mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-16 11:31:02 +02:00
* refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
363 lines
12 KiB
TypeScript
363 lines
12 KiB
TypeScript
import { isKtxRelationshipBenchmarkTuningEligible } from './relationship-benchmarks.js';
|
|
import type {
|
|
KtxRelationshipBenchmarkCaseResult,
|
|
KtxRelationshipBenchmarkFixture,
|
|
KtxRelationshipBenchmarkMode,
|
|
KtxRelationshipBenchmarkSuiteResult,
|
|
} from './relationship-benchmarks.js';
|
|
|
|
export type KtxRelationshipBenchmarkReportCaseStatus = 'run' | 'validation_blocked' | 'not_run';
|
|
|
|
export interface KtxRelationshipBenchmarkReportCase {
|
|
fixtureId: string;
|
|
fixtureName: string;
|
|
tier: string;
|
|
mode: KtxRelationshipBenchmarkMode;
|
|
status: KtxRelationshipBenchmarkReportCaseStatus;
|
|
reason: string | null;
|
|
tuningEligible: boolean;
|
|
metrics: {
|
|
pkRecall: number | null;
|
|
fkRecall: number | null;
|
|
acceptedOrReviewRecall: number | null;
|
|
acceptedFalsePositiveCount: number | null;
|
|
sqlQueries: number | null;
|
|
llmCalls: number | null;
|
|
runtimeSeconds: number | null;
|
|
};
|
|
falsePositives: {
|
|
pk: string[];
|
|
fk: string[];
|
|
};
|
|
falseNegatives: {
|
|
pk: string[];
|
|
fk: string[];
|
|
};
|
|
skippedComposite: {
|
|
pk: string[];
|
|
fk: string[];
|
|
};
|
|
}
|
|
|
|
export interface KtxRelationshipBenchmarkReport {
|
|
generatedAt: string;
|
|
headline: {
|
|
caseCount: number;
|
|
headlineCaseCount: number;
|
|
headlinePkRecall: number;
|
|
headlineFkRecall: number;
|
|
headlineAcceptedOrReviewRecall: number;
|
|
acceptedFalsePositiveCount: number;
|
|
validationBlockedCount: number;
|
|
};
|
|
cases: KtxRelationshipBenchmarkReportCase[];
|
|
}
|
|
|
|
function key(fixtureId: string, mode: KtxRelationshipBenchmarkMode): string {
|
|
return `${fixtureId}:${mode}`;
|
|
}
|
|
|
|
function fixed(value: number | null): string {
|
|
return value === null ? '-' : value.toFixed(3);
|
|
}
|
|
|
|
function reportCaseReason(input: {
|
|
fixture: KtxRelationshipBenchmarkFixture;
|
|
result: KtxRelationshipBenchmarkCaseResult;
|
|
}): string | null {
|
|
if (input.result.validationBlocked) {
|
|
return 'validation unavailable for this benchmark mode';
|
|
}
|
|
|
|
if (input.fixture.validationBudget !== undefined && input.result.predicted.reviewFk.length > 0) {
|
|
return `review candidate validation reasons: validation_unattempted (${input.result.predicted.reviewFk.length})`;
|
|
}
|
|
|
|
return null;
|
|
}
|
|
|
|
function reportCaseFromResult(input: {
|
|
fixture: KtxRelationshipBenchmarkFixture;
|
|
mode: KtxRelationshipBenchmarkMode;
|
|
result: KtxRelationshipBenchmarkCaseResult;
|
|
}): KtxRelationshipBenchmarkReportCase {
|
|
const status = input.result.validationBlocked ? 'validation_blocked' : 'run';
|
|
return {
|
|
fixtureId: input.fixture.id,
|
|
fixtureName: input.fixture.name,
|
|
tier: input.fixture.tier,
|
|
mode: input.mode,
|
|
status,
|
|
reason: reportCaseReason({ fixture: input.fixture, result: input.result }),
|
|
tuningEligible: isKtxRelationshipBenchmarkTuningEligible({
|
|
fixture: input.fixture,
|
|
mode: input.mode,
|
|
validationBlocked: input.result.validationBlocked,
|
|
}),
|
|
metrics: {
|
|
pkRecall: input.result.metrics.pkRecall,
|
|
fkRecall: input.result.metrics.fkRecall,
|
|
acceptedOrReviewRecall: input.result.metrics.acceptedOrReviewRecall,
|
|
acceptedFalsePositiveCount: input.result.metrics.acceptedFalsePositiveCount,
|
|
sqlQueries: input.result.metrics.sqlQueries,
|
|
llmCalls: input.result.metrics.llmCalls,
|
|
runtimeSeconds: input.result.metrics.runtimeSeconds,
|
|
},
|
|
falsePositives: input.result.falsePositives,
|
|
falseNegatives: input.result.falseNegatives,
|
|
skippedComposite: input.result.skippedComposite,
|
|
};
|
|
}
|
|
|
|
function notRunCase(input: {
|
|
fixture: KtxRelationshipBenchmarkFixture;
|
|
mode: KtxRelationshipBenchmarkMode;
|
|
reason: string;
|
|
}): KtxRelationshipBenchmarkReportCase {
|
|
return {
|
|
fixtureId: input.fixture.id,
|
|
fixtureName: input.fixture.name,
|
|
tier: input.fixture.tier,
|
|
mode: input.mode,
|
|
status: 'not_run',
|
|
reason: input.reason,
|
|
tuningEligible: false,
|
|
metrics: {
|
|
pkRecall: null,
|
|
fkRecall: null,
|
|
acceptedOrReviewRecall: null,
|
|
acceptedFalsePositiveCount: null,
|
|
sqlQueries: null,
|
|
llmCalls: null,
|
|
runtimeSeconds: null,
|
|
},
|
|
falsePositives: { pk: [], fk: [] },
|
|
falseNegatives: { pk: [], fk: [] },
|
|
skippedComposite: { pk: [], fk: [] },
|
|
};
|
|
}
|
|
|
|
export function buildKtxRelationshipBenchmarkReport(input: {
|
|
fixtures: readonly KtxRelationshipBenchmarkFixture[];
|
|
suite: KtxRelationshipBenchmarkSuiteResult;
|
|
modes: readonly KtxRelationshipBenchmarkMode[];
|
|
generatedAt?: string;
|
|
}): KtxRelationshipBenchmarkReport {
|
|
const resultsByKey = new Map(input.suite.cases.map((result) => [key(result.fixtureId, result.mode), result]));
|
|
const cases: KtxRelationshipBenchmarkReportCase[] = [];
|
|
|
|
for (const fixture of input.fixtures) {
|
|
const selectedModes = new Set(fixture.defaultModes);
|
|
for (const mode of input.modes) {
|
|
const result = resultsByKey.get(key(fixture.id, mode));
|
|
if (result) {
|
|
cases.push(reportCaseFromResult({ fixture, mode, result }));
|
|
continue;
|
|
}
|
|
cases.push(
|
|
notRunCase({
|
|
fixture,
|
|
mode,
|
|
reason: selectedModes.has(mode) ? 'mode produced no benchmark result' : 'mode not selected by fixture defaultModes',
|
|
}),
|
|
);
|
|
}
|
|
}
|
|
|
|
return {
|
|
generatedAt: input.generatedAt ?? new Date().toISOString(),
|
|
headline: {
|
|
caseCount: input.suite.aggregate.caseCount,
|
|
headlineCaseCount: input.suite.aggregate.headlineCaseCount,
|
|
headlinePkRecall: input.suite.aggregate.headlinePkRecall,
|
|
headlineFkRecall: input.suite.aggregate.headlineFkRecall,
|
|
headlineAcceptedOrReviewRecall: input.suite.aggregate.headlineAcceptedOrReviewRecall,
|
|
acceptedFalsePositiveCount: input.suite.cases.reduce(
|
|
(sum, result) => sum + result.metrics.acceptedFalsePositiveCount,
|
|
0,
|
|
),
|
|
validationBlockedCount: input.suite.validationBlockedCases.length,
|
|
},
|
|
cases,
|
|
};
|
|
}
|
|
|
|
type KtxRelationshipBenchmarkFailureSelector = (
|
|
item: KtxRelationshipBenchmarkReportCase,
|
|
) => readonly string[];
|
|
|
|
function sortedFailureLines(input: {
|
|
cases: readonly KtxRelationshipBenchmarkReportCase[];
|
|
select: KtxRelationshipBenchmarkFailureSelector;
|
|
}): string[] {
|
|
return input.cases
|
|
.flatMap((item) =>
|
|
input.select(item).map((value) => ({
|
|
fixtureId: item.fixtureId,
|
|
mode: item.mode,
|
|
status: item.status,
|
|
value,
|
|
})),
|
|
)
|
|
.sort((left, right) => {
|
|
const leftKey = `${left.fixtureId}:${left.mode}:${left.status}:${left.value}`;
|
|
const rightKey = `${right.fixtureId}:${right.mode}:${right.status}:${right.value}`;
|
|
return leftKey.localeCompare(rightKey);
|
|
})
|
|
.map((item) => `- \`${item.fixtureId}\` / \`${item.mode}\` / \`${item.status}\`: ${item.value}`);
|
|
}
|
|
|
|
function failureBlock(input: {
|
|
title: string;
|
|
cases: readonly KtxRelationshipBenchmarkReportCase[];
|
|
select: KtxRelationshipBenchmarkFailureSelector;
|
|
}): string[] {
|
|
const values = sortedFailureLines({ cases: input.cases, select: input.select });
|
|
return ['', `### ${input.title}`, '', ...(values.length > 0 ? values : ['- none'])];
|
|
}
|
|
|
|
function headlineFailureContextBlocks(report: KtxRelationshipBenchmarkReport): string[] {
|
|
const headlineCases = report.cases.filter((item) => item.tuningEligible);
|
|
const remainingPkMisses = sortedFailureLines({
|
|
cases: headlineCases,
|
|
select: (item) => item.falseNegatives.pk,
|
|
});
|
|
const remainingFkMisses = sortedFailureLines({
|
|
cases: headlineCases,
|
|
select: (item) => item.falseNegatives.fk,
|
|
});
|
|
|
|
return [
|
|
'',
|
|
'## Headline Failure Context',
|
|
'',
|
|
'Remaining headline misses after this run are listed here so recall gains and still-open algorithmic gaps are visible in the regenerated evidence report.',
|
|
'',
|
|
`- Remaining headline false-negative PKs: ${remainingPkMisses.length}`,
|
|
`- Remaining headline false-negative FKs: ${remainingFkMisses.length}`,
|
|
'',
|
|
'### Remaining Headline False Negative PKs',
|
|
'',
|
|
...(remainingPkMisses.length > 0 ? remainingPkMisses : ['- none']),
|
|
'',
|
|
'### Remaining Headline False Negative FKs',
|
|
'',
|
|
...(remainingFkMisses.length > 0 ? remainingFkMisses : ['- none']),
|
|
];
|
|
}
|
|
|
|
function failureDetailBlocks(report: KtxRelationshipBenchmarkReport): string[] {
|
|
const headlineCases = report.cases.filter((item) => item.tuningEligible);
|
|
const otherCases = report.cases.filter((item) => !item.tuningEligible);
|
|
|
|
return [
|
|
'',
|
|
'## Failure Details',
|
|
...failureBlock({
|
|
title: 'Headline False Positive PKs',
|
|
cases: headlineCases,
|
|
select: (item) => item.falsePositives.pk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Headline False Positive FKs',
|
|
cases: headlineCases,
|
|
select: (item) => item.falsePositives.fk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Headline False Negative PKs',
|
|
cases: headlineCases,
|
|
select: (item) => item.falseNegatives.pk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Headline False Negative FKs',
|
|
cases: headlineCases,
|
|
select: (item) => item.falseNegatives.fk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Other False Positive PKs',
|
|
cases: otherCases,
|
|
select: (item) => item.falsePositives.pk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Other False Positive FKs',
|
|
cases: otherCases,
|
|
select: (item) => item.falsePositives.fk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Other False Negative PKs',
|
|
cases: otherCases,
|
|
select: (item) => item.falseNegatives.pk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Other False Negative FKs',
|
|
cases: otherCases,
|
|
select: (item) => item.falseNegatives.fk,
|
|
}),
|
|
];
|
|
}
|
|
|
|
function compositeSkipBlocks(report: KtxRelationshipBenchmarkReport): string[] {
|
|
const headlineCases = report.cases.filter((item) => item.tuningEligible);
|
|
|
|
return [
|
|
'',
|
|
'## Composite Ground Truth Skips',
|
|
...failureBlock({
|
|
title: 'Skipped Composite PKs',
|
|
cases: headlineCases,
|
|
select: (item) => item.skippedComposite.pk,
|
|
}),
|
|
...failureBlock({
|
|
title: 'Skipped Composite FKs',
|
|
cases: headlineCases,
|
|
select: (item) => item.skippedComposite.fk,
|
|
}),
|
|
];
|
|
}
|
|
|
|
export function formatKtxRelationshipBenchmarkReportMarkdown(report: KtxRelationshipBenchmarkReport): string {
|
|
const lines = [
|
|
'# KTX Relationship Discovery Benchmark Evidence',
|
|
'',
|
|
`Generated: ${report.generatedAt}`,
|
|
'',
|
|
'## Headline',
|
|
'',
|
|
`- Cases run: ${report.headline.caseCount}`,
|
|
`- Headline cases: ${report.headline.headlineCaseCount}`,
|
|
`- Headline PK recall: ${fixed(report.headline.headlinePkRecall)}`,
|
|
`- Headline FK recall: ${fixed(report.headline.headlineFkRecall)}`,
|
|
`- Headline accepted-or-review recall: ${fixed(report.headline.headlineAcceptedOrReviewRecall)}`,
|
|
`- Accepted false positives: ${report.headline.acceptedFalsePositiveCount}`,
|
|
`- Validation-blocked cases: ${report.headline.validationBlockedCount}`,
|
|
'',
|
|
'## Cases',
|
|
'',
|
|
'| Fixture | Tier | Mode | Status | Tuning Eligible | PK Recall | FK Recall | Accepted+Review Recall | Accepted FP | Reason |',
|
|
'| --- | --- | --- | --- | --- | ---: | ---: | ---: | ---: | --- |',
|
|
];
|
|
|
|
for (const item of report.cases) {
|
|
lines.push(
|
|
[
|
|
`| ${item.fixtureId}`,
|
|
item.tier,
|
|
item.mode,
|
|
item.status,
|
|
item.tuningEligible ? 'yes' : 'no',
|
|
fixed(item.metrics.pkRecall),
|
|
fixed(item.metrics.fkRecall),
|
|
fixed(item.metrics.acceptedOrReviewRecall),
|
|
String(item.metrics.acceptedFalsePositiveCount ?? '-'),
|
|
`${item.reason ?? ''} |`,
|
|
].join(' | '),
|
|
);
|
|
}
|
|
|
|
lines.push(...headlineFailureContextBlocks(report));
|
|
lines.push(...failureDetailBlocks(report));
|
|
lines.push(...compositeSkipBlocks(report));
|
|
lines.push('');
|
|
|
|
return `${lines.join('\n')}\n`;
|
|
}
|