2026-05-16 12:06:34 +02:00
|
|
|
import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises';
|
|
|
|
|
import { tmpdir } from 'node:os';
|
|
|
|
|
import { join } from 'node:path';
|
2026-05-10 23:12:26 +02:00
|
|
|
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
|
|
|
|
|
|
|
|
|
// Module-level mock for 'ai' so generateText is a stub. This file is separate from
|
|
|
|
|
// memory-agent.service.spec.ts so the existing pure-helper tests don't load the mock.
|
|
|
|
|
vi.mock('ai', () => ({
|
|
|
|
|
generateText: vi.fn().mockResolvedValue({ text: '', toolCalls: [] }),
|
|
|
|
|
stepCountIs: (n: number) => n,
|
|
|
|
|
tool: (def: unknown) => def,
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
// Imported AFTER vi.mock so the mocked module is used.
|
|
|
|
|
import { generateText } from 'ai';
|
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 { SYSTEM_GIT_AUTHOR } from '../../context/tools/authors.js';
|
2026-05-10 23:12:26 +02:00
|
|
|
import { MemoryAgentService } from './memory-agent.service.js';
|
|
|
|
|
|
|
|
|
|
interface BuiltMocks {
|
|
|
|
|
appSettings: any;
|
|
|
|
|
prompt: any;
|
2026-05-10 20:44:07 -07:00
|
|
|
eventTracker: any;
|
2026-05-10 23:12:26 +02:00
|
|
|
telemetry: any;
|
|
|
|
|
skillsRegistry: any;
|
|
|
|
|
wikiService: any;
|
|
|
|
|
indexRepository: any;
|
|
|
|
|
knowledgeSlRefsRepository: any;
|
|
|
|
|
knowledgeRepository: any;
|
|
|
|
|
embeddingService: any;
|
|
|
|
|
semanticLayerService: any;
|
|
|
|
|
slSearchService: any;
|
|
|
|
|
dataSourcesService: any;
|
|
|
|
|
configService: any;
|
|
|
|
|
gitService: any;
|
|
|
|
|
lockingService: any;
|
|
|
|
|
slSourcesRepository: any;
|
|
|
|
|
sessionWorktreeService: any;
|
|
|
|
|
semanticLayerSourceReconciler: any;
|
|
|
|
|
agentRunner: any;
|
|
|
|
|
slValidator: any;
|
|
|
|
|
toolsetFactory: any;
|
2026-05-12 11:21:37 +02:00
|
|
|
logger: any;
|
2026-05-10 23:12:26 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const buildMocks = (overrides: Partial<BuiltMocks> = {}): BuiltMocks => {
|
|
|
|
|
const scopedConfig = { writeFile: vi.fn(), deleteFile: vi.fn() };
|
|
|
|
|
const scopedGit = { revParseHead: vi.fn().mockResolvedValue('basesha') };
|
|
|
|
|
const sessionWorktree = {
|
|
|
|
|
chatId: 'chat-1',
|
|
|
|
|
workdir: '/tmp/wt/session-chat-1',
|
|
|
|
|
branch: 'session/chat-1',
|
|
|
|
|
baseSha: 'basesha',
|
|
|
|
|
createdAt: new Date(),
|
|
|
|
|
git: scopedGit,
|
|
|
|
|
config: scopedConfig,
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const defaults: BuiltMocks = {
|
|
|
|
|
appSettings: {
|
|
|
|
|
settings: {
|
|
|
|
|
ai: {
|
|
|
|
|
knowledge: { userScopedKnowledgeEnabled: false },
|
|
|
|
|
slValidation: { probeRowCount: 1 },
|
|
|
|
|
},
|
|
|
|
|
llm: { memoryIngestionModel: 'test-model' },
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
prompt: { loadPrompt: vi.fn().mockResolvedValue('base framing') },
|
2026-05-10 20:44:07 -07:00
|
|
|
eventTracker: { trackEvent: vi.fn(), createTelemetryIntegration: vi.fn().mockReturnValue(undefined) },
|
2026-05-10 23:12:26 +02:00
|
|
|
telemetry: {
|
|
|
|
|
isEnabled: () => false,
|
|
|
|
|
appSettingsService: { settings: { telemetry: { recordInputs: false, recordOutputs: false } } },
|
|
|
|
|
systemConfigService: { config: { instance: { name: 'test-instance' } } },
|
|
|
|
|
},
|
|
|
|
|
skillsRegistry: {
|
|
|
|
|
listSkills: vi.fn().mockResolvedValue([]),
|
|
|
|
|
buildSkillsPrompt: vi.fn().mockReturnValue(''),
|
|
|
|
|
getSkill: vi.fn(),
|
|
|
|
|
stripFrontmatter: vi.fn(),
|
|
|
|
|
},
|
|
|
|
|
wikiService: {
|
|
|
|
|
forWorktree: vi.fn().mockReturnThis(),
|
|
|
|
|
readPage: vi.fn(),
|
|
|
|
|
syncSinglePage: vi.fn(),
|
|
|
|
|
deleteFromIndex: vi.fn(),
|
|
|
|
|
},
|
|
|
|
|
indexRepository: { listPagesForUser: vi.fn().mockResolvedValue([]) },
|
|
|
|
|
knowledgeSlRefsRepository: { syncFromWiki: vi.fn().mockResolvedValue({ inserted: 0, deleted: 0 }) },
|
|
|
|
|
knowledgeRepository: {},
|
|
|
|
|
embeddingService: { computeEmbedding: vi.fn() },
|
|
|
|
|
semanticLayerService: {
|
|
|
|
|
forWorktree: vi.fn().mockReturnThis(),
|
fix(context): merge overlay columns onto manifest columns by name (#94)
* fix(context): merge overlay columns onto manifest columns by name
composeOverlay was appending overlay columns to the manifest column list,
producing duplicate entries when dbt/metabase overlays declared a column
just to attach descriptions. The duplicates carried no `type`, so the
pydantic SourceDefinition rejected them at semantic-query time and broke
`ktx sl query` for every overlay-backed measure. Now overlay columns
match base columns by name (case-insensitive): same-name entries merge
onto the manifest (overlay fields win, type/role fall back to the base,
descriptions merge per source key) and only new names append.
* refactor(sl): split overlay columns from column_overrides and enforce TS/Python wire contract
Overlay sources now have two distinct collections: `columns:` for computed
columns (requiring `expr` + `type`) and `column_overrides:` for metadata
patches to inherited manifest columns. Composing or loading an overlay that
mixes the two — or references an unknown column — fails with a typed error.
Introduce `ResolvedSemanticLayerSource` / `resolvedSourceSchema` /
`toResolvedWire` as the strict shape sent to the Python engine, and add a
schema contract test that diffs Zod against the Pydantic JSON schema dumped
by `python -m semantic_layer dump-schema`. `SourceDefinition` is now
`extra="forbid"` on the Python side.
`loadAllSources` surfaces per-file load errors instead of swallowing them,
so validation/query paths can report manifest shard parse failures.
* fix(context): make scan description generation resilient and quiet
A transient sampleTable failure during ingest used to take out every
table in a connection: generateTableDescription returned a hardcoded
'Table not found' string into descriptions.ai, and KtxDescriptionGenerator
was constructed without a logger, so the failure left no trail anywhere.
- sampleTable / sampleColumn calls retry 3x with 200/400/800ms backoff,
honouring KtxScanContext.signal via a new KtxAbortedError.
- On retry exhaustion or missing capability, table generation falls back
to a metadata-only prompt built from column name / native type / comment
/ rawDescriptions. The column path follows the same rule -- call the
LLM when any of samples or rawDescriptions are available; skip only
when both are absent.
- Logger is now threaded from KtxScanContext into the generator. Failures
emit structured KtxScanWarning entries (new description_fallback_used
code, plus existing sampling_failed / enrichment_failed /
connector_capability_missing). ktx scan groups warnings by code so a
batch of identical failures collapses to one summary line plus sample.
- Returns null on failure instead of the 'Table not found' sentinel; the
manifest writer's existing guard already skips empty descriptions, so
schema YAML no longer carries misleading text. SCAN_MANAGED_DESCRIPTION_KEYS
already strips stale 'ai' on merge, so existing YAML clears on next run.
Also suppress AI SDK v6 'system in messages' warning: pull system messages
out of KtxMessageBuilder.wrapSimple's output via a new splitKtxSystemMessages
helper and pass them top-level to generateText (preserves cacheControl
providerOptions on the SystemModelMessage). Agent-runner's local
splitSystemPromptMessages dedupes onto the shared helper.
* test(docs): align examples-docs assertions with revamped docs
PR #103 (setup/guide doc revamp) reworded several CLI examples and
connection labels; the assertions in scripts/examples-docs.test.mjs
still referenced the pre-revamp wording and were failing in CI on main.
Update the regexes to match the post-revamp content:
- drop the `--json` flag from the sl-query example expectation
- move the `Driver:` / `Status: ok` probe to the connection reference,
which is where that output now lives (driver id is lowercase
`postgres`, not the display name `PostgreSQL`)
- drop the obsolete `Install \`uv\`...` troubleshooting line
- accept `<connectionId>` everywhere; the docs no longer use the
hyphenated `<connection-id>` form
- match the `warehouse` connection id used in the quickstart instead of
the `postgres-warehouse` id only used in the README and setup ref
* fix(sl): skip TS/Python schema contract test when uv is unavailable
The TypeScript checks CI job does not install uv or Python, so the
module-level `execFileSync('uv', ...)` in schemas.contract.test.ts threw
ENOENT and failed the suite. Wrap the schema dump in a try/catch and
guard the describe block with `describe.skipIf` so the test skips in
environments without uv. Local dev and any CI job that has uv on PATH
still runs the cross-language contract assertion.
2026-05-15 02:11:04 +02:00
|
|
|
loadAllSources: vi.fn().mockResolvedValue({ sources: [], loadErrors: [] }),
|
2026-05-10 23:12:26 +02:00
|
|
|
readSourceFile: vi.fn(),
|
|
|
|
|
},
|
|
|
|
|
slSearchService: { indexSources: vi.fn(), buildSearchText: vi.fn() },
|
|
|
|
|
dataSourcesService: {
|
|
|
|
|
listEnabledConnections: vi.fn().mockResolvedValue([]),
|
|
|
|
|
getConnectionById: vi.fn().mockResolvedValue({
|
|
|
|
|
id: 'conn-1',
|
|
|
|
|
name: 'Warehouse',
|
|
|
|
|
connectionType: 'POSTGRESQL',
|
|
|
|
|
}),
|
|
|
|
|
executeQuery: vi.fn(),
|
|
|
|
|
},
|
|
|
|
|
configService: {
|
|
|
|
|
enqueueCommitMessageJobForExternalCommit: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
writeFile: vi.fn(),
|
|
|
|
|
deleteFile: vi.fn(),
|
|
|
|
|
},
|
|
|
|
|
gitService: {
|
|
|
|
|
revParseHead: vi.fn().mockResolvedValue('basesha'),
|
|
|
|
|
squashMergeIntoMain: vi.fn().mockResolvedValue({ ok: true, squashSha: 'cafebabe', touchedPaths: ['a.yaml'] }),
|
|
|
|
|
},
|
|
|
|
|
lockingService: {
|
|
|
|
|
withLock: vi.fn().mockImplementation((_key: string, fn: () => Promise<unknown>) => fn()),
|
|
|
|
|
},
|
|
|
|
|
slSourcesRepository: { deleteByConnectionAndName: vi.fn() },
|
|
|
|
|
sessionWorktreeService: {
|
|
|
|
|
create: vi.fn().mockResolvedValue(sessionWorktree),
|
|
|
|
|
cleanup: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
},
|
|
|
|
|
semanticLayerSourceReconciler: { upsertRow: vi.fn() },
|
|
|
|
|
agentRunner: { runLoop: vi.fn().mockResolvedValue({ stopReason: 'natural' }) },
|
|
|
|
|
slValidator: { validateSingleSource: vi.fn().mockResolvedValue({ errors: [], warnings: [] }) },
|
|
|
|
|
toolsetFactory: {
|
|
|
|
|
createIngestWuToolset: vi.fn().mockReturnValue({
|
2026-05-16 12:06:34 +02:00
|
|
|
toRuntimeTools: vi.fn().mockReturnValue({}),
|
2026-05-10 23:12:26 +02:00
|
|
|
getAllTools: vi.fn().mockReturnValue([]),
|
|
|
|
|
}),
|
|
|
|
|
createToolset: vi.fn().mockReturnValue({
|
2026-05-16 12:06:34 +02:00
|
|
|
toRuntimeTools: vi.fn().mockReturnValue({}),
|
2026-05-10 23:12:26 +02:00
|
|
|
getAllTools: vi.fn().mockReturnValue([]),
|
|
|
|
|
}),
|
|
|
|
|
},
|
2026-05-12 11:21:37 +02:00
|
|
|
logger: { log: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() },
|
2026-05-10 23:12:26 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
return { ...defaults, ...overrides };
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const buildService = (mocks: BuiltMocks): MemoryAgentService =>
|
|
|
|
|
new MemoryAgentService({
|
|
|
|
|
settings: {
|
|
|
|
|
knowledge: {
|
|
|
|
|
userScopedKnowledgeEnabled: mocks.appSettings.settings.ai.knowledge.userScopedKnowledgeEnabled,
|
|
|
|
|
},
|
|
|
|
|
slValidation: {
|
|
|
|
|
probeRowCount: mocks.appSettings.settings.ai.slValidation.probeRowCount,
|
|
|
|
|
},
|
|
|
|
|
llm: {
|
|
|
|
|
memoryIngestionModel: mocks.appSettings.settings.llm.memoryIngestionModel,
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
promptService: mocks.prompt,
|
|
|
|
|
skillsRegistry: mocks.skillsRegistry,
|
|
|
|
|
wikiService: mocks.wikiService,
|
|
|
|
|
knowledgeIndex: mocks.indexRepository,
|
|
|
|
|
knowledgeSlRefs: mocks.knowledgeSlRefsRepository,
|
|
|
|
|
semanticLayerService: mocks.semanticLayerService,
|
|
|
|
|
slSearchService: mocks.slSearchService,
|
|
|
|
|
connections: {
|
|
|
|
|
listEnabledConnections: vi.fn().mockResolvedValue([]),
|
|
|
|
|
getConnectionById:
|
|
|
|
|
mocks.dataSourcesService.getConnectionById ??
|
|
|
|
|
vi.fn().mockResolvedValue({
|
|
|
|
|
id: 'conn-1',
|
|
|
|
|
name: 'Warehouse',
|
|
|
|
|
connectionType: 'POSTGRESQL',
|
|
|
|
|
}),
|
|
|
|
|
executeQuery: mocks.dataSourcesService.executeQuery,
|
|
|
|
|
},
|
|
|
|
|
rootFileStore: mocks.configService,
|
|
|
|
|
gitService: mocks.gitService,
|
|
|
|
|
lockingService: mocks.lockingService,
|
|
|
|
|
slSourcesRepository: mocks.slSourcesRepository,
|
|
|
|
|
sessionWorktreeService: mocks.sessionWorktreeService,
|
|
|
|
|
semanticLayerSourceReconciler: mocks.semanticLayerSourceReconciler,
|
|
|
|
|
agentRunner: mocks.agentRunner,
|
|
|
|
|
slValidator: mocks.slValidator,
|
|
|
|
|
toolsetFactory: mocks.toolsetFactory,
|
|
|
|
|
telemetry: {
|
2026-05-10 20:44:07 -07:00
|
|
|
trackMemoryIngestion: mocks.eventTracker.trackEvent,
|
2026-05-10 23:12:26 +02:00
|
|
|
},
|
2026-05-12 11:21:37 +02:00
|
|
|
logger: mocks.logger,
|
2026-05-10 23:12:26 +02:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
const baseInput = {
|
|
|
|
|
userId: 'u1',
|
|
|
|
|
chatId: 'chat-1',
|
|
|
|
|
// Long enough + with a definition keyword so the prefilter doesn't skip.
|
|
|
|
|
userMessage: 'going forward exclude cancelled orders from revenue, this is the canonical definition',
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const generateTextMock = vi.mocked(generateText);
|
|
|
|
|
|
|
|
|
|
beforeEach(() => {
|
|
|
|
|
generateTextMock.mockReset();
|
|
|
|
|
generateTextMock.mockResolvedValue({ text: '', toolCalls: [] } as never);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
afterEach(() => {
|
|
|
|
|
vi.restoreAllMocks();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('MemoryAgentService.ingest — session-branch orchestration', () => {
|
|
|
|
|
it('happy path: creates worktree, runs LLM loop, squash-merges, enqueues note, cleans up', async () => {
|
|
|
|
|
const mocks = buildMocks();
|
|
|
|
|
const svc = buildService(mocks);
|
|
|
|
|
|
|
|
|
|
const result = await svc.ingest(baseInput);
|
|
|
|
|
|
|
|
|
|
// Phase 1: session worktree was created from main's HEAD.
|
|
|
|
|
expect(mocks.sessionWorktreeService.create).toHaveBeenCalledWith('chat-1', 'basesha');
|
|
|
|
|
|
|
|
|
|
// Phase 2: LLM loop ran with the assembled tools/system/prompt.
|
|
|
|
|
expect(mocks.agentRunner.runLoop).toHaveBeenCalledOnce();
|
|
|
|
|
|
|
|
|
|
// Phase 3: squash-merged onto main.
|
|
|
|
|
expect(mocks.gitService.squashMergeIntoMain).toHaveBeenCalledWith(
|
|
|
|
|
'session/chat-1',
|
|
|
|
|
SYSTEM_GIT_AUTHOR.name,
|
|
|
|
|
SYSTEM_GIT_AUTHOR.email,
|
|
|
|
|
expect.stringContaining('[chat=chat-1]'),
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
// Note enqueue happened on the ROOT configService, not the scoped one. The single
|
|
|
|
|
// touched path is passed as the diff scope.
|
|
|
|
|
expect(mocks.configService.enqueueCommitMessageJobForExternalCommit).toHaveBeenCalledWith(
|
|
|
|
|
{ commitHash: 'cafebabe' },
|
|
|
|
|
expect.stringContaining('[chat=chat-1]'),
|
|
|
|
|
'a.yaml',
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
// Cleanup ran with success.
|
|
|
|
|
expect(mocks.sessionWorktreeService.cleanup).toHaveBeenCalledWith(
|
|
|
|
|
expect.objectContaining({ chatId: 'chat-1' }),
|
|
|
|
|
'success',
|
|
|
|
|
expect.any(Object),
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(result.commitHash).toBe('cafebabe');
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-16 12:06:34 +02:00
|
|
|
it('normalizes load_skill output to markdown while preserving structured payload', async () => {
|
|
|
|
|
const tempDir = await mkdtemp(join(tmpdir(), 'ktx-memory-skill-'));
|
|
|
|
|
const skillDir = join(tempDir, 'memory_agent');
|
|
|
|
|
await mkdir(skillDir, { recursive: true });
|
|
|
|
|
await writeFile(join(skillDir, 'SKILL.md'), '---\nname: memory_agent\n---\nSkill body', 'utf-8');
|
|
|
|
|
try {
|
|
|
|
|
const agentRunner = {
|
|
|
|
|
runLoop: vi.fn(async (params: any) => {
|
|
|
|
|
const result = await params.toolSet.load_skill.execute({ name: 'memory_agent' });
|
|
|
|
|
expect(result.markdown).toContain('memory_agent');
|
|
|
|
|
expect(result.structured).toMatchObject({ name: 'memory_agent' });
|
|
|
|
|
return { stopReason: 'natural' as const };
|
|
|
|
|
}),
|
|
|
|
|
};
|
|
|
|
|
const mocks = buildMocks({
|
|
|
|
|
agentRunner,
|
|
|
|
|
skillsRegistry: {
|
|
|
|
|
listSkills: vi.fn().mockResolvedValue([{ name: 'memory_agent', path: skillDir }]),
|
|
|
|
|
buildSkillsPrompt: vi.fn().mockReturnValue(''),
|
|
|
|
|
getSkill: vi.fn().mockResolvedValue({ name: 'memory_agent', path: skillDir }),
|
|
|
|
|
stripFrontmatter: vi.fn().mockReturnValue('Skill body'),
|
|
|
|
|
},
|
|
|
|
|
});
|
|
|
|
|
const svc = buildService(mocks);
|
|
|
|
|
|
|
|
|
|
await svc.ingest(baseInput);
|
|
|
|
|
|
|
|
|
|
expect(agentRunner.runLoop).toHaveBeenCalled();
|
|
|
|
|
} finally {
|
|
|
|
|
await rm(tempDir, { recursive: true, force: true });
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-12 11:21:37 +02:00
|
|
|
it('logs prompt debug output when KTX_MEMORY_AGENT_DEBUG_PROMPTS is enabled', async () => {
|
|
|
|
|
const previousDebugPrompts = process.env.KTX_MEMORY_AGENT_DEBUG_PROMPTS;
|
|
|
|
|
const mocks = buildMocks();
|
|
|
|
|
const svc = buildService(mocks);
|
|
|
|
|
|
|
|
|
|
try {
|
|
|
|
|
process.env.KTX_MEMORY_AGENT_DEBUG_PROMPTS = '1';
|
|
|
|
|
|
|
|
|
|
await svc.ingest(baseInput);
|
|
|
|
|
|
|
|
|
|
expect(mocks.logger.debug).toHaveBeenCalledWith(expect.stringContaining('[memory-agent prompt-debug] system='));
|
|
|
|
|
expect(mocks.logger.debug).toHaveBeenCalledWith(expect.stringContaining('[memory-agent prompt-debug] user='));
|
|
|
|
|
} finally {
|
|
|
|
|
if (previousDebugPrompts === undefined) {
|
|
|
|
|
delete process.env.KTX_MEMORY_AGENT_DEBUG_PROMPTS;
|
|
|
|
|
} else {
|
|
|
|
|
process.env.KTX_MEMORY_AGENT_DEBUG_PROMPTS = previousDebugPrompts;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2026-05-10 23:12:26 +02:00
|
|
|
it('empty path: squash returns no touched paths → no enqueue, cleanup(empty), commitHash=null', async () => {
|
|
|
|
|
const mocks = buildMocks();
|
|
|
|
|
mocks.gitService.squashMergeIntoMain.mockResolvedValue({
|
|
|
|
|
ok: true,
|
|
|
|
|
squashSha: 'basesha',
|
|
|
|
|
touchedPaths: [],
|
|
|
|
|
});
|
|
|
|
|
const svc = buildService(mocks);
|
|
|
|
|
|
|
|
|
|
const result = await svc.ingest(baseInput);
|
|
|
|
|
|
|
|
|
|
expect(mocks.configService.enqueueCommitMessageJobForExternalCommit).not.toHaveBeenCalled();
|
|
|
|
|
expect(mocks.sessionWorktreeService.cleanup).toHaveBeenCalledWith(expect.any(Object), 'empty', expect.any(Object));
|
|
|
|
|
expect(result.commitHash).toBeNull();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('conflict path: rolls back DB, cleanup(conflict, conflictPaths), returns commitHash=null with empty actions', async () => {
|
|
|
|
|
const mocks = buildMocks();
|
|
|
|
|
mocks.gitService.squashMergeIntoMain.mockResolvedValue({
|
|
|
|
|
ok: false,
|
|
|
|
|
conflict: true,
|
|
|
|
|
conflictPaths: ['semantic-layer/conn-x/fct_intakes.yaml'],
|
|
|
|
|
});
|
|
|
|
|
// Have the wikiService report a still-existing page in main, so rollback re-syncs.
|
|
|
|
|
mocks.wikiService.readPage.mockResolvedValue({
|
|
|
|
|
pageKey: 'phantom',
|
|
|
|
|
frontmatter: { summary: 'x', usage_mode: 'auto' },
|
|
|
|
|
content: 'body',
|
|
|
|
|
});
|
|
|
|
|
const svc = buildService(mocks);
|
|
|
|
|
|
|
|
|
|
const result = await svc.ingest(baseInput);
|
|
|
|
|
|
|
|
|
|
expect(mocks.gitService.squashMergeIntoMain).toHaveBeenCalled();
|
|
|
|
|
// Cleanup got the conflict outcome + the paths.
|
|
|
|
|
expect(mocks.sessionWorktreeService.cleanup).toHaveBeenCalledWith(expect.any(Object), 'conflict', {
|
|
|
|
|
conflictPaths: ['semantic-layer/conn-x/fct_intakes.yaml'],
|
|
|
|
|
});
|
|
|
|
|
expect(mocks.configService.enqueueCommitMessageJobForExternalCommit).not.toHaveBeenCalled();
|
|
|
|
|
expect(result.commitHash).toBeNull();
|
|
|
|
|
expect(result.actions).toEqual([]);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('crash path: post-loop step throws → cleanup(crash), commitHash=null', async () => {
|
|
|
|
|
const mocks = buildMocks();
|
|
|
|
|
// Force the cross-ref reconciler to throw, escaping into the outer try/catch and
|
|
|
|
|
// landing in the crash branch.
|
|
|
|
|
mocks.knowledgeSlRefsRepository.syncFromWiki.mockRejectedValue(new Error('db down'));
|
|
|
|
|
// squashMergeIntoMain shouldn't even be reached.
|
|
|
|
|
mocks.gitService.squashMergeIntoMain.mockRejectedValue(new Error('should not be called after crash'));
|
|
|
|
|
// Need a wiki action to trigger the cross-ref code path. Easiest: have the LLM mock
|
|
|
|
|
// not push actions, so syncFromWiki is never called and crash won't happen here.
|
|
|
|
|
// Instead, force the squash to throw.
|
|
|
|
|
mocks.knowledgeSlRefsRepository.syncFromWiki.mockResolvedValue({ inserted: 0, deleted: 0 });
|
|
|
|
|
mocks.gitService.squashMergeIntoMain.mockRejectedValue(new Error('git crashed'));
|
|
|
|
|
|
|
|
|
|
const svc = buildService(mocks);
|
|
|
|
|
|
|
|
|
|
const result = await svc.ingest(baseInput);
|
|
|
|
|
|
|
|
|
|
expect(mocks.sessionWorktreeService.cleanup).toHaveBeenCalledWith(expect.any(Object), 'crash', expect.any(Object));
|
|
|
|
|
expect(result.commitHash).toBeNull();
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('MemoryAgentService.ingest — concurrency regression', () => {
|
|
|
|
|
it('two parallel ingest() calls produce distinct squash commits (no absorption)', async () => {
|
|
|
|
|
// FIFO lock: each acquisition chains onto the previous holder's release. This is the
|
|
|
|
|
// same shape as production withLock — the test asserts that two parallel ingests
|
|
|
|
|
// sequence both their phase-1 (worktree create) and phase-3 (squash merge) calls
|
|
|
|
|
// without deadlocking, and produce distinct commits.
|
|
|
|
|
let chain: Promise<void> = Promise.resolve();
|
|
|
|
|
const lockingService = {
|
|
|
|
|
withLock: vi.fn().mockImplementation(async (_key: string, fn: () => Promise<unknown>) => {
|
|
|
|
|
const previous = chain;
|
|
|
|
|
let releaseMe!: () => void;
|
|
|
|
|
chain = new Promise<void>((resolve) => {
|
|
|
|
|
releaseMe = resolve;
|
|
|
|
|
});
|
|
|
|
|
await previous;
|
|
|
|
|
try {
|
|
|
|
|
return await fn();
|
|
|
|
|
} finally {
|
|
|
|
|
releaseMe();
|
|
|
|
|
}
|
|
|
|
|
}),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
let createCount = 0;
|
|
|
|
|
const sessionWorktreeService = {
|
|
|
|
|
create: vi.fn().mockImplementation((chatId: string) => {
|
|
|
|
|
createCount += 1;
|
|
|
|
|
return Promise.resolve({
|
|
|
|
|
chatId,
|
|
|
|
|
workdir: `/tmp/wt/session-${chatId}`,
|
|
|
|
|
branch: `session/${chatId}`,
|
|
|
|
|
baseSha: 'basesha',
|
|
|
|
|
createdAt: new Date(),
|
|
|
|
|
git: { revParseHead: vi.fn().mockResolvedValue('basesha') },
|
|
|
|
|
config: { writeFile: vi.fn() },
|
|
|
|
|
});
|
|
|
|
|
}),
|
|
|
|
|
cleanup: vi.fn().mockResolvedValue(undefined),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
let mergeCount = 0;
|
|
|
|
|
const gitService = {
|
|
|
|
|
revParseHead: vi.fn().mockResolvedValue('basesha'),
|
|
|
|
|
squashMergeIntoMain: vi.fn().mockImplementation(() => {
|
|
|
|
|
mergeCount += 1;
|
|
|
|
|
return Promise.resolve({
|
|
|
|
|
ok: true,
|
|
|
|
|
squashSha: `sha-${mergeCount}`,
|
|
|
|
|
touchedPaths: [`${mergeCount}.yaml`],
|
|
|
|
|
});
|
|
|
|
|
}),
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
const mocksA = buildMocks({ lockingService, sessionWorktreeService, gitService });
|
|
|
|
|
const mocksB = buildMocks({ lockingService, sessionWorktreeService, gitService });
|
|
|
|
|
const svcA = buildService(mocksA);
|
|
|
|
|
const svcB = buildService(mocksB);
|
|
|
|
|
|
|
|
|
|
const [a, b] = await Promise.all([
|
|
|
|
|
svcA.ingest({ ...baseInput, chatId: 'chat-A' }),
|
|
|
|
|
svcB.ingest({ ...baseInput, chatId: 'chat-B' }),
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
expect(createCount).toBe(2);
|
|
|
|
|
expect(gitService.squashMergeIntoMain).toHaveBeenCalledTimes(2);
|
|
|
|
|
expect(a.commitHash).not.toBeNull();
|
|
|
|
|
expect(b.commitHash).not.toBeNull();
|
|
|
|
|
expect(a.commitHash).not.toBe(b.commitHash);
|
|
|
|
|
});
|
|
|
|
|
});
|