ktx/packages/cli/test/context/llm/local-config.test.ts

271 lines
9 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { describe, expect, it, vi } from 'vitest';
import {
2026-05-10 23:51:24 +02:00
buildDefaultKtxProjectConfig,
type KtxProjectEmbeddingConfig,
type KtxProjectLlmConfig,
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
} from '../../../src/context/project/config.js';
2026-05-10 23:12:26 +02:00
import {
2026-05-10 23:51:24 +02:00
createLocalKtxEmbeddingProviderFromConfig,
createLocalKtxLlmProviderFromConfig,
feat(cli): add ingest LLM rate-limit governor with paced retries (#261) * feat(cli): add ingest rate limit governor * feat(cli): wire ingest rate-limit config * feat(cli): report provider rate-limit signals * feat(cli): show ingest rate-limit waits * fix(cli): complete rate-limit event coverage * fix(cli): abort ingest provider calls cleanly * fix(cli): propagate ingest cancellation * fix(cli): reject pre-aborted ingest rate-limit waits * fix(cli): honor Claude rate-limit reset waits * fix(cli): retry thrown Codex rate-limit failures * fix(cli): type Claude rate-limit result details * fix(cli): emit ingest rate-limit countdowns from rejected signals * fix(cli): report ai sdk rate-limit header utilization * fix(cli): gate LLM rate-limit retries on the governor budget The AI SDK and Codex runtimes retried 429 / opaque rate-limit failures up to 6-7 times with no backoff when constructed without a RateLimitGovernor (scan, memory, setup) or with pacing disabled, ignoring Retry-After and worsening the limit. The outer retry loop only cooperates with the governor's pause, so without active pacing there is no backoff to apply. Route the retry bound through a single source: RateLimitGovernor .maxRetryAttempts(), which returns retry.maxAttempts when enabled and 1 (no outer retry) when absent or disabled. All three runtimes (ai-sdk, codex, claude-code) now use it, so ingest.rateLimit.retry.maxAttempts genuinely controls attempts and the hard-coded 6 (plus Codex's off-by-one extra attempt) is gone. Backend-native retry (e.g. the AI SDK's maxRetries) still handles transient 429s. Also correct the ktx.yaml docs for maxWaitMs (caps each wait, not the whole run) and maxAttempts, and sync uv.lock ktx-sl/ktx-daemon to 0.9.0.
2026-06-05 12:10:27 +02:00
createLocalKtxLlmRuntimeFromConfig,
2026-05-10 23:51:24 +02:00
resolveLocalKtxEmbeddingConfig,
resolveLocalKtxLlmConfig,
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
} from '../../../src/context/llm/local-config.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
describe('local KTX LLM config', () => {
it('resolves env and file references into a KtxLlmConfig', () => {
const config: KtxProjectLlmConfig = {
2026-05-10 23:12:26 +02:00
provider: {
backend: 'gateway',
gateway: { api_key: 'env:AI_GATEWAY_API_KEY', base_url: 'https://gateway.example/v1' }, // pragma: allowlist secret
},
2026-05-10 23:51:24 +02:00
models: { default: 'env:KTX_MODEL', triage: 'anthropic/claude-haiku-4-5' },
2026-05-10 23:12:26 +02:00
promptCaching: { enabled: false },
};
expect(
2026-05-10 23:51:24 +02:00
resolveLocalKtxLlmConfig(config, {
2026-05-10 23:12:26 +02:00
AI_GATEWAY_API_KEY: 'gateway-key', // pragma: allowlist secret
2026-05-10 23:51:24 +02:00
KTX_MODEL: 'anthropic/claude-sonnet-4-6',
2026-05-10 23:12:26 +02:00
}),
).toEqual({
backend: 'gateway',
gateway: { apiKey: 'gateway-key', baseURL: 'https://gateway.example/v1' }, // pragma: allowlist secret
modelSlots: { default: 'anthropic/claude-sonnet-4-6', triage: 'anthropic/claude-haiku-4-5' },
promptCaching: { enabled: false },
});
});
it('resolves Vertex AI env references into a KtxLlmConfig', () => {
const config: KtxProjectLlmConfig = {
provider: {
backend: 'vertex',
vertex: { project: 'env:GOOGLE_VERTEX_PROJECT', location: 'env:GOOGLE_VERTEX_LOCATION' },
},
models: { default: 'env:KTX_MODEL' },
promptCaching: { enabled: true, vertexFallbackTo5m: true },
};
expect(
resolveLocalKtxLlmConfig(config, {
GOOGLE_VERTEX_PROJECT: 'local-gcp-project',
GOOGLE_VERTEX_LOCATION: 'us-east5',
KTX_MODEL: 'claude-sonnet-4-6',
}),
).toEqual({
backend: 'vertex',
vertex: { project: 'local-gcp-project', location: 'us-east5' },
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: { enabled: true, vertexFallbackTo5m: true },
});
});
it('ignores inactive Vertex AI references for non-Vertex backends', () => {
const config: KtxProjectLlmConfig = {
provider: {
backend: 'anthropic',
anthropic: { api_key: 'env:ANTHROPIC_API_KEY' }, // pragma: allowlist secret
vertex: { location: 'env:MISSING_VERTEX_LOCATION' },
},
models: { default: 'claude-sonnet-4-6' },
};
expect(
resolveLocalKtxLlmConfig(config, {
ANTHROPIC_API_KEY: 'sk-ant-test', // pragma: allowlist secret
}),
).toEqual({
backend: 'anthropic',
anthropic: { apiKey: 'sk-ant-test' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: undefined,
});
});
2026-05-10 23:12:26 +02:00
it('returns null when the local LLM backend is disabled', () => {
expect(
2026-05-10 23:51:24 +02:00
createLocalKtxLlmProviderFromConfig({
2026-05-10 23:12:26 +02:00
provider: { backend: 'none' },
models: {},
}),
).toBeNull();
});
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
it('constructs providers through LLM modules', () => {
2026-05-10 23:51:24 +02:00
const createKtxLlmProvider = vi.fn(() => ({ getModel: vi.fn() }) as never);
const result = createLocalKtxLlmProviderFromConfig(
2026-05-10 23:12:26 +02:00
{
provider: {
backend: 'anthropic',
anthropic: { api_key: 'env:ANTHROPIC_API_KEY' }, // pragma: allowlist secret
},
models: { default: 'claude-sonnet-4-6' },
},
2026-05-10 23:51:24 +02:00
{ env: { ANTHROPIC_API_KEY: 'sk-ant-test' }, createKtxLlmProvider }, // pragma: allowlist secret
2026-05-10 23:12:26 +02:00
);
expect(result).not.toBeNull();
2026-05-10 23:51:24 +02:00
expect(createKtxLlmProvider).toHaveBeenCalledWith({
2026-05-10 23:12:26 +02:00
backend: 'anthropic',
anthropic: { apiKey: 'sk-ant-test' }, // pragma: allowlist secret
modelSlots: { default: 'claude-sonnet-4-6' },
promptCaching: undefined,
});
});
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
it('inherits enabled prompt caching from LLM modules when local config omits promptCaching', () => {
2026-05-10 23:51:24 +02:00
const provider = createLocalKtxLlmProviderFromConfig({
2026-05-10 23:12:26 +02:00
provider: {
backend: 'gateway',
gateway: { base_url: 'https://gateway.example/v1' },
},
models: { default: 'anthropic/claude-sonnet-4-6' },
});
expect(provider?.promptCachingConfig()).toMatchObject({
enabled: true,
systemTtl: '1h',
toolsTtl: '1h',
historyTtl: '5m',
vertexFallbackTo5m: false,
});
});
feat(cli): add ingest LLM rate-limit governor with paced retries (#261) * feat(cli): add ingest rate limit governor * feat(cli): wire ingest rate-limit config * feat(cli): report provider rate-limit signals * feat(cli): show ingest rate-limit waits * fix(cli): complete rate-limit event coverage * fix(cli): abort ingest provider calls cleanly * fix(cli): propagate ingest cancellation * fix(cli): reject pre-aborted ingest rate-limit waits * fix(cli): honor Claude rate-limit reset waits * fix(cli): retry thrown Codex rate-limit failures * fix(cli): type Claude rate-limit result details * fix(cli): emit ingest rate-limit countdowns from rejected signals * fix(cli): report ai sdk rate-limit header utilization * fix(cli): gate LLM rate-limit retries on the governor budget The AI SDK and Codex runtimes retried 429 / opaque rate-limit failures up to 6-7 times with no backoff when constructed without a RateLimitGovernor (scan, memory, setup) or with pacing disabled, ignoring Retry-After and worsening the limit. The outer retry loop only cooperates with the governor's pause, so without active pacing there is no backoff to apply. Route the retry bound through a single source: RateLimitGovernor .maxRetryAttempts(), which returns retry.maxAttempts when enabled and 1 (no outer retry) when absent or disabled. All three runtimes (ai-sdk, codex, claude-code) now use it, so ingest.rateLimit.retry.maxAttempts genuinely controls attempts and the hard-coded 6 (plus Codex's off-by-one extra attempt) is gone. Backend-native retry (e.g. the AI SDK's maxRetries) still handles transient 429s. Also correct the ktx.yaml docs for maxWaitMs (caps each wait, not the whole run) and maxAttempts, and sync uv.lock ktx-sl/ktx-daemon to 0.9.0.
2026-06-05 12:10:27 +02:00
it('passes the rate-limit governor into created runtimes', () => {
const rateLimitGovernor = {} as never;
const createClaudeCodeRuntime = vi.fn(() => ({
generateText: vi.fn(),
generateObject: vi.fn(),
runAgentLoop: vi.fn(),
}));
const createCodexRuntime = vi.fn(() => ({
generateText: vi.fn(),
generateObject: vi.fn(),
runAgentLoop: vi.fn(),
}));
const createAiSdkRuntime = vi.fn(() => ({
generateText: vi.fn(),
generateObject: vi.fn(),
runAgentLoop: vi.fn(),
}));
const createKtxLlmProvider = vi.fn(() => ({
getModel: vi.fn(),
getModelByName: vi.fn(),
cacheMarker: vi.fn(),
repairToolCallHandler: vi.fn(),
thinkingProviderOptions: vi.fn(),
telemetryConfig: vi.fn(),
promptCachingConfig: vi.fn(),
activeBackend: vi.fn(() => 'anthropic'),
}));
createLocalKtxLlmRuntimeFromConfig(
{
provider: { backend: 'claude-code' },
models: { default: 'sonnet' },
promptCaching: undefined,
},
{ projectDir: '/tmp/project', env: {}, rateLimitGovernor, createClaudeCodeRuntime },
);
createLocalKtxLlmRuntimeFromConfig(
{
provider: { backend: 'codex' },
models: { default: 'codex' },
promptCaching: undefined,
},
{ projectDir: '/tmp/project', env: {}, rateLimitGovernor, createCodexRuntime },
);
createLocalKtxLlmRuntimeFromConfig(
{
provider: { backend: 'anthropic' },
models: { default: 'claude-sonnet-4-6' },
promptCaching: undefined,
},
{ env: {}, rateLimitGovernor, createAiSdkRuntime, createKtxLlmProvider: createKtxLlmProvider as never },
);
expect(createClaudeCodeRuntime).toHaveBeenCalledWith(expect.objectContaining({ rateLimitGovernor }));
expect(createCodexRuntime).toHaveBeenCalledWith(expect.objectContaining({ rateLimitGovernor }));
expect(createAiSdkRuntime).toHaveBeenCalledWith(expect.objectContaining({ rateLimitGovernor }));
});
2026-05-10 23:12:26 +02:00
});
2026-05-10 23:51:24 +02:00
describe('local KTX embedding config', () => {
2026-05-10 23:12:26 +02:00
it('resolves sentence-transformers config', () => {
2026-05-10 23:51:24 +02:00
const config: KtxProjectEmbeddingConfig = {
2026-05-10 23:12:26 +02:00
backend: 'sentence-transformers',
model: 'all-MiniLM-L6-v2',
dimensions: 384,
sentenceTransformers: { base_url: 'http://localhost:18081', pathPrefix: '' },
batchSize: 16,
};
2026-05-10 23:51:24 +02:00
expect(resolveLocalKtxEmbeddingConfig(config, {})).toEqual({
2026-05-10 23:12:26 +02:00
backend: 'sentence-transformers',
model: 'all-MiniLM-L6-v2',
dimensions: 384,
sentenceTransformers: { baseURL: 'http://localhost:18081', pathPrefix: '' },
batchSize: 16,
});
});
it('returns null when sentence-transformers has no base_url (managed daemon delegation)', () => {
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
const config: KtxProjectEmbeddingConfig = {
backend: 'sentence-transformers',
model: 'all-MiniLM-L6-v2',
dimensions: 384,
sentenceTransformers: {
base_url: '',
feat: npm-managed Python runtime for @kaelio/ktx (#7) * docs: add npm managed python runtime design * build: add bundled python runtime wheel builder * build: make local embedding dependencies optional * build: bundle python runtime wheel in cli artifacts * build: track bundled python runtime release artifact * test: verify bundled python runtime wheel * docs: add plan for bundled python runtime wheel * test: cover managed python runtime lifecycle * feat: add managed python runtime installer * feat: add runtime command runner * feat: expose runtime management commands * test: verify managed python runtime commands * docs: add plan for managed python runtime installer * feat: add managed python command helper * feat: use managed runtime for sl query compute * feat: route sl query managed runtime policy * docs: add plan for managed runtime sl query integration * feat: add managed runtime daemon metadata * feat: manage python daemon lifecycle * feat: add runtime daemon start stop commands * fix: verify managed runtime daemon lifecycle * docs: add plan for managed runtime daemon lifecycle * feat: add managed local embeddings config marker * feat: add managed local embeddings daemon helper * feat: use managed runtime for local embedding setup * feat: pass managed runtime policy through setup * docs: add plan for managed local embeddings runtime * feat: read CLI package metadata dynamically * feat: assemble public kaelio ktx npm package * feat: release one public kaelio ktx npm artifact * test: cover public kaelio ktx package invocations * chore: verify public kaelio ktx package artifacts * docs: add plan for public kaelio ktx npm package * test: verify managed runtime in public package smoke * test: finalize managed runtime release smoke * docs: add plan for managed runtime release smoke * test: specify local embeddings release smoke * feat: add local embeddings runtime smoke * chore: register local embeddings smoke * fix: verify local embeddings smoke * fix: restore artifact smoke python env helper * docs: add plan for managed local embeddings release smoke * refactor: share managed runtime install policy parsing * feat: use managed runtime for agent semantic queries * feat: use managed runtime for MCP semantic compute * docs: add plan for managed agent and MCP semantic runtime * feat(cli): add managed daemon HTTP helpers * feat(cli): route local adapters through managed daemon * feat(cli): use managed daemon for ingest helpers * feat(cli): pass managed daemon options to scan * feat(context): pass MCP ingest pull config options * feat(cli): pass managed daemon options to serve ingest * test: verify managed local ingest daemon runtime * docs: add plan for managed local ingest daemon runtime * docs: align managed runtime examples * docs: add plan for managed runtime docs cleanup * test: cover published package runtime smoke commands * test: validate published package smoke outputs * docs: add plan for published package runtime smoke * build: stamp public npm package version * release: add npm public release policy * release: add guarded npm publish script * release: document public npm release handoff * docs: add plan for public npm release handoff * test: cover managed runtime prune in package smoke * docs: document managed runtime prune * docs: add plan for managed runtime prune smoke and docs * chore: encode uv runtime prerequisite policy * fix: clarify missing uv runtime error * docs: document uv runtime prerequisite * docs: add plan for uv runtime prerequisite contract * refactor: limit release artifacts to public package runtime * chore: align release policy with bundled runtime wheel * docs: describe single public runtime artifact surface * test: verify single public runtime artifact contract * docs: add plan for single public runtime artifact cleanup * fix: align local embeddings smoke with public version * docs: add plan for local embeddings smoke public version * release: soft-launch as @kaelio/ktx@0.1.0-rc.0 on next tag Publish target moves to the pre-release version 0.1.0-rc.0 under the next dist-tag so npm install @kaelio/ktx (which resolves to latest) does not pick up the soft-launch build. Users opt in via @kaelio/ktx@next. * Fix release script boundary checks * Remove PostHog from public package bundle
2026-05-11 15:50:34 +02:00
pathPrefix: '',
},
};
expect(resolveLocalKtxEmbeddingConfig(config, {})).toBeNull();
});
feat(setup): add Claude Desktop target and MCP-first agent setup (#114) * feat(setup): add Claude Desktop target and MCP-first agent setup Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces the CLI-only agent install mode with MCP+analytics (default) and an optional admin CLI skill, renames the research skill to analytics, and lets interactive setup pick project vs global scope when every target supports it. Extracts a shared MCP server factory used by both HTTP and stdio entrypoints. * Add MCP agent client setup support * Polish setup output formatting * Add MCP tool polish design spec Design for slimming the MCP-registered surface from 25 to 11 tools, introducing memory_ingest, applying the per-tool polish kit (annotations, outputSchema, .describe(), in-band error wrapping, union-drift fixes, type-narrowed jsonToolResult), emitting progress notifications on sql_execution + sl_query, and refining the ktx-analytics SKILL.md to match. * Refine MCP tool polish design spec after adversarial review iteration 1 * Refine MCP tool polish design spec after adversarial review iteration 2 * Refine MCP tool polish design spec after adversarial review iteration 3 * refactor(context): rename memory capture service to ingest * feat(mcp): slim research tool surface * refactor(mcp): remove admin ports from server factory * refactor(cli): rename text ingest memory port * docs: update analytics skill for memory ingest * chore: verify mcp surface rename * Add MCP tool polish v1 surface change plan * feat(context): polish mcp tool metadata * fix(context): enforce resolved semantic layer compute sources * feat(context): emit mcp query progress stages * fix(context): keep mcp progress event internal * Add MCP tool polish v1 metadata & progress plan * Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
it('returns null when backend is openai but no apiKey is resolvable from env', () => {
const config: KtxProjectEmbeddingConfig = {
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 1536,
openai: { api_key: 'env:OPENAI_API_KEY' }, // pragma: allowlist secret
};
expect(resolveLocalKtxEmbeddingConfig(config, {})).toBeNull();
});
it('resolves openai embedding config from env', () => {
const config: KtxProjectEmbeddingConfig = {
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 1536,
openai: { api_key: 'env:OPENAI_API_KEY' }, // pragma: allowlist secret
};
expect(
resolveLocalKtxEmbeddingConfig(config, { OPENAI_API_KEY: 'sk-test' }), // pragma: allowlist secret
).toEqual({
backend: 'openai',
model: 'text-embedding-3-small',
dimensions: 1536,
openai: { apiKey: 'sk-test' }, // pragma: allowlist secret
batchSize: undefined,
});
});
it('returns null for the default disabled project embedding config', () => {
2026-05-10 23:51:24 +02:00
const createKtxEmbeddingProvider = vi.fn(() => ({}) as never);
const provider = createLocalKtxEmbeddingProviderFromConfig(
buildDefaultKtxProjectConfig().ingest.embeddings,
2026-05-10 23:51:24 +02:00
{ createKtxEmbeddingProvider },
2026-05-10 23:12:26 +02:00
);
expect(provider).toBeNull();
expect(createKtxEmbeddingProvider).not.toHaveBeenCalled();
2026-05-10 23:12:26 +02:00
});
it('returns null when embeddings are disabled', () => {
2026-05-10 23:51:24 +02:00
expect(createLocalKtxEmbeddingProviderFromConfig({ backend: 'none', dimensions: 8 })).toBeNull();
2026-05-10 23:12:26 +02:00
});
});