diff --git a/.gitignore b/.gitignore
index 112e7faa..d1098953 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,6 @@
+# Playwright CLI session artifacts (snapshots, console logs, screenshots)
+.playwright-cli/
+
# Python
__pycache__/
*.py[cod]
diff --git a/docs-site/components/logo.tsx b/docs-site/components/logo.tsx
index 4ab8f8ba..44ab7144 100644
--- a/docs-site/components/logo.tsx
+++ b/docs-site/components/logo.tsx
@@ -1,28 +1,36 @@
export function Logo() {
return (
-
+
+
+
+ KTX
+
+
+ by Kaelio
+
+
- KTX
-
-
Docs
diff --git a/docs-site/content/docs/ai-resources/index.mdx b/docs-site/content/docs/ai-resources/index.mdx
index be315453..37bae650 100644
--- a/docs-site/content/docs/ai-resources/index.mdx
+++ b/docs-site/content/docs/ai-resources/index.mdx
@@ -1,22 +1,37 @@
---
title: AI Resources
-description: Machine-readable docs and prompt recipes for coding assistants reading KTX documentation.
+description: Machine-readable docs, retrieval paths, and prompt recipes for coding assistants using KTX documentation.
---
-Use this section when a coding assistant, IDE agent, or automation system needs to understand the KTX documentation.
+Use this section when a coding assistant, IDE agent, or automation system needs
+to read, cite, or update KTX documentation. These resources are optimized for
+retrieval: agents can fetch small Markdown pages, use the full corpus only when
+needed, and copy prompts that point them at current setup and CLI behavior.
> **Documentation index**
>
-> Start with [`/llms.txt`](/llms.txt) to discover the available docs. Use [`/llms-full.txt`](/llms-full.txt) when the assistant needs the complete docs corpus in one Markdown response.
+> Start with [`/llms.txt`](/llms.txt) to discover the available docs. Use
+> [`/llms-full.txt`](/llms-full.txt) when the assistant needs the complete docs
+> corpus in one Markdown response.
-## Choose the right path
+## What agents can do
+
+| Need | Recommended path |
+|------|------------------|
+| Find the right setup or CLI page | Fetch [`/llms.txt`](/llms.txt), then read the smallest matching `.md` page |
+| Answer a setup question | Read [Agent Quickstart](/docs/ai-resources/agent-quickstart), then [Quickstart](/docs/getting-started/quickstart) or [ktx setup](/docs/cli-reference/ktx-setup) |
+| Quote a command or flag | Read the matching [CLI Reference](/docs/cli-reference) page as Markdown |
+| Update docs in this repo | Use [Agent Instructions](/docs/ai-resources/agent-instructions) and verify generated Markdown routes after editing |
+| Reuse a prompt | Copy from [Prompt Recipes](/docs/ai-resources/prompt-recipes) |
+
+## Section map
| Goal | Use this page |
|------|---------------|
-| Tell a coding assistant how to approach KTX docs | [Agent Quickstart](/docs/ai-resources/agent-quickstart) |
-| Fetch docs as Markdown instead of HTML | [Markdown Access](/docs/ai-resources/markdown-access) |
-| Add lightweight instructions to an assistant prompt | [Agent Instructions](/docs/ai-resources/agent-instructions) |
-| Copy prompts for common agent workflows | [Prompt Recipes](/docs/ai-resources/prompt-recipes) |
+| Give an assistant a task-first route through the docs | [Agent Quickstart](/docs/ai-resources/agent-quickstart) |
+| Fetch docs as Markdown instead of rendered HTML | [Markdown Access](/docs/ai-resources/markdown-access) |
+| Add lightweight KTX docs guidance to a system prompt | [Agent Instructions](/docs/ai-resources/agent-instructions) |
+| Copy prompts for setup, command lookup, and docs editing | [Prompt Recipes](/docs/ai-resources/prompt-recipes) |
## Available resources
@@ -26,13 +41,24 @@ Use this section when a coding assistant, IDE agent, or automation system needs
| [`/llms-full.txt`](/llms-full.txt) | Complete docs corpus in one plain-text Markdown response |
| `/docs/.md` | Per-page Markdown for any docs page |
| Page-level actions | Copy Markdown, view Markdown, or copy MDX from rendered docs pages |
-| Prompt recipes | Reusable prompts for docs lookup, setup help, and docs editing |
+| Prompt recipes | Reusable prompts for docs lookup, setup help, command discovery, and docs editing |
## Agent usage notes
-When an assistant is unsure where to begin, use this order:
+When an assistant is unsure where to begin, use this retrieval order:
1. Read [`/llms.txt`](/llms.txt).
-2. Fetch the specific Markdown page for the task.
-3. Use [Agent Quickstart](/docs/ai-resources/agent-quickstart) to choose the next command or page.
-4. Use page-level copy actions when the user wants the exact Markdown or MDX source.
+2. Fetch one or two specific Markdown pages for the task.
+3. Use [Agent Quickstart](/docs/ai-resources/agent-quickstart) to choose the
+ next command, guide, or CLI reference page.
+4. Use [`/llms-full.txt`](/llms-full.txt) only when the answer requires broad
+ context across setup, integrations, concepts, and CLI reference.
+5. Use page-level copy actions when the user wants exact generated Markdown or
+ source MDX.
+
+## Boundaries
+
+AI Resources explain how agents consume the docs. To install KTX into an
+agent client, use [Agent Clients](/docs/integrations/agent-clients). To set up a
+project, use [Quickstart](/docs/getting-started/quickstart) or
+[`ktx setup`](/docs/cli-reference/ktx-setup).
diff --git a/docs-site/content/docs/cli-reference/index.mdx b/docs-site/content/docs/cli-reference/index.mdx
index 4eb11648..c4ef07db 100644
--- a/docs-site/content/docs/cli-reference/index.mdx
+++ b/docs-site/content/docs/cli-reference/index.mdx
@@ -37,9 +37,7 @@ ktx
```
The public context-build entrypoint is `ktx ingest [connectionId]` or
-`ktx ingest --all`. Legacy command shapes such as `ktx scan`, `ktx ingest run`,
-`ktx ingest status`, `ktx ingest replay`, `ktx ingest watch`, and
-`ktx setup status` are not part of the current public CLI.
+`ktx ingest --all`.
## Global Options
diff --git a/docs-site/content/docs/community/contributing.mdx b/docs-site/content/docs/community/contributing.mdx
index 0434d159..ac960395 100644
--- a/docs-site/content/docs/community/contributing.mdx
+++ b/docs-site/content/docs/community/contributing.mdx
@@ -77,7 +77,7 @@ python/
examples/ # Example projects and fixtures
scripts/ # Workspace scripts (benchmarks, verification, release)
-docs/ # Documentation site (Fumadocs)
+docs-site/ # Documentation site (Fumadocs)
```
All TypeScript packages are ESM (`"type": "module"`) and use `NodeNext` module resolution. The Python projects use `pyproject.toml` for dependency management.
diff --git a/docs-site/content/docs/community/index.mdx b/docs-site/content/docs/community/index.mdx
new file mode 100644
index 00000000..25518bc8
--- /dev/null
+++ b/docs-site/content/docs/community/index.mdx
@@ -0,0 +1,54 @@
+---
+title: Community
+description: Contribute to KTX through code, docs, connectors, and examples.
+---
+
+KTX is an open-source context layer for database agents. The project welcomes
+focused contributions that improve setup, integrations, CLI behavior,
+documentation, connector coverage, and examples.
+
+## Where to start
+
+| Goal | Start here |
+|------|------------|
+| Prepare a local development checkout | [Contributing](/docs/community/contributing#development-setup) |
+| Understand the workspace layout | [Repository structure](/docs/community/contributing#repository-structure) |
+| Run verification before a pull request | [Running tests](/docs/community/contributing#running-tests) |
+| Add a database connector | [Adding a connector](/docs/community/contributing#adding-a-connector) |
+| Update docs for a user-visible CLI or setup change | [PR guidelines](/docs/community/contributing#pr-guidelines) |
+
+## Contribution areas
+
+| Area | Good first context |
+|------|--------------------|
+| CLI and setup | `packages/cli`, especially setup steps, command definitions, status checks, and smoke tests |
+| Context engine | `packages/context`, including project config, ingest orchestration, and semantic search |
+| Connectors | `packages/connector-*`, plus connector-specific tests and integration docs |
+| Python semantic layer | `python/ktx-sl` for planning and SQL generation |
+| Python daemon | `python/ktx-daemon` for the portable runtime API |
+| Documentation | `docs-site/content/docs` for public docs and `docs-site/tests` for docs behavior |
+
+## Development loop
+
+```bash
+pnpm install
+uv sync --all-groups
+pnpm run setup:dev
+pnpm run link:dev
+ktx-dev status
+```
+
+Use `ktx-dev` for local CLI testing after linking the development binary. Use
+the published `ktx` command when you are testing the released package in a
+separate analytics project.
+
+## Before submitting
+
+1. Keep the change focused on one behavior, connector, doc area, or workflow.
+2. Run the smallest tests that cover the changed surface.
+3. Run broader checks when changing shared exports, setup state, or generated files.
+4. Update `docs-site/content/docs/` when user-visible setup, CLI, configuration, or integration behavior changes.
+5. Do not commit local secrets, generated build output, virtualenvs, dependency directories, or local databases.
+
+For complete contributor setup and verification commands, read
+[Contributing](/docs/community/contributing).
diff --git a/docs-site/content/docs/community/meta.json b/docs-site/content/docs/community/meta.json
index 0f97320e..a9988c4e 100644
--- a/docs-site/content/docs/community/meta.json
+++ b/docs-site/content/docs/community/meta.json
@@ -1,5 +1,5 @@
{
"title": "Community",
"defaultOpen": true,
- "pages": ["contributing"]
+ "pages": ["index", "contributing"]
}
diff --git a/docs-site/content/docs/getting-started/quickstart.mdx b/docs-site/content/docs/getting-started/quickstart.mdx
index 4f0c3a65..335aedfa 100644
--- a/docs-site/content/docs/getting-started/quickstart.mdx
+++ b/docs-site/content/docs/getting-started/quickstart.mdx
@@ -1,254 +1,286 @@
---
title: Quickstart
-description: Set up KTX and build your first context in under 10 minutes.
+description: Set up KTX, build local context, and connect your coding agent.
---
-This guide walks you through `ktx setup` - an interactive wizard that configures your LLM provider, connects your database, optionally ingests from your existing tools, builds context, and installs agent integration.
+This guide gets a local analytics project ready for KTX. You will install the
+CLI, run the setup wizard, connect a database, build context, and install agent
+rules that teach your coding assistant which KTX commands to run.
-If you are a coding assistant trying to decide which KTX docs page to read, start with the [Agent Quickstart](/docs/ai-resources/agent-quickstart). This page is the human setup walkthrough.
+If you are a coding assistant choosing a docs route, start with the
+[Agent Quickstart](/docs/ai-resources/agent-quickstart). This page is the
+human setup walkthrough.
-## Workflow summary
+## What setup does
-Use this sequence when you are setting up KTX in an analytics project:
+`ktx setup` is the main project workflow. It can create or resume `ktx.yaml`,
+configure model and embedding providers, add database connections, add optional
+context sources, build the first context artifacts, and install agent
+integration.
-1. `npm install -g @kaelio/ktx` - install the published KTX CLI from npm.
-2. `ktx setup` - create or resume a KTX project.
+When you run bare `ktx` in an interactive terminal outside a KTX project, the
+CLI opens the same setup experience. Inside an existing project, `ktx setup`
+resumes incomplete work or opens a menu for changing setup, connecting an
+agent, checking status, or exploring a demo project.
-The setup wizard is stateful. If it exits before completion, rerun `ktx setup` in the same project directory to resume from the first incomplete step.
+## Install the CLI
-## Install and run setup
-
-Install the published [`@kaelio/ktx`](https://www.npmjs.com/package/@kaelio/ktx) CLI:
+Install the published `@kaelio/ktx` package:
```bash
npm install -g @kaelio/ktx
```
-Then run the setup wizard:
+Then run setup from the analytics project directory:
```bash
ktx setup
```
-The local checkout flow is only for contributors working on KTX itself. See [Contributing](/docs/community/contributing) for that setup.
+The local checkout workflow is only for KTX contributors. See
+[Contributing](/docs/community/contributing) for that path.
-The wizard walks through six steps. You can go back at any point, and if you exit early, rerunning `ktx setup` resumes where you left off.
+## Step 1: Choose the project
-## Step 1: Configure LLM
+In an interactive terminal, setup can create a new KTX project or resume the
+nearest existing project. The main project file is `ktx.yaml`.
-KTX uses an Anthropic model to enrich schema descriptions, generate semantic sources during ingestion, and reconcile metadata from your tools.
+For scripted setup, pass the project directory explicitly:
-The wizard asks how to find your API key:
-
-```
-◆ How should KTX find your Anthropic API key?
-│ ○ Use ANTHROPIC_API_KEY from the environment
-│ ○ Paste a key and save it as a local secret file
+```bash
+ktx setup --project-dir ./analytics
```
-If you choose to paste a key, KTX saves it in `.ktx/secrets/anthropic-api-key` with local file permissions. Your `ktx.yaml` stores a `file:` reference, never the raw key.
+If setup exits early, rerun `ktx setup` in the same directory. KTX tracks
+completed setup steps and resumes from the remaining work.
-Next, choose a model:
+## Step 2: Configure the LLM
-```
-◆ Which Anthropic model should KTX use?
-│ ○ Claude Sonnet 4.6 (recommended)
-│ ○ Claude Opus 4.6
-│ ○ Claude Haiku 4.5
-│ ○ Enter a model ID manually
-```
+KTX uses a Claude model for ingest agents that turn schemas, SQL, BI metadata,
+and documents into semantic-layer sources and wiki context.
-KTX runs a health check to verify your key and model work before saving.
+Setup supports two LLM provider paths:
-## Step 2: Configure embeddings
+| Provider | Use when | Credential model |
+|----------|----------|------------------|
+| Anthropic API | You have an Anthropic API key | `ANTHROPIC_API_KEY` or a local `file:` secret |
+| Google Vertex AI for Anthropic Claude | Your organization runs Claude through Google Cloud | Application Default Credentials plus Vertex project and location |
-KTX uses embeddings for semantic search over sources, wiki content, schema metadata, and relationship evidence.
+For Anthropic API, setup can read the key from the environment or save a pasted
+key to `.ktx/secrets/anthropic-api-key`. `ktx.yaml` stores an `env:` or `file:`
+reference, not the raw key.
-```
-◆ Which embedding option should KTX use?
-│ ○ Local sentence-transformers embeddings
-│ ○ OpenAI embeddings (recommended)
-```
+For Vertex AI, setup uses Google Application Default Credentials. It can read
+your active `gcloud` project, list visible projects, or accept explicit
+`--vertex-project` and `--vertex-location` values.
-**OpenAI embeddings** use `text-embedding-3-small` (1536 dimensions) and require an `OPENAI_API_KEY`.
+Setup checks the selected model before saving. Anthropic API setup fetches live
+Claude model choices when possible and falls back to bundled defaults if model
+discovery is unavailable.
-**Local embeddings** use `all-MiniLM-L6-v2` (384 dimensions) via the KTX managed Python runtime. No API key is needed. KTX can install and start the runtime during setup; to prepare it ahead of time, run:
+## Step 3: Configure embeddings
+
+KTX uses embeddings for semantic search over semantic-layer sources, wiki
+context, schema metadata, and relationship evidence.
+
+| Backend | Default model | Notes |
+|---------|---------------|-------|
+| OpenAI | `text-embedding-3-small` | Recommended for hosted embeddings. Requires an OpenAI API key. |
+| Local sentence-transformers | `all-MiniLM-L6-v2` | Runs through the KTX-managed Python runtime. No hosted embedding key is required. |
+
+OpenAI setup reads `OPENAI_API_KEY` or saves a local secret file. Local
+sentence-transformers setup can install and start the managed runtime during
+setup. To prepare that runtime before setup, run:
```bash
ktx dev runtime install --feature local-embeddings --yes
ktx dev runtime start --feature local-embeddings
```
-## Step 3: Connect a database
+## Step 4: Add a database
-Select one or more databases for KTX to connect to. The wizard supports
-SQLite, PostgreSQL, MySQL, ClickHouse, SQL Server, BigQuery, and Snowflake.
+KTX needs at least one primary database connection before it can build database
+context. The wizard supports SQLite, PostgreSQL, MySQL, ClickHouse, SQL Server,
+BigQuery, and Snowflake.
-For PostgreSQL, you can enter connection details field by field or paste a connection URL:
+You can usually enter connection fields interactively or provide a URL. Secret
+URLs can be stored as local files under `.ktx/secrets/` or referenced with
+`env:NAME` in `ktx.yaml`.
-```
-◆ How do you want to connect to PostgreSQL?
-│ ○ Enter connection details (host, port, database, user)
-│ ○ Paste a connection URL
-```
+After saving a connection, setup tests it and builds fast schema context:
-If your URL contains credentials, KTX saves it to `.ktx/secrets/` and writes a `file:` reference in `ktx.yaml`. You can also use `env:DATABASE_URL` to reference an environment variable.
-
-After connecting, KTX automatically runs a connection test and builds fast
-schema context:
-
-```
-Testing postgres-warehouse
+```text
+Testing warehouse
Connection test passed
- Driver: PostgreSQL - Status: ok
-Building schema context for postgres-warehouse
+Building schema context for warehouse
Running fast database ingest
-Schema context complete for postgres-warehouse
- Changes: 42 new tables
-
Database ready
- postgres-warehouse - PostgreSQL - schema context complete
+ warehouse - PostgreSQL - schema context complete
```
-For PostgreSQL, Snowflake, and BigQuery, the wizard can enable query-history
-ingest when the warehouse history feature is available. Query history is stored
-under `connections..context.queryHistory` in `ktx.yaml`.
+PostgreSQL, BigQuery, and Snowflake can also enable query-history ingest. Query
+history helps KTX learn common query patterns, joins, service-account filters,
+and warehouse-specific usage.
-## Step 4: Add context sources
+## Step 5: Add context sources
-Context sources let KTX ingest metadata from your existing analytics tools. This step is optional - you can skip it and add sources later.
+Context sources are optional, but they make the first context layer much richer.
+Setup can add:
-```
-◆ Which context sources should KTX ingest?
-│ ◻ dbt
-│ ◻ MetricFlow
-│ ◻ Metabase
-│ ◻ Looker
-│ ◻ LookML
-│ ◻ Notion
-```
+| Source | Typical input | What KTX learns |
+|--------|---------------|-----------------|
+| dbt | Local project or Git repo | Models, columns, tests, descriptions, tags |
+| MetricFlow | Local project or Git repo | Semantic models, metrics, dimensions, entities |
+| LookML | Local files or Git repo | Views, explores, dimensions, measures, joins |
+| Looker | API URL and credentials | Explores, looks, dashboards, model metadata |
+| Metabase | API URL and key | Questions, dashboards, BI database mappings |
+| Notion | Integration token and crawl settings | Business docs and knowledge pages |
-For **dbt**, point KTX at a local path or git URL. KTX reads your `dbt_project.yml` and schema files to extract model metadata:
+Setup maps BI and source metadata back to your primary warehouse connection so
+generated context points at the right tables.
-```
-◆ dbt source location
-│ ○ Local path
-│ ○ Git URL
-```
+You can skip this step and add sources later by rerunning `ktx setup`.
-For **Metabase** and **Looker**, you provide an API URL and credentials. KTX maps BI databases to your KTX primary source connections so it knows which warehouse tables the BI metadata refers to.
+## Step 6: Build context
-Context sources are saved to `ktx.yaml` and built during the next step.
+The context build turns configured databases and sources into local artifacts
+agents can read. It runs database ingest first, then source ingest and memory
+updates.
-## Step 5: Build context
+Fast database ingest records deterministic schema grounding. Deep ingest adds
+AI-enriched descriptions, embeddings, relationship evidence, and query-history
+context when configured.
-This is where KTX builds agent-ready context. It uses the database context
-depth saved by setup and ingests metadata from any configured context sources.
+When the build finishes, setup verifies that agent-ready context exists:
-```
-◆ Build KTX context for agents?
-│ ○ Build context now (recommended)
-│ ○ Leave context unbuilt and exit setup
-```
-
-Fast database context builds deterministic schema grounding. Deep database
-context also generates AI descriptions, embeddings, and relationship evidence
-when those capabilities are configured.
-
-For a small database (under 50 tables), this can take a few minutes. Larger
-warehouses can take longer. Context builds run in the foreground; press
-Ctrl+C to stop the current run and rerun `ktx setup` or `ktx ingest`
-when you are ready to try again.
-
-When the build completes, KTX verifies that agent-ready context was produced:
-
-```
+```text
KTX context is ready for agents.
Databases:
- postgres-warehouse: deep context complete
+ warehouse: deep context complete
Context sources:
- dbt-main: memory update complete
+ dbt_main: memory update complete
Verification:
Agent context: ready
Semantic search: ready
```
-## Step 6: Install agent integration
+If a foreground build is interrupted, rerun `ktx setup` or build the same target
+with `ktx ingest `.
-The final step connects KTX to your coding agent. Choose how agents should access the project:
+## Step 7: Install agent integration
-```
-◆ How should agents use this KTX project?
-│ ○ CLI tools and skills
+The final setup step installs project-local rules for your coding assistant.
+Supported targets are Claude Code, Codex, Cursor, OpenCode, and universal
+`.agents`.
+
+You can also run this step later:
+
+```bash
+ktx setup --agents --target codex
```
-Then select which agents to install for:
+Claude Code and Codex also support global installs:
-```
-◆ Which agent targets should KTX install?
-│ ◻ Claude Code
-│ ◻ Codex
-│ ◻ Cursor
-│ ◻ OpenCode
-│ ◻ Custom agent (.agents)
+```bash
+ktx setup --agents --target codex --global
```
-**CLI mode** writes a skill file (e.g., `.claude/skills/ktx/SKILL.md`) that teaches the agent to call KTX commands directly.
-
-**Custom agent** uses the universal `.agents` target for agents that can read project-local skills.
+Agent rules are CLI-based. They point agents at the KTX CLI path that created
+the file, so agents do not need a separate `ktx` binary in `PATH`. If the CLI
+path changes after reinstalling or moving a checkout, rerun `ktx setup --agents`.
## Generated files
-KTX writes project state as plain files so agents can inspect and edit changes in git.
+KTX writes plain files so people and agents can inspect changes in git.
-| Path | Created by | Purpose |
-|------|------------|---------|
-| `ktx.yaml` | `ktx setup` | Main project configuration: connections, LLM settings, embeddings, and context sources |
-| `.ktx/secrets/*` | `ktx setup` when file-backed secrets are selected | Local secret files referenced from `ktx.yaml`; do not commit these |
-| `semantic-layer//*.yaml` | context build, ingestion, or direct file edits | Semantic source definitions agents use for SQL generation |
-| `wiki/global/*.md` | ingestion, memory capture, or direct file edits | Shared business context and metric definitions |
-| `wiki/user//*.md` | memory capture or direct file edits | User-scoped notes for one agent/user context |
-| `.claude/skills/ktx/SKILL.md`, `.agents/skills/ktx/SKILL.md` | CLI-mode agent integration setup | Agent instructions for calling public `ktx` commands |
+| Path | Purpose |
+|------|---------|
+| `ktx.yaml` | Project configuration for LLMs, embeddings, connections, context sources, and setup state |
+| `.ktx/secrets/*` | Local secret files referenced from `ktx.yaml`; do not commit these |
+| `.ktx/setup/*` | Local setup and context-build state |
+| `.ktx/agents/install-manifest.json` | Manifest used to manage installed agent files |
+| `semantic-layer//*.yaml` | Semantic source definitions used for SQL generation |
+| `wiki/global/*.md` | Shared business context and metric definitions |
+| `wiki/user//*.md` | User-scoped notes and local context |
+| `.claude/skills/ktx/SKILL.md` | Claude Code project skill |
+| `.agents/skills/ktx/SKILL.md` | Codex or universal project skill |
+| `.cursor/rules/ktx.mdc` | Cursor project rule |
+| `.opencode/commands/ktx.md` | OpenCode project command |
-## Verify it worked
+## Verify setup
-Check your project status:
+Run:
```bash
ktx status
```
-```
+Example output:
+
+```text
KTX project: /home/user/analytics
Project ready: yes
LLM ready: yes (claude-sonnet-4-6)
Embeddings ready: yes (text-embedding-3-small)
-Databases configured: yes (postgres-warehouse)
-Context sources configured: yes (dbt-main)
+Databases configured: yes (warehouse)
+Context sources configured: yes (dbt_main)
KTX context built: yes
-Agent integration ready: yes (claude-code:project)
+Agent integration ready: yes (codex:project)
```
+Use JSON when an agent or script needs a structured readiness check:
+
+```bash
+ktx status --json
+```
+
+## Scripted setup example
+
+Use non-interactive setup when creating repeatable fixtures or automation:
+
+```bash
+ktx setup \
+ --project-dir ./analytics \
+ --no-input \
+ --skip-llm \
+ --skip-embeddings \
+ --database postgres \
+ --new-database-connection-id warehouse \
+ --database-url env:DATABASE_URL \
+ --database-schema public
+```
+
+Then build context:
+
+```bash
+ktx ingest warehouse --fast
+```
+
+See [ktx setup](/docs/cli-reference/ktx-setup) for the full automation flag
+surface.
+
## Common errors
-| Error or symptom | Likely cause | Recovery |
-|------------------|--------------|----------|
-| `ktx: command not found` | The KTX package is not installed globally, or the shell cannot find the global binary | Run `npm install -g @kaelio/ktx` and open a new shell |
-| LLM health check fails | Missing, invalid, or unauthorized Anthropic API key | Export `ANTHROPIC_API_KEY` or rerun `ktx setup` and choose the file-backed secret option |
-| OpenAI embedding check fails | `OPENAI_API_KEY` is missing when OpenAI embeddings are selected | Export `OPENAI_API_KEY`, or rerun setup and choose local sentence-transformers embeddings |
-| Local embeddings hang or fail | The managed Python runtime cannot start or the local model runtime is unavailable | Install `uv`, run `ktx dev runtime status`, then run `ktx dev runtime install --feature local-embeddings --yes` and rerun setup |
-| Database connection test fails | Credentials, network access, warehouse, database, or schema value is wrong | Test the same URL with the database's native client, then rerun `ktx setup` and reconfigure the connection |
-| `KTX context built: no` in `ktx status` | Setup saved configuration but did not build context | Run `ktx setup` and choose to build context now |
-| Agent integration is incomplete | Setup skipped the agents step or the target was not installed | Run `ktx setup --agents --target codex` using the target you need |
+| Symptom | Likely cause | Recovery |
+|---------|--------------|----------|
+| `ktx: command not found` | The global package is not installed or your shell cannot find it | Reinstall `@kaelio/ktx` and open a new shell |
+| Setup resumes the wrong project | `KTX_PROJECT_DIR` or the nearest `ktx.yaml` points somewhere else | Pass `--project-dir ` |
+| Anthropic health check fails | API key, model id, or access is invalid | Fix `ANTHROPIC_API_KEY` or rerun setup with a different key or model |
+| Vertex AI health check fails | Vertex API, Claude access, project, location, or IAM permissions are missing | Check the project, location, Application Default Credentials, and Vertex AI permissions |
+| OpenAI embeddings fail | `OPENAI_API_KEY` is missing or invalid | Export the key or choose local sentence-transformers embeddings |
+| Local embeddings fail | Managed Python runtime cannot install or start | Run `ktx dev runtime status`, then install the local embeddings runtime |
+| Database test fails | Credentials, network access, database, warehouse, or schema is wrong | Test the same values with the database's native client, then rerun setup |
+| Context is not built | Setup saved configuration but skipped or interrupted the build | Run `ktx setup` or `ktx ingest --all` |
+| Agent integration is incomplete | Setup skipped the agents step or installed a different target | Run `ktx setup --agents --target ` |
## Next steps
-- **Build more context** - learn about [database ingest](/docs/guides/building-context), relationship detection, and source ingestion workflows in the Building Context guide.
-- **Refine your semantic layer** - the [Writing Context](/docs/guides/writing-context) guide covers source YAML, measures, joins, and wiki pages.
-- **Understand the architecture** - read [The Context Layer](/docs/concepts/the-context-layer) to learn why a context layer is more than a semantic layer.
-- **Connect more agents** - see the [Agent Clients](/docs/integrations/agent-clients) integration page for per-tool setup details.
+- Build and refresh context with [Building Context](/docs/guides/building-context).
+- Edit semantic sources and wiki pages with [Writing Context](/docs/guides/writing-context).
+- Connect more tools with [Agent Clients](/docs/integrations/agent-clients).
+- Read [The Context Layer](/docs/concepts/the-context-layer) to understand the architecture.
diff --git a/docs-site/content/docs/guides/building-context.mdx b/docs-site/content/docs/guides/building-context.mdx
index e18bc3cb..c21b7921 100644
--- a/docs-site/content/docs/guides/building-context.mdx
+++ b/docs-site/content/docs/guides/building-context.mdx
@@ -1,171 +1,195 @@
---
title: Building Context
-description: Build database and source context from configured KTX connections.
+description: Build and refresh KTX context from databases, source tools, query history, and text.
---
-Building context reads your configured connections and writes local context that
-agents can use. Database connections produce schema context, and source
-connections such as dbt, Looker, Metabase, and Notion produce semantic sources
-and wiki pages.
+Building context turns configured connections into local semantic-layer sources
+and wiki pages. Agents use those files to understand your schema, business
+definitions, metric logic, joins, and known caveats before they write SQL.
+
+Use this guide after `ktx setup` has created `ktx.yaml` and at least one
+database or context-source connection.
+
+## The build loop
+
+Most projects use this loop:
+
+1. Check readiness with `ktx status`.
+2. Build one connection with `ktx ingest `, or build everything
+ with `ktx ingest --all`.
+3. Search or inspect the generated files under `semantic-layer/` and `wiki/`.
+4. Edit source YAML or Markdown when business logic needs refinement.
+5. Validate and query representative sources before handing the context to an
+ agent.
+
+`ktx ingest --all` runs database connections first, then context-source
+connections. That order lets dbt, BI, Notion, and text ingest attach context to
+known warehouse tables.
## Database ingest
-Database ingest connects to your warehouse and extracts structural metadata.
-KTX stores the results locally so agents can understand your schema without
-querying the database directly.
-
-### Running database ingest
+Database ingest connects to a configured warehouse and records local schema
+context. It gives agents table, column, type, constraint, and row-count
+grounding without requiring them to inspect the database directly.
```bash
-ktx ingest
-```
-
-This runs a fast schema ingest by default. You can choose the depth with public
-flags:
-
-| Flag | What it does |
-|------|-------------|
-| `--fast` | Tables, columns, types, constraints, and row counts |
-| `--deep` | Fast ingest plus AI-enriched database context |
-
-```bash
-# Build one connection quickly
-ktx ingest my-postgres --fast
-
-# Build AI-enriched database context
-ktx ingest my-postgres --deep
+# Build one configured database connection
+ktx ingest warehouse
# Build all configured connections
ktx ingest --all
```
-### Checking results
+Depth controls how much context KTX builds:
-Every ingest prints a summary and writes local artifacts. Use `ktx status`
-after ingest to review project readiness and follow-up setup work:
+| Flag | Best for | What it does |
+|------|----------|--------------|
+| `--fast` | First setup, quick refreshes, CI smoke checks | Deterministic schema ingest with tables, columns, types, constraints, and row counts |
+| `--deep` | Agent-ready context for real analysis | Fast ingest plus AI-enriched descriptions, embeddings, relationship evidence, and optional query history |
+
+Examples:
```bash
-ktx status
+ktx ingest warehouse --fast
+ktx ingest warehouse --deep
+ktx ingest --all --deep
```
-### Relationship detection
+Deep ingest needs LLM and embedding readiness. If those providers are not
+configured, run `ktx setup` or use `--fast`.
-Many databases lack declared foreign keys. KTX infers relationships by scoring column pairs across seven signals - name similarity, type compatibility, value overlap, embedding similarity, profile uniqueness, null rate, and structural priors. The weighted score determines each candidate's status:
+## Query history
-| Score range | Status | Meaning |
-|-------------|--------|---------|
-| ≥ 0.85 | `accepted` | High confidence - applied automatically |
-| 0.55 – 0.84 | `review` | Plausible - needs human review |
-| < 0.55 | `rejected` | Low confidence - not applied |
+PostgreSQL, BigQuery, and Snowflake can add query-history context. This helps
+KTX learn common joins, filters, service-account patterns, redaction rules, and
+usage-heavy query templates.
-Deep database ingest can include relationship evidence where the connector can
-provide it. Relationship review and calibration subcommands are not part of the
-current public CLI surface.
-
-## Ingestion
-
-Ingestion pulls semantic context from your existing analytics tools - dbt projects, Looker models, Metabase questions, and more - and writes it into your KTX project as semantic sources and wiki pages.
-
-### How it works
-
-Each ingest run follows this flow:
-
-1. An **adapter** extracts metadata from your tool (dbt manifest, LookML files, Metabase API, etc.)
-2. An **LLM agent** reconciles the extracted metadata with your existing context - it merges intelligently rather than overwriting
-3. **Semantic sources** (YAML) and **wiki pages** (Markdown) are written to your project directory
-
-### Running an ingest
+Enable it during setup, store it under `connections..context.queryHistory`,
+or request it for one run:
```bash
-ktx ingest my-dbt-source
+ktx ingest warehouse --deep --query-history
+ktx ingest warehouse --query-history-window-days 30
```
-Useful output flags:
+Use `--no-query-history` when you want to skip a stored query-history setting
+for one run.
+
+## Relationship evidence
+
+Many databases do not declare all foreign keys. KTX can score relationship
+candidates using signals such as name similarity, type compatibility, value
+overlap, embedding similarity, uniqueness, null rate, and structural priors.
+
+The public CLI does not expose separate relationship review subcommands.
+Relationship evidence is built as part of deep database ingest when the
+connector and readiness checks support it.
+
+## Context-source ingest
+
+Context-source connections pull business metadata from tools your team already
+uses. The current public `ktx ingest` command is connection-centric: pass one
+configured connection id, or pass `--all`.
+
+```bash
+# Build one source connection
+ktx ingest dbt_main
+
+# Build every configured database and source connection
+ktx ingest --all
+```
+
+Supported source types:
+
+| Driver | Typical source | Output |
+|--------|----------------|--------|
+| `dbt` | dbt project or Git repo | Semantic sources with model, column, test, tag, and description metadata |
+| `metricflow` | MetricFlow project or Git repo | Metrics, dimensions, entities, and semantic joins |
+| `lookml` | LookML files or Git repo | Views, explores, dimensions, measures, and joins |
+| `looker` | Looker API | Explores, looks, dashboards, and model metadata |
+| `metabase` | Metabase API | Questions, dashboards, table metadata, and mappings |
+| `notion` | Notion API | Wiki pages and business knowledge |
+
+Source ingest extracts metadata, reconciles it with existing local context, and
+writes semantic-layer YAML plus wiki Markdown. It merges rather than blindly
+overwriting local edits.
+
+## Text ingest
+
+Use `ktx ingest text` for notes, Markdown files, runbooks, Slack exports, or
+other free-form knowledge that should become searchable KTX memory.
+
+```bash
+# Capture a Markdown file
+ktx ingest text docs/revenue-notes.md --connection-id warehouse
+
+# Capture one stdin item
+printf "Refunds are excluded from net revenue." | ktx ingest text -
+
+# Capture direct text
+ktx ingest text --text "ARR excludes one-time implementation fees."
+```
+
+Useful flags:
| Flag | Description |
|------|-------------|
-| `--json` | Output as JSON |
-| `--plain` | Plain text output |
+| `--connection-id ` | Attach the captured memory to a KTX connection |
+| `--user-id ` | Attribute capture to a user scope, default `local-cli` |
+| `--json` | Print structured output |
+| `--fail-fast` | Stop after the first failed text item |
-Foreground context builds do not detach into background control sessions. If a
-run is interrupted, rerun `ktx ingest ` or `ktx ingest --all`.
+Text ingest is a good fit for small, high-signal documents. For system-specific
+connectors such as Notion, dbt, or Metabase, prefer configured source ingest so
+KTX can preserve source metadata.
-### Supported context sources
+## Output and artifacts
-| Driver | Source | What gets ingested |
-|--------|--------|--------------------|
-| `dbt` | dbt project | Model definitions, column descriptions, tests, tags |
-| `metricflow` | MetricFlow semantic models | Metrics, dimensions, entities, semantic joins |
-| `lookml` | LookML files | Views, explores, dimensions, measures, joins |
-| `looker` | Looker API | Explores, looks, dashboard metadata |
-| `metabase` | Metabase API | Questions, dashboards, table metadata |
-| `notion` | Notion API | Database pages, knowledge articles |
+Every ingest run prints a summary. Use `--json` when an agent or script needs a
+structured plan and per-target results.
-Query history is a database connection facet. Enable it with
-`connections..context.queryHistory` or pass `--query-history` for a current
-run. See [Context Sources](/docs/integrations/context-sources) for
-driver-specific setup and auth configuration.
-
-### What gets generated
-
-A typical dbt ingest produces semantic sources and wiki pages in your project:
-
-**Semantic source** (`semantic-layer/my-postgres/orders.yaml`):
-
-```yaml title="semantic-layer/my-postgres/orders.yaml"
-name: orders
-table: public.orders
-grain:
- - order_id
-columns:
- - name: order_id
- type: string
- description: Unique order identifier
- - name: customer_id
- type: string
- description: Foreign key to customers table
- - name: order_date
- type: time
- role: time
- description: Date the order was placed
- - name: total_amount
- type: number
- description: Total order value in USD
-measures:
- - name: total_revenue
- expr: SUM(total_amount)
- description: Sum of all order values
- - name: order_count
- expr: COUNT(DISTINCT order_id)
- description: Number of distinct orders
-joins:
- - to: customers
- on: orders.customer_id = customers.customer_id
- relationship: many_to_one
+```bash
+ktx ingest --all --json
```
-**Wiki page** (`wiki/global/order-status-definitions.md`):
+Typical generated files:
-```markdown
----
-summary: Business definitions for order status values
-tags: [orders, definitions]
-sl_refs: [orders]
----
+| Path | Created by | Purpose |
+|------|------------|---------|
+| `semantic-layer//*.yaml` | Database and source ingest | Queryable semantic source definitions |
+| `wiki/global/*.md` | Source, text, and memory ingest | Shared business definitions and notes |
+| `wiki/user//*.md` | Text and memory ingest | User-scoped context |
+| `.ktx/setup/context-build.json` | Setup context build | Resume and readiness state for setup |
-## Order Statuses
+Ingest sessions also record transcripts with tool calls, LLM responses, and
+write decisions. Inspect them when you need to debug why a source or wiki page
+was written a certain way.
-- **pending**: Order placed but not yet processed
-- **confirmed**: Payment received, awaiting fulfillment
-- **shipped**: Order dispatched to carrier
-- **delivered**: Order received by customer
-- **cancelled**: Order cancelled before shipment
+## Example: first full refresh
-Orders in "pending" status for more than 48 hours are flagged for review.
+After interactive setup:
+
+```bash
+ktx status
+ktx ingest --all --deep
+ktx status
```
-### Ingest transcripts
+Then inspect what changed:
-Every ingest session records a full transcript: tool calls, LLM responses, and
-write decisions. Inspect the stored transcript files when you need to debug why
-a source was written a certain way.
+```bash
+git status --short
+ktx sl list --json
+ktx wiki search "revenue" --json --limit 10
+```
+
+## Common errors
+
+| Symptom | Likely cause | Recovery |
+|---------|--------------|----------|
+| Connection not configured | The connection id is missing from `ktx.yaml` | Add it with `ktx setup` |
+| Deep readiness is missing | LLM or embeddings are not setup-ready | Run `ktx setup`, or rerun with `--fast` |
+| Query history is unsupported | The selected database driver does not expose query history | Run schema ingest without query-history flags |
+| No target selected | You omitted both a connection id and `--all` | Run `ktx ingest ` or `ktx ingest --all` |
+| Source flags have no effect | Depth and query-history flags were supplied for a source connector | Use those flags only for database connections |
+| Text ingest stops early | `--fail-fast` stopped on the first failed item | Fix the item or rerun without `--fail-fast` |
diff --git a/docs-site/content/docs/guides/serving-agents.mdx b/docs-site/content/docs/guides/serving-agents.mdx
index 4a93ae43..192b1c7f 100644
--- a/docs-site/content/docs/guides/serving-agents.mdx
+++ b/docs-site/content/docs/guides/serving-agents.mdx
@@ -1,59 +1,167 @@
---
title: Serving Agents
-description: Expose your context to Claude Code, Cursor, Codex, and other coding agents.
+description: Expose KTX context to Claude Code, Codex, Cursor, OpenCode, and custom agents.
---
-Once you've built and refined your context, expose it to coding agents through
-the public KTX CLI. Claude Code, Cursor, Codex, OpenCode, and custom agent
-workflows can call the same commands you use at a terminal.
+KTX serves agents through the public CLI and project-local instruction files.
+Agents do not need a separate server. They read the generated rules, call KTX
+commands, inspect local context files, and use JSON output when they need
+structured results.
-## CLI Commands
+## Recommended setup
-KTX public commands support JSON output for the context reads that agents use
-most often. Use `--project-dir` when the agent is not already running inside the
-KTX project directory.
-
-### Available commands
+Run the agent install step from a KTX project:
+
+```bash
+ktx setup --agents
+```
+
+Or install a specific target:
+
+```bash
+ktx setup --agents --target codex
+```
+
+Supported targets:
+
+| Target | Generated project file |
+|--------|------------------------|
+| Claude Code | `.claude/skills/ktx/SKILL.md` |
+| Codex | `.agents/skills/ktx/SKILL.md` |
+| Cursor | `.cursor/rules/ktx.mdc` |
+| OpenCode | `.opencode/commands/ktx.md` |
+| Universal `.agents` | `.agents/skills/ktx/SKILL.md` |
+
+Claude Code and Codex also support global installs:
+
+```bash
+ktx setup --agents --target claude-code --global
+ktx setup --agents --target codex --global
+```
+
+KTX records installed files in `.ktx/agents/install-manifest.json`. Rerun
+`ktx setup --agents` after moving a checkout or reinstalling the CLI so the
+generated instructions point at the current CLI path.
+
+## Agent command set
+
+All supported agent clients use the same command surface. Use `--project-dir`
+when the agent is running outside the KTX project directory.
+
+### Readiness
```bash
-# Check setup and context readiness
ktx status --json
```
-**Semantic layer:**
+Agents should run this before relying on context. It reports project, LLM,
+embedding, database, context-source, context-build, and agent-integration
+readiness.
+
+### Semantic layer discovery
```bash
-# List sources
ktx sl list --json
-ktx sl list --json --connection-id my-postgres
-ktx sl search "revenue" --json
+ktx sl list --connection-id warehouse --json
+ktx sl search "revenue" --json --limit 10
+```
-# Run a query from a JSON file
-ktx sl query --json \
- --connection-id my-postgres \
- --query-file query.json \
+Agents use these commands to discover source names, connection ids, measures,
+dimensions, and likely files to inspect.
+
+### Semantic-layer validation and queries
+
+```bash
+ktx sl validate orders --connection-id warehouse
+```
+
+Compile SQL before executing:
+
+```bash
+ktx sl query \
+ --connection-id warehouse \
+ --measure orders.total_revenue \
+ --dimension orders.created_date \
+ --format sql
+```
+
+Execute only when the task calls for live data:
+
+```bash
+ktx sl query \
+ --connection-id warehouse \
+ --measure orders.total_revenue \
+ --dimension orders.status \
--execute \
--max-rows 100
```
-**Wiki:**
+For complex calls, agents can write a JSON query object and pass it with
+`--query-file`.
+
+### Wiki context
```bash
-# Search wiki pages
+ktx wiki list --json
ktx wiki search "revenue recognition" --json --limit 10
```
-## Setting Up Your Agent
+Agents should search wiki context when a question depends on business
+definitions, metric caveats, process rules, or terms that are not obvious from
+schema names.
-The fastest way to connect an agent is through the setup wizard:
+### Context refresh
+
+Agents can refresh context when the user asks them to:
```bash
-ktx setup
+ktx ingest warehouse --fast
+ktx ingest --all
+ktx ingest text docs/revenue-notes.md --connection-id warehouse
```
-The agents step auto-detects installed tools and generates the right
-configuration. For manual setup or per-tool details, see the
-[Agent Clients](/docs/integrations/agent-clients) integration page.
+Use `--deep` only when LLM and embedding setup is ready and the user expects an
+AI-enriched refresh.
-After configuration, the agent can immediately call KTX commands to list
-sources, search wiki pages, and query your semantic layer.
+## Good agent behavior
+
+Agents should:
+
+- Run `ktx status --json` before using KTX context.
+- Use `ktx sl search` and `ktx wiki search` before writing SQL from memory.
+- Inspect the relevant YAML or Markdown files after search returns candidates.
+- Compile SQL with `ktx sl query --format sql` before executing.
+- Use `--max-rows` whenever executing a live query.
+- Validate edited semantic sources with `ktx sl validate`.
+- Keep generated context changes reviewable in git.
+
+Agents should not assume a background server, ORPC route, frontend app, or
+external migration system exists. KTX is a local context layer with a CLI and
+plain project files.
+
+## Manual setup
+
+Manual setup is useful for custom agents that can read project-local
+instructions but are not yet a named target.
+
+1. Install the universal target:
+
+ ```bash
+ ktx setup --agents --target universal
+ ```
+
+2. Configure the agent to read `.agents/skills/ktx/SKILL.md`.
+3. Open the agent in the KTX project directory.
+4. Ask it to run `ktx status --json` and summarize readiness.
+
+For per-client notes, see [Agent Clients](/docs/integrations/agent-clients).
+
+## Troubleshooting
+
+| Symptom | Likely cause | Recovery |
+|---------|--------------|----------|
+| Agent says KTX is unavailable | Agent did not load the generated instruction file | Rerun `ktx setup --agents --target ` and restart the agent session |
+| Agent command cannot find the project | Agent is running outside the KTX directory | Add `--project-dir ` or open the agent in the project root |
+| Generated rules point at a missing CLI path | CLI was moved, rebuilt, or reinstalled | Rerun `ktx setup --agents` |
+| Agent cannot find a metric | Context is missing or stale | Run `ktx sl search`, inspect source YAML, then refresh with `ktx ingest` if needed |
+| Agent query returns too many rows | The command executed without a result cap | Require `--max-rows` for executed queries |
diff --git a/docs-site/content/docs/guides/writing-context.mdx b/docs-site/content/docs/guides/writing-context.mdx
index 488e11e2..fe9d3fdb 100644
--- a/docs-site/content/docs/guides/writing-context.mdx
+++ b/docs-site/content/docs/guides/writing-context.mdx
@@ -1,295 +1,341 @@
---
title: Writing Context
-description: Write and refine semantic sources and wiki pages.
+description: Edit semantic sources and wiki pages so agents use your business logic.
---
-After building context through scanning and ingestion, you'll want to refine it - edit semantic sources to match your business logic, add wiki pages that capture tribal knowledge, and query your data through the semantic layer to verify everything works.
+KTX context is meant to be edited. Ingest gives you a grounded first draft, then
+you refine source YAML and wiki Markdown until agents can answer data questions
+with the same definitions your team uses.
-## Agent workflow summary
+Use this guide when you are adding measures, fixing joins, documenting business
+rules, or reviewing context changes made by an agent.
-Agents should refine context in this order:
+## Editing workflow
-1. `ktx sl list --json` - discover available sources and connection ids.
-2. `ktx sl search --json` - find source candidates for a concept.
-3. Edit the source YAML directly in `semantic-layer//`.
-4. `ktx sl validate --connection-id ` - verify columns, joins, and table references.
-5. `ktx sl query ... --format sql` - compile a representative query without executing it.
-6. `ktx wiki search ...` - check business context captured by ingest or memory.
+Use this order for most context changes:
-## Semantic Sources
+1. Discover existing context.
-Semantic sources are YAML files that describe your tables, columns, measures, and joins. They're the core of the context layer - the structured definitions that agents use to generate correct SQL.
+ ```bash
+ ktx sl list --json
+ ktx sl search "revenue" --json
+ ktx wiki search "revenue recognition" --json --limit 10
+ ```
-### Listing sources
+2. Edit the smallest relevant files under `semantic-layer//` or
+ `wiki/`.
+3. Validate semantic source changes.
-```bash
-# List all sources across connections
-ktx sl list
+ ```bash
+ ktx sl validate orders --connection-id warehouse
+ ```
-# List sources for a specific connection
-ktx sl list --connection-id my-postgres
+4. Compile a representative query before executing it.
-# Output as JSON
-ktx sl list --json
+ ```bash
+ ktx sl query \
+ --connection-id warehouse \
+ --measure orders.total_revenue \
+ --dimension orders.created_date \
+ --format sql
+ ```
+
+5. Search again using likely user wording to confirm the new context is
+ discoverable.
+
+## Semantic sources
+
+Semantic sources are YAML files that describe queryable entities. A source is
+usually a table, but it can also point at a custom SQL expression. Sources
+define the vocabulary agents use for measures, dimensions, segments, joins, and
+grain-aware query planning.
+
+Source files live at:
+
+```text
+semantic-layer//.yaml
```
-### Searching sources
-
-```bash
-ktx sl search "revenue" --connection-id my-postgres --json
-```
-
-Search returns ranked source summaries. To inspect or edit a source, open the
-YAML file under `semantic-layer//`.
-
-### The source schema
-
-A semantic source defines a single queryable entity - usually a table or a SQL expression. Here's a fully annotated example:
+### Minimal source
```yaml
name: orders
-description: Customer orders with line-item totals
-table: public.orders # or use `sql:` for a custom SQL expression
+description: Customer orders with booked revenue.
+table: public.orders
grain:
- - order_id # columns that uniquely identify a row
+ - order_id
+columns:
+ - name: order_id
+ type: string
+ description: Unique order identifier.
+ - name: order_date
+ type: time
+ role: time
+ description: Date the order was placed.
+ - name: total_amount
+ type: number
+ description: Booked order value in USD.
+measures:
+ - name: total_revenue
+ expr: SUM(total_amount)
+ description: Sum of booked order value before refunds.
+```
+
+### Full source shape
+
+```yaml
+name: orders
+description: Customer orders with line-item totals.
+table: public.orders
+grain:
+ - order_id
columns:
- name: order_id
- type: string # string | number | time | boolean
- description: Unique order identifier
+ type: string
+ description: Unique order identifier.
- name: order_date
type: time
- role: time # marks this as the default time dimension
- description: Date the order was placed
+ role: time
+ description: Date the order was placed.
- name: status
type: string
- visibility: public # public (default) | internal | hidden
- description: Current order status
+ visibility: public
+ description: Current order status.
- name: _etl_loaded_at
type: time
- visibility: hidden # hidden columns are excluded from agent queries
- description: Internal ETL timestamp
+ visibility: hidden
+ description: Internal load timestamp.
- name: total_amount
type: number
- description: Order total in USD
+ description: Order total in USD.
measures:
- name: total_revenue
expr: SUM(total_amount)
- description: Sum of all order values
+ description: Sum of all order values.
- name: order_count
expr: COUNT(DISTINCT order_id)
- description: Number of distinct orders
+ description: Number of distinct orders.
- name: avg_order_value
expr: AVG(total_amount)
- description: Average order value
+ description: Average booked order value.
- name: high_value_revenue
expr: SUM(total_amount)
filter: total_amount > 100
- description: Revenue from orders over $100
+ description: Revenue from orders over $100.
segments:
- - name: us_orders
- expr: country = 'US'
- description: Orders from US customers
+ - name: completed_orders
+ expr: status = 'completed'
+ description: Orders that completed fulfillment.
joins:
- to: customers
on: orders.customer_id = customers.customer_id
- relationship: many_to_one # many_to_one | one_to_many | one_to_one
+ relationship: many_to_one
- to: order_items
on: orders.order_id = order_items.order_id
relationship: one_to_many
- alias: items # optional alias for the joined source
+ alias: items
```
-Key fields:
+### Source fields
| Field | Required | Description |
|-------|----------|-------------|
-| `name` | Yes | Source identifier (lowercase, underscores) |
-| `table` or `sql` | Yes | Database table or custom SQL expression (exactly one) |
-| `grain` | Yes | Columns that define row uniqueness |
-| `columns` | No | Column definitions with type, role, visibility |
-| `measures` | No | Aggregation expressions (SUM, COUNT, AVG, etc.) |
-| `joins` | No | Relationships to other sources |
-| `segments` | No | Named filter conditions |
-| `inherits_columns_from` | No | Inherit column metadata from a manifest entry |
+| `name` | Yes | Source identifier. Use lowercase words and underscores. |
+| `table` or `sql` | Yes | Database table or custom SQL expression. Use exactly one. |
+| `grain` | Yes | Columns that uniquely identify a row at the source grain. |
+| `columns` | No | Column definitions with type, role, visibility, and descriptions. |
+| `measures` | No | Aggregation expressions such as `SUM`, `COUNT`, and `AVG`. |
+| `segments` | No | Named predicates agents can reuse. |
+| `joins` | No | Relationships to other semantic sources. |
+| `inherits_columns_from` | No | Inherit column metadata from a manifest entry. |
-Source component fields:
+### Component fields
| Component | Field | Required | Description |
|-----------|-------|----------|-------------|
-| Column | `name` | Yes | Column identifier as used in SQL expressions |
-| Column | `type` | Yes | Agent-facing type: `string`, `number`, `time`, or `boolean` |
-| Column | `role` | No | Special role such as `time` for default time dimensions |
-| Column | `visibility` | No | `public`, `internal`, or `hidden` |
-| Column | `description` | Strongly recommended | Human-readable business meaning |
-| Measure | `name` | Yes | Queryable metric name |
-| Measure | `expr` | Yes | SQL aggregation expression at the source grain |
-| Measure | `filter` | No | SQL predicate applied only to this measure |
-| Measure | `description` | Strongly recommended | Definition agents can cite and compare |
-| Segment | `name` | Yes | Reusable filter name |
-| Segment | `expr` | Yes | SQL predicate for the segment |
-| Join | `to` | Yes | Target semantic source name |
-| Join | `on` | Yes | SQL join condition using source names or aliases |
-| Join | `relationship` | Yes | `many_to_one`, `one_to_many`, or `one_to_one` |
-| Join | `alias` | No | Query alias for repeated or clearer joins |
+| Column | `name` | Yes | Column identifier used in SQL expressions. |
+| Column | `type` | Yes | Agent-facing type: `string`, `number`, `time`, or `boolean`. |
+| Column | `role` | No | Special role such as `time` for default time dimensions. |
+| Column | `visibility` | No | `public`, `internal`, or `hidden`. |
+| Column | `description` | Strongly recommended | Business meaning and usage notes. |
+| Measure | `name` | Yes | Queryable metric name. |
+| Measure | `expr` | Yes | SQL aggregation expression at the source grain. |
+| Measure | `filter` | No | SQL predicate applied only to this measure. |
+| Measure | `description` | Strongly recommended | Definition agents can cite and compare. |
+| Segment | `name` | Yes | Reusable filter name. |
+| Segment | `expr` | Yes | SQL predicate for the segment. |
+| Join | `to` | Yes | Target semantic source name. |
+| Join | `on` | Yes | SQL join condition using source names or aliases. |
+| Join | `relationship` | Yes | `many_to_one`, `one_to_many`, or `one_to_one`. |
+| Join | `alias` | No | Query alias for repeated or clearer joins. |
-Column visibility controls what agents see:
+### Visibility
-| Visibility | Behavior |
-|------------|----------|
-| `public` | Included in agent queries and listings (default) |
-| `internal` | Available for joins and measures but not shown to agents |
-| `hidden` | Excluded entirely - useful for ETL columns |
+| Visibility | Agent behavior |
+|------------|----------------|
+| `public` | Included in listings and available for agent queries. |
+| `internal` | Available for joins and measures, but not highlighted to agents. |
+| `hidden` | Excluded from agent-facing context. Use for ETL fields and sensitive internals. |
-### Editing a source
+## Measures
-Edit source files directly. They live at
-`semantic-layer//.yaml` in your project directory.
+Good measures have precise names, SQL expressions at the correct grain, and
+descriptions that say what is included and excluded.
-### Validating sources
-
-Validation checks a source definition against the actual database schema:
-
-```bash
-ktx sl validate orders --connection-id my-postgres
+```yaml
+measures:
+ - name: net_revenue
+ expr: SUM(total_amount - refunded_amount)
+ filter: status = 'completed'
+ description: Completed order revenue after refunds, excluding cancelled orders.
```
-This catches mismatches - columns that don't exist in the table, type mismatches, invalid join targets - before an agent tries to use the source.
+Prefer one canonical measure plus wiki synonyms over several nearly identical
+measures. If your team uses multiple definitions, document the distinction in a
+wiki page and link it with `sl_refs`.
-### Querying
+## Joins and grain
-The semantic layer compiles your measures and dimensions into SQL, optionally executing it against the database:
+`grain` and `relationship` prevent agents from producing double-counted SQL.
+State the row grain even when it seems obvious.
+
+```yaml
+grain:
+ - order_id
+joins:
+ - to: customers
+ on: orders.customer_id = customers.customer_id
+ relationship: many_to_one
+```
+
+Use `many_to_one` for dimensions such as customer, account, product, or plan.
+Use `one_to_many` only when the target can fan out the source rows, such as
+orders to order items.
+
+## Validate and query
+
+Validation checks source YAML against the live database schema:
+
+```bash
+ktx sl validate orders --connection-id warehouse
+```
+
+It catches missing columns, invalid join targets, and table-reference problems
+before an agent relies on the source.
+
+Compile a query to inspect generated SQL:
```bash
-# Compile a query to SQL
ktx sl query \
- --connection-id my-postgres \
- --measure total_revenue \
- --measure order_count \
- --dimension "order_date" \
- --filter "status = 'completed'" \
- --order-by order_date:desc \
+ --connection-id warehouse \
+ --measure orders.total_revenue \
+ --dimension orders.order_date \
+ --filter "orders.status = 'completed'" \
+ --order-by orders.order_date:desc \
--limit 10 \
--format sql
```
-This outputs the compiled SQL without executing it. To run the query:
+Execute only when you need live rows:
```bash
-# Execute and return results
ktx sl query \
- --connection-id my-postgres \
- --measure total_revenue \
- --dimension "order_date" \
+ --connection-id warehouse \
+ --measure orders.total_revenue \
+ --dimension orders.status \
--execute \
--max-rows 100
```
-Query flags:
+## Wiki pages
-| Flag | Description |
-|------|-------------|
-| `--measure ` | Measure to query (repeatable, at least one required) |
-| `--dimension ` | Dimension to group by (repeatable) |
-| `--filter ` | Filter expression (repeatable) |
-| `--segment ` | Named segment to apply (repeatable) |
-| `--order-by ` | Sort field, optionally with `:asc` or `:desc` (repeatable) |
-| `--limit ` | Maximum rows in the compiled query |
-| `--format ` | Output format: `json` (default) or `sql` |
-| `--execute` | Execute the query against the database |
-| `--max-rows ` | Maximum rows to return when executing |
-| `--include-empty` | Include empty/null rows in results |
+Wiki pages capture business context that does not belong in a single source
+file: metric policies, dashboard caveats, company vocabulary, data freshness,
+known issues, and source-of-truth notes.
-The query planner is grain-aware - it understands the cardinality of joins and avoids chasm traps (double-counting caused by many-to-many fan-outs). When you query measures that span multiple sources, KTX generates sub-queries at the correct grain before joining.
+Wiki files live under:
-### Workflow: edit and validate a source
-
-1. Open `semantic-layer/my-postgres/orders.yaml`.
-2. Edit the file to add columns, measures, joins, or descriptions.
-3. `ktx sl validate orders --connection-id my-postgres` - check the definition against the live schema.
-4. `ktx sl query --connection-id my-postgres --measure total_revenue --dimension order_date --format sql` - compile a representative query.
-
-If validation fails, fix the YAML before asking an agent to use the source. Common validation failures are missing columns, invalid join targets, and measure expressions that reference fields outside the source.
-
-## Wiki Pages
-
-Wiki pages are Markdown files that capture business context - definitions, rules, gotchas, and anything an agent needs to understand beyond what the schema tells it.
-
-### What they are
-
-When an agent asks "what counts as an active user?" or "why do revenue numbers differ between the dashboard and the SQL query?", the answer isn't in the schema. It's tribal knowledge that lives in Slack threads, Notion pages, or someone's head. Wiki pages make that context searchable and available to agents.
-
-### Organization
-
-Wiki pages are organized by scope:
-
-```
+```text
wiki/
-├── global/ # Cross-cutting definitions
-│ ├── order-status-definitions.md
-│ ├── revenue-recognition-rules.md
-│ └── data-freshness-sla.md
-└── user/
- └── local/ # User-scoped context
- ├── schema-conventions.md
- └── known-data-issues.md
+ global/
+ user//
```
-- **Global pages** apply across all connections - business definitions, metric standards, company terminology.
-- **User-scoped pages** are private to a user ID - personal notes, local gotchas, or context you do not want shared globally.
+Use global pages for shared business rules. Use user-scoped pages for local
+notes, personal conventions, or context that should not be shared broadly.
-### Editing pages
+### Wiki page example
-Create and edit wiki pages directly as Markdown files in the `wiki/`
-directory. Ingest and memory capture also create these pages automatically.
+```markdown
+---
+summary: Revenue recognition rules for finance reporting.
+tags: [revenue, finance, reporting]
+sl_refs: [orders]
+external_refs:
+ - type: notion
+ id: finance-revenue-policy
+---
-Wiki page fields:
+## Recognized Revenue
+
+Recognized revenue includes completed orders after refunds. It excludes
+cancelled orders, test orders, implementation fees, and tax.
+
+Finance reporting uses order completion date, not invoice creation date.
+```
+
+Useful frontmatter:
| Field | Required | Description |
|-------|----------|-------------|
-| Key | Yes | Stable page identifier used as the Markdown filename |
-| Summary | Yes | Short text shown in search results |
-| Content | Yes | Full Markdown business context |
-| Scope | No | `global` for shared context or `user` for user-scoped notes |
-| Tags | No | Search and organization labels |
-| External refs | No | Links or identifiers for source-of-truth systems |
-| Semantic-layer refs | No | Source names the page explains or constrains |
+| `summary` | Yes | Short text shown in search results. |
+| `tags` | No | Business terms and synonyms that improve search. |
+| `sl_refs` | No | Semantic source names the page explains or constrains. |
+| `external_refs` | No | Source-of-truth system links or ids. |
-### Listing pages
+## Add searchable business context
+
+1. Search first.
+
+ ```bash
+ ktx wiki search "active customer definition" --json --limit 10
+ ```
+
+2. If no page covers the rule, create or edit a Markdown file under
+ `wiki/global/`.
+3. Write a compact `summary` with the wording users are likely to ask.
+4. Add tags for synonyms and related business areas.
+5. Add `sl_refs` for relevant semantic sources.
+6. Search again with a user-like phrase.
+
+## Review context changes
+
+Before accepting agent-written context:
```bash
-ktx wiki list
+git diff -- semantic-layer wiki
+ktx sl validate orders --connection-id warehouse
+ktx sl search "revenue" --json
+ktx wiki search "revenue recognition" --json --limit 10
```
-### Searching
-
-```bash
-ktx wiki search "revenue recognition"
-```
-
-Search uses both full-text matching and semantic similarity - it finds relevant pages even when the exact terms don't match. Agents call this automatically when they need business context to answer a question.
-
-### Workflow: add searchable business context
-
-1. Search first: `ktx wiki search "order status definitions"`.
-2. If no page already covers the rule, create or edit a Markdown file under `wiki/global/`.
-3. Include concise frontmatter; agents see the summary before loading full content.
-4. Add `tags` values for the business area and `sl_refs` values for related semantic sources.
-5. Search again with the user's likely wording to confirm the page is discoverable.
+Check that definitions are specific, hidden columns stay hidden, joins have
+explicit relationships, and measures compile into the expected SQL.
## Common errors
-| Error or symptom | Likely cause | Recovery |
-|------------------|--------------|----------|
-| `ktx sl validate` reports a missing column | YAML references a column that is absent from the scanned table | Run a fresh scan or update the YAML to match the warehouse schema |
-| Query compilation double-counts a measure | Join relationship or grain is missing or wrong | Add `grain` and explicit `relationship` values, then validate and recompile |
-| Agent cannot find a metric | Measure name or description does not match business terminology | Add a measure description and a wiki page with common synonyms |
-| Wiki search misses a page | Summary and tags do not include likely user wording | Rewrite the summary and add relevant tags, then search again |
-| Semantic-layer changes are hard to review | The YAML edit is too large or unfocused | Split the change into smaller source-file edits, then review the git diff |
+| Symptom | Likely cause | Recovery |
+|---------|--------------|----------|
+| `ktx sl validate` reports a missing column | YAML references a column absent from the scanned table | Refresh database context or update the YAML |
+| Query compilation double-counts a measure | `grain` or join `relationship` is missing or wrong | Add explicit grain and relationship values, then recompile |
+| Agent cannot find a metric | Measure name and description do not match business terminology | Add a clearer measure description and a wiki page with synonyms |
+| Wiki search misses a page | Summary, tags, or content do not match user wording | Rewrite the summary and add likely synonyms |
+| Context diff is hard to review | One edit changed too many concepts | Split the change into focused source and wiki edits |
diff --git a/docs-site/content/docs/integrations/agent-clients.mdx b/docs-site/content/docs/integrations/agent-clients.mdx
index 6f7e7660..de628197 100644
--- a/docs-site/content/docs/integrations/agent-clients.mdx
+++ b/docs-site/content/docs/integrations/agent-clients.mdx
@@ -7,7 +7,46 @@ KTX integrates with coding agents through CLI skills and command files. These
files teach agents to call public `ktx` commands directly from the terminal for
semantic-layer context and wiki knowledge.
-Run `ktx setup` and select your agent targets, or configure manually using the snippets below.
+Run `ktx setup` and select your agent targets, or configure manually using the
+snippets below. Setup pins generated skill files to the KTX CLI path that
+created them, so agents do not need `ktx` on `PATH`.
+
+## Install with setup
+
+```bash
+ktx setup --agents
+```
+
+Use `--target` for one target:
+
+```bash
+ktx setup --agents --target codex
+```
+
+Use `--global` only with `claude-code` or `codex`:
+
+```bash
+ktx setup --agents --target claude-code --global
+ktx setup --agents --target codex --global
+```
+
+KTX records installed files in `.ktx/agents/install-manifest.json`. That
+manifest lets status checks report agent readiness and lets future cleanup
+remove only files KTX installed.
+
+## Generated files
+
+| Target | Project-scoped files | Global files |
+|--------|----------------------|--------------|
+| Claude Code | `.claude/skills/ktx/SKILL.md`, `.claude/rules/ktx.md` | `~/.claude/skills/ktx/SKILL.md`, `~/.claude/rules/ktx.md` |
+| Codex | `.agents/skills/ktx/SKILL.md`, `.codex/instructions/ktx.md` | `$CODEX_HOME/skills/ktx/SKILL.md`, `$CODEX_HOME/instructions/ktx.md` |
+| Cursor | `.cursor/rules/ktx.mdc` | Not supported |
+| OpenCode | `.opencode/commands/ktx.md` | Not supported |
+| Universal `.agents` | `.agents/skills/ktx/SKILL.md` | Not supported |
+
+Skill files list pinned `ktx` commands. Rule files tell the agent when KTX is
+appropriate, such as data schemas, metrics, dimensions, database structure, and
+SQL questions.
## Claude Code
@@ -15,11 +54,12 @@ Run `ktx setup` and select your agent targets, or configure manually using the s
During setup, select **Claude Code** from the agent targets. KTX writes:
-| Mode | File |
-|------|------|
-| CLI skills | `.claude/skills/ktx/SKILL.md` |
+| Scope | Files |
+|-------|-------|
+| Project | `.claude/skills/ktx/SKILL.md`, `.claude/rules/ktx.md` |
+| Global | `~/.claude/skills/ktx/SKILL.md`, `~/.claude/rules/ktx.md` |
-Both project-scoped and global installations are supported. Global installs write to `~/.claude/skills/ktx/SKILL.md`.
+Both project-scoped and global installations are supported.
### Manual CLI skills configuration
@@ -42,6 +82,7 @@ Available commands:
### Workflow tips
- Claude Code discovers skills automatically from `.claude/skills/`.
+- Claude rules in `.claude/rules/` tell Claude when KTX should be used.
- Global installation makes KTX available in all projects without per-project setup.
- Keep generated skills committed only when your team wants project-local agent instructions in git.
@@ -76,11 +117,13 @@ Create `.cursor/rules/ktx.mdc` with the same content structure as the Claude Cod
During setup, select **Codex** from the agent targets. KTX writes:
-| Mode | File |
-|------|------|
-| CLI skills | `.agents/skills/ktx/SKILL.md` |
+| Scope | Files |
+|-------|-------|
+| Project | `.agents/skills/ktx/SKILL.md`, `.codex/instructions/ktx.md` |
+| Global | `$CODEX_HOME/skills/ktx/SKILL.md`, `$CODEX_HOME/instructions/ktx.md` |
-Both project-scoped and global installations are supported. Global installs write to `$CODEX_HOME/skills/ktx/SKILL.md` (defaults to `~/.codex/skills/ktx/SKILL.md`).
+Both project-scoped and global installations are supported. `CODEX_HOME`
+defaults to `~/.codex`.
### Manual CLI skills configuration
@@ -90,6 +133,7 @@ Create `.agents/skills/ktx/SKILL.md` with the same content structure as Claude C
- Set `CODEX_HOME` to customize the global installation directory.
- Codex shares the `.agents/` directory structure with the universal format.
+- Codex instructions in `.codex/instructions/` tell Codex when KTX should be used.
- Global installation makes KTX available across all Codex sessions.
---
@@ -143,4 +187,5 @@ All supported agent clients call the same KTX CLI commands:
|---|---|---|---|---|
| CLI skills | Yes | Yes (.mdc) | Yes | Yes |
| Global install | Yes | No | Yes | No |
-| Config location | `.claude/skills/ktx/SKILL.md` | `.cursor/rules/ktx.mdc` | `.agents/skills/ktx/SKILL.md` | `.opencode/commands/ktx.md` |
+| Rule or instruction file | `.claude/rules/ktx.md` | `.cursor/rules/ktx.mdc` | `.codex/instructions/ktx.md` | `.opencode/commands/ktx.md` |
+| Skill file | `.claude/skills/ktx/SKILL.md` | Not separate | `.agents/skills/ktx/SKILL.md` | Not separate |
diff --git a/docs-site/content/docs/integrations/index.mdx b/docs-site/content/docs/integrations/index.mdx
new file mode 100644
index 00000000..8f77a624
--- /dev/null
+++ b/docs-site/content/docs/integrations/index.mdx
@@ -0,0 +1,70 @@
+---
+title: Integrations
+description: Connect KTX to warehouses, analytics tools, and coding agents.
+---
+
+KTX integrations bring trusted context into an analytics project and make that
+context available to coding agents through the CLI. Start with `ktx setup` when
+you want the guided flow, then use the integration reference pages for exact
+configuration fields, generated files, and manual setup.
+
+## Integration types
+
+| Type | What it connects | Start here |
+|------|------------------|------------|
+| Primary sources | Warehouses and databases that KTX scans for schemas, constraints, row counts, and optional query history | [Primary Sources](/docs/integrations/primary-sources) |
+| Context sources | Existing analytics and knowledge tools such as dbt, MetricFlow, LookML, Metabase, Looker, and Notion | [Context Sources](/docs/integrations/context-sources) |
+| Agent clients | Claude Code, Codex, Cursor, OpenCode, and universal `.agents` consumers | [Agent Clients](/docs/integrations/agent-clients) |
+
+## Recommended setup flow
+
+Use this order for a new project:
+
+1. Run `ktx setup` from the analytics project directory.
+2. Configure an LLM backend and embeddings so KTX can enrich and search context.
+3. Add at least one primary source connection.
+4. Add optional context sources that describe the same warehouse or business domain.
+5. Build context during setup, or run `ktx ingest ` later.
+6. Install agent integration with `ktx setup --agents` when the context is ready.
+
+For repeatable setup, pass `--project-dir`, `--no-input`, and the relevant
+automation flags documented in [`ktx setup`](/docs/cli-reference/ktx-setup).
+
+## What setup writes
+
+| Path | Purpose |
+|------|---------|
+| `ktx.yaml` | Main project configuration for providers, embeddings, connections, source mappings, query history, and setup state |
+| `.ktx/secrets/*` | Local file-backed secrets when you choose file references during setup |
+| `semantic-layer//` | YAML semantic sources generated by database and source ingestion |
+| `wiki/` | Markdown business context, definitions, and ingested knowledge |
+| `.ktx/agents/install-manifest.json` | Manifest of agent integration files installed by `ktx setup --agents` |
+| Agent client files | Skills, rules, or commands that teach agents when and how to call KTX |
+
+## Common commands
+
+```bash
+# Start or resume the guided flow
+ktx setup
+
+# Add or refresh every configured integration
+ktx ingest --all
+
+# Refresh one configured warehouse, source, or knowledge integration
+ktx ingest warehouse
+
+# Install one project-scoped agent target
+ktx setup --agents --target codex
+
+# Check whether integrations are ready
+ktx status
+```
+
+## Choosing docs
+
+Read [Primary Sources](/docs/integrations/primary-sources) when you need
+database driver fields, authentication formats, query history support, or
+warehouse-specific notes. Read [Context Sources](/docs/integrations/context-sources)
+when you need source adapter fields, repository authentication, BI tool mapping,
+or Notion crawl options. Read [Agent Clients](/docs/integrations/agent-clients)
+when you need generated file locations or manual agent configuration.
diff --git a/docs-site/content/docs/integrations/meta.json b/docs-site/content/docs/integrations/meta.json
index 70fe26ec..20dc642f 100644
--- a/docs-site/content/docs/integrations/meta.json
+++ b/docs-site/content/docs/integrations/meta.json
@@ -1,5 +1,5 @@
{
"title": "Integrations",
"defaultOpen": true,
- "pages": ["primary-sources", "context-sources", "agent-clients"]
+ "pages": ["index", "primary-sources", "context-sources", "agent-clients"]
}
diff --git a/docs-site/middleware.ts b/docs-site/middleware.ts
index 670ebd33..1b892076 100644
--- a/docs-site/middleware.ts
+++ b/docs-site/middleware.ts
@@ -12,12 +12,13 @@ export function middleware(request: NextRequest) {
}
const { pathname } = request.nextUrl;
- if (!pathname.startsWith("/docs/") || pathname.endsWith(".md")) {
+ const docsIndex = pathname.indexOf("/docs/");
+ if (docsIndex < 0 || pathname.endsWith(".md")) {
return NextResponse.next();
}
const rewriteUrl = request.nextUrl.clone();
- rewriteUrl.pathname = `/llms.mdx${pathname}`;
+ rewriteUrl.pathname = `${pathname.slice(0, docsIndex)}/llms.mdx${pathname.slice(docsIndex)}`;
return NextResponse.rewrite(rewriteUrl);
}
diff --git a/docs-site/next.config.mjs b/docs-site/next.config.mjs
index 8b28486f..a348acd0 100644
--- a/docs-site/next.config.mjs
+++ b/docs-site/next.config.mjs
@@ -4,6 +4,7 @@ const withMDX = createMDX();
/** @type {import('next').NextConfig} */
const config = {
+ basePath: "/ktx",
async rewrites() {
return [
{
@@ -12,6 +13,24 @@ const config = {
},
];
},
+ async redirects() {
+ return [
+ {
+ source: "/:path*",
+ has: [{ type: "host", value: "docs.ktx.sh" }],
+ destination: "https://docs.kaelio.com/ktx/:path*",
+ permanent: true,
+ basePath: false,
+ },
+ {
+ source: "/:path*",
+ has: [{ type: "host", value: "ktx.sh" }],
+ destination: "https://docs.kaelio.com/ktx/:path*",
+ permanent: true,
+ basePath: false,
+ },
+ ];
+ },
};
export default withMDX(config);
diff --git a/docs/superpowers/plans/2026-05-14-connection-driver-discriminated-union.md b/docs/superpowers/plans/2026-05-14-connection-driver-discriminated-union.md
new file mode 100644
index 00000000..eb8e812d
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-connection-driver-discriminated-union.md
@@ -0,0 +1,808 @@
+# Connection Driver Discriminated Union Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Replace the loose `connectionSchema` in `packages/context/src/project/config.ts` with a Zod 4 discriminated union keyed on `driver`, so that every driver's documented connection fields — including the `mappings` block — appear in the JSON schema emitted by `ktx dev schema`.
+
+**Architecture:** Add a new module `packages/context/src/project/driver-schemas.ts` that defines one `z.looseObject({ driver: z.literal('x'), ... })` per supported driver and combines them with `z.discriminatedUnion('driver', [...])`. Reuse the existing Metabase/Looker/LookML mapping shapes from `mappings-yaml-schema.ts` by exporting them. Wire the union into `config.ts`. Each per-driver shape stays `looseObject` so today's existing yaml configs with extra fields keep parsing.
+
+**Tech Stack:** TypeScript (Node 22+, ESM, `NodeNext`), Zod 4 (`^4.4.3`), Vitest, pnpm workspace.
+
+---
+
+## File Structure
+
+**Create:**
+- `packages/context/src/project/driver-schemas.ts` — per-driver Zod schemas + the discriminated union and exported types.
+- `packages/context/src/project/driver-schemas.test.ts` — unit tests for each driver schema and the union.
+
+**Modify:**
+- `packages/context/src/project/mappings-yaml-schema.ts` — export the three mapping shapes (`metabaseMappingsSchema`, `lookerMappingsSchema`, `lookmlMappingsSchema`) with `.describe()` annotations and a small description on each field so they surface meaningfully in JSON Schema.
+- `packages/context/src/project/config.ts:209-214` — replace `connectionSchema` with the discriminated union imported from `driver-schemas.ts`. Update `KtxProjectConnectionConfig` (line `272`) to be `z.infer` — still works because `connectionSchema` is the union name we keep.
+- `packages/context/src/project/index.ts` — re-export `KtxConnectionConfig` per-driver type aliases if useful (optional; only if tests need them).
+- `packages/context/src/project/config.test.ts` — add a test that the JSON schema now describes `mappings` for metabase/looker/lookml.
+
+**No changes needed:**
+- `packages/context/src/project/mappings-yaml-schema.ts` parsing helpers (`parseMetabaseMappingBootstrap`, etc.) keep working because `KtxProjectConnectionConfig` still has loose-object semantics per driver.
+- Doc files in `docs-site/` already show the `mappings` blocks correctly.
+
+---
+
+## Drivers In Scope
+
+The discriminated union enumerates the drivers actually used in code, fixtures, and docs (no `fake`/test-only driver — none exist in fixtures, verified via `grep "driver:\s*fake"`).
+
+Warehouse drivers (read `driver`, `url`; nothing else schema-modeled — kept `looseObject` so warehouse-specific overrides like `historicSql`/`context.queryHistory` pass through):
+- `postgres`, `postgresql` (separate literals; KTX normalizes `postgresql` → `postgres` at runtime, but ktx.yaml accepts both)
+- `mysql`
+- `snowflake`
+- `bigquery`
+- `sqlite`
+- `clickhouse`
+- `sqlserver`
+
+Context-source drivers (model documented fields):
+- `metabase` — `api_url`, `api_key`, `api_key_ref`, `network_proxy`/`networkProxy`, `mappings` (metabaseMappingsSchema).
+- `looker` — `base_url`, `client_id`, `client_secret`, `client_secret_ref`, `mappings` (lookerMappingsSchema).
+- `lookml` — `repoUrl` (camelCase intentional — matches code at `setup-sources.ts:1466`), `branch`, `path`, `auth_token_ref`, `mappings` (lookmlMappingsSchema).
+- `notion` — `auth_token`, `auth_token_ref`, `crawl_mode` (`'selected_roots' | 'all_accessible'`), `root_page_ids`, `root_database_ids`, `root_data_source_ids`, `max_pages_per_run`, `max_knowledge_creates_per_run`, `max_knowledge_updates_per_run`.
+- `dbt` — `source_dir`, `repo_url`, `branch`, `path`, `auth_token_ref`, `profiles_path`, `target`, `project_name`.
+- `metricflow` — `metricflow` (nested object: `repoUrl`, `branch`, `path`, `auth_token_ref`).
+
+Why not strict-object: existing warehouse connections may carry `historicSql` / `context.queryHistory` blocks and other driver-tunable fields not modeled here. `looseObject` preserves the current pass-through behavior while still surfacing the documented fields in JSON Schema.
+
+---
+
+## Task 1: Export and describe mapping shapes
+
+Make the three existing mapping schemas reusable and documented.
+
+**Files:**
+- Modify: `packages/context/src/project/mappings-yaml-schema.ts:4-31`
+- Test: `packages/context/src/project/mappings-yaml-schema.test.ts` (no behavior change — existing tests must still pass)
+
+- [ ] **Step 1: Add a failing test that imports the new exports**
+
+Append to `packages/context/src/project/mappings-yaml-schema.test.ts` (inside the existing `describe` block):
+
+```typescript
+import {
+ metabaseMappingsSchema,
+ lookerMappingsSchema,
+ lookmlMappingsSchema,
+} from './mappings-yaml-schema.js';
+
+// ...inside describe(...)
+
+it('exports mapping shapes that parse documented examples', () => {
+ expect(metabaseMappingsSchema.parse({ databaseMappings: { '1': 'wh' } })).toMatchObject({
+ databaseMappings: { '1': 'wh' },
+ syncMode: 'ALL',
+ });
+ expect(lookerMappingsSchema.parse({ connectionMappings: { x: 'wh' } })).toEqual({
+ connectionMappings: { x: 'wh' },
+ });
+ expect(lookmlMappingsSchema.parse({ expectedLookerConnectionName: 'x' })).toEqual({
+ expectedLookerConnectionName: 'x',
+ });
+});
+```
+
+- [ ] **Step 2: Run test to verify it fails**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/mappings-yaml-schema.test.ts`
+Expected: FAIL with `metabaseMappingsSchema is not exported` or equivalent module-resolution error.
+
+- [ ] **Step 3: Add `export` and `.describe()` to the three schemas**
+
+In `packages/context/src/project/mappings-yaml-schema.ts`, change the three internal `const` declarations:
+
+```typescript
+export const metabaseMappingsSchema = z
+ .object({
+ databaseMappings: z
+ .record(z.string(), stringTargetSchema)
+ .default({})
+ .describe('Map of Metabase database ID (positive integer string) to KTX connection ID. Use null to explicitly unmap.'),
+ syncEnabled: z
+ .record(z.string(), z.boolean())
+ .default({})
+ .describe('Per-Metabase-database sync toggle, keyed by Metabase database ID string.'),
+ syncMode: metabaseSyncModeSchema
+ .default('ALL')
+ .describe('Sync scope: ALL ingests every mapped DB; ONLY restricts to syncEnabled=true; EXCEPT excludes syncEnabled=true.'),
+ selections: metabaseSelectionsSchema
+ .default({ collections: [], items: [] })
+ .describe('Optional Metabase collection and item IDs to scope ingest.'),
+ defaultTagNames: z
+ .array(z.string().min(1))
+ .default([])
+ .describe('Default tag names applied to ingested Metabase artifacts.'),
+ })
+ .describe('Metabase database-to-warehouse mapping and sync configuration.');
+
+export const lookerMappingsSchema = z
+ .object({
+ connectionMappings: z
+ .record(z.string().min(1), stringTargetSchema)
+ .default({})
+ .describe('Map of Looker connection name to KTX connection ID. Use null to explicitly unmap.'),
+ })
+ .describe('Looker connection-to-warehouse mapping configuration.');
+
+export const lookmlMappingsSchema = z
+ .object({
+ expectedLookerConnectionName: z
+ .string()
+ .min(1)
+ .nullable()
+ .default(null)
+ .describe('Looker connection name that LookML models must declare; mismatches block sl_write_source at ingest time.'),
+ })
+ .describe('LookML connection-name expectation for ingest gating.');
+```
+
+Leave `metabaseSyncModeSchema`, `metabaseSelectionsSchema`, `stringTargetSchema`, and `positiveIntegerValueSchema` private (no need to export). Leave all parsing helpers (`parseMetabaseMappingBootstrap` etc.) unchanged — they keep working because `.describe()` does not change runtime behavior.
+
+- [ ] **Step 4: Run test to verify it passes and existing tests still pass**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/mappings-yaml-schema.test.ts`
+Expected: PASS for all tests including the new one.
+
+- [ ] **Step 5: Type-check the package**
+
+Run: `pnpm --filter @ktx/context run type-check`
+Expected: PASS.
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add packages/context/src/project/mappings-yaml-schema.ts packages/context/src/project/mappings-yaml-schema.test.ts
+git commit -m "refactor(context): export and describe mapping shape schemas"
+```
+
+---
+
+## Task 2: Create the driver-schemas module — warehouse drivers
+
+Add the new module with the seven warehouse driver schemas first. Smaller surface, easier to validate.
+
+**Files:**
+- Create: `packages/context/src/project/driver-schemas.ts`
+- Test: `packages/context/src/project/driver-schemas.test.ts`
+
+- [ ] **Step 1: Write failing tests for warehouse driver schemas**
+
+Create `packages/context/src/project/driver-schemas.test.ts`:
+
+```typescript
+import { describe, expect, it } from 'vitest';
+import { connectionConfigSchema } from './driver-schemas.js';
+
+describe('connectionConfigSchema (driver discriminated union)', () => {
+ it.each([
+ ['postgres', 'postgres://user:pass@host:5432/db'], // pragma: allowlist secret
+ ['postgresql', 'postgresql://user:pass@host:5432/db'], // pragma: allowlist secret
+ ['mysql', 'mysql://user:pass@host:3306/db'], // pragma: allowlist secret
+ ['snowflake', 'snowflake://account/db'],
+ ['bigquery', 'bigquery://project/dataset'],
+ ['sqlite', 'sqlite:///tmp/db.sqlite'],
+ ['clickhouse', 'clickhouse://host:8123/db'],
+ ['sqlserver', 'sqlserver://host:1433;database=db'],
+ ])('parses %s warehouse connection', (driver, url) => {
+ expect(connectionConfigSchema.parse({ driver, url })).toMatchObject({ driver, url });
+ });
+
+ it('preserves unknown warehouse fields via looseObject passthrough', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'postgres',
+ url: 'postgres://x',
+ historicSql: { enabled: true },
+ context: { queryHistory: { enabled: false } },
+ });
+ expect(parsed).toMatchObject({
+ driver: 'postgres',
+ historicSql: { enabled: true },
+ context: { queryHistory: { enabled: false } },
+ });
+ });
+
+ it('rejects an unknown driver', () => {
+ expect(() => connectionConfigSchema.parse({ driver: 'nope', url: 'x' })).toThrow();
+ });
+});
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/driver-schemas.test.ts`
+Expected: FAIL — `driver-schemas.js` not found.
+
+- [ ] **Step 3: Create `driver-schemas.ts` with warehouse drivers only**
+
+Create `packages/context/src/project/driver-schemas.ts`:
+
+```typescript
+import * as z from 'zod';
+
+const warehouseDrivers = [
+ 'postgres',
+ 'postgresql',
+ 'mysql',
+ 'snowflake',
+ 'bigquery',
+ 'sqlite',
+ 'clickhouse',
+ 'sqlserver',
+] as const;
+
+function warehouseConnectionSchema(driver: (typeof warehouseDrivers)[number]) {
+ return z
+ .looseObject({
+ driver: z.literal(driver),
+ url: z
+ .string()
+ .min(1)
+ .optional()
+ .describe('Warehouse connection URL or DSN; may contain environment-variable references like env:DATABASE_URL.'),
+ })
+ .describe(`${driver} warehouse connection. Additional driver-tunable fields (e.g. historicSql, context.queryHistory) are accepted and passed through.`);
+}
+
+export const connectionConfigSchema = z.discriminatedUnion(
+ 'driver',
+ warehouseDrivers.map(warehouseConnectionSchema),
+);
+
+export type KtxConnectionConfig = z.infer;
+```
+
+- [ ] **Step 4: Run tests to verify they pass**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/driver-schemas.test.ts`
+Expected: PASS for all eight warehouse drivers + passthrough + unknown-driver rejection.
+
+- [ ] **Step 5: Type-check**
+
+Run: `pnpm --filter @ktx/context run type-check`
+Expected: PASS.
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add packages/context/src/project/driver-schemas.ts packages/context/src/project/driver-schemas.test.ts
+git commit -m "feat(context): add driver-schemas module with warehouse drivers"
+```
+
+---
+
+## Task 3: Add Metabase, Looker, LookML driver schemas (the mapping-bearing ones)
+
+These are the most important drivers — they're why we're doing this refactor.
+
+**Files:**
+- Modify: `packages/context/src/project/driver-schemas.ts`
+- Modify: `packages/context/src/project/driver-schemas.test.ts`
+
+- [ ] **Step 1: Write failing tests**
+
+Append to `packages/context/src/project/driver-schemas.test.ts`:
+
+```typescript
+describe('connectionConfigSchema — context source drivers with mappings', () => {
+ it('parses a metabase connection with mappings', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'metabase',
+ api_url: 'https://metabase.example.com',
+ api_key_ref: 'env:METABASE_API_KEY', // pragma: allowlist secret
+ mappings: {
+ databaseMappings: { '3': 'prod-warehouse' },
+ syncEnabled: { '3': true },
+ syncMode: 'ONLY',
+ },
+ });
+ expect(parsed).toMatchObject({
+ driver: 'metabase',
+ api_url: 'https://metabase.example.com',
+ mappings: {
+ databaseMappings: { '3': 'prod-warehouse' },
+ syncMode: 'ONLY',
+ },
+ });
+ });
+
+ it('parses a looker connection with connectionMappings', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'looker',
+ base_url: 'https://looker.example.com',
+ client_id: 'abc',
+ client_secret_ref: 'env:LOOKER_CLIENT_SECRET', // pragma: allowlist secret
+ mappings: { connectionMappings: { bigquery_prod: 'wh' } },
+ });
+ expect(parsed.mappings).toEqual({ connectionMappings: { bigquery_prod: 'wh' } });
+ });
+
+ it('parses a lookml connection with expectedLookerConnectionName', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'lookml',
+ repoUrl: 'https://github.com/acme/looker.git',
+ branch: 'main',
+ mappings: { expectedLookerConnectionName: 'bigquery_prod' },
+ });
+ expect(parsed.mappings).toEqual({ expectedLookerConnectionName: 'bigquery_prod' });
+ });
+
+ it('rejects metabase mapping with non-integer database key', () => {
+ expect(() =>
+ connectionConfigSchema.parse({
+ driver: 'metabase',
+ api_url: 'https://x',
+ mappings: { databaseMappings: { 'abc': 'wh' } },
+ }),
+ ).toThrow();
+ });
+});
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/driver-schemas.test.ts`
+Expected: FAIL — `driver: 'metabase'` is not in the discriminated union.
+
+- [ ] **Step 3: Extend `driver-schemas.ts` with metabase/looker/lookml schemas**
+
+Edit `packages/context/src/project/driver-schemas.ts` — add imports and the three new schemas, and include them in the union:
+
+```typescript
+import * as z from 'zod';
+import {
+ lookerMappingsSchema,
+ lookmlMappingsSchema,
+ metabaseMappingsSchema,
+} from './mappings-yaml-schema.js';
+
+// ... (warehouseDrivers + warehouseConnectionSchema stay as-is) ...
+
+const positiveIntKeyMessage = (field: string) =>
+ `${field} keys must be positive-integer strings (e.g. "1", "42")`;
+
+const positiveIntKeyRegex = /^[1-9]\d*$/;
+
+const metabaseMappingsStrictSchema = metabaseMappingsSchema.superRefine((value, ctx) => {
+ for (const key of Object.keys(value.databaseMappings ?? {})) {
+ if (!positiveIntKeyRegex.test(key)) {
+ ctx.addIssue({ code: 'custom', path: ['databaseMappings', key], message: positiveIntKeyMessage('databaseMappings') });
+ }
+ }
+ for (const key of Object.keys(value.syncEnabled ?? {})) {
+ if (!positiveIntKeyRegex.test(key)) {
+ ctx.addIssue({ code: 'custom', path: ['syncEnabled', key], message: positiveIntKeyMessage('syncEnabled') });
+ }
+ }
+});
+
+const metabaseConnectionSchema = z
+ .looseObject({
+ driver: z.literal('metabase'),
+ api_url: z.string().url().describe('Metabase instance API URL (e.g. https://metabase.example.com).'),
+ api_key: z.string().min(1).optional().describe('Literal Metabase API key. Prefer api_key_ref for safety.'),
+ api_key_ref: z
+ .string()
+ .min(1)
+ .optional()
+ .describe('Reference to Metabase API key (e.g. env:METABASE_API_KEY or file:/path).'),
+ network_proxy: z
+ .looseObject({})
+ .optional()
+ .describe('Optional network proxy configuration (snake_case form).'),
+ networkProxy: z
+ .looseObject({})
+ .optional()
+ .describe('Optional network proxy configuration (camelCase form).'),
+ mappings: metabaseMappingsStrictSchema.optional().describe('Metabase database-to-warehouse mappings and sync configuration.'),
+ })
+ .describe('Metabase context-source connection.');
+
+const lookerConnectionSchema = z
+ .looseObject({
+ driver: z.literal('looker'),
+ base_url: z.string().url().describe('Looker instance base URL (e.g. https://looker.example.com).'),
+ client_id: z.string().min(1).describe('Looker OAuth client ID.'),
+ client_secret: z.string().min(1).optional().describe('Literal Looker OAuth client secret. Prefer client_secret_ref.'),
+ client_secret_ref: z
+ .string()
+ .min(1)
+ .optional()
+ .describe('Reference to Looker OAuth client secret (e.g. env:LOOKER_CLIENT_SECRET).'),
+ mappings: lookerMappingsSchema.optional().describe('Looker connection-name to KTX warehouse mappings.'),
+ })
+ .describe('Looker context-source connection.');
+
+const lookmlConnectionSchema = z
+ .looseObject({
+ driver: z.literal('lookml'),
+ repoUrl: z
+ .string()
+ .min(1)
+ .describe('Git URL of the LookML project (https, ssh, or file:). Field is camelCase by convention.'),
+ branch: z.string().min(1).optional().describe('Git branch (default "main" downstream).'),
+ path: z.string().optional().describe('Subdirectory within the repo when the LookML project lives in a monorepo.'),
+ auth_token_ref: z.string().min(1).optional().describe('Reference to Git auth token for private repos (e.g. env:GITHUB_TOKEN).'),
+ mappings: lookmlMappingsSchema.optional().describe('LookML expected-connection mapping for ingest gating.'),
+ })
+ .describe('LookML context-source connection.');
+
+export const connectionConfigSchema = z.discriminatedUnion(
+ 'driver',
+ [
+ ...warehouseDrivers.map(warehouseConnectionSchema),
+ metabaseConnectionSchema,
+ lookerConnectionSchema,
+ lookmlConnectionSchema,
+ ],
+);
+```
+
+Important: the existing `parseMetabaseMappingBootstrap` in `mappings-yaml-schema.ts` already enforces positive-integer keys via `assertPositiveIntegerKeys`. Adding `metabaseMappingsStrictSchema` here gives the same guarantee at the top-level config parse, so a malformed ktx.yaml fails fast at `parseKtxProjectConfig` time rather than at ingest time.
+
+- [ ] **Step 4: Run tests to verify they pass**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/driver-schemas.test.ts`
+Expected: PASS.
+
+- [ ] **Step 5: Type-check**
+
+Run: `pnpm --filter @ktx/context run type-check`
+Expected: PASS.
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add packages/context/src/project/driver-schemas.ts packages/context/src/project/driver-schemas.test.ts
+git commit -m "feat(context): add metabase, looker, lookml driver schemas with mappings"
+```
+
+---
+
+## Task 4: Add Notion, dbt, MetricFlow driver schemas
+
+The remaining context-source drivers; no `mappings` for these, but plenty of driver-specific fields.
+
+**Files:**
+- Modify: `packages/context/src/project/driver-schemas.ts`
+- Modify: `packages/context/src/project/driver-schemas.test.ts`
+
+- [ ] **Step 1: Write failing tests**
+
+Append to `packages/context/src/project/driver-schemas.test.ts`:
+
+```typescript
+describe('connectionConfigSchema — notion / dbt / metricflow', () => {
+ it('parses a notion connection with selected_roots crawl', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'notion',
+ auth_token_ref: 'env:NOTION_TOKEN',
+ crawl_mode: 'selected_roots',
+ root_page_ids: ['abc', 'def'],
+ max_pages_per_run: 500,
+ });
+ expect(parsed).toMatchObject({
+ driver: 'notion',
+ crawl_mode: 'selected_roots',
+ root_page_ids: ['abc', 'def'],
+ max_pages_per_run: 500,
+ });
+ });
+
+ it('rejects notion with unknown crawl_mode', () => {
+ expect(() =>
+ connectionConfigSchema.parse({
+ driver: 'notion',
+ auth_token_ref: 'env:NOTION_TOKEN',
+ crawl_mode: 'everything',
+ }),
+ ).toThrow();
+ });
+
+ it('parses a dbt connection from a local source_dir', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'dbt',
+ source_dir: '/tmp/dbt-project',
+ target: 'dev',
+ });
+ expect(parsed).toMatchObject({ driver: 'dbt', source_dir: '/tmp/dbt-project', target: 'dev' });
+ });
+
+ it('parses a metricflow connection with nested config', () => {
+ const parsed = connectionConfigSchema.parse({
+ driver: 'metricflow',
+ metricflow: {
+ repoUrl: 'https://github.com/acme/sl.git',
+ branch: 'main',
+ },
+ });
+ expect(parsed).toMatchObject({
+ driver: 'metricflow',
+ metricflow: { repoUrl: 'https://github.com/acme/sl.git' },
+ });
+ });
+});
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/driver-schemas.test.ts`
+Expected: FAIL — `driver: 'notion'` etc. not in union.
+
+- [ ] **Step 3: Extend `driver-schemas.ts`**
+
+Add to `packages/context/src/project/driver-schemas.ts` before the final `connectionConfigSchema` export:
+
+```typescript
+const notionConnectionSchema = z
+ .looseObject({
+ driver: z.literal('notion'),
+ auth_token: z.string().min(1).optional().describe('Literal Notion integration token. Prefer auth_token_ref.'),
+ auth_token_ref: z
+ .string()
+ .min(1)
+ .optional()
+ .describe('Reference to Notion integration token (e.g. env:NOTION_TOKEN).'),
+ crawl_mode: z
+ .enum(['selected_roots', 'all_accessible'])
+ .optional()
+ .describe('Crawl scope. "selected_roots" requires at least one of root_page_ids, root_database_ids, root_data_source_ids.'),
+ root_page_ids: z.array(z.string().min(1)).optional().describe('Notion page IDs to crawl when crawl_mode is selected_roots.'),
+ root_database_ids: z.array(z.string().min(1)).optional().describe('Notion database IDs to crawl when crawl_mode is selected_roots.'),
+ root_data_source_ids: z
+ .array(z.string().min(1))
+ .optional()
+ .describe('Notion data source IDs to crawl when crawl_mode is selected_roots.'),
+ max_pages_per_run: z
+ .number()
+ .int()
+ .min(1)
+ .max(10000)
+ .optional()
+ .describe('Maximum Notion pages fetched in a single ingest run.'),
+ max_knowledge_creates_per_run: z
+ .number()
+ .int()
+ .min(0)
+ .max(25)
+ .optional()
+ .describe('Maximum new wiki pages created per run.'),
+ max_knowledge_updates_per_run: z
+ .number()
+ .int()
+ .min(0)
+ .max(100)
+ .optional()
+ .describe('Maximum existing wiki pages updated per run.'),
+ })
+ .describe('Notion context-source connection.');
+
+const dbtConnectionSchema = z
+ .looseObject({
+ driver: z.literal('dbt'),
+ source_dir: z.string().min(1).optional().describe('Absolute or project-relative path to a local dbt project.'),
+ repo_url: z.string().min(1).optional().describe('Git URL of the dbt project (https, ssh, or file:).'),
+ branch: z.string().min(1).optional().describe('Git branch when using repo_url.'),
+ path: z.string().optional().describe('Subdirectory within the repo when the dbt project lives in a monorepo.'),
+ auth_token_ref: z.string().min(1).optional().describe('Reference to Git auth token for private repos.'),
+ profiles_path: z.string().optional().describe('Override path to dbt profiles.yml.'),
+ target: z.string().min(1).optional().describe('dbt target name (e.g. dev, prod).'),
+ project_name: z.string().min(1).optional().describe('Override auto-detected dbt project name.'),
+ })
+ .describe('dbt context-source connection.');
+
+const metricflowConnectionSchema = z
+ .looseObject({
+ driver: z.literal('metricflow'),
+ metricflow: z
+ .looseObject({
+ repoUrl: z.string().min(1).describe('Git URL of the MetricFlow / SL project.'),
+ branch: z.string().min(1).optional().describe('Git branch (default "main").'),
+ path: z.string().optional().describe('Subdirectory within the repo when the SL config lives in a monorepo.'),
+ auth_token_ref: z.string().min(1).optional().describe('Reference to Git auth token for private repos.'),
+ })
+ .describe('Nested MetricFlow configuration block.'),
+ })
+ .describe('MetricFlow / SL context-source connection.');
+```
+
+Then update the final union:
+
+```typescript
+export const connectionConfigSchema = z.discriminatedUnion(
+ 'driver',
+ [
+ ...warehouseDrivers.map(warehouseConnectionSchema),
+ metabaseConnectionSchema,
+ lookerConnectionSchema,
+ lookmlConnectionSchema,
+ notionConnectionSchema,
+ dbtConnectionSchema,
+ metricflowConnectionSchema,
+ ],
+);
+```
+
+- [ ] **Step 4: Run tests to verify they pass**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/driver-schemas.test.ts`
+Expected: PASS.
+
+- [ ] **Step 5: Type-check**
+
+Run: `pnpm --filter @ktx/context run type-check`
+Expected: PASS.
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add packages/context/src/project/driver-schemas.ts packages/context/src/project/driver-schemas.test.ts
+git commit -m "feat(context): add notion, dbt, metricflow driver schemas"
+```
+
+---
+
+## Task 5: Wire the discriminated union into `config.ts`
+
+Now switch the top-level `connectionSchema` to the new union. This is the change that flips JSON-schema output.
+
+**Files:**
+- Modify: `packages/context/src/project/config.ts:209-214, 272`
+- Test: `packages/context/src/project/config.test.ts` — add a JSON-schema assertion.
+
+- [ ] **Step 1: Write a failing test for the JSON schema output**
+
+Append to `packages/context/src/project/config.test.ts`:
+
+```typescript
+import { generateKtxProjectConfigJsonSchema } from './config.js';
+
+describe('generateKtxProjectConfigJsonSchema', () => {
+ it('emits the metabase mappings shape under connections', () => {
+ const schema = generateKtxProjectConfigJsonSchema();
+ const serialized = JSON.stringify(schema);
+ expect(serialized).toContain('databaseMappings');
+ expect(serialized).toContain('connectionMappings');
+ expect(serialized).toContain('expectedLookerConnectionName');
+ });
+});
+```
+
+- [ ] **Step 2: Run test to verify it fails**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/config.test.ts`
+Expected: FAIL — the strings are not in the emitted schema yet because `connectionSchema` is still loose.
+
+- [ ] **Step 3: Replace `connectionSchema` in `config.ts`**
+
+In `packages/context/src/project/config.ts`, delete lines `209-214`:
+
+```typescript
+const connectionSchema = z
+ .looseObject({
+ driver: z.string().min(1).optional().describe('Connector driver identifier (e.g. "postgres", "bigquery", "snowflake").'),
+ url: z.string().optional().describe('Connection URL or DSN. Format depends on the driver; may contain environment-variable references.'),
+ })
+ .describe('A single database/connector connection entry. Additional driver-specific fields are accepted and passed through.');
+```
+
+Replace with an import + re-bind at the top of the file (after the existing imports):
+
+```typescript
+import { connectionConfigSchema } from './driver-schemas.js';
+
+const connectionSchema = connectionConfigSchema;
+```
+
+(Re-binding to the local name `connectionSchema` keeps the rest of the file unchanged, including the export of `KtxProjectConnectionConfig` at line `272`.)
+
+- [ ] **Step 4: Run the new test plus existing config tests**
+
+Run: `pnpm --filter @ktx/context exec vitest run src/project/`
+Expected: PASS for all tests.
+
+If any existing test fails (e.g. a fixture used an undocumented driver string), update the fixture or expand the union — do not loosen the union.
+
+- [ ] **Step 5: Run the full context test suite to catch downstream regressions**
+
+Run: `pnpm --filter @ktx/context run test`
+Expected: PASS.
+
+- [ ] **Step 6: Type-check the workspace**
+
+Run: `pnpm run type-check`
+Expected: PASS. `KtxProjectConnectionConfig` is now a union; any consumer that destructured fields not present on every driver branch will surface here.
+
+If type-check fails in a consumer, the fix is usually `if (connection.driver === 'metabase')` style narrowing — or, for code that already does this dynamically (e.g. `String(connection.driver).toLowerCase() === 'metabase'`), an explicit cast at the call site is acceptable. Do not add `as any`; prefer narrowing.
+
+- [ ] **Step 7: Commit**
+
+```bash
+git add packages/context/src/project/config.ts packages/context/src/project/config.test.ts
+git commit -m "refactor(context): make connectionSchema a driver-discriminated union"
+```
+
+---
+
+## Task 6: Verify the user-visible result and CLI smoke
+
+Confirm the original bug is fixed and the CLI behavior is unchanged.
+
+**Files:** none modified in this task.
+
+- [ ] **Step 1: Build the CLI**
+
+Run: `pnpm run build`
+Expected: PASS.
+
+- [ ] **Step 2: Confirm `ktx dev schema | rg -i mapping` now returns hits**
+
+Run: `node scripts/run-ktx.mjs -- dev schema | rg -i mapping`
+Expected: multiple lines, including the `databaseMappings`, `connectionMappings`, `expectedLookerConnectionName` keys and their descriptions.
+
+- [ ] **Step 3: Run the CLI smoke**
+
+Run: `pnpm --filter @ktx/cli run smoke`
+Expected: PASS.
+
+- [ ] **Step 4: Run the broader workspace test suite**
+
+Run: `pnpm run test 2>&1 | tee /tmp/ktx-test-output.log`
+Expected: PASS. Inspect `/tmp/ktx-test-output.log` if anything fails.
+
+- [ ] **Step 5: Run pre-commit on changed files**
+
+Run: `pnpm run check`
+Expected: PASS.
+
+- [ ] **Step 6: Knip dead-code sweep (in case we introduced unused exports)**
+
+Run: `pnpm run dead-code`
+Expected: PASS — or, if Knip flags `KtxConnectionConfig` as unused, decide whether to export it from `packages/context/src/project/index.ts` (preferred — it documents intent) or drop the export.
+
+If exporting: add to `packages/context/src/project/index.ts`:
+
+```typescript
+export type { KtxConnectionConfig } from './driver-schemas.js';
+```
+
+- [ ] **Step 7: Final commit if any docs / index changes were made**
+
+```bash
+git status --short
+# If only docs/index were touched in step 6:
+git add packages/context/src/project/index.ts
+git commit -m "chore(context): re-export KtxConnectionConfig from project package"
+```
+
+---
+
+## Self-Review
+
+**1. Spec coverage:** Original request was "I need to be able to see full schema" with chosen approach option 1 (discriminated union). Task 5 step 2 verifies that `ktx dev schema | rg -i mapping` now returns hits. Task 6 step 2 is the explicit end-to-end check. All catalogued drivers (warehouse + metabase + looker + lookml + notion + dbt + metricflow) have a schema and a test. ✅
+
+**2. Placeholder scan:** No "TBD", "add validation", "similar to Task N", or skipped code. Every step has the actual code or command. ✅
+
+**3. Type consistency:**
+- `connectionConfigSchema` is defined in Task 2 and extended (not renamed) in Tasks 3–4. ✅
+- `KtxConnectionConfig` (new type) appears only in `driver-schemas.ts` and the optional re-export in Task 6. `KtxProjectConnectionConfig` (existing type at `config.ts:272`) keeps its name. ✅
+- `metabaseMappingsSchema`, `lookerMappingsSchema`, `lookmlMappingsSchema` — Task 1 exports them; Task 3 imports them by the same names. ✅
+- `metabaseMappingsStrictSchema` is defined and used in Task 3 only. ✅
+- The `warehouseDrivers` array and `warehouseConnectionSchema` helper are introduced in Task 2 and reused unchanged in Task 4's union extension. ✅
+
+---
+
+## Execution Handoff
+
+Plan complete and saved to `docs/superpowers/plans/2026-05-14-connection-driver-discriminated-union.md`. Two execution options:
+
+**1. Subagent-Driven (recommended)** — I dispatch a fresh subagent per task, review between tasks, fast iteration.
+
+**2. Inline Execution** — Execute tasks in this session using executing-plans, batch execution with checkpoints.
+
+Which approach?
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-dictionary-search.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-dictionary-search.md
new file mode 100644
index 00000000..63663937
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-dictionary-search.md
@@ -0,0 +1,939 @@
+# Research Agent MCP Dictionary Search Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Add the MCP-shaped `dictionary_search` tool so external research agents can resolve user-mentioned literal values to profile-sampled warehouse columns.
+
+**Architecture:** Reuse the existing relationship-profile dictionary extraction as the source of truth, add a focused local dictionary-search service that reports coverage and non-authoritative misses per connection, then register the service through the MCP context tool surface and local project ports. The service re-reads the latest profile artifact on each call instead of keeping a long-lived cache, so scan freshness is correct for the MCP daemon v1.
+
+**Tech Stack:** TypeScript, Vitest, Zod, KTX local file store, relationship-profile artifacts, KTX MCP context ports.
+
+---
+
+## Current Audit
+
+Original spec: `docs/superpowers/specs/2026-05-14-research-agent-mcp-tools-design.md`
+
+Implemented v1 slices:
+
+- `docs/superpowers/plans/2026-05-14-research-agent-mcp-sql-execution-foundation.md` is implemented. Current source has sqlglot read-only validation in `python/ktx-daemon/src/ktx_daemon/sql_analysis.py`, `SqlAnalysisPort.validateReadOnly()` in `packages/context/src/sql-analysis/ports.ts`, MCP `sql_execution` registration in `packages/context/src/mcp/context-tools.ts`, and local connector execution gated by validation in `packages/context/src/mcp/local-project-ports.ts`.
+- `docs/superpowers/plans/2026-05-14-research-agent-mcp-entity-details.md` is implemented. Current source has `packages/context/src/scan/entity-details.ts`, MCP `entity_details` registration in `packages/context/src/mcp/context-tools.ts`, and local project wiring in `packages/context/src/mcp/local-project-ports.ts`.
+
+V1-blocking gaps remaining against the original spec:
+
+- `dictionary_search` is not registered on the MCP surface and `KtxMcpContextPorts` has no dictionary-search port.
+- `discover_data` is not registered on the MCP surface and the unified ranked result shape is not implemented.
+- The ingest-side warehouse-verification tools still use `connectionName` / `targets` / `rowLimit` contracts and have not been fully converged with shared MCP-shaped services.
+- `ktx mcp start|stop|status|logs` and the HTTP Streamable MCP daemon do not exist.
+- `ktx setup-agents` does not install MCP client config entries or the `ktx-research` skill.
+
+This plan covers only the next focused blocker: MCP `dictionary_search`. Later plans still need to cover `discover_data`, ingest contract convergence, the HTTP daemon, and setup-agent/research-skill installation.
+
+Non-blocking or explicitly out-of-scope gaps:
+
+- Python code execution over MCP.
+- Stdio MCP transport.
+- OS-level auto-start.
+- Native TLS, audit logging, rate limiting, per-tool authorization, and multi-project daemon routing.
+- Streaming SQL results.
+
+## File Structure
+
+Create:
+
+- `packages/context/src/sl/dictionary-search.ts`
+ - Reads the latest `relationship-profile.json` per searched connection.
+ - Uses `loadLatestSlDictionaryEntries()` for dictionary entries.
+ - Returns spec-shaped `searched` coverage records, matches, and per-value miss reasons.
+ - Re-reads artifacts per call rather than caching, satisfying MCP freshness for v1.
+- `packages/context/src/sl/dictionary-search.test.ts`
+ - Covers matches, non-authoritative misses, missing profile artifacts, no candidate columns, case-insensitive substring matching, and connection scoping.
+
+Modify:
+
+- `packages/context/src/sl/index.ts`
+ - Export the new service and response types.
+- `packages/context/src/mcp/types.ts`
+ - Add `KtxDictionarySearchMcpPort` and include `dictionarySearch` in `KtxMcpContextPorts`.
+- `packages/context/src/mcp/context-tools.ts`
+ - Add the `dictionary_search` Zod schema and registration.
+- `packages/context/src/mcp/server.test.ts`
+ - Assert MCP registration and structured output for `dictionary_search`.
+- `packages/context/src/mcp/local-project-ports.ts`
+ - Wire local project dictionary search to the new service.
+- `packages/context/src/mcp/local-project-ports.test.ts`
+ - Cover local-port `dictionary_search` success and missing-profile behavior.
+- `packages/context/src/mcp/index.ts`
+ - Export the new MCP port type if it is not already covered by existing barrel exports.
+
+## Task 1: Add The Dictionary Search Service
+
+**Files:**
+- Create: `packages/context/src/sl/dictionary-search.test.ts`
+- Create: `packages/context/src/sl/dictionary-search.ts`
+- Modify: `packages/context/src/sl/index.ts`
+
+- [ ] **Step 1: Write failing service tests**
+
+Create `packages/context/src/sl/dictionary-search.test.ts`:
+
+```typescript
+import { mkdtemp, rm } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+import { initKtxProject, type KtxLocalProject } from '../project/index.js';
+import { createKtxDictionarySearchService } from './dictionary-search.js';
+
+describe('createKtxDictionarySearchService', () => {
+ let tempDir: string;
+ let project: KtxLocalProject;
+
+ beforeEach(async () => {
+ tempDir = await mkdtemp(join(tmpdir(), 'ktx-dictionary-search-'));
+ project = await initKtxProject({ projectDir: join(tempDir, 'project'), projectName: 'warehouse' });
+ project.config.connections.warehouse = { driver: 'postgres', url: 'env:DATABASE_URL' };
+ project.config.connections.billing = { driver: 'postgres', url: 'env:BILLING_DATABASE_URL' };
+ });
+
+ afterEach(async () => {
+ await rm(tempDir, { recursive: true, force: true });
+ });
+
+ async function seedProfile(input: {
+ connectionId: string;
+ syncId: string;
+ columns: Record;
+ }): Promise {
+ await project.fileStore.writeFile(
+ `raw-sources/${input.connectionId}/live-database/${input.syncId}/enrichment/relationship-profile.json`,
+ `${JSON.stringify(
+ {
+ connectionId: input.connectionId,
+ driver: 'postgres',
+ sqlAvailable: true,
+ queryCount: 4,
+ tables: [],
+ columns: input.columns,
+ warnings: [],
+ },
+ null,
+ 2,
+ )}\n`,
+ 'ktx',
+ 'ktx@example.com',
+ 'Seed relationship profile',
+ );
+ }
+
+ it('returns matches and non-authoritative misses across configured connections', async () => {
+ await seedProfile({
+ connectionId: 'warehouse',
+ syncId: 'sync-1',
+ columns: {
+ 'orders.status': {
+ table: { catalog: null, db: 'public', name: 'orders' },
+ column: 'status',
+ nativeType: 'text',
+ normalizedType: 'string',
+ distinctCount: 3,
+ sampleValues: ['paid', 'refunded', 'pending'],
+ },
+ },
+ });
+ await seedProfile({
+ connectionId: 'billing',
+ syncId: 'sync-2',
+ columns: {
+ 'customers.name': {
+ table: { catalog: null, db: 'public', name: 'customers' },
+ column: 'name',
+ nativeType: 'text',
+ normalizedType: 'string',
+ distinctCount: 4,
+ sampleValues: ['Acme Corp', 'Globex'],
+ },
+ },
+ });
+ const service = createKtxDictionarySearchService(project);
+
+ await expect(service.search({ values: ['PAID', 'missing'] })).resolves.toEqual({
+ searched: [
+ {
+ connectionId: 'billing',
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 1,
+ syncId: 'sync-2',
+ profiledAt: null,
+ },
+ status: 'ready',
+ },
+ {
+ connectionId: 'warehouse',
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 1,
+ syncId: 'sync-1',
+ profiledAt: null,
+ },
+ status: 'ready',
+ },
+ ],
+ results: [
+ {
+ value: 'PAID',
+ matches: [
+ {
+ connectionId: 'warehouse',
+ sourceName: 'orders',
+ columnName: 'status',
+ matchedValue: 'paid',
+ cardinality: 3,
+ },
+ ],
+ misses: [{ connectionId: 'billing', reason: 'value_not_in_sample' }],
+ },
+ {
+ value: 'missing',
+ matches: [],
+ misses: [
+ { connectionId: 'billing', reason: 'value_not_in_sample' },
+ { connectionId: 'warehouse', reason: 'value_not_in_sample' },
+ ],
+ },
+ ],
+ });
+ });
+
+ it('distinguishes missing profile artifacts from profiles with no candidate columns', async () => {
+ await seedProfile({
+ connectionId: 'billing',
+ syncId: 'sync-empty',
+ columns: {
+ 'events.id': {
+ table: { catalog: null, db: 'public', name: 'events' },
+ column: 'id',
+ nativeType: 'integer',
+ normalizedType: 'integer',
+ distinctCount: 100,
+ sampleValues: [1, 2, 3],
+ },
+ },
+ });
+ const service = createKtxDictionarySearchService(project);
+
+ await expect(service.search({ values: ['Acme'] })).resolves.toEqual({
+ searched: [
+ {
+ connectionId: 'billing',
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 0,
+ syncId: 'sync-empty',
+ profiledAt: null,
+ },
+ status: 'no_candidate_columns',
+ },
+ {
+ connectionId: 'warehouse',
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 0,
+ syncId: null,
+ profiledAt: null,
+ },
+ status: 'no_profile_artifact',
+ },
+ ],
+ results: [
+ {
+ value: 'Acme',
+ matches: [],
+ misses: [
+ { connectionId: 'billing', reason: 'no_candidate_columns' },
+ { connectionId: 'warehouse', reason: 'no_profile_artifact' },
+ ],
+ },
+ ],
+ });
+ });
+
+ it('scopes search to the requested connection', async () => {
+ await seedProfile({
+ connectionId: 'warehouse',
+ syncId: 'sync-1',
+ columns: {
+ 'orders.status': {
+ table: { catalog: null, db: 'public', name: 'orders' },
+ column: 'status',
+ nativeType: 'text',
+ normalizedType: 'string',
+ distinctCount: 3,
+ sampleValues: ['paid'],
+ },
+ },
+ });
+ await seedProfile({
+ connectionId: 'billing',
+ syncId: 'sync-2',
+ columns: {
+ 'invoices.status': {
+ table: { catalog: null, db: 'public', name: 'invoices' },
+ column: 'status',
+ nativeType: 'text',
+ normalizedType: 'string',
+ distinctCount: 2,
+ sampleValues: ['paid'],
+ },
+ },
+ });
+ const service = createKtxDictionarySearchService(project);
+
+ await expect(service.search({ connectionId: 'billing', values: ['paid'] })).resolves.toMatchObject({
+ searched: [{ connectionId: 'billing', status: 'ready' }],
+ results: [
+ {
+ value: 'paid',
+ matches: [{ connectionId: 'billing', sourceName: 'invoices', columnName: 'status', matchedValue: 'paid' }],
+ misses: [],
+ },
+ ],
+ });
+ });
+});
+```
+
+- [ ] **Step 2: Run service tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/sl/dictionary-search.test.ts
+```
+
+Expected: FAIL with `Cannot find module './dictionary-search.js'`.
+
+- [ ] **Step 3: Implement the dictionary search service**
+
+Create `packages/context/src/sl/dictionary-search.ts`:
+
+```typescript
+import type { KtxLocalProject } from '../project/index.js';
+import { loadLatestSlDictionaryEntries, type SlDictionaryEntry } from './sl-dictionary-profile.js';
+
+export type KtxDictionarySearchStatus = 'ready' | 'no_profile_artifact' | 'no_candidate_columns';
+export type KtxDictionarySearchMissReason = 'no_profile_artifact' | 'no_candidate_columns' | 'value_not_in_sample';
+
+export interface KtxDictionarySearchInput {
+ values: string[];
+ connectionId?: string;
+}
+
+export interface KtxDictionarySearchCoverage {
+ sampledRows: number | null;
+ valuesPerColumn: number | null;
+ profiledColumns: number;
+ syncId: string | null;
+ profiledAt: string | null;
+}
+
+export interface KtxDictionarySearchSearchedConnection {
+ connectionId: string;
+ coverage: KtxDictionarySearchCoverage;
+ status: KtxDictionarySearchStatus;
+}
+
+export interface KtxDictionarySearchMatch {
+ connectionId: string;
+ sourceName: string;
+ columnName: string;
+ matchedValue: string;
+ cardinality: number | null;
+}
+
+export interface KtxDictionarySearchMiss {
+ connectionId: string;
+ reason: KtxDictionarySearchMissReason;
+}
+
+export interface KtxDictionarySearchValueResult {
+ value: string;
+ matches: KtxDictionarySearchMatch[];
+ misses: KtxDictionarySearchMiss[];
+}
+
+export interface KtxDictionarySearchResponse {
+ searched: KtxDictionarySearchSearchedConnection[];
+ results: KtxDictionarySearchValueResult[];
+}
+
+interface RelationshipProfileArtifact {
+ connectionId?: string;
+ profileSampleRows?: unknown;
+ sampleValuesPerColumn?: unknown;
+ profiledAt?: unknown;
+ extractedAt?: unknown;
+}
+
+function uniqueSorted(values: Iterable): string[] {
+ return [...new Set([...values].filter((value) => value.trim().length > 0))].sort((left, right) =>
+ left.localeCompare(right),
+ );
+}
+
+function latestProfileSyncId(path: string): string | null {
+ const parts = path.split('/');
+ return parts.at(-3) ?? null;
+}
+
+function optionalNumber(value: unknown): number | null {
+ return typeof value === 'number' && Number.isFinite(value) ? value : null;
+}
+
+function optionalString(value: unknown): string | null {
+ return typeof value === 'string' && value.trim().length > 0 ? value : null;
+}
+
+async function latestProfilePath(project: KtxLocalProject, connectionId: string): Promise {
+ const root = `raw-sources/${connectionId}/live-database`;
+ let files: string[];
+ try {
+ files = (await project.fileStore.listFiles(root)).files;
+ } catch {
+ return null;
+ }
+ return files
+ .filter((path) => path.endsWith('/enrichment/relationship-profile.json'))
+ .sort((left, right) => left.localeCompare(right))
+ .at(-1) ?? null;
+}
+
+async function readProfile(project: KtxLocalProject, path: string): Promise {
+ const raw = await project.fileStore.readFile(path);
+ const parsed = JSON.parse(raw.content) as unknown;
+ return typeof parsed === 'object' && parsed !== null && !Array.isArray(parsed)
+ ? (parsed as RelationshipProfileArtifact)
+ : {};
+}
+
+function profiledColumnCount(entries: readonly SlDictionaryEntry[]): number {
+ return new Set(entries.map((entry) => `${entry.sourceName}\u001f${entry.columnName}`)).size;
+}
+
+async function searchedConnection(
+ project: KtxLocalProject,
+ connectionId: string,
+ entries: readonly SlDictionaryEntry[],
+): Promise {
+ const path = await latestProfilePath(project, connectionId);
+ if (!path) {
+ return {
+ connectionId,
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 0,
+ syncId: null,
+ profiledAt: null,
+ },
+ status: 'no_profile_artifact',
+ };
+ }
+
+ const profile = await readProfile(project, path);
+ const count = profiledColumnCount(entries);
+ return {
+ connectionId,
+ coverage: {
+ sampledRows: optionalNumber(profile.profileSampleRows),
+ valuesPerColumn: optionalNumber(profile.sampleValuesPerColumn),
+ profiledColumns: count,
+ syncId: latestProfileSyncId(path),
+ profiledAt: optionalString(profile.profiledAt) ?? optionalString(profile.extractedAt),
+ },
+ status: count > 0 ? 'ready' : 'no_candidate_columns',
+ };
+}
+
+function entryMatchesValue(entry: SlDictionaryEntry, value: string): boolean {
+ return entry.value.toLowerCase().includes(value.toLowerCase());
+}
+
+function toMatch(entry: SlDictionaryEntry): KtxDictionarySearchMatch {
+ return {
+ connectionId: entry.connectionId,
+ sourceName: entry.sourceName,
+ columnName: entry.columnName,
+ matchedValue: entry.value,
+ cardinality: entry.cardinality,
+ };
+}
+
+function sortMatches(matches: KtxDictionarySearchMatch[]): KtxDictionarySearchMatch[] {
+ return matches.sort(
+ (left, right) =>
+ left.connectionId.localeCompare(right.connectionId) ||
+ left.sourceName.localeCompare(right.sourceName) ||
+ left.columnName.localeCompare(right.columnName) ||
+ left.matchedValue.localeCompare(right.matchedValue),
+ );
+}
+
+function missReason(status: KtxDictionarySearchStatus): KtxDictionarySearchMissReason {
+ return status === 'ready' ? 'value_not_in_sample' : status;
+}
+
+export function createKtxDictionarySearchService(project: KtxLocalProject) {
+ return {
+ async search(input: KtxDictionarySearchInput): Promise {
+ const connectionIds = input.connectionId ? [input.connectionId] : uniqueSorted(Object.keys(project.config.connections));
+ const entries = await loadLatestSlDictionaryEntries(project, connectionIds);
+ const entriesByConnection = new Map();
+ for (const connectionId of connectionIds) {
+ entriesByConnection.set(
+ connectionId,
+ entries.filter((entry) => entry.connectionId === connectionId),
+ );
+ }
+
+ const searched = (
+ await Promise.all(
+ connectionIds.map((connectionId) =>
+ searchedConnection(project, connectionId, entriesByConnection.get(connectionId) ?? []),
+ ),
+ )
+ ).sort((left, right) => left.connectionId.localeCompare(right.connectionId));
+ const searchedByConnection = new Map(searched.map((connection) => [connection.connectionId, connection]));
+
+ return {
+ searched,
+ results: input.values.map((value) => {
+ const matches = sortMatches(entries.filter((entry) => entryMatchesValue(entry, value)).map(toMatch));
+ const matchedConnections = new Set(matches.map((match) => match.connectionId));
+ return {
+ value,
+ matches,
+ misses: searched
+ .filter((connection) => !matchedConnections.has(connection.connectionId))
+ .map((connection) => ({
+ connectionId: connection.connectionId,
+ reason: missReason(searchedByConnection.get(connection.connectionId)?.status ?? 'no_profile_artifact'),
+ })),
+ };
+ }),
+ };
+ },
+ };
+}
+```
+
+- [ ] **Step 4: Export the service**
+
+In `packages/context/src/sl/index.ts`, add:
+
+```typescript
+export {
+ createKtxDictionarySearchService,
+} from './dictionary-search.js';
+export type {
+ KtxDictionarySearchCoverage,
+ KtxDictionarySearchInput,
+ KtxDictionarySearchMatch,
+ KtxDictionarySearchMiss,
+ KtxDictionarySearchMissReason,
+ KtxDictionarySearchResponse,
+ KtxDictionarySearchSearchedConnection,
+ KtxDictionarySearchStatus,
+ KtxDictionarySearchValueResult,
+} from './dictionary-search.js';
+```
+
+- [ ] **Step 5: Run service tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/sl/dictionary-search.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 6: Commit the service slice**
+
+Run:
+
+```bash
+git add packages/context/src/sl/dictionary-search.ts packages/context/src/sl/dictionary-search.test.ts packages/context/src/sl/index.ts
+git commit -m "feat(context): add dictionary search service"
+```
+
+## Task 2: Register The MCP `dictionary_search` Tool
+
+**Files:**
+- Modify: `packages/context/src/mcp/types.ts`
+- Modify: `packages/context/src/mcp/context-tools.ts`
+- Modify: `packages/context/src/mcp/server.test.ts`
+- Modify: `packages/context/src/mcp/index.ts`
+
+- [ ] **Step 1: Add MCP port types**
+
+In `packages/context/src/mcp/types.ts`, extend the imports:
+
+```typescript
+import type { KtxDictionarySearchInput, KtxDictionarySearchResponse } from '../sl/index.js';
+```
+
+Add this interface near the other MCP port interfaces:
+
+```typescript
+export interface KtxDictionarySearchMcpPort {
+ search(input: KtxDictionarySearchInput): Promise;
+}
+```
+
+Add the new optional port to `KtxMcpContextPorts`:
+
+```typescript
+export interface KtxMcpContextPorts {
+ connections?: KtxConnectionsMcpPort;
+ knowledge?: KtxKnowledgeMcpPort;
+ semanticLayer?: KtxSemanticLayerMcpPort;
+ entityDetails?: KtxEntityDetailsMcpPort;
+ dictionarySearch?: KtxDictionarySearchMcpPort;
+ sqlExecution?: KtxSqlExecutionMcpPort;
+ ingest?: KtxIngestMcpPort;
+ scan?: KtxScanMcpPort;
+}
+```
+
+- [ ] **Step 2: Write failing MCP registration test**
+
+In `packages/context/src/mcp/server.test.ts`, update the type import list to include:
+
+```typescript
+KtxDictionarySearchMcpPort,
+```
+
+Add this test after the `entity_details` registration test:
+
+```typescript
+ it('registers dictionary_search when the host provides a dictionary-search port', async () => {
+ const fake = makeFakeServer();
+ const dictionarySearch: KtxDictionarySearchMcpPort = {
+ search: vi.fn().mockResolvedValue({
+ searched: [
+ {
+ connectionId: 'warehouse',
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 1,
+ syncId: 'sync-1',
+ profiledAt: null,
+ },
+ status: 'ready',
+ },
+ ],
+ results: [
+ {
+ value: 'paid',
+ matches: [
+ {
+ connectionId: 'warehouse',
+ sourceName: 'orders',
+ columnName: 'status',
+ matchedValue: 'paid',
+ cardinality: 3,
+ },
+ ],
+ misses: [],
+ },
+ ],
+ }),
+ };
+
+ createKtxMcpServer({
+ server: fake.server,
+ userContext: { userId: 'local-user' },
+ contextTools: { dictionarySearch },
+ });
+
+ expect(fake.tools.map((tool) => tool.name)).toEqual(['dictionary_search']);
+ await expect(
+ getTool(fake.tools, 'dictionary_search').handler({
+ connectionId: 'warehouse',
+ values: ['paid'],
+ }),
+ ).resolves.toMatchObject({
+ structuredContent: {
+ searched: [{ connectionId: 'warehouse', status: 'ready' }],
+ results: [
+ {
+ value: 'paid',
+ matches: [{ connectionId: 'warehouse', sourceName: 'orders', columnName: 'status' }],
+ misses: [],
+ },
+ ],
+ },
+ });
+ expect(dictionarySearch.search).toHaveBeenCalledWith({
+ connectionId: 'warehouse',
+ values: ['paid'],
+ });
+ });
+```
+
+- [ ] **Step 3: Run failing MCP registration test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts -t "dictionary_search"
+```
+
+Expected: FAIL because `dictionary_search` is not registered.
+
+- [ ] **Step 4: Add the MCP schema and registration**
+
+In `packages/context/src/mcp/context-tools.ts`, add the input schema near the other research schemas:
+
+```typescript
+const dictionarySearchSchema = z.object({
+ values: z.array(z.string().min(1)).min(1).max(20),
+ connectionId: connectionIdSchema.optional(),
+});
+```
+
+Add this registration block after `entity_details` and before `sql_execution`:
+
+```typescript
+ if (ports.dictionarySearch) {
+ const dictionarySearch = ports.dictionarySearch;
+ registerParsedTool(
+ server,
+ 'dictionary_search',
+ {
+ title: 'Dictionary Search',
+ description:
+ 'Search profile-sampled warehouse values and report matching connection/source/column locations plus non-authoritative miss reasons.',
+ inputSchema: dictionarySearchSchema.shape,
+ },
+ dictionarySearchSchema,
+ async (input) => jsonToolResult(await dictionarySearch.search(input)),
+ );
+ }
+```
+
+- [ ] **Step 5: Confirm MCP barrel exports**
+
+Open `packages/context/src/mcp/index.ts`. If it exports from `./types.js`, no change is needed. If it lists named type exports, add `KtxDictionarySearchMcpPort` to that list.
+
+- [ ] **Step 6: Run MCP registration test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts -t "dictionary_search"
+```
+
+Expected: PASS.
+
+- [ ] **Step 7: Commit MCP registration**
+
+Run:
+
+```bash
+git add packages/context/src/mcp/types.ts packages/context/src/mcp/context-tools.ts packages/context/src/mcp/server.test.ts packages/context/src/mcp/index.ts
+git commit -m "feat(context): register MCP dictionary search tool"
+```
+
+## Task 3: Wire Local Project MCP Ports
+
+**Files:**
+- Modify: `packages/context/src/mcp/local-project-ports.ts`
+- Modify: `packages/context/src/mcp/local-project-ports.test.ts`
+
+- [ ] **Step 1: Write failing local-port tests**
+
+In `packages/context/src/mcp/local-project-ports.test.ts`, add this test after the entity-details local-port tests:
+
+```typescript
+ it('exposes local dictionary search through MCP ports', async () => {
+ const project = await initKtxProject({ projectDir: tempDir, projectName: 'warehouse' });
+ project.config.connections.warehouse = {
+ driver: 'postgres',
+ url: 'env:DATABASE_URL',
+ };
+ await project.fileStore.writeFile(
+ 'raw-sources/warehouse/live-database/sync-1/enrichment/relationship-profile.json',
+ `${JSON.stringify(
+ {
+ connectionId: 'warehouse',
+ driver: 'postgres',
+ sqlAvailable: true,
+ queryCount: 4,
+ tables: [],
+ columns: {
+ 'orders.status': {
+ table: { catalog: null, db: 'public', name: 'orders' },
+ column: 'status',
+ nativeType: 'text',
+ normalizedType: 'string',
+ distinctCount: 2,
+ sampleValues: ['paid', 'refunded'],
+ },
+ },
+ warnings: [],
+ },
+ null,
+ 2,
+ )}\n`,
+ 'ktx',
+ 'ktx@example.com',
+ 'Seed dictionary profile',
+ );
+
+ const ports = createLocalProjectMcpContextPorts(project);
+
+ await expect(ports.dictionarySearch?.search({ values: ['paid'] })).resolves.toMatchObject({
+ searched: [{ connectionId: 'warehouse', status: 'ready' }],
+ results: [
+ {
+ value: 'paid',
+ matches: [{ connectionId: 'warehouse', sourceName: 'orders', columnName: 'status', matchedValue: 'paid' }],
+ misses: [],
+ },
+ ],
+ });
+ });
+
+ it('reports missing local dictionary profiles through MCP ports', async () => {
+ const project = await initKtxProject({ projectDir: tempDir, projectName: 'warehouse' });
+ project.config.connections.warehouse = {
+ driver: 'postgres',
+ url: 'env:DATABASE_URL',
+ };
+
+ const ports = createLocalProjectMcpContextPorts(project);
+
+ await expect(ports.dictionarySearch?.search({ values: ['paid'] })).resolves.toEqual({
+ searched: [
+ {
+ connectionId: 'warehouse',
+ coverage: {
+ sampledRows: null,
+ valuesPerColumn: null,
+ profiledColumns: 0,
+ syncId: null,
+ profiledAt: null,
+ },
+ status: 'no_profile_artifact',
+ },
+ ],
+ results: [
+ {
+ value: 'paid',
+ matches: [],
+ misses: [{ connectionId: 'warehouse', reason: 'no_profile_artifact' }],
+ },
+ ],
+ });
+ });
+```
+
+- [ ] **Step 2: Run failing local-port tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/local-project-ports.test.ts -t "dictionary"
+```
+
+Expected: FAIL because `ports.dictionarySearch` is undefined.
+
+- [ ] **Step 3: Wire the local port**
+
+In `packages/context/src/mcp/local-project-ports.ts`, update the SL import block to include:
+
+```typescript
+createKtxDictionarySearchService,
+```
+
+Add this port to the `ports` object returned by `createLocalProjectMcpContextPorts()` near `entityDetails`:
+
+```typescript
+ dictionarySearch: {
+ async search(input) {
+ return createKtxDictionarySearchService(project).search(input);
+ },
+ },
+```
+
+- [ ] **Step 4: Run local-port tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/local-project-ports.test.ts -t "dictionary"
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Commit local-port wiring**
+
+Run:
+
+```bash
+git add packages/context/src/mcp/local-project-ports.ts packages/context/src/mcp/local-project-ports.test.ts
+git commit -m "feat(context): expose local MCP dictionary search"
+```
+
+## Task 4: Final Verification
+
+**Files:**
+- Verify all files changed in Tasks 1-3.
+
+- [ ] **Step 1: Run focused tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/sl/dictionary-search.test.ts src/mcp/server.test.ts src/mcp/local-project-ports.test.ts
+```
+
+Expected: PASS for dictionary-search service, MCP registration, and local-port coverage.
+
+- [ ] **Step 2: Run context type-check**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context run type-check
+```
+
+Expected: PASS.
+
+- [ ] **Step 3: Inspect diff**
+
+Run:
+
+```bash
+git status --short
+git diff --stat HEAD
+```
+
+Expected: only the dictionary-search service, MCP type/registration, tests, and exports changed.
+
+- [ ] **Step 4: Commit verification note if needed**
+
+If the previous tasks already committed all source changes, do not create an empty commit. If a small follow-up fix was required during verification, commit only those files:
+
+```bash
+git add packages/context/src/sl/dictionary-search.ts packages/context/src/sl/dictionary-search.test.ts packages/context/src/sl/index.ts packages/context/src/mcp/types.ts packages/context/src/mcp/context-tools.ts packages/context/src/mcp/server.test.ts packages/context/src/mcp/index.ts packages/context/src/mcp/local-project-ports.ts packages/context/src/mcp/local-project-ports.test.ts
+git commit -m "test(context): cover MCP dictionary search"
+```
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-discover-data.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-discover-data.md
new file mode 100644
index 00000000..a917eb72
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-discover-data.md
@@ -0,0 +1,1315 @@
+# Research Agent MCP Discover Data Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Add the MCP-shaped `discover_data` tool so external research agents get one ranked discovery view across wiki pages, semantic-layer sources/measures/dimensions, and raw warehouse schema.
+
+**Architecture:** Create a focused local discovery service in `packages/context/src/search/discover.ts` that builds deterministic per-kind refs from existing wiki, semantic-layer, and latest scan artifacts, fuses the wiki/SL/raw sub-searches with the existing RRF core, and re-reads local artifacts on every call for MCP daemon freshness. Register the service through the MCP context port and local project MCP ports without changing the existing ingest-only `discover_data` adapter yet.
+
+**Tech Stack:** TypeScript, Vitest, Zod, KTX local file store, KTX wiki/SL/scan services, KTX MCP context ports, existing `HybridSearchCore`/RRF search utilities.
+
+---
+
+## Audit Summary
+
+Original spec: `docs/superpowers/specs/2026-05-14-research-agent-mcp-tools-design.md`
+
+Implemented v1 slices confirmed in current source:
+
+- Existing in-process MCP semantic runtime exists in `packages/context/src/mcp/server.ts`, `packages/context/src/mcp/context-tools.ts`, and `packages/context/src/mcp/local-project-ports.ts`.
+- Ingest-only warehouse verification tools exist under `packages/context/src/ingest/tools/warehouse-verification/`.
+- MCP `sql_execution` is implemented and parser-gated: `python/ktx-daemon/src/ktx_daemon/sql_analysis.py` has `validate_read_only_sql_response`, `python/ktx-daemon/src/ktx_daemon/app.py` exposes `POST /sql/validate-read-only`, `packages/context/src/sql-analysis/ports.ts` has `validateReadOnly()`, and `packages/context/src/mcp/context-tools.ts` registers `sql_execution`.
+- MCP `entity_details` is implemented: `packages/context/src/scan/entity-details.ts`, `KtxEntityDetailsMcpPort`, context-tool registration, and local project wiring all exist.
+- MCP `dictionary_search` is implemented: `packages/context/src/sl/dictionary-search.ts`, `KtxDictionarySearchMcpPort`, context-tool registration, and local project wiring all exist.
+
+V1-blocking gaps still open:
+
+- `discover_data` is not implemented on the MCP surface. There is no `packages/context/src/search/discover.ts`, no `KtxDiscoverDataMcpPort`, no `ports.discover`, no MCP registration, and no local project wiring.
+- `ktx mcp start|stop|status|logs` and the HTTP Streamable MCP daemon do not exist. There is no `packages/cli/src/commands/mcp-commands.ts`, no `packages/cli/src/managed-mcp-daemon.ts`, and `packages/cli/src/cli-program.ts` does not register an `mcp` command subtree.
+- `ktx setup-agents` does not install `ktx-research`, write Claude Code/Cursor MCP JSON entries, or print Codex/opencode snippets. `plannedKtxAgentFiles()` still installs only the existing `ktx` skill/rule files.
+- Ingest-side warehouse verification tools still use `connectionName`, `targets`, and `rowLimit` contracts. The original spec says these should converge on `connectionId` naming, but that cleanup can be planned after the MCP research surface is complete because this plan adds a separate MCP adapter with the required shape.
+
+Non-blocking or explicitly out-of-scope gaps:
+
+- Python code execution via MCP.
+- Stdio MCP transport.
+- OS-level auto-start.
+- Native TLS, audit logging, rate limiting, per-tool authorization, and multi-project daemon routing.
+- Streaming SQL results.
+
+This plan covers only the next dependency-ordered v1 blocker: MCP `discover_data`. Later v1 plans still need to cover the HTTP daemon and setup-agent/research-skill installation.
+
+## File Structure
+
+Create:
+
+- `packages/context/src/search/discover.ts`
+ - Defines MCP-shaped `discover_data` input, ref, and response types.
+ - Searches wiki pages through `searchLocalKnowledgePages()` and `readLocalKnowledgePage()`.
+ - Searches semantic-layer records through `loadLocalSlSourceRecords()`.
+ - Searches raw schema by reading the latest `raw-sources//live-database/` scan artifacts directly.
+ - Fuses wiki, SL, and raw-schema candidates with `HybridSearchCore` using equal lane weights and normalizes final scores to `0..1`.
+ - Re-reads artifacts on every call; no long-lived cache.
+- `packages/context/src/search/discover.test.ts`
+ - Covers unified result shape, kind filtering, connection scoping, score normalization, snippet cap, raw table refs, and freshness after a newer scan appears.
+
+Modify:
+
+- `packages/context/src/search/index.ts`
+ - Export `createKtxDiscoverDataService` and discover types.
+- `packages/context/src/mcp/types.ts`
+ - Add `KtxDiscoverDataMcpPort` and `discover?: KtxDiscoverDataMcpPort` to `KtxMcpContextPorts`.
+- `packages/context/src/mcp/context-tools.ts`
+ - Add the `discover_data` Zod schema and tool registration.
+- `packages/context/src/mcp/server.test.ts`
+ - Assert `discover_data` registration and structured array output.
+- `packages/context/src/mcp/local-project-ports.ts`
+ - Wire local project `discover.search()` to `createKtxDiscoverDataService()`.
+- `packages/context/src/mcp/local-project-ports.test.ts`
+ - Cover local-port `discover_data` across wiki, SL, and raw schema.
+- `packages/context/src/mcp/index.ts`
+ - Export the new MCP port type if it is not already covered by existing barrel exports.
+
+## Task 1: Add The Local Discover Data Service
+
+**Files:**
+- Create: `packages/context/src/search/discover.test.ts`
+- Create: `packages/context/src/search/discover.ts`
+- Modify: `packages/context/src/search/index.ts`
+
+- [ ] **Step 1: Write failing service tests**
+
+Create `packages/context/src/search/discover.test.ts`:
+
+```typescript
+import { mkdtemp, rm } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+import { initKtxProject, type KtxLocalProject } from '../project/index.js';
+import { writeLocalKnowledgePage } from '../wiki/local-knowledge.js';
+import { createKtxDiscoverDataService } from './discover.js';
+
+describe('createKtxDiscoverDataService', () => {
+ let tempDir: string;
+ let project: KtxLocalProject;
+
+ beforeEach(async () => {
+ tempDir = await mkdtemp(join(tmpdir(), 'ktx-discover-data-'));
+ project = await initKtxProject({ projectDir: join(tempDir, 'project'), projectName: 'warehouse' });
+ project.config.connections.warehouse = { driver: 'postgres', url: 'env:DATABASE_URL' };
+ project.config.connections.billing = { driver: 'postgres', url: 'env:BILLING_DATABASE_URL' };
+ });
+
+ afterEach(async () => {
+ await rm(tempDir, { recursive: true, force: true });
+ });
+
+ async function seedWiki(): Promise {
+ await writeLocalKnowledgePage(project, {
+ key: 'orders-playbook',
+ scope: 'GLOBAL',
+ summary: 'Paid order operations',
+ content: 'Use paid orders and order_count to inspect monthly customer activity for Acme Corp.',
+ tags: ['orders'],
+ });
+ }
+
+ async function seedSl(): Promise {
+ await project.fileStore.writeFile(
+ 'semantic-layer/warehouse/orders.yaml',
+ [
+ 'name: orders',
+ 'descriptions:',
+ ' user: Paid order facts',
+ 'table: public.orders',
+ 'grain: [id]',
+ 'columns:',
+ ' - name: status',
+ ' type: string',
+ ' descriptions:',
+ ' user: Payment status for the order',
+ ' - name: ordered_at',
+ ' type: time',
+ 'measures:',
+ ' - name: order_count',
+ ' expr: count(*)',
+ ' description: Number of paid orders',
+ '',
+ ].join('\n'),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed sl source',
+ );
+ }
+
+ async function seedScan(input: {
+ connectionId?: string;
+ syncId: string;
+ tableName?: string;
+ comment?: string;
+ sampleValues?: string[];
+ }): Promise {
+ const connectionId = input.connectionId ?? 'warehouse';
+ const root = `raw-sources/${connectionId}/live-database/${input.syncId}`;
+ const tableName = input.tableName ?? 'orders';
+ await project.fileStore.writeFile(
+ `${root}/connection.json`,
+ JSON.stringify(
+ {
+ connectionId,
+ driver: 'postgres',
+ extractedAt: `2026-05-14T09:00:00.000Z`,
+ scope: { schemas: ['public'] },
+ },
+ null,
+ 2,
+ ),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed scan connection',
+ );
+ await project.fileStore.writeFile(
+ `${root}/tables/public-${tableName}.json`,
+ JSON.stringify(
+ {
+ catalog: null,
+ db: 'public',
+ name: tableName,
+ kind: 'table',
+ comment: input.comment ?? 'Orders table from warehouse',
+ estimatedRows: 123,
+ descriptions: { db: input.comment ?? 'Orders table from warehouse' },
+ columns: [
+ {
+ name: 'id',
+ nativeType: 'integer',
+ normalizedType: 'integer',
+ dimensionType: 'number',
+ nullable: false,
+ primaryKey: true,
+ comment: 'Order id',
+ },
+ {
+ name: 'status',
+ nativeType: 'text',
+ normalizedType: 'text',
+ dimensionType: 'string',
+ nullable: false,
+ primaryKey: false,
+ comment: 'Order status',
+ sampleValues: input.sampleValues ?? ['paid', 'pending'],
+ },
+ ],
+ foreignKeys: [],
+ },
+ null,
+ 2,
+ ),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed table',
+ );
+ await project.fileStore.writeFile(
+ `${root}/scan-report.json`,
+ JSON.stringify(
+ {
+ connectionId,
+ driver: 'postgres',
+ syncId: input.syncId,
+ runId: `scan-${input.syncId}`,
+ trigger: 'mcp',
+ mode: 'enriched',
+ dryRun: false,
+ artifactPaths: {
+ rawSourcesDir: root,
+ reportPath: `${root}/scan-report.json`,
+ manifestShards: [],
+ enrichmentArtifacts: [],
+ },
+ diffSummary: {
+ tablesAdded: 1,
+ tablesModified: 0,
+ tablesDeleted: 0,
+ tablesUnchanged: 0,
+ columnsAdded: 0,
+ columnsModified: 0,
+ columnsDeleted: 0,
+ },
+ manifestShardsWritten: 0,
+ structuralSyncStats: {
+ tablesCreated: 0,
+ tablesUpdated: 0,
+ tablesDeleted: 0,
+ columnsCreated: 0,
+ columnsUpdated: 0,
+ columnsDeleted: 0,
+ },
+ enrichment: {
+ dataDictionary: 'completed',
+ tableDescriptions: 'completed',
+ columnDescriptions: 'completed',
+ embeddings: 'skipped',
+ deterministicRelationships: 'skipped',
+ llmRelationshipValidation: 'skipped',
+ statisticalValidation: 'skipped',
+ },
+ capabilityGaps: [],
+ warnings: [],
+ relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
+ enrichmentState: { resumedStages: [], completedStages: [], failedStages: [] },
+ createdAt: '2026-05-14T09:00:00.000Z',
+ },
+ null,
+ 2,
+ ),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed scan report',
+ );
+ }
+
+ it('returns unified ranked refs across wiki, semantic-layer, and raw schema', async () => {
+ await seedWiki();
+ await seedSl();
+ await seedScan({ syncId: 'sync-1', sampleValues: ['paid', 'refunded'] });
+ const service = createKtxDiscoverDataService(project, { userId: 'local-user' });
+
+ const results = await service.search({ query: 'paid orders', connectionId: 'warehouse', limit: 10 });
+
+ expect(results.map((result) => result.kind)).toEqual(
+ expect.arrayContaining(['wiki', 'sl_source', 'sl_measure', 'sl_dimension', 'table', 'column']),
+ );
+ expect(results.every((result) => result.score >= 0 && result.score <= 1)).toBe(true);
+ expect(results.every((result) => result.snippet === null || result.snippet.length <= 200)).toBe(true);
+ expect(results).toContainEqual(
+ expect.objectContaining({
+ kind: 'table',
+ id: 'public.orders',
+ connectionId: 'warehouse',
+ tableRef: { catalog: null, db: 'public', name: 'orders' },
+ matchedOn: expect.stringMatching(/name|description|comment|display/),
+ }),
+ );
+ expect(results).toContainEqual(
+ expect.objectContaining({
+ kind: 'column',
+ id: 'public.orders.status',
+ connectionId: 'warehouse',
+ columnName: 'status',
+ matchedOn: expect.stringMatching(/name|comment|description|sample_value/),
+ }),
+ );
+ expect(results).toContainEqual(
+ expect.objectContaining({
+ kind: 'sl_measure',
+ id: 'orders.order_count',
+ connectionId: 'warehouse',
+ summary: 'Number of paid orders',
+ snippet: 'count(*)',
+ matchedOn: expect.stringMatching(/name|description|expr/),
+ }),
+ );
+ });
+
+ it('honors kind filters and connection scope', async () => {
+ await seedWiki();
+ await seedSl();
+ await seedScan({ syncId: 'sync-1', connectionId: 'warehouse', tableName: 'orders' });
+ await seedScan({ syncId: 'sync-2', connectionId: 'billing', tableName: 'invoices', comment: 'Billing invoices' });
+ const service = createKtxDiscoverDataService(project);
+
+ const results = await service.search({
+ query: 'orders',
+ connectionId: 'warehouse',
+ kinds: ['table', 'column'],
+ limit: 10,
+ });
+
+ expect(results.every((result) => result.kind === 'table' || result.kind === 'column')).toBe(true);
+ expect(results.every((result) => result.connectionId === 'warehouse')).toBe(true);
+ expect(results.some((result) => result.id.includes('invoices'))).toBe(false);
+ expect(results.some((result) => result.kind === 'wiki')).toBe(false);
+ });
+
+ it('re-reads the latest scan artifacts on each call', async () => {
+ await seedScan({ syncId: 'sync-1', tableName: 'orders', comment: 'Old orders table' });
+ const service = createKtxDiscoverDataService(project);
+ await expect(service.search({ query: 'orders', connectionId: 'warehouse', kinds: ['table'], limit: 10 })).resolves.toEqual(
+ expect.arrayContaining([expect.objectContaining({ id: 'public.orders' })]),
+ );
+
+ await seedScan({ syncId: 'sync-2', tableName: 'invoices', comment: 'Invoice facts' });
+ const fresh = await service.search({ query: 'invoice', connectionId: 'warehouse', kinds: ['table'], limit: 10 });
+
+ expect(fresh).toEqual(expect.arrayContaining([expect.objectContaining({ id: 'public.invoices' })]));
+ expect(fresh.some((result) => result.id === 'public.orders')).toBe(false);
+ });
+});
+```
+
+- [ ] **Step 2: Run the failing service tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/search/discover.test.ts
+```
+
+Expected: FAIL with `Cannot find module './discover.js'`.
+
+- [ ] **Step 3: Implement the discover service**
+
+Create `packages/context/src/search/discover.ts`:
+
+```typescript
+import type { KtxEmbeddingPort } from '../core/index.js';
+import type { KtxLocalProject } from '../project/index.js';
+import type { KtxScanReport, KtxSchemaColumn, KtxSchemaTable, KtxTableRef } from '../scan/index.js';
+import { DEFAULT_PRIORITY, loadLocalSlSourceRecords, resolveDescription } from '../sl/index.js';
+import type { SemanticLayerSource } from '../sl/index.js';
+import { readLocalKnowledgePage, searchLocalKnowledgePages } from '../wiki/local-knowledge.js';
+import { HybridSearchCore, type FusedSearchCandidate, type SearchCandidateGenerator } from './index.js';
+
+export type KtxDiscoverDataKind = 'wiki' | 'sl_source' | 'sl_measure' | 'sl_dimension' | 'table' | 'column';
+export type KtxDiscoverDataMatchedOn =
+ | 'name'
+ | 'display'
+ | 'description'
+ | 'comment'
+ | 'expr'
+ | 'sample_value'
+ | 'body';
+
+export interface KtxDiscoverDataInput {
+ query: string;
+ connectionId?: string;
+ kinds?: KtxDiscoverDataKind[];
+ limit?: number;
+}
+
+export interface KtxDiscoverDataRef {
+ kind: KtxDiscoverDataKind;
+ id: string;
+ score: number;
+ summary: string | null;
+ snippet: string | null;
+ matchedOn: KtxDiscoverDataMatchedOn;
+ connectionId?: string;
+ tableRef?: KtxTableRef;
+ columnName?: string;
+}
+
+export type KtxDiscoverDataResponse = KtxDiscoverDataRef[];
+
+export interface KtxDiscoverDataServiceOptions {
+ userId?: string;
+ embeddingService?: KtxEmbeddingPort | null;
+}
+
+interface CandidateRecord {
+ ref: Omit;
+ rankScore: number;
+}
+
+type RawTable = KtxSchemaTable & {
+ descriptions?: Record;
+ columns: Array; sampleValues?: unknown[] }>;
+};
+
+interface LatestScan {
+ report: KtxScanReport;
+ rawSourcesDir: string;
+ tables: RawTable[];
+}
+
+const ALL_KINDS: KtxDiscoverDataKind[] = ['wiki', 'sl_source', 'sl_measure', 'sl_dimension', 'table', 'column'];
+
+function normalize(value: string | null | undefined): string {
+ return (value ?? '').toLowerCase();
+}
+
+function queryTerms(query: string): string[] {
+ return query
+ .toLowerCase()
+ .split(/[^a-z0-9_]+/u)
+ .map((term) => term.trim())
+ .filter(Boolean);
+}
+
+function hasKind(kinds: ReadonlySet, kind: KtxDiscoverDataKind): boolean {
+ return kinds.has(kind);
+}
+
+function cap200(value: string | null | undefined): string | null {
+ if (!value) {
+ return null;
+ }
+ const compact = value.replace(/\s+/g, ' ').trim();
+ return compact.length > 200 ? compact.slice(0, 200) : compact;
+}
+
+function snippetAround(text: string | null | undefined, terms: readonly string[]): string | null {
+ if (!text) {
+ return null;
+ }
+ const lower = text.toLowerCase();
+ const index = terms.map((term) => lower.indexOf(term)).filter((position) => position >= 0).sort((a, b) => a - b)[0] ?? 0;
+ return cap200(text.slice(Math.max(0, index - 60), index + 140));
+}
+
+function textScore(value: string | null | undefined, terms: readonly string[]): number {
+ const haystack = normalize(value);
+ if (!haystack || terms.length === 0) {
+ return 0;
+ }
+ const matched = terms.filter((term) => haystack.includes(term)).length;
+ return matched / terms.length;
+}
+
+function bestField(
+ fields: Array<{ matchedOn: KtxDiscoverDataMatchedOn; text: string | null | undefined; weight: number }>,
+ terms: readonly string[],
+): { matchedOn: KtxDiscoverDataMatchedOn; score: number; text: string | null } | null {
+ const scored = fields
+ .map((field) => ({
+ matchedOn: field.matchedOn,
+ score: textScore(field.text, terms) * field.weight,
+ text: field.text ?? null,
+ }))
+ .filter((field) => field.score > 0)
+ .sort((left, right) => right.score - left.score || left.matchedOn.localeCompare(right.matchedOn));
+ return scored[0] ?? null;
+}
+
+function displayForTable(table: KtxTableRef): string {
+ return [table.catalog, table.db, table.name].filter((part): part is string => Boolean(part)).join('.');
+}
+
+function tableRef(table: KtxSchemaTable): KtxTableRef {
+ return { catalog: table.catalog, db: table.db, name: table.name };
+}
+
+async function readJson(project: KtxLocalProject, path: string): Promise {
+ return JSON.parse((await project.fileStore.readFile(path)).content) as T;
+}
+
+async function latestScan(project: KtxLocalProject, connectionId: string): Promise {
+ const root = `raw-sources/${connectionId}/live-database`;
+ let files: string[];
+ try {
+ files = (await project.fileStore.listFiles(root)).files;
+ } catch {
+ return null;
+ }
+
+ const reportPath = files.filter((path) => path.endsWith('/scan-report.json')).sort().at(-1);
+ if (!reportPath) {
+ return null;
+ }
+ const report = await readJson(project, reportPath);
+ const rawSourcesDir = report.artifactPaths.rawSourcesDir ?? reportPath.slice(0, -'/scan-report.json'.length);
+ const listedTables = await project.fileStore.listFiles(`${rawSourcesDir}/tables`);
+ const tables: RawTable[] = [];
+ for (const path of listedTables.files.filter((file) => file.endsWith('.json')).sort()) {
+ tables.push(await readJson(project, path));
+ }
+ return { report, rawSourcesDir, tables };
+}
+
+function configuredConnectionIds(project: KtxLocalProject, connectionId?: string): string[] {
+ return connectionId ? [connectionId] : Object.keys(project.config.connections).sort();
+}
+
+async function wikiCandidates(
+ project: KtxLocalProject,
+ input: KtxDiscoverDataInput,
+ options: KtxDiscoverDataServiceOptions,
+ terms: readonly string[],
+): Promise {
+ const searchResults = await searchLocalKnowledgePages(project, {
+ query: input.query,
+ userId: options.userId,
+ embeddingService: options.embeddingService ?? null,
+ limit: Math.max(input.limit ?? 15, 25),
+ });
+ const records: CandidateRecord[] = [];
+ for (const result of searchResults) {
+ const page = await readLocalKnowledgePage(project, { key: result.key, userId: options.userId });
+ const content = page?.content ?? '';
+ const matched = bestField(
+ [
+ { matchedOn: 'name', text: result.key, weight: 1.1 },
+ { matchedOn: 'description', text: result.summary, weight: 1 },
+ { matchedOn: 'body', text: content, weight: 0.8 },
+ ],
+ terms,
+ );
+ records.push({
+ rankScore: result.score + (matched?.score ?? 0),
+ ref: {
+ kind: 'wiki',
+ id: result.key,
+ summary: result.summary || null,
+ snippet: snippetAround(content, terms),
+ matchedOn: matched?.matchedOn ?? 'body',
+ },
+ });
+ }
+ return records.sort((left, right) => right.rankScore - left.rankScore || left.ref.id.localeCompare(right.ref.id));
+}
+
+async function slCandidates(
+ project: KtxLocalProject,
+ input: KtxDiscoverDataInput,
+ kinds: ReadonlySet,
+ terms: readonly string[],
+): Promise {
+ const records: CandidateRecord[] = [];
+ for (const connectionId of configuredConnectionIds(project, input.connectionId)) {
+ const sources = await loadLocalSlSourceRecords(project, { connectionId }).catch(() => []);
+ for (const sourceRecord of sources) {
+ const source = sourceRecord.source;
+ if (hasKind(kinds, 'sl_source')) {
+ const description = resolveDescription(source.descriptions, { priority: DEFAULT_PRIORITY });
+ const matched = bestField(
+ [
+ { matchedOn: 'name', text: source.name, weight: 1.2 },
+ { matchedOn: 'description', text: description, weight: 1 },
+ { matchedOn: 'display', text: source.table ?? source.sql ?? null, weight: 0.8 },
+ ],
+ terms,
+ );
+ if (matched) {
+ records.push({
+ rankScore: matched.score,
+ ref: {
+ kind: 'sl_source',
+ id: source.name,
+ connectionId,
+ summary: description,
+ snippet:
+ matched.matchedOn === 'description'
+ ? snippetAround(description, terms)
+ : cap200(`${source.name}: ${[...source.measures.map((measure) => measure.name), ...source.columns.map((column) => column.name)].slice(0, 3).join(', ')}`),
+ matchedOn: matched.matchedOn,
+ },
+ });
+ }
+ }
+
+ if (hasKind(kinds, 'sl_measure')) {
+ for (const measure of source.measures) {
+ const matched = bestField(
+ [
+ { matchedOn: 'name', text: measure.name, weight: 1.2 },
+ { matchedOn: 'description', text: measure.description, weight: 1 },
+ { matchedOn: 'expr', text: measure.expr, weight: 0.9 },
+ ],
+ terms,
+ );
+ if (matched) {
+ records.push({
+ rankScore: matched.score,
+ ref: {
+ kind: 'sl_measure',
+ id: `${source.name}.${measure.name}`,
+ connectionId,
+ summary: measure.description ?? null,
+ snippet: cap200(measure.expr),
+ matchedOn: matched.matchedOn,
+ },
+ });
+ }
+ }
+ }
+
+ if (hasKind(kinds, 'sl_dimension')) {
+ for (const column of source.columns) {
+ const description = resolveDescription(column.descriptions, { priority: DEFAULT_PRIORITY });
+ const matched = bestField(
+ [
+ { matchedOn: 'name', text: column.name, weight: 1.2 },
+ { matchedOn: 'description', text: description, weight: 1 },
+ { matchedOn: 'expr', text: column.expr, weight: 0.9 },
+ ],
+ terms,
+ );
+ if (matched) {
+ records.push({
+ rankScore: matched.score,
+ ref: {
+ kind: 'sl_dimension',
+ id: `${source.name}.${column.name}`,
+ connectionId,
+ summary: description,
+ snippet: cap200(`${column.name} (${column.type})`),
+ matchedOn: matched.matchedOn,
+ },
+ });
+ }
+ }
+ }
+ }
+ }
+ return records.sort((left, right) => right.rankScore - left.rankScore || left.ref.id.localeCompare(right.ref.id));
+}
+
+async function rawCandidates(
+ project: KtxLocalProject,
+ input: KtxDiscoverDataInput,
+ kinds: ReadonlySet,
+ terms: readonly string[],
+): Promise {
+ const records: CandidateRecord[] = [];
+ for (const connectionId of configuredConnectionIds(project, input.connectionId)) {
+ const scan = await latestScan(project, connectionId);
+ if (!scan) {
+ continue;
+ }
+ for (const table of scan.tables) {
+ const ref = tableRef(table);
+ const display = displayForTable(ref);
+ const tableDescription = resolveDescription(table.descriptions, { priority: DEFAULT_PRIORITY }) ?? table.comment;
+ if (hasKind(kinds, 'table')) {
+ const matched = bestField(
+ [
+ { matchedOn: 'name', text: table.name, weight: 1.2 },
+ { matchedOn: 'display', text: display, weight: 1.1 },
+ { matchedOn: 'description', text: tableDescription, weight: 1 },
+ { matchedOn: 'comment', text: table.comment, weight: 1 },
+ ],
+ terms,
+ );
+ if (matched) {
+ records.push({
+ rankScore: matched.score,
+ ref: {
+ kind: 'table',
+ id: display,
+ connectionId,
+ tableRef: ref,
+ summary: tableDescription,
+ snippet:
+ matched.matchedOn === 'description' || matched.matchedOn === 'comment'
+ ? snippetAround(matched.text, terms)
+ : cap200(table.columns.slice(0, 5).map((column) => column.name).join(', ')),
+ matchedOn: matched.matchedOn,
+ },
+ });
+ }
+ }
+
+ if (hasKind(kinds, 'column')) {
+ for (const column of table.columns) {
+ const columnDescription = resolveDescription(column.descriptions, { priority: DEFAULT_PRIORITY }) ?? column.comment;
+ const samples = (column.sampleValues ?? []).map((value) => String(value)).slice(0, 5);
+ const matched = bestField(
+ [
+ { matchedOn: 'name', text: column.name, weight: 1.2 },
+ { matchedOn: 'display', text: `${display}.${column.name}`, weight: 1.1 },
+ { matchedOn: 'description', text: columnDescription, weight: 1 },
+ { matchedOn: 'comment', text: column.comment, weight: 1 },
+ { matchedOn: 'sample_value', text: samples.join(' '), weight: 0.9 },
+ ],
+ terms,
+ );
+ if (matched) {
+ records.push({
+ rankScore: matched.score,
+ ref: {
+ kind: 'column',
+ id: `${display}.${column.name}`,
+ connectionId,
+ tableRef: ref,
+ columnName: column.name,
+ summary: columnDescription,
+ snippet:
+ matched.matchedOn === 'sample_value'
+ ? cap200(`${column.nativeType} - samples: ${samples.join(', ')}`)
+ : matched.matchedOn === 'description' || matched.matchedOn === 'comment'
+ ? snippetAround(matched.text, terms)
+ : cap200(column.nativeType),
+ matchedOn: matched.matchedOn,
+ },
+ });
+ }
+ }
+ }
+ }
+ }
+ return records.sort((left, right) => right.rankScore - left.rankScore || left.ref.id.localeCompare(right.ref.id));
+}
+
+function generator(name: string, candidates: CandidateRecord[], refsByKey: Map>): SearchCandidateGenerator {
+ candidates.forEach((candidate) => refsByKey.set(`${candidate.ref.kind}:${candidate.ref.connectionId ?? ''}:${candidate.ref.id}`, candidate.ref));
+ return {
+ lane: name,
+ weight: 1,
+ async generate() {
+ return {
+ candidates: candidates.map((candidate, index) => ({
+ id: `${candidate.ref.kind}:${candidate.ref.connectionId ?? ''}:${candidate.ref.id}`,
+ rank: index + 1,
+ rawScore: candidate.rankScore,
+ })),
+ };
+ },
+ };
+}
+
+function hydrate(fused: FusedSearchCandidate[], refsByKey: Map>): KtxDiscoverDataRef[] {
+ const maxScore = Math.max(...fused.map((candidate) => candidate.score), 0);
+ return fused
+ .map((candidate) => {
+ const ref = refsByKey.get(candidate.id);
+ if (!ref) {
+ return null;
+ }
+ return {
+ ...ref,
+ score: maxScore > 0 ? Number((candidate.score / maxScore).toFixed(6)) : 0,
+ };
+ })
+ .filter((result): result is KtxDiscoverDataRef => result !== null);
+}
+
+export function createKtxDiscoverDataService(
+ project: KtxLocalProject,
+ options: KtxDiscoverDataServiceOptions = {},
+): { search(input: KtxDiscoverDataInput): Promise } {
+ return {
+ async search(input) {
+ const limit = Math.max(1, Math.min(input.limit ?? 15, 50));
+ const query = input.query.trim();
+ if (!query) {
+ return [];
+ }
+ const kinds = new Set(input.kinds ?? ALL_KINDS);
+ const terms = queryTerms(query);
+ const refsByKey = new Map>();
+ const generators: SearchCandidateGenerator[] = [];
+
+ if (hasKind(kinds, 'wiki')) {
+ generators.push(generator('wiki', await wikiCandidates(project, { ...input, limit }, options, terms), refsByKey));
+ }
+ if (hasKind(kinds, 'sl_source') || hasKind(kinds, 'sl_measure') || hasKind(kinds, 'sl_dimension')) {
+ generators.push(generator('semantic_layer', await slCandidates(project, { ...input, limit }, kinds, terms), refsByKey));
+ }
+ if (hasKind(kinds, 'table') || hasKind(kinds, 'column')) {
+ generators.push(generator('raw_schema', await rawCandidates(project, { ...input, limit }, kinds, terms), refsByKey));
+ }
+ if (generators.length === 0) {
+ return [];
+ }
+
+ const result = await new HybridSearchCore().search({
+ queryText: query,
+ limit,
+ generators,
+ laneWeights: { wiki: 1, semantic_layer: 1, raw_schema: 1 },
+ });
+ return hydrate(result.results, refsByKey);
+ },
+ };
+}
+```
+
+- [ ] **Step 4: Export the service**
+
+In `packages/context/src/search/index.ts`, add:
+
+```typescript
+export { createKtxDiscoverDataService } from './discover.js';
+export type {
+ KtxDiscoverDataInput,
+ KtxDiscoverDataKind,
+ KtxDiscoverDataMatchedOn,
+ KtxDiscoverDataRef,
+ KtxDiscoverDataResponse,
+ KtxDiscoverDataServiceOptions,
+} from './discover.js';
+```
+
+- [ ] **Step 5: Run service tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/search/discover.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 6: Commit the service**
+
+Run:
+
+```bash
+git add packages/context/src/search/discover.ts packages/context/src/search/discover.test.ts packages/context/src/search/index.ts
+git commit -m "feat: add MCP discover data service"
+```
+
+Expected: commit succeeds.
+
+## Task 2: Register `discover_data` In The MCP Tool Surface
+
+**Files:**
+- Modify: `packages/context/src/mcp/types.ts`
+- Modify: `packages/context/src/mcp/context-tools.ts`
+- Modify: `packages/context/src/mcp/server.test.ts`
+- Modify: `packages/context/src/mcp/index.ts`
+
+- [ ] **Step 1: Write failing MCP registration test**
+
+In `packages/context/src/mcp/server.test.ts`, extend the import from `./types.js` to include:
+
+```typescript
+ KtxDiscoverDataMcpPort,
+```
+
+Add this test after the `dictionary_search` registration test:
+
+```typescript
+ it('registers discover_data when the host provides a discover port', async () => {
+ const fake = makeFakeServer();
+ const discover: KtxDiscoverDataMcpPort = {
+ search: vi.fn().mockResolvedValue([
+ {
+ kind: 'table',
+ id: 'public.orders',
+ score: 1,
+ summary: 'Orders table',
+ snippet: 'id, status',
+ matchedOn: 'name',
+ connectionId: 'warehouse',
+ tableRef: { catalog: null, db: 'public', name: 'orders' },
+ },
+ ]),
+ };
+
+ createKtxMcpServer({
+ server: fake.server,
+ userContext: { userId: 'local-user' },
+ contextTools: { discover },
+ });
+
+ expect(fake.tools.map((tool) => tool.name)).toEqual(['discover_data']);
+ await expect(
+ getTool(fake.tools, 'discover_data').handler({
+ query: 'orders',
+ connectionId: 'warehouse',
+ kinds: ['table'],
+ limit: 5,
+ }),
+ ).resolves.toMatchObject({
+ structuredContent: [
+ {
+ kind: 'table',
+ id: 'public.orders',
+ connectionId: 'warehouse',
+ tableRef: { catalog: null, db: 'public', name: 'orders' },
+ },
+ ],
+ });
+ expect(discover.search).toHaveBeenCalledWith({
+ query: 'orders',
+ connectionId: 'warehouse',
+ kinds: ['table'],
+ limit: 5,
+ });
+ });
+```
+
+- [ ] **Step 2: Run the failing MCP registration test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts -t "discover_data"
+```
+
+Expected: FAIL with an import or type error for `KtxDiscoverDataMcpPort`.
+
+- [ ] **Step 3: Add MCP discover port types**
+
+In `packages/context/src/mcp/types.ts`, add this import near the other search/scan imports:
+
+```typescript
+import type { KtxDiscoverDataInput, KtxDiscoverDataResponse } from '../search/index.js';
+```
+
+Add this interface after `KtxDictionarySearchMcpPort`:
+
+```typescript
+export interface KtxDiscoverDataMcpPort {
+ search(input: KtxDiscoverDataInput): Promise;
+}
+```
+
+Add this optional port to `KtxMcpContextPorts`:
+
+```typescript
+ discover?: KtxDiscoverDataMcpPort;
+```
+
+- [ ] **Step 4: Add the Zod schema and registration**
+
+In `packages/context/src/mcp/context-tools.ts`, add this schema after `dictionarySearchSchema`:
+
+```typescript
+const discoverDataKindSchema = z.enum(['wiki', 'sl_source', 'sl_measure', 'sl_dimension', 'table', 'column']);
+
+const discoverDataSchema = z.object({
+ query: z.string().min(1),
+ connectionId: connectionIdSchema.optional(),
+ kinds: z.array(discoverDataKindSchema).optional(),
+ limit: z.number().int().min(1).max(50).default(15).optional(),
+});
+```
+
+Add this registration block after the `dictionary_search` registration block and before `sql_execution`:
+
+```typescript
+ if (ports.discover) {
+ const discover = ports.discover;
+ registerParsedTool(
+ server,
+ 'discover_data',
+ {
+ title: 'Discover Data',
+ description:
+ 'Search across KTX wiki pages, semantic-layer sources/measures/dimensions, and raw warehouse schema refs.',
+ inputSchema: discoverDataSchema.shape,
+ },
+ discoverDataSchema,
+ async (input) => jsonToolResult(await discover.search(input)),
+ );
+ }
+```
+
+- [ ] **Step 5: Export MCP port types**
+
+Check `packages/context/src/mcp/index.ts`. If it already exports all types from `./types.js`, leave it unchanged. If it lists individual type exports, add:
+
+```typescript
+export type { KtxDiscoverDataMcpPort } from './types.js';
+```
+
+- [ ] **Step 6: Run MCP registration tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts -t "discover_data"
+```
+
+Expected: PASS.
+
+- [ ] **Step 7: Commit MCP registration**
+
+Run:
+
+```bash
+git add packages/context/src/mcp/types.ts packages/context/src/mcp/context-tools.ts packages/context/src/mcp/server.test.ts packages/context/src/mcp/index.ts
+git commit -m "feat: expose discover data MCP tool"
+```
+
+Expected: commit succeeds.
+
+## Task 3: Wire Local Project MCP Ports
+
+**Files:**
+- Modify: `packages/context/src/mcp/local-project-ports.ts`
+- Modify: `packages/context/src/mcp/local-project-ports.test.ts`
+
+- [ ] **Step 1: Write failing local-port test**
+
+In `packages/context/src/mcp/local-project-ports.test.ts`, add this test inside the existing `describe('createLocalProjectMcpContextPorts', ...)` block:
+
+```typescript
+ it('exposes local project discover_data across wiki, semantic-layer, and raw schema', async () => {
+ await project.fileStore.writeFile(
+ 'wiki/global/orders-playbook.md',
+ [
+ '---',
+ 'summary: Paid order operations',
+ 'tags: [orders]',
+ 'refs: []',
+ 'sl_refs: []',
+ 'usage_mode: auto',
+ '---',
+ '',
+ 'Paid orders are used for customer activity analysis.',
+ '',
+ ].join('\n'),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed wiki',
+ );
+ await project.fileStore.writeFile(
+ 'semantic-layer/warehouse/orders.yaml',
+ [
+ 'name: orders',
+ 'descriptions:',
+ ' user: Paid order facts',
+ 'table: public.orders',
+ 'grain: [id]',
+ 'columns:',
+ ' - name: status',
+ ' type: string',
+ ' descriptions:',
+ ' user: Payment status',
+ 'measures:',
+ ' - name: order_count',
+ ' expr: count(*)',
+ ' description: Number of paid orders',
+ '',
+ ].join('\n'),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed sl',
+ );
+ await project.fileStore.writeFile(
+ 'raw-sources/warehouse/live-database/sync-1/connection.json',
+ JSON.stringify({ connectionId: 'warehouse', driver: 'postgres', extractedAt: '2026-05-14T09:00:00.000Z' }, null, 2),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed connection',
+ );
+ await project.fileStore.writeFile(
+ 'raw-sources/warehouse/live-database/sync-1/tables/public-orders.json',
+ JSON.stringify(
+ {
+ catalog: null,
+ db: 'public',
+ name: 'orders',
+ kind: 'table',
+ comment: 'Orders table',
+ estimatedRows: 10,
+ columns: [
+ {
+ name: 'status',
+ nativeType: 'text',
+ normalizedType: 'text',
+ dimensionType: 'string',
+ nullable: false,
+ primaryKey: false,
+ comment: 'Order status',
+ sampleValues: ['paid'],
+ },
+ ],
+ foreignKeys: [],
+ },
+ null,
+ 2,
+ ),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed table',
+ );
+ await project.fileStore.writeFile(
+ 'raw-sources/warehouse/live-database/sync-1/scan-report.json',
+ JSON.stringify(
+ {
+ connectionId: 'warehouse',
+ driver: 'postgres',
+ syncId: 'sync-1',
+ runId: 'scan-1',
+ trigger: 'mcp',
+ mode: 'enriched',
+ dryRun: false,
+ artifactPaths: {
+ rawSourcesDir: 'raw-sources/warehouse/live-database/sync-1',
+ reportPath: 'raw-sources/warehouse/live-database/sync-1/scan-report.json',
+ manifestShards: [],
+ enrichmentArtifacts: [],
+ },
+ diffSummary: {
+ tablesAdded: 1,
+ tablesModified: 0,
+ tablesDeleted: 0,
+ tablesUnchanged: 0,
+ columnsAdded: 0,
+ columnsModified: 0,
+ columnsDeleted: 0,
+ },
+ manifestShardsWritten: 0,
+ structuralSyncStats: {
+ tablesCreated: 0,
+ tablesUpdated: 0,
+ tablesDeleted: 0,
+ columnsCreated: 0,
+ columnsUpdated: 0,
+ columnsDeleted: 0,
+ },
+ enrichment: {
+ dataDictionary: 'completed',
+ tableDescriptions: 'completed',
+ columnDescriptions: 'completed',
+ embeddings: 'skipped',
+ deterministicRelationships: 'skipped',
+ llmRelationshipValidation: 'skipped',
+ statisticalValidation: 'skipped',
+ },
+ capabilityGaps: [],
+ warnings: [],
+ relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
+ enrichmentState: { resumedStages: [], completedStages: [], failedStages: [] },
+ createdAt: '2026-05-14T09:00:00.000Z',
+ },
+ null,
+ 2,
+ ),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed scan report',
+ );
+
+ const ports = createLocalProjectMcpContextPorts(project);
+ const results = await ports.discover?.search({ query: 'paid orders', connectionId: 'warehouse', limit: 10 });
+
+ expect(results).toEqual(
+ expect.arrayContaining([
+ expect.objectContaining({ kind: 'wiki', id: 'orders-playbook' }),
+ expect.objectContaining({ kind: 'sl_source', id: 'orders', connectionId: 'warehouse' }),
+ expect.objectContaining({ kind: 'table', id: 'public.orders', connectionId: 'warehouse' }),
+ ]),
+ );
+ });
+```
+
+- [ ] **Step 2: Run the failing local-port test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/local-project-ports.test.ts -t "discover_data"
+```
+
+Expected: FAIL because `ports.discover` is undefined.
+
+- [ ] **Step 3: Wire the local port**
+
+In `packages/context/src/mcp/local-project-ports.ts`, add `createKtxDiscoverDataService` to the search import block:
+
+```typescript
+import { createKtxDiscoverDataService } from '../search/index.js';
+```
+
+Add this port in the `ports` object after `dictionarySearch`:
+
+```typescript
+ discover: {
+ async search(input) {
+ return createKtxDiscoverDataService(project, { userId: 'local', embeddingService }).search(input);
+ },
+ },
+```
+
+- [ ] **Step 4: Run local-port test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/local-project-ports.test.ts -t "discover_data"
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Commit local-port wiring**
+
+Run:
+
+```bash
+git add packages/context/src/mcp/local-project-ports.ts packages/context/src/mcp/local-project-ports.test.ts
+git commit -m "feat: wire local discover data MCP port"
+```
+
+Expected: commit succeeds.
+
+## Task 4: Verify The Discover Slice
+
+**Files:**
+- Verify: `packages/context/src/search/discover.ts`
+- Verify: `packages/context/src/mcp/context-tools.ts`
+- Verify: `packages/context/src/mcp/local-project-ports.ts`
+
+- [ ] **Step 1: Run focused tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/search/discover.test.ts src/mcp/server.test.ts src/mcp/local-project-ports.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 2: Run context type-check**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context run type-check
+```
+
+Expected: PASS.
+
+- [ ] **Step 3: Run context test suite**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context run test
+```
+
+Expected: PASS.
+
+- [ ] **Step 4: Check diff hygiene**
+
+Run:
+
+```bash
+git diff --check
+```
+
+Expected: no output and exit code 0.
+
+- [ ] **Step 5: Document remaining v1 blockers in handoff**
+
+Run:
+
+```bash
+test -e packages/context/src/search/discover.ts; printf 'discover:%s\n' "$?"
+test -e packages/cli/src/commands/mcp-commands.ts; printf 'mcp-commands:%s\n' "$?"
+test -e packages/cli/src/managed-mcp-daemon.ts; printf 'managed-mcp:%s\n' "$?"
+test -e packages/cli/src/skills/research/SKILL.md; printf 'research-skill:%s\n' "$?"
+```
+
+Expected after this plan is implemented:
+
+```text
+discover:0
+mcp-commands:1
+managed-mcp:1
+research-skill:1
+```
+
+- [ ] **Step 6: Commit verification notes if code changed during verification**
+
+If verification required code fixes, run:
+
+```bash
+git status --short
+git add packages/context/src/search/discover.ts packages/context/src/search/discover.test.ts packages/context/src/search/index.ts packages/context/src/mcp/types.ts packages/context/src/mcp/context-tools.ts packages/context/src/mcp/server.test.ts packages/context/src/mcp/local-project-ports.ts packages/context/src/mcp/local-project-ports.test.ts packages/context/src/mcp/index.ts
+git commit -m "test: verify MCP discover data"
+```
+
+Expected: commit succeeds only when there are verification fixes to commit. If `git status --short` is empty, skip this commit.
+
+## Self-Review
+
+- Spec coverage: this plan covers the MCP-shaped `discover_data` input/output contract, kind filtering, optional `connectionId`, RRF fusion across wiki/SL/raw lanes, deterministic summary/snippet provenance, raw `tableRef` and `columnName`, score normalization, local project MCP registration, and freshness by re-reading artifacts on every call.
+- Remaining v1-blocking spec coverage after this slice: HTTP Streamable MCP daemon, `ktx mcp` CLI lifecycle commands, setup-agent MCP config writers/snippet printers, `ktx-research` skill installation, and ingest-side `connectionName` contract convergence.
+- Placeholder scan: no placeholder or deferred-work wording remains in this plan.
+- Type consistency: `KtxDiscoverDataInput`, `KtxDiscoverDataRef`, `KtxDiscoverDataResponse`, and `KtxDiscoverDataMcpPort` are defined before use and match the MCP/local-port registration snippets.
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-entity-details.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-entity-details.md
new file mode 100644
index 00000000..db165c02
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-entity-details.md
@@ -0,0 +1,1175 @@
+# Research Agent MCP Entity Details Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Add the MCP-shaped `entity_details` tool so external research agents can inspect raw table and column metadata from the latest scan snapshot.
+
+**Architecture:** Build a focused scan service over persisted `raw-sources//live-database/` artifacts, using `scan-report.json` as the latest scan identity and `readLocalScanStructuralSnapshot()` as the schema reader. Register `entity_details` as an MCP context tool with pure structured output, then expose it through local project MCP ports.
+
+**Tech Stack:** TypeScript, Vitest, Zod, KTX local file store, KTX scan artifacts, KTX MCP context ports.
+
+---
+
+## Current Audit
+
+Original spec: `docs/superpowers/specs/2026-05-14-research-agent-mcp-tools-design.md`
+
+Implemented v1 slice:
+
+- `docs/superpowers/plans/2026-05-14-research-agent-mcp-sql-execution-foundation.md` is implemented. Evidence in current source:
+ - Python sqlglot validation exists at `python/ktx-daemon/src/ktx_daemon/sql_analysis.py`.
+ - `POST /sql/validate-read-only` exists at `python/ktx-daemon/src/ktx_daemon/app.py`.
+ - `SqlAnalysisPort.validateReadOnly()` exists at `packages/context/src/sql-analysis/ports.ts`.
+ - MCP `sql_execution` registration exists at `packages/context/src/mcp/context-tools.ts`.
+ - Local MCP SQL execution validates through `SqlAnalysisPort` before connector execution in `packages/context/src/mcp/local-project-ports.ts`.
+
+V1-blocking gaps after that slice:
+
+- `entity_details` is not registered on the MCP surface.
+- `discover_data` is not registered on the MCP surface.
+- `dictionary_search` is not registered on the MCP surface.
+- `ktx mcp start|stop|status|logs` and the HTTP Streamable MCP daemon do not exist.
+- `ktx setup-agents` does not install MCP client config or a `ktx-research` skill.
+- Ingest-side warehouse verification still uses `connectionName` contracts in places; the MCP surface must use `connectionId`.
+
+This plan covers only the next dependency-aware v1 blocker: MCP `entity_details`. Later plans still need to cover `dictionary_search`, `discover_data`, the HTTP daemon, and setup-agent/research-skill installation.
+
+## File Structure
+
+Create:
+
+- `packages/context/src/scan/entity-details.ts`
+ - Reads latest live-database scan artifacts for a connection.
+ - Resolves driver display strings or structured table refs.
+ - Returns structured table/column metadata and structured per-entity errors.
+- `packages/context/src/scan/entity-details.test.ts`
+ - Covers latest-scan selection, display-string resolution, structured refs, column filtering, ambiguity, missing scan, and missing columns.
+
+Modify:
+
+- `packages/context/src/scan/index.ts`
+ - Export the new service and types.
+- `packages/context/src/mcp/types.ts`
+ - Add `KtxEntityDetailsMcpPort` and response types to `KtxMcpContextPorts`.
+- `packages/context/src/mcp/context-tools.ts`
+ - Add the `entity_details` input schema and registration.
+- `packages/context/src/mcp/server.test.ts`
+ - Assert the MCP tool registration and structured output.
+- `packages/context/src/mcp/local-project-ports.ts`
+ - Wire the local project port to the scan entity-details service.
+- `packages/context/src/mcp/local-project-ports.test.ts`
+ - Cover local-port `entity_details` success and missing-scan behavior.
+- `packages/context/src/mcp/index.ts`
+ - Export the new MCP port/response types.
+
+## Task 1: Add The Scan Entity Details Service
+
+**Files:**
+- Create: `packages/context/src/scan/entity-details.test.ts`
+- Create: `packages/context/src/scan/entity-details.ts`
+- Modify: `packages/context/src/scan/index.ts`
+
+- [ ] **Step 1: Write failing service tests**
+
+Create `packages/context/src/scan/entity-details.test.ts`:
+
+```typescript
+import { mkdtemp, rm } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+import { initKtxProject, type KtxLocalProject } from '../project/index.js';
+import { createKtxEntityDetailsService } from './entity-details.js';
+import type { KtxConnectionDriver, KtxScanReport, KtxSchemaTable } from './types.js';
+
+describe('createKtxEntityDetailsService', () => {
+ let tempDir: string;
+ let project: KtxLocalProject;
+
+ beforeEach(async () => {
+ tempDir = await mkdtemp(join(tmpdir(), 'ktx-entity-details-service-'));
+ project = await initKtxProject({ projectDir: join(tempDir, 'project'), projectName: 'warehouse' });
+ });
+
+ afterEach(async () => {
+ await rm(tempDir, { recursive: true, force: true });
+ });
+
+ function scanReport(input: {
+ connectionId: string;
+ syncId: string;
+ runId: string;
+ driver?: KtxConnectionDriver;
+ createdAt?: string;
+ }): KtxScanReport {
+ const rawSourcesDir = `raw-sources/${input.connectionId}/live-database/${input.syncId}`;
+ return {
+ connectionId: input.connectionId,
+ driver: input.driver ?? 'postgres',
+ syncId: input.syncId,
+ runId: input.runId,
+ trigger: 'mcp',
+ mode: 'structural',
+ dryRun: false,
+ artifactPaths: {
+ rawSourcesDir,
+ reportPath: `${rawSourcesDir}/scan-report.json`,
+ manifestShards: [],
+ enrichmentArtifacts: [],
+ },
+ diffSummary: { added: 0, modified: 0, deleted: 0, unchanged: 1 },
+ manifestShardsWritten: 0,
+ structuralSyncStats: { tablesWritten: 1, tablesDeleted: 0, foreignKeysWritten: 0 },
+ enrichment: {
+ dataDictionary: 'skipped',
+ tableDescriptions: 'skipped',
+ columnDescriptions: 'skipped',
+ embeddings: 'skipped',
+ deterministicRelationships: 'skipped',
+ llmRelationshipValidation: 'skipped',
+ statisticalValidation: 'skipped',
+ },
+ capabilityGaps: [],
+ warnings: [],
+ relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
+ enrichmentState: { resumedStages: [], completedStages: [], failedStages: [] },
+ createdAt: input.createdAt ?? '2026-05-14T09:00:00.000Z',
+ };
+ }
+
+ function ordersTable(input: { db?: string | null; estimatedRows?: number | null } = {}): KtxSchemaTable {
+ return {
+ catalog: null,
+ db: input.db ?? 'public',
+ name: 'orders',
+ kind: 'table',
+ comment: 'Customer orders',
+ estimatedRows: input.estimatedRows ?? 12,
+ columns: [
+ {
+ name: 'id',
+ nativeType: 'integer',
+ normalizedType: 'integer',
+ dimensionType: 'number',
+ nullable: false,
+ primaryKey: true,
+ comment: 'Order id',
+ },
+ {
+ name: 'status',
+ nativeType: 'text',
+ normalizedType: 'text',
+ dimensionType: 'string',
+ nullable: false,
+ primaryKey: false,
+ comment: 'Order status',
+ },
+ ],
+ foreignKeys: [
+ {
+ fromColumn: 'customer_id',
+ toCatalog: null,
+ toDb: 'public',
+ toTable: 'customers',
+ toColumn: 'id',
+ constraintName: 'orders_customer_id_fkey',
+ },
+ ],
+ };
+ }
+
+ async function seedScan(input: {
+ connectionId?: string;
+ syncId: string;
+ runId: string;
+ driver?: KtxConnectionDriver;
+ extractedAt?: string;
+ tables?: KtxSchemaTable[];
+ }): Promise {
+ const connectionId = input.connectionId ?? 'warehouse';
+ const report = scanReport({
+ connectionId,
+ syncId: input.syncId,
+ runId: input.runId,
+ driver: input.driver,
+ createdAt: input.extractedAt,
+ });
+ const root = report.artifactPaths.rawSourcesDir;
+ await project.fileStore.writeFile(
+ `${root}/connection.json`,
+ JSON.stringify(
+ {
+ connectionId,
+ driver: report.driver,
+ extractedAt: input.extractedAt ?? report.createdAt,
+ scope: { schemas: ['public'] },
+ },
+ null,
+ 2,
+ ),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed connection',
+ );
+ for (const table of input.tables ?? [ordersTable()]) {
+ await project.fileStore.writeFile(
+ `${root}/tables/${table.db ?? 'default'}-${table.name}.json`,
+ JSON.stringify(table, null, 2),
+ 'ktx',
+ 'ktx@example.com',
+ `seed ${table.name}`,
+ );
+ }
+ await project.fileStore.writeFile(
+ `${root}/scan-report.json`,
+ JSON.stringify(report, null, 2),
+ 'ktx',
+ 'ktx@example.com',
+ 'seed scan report',
+ );
+ }
+
+ it('returns the latest scan snapshot table details for a display string', async () => {
+ await seedScan({ syncId: 'sync-1', runId: 'scan-old', extractedAt: '2026-05-14T08:00:00.000Z' });
+ await seedScan({
+ syncId: 'sync-2',
+ runId: 'scan-new',
+ extractedAt: '2026-05-14T09:00:00.000Z',
+ tables: [ordersTable({ estimatedRows: 99 })],
+ });
+ const service = createKtxEntityDetailsService(project);
+
+ const result = await service.read({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders' }],
+ });
+
+ expect(result.results).toHaveLength(1);
+ expect(result.results[0]).toMatchObject({
+ ok: true,
+ connectionId: 'warehouse',
+ display: 'public.orders',
+ estimatedRows: 99,
+ snapshot: {
+ syncId: 'sync-2',
+ scanRunId: 'scan-new',
+ extractedAt: '2026-05-14T09:00:00.000Z',
+ },
+ columns: [
+ { name: 'id', nativeType: 'integer', primaryKey: true },
+ { name: 'status', nativeType: 'text', nullable: false },
+ ],
+ });
+ });
+
+ it('filters requested columns while keeping full-table foreign keys', async () => {
+ await seedScan({ syncId: 'sync-1', runId: 'scan-1' });
+ const service = createKtxEntityDetailsService(project);
+
+ const result = await service.read({
+ connectionId: 'warehouse',
+ entities: [{ table: { catalog: null, db: 'public', name: 'orders' }, columns: ['status'] }],
+ });
+
+ expect(result.results[0]).toMatchObject({
+ ok: true,
+ columns: [{ name: 'status' }],
+ foreignKeys: [
+ {
+ fromColumn: 'customer_id',
+ toDb: 'public',
+ toTable: 'customers',
+ toColumn: 'id',
+ },
+ ],
+ });
+ });
+
+ it('returns a structured missing-scan error', async () => {
+ const service = createKtxEntityDetailsService(project);
+
+ const result = await service.read({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders' }],
+ });
+
+ expect(result.results).toEqual([
+ {
+ ok: false,
+ connectionId: 'warehouse',
+ table: 'public.orders',
+ error: {
+ code: 'scan_missing',
+ message: 'No live-database scan found for connection "warehouse"; run `ktx ingest warehouse` or `ktx scan warehouse`.',
+ },
+ },
+ ]);
+ });
+
+ it('reports ambiguous bare table names across schemas', async () => {
+ await seedScan({
+ syncId: 'sync-1',
+ runId: 'scan-1',
+ tables: [ordersTable({ db: 'public' }), ordersTable({ db: 'archive' })],
+ });
+ const service = createKtxEntityDetailsService(project);
+
+ const result = await service.read({
+ connectionId: 'warehouse',
+ entities: [{ table: 'orders' }],
+ });
+
+ expect(result.results[0]).toMatchObject({
+ ok: false,
+ error: {
+ code: 'ambiguous_table',
+ candidates: [
+ { tableRef: { catalog: null, db: 'archive', name: 'orders' }, display: 'archive.orders' },
+ { tableRef: { catalog: null, db: 'public', name: 'orders' }, display: 'public.orders' },
+ ],
+ },
+ });
+ });
+
+ it('reports missing requested columns with available column candidates', async () => {
+ await seedScan({ syncId: 'sync-1', runId: 'scan-1' });
+ const service = createKtxEntityDetailsService(project);
+
+ const result = await service.read({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders', columns: ['status', 'plan_tier'] }],
+ });
+
+ expect(result.results[0]).toMatchObject({
+ ok: false,
+ error: {
+ code: 'column_not_found',
+ message: 'Column(s) not found on public.orders: plan_tier',
+ candidates: ['id', 'status'],
+ },
+ });
+ });
+});
+```
+
+- [ ] **Step 2: Run failing service tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/scan/entity-details.test.ts
+```
+
+Expected: FAIL because `packages/context/src/scan/entity-details.ts` does not exist.
+
+- [ ] **Step 3: Implement the service**
+
+Create `packages/context/src/scan/entity-details.ts`:
+
+```typescript
+import type { KtxLocalProject } from '../project/index.js';
+import { readLocalScanStructuralSnapshot } from './local-structural-artifacts.js';
+import type {
+ KtxConnectionDriver,
+ KtxScanReport,
+ KtxSchemaColumn,
+ KtxSchemaSnapshot,
+ KtxSchemaTable,
+ KtxTableRef,
+} from './types.js';
+
+export type KtxEntityDetailsTableInput = string | KtxTableRef;
+
+export interface KtxEntityDetailsInput {
+ connectionId: string;
+ entities: Array<{
+ table: KtxEntityDetailsTableInput;
+ columns?: string[];
+ }>;
+}
+
+export interface KtxEntityDetailsSnapshotInfo {
+ syncId: string;
+ extractedAt: string;
+ scanRunId: string | null;
+}
+
+export interface KtxEntityDetailsColumn {
+ name: string;
+ nativeType: string;
+ normalizedType: string;
+ dimensionType: KtxSchemaColumn['dimensionType'];
+ nullable: boolean;
+ primaryKey: boolean;
+ comment: string | null;
+}
+
+export interface KtxEntityDetailsRecord {
+ ok: true;
+ connectionId: string;
+ tableRef: KtxTableRef;
+ display: string;
+ kind: KtxSchemaTable['kind'];
+ comment: string | null;
+ estimatedRows: number | null;
+ columns: KtxEntityDetailsColumn[];
+ foreignKeys: KtxSchemaTable['foreignKeys'];
+ snapshot: KtxEntityDetailsSnapshotInfo;
+}
+
+export type KtxEntityDetailsErrorCode = 'scan_missing' | 'table_not_found' | 'ambiguous_table' | 'column_not_found';
+
+export interface KtxEntityDetailsErrorResult {
+ ok: false;
+ connectionId: string;
+ table: KtxEntityDetailsTableInput;
+ snapshot?: KtxEntityDetailsSnapshotInfo;
+ error: {
+ code: KtxEntityDetailsErrorCode;
+ message: string;
+ candidates?: Array<{ tableRef: KtxTableRef; display: string }> | string[];
+ };
+}
+
+export interface KtxEntityDetailsResponse {
+ results: Array;
+}
+
+interface LatestScan {
+ report: KtxScanReport;
+ snapshot: KtxSchemaSnapshot;
+}
+
+interface ResolveResult {
+ table: KtxSchemaTable | null;
+ error?: Omit & { message: string };
+}
+
+function normalize(value: string | null | undefined): string {
+ return (value ?? '').toLowerCase();
+}
+
+function refsEqual(left: KtxTableRef, right: KtxTableRef): boolean {
+ return (
+ normalize(left.catalog) === normalize(right.catalog) &&
+ normalize(left.db) === normalize(right.db) &&
+ normalize(left.name) === normalize(right.name)
+ );
+}
+
+function cleanIdentifierPart(part: string): string {
+ return part.trim().replace(/^["'`\[]|["'`\]]$/g, '');
+}
+
+function splitDisplay(display: string): string[] {
+ return display
+ .trim()
+ .split('.')
+ .map(cleanIdentifierPart)
+ .filter(Boolean);
+}
+
+function displayForTable(driver: KtxConnectionDriver, table: KtxTableRef): string {
+ if (driver === 'sqlite') {
+ return table.name;
+ }
+ return [table.catalog, table.db, table.name].filter((part): part is string => Boolean(part)).join('.');
+}
+
+function tableRef(table: KtxSchemaTable): KtxTableRef {
+ return { catalog: table.catalog, db: table.db, name: table.name };
+}
+
+function candidateList(driver: KtxConnectionDriver, tables: KtxSchemaTable[]): Array<{ tableRef: KtxTableRef; display: string }> {
+ return tables
+ .map((table) => ({
+ tableRef: tableRef(table),
+ display: displayForTable(driver, table),
+ }))
+ .sort((left, right) => left.display.localeCompare(right.display));
+}
+
+function parseDisplayRef(driver: KtxConnectionDriver, display: string): KtxTableRef | null {
+ const parts = splitDisplay(display);
+ if (driver === 'sqlite') {
+ return parts.length === 1 ? { catalog: null, db: null, name: parts[0]! } : null;
+ }
+ if (driver === 'bigquery' || driver === 'snowflake' || driver === 'sqlserver') {
+ return parts.length === 3 ? { catalog: parts[0]!, db: parts[1]!, name: parts[2]! } : null;
+ }
+ if (parts.length === 2) {
+ return { catalog: null, db: parts[0]!, name: parts[1]! };
+ }
+ if (parts.length === 3) {
+ return { catalog: parts[0]!, db: parts[1]!, name: parts[2]! };
+ }
+ return null;
+}
+
+function resolveTable(snapshot: KtxSchemaSnapshot, input: KtxEntityDetailsTableInput): ResolveResult {
+ if (typeof input !== 'string') {
+ const table = snapshot.tables.find((candidate) => refsEqual(candidate, input)) ?? null;
+ return table
+ ? { table }
+ : {
+ table: null,
+ error: {
+ code: 'table_not_found',
+ message: `Table not found in latest scan: ${displayForTable(snapshot.driver, input)}`,
+ candidates: candidateList(snapshot.driver, snapshot.tables),
+ },
+ };
+ }
+
+ const parsed = parseDisplayRef(snapshot.driver, input);
+ if (parsed) {
+ const table = snapshot.tables.find((candidate) => refsEqual(candidate, parsed)) ?? null;
+ return table
+ ? { table }
+ : {
+ table: null,
+ error: {
+ code: 'table_not_found',
+ message: `Table not found in latest scan: ${input}`,
+ candidates: candidateList(snapshot.driver, snapshot.tables),
+ },
+ };
+ }
+
+ const byName = snapshot.tables.filter((candidate) => normalize(candidate.name) === normalize(input));
+ if (byName.length === 1) {
+ return { table: byName[0]! };
+ }
+ if (byName.length > 1) {
+ return {
+ table: null,
+ error: {
+ code: 'ambiguous_table',
+ message: `Table name "${input}" is ambiguous across schemas/catalogs; pass a structured table ref.`,
+ candidates: candidateList(snapshot.driver, byName),
+ },
+ };
+ }
+ return {
+ table: null,
+ error: {
+ code: 'table_not_found',
+ message: `Table not found in latest scan: ${input}`,
+ candidates: candidateList(snapshot.driver, snapshot.tables),
+ },
+ };
+}
+
+function toColumn(column: KtxSchemaColumn): KtxEntityDetailsColumn {
+ return {
+ name: column.name,
+ nativeType: column.nativeType,
+ normalizedType: column.normalizedType,
+ dimensionType: column.dimensionType,
+ nullable: column.nullable,
+ primaryKey: column.primaryKey,
+ comment: column.comment,
+ };
+}
+
+function snapshotInfo(report: KtxScanReport, snapshot: KtxSchemaSnapshot): KtxEntityDetailsSnapshotInfo {
+ return {
+ syncId: report.syncId,
+ extractedAt: snapshot.extractedAt,
+ scanRunId: report.runId ?? null,
+ };
+}
+
+async function readJson(project: KtxLocalProject, path: string): Promise {
+ return JSON.parse((await project.fileStore.readFile(path)).content) as T;
+}
+
+async function latestScan(project: KtxLocalProject, connectionId: string): Promise {
+ const root = `raw-sources/${connectionId}/live-database`;
+ let listed;
+ try {
+ listed = await project.fileStore.listFiles(root);
+ } catch {
+ return null;
+ }
+ const reportPath = listed.files.filter((path) => path.endsWith('/scan-report.json')).sort().at(-1);
+ if (!reportPath) {
+ return null;
+ }
+ const report = await readJson(project, reportPath);
+ const rawSourcesDir = report.artifactPaths.rawSourcesDir ?? reportPath.slice(0, -'/scan-report.json'.length);
+ const snapshot = await readLocalScanStructuralSnapshot({
+ project,
+ connectionId,
+ driver: report.driver,
+ rawSourcesDir,
+ extractedAtFallback: report.createdAt,
+ });
+ return { report, snapshot };
+}
+
+export function createKtxEntityDetailsService(project: KtxLocalProject) {
+ return {
+ async read(input: KtxEntityDetailsInput): Promise {
+ const scan = await latestScan(project, input.connectionId);
+ if (!scan) {
+ return {
+ results: input.entities.map((entity) => ({
+ ok: false,
+ connectionId: input.connectionId,
+ table: entity.table,
+ error: {
+ code: 'scan_missing',
+ message: `No live-database scan found for connection "${input.connectionId}"; run \`ktx ingest ${input.connectionId}\` or \`ktx scan ${input.connectionId}\`.`,
+ },
+ })),
+ };
+ }
+
+ const info = snapshotInfo(scan.report, scan.snapshot);
+ const results: KtxEntityDetailsResponse['results'] = [];
+ for (const entity of input.entities) {
+ const resolved = resolveTable(scan.snapshot, entity.table);
+ if (!resolved.table) {
+ results.push({
+ ok: false,
+ connectionId: input.connectionId,
+ table: entity.table,
+ snapshot: info,
+ error: resolved.error!,
+ });
+ continue;
+ }
+
+ const requested = new Set((entity.columns ?? []).map((column) => normalize(column)));
+ const columns = requested.size
+ ? resolved.table.columns.filter((column) => requested.has(normalize(column.name)))
+ : resolved.table.columns;
+ if (requested.size && columns.length !== requested.size) {
+ const found = new Set(columns.map((column) => normalize(column.name)));
+ const missing = [...requested].filter((column) => !found.has(column));
+ results.push({
+ ok: false,
+ connectionId: input.connectionId,
+ table: entity.table,
+ snapshot: info,
+ error: {
+ code: 'column_not_found',
+ message: `Column(s) not found on ${displayForTable(scan.snapshot.driver, resolved.table)}: ${missing.join(', ')}`,
+ candidates: resolved.table.columns.map((column) => column.name),
+ },
+ });
+ continue;
+ }
+
+ results.push({
+ ok: true,
+ connectionId: input.connectionId,
+ tableRef: tableRef(resolved.table),
+ display: displayForTable(scan.snapshot.driver, resolved.table),
+ kind: resolved.table.kind,
+ comment: resolved.table.comment,
+ estimatedRows: resolved.table.estimatedRows,
+ columns: columns.map(toColumn),
+ foreignKeys: resolved.table.foreignKeys,
+ snapshot: info,
+ });
+ }
+ return { results };
+ },
+ };
+}
+```
+
+In `packages/context/src/scan/index.ts`, add these exports near the other scan-service exports:
+
+```typescript
+export type {
+ KtxEntityDetailsColumn,
+ KtxEntityDetailsErrorCode,
+ KtxEntityDetailsErrorResult,
+ KtxEntityDetailsInput,
+ KtxEntityDetailsRecord,
+ KtxEntityDetailsResponse,
+ KtxEntityDetailsSnapshotInfo,
+ KtxEntityDetailsTableInput,
+} from './entity-details.js';
+export { createKtxEntityDetailsService } from './entity-details.js';
+```
+
+- [ ] **Step 4: Run service tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/scan/entity-details.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Commit the scan service**
+
+Run:
+
+```bash
+git add packages/context/src/scan/entity-details.ts packages/context/src/scan/entity-details.test.ts packages/context/src/scan/index.ts
+git commit -m "feat(context): add scan-backed entity details service"
+```
+
+## Task 2: Register The MCP `entity_details` Tool
+
+**Files:**
+- Modify: `packages/context/src/mcp/types.ts`
+- Modify: `packages/context/src/mcp/context-tools.ts`
+- Modify: `packages/context/src/mcp/server.test.ts`
+- Modify: `packages/context/src/mcp/index.ts`
+
+- [ ] **Step 1: Add MCP port types**
+
+In `packages/context/src/mcp/types.ts`, add this import near the other type imports:
+
+```typescript
+import type { KtxEntityDetailsInput, KtxEntityDetailsResponse } from '../scan/entity-details.js';
+```
+
+Add this interface immediately before `KtxSqlExecutionResponse`:
+
+```typescript
+export interface KtxEntityDetailsMcpPort {
+ read(input: KtxEntityDetailsInput): Promise;
+}
+```
+
+Add this optional port to `KtxMcpContextPorts`:
+
+```typescript
+ entityDetails?: KtxEntityDetailsMcpPort;
+```
+
+- [ ] **Step 2: Write failing MCP registration test**
+
+In `packages/context/src/mcp/server.test.ts`, update the `./types.js` import to include `KtxEntityDetailsMcpPort`.
+
+Add this test after the `sql_execution` registration test:
+
+```typescript
+ it('registers entity_details when the host provides an entity-details port', async () => {
+ const fake = makeFakeServer();
+ const entityDetails: KtxEntityDetailsMcpPort = {
+ read: vi.fn().mockResolvedValue({
+ results: [
+ {
+ ok: true,
+ connectionId: 'warehouse',
+ tableRef: { catalog: null, db: 'public', name: 'orders' },
+ display: 'public.orders',
+ kind: 'table',
+ comment: 'Customer orders',
+ estimatedRows: 12,
+ columns: [
+ {
+ name: 'id',
+ nativeType: 'integer',
+ normalizedType: 'integer',
+ dimensionType: 'number',
+ nullable: false,
+ primaryKey: true,
+ comment: null,
+ },
+ ],
+ foreignKeys: [],
+ snapshot: {
+ syncId: 'sync-1',
+ extractedAt: '2026-05-14T09:00:00.000Z',
+ scanRunId: 'scan-1',
+ },
+ },
+ ],
+ }),
+ };
+
+ createKtxMcpServer({
+ server: fake.server,
+ userContext: { userId: 'local-user' },
+ contextTools: { entityDetails },
+ });
+
+ expect(fake.tools.map((tool) => tool.name)).toEqual(['entity_details']);
+ await expect(
+ getTool(fake.tools, 'entity_details').handler({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders', columns: ['id'] }],
+ }),
+ ).resolves.toMatchObject({
+ structuredContent: {
+ results: [
+ {
+ ok: true,
+ connectionId: 'warehouse',
+ display: 'public.orders',
+ columns: [{ name: 'id' }],
+ },
+ ],
+ },
+ });
+ expect(entityDetails.read).toHaveBeenCalledWith({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders', columns: ['id'] }],
+ });
+ });
+```
+
+- [ ] **Step 3: Run failing MCP registration test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts -t entity_details
+```
+
+Expected: FAIL because `entity_details` is not registered.
+
+- [ ] **Step 4: Add schema and registration**
+
+In `packages/context/src/mcp/context-tools.ts`, add this schema after `scanArtifactReadSchema` and before `sqlExecutionSchema`:
+
+```typescript
+const entityDetailsTableRefSchema = z.object({
+ catalog: z.string().nullable(),
+ db: z.string().nullable(),
+ name: z.string().min(1),
+});
+
+const entityDetailsSchema = z.object({
+ connectionId: connectionIdSchema,
+ entities: z
+ .array(
+ z.object({
+ table: z.union([z.string().min(1), entityDetailsTableRefSchema]),
+ columns: z.array(z.string().min(1)).optional(),
+ }),
+ )
+ .min(1)
+ .max(20),
+});
+```
+
+Add this registration block in `registerKtxContextTools`, after the semantic-layer block and before the `sqlExecution` block:
+
+```typescript
+ if (ports.entityDetails) {
+ const entityDetails = ports.entityDetails;
+ registerParsedTool(
+ server,
+ 'entity_details',
+ {
+ title: 'Entity Details',
+ description:
+ 'Read raw table and column metadata from the latest KTX live-database scan snapshot.',
+ inputSchema: entityDetailsSchema.shape,
+ },
+ entityDetailsSchema,
+ async (input) => jsonToolResult(await entityDetails.read(input)),
+ );
+ }
+```
+
+In `packages/context/src/mcp/index.ts`, add `KtxEntityDetailsMcpPort` to the exported type list.
+
+- [ ] **Step 5: Run MCP registration test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts -t entity_details
+```
+
+Expected: PASS.
+
+- [ ] **Step 6: Commit MCP registration**
+
+Run:
+
+```bash
+git add packages/context/src/mcp/types.ts packages/context/src/mcp/context-tools.ts packages/context/src/mcp/server.test.ts packages/context/src/mcp/index.ts
+git commit -m "feat(context): register MCP entity details tool"
+```
+
+## Task 3: Wire Local Project MCP Ports
+
+**Files:**
+- Modify: `packages/context/src/mcp/local-project-ports.ts`
+- Modify: `packages/context/src/mcp/local-project-ports.test.ts`
+
+- [ ] **Step 1: Write failing local-port tests**
+
+In `packages/context/src/mcp/local-project-ports.test.ts`, add this helper after `testConnector`:
+
+```typescript
+ async function seedScanReport(projectDir: string, syncId = 'sync-1'): Promise {
+ const root = `raw-sources/warehouse/live-database/${syncId}`;
+ await mkdir(join(projectDir, root, 'tables'), { recursive: true });
+ await writeFile(
+ join(projectDir, root, 'connection.json'),
+ JSON.stringify(
+ {
+ connectionId: 'warehouse',
+ driver: 'postgres',
+ extractedAt: '2026-05-14T09:00:00.000Z',
+ scope: { schemas: ['public'] },
+ },
+ null,
+ 2,
+ ),
+ 'utf-8',
+ );
+ await writeFile(
+ join(projectDir, root, 'tables', 'orders.json'),
+ JSON.stringify(
+ {
+ catalog: null,
+ db: 'public',
+ name: 'orders',
+ kind: 'table',
+ comment: 'Customer orders',
+ estimatedRows: 12,
+ columns: [
+ {
+ name: 'id',
+ nativeType: 'integer',
+ normalizedType: 'integer',
+ dimensionType: 'number',
+ nullable: false,
+ primaryKey: true,
+ comment: null,
+ },
+ ],
+ foreignKeys: [],
+ },
+ null,
+ 2,
+ ),
+ 'utf-8',
+ );
+ await writeFile(
+ join(projectDir, root, 'scan-report.json'),
+ JSON.stringify(
+ {
+ connectionId: 'warehouse',
+ driver: 'postgres',
+ syncId,
+ runId: 'scan-1',
+ trigger: 'mcp',
+ mode: 'structural',
+ dryRun: false,
+ artifactPaths: {
+ rawSourcesDir: root,
+ reportPath: `${root}/scan-report.json`,
+ manifestShards: [],
+ enrichmentArtifacts: [],
+ },
+ diffSummary: { added: 0, modified: 0, deleted: 0, unchanged: 1 },
+ manifestShardsWritten: 0,
+ structuralSyncStats: { tablesWritten: 1, tablesDeleted: 0, foreignKeysWritten: 0 },
+ enrichment: {
+ dataDictionary: 'skipped',
+ tableDescriptions: 'skipped',
+ columnDescriptions: 'skipped',
+ embeddings: 'skipped',
+ deterministicRelationships: 'skipped',
+ llmRelationshipValidation: 'skipped',
+ statisticalValidation: 'skipped',
+ },
+ capabilityGaps: [],
+ warnings: [],
+ relationships: { accepted: 0, review: 0, rejected: 0, skipped: 0 },
+ enrichmentState: { resumedStages: [], completedStages: [], failedStages: [] },
+ createdAt: '2026-05-14T09:00:00.000Z',
+ },
+ null,
+ 2,
+ ),
+ 'utf-8',
+ );
+ }
+```
+
+Add these tests after the MCP SQL tests:
+
+```typescript
+ it('exposes local scan entity details through MCP ports', async () => {
+ const project = await initKtxProject({ projectDir: tempDir, projectName: 'warehouse' });
+ project.config.connections.warehouse = {
+ driver: 'postgres',
+ url: 'env:DATABASE_URL',
+ };
+ await seedScanReport(project.projectDir);
+ const ports = createLocalProjectMcpContextPorts(project);
+
+ await expect(
+ ports.entityDetails?.read({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders', columns: ['id'] }],
+ }),
+ ).resolves.toMatchObject({
+ results: [
+ {
+ ok: true,
+ connectionId: 'warehouse',
+ display: 'public.orders',
+ columns: [{ name: 'id', nativeType: 'integer' }],
+ snapshot: { syncId: 'sync-1', scanRunId: 'scan-1' },
+ },
+ ],
+ });
+ });
+
+ it('returns a structured local entity-details error when no scan exists', async () => {
+ const project = await initKtxProject({ projectDir: tempDir, projectName: 'warehouse' });
+ project.config.connections.warehouse = {
+ driver: 'postgres',
+ url: 'env:DATABASE_URL',
+ };
+ const ports = createLocalProjectMcpContextPorts(project);
+
+ await expect(
+ ports.entityDetails?.read({
+ connectionId: 'warehouse',
+ entities: [{ table: 'public.orders' }],
+ }),
+ ).resolves.toMatchObject({
+ results: [
+ {
+ ok: false,
+ connectionId: 'warehouse',
+ error: { code: 'scan_missing' },
+ },
+ ],
+ });
+ });
+```
+
+- [ ] **Step 2: Run failing local-port tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/local-project-ports.test.ts -t "entity details"
+```
+
+Expected: FAIL because `ports.entityDetails` is undefined.
+
+- [ ] **Step 3: Wire the service into local ports**
+
+In `packages/context/src/mcp/local-project-ports.ts`, update the scan import block to include `createKtxEntityDetailsService`:
+
+```typescript
+ createKtxEntityDetailsService,
+```
+
+In the initial `ports` object returned by `createLocalProjectMcpContextPorts`, add this sibling after `semanticLayer` and before the closing `};`:
+
+```typescript
+ entityDetails: {
+ async read(input) {
+ return createKtxEntityDetailsService(project).read(input);
+ },
+ },
+```
+
+- [ ] **Step 4: Run local-port tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/mcp/local-project-ports.test.ts -t "entity details"
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Commit local-port wiring**
+
+Run:
+
+```bash
+git add packages/context/src/mcp/local-project-ports.ts packages/context/src/mcp/local-project-ports.test.ts
+git commit -m "feat(context): expose local MCP entity details"
+```
+
+## Task 4: Verification
+
+**Files:**
+- Verify: all files changed in Tasks 1-3
+
+- [ ] **Step 1: Run focused context tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/scan/entity-details.test.ts src/mcp/server.test.ts src/mcp/local-project-ports.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 2: Run context type-check**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context run type-check
+```
+
+Expected: PASS.
+
+- [ ] **Step 3: Run dead-code check for new exports**
+
+Run:
+
+```bash
+pnpm run dead-code
+```
+
+Expected: PASS. If Knip reports unrelated pre-existing findings, record the exact unrelated findings and do not broaden this entity-details slice.
+
+- [ ] **Step 4: Confirm remaining v1 blockers still need later plans**
+
+Run:
+
+```bash
+test -e packages/context/src/sl/dictionary-search.ts; printf 'dictionary-search:%s\n' "$?"
+test -e packages/context/src/search/discover.ts; printf 'discover:%s\n' "$?"
+test -e packages/cli/src/commands/mcp-commands.ts; printf 'mcp-commands:%s\n' "$?"
+test -e packages/cli/src/skills/research/SKILL.md; printf 'research-skill:%s\n' "$?"
+```
+
+Expected:
+
+```text
+dictionary-search:1
+discover:1
+mcp-commands:1
+research-skill:1
+```
+
+These markers mean this plan landed `entity_details` only and did not claim the remaining research-agent v1 work.
+
+- [ ] **Step 5: Commit verification-only doc changes if any**
+
+Run:
+
+```bash
+git status --short
+```
+
+Expected: no uncommitted source changes after the task commits. If verification updates this plan document, commit only the plan document with:
+
+```bash
+git add docs/superpowers/plans/2026-05-14-research-agent-mcp-entity-details.md
+git commit -m "docs: record research MCP entity details plan"
+```
+
+## Self-Review
+
+- Spec coverage for this slice: covers MCP `entity_details`, latest scan freshness by reading `scan-report.json` on each call, structured table refs, driver display strings, column filtering, FK preservation, snapshot freshness, and structured errors.
+- Remaining spec coverage after this slice: `dictionary_search`, `discover_data`, `ktx mcp` HTTP daemon, setup-agent MCP config, and `ktx-research` skill are still v1-blocking and need later plans.
+- Type consistency: `KtxEntityDetailsInput` is reused by the scan service, MCP port, schema parser, and local project port.
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-http-daemon.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-http-daemon.md
new file mode 100644
index 00000000..00645dec
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-http-daemon.md
@@ -0,0 +1,1561 @@
+# Research Agent MCP HTTP Daemon Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Add the HTTP-only `ktx mcp start|stop|status|logs` daemon so external MCP clients can reach the already implemented KTX research tools.
+
+**Architecture:** Keep the MCP tool contracts in `@ktx/context` and add CLI-owned HTTP hosting/lifecycle code. The public `ktx mcp start` command either runs a foreground HTTP server or spawns a hidden foreground child command, persists daemon state to `.ktx/mcp.json`, and writes logs to `.ktx/logs/mcp.log`; the HTTP server uses stateful `StreamableHTTPServerTransport` sessions with explicit host/origin/token checks.
+
+**Tech Stack:** TypeScript, Node 22 `node:http`, Commander, `@modelcontextprotocol/sdk@1.29.0`, Zod, Vitest, KTX managed Python daemon helpers.
+
+---
+
+## Audit Summary
+
+Original spec: `docs/superpowers/specs/2026-05-14-research-agent-mcp-tools-design.md`
+
+Implemented v1 slices confirmed in current source:
+
+- MCP `sql_execution` is implemented and parser-gated: `python/ktx-daemon/src/ktx_daemon/sql_analysis.py` validates SQL with sqlglot, `python/ktx-daemon/src/ktx_daemon/app.py` exposes `/sql/validate-read-only`, `packages/context/src/mcp/context-tools.ts` registers `sql_execution`, and `packages/context/src/mcp/local-project-ports.ts` only exposes it when both SQL analysis and local scan connector creation are available.
+- MCP `entity_details` is implemented: `packages/context/src/scan/entity-details.ts`, `KtxEntityDetailsMcpPort`, context-tool registration, and local project wiring all exist.
+- MCP `dictionary_search` is implemented: `packages/context/src/sl/dictionary-search.ts`, `KtxDictionarySearchMcpPort`, context-tool registration, and local project wiring all exist.
+- MCP `discover_data` is implemented: `packages/context/src/search/discover.ts`, `KtxDiscoverDataMcpPort`, context-tool registration, and local project wiring all exist.
+
+Remaining v1-blocking gaps:
+
+- `ktx mcp start|stop|status|logs` and the HTTP Streamable MCP daemon are missing. There is no `packages/cli/src/commands/mcp-commands.ts`, no `packages/cli/src/managed-mcp-daemon.ts`, and `packages/cli/src/cli-program.ts` does not register an `mcp` subtree.
+- `ktx setup-agents` does not install MCP client config entries or the `ktx-research` skill. `plannedKtxAgentFiles()` still installs only the existing `ktx` skill/rules.
+- Ingest-side warehouse verification tools still use `connectionName`, not the spec-required `connectionId`, and `WarehouseCatalogService` still exposes `connectionName` in its service contract.
+
+Non-blocking gaps:
+
+- TLS, audit logging, rate limiting, per-tool authorization, OS-level autostart, stdio MCP transport, and multi-project switching remain explicitly out of scope for v1.
+
+This plan covers only the next dependency-aware blocker: the HTTP Streamable MCP daemon and `ktx mcp` lifecycle command subtree. After this plan lands, the remaining v1 plans are setup-agent/research-skill installation and ingest warehouse-verification contract convergence.
+
+## Documentation Notes
+
+- Context7 was checked for current MCP TypeScript SDK Streamable HTTP examples.
+- The local `@modelcontextprotocol/sdk@1.29.0` package metadata was checked with `pnpm view`; its exported import path supports `@modelcontextprotocol/sdk/server/streamableHttp.js`.
+- The 1.29.0 tarball types show `StreamableHTTPServerTransport` accepts `sessionIdGenerator`, `onsessioninitialized`, `onsessionclosed`, `allowedHosts`, `allowedOrigins`, and `enableDnsRebindingProtection`, and exposes `handleRequest(req, res, parsedBody?)`.
+
+## File Structure
+
+- Create `packages/cli/src/mcp-http-server.ts`
+ - Owns the foreground HTTP server.
+ - Validates Host, Origin, and bearer token policy before handing requests to the MCP SDK transport.
+ - Hosts `/health` and stateful `/mcp` `POST`/`GET`/`DELETE`.
+ - Builds a fresh `McpServer` per session with `createDefaultKtxMcpServer()`.
+- Create `packages/cli/src/mcp-http-server.test.ts`
+ - Unit tests for host normalization, origin validation, token enforcement, `/health`, initialize session creation, unknown-session rejection, and DELETE cleanup.
+- Create `packages/cli/src/managed-mcp-daemon.ts`
+ - Owns `.ktx/mcp.json`, `.ktx/logs/mcp.log`, background spawning, status probes, stop, and log reading.
+- Create `packages/cli/src/managed-mcp-daemon.test.ts`
+ - Unit tests for state paths, start spawn arguments, token redaction from state/argv, status, stale state, stop, and log tailing.
+- Create `packages/cli/src/commands/mcp-commands.ts`
+ - Registers public `start|stop|status|logs` and hidden `serve-internal`.
+- Create `packages/cli/src/commands/mcp-commands.test.ts`
+ - Command-level tests for option parsing, non-loopback token requirement, state output, and hidden server command wiring.
+- Modify `packages/cli/src/cli-program.ts`
+ - Add `mcp` to project-aware root commands.
+ - Register the MCP command subtree.
+- Modify `packages/cli/package.json`
+ - Add `@modelcontextprotocol/sdk` as a direct dependency of `@ktx/cli`, because the CLI package will import the Streamable HTTP transport directly.
+
+## Task 1: Add MCP HTTP Security Helper Tests
+
+**Files:**
+- Create: `packages/cli/src/mcp-http-server.test.ts`
+- Create later: `packages/cli/src/mcp-http-server.ts`
+
+- [ ] **Step 1: Write the failing security helper tests**
+
+Create `packages/cli/src/mcp-http-server.test.ts` with:
+
+```typescript
+import { describe, expect, it } from 'vitest';
+import {
+ buildMcpSecurityConfig,
+ isMcpRequestAuthorized,
+ normalizeHostHeader,
+} from './mcp-http-server.js';
+
+describe('normalizeHostHeader', () => {
+ it('normalizes host headers before allow-list comparison', () => {
+ expect(normalizeHostHeader('LOCALHOST:7878')).toBe('localhost');
+ expect(normalizeHostHeader('127.0.0.1:7878')).toBe('127.0.0.1');
+ expect(normalizeHostHeader('[::1]:7878')).toBe('::1');
+ expect(normalizeHostHeader(' Example.COM ')).toBe('example.com');
+ });
+});
+
+describe('buildMcpSecurityConfig', () => {
+ it('allows loopback hosts without a token', () => {
+ const config = buildMcpSecurityConfig({
+ host: '127.0.0.1',
+ port: 7878,
+ token: undefined,
+ allowedHosts: [],
+ allowedOrigins: [],
+ });
+
+ expect(config.token).toBeUndefined();
+ expect(config.allowedHosts).toEqual(['localhost', '127.0.0.1', '::1']);
+ });
+
+ it('requires a token for non-loopback binding', () => {
+ expect(() =>
+ buildMcpSecurityConfig({
+ host: '0.0.0.0',
+ port: 7878,
+ token: undefined,
+ allowedHosts: [],
+ allowedOrigins: [],
+ }),
+ ).toThrow('Binding KTX MCP to 0.0.0.0 requires --token or KTX_MCP_TOKEN');
+ });
+
+ it('validates allowed origins as full origins', () => {
+ expect(() =>
+ buildMcpSecurityConfig({
+ host: '127.0.0.1',
+ port: 7878,
+ token: undefined,
+ allowedHosts: [],
+ allowedOrigins: ['localhost:7878'],
+ }),
+ ).toThrow('Allowed origin must be a full origin URL');
+ });
+});
+
+describe('isMcpRequestAuthorized', () => {
+ const config = buildMcpSecurityConfig({
+ host: '0.0.0.0',
+ port: 7878,
+ token: 'secret-token',
+ allowedHosts: ['mcp.example.test'],
+ allowedOrigins: ['https://mcp.example.test'],
+ });
+
+ it('accepts a valid host, origin, and bearer token', () => {
+ expect(
+ isMcpRequestAuthorized(
+ {
+ path: '/mcp',
+ headers: {
+ host: 'mcp.example.test:7878',
+ origin: 'https://mcp.example.test',
+ authorization: 'Bearer secret-token',
+ },
+ },
+ config,
+ ),
+ ).toEqual({ ok: true });
+ });
+
+ it('rejects bad host headers before MCP handling', () => {
+ expect(
+ isMcpRequestAuthorized(
+ { path: '/health', headers: { host: 'evil.example.test' } },
+ config,
+ ),
+ ).toEqual({ ok: false, status: 403, message: 'Host header is not allowed for KTX MCP.' });
+ });
+
+ it('rejects browser origins unless explicitly allowed', () => {
+ expect(
+ isMcpRequestAuthorized(
+ {
+ path: '/health',
+ headers: { host: 'mcp.example.test', origin: 'https://evil.example.test' },
+ },
+ config,
+ ),
+ ).toEqual({ ok: false, status: 403, message: 'Origin header is not allowed for KTX MCP.' });
+ });
+
+ it('requires bearer auth on /mcp when token auth is enabled', () => {
+ expect(
+ isMcpRequestAuthorized(
+ { path: '/mcp', headers: { host: 'mcp.example.test', authorization: 'Bearer wrong' } },
+ config,
+ ),
+ ).toEqual({ ok: false, status: 401, message: 'Missing or invalid KTX MCP bearer token.' });
+ });
+
+ it('does not require bearer auth on /health', () => {
+ expect(isMcpRequestAuthorized({ path: '/health', headers: { host: 'mcp.example.test' } }, config)).toEqual({
+ ok: true,
+ });
+ });
+});
+```
+
+- [ ] **Step 2: Run the new tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/mcp-http-server.test.ts
+```
+
+Expected: FAIL because `./mcp-http-server.js` does not exist.
+
+- [ ] **Step 3: Implement the security helpers**
+
+Create `packages/cli/src/mcp-http-server.ts` with the helper surface first:
+
+```typescript
+import type { IncomingHttpHeaders } from 'node:http';
+
+const DEFAULT_ALLOWED_HOSTS = ['localhost', '127.0.0.1', '::1'] as const;
+
+export interface McpSecurityConfigInput {
+ host: string;
+ port: number;
+ token?: string;
+ allowedHosts: string[];
+ allowedOrigins: string[];
+}
+
+export interface McpSecurityConfig {
+ host: string;
+ port: number;
+ token?: string;
+ allowedHosts: string[];
+ allowedOrigins: string[];
+}
+
+export type McpAuthorizationResult =
+ | { ok: true }
+ | { ok: false; status: 401 | 403; message: string };
+
+function isLoopbackHost(host: string): boolean {
+ const normalized = normalizeHostHeader(host);
+ return normalized === 'localhost' || normalized === '127.0.0.1' || normalized === '::1';
+}
+
+export function normalizeHostHeader(value: string): string {
+ const trimmed = value.trim().toLowerCase();
+ if (trimmed.startsWith('[')) {
+ const close = trimmed.indexOf(']');
+ return close >= 0 ? trimmed.slice(1, close) : trimmed.replace(/^\[/, '');
+ }
+ const colon = trimmed.lastIndexOf(':');
+ if (colon > -1 && trimmed.indexOf(':') === colon) {
+ return trimmed.slice(0, colon);
+ }
+ return trimmed;
+}
+
+function fullOrigin(value: string): string {
+ let parsed: URL;
+ try {
+ parsed = new URL(value);
+ } catch {
+ throw new Error(`Allowed origin must be a full origin URL: ${value}`);
+ }
+ if (!parsed.protocol || !parsed.host || parsed.pathname !== '/' || parsed.search || parsed.hash) {
+ throw new Error(`Allowed origin must be a full origin URL: ${value}`);
+ }
+ return parsed.origin;
+}
+
+export function buildMcpSecurityConfig(input: McpSecurityConfigInput): McpSecurityConfig {
+ if (!isLoopbackHost(input.host) && !input.token) {
+ throw new Error(`Binding KTX MCP to ${input.host} requires --token or KTX_MCP_TOKEN`);
+ }
+ const allowedHostSet = new Set(DEFAULT_ALLOWED_HOSTS);
+ if (!isLoopbackHost(input.host)) {
+ allowedHostSet.add(normalizeHostHeader(input.host));
+ }
+ for (const host of input.allowedHosts) {
+ allowedHostSet.add(normalizeHostHeader(host));
+ }
+ return {
+ host: input.host,
+ port: input.port,
+ ...(input.token ? { token: input.token } : {}),
+ allowedHosts: [...allowedHostSet],
+ allowedOrigins: input.allowedOrigins.map(fullOrigin),
+ };
+}
+
+function headerValue(headers: IncomingHttpHeaders | Record, name: string): string | undefined {
+ const value = headers[name.toLowerCase()];
+ return Array.isArray(value) ? value[0] : value;
+}
+
+export function isMcpRequestAuthorized(
+ request: { path: string; headers: IncomingHttpHeaders | Record },
+ config: McpSecurityConfig,
+): McpAuthorizationResult {
+ const host = headerValue(request.headers, 'host');
+ if (!host || !config.allowedHosts.includes(normalizeHostHeader(host))) {
+ return { ok: false, status: 403, message: 'Host header is not allowed for KTX MCP.' };
+ }
+ const origin = headerValue(request.headers, 'origin');
+ if (origin && !config.allowedOrigins.includes(origin)) {
+ return { ok: false, status: 403, message: 'Origin header is not allowed for KTX MCP.' };
+ }
+ if (request.path === '/mcp' && config.token) {
+ const auth = headerValue(request.headers, 'authorization');
+ if (auth !== `Bearer ${config.token}`) {
+ return { ok: false, status: 401, message: 'Missing or invalid KTX MCP bearer token.' };
+ }
+ }
+ return { ok: true };
+}
+```
+
+- [ ] **Step 4: Run the security helper tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/mcp-http-server.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add packages/cli/src/mcp-http-server.ts packages/cli/src/mcp-http-server.test.ts
+git commit -m "feat(cli): add mcp http security helpers"
+```
+
+## Task 2: Add Foreground MCP HTTP Server
+
+**Files:**
+- Modify: `packages/cli/src/mcp-http-server.ts`
+- Modify: `packages/cli/src/mcp-http-server.test.ts`
+- Modify: `packages/cli/package.json`
+
+- [ ] **Step 1: Add the direct SDK dependency to the CLI package**
+
+In `packages/cli/package.json`, add this dependency inside `"dependencies"`:
+
+```json
+"@modelcontextprotocol/sdk": "^1.29.0"
+```
+
+Keep the dependency list alphabetized by package name.
+
+- [ ] **Step 2: Write failing HTTP server behavior tests**
+
+Append these imports to `packages/cli/src/mcp-http-server.test.ts`:
+
+```typescript
+import { request } from 'node:http';
+import { AddressInfo } from 'node:net';
+import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
+import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js';
+import { runKtxMcpHttpServer } from './mcp-http-server.js';
+```
+
+Append these helpers and tests:
+
+```typescript
+function postJson(port: number, path: string, body: unknown, headers: Record = {}) {
+ return new Promise<{ status: number; headers: Record; body: string }>(
+ (resolve, reject) => {
+ const payload = JSON.stringify(body);
+ const req = request(
+ {
+ host: '127.0.0.1',
+ port,
+ path,
+ method: 'POST',
+ headers: {
+ host: `127.0.0.1:${port}`,
+ 'content-type': 'application/json',
+ 'content-length': Buffer.byteLength(payload),
+ ...headers,
+ },
+ },
+ (res) => {
+ const chunks: Buffer[] = [];
+ res.on('data', (chunk: Buffer) => chunks.push(chunk));
+ res.on('end', () =>
+ resolve({
+ status: res.statusCode ?? 0,
+ headers: res.headers,
+ body: Buffer.concat(chunks).toString('utf8'),
+ }),
+ );
+ },
+ );
+ req.on('error', reject);
+ req.end(payload);
+ },
+ );
+}
+
+function get(port: number, path: string, headers: Record = {}) {
+ return new Promise<{ status: number; headers: Record; body: string }>(
+ (resolve, reject) => {
+ const req = request(
+ {
+ host: '127.0.0.1',
+ port,
+ path,
+ method: 'GET',
+ headers: { host: `127.0.0.1:${port}`, ...headers },
+ },
+ (res) => {
+ const chunks: Buffer[] = [];
+ res.on('data', (chunk: Buffer) => chunks.push(chunk));
+ res.on('end', () =>
+ resolve({
+ status: res.statusCode ?? 0,
+ headers: res.headers,
+ body: Buffer.concat(chunks).toString('utf8'),
+ }),
+ );
+ },
+ );
+ req.on('error', reject);
+ req.end();
+ },
+ );
+}
+
+function createTestMcpServer() {
+ return () => {
+ const server = new McpServer({ name: 'ktx-test', version: '0.0.0-test' });
+ server.registerTool('ping', { inputSchema: {} }, async () => ({
+ content: [{ type: 'text', text: 'pong' }],
+ }));
+ return server;
+ };
+}
+
+describe('runKtxMcpHttpServer', () => {
+ it('serves /health with project metadata', async () => {
+ const handle = await runKtxMcpHttpServer({
+ projectDir: '/tmp/ktx-project',
+ host: '127.0.0.1',
+ port: 0,
+ allowedHosts: [],
+ allowedOrigins: [],
+ createMcpServer: createTestMcpServer(),
+ });
+ try {
+ const port = (handle.server.address() as AddressInfo).port;
+ const response = await get(port, '/health');
+ expect(response.status).toBe(200);
+ expect(JSON.parse(response.body)).toEqual({
+ status: 'ok',
+ projectDir: '/tmp/ktx-project',
+ port,
+ });
+ } finally {
+ await handle.close();
+ }
+ });
+
+ it('allocates a stateful MCP session on initialize', async () => {
+ const handle = await runKtxMcpHttpServer({
+ projectDir: '/tmp/ktx-project',
+ host: '127.0.0.1',
+ port: 0,
+ allowedHosts: [],
+ allowedOrigins: [],
+ createMcpServer: createTestMcpServer(),
+ });
+ try {
+ const port = (handle.server.address() as AddressInfo).port;
+ const response = await postJson(port, '/mcp', {
+ jsonrpc: '2.0',
+ id: 1,
+ method: 'initialize',
+ params: {
+ protocolVersion: '2025-06-18',
+ capabilities: {},
+ clientInfo: { name: 'vitest', version: '0.0.0' },
+ },
+ });
+
+ expect(response.status).toBe(200);
+ expect(response.headers['mcp-session-id']).toBeTruthy();
+ } finally {
+ await handle.close();
+ }
+ });
+
+ it('rejects unknown session ids with 404', async () => {
+ const handle = await runKtxMcpHttpServer({
+ projectDir: '/tmp/ktx-project',
+ host: '127.0.0.1',
+ port: 0,
+ allowedHosts: [],
+ allowedOrigins: [],
+ createMcpServer: createTestMcpServer(),
+ });
+ try {
+ const port = (handle.server.address() as AddressInfo).port;
+ const response = await postJson(
+ port,
+ '/mcp',
+ { jsonrpc: '2.0', id: 2, method: 'tools/list', params: {} },
+ { 'mcp-session-id': 'missing-session' },
+ );
+
+ expect(response.status).toBe(404);
+ expect(response.body).toContain('Unknown MCP session');
+ } finally {
+ await handle.close();
+ }
+ });
+});
+```
+
+- [ ] **Step 3: Run the HTTP server tests to verify the new cases fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/mcp-http-server.test.ts
+```
+
+Expected: FAIL because `runKtxMcpHttpServer` is not implemented.
+
+- [ ] **Step 4: Implement the foreground server**
+
+Extend `packages/cli/src/mcp-http-server.ts` with:
+
+```typescript
+import { randomUUID } from 'node:crypto';
+import { createServer, type IncomingMessage, type Server, type ServerResponse } from 'node:http';
+import { createDefaultKtxMcpServer } from '@ktx/context/mcp';
+import { createLocalProjectMcpContextPorts } from '@ktx/context/mcp';
+import { createLocalProjectMemoryCapture } from '@ktx/context/memory';
+import { loadKtxProject, type KtxLocalProject } from '@ktx/context/project';
+import { isInitializeRequest } from '@modelcontextprotocol/sdk/types.js';
+import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js';
+import type { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
+import type { KtxCliIo } from './cli-runtime.js';
+import { createKtxCliIngestQueryExecutor } from './ingest-query-executor.js';
+import { createKtxCliScanConnector } from './local-scan-connectors.js';
+import { createManagedPythonSemanticLayerComputePort } from './managed-python-command.js';
+import { createManagedDaemonSqlAnalysisPort } from './managed-python-http.js';
+
+export interface KtxMcpHttpServerHandle {
+ server: Server;
+ close(): Promise;
+}
+
+export interface RunKtxMcpHttpServerOptions extends McpSecurityConfigInput {
+ projectDir: string;
+ cliVersion?: string;
+ io?: KtxCliIo;
+ createMcpServer?: () => McpServer;
+ loadProject?: typeof loadKtxProject;
+}
+
+function writeJson(res: ServerResponse, status: number, body: object): void {
+ const payload = `${JSON.stringify(body)}\n`;
+ res.writeHead(status, {
+ 'content-type': 'application/json',
+ 'content-length': Buffer.byteLength(payload),
+ });
+ res.end(payload);
+}
+
+function writeText(res: ServerResponse, status: number, body: string): void {
+ res.writeHead(status, { 'content-type': 'text/plain; charset=utf-8' });
+ res.end(body);
+}
+
+function requestPath(req: IncomingMessage): string {
+ const url = new URL(req.url ?? '/', 'http://127.0.0.1');
+ return url.pathname;
+}
+
+async function readJsonBody(req: IncomingMessage): Promise {
+ const chunks: Buffer[] = [];
+ for await (const chunk of req) {
+ chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
+ }
+ const raw = Buffer.concat(chunks).toString('utf8');
+ return raw.trim().length === 0 ? undefined : (JSON.parse(raw) as unknown);
+}
+
+async function defaultMcpServerFactory(input: {
+ project: KtxLocalProject;
+ projectDir: string;
+ cliVersion: string;
+ io?: KtxCliIo;
+}): Promise<() => McpServer> {
+ const queryExecutor = createKtxCliIngestQueryExecutor(input.project);
+ const semanticLayerCompute = await createManagedPythonSemanticLayerComputePort({
+ cliVersion: input.cliVersion,
+ installPolicy: 'auto',
+ io: input.io ?? {
+ stdout: { write() {} },
+ stderr: { write() {} },
+ },
+ });
+ const sqlAnalysis = createManagedDaemonSqlAnalysisPort({
+ cliVersion: input.cliVersion,
+ projectDir: input.projectDir,
+ installPolicy: 'auto',
+ io: input.io ?? {
+ stdout: { write() {} },
+ stderr: { write() {} },
+ },
+ });
+ const contextTools = createLocalProjectMcpContextPorts(input.project, {
+ semanticLayerCompute,
+ queryExecutor,
+ sqlAnalysis,
+ localScan: {
+ createConnector: async (connectionId) => createKtxCliScanConnector(input.project, connectionId),
+ },
+ localIngest: {
+ semanticLayerCompute,
+ queryExecutor,
+ },
+ });
+ let memoryCapture;
+ try {
+ memoryCapture = createLocalProjectMemoryCapture(input.project, { semanticLayerCompute, queryExecutor });
+ } catch (error) {
+ input.io?.stderr.write(`KTX MCP memory_capture disabled: ${error instanceof Error ? error.message : String(error)}\n`);
+ }
+
+ return () =>
+ createDefaultKtxMcpServer({
+ name: 'ktx',
+ version: input.cliVersion,
+ userContext: { userId: 'local' },
+ contextTools,
+ memoryCapture,
+ });
+}
+
+export async function runKtxMcpHttpServer(options: RunKtxMcpHttpServerOptions): Promise {
+ const config = buildMcpSecurityConfig(options);
+ const project =
+ options.createMcpServer === undefined
+ ? await (options.loadProject ?? loadKtxProject)({ projectDir: options.projectDir })
+ : undefined;
+ const createMcpServer =
+ options.createMcpServer ??
+ (await defaultMcpServerFactory({
+ project: project!,
+ projectDir: options.projectDir,
+ cliVersion: options.cliVersion ?? '0.0.0-private',
+ io: options.io,
+ }));
+ const sessions = new Map();
+
+ async function newTransport(): Promise {
+ let transport: StreamableHTTPServerTransport;
+ transport = new StreamableHTTPServerTransport({
+ sessionIdGenerator: () => randomUUID(),
+ onsessioninitialized: (sessionId) => {
+ sessions.set(sessionId, transport);
+ },
+ onsessionclosed: (sessionId) => {
+ sessions.delete(sessionId);
+ },
+ allowedHosts: config.allowedHosts,
+ allowedOrigins: config.allowedOrigins,
+ enableDnsRebindingProtection: true,
+ });
+ transport.onclose = () => {
+ if (transport.sessionId) {
+ sessions.delete(transport.sessionId);
+ }
+ };
+ await createMcpServer().connect(transport);
+ return transport;
+ }
+
+ const server = createServer(async (req, res) => {
+ const path = requestPath(req);
+ const auth = isMcpRequestAuthorized({ path, headers: req.headers }, config);
+ if (!auth.ok) {
+ writeText(res, auth.status, auth.message);
+ return;
+ }
+
+ if (path === '/health' && req.method === 'GET') {
+ const address = server.address();
+ const port = typeof address === 'object' && address ? address.port : config.port;
+ writeJson(res, 200, { status: 'ok', projectDir: options.projectDir, port });
+ return;
+ }
+
+ if (path !== '/mcp' || !['POST', 'GET', 'DELETE'].includes(req.method ?? '')) {
+ writeText(res, 404, 'Not found');
+ return;
+ }
+
+ const sessionId = req.headers['mcp-session-id'];
+ const normalizedSessionId = Array.isArray(sessionId) ? sessionId[0] : sessionId;
+
+ if (req.method === 'POST') {
+ let body: unknown;
+ try {
+ body = await readJsonBody(req);
+ } catch (error) {
+ writeText(res, 400, `Invalid JSON body: ${error instanceof Error ? error.message : String(error)}`);
+ return;
+ }
+ const existing = normalizedSessionId ? sessions.get(normalizedSessionId) : undefined;
+ if (existing) {
+ await existing.handleRequest(req, res, body);
+ return;
+ }
+ if (normalizedSessionId) {
+ writeText(res, 404, `Unknown MCP session: ${normalizedSessionId}`);
+ return;
+ }
+ if (!isInitializeRequest(body)) {
+ writeText(res, 400, 'MCP initialize request is required before session traffic.');
+ return;
+ }
+ await (await newTransport()).handleRequest(req, res, body);
+ return;
+ }
+
+ if (!normalizedSessionId || !sessions.has(normalizedSessionId)) {
+ writeText(res, 404, normalizedSessionId ? `Unknown MCP session: ${normalizedSessionId}` : 'Missing MCP session id.');
+ return;
+ }
+ await sessions.get(normalizedSessionId)!.handleRequest(req, res);
+ });
+
+ await new Promise((resolve, reject) => {
+ server.once('error', reject);
+ server.listen(config.port, config.host, () => {
+ server.off('error', reject);
+ resolve();
+ });
+ });
+
+ return {
+ server,
+ async close() {
+ for (const transport of sessions.values()) {
+ await transport.close();
+ }
+ await new Promise((resolve, reject) => {
+ server.close((error) => (error ? reject(error) : resolve()));
+ });
+ },
+ };
+}
+```
+
+- [ ] **Step 5: Run the HTTP server tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/mcp-http-server.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add packages/cli/package.json packages/cli/src/mcp-http-server.ts packages/cli/src/mcp-http-server.test.ts
+git commit -m "feat(cli): host mcp over streamable http"
+```
+
+## Task 3: Add Managed MCP Daemon Lifecycle
+
+**Files:**
+- Create: `packages/cli/src/managed-mcp-daemon.ts`
+- Create: `packages/cli/src/managed-mcp-daemon.test.ts`
+
+- [ ] **Step 1: Write failing daemon lifecycle tests**
+
+Create `packages/cli/src/managed-mcp-daemon.test.ts` with:
+
+```typescript
+import { mkdir, mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import {
+ mcpDaemonLayout,
+ readKtxMcpDaemonStatus,
+ startKtxMcpDaemon,
+ stopKtxMcpDaemon,
+ type KtxMcpDaemonChild,
+ type KtxMcpDaemonState,
+} from './managed-mcp-daemon.js';
+
+function child(pid = 4242): KtxMcpDaemonChild {
+ return { pid, unref: vi.fn() };
+}
+
+function state(projectDir: string, overrides: Partial = {}): KtxMcpDaemonState {
+ return {
+ schemaVersion: 1,
+ pid: 4242,
+ host: '127.0.0.1',
+ port: 7878,
+ tokenAuth: false,
+ projectDir,
+ startedAt: '2026-05-14T00:00:00.000Z',
+ logPath: join(projectDir, '.ktx/logs/mcp.log'),
+ ...overrides,
+ };
+}
+
+describe('managed MCP daemon lifecycle', () => {
+ let tempDir: string;
+ let projectDir: string;
+
+ beforeEach(async () => {
+ tempDir = await mkdtemp(join(tmpdir(), 'ktx-mcp-daemon-'));
+ projectDir = join(tempDir, 'project');
+ await mkdir(projectDir, { recursive: true });
+ });
+
+ afterEach(async () => {
+ await rm(tempDir, { recursive: true, force: true });
+ });
+
+ it('uses the spec state and log paths', () => {
+ expect(mcpDaemonLayout(projectDir)).toEqual({
+ statePath: join(projectDir, '.ktx/mcp.json'),
+ logPath: join(projectDir, '.ktx/logs/mcp.log'),
+ });
+ });
+
+ it('starts a detached child and writes state without the token value', async () => {
+ const spawnDaemon = vi.fn(() => child(5555));
+ await startKtxMcpDaemon({
+ projectDir,
+ cliVersion: '0.0.0-test',
+ host: '0.0.0.0',
+ port: 7879,
+ token: 'secret-token',
+ allowedHosts: ['mcp.example.test'],
+ allowedOrigins: ['https://mcp.example.test'],
+ binPath: '/repo/packages/cli/dist/bin.js',
+ spawnDaemon,
+ processAlive: vi.fn(() => false),
+ portAvailable: vi.fn(async () => true),
+ now: () => new Date('2026-05-14T00:00:00.000Z'),
+ });
+
+ expect(spawnDaemon).toHaveBeenCalledWith(
+ process.execPath,
+ [
+ '/repo/packages/cli/dist/bin.js',
+ '--project-dir',
+ projectDir,
+ 'mcp',
+ 'serve-internal',
+ '--host',
+ '0.0.0.0',
+ '--port',
+ '7879',
+ '--allowed-host',
+ 'mcp.example.test',
+ '--allowed-origin',
+ 'https://mcp.example.test',
+ ],
+ expect.objectContaining({
+ detached: true,
+ env: expect.objectContaining({ KTX_MCP_TOKEN: 'secret-token' }),
+ }),
+ );
+ expect(JSON.stringify(JSON.parse(await readFile(join(projectDir, '.ktx/mcp.json'), 'utf8')))).not.toContain(
+ 'secret-token',
+ );
+ });
+
+ it('reports running when the process is alive and health passes', async () => {
+ await mkdir(join(projectDir, '.ktx'), { recursive: true });
+ await writeFile(join(projectDir, '.ktx/mcp.json'), `${JSON.stringify(state(projectDir), null, 2)}\n`);
+
+ const status = await readKtxMcpDaemonStatus({
+ projectDir,
+ processAlive: vi.fn(() => true),
+ fetchHealth: vi.fn(async () => ({ ok: true, body: { status: 'ok', projectDir, port: 7878 } })),
+ });
+
+ expect(status.kind).toBe('running');
+ expect(status.url).toBe('http://127.0.0.1:7878/mcp');
+ });
+
+ it('stops a recorded daemon and removes state', async () => {
+ await mkdir(join(projectDir, '.ktx'), { recursive: true });
+ await writeFile(join(projectDir, '.ktx/mcp.json'), `${JSON.stringify(state(projectDir), null, 2)}\n`);
+ const alive = new Set([4242]);
+ const killProcess = vi.fn((pid: number) => alive.delete(pid));
+
+ await expect(
+ stopKtxMcpDaemon({
+ projectDir,
+ processAlive: vi.fn((pid) => alive.has(pid)),
+ killProcess,
+ stopGraceMs: 1,
+ pollIntervalMs: 1,
+ }),
+ ).resolves.toEqual({ status: 'stopped' });
+
+ expect(killProcess).toHaveBeenCalledWith(4242, 'SIGTERM');
+ await expect(readFile(join(projectDir, '.ktx/mcp.json'), 'utf8')).rejects.toThrow();
+ });
+});
+```
+
+- [ ] **Step 2: Run the lifecycle tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/managed-mcp-daemon.test.ts
+```
+
+Expected: FAIL because `./managed-mcp-daemon.js` does not exist.
+
+- [ ] **Step 3: Implement lifecycle state, start, status, and stop**
+
+Create `packages/cli/src/managed-mcp-daemon.ts` with:
+
+```typescript
+import { spawn } from 'node:child_process';
+import { mkdir, open, readFile, rm, writeFile } from 'node:fs/promises';
+import { createServer } from 'node:net';
+import { dirname, join } from 'node:path';
+import { setTimeout as delay } from 'node:timers/promises';
+import { z } from 'zod';
+
+export interface KtxMcpDaemonState {
+ schemaVersion: 1;
+ pid: number;
+ host: string;
+ port: number;
+ tokenAuth: boolean;
+ projectDir: string;
+ startedAt: string;
+ logPath: string;
+}
+
+export interface KtxMcpDaemonChild {
+ pid?: number;
+ unref(): void;
+}
+
+export type KtxMcpDaemonStatus =
+ | { kind: 'stopped'; detail: string }
+ | { kind: 'running'; detail: string; state: KtxMcpDaemonState; url: string }
+ | { kind: 'stale'; detail: string; state?: KtxMcpDaemonState };
+
+const stateSchema = z.object({
+ schemaVersion: z.literal(1),
+ pid: z.number().int().positive(),
+ host: z.string().min(1),
+ port: z.number().int().min(1).max(65535),
+ tokenAuth: z.boolean(),
+ projectDir: z.string().min(1),
+ startedAt: z.string().min(1),
+ logPath: z.string().min(1),
+});
+
+export function mcpDaemonLayout(projectDir: string): { statePath: string; logPath: string } {
+ return {
+ statePath: join(projectDir, '.ktx/mcp.json'),
+ logPath: join(projectDir, '.ktx/logs/mcp.log'),
+ };
+}
+
+function defaultProcessAlive(pid: number): boolean {
+ try {
+ process.kill(pid, 0);
+ return true;
+ } catch {
+ return false;
+ }
+}
+
+function defaultKillProcess(pid: number, signal: NodeJS.Signals): void {
+ try {
+ process.kill(pid, signal);
+ } catch (error) {
+ if ((error as { code?: unknown }).code !== 'ESRCH') {
+ throw error;
+ }
+ }
+}
+
+async function readState(projectDir: string): Promise {
+ try {
+ return stateSchema.parse(JSON.parse(await readFile(mcpDaemonLayout(projectDir).statePath, 'utf8')) as unknown);
+ } catch (error) {
+ if ((error as { code?: unknown }).code === 'ENOENT') {
+ return undefined;
+ }
+ throw error;
+ }
+}
+
+async function writeState(projectDir: string, state: KtxMcpDaemonState): Promise {
+ const { statePath } = mcpDaemonLayout(projectDir);
+ await mkdir(dirname(statePath), { recursive: true });
+ await writeFile(statePath, `${JSON.stringify(state, null, 2)}\n`, 'utf8');
+}
+
+async function defaultPortAvailable(host: string, port: number): Promise {
+ return await new Promise((resolve) => {
+ const server = createServer();
+ server.once('error', () => resolve(false));
+ server.listen(port, host, () => server.close(() => resolve(true)));
+ });
+}
+
+function defaultSpawnDaemon(
+ command: string,
+ args: string[],
+ options: { detached: boolean; stdio: ['ignore', number, number]; env: NodeJS.ProcessEnv },
+): KtxMcpDaemonChild {
+ return spawn(command, args, options);
+}
+
+async function defaultFetchHealth(state: KtxMcpDaemonState): Promise<{ ok: boolean; body: unknown; detail?: string }> {
+ try {
+ const response = await fetch(`http://${state.host}:${state.port}/health`, {
+ headers: { host: `${state.host}:${state.port}` },
+ });
+ const body = await response.json();
+ return { ok: response.ok, body, detail: response.ok ? undefined : `HTTP ${response.status}` };
+ } catch (error) {
+ return { ok: false, body: null, detail: error instanceof Error ? error.message : String(error) };
+ }
+}
+
+export async function startKtxMcpDaemon(options: {
+ projectDir: string;
+ cliVersion: string;
+ host: string;
+ port: number;
+ token?: string;
+ allowedHosts: string[];
+ allowedOrigins: string[];
+ binPath: string;
+ processAlive?: (pid: number) => boolean;
+ portAvailable?: (host: string, port: number) => Promise;
+ spawnDaemon?: typeof defaultSpawnDaemon;
+ now?: () => Date;
+}): Promise<{ status: 'started'; state: KtxMcpDaemonState; url: string }> {
+ const existing = await readState(options.projectDir).catch(() => undefined);
+ const processAlive = options.processAlive ?? defaultProcessAlive;
+ if (existing && processAlive(existing.pid)) {
+ throw new Error(`KTX MCP daemon is already recorded at http://${existing.host}:${existing.port}/mcp`);
+ }
+ const portAvailable = options.portAvailable ?? defaultPortAvailable;
+ if (!(await portAvailable(options.host, options.port))) {
+ throw new Error(`Port ${options.port} is already in use. Choose another port with --port .`);
+ }
+
+ const { logPath } = mcpDaemonLayout(options.projectDir);
+ await mkdir(dirname(logPath), { recursive: true });
+ const log = await open(logPath, 'a');
+ const args = [
+ options.binPath,
+ '--project-dir',
+ options.projectDir,
+ 'mcp',
+ 'serve-internal',
+ '--host',
+ options.host,
+ '--port',
+ String(options.port),
+ ...options.allowedHosts.flatMap((host) => ['--allowed-host', host]),
+ ...options.allowedOrigins.flatMap((origin) => ['--allowed-origin', origin]),
+ ];
+ const child = (options.spawnDaemon ?? defaultSpawnDaemon)(process.execPath, args, {
+ detached: true,
+ stdio: ['ignore', log.fd, log.fd],
+ env: {
+ ...process.env,
+ KTX_CLI_VERSION: options.cliVersion,
+ ...(options.token ? { KTX_MCP_TOKEN: options.token } : {}),
+ },
+ });
+ if (!child.pid) {
+ throw new Error('Failed to start KTX MCP daemon: child process pid was not available.');
+ }
+ child.unref();
+ const state: KtxMcpDaemonState = {
+ schemaVersion: 1,
+ pid: child.pid,
+ host: options.host,
+ port: options.port,
+ tokenAuth: Boolean(options.token),
+ projectDir: options.projectDir,
+ startedAt: (options.now ?? (() => new Date()))().toISOString(),
+ logPath,
+ };
+ await writeState(options.projectDir, state);
+ return { status: 'started', state, url: `http://${state.host}:${state.port}/mcp` };
+}
+
+export async function readKtxMcpDaemonStatus(options: {
+ projectDir: string;
+ processAlive?: (pid: number) => boolean;
+ fetchHealth?: (state: KtxMcpDaemonState) => Promise<{ ok: boolean; body: unknown; detail?: string }>;
+}): Promise {
+ let state: KtxMcpDaemonState | undefined;
+ try {
+ state = await readState(options.projectDir);
+ } catch (error) {
+ return { kind: 'stale', detail: `MCP daemon state is invalid: ${error instanceof Error ? error.message : String(error)}` };
+ }
+ if (!state) {
+ return { kind: 'stopped', detail: `No MCP daemon state at ${mcpDaemonLayout(options.projectDir).statePath}` };
+ }
+ const processAlive = options.processAlive ?? defaultProcessAlive;
+ if (!processAlive(state.pid)) {
+ return { kind: 'stale', detail: `MCP daemon process ${state.pid} is not running`, state };
+ }
+ const health = await (options.fetchHealth ?? defaultFetchHealth)(state);
+ if (!health.ok) {
+ return { kind: 'stale', detail: health.detail ?? 'MCP daemon health check failed', state };
+ }
+ return {
+ kind: 'running',
+ detail: `KTX MCP daemon running at http://${state.host}:${state.port}/mcp`,
+ state,
+ url: `http://${state.host}:${state.port}/mcp`,
+ };
+}
+
+export async function stopKtxMcpDaemon(options: {
+ projectDir: string;
+ processAlive?: (pid: number) => boolean;
+ killProcess?: (pid: number, signal: NodeJS.Signals) => void;
+ stopGraceMs?: number;
+ pollIntervalMs?: number;
+}): Promise<{ status: 'stopped' | 'already-stopped' }> {
+ const state = await readState(options.projectDir);
+ const { statePath } = mcpDaemonLayout(options.projectDir);
+ if (!state) {
+ return { status: 'already-stopped' };
+ }
+ const processAlive = options.processAlive ?? defaultProcessAlive;
+ const killProcess = options.killProcess ?? defaultKillProcess;
+ if (processAlive(state.pid)) {
+ killProcess(state.pid, 'SIGTERM');
+ const deadline = Date.now() + (options.stopGraceMs ?? 10_000);
+ while (Date.now() <= deadline && processAlive(state.pid)) {
+ await delay(options.pollIntervalMs ?? 100);
+ }
+ if (processAlive(state.pid)) {
+ killProcess(state.pid, 'SIGKILL');
+ }
+ }
+ await rm(statePath, { force: true });
+ return { status: 'stopped' };
+}
+```
+
+- [ ] **Step 4: Run the daemon lifecycle tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/managed-mcp-daemon.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add packages/cli/src/managed-mcp-daemon.ts packages/cli/src/managed-mcp-daemon.test.ts
+git commit -m "feat(cli): manage mcp daemon lifecycle"
+```
+
+## Task 4: Register `ktx mcp` Commands
+
+**Files:**
+- Create: `packages/cli/src/commands/mcp-commands.ts`
+- Create: `packages/cli/src/commands/mcp-commands.test.ts`
+- Modify: `packages/cli/src/cli-program.ts`
+
+- [ ] **Step 1: Write failing command tests**
+
+Create `packages/cli/src/commands/mcp-commands.test.ts` with:
+
+```typescript
+import { Command } from '@commander-js/extra-typings';
+import { describe, expect, it, vi } from 'vitest';
+import type { KtxCliCommandContext } from '../cli-program.js';
+import { registerMcpCommands } from './mcp-commands.js';
+
+function makeContext(overrides: Partial = {}): KtxCliCommandContext {
+ let exitCode = 0;
+ return {
+ io: {
+ stdout: { write: vi.fn() },
+ stderr: { write: vi.fn() },
+ },
+ deps: {},
+ packageInfo: { name: '@ktx/cli', version: '0.0.0-test' },
+ setExitCode: (code) => {
+ exitCode = code;
+ },
+ runInit: vi.fn(),
+ writeDebug: vi.fn(),
+ ...overrides,
+ get exitCode() {
+ return exitCode;
+ },
+ } as KtxCliCommandContext;
+}
+
+describe('registerMcpCommands', () => {
+ it('registers the public mcp lifecycle commands', () => {
+ const program = new Command().exitOverride();
+ registerMcpCommands(program, makeContext());
+ const mcp = program.commands.find((command) => command.name() === 'mcp');
+
+ expect(mcp?.commands.map((command) => command.name()).sort()).toEqual([
+ 'logs',
+ 'serve-internal',
+ 'start',
+ 'status',
+ 'stop',
+ ]);
+ expect(mcp?.commands.find((command) => command.name() === 'serve-internal')?.hidden).toBe(true);
+ });
+
+ it('rejects non-loopback start without token before spawning', async () => {
+ const program = new Command().exitOverride();
+ const startDaemon = vi.fn();
+ const context = makeContext({ deps: { mcp: { startDaemon } } } as Partial);
+ registerMcpCommands(program, context);
+
+ await expect(program.parseAsync(['mcp', 'start', '--host', '0.0.0.0'], { from: 'user' })).rejects.toThrow(
+ 'Binding KTX MCP to 0.0.0.0 requires --token or KTX_MCP_TOKEN',
+ );
+ expect(startDaemon).not.toHaveBeenCalled();
+ });
+});
+```
+
+If `KtxCliDeps` does not yet include `mcp`, add this test helper shape in the test file:
+
+```typescript
+type TestDeps = KtxCliCommandContext['deps'] & {
+ mcp?: {
+ startDaemon?: unknown;
+ stopDaemon?: unknown;
+ readStatus?: unknown;
+ runServer?: unknown;
+ };
+};
+```
+
+Then cast `deps: { mcp: { startDaemon } } as TestDeps`.
+
+- [ ] **Step 2: Run the command tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/commands/mcp-commands.test.ts
+```
+
+Expected: FAIL because `./mcp-commands.js` does not exist.
+
+- [ ] **Step 3: Add MCP command dependency hooks**
+
+Find `KtxCliDeps` in `packages/cli/src/cli-runtime.ts` and add:
+
+```typescript
+ mcp?: {
+ startDaemon?: typeof import('./managed-mcp-daemon.js').startKtxMcpDaemon;
+ stopDaemon?: typeof import('./managed-mcp-daemon.js').stopKtxMcpDaemon;
+ readStatus?: typeof import('./managed-mcp-daemon.js').readKtxMcpDaemonStatus;
+ runServer?: typeof import('./mcp-http-server.js').runKtxMcpHttpServer;
+ };
+```
+
+- [ ] **Step 4: Implement the MCP command subtree**
+
+Create `packages/cli/src/commands/mcp-commands.ts` with:
+
+```typescript
+import { spawn } from 'node:child_process';
+import { readFile } from 'node:fs/promises';
+import { fileURLToPath } from 'node:url';
+import { Command } from '@commander-js/extra-typings';
+import {
+ buildMcpSecurityConfig,
+ runKtxMcpHttpServer,
+} from '../mcp-http-server.js';
+import {
+ mcpDaemonLayout,
+ readKtxMcpDaemonStatus,
+ startKtxMcpDaemon,
+ stopKtxMcpDaemon,
+} from '../managed-mcp-daemon.js';
+import {
+ collectOption,
+ parsePositiveIntegerOption,
+ resolveCommandProjectDir,
+ type KtxCliCommandContext,
+} from '../cli-program.js';
+
+function tokenFromOption(value: string | undefined): string | undefined {
+ return value ?? process.env.KTX_MCP_TOKEN;
+}
+
+function binPath(): string {
+ return fileURLToPath(new URL('../bin.js', import.meta.url));
+}
+
+export function registerMcpCommands(program: Command, context: KtxCliCommandContext): void {
+ const mcp = program.command('mcp').description('Run the KTX MCP HTTP server');
+
+ mcp
+ .command('start')
+ .description('Start the KTX MCP HTTP server')
+ .option('--host ', 'Host to bind', '127.0.0.1')
+ .option('--port ', 'Port to bind', parsePositiveIntegerOption, 7878)
+ .option('--token ', 'Bearer token required for non-loopback binding')
+ .option('--foreground', 'Run in the foreground', false)
+ .option('--allowed-host ', 'Additional allowed Host header', collectOption, [])
+ .option('--allowed-origin ', 'Allowed browser Origin header', collectOption, [])
+ .action(async (options, command) => {
+ const projectDir = resolveCommandProjectDir(command);
+ const token = tokenFromOption(options.token);
+ buildMcpSecurityConfig({
+ host: options.host,
+ port: options.port,
+ token,
+ allowedHosts: options.allowedHost,
+ allowedOrigins: options.allowedOrigin,
+ });
+ if (options.foreground) {
+ await (context.deps.mcp?.runServer ?? runKtxMcpHttpServer)({
+ projectDir,
+ cliVersion: context.packageInfo.version,
+ host: options.host,
+ port: options.port,
+ token,
+ allowedHosts: options.allowedHost,
+ allowedOrigins: options.allowedOrigin,
+ io: context.io,
+ });
+ context.io.stdout.write(`KTX MCP server listening at http://${options.host}:${options.port}/mcp\n`);
+ return;
+ }
+ const result = await (context.deps.mcp?.startDaemon ?? startKtxMcpDaemon)({
+ projectDir,
+ cliVersion: context.packageInfo.version,
+ host: options.host,
+ port: options.port,
+ token,
+ allowedHosts: options.allowedHost,
+ allowedOrigins: options.allowedOrigin,
+ binPath: binPath(),
+ });
+ context.io.stdout.write(`KTX MCP daemon started: ${result.url}\n`);
+ });
+
+ mcp.command('stop').description('Stop the KTX MCP daemon').action(async (_options, command) => {
+ const result = await (context.deps.mcp?.stopDaemon ?? stopKtxMcpDaemon)({
+ projectDir: resolveCommandProjectDir(command),
+ });
+ context.io.stdout.write(result.status === 'stopped' ? 'KTX MCP daemon stopped.\n' : 'KTX MCP daemon is not running.\n');
+ });
+
+ mcp.command('status').description('Show KTX MCP daemon status').action(async (_options, command) => {
+ const status = await (context.deps.mcp?.readStatus ?? readKtxMcpDaemonStatus)({
+ projectDir: resolveCommandProjectDir(command),
+ });
+ context.io.stdout.write(`${status.detail}\n`);
+ if (status.kind === 'running') {
+ context.io.stdout.write(`URL: ${status.url}\n`);
+ context.io.stdout.write(`PID: ${status.state.pid}\n`);
+ context.io.stdout.write(`Token auth: ${status.state.tokenAuth ? 'enabled' : 'disabled'}\n`);
+ context.io.stdout.write(`Project: ${status.state.projectDir}\n`);
+ }
+ });
+
+ mcp.command('logs').description('Print the KTX MCP daemon log').option('--follow', 'Follow log output', false).action(async (options, command) => {
+ const logPath = mcpDaemonLayout(resolveCommandProjectDir(command)).logPath;
+ if (options.follow) {
+ const child = spawn('tail', ['-f', logPath], { stdio: ['ignore', 'pipe', 'pipe'] });
+ child.stdout?.on('data', (chunk: Buffer) => context.io.stdout.write(chunk.toString('utf8')));
+ child.stderr?.on('data', (chunk: Buffer) => context.io.stderr.write(chunk.toString('utf8')));
+ await new Promise((resolve) => child.on('close', resolve));
+ return;
+ }
+ context.io.stdout.write(await readFile(logPath, 'utf8'));
+ });
+
+ mcp
+ .command('serve-internal', { hidden: true })
+ .option('--host ', 'Host to bind', '127.0.0.1')
+ .requiredOption('--port ', 'Port to bind', parsePositiveIntegerOption)
+ .option('--allowed-host ', 'Additional allowed Host header', collectOption, [])
+ .option('--allowed-origin ', 'Allowed browser Origin header', collectOption, [])
+ .action(async (options, command) => {
+ await (context.deps.mcp?.runServer ?? runKtxMcpHttpServer)({
+ projectDir: resolveCommandProjectDir(command),
+ cliVersion: context.packageInfo.version,
+ host: options.host,
+ port: options.port,
+ token: process.env.KTX_MCP_TOKEN,
+ allowedHosts: options.allowedHost,
+ allowedOrigins: options.allowedOrigin,
+ io: context.io,
+ });
+ });
+}
+```
+
+- [ ] **Step 5: Wire the command into the root CLI**
+
+In `packages/cli/src/cli-program.ts`:
+
+Add the import:
+
+```typescript
+import { registerMcpCommands } from './commands/mcp-commands.js';
+```
+
+Change:
+
+```typescript
+const PROJECT_AWARE_ROOT_COMMANDS = new Set(['setup', 'connection', 'ingest', 'wiki', 'sl', 'status']);
+```
+
+to:
+
+```typescript
+const PROJECT_AWARE_ROOT_COMMANDS = new Set(['setup', 'connection', 'ingest', 'wiki', 'sl', 'status', 'mcp']);
+```
+
+Add registration after `registerStatusCommands(program, context);`:
+
+```typescript
+ registerMcpCommands(program, context);
+```
+
+- [ ] **Step 6: Run command tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/commands/mcp-commands.test.ts src/cli-program.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 7: Commit**
+
+```bash
+git add \
+ packages/cli/src/commands/mcp-commands.ts \
+ packages/cli/src/commands/mcp-commands.test.ts \
+ packages/cli/src/cli-program.ts \
+ packages/cli/src/cli-runtime.ts
+git commit -m "feat(cli): add ktx mcp commands"
+```
+
+## Task 5: Final Verification And Handoff
+
+**Files:**
+- Verify: `packages/cli/src/mcp-http-server.ts`
+- Verify: `packages/cli/src/managed-mcp-daemon.ts`
+- Verify: `packages/cli/src/commands/mcp-commands.ts`
+- Verify: `packages/cli/package.json`
+
+- [ ] **Step 1: Run focused CLI tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run \
+ src/mcp-http-server.test.ts \
+ src/managed-mcp-daemon.test.ts \
+ src/commands/mcp-commands.test.ts \
+ src/cli-program.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 2: Run CLI type-check**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli run type-check
+```
+
+Expected: PASS.
+
+- [ ] **Step 3: Run CLI package tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli run test
+```
+
+Expected: PASS.
+
+- [ ] **Step 4: Run workspace type-check**
+
+Run:
+
+```bash
+pnpm run type-check
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Confirm remaining v1 blockers**
+
+Run:
+
+```bash
+test -e packages/cli/src/skills/research/SKILL.md; printf 'research-skill:%s\n' "$?"
+rg -n "connectionName" packages/context/src/ingest/tools/warehouse-verification
+rg -n "mcpServers|mcp_servers|opencode|KTX_MCP_TOKEN" packages/cli/src/setup-agents.ts packages/cli/src/setup-agents.test.ts
+```
+
+Expected after this plan is implemented:
+
+```text
+research-skill:1
+```
+
+Expected `rg "connectionName"`: matches remain under `packages/context/src/ingest/tools/warehouse-verification`, proving ingest contract convergence still needs a later v1 plan.
+
+Expected setup-agent `rg`: no complete MCP client config writer/snippet matrix yet, proving setup-agent/research-skill installation still needs a later v1 plan.
+
+- [ ] **Step 6: Commit final fixes if verification required any**
+
+If verification required changes, commit them:
+
+```bash
+git add packages/cli/src packages/cli/package.json pnpm-lock.yaml
+git commit -m "fix(cli): stabilize mcp daemon verification"
+```
+
+If no verification changes were needed, do not create an empty commit.
+
+## Self-Review
+
+- Spec coverage in this plan: covers `ktx mcp start|stop|status|logs`, foreground/background lifecycle, `.ktx/mcp.json`, `.ktx/logs/mcp.log`, HTTP-only `/mcp`, `/health`, stateful sessions, Host/Origin validation, non-loopback token requirement, and bearer checks on `/mcp`.
+- Remaining v1-blocking spec coverage after this plan: setup-agent MCP client config installation, `ktx-research` skill installation, and ingest-side warehouse-verification `connectionName` to `connectionId` contract convergence.
+- Placeholder scan: the plan contains no deferred work markers or vague implementation instructions.
+- Type consistency: public names are consistent across tasks: `runKtxMcpHttpServer`, `buildMcpSecurityConfig`, `isMcpRequestAuthorized`, `mcpDaemonLayout`, `startKtxMcpDaemon`, `readKtxMcpDaemonStatus`, `stopKtxMcpDaemon`, and `registerMcpCommands`.
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-ingest-contract-convergence.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-ingest-contract-convergence.md
new file mode 100644
index 00000000..b57d72b9
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-ingest-contract-convergence.md
@@ -0,0 +1,804 @@
+# Research Agent MCP Ingest Contract Convergence Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Finish the v1 research-agent MCP spec by converging the existing ingest warehouse-verification tools on `connectionId` terminology and a shared raw-schema catalog service.
+
+**Architecture:** Move the existing warehouse catalog reader out of the ingest-only tool folder into `packages/context/src/scan/warehouse-catalog.ts`, rename its public contract from `connectionName` to `connectionId`, and make the ingest adapters consume that shared service. Keep the ingest tools' ingest-specific output shape (`markdown` plus `structured`) and their existing `targets` / `rowLimit` controls; the v1 blocker is the divergent connection parameter and stale prompt guidance, not changing ingest output into the MCP pure-structured shape.
+
+**Tech Stack:** TypeScript, Zod, Vitest, existing KTX local file-store scan artifacts, existing ingest BaseTool framework.
+
+---
+
+## Audit Summary
+
+Implemented and no longer v1-blocking:
+
+- MCP `sql_execution`, `entity_details`, `dictionary_search`, and `discover_data` are registered in `packages/context/src/mcp/context-tools.ts` and wired through local project ports.
+- `sql_execution` is parser-gated through the Python sqlglot validator before reaching local scan connectors.
+- The HTTP-only `ktx mcp` daemon exists with Streamable HTTP `POST`, `GET`, and `DELETE` handling, session tracking, host/origin checks, token checks for `/mcp`, lifecycle state, and CLI commands.
+- `ktx setup-agents` installs the `ktx-research` skill, writes Claude/Cursor JSON MCP config entries, and prints Codex/opencode snippets.
+
+Remaining v1 blocker:
+
+- The ingest warehouse-verification tools still expose and teach `connectionName` while the spec requires `connectionId` across `warehouse-verification/*.tool.ts`, `WarehouseCatalogService`, callers, tests, and prompt assets.
+
+Non-blocking follow-ups not covered here:
+
+- `ktx mcp status` does not print `startedAt` as a separate line, although the state file records it.
+- `ktx setup-agents` writes safe `${KTX_MCP_TOKEN}` references for shared project configs, but it does not offer the spec's optional skip prompt when token auth is active.
+- `discover_data` sample-value snippets use ASCII `" - samples: "` instead of the spec prose's middle-dot separator.
+
+## File Structure
+
+- Move: `packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.ts` to `packages/context/src/scan/warehouse-catalog.ts`
+ - Shared live-database scan catalog reader, display resolver, raw schema search, and table detail source of truth.
+- Modify: `packages/context/src/scan/index.ts`
+ - Export the shared warehouse catalog service and public types.
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/entity-details.tool.ts`
+ - Accept `connectionId`, call shared catalog service, and emit connectionId-shaped markdown and structured output.
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/discover-data.tool.ts`
+ - Accept optional `connectionId`, search raw schema via shared catalog service, and teach follow-up calls with `connectionId`.
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/sql-execution.tool.ts`
+ - Accept `connectionId`, keep `rowLimit`, and pass `connectionId` to `SlConnectionCatalogPort.executeQuery`.
+- Modify tests:
+ - `packages/context/src/ingest/tools/warehouse-verification/entity-details.tool.test.ts`
+ - `packages/context/src/ingest/tools/warehouse-verification/discover-data.tool.test.ts`
+ - `packages/context/src/ingest/tools/warehouse-verification/sql-execution.tool.test.ts`
+ - `packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.test.ts`
+ - Rename the service test file to `packages/context/src/scan/warehouse-catalog.test.ts`.
+- Modify prompt assets:
+ - `packages/context/skills/_shared/identifier-verification.md`
+ - `packages/context/skills/dbt_ingest/SKILL.md`
+ - `packages/context/skills/historic_sql_patterns/SKILL.md`
+ - `packages/context/skills/historic_sql_table_digest/SKILL.md`
+ - `packages/context/skills/live_database_ingest/SKILL.md`
+ - `packages/context/skills/looker_ingest/SKILL.md`
+ - `packages/context/skills/lookml_ingest/SKILL.md`
+ - `packages/context/skills/metabase_ingest/SKILL.md`
+ - `packages/context/skills/metricflow_ingest/SKILL.md`
+ - `packages/context/skills/notion_synthesize/SKILL.md`
+ - `packages/context/skills/sl_capture/SKILL.md`
+ - `packages/context/skills/wiki_capture/SKILL.md`
+ - Preserve Looker/LookML prose where `connectionName` refers to a Looker runtime field, not a KTX tool parameter.
+
+## Task 1: Add Failing Contract Tests
+
+**Files:**
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/entity-details.tool.test.ts`
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/discover-data.tool.test.ts`
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/sql-execution.tool.test.ts`
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.test.ts`
+- Modify: `packages/context/src/ingest/ingest-runtime-assets.test.ts`
+
+- [ ] **Step 1: Add entity_details input-contract coverage**
+
+Add this test inside the existing `describe('EntityDetailsTool', ...)` block:
+
+```typescript
+it('uses connectionId as the public input field', async () => {
+ expect(
+ tool.parseInput({
+ connectionId: 'warehouse',
+ targets: [{ display: 'public.orders' }],
+ }),
+ ).toEqual({
+ connectionId: 'warehouse',
+ targets: [{ display: 'public.orders' }],
+ });
+
+ expect(() =>
+ tool.parseInput({
+ connectionName: 'warehouse',
+ targets: [{ display: 'public.orders' }],
+ }),
+ ).toThrow();
+});
+```
+
+Update the existing `tool.call(...)` inputs in the same test file from `connectionName` to `connectionId`. For example:
+
+```typescript
+const result = await tool.call({ connectionId: 'warehouse', targets: [{ display: 'public.orders' }] }, context);
+```
+
+- [ ] **Step 2: Add sql_execution input-contract coverage**
+
+Add this test inside `packages/context/src/ingest/tools/warehouse-verification/sql-execution.tool.test.ts`:
+
+```typescript
+it('uses connectionId as the public input field', () => {
+ expect(
+ tool.parseInput({
+ connectionId: 'warehouse',
+ sql: 'select 1',
+ rowLimit: 5,
+ }),
+ ).toEqual({
+ connectionId: 'warehouse',
+ sql: 'select 1',
+ rowLimit: 5,
+ });
+
+ expect(() =>
+ tool.parseInput({
+ connectionName: 'warehouse',
+ sql: 'select 1',
+ rowLimit: 5,
+ }),
+ ).toThrow();
+});
+```
+
+Update the existing `tool.call(...)` inputs in the same test file from `connectionName` to `connectionId`.
+
+- [ ] **Step 3: Add discover_data input and hint coverage**
+
+Update the existing discover tests so the first case calls:
+
+```typescript
+const result = await tool.call({ query: 'orders', connectionId: 'warehouse', limit: 5 }, context);
+```
+
+Change the routing-hint assertions to:
+
+```typescript
+expect(result.markdown).toContain('use `entity_details({connectionId, targets: [{display}]})`');
+```
+
+In the multi-connection test, use a `connectionId` hit field and assert the follow-up call is connectionId-shaped:
+
+```typescript
+catalog.searchByName.mockImplementation(async (connectionId: string, query: string) => [
+ {
+ kind: 'table',
+ connectionId,
+ ref: { catalog: null, db: 'public', name: `${connectionId}_${query}` },
+ display: `public.${connectionId}_${query}`,
+ matchedOn: 'name',
+ },
+]);
+
+const result = await tool.call({ query: 'orders', limit: 10 }, multiConnectionContext);
+
+expect(catalog.searchByName).toHaveBeenCalledWith('analytics', 'orders', 10);
+expect(catalog.searchByName).toHaveBeenCalledWith('warehouse', 'orders', 10);
+expect(result.markdown).toContain('connectionId=analytics');
+expect(result.markdown).toContain('connectionId=warehouse');
+expect(result.markdown).toContain(
+ 'entity_details({connectionId: "analytics", targets: [{display: "public.analytics_orders"}]})',
+);
+expect(result.structured.raw?.hits.map((hit) => hit.connectionId)).toEqual(['analytics', 'warehouse']);
+```
+
+Add a parse contract test:
+
+```typescript
+it('uses connectionId as the optional connection filter', () => {
+ expect(tool.parseInput({ query: 'orders', connectionId: 'warehouse', limit: 5 })).toEqual({
+ query: 'orders',
+ connectionId: 'warehouse',
+ limit: 5,
+ });
+
+ expect(() => tool.parseInput({ query: 'orders', connectionName: 'warehouse', limit: 5 })).toThrow();
+});
+```
+
+- [ ] **Step 4: Add shared catalog output coverage**
+
+Rename `packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.test.ts` to `packages/context/src/scan/warehouse-catalog.test.ts`.
+
+Update the import to:
+
+```typescript
+import { WarehouseCatalogService } from './warehouse-catalog.js';
+```
+
+Update the main detail assertion to use `connectionId`:
+
+```typescript
+const detail = await catalog.getTable({ connectionId: 'warehouse', catalog: null, db: 'public', name: 'orders' });
+
+expect(detail).toMatchObject({
+ connectionId: 'warehouse',
+ display: 'public.orders',
+});
+expect(detail).not.toHaveProperty('connectionName');
+```
+
+Add raw hit coverage:
+
+```typescript
+const hits = await catalog.searchByName('warehouse', 'orders', 5);
+expect(hits[0]).toMatchObject({
+ kind: 'table',
+ connectionId: 'warehouse',
+ display: 'public.orders',
+});
+expect(hits[0]).not.toHaveProperty('connectionName');
+```
+
+- [ ] **Step 5: Update prompt-asset test expectations first**
+
+In `packages/context/src/ingest/ingest-runtime-assets.test.ts`, change the identifier verification expectations to:
+
+```typescript
+expect(shared).toContain('sql_execution({connectionId, sql: "SELECT DISTINCT');
+expect(shared).toContain('sql_execution({connectionId, sql: "SELECT 1 FROM');
+expect(shared).not.toContain('entity_details({connectionName');
+expect(shared).not.toContain('sql_execution({connectionName');
+```
+
+- [ ] **Step 6: Run focused tests and verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run \
+ src/ingest/tools/warehouse-verification/entity-details.tool.test.ts \
+ src/ingest/tools/warehouse-verification/discover-data.tool.test.ts \
+ src/ingest/tools/warehouse-verification/sql-execution.tool.test.ts \
+ src/scan/warehouse-catalog.test.ts \
+ src/ingest/ingest-runtime-assets.test.ts
+```
+
+Expected: FAIL because schemas still require `connectionName`, the catalog service still returns `connectionName`, and the prompt asset still contains old tool-call examples.
+
+## Task 2: Move And Rename The Shared Warehouse Catalog Service
+
+**Files:**
+- Move: `packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.ts` to `packages/context/src/scan/warehouse-catalog.ts`
+- Modify: `packages/context/src/scan/index.ts`
+- Delete: `packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.ts`
+
+- [ ] **Step 1: Move the service into the scan package**
+
+Run:
+
+```bash
+git mv packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.ts packages/context/src/scan/warehouse-catalog.ts
+```
+
+- [ ] **Step 2: Fix imports for the new location**
+
+In `packages/context/src/scan/warehouse-catalog.ts`, change the imports at the top to:
+
+```typescript
+import { getDialectForDriver } from '../connections/index.js';
+import type { KtxFileStorePort } from '../core/index.js';
+import type {
+ KtxConnectionDriver,
+ KtxSchemaColumn,
+ KtxSchemaForeignKey,
+ KtxSchemaTable,
+ KtxTableRef,
+} from './types.js';
+```
+
+- [ ] **Step 3: Rename public catalog fields and method parameters**
+
+In `packages/context/src/scan/warehouse-catalog.ts`, rename the service's public contract to this shape:
+
+```typescript
+export interface TableDetail {
+ connectionId: string;
+ catalog: string | null;
+ db: string | null;
+ name: string;
+ display: string;
+ kind: string;
+ comment: string | null;
+ description: string | null;
+ rowCount: number | null;
+ columns: WarehouseColumnDetail[];
+ foreignKeys: KtxSchemaForeignKey[];
+}
+
+export type RawSchemaHit =
+ | {
+ kind: 'table';
+ connectionId: string;
+ ref: KtxTableRef;
+ display: string;
+ matchedOn: 'name' | 'db' | 'comment' | 'description';
+ }
+ | {
+ kind: 'column';
+ connectionId: string;
+ ref: KtxTableRef & { column: string };
+ display: string;
+ matchedOn: 'name' | 'comment' | 'description';
+ };
+
+interface ConnectionCatalog {
+ connectionId: string;
+ syncId: string;
+ driver: CatalogDriver;
+ tables: KtxSchemaTable[];
+ profile: RelationshipProfileArtifact | null;
+}
+```
+
+Update the method signatures to:
+
+```typescript
+async hasScan(connectionId: string): Promise
+async getLatestSyncId(connectionId: string): Promise
+async listTables(connectionId: string): Promise
+async getTable(ref: { connectionId: string } & KtxTableRef): Promise
+async resolveDisplay(connectionId: string, display: string): Promise<{ resolved: KtxTableRef | null; candidates: KtxTableRef[]; dialect: string }>
+async resolveDisplayTarget(connectionId: string, display: string): Promise
+async searchByName(connectionId: string, query: string, limit: number): Promise
+private loadCatalog(connectionId: string): Promise
+private async readCatalog(connectionId: string): Promise
+```
+
+Within those methods, use `connectionId` for the cache key, raw artifact root, returned `TableDetail.connectionId`, and returned `RawSchemaHit.connectionId`.
+
+- [ ] **Step 4: Export the shared service**
+
+Add these exports to `packages/context/src/scan/index.ts` near the existing entity-details exports:
+
+```typescript
+export type {
+ DisplayTargetResolution,
+ RawSchemaHit,
+ TableDetail,
+ WarehouseCatalogServiceDeps,
+} from './warehouse-catalog.js';
+export { WarehouseCatalogService } from './warehouse-catalog.js';
+```
+
+- [ ] **Step 5: Run the catalog test**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/scan/warehouse-catalog.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 6: Commit the shared catalog move**
+
+Run:
+
+```bash
+git add packages/context/src/scan/warehouse-catalog.ts packages/context/src/scan/warehouse-catalog.test.ts packages/context/src/scan/index.ts packages/context/src/ingest/tools/warehouse-verification/warehouse-catalog.service.ts
+git commit -m "refactor(context): share warehouse catalog service"
+```
+
+## Task 3: Rename Ingest Warehouse-Verification Tool Inputs
+
+**Files:**
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/entity-details.tool.ts`
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/discover-data.tool.ts`
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/sql-execution.tool.ts`
+- Modify: `packages/context/src/ingest/tools/warehouse-verification/index.ts`
+
+- [ ] **Step 1: Update imports from the shared scan service**
+
+In `entity-details.tool.ts`, use:
+
+```typescript
+import { WarehouseCatalogService, type TableDetail } from '../../../scan/warehouse-catalog.js';
+```
+
+In `discover-data.tool.ts`, use:
+
+```typescript
+import { WarehouseCatalogService, type RawSchemaHit } from '../../../scan/warehouse-catalog.js';
+```
+
+In `index.ts`, use:
+
+```typescript
+import { WarehouseCatalogService } from '../../../scan/warehouse-catalog.js';
+```
+
+- [ ] **Step 2: Rename entity_details input and calls**
+
+In `entity-details.tool.ts`, update the schema:
+
+```typescript
+const entityDetailsInputSchema = z.object({
+ connectionId: z.string().regex(/^[a-zA-Z0-9][a-zA-Z0-9_-]*$/),
+ targets: z.array(targetSchema).min(1).max(50),
+});
+```
+
+Update `resolveTarget`:
+
+```typescript
+async function resolveTarget(
+ catalog: WarehouseCatalogService,
+ connectionId: string,
+ target: EntityDetailsTarget,
+): Promise<{ resolved: (KtxTableRef & { column?: string }) | null; candidates: KtxTableRef[] }> {
+ if ('display' in target) {
+ return catalog.resolveDisplayTarget(connectionId, target.display);
+ }
+
+ const candidateResolution = await catalog.resolveDisplayTarget(connectionId, targetLabel(target));
+ return {
+ resolved: {
+ catalog: target.catalog,
+ db: target.db,
+ name: target.name,
+ column: target.column,
+ },
+ candidates: candidateResolution.candidates,
+ };
+}
+```
+
+Update the start of `call`:
+
+```typescript
+async call(input: EntityDetailsInput, context: ToolContext): Promise> {
+ const allowed = allowedConnectionNames(context);
+ if (allowed && !allowed.has(input.connectionId)) {
+ return {
+ markdown: `Connection "${input.connectionId}" is not available to this ingest stage.`,
+ structured: { resolved: [], missing: [], scanAvailable: false },
+ };
+ }
+
+ const catalog = this.catalogFactory(context);
+ const scanAvailable = await catalog.hasScan(input.connectionId);
+ if (!scanAvailable) {
+ return {
+ markdown: `No live-database scan available for connection "${input.connectionId}"; run \`ktx scan\` first.`,
+ structured: { resolved: [], missing: [], scanAvailable: false },
+ };
+ }
+```
+
+Update the table lookup:
+
+```typescript
+const resolution = await resolveTarget(catalog, input.connectionId, target);
+const detail = await catalog.getTable({ connectionId: input.connectionId, ...resolution.resolved });
+```
+
+- [ ] **Step 3: Rename sql_execution input and calls**
+
+In `sql-execution.tool.ts`, update the schema:
+
+```typescript
+const sqlExecutionInputSchema = z.object({
+ connectionId: z.string().regex(/^[a-zA-Z0-9][a-zA-Z0-9_-]*$/),
+ sql: z.string().min(1),
+ rowLimit: z.number().int().positive().max(1000).optional().default(100),
+});
+```
+
+Update the allowed-connection guard:
+
+```typescript
+const allowed = context.session?.allowedConnectionNames;
+if (allowed && !allowed.has(input.connectionId)) {
+ return {
+ markdown: `Connection "${input.connectionId}" is not available to this ingest stage.`,
+ structured: {
+ headers: [],
+ rows: [],
+ rowCount: 0,
+ truncated: false,
+ sql: input.sql,
+ wrappedSql: '',
+ error: 'connection_not_allowed',
+ },
+ };
+}
+```
+
+Update execution:
+
+```typescript
+const result = await this.connections.executeQuery(input.connectionId, wrappedSql);
+```
+
+- [ ] **Step 4: Rename discover_data input, raw hits, and routing hints**
+
+In `discover-data.tool.ts`, update the schema:
+
+```typescript
+const discoverDataInputSchema = z.object({
+ query: z.string().optional(),
+ connectionId: z.string().regex(/^[a-zA-Z0-9][a-zA-Z0-9_-]*$/).optional(),
+ limit: z.number().int().positive().max(50).optional().default(10),
+ sourceName: z.string().optional(),
+});
+```
+
+Update the out-of-scope check:
+
+```typescript
+if (input.connectionId && allowed && !allowed.has(input.connectionId)) {
+ return {
+ markdown: `Connection "${input.connectionId}" is not available to this ingest stage.`,
+ structured: { wiki: null, sl: null, raw: null },
+ };
+}
+```
+
+Update the source inspect mode:
+
+```typescript
+const sl = await this.deps.slDiscoverTool.call(
+ { sourceName: input.sourceName, connectionId: input.connectionId },
+ context,
+);
+```
+
+Update the SL discover call:
+
+```typescript
+const slResult = await this.deps.slDiscoverTool.call(
+ { query: query || undefined, connectionId: input.connectionId },
+ context,
+);
+```
+
+Update the raw search loop and hints:
+
+```typescript
+const connections = input.connectionId ? [input.connectionId] : [...(allowed ?? [])].sort();
+const rawHits: RawSchemaHit[] = [];
+for (const connectionId of connections) {
+ rawHits.push(...(await catalog.searchByName(connectionId, query, limit)));
+}
+if (rawHits.length > 0) {
+ parts.push(
+ '## Raw Warehouse Schema',
+ '> use `entity_details({connectionId, targets: [{display}]})` for full DDL + sample values',
+ );
+ parts.push(
+ rawHits
+ .slice(0, limit)
+ .map(
+ (hit) =>
+ `- ${hit.kind}: ${hit.display} [connectionId=${hit.connectionId}] (matched on ${hit.matchedOn}) - ` +
+ `follow up with \`entity_details({connectionId: "${hit.connectionId}", targets: [{display: "${hit.display}"}]})\``,
+ )
+ .join('\n'),
+ );
+ raw = { hits: rawHits.slice(0, limit) };
+}
+```
+
+- [ ] **Step 5: Run focused tool tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run \
+ src/ingest/tools/warehouse-verification/entity-details.tool.test.ts \
+ src/ingest/tools/warehouse-verification/discover-data.tool.test.ts \
+ src/ingest/tools/warehouse-verification/sql-execution.tool.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 6: Commit the ingest tool contract rename**
+
+Run:
+
+```bash
+git add packages/context/src/ingest/tools/warehouse-verification/entity-details.tool.ts packages/context/src/ingest/tools/warehouse-verification/discover-data.tool.ts packages/context/src/ingest/tools/warehouse-verification/sql-execution.tool.ts packages/context/src/ingest/tools/warehouse-verification/index.ts packages/context/src/ingest/tools/warehouse-verification/*.test.ts
+git commit -m "refactor(context): use connectionId in warehouse verification tools"
+```
+
+## Task 4: Update Prompt Assets And Runtime Tests
+
+**Files:**
+- Modify: `packages/context/skills/_shared/identifier-verification.md`
+- Modify: `packages/context/skills/dbt_ingest/SKILL.md`
+- Modify: `packages/context/skills/historic_sql_patterns/SKILL.md`
+- Modify: `packages/context/skills/historic_sql_table_digest/SKILL.md`
+- Modify: `packages/context/skills/live_database_ingest/SKILL.md`
+- Modify: `packages/context/skills/looker_ingest/SKILL.md`
+- Modify: `packages/context/skills/lookml_ingest/SKILL.md`
+- Modify: `packages/context/skills/metabase_ingest/SKILL.md`
+- Modify: `packages/context/skills/metricflow_ingest/SKILL.md`
+- Modify: `packages/context/skills/notion_synthesize/SKILL.md`
+- Modify: `packages/context/skills/sl_capture/SKILL.md`
+- Modify: `packages/context/skills/wiki_capture/SKILL.md`
+- Modify: `packages/context/src/ingest/ingest-runtime-assets.test.ts`
+
+- [ ] **Step 1: Update the shared identifier verification protocol**
+
+Replace the tool-call examples in `packages/context/skills/_shared/identifier-verification.md` with:
+
+```markdown
+2. `entity_details({connectionId, targets: [{display: ""}]})` -
+ confirm the identifier resolves; inspect native types, FK/PK, and
+ sampleValues.
+3. For literal values from the source, such as status codes or plan tiers,
+ check whether they appear in `entity_details` sampleValues for the relevant
+ column. If sampleValues is short or the sample may have missed real values,
+ run a `sql_execution` probe with the same warehouse connection id:
+ `sql_execution({connectionId, sql: "SELECT DISTINCT FROM [ LIMIT 50"})`.
+4. If the candidate identifier still does not resolve, do one of:
+ - Use `sql_execution({connectionId, sql: "SELECT 1 FROM ][ LIMIT 0"})`.
+ If it errors, the identifier is fictional.
+```
+
+- [ ] **Step 2: Update copied skill assets**
+
+In the listed `packages/context/skills/*/SKILL.md` files, replace only KTX tool-call examples:
+
+```text
+entity_details({connectionName, targets:
+```
+
+with:
+
+```text
+entity_details({connectionId, targets:
+```
+
+Replace:
+
+```text
+sql_execution({connectionName, sql:
+```
+
+with:
+
+```text
+sql_execution({connectionId, sql:
+```
+
+Replace concrete KTX tool-call examples like:
+
+```text
+sql_execution({connectionName: "warehouse", sql:
+```
+
+with:
+
+```text
+sql_execution({connectionId: "warehouse", sql:
+```
+
+In `packages/context/skills/sl_capture/SKILL.md`, replace the JSON field inside the example object:
+
+```yaml
+connectionName: "warehouse",
+```
+
+with:
+
+```yaml
+connectionId: "warehouse",
+```
+
+Do not change `packages/context/skills/looker_ingest/SKILL.md` text that defines Looker runtime `connectionName`, and do not change LookML parser docs where `connectionName` names a LookML model property.
+
+- [ ] **Step 3: Update runtime asset tests**
+
+In `packages/context/src/ingest/ingest-runtime-assets.test.ts`, ensure the identifier test asserts the new examples:
+
+```typescript
+expect(shared).toContain('sql_execution({connectionId, sql: "SELECT DISTINCT');
+expect(shared).toContain('sql_execution({connectionId, sql: "SELECT 1 FROM');
+expect(shared).not.toContain('entity_details({connectionName');
+expect(shared).not.toContain('sql_execution({connectionName');
+```
+
+- [ ] **Step 4: Run prompt asset checks**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run src/ingest/ingest-runtime-assets.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Verify stale tool-call examples are gone**
+
+Run:
+
+```bash
+rg -n "entity_details\\(\\{connectionName|sql_execution\\(\\{connectionName|connectionName=" packages/context/skills packages/context/src/ingest/ingest-runtime-assets.test.ts
+```
+
+Expected: no output. If this reports Looker/LookML prose that is not a KTX tool-call example, narrow the regex and keep the Looker/LookML prose unchanged.
+
+- [ ] **Step 6: Commit prompt asset updates**
+
+Run:
+
+```bash
+git add packages/context/skills packages/context/src/ingest/ingest-runtime-assets.test.ts
+git commit -m "docs(context): update ingest verification prompts for connectionId"
+```
+
+## Task 5: Final Verification
+
+**Files:**
+- Verify all files changed in Tasks 1-4.
+
+- [ ] **Step 1: Run focused research-agent ingest tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context exec vitest run \
+ src/scan/warehouse-catalog.test.ts \
+ src/ingest/tools/warehouse-verification/entity-details.tool.test.ts \
+ src/ingest/tools/warehouse-verification/discover-data.tool.test.ts \
+ src/ingest/tools/warehouse-verification/sql-execution.tool.test.ts \
+ src/ingest/ingest-runtime-assets.test.ts
+```
+
+Expected: PASS.
+
+- [ ] **Step 2: Run context type-check**
+
+Run:
+
+```bash
+pnpm --filter @ktx/context run type-check
+```
+
+Expected: PASS.
+
+- [ ] **Step 3: Run dead-code checks after TypeScript changes**
+
+Run:
+
+```bash
+pnpm run dead-code
+```
+
+Expected: PASS. If Knip reports unrelated pre-existing findings, record the exact unrelated findings in the implementation handoff and do not add broad ignores.
+
+- [ ] **Step 4: Verify the v1-blocking old contract is gone**
+
+Run:
+
+```bash
+rg -n "connectionName" packages/context/src/ingest/tools/warehouse-verification packages/context/src/scan/warehouse-catalog.ts packages/context/src/scan/warehouse-catalog.test.ts
+```
+
+Expected: no output.
+
+Run:
+
+```bash
+rg -n "entity_details\\(\\{connectionName|sql_execution\\(\\{connectionName|connectionName=" packages/context/skills packages/context/src/ingest/ingest-runtime-assets.test.ts
+```
+
+Expected: no output.
+
+- [ ] **Step 5: Inspect git status**
+
+Run:
+
+```bash
+git status --short
+```
+
+Expected: only the intended scan catalog move, warehouse-verification tools/tests, prompt assets, and ingest runtime asset test changes are present.
+
+- [ ] **Step 6: Commit final fixes if verification required any**
+
+If Steps 1-5 required follow-up edits, commit those edits:
+
+```bash
+git add packages/context/src packages/context/skills
+git commit -m "test(context): verify warehouse verification connectionId contract"
+```
+
+If `git status --short` is empty after the earlier task commits, skip this commit.
+
+## Self-Review
+
+- Spec coverage: This plan covers the remaining v1 requirement that ingest-side warehouse verification uses `connectionId` and shares the raw-schema catalog service instead of preserving a divergent `connectionName` contract.
+- Placeholder scan: The plan contains no deferred-work marker phrases.
+- Type consistency: The plan uses `connectionId` consistently in public tool inputs, `TableDetail`, `RawSchemaHit`, `WarehouseCatalogService` method parameters, tests, and prompt assets.
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-setup-agents.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-setup-agents.md
new file mode 100644
index 00000000..13f66764
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-setup-agents.md
@@ -0,0 +1,938 @@
+# Research Agent MCP Setup Agents Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Make `ktx setup-agents` install the `ktx-research` skill and configure or print MCP client entries that point agents at the local `ktx mcp` HTTP endpoint.
+
+**Architecture:** Keep `packages/cli/src/setup-agents.ts` as the setup orchestration point. Add a small MCP-client config planner/writer in the same module, backed by `.ktx/mcp.json` when present, and install the research skill from a copied runtime asset so source checkouts and published CLI builds use the same `SKILL.md`.
+
+**Tech Stack:** TypeScript, Vitest, Node fs/path APIs, Commander setup options, KTX MCP daemon state, JSON config writers.
+
+---
+
+## Current Audit
+
+Original spec: `docs/superpowers/specs/2026-05-14-research-agent-mcp-tools-design.md`
+
+Implemented v1 slices confirmed in current source:
+
+- MCP `sql_execution`, `entity_details`, `dictionary_search`, and `discover_data` are registered in `packages/context/src/mcp/context-tools.ts`.
+- Local project MCP ports wire all four tools in `packages/context/src/mcp/local-project-ports.ts`.
+- Parser-backed SQL validation exists in `python/ktx-daemon/src/ktx_daemon/sql_analysis.py` and is exposed through `POST /sql/validate-read-only`.
+- `ktx mcp start|stop|status|logs` exists in `packages/cli/src/commands/mcp-commands.ts`, with HTTP hosting in `packages/cli/src/mcp-http-server.ts` and daemon state in `packages/cli/src/managed-mcp-daemon.ts`.
+- Targeted verification passed:
+ - `pnpm --filter @ktx/context exec vitest run src/mcp/server.test.ts src/search/discover.test.ts src/scan/entity-details.test.ts src/sl/dictionary-search.test.ts`
+ - `pnpm --filter @ktx/cli exec vitest run src/mcp-http-server.test.ts src/managed-mcp-daemon.test.ts src/commands/mcp-commands.test.ts src/setup-agents.test.ts`
+
+V1-blocking gaps remaining against the original spec:
+
+- `ktx setup-agents` still installs only the existing `ktx` agent files; it does not install `ktx-research`.
+- `ktx setup-agents` does not write Claude Code or Cursor MCP JSON config entries.
+- `ktx setup-agents` does not print Codex or opencode copy-paste snippets.
+- `ktx setup-agents --remove` cannot remove written MCP JSON keys because none are written or tracked.
+- The ingest-side warehouse-verification tools still use `connectionName`, `targets`, and `rowLimit`, and `WarehouseCatalogService` still exposes connection-name terminology. That is a separate v1-blocking subsystem and is not mixed into this setup-agent plan.
+
+Non-blocking or explicitly out-of-scope gaps:
+
+- Python code execution over MCP.
+- Stdio MCP transport.
+- OS-level auto-start.
+- Native TLS, audit logging, rate limiting, per-tool authorization, and multi-project daemon routing.
+- Streaming SQL results.
+
+## File Structure
+
+Create:
+
+- `packages/cli/src/skills/research/SKILL.md`
+ - Canonical research skill body from the spec.
+ - Copied into `dist/skills/research/SKILL.md` during `@ktx/cli` build.
+- `packages/cli/scripts/copy-runtime-assets.mjs`
+ - Copies `src/skills` into `dist/skills` after TypeScript compilation.
+
+Modify:
+
+- `packages/cli/package.json`
+ - Append the runtime asset copy step to the `build` script.
+- `packages/cli/src/setup-agents.ts`
+ - Add `local` agent scope for Claude Code's per-project private config path.
+ - Add `research-skill` file entries in `plannedKtxAgentFiles()`.
+ - Read the research skill asset when writing research-skill entries.
+ - Add MCP endpoint resolution from `.ktx/mcp.json`, falling back to `http://localhost:7878/mcp`.
+ - Add JSON writers for Claude Code and Cursor MCP entries.
+ - Add printed snippets for Codex and opencode.
+ - Track written JSON keys in the install manifest.
+ - Print the daemon-start hint when the daemon is not currently running.
+- `packages/cli/src/setup-agents.test.ts`
+ - Cover research skill install paths, MCP JSON writers, snippets, manifest removal, token handling, and no literal-token rendering.
+- `packages/cli/src/commands/setup-commands.ts`
+ - Add `--local` for Claude Code local-scope setup.
+ - Reject `--local` with non-Claude targets and reject `--local --global`.
+- `packages/cli/src/setup.ts`
+ - No behavior change beyond accepting `KtxAgentScope` with the new `local` value.
+- `packages/cli/src/cli-program.ts`
+ - Keep the default bare setup `agentScope: 'project'`; no code change needed unless TypeScript requires the widened scope type in nearby annotations.
+
+## Task 1: Add The Research Skill Runtime Asset
+
+**Files:**
+- Create: `packages/cli/src/skills/research/SKILL.md`
+- Create: `packages/cli/scripts/copy-runtime-assets.mjs`
+- Modify: `packages/cli/package.json`
+- Modify: `packages/cli/src/setup-agents.test.ts`
+- Modify: `packages/cli/src/setup-agents.ts`
+
+- [ ] **Step 1: Write the failing research-skill install tests**
+
+In `packages/cli/src/setup-agents.test.ts`, update the first test to expect `ktx-research` entries. Replace the project-scoped assertions with:
+
+```typescript
+ it('plans project-scoped CLI and research files for every target', () => {
+ expect(plannedKtxAgentFiles({ projectDir: tempDir, target: 'claude-code', scope: 'project', mode: 'cli' })).toEqual([
+ { kind: 'file', path: join(tempDir, '.claude/skills/ktx/SKILL.md'), role: 'skill' },
+ { kind: 'file', path: join(tempDir, '.claude/skills/ktx-research/SKILL.md'), role: 'research-skill' },
+ { kind: 'file', path: join(tempDir, '.claude/rules/ktx.md'), role: 'rule' },
+ ]);
+ expect(plannedKtxAgentFiles({ projectDir: tempDir, target: 'codex', scope: 'project', mode: 'cli' })).toEqual([
+ { kind: 'file', path: join(tempDir, '.agents/skills/ktx/SKILL.md'), role: 'skill' },
+ { kind: 'file', path: join(tempDir, '.agents/skills/ktx-research/SKILL.md'), role: 'research-skill' },
+ { kind: 'file', path: join(tempDir, '.codex/instructions/ktx.md'), role: 'rule' },
+ ]);
+ expect(plannedKtxAgentFiles({ projectDir: tempDir, target: 'cursor', scope: 'project', mode: 'cli' })).toEqual([
+ { kind: 'file', path: join(tempDir, '.cursor/rules/ktx.mdc') },
+ { kind: 'file', path: join(tempDir, '.cursor/rules/ktx-research.mdc'), role: 'research-skill' },
+ ]);
+ expect(plannedKtxAgentFiles({ projectDir: tempDir, target: 'opencode', scope: 'project', mode: 'cli' })).toEqual([
+ { kind: 'file', path: join(tempDir, '.opencode/commands/ktx.md') },
+ { kind: 'file', path: join(tempDir, '.opencode/commands/ktx-research.md'), role: 'research-skill' },
+ ]);
+ expect(plannedKtxAgentFiles({ projectDir: tempDir, target: 'universal', scope: 'project', mode: 'cli' })).toEqual([
+ { kind: 'file', path: join(tempDir, '.agents/skills/ktx/SKILL.md') },
+ { kind: 'file', path: join(tempDir, '.agents/skills/ktx-research/SKILL.md'), role: 'research-skill' },
+ ]);
+ });
+```
+
+Add this test after `installs target files, writes a manifest, and marks agents complete`:
+
+```typescript
+ it('installs the research skill from the runtime asset', async () => {
+ const io = makeIo();
+
+ await expect(
+ runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'universal',
+ scope: 'project',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ io.io,
+ ),
+ ).resolves.toMatchObject({ status: 'ready' });
+
+ const researchSkill = await readFile(join(tempDir, '.agents/skills/ktx-research/SKILL.md'), 'utf-8');
+ expect(researchSkill).toContain('name: ktx-research');
+ expect(researchSkill).toContain('Always run `discover_data` before writing SQL.');
+ expect(researchSkill).toContain('Treat a `dictionary_search` miss as non-authoritative.');
+ });
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts
+```
+
+Expected: FAIL because `plannedKtxAgentFiles()` does not return `ktx-research` entries and the installed research skill file does not exist.
+
+- [ ] **Step 3: Add the research skill asset**
+
+Create `packages/cli/src/skills/research/SKILL.md`:
+
+```markdown
+---
+name: ktx-research
+description: Use when answering a question that needs data from a KTX-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, or any data-investigation request. Triggers even when the user does not say "research"; if the answer requires querying a configured KTX connection, this skill applies.
+---
+
+# KTX Research Workflow
+
+You have access to KTX MCP tools for investigating data. Follow this workflow.
+
+
+1. **Discover** - call `discover_data` first to see what exists across wiki, semantic-layer sources, and raw tables. Returns refs only.
+2. **Inspect top hits in parallel** - for each promising ref:
+ - `kind: 'wiki'` -> `wiki_read`
+ - `kind: 'sl_source'`, `kind: 'sl_measure'`, or `kind: 'sl_dimension'` -> `sl_read_source`
+ - `kind: 'table'` or `kind: 'column'` -> `entity_details`
+3. **Resolve literals** - if the user named a value such as "Acme Corp" or "status=shipped", call `dictionary_search` to find which column holds it.
+4. **Query** -
+ - Prefer `sl_query` when the semantic layer covers the question.
+ - Use `sql_execution` only for questions the semantic layer does not cover.
+5. **Capture learnings** - at the end of the turn, call `memory_capture` so future turns benefit. Skip when the answer carries no durable knowledge.
+
+
+
+- Always run `discover_data` before writing SQL. Do not guess table names.
+- Prefer the semantic layer over raw SQL when both can answer the question; measures are the source of truth.
+- Read entity details before writing SQL against an unfamiliar table. Do not assume column names.
+- Treat `sql_execution` as read-only. Writes are rejected by the server.
+- Validate value mentions with `dictionary_search` instead of guessing case or spelling. Treat a `dictionary_search` miss as non-authoritative. The index is built from profile-sampled values, so a missing value may simply have been outside the sample. Follow up with `sql_execution` against the most plausible columns before concluding the value is absent.
+
+
+
+**Input:** "How many orders did Acme Corp place last month?"
+
+**Workflow:**
+1. `dictionary_search({ values: ["Acme Corp"] })` finds `customers.name`.
+2. `discover_data({ query: "orders customer monthly" })` finds an orders semantic-layer source.
+3. `sl_read_source({ connectionId: "warehouse", sourceName: "orders_facts" })` confirms the source grain, measures, and dimensions.
+4. `sl_query({ connectionId: "warehouse", measures: ["order_count"], filters: ["customer_name = 'Acme Corp'"] })` answers through the semantic layer.
+5. `memory_capture({ userMessage, assistantMessage })` captures the durable finding.
+
+---
+
+**Input:** "What columns does the events table have?"
+
+**Workflow:**
+1. `discover_data({ query: "events table" })` returns a `table` ref.
+2. `entity_details({ connectionId: "warehouse", entities: [{ table: "analytics.events" }] })` returns columns, types, and foreign keys.
+3. Answer directly. No query is needed.
+
+```
+
+- [ ] **Step 4: Copy skill assets during CLI build**
+
+Create `packages/cli/scripts/copy-runtime-assets.mjs`:
+
+```javascript
+import { cp, mkdir, rm } from 'node:fs/promises';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const packageRoot = fileURLToPath(new URL('..', import.meta.url));
+const skillsSource = join(packageRoot, 'src', 'skills');
+const skillsTarget = join(packageRoot, 'dist', 'skills');
+
+await rm(skillsTarget, { recursive: true, force: true });
+await mkdir(dirname(skillsTarget), { recursive: true });
+await cp(skillsSource, skillsTarget, { recursive: true });
+```
+
+Modify `packages/cli/package.json`:
+
+```json
+"build": "node -e \"fs.rmSync('dist', { recursive: true, force: true })\" && tsc -p tsconfig.json && node scripts/copy-runtime-assets.mjs && node ../../scripts/prepare-cli-bin.mjs"
+```
+
+- [ ] **Step 5: Add research-skill install entries and content loading**
+
+In `packages/cli/src/setup-agents.ts`, update the manifest entry role type:
+
+```typescript
+| { kind: 'file'; path: string; role?: 'skill' | 'rule' | 'research-skill' }
+```
+
+Add this helper near `ktxCliLauncher()`:
+
+```typescript
+async function readResearchSkillContent(): Promise {
+ const path = fileURLToPath(new URL('./skills/research/SKILL.md', import.meta.url));
+ const content = await readFile(path, 'utf-8');
+ return content.endsWith('\n') ? content : `${content}\n`;
+}
+```
+
+Update `plannedKtxAgentFiles()` so every supported project target includes the `ktx-research` entry shown in Step 1. For global targets, return:
+
+```typescript
+if (input.scope === 'global') {
+ if (input.target === 'claude-code') {
+ const home = process.env.HOME ?? '';
+ return [
+ { kind: 'file', path: join(home, '.claude/skills/ktx/SKILL.md'), role: 'skill' as const },
+ { kind: 'file', path: join(home, '.claude/skills/ktx-research/SKILL.md'), role: 'research-skill' as const },
+ { kind: 'file', path: join(home, '.claude/rules/ktx.md'), role: 'rule' as const },
+ ];
+ }
+ if (input.target === 'codex') {
+ const codexHome = process.env.CODEX_HOME ?? join(process.env.HOME ?? '', '.codex');
+ return [
+ { kind: 'file', path: join(codexHome, 'skills/ktx/SKILL.md'), role: 'skill' as const },
+ { kind: 'file', path: join(codexHome, 'skills/ktx-research/SKILL.md'), role: 'research-skill' as const },
+ { kind: 'file', path: join(codexHome, 'instructions/ktx.md'), role: 'rule' as const },
+ ];
+ }
+ if (input.target === 'cursor' || input.target === 'opencode') {
+ return [];
+ }
+ throw new Error(`Global ${input.target} installation is not supported; omit --global.`);
+}
+```
+
+In `installTarget()`, switch the file content selection to:
+
+```typescript
+const content =
+ entry.role === 'rule'
+ ? ruleInstructionContent({ projectDir: input.projectDir })
+ : entry.role === 'research-skill'
+ ? await readResearchSkillContent()
+ : cliInstructionContent({ projectDir: input.projectDir, launcher });
+```
+
+- [ ] **Step 6: Run tests to verify the research skill passes**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts
+```
+
+Expected: PASS for the research skill install tests. MCP config tests are added in the next task and will fail until implemented.
+
+- [ ] **Step 7: Commit**
+
+```bash
+git add packages/cli/src/skills/research/SKILL.md packages/cli/scripts/copy-runtime-assets.mjs packages/cli/package.json packages/cli/src/setup-agents.ts packages/cli/src/setup-agents.test.ts
+git commit -m "feat(cli): install KTX research skill"
+```
+
+## Task 2: Add MCP Client Config Planning And Rendering
+
+**Files:**
+- Modify: `packages/cli/src/setup-agents.test.ts`
+- Modify: `packages/cli/src/setup-agents.ts`
+
+- [ ] **Step 1: Write failing MCP config planner tests**
+
+In `packages/cli/src/setup-agents.test.ts`, add these tests before `removes only manifest-listed files`:
+
+```typescript
+ it('writes Claude Code project MCP config and tracks the json key', async () => {
+ const io = makeIo();
+
+ await expect(
+ runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'claude-code',
+ scope: 'project',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ io.io,
+ ),
+ ).resolves.toMatchObject({ status: 'ready' });
+
+ const mcpJson = JSON.parse(await readFile(join(tempDir, '.mcp.json'), 'utf-8')) as {
+ mcpServers: { ktx: { type: string; url: string; headers?: Record } };
+ };
+ expect(mcpJson.mcpServers.ktx).toEqual({ type: 'http', url: 'http://localhost:7878/mcp' });
+ expect(await readKtxAgentInstallManifest(tempDir)).toMatchObject({
+ entries: expect.arrayContaining([{ kind: 'json-key', path: join(tempDir, '.mcp.json'), jsonPath: ['mcpServers', 'ktx'] }]),
+ });
+ expect(io.stdout()).toContain('Run `ktx mcp start` to enable the configured KTX MCP server.');
+ });
+
+ it('writes Cursor project MCP config', async () => {
+ const io = makeIo();
+
+ await runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'cursor',
+ scope: 'project',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ io.io,
+ );
+
+ const cursorJson = JSON.parse(await readFile(join(tempDir, '.cursor/mcp.json'), 'utf-8')) as {
+ mcpServers: { ktx: { url: string; headers?: Record } };
+ };
+ expect(cursorJson.mcpServers.ktx).toEqual({ url: 'http://localhost:7878/mcp' });
+ });
+
+ it('prints Codex and opencode snippets without mutating printed-only config files', async () => {
+ const codexIo = makeIo();
+ await runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'codex',
+ scope: 'project',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ codexIo.io,
+ );
+ expect(codexIo.stdout()).toContain('[mcp_servers.ktx]');
+ expect(codexIo.stdout()).toContain('url = "http://localhost:7878/mcp"');
+
+ const opencodeIo = makeIo();
+ await runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'opencode',
+ scope: 'project',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ opencodeIo.io,
+ );
+ expect(opencodeIo.stdout()).toContain('"mcp"');
+ expect(opencodeIo.stdout()).toContain('"type": "remote"');
+ await expect(readFile(join(tempDir, 'opencode.json'), 'utf-8')).rejects.toThrow();
+ });
+
+ it('uses MCP daemon state for port and token metadata without rendering literal tokens', async () => {
+ await mkdir(join(tempDir, '.ktx'), { recursive: true });
+ await writeFile(
+ join(tempDir, '.ktx/mcp.json'),
+ `${JSON.stringify(
+ {
+ schemaVersion: 1,
+ pid: 999999,
+ host: '127.0.0.1',
+ port: 8787,
+ tokenAuth: true,
+ projectDir: tempDir,
+ startedAt: '2026-05-14T00:00:00.000Z',
+ logPath: join(tempDir, '.ktx/logs/mcp.log'),
+ },
+ null,
+ 2,
+ )}\n`,
+ 'utf-8',
+ );
+ const io = makeIo();
+ const previousToken = process.env.KTX_MCP_TOKEN;
+ process.env.KTX_MCP_TOKEN = 'secret-token';
+
+ try {
+ await runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'claude-code',
+ scope: 'project',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ io.io,
+ );
+
+ const rendered = JSON.stringify(JSON.parse(await readFile(join(tempDir, '.mcp.json'), 'utf-8')));
+ expect(rendered).toContain('http://127.0.0.1:8787/mcp');
+ expect(rendered).toContain('Bearer ${KTX_MCP_TOKEN}');
+ expect(rendered).not.toContain('secret-token');
+ expect(io.stdout()).toContain('Run `ktx mcp start` to enable the configured KTX MCP server.');
+ } finally {
+ process.env.KTX_MCP_TOKEN = previousToken;
+ }
+ });
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts
+```
+
+Expected: FAIL because no MCP config writer or snippet renderer exists.
+
+- [ ] **Step 3: Add JSON helpers and MCP endpoint resolution**
+
+In `packages/cli/src/setup-agents.ts`, add `existsSync` and `readKtxMcpDaemonStatus` imports:
+
+```typescript
+import { existsSync } from 'node:fs';
+import { readKtxMcpDaemonStatus } from './managed-mcp-daemon.js';
+```
+
+Add these types and helpers after `type InstallEntry`:
+
+```typescript
+interface KtxMcpEndpointInfo {
+ url: string;
+ tokenAuth: boolean;
+ running: boolean;
+}
+
+interface KtxMcpClientInstallResult {
+ entries: InstallEntry[];
+ snippets: string[];
+ notices: string[];
+}
+
+async function readJsonObject(path: string): Promise> {
+ if (!existsSync(path)) return {};
+ const parsed = JSON.parse(await readFile(path, 'utf-8')) as unknown;
+ if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) {
+ throw new Error(`Expected JSON object in ${path}`);
+ }
+ return parsed as Record;
+}
+
+function objectAtPath(root: Record, jsonPath: string[]): Record {
+ let cursor = root;
+ for (const segment of jsonPath) {
+ const current = cursor[segment];
+ if (!current || typeof current !== 'object' || Array.isArray(current)) {
+ cursor[segment] = {};
+ }
+ cursor = cursor[segment] as Record;
+ }
+ return cursor;
+}
+
+async function writeJsonKey(path: string, jsonPath: string[], value: unknown): Promise {
+ const root = await readJsonObject(path);
+ const parent = objectAtPath(root, jsonPath.slice(0, -1));
+ parent[jsonPath.at(-1) as string] = value;
+ await mkdir(dirname(path), { recursive: true });
+ await writeFile(path, `${JSON.stringify(root, null, 2)}\n`, 'utf-8');
+}
+
+async function resolveMcpEndpoint(projectDir: string): Promise {
+ const status = await readKtxMcpDaemonStatus({ projectDir }).catch(() => null);
+ if (status?.kind === 'running') {
+ return {
+ url: status.url,
+ tokenAuth: status.state.tokenAuth,
+ running: true,
+ };
+ }
+ if (status?.kind === 'stale' && status.state) {
+ return {
+ url: `http://${status.state.host}:${status.state.port}/mcp`,
+ tokenAuth: status.state.tokenAuth || Boolean(process.env.KTX_MCP_TOKEN),
+ running: false,
+ };
+ }
+ return {
+ url: 'http://localhost:7878/mcp',
+ tokenAuth: Boolean(process.env.KTX_MCP_TOKEN),
+ running: false,
+ };
+}
+```
+
+- [ ] **Step 4: Add MCP entry renderers**
+
+Add these helpers after `resolveMcpEndpoint()`:
+
+```typescript
+function tokenHeaders(endpoint: KtxMcpEndpointInfo): Record | undefined {
+ return endpoint.tokenAuth ? { Authorization: 'Bearer ${KTX_MCP_TOKEN}' } : undefined;
+}
+
+function claudeMcpEntry(endpoint: KtxMcpEndpointInfo): Record {
+ return {
+ type: 'http',
+ url: endpoint.url,
+ ...(tokenHeaders(endpoint) ? { headers: tokenHeaders(endpoint) } : {}),
+ };
+}
+
+function cursorMcpEntry(endpoint: KtxMcpEndpointInfo): Record {
+ return {
+ url: endpoint.url,
+ ...(tokenHeaders(endpoint) ? { headers: tokenHeaders(endpoint) } : {}),
+ };
+}
+
+function codexSnippet(endpoint: KtxMcpEndpointInfo): string {
+ if (endpoint.tokenAuth) {
+ return [
+ 'Codex MCP config does not currently document HTTP headers.',
+ 'Run KTX on loopback without token auth for Codex, or configure headers after Codex documents support.',
+ ].join('\n');
+ }
+ return [`[mcp_servers.ktx]`, `url = "${endpoint.url}"`].join('\n');
+}
+
+function opencodeSnippet(endpoint: KtxMcpEndpointInfo): string {
+ return JSON.stringify(
+ {
+ mcp: {
+ ktx: {
+ type: 'remote',
+ url: endpoint.url,
+ enabled: true,
+ ...(tokenHeaders(endpoint) ? { headers: tokenHeaders(endpoint) } : {}),
+ },
+ },
+ },
+ null,
+ 2,
+ );
+}
+
+function claudeConfigPath(projectDir: string, scope: KtxAgentScope): { path: string; jsonPath: string[] } {
+ const home = process.env.HOME ?? '';
+ if (scope === 'global') {
+ return { path: join(home, '.claude.json'), jsonPath: ['mcpServers', 'ktx'] };
+ }
+ if (scope === 'local') {
+ return { path: join(home, '.claude.json'), jsonPath: ['projects', resolve(projectDir), 'mcpServers', 'ktx'] };
+ }
+ return { path: join(resolve(projectDir), '.mcp.json'), jsonPath: ['mcpServers', 'ktx'] };
+}
+
+function cursorConfigPath(projectDir: string, scope: KtxAgentScope): { path: string; jsonPath: string[] } {
+ const home = process.env.HOME ?? '';
+ return {
+ path: scope === 'global' ? join(home, '.cursor/mcp.json') : join(resolve(projectDir), '.cursor/mcp.json'),
+ jsonPath: ['mcpServers', 'ktx'],
+ };
+}
+```
+
+- [ ] **Step 5: Add the MCP client install planner**
+
+Add this function after the snippet helpers:
+
+```typescript
+async function installMcpClientConfig(input: {
+ projectDir: string;
+ target: KtxAgentTarget;
+ scope: KtxAgentScope;
+}): Promise {
+ const endpoint = await resolveMcpEndpoint(input.projectDir);
+ const entries: InstallEntry[] = [];
+ const snippets: string[] = [];
+ const notices: string[] = [];
+
+ if (!endpoint.running) {
+ notices.push('Run `ktx mcp start` to enable the configured KTX MCP server.');
+ }
+
+ if (input.target === 'claude-code') {
+ const config = claudeConfigPath(input.projectDir, input.scope);
+ await writeJsonKey(config.path, config.jsonPath, claudeMcpEntry(endpoint));
+ entries.push({ kind: 'json-key', path: config.path, jsonPath: config.jsonPath });
+ } else if (input.target === 'cursor') {
+ const config = cursorConfigPath(input.projectDir, input.scope);
+ await writeJsonKey(config.path, config.jsonPath, cursorMcpEntry(endpoint));
+ entries.push({ kind: 'json-key', path: config.path, jsonPath: config.jsonPath });
+ } else if (input.target === 'codex') {
+ snippets.push(`Codex MCP snippet for ~/.codex/config.toml:\n${codexSnippet(endpoint)}`);
+ } else if (input.target === 'opencode') {
+ const path =
+ input.scope === 'global' ? '~/.config/opencode/opencode.json' : `${relative(input.projectDir, join(input.projectDir, 'opencode.json'))}`;
+ snippets.push(`opencode MCP snippet for ${path}:\n${opencodeSnippet(endpoint)}`);
+ }
+
+ return { entries, snippets, notices };
+}
+```
+
+- [ ] **Step 6: Call the MCP planner during setup**
+
+Keep `installTarget()` responsible only for writing agent files and returning those file entries.
+
+In `runKtxSetupAgentsStep()`, replace the current install loop:
+
+```typescript
+ const entries: InstallEntry[] = [];
+ for (const install of installs) entries.push(...(await installTarget({ projectDir: args.projectDir, ...install })));
+```
+
+with:
+
+```typescript
+ const entries: InstallEntry[] = [];
+ const snippets: string[] = [];
+ const notices = new Set();
+ for (const install of installs) {
+ entries.push(...(await installTarget({ projectDir: args.projectDir, ...install })));
+ const mcpResult = await installMcpClientConfig({ projectDir: args.projectDir, target: install.target, scope: install.scope });
+ entries.push(...mcpResult.entries);
+ for (const snippet of mcpResult.snippets) snippets.push(snippet);
+ for (const notice of mcpResult.notices) notices.add(notice);
+ }
+```
+
+After the install summary write:
+
+```typescript
+ for (const snippet of snippets) {
+ io.stdout.write(`\n${snippet}\n`);
+ }
+ for (const notice of notices) {
+ io.stdout.write(`\n${notice}\n`);
+ }
+```
+
+- [ ] **Step 7: Run tests to verify MCP config passes**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts
+```
+
+Expected: PASS for research-skill and MCP config tests.
+
+- [ ] **Step 8: Commit**
+
+```bash
+git add packages/cli/src/setup-agents.ts packages/cli/src/setup-agents.test.ts
+git commit -m "feat(cli): configure MCP clients in setup agents"
+```
+
+## Task 3: Add Claude Local Scope
+
+**Files:**
+- Modify: `packages/cli/src/commands/setup-commands.ts`
+- Modify: `packages/cli/src/setup-agents.ts`
+- Modify: `packages/cli/src/setup-agents.test.ts`
+- Modify: `packages/cli/src/setup.test.ts`
+- Modify: `packages/cli/src/index.test.ts`
+
+- [ ] **Step 1: Write failing local-scope tests**
+
+Add this test to `packages/cli/src/setup-agents.test.ts`:
+
+```typescript
+ it('writes Claude Code local MCP config under the project key in ~/.claude.json', async () => {
+ const home = await mkdtemp(join(tmpdir(), 'ktx-setup-agents-home-'));
+ const previousHome = process.env.HOME;
+ process.env.HOME = home;
+ try {
+ const io = makeIo();
+ await runKtxSetupAgentsStep(
+ {
+ projectDir: tempDir,
+ inputMode: 'disabled',
+ yes: true,
+ agents: true,
+ target: 'claude-code',
+ scope: 'local',
+ mode: 'cli',
+ skipAgents: false,
+ },
+ io.io,
+ );
+
+ const config = JSON.parse(await readFile(join(home, '.claude.json'), 'utf-8')) as {
+ projects: Record;
+ };
+ expect(config.projects[tempDir].mcpServers.ktx).toEqual({ type: 'http', url: 'http://localhost:7878/mcp' });
+ } finally {
+ process.env.HOME = previousHome;
+ await rm(home, { recursive: true, force: true });
+ }
+ });
+```
+
+Add these command-level tests after the existing `dispatches setup agent flags` test in `packages/cli/src/index.test.ts`:
+
+```typescript
+ it('rejects --local with non-Claude targets', async () => {
+ const setup = vi.fn(async () => 0);
+ const setupIo = makeIo();
+
+ await expect(
+ runKtxCli(
+ ['--project-dir', tempDir, 'setup', '--agents', '--target', 'cursor', '--local', '--no-input'],
+ setupIo.io,
+ { setup },
+ ),
+ ).resolves.toBe(0);
+
+ expect(setupIo.stderr()).toContain('--local is only supported with --target claude-code');
+ expect(setup).not.toHaveBeenCalled();
+ });
+
+ it('rejects --local and --global together', async () => {
+ const setup = vi.fn(async () => 0);
+ const setupIo = makeIo();
+
+ await expect(
+ runKtxCli(
+ ['--project-dir', tempDir, 'setup', '--agents', '--target', 'claude-code', '--local', '--global', '--no-input'],
+ setupIo.io,
+ { setup },
+ ),
+ ).resolves.toBe(0);
+
+ expect(setupIo.stderr()).toContain('Choose only one agent scope: --local or --global.');
+ expect(setup).not.toHaveBeenCalled();
+ });
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts src/index.test.ts
+```
+
+Expected: FAIL because `KtxAgentScope` does not include `local` and the setup command has no `--local` option.
+
+- [ ] **Step 3: Add the local scope type and command option**
+
+In `packages/cli/src/setup-agents.ts`, change:
+
+```typescript
+export type KtxAgentScope = 'project' | 'global';
+```
+
+to:
+
+```typescript
+export type KtxAgentScope = 'project' | 'global' | 'local';
+```
+
+In `packages/cli/src/commands/setup-commands.ts`, add `local` to `isOnlyAgentOptions()`:
+
+```typescript
+'local',
+```
+
+Add the command option after `--global`:
+
+```typescript
+.option('--local', 'Install Claude Code MCP config into the private per-project ~/.claude.json scope', false)
+```
+
+In the setup action before `const mode = ...`, add:
+
+```typescript
+ if (options.local && options.global) {
+ context.io.stderr.write('Choose only one agent scope: --local or --global.\n');
+ context.setExitCode(1);
+ return;
+ }
+ if (options.local && options.target && options.target !== 'claude-code') {
+ context.io.stderr.write('--local is only supported with --target claude-code.\n');
+ context.setExitCode(1);
+ return;
+ }
+```
+
+Replace:
+
+```typescript
+const resolvedAgentScope = options.global ? 'global' : 'project';
+```
+
+with:
+
+```typescript
+const resolvedAgentScope = options.local ? 'local' : options.global ? 'global' : 'project';
+```
+
+- [ ] **Step 4: Run local-scope tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts src/index.test.ts
+```
+
+Expected: PASS for the new local-scope coverage.
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add packages/cli/src/commands/setup-commands.ts packages/cli/src/setup-agents.ts packages/cli/src/setup-agents.test.ts packages/cli/src/setup.test.ts packages/cli/src/index.test.ts
+git commit -m "feat(cli): support Claude local MCP setup scope"
+```
+
+## Task 4: Final Verification
+
+**Files:**
+- Verify all files changed in Tasks 1-3.
+
+- [ ] **Step 1: Run focused CLI tests**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli exec vitest run src/setup-agents.test.ts src/commands/mcp-commands.test.ts src/mcp-http-server.test.ts src/managed-mcp-daemon.test.ts
+```
+
+Expected: all selected test files pass.
+
+- [ ] **Step 2: Run CLI type-check**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli run type-check
+```
+
+Expected: TypeScript completes with no errors.
+
+- [ ] **Step 3: Run CLI build**
+
+Run:
+
+```bash
+pnpm --filter @ktx/cli run build
+```
+
+Expected: build succeeds and `packages/cli/dist/skills/research/SKILL.md` exists.
+
+- [ ] **Step 4: Run dead-code check for the changed TypeScript surface**
+
+Run:
+
+```bash
+pnpm run dead-code
+```
+
+Expected: Biome and Knip complete with no new findings from the setup-agent changes.
+
+- [ ] **Step 5: Inspect git status**
+
+Run:
+
+```bash
+git status --short
+```
+
+Expected: only intended setup-agent, skill asset, package script, and test files are modified.
+
+## Self-Review
+
+Spec coverage:
+
+- Covers `ktx-research` skill installation paths for Claude Code, Codex, Cursor, opencode, and universal project targets.
+- Covers Claude Code and Cursor JSON MCP writers.
+- Covers Codex and opencode printed snippets.
+- Covers token handling with `${KTX_MCP_TOKEN}` and no literal token rendering.
+- Covers `.ktx/mcp.json` port selection and daemon-start hint.
+- Covers manifest tracking for written JSON keys and removal through existing `json-key` cleanup.
+
+Known v1 gap not covered by this plan:
+
+- Ingest warehouse-verification contract convergence from `connectionName` to `connectionId`, shared service extraction, and caller/test updates remains v1-blocking and needs its own focused plan after this setup-agent slice lands.
diff --git a/docs/superpowers/plans/2026-05-14-research-agent-mcp-sql-execution-foundation.md b/docs/superpowers/plans/2026-05-14-research-agent-mcp-sql-execution-foundation.md
new file mode 100644
index 00000000..94611b90
--- /dev/null
+++ b/docs/superpowers/plans/2026-05-14-research-agent-mcp-sql-execution-foundation.md
@@ -0,0 +1,999 @@
+# Research Agent MCP SQL Execution Foundation Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Add the parser-backed safety prerequisite and MCP `sql_execution` surface needed before the research-agent MCP tools can safely execute warehouse SQL.
+
+**Architecture:** Keep connector `executeReadOnly()` as the execution path, but make the MCP adapter require a sqlglot-backed validator before calling any connector. Extend the existing Python SQL-analysis daemon with a read-only validation endpoint, expose it through the TypeScript SQL-analysis port, then register an MCP `sql_execution` tool only when the host provides that validator and a local scan connector factory.
+
+**Tech Stack:** TypeScript, Vitest, Zod, Python, pytest, FastAPI, sqlglot, KTX MCP context ports, KTX scan connectors.
+
+---
+
+## Audit Summary
+
+Original spec: `docs/superpowers/specs/2026-05-14-research-agent-mcp-tools-design.md`
+
+Implemented plans that overlap with the spec:
+
+- `docs/superpowers/plans/2026-05-11-managed-agent-mcp-semantic-runtime.md` is implemented for the existing in-process MCP semantic runtime. Current evidence: `packages/context/src/mcp/context-tools.ts` registers `connection_*`, `wiki_*`, `sl_*`, `ingest_*`, and `scan_*` tools, and `packages/context/src/mcp/local-project-ports.ts` provides local ports for those surfaces.
+- `docs/superpowers/plans/2026-05-12-warehouse-verification-tools.md` plus its May 12 and May 13 closure plans are implemented for ingest-only warehouse verification. Current evidence: `packages/context/src/ingest/tools/warehouse-verification/{discover-data,entity-details,sql-execution,warehouse-catalog.service}.ts` exist and are wired for ingest agents.
+
+V1-blocking gaps remaining against the original spec:
+
+- The public MCP research tools are not registered. `KtxMcpContextPorts` has no `discover`, `entityDetails`, `dictionarySearch`, or `sqlExecution` ports.
+- The existing ingest `discover_data`, `entity_details`, and `sql_execution` tools use `connectionName`, `targets`, and `rowLimit`, and return markdown plus structured output. The spec requires MCP-shaped `connectionId`, `entities` / `maxRows`, and pure structured outputs.
+- `sql_execution` cannot be safely exposed yet: `packages/context/src/connections/read-only-sql.ts` still uses first-token regex checks. The spec requires a sqlglot/AST-backed guard or connector-side read-only session before MCP registration.
+- `packages/context/src/scan/entity-details.ts`, `packages/context/src/sl/dictionary-search.ts`, and `packages/context/src/search/discover.ts` do not exist.
+- `WarehouseCatalogService` caches by connection only and does not invalidate when latest scan artifact identity advances.
+- `dictionary_search` has no MCP service, no coverage metadata, and no per-connection miss reasons.
+- `discover_data` has no unified ranked MCP result shape with `summary`, `snippet`, `matchedOn`, `kind`, `tableRef`, and RRF fusion across wiki, SL, and raw schema.
+- `ktx mcp start|stop|status|logs` does not exist, and no HTTP Streamable MCP daemon exists.
+- `ktx setup-agents` installs only the existing `ktx` CLI skill/rules; it does not install `ktx-research` or MCP client config entries/snippets.
+
+Non-blocking or explicitly out-of-scope gaps:
+
+- Python code execution over MCP.
+- Stdio MCP transport.
+- OS-level auto-start.
+- Native TLS, audit logging, rate limiting, per-tool authorization, and multi-project daemon routing.
+- Streaming SQL results.
+- Full DDL-style ingest `entity_details` markdown formatting and hard write-time validation in ingest writer tools.
+
+This plan covers the first prerequisite blocker: parser-backed SQL validation and MCP `sql_execution`. The remaining v1-blocking tool, daemon, and setup-agent work stays visible for subsequent plans.
+
+## File Structure
+
+Create no new files.
+
+Modify these files:
+
+- `python/ktx-daemon/src/ktx_daemon/sql_analysis.py`: add a sqlglot-backed read-only SQL validator.
+- `python/ktx-daemon/src/ktx_daemon/app.py`: expose `POST /sql/validate-read-only`.
+- `python/ktx-daemon/tests/test_sql_analysis.py`: cover accepted SELECT/WITH and rejected CTE-DML, multi-statement, command, pragma, and parse-error payloads.
+- `python/ktx-daemon/tests/test_app.py`: cover the new HTTP endpoint.
+- `packages/context/src/sql-analysis/ports.ts`: add `validateReadOnly()` to `SqlAnalysisPort`.
+- `packages/context/src/sql-analysis/http-sql-analysis-port.ts`: call `/sql/validate-read-only` and map its response.
+- `packages/context/src/sql-analysis/http-sql-analysis-port.test.ts`: cover request and response mapping.
+- `packages/context/src/mcp/types.ts`: add `KtxSqlExecutionMcpPort` and `sqlExecution` to `KtxMcpContextPorts`.
+- `packages/context/src/mcp/context-tools.ts`: add the MCP `sql_execution` schema and registration.
+- `packages/context/src/mcp/server.test.ts`: assert MCP registration and structured output for `sql_execution`.
+- `packages/context/src/mcp/local-project-ports.ts`: expose local project SQL execution only when both `SqlAnalysisPort.validateReadOnly()` and a local scan connector factory are available.
+- `packages/context/src/mcp/local-project-ports.test.ts`: cover validator success and validator rejection.
+
+### Task 1: Add sqlglot Read-Only Validation
+
+**Files:**
+- Modify: `python/ktx-daemon/tests/test_sql_analysis.py`
+- Modify: `python/ktx-daemon/src/ktx_daemon/sql_analysis.py`
+- Modify: `python/ktx-daemon/tests/test_app.py`
+- Modify: `python/ktx-daemon/src/ktx_daemon/app.py`
+
+- [ ] **Step 1: Write failing sqlglot validator tests**
+
+In `python/ktx-daemon/tests/test_sql_analysis.py`, update the import block to include the new request model and function:
+
+```python
+from ktx_daemon.sql_analysis import (
+ AnalyzeSqlBatchItem,
+ AnalyzeSqlBatchRequest,
+ ValidateReadOnlySqlRequest,
+ _columns_from_nodes,
+ analyze_sql_batch_response,
+ validate_read_only_sql_response,
+)
+```
+
+Add these tests after `test_columns_from_nodes_ignores_non_expression_clause_values`:
+
+```python
+def test_validate_read_only_sql_accepts_select_and_with_queries() -> None:
+ select_response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(
+ dialect="postgres",
+ sql="select id, status from public.orders where status = 'paid'",
+ )
+ )
+ with_response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(
+ dialect="postgres",
+ sql=(
+ "with paid as (select * from public.orders where status = 'paid') "
+ "select count(*) from paid"
+ ),
+ )
+ )
+
+ assert select_response.ok is True
+ assert select_response.error is None
+ assert with_response.ok is True
+ assert with_response.error is None
+
+
+def test_validate_read_only_sql_rejects_cte_dml() -> None:
+ response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(
+ dialect="postgres",
+ sql="with x as (insert into audit.events values (1) returning *) select * from x",
+ )
+ )
+
+ assert response.ok is False
+ assert response.error == "SQL contains read/write operation: Insert"
+
+
+def test_validate_read_only_sql_rejects_multi_statement_payloads() -> None:
+ response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(
+ dialect="postgres",
+ sql="select * from public.orders; delete from public.orders",
+ )
+ )
+
+ assert response.ok is False
+ assert response.error == "Only one SQL statement can be executed."
+
+
+def test_validate_read_only_sql_rejects_commands_and_pragmas() -> None:
+ command_response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(dialect="postgres", sql="call refresh_stats()")
+ )
+ pragma_response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(dialect="sqlite", sql="pragma table_info(users)")
+ )
+
+ assert command_response.ok is False
+ assert command_response.error == "SQL contains read/write operation: Command"
+ assert pragma_response.ok is False
+ assert pragma_response.error == "SQL contains read/write operation: Pragma"
+
+
+def test_validate_read_only_sql_reports_parse_errors() -> None:
+ response = validate_read_only_sql_response(
+ ValidateReadOnlySqlRequest(dialect="postgres", sql="select * from where")
+ )
+
+ assert response.ok is False
+ assert response.error is not None
+ assert "Invalid expression" in response.error
+```
+
+- [ ] **Step 2: Run failing Python validator tests**
+
+Run:
+
+```bash
+source .venv/bin/activate && uv run pytest python/ktx-daemon/tests/test_sql_analysis.py -q
+```
+
+Expected: FAIL with an import error for `ValidateReadOnlySqlRequest` or `validate_read_only_sql_response`.
+
+- [ ] **Step 3: Implement the sqlglot validator**
+
+In `python/ktx-daemon/src/ktx_daemon/sql_analysis.py`, add this model after `AnalyzeSqlBatchResponse`:
+
+```python
+class ValidateReadOnlySqlRequest(BaseModel):
+ dialect: str
+ sql: str
+
+
+class ValidateReadOnlySqlResponse(BaseModel):
+ ok: bool
+ error: str | None = None
+```
+
+Add this constant after the model definitions:
+
+```python
+_READ_ONLY_ROOT_TYPES = (exp.Select, exp.Union)
+_READ_WRITE_NODE_TYPES = (
+ exp.Alter,
+ exp.Analyze,
+ exp.Cache,
+ exp.Command,
+ exp.Commit,
+ exp.Copy,
+ exp.Create,
+ exp.Delete,
+ exp.Describe,
+ exp.Drop,
+ exp.Execute,
+ exp.Grant,
+ exp.Insert,
+ exp.Merge,
+ exp.Pragma,
+ exp.Refresh,
+ exp.Revoke,
+ exp.Rollback,
+ exp.Set,
+ exp.Show,
+ exp.Transaction,
+ exp.TruncateTable,
+ exp.Uncache,
+ exp.Update,
+ exp.Use,
+)
+```
+
+Add this function after `_analyze_payload`:
+
+```python
+def validate_read_only_sql_response(
+ request: ValidateReadOnlySqlRequest,
+) -> ValidateReadOnlySqlResponse:
+ try:
+ statements = sqlglot.parse(request.sql, read=request.dialect)
+ except sqlglot.errors.SqlglotError as exc:
+ return ValidateReadOnlySqlResponse(ok=False, error=str(exc))
+
+ if len(statements) != 1:
+ return ValidateReadOnlySqlResponse(
+ ok=False,
+ error="Only one SQL statement can be executed.",
+ )
+
+ tree = statements[0]
+ if tree is None:
+ return ValidateReadOnlySqlResponse(ok=False, error="SQL did not parse to a statement.")
+ if not isinstance(tree, _READ_ONLY_ROOT_TYPES):
+ return ValidateReadOnlySqlResponse(
+ ok=False,
+ error=f"SQL contains read/write operation: {type(tree).__name__}",
+ )
+
+ for node in tree.walk():
+ if isinstance(node, _READ_WRITE_NODE_TYPES):
+ return ValidateReadOnlySqlResponse(
+ ok=False,
+ error=f"SQL contains read/write operation: {type(node).__name__}",
+ )
+
+ return ValidateReadOnlySqlResponse(ok=True, error=None)
+```
+
+- [ ] **Step 4: Run Python validator tests**
+
+Run:
+
+```bash
+source .venv/bin/activate && uv run pytest python/ktx-daemon/tests/test_sql_analysis.py -q
+```
+
+Expected: PASS.
+
+- [ ] **Step 5: Write failing HTTP endpoint test**
+
+In `python/ktx-daemon/tests/test_app.py`, add this test after `test_sql_parse_table_identifier_endpoint`:
+
+```python
+def test_sql_validate_read_only_endpoint() -> None:
+ client = TestClient(create_app())
+
+ ok_response = client.post(
+ "/sql/validate-read-only",
+ json={"dialect": "postgres", "sql": "select * from public.orders"},
+ )
+ bad_response = client.post(
+ "/sql/validate-read-only",
+ json={
+ "dialect": "postgres",
+ "sql": "with x as (insert into audit.events values (1) returning *) select * from x",
+ },
+ )
+
+ assert ok_response.status_code == 200
+ assert ok_response.json() == {"ok": True, "error": None}
+ assert bad_response.status_code == 200
+ assert bad_response.json() == {
+ "ok": False,
+ "error": "SQL contains read/write operation: Insert",
+ }
+```
+
+- [ ] **Step 6: Run failing HTTP endpoint test**
+
+Run:
+
+```bash
+source .venv/bin/activate && uv run pytest python/ktx-daemon/tests/test_app.py -q -k validate_read_only
+```
+
+Expected: FAIL with HTTP 404 for `/sql/validate-read-only`.
+
+- [ ] **Step 7: Register the HTTP endpoint**
+
+In `python/ktx-daemon/src/ktx_daemon/app.py`, update the SQL-analysis import to include the new symbols:
+
+```python
+from ktx_daemon.sql_analysis import (
+ AnalyzeSqlBatchRequest,
+ AnalyzeSqlBatchResponse,
+ ValidateReadOnlySqlRequest,
+ ValidateReadOnlySqlResponse,
+ analyze_sql_batch_response,
+ validate_read_only_sql_response,
+)
+```
+
+Add this endpoint immediately before the existing `@app.post("/sql/analyze-batch", ...)` route:
+
+```python
+ @app.post("/sql/validate-read-only", response_model=ValidateReadOnlySqlResponse)
+ async def sql_validate_read_only(
+ request: ValidateReadOnlySqlRequest,
+ ) -> ValidateReadOnlySqlResponse:
+ try:
+ return validate_read_only_sql_response(request)
+ except Exception as error:
+ logger.exception("SQL read-only validation failed: %s", error)
+ raise HTTPException(
+ status_code=500,
+ detail=f"SQL read-only validation failed: {error}",
+ ) from error
+```
+
+- [ ] **Step 8: Run Python HTTP endpoint test**
+
+Run:
+
+```bash
+source .venv/bin/activate && uv run pytest python/ktx-daemon/tests/test_app.py -q -k validate_read_only
+```
+
+Expected: PASS.
+
+- [ ] **Step 9: Commit Python validator**
+
+Run:
+
+```bash
+git add python/ktx-daemon/src/ktx_daemon/sql_analysis.py python/ktx-daemon/src/ktx_daemon/app.py python/ktx-daemon/tests/test_sql_analysis.py python/ktx-daemon/tests/test_app.py
+git commit -m "feat(daemon): validate read-only SQL with sqlglot"
+```
+
+### Task 2: Expose Read-Only Validation Through the TypeScript SQL-Analysis Port
+
+**Files:**
+- Modify: `packages/context/src/sql-analysis/ports.ts`
+- Modify: `packages/context/src/sql-analysis/http-sql-analysis-port.test.ts`
+- Modify: `packages/context/src/sql-analysis/http-sql-analysis-port.ts`
+
+- [ ] **Step 1: Add the port contract**
+
+In `packages/context/src/sql-analysis/ports.ts`, add this interface after `SqlAnalysisBatchResult`:
+
+```typescript
+export interface SqlReadOnlyValidationResult {
+ ok: boolean;
+ error?: string | null;
+}
+```
+
+Update `SqlAnalysisPort` to include the new method:
+
+```typescript
+export interface SqlAnalysisPort {
+ analyzeForFingerprint(sql: string, dialect: SqlAnalysisDialect): Promise;
+ analyzeBatch(
+ items: SqlAnalysisBatchItem[],
+ dialect: SqlAnalysisDialect,
+ ): Promise]