ktx/packages/cli/src/context/project/project.ts

157 lines
5.2 KiB
TypeScript
Raw Normal View History

2026-05-10 23:12:26 +02:00
import { promises as fs } from 'node:fs';
import { basename, dirname, join, resolve } from 'node:path';
import { classifyKtxRepoOwnership, GitService, KtxForeignGitRepositoryError } from '../../context/core/git.service.js';
chore(workspace): gate dead-code with knip production mode (#196) * 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.
2026-05-21 15:28:58 +02:00
import { type KtxCoreConfig, type KtxLogger, noopLogger } from '../../context/core/config.js';
2026-05-10 23:51:24 +02:00
import type { KtxProjectConfig } from './config.js';
import { buildDefaultKtxProjectConfig, parseKtxProjectConfig, serializeKtxProjectConfig } from './config.js';
2026-05-10 23:12:26 +02:00
import { LocalGitFileStore } from './local-git-file-store.js';
2026-05-10 23:51:24 +02:00
export interface InitKtxProjectOptions {
2026-05-10 23:12:26 +02:00
projectDir: string;
force?: boolean;
authorName?: string;
authorEmail?: string;
2026-05-10 23:51:24 +02:00
logger?: KtxLogger;
2026-05-10 23:12:26 +02:00
}
2026-05-10 23:51:24 +02:00
export interface LoadKtxProjectOptions {
2026-05-10 23:12:26 +02:00
projectDir: string;
authorName?: string;
authorEmail?: string;
2026-05-10 23:51:24 +02:00
logger?: KtxLogger;
2026-05-10 23:12:26 +02:00
}
2026-05-10 23:51:24 +02:00
export interface KtxLocalProject {
2026-05-10 23:12:26 +02:00
projectDir: string;
configPath: string;
2026-05-10 23:51:24 +02:00
config: KtxProjectConfig;
coreConfig: KtxCoreConfig;
2026-05-10 23:12:26 +02:00
git: GitService;
fileStore: LocalGitFileStore;
}
2026-05-10 23:51:24 +02:00
export interface InitKtxProjectResult extends KtxLocalProject {
2026-05-10 23:12:26 +02:00
commitHash: string | null;
}
const TRACKED_SCAFFOLD_FILES: Array<{ path: string; content: string }> = [
2026-05-11 00:31:15 -07:00
{
path: '.ktx/.gitignore',
content: 'cache/\ndb.sqlite\ndb.sqlite-*\ningest-transcripts/\nsecrets/\nsetup/\nagents/\n',
},
2026-05-10 23:51:24 +02:00
{ path: '.ktx/prompts/.gitkeep', content: '' },
{ path: '.ktx/skills/.gitkeep', content: '' },
{ path: 'wiki/global/.gitkeep', content: '' },
2026-05-10 23:12:26 +02:00
{ path: 'semantic-layer/.gitkeep', content: '' },
{ path: 'raw-sources/.gitkeep', content: '' },
];
2026-05-10 23:51:24 +02:00
function createCoreConfig(projectDir: string, authorName: string, authorEmail: string): KtxCoreConfig {
2026-05-10 23:12:26 +02:00
return {
storage: {
configDir: projectDir,
homeDir: dirname(projectDir),
2026-05-10 23:51:24 +02:00
worktreesDir: join(projectDir, '.ktx/worktrees'),
2026-05-10 23:12:26 +02:00
},
git: {
userName: authorName,
userEmail: authorEmail,
2026-05-10 23:51:24 +02:00
bootstrapMessage: 'Initialize ktx project repository',
2026-05-10 23:12:26 +02:00
bootstrapAuthor: authorName,
bootstrapAuthorEmail: authorEmail,
},
};
}
async function fileExists(path: string): Promise<boolean> {
try {
await fs.access(path);
return true;
} catch {
return false;
}
}
async function writeProjectFile(projectDir: string, relativePath: string, content: string): Promise<void> {
const absolutePath = join(projectDir, relativePath);
await fs.mkdir(dirname(absolutePath), { recursive: true });
await fs.writeFile(absolutePath, content, 'utf-8');
}
async function createRuntime(
projectDir: string,
2026-05-10 23:51:24 +02:00
config: KtxProjectConfig,
2026-05-10 23:12:26 +02:00
authorName: string,
authorEmail: string,
2026-05-10 23:51:24 +02:00
logger: KtxLogger,
): Promise<KtxLocalProject> {
2026-05-10 23:12:26 +02:00
const coreConfig = createCoreConfig(projectDir, authorName, authorEmail);
const git = new GitService(coreConfig, logger);
await git.onModuleInit();
return {
projectDir,
2026-05-10 23:51:24 +02:00
configPath: join(projectDir, 'ktx.yaml'),
2026-05-10 23:12:26 +02:00
config,
coreConfig,
git,
fileStore: new LocalGitFileStore({ rootDir: projectDir, git }),
};
}
2026-05-10 23:51:24 +02:00
export async function initKtxProject(options: InitKtxProjectOptions): Promise<InitKtxProjectResult> {
2026-05-10 23:12:26 +02:00
const projectDir = resolve(options.projectDir);
const projectName = basename(projectDir) || 'ktx-project';
2026-05-10 23:51:24 +02:00
const authorName = options.authorName ?? 'ktx';
const authorEmail = options.authorEmail ?? 'ktx@example.com';
2026-05-10 23:12:26 +02:00
const logger = options.logger ?? noopLogger;
2026-05-10 23:51:24 +02:00
const configPath = join(projectDir, 'ktx.yaml');
2026-05-10 23:12:26 +02:00
await fs.mkdir(projectDir, { recursive: true });
if (!options.force && (await fileExists(configPath))) {
2026-05-10 23:51:24 +02:00
throw new Error(`Project already contains ktx.yaml: ${configPath}`);
2026-05-10 23:12:26 +02:00
}
// Must run before ktx.yaml is written: once that file exists the directory
// classifies as ktx-managed, so a foreign repo would be silently adopted.
if ((await classifyKtxRepoOwnership(projectDir)) === 'foreign') {
throw new KtxForeignGitRepositoryError(projectDir);
}
const config = buildDefaultKtxProjectConfig();
2026-05-10 23:12:26 +02:00
// ktx.yaml (the ownership signal) is written before git init, so an
// interrupted init can never leave a bare `.git` without it — residue that
// would classify as a foreign repo and be unrecoverable.
2026-05-10 23:51:24 +02:00
await fs.mkdir(join(projectDir, '.ktx/cache'), { recursive: true });
2026-05-10 23:12:26 +02:00
for (const file of TRACKED_SCAFFOLD_FILES) {
await writeProjectFile(projectDir, file.path, file.content);
}
await writeProjectFile(projectDir, 'ktx.yaml', serializeKtxProjectConfig(config));
const runtime = await createRuntime(projectDir, config, authorName, authorEmail, logger);
2026-05-10 23:12:26 +02:00
const commit = await runtime.git.commitFiles(
2026-05-10 23:51:24 +02:00
['ktx.yaml', ...TRACKED_SCAFFOLD_FILES.map((file) => file.path)],
`Initialize ktx project: ${projectName}`,
2026-05-10 23:12:26 +02:00
authorName,
authorEmail,
);
return {
...runtime,
commitHash: commit.commitHash,
};
}
2026-05-10 23:51:24 +02:00
export async function loadKtxProject(options: LoadKtxProjectOptions): Promise<KtxLocalProject> {
2026-05-10 23:12:26 +02:00
const projectDir = resolve(options.projectDir);
2026-05-10 23:51:24 +02:00
const authorName = options.authorName ?? 'ktx';
const authorEmail = options.authorEmail ?? 'ktx@example.com';
2026-05-10 23:12:26 +02:00
const logger = options.logger ?? noopLogger;
2026-05-10 23:51:24 +02:00
const configPath = join(projectDir, 'ktx.yaml');
2026-05-10 23:12:26 +02:00
const raw = await fs.readFile(configPath, 'utf-8');
2026-05-10 23:51:24 +02:00
const config = parseKtxProjectConfig(raw);
2026-05-10 23:12:26 +02:00
return createRuntime(projectDir, config, authorName, authorEmail, logger);
}