apunkt/ktx
1
0
Fork 0
mirror of https://github.com/Kaelio/ktx.git synced 2026-07-04 10:52:13 +02:00
Code Issues Projects Releases Packages Wiki Activity

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

Browse source
This commit is contained in:
Andrey Avtomonov 2026-05-12 23:48:12 +02:00
parent fc92ba11c0
commit 3a1fe3416d
4 changed files with 21 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

4
packages/context/src/ingest/adapters/notion/chunk.ts
View file

@ -8,7 +8,7 @@ const MAX_NOTION_WORK_UNIT_CHARS = 40_000;
export const NOTION_ORG_KNOWLEDGE_WARNING =
'Anything accessible to this Notion integration can become organization knowledge.';
const NOTION_SL_WRITE_GUIDANCE =
'Write wiki entries with wiki_write. Wiki keys must be flat slugs like orbit-company-overview, not orbit/company-overview. Search existing wiki pages for the same tables or sl_refs before creating a new page. Only write or edit SL sources after sl_discover/sl_read_source confirms a mapped non-Notion target source; if no mapped target exists, emit_unmapped_fallback and keep the fact wiki-only. Notion dataSourceCount counts Notion databases/data sources only, not warehouse/dbt mappings. If a warehouse/dbt connection exists but the named table or source is absent, use reason no_physical_table rather than no_connection_mapping. Do not create SL sources under the Notion connection just because a page mentions a warehouse table.';
'Write wiki entries with wiki_write. Wiki keys must be flat slugs like orbit-company-overview, not orbit/company-overview. Search existing wiki pages, SL sources, and raw warehouse schema for the same tables or sl_refs with discover_data before creating a new page. Only write or edit SL sources after discover_data plus sl_discover/sl_read_source or entity_details confirms a mapped non-Notion target source; if no mapped target exists, emit_unmapped_fallback and keep the fact wiki-only. Notion dataSourceCount counts Notion databases/data sources only, not warehouse/dbt mappings. If a warehouse/dbt connection exists but the named table or source is absent, use reason no_physical_table rather than no_connection_mapping. Do not create SL sources under the Notion connection just because a page mentions a warehouse table.';
async function walk(root: string): Promise<string[]> {
const entries = await readdir(root, { withFileTypes: true, recursive: true });
@ -117,7 +117,7 @@ export async function chunkNotionStagedDir(stagedDir: string, diffSet?: DiffSet)
reconcileNotes: [
`Notion maxKnowledgeCreatesPerRun=${manifest.maxKnowledgeCreatesPerRun}`,
`Notion maxKnowledgeUpdatesPerRun=${manifest.maxKnowledgeUpdatesPerRun}`,
'Notion dataSourceCount is Notion-only; use sl_discover for warehouse/dbt mapping decisions.',
'Notion dataSourceCount is Notion-only; use discover_data/entity_details for warehouse/dbt mapping decisions.',
'Reconcile Notion wiki pages sharing tables/sl_refs before creating distinct artifacts.',
],
contextReport: {

4
packages/context/src/ingest/adapters/notion/notion.adapter.test.ts
View file

@ -250,6 +250,8 @@ describe('NotionSourceAdapter', () => {
});
expect(result.workUnits[0].notes).toContain('Synthesize durable wiki and SL knowledge');
expect(result.workUnits[0].notes).toContain('emit_unmapped_fallback');
expect(result.workUnits[0].notes).toContain('discover_data');
expect(result.workUnits[0].notes).toContain('entity_details');
expect(result.workUnits[0].notes).toContain('use reason no_physical_table rather than no_connection_mapping');
expect(result.workUnits[0].notes).toContain('Do not create SL sources under the Notion connection');
expect(result.workUnits[0].notes).toContain(
@ -258,7 +260,7 @@ describe('NotionSourceAdapter', () => {
expect(result.reconcileNotes).toEqual([
'Notion maxKnowledgeCreatesPerRun=25',
'Notion maxKnowledgeUpdatesPerRun=20',
'Notion dataSourceCount is Notion-only; use sl_discover for warehouse/dbt mapping decisions.',
'Notion dataSourceCount is Notion-only; use discover_data/entity_details for warehouse/dbt mapping decisions.',
'Reconcile Notion wiki pages sharing tables/sl_refs before creating distinct artifacts.',
]);
expect(result.contextReport).toEqual({ capped: false, warnings: [NOTION_ORG_KNOWLEDGE_WARNING] });

12
packages/context/src/ingest/ingest-prompts.test.ts
View file

@ -29,6 +29,18 @@ describe('ingest prompt assets', () => {
expect(prompt).not.toMatch(forbiddenProductPattern());
});
it('uses shipped warehouse verification tools in the WorkUnit prompt', async () => {
const prompt = await readFile(
new URL('../../prompts/memory_agent_bundle_ingest_work_unit.md', import.meta.url),
'utf-8',
);
expect(prompt).toContain('discover_data');
expect(prompt).toContain('entity_details');
expect(prompt).not.toContain('wiki_sl_search');
expect(prompt).not.toContain('sl_describe_table');
});
it('does not route historic-SQL through page-triage prompt examples', async () => {
const prompt = await readFile(new URL('../../prompts/skills/page_triage_classifier.md', import.meta.url), 'utf-8');