension/dist/cognitive-routing-v2/projection.js +0 -330
- package/pi-extension/dist/cognitive-routing-v2/runtime.js +0 -2181
- package/pi-extension/dist/cognitive-routing-v2/tools.js +0 -60
- package/pi-extension/dist/context-virtualization/commands.js +0 -89
- package/pi-extension/dist/context-virtualization/projector.js +0 -42
- package/pi-extension/dist/context-virtualization/runtime.js +0 -378
- package/pi-extension/dist/context-virtualization/state.js +0 -57
- package/pi-extension/dist/context-virtualization/types.js +0 -10
- package/pi-extension/dist/conversation-history/passages.js +0 -66
- package/pi-extension/dist/conversation-history/ranking.js +0 -105
- package/pi-extension/dist/conversation-history/runtime.js +0 -226
- package/pi-extension/dist/conversation-history/search.js +0 -56
- package/pi-extension/dist/conversation-history/types.js +0 -1
- package/pi-extension/dist/freeflow-context/resolver.js +0 -120
- package/pi-extension/dist/freeflow-context/runtime.js +0 -80
- package/pi-extension/dist/freeflow-context/source-projector.js +0 -95
- package/pi-extension/dist/freeflow-context/tool.js +0 -314
- package/pi-extension/dist/freeflow-context/types.js +0 -12
- package/pi-extension/dist/freeflow-context/visibility.js +0 -28
- package/pi-extension/dist/integrations/mcp-config.js +0 -29
- package/pi-extension/dist/runtime/runtime-context.js +0 -754
- package/pi-extension/dist/runtime/runtime-identity.js +0 -5
- package/pi-extension/dist/session-sources/provenance.js +0 -32
- package/pi-extension/dist/settings/settings-ui.js +0 -1360
- package/pi-extension/dist/ui/text-component.js +0 -57
- package/pi-extension/src/cognitive-routing-v2/budget.ts +0 -42
- package/pi-extension/src/cognitive-routing-v2/config.ts +0 -173
- package/pi-extension/src/cognitive-routing-v2/projection.ts +0 -375
- package/pi-extension/src/cognitive-routing-v2/render.ts +0 -277
- package/pi-extension/src/cognitive-routing-v2/runtime.ts +0 -2241
- package/pi-extension/src/cognitive-routing-v2/schemas.ts +0 -180
- package/pi-extension/src/cognitive-routing-v2/state.ts +0 -839
- package/pi-extension/src/cognitive-routing-v2/tools.ts +0 -62
- package/pi-extension/src/cognitive-routing-v2/types.ts +0 -254
- package/pi-extension/src/context-virtualization/commands.ts +0 -111
- package/pi-extension/src/context-virtualization/projector.ts +0 -62
- package/pi-extension/src/context-virtualization/runtime.ts +0 -428
- package/pi-extension/src/context-virtualization/state.ts +0 -79
- package/pi-extension/src/context-virtualization/types.ts +0 -92
- package/pi-extension/src/conversation-history/passages.ts +0 -81
- package/pi-extension/src/conversation-history/ranking.ts +0 -155
- package/pi-extension/src/conversation-history/runtime.ts +0 -250
- package/pi-extension/src/conversation-history/search.ts +0 -79
- package/pi-extension/src/conversation-history/types.ts +0 -31
- package/pi-extension/src/freeflow-context/resolver.ts +0 -139
- package/pi-extension/src/freeflow-context/runtime.ts +0 -100
- package/pi-extension/src/freeflow-context/source-projector.ts +0 -106
- package/pi-extension/src/freeflow-context/tool.ts +0 -366
- package/pi-extension/src/freeflow-context/types.ts +0 -70
- package/pi-extension/src/freeflow-context/visibility.ts +0 -53
- package/pi-extension/src/index.ts +0 -390
- package/pi-extension/src/integrations/mcp-config.ts +0 -32
- package/pi-extension/src/provider-support/astra/adapter.ts +0 -108
- package/pi-extension/src/provider-support/astra/history.ts +0 -145
- package/pi-extension/src/provider-support/astra/index.ts +0 -12
- package/pi-extension/src/provider-support/astra/session-state.ts +0 -113
- package/pi-extension/src/provider-support/index.ts +0 -5
- package/pi-extension/src/runtime/request-history.ts +0 -243
- package/pi-extension/src/runtime/runtime-context.ts +0 -860
- package/pi-extension/src/runtime/runtime-identity.ts +0 -8
- package/pi-extension/src/session-sources/events.ts +0 -230
- package/pi-extension/src/session-sources/provenance.ts +0 -39
- package/pi-extension/src/session-sources/read-only-session.ts +0 -170
- package/pi-extension/src/session-sources/sources.ts +0 -334
- package/pi-extension/src/settings/settings-tui.ts +0 -501
- package/pi-extension/src/settings/settings-ui.ts +0 -1652
- package/pi-extension/src/ui/text-component.ts +0 -66
- package/pi-extension/tests/cache-reuse/history.test.js +0 -117
- package/pi-extension/tests/cache-reuse/native.test.js +0 -91
- package/pi-extension/tests/cache-reuse/settings.test.js +0 -211
- package/pi-extension/tests/cognitive-routing-v2/communication.test.js +0 -577
- package/pi-extension/tests/cognitive-routing-v2/compaction-input.test.js +0 -183
- package/pi-extension/tests/cognitive-routing-v2/delegation.test.js +0 -557
- package/pi-extension/tests/cognitive-routing-v2/native.test.js +0 -474
- package/pi-extension/tests/cognitive-routing-v2/performance.test.js +0 -87
- package/pi-extension/tests/cognitive-routing-v2/persistence.test.js +0 -300
- package/pi-extension/tests/cognitive-routing-v2/projection.test.js +0 -241
- package/pi-extension/tests/cognitive-routing-v2/recovery.test.js +0 -1034
- package/pi-extension/tests/cognitive-routing-v2/render.test.js +0 -244
- package/pi-extension/tests/cognitive-routing-v2/runtime.test.js +0 -423
- package/pi-extension/tests/cognitive-routing-v2/stabilization.test.js +0 -521
- package/pi-extension/tests/cognitive-routing-v2/state.test.js +0 -586
- package/pi-extension/tests/context-virtualization/extension.test.js +0 -775
- package/pi-extension/tests/context-virtualization/projector.test.js +0 -110
- package/pi-extension/tests/context-virtualization/runtime.test.js +0 -230
- package/pi-extension/tests/conversation-history/runtime.test.js +0 -98
- package/pi-extension/tests/conversation-history/search.test.js +0 -97
- package/pi-extension/tests/fixtures/pi-host.js +0 -4
- package/pi-extension/tests/fixtures/routing-native.js +0 -191
- package/pi-extension/tests/integration/mode-free-core.test.js +0 -220
- package/pi-extension/tests/integration/pi-extension.test.js +0 -1447
- package/pi-extension/tests/integration/prompt-architecture.test.js +0 -447
- package/pi-extension/tests/integration/unaffected-regressions.test.js +0 -478
- package/pi-extension/tests/provider-support/astra-boundaries.test.js +0 -75
- package/pi-extension/tests/provider-support/astra.test.js +0 -306
- package/pi-extension/tests/provider-support/cli.test.js +0 -92
- package/pi-extension/tests/provider-support/native.test.js +0 -183
- package/pi-extension/tests/settings/settings-tui.test.js +0 -243
- package/pi-extension/tsconfig.json +0 -16
- package/plugin.json +0 -33
- package/runtime/prompts/context-virtualization.md +0 -3
- package/runtime/prompts/conversation-history.md +0 -3
- package/skills/action-selection/SKILL.md +0 -100
- package/skills/action-selection/references/trajectory-stalls.md +0 -71
- package/skills/bypass/SKILL.md +0 -153
- package/skills/commit-work/SKILL.md +0 -145
- package/skills/commit-work/references/git-state-edges.md +0 -94
- package/skills/commit-work/references/simple-push.md +0 -92
- package/skills/commit-work/references/staging-decisions.md +0 -106
- package/skills/decision-gate/SKILL.md +0 -106
- package/skills/design-for-depth/SKILL.md +0 -117
- package/skills/design-for-depth/references/design-pressure-signals.md +0 -182
- package/skills/design-for-depth/references/implementation-decisions.md +0 -76
- package/skills/design-for-depth/references/interface-design-loop.md +0 -136
- package/skills/design-for-depth/references/module-and-dependency-design.md +0 -147
- package/skills/design-for-depth/references/software-design-philosophy.md +0 -202
- package/skills/design-for-depth/references/state-and-failure-boundaries.md +0 -136
- package/skills/diagnose-failure/SKILL.md +0 -125
- package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +0 -48
- package/skills/diagnose-failure/references/flaky-and-performance-diagnosis.md +0 -51
- package/skills/discuss/SKILL.md +0 -116
- package/skills/evaluate-skill/SKILL.md +0 -219
- package/skills/evaluate-skill/references/evaluation-definition-schema.md +0 -385
- package/skills/evaluate-skill/references/evaluation-design.md +0 -112
- package/skills/evaluate-skill/references/execution-and-evidence.md +0 -90
- package/skills/evaluate-skill/references/review-and-revision.md +0 -92
- package/skills/evaluate-skill/scripts/lib/definitions.mjs +0 -407
- package/skills/evaluate-skill/scripts/lib/grade-comparison.mjs +0 -60
- package/skills/evaluate-skill/scripts/lib/grade.mjs +0 -64
- package/skills/evaluate-skill/scripts/lib/runner.mjs +0 -368
- package/skills/evaluate-skill/scripts/pi-guard.mjs +0 -164
- package/skills/evaluate-skill/scripts/skill-eval.mjs +0 -102
- package/skills/execute-work/references/execute-work-edges.md +0 -68
- package/skills/finish-branch/SKILL.md +0 -117
- package/skills/finish-branch/references/integration-options.md +0 -80
- package/skills/handoff/SKILL.md +0 -82
- package/skills/handoff/references/handoff-templates.md +0 -150
- package/skills/launch-work/SKILL.md +0 -116
- package/skills/launch-work/references/launch-readiness.md +0 -85
- package/skills/migration-work/SKILL.md +0 -115
- package/skills/migration-work/references/migration-lifecycle.md +0 -82
- package/skills/release-work/SKILL.md +0 -118
- package/skills/release-work/references/release-evidence.md +0 -78
- package/skills/review-artifact/SKILL.md +0 -142
- package/skills/review-artifact/references/adjudicate-artifact-review.md +0 -101
- package/skills/review-artifact/references/independent-artifact-reviewer-contract.md +0 -159
- package/skills/review-work/references/adjudicate-work-review.md +0 -97
- package/skills/review-work/references/independent-work-reviewer-contract.md +0 -139
- package/skills/review-work/references/security-risk-lens.md +0 -69
- package/skills/setup-freeflow/references/activation-contract.md +0 -109
- package/skills/setup-freeflow/references/host-setup.md +0 -67
- package/skills/simplify-code/SKILL.md +0 -85
- package/skills/simplify-code/references/simplification-patterns.md +0 -70
- package/skills/verify-work/references/browser-runtime-evidence.md +0 -55
- package/skills/verify-work/references/integration-evidence.md +0 -47
- package/skills/verify-work/references/performance-evidence.md +0 -57
- package/skills/workflow/SKILL.md +0 -127
- package/skills/workflow/references/domain-skill-composition.md +0 -43
- package/skills/write-plan/SKILL.md +0 -92
- package/skills/write-plan/references/plan-shapes.md +0 -156
- package/skills/write-skill/references/activation-boundaries.md +0 -104
- package/skills/write-skill/references/agent-first-instructions.md +0 -121
- package/skills/write-skill/references/progressive-disclosure.md +0 -127
- package/skills/write-skill/references/skill-dependency-graphs.md +0 -190
- package/skills/write-spec/SKILL.md +0 -92
- package/skills/write-spec/references/artifact-standards.md +0 -86
- package/skills/write-spec/references/decision-records.md +0 -78
- package/skills/write-spec/references/spec-shapes.md +0 -143
- /package/pi-extension/dist/{cognitive-routing-v2 → cognitive-routing}/budget.js +0 -0
- /package/skills/{evaluate-skill → evaluate-behavior}/scripts/lib/evidence.mjs +0 -0
- /package/skills/{evaluate-skill → evaluate-behavior}/scripts/pi-observer.mjs +0 -0
|
@@ -1,407 +0,0 @@
|
|
|
1
|
-
import { readFile, realpath } from "node:fs/promises";
|
|
2
|
-
import path from "node:path";
|
|
3
|
-
|
|
4
|
-
const ID = /^[a-z][a-z0-9]*(?:-[a-z0-9]+)*$/;
|
|
5
|
-
const EVALUATION_TYPES = new Set(["description", "body", "end-to-end"]);
|
|
6
|
-
const VARIANTS = ["baseline", "candidate"];
|
|
7
|
-
const EVALUATION_HOSTS = new Set(["pi", "piflow"]);
|
|
8
|
-
const RESERVED_ENVIRONMENT_KEYS = new Set([
|
|
9
|
-
"PATH",
|
|
10
|
-
"HOME",
|
|
11
|
-
"PWD",
|
|
12
|
-
"OLDPWD",
|
|
13
|
-
"SHELL",
|
|
14
|
-
"BASH_ENV",
|
|
15
|
-
"NODE_OPTIONS",
|
|
16
|
-
"NODE_PATH",
|
|
17
|
-
"PI_PACKAGE_DIR",
|
|
18
|
-
"PIFLOW_CODING_AGENT_DIR",
|
|
19
|
-
"PIFLOW_CODING_AGENT_SESSION_DIR",
|
|
20
|
-
]);
|
|
21
|
-
|
|
22
|
-
export class DefinitionError extends Error {
|
|
23
|
-
constructor(code, message, definitionPath = null) {
|
|
24
|
-
super(message);
|
|
25
|
-
this.name = "DefinitionError";
|
|
26
|
-
this.code = code;
|
|
27
|
-
this.definitionPath = definitionPath;
|
|
28
|
-
}
|
|
29
|
-
}
|
|
30
|
-
|
|
31
|
-
function fail(code, message, definitionPath) {
|
|
32
|
-
throw new DefinitionError(code, message, definitionPath);
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
function isPlainObject(value) {
|
|
36
|
-
return value !== null && typeof value === "object" && !Array.isArray(value);
|
|
37
|
-
}
|
|
38
|
-
|
|
39
|
-
function requireObject(value, label, definitionPath) {
|
|
40
|
-
if (!isPlainObject(value)) fail("invalid-definition", `${label} must be an object`, definitionPath);
|
|
41
|
-
return value;
|
|
42
|
-
}
|
|
43
|
-
|
|
44
|
-
function requireExactKeys(value, required, optional, label, definitionPath) {
|
|
45
|
-
const object = requireObject(value, label, definitionPath);
|
|
46
|
-
const allowed = new Set([...required, ...optional]);
|
|
47
|
-
for (const key of required) {
|
|
48
|
-
if (!Object.hasOwn(object, key)) fail("invalid-definition", `${label} is missing ${key}`, definitionPath);
|
|
49
|
-
}
|
|
50
|
-
for (const key of Object.keys(object)) {
|
|
51
|
-
if (!allowed.has(key)) fail("invalid-definition", `${label} contains unsupported field ${key}`, definitionPath);
|
|
52
|
-
}
|
|
53
|
-
return object;
|
|
54
|
-
}
|
|
55
|
-
|
|
56
|
-
function requireId(value, label, definitionPath) {
|
|
57
|
-
if (typeof value !== "string" || value.length > 64 || !ID.test(value)) {
|
|
58
|
-
fail(
|
|
59
|
-
"invalid-definition",
|
|
60
|
-
`${label} must start with a lowercase letter and use lowercase letters, numbers, or single hyphens up to 64 characters`,
|
|
61
|
-
definitionPath,
|
|
62
|
-
);
|
|
63
|
-
}
|
|
64
|
-
return value;
|
|
65
|
-
}
|
|
66
|
-
|
|
67
|
-
function requireString(value, label, definitionPath) {
|
|
68
|
-
if (typeof value !== "string" || value.trim() === "") {
|
|
69
|
-
fail("invalid-definition", `${label} must be a non-empty string`, definitionPath);
|
|
70
|
-
}
|
|
71
|
-
return value;
|
|
72
|
-
}
|
|
73
|
-
|
|
74
|
-
function requireStringArray(value, label, definitionPath, { paths = false, unique = false } = {}) {
|
|
75
|
-
if (!Array.isArray(value)) fail("invalid-definition", `${label} must be an array`, definitionPath);
|
|
76
|
-
const seen = new Set();
|
|
77
|
-
return value.map((entry, index) => {
|
|
78
|
-
const string = requireString(entry, `${label}[${index}]`, definitionPath);
|
|
79
|
-
if (paths) requireSafeRelativePath(string, `${label}[${index}]`, definitionPath);
|
|
80
|
-
if (unique && seen.has(string)) {
|
|
81
|
-
fail("invalid-definition", `${label} contains duplicate ${string}`, definitionPath);
|
|
82
|
-
}
|
|
83
|
-
seen.add(string);
|
|
84
|
-
return string;
|
|
85
|
-
});
|
|
86
|
-
}
|
|
87
|
-
|
|
88
|
-
function requireSafeRelativePath(value, label, definitionPath) {
|
|
89
|
-
const string = requireString(value, label, definitionPath);
|
|
90
|
-
const normalized = path.normalize(string);
|
|
91
|
-
if (path.isAbsolute(string) || normalized === "." || normalized === ".." || normalized.startsWith(`..${path.sep}`)) {
|
|
92
|
-
fail("unsafe-path", `${label} must stay inside the definition root`, definitionPath);
|
|
93
|
-
}
|
|
94
|
-
return string;
|
|
95
|
-
}
|
|
96
|
-
|
|
97
|
-
function requireSuiteReference(value, label, definitionPath) {
|
|
98
|
-
const string = requireString(value, label, definitionPath);
|
|
99
|
-
if (path.isAbsolute(string) || path.normalize(string) === ".") {
|
|
100
|
-
fail("unsafe-path", `${label} must be relative to the suite file`, definitionPath);
|
|
101
|
-
}
|
|
102
|
-
return string;
|
|
103
|
-
}
|
|
104
|
-
|
|
105
|
-
function validateInput(value, definitionPath) {
|
|
106
|
-
const input = requireExactKeys(value, [], ["prompt", "turns"], "group.input", definitionPath);
|
|
107
|
-
const hasPrompt = Object.hasOwn(input, "prompt");
|
|
108
|
-
const hasTurns = Object.hasOwn(input, "turns");
|
|
109
|
-
if (hasPrompt === hasTurns) {
|
|
110
|
-
fail("invalid-definition", "group.input must contain exactly one of prompt or turns", definitionPath);
|
|
111
|
-
}
|
|
112
|
-
if (hasPrompt) requireString(input.prompt, "group.input.prompt", definitionPath);
|
|
113
|
-
if (hasTurns) {
|
|
114
|
-
const turns = requireStringArray(input.turns, "group.input.turns", definitionPath);
|
|
115
|
-
if (turns.length === 0) fail("invalid-definition", "group.input.turns must not be empty", definitionPath);
|
|
116
|
-
}
|
|
117
|
-
}
|
|
118
|
-
|
|
119
|
-
function validateSource(value, label, definitionPath) {
|
|
120
|
-
const source = requireObject(value, label, definitionPath);
|
|
121
|
-
if (source.kind === "working-tree") {
|
|
122
|
-
requireExactKeys(source, ["kind"], [], label, definitionPath);
|
|
123
|
-
return;
|
|
124
|
-
}
|
|
125
|
-
if (source.kind === "git") {
|
|
126
|
-
requireExactKeys(source, ["kind", "ref"], [], label, definitionPath);
|
|
127
|
-
requireString(source.ref, `${label}.ref`, definitionPath);
|
|
128
|
-
return;
|
|
129
|
-
}
|
|
130
|
-
fail("invalid-definition", `${label}.kind must be working-tree or git`, definitionPath);
|
|
131
|
-
}
|
|
132
|
-
|
|
133
|
-
function validateEnvironment(value, label, definitionPath) {
|
|
134
|
-
const environment = requireExactKeys(value, ["source", "skills", "target", "context"], [], label, definitionPath);
|
|
135
|
-
validateSource(environment.source, `${label}.source`, definitionPath);
|
|
136
|
-
const skills = requireStringArray(environment.skills, `${label}.skills`, definitionPath, { paths: true });
|
|
137
|
-
requireStringArray(environment.context, `${label}.context`, definitionPath, { paths: true });
|
|
138
|
-
if (
|
|
139
|
-
environment.target !== null &&
|
|
140
|
-
(!Number.isInteger(environment.target) || environment.target < 0 || environment.target >= skills.length)
|
|
141
|
-
) {
|
|
142
|
-
fail("invalid-definition", `${label}.target must be null or an index into skills`, definitionPath);
|
|
143
|
-
}
|
|
144
|
-
}
|
|
145
|
-
|
|
146
|
-
function validateRuntime(value, definitionPath) {
|
|
147
|
-
const runtime = requireExactKeys(
|
|
148
|
-
value,
|
|
149
|
-
["host", "extensions", "environment", "session"],
|
|
150
|
-
[],
|
|
151
|
-
"group.runtime",
|
|
152
|
-
definitionPath,
|
|
153
|
-
);
|
|
154
|
-
if (!EVALUATION_HOSTS.has(runtime.host)) {
|
|
155
|
-
fail("invalid-definition", "group.runtime.host must be pi or piflow", definitionPath);
|
|
156
|
-
}
|
|
157
|
-
if (!Array.isArray(runtime.extensions)) {
|
|
158
|
-
fail("invalid-definition", "group.runtime.extensions must be an array", definitionPath);
|
|
159
|
-
}
|
|
160
|
-
const bundleIds = new Set();
|
|
161
|
-
for (const [index, entry] of runtime.extensions.entries()) {
|
|
162
|
-
const bundle = requireExactKeys(
|
|
163
|
-
entry,
|
|
164
|
-
["entry", "resources"],
|
|
165
|
-
[],
|
|
166
|
-
`group.runtime.extensions[${index}]`,
|
|
167
|
-
definitionPath,
|
|
168
|
-
);
|
|
169
|
-
requireSafeRelativePath(bundle.entry, `group.runtime.extensions[${index}].entry`, definitionPath);
|
|
170
|
-
const resources = requireStringArray(
|
|
171
|
-
bundle.resources,
|
|
172
|
-
`group.runtime.extensions[${index}].resources`,
|
|
173
|
-
definitionPath,
|
|
174
|
-
{ paths: true, unique: true },
|
|
175
|
-
);
|
|
176
|
-
if (resources.length === 0) {
|
|
177
|
-
fail("invalid-definition", `group.runtime.extensions[${index}].resources must not be empty`, definitionPath);
|
|
178
|
-
}
|
|
179
|
-
const bundleId = `${bundle.entry}\u0000${resources.join("\u0000")}`;
|
|
180
|
-
if (bundleIds.has(bundleId)) {
|
|
181
|
-
fail("invalid-definition", "group.runtime.extensions contains duplicate bundles", definitionPath);
|
|
182
|
-
}
|
|
183
|
-
bundleIds.add(bundleId);
|
|
184
|
-
}
|
|
185
|
-
if (typeof runtime.session !== "boolean") {
|
|
186
|
-
fail("invalid-definition", "group.runtime.session must be a boolean", definitionPath);
|
|
187
|
-
}
|
|
188
|
-
const environment = requireExactKeys(
|
|
189
|
-
runtime.environment,
|
|
190
|
-
["literal", "inherit"],
|
|
191
|
-
[],
|
|
192
|
-
"group.runtime.environment",
|
|
193
|
-
definitionPath,
|
|
194
|
-
);
|
|
195
|
-
const literal = requireObject(environment.literal, "group.runtime.environment.literal", definitionPath);
|
|
196
|
-
const inherited = requireStringArray(environment.inherit, "group.runtime.environment.inherit", definitionPath, {
|
|
197
|
-
unique: true,
|
|
198
|
-
});
|
|
199
|
-
const literalKeys = new Set(Object.keys(literal).map((key) => key.toUpperCase()));
|
|
200
|
-
for (const [key, value] of Object.entries(literal)) {
|
|
201
|
-
const normalizedKey = key.toUpperCase();
|
|
202
|
-
if (
|
|
203
|
-
!/^[A-Za-z_][A-Za-z0-9_]*$/.test(key) ||
|
|
204
|
-
isBlockedEnvironmentKey(normalizedKey) ||
|
|
205
|
-
/TOKEN|SECRET|PASSWORD|API[_-]?KEY|PRIVATE[_-]?KEY|CREDENTIAL/i.test(key)
|
|
206
|
-
) {
|
|
207
|
-
fail(
|
|
208
|
-
"invalid-definition",
|
|
209
|
-
`group.runtime.environment.literal contains a reserved or secret-like key: ${key}`,
|
|
210
|
-
definitionPath,
|
|
211
|
-
);
|
|
212
|
-
}
|
|
213
|
-
if (typeof value !== "string") {
|
|
214
|
-
fail("invalid-definition", `group.runtime.environment.literal.${key} must be a string`, definitionPath);
|
|
215
|
-
}
|
|
216
|
-
}
|
|
217
|
-
for (const key of inherited) {
|
|
218
|
-
const normalizedKey = key.toUpperCase();
|
|
219
|
-
if (!/^[A-Za-z_][A-Za-z0-9_]*$/.test(key) || isBlockedEnvironmentKey(normalizedKey)) {
|
|
220
|
-
fail("invalid-definition", `group.runtime.environment.inherit contains an invalid key: ${key}`, definitionPath);
|
|
221
|
-
}
|
|
222
|
-
if (literalKeys.has(normalizedKey)) {
|
|
223
|
-
fail(
|
|
224
|
-
"invalid-definition",
|
|
225
|
-
`group.runtime.environment key is declared as both literal and inherited: ${key}`,
|
|
226
|
-
definitionPath,
|
|
227
|
-
);
|
|
228
|
-
}
|
|
229
|
-
}
|
|
230
|
-
}
|
|
231
|
-
|
|
232
|
-
function isBlockedEnvironmentKey(normalizedKey) {
|
|
233
|
-
return (
|
|
234
|
-
RESERVED_ENVIRONMENT_KEYS.has(normalizedKey) ||
|
|
235
|
-
normalizedKey.startsWith("SKILL_EVAL_") ||
|
|
236
|
-
normalizedKey.startsWith("PI_") ||
|
|
237
|
-
normalizedKey.startsWith("LD_") ||
|
|
238
|
-
normalizedKey.startsWith("DYLD_")
|
|
239
|
-
);
|
|
240
|
-
}
|
|
241
|
-
|
|
242
|
-
function validateExpectations(value, definitionPath) {
|
|
243
|
-
if (!Array.isArray(value)) fail("invalid-definition", "group.expectations must be an array", definitionPath);
|
|
244
|
-
const ids = new Set();
|
|
245
|
-
for (const [index, entry] of value.entries()) {
|
|
246
|
-
const expectation = requireObject(entry, `group.expectations[${index}]`, definitionPath);
|
|
247
|
-
requireId(expectation.id, `group.expectations[${index}].id`, definitionPath);
|
|
248
|
-
requireString(expectation.kind, `group.expectations[${index}].kind`, definitionPath);
|
|
249
|
-
if (ids.has(expectation.id)) {
|
|
250
|
-
fail("invalid-definition", `group.expectations contains duplicate ID ${expectation.id}`, definitionPath);
|
|
251
|
-
}
|
|
252
|
-
ids.add(expectation.id);
|
|
253
|
-
}
|
|
254
|
-
}
|
|
255
|
-
|
|
256
|
-
function validateModel(value, definitionPath) {
|
|
257
|
-
const model = requireExactKeys(value, ["model"], ["thinking"], "group.model", definitionPath);
|
|
258
|
-
requireString(model.model, "group.model.model", definitionPath);
|
|
259
|
-
if (Object.hasOwn(model, "thinking")) requireString(model.thinking, "group.model.thinking", definitionPath);
|
|
260
|
-
}
|
|
261
|
-
|
|
262
|
-
function validateGroup(value, definitionPath) {
|
|
263
|
-
const group = requireExactKeys(
|
|
264
|
-
value,
|
|
265
|
-
[
|
|
266
|
-
"schema_version",
|
|
267
|
-
"kind",
|
|
268
|
-
"id",
|
|
269
|
-
"type",
|
|
270
|
-
"input",
|
|
271
|
-
"fixture",
|
|
272
|
-
"tools",
|
|
273
|
-
"variants",
|
|
274
|
-
"expectations",
|
|
275
|
-
"review_questions",
|
|
276
|
-
],
|
|
277
|
-
["model", "runtime"],
|
|
278
|
-
"group",
|
|
279
|
-
definitionPath,
|
|
280
|
-
);
|
|
281
|
-
if (group.schema_version !== 1) fail("unsupported-schema", "group.schema_version must be 1", definitionPath);
|
|
282
|
-
if (group.kind !== "group") fail("invalid-definition", "group.kind must be group", definitionPath);
|
|
283
|
-
requireId(group.id, "group.id", definitionPath);
|
|
284
|
-
if (!EVALUATION_TYPES.has(group.type)) {
|
|
285
|
-
fail("invalid-definition", "group.type must be description, body, or end-to-end", definitionPath);
|
|
286
|
-
}
|
|
287
|
-
validateInput(group.input, definitionPath);
|
|
288
|
-
if (group.fixture !== null) requireSafeRelativePath(group.fixture, "group.fixture", definitionPath);
|
|
289
|
-
requireStringArray(group.tools, "group.tools", definitionPath, { unique: true });
|
|
290
|
-
if (Object.hasOwn(group, "runtime")) validateRuntime(group.runtime, definitionPath);
|
|
291
|
-
const variants = requireExactKeys(group.variants, VARIANTS, [], "group.variants", definitionPath);
|
|
292
|
-
for (const variant of VARIANTS) validateEnvironment(variants[variant], `group.variants.${variant}`, definitionPath);
|
|
293
|
-
if (variants.candidate.target === null && variants.candidate.skills.length > 0) {
|
|
294
|
-
fail(
|
|
295
|
-
"invalid-definition",
|
|
296
|
-
"group.variants.candidate.target must identify the candidate target skill when candidate skills are declared",
|
|
297
|
-
definitionPath,
|
|
298
|
-
);
|
|
299
|
-
}
|
|
300
|
-
validateExpectations(group.expectations, definitionPath);
|
|
301
|
-
requireStringArray(group.review_questions, "group.review_questions", definitionPath);
|
|
302
|
-
if (Object.hasOwn(group, "model")) validateModel(group.model, definitionPath);
|
|
303
|
-
return group;
|
|
304
|
-
}
|
|
305
|
-
|
|
306
|
-
function validateSuite(value, definitionPath) {
|
|
307
|
-
const suite = requireExactKeys(value, ["schema_version", "kind", "id", "groups"], [], "suite", definitionPath);
|
|
308
|
-
if (suite.schema_version !== 1) fail("unsupported-schema", "suite.schema_version must be 1", definitionPath);
|
|
309
|
-
if (suite.kind !== "suite") fail("invalid-definition", "suite.kind must be suite", definitionPath);
|
|
310
|
-
requireId(suite.id, "suite.id", definitionPath);
|
|
311
|
-
const groups = requireStringArray(suite.groups, "suite.groups", definitionPath, { unique: true });
|
|
312
|
-
for (const [index, reference] of groups.entries()) {
|
|
313
|
-
requireSuiteReference(reference, `suite.groups[${index}]`, definitionPath);
|
|
314
|
-
}
|
|
315
|
-
if (groups.length === 0) fail("invalid-definition", "suite.groups must not be empty", definitionPath);
|
|
316
|
-
return suite;
|
|
317
|
-
}
|
|
318
|
-
|
|
319
|
-
function isContained(root, target) {
|
|
320
|
-
const relative = path.relative(root, target);
|
|
321
|
-
return relative === "" || (!relative.startsWith(`..${path.sep}`) && relative !== ".." && !path.isAbsolute(relative));
|
|
322
|
-
}
|
|
323
|
-
|
|
324
|
-
async function readJsonFile(file, root) {
|
|
325
|
-
const lexicalFile = path.resolve(file);
|
|
326
|
-
if (!isContained(root, lexicalFile)) fail("unsafe-path", `Definition escapes root: ${file}`, lexicalFile);
|
|
327
|
-
|
|
328
|
-
let canonicalRoot;
|
|
329
|
-
let canonicalFile;
|
|
330
|
-
try {
|
|
331
|
-
[canonicalRoot, canonicalFile] = await Promise.all([realpath(root), realpath(lexicalFile)]);
|
|
332
|
-
} catch {
|
|
333
|
-
fail("unreadable-definition", `Cannot resolve definition: ${lexicalFile}`, lexicalFile);
|
|
334
|
-
}
|
|
335
|
-
if (!isContained(canonicalRoot, canonicalFile)) {
|
|
336
|
-
fail("unsafe-path", `Definition symlink escapes root: ${lexicalFile}`, lexicalFile);
|
|
337
|
-
}
|
|
338
|
-
|
|
339
|
-
let contents;
|
|
340
|
-
try {
|
|
341
|
-
contents = await readFile(canonicalFile, "utf8");
|
|
342
|
-
} catch {
|
|
343
|
-
fail("unreadable-definition", `Cannot read definition: ${lexicalFile}`, lexicalFile);
|
|
344
|
-
}
|
|
345
|
-
try {
|
|
346
|
-
return { value: JSON.parse(contents), file: lexicalFile };
|
|
347
|
-
} catch {
|
|
348
|
-
fail("invalid-json", `Definition is not valid JSON: ${lexicalFile}`, lexicalFile);
|
|
349
|
-
}
|
|
350
|
-
}
|
|
351
|
-
|
|
352
|
-
export async function loadDefinition(file, { root = process.cwd() } = {}) {
|
|
353
|
-
const definitionRoot = path.resolve(root);
|
|
354
|
-
const loaded = await readJsonFile(file, definitionRoot);
|
|
355
|
-
const object = requireObject(loaded.value, "definition", loaded.file);
|
|
356
|
-
if (object.kind === "group") return validateGroup(object, loaded.file);
|
|
357
|
-
if (object.kind !== "suite") fail("invalid-definition", "definition.kind must be group or suite", loaded.file);
|
|
358
|
-
|
|
359
|
-
const suite = validateSuite(object, loaded.file);
|
|
360
|
-
const groups = [];
|
|
361
|
-
const ids = new Set();
|
|
362
|
-
for (const reference of suite.groups) {
|
|
363
|
-
const groupFile = path.resolve(path.dirname(loaded.file), reference);
|
|
364
|
-
const groupLoaded = await readJsonFile(groupFile, definitionRoot);
|
|
365
|
-
const group = validateGroup(groupLoaded.value, groupLoaded.file);
|
|
366
|
-
if (ids.has(group.id)) fail("invalid-definition", `suite contains duplicate group ID ${group.id}`, loaded.file);
|
|
367
|
-
ids.add(group.id);
|
|
368
|
-
groups.push(group);
|
|
369
|
-
}
|
|
370
|
-
return { ...suite, groups };
|
|
371
|
-
}
|
|
372
|
-
|
|
373
|
-
function variantSelection(selected) {
|
|
374
|
-
return {
|
|
375
|
-
baseline: selected === null || selected === "baseline" ? "selected" : "not-selected",
|
|
376
|
-
candidate: selected === null || selected === "candidate" ? "selected" : "not-selected",
|
|
377
|
-
};
|
|
378
|
-
}
|
|
379
|
-
|
|
380
|
-
export function selectDefinition(definition, { group = null, variant = null } = {}) {
|
|
381
|
-
if (variant !== null && !VARIANTS.includes(variant)) {
|
|
382
|
-
fail("invalid-selector", "variant must be baseline or candidate", null);
|
|
383
|
-
}
|
|
384
|
-
if (definition.kind === "group" && group !== null) {
|
|
385
|
-
fail("invalid-selector", "--group cannot be used with a direct group definition", null);
|
|
386
|
-
}
|
|
387
|
-
|
|
388
|
-
const available = definition.kind === "group" ? [definition] : definition.groups;
|
|
389
|
-
let selected = available;
|
|
390
|
-
if (group !== null) {
|
|
391
|
-
const position = typeof group === "number" || /^\d+$/.test(group) ? Number(group) : null;
|
|
392
|
-
selected =
|
|
393
|
-
position === null ? available.filter((entry) => entry.id === group) : [available[position - 1]].filter(Boolean);
|
|
394
|
-
if (selected.length === 0) fail("unknown-group", `Unknown group selector: ${group}`, null);
|
|
395
|
-
}
|
|
396
|
-
|
|
397
|
-
return {
|
|
398
|
-
kind: "selection",
|
|
399
|
-
definitionKind: definition.kind,
|
|
400
|
-
id: definition.id,
|
|
401
|
-
groups: selected.map((entry) => ({
|
|
402
|
-
position: available.indexOf(entry) + 1,
|
|
403
|
-
group: entry,
|
|
404
|
-
variants: variantSelection(variant),
|
|
405
|
-
})),
|
|
406
|
-
};
|
|
407
|
-
}
|
|
@@ -1,60 +0,0 @@
|
|
|
1
|
-
import { isDeepStrictEqual } from "node:util";
|
|
2
|
-
|
|
3
|
-
import { hasOwn } from "./grade-support.mjs";
|
|
4
|
-
|
|
5
|
-
export function gradeComparisons(expectations, checks) {
|
|
6
|
-
/** @type {Map<string, any[]>} */
|
|
7
|
-
const grouped = new Map();
|
|
8
|
-
const errors = /** @type {any[]} */ ([]);
|
|
9
|
-
for (const expectation of expectations) {
|
|
10
|
-
if (!hasOwn(expectation, "comparison")) continue;
|
|
11
|
-
if (typeof expectation.comparison !== "string" || !/^[a-z][a-z0-9]*(?:-[a-z0-9]+)*$/.test(expectation.comparison)) {
|
|
12
|
-
errors.push({ id: expectation.id, reason: "invalid comparison identity" });
|
|
13
|
-
continue;
|
|
14
|
-
}
|
|
15
|
-
const entries = grouped.get(expectation.comparison) ?? [];
|
|
16
|
-
entries.push(expectation);
|
|
17
|
-
grouped.set(expectation.comparison, entries);
|
|
18
|
-
}
|
|
19
|
-
|
|
20
|
-
/** @type {Map<string, any>} */
|
|
21
|
-
const byCheck = new Map(checks.map((check) => [check.id, check]));
|
|
22
|
-
const comparisons = /** @type {any[]} */ ([]);
|
|
23
|
-
for (const [id, entries] of grouped) {
|
|
24
|
-
const baselineExpectation = entries.find((entry) => entry.variant === "baseline");
|
|
25
|
-
const candidateExpectation = entries.find((entry) => entry.variant === "candidate");
|
|
26
|
-
if (entries.length !== 2 || !baselineExpectation || !candidateExpectation) {
|
|
27
|
-
errors.push({ id, reason: "comparison requires one baseline and one candidate expectation" });
|
|
28
|
-
continue;
|
|
29
|
-
}
|
|
30
|
-
const baseline = byCheck.get(baselineExpectation.id);
|
|
31
|
-
const candidate = byCheck.get(candidateExpectation.id);
|
|
32
|
-
if (!sameCheck(baseline, candidate)) {
|
|
33
|
-
errors.push({ id, reason: "comparison expectations must describe the same deterministic check" });
|
|
34
|
-
continue;
|
|
35
|
-
}
|
|
36
|
-
comparisons.push({
|
|
37
|
-
id,
|
|
38
|
-
kind: baseline.kind,
|
|
39
|
-
baseline: { check: baseline.id, state: baseline.state },
|
|
40
|
-
candidate: { check: candidate.id, state: candidate.state },
|
|
41
|
-
transition: transition(baseline.state, candidate.state),
|
|
42
|
-
});
|
|
43
|
-
}
|
|
44
|
-
return { comparisons, errors };
|
|
45
|
-
}
|
|
46
|
-
|
|
47
|
-
function sameCheck(baseline, candidate) {
|
|
48
|
-
return (
|
|
49
|
-
baseline !== undefined &&
|
|
50
|
-
candidate !== undefined &&
|
|
51
|
-
baseline.kind === candidate.kind &&
|
|
52
|
-
isDeepStrictEqual(baseline.expected, candidate.expected)
|
|
53
|
-
);
|
|
54
|
-
}
|
|
55
|
-
|
|
56
|
-
function transition(baseline, candidate) {
|
|
57
|
-
return [baseline, candidate].every((state) => state === "pass" || state === "fail")
|
|
58
|
-
? `${baseline}-to-${candidate}`
|
|
59
|
-
: "unavailable";
|
|
60
|
-
}
|
|
@@ -1,64 +0,0 @@
|
|
|
1
|
-
import { gradeComparisons } from "./grade-comparison.mjs";
|
|
2
|
-
import {
|
|
3
|
-
gradeContextText,
|
|
4
|
-
gradeResourceRead,
|
|
5
|
-
gradeResponseText,
|
|
6
|
-
gradeSkillRead,
|
|
7
|
-
gradeToolCall,
|
|
8
|
-
} from "./grade-interaction.mjs";
|
|
9
|
-
import { gradeChangedPaths, gradeFileText, gradeJson, gradePath } from "./grade-workspace.mjs";
|
|
10
|
-
|
|
11
|
-
const GRADERS = new Map([
|
|
12
|
-
["skill-read", gradeSkillRead],
|
|
13
|
-
["resource-read", gradeResourceRead],
|
|
14
|
-
["path", gradePath],
|
|
15
|
-
["changed-paths", gradeChangedPaths],
|
|
16
|
-
["file-text", gradeFileText],
|
|
17
|
-
["json", gradeJson],
|
|
18
|
-
["response-text", gradeResponseText],
|
|
19
|
-
["context-text", gradeContextText],
|
|
20
|
-
["tool-call", gradeToolCall],
|
|
21
|
-
]);
|
|
22
|
-
|
|
23
|
-
/**
|
|
24
|
-
* @param {any} group
|
|
25
|
-
* @param {any} runs
|
|
26
|
-
* @param {any} evidence
|
|
27
|
-
* @returns {Promise<any>}
|
|
28
|
-
*/
|
|
29
|
-
export async function gradeDeterministic(group, runs, evidence) {
|
|
30
|
-
const checks = /** @type {Array<any>} */ ([]);
|
|
31
|
-
const errors = /** @type {Array<any>} */ ([]);
|
|
32
|
-
|
|
33
|
-
for (const expectation of group.expectations) {
|
|
34
|
-
const grader = GRADERS.get(expectation.kind);
|
|
35
|
-
if (!grader) {
|
|
36
|
-
errors.push({ id: expectation.id, reason: `unsupported expectation kind: ${expectation.kind}` });
|
|
37
|
-
continue;
|
|
38
|
-
}
|
|
39
|
-
try {
|
|
40
|
-
const result = await grader(group, runs, expectation);
|
|
41
|
-
if (result.error) errors.push({ id: expectation.id, reason: result.error });
|
|
42
|
-
else checks.push(result);
|
|
43
|
-
} catch (error) {
|
|
44
|
-
errors.push({ id: expectation.id, reason: error instanceof Error ? error.message : String(error) });
|
|
45
|
-
}
|
|
46
|
-
}
|
|
47
|
-
|
|
48
|
-
const compared = gradeComparisons(group.expectations, checks);
|
|
49
|
-
errors.push(...compared.errors);
|
|
50
|
-
return {
|
|
51
|
-
schema_version: 1,
|
|
52
|
-
state: reportState(checks, errors),
|
|
53
|
-
evidence,
|
|
54
|
-
checks,
|
|
55
|
-
comparisons: compared.comparisons,
|
|
56
|
-
errors,
|
|
57
|
-
};
|
|
58
|
-
}
|
|
59
|
-
|
|
60
|
-
function reportState(checks, errors) {
|
|
61
|
-
if (errors.length > 0) return "grade-error";
|
|
62
|
-
if (checks.length > 0 && checks.every((check) => check.state === "unavailable")) return "unavailable";
|
|
63
|
-
return "complete";
|
|
64
|
-
}
|