apunkt/ktx
1
0
Fork 0
mirror of https://github.com/Kaelio/ktx.git synced 2026-06-28 08:49:38 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat(context): add warehouse verification tools (#46)

Browse source 
* feat(context): add warehouse dialect dispatch

* feat(context): read warehouse scan catalog

* feat(context): add entity details verification tool

* feat(context): add ingest SQL verification tool

* feat(context): add raw warehouse discovery tool

* feat(context): expose warehouse verification tools to ingest

* docs(context): add ingest identifier verification protocol

* test(context): guard ingest identifier verification prompts

* chore(context): verify warehouse verification tools

* docs: add warehouse verification tools plan and spec

* fix(context): expose target warehouses to Notion ingest

* fix(context): update ingest prompts for warehouse verification tools

* fix(context): scope raw schema discovery to allowed connections

* fix(context): verify warehouse column display targets

* docs: add notion warehouse verification gap closure plan

* fix(context): include raw discovery connection names

* fix(context): expose warehouse targets for LookML and MetricFlow

* fix(context): pass connection config to ingest query executors

* fix(cli): enable read-only SQL probes for local ingest

* docs: add warehouse verification final v1 closure plan

* fix(context): align warehouse sql probe prompt shape

* docs: add warehouse verification prompt shape closure plan

* test(context): catch connectionless sql execution prompt examples

* fix(context): include connection name in sl capture sql example

* docs: add warehouse verification sql example closure plan

* fix(context): report structured entity detail misses

* docs: add warehouse verification structured target miss closure plan

* fix: report untracked squash merge conflicts

* feat: require ingest verification ledger

* fix: stabilize ingest wiki references
This commit is contained in:
Andrey Avtomonov 2026-05-13 13:43:23 +02:00 • committed by GitHub
parent bcb0d2f8f7
commit c22248dabf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
89 changed files with 7818 additions and 191 deletions
Download patch file Download diff file Expand all files Collapse all files

68
packages/context/src/ingest/ingest-bundle.runner.test.ts
View file

@ -409,6 +409,38 @@ describe('IngestBundleRunner — Stages 1 → 7', () => {
);
});
it('threads target warehouse connection names into WorkUnit and reconcile tool sessions', async () => {
const deps = makeDeps();
const sessions: any[] = [];
deps.adapter.listTargetConnectionIds = vi.fn().mockResolvedValue(['warehouse']);
deps.toolsetFactory.createIngestWuToolset.mockImplementation((toolSession: any) => {
sessions.push(toolSession);
return {
toAiSdkTools: vi.fn().mockReturnValue({}),
getAllTools: vi.fn().mockReturnValue([]),
getToolNames: vi.fn().mockReturnValue([]),
};
});
deps.agentRunner.runLoop.mockResolvedValue({ stopReason: 'natural' });
const runner = buildRunner(deps);
(runner as any).stageRawFilesStage1 = vi.fn().mockResolvedValue({
currentHashes: new Map([['a.yml', 'h1']]),
rawDirInWorktree: 'raw-sources/notion/fake/s',
});
(runner as any).resolveStagedDir = vi.fn().mockResolvedValue('/tmp/stage/upload-x');
await runner.run({
jobId: 'j1',
connectionId: 'notion',
sourceKey: 'fake',
trigger: 'upload',
bundleRef: { kind: 'upload', uploadId: 'upload-x' },
});
expect([...sessions[0].allowedConnectionNames].sort()).toEqual(['notion', 'warehouse']);
});
it('reuses document evidence indexing and page triage for document WorkUnits', async () => {
const deps = makeDeps();
deps.adapter.source = 'notion';
@ -643,6 +675,14 @@ describe('IngestBundleRunner — Stages 1 → 7', () => {
});
}
if (params.telemetryTags.operationName === 'ingest-bundle-reconcile') {
await params.toolSet.record_verification_ledger.execute(
{
summary: 'Reconciliation emits no warehouse identifiers before fallback recording.',
verifiedIdentifiers: [],
unverifiedIdentifiers: [],
},
{ toolCallId: 'ledger-1', messages: [] },
);
await params.toolSet.emit_conflict_resolution.execute(
{
kind: 'near_duplicate',
@ -811,6 +851,14 @@ describe('IngestBundleRunner — Stages 1 → 7', () => {
{ path: 'a.yml', startLine: 1, endLine: 2 },
{ toolCallId: 'read-1', messages: [] },
);
await params.toolSet.record_verification_ledger.execute(
{
summary: 'Wiki write contains no warehouse identifiers.',
verifiedIdentifiers: [],
unverifiedIdentifiers: [],
},
{ toolCallId: 'ledger-1', messages: [] },
);
await params.toolSet.wiki_write.execute(
{ key: 'knowledge/a.md', content: 'safe summary' },
{ toolCallId: 'wiki-1', messages: [] },
@ -850,9 +898,9 @@ describe('IngestBundleRunner — Stages 1 → 7', () => {
{
unitKey: 'u1',
path: '/tmp/ktx-test/run/wu-transcripts/j1/u1.jsonl',
toolCallCount: 2,
toolCallCount: 3,
errorCount: 0,
toolNames: ['read_raw_span', 'wiki_write'],
toolNames: ['read_raw_span', 'record_verification_ledger', 'wiki_write'],
},
],
}),
@ -864,6 +912,14 @@ describe('IngestBundleRunner — Stages 1 → 7', () => {
const deps = makeDeps();
deps.agentRunner.runLoop.mockImplementation(async (params: any) => {
if (params.telemetryTags.operationName === 'ingest-bundle-wu') {
await params.toolSet.record_verification_ledger.execute(
{
summary: 'Unmapped fallback records an unsupported conversion metric without verified warehouse identifiers.',
verifiedIdentifiers: [],
unverifiedIdentifiers: [],
},
{ toolCallId: 'ledger-1', messages: [] },
);
await params.toolSet.emit_unmapped_fallback.execute(
{
rawPath: 'a.yml',
@ -920,6 +976,14 @@ describe('IngestBundleRunner — Stages 1 → 7', () => {
});
deps.agentRunner.runLoop.mockImplementation(async (params: any) => {
if (params.telemetryTags.operationName === 'ingest-bundle-reconcile') {
await params.toolSet.record_verification_ledger.execute(
{
summary: 'Reconciliation records conflict, eviction, and fallback decisions without warehouse identifiers.',
verifiedIdentifiers: [],
unverifiedIdentifiers: [],
},
{ toolCallId: 'ledger-1', messages: [] },
);
await params.toolSet.emit_conflict_resolution.execute(
{
kind: 'near_duplicate',