mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +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.
178 lines
6.4 KiB
TypeScript
178 lines
6.4 KiB
TypeScript
import type { MemoryFlowEvent, MemoryFlowReplayInput } from './context/ingest/memory-flow/types.js';
|
|
|
|
const DEFAULT_INPUT_TOKENS_PER_STEP = 4500;
|
|
const DEFAULT_OUTPUT_TOKENS_PER_STEP = 700;
|
|
const DEFAULT_INPUT_PRICE_PER_MTOK_USD = 3;
|
|
const DEFAULT_OUTPUT_PRICE_PER_MTOK_USD = 15;
|
|
|
|
interface DemoMetricsTuning {
|
|
inputTokensPerStep?: number;
|
|
outputTokensPerStep?: number;
|
|
inputPricePerMTokUsd?: number;
|
|
outputPricePerMTokUsd?: number;
|
|
}
|
|
|
|
interface DemoMetricsSnapshot {
|
|
elapsedMs: number;
|
|
etaMs: number | null;
|
|
agentSteps: number;
|
|
agentStepBudget: number;
|
|
toolCalls: number;
|
|
workUnitsStarted: number;
|
|
workUnitsFinished: number;
|
|
workUnitsTotal: number;
|
|
estimatedInputTokens: number;
|
|
estimatedOutputTokens: number;
|
|
estimatedTokens: number;
|
|
estimatedCostUsd: number;
|
|
tokensPerSec: number;
|
|
status: MemoryFlowReplayInput['status'];
|
|
isCostEstimated: boolean;
|
|
}
|
|
|
|
function eventsOf<T extends MemoryFlowEvent['type']>(
|
|
events: MemoryFlowEvent[],
|
|
type: T,
|
|
): Array<Extract<MemoryFlowEvent, { type: T }>> {
|
|
return events.filter((event): event is Extract<MemoryFlowEvent, { type: T }> => event.type === type);
|
|
}
|
|
|
|
function maxAgentStep(events: MemoryFlowEvent[]): { step: number; budget: number } {
|
|
const steps = eventsOf(events, 'work_unit_step');
|
|
const started = eventsOf(events, 'work_unit_started');
|
|
const stepIndex = steps.reduce((max, event) => Math.max(max, event.stepIndex), 0);
|
|
const stepBudget = Math.max(
|
|
0,
|
|
...steps.map((event) => event.stepBudget),
|
|
...started.map((event) => event.stepBudget),
|
|
);
|
|
return { step: stepIndex, budget: stepBudget };
|
|
}
|
|
|
|
function totalToolCalls(input: MemoryFlowReplayInput): number {
|
|
return input.details.transcripts.reduce((total, transcript) => total + transcript.toolCallCount, 0);
|
|
}
|
|
|
|
function workUnitProgress(input: MemoryFlowReplayInput): { started: number; finished: number; total: number } {
|
|
const started = eventsOf(input.events, 'work_unit_started').length;
|
|
const finished = eventsOf(input.events, 'work_unit_finished').length;
|
|
const planned = input.plannedWorkUnits.length;
|
|
const planEvent = eventsOf(input.events, 'chunks_planned').at(-1);
|
|
const total = planned || planEvent?.workUnitCount || started || finished || 0;
|
|
return { started, finished, total };
|
|
}
|
|
|
|
function elapsedMsFromEvents(events: MemoryFlowEvent[], nowMs: number): number {
|
|
const stamped = events
|
|
.map((event) => (event.emittedAt ? Date.parse(event.emittedAt) : Number.NaN))
|
|
.filter((value) => Number.isFinite(value));
|
|
if (stamped.length === 0) return 0;
|
|
const first = Math.min(...stamped);
|
|
return Math.max(0, nowMs - first);
|
|
}
|
|
|
|
function estimateEtaMs(
|
|
elapsedMs: number,
|
|
finished: number,
|
|
total: number,
|
|
status: MemoryFlowReplayInput['status'],
|
|
): number | null {
|
|
if (status !== 'running') return 0;
|
|
if (total === 0 || finished === 0 || elapsedMs === 0) return null;
|
|
const perUnit = elapsedMs / finished;
|
|
const remaining = Math.max(0, total - finished);
|
|
return Math.round(perUnit * remaining);
|
|
}
|
|
|
|
export function buildDemoMetrics(
|
|
input: MemoryFlowReplayInput,
|
|
options: { now?: () => number; tuning?: DemoMetricsTuning } = {},
|
|
): DemoMetricsSnapshot {
|
|
const tuning = options.tuning ?? {};
|
|
const inputTokensPerStep = tuning.inputTokensPerStep ?? DEFAULT_INPUT_TOKENS_PER_STEP;
|
|
const outputTokensPerStep = tuning.outputTokensPerStep ?? DEFAULT_OUTPUT_TOKENS_PER_STEP;
|
|
const inputPrice = tuning.inputPricePerMTokUsd ?? DEFAULT_INPUT_PRICE_PER_MTOK_USD;
|
|
const outputPrice = tuning.outputPricePerMTokUsd ?? DEFAULT_OUTPUT_PRICE_PER_MTOK_USD;
|
|
const nowMs = (options.now ?? Date.now)();
|
|
const elapsedMs = elapsedMsFromEvents(input.events, nowMs);
|
|
|
|
const { step, budget } = maxAgentStep(input.events);
|
|
const toolCalls = totalToolCalls(input);
|
|
const progress = workUnitProgress(input);
|
|
const finishedCount = eventsOf(input.events, 'work_unit_finished').length;
|
|
const stepDriver = Math.max(step, toolCalls, finishedCount * 4);
|
|
|
|
const inputTokens = stepDriver * inputTokensPerStep;
|
|
const outputTokens = stepDriver * outputTokensPerStep;
|
|
const totalTokens = inputTokens + outputTokens;
|
|
const cost = (inputTokens / 1_000_000) * inputPrice + (outputTokens / 1_000_000) * outputPrice;
|
|
|
|
const elapsedSec = elapsedMs / 1000;
|
|
const tokensPerSec = elapsedSec > 0 ? totalTokens / elapsedSec : 0;
|
|
|
|
return {
|
|
elapsedMs,
|
|
etaMs: estimateEtaMs(elapsedMs, progress.finished, progress.total, input.status),
|
|
agentSteps: step,
|
|
agentStepBudget: budget,
|
|
toolCalls,
|
|
workUnitsStarted: progress.started,
|
|
workUnitsFinished: progress.finished,
|
|
workUnitsTotal: progress.total,
|
|
estimatedInputTokens: inputTokens,
|
|
estimatedOutputTokens: outputTokens,
|
|
estimatedTokens: totalTokens,
|
|
estimatedCostUsd: cost,
|
|
tokensPerSec,
|
|
status: input.status,
|
|
isCostEstimated: true,
|
|
};
|
|
}
|
|
|
|
export function formatDuration(ms: number): string {
|
|
if (!Number.isFinite(ms) || ms < 0) return '--';
|
|
const totalSec = Math.round(ms / 1000);
|
|
if (totalSec < 60) return `${totalSec}s`;
|
|
const min = Math.floor(totalSec / 60);
|
|
const sec = totalSec % 60;
|
|
if (min < 60) return `${min}m${sec.toString().padStart(2, '0')}s`;
|
|
const hr = Math.floor(min / 60);
|
|
return `${hr}h${(min % 60).toString().padStart(2, '0')}m`;
|
|
}
|
|
|
|
/** @internal */
|
|
export function formatEta(ms: number | null, status: MemoryFlowReplayInput['status']): string {
|
|
if (status !== 'running') return 'done';
|
|
if (ms === null) return 'estimating...';
|
|
return formatDuration(ms);
|
|
}
|
|
|
|
export function formatCost(usd: number): string {
|
|
if (!Number.isFinite(usd) || usd <= 0) return '$0.000';
|
|
if (usd < 0.001) return '<$0.001';
|
|
if (usd < 1) return `$${usd.toFixed(3)}`;
|
|
return `$${usd.toFixed(2)}`;
|
|
}
|
|
|
|
/** @internal */
|
|
export function formatTokens(n: number): string {
|
|
if (!Number.isFinite(n) || n <= 0) return '0';
|
|
if (n < 1000) return `${Math.round(n)}`;
|
|
if (n < 1_000_000) return `${(n / 1000).toFixed(1)}K`;
|
|
return `${(n / 1_000_000).toFixed(2)}M`;
|
|
}
|
|
|
|
/** @internal */
|
|
export function formatTokensPerSec(n: number): string {
|
|
if (!Number.isFinite(n) || n <= 0) return '0/s';
|
|
if (n < 1000) return `${Math.round(n)}/s`;
|
|
return `${(n / 1000).toFixed(1)}K/s`;
|
|
}
|
|
|
|
const PROGRESS_BAR_WIDTH = 12;
|
|
/** @internal */
|
|
export function progressBar(ratio: number, width: number = PROGRESS_BAR_WIDTH): string {
|
|
const clamped = Math.max(0, Math.min(1, ratio));
|
|
const filled = Math.round(clamped * width);
|
|
return `${'#'.repeat(filled)}${'-'.repeat(Math.max(0, width - filled))}`;
|
|
}
|