Commit graph

6 commits

Author SHA1 Message Date
Andrey Avtomonov
b759a4a286
feat(mcp):added MCP server (#97)
* docs(specs): design research-agent MCP tools and ktx mcp daemon

Adds the 2026-05-14 design spec for exposing four new MCP tools
(discover_data, entity_details, dictionary_search, sql_execution),
shipping a ktx-research skill, and introducing an HTTP-only ktx mcp
daemon so external agents can use KTX as a research-capable context
layer.

* Refine research-agent MCP tools spec after adversarial review iteration 1

* Refine research-agent MCP tools spec after adversarial review iteration 2

* Refine research-agent MCP tools spec after adversarial review iteration 3

* Refine spec: drop connectionName compat carve-out and ground summary/snippet provenance per kind

* feat(daemon): validate read-only SQL with sqlglot

* feat(context): expose read-only SQL validation port

* feat(context): register MCP sql execution tool

* feat(context): execute MCP SQL through validated connector path

* test(context): update SQL analysis port fixtures

* docs: add research-agent MCP sql execution foundation plan

* feat(context): add scan-backed entity details service

* feat(context): register MCP entity details tool

* feat(context): expose local MCP entity details

* test(context): align entity details scan fixtures

* docs: add research-agent MCP entity_details plan

* feat(context): add dictionary search service

* feat(context): register MCP dictionary search tool

* feat(context): expose local MCP dictionary search

* docs: add research-agent MCP dictionary_search plan

* feat: add MCP discover data service

* feat: expose discover data MCP tool

* feat: wire local discover data MCP port

* docs: add research-agent MCP discover_data plan

* feat(cli): add mcp http security helpers

* feat(cli): host mcp over streamable http

* feat(cli): manage mcp daemon lifecycle

* feat(cli): add ktx mcp commands

* fix(cli): stabilize mcp daemon verification

* docs: add research-agent MCP http daemon plan

* feat(cli): install KTX research skill

* feat(cli): configure MCP clients in setup agents

* feat(cli): support Claude local MCP setup scope

* docs: add research-agent MCP setup-agents plan

* refactor(context): use connectionId in warehouse verification tools

* docs(context): update ingest verification prompts for connectionId

* docs: add research-agent MCP ingest contract convergence plan

* chore: build runtime artifacts in conductor setup

---------

Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-15 02:35:09 +02:00
Andrey Avtomonov
c7c5f63a66
feat(cli): extend ktx connection test to every supported driver (#92)
* feat(cli): extend `ktx connection test` to every supported driver

Dispatch by driver: native DBs now call `connector.testConnection()`
(was `introspect(dryRun)`), looker/notion/metabase hit their auth
endpoints, and dbt/metricflow/lookml run `git ls-remote` via the
existing `testRepoConnection` helper. Unknown drivers exit 1 with a
listing of supported ones.

* feat(cli): add `ktx connection test --all` summary list

Tests every configured connection in parallel and renders a single
Clack-style list (◇/│/◆/└, green ✓ / red ✗) consistent with sl list,
with per-row detail and a passed/failed footer. Exits non-zero if any
connection fails. Single-id `ktx connection test` output is preserved.

* fix(cli): read metabase status url from api_url

`ktx status` was probing `url` / `base_url` on metabase connections, but
ktx.yaml stores it as `api_url`, so the field always reported "url not
set". Read `api_url` directly and align the warning text with the actual
key.
2026-05-14 16:21:18 +02:00
Andrey Avtomonov
49f1e2720e
fix(llm): wire prompt caching through all Anthropic call sites (#90)
* fix(llm): wire prompt caching through all Anthropic call sites

- page-triage classifier + light-extraction now put the static skill
  prompt in `system:` so the per-document caches hit instead of
  re-sending boilerplate in the user message every call.
- Description generation builders return `{ system, user }` with
  instruction text + word limit moved into the cacheable system.
- Relationship-LLM proposal framing moved to `system:`.
- `KtxMessageBuilder.wrapSimple` skips the history breakpoint for
  single-message calls (cache write that could never be reused).
- Gateway backend now sets `anthropic-beta: extended-cache-ttl-2025-04-11`
  so 1h TTLs don't silently downgrade to 5m on Gateway routes.

* fix(llm): keep wrapSimple history breakpoint so multi-step agent loops cache

Reverts the wrapSimple `messages.length > 1` guard from the prior commit.
agent-runner uses wrapSimple with a single user message, but generateText
runs a multi-step tool loop inside it — the cache marker on the first user
message is reused by every subsequent step, so it isn't waste.
The release validator (scripts/validate-llm-debug-jsonl.mjs) also requires
a `message-part` marker target in captured debug JSONL.
2026-05-14 15:36:27 +02:00
Luca Martial
52ddb061a4 Add scan table filtering 2026-05-12 18:22:03 -07:00
Andrey Avtomonov
3ce510b55b rename klo to ktx 2026-05-10 23:51:24 +02:00
Andrey Avtomonov
1a42152e6f Initial open-source release 2026-05-10 23:12:26 +02:00