ktx/packages/cli/src/context/llm/ai-sdk-runtime.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

165 lines
6 KiB
TypeScript

import { KtxMessageBuilder, splitKtxSystemMessages } from '../../llm/message-builder.js';
import type { KtxLlmProvider } from '../../llm/types.js';
import { generateText, Output, stepCountIs, type FlexibleSchema, type TelemetrySettings, type ToolSet } from 'ai';
import type { z } from 'zod';
import { noopLogger, type KtxLogger } from '../../context/core/config.js';
import { summarizeKtxLlmDebugRequest, type KtxLlmDebugRequestRecorder } from './debug-request-recorder.js';
import { createAiSdkToolSet } from './runtime-tools.js';
import type {
KtxGenerateObjectInput,
KtxGenerateTextInput,
KtxLlmRuntimePort,
RunLoopParams,
RunLoopResult,
} from './runtime-port.js';
interface AgentTelemetryPort {
createTelemetry(tags: Record<string, string>): TelemetrySettings;
}
export interface AiSdkKtxLlmRuntimeDeps {
llmProvider: KtxLlmProvider;
telemetry?: AgentTelemetryPort;
logger?: KtxLogger;
debugRequestRecorder?: KtxLlmDebugRequestRecorder;
}
function hasTools(tools: Record<string, unknown>): boolean {
return Object.keys(tools).length > 0;
}
export class AiSdkKtxLlmRuntime implements KtxLlmRuntimePort {
private readonly logger: KtxLogger;
constructor(private readonly deps: AiSdkKtxLlmRuntimeDeps) {
this.logger = deps.logger ?? noopLogger;
}
async generateText(input: KtxGenerateTextInput): Promise<string> {
const model = this.deps.llmProvider.getModel(input.role);
if ((model as { provider?: string }).provider === 'deterministic') {
return `Deterministic description for ${input.prompt.slice(0, 64).trim() || 'data source'}`;
}
const tools = createAiSdkToolSet(input.tools ?? {});
const built = new KtxMessageBuilder(this.deps.llmProvider).wrapSimple({
system: input.system,
messages: [{ role: 'user', content: input.prompt }],
tools,
model,
});
const split = splitKtxSystemMessages(built.messages);
const result = await generateText({
model,
temperature: input.temperature ?? 0,
...(split.system ? { system: split.system } : {}),
messages: split.messages,
tools: built.tools as ToolSet,
...(hasTools(tools)
? {
experimental_repairToolCall: this.deps.llmProvider.repairToolCallHandler({
source: `ktx-${input.role}`,
}),
}
: {}),
});
if (typeof result.text !== 'string') {
throw new Error('KTX LLM text generation returned no text');
}
return result.text;
}
async generateObject<TOutput, TSchema extends z.ZodType<TOutput>>(
input: KtxGenerateObjectInput<TOutput, TSchema>,
): Promise<TOutput> {
const model = this.deps.llmProvider.getModel(input.role);
const tools = createAiSdkToolSet(input.tools ?? {});
const built = new KtxMessageBuilder(this.deps.llmProvider).wrapSimple({
system: input.system,
messages: [{ role: 'user', content: input.prompt }],
tools,
model,
});
const split = splitKtxSystemMessages(built.messages);
const result = await generateText({
model,
temperature: input.temperature ?? 0,
...(split.system ? { system: split.system } : {}),
messages: split.messages,
tools: built.tools as ToolSet,
...(hasTools(tools)
? {
experimental_repairToolCall: this.deps.llmProvider.repairToolCallHandler({
source: `ktx-${input.role}`,
}),
}
: {}),
output: Output.object({ schema: input.schema as unknown as FlexibleSchema<TOutput> }),
});
if (result.output == null) {
throw new Error('KTX LLM object generation returned no output');
}
return result.output as TOutput;
}
async runAgentLoop(params: RunLoopParams): Promise<RunLoopResult> {
let stepIndex = 0;
try {
const model = this.deps.llmProvider.getModel(params.modelRole);
const tools = createAiSdkToolSet(params.toolSet);
const builder = new KtxMessageBuilder(this.deps.llmProvider);
const built = builder.wrapSimple({
system: params.systemPrompt,
messages: [{ role: 'user', content: params.userPrompt }],
tools,
model,
});
const promptMessages = splitKtxSystemMessages(built.messages);
await this.deps.debugRequestRecorder?.record(
summarizeKtxLlmDebugRequest({
operationName: params.telemetryTags.operationName ?? 'ktx-agent-runner',
source: params.telemetryTags.source,
jobId: params.telemetryTags.jobId,
unitKey: params.telemetryTags.unitKey,
modelRole: params.modelRole,
modelId: (model as { modelId?: string }).modelId ?? params.modelRole,
messages: built.messages,
tools: built.tools as Record<string, { providerOptions?: unknown }>,
}),
);
await generateText({
model,
temperature: 0,
stopWhen: stepCountIs(params.stepBudget),
experimental_telemetry: this.deps.telemetry?.createTelemetry(params.telemetryTags) ?? this.deps.llmProvider.telemetryConfig(),
experimental_repairToolCall: this.deps.llmProvider.repairToolCallHandler({
source: params.telemetryTags.operationName ?? 'ktx-agent-runner',
}),
...(promptMessages.system ? { system: promptMessages.system } : {}),
messages: promptMessages.messages,
tools: built.tools as ToolSet,
onStepFinish: async () => {
stepIndex += 1;
if (!params.onStepFinish) {
return;
}
try {
await params.onStepFinish({ stepIndex, stepBudget: params.stepBudget });
} catch (err) {
this.logger.warn(
`[agent-runner] onStepFinish callback threw; ignoring: ${
err instanceof Error ? err.message : String(err)
}`,
);
}
},
});
return { stopReason: 'natural' };
} catch (error) {
const err = error instanceof Error ? error : new Error(String(error));
this.logger.warn(`[agent-runner] loop failed: ${err.message}`);
return { stopReason: 'error', error: err };
}
}
}