mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-19 08:28:06 +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.
211 lines
5 KiB
TypeScript
211 lines
5 KiB
TypeScript
import { randomUUID } from 'node:crypto';
|
|
import { mkdirSync } from 'node:fs';
|
|
import { dirname, join } from 'node:path';
|
|
import Database from 'better-sqlite3';
|
|
import type { MemoryRunRecord, MemoryRunStatus, MemoryRunStorePort } from './memory-runs.js';
|
|
import type { MemoryAgentResult } from './types.js';
|
|
|
|
export interface LocalMemoryRunStoreOptions {
|
|
projectDir: string;
|
|
idFactory?: () => string;
|
|
}
|
|
|
|
type MemoryRunRow = {
|
|
id: string;
|
|
status: string;
|
|
stage: string;
|
|
input_hash: string;
|
|
chat_id: string | null;
|
|
output_summary_json: string | null;
|
|
error: string | null;
|
|
};
|
|
|
|
function localMemoryDbPath(projectDir: string): string {
|
|
return join(projectDir, '.ktx', 'db.sqlite');
|
|
}
|
|
|
|
function isSafeRunId(runId: string): boolean {
|
|
return /^[a-zA-Z0-9][a-zA-Z0-9_.-]*$/.test(runId);
|
|
}
|
|
|
|
function isMemoryRunStatus(value: unknown): value is MemoryRunStatus {
|
|
return value === 'running' || value === 'done' || value === 'error';
|
|
}
|
|
|
|
function parseOutputSummary(raw: string | null): MemoryAgentResult | null {
|
|
if (!raw) {
|
|
return null;
|
|
}
|
|
return JSON.parse(raw) as MemoryAgentResult;
|
|
}
|
|
|
|
function rowToRecord(row: MemoryRunRow): MemoryRunRecord | null {
|
|
if (!isMemoryRunStatus(row.status)) {
|
|
return null;
|
|
}
|
|
return {
|
|
id: row.id,
|
|
status: row.status,
|
|
stage: row.stage,
|
|
inputHash: row.input_hash,
|
|
chatId: row.chat_id,
|
|
outputSummary: parseOutputSummary(row.output_summary_json),
|
|
error: row.error,
|
|
};
|
|
}
|
|
|
|
export class LocalMemoryRunStore implements MemoryRunStorePort {
|
|
private readonly db: Database.Database;
|
|
private readonly idFactory: () => string;
|
|
|
|
constructor(options: LocalMemoryRunStoreOptions) {
|
|
const dbPath = localMemoryDbPath(options.projectDir);
|
|
mkdirSync(dirname(dbPath), { recursive: true });
|
|
this.db = new Database(dbPath);
|
|
this.db.pragma('journal_mode = WAL');
|
|
this.db.pragma('foreign_keys = ON');
|
|
this.db.exec(`
|
|
CREATE TABLE IF NOT EXISTS local_memory_runs (
|
|
id TEXT PRIMARY KEY,
|
|
status TEXT NOT NULL,
|
|
stage TEXT NOT NULL,
|
|
input_hash TEXT NOT NULL,
|
|
chat_id TEXT,
|
|
output_summary_json TEXT,
|
|
error TEXT,
|
|
created_at TEXT NOT NULL,
|
|
updated_at TEXT NOT NULL
|
|
);
|
|
|
|
CREATE INDEX IF NOT EXISTS local_memory_runs_status_updated_idx
|
|
ON local_memory_runs (status, updated_at DESC);
|
|
`);
|
|
this.idFactory = options.idFactory ?? (() => `memory-${randomUUID()}`);
|
|
}
|
|
|
|
async createRunning(args: { inputHash: string; chatId?: string | null }): Promise<{ id: string }> {
|
|
const now = new Date().toISOString();
|
|
const id = this.idFactory();
|
|
this.db
|
|
.prepare(
|
|
`
|
|
INSERT INTO local_memory_runs (
|
|
id,
|
|
status,
|
|
stage,
|
|
input_hash,
|
|
chat_id,
|
|
output_summary_json,
|
|
error,
|
|
created_at,
|
|
updated_at
|
|
)
|
|
VALUES (
|
|
@id,
|
|
'running',
|
|
'queued',
|
|
@inputHash,
|
|
@chatId,
|
|
NULL,
|
|
NULL,
|
|
@now,
|
|
@now
|
|
)
|
|
`,
|
|
)
|
|
.run({
|
|
id,
|
|
inputHash: args.inputHash,
|
|
chatId: args.chatId ?? null,
|
|
now,
|
|
});
|
|
return { id };
|
|
}
|
|
|
|
async markRunning(id: string, stage: string): Promise<void> {
|
|
this.updateRun(id, {
|
|
status: 'running',
|
|
stage,
|
|
outputSummaryJson: null,
|
|
error: null,
|
|
});
|
|
}
|
|
|
|
async markDone(id: string, outputSummary: MemoryAgentResult): Promise<void> {
|
|
this.updateRun(id, {
|
|
status: 'done',
|
|
stage: 'done',
|
|
outputSummaryJson: JSON.stringify(outputSummary),
|
|
error: null,
|
|
});
|
|
}
|
|
|
|
async markError(id: string, error: string): Promise<void> {
|
|
this.updateRun(id, {
|
|
status: 'error',
|
|
stage: 'error',
|
|
outputSummaryJson: null,
|
|
error,
|
|
});
|
|
}
|
|
|
|
async findById(id: string): Promise<MemoryRunRecord | null> {
|
|
if (!isSafeRunId(id)) {
|
|
return null;
|
|
}
|
|
const row = this.db
|
|
.prepare(
|
|
`
|
|
SELECT
|
|
id,
|
|
status,
|
|
stage,
|
|
input_hash,
|
|
chat_id,
|
|
output_summary_json,
|
|
error
|
|
FROM local_memory_runs
|
|
WHERE id = ?
|
|
`,
|
|
)
|
|
.get(id) as MemoryRunRow | undefined;
|
|
|
|
return row ? rowToRecord(row) : null;
|
|
}
|
|
|
|
private updateRun(
|
|
id: string,
|
|
input: {
|
|
status: MemoryRunStatus;
|
|
stage: string;
|
|
outputSummaryJson: string | null;
|
|
error: string | null;
|
|
},
|
|
): void {
|
|
const result = this.db
|
|
.prepare(
|
|
`
|
|
UPDATE local_memory_runs
|
|
SET
|
|
status = @status,
|
|
stage = @stage,
|
|
output_summary_json = @outputSummaryJson,
|
|
error = @error,
|
|
updated_at = @updatedAt
|
|
WHERE id = @id
|
|
`,
|
|
)
|
|
.run({
|
|
id,
|
|
status: input.status,
|
|
stage: input.stage,
|
|
outputSummaryJson: input.outputSummaryJson,
|
|
error: input.error,
|
|
updatedAt: new Date().toISOString(),
|
|
});
|
|
|
|
if (result.changes === 0) {
|
|
throw new Error(`Memory run not found: ${id}`);
|
|
}
|
|
}
|
|
}
|