ktx/packages/cli/src/context/tools/base-tool.ts
Andrey Avtomonov 2366b00301
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

193 lines
5.9 KiB
TypeScript

import { tool } from 'ai';
import { z, type ZodType } from 'zod';
import { noopLogger, type KtxLogger } from '../../context/core/config.js';
import type { KtxRuntimeToolDescriptor } from '../llm/runtime-port.js';
import { normalizeKtxRuntimeToolOutput } from '../llm/runtime-tools.js';
import type { IngestToolMetadata, ToolSession } from './tool-session.js';
export interface ToolOutput<T = unknown> {
markdown: string;
structured: T;
}
interface ToolTimingTrackerPort {
recordToolExecutionStart(messageId: string, toolName: string, toolCallId: string): void;
recordToolExecutionEnd(messageId: string, toolName: string, toolCallId: string, state: string): void;
}
interface ToolProgressRelayPort {
emit(event: unknown): void;
}
type ChatSource =
| 'RESEARCH'
| 'DASHBOARD'
| 'WIDGET_CONFIG'
| 'EVALUATION'
| 'METRIC_WORKSHOP'
| 'INPUT_CONFIG'
| 'SCHEDULED_RESEARCH'
| 'DASHBOARD_GENERATION';
export interface ToolContext {
sourceId: string;
messageId: string;
userId: string;
userRoles?: string[];
authToken?: string;
currentUserMessage?: string;
toolCallId?: string;
toolCallHistory?: string[];
timingTracker?: ToolTimingTrackerPort;
source?: ChatSource;
dashboardId?: string;
methodologyEntries?: MethodologyEntry[];
progressRelay?: ToolProgressRelayPort;
connectionId?: string;
ingest?: IngestToolMetadata;
/**
* Per-session state (ingest WU, memory-agent post-turn). When present, SL/wiki
* tools use session-scoped services and emit touched-set entries instead of
* writing to shared indexes immediately. Non-session callers leave this unset.
*/
session?: ToolSession;
currentDefinition?: {
sql: string;
measures: unknown[];
dimensions: unknown[];
parameters: unknown[];
segments: unknown[];
name?: string;
description?: string;
};
}
interface MethodologyEntry {
key: string;
toolName: string;
label: string;
args: Record<string, unknown>;
result?: unknown;
}
/**
* SECURITY: All tools require authentication. userId must always be provided in ToolContext.
*/
export abstract class BaseTool<TInput extends ZodType = ZodType> {
protected readonly logger: KtxLogger;
abstract readonly name: string;
constructor(logger: KtxLogger = noopLogger) {
this.logger = logger;
}
abstract get description(): string;
abstract get inputSchema(): TInput;
abstract call(input: z.infer<TInput>, context: ToolContext): Promise<any>;
getParametersSchema(): {
type: 'object';
properties: Record<string, any>;
required?: string[];
} {
const jsonSchema = z.toJSONSchema(this.inputSchema, {
target: 'draft-7',
});
return jsonSchema as any;
}
toAnthropicFormat(): {
name: string;
description: string;
input_schema: {
type: 'object';
properties: Record<string, any>;
required?: string[];
};
} {
return {
name: this.name,
description: this.description,
input_schema: this.getParametersSchema(),
};
}
toAiSdkTool(context: ToolContext): any {
const toolName = this.name;
const logger = this.logger;
return tool({
description: this.description,
inputSchema: this.inputSchema,
execute: async (params, { toolCallId }) => {
// Create context copy with current toolCallId (safe for parallel execution)
const callContext = { ...context, toolCallId };
// Record tool execution start (input generation has already been tracked via onChunk)
if (callContext.timingTracker && toolCallId) {
callContext.timingTracker.recordToolExecutionStart(callContext.messageId, toolName, toolCallId);
}
let state = 'completed';
try {
if (!callContext.userId) {
throw new Error('Authentication required: userId must be provided in ToolContext');
}
const parsedInput = this.parseInput(params as Record<string, any>);
const result = await this.call(parsedInput, callContext);
return result;
} catch (error) {
state = 'error';
this.logger.error(
`Tool ${this.name} execution failed: ${error instanceof Error ? error.message : String(error)}`,
);
throw error;
} finally {
// Record tool execution end
if (callContext.timingTracker && toolCallId) {
callContext.timingTracker.recordToolExecutionEnd(callContext.messageId, toolName, toolCallId, state);
}
}
},
// Send only markdown to the LLM; tool callers still receive the structured output.
toModelOutput: ({ output }) => {
if (output && typeof output === 'object' && 'markdown' in output) {
return { type: 'content', value: [{ type: 'text', text: output.markdown as string }] };
}
if (typeof output !== 'string') {
logger.warn(`Tool ${toolName} returned unexpected output type: ${typeof output}. Coercing to string.`);
}
return { type: 'content', value: [{ type: 'text', text: String(output) }] };
},
});
}
toRuntimeTool(context: ToolContext): KtxRuntimeToolDescriptor {
const toolName = this.name;
return {
name: toolName,
description: this.description,
inputSchema: this.inputSchema as unknown as KtxRuntimeToolDescriptor['inputSchema'],
execute: async (params) => {
const callContext = { ...context };
if (!callContext.userId) {
throw new Error('Authentication required: userId must be provided in ToolContext');
}
const parsedInput = this.parseInput(params as Record<string, any>);
return normalizeKtxRuntimeToolOutput(await this.call(parsedInput, callContext));
},
};
}
parseInput(input: Record<string, any>): z.infer<TInput> {
return this.inputSchema.parse(input);
}
protected getCurrentUserQuery(context: ToolContext): string | null {
return context.currentUserMessage ?? null;
}
}