2026-05-10 23:12:26 +02:00
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
|
|
import io
|
|
|
|
|
import json
|
|
|
|
|
import os
|
|
|
|
|
import subprocess
|
|
|
|
|
import sys
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
from typing import Any
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ORDERS_SOURCE = {
|
|
|
|
|
"name": "orders",
|
|
|
|
|
"table": "public.orders",
|
|
|
|
|
"grain": ["id"],
|
|
|
|
|
"columns": [
|
|
|
|
|
{"name": "id", "type": "number"},
|
|
|
|
|
{"name": "status", "type": "string"},
|
|
|
|
|
{"name": "amount", "type": "number"},
|
|
|
|
|
],
|
|
|
|
|
"joins": [],
|
|
|
|
|
"measures": [{"name": "order_count", "expr": "count(*)"}],
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def run_daemon_command(
|
|
|
|
|
command: str, payload: dict[str, object]
|
|
|
|
|
) -> subprocess.CompletedProcess[str]:
|
|
|
|
|
env = os.environ.copy()
|
|
|
|
|
src_path = str(Path(__file__).resolve().parents[1] / "src")
|
|
|
|
|
env["PYTHONPATH"] = src_path + os.pathsep + env.get("PYTHONPATH", "")
|
|
|
|
|
return subprocess.run(
|
2026-05-10 23:51:24 +02:00
|
|
|
[sys.executable, "-m", "ktx_daemon", command],
|
2026-05-10 23:12:26 +02:00
|
|
|
input=json.dumps(payload),
|
|
|
|
|
text=True,
|
|
|
|
|
capture_output=True,
|
|
|
|
|
check=False,
|
|
|
|
|
env=env,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_semantic_query_command_reads_stdin_and_writes_json() -> None:
|
|
|
|
|
result = run_daemon_command(
|
|
|
|
|
"semantic-query",
|
|
|
|
|
{
|
|
|
|
|
"sources": [ORDERS_SOURCE],
|
|
|
|
|
"dialect": "postgres",
|
|
|
|
|
"query": {
|
|
|
|
|
"measures": ["orders.order_count"],
|
|
|
|
|
"dimensions": ["orders.status"],
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert result.returncode == 0, result.stderr
|
|
|
|
|
parsed = json.loads(result.stdout)
|
|
|
|
|
assert "public.orders" in parsed["sql"]
|
|
|
|
|
assert parsed["columns"][0]["name"] == "orders.status"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_semantic_validate_command_reads_stdin_and_writes_json() -> None:
|
|
|
|
|
result = run_daemon_command(
|
|
|
|
|
"semantic-validate",
|
|
|
|
|
{"sources": [ORDERS_SOURCE], "dialect": "postgres"},
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert result.returncode == 0, result.stderr
|
|
|
|
|
parsed = json.loads(result.stdout)
|
|
|
|
|
assert parsed == {
|
|
|
|
|
"valid": True,
|
|
|
|
|
"errors": [],
|
|
|
|
|
"warnings": [],
|
|
|
|
|
"per_source_warnings": {},
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_command_returns_nonzero_for_invalid_json() -> None:
|
|
|
|
|
env = os.environ.copy()
|
|
|
|
|
src_path = str(Path(__file__).resolve().parents[1] / "src")
|
|
|
|
|
env["PYTHONPATH"] = src_path + os.pathsep + env.get("PYTHONPATH", "")
|
|
|
|
|
result = subprocess.run(
|
2026-05-10 23:51:24 +02:00
|
|
|
[sys.executable, "-m", "ktx_daemon", "semantic-query"],
|
2026-05-10 23:12:26 +02:00
|
|
|
input="{",
|
|
|
|
|
text=True,
|
|
|
|
|
capture_output=True,
|
|
|
|
|
check=False,
|
|
|
|
|
env=env,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert result.returncode == 1
|
|
|
|
|
assert "Expecting property name enclosed in double quotes" in result.stderr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_serve_http_command_starts_uvicorn_without_reading_stdin(
|
|
|
|
|
monkeypatch,
|
|
|
|
|
) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
calls: list[dict[str, object]] = []
|
|
|
|
|
|
|
|
|
|
class FailingStdin:
|
|
|
|
|
def read(self) -> str:
|
|
|
|
|
raise AssertionError("serve-http must not read stdin JSON")
|
|
|
|
|
|
|
|
|
|
def fake_run_http_server(
|
|
|
|
|
*,
|
|
|
|
|
host: str,
|
|
|
|
|
port: int,
|
|
|
|
|
log_level: str,
|
|
|
|
|
enable_code_execution: bool,
|
|
|
|
|
) -> None:
|
|
|
|
|
calls.append(
|
|
|
|
|
{
|
|
|
|
|
"host": host,
|
|
|
|
|
"port": port,
|
|
|
|
|
"log_level": log_level,
|
|
|
|
|
"enable_code_execution": enable_code_execution,
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(sys, "stdin", FailingStdin())
|
|
|
|
|
monkeypatch.setattr(daemon_main, "run_http_server", fake_run_http_server)
|
|
|
|
|
|
|
|
|
|
assert (
|
|
|
|
|
daemon_main.main(
|
|
|
|
|
[
|
|
|
|
|
"serve-http",
|
|
|
|
|
"--host",
|
|
|
|
|
"127.0.0.1",
|
|
|
|
|
"--port",
|
|
|
|
|
"9191",
|
|
|
|
|
"--log-level",
|
|
|
|
|
"warning",
|
|
|
|
|
]
|
|
|
|
|
)
|
|
|
|
|
== 0
|
|
|
|
|
)
|
|
|
|
|
assert calls == [
|
|
|
|
|
{
|
|
|
|
|
"host": "127.0.0.1",
|
|
|
|
|
"port": 9191,
|
|
|
|
|
"log_level": "warning",
|
|
|
|
|
"enable_code_execution": False,
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_serve_http_command_defaults_to_loopback(monkeypatch) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
calls: list[dict[str, object]] = []
|
|
|
|
|
|
|
|
|
|
def fake_run_http_server(
|
|
|
|
|
*,
|
|
|
|
|
host: str,
|
|
|
|
|
port: int,
|
|
|
|
|
log_level: str,
|
|
|
|
|
enable_code_execution: bool,
|
|
|
|
|
) -> None:
|
|
|
|
|
calls.append(
|
|
|
|
|
{
|
|
|
|
|
"host": host,
|
|
|
|
|
"port": port,
|
|
|
|
|
"log_level": log_level,
|
|
|
|
|
"enable_code_execution": enable_code_execution,
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(daemon_main, "run_http_server", fake_run_http_server)
|
|
|
|
|
|
|
|
|
|
assert daemon_main.main(["serve-http"]) == 0
|
|
|
|
|
assert calls == [
|
|
|
|
|
{
|
|
|
|
|
"host": "127.0.0.1",
|
|
|
|
|
"port": 8765,
|
|
|
|
|
"log_level": "info",
|
|
|
|
|
"enable_code_execution": False,
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_serve_http_command_can_enable_code_execution(monkeypatch) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
calls: list[dict[str, object]] = []
|
|
|
|
|
|
|
|
|
|
def fake_run_http_server(
|
|
|
|
|
*,
|
|
|
|
|
host: str,
|
|
|
|
|
port: int,
|
|
|
|
|
log_level: str,
|
|
|
|
|
enable_code_execution: bool,
|
|
|
|
|
) -> None:
|
|
|
|
|
calls.append(
|
|
|
|
|
{
|
|
|
|
|
"host": host,
|
|
|
|
|
"port": port,
|
|
|
|
|
"log_level": log_level,
|
|
|
|
|
"enable_code_execution": enable_code_execution,
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(daemon_main, "run_http_server", fake_run_http_server)
|
|
|
|
|
|
|
|
|
|
assert daemon_main.main(["serve-http", "--enable-code-execution"]) == 0
|
|
|
|
|
assert calls == [
|
|
|
|
|
{
|
|
|
|
|
"host": "127.0.0.1",
|
|
|
|
|
"port": 8765,
|
|
|
|
|
"log_level": "info",
|
|
|
|
|
"enable_code_execution": True,
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_lookml_parse_command_reads_stdin_and_writes_json() -> None:
|
|
|
|
|
result = run_daemon_command(
|
|
|
|
|
"lookml-parse",
|
|
|
|
|
{
|
|
|
|
|
"files": [
|
|
|
|
|
{
|
|
|
|
|
"path": "views/orders.view.lkml",
|
|
|
|
|
"content": """
|
|
|
|
|
view: orders {
|
|
|
|
|
sql_table_name: public.orders ;;
|
|
|
|
|
|
|
|
|
|
dimension: id {
|
|
|
|
|
primary_key: yes
|
|
|
|
|
type: number
|
|
|
|
|
sql: ${TABLE}.id ;;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
measure: order_count {
|
|
|
|
|
type: count
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
""",
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"dialect": "postgres",
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert result.returncode == 0, result.stderr
|
|
|
|
|
parsed = json.loads(result.stdout)
|
|
|
|
|
assert parsed["views"][0]["name"] == "orders"
|
|
|
|
|
assert parsed["views"][0]["table_ref"] == "public.orders"
|
|
|
|
|
assert parsed["views"][0]["measures"][0]["expr"] == "count(*)"
|
|
|
|
|
assert parsed["joins"] == []
|
|
|
|
|
assert parsed["skipped_views"] == []
|
|
|
|
|
assert parsed["warnings"] == []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_semantic_generate_sources_command_reads_stdin_and_writes_json() -> None:
|
|
|
|
|
result = run_daemon_command(
|
|
|
|
|
"semantic-generate-sources",
|
|
|
|
|
{
|
|
|
|
|
"tables": [
|
|
|
|
|
{
|
|
|
|
|
"name": "orders",
|
|
|
|
|
"db": "public",
|
|
|
|
|
"columns": [
|
|
|
|
|
{"name": "id", "type": "integer", "primary_key": True},
|
|
|
|
|
{"name": "amount", "type": "decimal"},
|
|
|
|
|
],
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"links": [],
|
|
|
|
|
"dialect": "postgres",
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert result.returncode == 0, result.stderr
|
|
|
|
|
parsed = json.loads(result.stdout)
|
|
|
|
|
assert parsed["source_count"] == 1
|
|
|
|
|
assert parsed["sources"][0]["name"] == "orders"
|
|
|
|
|
assert parsed["sources"][0]["table"] == "public.orders"
|
|
|
|
|
assert parsed["sources"][0]["measures"] == [
|
|
|
|
|
{
|
|
|
|
|
"name": "record_count",
|
|
|
|
|
"expr": "count(id)",
|
|
|
|
|
"segments": [],
|
|
|
|
|
"description": "Count of orders records",
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "total_amount",
|
|
|
|
|
"expr": "sum(amount)",
|
|
|
|
|
"segments": [],
|
|
|
|
|
"description": "Sum of amount",
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"name": "avg_amount",
|
|
|
|
|
"expr": "avg(amount)",
|
|
|
|
|
"segments": [],
|
|
|
|
|
"description": "Average of amount",
|
|
|
|
|
},
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_database_introspect_command_reads_stdin_and_writes_json(
|
|
|
|
|
monkeypatch, capsys
|
|
|
|
|
) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
|
|
|
|
from ktx_daemon.database_introspection import (
|
2026-05-10 23:12:26 +02:00
|
|
|
DatabaseIntrospectionResponse,
|
|
|
|
|
LiveDatabaseColumn,
|
|
|
|
|
LiveDatabaseTable,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
def fake_introspect(request):
|
|
|
|
|
assert request.connection_id == "warehouse"
|
|
|
|
|
assert request.driver == "postgres"
|
|
|
|
|
assert request.schemas == ["public"]
|
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204)
* feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure
Snowflake setup previously asked for a single schema as free text, then
ran a multiselect against the discovered schemas — two schema questions
back-to-back, with the first being only a session bootstrap. The SDK's
`schema` is optional, so the bootstrap step is unnecessary.
- Remove the free-text Snowflake schema prompt; only pass `schema` to
snowflake-sdk when one is configured.
- When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the
user for a comma-separated list, persist it as `schema_names`, and use
it as both the table-list filter and the multiselect default. Applies
to every driver with a scope-discovery spec, not just Snowflake.
- Update docs to lead with `schema_names`; keep `schema_name` as a
documented single-schema shorthand.
* fix(snowflake): keep introspecting when primary-key discovery is denied
The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and
INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the
connection role may not have. Previously a 'SQL compilation error:
Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist
or not authorized' aborted the entire introspect — schemas, columns,
and row counts were all discarded over a missing nice-to-have.
Wrap the constraint query in try/catch, log a one-line warning per
schema, and return an empty PK map. Columns end up with
primaryKey=false; relationship inference still has FK and profiling
to fall back on.
* fix(scan): unblock relationship discovery on Snowflake
Two adjacent bugs prevented the scan's relationship pipeline from producing
any joins on a Snowflake warehouse:
- relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch
for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table
profile query failed with "Unknown function GROUP_CONCAT". Add an explicit
Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter
(Snowflake requires the delimiter to be a constant, so CHR(31) is rejected).
- description-generation.ts destructured `connector.sampleTable` and
`connector.sampleColumn` into bare locals, losing the `this` binding when
the class-method connectors (Snowflake, Postgres, MySQL) were invoked.
Every sample call threw "Cannot read properties of undefined (reading
'assertConnection')" and degraded LLM descriptions to metadata-only
prompts. Call the methods through the connector instead.
Without these, even after the primary-key probe is allowed to fail softly,
the scan ends up with 0 validated relationships and an empty `joins:` block
in every shard YAML.
* test(scan): cover table-ref helpers
* feat(scan): plumb tableScope through live-database introspection port
* feat(scan): apply tableScope during metadata fetch
* feat(scan): enforce table scope at fetch boundary
* feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206)
* feat(cli): add RSA key-pair auth option to Snowflake setup wizard
Extends the interactive Snowflake setup flow with an authentication-method
prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key
path (env/file/absolute) and an optional passphrase; the resulting connection
config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead
of `password`.
* feat(scan): pool Snowflake sessions
* fix(scan): reuse structural snapshots and cleanup connectors
* feat(scan): parallelize relationship profiling
* feat(scan): batch table description generation
* docs: document Snowflake ingest concurrency knobs
* fix(scan): close Snowflake ingest perf verification gaps
* fix(scan): keep batched description failure bounded
* feat(scan): dispatch query-history probes by connection driver
Extract historic-sql dialect resolution into a shared helper so the
status-project readiness check and the local ingest factory agree on
which connections enable query history and which probe to run. The
status command now picks the postgres/snowflake/bigquery probe based on
the connection's driver instead of always reporting against postgres,
which previously caused snowflake connections with queryHistory.enabled
to surface a misleading "driver is snowflake" failure.
Also drops a noisy console.warn from Snowflake primary-key discovery —
INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only
roles and the FK + profiling paths handle the empty PK map already.
* fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject
The Claude Code agent SDK announces an internal pseudo-tool named
StructuredOutput in the system/init message whenever outputFormat is set
to { type: 'json_schema' }. The runtime's isolation check built its
allowedToolIds set only from MCP tool ids and treated StructuredOutput
as an unexpected host-injected tool, so every generateObject call threw
"Claude Code runtime isolation failed: tools=StructuredOutput ..." and
the table-descriptions and relationship-LLM-proposal enrichment stages
recorded null output across the board.
Whitelist StructuredOutput specifically in generateObject's
allowedToolIds — the check also enforces missing_tools symmetry, so
generateText and runAgentLoop, which do not see StructuredOutput, must
not require it.
generateObject also ran with maxTurns: 1, which the model intermittently
breached when it emitted thinking text before the structured response.
Raised to 5 to give the schema-bound call enough headroom without
allowing unbounded loops. The existing tests now exercise the path with
an init message that announces StructuredOutput so the regression cannot
slip back in.
* chore(scripts): add ktx-reset.sh project-cleanup helper
Convenience script for repeatable ingest testing: takes a project
directory and prunes everything except ktx.yaml and .ktx/secrets/, so
the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
|
|
|
assert request.table_scope is not None
|
|
|
|
|
assert request.table_scope[0].db == "public"
|
|
|
|
|
assert request.table_scope[0].name == "orders"
|
2026-05-10 23:12:26 +02:00
|
|
|
return DatabaseIntrospectionResponse(
|
|
|
|
|
connection_id="warehouse",
|
|
|
|
|
extracted_at="2026-04-28T10:00:00+00:00",
|
|
|
|
|
metadata={"driver": "postgres", "schemas": ["public"]},
|
|
|
|
|
tables=[
|
|
|
|
|
LiveDatabaseTable(
|
|
|
|
|
catalog="warehouse",
|
|
|
|
|
db="public",
|
|
|
|
|
name="orders",
|
|
|
|
|
columns=[
|
|
|
|
|
LiveDatabaseColumn(
|
|
|
|
|
name="id",
|
|
|
|
|
type="integer",
|
|
|
|
|
nullable=False,
|
|
|
|
|
primary_key=True,
|
|
|
|
|
)
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(daemon_main, "introspect_database_response", fake_introspect)
|
|
|
|
|
monkeypatch.setattr(
|
|
|
|
|
sys,
|
|
|
|
|
"stdin",
|
|
|
|
|
io.StringIO(
|
fix(snowflake): unblock multi-schema ingest and relationship discovery (#204)
* feat(setup): drop redundant Snowflake schema prompt; fall back to free-text on listSchemas failure
Snowflake setup previously asked for a single schema as free text, then
ran a multiselect against the discovered schemas — two schema questions
back-to-back, with the first being only a session bootstrap. The SDK's
`schema` is optional, so the bootstrap step is unnecessary.
- Remove the free-text Snowflake schema prompt; only pass `schema` to
snowflake-sdk when one is configured.
- When `listSchemas()` fails (e.g. role lacks SHOW SCHEMAS), prompt the
user for a comma-separated list, persist it as `schema_names`, and use
it as both the table-list filter and the multiselect default. Applies
to every driver with a scope-discovery spec, not just Snowflake.
- Update docs to lead with `schema_names`; keep `schema_name` as a
documented single-schema shorthand.
* fix(snowflake): keep introspecting when primary-key discovery is denied
The PK query joins INFORMATION_SCHEMA.TABLE_CONSTRAINTS and
INFORMATION_SCHEMA.KEY_COLUMN_USAGE, which require grants the
connection role may not have. Previously a 'SQL compilation error:
Object ANALYTICS.INFORMATION_SCHEMA.KEY_COLUMN_USAGE does not exist
or not authorized' aborted the entire introspect — schemas, columns,
and row counts were all discarded over a missing nice-to-have.
Wrap the constraint query in try/catch, log a one-line warning per
schema, and return an empty PK map. Columns end up with
primaryKey=false; relationship inference still has FK and profiling
to fall back on.
* fix(scan): unblock relationship discovery on Snowflake
Two adjacent bugs prevented the scan's relationship pipeline from producing
any joins on a Snowflake warehouse:
- relationship-profiling.ts fell through to a default `GROUP_CONCAT` branch
for unknown drivers. Snowflake has no GROUP_CONCAT, so every per-table
profile query failed with "Unknown function GROUP_CONCAT". Add an explicit
Snowflake branch that uses LISTAGG with a literal '\x1f' delimiter
(Snowflake requires the delimiter to be a constant, so CHR(31) is rejected).
- description-generation.ts destructured `connector.sampleTable` and
`connector.sampleColumn` into bare locals, losing the `this` binding when
the class-method connectors (Snowflake, Postgres, MySQL) were invoked.
Every sample call threw "Cannot read properties of undefined (reading
'assertConnection')" and degraded LLM descriptions to metadata-only
prompts. Call the methods through the connector instead.
Without these, even after the primary-key probe is allowed to fail softly,
the scan ends up with 0 validated relationships and an empty `joins:` block
in every shard YAML.
* test(scan): cover table-ref helpers
* feat(scan): plumb tableScope through live-database introspection port
* feat(scan): apply tableScope during metadata fetch
* feat(scan): enforce table scope at fetch boundary
* feat(scan): pool Snowflake sessions and batch enrichment for faster ingest (#206)
* feat(cli): add RSA key-pair auth option to Snowflake setup wizard
Extends the interactive Snowflake setup flow with an authentication-method
prompt (password vs RSA/JWT key-pair). The RSA branch collects a private-key
path (env/file/absolute) and an optional passphrase; the resulting connection
config records `authMethod: 'rsa'` with `privateKey` and `passphrase` instead
of `password`.
* feat(scan): pool Snowflake sessions
* fix(scan): reuse structural snapshots and cleanup connectors
* feat(scan): parallelize relationship profiling
* feat(scan): batch table description generation
* docs: document Snowflake ingest concurrency knobs
* fix(scan): close Snowflake ingest perf verification gaps
* fix(scan): keep batched description failure bounded
* feat(scan): dispatch query-history probes by connection driver
Extract historic-sql dialect resolution into a shared helper so the
status-project readiness check and the local ingest factory agree on
which connections enable query history and which probe to run. The
status command now picks the postgres/snowflake/bigquery probe based on
the connection's driver instead of always reporting against postgres,
which previously caused snowflake connections with queryHistory.enabled
to surface a misleading "driver is snowflake" failure.
Also drops a noisy console.warn from Snowflake primary-key discovery —
INFORMATION_SCHEMA.KEY_COLUMN_USAGE is commonly ungranted for read-only
roles and the FK + profiling paths handle the empty PK map already.
* fix(llm): allow StructuredOutput tool and raise maxTurns for generateObject
The Claude Code agent SDK announces an internal pseudo-tool named
StructuredOutput in the system/init message whenever outputFormat is set
to { type: 'json_schema' }. The runtime's isolation check built its
allowedToolIds set only from MCP tool ids and treated StructuredOutput
as an unexpected host-injected tool, so every generateObject call threw
"Claude Code runtime isolation failed: tools=StructuredOutput ..." and
the table-descriptions and relationship-LLM-proposal enrichment stages
recorded null output across the board.
Whitelist StructuredOutput specifically in generateObject's
allowedToolIds — the check also enforces missing_tools symmetry, so
generateText and runAgentLoop, which do not see StructuredOutput, must
not require it.
generateObject also ran with maxTurns: 1, which the model intermittently
breached when it emitted thinking text before the structured response.
Raised to 5 to give the schema-bound call enough headroom without
allowing unbounded loops. The existing tests now exercise the path with
an init message that announces StructuredOutput so the regression cannot
slip back in.
* chore(scripts): add ktx-reset.sh project-cleanup helper
Convenience script for repeatable ingest testing: takes a project
directory and prunes everything except ktx.yaml and .ktx/secrets/, so
the next ktx setup or ktx ingest run starts from a known-clean state.
2026-05-23 10:41:30 +02:00
|
|
|
'{"connection_id":"warehouse","driver":"postgres","url":"postgresql://readonly@example.test/warehouse","schemas":["public"],"table_scope":[{"db":"public","name":"orders"}]}'
|
2026-05-10 23:12:26 +02:00
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert daemon_main.main(["database-introspect"]) == 0
|
|
|
|
|
captured = capsys.readouterr()
|
|
|
|
|
parsed = json.loads(captured.out)
|
|
|
|
|
assert parsed["connection_id"] == "warehouse"
|
|
|
|
|
assert parsed["metadata"] == {"driver": "postgres", "schemas": ["public"]}
|
|
|
|
|
assert parsed["tables"][0]["name"] == "orders"
|
|
|
|
|
assert captured.err == ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_embedding_compute_command_reads_stdin_and_writes_json(
|
|
|
|
|
monkeypatch, capsys
|
|
|
|
|
) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
|
|
|
|
from ktx_daemon.embeddings import ComputeEmbeddingResponse
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
def fake_compute(request):
|
|
|
|
|
assert request.text == "hello"
|
|
|
|
|
return ComputeEmbeddingResponse(embedding=[1.0, 2.0, 3.0])
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(daemon_main, "compute_embedding_response", fake_compute)
|
|
|
|
|
monkeypatch.setattr(sys, "stdin", io.StringIO('{"text": "hello"}'))
|
|
|
|
|
|
|
|
|
|
assert daemon_main.main(["embedding-compute"]) == 0
|
|
|
|
|
captured = capsys.readouterr()
|
|
|
|
|
assert json.loads(captured.out) == {"embedding": [1.0, 2.0, 3.0]}
|
|
|
|
|
assert captured.err == ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_embedding_compute_bulk_command_reads_stdin_and_writes_json(
|
|
|
|
|
monkeypatch, capsys
|
|
|
|
|
) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
|
|
|
|
from ktx_daemon.embeddings import ComputeEmbeddingBulkResponse
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
def fake_compute(request):
|
|
|
|
|
assert request.texts == ["hello", "world"]
|
|
|
|
|
return ComputeEmbeddingBulkResponse(embeddings=[[1.0, 2.0], [3.0, 4.0]])
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(daemon_main, "compute_embedding_bulk_response", fake_compute)
|
|
|
|
|
monkeypatch.setattr(sys, "stdin", io.StringIO('{"texts": ["hello", "world"]}'))
|
|
|
|
|
|
|
|
|
|
assert daemon_main.main(["embedding-compute-bulk"]) == 0
|
|
|
|
|
captured = capsys.readouterr()
|
|
|
|
|
assert json.loads(captured.out) == {"embeddings": [[1.0, 2.0], [3.0, 4.0]]}
|
|
|
|
|
assert captured.err == ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_code_execute_command_reads_stdin_and_writes_json(monkeypatch, capsys) -> None:
|
2026-05-10 23:51:24 +02:00
|
|
|
from ktx_daemon import __main__ as daemon_main
|
|
|
|
|
from ktx_daemon.code_execution import ExecuteCodeResponse
|
2026-05-10 23:12:26 +02:00
|
|
|
|
|
|
|
|
calls: list[dict[str, Any]] = []
|
|
|
|
|
|
|
|
|
|
def fake_execute(request, *, nest_api_url, auth_header):
|
|
|
|
|
calls.append(
|
|
|
|
|
{
|
|
|
|
|
"request": request,
|
|
|
|
|
"nest_api_url": nest_api_url,
|
|
|
|
|
"auth_header": auth_header,
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
return ExecuteCodeResponse(
|
|
|
|
|
formatted_result="\n\n=== Result ===\n\n7",
|
|
|
|
|
result=7,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr(daemon_main, "execute_code_response", fake_execute)
|
|
|
|
|
monkeypatch.setattr(sys, "stdin", io.StringIO('{"code": "result = 7"}'))
|
|
|
|
|
|
|
|
|
|
assert daemon_main.main(["code-execute"]) == 0
|
|
|
|
|
captured = capsys.readouterr()
|
|
|
|
|
assert json.loads(captured.out) == {
|
|
|
|
|
"formatted_result": "\n\n=== Result ===\n\n7",
|
|
|
|
|
"result": 7,
|
|
|
|
|
"console_output": None,
|
|
|
|
|
"error": None,
|
|
|
|
|
"message": None,
|
|
|
|
|
"visualizations": None,
|
|
|
|
|
}
|
|
|
|
|
assert captured.err == ""
|
|
|
|
|
assert calls[0]["request"].code == "result = 7"
|
|
|
|
|
assert calls[0]["nest_api_url"] is None
|
|
|
|
|
assert calls[0]["auth_header"] is None
|