mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-13 08:15:14 +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.
229 lines
5.2 KiB
TypeScript
229 lines
5.2 KiB
TypeScript
export interface SqlEdit {
|
|
oldText: string;
|
|
newText: string;
|
|
reason?: string;
|
|
}
|
|
|
|
interface SqlEditResult {
|
|
success: boolean;
|
|
sql: string;
|
|
appliedEdits: number;
|
|
errors: string[];
|
|
}
|
|
|
|
type ReplacerResult = { sql: string; note?: string } | { error: string } | null;
|
|
|
|
function exactReplacer(sql: string, oldText: string, newText: string): ReplacerResult {
|
|
if (oldText.length === 0) {
|
|
return null;
|
|
}
|
|
|
|
let count = 0;
|
|
let idx = -1;
|
|
let searchFrom = 0;
|
|
|
|
while (true) {
|
|
const found = sql.indexOf(oldText, searchFrom);
|
|
if (found === -1) {
|
|
break;
|
|
}
|
|
count++;
|
|
idx = found;
|
|
searchFrom = found + 1;
|
|
}
|
|
|
|
if (count === 0) {
|
|
return null;
|
|
}
|
|
if (count > 1) {
|
|
return { error: `Found ${count} matches for text, expected 1. Add more surrounding context.` };
|
|
}
|
|
|
|
return { sql: sql.slice(0, idx) + newText + sql.slice(idx + oldText.length) };
|
|
}
|
|
|
|
function buildCharacterMap(original: string): number[] {
|
|
const map: number[] = [];
|
|
for (let i = 0; i < original.length; i++) {
|
|
if (/\s/.test(original[i])) {
|
|
if (map.length === 0 || !/\s/.test(original[i - 1])) {
|
|
map.push(i);
|
|
}
|
|
} else {
|
|
map.push(i);
|
|
}
|
|
}
|
|
return map;
|
|
}
|
|
|
|
function whitespaceNormalizedReplacer(sql: string, oldText: string, newText: string): ReplacerResult {
|
|
const normalizedSql = sql.replace(/\s+/g, ' ');
|
|
const normalizedOldText = oldText.replace(/\s+/g, ' ');
|
|
|
|
if (normalizedOldText.length === 0) {
|
|
return null;
|
|
}
|
|
|
|
let count = 0;
|
|
let matchIdx = -1;
|
|
let searchFrom = 0;
|
|
|
|
while (true) {
|
|
const found = normalizedSql.indexOf(normalizedOldText, searchFrom);
|
|
if (found === -1) {
|
|
break;
|
|
}
|
|
count++;
|
|
matchIdx = found;
|
|
searchFrom = found + 1;
|
|
}
|
|
|
|
if (count === 0) {
|
|
return null;
|
|
}
|
|
if (count > 1) {
|
|
return null;
|
|
}
|
|
|
|
const charMap = buildCharacterMap(sql);
|
|
|
|
const originalStart = charMap[matchIdx];
|
|
const normalizedEnd = matchIdx + normalizedOldText.length;
|
|
|
|
let originalEnd: number;
|
|
if (normalizedEnd >= charMap.length) {
|
|
originalEnd = sql.length;
|
|
} else {
|
|
originalEnd = charMap[normalizedEnd];
|
|
}
|
|
|
|
return { sql: sql.slice(0, originalStart) + newText + sql.slice(originalEnd) };
|
|
}
|
|
|
|
function levenshteinDistance(a: string, b: string): number {
|
|
const m = a.length;
|
|
const n = b.length;
|
|
|
|
if (m === 0) {
|
|
return n;
|
|
}
|
|
if (n === 0) {
|
|
return m;
|
|
}
|
|
|
|
const dp: number[][] = Array.from({ length: m + 1 }, () => Array(n + 1).fill(0));
|
|
|
|
for (let i = 0; i <= m; i++) {
|
|
dp[i][0] = i;
|
|
}
|
|
for (let j = 0; j <= n; j++) {
|
|
dp[0][j] = j;
|
|
}
|
|
|
|
for (let i = 1; i <= m; i++) {
|
|
for (let j = 1; j <= n; j++) {
|
|
const cost = a[i - 1] === b[j - 1] ? 0 : 1;
|
|
dp[i][j] = Math.min(dp[i - 1][j] + 1, dp[i][j - 1] + 1, dp[i - 1][j - 1] + cost);
|
|
}
|
|
}
|
|
|
|
return dp[m][n];
|
|
}
|
|
|
|
function fuzzyReplacer(sql: string, oldText: string, newText: string): ReplacerResult {
|
|
if (oldText.length === 0) {
|
|
return null;
|
|
}
|
|
|
|
const targetLen = oldText.length;
|
|
const minWindow = Math.max(1, Math.floor(targetLen * 0.85));
|
|
const maxWindow = Math.ceil(targetLen * 1.15);
|
|
|
|
let bestDistance = Infinity;
|
|
let bestStart = -1;
|
|
let bestEnd = -1;
|
|
|
|
for (let windowLen = minWindow; windowLen <= maxWindow; windowLen++) {
|
|
if (windowLen > sql.length) {
|
|
break;
|
|
}
|
|
|
|
for (let start = 0; start <= sql.length - windowLen; start++) {
|
|
const candidate = sql.slice(start, start + windowLen);
|
|
const distance = levenshteinDistance(candidate, oldText);
|
|
if (distance < bestDistance) {
|
|
bestDistance = distance;
|
|
bestStart = start;
|
|
bestEnd = start + windowLen;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (bestStart === -1) {
|
|
return null;
|
|
}
|
|
|
|
const maxLen = Math.max(oldText.length, bestEnd - bestStart);
|
|
const similarity = 1 - bestDistance / maxLen;
|
|
|
|
if (similarity < 0.85) {
|
|
return null;
|
|
}
|
|
|
|
const matchedText = sql.slice(bestStart, bestEnd);
|
|
return {
|
|
sql: sql.slice(0, bestStart) + newText + sql.slice(bestEnd),
|
|
note: `Fuzzy match used (similarity: ${(similarity * 100).toFixed(1)}%, matched: "${matchedText}")`,
|
|
};
|
|
}
|
|
|
|
interface ApplySqlEditsOptions {
|
|
exactOnly?: boolean;
|
|
}
|
|
|
|
export function applySqlEdits(sql: string, edits: SqlEdit[], options?: ApplySqlEditsOptions): SqlEditResult {
|
|
let currentSql = sql;
|
|
let appliedEdits = 0;
|
|
const errors: string[] = [];
|
|
|
|
for (const edit of edits) {
|
|
const replacers = options?.exactOnly
|
|
? [exactReplacer]
|
|
: [exactReplacer, whitespaceNormalizedReplacer, fuzzyReplacer];
|
|
let applied = false;
|
|
|
|
for (const replacer of replacers) {
|
|
const result = replacer(currentSql, edit.oldText, edit.newText);
|
|
|
|
if (result === null) {
|
|
continue;
|
|
}
|
|
|
|
if ('error' in result) {
|
|
const context = edit.reason ? ` (reason: ${edit.reason})` : '';
|
|
errors.push(`${result.error}${context}`);
|
|
applied = true;
|
|
break;
|
|
}
|
|
|
|
currentSql = result.sql;
|
|
appliedEdits++;
|
|
applied = true;
|
|
break;
|
|
}
|
|
|
|
if (!applied) {
|
|
const context = edit.reason ? ` (reason: ${edit.reason})` : '';
|
|
errors.push(
|
|
`No match found for edit${context}: "${edit.oldText.slice(0, 80)}${edit.oldText.length > 80 ? '...' : ''}"`,
|
|
);
|
|
}
|
|
}
|
|
|
|
return {
|
|
success: errors.length === 0,
|
|
sql: currentSql,
|
|
appliedEdits,
|
|
errors,
|
|
};
|
|
}
|