feat: merge ingest and scan

* docs: add CLI component reuse guidance

* docs: add unified ingest ux design

* Refine unified ingest UX design after adversarial review iteration 1

* Refine unified ingest UX design after adversarial review iteration 2

* Refine unified ingest UX design after adversarial review iteration 3

* feat(cli): route public connection ingest command

* feat(cli): hide standalone scan from public help

* feat(cli): plan public ingest depth and query history

* feat(cli): execute public database ingest facets

* feat(ingest): read connection query history config

* fix(cli): use public ingest wording

* fix(config): stop generating ingest adapter allow lists

* docs: document public ingest command

* test: align ingest surface expectations

* docs: add unified ingest public CLI surface plan

* feat(cli): preflight deep public ingest readiness

* feat(setup): store query history in connection context

* feat(setup): store database context depth

* feat(setup): verify context readiness by database depth

* fix(setup): keep context build foreground only

* fix(config): reject reserved ingest connection ids

* test: close unified ingest v1 expectations

* docs: add unified ingest v1 closure plan

* fix(ingest): bypass adapter allow-list for public source ingest

* fix(ingest): honor query history window intent

* fix(ingest): hide scan internals from public database ingest

* feat(ingest): use foreground view for interactive public ingest

* fix(setup): use schema context and query history wording

* test(cli): verify unified ingest public output

* docs: add unified ingest v1 public output closure plan

* fix(setup): forward query history flags

* fix(setup): prompt for postgres query history

* fix(status): report query history readiness

* fix(ingest): remove legacy public guidance

* fix(ingest): polish foreground retry copy

* docs(examples): use unified query history wording

* chore(ingest): finish public query history cleanup

* docs: add unified ingest v1 query history status cleanup plan

* test(docs): cover unified ingest public docs

* docs: align ingest CLI reference with unified UX

* docs: update context build guides for unified ingest

* docs: update setup and primary source ingest wording

* docs: stop advertising adapter-backed example ingest

* docs: close unified ingest public docs gaps

* docs: add unified ingest v1 docs site closure plan

* fix: render unified ingest foreground warnings

* fix: explain query history schema order

* fix: add public ingest retry guidance

* fix: align setup next steps with unified ingest

* fix: remove scan wording from demo progress

* test: verify unified ingest ux closure

* docs: add unified ingest v1 foreground and retry closure plan

* fix(cli): preserve query-history pull config in public ingest

* fix(cli): omit hidden commands from docs command tree

* test(cli): close unified ingest final public surface checks

* docs: add unified ingest v1 final public surface closure plan

* fix(cli): use public source labels in ingest reports

* fix(cli): suppress low-level public ingest output

* test(cli): verify unified ingest public plain output

* docs: add unified ingest v1 public plain output closure plan

* fix(cli): add public ingest copy sanitizers

* fix(cli): sanitize public ingest progress copy

* fix(cli): rename setup schema scope prompt

* docs(plan): add progress copy closure; test: align setup back-nav fixture

Adds the iter9 plan and updates the setup back-navigation test fixture
to pass disableQueryHistory plus listSchemas/listTables stubs that the
unified ingest setup step now requires.

* docs(plan): add final ux labels plan with narrowed label scans

* fix(cli): aggregate unsupported query-history warnings

* fix(cli): align setup database labels

* test(cli): fix setup database test type-check

* fix(cli): remove primary-source wording from setup output

* test(cli): verify unified ingest setup closure

* docs(plan): add unified ingest v1 verification copy closure plan

* fix(cli): remove top-level scan command

* fix(cli): remove legacy ingest and wiki commands

* Merge scan into ingest flow

* feat(cli): split ingest progress into per-phase rows, rename work units to tasks

Each database target in the unified ingest dashboard now renders one row per
real subprocess (Schema, then Query history when enabled) instead of a single
combined bar. Each phase has its own monotonic 0-100% bar so the progress
never snaps back to zero when historic-sql starts after scan completes.
Completed phases keep their final bar, summary, and elapsed time visible as
an inline audit trail; queued and skipped phases are shown explicitly.

Also rename user-facing "work units" / "Failed work units" to "tasks" /
"Failed tasks" in ingest output and parseIngestSummary. The parser still
accepts the legacy "Work units:" wording in captured output for backward
compat. Internal memory-flow event names and type fields are left alone.

* Fix test harness failures

* Fix CI smoke checks

---------

Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
This commit is contained in:
Andrey Avtomonov 2026-05-14 01:43:06 +02:00 committed by GitHub
parent 1a472cf3ed
commit b00c1a11a9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
118 changed files with 16890 additions and 2992 deletions

View file

@ -2,6 +2,21 @@ import { describe, expect, it } from 'vitest';
import { buildDefaultKtxProjectConfig, parseKtxProjectConfig, serializeKtxProjectConfig } from './config.js';
describe('KTX project config', () => {
it.each(['status', 'replay', 'run', 'watch'])('accepts former ingest subcommand name "%s" as a connection id', (connectionId) => {
expect(
parseKtxProjectConfig(`
project: reserved-test
connections:
${connectionId}:
driver: postgres
`),
).toMatchObject({
connections: {
[connectionId]: { driver: 'postgres' },
},
});
});
it('builds the default standalone project config', () => {
expect(buildDefaultKtxProjectConfig('warehouse')).toEqual({
project: 'warehouse',
@ -21,7 +36,7 @@ describe('KTX project config', () => {
models: {},
},
ingest: {
adapters: ['live-database', 'lookml', 'metabase', 'metricflow', 'notion'],
adapters: [],
embeddings: {
backend: 'deterministic',
model: 'deterministic',
@ -67,13 +82,12 @@ describe('KTX project config', () => {
const parsed = parseKtxProjectConfig(serialized);
expect(serialized).toContain('project: warehouse');
expect(serialized).toContain('live-database');
expect(serialized).toContain('notion');
expect(serialized).not.toContain('live-database');
expect(serialized).toContain(
' embeddings:\n backend: deterministic\n model: deterministic\n dimensions: 8',
);
expect(parsed.project).toBe('warehouse');
expect(parsed.ingest.adapters).toEqual(['live-database', 'lookml', 'metabase', 'metricflow', 'notion']);
expect(parsed.ingest.adapters).toEqual([]);
expect(parsed.ingest.embeddings).toEqual({
backend: 'deterministic',
model: 'deterministic',

View file

@ -391,7 +391,7 @@ export function buildDefaultKtxProjectConfig(projectName = 'ktx-project'): KtxPr
models: {},
},
ingest: {
adapters: ['live-database', 'lookml', 'metabase', 'metricflow', 'notion'],
adapters: [],
embeddings: {
backend: 'deterministic',
model: 'deterministic',
@ -484,6 +484,9 @@ export function parseKtxProjectConfig(raw: string): KtxProjectConfig {
...(isRecord(scanEnrichment.embeddings) ? { embeddings: scanEmbeddings } : {}),
};
const parsedScanRelationships = parseScanRelationshipConfig(scanRelationships, defaults.scan.relationships);
const parsedConnections = isRecord(parsed.connections)
? (parsed.connections as Record<string, KtxProjectConnectionConfig>)
: defaults.connections;
return {
project: project.trim(),
@ -494,9 +497,7 @@ export function parseKtxProjectConfig(raw: string): KtxProjectConfig {
},
}
: {}),
connections: isRecord(parsed.connections)
? (parsed.connections as Record<string, KtxProjectConnectionConfig>)
: defaults.connections,
connections: parsedConnections,
storage: {
state: storage.state === 'sqlite' ? 'sqlite' : defaults.storage.state,
search: storage.search === 'sqlite-fts5' ? 'sqlite-fts5' : defaults.storage.search,
@ -529,5 +530,15 @@ export function parseKtxProjectConfig(raw: string): KtxProjectConfig {
}
export function serializeKtxProjectConfig(config: KtxProjectConfig): string {
return `${YAML.stringify(config, { indent: 2, lineWidth: 0 }).trimEnd()}\n`;
const serializedConfig =
config.ingest.adapters.length === 0
? {
...config,
ingest: {
embeddings: config.ingest.embeddings,
workUnits: config.ingest.workUnits,
},
}
: config;
return `${YAML.stringify(serializedConfig, { indent: 2, lineWidth: 0 }).trimEnd()}\n`;
}

View file

@ -6,7 +6,11 @@ export type {
KtxSearchBackend,
KtxStorageState,
} from './config.js';
export { buildDefaultKtxProjectConfig, parseKtxProjectConfig, serializeKtxProjectConfig } from './config.js';
export {
buildDefaultKtxProjectConfig,
parseKtxProjectConfig,
serializeKtxProjectConfig,
} from './config.js';
export type { LocalGitFileStoreDeps } from './local-git-file-store.js';
export { LocalGitFileStore } from './local-git-file-store.js';
export { ktxLocalStateDbPath } from './local-state-db.js';