2026-05-10 23:12:26 +02:00
import { access , mkdtemp , readFile , rm } from 'node:fs/promises' ;
import { tmpdir } from 'node:os' ;
import { join } from 'node:path' ;
import { afterEach , beforeEach , describe , expect , it , vi } from 'vitest' ;
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 { initKtxProject } from '../../context/project/project.js' ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
import { createLocalProjectMemoryIngest } from './local-memory.js' ;
2026-05-10 23:12:26 +02:00
import { LocalMemoryRunStore } from './local-memory-runs.js' ;
vi . mock ( 'ai' , ( ) = > ( {
generateText : vi.fn ( ) . mockResolvedValue ( { text : '' , toolCalls : [ ] } ) ,
stepCountIs : ( stepBudget : number ) = > stepBudget ,
tool : ( definition : unknown ) = > definition ,
} ) ) ;
async function expectPathMissing ( path : string ) : Promise < void > {
await expect ( access ( path ) ) . rejects . toThrow ( ) ;
}
describe ( 'LocalMemoryRunStore' , ( ) = > {
let tempDir : string ;
beforeEach ( async ( ) = > {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp ( join ( tmpdir ( ) , 'ktx-local-memory-runs-' ) ) ;
2026-05-10 23:12:26 +02:00
} ) ;
afterEach ( async ( ) = > {
await rm ( tempDir , { recursive : true , force : true } ) ;
} ) ;
it ( 'persists running, done, and reloadable memory run status in SQLite' , async ( ) = > {
const store = new LocalMemoryRunStore ( {
projectDir : tempDir ,
idFactory : ( ) = > 'memory-run-1' ,
} ) ;
const created = await store . createRunning ( { inputHash : 'hash-1' , chatId : 'chat-1' } ) ;
expect ( created ) . toEqual ( { id : 'memory-run-1' } ) ;
await store . markRunning ( 'memory-run-1' , 'capturing' ) ;
await store . markDone ( 'memory-run-1' , {
signalDetected : true ,
actions : [ { target : 'wiki' , type : 'created' , key : 'revenue' , detail : 'Revenue definition' } ] ,
2026-05-13 16:05:58 +02:00
skillsLoaded : [ 'wiki_capture' ] ,
2026-05-10 23:12:26 +02:00
commitHash : 'abc123' ,
} ) ;
2026-05-10 23:51:24 +02:00
await expect ( access ( join ( tempDir , '.ktx/db.sqlite' ) ) ) . resolves . toBeUndefined ( ) ;
await expectPathMissing ( join ( tempDir , '.ktx/memory-runs/memory-run-1.json' ) ) ;
2026-05-10 23:12:26 +02:00
await expect ( store . findById ( 'memory-run-1' ) ) . resolves . toMatchObject ( {
id : 'memory-run-1' ,
status : 'done' ,
stage : 'done' ,
inputHash : 'hash-1' ,
chatId : 'chat-1' ,
error : null ,
outputSummary : {
signalDetected : true ,
commitHash : 'abc123' ,
} ,
} ) ;
const reloaded = new LocalMemoryRunStore ( { projectDir : tempDir } ) ;
await expect ( reloaded . findById ( 'memory-run-1' ) ) . resolves . toMatchObject ( {
id : 'memory-run-1' ,
status : 'done' ,
stage : 'done' ,
inputHash : 'hash-1' ,
chatId : 'chat-1' ,
outputSummary : {
actions : [ { target : 'wiki' , type : 'created' , key : 'revenue' , detail : 'Revenue definition' } ] ,
2026-05-13 16:05:58 +02:00
skillsLoaded : [ 'wiki_capture' ] ,
2026-05-10 23:12:26 +02:00
signalDetected : true ,
commitHash : 'abc123' ,
} ,
} ) ;
} ) ;
} ) ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
describe ( 'createLocalProjectMemoryIngest' , ( ) = > {
2026-05-10 23:12:26 +02:00
let tempDir : string ;
beforeEach ( async ( ) = > {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp ( join ( tmpdir ( ) , 'ktx-local-memory-' ) ) ;
2026-05-10 23:12:26 +02:00
} ) ;
afterEach ( async ( ) = > {
await rm ( tempDir , { recursive : true , force : true } ) ;
} ) ;
2026-05-21 10:38:23 +02:00
it ( 'warns when embeddings are configured but memory ingest is created without an embedding provider' , async ( ) = > {
const project = await initKtxProject ( { projectDir : tempDir } ) ;
project . config . ingest . embeddings = {
backend : 'openai' ,
model : 'text-embedding-3-small' ,
dimensions : 1536 ,
} ;
const logger = { log : vi.fn ( ) , warn : vi.fn ( ) , error : vi.fn ( ) } ;
createLocalProjectMemoryIngest ( project , {
agentRunner : { runLoop : vi.fn ( ) } as never ,
logger : logger as never ,
} ) ;
expect ( logger . warn ) . toHaveBeenCalledWith (
'[memory-ingest] embeddings backend "openai" is configured but no embedding provider was passed; semantic search will fall back to a no-op embedding port.' ,
) ;
} ) ;
2026-05-10 23:12:26 +02:00
it ( 'captures a wiki page through the local memory agent and persists pollable status' , async ( ) = > {
2026-05-14 17:39:31 +02:00
const project = await initKtxProject ( { projectDir : tempDir } ) ;
2026-05-10 23:12:26 +02:00
const agentRunner = {
runLoop : async ( {
toolSet ,
} : {
toolSet : Record < string , { execute : ( input : unknown , options ? : { toolCallId ? : string } ) = > Promise < unknown > } > ;
} ) = > {
2026-05-13 16:05:58 +02:00
await toolSet . load_skill . execute ( { name : 'wiki_capture' } ) ;
2026-05-10 23:12:26 +02:00
await toolSet . wiki_write . execute (
{
key : 'revenue' ,
summary : 'Revenue definition' ,
content : 'Revenue means paid order value net of refunds.' ,
tags : [ 'finance' ] ,
} ,
{ toolCallId : 'wiki-write' } ,
) ;
return { stopReason : 'natural' as const } ;
} ,
} ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
const ingest = createLocalProjectMemoryIngest ( project , {
2026-05-10 23:12:26 +02:00
agentRunner : agentRunner as never ,
runIdFactory : ( ) = > 'memory-run-1' ,
} ) ;
await expect (
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
ingest . ingest ( {
2026-05-10 23:12:26 +02:00
userId : 'local-user' ,
chatId : 'chat-1' ,
userMessage : 'define revenue as paid order value net of refunds' ,
assistantMessage : 'Captured.' ,
sourceType : 'external_ingest' ,
} ) ,
) . resolves . toEqual ( { runId : 'memory-run-1' } ) ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
await ingest . waitForRun ( 'memory-run-1' ) ;
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
await expect ( access ( join ( project . projectDir , '.ktx/db.sqlite' ) ) ) . resolves . toBeUndefined ( ) ;
await expectPathMissing ( join ( project . projectDir , '.ktx/memory-runs/memory-run-1.json' ) ) ;
2026-05-10 23:12:26 +02:00
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
await expect ( ingest . status ( 'memory-run-1' ) ) . resolves . toMatchObject ( {
2026-05-10 23:12:26 +02:00
runId : 'memory-run-1' ,
status : 'done' ,
done : true ,
captured : { wiki : [ 'revenue' ] , sl : [ ] , xrefs : [ ] } ,
2026-05-13 16:05:58 +02:00
skillsLoaded : [ 'wiki_capture' ] ,
2026-05-10 23:12:26 +02:00
signalDetected : true ,
} ) ;
2026-05-13 16:05:58 +02:00
await expect ( readFile ( join ( project . projectDir , 'wiki/global/revenue.md' ) , 'utf-8' ) ) . resolves . toContain (
2026-05-10 23:12:26 +02:00
'Revenue means paid order value net of refunds.' ,
) ;
} ) ;
it ( 'captures a semantic-layer source for a named local connection id' , async ( ) = > {
2026-05-14 17:39:31 +02:00
const project = await initKtxProject ( { projectDir : tempDir } ) ;
2026-05-13 19:37:25 +02:00
project . config . connections . warehouse = { driver : 'postgres' } ;
2026-05-10 23:12:26 +02:00
const agentRunner = {
runLoop : async ( {
toolSet ,
} : {
toolSet : Record < string , { execute : ( input : unknown , options ? : { toolCallId ? : string } ) = > Promise < unknown > } > ;
} ) = > {
await toolSet . load_skill . execute ( { name : 'sl' } ) ;
await toolSet . sl_write_source . execute (
{
connectionId : 'warehouse' ,
sourceName : 'orders' ,
source : {
name : 'orders' ,
table : 'public.orders' ,
grain : [ 'id' ] ,
columns : [ { name : 'id' , type : 'number' } ] ,
joins : [ ] ,
measures : [ { name : 'order_count' , expr : 'count(*)' } ] ,
} ,
} ,
{ toolCallId : 'sl-write' } ,
) ;
return { stopReason : 'natural' as const } ;
} ,
} ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
const ingest = createLocalProjectMemoryIngest ( project , {
2026-05-10 23:12:26 +02:00
agentRunner : agentRunner as never ,
runIdFactory : ( ) = > 'memory-run-2' ,
} ) ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
await ingest . ingest ( {
2026-05-10 23:12:26 +02:00
userId : 'local-user' ,
chatId : 'chat-2' ,
userMessage : 'going forward define orders count as count of public orders' ,
assistantMessage : 'Captured.' ,
connectionId : 'warehouse' ,
sourceType : 'external_ingest' ,
} ) ;
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
await ingest . waitForRun ( 'memory-run-2' ) ;
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
await expect ( access ( join ( project . projectDir , '.ktx/db.sqlite' ) ) ) . resolves . toBeUndefined ( ) ;
await expectPathMissing ( join ( project . projectDir , '.ktx/memory-runs/memory-run-2.json' ) ) ;
2026-05-10 23:12:26 +02:00
feat(setup): add Claude Desktop target and MCP-first agent setup (#114)
* feat(setup): add Claude Desktop target and MCP-first agent setup
Adds `ktx mcp stdio` and a `claude-desktop` setup target that generates a
local plugin ZIP wiring the analytics skill and a stdio MCP config. Replaces
the CLI-only agent install mode with MCP+analytics (default) and an optional
admin CLI skill, renames the research skill to analytics, and lets interactive
setup pick project vs global scope when every target supports it. Extracts a
shared MCP server factory used by both HTTP and stdio entrypoints.
* Add MCP agent client setup support
* Polish setup output formatting
* Add MCP tool polish design spec
Design for slimming the MCP-registered surface from 25 to 11 tools,
introducing memory_ingest, applying the per-tool polish kit (annotations,
outputSchema, .describe(), in-band error wrapping, union-drift fixes,
type-narrowed jsonToolResult), emitting progress notifications on
sql_execution + sl_query, and refining the ktx-analytics SKILL.md to
match.
* Refine MCP tool polish design spec after adversarial review iteration 1
* Refine MCP tool polish design spec after adversarial review iteration 2
* Refine MCP tool polish design spec after adversarial review iteration 3
* refactor(context): rename memory capture service to ingest
* feat(mcp): slim research tool surface
* refactor(mcp): remove admin ports from server factory
* refactor(cli): rename text ingest memory port
* docs: update analytics skill for memory ingest
* chore: verify mcp surface rename
* Add MCP tool polish v1 surface change plan
* feat(context): polish mcp tool metadata
* fix(context): enforce resolved semantic layer compute sources
* feat(context): emit mcp query progress stages
* fix(context): keep mcp progress event internal
* Add MCP tool polish v1 metadata & progress plan
* Fix CI snapshot and docs checks
2026-05-16 11:39:55 +02:00
await expect ( ingest . status ( 'memory-run-2' ) ) . resolves . toMatchObject ( {
2026-05-10 23:12:26 +02:00
runId : 'memory-run-2' ,
status : 'done' ,
captured : { wiki : [ ] , sl : [ 'orders' ] , xrefs : [ ] } ,
skillsLoaded : [ 'sl' ] ,
signalDetected : true ,
} ) ;
await expect ( readFile ( join ( project . projectDir , 'semantic-layer/warehouse/orders.yaml' ) , 'utf-8' ) ) . resolves . toContain (
'order_count' ,
) ;
} ) ;
} ) ;