Skip to content

fix: ignore non-deterministic SQL parameters when matching Postgres query mocks #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jy-tan merged 1 commit into from
Feb 4, 2026
Merged

fix: ignore non-deterministic SQL parameters when matching Postgres query mocks #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions drift/instrumentation/psycopg/instrumentation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
from opentelemetry.trace import StatusCode as OTelStatusCode

from ...core.drift_sdk import TuskDrift
from ...core.json_schema_helper import JsonSchemaHelper
from ...core.json_schema_helper import JsonSchemaHelper, SchemaMerge
from ...core.mode_utils import handle_record_mode, handle_replay_mode
from ...core.tracing import TdSpanAttributes
from ...core.tracing.span_utils import CreateSpanOptions, SpanUtils
Expand Down Expand Up @@ -1468,7 +1468,21 @@ def _set_span_attributes(
input_value: The input data dictionary (query, parameters, etc.)
output_value: The output data dictionary (rows, rowcount, error, etc.)
"""
input_result = JsonSchemaHelper.generate_schema_and_hash(input_value, {})
# IMPORTANT: Tell the exporter (otel_converter) how to generate schema + hashes.
# The exporter recomputes the schema/hashes at export time from td.input_value and td.input_schema_merges.
# Mark parameters as match_importance=0.0 so non-deterministic values (e.g. timestamps) don't prevent mock matching.
span.set_attribute(
TdSpanAttributes.INPUT_SCHEMA_MERGES,
json.dumps({"parameters": {"match_importance": 0.0}}),
)

# Set match_importance=0 for parameters to allow fuzzy matching on query text
# This handles non-deterministic values like timestamps while still exact-matching
# deterministic values like IDs (exact hash match takes priority over reduced hash)
input_result = JsonSchemaHelper.generate_schema_and_hash(
input_value,
{"parameters": SchemaMerge(match_importance=0.0)},
)
output_result = JsonSchemaHelper.generate_schema_and_hash(output_value, {})

span.set_attribute(TdSpanAttributes.INPUT_VALUE, json.dumps(input_value))
Expand Down Expand Up @@ -1614,6 +1628,7 @@ def _try_get_mock(
submodule_name="query",
input_value=input_value,
kind=SpanKind.CLIENT,
input_schema_merges={"parameters": SchemaMerge(match_importance=0.0)},
is_pre_app_start=not sdk.app_ready,
)

Expand Down
22 changes: 20 additions & 2 deletions drift/instrumentation/psycopg2/instrumentation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
from opentelemetry.trace import StatusCode as OTelStatusCode

from ...core.drift_sdk import TuskDrift
from ...core.json_schema_helper import JsonSchemaHelper
from ...core.json_schema_helper import JsonSchemaHelper, SchemaMerge
from ...core.mode_utils import handle_record_mode, handle_replay_mode
from ...core.tracing import TdSpanAttributes
from ...core.tracing.span_utils import CreateSpanOptions, SpanUtils
Expand Down Expand Up @@ -822,6 +822,9 @@ def _try_get_mock(
# Use centralized mock finding utility
from ...core.mock_utils import find_mock_response_sync

# Set match_importance=0 for parameters to allow fuzzy matching on query text
# This handles non-deterministic values like timestamps while still exact-matching
# deterministic values like IDs (exact hash match takes priority over reduced hash)
mock_response_output = find_mock_response_sync(
sdk=sdk,
trace_id=trace_id,
Expand All @@ -833,6 +836,7 @@ def _try_get_mock(
submodule_name="query",
input_value=input_value,
kind=SpanKind.CLIENT,
input_schema_merges={"parameters": SchemaMerge(match_importance=0.0)},
is_pre_app_start=not sdk.app_ready,
)

Expand Down Expand Up @@ -984,6 +988,14 @@ def _finalize_query_span(
# Serialize parameters to handle datetime and other non-JSON types
input_value["parameters"] = serialize_value(params)

# IMPORTANT: Tell the exporter (otel_converter) how to generate schema + hashes.
# The exporter recomputes the schema/hashes at export time from td.input_value and td.input_schema_merges.
# Mark parameters as match_importance=0.0 so non-deterministic values (e.g. timestamps) don't prevent mock matching.
span.set_attribute(
TdSpanAttributes.INPUT_SCHEMA_MERGES,
json.dumps({"parameters": {"match_importance": 0.0}}),
)

# Build output value
output_value = {}

Expand Down Expand Up @@ -1078,7 +1090,13 @@ def patched_fetchall():
logger.debug(f"Error getting query metadata: {e}")

# Generate schemas and hashes
input_result = JsonSchemaHelper.generate_schema_and_hash(input_value, {})
# Set match_importance=0 for parameters to allow fuzzy matching on query text
# This handles non-deterministic values like timestamps while still exact-matching
# deterministic values like IDs (exact hash match takes priority over reduced hash)
input_result = JsonSchemaHelper.generate_schema_and_hash(
input_value,
{"parameters": SchemaMerge(match_importance=0.0)},
)
output_result = JsonSchemaHelper.generate_schema_and_hash(output_value, {})

# Set span attributes
Expand Down