2026-05-10 23:12:26 +02:00
import { mkdir , mkdtemp , rm , writeFile } from 'node:fs/promises' ;
import { tmpdir } from 'node:os' ;
import { join } from 'node:path' ;
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
import type { AgentRunnerPort } from '../../../src/context/llm/runtime-port.js' ;
import { initKtxProject , type KtxLocalProject , loadKtxProject } from '../../../src/context/project/project.js' ;
2026-05-13 13:43:23 +02:00
import { afterEach , beforeEach , describe , expect , it , vi } from 'vitest' ;
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
import { FakeSourceAdapter } from '../../../src/context/ingest/adapters/fake/fake.adapter.js' ;
import { createLocalBundleIngestRuntime } from '../../../src/context/ingest/local-bundle-runtime.js' ;
2026-05-10 23:12:26 +02:00
type RuntimeWithConnectionDeps = {
deps : {
connections : {
listEnabledConnections ( ids : string [ ] ) : Promise < Array < { id : string ; name : string ; connectionType : string } > > ;
getConnectionById ( connectionId : string ) : Promise < { id : string ; name : string ; connectionType : string } | null > ;
2026-05-13 13:43:23 +02:00
executeQuery ( connectionId : string , sql : string ) : Promise < unknown > ;
2026-05-10 23:12:26 +02:00
} ;
} ;
} ;
2026-05-18 13:38:06 +02:00
type RuntimeWithSlValidationDeps = {
deps : {
slValidator : {
validateSingleSource (
deps : unknown ,
connectionId : string ,
sourceName : string ,
) : Promise < { errors : string [ ] ; warnings : string [ ] } > ;
} ;
} ;
} ;
type RuntimeWithSettingsDeps = {
deps : {
settings : Record < string , unknown > ;
} ;
} ;
2026-05-16 12:06:34 +02:00
function testAgentRunner ( ) : AgentRunnerPort {
return { runLoop : vi.fn ( ) . mockResolvedValue ( { stopReason : 'natural' as const } ) } ;
}
2026-05-10 23:12:26 +02:00
describe ( 'createLocalBundleIngestRuntime' , ( ) = > {
let tempDir : string ;
2026-05-10 23:51:24 +02:00
let project : KtxLocalProject ;
2026-05-10 23:12:26 +02:00
beforeEach ( async ( ) = > {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp ( join ( tmpdir ( ) , 'ktx-local-bundle-runtime-' ) ) ;
2026-05-10 23:12:26 +02:00
const projectDir = join ( tempDir , 'project' ) ;
2026-05-14 17:39:31 +02:00
await initKtxProject ( { projectDir } ) ;
2026-05-10 23:12:26 +02:00
await writeFile (
2026-05-10 23:51:24 +02:00
join ( projectDir , 'ktx.yaml' ) ,
2026-05-10 23:12:26 +02:00
[
'connections:' ,
' warehouse:' ,
' driver: postgres' ,
'ingest:' ,
' adapters:' ,
' - fake' ,
' embeddings:' ,
2026-05-19 16:40:01 +02:00
' backend: none' ,
2026-05-10 23:12:26 +02:00
'' ,
] . join ( '\n' ) ,
'utf-8' ,
) ;
2026-05-10 23:51:24 +02:00
project = await loadKtxProject ( { projectDir } ) ;
2026-05-10 23:12:26 +02:00
} ) ;
afterEach ( async ( ) = > {
await rm ( tempDir , { recursive : true , force : true } ) ;
} ) ;
it ( 'requires an agent runner or configured local ingest LLM' , ( ) = > {
expect ( ( ) = >
createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
} ) ,
2026-05-12 10:26:07 +02:00
) . toThrow (
[
feat: add codex llm backend for ktx runtime work (#253)
* feat: add codex sdk runner foundation
* feat: parse codex runtime events
* feat: expose codex runtime mcp tools
* feat: add codex llm runtime
* feat: wire codex llm backend
* test: avoid Array.fromAsync in codex runner test
* docs: document codex llm backend
* fix: tighten codex runtime config ownership
* fix: use codex sdk env and thread options
* fix: parse codex sdk event shapes
* test: add codex backend live smoke
* docs: clarify codex backend isolation
* fix: drive codex loop metrics from mcp events
* fix: enforce codex local step budget
* docs: disclose codex isolation limits
* fix: count all codex agent steps and stream step callbacks live
The agent-loop step budget only counted completed mcp_tool_call items, so
built-in command_execution steps (which the public Codex SDK/CLI surface can
still expose) never decremented the budget, letting ingest/reconciliation run
past stepBudget until Codex stopped on its own. onStepFinish was also replayed
only after the whole stream drained, so live work_unit_step / reconciliation
progress appeared stuck until the Codex process exited.
collectEvents is now the single live step accumulator: it counts every
completed agent-action item via a shared isCompletedAgentStep predicate
(command_execution, mcp_tool_call, file_change, web_search), fires onStepFinish
as each step completes, and enforces the budget on that broader count. A
no-tool turn still counts as one step. toolFailures stays MCP-specific, since a
non-zero command exit is normal agent exploration, not a loop failure.
* test: align ingest llm-guard assertions with codex backend
The skip-llm ingest guard message now lists codex as a valid backend and
mentions a Claude Code/Codex session plus a codex setup hint, but this slow
suite test still asserted the pre-codex wording. Update it to match the
production message (already covered by the local-bundle-runtime unit test) and
add the codex setup-line assertion.
* fix: treat codex error:null tool calls as success
The Codex SDK serializes error: null on successful mcp_tool_call items, so
the failure check (item.error !== undefined) flagged every successful tool
call as failed with the empty-payload default "Codex turn failed". This
killed every ingest work unit under the codex backend before it could
produce a patch.
Key on status === 'failed' (authoritative, always set) and only treat a
populated error object as a failure. Add a regression test built from a
verbatim real-SDK event capture.
* fix: default codex backend to gpt-5.5 and report real probe errors
The previous default gpt-5.3-codex is an API-key-only model that the OpenAI
API rejects under ChatGPT-account (subscription) auth, so codex status/setup
failed with a misleading "authentication is not usable" message even though
auth was fine.
- Default codex model is now gpt-5.5 (works on both subscription and API-key
auth); the curated setup picker offers gpt-5.5 / gpt-5.4 / gpt-5.4-mini and
keeps free-form entry for account-specific ids (e.g. gpt-5.3-codex-spark).
- runCodexAuthProbe now distinguishes "model not available" from an auth
failure and surfaces the real API error: collectEvents retains stream
events when the SDK throws on a non-zero exit, and the API error JSON
envelope is unwrapped to its human-readable message.
- The Codex isolation warning now renders inside the clack setup frame.
- Docs updated to gpt-5.5 with a note that *-codex ids require API-key auth.
* fix: require llm.models.default in status and match codex probe remediation
Status reported a project ready when a non-none LLM backend was configured
without llm.models.default, but the runtime (resolveModelSlots) hard-requires
it, so ingest/scan/memory threw after `ktx status` said the project was usable.
buildLlmStatus now fails for any non-none backend missing models.default and no
longer invents a fallback model for claude-code/codex.
Codex probe failures now carry a category-matched fix: a model-access failure
steers the user at llm.models.default instead of the auth/install remediation.
runCodexAuthProbe returns the fix and status consumes it; the message stays
self-sufficient so setup output is unchanged.
Docs: README now lists the codex backend and local Codex auth; ktx-setup.mdx
states --llm-model only accepts codex/default or gpt-*/codex-* ids.
Repaired four doctor fixtures that configured a backend without models.default
(the now-correctly-blocked config) and added coverage for the new behavior.
2026-06-02 13:57:11 +02:00
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, claude-code, or codex, or an injected agentRunner.' ,
'Configure a local Claude Code/Codex session or API-backed LLM, then rerun ingest:' ,
2026-05-16 12:06:34 +02:00
` ktx setup --project-dir ${ project . projectDir } --llm-backend claude-code --no-input ` ,
feat: add codex llm backend for ktx runtime work (#253)
* feat: add codex sdk runner foundation
* feat: parse codex runtime events
* feat: expose codex runtime mcp tools
* feat: add codex llm runtime
* feat: wire codex llm backend
* test: avoid Array.fromAsync in codex runner test
* docs: document codex llm backend
* fix: tighten codex runtime config ownership
* fix: use codex sdk env and thread options
* fix: parse codex sdk event shapes
* test: add codex backend live smoke
* docs: clarify codex backend isolation
* fix: drive codex loop metrics from mcp events
* fix: enforce codex local step budget
* docs: disclose codex isolation limits
* fix: count all codex agent steps and stream step callbacks live
The agent-loop step budget only counted completed mcp_tool_call items, so
built-in command_execution steps (which the public Codex SDK/CLI surface can
still expose) never decremented the budget, letting ingest/reconciliation run
past stepBudget until Codex stopped on its own. onStepFinish was also replayed
only after the whole stream drained, so live work_unit_step / reconciliation
progress appeared stuck until the Codex process exited.
collectEvents is now the single live step accumulator: it counts every
completed agent-action item via a shared isCompletedAgentStep predicate
(command_execution, mcp_tool_call, file_change, web_search), fires onStepFinish
as each step completes, and enforces the budget on that broader count. A
no-tool turn still counts as one step. toolFailures stays MCP-specific, since a
non-zero command exit is normal agent exploration, not a loop failure.
* test: align ingest llm-guard assertions with codex backend
The skip-llm ingest guard message now lists codex as a valid backend and
mentions a Claude Code/Codex session plus a codex setup hint, but this slow
suite test still asserted the pre-codex wording. Update it to match the
production message (already covered by the local-bundle-runtime unit test) and
add the codex setup-line assertion.
* fix: treat codex error:null tool calls as success
The Codex SDK serializes error: null on successful mcp_tool_call items, so
the failure check (item.error !== undefined) flagged every successful tool
call as failed with the empty-payload default "Codex turn failed". This
killed every ingest work unit under the codex backend before it could
produce a patch.
Key on status === 'failed' (authoritative, always set) and only treat a
populated error object as a failure. Add a regression test built from a
verbatim real-SDK event capture.
* fix: default codex backend to gpt-5.5 and report real probe errors
The previous default gpt-5.3-codex is an API-key-only model that the OpenAI
API rejects under ChatGPT-account (subscription) auth, so codex status/setup
failed with a misleading "authentication is not usable" message even though
auth was fine.
- Default codex model is now gpt-5.5 (works on both subscription and API-key
auth); the curated setup picker offers gpt-5.5 / gpt-5.4 / gpt-5.4-mini and
keeps free-form entry for account-specific ids (e.g. gpt-5.3-codex-spark).
- runCodexAuthProbe now distinguishes "model not available" from an auth
failure and surfaces the real API error: collectEvents retains stream
events when the SDK throws on a non-zero exit, and the API error JSON
envelope is unwrapped to its human-readable message.
- The Codex isolation warning now renders inside the clack setup frame.
- Docs updated to gpt-5.5 with a note that *-codex ids require API-key auth.
* fix: require llm.models.default in status and match codex probe remediation
Status reported a project ready when a non-none LLM backend was configured
without llm.models.default, but the runtime (resolveModelSlots) hard-requires
it, so ingest/scan/memory threw after `ktx status` said the project was usable.
buildLlmStatus now fails for any non-none backend missing models.default and no
longer invents a fallback model for claude-code/codex.
Codex probe failures now carry a category-matched fix: a model-access failure
steers the user at llm.models.default instead of the auth/install remediation.
runCodexAuthProbe returns the fix and status consumes it; the message stays
self-sufficient so setup output is unchanged.
Docs: README now lists the codex backend and local Codex auth; ktx-setup.mdx
states --llm-model only accepts codex/default or gpt-*/codex-* ids.
Repaired four doctor fixtures that configured a backend without models.default
(the now-correctly-blocked config) and added coverage for the new behavior.
2026-06-02 13:57:11 +02:00
` ktx setup --project-dir ${ project . projectDir } --llm-backend codex --llm-model gpt-5.5 --no-input ` ,
2026-05-19 19:23:35 +02:00
` ktx setup --project-dir ${ project . projectDir } --llm-backend anthropic --anthropic-api-key-env ANTHROPIC_API_KEY --llm-model claude-sonnet-4-6 --no-input ` ,
2026-05-12 10:26:07 +02:00
] . join ( '\n' ) ,
) ;
2026-05-10 23:12:26 +02:00
} ) ;
2026-05-16 12:06:34 +02:00
it ( 'uses a runtime-backed agent runner when claude-code is configured' , ( ) = > {
const runtime = {
generateText : vi.fn ( ) ,
generateObject : vi.fn ( ) ,
runAgentLoop : vi.fn ( async ( ) = > ( { stopReason : 'natural' as const } ) ) ,
} ;
project . config . llm = {
provider : { backend : 'claude-code' } ,
models : { default : 'sonnet' } ,
promptCaching : { enabled : false } ,
} ;
const createLlmRuntime = vi . fn ( ( ) = > runtime ) ;
const created = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
createLlmRuntime ,
} ) ;
expect ( created ) . toBeDefined ( ) ;
expect ( createLlmRuntime ) . toHaveBeenCalledWith (
project . config . llm ,
expect . objectContaining ( { projectDir : project.projectDir } ) ,
) ;
} ) ;
2026-05-21 10:38:23 +02:00
it ( 'warns when embeddings are configured but no embedding provider is supplied' , ( ) = > {
const logger = { log : vi.fn ( ) , warn : vi.fn ( ) , error : vi.fn ( ) } ;
project . config . ingest . embeddings = {
backend : 'openai' ,
model : 'text-embedding-3-small' ,
dimensions : 1536 ,
} ;
createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner : testAgentRunner ( ) ,
logger : logger as never ,
} ) ;
expect ( logger . warn ) . toHaveBeenCalledWith (
'[local-bundle-runtime] embeddings backend "openai" is configured but no embedding provider was passed; embedding-dependent stages will run against a no-op embedding port.' ,
) ;
} ) ;
2026-05-10 23:12:26 +02:00
it ( 'builds runner deps with local SQLite stores and context tools enabled' , async ( ) = > {
2026-05-16 12:06:34 +02:00
const agentRunner = testAgentRunner ( ) ;
2026-05-10 23:12:26 +02:00
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner ,
jobIdFactory : ( ) = > 'job-1' ,
} ) ;
expect ( runtime . nextJobId ( ) ) . toBe ( 'job-1' ) ;
2026-05-10 23:51:24 +02:00
expect ( runtime . storage . resolvePullDir ( 'job-1' ) ) . toBe ( join ( project . projectDir , '.ktx/cache/local-ingest/job-1/pull' ) ) ;
2026-05-10 23:12:26 +02:00
expect ( runtime . storage . resolveUploadDir ( 'job-1' ) ) . toBe (
2026-05-10 23:51:24 +02:00
join ( project . projectDir , '.ktx/cache/local-ingest/job-1/upload' ) ,
2026-05-10 23:12:26 +02:00
) ;
expect ( runtime . storage . resolveTranscriptDir ( 'job-1' ) ) . toBe (
2026-05-10 23:51:24 +02:00
join ( project . projectDir , '.ktx/ingest-transcripts/job-1' ) ,
2026-05-10 23:12:26 +02:00
) ;
await mkdir ( runtime . storage . resolveUploadDir ( 'job-1' ) , { recursive : true } ) ;
} ) ;
it ( 'exposes canonical warehouse connection types to local ingest SL tools' , async ( ) = > {
project . config . connections . warehouse = {
driver : 'postgres' ,
url : 'postgresql://readonly@db.example.test/analytics' ,
} ;
project . config . connections . bq = {
driver : 'bigquery' ,
project_id : 'acme' ,
dataset_id : 'warehouse' ,
} ;
2026-05-16 12:06:34 +02:00
const agentRunner = testAgentRunner ( ) ;
2026-05-10 23:12:26 +02:00
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner ,
} ) ;
const connections = ( runtime . runner as unknown as RuntimeWithConnectionDeps ) . deps . connections ;
await expect ( connections . getConnectionById ( 'warehouse' ) ) . resolves . toMatchObject ( {
id : 'warehouse' ,
connectionType : 'POSTGRESQL' ,
} ) ;
await expect ( connections . listEnabledConnections ( [ 'warehouse' , 'bq' ] ) ) . resolves . toEqual ( [
{ id : 'warehouse' , name : 'warehouse' , connectionType : 'POSTGRESQL' } ,
{ id : 'bq' , name : 'bq' , connectionType : 'BIGQUERY' } ,
] ) ;
} ) ;
2026-05-18 13:38:06 +02:00
it ( 'validates manifest-backed scan sources during local ingest gates' , async ( ) = > {
await project . fileStore . writeFile (
'semantic-layer/warehouse/_schema/public.yaml' ,
[
'tables:' ,
' payments:' ,
' table: public.payments' ,
' columns:' ,
' - name: payment_id' ,
' type: string' ,
' - name: amount' ,
' type: number' ,
'' ,
] . join ( '\n' ) ,
'ktx' ,
'ktx@example.com' ,
'Add warehouse manifest' ,
) ;
const agentRunner = testAgentRunner ( ) ;
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner ,
} ) ;
const deps = ( runtime . runner as unknown as RuntimeWithSlValidationDeps ) . deps ;
await expect ( deps . slValidator . validateSingleSource ( deps , 'warehouse' , 'payments' ) ) . resolves . toEqual ( {
errors : [ ] ,
warnings : expect.any ( Array ) ,
} ) ;
} ) ;
it ( 'does not mask malformed direct overlays with manifest-backed fallback validation' , async ( ) = > {
await project . fileStore . writeFile (
'semantic-layer/warehouse/_schema/public.yaml' ,
[
'tables:' ,
' payments:' ,
' table: public.payments' ,
' columns:' ,
' - name: payment_id' ,
' type: string' ,
'' ,
] . join ( '\n' ) ,
'ktx' ,
'ktx@example.com' ,
'Add warehouse manifest' ,
) ;
await project . fileStore . writeFile (
'semantic-layer/warehouse/payments.yaml' ,
[ 'name: payments' , 'columns:' , ' - [' , '' ] . join ( '\n' ) ,
'ktx' ,
'ktx@example.com' ,
'Add malformed overlay' ,
) ;
const agentRunner = testAgentRunner ( ) ;
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner ,
} ) ;
const deps = ( runtime . runner as unknown as RuntimeWithSlValidationDeps ) . deps ;
await expect ( deps . slValidator . validateSingleSource ( deps , 'warehouse' , 'payments' ) ) . resolves . toEqual ( {
errors : [ expect . stringContaining ( 'invalid YAML' ) ] ,
warnings : [ ] ,
} ) ;
} ) ;
2026-05-13 13:43:23 +02:00
it ( 'passes project connection config to local ingest query executors' , async ( ) = > {
2026-05-16 12:06:34 +02:00
const agentRunner = testAgentRunner ( ) ;
2026-05-13 13:43:23 +02:00
const queryExecutor = {
execute : vi.fn ( async ( ) = > ( {
headers : [ 'answer' ] ,
rows : [ [ 1 ] ] ,
totalRows : 1 ,
command : 'SELECT' ,
rowCount : 1 ,
} ) ) ,
} ;
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner ,
queryExecutor ,
} ) ;
const connections = ( runtime . runner as unknown as RuntimeWithConnectionDeps ) . deps . connections ;
await expect ( connections . executeQuery ( 'warehouse' , 'select 1' ) ) . resolves . toMatchObject ( {
headers : [ 'answer' ] ,
} ) ;
expect ( queryExecutor . execute ) . toHaveBeenCalledWith ( {
connectionId : 'warehouse' ,
projectDir : project.projectDir ,
connection : project.config.connections.warehouse ,
sql : 'select 1' ,
} ) ;
} ) ;
2026-05-18 13:38:06 +02:00
it ( 'defaults local bundle ingest to isolated diffs without a shared-worktree fallback setting' , ( ) = > {
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
agentRunner : testAgentRunner ( ) ,
} ) ;
const settings = ( runtime . runner as unknown as RuntimeWithSettingsDeps ) . deps . settings ;
const fallbackSettingKey = [ 'sharedWorktree' , 'SourceKeys' ] . join ( '' ) ;
expect ( settings ) . not . toHaveProperty ( fallbackSettingKey ) ;
expect ( Object . keys ( settings ) . sort ( ) ) . toEqual ( [
'ingestTraceLevel' ,
'memoryIngestionModel' ,
'probeRowCount' ,
feat(cli): profile ingest runs and split model vs tool time (#249)
* feat(cli): profile ingest runs to find where wall-clock time goes
Add opt-in profiling for `ktx ingest`. Each timed phase, work unit, and
agent loop now records durationMs / step count / token usage in the
trace, and a post-run aggregator rolls them up into a "where did the
time go" report printed to stderr.
Enable per run with KTX_PROFILE_INGEST (1/true -> human table, json ->
raw structured profile) or persistently via `ingest.profile` in
ktx.yaml. The json form emits raw milliseconds, token counts, and a
summary.headline one-line diagnosis so coding agents can parse it
directly; json wins when both env and config request profiling.
- runtime-port: RunLoopMetrics (totalMs, usage, stepCount,
stepBoundariesMs) plus onMetrics callbacks on text/object generation
- ai-sdk + claude-code runtimes: capture per-loop timing and token usage
- work-unit-executor and stages 3/4: thread metrics into trace events
- ingest-bundle.runner: time worktree / triage / clustering / index /
reconcile / squash phases and emit the profile in a finally block
(best-effort; never affects the run outcome)
- ingest-profile: new trace+transcript aggregator with table/json formatters
- config: ingest.profile flag; docs: profiling section in ktx-ingest.mdx
* fix(cli): flush tool-call logs before reading ingest profile
Tool transcripts are appended fire-and-forget so the agent hot path never
blocks on logging. The ingest profiler read them before the writes settled,
so per-work-unit toolMs (and the model-vs-tool split derived from it) could
be incomplete. Track in-flight appends and expose flushToolCallLogs() —
bounded by a timeout so it can never hang — and flush before the profiler
reads the transcript.
2026-06-01 15:49:17 +02:00
'profileIngest' ,
2026-05-18 13:38:06 +02:00
'workUnitFailureMode' ,
'workUnitMaxConcurrency' ,
'workUnitStepBudget' ,
] ) ;
} ) ;
2026-05-10 23:12:26 +02:00
it ( 'accepts a debug LLM request file when constructing the default agent runner' , async ( ) = > {
await writeFile (
2026-05-10 23:51:24 +02:00
join ( project . projectDir , 'ktx.yaml' ) ,
2026-05-10 23:12:26 +02:00
[
'connections:' ,
' warehouse:' ,
' driver: postgres' ,
'llm:' ,
' provider:' ,
' backend: gateway' ,
' gateway:' ,
' base_url: https://gateway.example/v1' ,
' models:' ,
' default: anthropic/claude-sonnet-4-6' ,
'ingest:' ,
' adapters:' ,
' - fake' ,
' embeddings:' ,
2026-05-19 16:40:01 +02:00
' backend: none' ,
2026-05-10 23:12:26 +02:00
'' ,
] . join ( '\n' ) ,
'utf-8' ,
) ;
2026-05-10 23:51:24 +02:00
project = await loadKtxProject ( { projectDir : project.projectDir } ) ;
2026-05-10 23:12:26 +02:00
const runtime = createLocalBundleIngestRuntime ( {
project ,
adapters : [ new FakeSourceAdapter ( ) ] ,
2026-05-10 23:51:24 +02:00
llmDebugRequestFile : join ( project . projectDir , '.ktx' , 'llm-debug.jsonl' ) ,
2026-05-10 23:12:26 +02:00
} ) ;
2026-05-10 23:51:24 +02:00
expect ( runtime . storage . resolvePullDir ( 'job-1' ) ) . toBe ( join ( project . projectDir , '.ktx/cache/local-ingest/job-1/pull' ) ) ;
2026-05-10 23:12:26 +02:00
} ) ;
} ) ;