@hassangameryt/freeflow 0.2.0 → 0.4.0
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 +1 -1
- package/.claude-plugin/marketplace.json +4 -4
- package/{plugins/freeflow/.claude-plugin → .claude-plugin}/plugin.json +5 -2
- package/{plugins/freeflow/.codex-plugin → .codex-plugin}/plugin.json +8 -9
- package/README.md +194 -127
- package/assets/feedback-loop.png +0 -0
- package/assets/freeflow-plugin-icon.png +0 -0
- package/assets/freeflow_workflow_map.png +0 -0
- package/assets/workflow.png +0 -0
- package/command-surface.json +129 -0
- package/hooks/freeflow-runtime-context.mjs +419 -0
- package/hooks/tests/check-runtime-context-hook.sh +223 -0
- package/package.json +41 -22
- package/pi-extension/dist/index.js +269 -0
- package/pi-extension/dist/integrations/mcp-config.js +29 -0
- package/pi-extension/dist/output-router/host-producer-identification.js +232 -0
- package/pi-extension/dist/output-router/native-safety-net.js +216 -0
- package/pi-extension/dist/output-router/observed-tool-routing.js +122 -0
- package/pi-extension/dist/output-router/renderers.js +1023 -0
- package/pi-extension/dist/output-router/router-tools.js +554 -0
- package/pi-extension/dist/output-router/schemas.js +383 -0
- package/pi-extension/dist/output-router/status.js +744 -0
- package/pi-extension/dist/output-router/utils.js +502 -0
- package/pi-extension/dist/runtime/runtime-context.js +798 -0
- package/pi-extension/dist/settings/settings-tui.js +314 -0
- package/pi-extension/dist/settings/settings-ui.js +1487 -0
- package/pi-extension/freeflow/index.js +1 -0
- package/pi-extension/src/index.ts +295 -0
- package/pi-extension/src/integrations/mcp-config.ts +32 -0
- package/pi-extension/src/output-router/host-producer-identification.ts +256 -0
- package/pi-extension/src/output-router/native-safety-net.ts +248 -0
- package/pi-extension/src/output-router/observed-tool-routing.ts +134 -0
- package/pi-extension/src/output-router/renderers.ts +1108 -0
- package/pi-extension/src/output-router/router-tools.ts +579 -0
- package/pi-extension/src/output-router/schemas.ts +387 -0
- package/pi-extension/src/output-router/status.ts +791 -0
- package/pi-extension/src/output-router/utils.ts +554 -0
- package/pi-extension/src/runtime/runtime-context.ts +895 -0
- package/pi-extension/src/settings/settings-tui.ts +408 -0
- package/pi-extension/src/settings/settings-ui.ts +1730 -0
- package/pi-extension/tests/integration/pi-extension.test.js +4018 -0
- package/pi-extension/tests/output-router/observed-producers.test.js +132 -0
- package/pi-extension/tests/output-router/search.test.js +722 -0
- package/pi-extension/tests/settings/settings-tui.test.js +243 -0
- package/pi-extension/tsconfig.json +16 -0
- package/{plugins/freeflow/router/dist → router/dist/benchmarks}/benchmark-harness.d.ts +16 -13
- package/router/dist/benchmarks/benchmark-harness.js +92 -0
- package/router/dist/benchmarks/benchmarks.d.ts +109 -0
- package/router/dist/benchmarks/benchmarks.js +979 -0
- package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +95 -0
- package/router/dist/benchmarks/codex-qa-benchmarks.js +500 -0
- package/router/dist/benchmarks/command-benchmarks.d.ts +143 -0
- package/router/dist/benchmarks/command-benchmarks.js +698 -0
- package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +82 -0
- package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +773 -0
- package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +132 -0
- package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1380 -0
- package/router/dist/benchmarks/context-saving-baseline.d.ts +60 -0
- package/router/dist/benchmarks/context-saving-baseline.js +470 -0
- package/router/dist/benchmarks/index-benchmarks.d.ts +103 -0
- package/router/dist/benchmarks/index-benchmarks.js +862 -0
- package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +101 -0
- package/router/dist/benchmarks/storage-policy-benchmarks.js +618 -0
- package/router/dist/benchmarks/vault-index-benchmarks.d.ts +56 -0
- package/router/dist/benchmarks/vault-index-benchmarks.js +322 -0
- package/router/dist/config/config.d.ts +103 -0
- package/router/dist/config/config.js +632 -0
- package/{plugins/freeflow/router/dist → router/dist/config}/router-contract.d.ts +2 -2
- package/router/dist/config/router-contract.js +54 -0
- package/{plugins/freeflow/router/dist → router/dist/config}/schema.d.ts +19 -10
- package/router/dist/config/schema.js +648 -0
- package/router/dist/config/types.d.ts +573 -0
- package/router/dist/config/types.js +41 -0
- package/router/dist/evidence/bounded-evidence.d.ts +40 -0
- package/router/dist/evidence/bounded-evidence.js +323 -0
- package/router/dist/evidence/evidence-range-selector.d.ts +24 -0
- package/router/dist/evidence/evidence-range-selector.js +232 -0
- package/router/dist/evidence/evidence-search.d.ts +27 -0
- package/router/dist/evidence/evidence-search.js +490 -0
- package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence.d.ts +18 -18
- package/router/dist/evidence/evidence.js +200 -0
- package/router/dist/evidence/failure-contracts.d.ts +37 -0
- package/router/dist/evidence/failure-contracts.js +166 -0
- package/router/dist/evidence/line-ranges.d.ts +24 -0
- package/router/dist/evidence/line-ranges.js +22 -0
- package/router/dist/experiments/local-index.d.ts +64 -0
- package/router/dist/experiments/local-index.js +581 -0
- package/router/dist/index.d.ts +30 -0
- package/router/dist/index.js +32 -0
- package/router/dist/local/local-traversal.d.ts +18 -0
- package/router/dist/local/local-traversal.js +334 -0
- package/router/dist/processing/engine.d.ts +132 -0
- package/router/dist/processing/engine.js +533 -0
- package/router/dist/processing/reducers.d.ts +280 -0
- package/router/dist/processing/reducers.js +1673 -0
- package/router/dist/processing/renderers.d.ts +31 -0
- package/router/dist/processing/renderers.js +195 -0
- package/router/dist/processing/scripts.d.ts +91 -0
- package/router/dist/processing/scripts.js +386 -0
- package/{plugins/freeflow/router/dist → router/dist/repo}/repo-traversal.d.ts +9 -9
- package/router/dist/repo/repo-traversal.js +245 -0
- package/router/dist/routing/observed-reducers.d.ts +41 -0
- package/router/dist/routing/observed-reducers.js +661 -0
- package/router/dist/routing/observed-routing.d.ts +26 -0
- package/router/dist/routing/observed-routing.js +378 -0
- package/router/dist/routing/parsers.d.ts +16 -0
- package/router/dist/routing/parsers.js +521 -0
- package/router/dist/routing/run-filters.d.ts +60 -0
- package/router/dist/routing/run-filters.js +238 -0
- package/router/dist/routing/run-reducers.d.ts +49 -0
- package/router/dist/routing/run-reducers.js +122 -0
- package/router/dist/sandbox/adapter-roots.d.ts +46 -0
- package/router/dist/sandbox/adapter-roots.js +66 -0
- package/router/dist/sandbox/eryx-python-adapter.d.ts +13 -0
- package/router/dist/sandbox/eryx-python-adapter.js +868 -0
- package/router/dist/sandbox/jq-wasm-adapter.d.ts +9 -0
- package/router/dist/sandbox/jq-wasm-adapter.js +429 -0
- package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +13 -0
- package/router/dist/sandbox/quickjs-wasi-adapter.js +384 -0
- package/router/dist/sandbox/script-sandbox.d.ts +134 -0
- package/router/dist/sandbox/script-sandbox.js +337 -0
- package/router/dist/setup/script-transform-adapters.d.ts +32 -0
- package/router/dist/setup/script-transform-adapters.js +278 -0
- package/router/dist/tools/batch.d.ts +33 -0
- package/router/dist/tools/batch.js +586 -0
- package/router/dist/tools/run.d.ts +62 -0
- package/router/dist/tools/run.js +1304 -0
- package/router/dist/tools/search.d.ts +66 -0
- package/router/dist/tools/search.js +1364 -0
- package/router/dist/transform/engine.d.ts +168 -0
- package/router/dist/transform/engine.js +2072 -0
- package/router/dist/vault/vault-index.d.ts +125 -0
- package/router/dist/vault/vault-index.js +416 -0
- package/router/dist/vault/vault.d.ts +138 -0
- package/router/dist/vault/vault.js +630 -0
- package/runtime/interaction-contract.md +16 -0
- package/skills/bypass/SKILL.md +82 -0
- package/skills/commit-work/SKILL.md +106 -0
- package/skills/commit-work/references/staging-decisions.md +73 -0
- package/skills/decision-gate/SKILL.md +48 -0
- package/skills/design-for-depth/SKILL.md +106 -0
- package/skills/design-for-depth/references/design-pressure-signals.md +314 -0
- package/skills/design-for-depth/references/interface-design-loop.md +156 -0
- package/skills/design-for-depth/references/software-design-philosophy.md +248 -0
- package/skills/diagnose-failure/SKILL.md +105 -0
- package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +36 -0
- package/skills/diagnose-failure/references/flaky-and-performance.md +43 -0
- package/skills/discuss/SKILL.md +121 -0
- package/skills/discuss/references/checkpoints.md +66 -0
- package/skills/evaluate-skill/SKILL.md +105 -0
- package/skills/evaluate-skill/references/definition-schema.md +345 -0
- package/skills/evaluate-skill/references/evaluation-design.md +86 -0
- package/skills/evaluate-skill/references/execution-and-evidence.md +85 -0
- package/skills/evaluate-skill/references/review-and-revision.md +51 -0
- package/skills/evaluate-skill/scripts/lib/definitions.mjs +296 -0
- package/skills/evaluate-skill/scripts/lib/evidence.mjs +46 -0
- package/skills/evaluate-skill/scripts/lib/grade-comparison.mjs +60 -0
- package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +148 -0
- package/skills/evaluate-skill/scripts/lib/grade-support.mjs +126 -0
- package/skills/evaluate-skill/scripts/lib/grade-workspace.mjs +192 -0
- package/skills/evaluate-skill/scripts/lib/grade.mjs +56 -0
- package/skills/evaluate-skill/scripts/lib/pi.mjs +489 -0
- package/skills/evaluate-skill/scripts/lib/process.mjs +79 -0
- package/skills/evaluate-skill/scripts/lib/rpc.mjs +444 -0
- package/skills/evaluate-skill/scripts/lib/runner.mjs +346 -0
- package/skills/evaluate-skill/scripts/lib/sandbox.mjs +409 -0
- package/skills/evaluate-skill/scripts/lib/view.mjs +337 -0
- package/skills/evaluate-skill/scripts/pi-guard.mjs +164 -0
- package/skills/evaluate-skill/scripts/skill-eval.mjs +101 -0
- package/skills/execute-work/SKILL.md +99 -0
- package/skills/execute-work/references/code-practices.md +78 -0
- package/skills/execute-work/references/execution-loop.md +77 -0
- package/skills/finish-branch/SKILL.md +117 -0
- package/skills/finish-branch/references/integration-options.md +80 -0
- package/skills/handoff/SKILL.md +92 -0
- package/skills/handoff/references/templates.md +141 -0
- package/skills/launch-work/SKILL.md +116 -0
- package/skills/launch-work/references/launch-readiness.md +85 -0
- package/skills/migration-work/SKILL.md +115 -0
- package/skills/migration-work/references/migration-lifecycle.md +82 -0
- package/skills/mode-contract/SKILL.md +82 -0
- package/skills/output-router/SKILL.md +206 -0
- package/skills/output-router/references/safety-policy.md +40 -0
- package/skills/release-work/SKILL.md +118 -0
- package/skills/release-work/references/release-evidence.md +78 -0
- package/skills/review-artifact/SKILL.md +126 -0
- package/skills/review-artifact/references/reviewer-prompt.md +148 -0
- package/skills/review-work/SKILL.md +126 -0
- package/skills/review-work/references/reviewer-prompt.md +134 -0
- package/skills/review-work/references/security-risk-lens.md +67 -0
- package/skills/setup-freeflow/SKILL.md +98 -0
- package/skills/setup-freeflow/references/activation-contract.md +120 -0
- package/skills/setup-freeflow/references/host-setup.md +72 -0
- package/skills/setup-freeflow/references/output-router-setup.md +110 -0
- package/skills/simplify-code/SKILL.md +80 -0
- package/skills/simplify-code/references/simplification-patterns.md +70 -0
- package/skills/tdd/SKILL.md +96 -0
- package/skills/tdd/references/test-design.md +96 -0
- package/skills/track-work/SKILL.md +84 -0
- package/skills/track-work/references/working-record-schema.md +378 -0
- package/skills/verify-work/SKILL.md +85 -0
- package/skills/verify-work/references/browser-runtime-evidence.md +55 -0
- package/skills/verify-work/references/integration-evidence.md +51 -0
- package/skills/verify-work/references/performance-evidence.md +57 -0
- package/skills/workflow/SKILL.md +91 -0
- package/skills/workflow/references/domain-skill-composition.md +57 -0
- package/skills/workflow/references/workflow-loop.md +92 -0
- package/skills/write-plan/SKILL.md +123 -0
- package/skills/write-plan/references/plan-shapes.md +156 -0
- package/skills/write-skill/SKILL.md +119 -0
- package/skills/write-skill/references/activation-boundaries.md +62 -0
- package/skills/write-skill/references/agent-first-instructions.md +87 -0
- package/skills/write-skill/references/progressive-disclosure.md +63 -0
- package/skills/write-skill/scripts/lib/skill-author.mjs +653 -0
- package/skills/write-skill/scripts/skill-author.mjs +104 -0
- package/skills/write-spec/SKILL.md +104 -0
- package/skills/write-spec/references/artifact-standards.md +86 -0
- package/skills/write-spec/references/decision-records.md +77 -0
- package/skills/write-spec/references/spec-shapes.md +128 -0
- package/plugins/freeflow/command-surface.json +0 -77
- package/plugins/freeflow/docs/README.md +0 -40
- package/plugins/freeflow/docs/adr/0001-three-modes.md +0 -27
- package/plugins/freeflow/docs/adr/0002-evals-before-hooks.md +0 -17
- package/plugins/freeflow/docs/adr/0003-release-boundary.md +0 -21
- package/plugins/freeflow/docs/adr/0004-research-replaces-shallow-discovery-skills.md +0 -26
- package/plugins/freeflow/docs/adr/README.md +0 -8
- package/plugins/freeflow/docs/architecture.md +0 -86
- package/plugins/freeflow/docs/output-router.md +0 -212
- package/plugins/freeflow/docs/release-evidence.md +0 -69
- package/plugins/freeflow/docs/skills.md +0 -43
- package/plugins/freeflow/docs/workflow.md +0 -57
- package/plugins/freeflow/hooks/freeflow-runtime-context.mjs +0 -257
- package/plugins/freeflow/pi-extension/index.js +0 -1176
- package/plugins/freeflow/router/dist/benchmark-harness.js +0 -92
- package/plugins/freeflow/router/dist/benchmarks.d.ts +0 -102
- package/plugins/freeflow/router/dist/benchmarks.js +0 -880
- package/plugins/freeflow/router/dist/bounded-evidence.d.ts +0 -40
- package/plugins/freeflow/router/dist/bounded-evidence.js +0 -310
- package/plugins/freeflow/router/dist/codex-qa-benchmarks.d.ts +0 -91
- package/plugins/freeflow/router/dist/codex-qa-benchmarks.js +0 -461
- package/plugins/freeflow/router/dist/command-benchmarks.d.ts +0 -128
- package/plugins/freeflow/router/dist/command-benchmarks.js +0 -652
- package/plugins/freeflow/router/dist/config.d.ts +0 -22
- package/plugins/freeflow/router/dist/config.js +0 -114
- package/plugins/freeflow/router/dist/evidence-range-selector.d.ts +0 -22
- package/plugins/freeflow/router/dist/evidence-range-selector.js +0 -180
- package/plugins/freeflow/router/dist/evidence-search.d.ts +0 -25
- package/plugins/freeflow/router/dist/evidence-search.js +0 -450
- package/plugins/freeflow/router/dist/evidence.js +0 -196
- package/plugins/freeflow/router/dist/experimental-local-index.d.ts +0 -1
- package/plugins/freeflow/router/dist/experimental-local-index.js +0 -1
- package/plugins/freeflow/router/dist/experiments/local-index.d.ts +0 -58
- package/plugins/freeflow/router/dist/experiments/local-index.js +0 -562
- package/plugins/freeflow/router/dist/index-benchmarks.d.ts +0 -84
- package/plugins/freeflow/router/dist/index-benchmarks.js +0 -458
- package/plugins/freeflow/router/dist/index.d.ts +0 -12
- package/plugins/freeflow/router/dist/index.js +0 -12
- package/plugins/freeflow/router/dist/line-ranges.d.ts +0 -22
- package/plugins/freeflow/router/dist/line-ranges.js +0 -22
- package/plugins/freeflow/router/dist/parsers.d.ts +0 -16
- package/plugins/freeflow/router/dist/parsers.js +0 -473
- package/plugins/freeflow/router/dist/repo-traversal.js +0 -242
- package/plugins/freeflow/router/dist/retrieve.d.ts +0 -33
- package/plugins/freeflow/router/dist/retrieve.js +0 -855
- package/plugins/freeflow/router/dist/router-contract.js +0 -54
- package/plugins/freeflow/router/dist/run.d.ts +0 -26
- package/plugins/freeflow/router/dist/run.js +0 -356
- package/plugins/freeflow/router/dist/schema.js +0 -354
- package/plugins/freeflow/router/dist/types.d.ts +0 -234
- package/plugins/freeflow/router/dist/types.js +0 -9
- package/plugins/freeflow/router/dist/vault.d.ts +0 -80
- package/plugins/freeflow/router/dist/vault.js +0 -484
- package/plugins/freeflow/skills/bypass/SKILL.md +0 -68
- package/plugins/freeflow/skills/commit-work/SKILL.md +0 -98
- package/plugins/freeflow/skills/commit-work/references/staging-decisions.md +0 -51
- package/plugins/freeflow/skills/diagnose-failure/SKILL.md +0 -95
- package/plugins/freeflow/skills/diagnose-failure/references/feedback-loop-catalog.md +0 -25
- package/plugins/freeflow/skills/diagnose-failure/references/flaky-and-performance.md +0 -31
- package/plugins/freeflow/skills/evaluate-skill/SKILL.md +0 -96
- package/plugins/freeflow/skills/evaluate-skill/references/eval-patterns.md +0 -41
- package/plugins/freeflow/skills/evaluate-skill/references/grading-priority.md +0 -33
- package/plugins/freeflow/skills/execute-plan/SKILL.md +0 -132
- package/plugins/freeflow/skills/execute-plan/references/execution-map.md +0 -122
- package/plugins/freeflow/skills/handoff/SKILL.md +0 -66
- package/plugins/freeflow/skills/handoff/references/templates.md +0 -64
- package/plugins/freeflow/skills/interview-gate/SKILL.md +0 -90
- package/plugins/freeflow/skills/mode-contract/SKILL.md +0 -79
- package/plugins/freeflow/skills/output-router/SKILL.md +0 -69
- package/plugins/freeflow/skills/output-router/references/safety-policy.md +0 -33
- package/plugins/freeflow/skills/research/ARTIFACT-DESTINATIONS.md +0 -58
- package/plugins/freeflow/skills/research/CHECKPOINTS.md +0 -74
- package/plugins/freeflow/skills/research/LANGUAGE.md +0 -61
- package/plugins/freeflow/skills/research/SKILL.md +0 -128
- package/plugins/freeflow/skills/review-artifact/SKILL.md +0 -115
- package/plugins/freeflow/skills/review-artifact/references/reviewer-prompt.md +0 -56
- package/plugins/freeflow/skills/review-work/SKILL.md +0 -96
- package/plugins/freeflow/skills/review-work/references/reviewer-prompt.md +0 -97
- package/plugins/freeflow/skills/setup-freeflow/SKILL.md +0 -94
- package/plugins/freeflow/skills/setup-freeflow/references/activation-contract.md +0 -99
- package/plugins/freeflow/skills/setup-freeflow/references/host-setup.md +0 -35
- package/plugins/freeflow/skills/setup-freeflow/references/output-router-setup.md +0 -52
- package/plugins/freeflow/skills/verify-work/SKILL.md +0 -62
- package/plugins/freeflow/skills/workflow/SKILL.md +0 -95
- package/plugins/freeflow/skills/workflow/references/workflow-map.md +0 -102
- package/plugins/freeflow/skills/write-plan/SKILL.md +0 -88
- package/plugins/freeflow/skills/write-plan/references/plan-shapes.md +0 -70
- package/plugins/freeflow/skills/write-skill/SKILL.md +0 -88
- package/plugins/freeflow/skills/write-spec/SKILL.md +0 -90
- package/plugins/freeflow/skills/write-spec/references/artifact-standards.md +0 -67
- package/plugins/freeflow/skills/write-spec/references/spec-shapes.md +0 -69
- /package/{plugins/freeflow/assets → assets}/freeflow-plugin-icon-transparent.png +0 -0
- /package/{plugins/freeflow/hooks → hooks}/hooks.json +0 -0
|
@@ -1,92 +0,0 @@
|
|
|
1
|
-
import { mkdir, writeFile } from "node:fs/promises";
|
|
2
|
-
import { basename, dirname, resolve } from "node:path";
|
|
3
|
-
export function normalizeIterations(value, defaultIterations = 3) {
|
|
4
|
-
if (typeof value === "number" && Number.isFinite(value) && value > 0) {
|
|
5
|
-
return Math.max(1, Math.floor(value));
|
|
6
|
-
}
|
|
7
|
-
if (Number.isFinite(defaultIterations) && defaultIterations > 0) {
|
|
8
|
-
return Math.max(1, Math.floor(defaultIterations));
|
|
9
|
-
}
|
|
10
|
-
return 1;
|
|
11
|
-
}
|
|
12
|
-
export function approximateTokens(bytes) {
|
|
13
|
-
return Math.ceil(bytes / 4);
|
|
14
|
-
}
|
|
15
|
-
export function percentile(values, quantile) {
|
|
16
|
-
if (values.length === 0) {
|
|
17
|
-
return 0;
|
|
18
|
-
}
|
|
19
|
-
const sorted = [...values].sort((a, b) => a - b);
|
|
20
|
-
const index = Math.min(sorted.length - 1, Math.max(0, Math.ceil(sorted.length * quantile) - 1));
|
|
21
|
-
return sorted[index] ?? 0;
|
|
22
|
-
}
|
|
23
|
-
export function latencySummary(values) {
|
|
24
|
-
return {
|
|
25
|
-
p50: percentile(values, 0.5),
|
|
26
|
-
p95: percentile(values, 0.95),
|
|
27
|
-
};
|
|
28
|
-
}
|
|
29
|
-
export function averagePercent(values) {
|
|
30
|
-
if (values.length === 0) {
|
|
31
|
-
return 0;
|
|
32
|
-
}
|
|
33
|
-
return roundPercent(values.reduce((sum, value) => sum + value, 0) / values.length);
|
|
34
|
-
}
|
|
35
|
-
export function medianPercent(values) {
|
|
36
|
-
return roundPercent(percentile(values, 0.5));
|
|
37
|
-
}
|
|
38
|
-
export function reductionPercent(raw, routed) {
|
|
39
|
-
if (raw <= 0) {
|
|
40
|
-
return 0;
|
|
41
|
-
}
|
|
42
|
-
return roundPercent(((raw - routed) / raw) * 100);
|
|
43
|
-
}
|
|
44
|
-
export function formatPercent(value) {
|
|
45
|
-
return `${value.toFixed(2)}%`;
|
|
46
|
-
}
|
|
47
|
-
export function escapeMarkdownTableCell(value) {
|
|
48
|
-
return value.replace(/\|/g, "\\|").replace(/\n/g, " ");
|
|
49
|
-
}
|
|
50
|
-
export function defaultJsonRunReportPath(markdownReportPath) {
|
|
51
|
-
const markdownName = basename(markdownReportPath);
|
|
52
|
-
const jsonName = markdownName.endsWith(".md") ? `${markdownName.slice(0, -".md".length)}.json` : `${markdownName}.json`;
|
|
53
|
-
return resolve(process.cwd(), "plugins/freeflow/evals/runs/output-router", jsonName);
|
|
54
|
-
}
|
|
55
|
-
export function parseBenchmarkCliArgs(argv, defaults) {
|
|
56
|
-
let iterations;
|
|
57
|
-
let reportPath = defaults.reportPath;
|
|
58
|
-
let jsonReportPath;
|
|
59
|
-
for (const arg of argv) {
|
|
60
|
-
if (arg.startsWith("--iterations=")) {
|
|
61
|
-
const value = Number(arg.slice("--iterations=".length));
|
|
62
|
-
if (Number.isFinite(value) && value > 0) {
|
|
63
|
-
iterations = value;
|
|
64
|
-
}
|
|
65
|
-
}
|
|
66
|
-
else if (arg.startsWith("--report=")) {
|
|
67
|
-
reportPath = resolve(process.cwd(), arg.slice("--report=".length));
|
|
68
|
-
}
|
|
69
|
-
else if (arg.startsWith("--json-report=")) {
|
|
70
|
-
const value = arg.slice("--json-report=".length);
|
|
71
|
-
jsonReportPath = value === "off" ? false : resolve(process.cwd(), value);
|
|
72
|
-
}
|
|
73
|
-
}
|
|
74
|
-
const parsed = iterations === undefined ? { reportPath } : { iterations, reportPath };
|
|
75
|
-
return jsonReportPath === undefined ? parsed : { ...parsed, jsonReportPath };
|
|
76
|
-
}
|
|
77
|
-
export async function writeBenchmarkReportPair(options) {
|
|
78
|
-
await mkdir(dirname(options.markdownReportPath), { recursive: true });
|
|
79
|
-
await writeFile(options.markdownReportPath, options.renderMarkdown(options.report), "utf8");
|
|
80
|
-
if (options.jsonReportPath === false) {
|
|
81
|
-
return { markdown: options.markdownReportPath };
|
|
82
|
-
}
|
|
83
|
-
if (options.jsonReportPath) {
|
|
84
|
-
await mkdir(dirname(options.jsonReportPath), { recursive: true });
|
|
85
|
-
await writeFile(options.jsonReportPath, `${JSON.stringify(options.report, null, 2)}\n`, "utf8");
|
|
86
|
-
return { markdown: options.markdownReportPath, json: options.jsonReportPath };
|
|
87
|
-
}
|
|
88
|
-
return { markdown: options.markdownReportPath };
|
|
89
|
-
}
|
|
90
|
-
function roundPercent(value) {
|
|
91
|
-
return Math.round(value * 100) / 100;
|
|
92
|
-
}
|
|
@@ -1,102 +0,0 @@
|
|
|
1
|
-
export interface RunRouterBenchmarksOptions {
|
|
2
|
-
iterations?: number;
|
|
3
|
-
generatedAt?: string;
|
|
4
|
-
}
|
|
5
|
-
export interface RouterBenchmarkReport {
|
|
6
|
-
generatedAt: string;
|
|
7
|
-
iterations: number;
|
|
8
|
-
summary: RouterBenchmarkSummary;
|
|
9
|
-
fixtures: RouterBenchmarkFixtureResult[];
|
|
10
|
-
skippedExternalTools: SkippedExternalTool[];
|
|
11
|
-
}
|
|
12
|
-
export interface RouterBenchmarkSummary {
|
|
13
|
-
fixtures: number;
|
|
14
|
-
modeResults: number;
|
|
15
|
-
improved: ModeSummary;
|
|
16
|
-
nativeBaseline: ModeSummary;
|
|
17
|
-
freeflowBaseline: ModeSummary;
|
|
18
|
-
generatedFalsePositiveCount: number;
|
|
19
|
-
sandboxFailureFixed: boolean;
|
|
20
|
-
}
|
|
21
|
-
export interface ModeSummary {
|
|
22
|
-
passed: number;
|
|
23
|
-
failed: number;
|
|
24
|
-
skipped: number;
|
|
25
|
-
pathCorrect: number;
|
|
26
|
-
spanCorrect: number;
|
|
27
|
-
excerptComplete: number;
|
|
28
|
-
generatedFalsePositiveCount: number;
|
|
29
|
-
totalRawBytes: number;
|
|
30
|
-
totalRoutedBytes: number;
|
|
31
|
-
totalRawTokensApprox: number;
|
|
32
|
-
totalRoutedTokensApprox: number;
|
|
33
|
-
weightedByteReductionPercent: number;
|
|
34
|
-
weightedTokenReductionPercent: number;
|
|
35
|
-
averageByteReductionPercent: number;
|
|
36
|
-
medianByteReductionPercent: number;
|
|
37
|
-
averageTokenReductionPercent: number;
|
|
38
|
-
medianTokenReductionPercent: number;
|
|
39
|
-
}
|
|
40
|
-
export interface RouterBenchmarkFixtureResult {
|
|
41
|
-
id: string;
|
|
42
|
-
title: string;
|
|
43
|
-
kind: BenchmarkKind;
|
|
44
|
-
expected: BenchmarkExpected;
|
|
45
|
-
results: RouterBenchmarkModeResult[];
|
|
46
|
-
}
|
|
47
|
-
export interface RouterBenchmarkModeResult {
|
|
48
|
-
mode: BenchmarkMode;
|
|
49
|
-
toolPathUsed: string;
|
|
50
|
-
skipped: boolean;
|
|
51
|
-
skipReason?: string;
|
|
52
|
-
rawBytes: number;
|
|
53
|
-
rawTokensApprox: number;
|
|
54
|
-
routedBytes: number;
|
|
55
|
-
routedTokensApprox: number;
|
|
56
|
-
byteReductionPercent: number;
|
|
57
|
-
tokenReductionPercent: number;
|
|
58
|
-
latencyMs: {
|
|
59
|
-
p50: number;
|
|
60
|
-
p95: number;
|
|
61
|
-
};
|
|
62
|
-
actualPath?: string;
|
|
63
|
-
actualLines?: string;
|
|
64
|
-
correctness: CorrectnessResult;
|
|
65
|
-
recovery: RecoveryResult;
|
|
66
|
-
notes: string[];
|
|
67
|
-
}
|
|
68
|
-
export interface BenchmarkExpected {
|
|
69
|
-
path?: string;
|
|
70
|
-
pathIncludes?: string;
|
|
71
|
-
lines?: string;
|
|
72
|
-
requiredExcerpt?: string[];
|
|
73
|
-
}
|
|
74
|
-
export interface CorrectnessResult {
|
|
75
|
-
passed: boolean;
|
|
76
|
-
pathCorrect: boolean;
|
|
77
|
-
spanCorrect: boolean;
|
|
78
|
-
excerptComplete: boolean;
|
|
79
|
-
generatedFalsePositive: boolean;
|
|
80
|
-
}
|
|
81
|
-
export interface RecoveryResult {
|
|
82
|
-
status: "passed" | "failed" | "not-applicable" | "skipped";
|
|
83
|
-
detail: string;
|
|
84
|
-
}
|
|
85
|
-
export interface SkippedExternalTool {
|
|
86
|
-
name: string;
|
|
87
|
-
reason: string;
|
|
88
|
-
}
|
|
89
|
-
type BenchmarkKind = "repo-query" | "repo-expand" | "vault-query";
|
|
90
|
-
type BenchmarkMode = "native-baseline-proxy" | "pre-hardening-freeflow-proxy" | "improved-freeflow-router";
|
|
91
|
-
export declare function runRouterBenchmarks(options?: RunRouterBenchmarksOptions): Promise<RouterBenchmarkReport>;
|
|
92
|
-
export declare function renderRouterBenchmarkReport(report: RouterBenchmarkReport): string;
|
|
93
|
-
export declare function writeRouterBenchmarkReport(report: RouterBenchmarkReport, reportPath: string): Promise<void>;
|
|
94
|
-
export declare function writeRouterBenchmarkJsonReport(report: RouterBenchmarkReport, reportPath: string): Promise<void>;
|
|
95
|
-
export interface WriteRouterBenchmarkReportsOptions {
|
|
96
|
-
jsonReportPath?: string | false;
|
|
97
|
-
}
|
|
98
|
-
export declare function writeRouterBenchmarkReports(report: RouterBenchmarkReport, markdownReportPath: string, options?: WriteRouterBenchmarkReportsOptions): Promise<{
|
|
99
|
-
markdown: string;
|
|
100
|
-
json?: string;
|
|
101
|
-
}>;
|
|
102
|
-
export {};
|