mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-07 07:55:13 +02:00
* 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.
256 lines
9.5 KiB
Python
256 lines
9.5 KiB
Python
from __future__ import annotations
|
|
|
|
import logging
|
|
import re
|
|
from copy import deepcopy
|
|
from pathlib import Path
|
|
|
|
import yaml
|
|
|
|
from semantic_layer.manifest import (
|
|
Manifest,
|
|
_description_sources,
|
|
_resolve_description,
|
|
project_manifest_entry,
|
|
validate_overlay,
|
|
)
|
|
from semantic_layer.models import (
|
|
JoinDeclaration,
|
|
MeasureDefinition,
|
|
Segment,
|
|
SourceColumn,
|
|
SourceDefinition,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_SCHEMA_DIR = "_schema"
|
|
|
|
|
|
def _normalize_ws(s: str) -> str:
|
|
"""Collapse whitespace for join deduplication."""
|
|
return re.sub(r"\s+", " ", s.strip())
|
|
|
|
|
|
class SourceLoader:
|
|
def __init__(self, sources_dir: str | Path):
|
|
self.sources_dir = Path(sources_dir)
|
|
|
|
def load_all(self) -> dict[str, SourceDefinition]:
|
|
"""Load all sources using two-tier architecture.
|
|
|
|
1. Load _schema/*.yaml manifest shards → project to SourceDefinitions
|
|
2. Load *.yaml files outside _schema/
|
|
- Has `sql` or `table` → standalone source (load directly)
|
|
- Otherwise → overlay (compose with matching manifest entry)
|
|
3. Validate cross-references
|
|
"""
|
|
sources: dict[str, SourceDefinition] = {}
|
|
description_sources: dict[str, dict[str, str] | None] = {}
|
|
|
|
# 1. Load manifest shards
|
|
schema_dir = self.sources_dir / _SCHEMA_DIR
|
|
if schema_dir.is_dir():
|
|
for path in sorted(schema_dir.glob("*.yaml")):
|
|
manifest = self._load_manifest_shard(path)
|
|
for name, entry in manifest.tables.items():
|
|
if name in sources:
|
|
raise ValueError(
|
|
f"Duplicate source name '{name}' in manifest shard {path}"
|
|
)
|
|
sources[name] = project_manifest_entry(name, entry)
|
|
description_sources[name] = _description_sources(entry.descriptions)
|
|
|
|
# 2. Load files outside _schema/
|
|
for path in sorted(self.sources_dir.rglob("*.yaml")):
|
|
# Skip manifest shards
|
|
if _is_in_schema_dir(path, self.sources_dir):
|
|
continue
|
|
|
|
with open(path) as f:
|
|
data = yaml.safe_load(f)
|
|
|
|
if not isinstance(data, dict):
|
|
continue
|
|
|
|
name = data.get("name")
|
|
if not name:
|
|
continue
|
|
|
|
if data.get("sql") or data.get("table"):
|
|
# Standalone source — load directly
|
|
if name in sources:
|
|
raise ValueError(
|
|
f"Duplicate source name '{name}': standalone file {path} "
|
|
f"conflicts with manifest entry"
|
|
)
|
|
sources[name] = SourceDefinition(**data)
|
|
else:
|
|
# Overlay — validate and compose with matching manifest entry
|
|
base = sources.get(name)
|
|
if base:
|
|
errors = validate_overlay(data, {c.name for c in base.columns})
|
|
if errors:
|
|
raise ValueError(
|
|
f"Invalid overlay '{name}' in {path}: {'; '.join(errors)}"
|
|
)
|
|
(
|
|
sources[name],
|
|
description_sources[name],
|
|
) = self._compose(base, data, description_sources.get(name))
|
|
else:
|
|
errors = validate_overlay(data)
|
|
if errors:
|
|
raise ValueError(
|
|
f"Invalid overlay '{name}' in {path}: {'; '.join(errors)}"
|
|
)
|
|
logger.warning(
|
|
"Orphan overlay '%s' in %s: no matching manifest entry, skipping",
|
|
name,
|
|
path,
|
|
)
|
|
|
|
self._validate_cross_references(sources)
|
|
return sources
|
|
|
|
def load_file(self, path: str | Path) -> SourceDefinition:
|
|
"""Load and validate a single standalone YAML source definition."""
|
|
path = Path(path)
|
|
with open(path) as f:
|
|
data = yaml.safe_load(f)
|
|
source = SourceDefinition(**data)
|
|
if not source.table and not source.sql:
|
|
raise ValueError(
|
|
f"Standalone source '{source.name}' in {path} must have 'table' or 'sql'"
|
|
)
|
|
return source
|
|
|
|
def _load_manifest_shard(self, path: Path) -> Manifest:
|
|
"""Load a single manifest shard file."""
|
|
with open(path) as f:
|
|
data = yaml.safe_load(f)
|
|
return Manifest(**data)
|
|
|
|
def _compose(
|
|
self,
|
|
base: SourceDefinition,
|
|
overlay: dict,
|
|
base_description_sources: dict[str, str] | None = None,
|
|
) -> tuple[SourceDefinition, dict[str, str] | None]:
|
|
"""Compose a manifest-projected SourceDefinition with an overlay."""
|
|
source = deepcopy(base)
|
|
description_sources = dict(base_description_sources or {})
|
|
|
|
if overlay.get("descriptions"):
|
|
description_sources.update(
|
|
{
|
|
source_name: text
|
|
for source_name, text in overlay["descriptions"].items()
|
|
if text
|
|
}
|
|
)
|
|
if overlay.get("descriptions"):
|
|
source.description = _resolve_description(
|
|
description_sources or None,
|
|
)
|
|
|
|
excluded = set(overlay.get("exclude_columns", []))
|
|
overrides = overlay.get("column_overrides", [])
|
|
override_names = {override.get("name") for override in overrides}
|
|
conflicts = sorted(name for name in override_names if name in excluded)
|
|
if conflicts:
|
|
raise ValueError(
|
|
"column_overrides conflict with exclude_columns: "
|
|
+ ", ".join(conflicts)
|
|
)
|
|
|
|
base_by_name = {column.name: column for column in base.columns}
|
|
|
|
for override in overrides:
|
|
name = override.get("name")
|
|
base_column = base_by_name.get(name)
|
|
if base_column is None:
|
|
raise ValueError(
|
|
f"column '{name}' in column_overrides does not exist on manifest source '{base.name}'"
|
|
)
|
|
|
|
excluded = set(overlay.get("exclude_columns", []))
|
|
source.columns = [c for c in source.columns if c.name not in excluded]
|
|
|
|
columns_by_name = {column.name: column for column in source.columns}
|
|
|
|
for override in overrides:
|
|
name = override["name"]
|
|
base_column = base_by_name[name]
|
|
merged = base_column.model_dump(mode="python", exclude_none=True)
|
|
base_descriptions = merged.get("descriptions") or {}
|
|
override_data = dict(override)
|
|
override_descriptions = override_data.get("descriptions") or {}
|
|
merged.update(override_data)
|
|
if base_descriptions or override_descriptions:
|
|
merged["descriptions"] = {
|
|
**base_descriptions,
|
|
**override_descriptions,
|
|
}
|
|
columns_by_name[name] = SourceColumn(**merged)
|
|
source.columns = list(columns_by_name.values())
|
|
|
|
# Append computed columns. Manifest column names cannot be reused here;
|
|
# use column_overrides for metadata patches.
|
|
for col in overlay.get("columns", []):
|
|
name = col.get("name")
|
|
if name in base_by_name:
|
|
raise ValueError(
|
|
f"column '{name}' in columns patches a manifest column on '{base.name}' — move it to 'column_overrides:'"
|
|
)
|
|
source.columns.append(SourceColumn(**col))
|
|
|
|
# Set measures
|
|
source.measures = [MeasureDefinition(**m) for m in overlay.get("measures", [])]
|
|
|
|
# Set segments
|
|
source.segments = [Segment(**s) for s in overlay.get("segments", [])]
|
|
|
|
# Override grain
|
|
if overlay.get("grain"):
|
|
source.grain = overlay["grain"]
|
|
|
|
# Union + dedupe joins, apply suppressions
|
|
disabled = {_normalize_ws(j) for j in overlay.get("disable_joins", [])}
|
|
manifest_joins = [
|
|
j for j in source.joins if _normalize_ws(j.on) not in disabled
|
|
]
|
|
overlay_joins = [JoinDeclaration(**j) for j in overlay.get("joins", [])]
|
|
existing_keys = {f"{j.to}::{_normalize_ws(j.on)}" for j in manifest_joins}
|
|
new_joins = [
|
|
j
|
|
for j in overlay_joins
|
|
if f"{j.to}::{_normalize_ws(j.on)}" not in existing_keys
|
|
]
|
|
source.joins = manifest_joins + new_joins
|
|
|
|
if not source.table and not source.sql:
|
|
raise ValueError("resolved source must have 'table' or 'sql'")
|
|
if source.table and source.sql:
|
|
raise ValueError("'table' and 'sql' are mutually exclusive")
|
|
|
|
return source, (description_sources or None)
|
|
|
|
def _validate_cross_references(self, sources: dict[str, SourceDefinition]) -> None:
|
|
"""Validate that all join targets reference existing sources."""
|
|
for source in sources.values():
|
|
for join in source.joins:
|
|
if join.to not in sources:
|
|
raise ValueError(
|
|
f"Source '{source.name}' joins to '{join.to}', "
|
|
f"but '{join.to}' is not defined"
|
|
)
|
|
|
|
|
|
def _is_in_schema_dir(path: Path, sources_dir: Path) -> bool:
|
|
"""Check if a path is inside the _schema/ directory."""
|
|
try:
|
|
path.relative_to(sources_dir / _SCHEMA_DIR)
|
|
return True
|
|
except ValueError:
|
|
return False
|