Reserved-word columns (like, default, ...) referenced as source.col were
quoted with postgres double quotes even on BigQuery/MySQL, where a
double-quoted token is a string literal, not an identifier -- the
"Unexpected string literal" semantic-layer errors. quote_reserved_identifiers
now uses the identifier quote char of the dialect it will be parsed in
(backtick for BigQuery/MySQL), threaded through the planner and generator
parse sites; week_<weekday> granularity now emits WEEK(<weekday>) on BigQuery
instead of the invalid WEEK_MONDAY.
On the telemetry side, warehouse rejections from the sl_query execution path
are classified as expected (KtxQueryError) via a new shared markExpected()
helper, so routine agent/warehouse query failures stop reaching PostHog Error
Tracking as ktx faults; the sql_execution catch is refactored onto the same
helper. The daemon-compile boundary is deliberately left unclassified here so
genuine daemon crashes stay visible.
* feat(sl): add predefined_measures_only guard to semantic query planning
SemanticQuery gains a predefined_measures_only flag; the planner rejects
any measure resolved with Provenance.COMPOSED (runtime aggregate
expressions and query-time derivations) while predefined measures,
predefined derived chains, dimensions, filters, and segments pass.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(config): add per-connection query_policy to warehouse connections
query_policy: semantic-layer-only | read-only-sql (default) on the
warehouse connection schema, plus a policy module with the raw-SQL
guard, federated member restriction lookup, and the project-level
predicate used to gate sql_execution registration.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(cli): enforce query_policy on raw SQL through one shared executor
ktx sql and the MCP sql_execution tool now share executeProjectRawSql
(resolve, policy check, read-only validation, execute), collapsing
their duplicated validate-then-execute paths. Restricted connections
are rejected before validation; federated raw SQL is rejected when any
member is restricted. sql_execution is not registered when every SQL
connection is restricted, and connection_list marks restricted
connections so agents route to sl_query. executeProjectReadOnlySql
stays generic for ktx-internal SQL (scan, ingest, SL-generated).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(sl): compile queries with predefined_measures_only from query_policy
compileLocalSlQuery injects the flag from the connection's query_policy,
never from caller input, covering both ktx sl query and the MCP
sl_query tool through the daemon compile path.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: document query_policy semantic-layer-only
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sl): close semantic-layer-only bypasses via filters and federated hint
The predefined_measures_only guard only inspected query.measures, so a
composed aggregate written into `filters` slipped through _classify_filters
into a HAVING clause untouched — letting a restricted agent evaluate
arbitrary aggregates (e.g. threshold-probing `sum(x) BETWEEN a AND b`).
Reject filter clauses that compose an aggregate function; a HAVING that
compares a predefined measure by name (`orders.revenue > 100`) still works.
Also make the federated sl_query error policy-aware: when a member is
restricted, raw federated SQL is disabled too, so stop directing the agent
to `ktx sql -c _ktx_federated` / sql_execution (a guaranteed failure) and
point to per-connection semantic-layer queries instead.
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
* fix(sl): parse user filter expressions as predicates, not projections
User-authored filters and segments were parsed in a projection context
(`SELECT {expr}`). On T-SQL a top-level `col = 'value'` projection is the
`alias = expression` aliasing syntax, so an equality filter parsed this way
became `'value' AS col` — dropping the comparison entirely and silently
skipping computed-column expansion (the column hid behind the alias).
Parse user fragments as predicates (`SELECT * WHERE {expr}`) at every parse
site — the parser cache, measure-filter CASE WHEN generation, computed-column
expansion, and measure-filter/segment column qualification. For plain
non-condition expressions the column set is identical, so this is a no-op
everywhere except the T-SQL alias case it fixes.
Add cross-dialect regression tests (tsql, postgres, snowflake, bigquery)
locking equality filters/segments to comparison shape and confirming `= 'x'`
now matches `IN ('x')` on T-SQL.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Shorten T-SQL predicate comments
* docs(sl): tighten T-SQL predicate docstrings and AGENTS docstring rule
Trim the parser and regression-test docstrings to the 1-3 line bar and
extend the AGENTS.md comment guidance to cover docstrings explicitly.
* refactor(sl): route all filter parsing through parse_predicate
Consolidate the predicate-context parse into a single parse_predicate
helper and route every filter-parsing call site through it: measure
CASE-WHEN filters, segments, computed-column-in-filter, the
aggregate-locality HAVING rewrite, and the planner OR-mixing /
top-level-AND split. The locality and split paths still parsed user
filters in projection context, so a named-measure equality filter
compiled to `0 AS measure` on T-SQL. Add a locality regression test
covering the HAVING rewrite path.
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
* fix(context): merge overlay columns onto manifest columns by name
composeOverlay was appending overlay columns to the manifest column list,
producing duplicate entries when dbt/metabase overlays declared a column
just to attach descriptions. The duplicates carried no `type`, so the
pydantic SourceDefinition rejected them at semantic-query time and broke
`ktx sl query` for every overlay-backed measure. Now overlay columns
match base columns by name (case-insensitive): same-name entries merge
onto the manifest (overlay fields win, type/role fall back to the base,
descriptions merge per source key) and only new names append.
* refactor(sl): split overlay columns from column_overrides and enforce TS/Python wire contract
Overlay sources now have two distinct collections: `columns:` for computed
columns (requiring `expr` + `type`) and `column_overrides:` for metadata
patches to inherited manifest columns. Composing or loading an overlay that
mixes the two — or references an unknown column — fails with a typed error.
Introduce `ResolvedSemanticLayerSource` / `resolvedSourceSchema` /
`toResolvedWire` as the strict shape sent to the Python engine, and add a
schema contract test that diffs Zod against the Pydantic JSON schema dumped
by `python -m semantic_layer dump-schema`. `SourceDefinition` is now
`extra="forbid"` on the Python side.
`loadAllSources` surfaces per-file load errors instead of swallowing them,
so validation/query paths can report manifest shard parse failures.
* fix(context): make scan description generation resilient and quiet
A transient sampleTable failure during ingest used to take out every
table in a connection: generateTableDescription returned a hardcoded
'Table not found' string into descriptions.ai, and KtxDescriptionGenerator
was constructed without a logger, so the failure left no trail anywhere.
- sampleTable / sampleColumn calls retry 3x with 200/400/800ms backoff,
honouring KtxScanContext.signal via a new KtxAbortedError.
- On retry exhaustion or missing capability, table generation falls back
to a metadata-only prompt built from column name / native type / comment
/ rawDescriptions. The column path follows the same rule -- call the
LLM when any of samples or rawDescriptions are available; skip only
when both are absent.
- Logger is now threaded from KtxScanContext into the generator. Failures
emit structured KtxScanWarning entries (new description_fallback_used
code, plus existing sampling_failed / enrichment_failed /
connector_capability_missing). ktx scan groups warnings by code so a
batch of identical failures collapses to one summary line plus sample.
- Returns null on failure instead of the 'Table not found' sentinel; the
manifest writer's existing guard already skips empty descriptions, so
schema YAML no longer carries misleading text. SCAN_MANAGED_DESCRIPTION_KEYS
already strips stale 'ai' on merge, so existing YAML clears on next run.
Also suppress AI SDK v6 'system in messages' warning: pull system messages
out of KtxMessageBuilder.wrapSimple's output via a new splitKtxSystemMessages
helper and pass them top-level to generateText (preserves cacheControl
providerOptions on the SystemModelMessage). Agent-runner's local
splitSystemPromptMessages dedupes onto the shared helper.
* test(docs): align examples-docs assertions with revamped docs
PR #103 (setup/guide doc revamp) reworded several CLI examples and
connection labels; the assertions in scripts/examples-docs.test.mjs
still referenced the pre-revamp wording and were failing in CI on main.
Update the regexes to match the post-revamp content:
- drop the `--json` flag from the sl-query example expectation
- move the `Driver:` / `Status: ok` probe to the connection reference,
which is where that output now lives (driver id is lowercase
`postgres`, not the display name `PostgreSQL`)
- drop the obsolete `Install \`uv\`...` troubleshooting line
- accept `<connectionId>` everywhere; the docs no longer use the
hyphenated `<connection-id>` form
- match the `warehouse` connection id used in the quickstart instead of
the `postgres-warehouse` id only used in the README and setup ref
* fix(sl): skip TS/Python schema contract test when uv is unavailable
The TypeScript checks CI job does not install uv or Python, so the
module-level `execFileSync('uv', ...)` in schemas.contract.test.ts threw
ENOENT and failed the suite. Wrap the schema dump in a try/catch and
guard the describe block with `describe.skipIf` so the test skips in
environments without uv. Local dev and any CI job that has uv on PATH
still runs the cross-language contract assertion.
