@hassangameryt/freeflow 0.5.0 → 0.6.0
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/.claude-plugin/marketplace.json +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/.codex-plugin/plugin.json +1 -1
- package/README.md +148 -154
- package/capabilities/cognitive-routing/SKILL.md +229 -0
- package/capabilities/context-virtualization/SKILL.md +103 -0
- package/capabilities/conversation-history/SKILL.md +53 -0
- package/command-surface.json +6 -13
- package/hooks/freeflow-runtime-context.mjs +35 -91
- package/hooks/tests/check-runtime-context-hook.sh +56 -39
- package/package.json +24 -16
- package/pi-extension/dist/cognitive-routing/commands.js +96 -0
- package/pi-extension/dist/cognitive-routing/config.js +236 -0
- package/pi-extension/dist/cognitive-routing/controller.js +862 -0
- package/pi-extension/dist/cognitive-routing/history.js +439 -0
- package/pi-extension/dist/cognitive-routing/host.js +126 -0
- package/pi-extension/dist/cognitive-routing/runtime.js +43 -0
- package/pi-extension/dist/cognitive-routing/tool.js +211 -0
- package/pi-extension/dist/cognitive-routing/types.js +6 -0
- package/pi-extension/dist/context-virtualization/commands.js +89 -0
- package/pi-extension/dist/context-virtualization/projector.js +42 -0
- package/pi-extension/dist/context-virtualization/runtime.js +356 -0
- package/pi-extension/dist/context-virtualization/state.js +57 -0
- package/pi-extension/dist/context-virtualization/types.js +10 -0
- package/pi-extension/dist/conversation-history/passages.js +66 -0
- package/pi-extension/dist/conversation-history/ranking.js +105 -0
- package/pi-extension/dist/conversation-history/runtime.js +226 -0
- package/pi-extension/dist/conversation-history/search.js +56 -0
- package/pi-extension/dist/conversation-history/types.js +1 -0
- package/pi-extension/dist/freeflow-context/resolver.js +120 -0
- package/pi-extension/dist/freeflow-context/runtime.js +80 -0
- package/pi-extension/dist/freeflow-context/source-projector.js +95 -0
- package/pi-extension/dist/freeflow-context/tool.js +308 -0
- package/pi-extension/dist/freeflow-context/types.js +12 -0
- package/pi-extension/dist/freeflow-context/visibility.js +28 -0
- package/pi-extension/dist/index.js +516 -98
- package/pi-extension/dist/runtime/runtime-context.js +318 -271
- package/pi-extension/dist/runtime/runtime-identity.js +5 -0
- package/pi-extension/dist/settings/settings-tui.js +78 -0
- package/pi-extension/dist/settings/settings-ui.js +593 -563
- package/pi-extension/dist/ui/text-component.js +57 -0
- package/pi-extension/src/cognitive-routing/commands.ts +119 -0
- package/pi-extension/src/cognitive-routing/config.ts +307 -0
- package/pi-extension/src/cognitive-routing/controller.ts +1118 -0
- package/pi-extension/src/cognitive-routing/history.ts +638 -0
- package/pi-extension/src/cognitive-routing/host.ts +172 -0
- package/pi-extension/src/cognitive-routing/runtime.ts +57 -0
- package/pi-extension/src/cognitive-routing/tool.ts +272 -0
- package/pi-extension/src/cognitive-routing/types.ts +89 -0
- package/pi-extension/src/context-virtualization/commands.ts +111 -0
- package/pi-extension/src/context-virtualization/projector.ts +62 -0
- package/pi-extension/src/context-virtualization/runtime.ts +406 -0
- package/pi-extension/src/context-virtualization/state.ts +79 -0
- package/pi-extension/src/context-virtualization/types.ts +92 -0
- package/pi-extension/src/conversation-history/passages.ts +81 -0
- package/pi-extension/src/conversation-history/ranking.ts +155 -0
- package/pi-extension/src/conversation-history/runtime.ts +250 -0
- package/pi-extension/src/conversation-history/search.ts +79 -0
- package/pi-extension/src/conversation-history/types.ts +31 -0
- package/pi-extension/src/freeflow-context/resolver.ts +139 -0
- package/pi-extension/src/freeflow-context/runtime.ts +100 -0
- package/pi-extension/src/freeflow-context/source-projector.ts +106 -0
- package/pi-extension/src/freeflow-context/tool.ts +360 -0
- package/pi-extension/src/freeflow-context/types.ts +70 -0
- package/pi-extension/src/freeflow-context/visibility.ts +53 -0
- package/pi-extension/src/index.ts +553 -101
- package/pi-extension/src/runtime/runtime-context.ts +339 -281
- package/pi-extension/src/runtime/runtime-identity.ts +8 -0
- package/pi-extension/src/settings/settings-tui.ts +93 -0
- package/pi-extension/src/settings/settings-ui.ts +700 -613
- package/pi-extension/src/ui/text-component.ts +66 -0
- package/pi-extension/tests/cognitive-routing/commands.test.js +134 -0
- package/pi-extension/tests/cognitive-routing/controller.test.js +1099 -0
- package/pi-extension/tests/cognitive-routing/extension-lifecycle.test.js +1071 -0
- package/pi-extension/tests/cognitive-routing/history.test.js +274 -0
- package/pi-extension/tests/cognitive-routing/host-fixture.js +4 -0
- package/pi-extension/tests/cognitive-routing/host-identity.test.js +63 -0
- package/pi-extension/tests/cognitive-routing/profile-resolution.test.js +236 -0
- package/pi-extension/tests/cognitive-routing/tool.test.js +230 -0
- package/pi-extension/tests/context-virtualization/extension.test.js +749 -0
- package/pi-extension/tests/context-virtualization/projector.test.js +110 -0
- package/pi-extension/tests/context-virtualization/runtime.test.js +216 -0
- package/pi-extension/tests/conversation-history/runtime.test.js +98 -0
- package/pi-extension/tests/conversation-history/search.test.js +97 -0
- package/pi-extension/tests/integration/pi-extension.test.js +927 -2048
- package/pi-extension/tests/integration/prompt-architecture.test.js +305 -0
- package/runtime/prompts/cognitive-routing.md +9 -0
- package/runtime/prompts/context-virtualization.md +3 -0
- package/runtime/prompts/conversation-history.md +3 -0
- package/runtime/prompts/core.md +13 -0
- package/runtime/prompts/interaction-contract.md +7 -0
- package/runtime/prompts/skills.md +65 -0
- package/skills/action-selection/SKILL.md +91 -0
- package/skills/bypass/SKILL.md +3 -2
- package/skills/commit-work/SKILL.md +1 -1
- package/skills/commit-work/references/staging-decisions.md +1 -1
- package/skills/decision-gate/SKILL.md +1 -1
- package/skills/design-for-depth/SKILL.md +14 -33
- package/skills/design-for-depth/references/design-pressure-signals.md +1 -1
- package/skills/design-for-depth/references/interface-design-loop.md +1 -1
- package/skills/design-for-depth/references/software-design-philosophy.md +1 -1
- package/skills/diagnose-failure/SKILL.md +20 -14
- package/skills/diagnose-failure/references/diagnostic-loop-catalog.md +1 -3
- package/skills/diagnose-failure/references/{flaky-and-performance.md → flaky-and-performance-diagnosis.md} +1 -1
- package/skills/discuss/SKILL.md +34 -22
- package/skills/discuss/references/discussion-continuity.md +71 -0
- package/skills/evaluate-skill/SKILL.md +5 -5
- package/skills/evaluate-skill/references/{definition-schema.md → evaluation-definition-schema.md} +42 -2
- package/skills/evaluate-skill/references/execution-and-evidence.md +8 -3
- package/skills/evaluate-skill/scripts/lib/definitions.mjs +114 -3
- package/skills/evaluate-skill/scripts/lib/grade-interaction.mjs +156 -1
- package/skills/evaluate-skill/scripts/lib/grade.mjs +9 -1
- package/skills/evaluate-skill/scripts/lib/pi.mjs +147 -32
- package/skills/evaluate-skill/scripts/lib/rpc.mjs +4 -4
- package/skills/evaluate-skill/scripts/lib/runner.mjs +36 -14
- package/skills/evaluate-skill/scripts/lib/sandbox.mjs +92 -0
- package/skills/evaluate-skill/scripts/pi-guard.mjs +1 -1
- package/skills/evaluate-skill/scripts/pi-observer.mjs +66 -0
- package/skills/evaluate-skill/scripts/skill-eval.mjs +6 -5
- package/skills/execute-work/SKILL.md +18 -15
- package/skills/execute-work/references/code-practices.md +1 -1
- package/skills/execute-work/references/execute-work-edges.md +42 -0
- package/skills/finish-branch/SKILL.md +2 -2
- package/skills/finish-branch/references/integration-options.md +1 -1
- package/skills/handoff/SKILL.md +3 -3
- package/skills/launch-work/SKILL.md +1 -1
- package/skills/launch-work/references/launch-readiness.md +2 -2
- package/skills/migration-work/SKILL.md +2 -2
- package/skills/migration-work/references/migration-lifecycle.md +1 -1
- package/skills/mode-contract/SKILL.md +4 -4
- package/skills/release-work/SKILL.md +1 -1
- package/skills/release-work/references/release-evidence.md +1 -1
- package/skills/review-artifact/SKILL.md +28 -26
- package/skills/review-work/SKILL.md +28 -26
- package/skills/review-work/references/{reviewer-prompt.md → independent-work-reviewer-contract.md} +1 -1
- package/skills/review-work/references/security-risk-lens.md +1 -1
- package/skills/setup-freeflow/SKILL.md +3 -1
- package/skills/setup-freeflow/references/activation-contract.md +2 -2
- package/skills/setup-freeflow/references/host-setup.md +2 -2
- package/skills/simplify-code/SKILL.md +1 -1
- package/skills/simplify-code/references/simplification-patterns.md +1 -1
- package/skills/tdd/SKILL.md +18 -38
- package/skills/tdd/references/test-design.md +2 -2
- package/skills/track-work/SKILL.md +362 -58
- package/skills/track-work/scripts/lib/codec.mjs +570 -0
- package/skills/track-work/scripts/lib/commands.mjs +568 -0
- package/skills/track-work/scripts/lib/contract.mjs +303 -0
- package/skills/track-work/scripts/lib/model.mjs +506 -0
- package/skills/track-work/scripts/lib/operations.mjs +965 -0
- package/skills/track-work/scripts/lib/record-store.mjs +264 -0
- package/skills/track-work/scripts/lib/result.mjs +37 -0
- package/skills/track-work/scripts/lib/rewrites.mjs +740 -0
- package/skills/track-work/scripts/lib/schema.mjs +277 -0
- package/skills/track-work/scripts/lib/source-inventory.mjs +162 -0
- package/skills/track-work/scripts/lib/views.mjs +443 -0
- package/skills/track-work/scripts/lib/workspace.mjs +134 -0
- package/skills/track-work/scripts/working-record.mjs +122 -0
- package/skills/verify-work/SKILL.md +14 -2
- package/skills/verify-work/references/browser-runtime-evidence.md +1 -1
- package/skills/verify-work/references/integration-evidence.md +1 -1
- package/skills/verify-work/references/performance-evidence.md +1 -1
- package/skills/workflow/SKILL.md +105 -53
- package/skills/workflow/references/domain-skill-composition.md +22 -42
- package/skills/write-plan/SKILL.md +1 -1
- package/skills/write-skill/SKILL.md +3 -2
- package/skills/write-skill/references/progressive-disclosure.md +17 -3
- package/capabilities/output-router/SKILL.md +0 -206
- package/capabilities/output-router/references/safety-policy.md +0 -40
- package/capabilities/output-router/references/setup.md +0 -110
- package/pi-extension/dist/output-router/host-producer-identification.js +0 -232
- package/pi-extension/dist/output-router/native-safety-net.js +0 -216
- package/pi-extension/dist/output-router/observed-tool-routing.js +0 -122
- package/pi-extension/dist/output-router/renderers.js +0 -1023
- package/pi-extension/dist/output-router/router-tools.js +0 -554
- package/pi-extension/dist/output-router/schemas.js +0 -383
- package/pi-extension/dist/output-router/status.js +0 -744
- package/pi-extension/dist/output-router/utils.js +0 -502
- package/pi-extension/src/output-router/host-producer-identification.ts +0 -256
- package/pi-extension/src/output-router/native-safety-net.ts +0 -248
- package/pi-extension/src/output-router/observed-tool-routing.ts +0 -134
- package/pi-extension/src/output-router/renderers.ts +0 -1108
- package/pi-extension/src/output-router/router-tools.ts +0 -579
- package/pi-extension/src/output-router/schemas.ts +0 -387
- package/pi-extension/src/output-router/status.ts +0 -791
- package/pi-extension/src/output-router/utils.ts +0 -554
- package/pi-extension/tests/output-router/observed-producers.test.js +0 -132
- package/pi-extension/tests/output-router/search.test.js +0 -722
- package/router/dist/benchmarks/benchmark-harness.d.ts +0 -35
- package/router/dist/benchmarks/benchmark-harness.js +0 -92
- package/router/dist/benchmarks/benchmarks.d.ts +0 -109
- package/router/dist/benchmarks/benchmarks.js +0 -979
- package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +0 -95
- package/router/dist/benchmarks/codex-qa-benchmarks.js +0 -500
- package/router/dist/benchmarks/command-benchmarks.d.ts +0 -143
- package/router/dist/benchmarks/command-benchmarks.js +0 -698
- package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +0 -82
- package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +0 -773
- package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +0 -132
- package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +0 -1380
- package/router/dist/benchmarks/context-saving-baseline.d.ts +0 -60
- package/router/dist/benchmarks/context-saving-baseline.js +0 -470
- package/router/dist/benchmarks/index-benchmarks.d.ts +0 -103
- package/router/dist/benchmarks/index-benchmarks.js +0 -862
- package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +0 -101
- package/router/dist/benchmarks/storage-policy-benchmarks.js +0 -618
- package/router/dist/benchmarks/vault-index-benchmarks.d.ts +0 -56
- package/router/dist/benchmarks/vault-index-benchmarks.js +0 -322
- package/router/dist/config/config.d.ts +0 -103
- package/router/dist/config/config.js +0 -632
- package/router/dist/config/router-contract.d.ts +0 -10
- package/router/dist/config/router-contract.js +0 -54
- package/router/dist/config/schema.d.ts +0 -27
- package/router/dist/config/schema.js +0 -648
- package/router/dist/config/types.d.ts +0 -573
- package/router/dist/config/types.js +0 -41
- package/router/dist/evidence/bounded-evidence.d.ts +0 -40
- package/router/dist/evidence/bounded-evidence.js +0 -323
- package/router/dist/evidence/evidence-range-selector.d.ts +0 -24
- package/router/dist/evidence/evidence-range-selector.js +0 -232
- package/router/dist/evidence/evidence-search.d.ts +0 -27
- package/router/dist/evidence/evidence-search.js +0 -490
- package/router/dist/evidence/evidence.d.ts +0 -38
- package/router/dist/evidence/evidence.js +0 -200
- package/router/dist/evidence/failure-contracts.d.ts +0 -37
- package/router/dist/evidence/failure-contracts.js +0 -166
- package/router/dist/evidence/line-ranges.d.ts +0 -24
- package/router/dist/evidence/line-ranges.js +0 -22
- package/router/dist/experiments/local-index.d.ts +0 -64
- package/router/dist/experiments/local-index.js +0 -581
- package/router/dist/index.d.ts +0 -30
- package/router/dist/index.js +0 -32
- package/router/dist/local/local-traversal.d.ts +0 -18
- package/router/dist/local/local-traversal.js +0 -334
- package/router/dist/processing/engine.d.ts +0 -132
- package/router/dist/processing/engine.js +0 -533
- package/router/dist/processing/reducers.d.ts +0 -280
- package/router/dist/processing/reducers.js +0 -1673
- package/router/dist/processing/renderers.d.ts +0 -31
- package/router/dist/processing/renderers.js +0 -195
- package/router/dist/processing/scripts.d.ts +0 -91
- package/router/dist/processing/scripts.js +0 -386
- package/router/dist/repo/repo-traversal.d.ts +0 -18
- package/router/dist/repo/repo-traversal.js +0 -245
- package/router/dist/routing/observed-reducers.d.ts +0 -41
- package/router/dist/routing/observed-reducers.js +0 -661
- package/router/dist/routing/observed-routing.d.ts +0 -26
- package/router/dist/routing/observed-routing.js +0 -378
- package/router/dist/routing/parsers.d.ts +0 -16
- package/router/dist/routing/parsers.js +0 -521
- package/router/dist/routing/run-filters.d.ts +0 -60
- package/router/dist/routing/run-filters.js +0 -238
- package/router/dist/routing/run-reducers.d.ts +0 -49
- package/router/dist/routing/run-reducers.js +0 -122
- package/router/dist/sandbox/adapter-roots.d.ts +0 -46
- package/router/dist/sandbox/adapter-roots.js +0 -66
- package/router/dist/sandbox/eryx-python-adapter.d.ts +0 -13
- package/router/dist/sandbox/eryx-python-adapter.js +0 -868
- package/router/dist/sandbox/jq-wasm-adapter.d.ts +0 -9
- package/router/dist/sandbox/jq-wasm-adapter.js +0 -429
- package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +0 -13
- package/router/dist/sandbox/quickjs-wasi-adapter.js +0 -384
- package/router/dist/sandbox/script-sandbox.d.ts +0 -134
- package/router/dist/sandbox/script-sandbox.js +0 -337
- package/router/dist/setup/script-transform-adapters.d.ts +0 -32
- package/router/dist/setup/script-transform-adapters.js +0 -278
- package/router/dist/tools/batch.d.ts +0 -33
- package/router/dist/tools/batch.js +0 -586
- package/router/dist/tools/run.d.ts +0 -62
- package/router/dist/tools/run.js +0 -1304
- package/router/dist/tools/search.d.ts +0 -66
- package/router/dist/tools/search.js +0 -1364
- package/router/dist/transform/engine.d.ts +0 -168
- package/router/dist/transform/engine.js +0 -2072
- package/router/dist/vault/vault-index.d.ts +0 -125
- package/router/dist/vault/vault-index.js +0 -416
- package/router/dist/vault/vault.d.ts +0 -138
- package/router/dist/vault/vault.js +0 -630
- package/runtime/interaction-contract.md +0 -16
- package/skills/discuss/references/checkpoints.md +0 -66
- package/skills/execute-work/references/execution-loop.md +0 -77
- package/skills/track-work/references/working-record-schema.md +0 -378
- package/skills/workflow/references/workflow-loop.md +0 -92
- /package/skills/handoff/references/{templates.md → handoff-templates.md} +0 -0
- /package/skills/review-artifact/references/{reviewer-prompt.md → independent-artifact-reviewer-contract.md} +0 -0
|
@@ -1,618 +0,0 @@
|
|
|
1
|
-
import { createHash } from "node:crypto";
|
|
2
|
-
import { readdir, rm, stat } from "node:fs/promises";
|
|
3
|
-
import { tmpdir } from "node:os";
|
|
4
|
-
import { join, resolve } from "node:path";
|
|
5
|
-
import { fileURLToPath } from "node:url";
|
|
6
|
-
import { mkdtemp } from "node:fs/promises";
|
|
7
|
-
import { performance } from "node:perf_hooks";
|
|
8
|
-
import {
|
|
9
|
-
approximateTokens,
|
|
10
|
-
defaultJsonRunReportPath,
|
|
11
|
-
escapeMarkdownTableCell as escapeTable,
|
|
12
|
-
formatPercent,
|
|
13
|
-
latencySummary,
|
|
14
|
-
normalizeIterations,
|
|
15
|
-
parseBenchmarkCliArgs,
|
|
16
|
-
reductionPercent,
|
|
17
|
-
writeBenchmarkReportPair,
|
|
18
|
-
} from "./benchmark-harness.js";
|
|
19
|
-
import {
|
|
20
|
-
commandOutputFingerprints,
|
|
21
|
-
createVault,
|
|
22
|
-
findExactDuplicateCommandOutput,
|
|
23
|
-
readOutputText,
|
|
24
|
-
storeCommandOutput,
|
|
25
|
-
storeMetadataOutput,
|
|
26
|
-
} from "../vault/vault.js";
|
|
27
|
-
const DEFAULT_ITERATIONS = 2;
|
|
28
|
-
const LARGE_EXACT_THRESHOLD_BYTES = 8 * 1024;
|
|
29
|
-
const FIXTURES = createStoragePolicyFixtures();
|
|
30
|
-
const POLICIES = [
|
|
31
|
-
{
|
|
32
|
-
id: "store-everything",
|
|
33
|
-
label: "Store everything exactly",
|
|
34
|
-
description:
|
|
35
|
-
"Current baseline: every command output is vaulted exactly, so recovery is maximally useful and storage/privacy surface is largest.",
|
|
36
|
-
decide() {
|
|
37
|
-
return "exact";
|
|
38
|
-
},
|
|
39
|
-
},
|
|
40
|
-
{
|
|
41
|
-
id: "threshold-exact",
|
|
42
|
-
label: "Threshold exact storage",
|
|
43
|
-
description: `Exact storage only when combined output is at least ${LARGE_EXACT_THRESHOLD_BYTES} bytes; smaller outputs are metadata-only. This intentionally tests whether a threshold alone would drop exact failure/verification recovery.`,
|
|
44
|
-
decide(input) {
|
|
45
|
-
return input.rawCombinedBytes >= LARGE_EXACT_THRESHOLD_BYTES ? "exact" : "metadata";
|
|
46
|
-
},
|
|
47
|
-
},
|
|
48
|
-
{
|
|
49
|
-
id: "metadata-small-exact-large-hybrid",
|
|
50
|
-
label: "Metadata-small / exact-large hybrid",
|
|
51
|
-
description: `Small non-sensitive outputs become metadata-only; exactness-sensitive or >= ${LARGE_EXACT_THRESHOLD_BYTES} byte outputs remain exactly recoverable.`,
|
|
52
|
-
decide(input) {
|
|
53
|
-
return input.fixture.exactnessSensitive || input.rawCombinedBytes >= LARGE_EXACT_THRESHOLD_BYTES
|
|
54
|
-
? "exact"
|
|
55
|
-
: "metadata";
|
|
56
|
-
},
|
|
57
|
-
},
|
|
58
|
-
{
|
|
59
|
-
id: "duplicate-output-dedupe",
|
|
60
|
-
label: "Duplicate output dedupe",
|
|
61
|
-
description:
|
|
62
|
-
"First occurrence is stored exactly; exact duplicates become metadata-only records that point at the prior exact output.",
|
|
63
|
-
decide(input) {
|
|
64
|
-
return input.duplicate ? "duplicate-metadata" : "exact";
|
|
65
|
-
},
|
|
66
|
-
},
|
|
67
|
-
{
|
|
68
|
-
id: "hybrid-dedupe",
|
|
69
|
-
label: "Hybrid exactness + duplicate dedupe",
|
|
70
|
-
description: `Exactness-sensitive or >= ${LARGE_EXACT_THRESHOLD_BYTES} byte outputs stay exactly recoverable; exact duplicates of those outputs become metadata pointers; small non-sensitive outputs are metadata-only.`,
|
|
71
|
-
decide(input) {
|
|
72
|
-
const shouldStoreExact =
|
|
73
|
-
input.fixture.exactnessSensitive || input.rawCombinedBytes >= LARGE_EXACT_THRESHOLD_BYTES;
|
|
74
|
-
if (!shouldStoreExact) {
|
|
75
|
-
return "metadata";
|
|
76
|
-
}
|
|
77
|
-
return input.duplicate ? "duplicate-metadata" : "exact";
|
|
78
|
-
},
|
|
79
|
-
},
|
|
80
|
-
];
|
|
81
|
-
export async function runStoragePolicyBenchmarks(options = {}) {
|
|
82
|
-
const iterations = normalizeIterations(options.iterations, DEFAULT_ITERATIONS);
|
|
83
|
-
const policies = [];
|
|
84
|
-
for (const policy of POLICIES) {
|
|
85
|
-
policies.push(await runPolicy(policy, iterations));
|
|
86
|
-
}
|
|
87
|
-
return {
|
|
88
|
-
generatedAt: options.generatedAt ?? new Date().toISOString(),
|
|
89
|
-
iterations,
|
|
90
|
-
summary: summarizeStoragePolicyReport(policies),
|
|
91
|
-
fixtures: FIXTURES,
|
|
92
|
-
policies,
|
|
93
|
-
};
|
|
94
|
-
}
|
|
95
|
-
export function renderStoragePolicyBenchmarkReport(report) {
|
|
96
|
-
const date = report.generatedAt.slice(0, 10);
|
|
97
|
-
const lines = [
|
|
98
|
-
"# Storage Policy Benchmark Report - Iteration 1",
|
|
99
|
-
"",
|
|
100
|
-
`Date: ${date}`,
|
|
101
|
-
"",
|
|
102
|
-
"## Scope",
|
|
103
|
-
"",
|
|
104
|
-
"Benchmark-only experiment for Freeflow vault storage policies. This report does not change runtime defaults or repo config. It compares exact storage, threshold storage, hybrid metadata/exact storage, and duplicate-output dedupe using deterministic command-output fixtures.",
|
|
105
|
-
"",
|
|
106
|
-
"## Summary",
|
|
107
|
-
"",
|
|
108
|
-
`- Fixtures: ${report.summary.fixtures}`,
|
|
109
|
-
`- Policies: ${report.summary.policies}`,
|
|
110
|
-
`- Safe candidates for further evaluation: ${report.summary.safeCandidateIds.join(", ") || "none"}`,
|
|
111
|
-
`- Disqualified by exact-recovery safety: ${report.summary.disqualifiedCandidateIds.join(", ") || "none"}`,
|
|
112
|
-
`- Runtime default changed: ${report.summary.defaultUnchanged ? "no" : "yes"}`,
|
|
113
|
-
"",
|
|
114
|
-
"## Policy Results",
|
|
115
|
-
"",
|
|
116
|
-
"| Policy | Exact-sensitive recovery | Storage bytes | Index bytes | Exact stored bytes | Storage reduction | Token-surface reduction | Privacy surface | Metadata-only | Duplicate metadata | Latency p50/p95 | Notes |",
|
|
117
|
-
"| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | --- |",
|
|
118
|
-
];
|
|
119
|
-
for (const policy of report.policies) {
|
|
120
|
-
lines.push(
|
|
121
|
-
[
|
|
122
|
-
escapeTable(policy.label),
|
|
123
|
-
`${policy.safety.exactnessSensitiveRecoverable}/${policy.safety.exactnessSensitiveFixtures}`,
|
|
124
|
-
String(policy.totals.storageBytes),
|
|
125
|
-
String(policy.totals.indexBytes),
|
|
126
|
-
String(policy.totals.exactStoredCombinedBytes),
|
|
127
|
-
formatPercent(policy.totals.storageReductionPercent),
|
|
128
|
-
formatPercent(policy.totals.tokenSurfaceReductionPercent),
|
|
129
|
-
formatPercent(policy.totals.privacySurfacePercent),
|
|
130
|
-
String(policy.totals.metadataOnlyRecords),
|
|
131
|
-
String(policy.totals.duplicateMetadataRecords),
|
|
132
|
-
`${policy.totals.latencyMs.p50.toFixed(2)}/${policy.totals.latencyMs.p95.toFixed(2)}`,
|
|
133
|
-
escapeTable(policy.notes.join(" ")),
|
|
134
|
-
]
|
|
135
|
-
.join(" | ")
|
|
136
|
-
.replace(/^/, "| ")
|
|
137
|
-
.replace(/$/, " |"),
|
|
138
|
-
);
|
|
139
|
-
}
|
|
140
|
-
lines.push("", "## Candidate Notes", "");
|
|
141
|
-
for (const policy of report.policies) {
|
|
142
|
-
lines.push(`### ${policy.label}`, "", policy.description, "");
|
|
143
|
-
lines.push(`- Exactness-sensitive recovery: ${policy.safety.exactnessSensitiveRecoveryPassed ? "pass" : "fail"}`);
|
|
144
|
-
lines.push(`- Metadata-only recovery labeled: ${policy.safety.metadataOnlyRecoveryLabeled ? "yes" : "no"}`);
|
|
145
|
-
lines.push(`- Repeated outputs deduped: ${policy.safety.repeatedOutputsDeduped ? "yes" : "no"}`);
|
|
146
|
-
lines.push(
|
|
147
|
-
"",
|
|
148
|
-
"| Fixture | Iteration | Record | Recovery | Exact bytes | Notes |",
|
|
149
|
-
"| --- | ---: | --- | --- | ---: | --- |",
|
|
150
|
-
);
|
|
151
|
-
for (const fixture of policy.fixtures) {
|
|
152
|
-
lines.push(
|
|
153
|
-
[
|
|
154
|
-
escapeTable(fixture.fixtureId),
|
|
155
|
-
String(fixture.iteration),
|
|
156
|
-
`${fixture.recordKind}/${fixture.recoverability}`,
|
|
157
|
-
fixture.usefulRecovery,
|
|
158
|
-
String(fixture.exactStoredCombinedBytes),
|
|
159
|
-
escapeTable(fixture.notes.join(" ")),
|
|
160
|
-
]
|
|
161
|
-
.join(" | ")
|
|
162
|
-
.replace(/^/, "| ")
|
|
163
|
-
.replace(/$/, " |"),
|
|
164
|
-
);
|
|
165
|
-
}
|
|
166
|
-
lines.push("");
|
|
167
|
-
}
|
|
168
|
-
lines.push(
|
|
169
|
-
"## Decision Boundary",
|
|
170
|
-
"",
|
|
171
|
-
"This benchmark intentionally stops before changing defaults. Any storage default change still needs a product/safety decision because metadata-only storage changes exact recovery semantics and privacy surface.",
|
|
172
|
-
"",
|
|
173
|
-
);
|
|
174
|
-
return `${lines.join("\n")}\n`;
|
|
175
|
-
}
|
|
176
|
-
export async function writeStoragePolicyBenchmarkReports(
|
|
177
|
-
report,
|
|
178
|
-
markdownReportPath = defaultReportPath(),
|
|
179
|
-
options = {},
|
|
180
|
-
) {
|
|
181
|
-
return writeBenchmarkReportPair({
|
|
182
|
-
report,
|
|
183
|
-
markdownReportPath,
|
|
184
|
-
jsonReportPath: options.jsonReportPath,
|
|
185
|
-
renderMarkdown: renderStoragePolicyBenchmarkReport,
|
|
186
|
-
});
|
|
187
|
-
}
|
|
188
|
-
async function runPolicy(policy, iterations) {
|
|
189
|
-
const temp = await createTempDir(`freeflow-storage-policy-${policy.id}-`);
|
|
190
|
-
const vault = createVault({ root: temp.path });
|
|
191
|
-
const sessionId = `storage-policy-${policy.id}`;
|
|
192
|
-
const fixtureResults = [];
|
|
193
|
-
try {
|
|
194
|
-
for (let iteration = 1; iteration <= iterations; iteration += 1) {
|
|
195
|
-
for (const fixture of FIXTURES) {
|
|
196
|
-
fixtureResults.push(await runPolicyFixture({ policy, vault, sessionId, fixture, iteration }));
|
|
197
|
-
}
|
|
198
|
-
}
|
|
199
|
-
const storageBytes = await directorySize(temp.path);
|
|
200
|
-
const indexBytes = await directorySize(join(temp.path, "index"));
|
|
201
|
-
return buildPolicyResult({ policy, fixtureResults, storageBytes, indexBytes });
|
|
202
|
-
} finally {
|
|
203
|
-
await temp.cleanup();
|
|
204
|
-
}
|
|
205
|
-
}
|
|
206
|
-
async function runPolicyFixture(options) {
|
|
207
|
-
const combined = combineOutputSections(options.fixture.stdout, options.fixture.stderr);
|
|
208
|
-
const rawCombinedBytes = byteLength(combined);
|
|
209
|
-
const fingerprints = commandOutputFingerprints({
|
|
210
|
-
command: options.fixture.command,
|
|
211
|
-
stdout: options.fixture.stdout,
|
|
212
|
-
stderr: options.fixture.stderr,
|
|
213
|
-
combined,
|
|
214
|
-
executionStatus: options.fixture.executionStatus,
|
|
215
|
-
exitCode: options.fixture.exitCode,
|
|
216
|
-
});
|
|
217
|
-
const duplicate = await findExactDuplicateCommandOutput(options.vault, {
|
|
218
|
-
sessionId: options.sessionId,
|
|
219
|
-
fingerprints,
|
|
220
|
-
}).catch(() => undefined);
|
|
221
|
-
const decisionInput = { fixture: options.fixture, combined, rawCombinedBytes };
|
|
222
|
-
if (duplicate !== undefined) {
|
|
223
|
-
decisionInput.duplicate = duplicate;
|
|
224
|
-
}
|
|
225
|
-
const decision = options.policy.decide(decisionInput);
|
|
226
|
-
const storeOptions = { ...options, combined, rawCombinedBytes, fingerprints, decision };
|
|
227
|
-
if (duplicate !== undefined) {
|
|
228
|
-
Object.assign(storeOptions, { duplicate });
|
|
229
|
-
}
|
|
230
|
-
const observation = await storeWithPolicy(storeOptions);
|
|
231
|
-
const recovery = await checkRecovery({ ...options, observation, combined });
|
|
232
|
-
return {
|
|
233
|
-
fixtureId: options.fixture.id,
|
|
234
|
-
iteration: options.iteration,
|
|
235
|
-
outputId: observation.record.outputId,
|
|
236
|
-
recordKind: observation.record.kind,
|
|
237
|
-
persistence: observation.record.persistence.status,
|
|
238
|
-
recoverability: observation.record.persistence.recoverability,
|
|
239
|
-
rawCombinedBytes,
|
|
240
|
-
exactStoredCombinedBytes: observation.exactStoredCombinedBytes,
|
|
241
|
-
latencyMs: observation.latencyMs,
|
|
242
|
-
exactRecovery: recovery.exactRecovery,
|
|
243
|
-
usefulRecovery: recovery.usefulRecovery,
|
|
244
|
-
...(observation.duplicateOf !== undefined ? { duplicateOf: observation.duplicateOf } : {}),
|
|
245
|
-
exactnessSensitive: options.fixture.exactnessSensitive,
|
|
246
|
-
notes: recovery.notes,
|
|
247
|
-
};
|
|
248
|
-
}
|
|
249
|
-
async function storeWithPolicy(options) {
|
|
250
|
-
const startedAt = performance.now();
|
|
251
|
-
if (options.decision === "exact") {
|
|
252
|
-
const record = await storeCommandOutput(options.vault, {
|
|
253
|
-
sessionId: options.sessionId,
|
|
254
|
-
command: options.fixture.command,
|
|
255
|
-
stdout: options.fixture.stdout,
|
|
256
|
-
stderr: options.fixture.stderr,
|
|
257
|
-
combined: options.combined,
|
|
258
|
-
executionStatus: options.fixture.executionStatus,
|
|
259
|
-
exitCode: options.fixture.exitCode,
|
|
260
|
-
decisionIds: [
|
|
261
|
-
decisionId("storage-policy", options.policy.id, options.fixture.id, String(options.iteration), "exact"),
|
|
262
|
-
],
|
|
263
|
-
producer: { kind: "command", name: "storage-policy-experiment" },
|
|
264
|
-
});
|
|
265
|
-
return {
|
|
266
|
-
record,
|
|
267
|
-
decision: options.decision,
|
|
268
|
-
latencyMs: performance.now() - startedAt,
|
|
269
|
-
rawCombinedBytes: options.rawCombinedBytes,
|
|
270
|
-
exactStoredCombinedBytes: options.rawCombinedBytes,
|
|
271
|
-
};
|
|
272
|
-
}
|
|
273
|
-
const duplicateOf = options.decision === "duplicate-metadata" ? options.duplicate?.outputId : undefined;
|
|
274
|
-
const record = await storeMetadataOutput(options.vault, {
|
|
275
|
-
sessionId: options.sessionId,
|
|
276
|
-
sourceKind: "other",
|
|
277
|
-
rawLineCount: countLines(options.combined),
|
|
278
|
-
rawByteCount: options.rawCombinedBytes,
|
|
279
|
-
rawSha256: sha256Text(options.combined),
|
|
280
|
-
decisionIds: [
|
|
281
|
-
decisionId("storage-policy", options.policy.id, options.fixture.id, String(options.iteration), options.decision),
|
|
282
|
-
],
|
|
283
|
-
producer: { kind: "command", name: "storage-policy-experiment" },
|
|
284
|
-
metadata: {
|
|
285
|
-
policy: options.policy.id,
|
|
286
|
-
command: options.fixture.command,
|
|
287
|
-
executionStatus: options.fixture.executionStatus,
|
|
288
|
-
exitCode: options.fixture.exitCode,
|
|
289
|
-
exactnessSensitive: options.fixture.exactnessSensitive,
|
|
290
|
-
...(duplicateOf !== undefined ? { duplicateOf } : {}),
|
|
291
|
-
},
|
|
292
|
-
});
|
|
293
|
-
return {
|
|
294
|
-
record,
|
|
295
|
-
decision: options.decision,
|
|
296
|
-
latencyMs: performance.now() - startedAt,
|
|
297
|
-
rawCombinedBytes: options.rawCombinedBytes,
|
|
298
|
-
exactStoredCombinedBytes: 0,
|
|
299
|
-
...(duplicateOf !== undefined ? { duplicateOf } : {}),
|
|
300
|
-
};
|
|
301
|
-
}
|
|
302
|
-
async function checkRecovery(options) {
|
|
303
|
-
const notes = [];
|
|
304
|
-
if (options.observation.record.kind === "command") {
|
|
305
|
-
try {
|
|
306
|
-
const recovered = await readOutputText(
|
|
307
|
-
options.vault,
|
|
308
|
-
options.sessionId,
|
|
309
|
-
options.observation.record.outputId,
|
|
310
|
-
"combined",
|
|
311
|
-
);
|
|
312
|
-
const passed = recovered === options.combined;
|
|
313
|
-
notes.push(passed ? "exact combined recovery passed" : "exact combined recovery mismatch");
|
|
314
|
-
return { exactRecovery: passed ? "passed" : "failed", usefulRecovery: passed ? "exact" : "none", notes };
|
|
315
|
-
} catch (error) {
|
|
316
|
-
notes.push(`exact recovery failed: ${errorMessage(error)}`);
|
|
317
|
-
return { exactRecovery: "failed", usefulRecovery: "none", notes };
|
|
318
|
-
}
|
|
319
|
-
}
|
|
320
|
-
if (options.observation.duplicateOf !== undefined) {
|
|
321
|
-
try {
|
|
322
|
-
const recovered = await readOutputText(
|
|
323
|
-
options.vault,
|
|
324
|
-
options.sessionId,
|
|
325
|
-
options.observation.duplicateOf,
|
|
326
|
-
"combined",
|
|
327
|
-
);
|
|
328
|
-
const passed = recovered === options.combined;
|
|
329
|
-
notes.push(
|
|
330
|
-
passed
|
|
331
|
-
? `metadata duplicate points to exact outputId=${options.observation.duplicateOf}`
|
|
332
|
-
: `metadata duplicate pointer mismatch outputId=${options.observation.duplicateOf}`,
|
|
333
|
-
);
|
|
334
|
-
return { exactRecovery: "not-exact", usefulRecovery: passed ? "duplicate-ref" : "none", notes };
|
|
335
|
-
} catch (error) {
|
|
336
|
-
notes.push(`duplicate reference recovery failed: ${errorMessage(error)}`);
|
|
337
|
-
return { exactRecovery: "not-exact", usefulRecovery: "none", notes };
|
|
338
|
-
}
|
|
339
|
-
}
|
|
340
|
-
notes.push("metadata-only record intentionally has no raw exact recovery");
|
|
341
|
-
return { exactRecovery: "not-exact", usefulRecovery: "metadata-only", notes };
|
|
342
|
-
}
|
|
343
|
-
function buildPolicyResult(options) {
|
|
344
|
-
const rawCombinedBytes = sum(options.fixtureResults.map((fixture) => fixture.rawCombinedBytes));
|
|
345
|
-
const exactStoredCombinedBytes = sum(options.fixtureResults.map((fixture) => fixture.exactStoredCombinedBytes));
|
|
346
|
-
const latency = latencySummary(options.fixtureResults.map((fixture) => fixture.latencyMs));
|
|
347
|
-
const exactnessSensitiveFixtures = options.fixtureResults.filter((fixture) => fixture.exactnessSensitive).length;
|
|
348
|
-
const exactnessSensitiveRecoverable = options.fixtureResults.filter(
|
|
349
|
-
(fixture) =>
|
|
350
|
-
fixture.exactnessSensitive && (fixture.usefulRecovery === "exact" || fixture.usefulRecovery === "duplicate-ref"),
|
|
351
|
-
).length;
|
|
352
|
-
const metadataOnlyRecords = options.fixtureResults.filter((fixture) => fixture.recordKind === "metadata").length;
|
|
353
|
-
const duplicateMetadataRecords = options.fixtureResults.filter(
|
|
354
|
-
(fixture) => fixture.usefulRecovery === "duplicate-ref",
|
|
355
|
-
).length;
|
|
356
|
-
const repeatedOutputsDeduped = duplicateMetadataRecords > 0;
|
|
357
|
-
const safety = {
|
|
358
|
-
exactnessSensitiveFixtures,
|
|
359
|
-
exactnessSensitiveRecoverable,
|
|
360
|
-
exactnessSensitiveRecoveryPassed: exactnessSensitiveRecoverable === exactnessSensitiveFixtures,
|
|
361
|
-
metadataOnlyRecoveryLabeled: options.fixtureResults.every(
|
|
362
|
-
(fixture) => fixture.recordKind !== "metadata" || fixture.recoverability === "metadata_only",
|
|
363
|
-
),
|
|
364
|
-
repeatedOutputsDeduped,
|
|
365
|
-
};
|
|
366
|
-
const notes = [];
|
|
367
|
-
if (!safety.exactnessSensitiveRecoveryPassed) {
|
|
368
|
-
notes.push("disqualified: exactness-sensitive failure/verification output would lose exact recovery");
|
|
369
|
-
}
|
|
370
|
-
if (options.policy.id === "threshold-exact" && !safety.exactnessSensitiveRecoveryPassed) {
|
|
371
|
-
notes.push("threshold-only policy is unsafe without an exactness-sensitive override");
|
|
372
|
-
}
|
|
373
|
-
if (options.policy.id === "metadata-small-exact-large-hybrid" && safety.exactnessSensitiveRecoveryPassed) {
|
|
374
|
-
notes.push("hybrid preserved exact recovery for sensitive fixtures while reducing exact raw storage");
|
|
375
|
-
}
|
|
376
|
-
if (options.policy.id === "duplicate-output-dedupe" && repeatedOutputsDeduped) {
|
|
377
|
-
notes.push("duplicates kept metadata pointers to prior exact output");
|
|
378
|
-
}
|
|
379
|
-
if (options.policy.id === "hybrid-dedupe" && safety.exactnessSensitiveRecoveryPassed && repeatedOutputsDeduped) {
|
|
380
|
-
notes.push(
|
|
381
|
-
"hybrid+dedupe preserved exact-sensitive recovery while metadata-only small output and duplicate pointers reduced exact raw storage",
|
|
382
|
-
);
|
|
383
|
-
}
|
|
384
|
-
return {
|
|
385
|
-
policyId: options.policy.id,
|
|
386
|
-
label: options.policy.label,
|
|
387
|
-
description: options.policy.description,
|
|
388
|
-
totals: {
|
|
389
|
-
rawCombinedBytes,
|
|
390
|
-
rawCombinedTokensApprox: approximateTokens(rawCombinedBytes),
|
|
391
|
-
exactStoredCombinedBytes,
|
|
392
|
-
exactStoredTokensApprox: approximateTokens(exactStoredCombinedBytes),
|
|
393
|
-
storageBytes: options.storageBytes,
|
|
394
|
-
indexBytes: options.indexBytes,
|
|
395
|
-
metadataOnlyRecords,
|
|
396
|
-
exactRecords: options.fixtureResults.length - metadataOnlyRecords,
|
|
397
|
-
duplicateMetadataRecords,
|
|
398
|
-
storageReductionPercent: reductionPercent(rawCombinedBytes, exactStoredCombinedBytes),
|
|
399
|
-
tokenSurfaceReductionPercent: reductionPercent(
|
|
400
|
-
approximateTokens(rawCombinedBytes),
|
|
401
|
-
approximateTokens(exactStoredCombinedBytes),
|
|
402
|
-
),
|
|
403
|
-
privacySurfacePercent:
|
|
404
|
-
rawCombinedBytes > 0 ? Math.round((exactStoredCombinedBytes / rawCombinedBytes) * 10_000) / 100 : 0,
|
|
405
|
-
latencyMs: latency,
|
|
406
|
-
},
|
|
407
|
-
safety,
|
|
408
|
-
fixtures: options.fixtureResults,
|
|
409
|
-
notes,
|
|
410
|
-
};
|
|
411
|
-
}
|
|
412
|
-
function summarizeStoragePolicyReport(policies) {
|
|
413
|
-
const safeCandidateIds = policies
|
|
414
|
-
.filter((policy) => policy.safety.exactnessSensitiveRecoveryPassed && policy.safety.metadataOnlyRecoveryLabeled)
|
|
415
|
-
.map((policy) => policy.policyId);
|
|
416
|
-
const disqualifiedCandidateIds = policies
|
|
417
|
-
.filter((policy) => !policy.safety.exactnessSensitiveRecoveryPassed || !policy.safety.metadataOnlyRecoveryLabeled)
|
|
418
|
-
.map((policy) => policy.policyId);
|
|
419
|
-
return {
|
|
420
|
-
fixtures: FIXTURES.length,
|
|
421
|
-
policies: policies.length,
|
|
422
|
-
safeCandidateIds,
|
|
423
|
-
disqualifiedCandidateIds,
|
|
424
|
-
defaultUnchanged: true,
|
|
425
|
-
};
|
|
426
|
-
}
|
|
427
|
-
function createStoragePolicyFixtures() {
|
|
428
|
-
const largeLines =
|
|
429
|
-
Array.from(
|
|
430
|
-
{ length: 300 },
|
|
431
|
-
(_, index) => `large log line ${String(index + 1).padStart(3, "0")} ${"x".repeat(80)}`,
|
|
432
|
-
).join("\n") + "\nLARGE_LOG_SENTINEL exact tail\n";
|
|
433
|
-
return [
|
|
434
|
-
{
|
|
435
|
-
id: "small-success",
|
|
436
|
-
title: "Small successful command output",
|
|
437
|
-
command: "echo ok",
|
|
438
|
-
stdout: "ok\n",
|
|
439
|
-
stderr: "",
|
|
440
|
-
executionStatus: "success",
|
|
441
|
-
exitCode: 0,
|
|
442
|
-
exactnessSensitive: false,
|
|
443
|
-
},
|
|
444
|
-
{
|
|
445
|
-
id: "small-failure",
|
|
446
|
-
title: "Small failed command with exact diagnostic",
|
|
447
|
-
command: "npm test",
|
|
448
|
-
stdout: "Tests: 1 failed, 24 passed, 25 total\n",
|
|
449
|
-
stderr: "AssertionError: STORAGE_POLICY_FAILURE_SENTINEL\n",
|
|
450
|
-
executionStatus: "failed",
|
|
451
|
-
exitCode: 1,
|
|
452
|
-
exactnessSensitive: true,
|
|
453
|
-
},
|
|
454
|
-
{
|
|
455
|
-
id: "verification-output",
|
|
456
|
-
title: "Verification output with completion claim evidence",
|
|
457
|
-
command: "npm run verify",
|
|
458
|
-
stdout: "Verification passed: STORAGE_POLICY_VERIFY_SENTINEL\n",
|
|
459
|
-
stderr: "",
|
|
460
|
-
executionStatus: "success",
|
|
461
|
-
exitCode: 0,
|
|
462
|
-
exactnessSensitive: true,
|
|
463
|
-
},
|
|
464
|
-
{
|
|
465
|
-
id: "large-log",
|
|
466
|
-
title: "Large noisy log output",
|
|
467
|
-
command: "tail huge.log",
|
|
468
|
-
stdout: largeLines,
|
|
469
|
-
stderr: "",
|
|
470
|
-
executionStatus: "success",
|
|
471
|
-
exitCode: 0,
|
|
472
|
-
exactnessSensitive: false,
|
|
473
|
-
},
|
|
474
|
-
{
|
|
475
|
-
id: "large-log-repeat",
|
|
476
|
-
title: "Large noisy log repeated output",
|
|
477
|
-
command: "tail huge.log",
|
|
478
|
-
stdout: largeLines,
|
|
479
|
-
stderr: "",
|
|
480
|
-
executionStatus: "success",
|
|
481
|
-
exitCode: 0,
|
|
482
|
-
exactnessSensitive: false,
|
|
483
|
-
repeatedGroup: "large-log",
|
|
484
|
-
},
|
|
485
|
-
{
|
|
486
|
-
id: "repeated-failure-a",
|
|
487
|
-
title: "Repeated exactness-sensitive failure first occurrence",
|
|
488
|
-
command: "npm test -- repeated",
|
|
489
|
-
stdout: "Tests: 1 failed, 24 passed, 25 total\n",
|
|
490
|
-
stderr: "AssertionError: REPEATED_STORAGE_POLICY_FAILURE_SENTINEL\n",
|
|
491
|
-
executionStatus: "failed",
|
|
492
|
-
exitCode: 1,
|
|
493
|
-
exactnessSensitive: true,
|
|
494
|
-
repeatedGroup: "failure",
|
|
495
|
-
},
|
|
496
|
-
{
|
|
497
|
-
id: "repeated-failure-b",
|
|
498
|
-
title: "Repeated exactness-sensitive failure second occurrence",
|
|
499
|
-
command: "npm test -- repeated",
|
|
500
|
-
stdout: "Tests: 1 failed, 24 passed, 25 total\n",
|
|
501
|
-
stderr: "AssertionError: REPEATED_STORAGE_POLICY_FAILURE_SENTINEL\n",
|
|
502
|
-
executionStatus: "failed",
|
|
503
|
-
exitCode: 1,
|
|
504
|
-
exactnessSensitive: true,
|
|
505
|
-
repeatedGroup: "failure",
|
|
506
|
-
},
|
|
507
|
-
{
|
|
508
|
-
id: "repeat-a",
|
|
509
|
-
title: "Repeated output first occurrence",
|
|
510
|
-
command: "fixture repeat",
|
|
511
|
-
stdout: "REPEATED_STORAGE_POLICY_SENTINEL\n",
|
|
512
|
-
stderr: "",
|
|
513
|
-
executionStatus: "success",
|
|
514
|
-
exitCode: 0,
|
|
515
|
-
exactnessSensitive: false,
|
|
516
|
-
repeatedGroup: "repeat",
|
|
517
|
-
},
|
|
518
|
-
{
|
|
519
|
-
id: "repeat-b",
|
|
520
|
-
title: "Repeated output second occurrence",
|
|
521
|
-
command: "fixture repeat",
|
|
522
|
-
stdout: "REPEATED_STORAGE_POLICY_SENTINEL\n",
|
|
523
|
-
stderr: "",
|
|
524
|
-
executionStatus: "success",
|
|
525
|
-
exitCode: 0,
|
|
526
|
-
exactnessSensitive: false,
|
|
527
|
-
repeatedGroup: "repeat",
|
|
528
|
-
},
|
|
529
|
-
];
|
|
530
|
-
}
|
|
531
|
-
async function directorySize(path) {
|
|
532
|
-
try {
|
|
533
|
-
const info = await stat(path);
|
|
534
|
-
if (info.isFile()) {
|
|
535
|
-
return info.size;
|
|
536
|
-
}
|
|
537
|
-
if (!info.isDirectory()) {
|
|
538
|
-
return 0;
|
|
539
|
-
}
|
|
540
|
-
} catch {
|
|
541
|
-
return 0;
|
|
542
|
-
}
|
|
543
|
-
const entries = await readdir(path, { withFileTypes: true });
|
|
544
|
-
let total = 0;
|
|
545
|
-
for (const entry of entries) {
|
|
546
|
-
total += await directorySize(join(path, entry.name));
|
|
547
|
-
}
|
|
548
|
-
return total;
|
|
549
|
-
}
|
|
550
|
-
async function createTempDir(prefix) {
|
|
551
|
-
const path = await mkdtemp(resolve(tmpdir(), prefix));
|
|
552
|
-
return {
|
|
553
|
-
path,
|
|
554
|
-
cleanup: async () => {
|
|
555
|
-
await rm(path, { recursive: true, force: true });
|
|
556
|
-
},
|
|
557
|
-
};
|
|
558
|
-
}
|
|
559
|
-
function combineOutputSections(stdout, stderr) {
|
|
560
|
-
if (stdout.length === 0) {
|
|
561
|
-
return stderr;
|
|
562
|
-
}
|
|
563
|
-
if (stderr.length === 0) {
|
|
564
|
-
return stdout;
|
|
565
|
-
}
|
|
566
|
-
return `[stdout]\n${stdout}\n[stderr]\n${stderr}`;
|
|
567
|
-
}
|
|
568
|
-
function countLines(text) {
|
|
569
|
-
if (text.length === 0) {
|
|
570
|
-
return 0;
|
|
571
|
-
}
|
|
572
|
-
return text.split("\n").length;
|
|
573
|
-
}
|
|
574
|
-
function sum(values) {
|
|
575
|
-
return values.reduce((total, value) => total + value, 0);
|
|
576
|
-
}
|
|
577
|
-
function byteLength(value) {
|
|
578
|
-
return Buffer.byteLength(value, "utf8");
|
|
579
|
-
}
|
|
580
|
-
function sha256Text(value) {
|
|
581
|
-
return createHash("sha256").update(value).digest("hex");
|
|
582
|
-
}
|
|
583
|
-
function decisionId(...parts) {
|
|
584
|
-
return `ffdec_${sha256Text(parts.join("\0")).slice(0, 16)}`;
|
|
585
|
-
}
|
|
586
|
-
function errorMessage(error) {
|
|
587
|
-
return error instanceof Error ? error.message : String(error);
|
|
588
|
-
}
|
|
589
|
-
function defaultReportPath() {
|
|
590
|
-
return resolve(process.cwd(), "router/evals/reports/storage-policy-benchmark-1-report.md");
|
|
591
|
-
}
|
|
592
|
-
async function runCli() {
|
|
593
|
-
const { iterations, reportPath, jsonReportPath } = parseBenchmarkCliArgs(process.argv.slice(2), {
|
|
594
|
-
reportPath: defaultReportPath(),
|
|
595
|
-
});
|
|
596
|
-
const options = {};
|
|
597
|
-
if (iterations !== undefined) {
|
|
598
|
-
options.iterations = iterations;
|
|
599
|
-
}
|
|
600
|
-
const report = await runStoragePolicyBenchmarks(options);
|
|
601
|
-
const reports = await writeStoragePolicyBenchmarkReports(report, reportPath, {
|
|
602
|
-
jsonReportPath: jsonReportPath === undefined ? defaultJsonRunReportPath(reportPath) : jsonReportPath,
|
|
603
|
-
});
|
|
604
|
-
const shortId = createHash("sha256").update(JSON.stringify(report.summary)).digest("hex").slice(0, 8);
|
|
605
|
-
console.log(
|
|
606
|
-
`Freeflow storage policy benchmark ${shortId}: safe candidates ${report.summary.safeCandidateIds.join(", ") || "none"}`,
|
|
607
|
-
);
|
|
608
|
-
console.log(`Markdown report: ${reports.markdown}`);
|
|
609
|
-
if (reports.json) {
|
|
610
|
-
console.log(`JSON run data: ${reports.json}`);
|
|
611
|
-
}
|
|
612
|
-
if (report.summary.safeCandidateIds.length === 0) {
|
|
613
|
-
process.exitCode = 1;
|
|
614
|
-
}
|
|
615
|
-
}
|
|
616
|
-
if (process.argv[1] && fileURLToPath(import.meta.url) === resolve(process.argv[1])) {
|
|
617
|
-
await runCli();
|
|
618
|
-
}
|
|
@@ -1,56 +0,0 @@
|
|
|
1
|
-
export interface RunVaultIndexStorageBenchmarkOptions {
|
|
2
|
-
iterations?: number;
|
|
3
|
-
generatedAt?: string;
|
|
4
|
-
}
|
|
5
|
-
export interface VaultIndexStorageBenchmarkReport {
|
|
6
|
-
generatedAt: string;
|
|
7
|
-
iterations: number;
|
|
8
|
-
summary: VaultIndexStorageBenchmarkSummary;
|
|
9
|
-
candidates: VaultIndexStorageCandidateResult[];
|
|
10
|
-
}
|
|
11
|
-
export interface VaultIndexStorageBenchmarkSummary {
|
|
12
|
-
selectedEngine: string;
|
|
13
|
-
selectedReason: string;
|
|
14
|
-
fixtures: number;
|
|
15
|
-
localSidecarPassed: boolean;
|
|
16
|
-
scannerBaselinePassed: boolean;
|
|
17
|
-
sqliteFtsStatus: "not-run" | "available" | "failed";
|
|
18
|
-
localAppendMs: LatencyPair;
|
|
19
|
-
localQueryMs: LatencyPair;
|
|
20
|
-
scanQueryMs: LatencyPair;
|
|
21
|
-
localQueryReductionPercent: number;
|
|
22
|
-
}
|
|
23
|
-
export interface LatencyPair {
|
|
24
|
-
p50: number;
|
|
25
|
-
p95: number;
|
|
26
|
-
}
|
|
27
|
-
export interface VaultIndexStorageCandidateResult {
|
|
28
|
-
candidate: string;
|
|
29
|
-
status: "pass" | "fail" | "not-run";
|
|
30
|
-
adopted: boolean;
|
|
31
|
-
appendMs?: LatencyPair;
|
|
32
|
-
queryMs?: LatencyPair;
|
|
33
|
-
rawBytes?: number;
|
|
34
|
-
resultBytes?: number;
|
|
35
|
-
reductionPercent?: number;
|
|
36
|
-
checks: string[];
|
|
37
|
-
notes: string[];
|
|
38
|
-
}
|
|
39
|
-
export declare function runVaultIndexStorageBenchmark(
|
|
40
|
-
options?: RunVaultIndexStorageBenchmarkOptions,
|
|
41
|
-
): Promise<VaultIndexStorageBenchmarkReport>;
|
|
42
|
-
export declare function renderVaultIndexStorageBenchmarkReport(report: VaultIndexStorageBenchmarkReport): string;
|
|
43
|
-
export declare function writeVaultIndexStorageBenchmarkReport(
|
|
44
|
-
report: VaultIndexStorageBenchmarkReport,
|
|
45
|
-
reportPath: string,
|
|
46
|
-
): Promise<void>;
|
|
47
|
-
export declare function writeVaultIndexStorageBenchmarkReports(
|
|
48
|
-
report: VaultIndexStorageBenchmarkReport,
|
|
49
|
-
markdownReportPath: string,
|
|
50
|
-
options?: {
|
|
51
|
-
jsonReportPath?: string | false;
|
|
52
|
-
},
|
|
53
|
-
): Promise<{
|
|
54
|
-
markdown: string;
|
|
55
|
-
json?: string;
|
|
56
|
-
}>;
|