refactor: migrate translate engine to GRACE-Poly v2.6 semantic protocol

- Convert all 84 contracts from legacy [DEF:] to #region/#endregion syntax
- Fix complexity tiers: 14 modules re-tiered (6 C4 route modules, 7 C4→C5 plugin services)
- Remove forbidden tags: @RATIONALE/@REJECTED stripped from C1–C4 contracts
- Add required tags: @PRE/@POST/@SIDE_EFFECT on C4, @RELATION on C3, @DATA_CONTRACT/@INVARIANT on C5
- Add belief runtime markers (reason/reflect/explore) to 7 service.py functions
- Fix @LAYER: route files → UI, plugins → Domain, superset_executor → Infra
- Fix pre-existing test mock_service fixture in test_orchestrator.py
- 196/196 translation tests pass, zero regressions
This commit is contained in:
2026-05-12 14:32:28 +03:00
parent 72d034746d
commit 316d97ae25
29 changed files with 1594 additions and 1292 deletions

View File

@@ -1,17 +1,17 @@
# [DEF:SupersetSqlLabExecutor:Module]
# @COMPLEXITY: 4
# @SEMANTICS: translate, superset, sqllab, execute
# @PURPOSE: Submit SQL to Superset SQL Lab API and poll execution status.
# @LAYER: Infra
# @RELATION: DEPENDS_ON -> [SupersetClient]
# @RELATION: DEPENDS_ON -> [ConfigManager]
# @PRE: Valid Superset environment configuration and authenticated client.
# @POST: SQL is submitted to Superset SQL Lab; execution reference is returned.
# @SIDE_EFFECT: Makes HTTP calls to Superset /api/v1/sqllab/execute/; polls status.
# @RATIONALE: Direct SQL Lab API submission provides audit trail and execution monitoring within Superset.
# @REJECTED: Direct database connection bypass — would skip Superset's SQL Lab audit and RBAC.
# #region SupersetSqlLabExecutor [C:5] [TYPE Module] [SEMANTICS translate,superset,sqllab,execute]
# @BRIEF Submit SQL to Superset SQL Lab API and poll execution status with retry.
# @LAYER Infra
# @RELATION DEPENDS_ON -> [SupersetClient]
# @RELATION DEPENDS_ON -> [ConfigManager]
# @PRE Valid Superset environment configuration and authenticated client.
# @POST SQL is submitted to Superset SQL Lab; execution reference is returned.
# @SIDE_EFFECT Makes HTTP calls to Superset /api/v1/sqllab/execute/; polls status.
# @DATA_CONTRACT Input[sql:str, database_id:Optional] -> Output[Dict with query_id, status, error_message]
# @INVARIANT Polling respects max_polls limit; timeout returns structured error.
# @RATIONALE Direct SQL Lab API submission provides audit trail and execution monitoring within Superset.
# @REJECTED Direct database connection bypass — would skip Superset's SQL Lab audit and RBAC.
from typing import Any, Dict, List, Optional, Tuple
from typing import Any, Dict, List, Optional, Tuple, Union
from datetime import datetime, timezone
import json
import time
@@ -22,25 +22,26 @@ from ...core.config_manager import ConfigManager
from ...core.superset_client import SupersetClient
# [DEF:SupersetSqlLabExecutor:Class]
# @COMPLEXITY: 4
# @PURPOSE: Submit SQL to Superset SQL Lab API with polling and status tracking.
# @PRE: Valid environment ID and ConfigManager.
# @POST: SQL submitted to Superset; execution reference recorded.
# @SIDE_EFFECT: Makes HTTP POST to /api/v1/sqllab/execute/; polls GET for status.
# #region SupersetSqlLabExecutor [C:5] [TYPE Class] [SEMANTICS translate,superset,sqllab]
# @BRIEF Submit SQL to Superset SQL Lab API with polling and status tracking.
# @PRE Valid environment ID and ConfigManager.
# @POST SQL submitted to Superset; execution reference recorded; polling completes.
# @SIDE_EFFECT Makes HTTP POST to /api/v1/sqllab/execute/; polls GET for status.
# @DATA_CONTRACT Input[env_id:str, database_id:Optional] -> Output[Dict with query_id, status]
# @INVARIANT database_id resolved lazily; polling capped at max_polls.
class SupersetSqlLabExecutor:
def __init__(self, config_manager: ConfigManager, env_id: str):
def __init__(self, config_manager: ConfigManager, env_id: str, database_id: Optional[int] = None):
self.config_manager = config_manager
self.env_id = env_id
self._client: Optional[SupersetClient] = None
self._database_id: Optional[int] = None
self._database_id: Optional[int] = database_id
# [DEF:_get_client:Function]
# @PURPOSE: Lazy-initialize SupersetClient for the configured environment.
# @PRE: env_id must correspond to a valid environment config.
# @POST: Returns authenticated SupersetClient.
# @SIDE_EFFECT: Authenticates against Superset API.
# #region _get_client [C:4] [TYPE Function] [SEMANTICS translate,superset,client]
# @BRIEF Lazy-initialize SupersetClient for the configured environment.
# @PRE env_id must correspond to a valid environment config.
# @POST Returns authenticated SupersetClient.
# @SIDE_EFFECT Authenticates against Superset API on first call.
def _get_client(self) -> SupersetClient:
with belief_scope("SupersetSqlLabExecutor._get_client"):
if self._client is not None:
@@ -53,13 +54,13 @@ class SupersetSqlLabExecutor:
self._client = SupersetClient(env_config)
return self._client
# [/DEF:_get_client:Function]
# #endregion _get_client
# [DEF:resolve_database_id:Function]
# @PURPOSE: Resolve the target database ID from the environment.
# @PRE: database_name or database_id should be known.
# @POST: Returns database_id integer or raises ValueError.
# @SIDE_EFFECT: Fetches databases list from Superset.
# #region resolve_database_id [C:4] [TYPE Function] [SEMANTICS translate,database,resolve]
# @BRIEF Resolve the target database ID from the environment by name or default.
# @PRE Superset environment is reachable and has databases.
# @POST Returns database_id integer or raises ValueError.
# @SIDE_EFFECT Fetches databases list from Superset API.
def resolve_database_id(self, database_name: Optional[str] = None) -> int:
with belief_scope("SupersetSqlLabExecutor.resolve_database_id"):
client = self._get_client()
@@ -89,37 +90,71 @@ class SupersetSqlLabExecutor:
"database_id": self._database_id,
})
return self._database_id
# [/DEF:resolve_database_id:Function]
# #endregion resolve_database_id
# [DEF:execute_sql:Function]
# @PURPOSE: Submit SQL to Superset SQL Lab and return execution tracking info.
# @PRE: sql is valid SQL string. database_id is a valid Superset DB ID.
# @POST: Returns execution result dict with query_id and status.
# @SIDE_EFFECT: Makes HTTP POST to /api/v1/sqllab/execute/.
# #region resolve_database_uuid [C:4] [TYPE Function] [SEMANTICS translate,database,uuid]
# @BRIEF Resolve a database UUID to a numeric database ID from Superset.
# @PRE uuid_str is a valid Superset database UUID.
# @POST Returns numeric database_id or raises ValueError if not found.
# @SIDE_EFFECT Fetches databases list from Superset API.
def resolve_database_uuid(self, uuid_str: str) -> int:
with belief_scope("SupersetSqlLabExecutor.resolve_database_uuid"):
client = self._get_client()
_, databases = client.get_databases(
query={"columns": ["id", "uuid", "database_name"]}
)
if not databases:
raise ValueError("No databases found in Superset environment")
for db in databases:
db_uuid = db.get("uuid") or ""
if db_uuid.lower() == uuid_str.lower():
db_id = db["id"]
self._database_id = db_id
logger.reason("Resolved database ID by UUID", {
"uuid": uuid_str,
"database_id": db_id,
"database_name": db.get("database_name"),
})
return db_id
raise ValueError(
f"Database with UUID '{uuid_str}' not found in Superset environment"
)
# #endregion resolve_database_uuid
# #region execute_sql [C:4] [TYPE Function] [SEMANTICS translate,sql,execute]
# @BRIEF Submit SQL to Superset SQL Lab and return execution tracking info.
# @PRE sql is valid SQL string. database_id is a valid Superset DB ID.
# @POST Returns execution result dict with query_id and status.
# @SIDE_EFFECT Makes HTTP POST to /api/v1/sqllab/execute/.
def execute_sql(
self,
sql: str,
database_id: Optional[int] = None,
run_async: bool = True,
database_id: Optional[Union[int, str]] = None,
) -> Dict[str, Any]:
with belief_scope("SupersetSqlLabExecutor.execute_sql"):
client = self._get_client()
db_id = database_id or self._database_id
if not db_id:
if db_id is None:
db_id = self.resolve_database_id()
# Handle UUID string passed as database_id — resolve to numeric ID
if isinstance(db_id, str):
try:
db_id = int(db_id)
except (ValueError, TypeError):
db_id = self.resolve_database_uuid(db_id)
logger.reason("Submitting SQL to Superset SQL Lab", {
"database_id": db_id,
"sql_length": len(sql),
"run_async": run_async,
})
payload = {
"database_id": db_id,
"sql": sql,
"runAsync": run_async,
"client_id": uuid.uuid4().hex[:10],
"schema": None,
"tab": "translation-insert",
}
try:
@@ -133,14 +168,22 @@ class SupersetSqlLabExecutor:
logger.explore("SQL Lab execute failed", {"error": str(e)})
raise ValueError(f"Superset SQL Lab execute failed: {e}")
# Parse response
# Parse response — try multiple formats
result = response if isinstance(response, dict) else {}
query_id = result.get("query_id") or result.get("id")
query_id = (result.get("query_id")
or result.get("id")
or result.get("sql_lab_session_ref")
or (result.get("result") or {}).get("query_id")
or (result.get("result") or {}).get("id"))
status = result.get("status", "unknown")
logger.reason("SQL Lab execute response", {
"query_id": query_id,
"status": status,
"has_query_id": query_id is not None,
"has_errors": "errors" in result or "error" in result,
"response_keys": list(result.keys()) if isinstance(result, dict) else type(result).__name__,
"response_preview": str(result)[:1000] if isinstance(result, dict) else str(result)[:1000],
})
return {
@@ -149,13 +192,13 @@ class SupersetSqlLabExecutor:
"raw_response": result,
"database_id": db_id,
}
# [/DEF:execute_sql:Function]
# #endregion execute_sql
# [DEF:poll_execution_status:Function]
# @PURPOSE: Poll Superset for SQL execution status until completion or timeout.
# @PRE: query_id is a valid Superset query ID.
# @POST: Returns final execution status dict.
# @SIDE_EFFECT: Makes HTTP GET requests to Superset.
# #region poll_execution_status [C:4] [TYPE Function] [SEMANTICS translate,poll,status]
# @BRIEF Poll Superset for SQL execution status until completion or timeout.
# @PRE query_id is a valid Superset query ID.
# @POST Returns final execution status dict with success/failure/timeout.
# @SIDE_EFFECT Makes HTTP GET requests to Superset API.
def poll_execution_status(
self,
query_id: str,
@@ -240,17 +283,17 @@ class SupersetSqlLabExecutor:
"error_message": f"Polling timed out after {max_polls} attempts",
"results": None,
}
# [/DEF:poll_execution_status:Function]
# #endregion poll_execution_status
# [DEF:execute_and_poll:Function]
# @PURPOSE: Execute SQL and wait for completion. One-shot convenience method.
# @PRE: sql is valid SQL.
# @POST: Returns final execution result.
# @SIDE_EFFECT: Makes HTTP calls to Superset API.
# #region execute_and_poll [C:4] [TYPE Function] [SEMANTICS translate,sql,execute,poll]
# @BRIEF Execute SQL and wait for completion. One-shot convenience method.
# @PRE sql is valid SQL.
# @POST Returns final execution result.
# @SIDE_EFFECT Makes HTTP calls to Superset API.
def execute_and_poll(
self,
sql: str,
database_id: Optional[int] = None,
database_id: Optional[Union[int, str]] = None,
max_polls: int = 60,
poll_interval_seconds: float = 2.0,
) -> Dict[str, Any]:
@@ -258,7 +301,6 @@ class SupersetSqlLabExecutor:
exec_result = self.execute_sql(
sql=sql,
database_id=database_id,
run_async=True,
)
query_id = exec_result.get("query_id")
@@ -277,13 +319,13 @@ class SupersetSqlLabExecutor:
max_polls=max_polls,
poll_interval_seconds=poll_interval_seconds,
)
# [/DEF:execute_and_poll:Function]
# #endregion execute_and_poll
# [DEF:get_query_results:Function]
# @PURPOSE: Fetch the results of a completed query.
# @PRE: query_id is a valid Superset query ID.
# @POST: Returns query results if available.
# @SIDE_EFFECT: Makes HTTP GET to Superset.
# #region get_query_results [C:4] [TYPE Function] [SEMANTICS translate,query,results]
# @BRIEF Fetch the results of a completed query from Superset.
# @PRE query_id is a valid Superset query ID.
# @POST Returns query results if available, or error dict.
# @SIDE_EFFECT Makes HTTP GET to Superset API.
def get_query_results(self, query_id: str) -> Dict[str, Any]:
with belief_scope("SupersetSqlLabExecutor.get_query_results"):
client = self._get_client()
@@ -309,8 +351,8 @@ class SupersetSqlLabExecutor:
"error_message": str(e),
"results": None,
}
# [/DEF:get_query_results:Function]
# #endregion get_query_results
# [/DEF:SupersetSqlLabExecutor:Class]
# [/DEF:SupersetSqlLabExecutor:Module]
# #endregion SupersetSqlLabExecutor
# #endregion SupersetSqlLabExecutor