Compare commits

..

2 Commits

Author SHA1 Message Date
nityanandagohain
006a272297 fix: address comment 2026-10-30 18:02:48 +05:30
nityanandagohain
de24f430c2 feat(aiobservability): read the messages the Langfuse SDK writes 2026-10-30 17:38:50 +05:30
33 changed files with 196 additions and 320 deletions

View File

@@ -12131,8 +12131,6 @@ components:
additionalProperties:
type: string
type: object
scope:
$ref: '#/components/schemas/SpantypesScope'
spanId:
type: string
timestamp:
@@ -12149,7 +12147,6 @@ components:
- event
- attributes
- resource
- scope
type: object
SpantypesGettableFlamegraphTrace:
properties:
@@ -12390,16 +12387,6 @@ components:
nullable: true
type: array
type: object
SpantypesScope:
properties:
attributes:
additionalProperties: {}
type: object
name:
type: string
version:
type: string
type: object
SpantypesSpanAggregation:
properties:
aggregation:
@@ -12769,8 +12756,6 @@ components:
type: object
response_status_code:
type: string
scope:
$ref: '#/components/schemas/SpantypesScope'
span_id:
type: string
status_code:

View File

@@ -17,7 +17,7 @@ Condition: `model`, `llm.input_messages` (OpenInference sets `llm.model_name` fr
| `gen_ai.response.model`, last source for the request model | vLLM, which writes only the response model |
| `ai.model.id`, `ai.model.provider`, `ai.response.model`, `ai.response.finishReason`, `ai.prompt.messages`, `ai.response.text`, `ai.response.toolCalls`, `ai.usage.promptTokens`, `ai.usage.completionTokens` | Vercel AI SDK v4, Mastra |
| `ai.usage.inputTokens`, `ai.usage.outputTokens`, `ai.usage.cachedInputTokens`, `ai.usage.reasoningTokens` | Vercel AI SDK v5 |
| `langfuse.observation.model.name`, `langfuse.session.id` | Langfuse SDK v3 |
| `langfuse.observation.model.name`, `langfuse.observation.input`, `langfuse.observation.output`, `langfuse.observation.type`, `langfuse.session.id` | Langfuse SDK v3 (Python) and v4 (JS), LiteLLM `langfuse_otel` callback |
| `session.id` | OpenInference, Langfuse, Claude Code |
| `gen_ai.client.session_id` | opentelemetry-hooks runner (Cursor, Copilot, Claude Code hooks) |
| `model`, `input_tokens`, `output_tokens`, `cache_read_tokens`, `cache_creation_tokens` | Claude Code `claude_code.llm_request` spans ([docs](https://code.claude.com/docs/en/monitoring-usage#span-attributes)) |

View File

@@ -13264,23 +13264,6 @@ export type SpantypesFlamegraphSpanDTOAttributes = { [key: string]: unknown };
export type SpantypesFlamegraphSpanDTOResource = { [key: string]: string };
export type SpantypesScopeDTOAttributes = { [key: string]: unknown };
export interface SpantypesScopeDTO {
/**
* @type object
*/
attributes?: SpantypesScopeDTOAttributes;
/**
* @type string
*/
name?: string;
/**
* @type string
*/
version?: string;
}
export interface SpantypesFlamegraphSpanDTO {
/**
* @type object
@@ -13316,7 +13299,6 @@ export interface SpantypesFlamegraphSpanDTO {
* @type object
*/
resource: SpantypesFlamegraphSpanDTOResource;
scope: SpantypesScopeDTO;
/**
* @type string
*/
@@ -13862,7 +13844,6 @@ export interface SpantypesWaterfallSpanDTO {
* @type string
*/
response_status_code?: string;
scope?: SpantypesScopeDTO;
/**
* @type string
*/

View File

@@ -20,7 +20,6 @@ function makeSpan(
event: [],
resource: {},
attributes: {},
scope: {},
...overrides,
};
}

View File

@@ -12,7 +12,6 @@ export const MOCK_SPAN: FlamegraphSpan = {
event: [],
resource: {},
attributes: {},
scope: {},
};
/** Nested spans structure for findSpanById tests */

View File

@@ -518,7 +518,6 @@ const flamegraphSpan = (span: BuiltSpan): SpantypesFlamegraphSpanDTO => ({
level: span.level,
attributes: span.template.attributes,
resource: resourceOf(span),
scope: {},
event: [],
});

View File

@@ -1,5 +1,5 @@
{
"version": 4,
"version": 5,
"definition": {
"name": "gen_ai.llm",
"condition": {
@@ -134,6 +134,12 @@
"fieldContext": "attribute",
"config": {
"sources": [
{
"key": "langfuse.observation.type",
"context": "attribute",
"operation": "copy",
"priority": 40
},
{
"key": "openinference.span.kind",
"context": "attribute",
@@ -356,6 +362,12 @@
"fieldContext": "attribute",
"config": {
"sources": [
{
"key": "langfuse.observation.input",
"context": "attribute",
"operation": "move",
"priority": 40
},
{
"key": "gen_ai.prompt",
"context": "attribute",
@@ -382,6 +394,12 @@
"fieldContext": "attribute",
"config": {
"sources": [
{
"key": "langfuse.observation.output",
"context": "attribute",
"operation": "move",
"priority": 40
},
{
"key": "gen_ai.completion",
"context": "attribute",

View File

@@ -28,7 +28,7 @@ const colServiceName = `resource_string_service$$$$name` // $ gets escaped so $$
// JSON holds the attributes.
var storableSpanColumns = []string{
"DISTINCT ON (span_id) timestamp", "duration_nano", "span_id", "has_error", "kind",
colServiceName, "name", "attributes", "resources_string", "scope",
colServiceName, "name", "attributes", "resources_string",
"if(notEmpty(attributes), map(), attributes_string) AS attributes_string",
"if(notEmpty(attributes), map(), attributes_number) AS attributes_number",
"if(notEmpty(attributes), map(), attributes_bool) AS attributes_bool",
@@ -382,7 +382,6 @@ func (s *traceStore) GetFlamegraphSpans(ctx context.Context, traceID string, sta
"if(notEmpty(attributes), map(), any(attributes_number)) AS attributes_number",
"if(notEmpty(attributes), map(), any(attributes_bool)) AS attributes_bool",
"any(resources_string) AS resources_string",
"any(scope) AS scope",
)
sb.From(fmt.Sprintf("%s.%s", spantypes.TraceDB, spantypes.TraceTable))
conditions := []string{

View File

@@ -154,7 +154,7 @@ func TestGetSpanCountByField(t *testing.T) {
}
func TestGetTraceSpans(t *testing.T) {
expectedSQL := "SELECT DISTINCT ON (span_id) timestamp, duration_nano, span_id, has_error, kind, resource_string_service$$name, name, attributes, resources_string, scope, if(notEmpty(attributes), map(), attributes_string) AS attributes_string, if(notEmpty(attributes), map(), attributes_number) AS attributes_number, if(notEmpty(attributes), map(), attributes_bool) AS attributes_bool, events, status_message, status_code_string, kind_string, parent_span_id, flags, is_remote, trace_state, status_code, db_name, db_operation, http_method, http_url, http_host, external_http_method, external_http_url, response_status_code, links as references FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY timestamp ASC, name ASC"
expectedSQL := "SELECT DISTINCT ON (span_id) timestamp, duration_nano, span_id, has_error, kind, resource_string_service$$name, name, attributes, resources_string, if(notEmpty(attributes), map(), attributes_string) AS attributes_string, if(notEmpty(attributes), map(), attributes_number) AS attributes_number, if(notEmpty(attributes), map(), attributes_bool) AS attributes_bool, events, status_message, status_code_string, kind_string, parent_span_id, flags, is_remote, trace_state, status_code, db_name, db_operation, http_method, http_url, http_host, external_http_method, external_http_url, response_status_code, links as references FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY timestamp ASC, name ASC"
s := newTestStore(sqlmock.QueryMatcherEqual)
s.Mock().ExpectSelect(expectedSQL).
@@ -171,12 +171,12 @@ func TestGetFlamegraphSpans(t *testing.T) {
}{
{
name: "NoSpanIDs_GeneratesBaseSQL",
sql: "SELECT span_id, any(parent_span_id) AS parent_span_id, any(timestamp) AS timestamp, any(duration_nano) AS duration_nano, any(has_error) AS has_error, any(name) AS name, any(events) AS events, any(attributes) AS attributes, if(notEmpty(attributes), map(), any(attributes_string)) AS attributes_string, if(notEmpty(attributes), map(), any(attributes_number)) AS attributes_number, if(notEmpty(attributes), map(), any(attributes_bool)) AS attributes_bool, any(resources_string) AS resources_string, any(scope) AS scope FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY span_id ORDER BY timestamp ASC, name ASC",
sql: "SELECT span_id, any(parent_span_id) AS parent_span_id, any(timestamp) AS timestamp, any(duration_nano) AS duration_nano, any(has_error) AS has_error, any(name) AS name, any(events) AS events, any(attributes) AS attributes, if(notEmpty(attributes), map(), any(attributes_string)) AS attributes_string, if(notEmpty(attributes), map(), any(attributes_number)) AS attributes_number, if(notEmpty(attributes), map(), any(attributes_bool)) AS attributes_bool, any(resources_string) AS resources_string FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY span_id ORDER BY timestamp ASC, name ASC",
},
{
name: "WithSpanIDs_GeneratesInClauseSQL",
spanIDs: []string{"span-1", "span-2"},
sql: "SELECT span_id, any(parent_span_id) AS parent_span_id, any(timestamp) AS timestamp, any(duration_nano) AS duration_nano, any(has_error) AS has_error, any(name) AS name, any(events) AS events, any(attributes) AS attributes, if(notEmpty(attributes), map(), any(attributes_string)) AS attributes_string, if(notEmpty(attributes), map(), any(attributes_number)) AS attributes_number, if(notEmpty(attributes), map(), any(attributes_bool)) AS attributes_bool, any(resources_string) AS resources_string, any(scope) AS scope FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND span_id IN (?, ?) GROUP BY span_id ORDER BY timestamp ASC, name ASC",
sql: "SELECT span_id, any(parent_span_id) AS parent_span_id, any(timestamp) AS timestamp, any(duration_nano) AS duration_nano, any(has_error) AS has_error, any(name) AS name, any(events) AS events, any(attributes) AS attributes, if(notEmpty(attributes), map(), any(attributes_string)) AS attributes_string, if(notEmpty(attributes), map(), any(attributes_number)) AS attributes_number, if(notEmpty(attributes), map(), any(attributes_bool)) AS attributes_bool, any(resources_string) AS resources_string FROM signoz_traces.distributed_signoz_index_v3 WHERE trace_id = ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND span_id IN (?, ?) GROUP BY span_id ORDER BY timestamp ASC, name ASC",
},
}

View File

@@ -43,15 +43,13 @@ func stripKeyAlias(name string) string {
// unwrapVariant decodes a scan envelope: the chcol.Variant the driver scans a Dynamic column (a JSON
// path such as body_v2.level) into, and the JSONValue a whole JSON column scans into. The attributes
// bag decodes flat so its dotted keys merge with the legacy attribute maps and a key stored at both a
// scalar and an object path stays two keys; the scope decodes flat too, keeping its attributes dotted;
// every other JSON column decodes nested.
// scalar and an object path stays two keys; every other JSON column decodes nested.
func unwrapVariant(name string, val any) any {
switch v := val.(type) {
case chcol.Variant:
return v.Any()
case telemetrystoretypes.JSONValue:
switch name {
case "attributes", "scope":
if name == "attributes" {
return v.Flatten()
}
return v.Nest()
@@ -628,9 +626,6 @@ func mergeSpanAttributeColumns(data map[string]any) {
if raw, ok := data["links"]; ok {
data["links"] = spantypes.ParseLinks(raw)
}
if column, ok := data["scope"].(map[string]any); ok {
data["scope"] = spantypes.NewScope(column)
}
}
// numericAsFloat converts numeric types to float64 efficiently.

View File

@@ -95,9 +95,6 @@ func jsonColumn(paths map[string]any) telemetrystoretypes.JSONValue {
func TestUnwrapVariant(t *testing.T) {
jsonCol := jsonColumn(map[string]any{"level": "error", "attrs.code": int64(500)})
nullCol := jsonColumn(map[string]any{"level": "error", "absent": chcol.Variant{}})
scopeAttrs := chcol.NewJSON()
scopeAttrs.SetValueAtPath("lib.lang", "go")
scopeCol := jsonColumn(map[string]any{"name": "io.opentelemetry.http", "version": "1.2.0", "attributes": scopeAttrs})
testCases := []struct {
name string
@@ -111,7 +108,6 @@ func TestUnwrapVariant(t *testing.T) {
{name: "JSONColumnNested", column: "body_v2", input: jsonCol, want: map[string]any{"level": "error", "attrs": map[string]any{"code": float64(500)}}},
{name: "AttributesColumnFlat", column: "attributes", input: jsonCol, want: map[string]any{"level": "error", "attrs.code": float64(500)}},
{name: "AttributesColumnDropsNullPaths", column: "attributes", input: nullCol, want: map[string]any{"level": "error"}},
{name: "ScopeColumnFlat", column: "scope", input: scopeCol, want: map[string]any{"name": "io.opentelemetry.http", "version": "1.2.0", "attributes": map[string]any{"lib.lang": "go"}}},
}
for _, testCase := range testCases {
t.Run(testCase.name, func(t *testing.T) {
@@ -136,32 +132,6 @@ func TestMergeSpanAttributeColumns_EmptyEventsAndLinks(t *testing.T) {
}
}
func TestMergeSpanAttributeColumns_Scope(t *testing.T) {
testCases := []struct {
name string
scope map[string]any
want spantypes.Scope
}{
{
name: "SetFields_Kept",
scope: map[string]any{"name": "io.opentelemetry.http", "version": "1.2.0", "attributes": map[string]any{"lib.lang": "go"}},
want: spantypes.Scope{"name": "io.opentelemetry.http", "version": "1.2.0", "attributes": map[string]any{"lib.lang": "go"}},
},
{
name: "UnsetDeclaredPaths_Empty",
scope: map[string]any{"name": "", "version": "", "attributes": map[string]any{}},
want: spantypes.Scope{},
},
}
for _, testCase := range testCases {
t.Run(testCase.name, func(t *testing.T) {
data := map[string]any{"scope": testCase.scope}
mergeSpanAttributeColumns(data)
assert.Equal(t, testCase.want, data["scope"])
})
}
}
// readAsRaw decodes the JSON column into a flat bag of dotted keys before this runs; mergeSpanAttributeColumns
// copies that bag and overlays the legacy string/number/bool maps, which win on collision.
func TestMergeSpanAttributeColumns_JSONColumn(t *testing.T) {

View File

@@ -45,7 +45,7 @@ SELECT timestamp AS __SELECT_KEY_0_timestamp, trace_id AS __SELECT_KEY_1_trace_i
http_url AS __SELECT_KEY_17_http_url, external_http_method AS __SELECT_KEY_18_external_http_method,
http_method AS __SELECT_KEY_19_http_method, http_host AS __SELECT_KEY_20_http_host, db_name AS __SELECT_KEY_21_db_name,
db_operation AS __SELECT_KEY_22_db_operation, has_error AS __SELECT_KEY_23_has_error, is_remote AS __SELECT_KEY_24_is_remote,
attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope
attributes_string, attributes_number, attributes_bool, resources_string, attributes
FROM signoz_traces.distributed_signoz_index_v3
WHERE trace_id GLOBAL IN (SELECT trace_id FROM __trace_scope)
AND (((mapContains(attributes_string, 'gen_ai.request.model')

View File

@@ -676,7 +676,7 @@ SELECT timestamp AS __SELECT_KEY_0_timestamp, trace_id AS __SELECT_KEY_1_trace_i
http_url AS __SELECT_KEY_17_http_url, external_http_method AS __SELECT_KEY_18_external_http_method,
http_method AS __SELECT_KEY_19_http_method, http_host AS __SELECT_KEY_20_http_host, db_name AS __SELECT_KEY_21_db_name,
db_operation AS __SELECT_KEY_22_db_operation, has_error AS __SELECT_KEY_23_has_error, is_remote AS __SELECT_KEY_24_is_remote,
attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope
attributes_string, attributes_number, attributes_bool, resources_string, attributes
FROM signoz_traces.distributed_signoz_index_v3
WHERE (((mapContains(attributes_string, 'gen_ai.request.model')
OR mapContains(attributes_string, 'gen_ai.tool.name')

View File

@@ -581,7 +581,7 @@ func TestStatementBuilderListQuery(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint) SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY multiIf(mapContains(attributes_string, 'user.id'), attributes_string['user.id'], NULL) desc LIMIT ?",
Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint) SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY multiIf(mapContains(attributes_string, 'user.id'), attributes_string['user.id'], NULL) desc LIMIT ?",
Args: []any{"redis-manual", "%service.name%", "%service.name\":\"redis-manual%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -837,7 +837,7 @@ func TestStatementBuilderListQueryWithCorruptData(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -879,7 +879,7 @@ func TestStatementBuilderListQueryWithCorruptData(t *testing.T) {
}},
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY timestamp asc LIMIT ?",
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? ORDER BY timestamp asc LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -906,7 +906,7 @@ func TestStatementBuilderListQueryWithCorruptData(t *testing.T) {
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},

View File

@@ -124,7 +124,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B AS (WITH RECURSIVE up AS (SELECT d.trace_id, d.span_id, d.parent_span_id, 0 AS depth FROM B AS d UNION ALL SELECT p.trace_id, p.span_id, p.parent_span_id, up.depth + 1 FROM all_spans AS p JOIN up ON p.trace_id = up.trace_id AND p.span_id = up.parent_span_id WHERE up.depth < 100) SELECT DISTINCT a.* FROM A AS a GLOBAL INNER JOIN (SELECT DISTINCT trace_id, span_id FROM up WHERE depth > 0 ) AS ancestors ON ancestors.trace_id = a.trace_id AND ancestors.span_id = a.span_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM A_INDIR_DESC_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B AS (WITH RECURSIVE up AS (SELECT d.trace_id, d.span_id, d.parent_span_id, 0 AS depth FROM B AS d UNION ALL SELECT p.trace_id, p.span_id, p.parent_span_id, up.depth + 1 FROM all_spans AS p JOIN up ON p.trace_id = up.trace_id AND p.span_id = up.parent_span_id WHERE up.depth < 100) SELECT DISTINCT a.* FROM A AS a GLOBAL INNER JOIN (SELECT DISTINCT trace_id, span_id FROM up WHERE depth > 0 ) AS ancestors ON ancestors.trace_id = a.trace_id AND ancestors.span_id = a.span_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM A_INDIR_DESC_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "gateway", "%service.name%", "%service.name\":\"gateway%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "database", "%service.name%", "%service.name\":\"database%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 5},
},
expectedErr: nil,
@@ -161,7 +161,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_AND_B AS (SELECT l.* FROM A AS l INNER JOIN B AS r ON l.trace_id = r.trace_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM A_AND_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_AND_B AS (SELECT l.* FROM A AS l INNER JOIN B AS r ON l.trace_id = r.trace_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM A_AND_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "backend", "%service.name%", "%service.name\":\"backend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 15},
},
expectedErr: nil,
@@ -198,7 +198,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_OR_B AS (SELECT * FROM A UNION DISTINCT SELECT * FROM B) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM A_OR_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_OR_B AS (SELECT * FROM A UNION DISTINCT SELECT * FROM B) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM A_OR_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "backend", "%service.name%", "%service.name\":\"backend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 20},
},
expectedErr: nil,
@@ -235,7 +235,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_not_B AS (SELECT l.* FROM A AS l WHERE l.trace_id GLOBAL NOT IN (SELECT DISTINCT trace_id FROM B)) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM A_not_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_not_B AS (SELECT l.* FROM A AS l WHERE l.trace_id GLOBAL NOT IN (SELECT DISTINCT trace_id FROM B)) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM A_not_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "backend", "%service.name%", "%service.name\":\"backend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -400,7 +400,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_DIR_DESC_B AS (SELECT p.* FROM A AS p INNER JOIN B AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id), __resource_filter_C AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), C AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_C) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_D AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), D AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_D) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), C_DIR_DESC_D AS (SELECT p.* FROM C AS p INNER JOIN D AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id), A_DIR_DESC_B_AND_C_DIR_DESC_D AS (SELECT l.* FROM A_DIR_DESC_B AS l INNER JOIN C_DIR_DESC_D AS r ON l.trace_id = r.trace_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM A_DIR_DESC_B_AND_C_DIR_DESC_D ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_DIR_DESC_B AS (SELECT p.* FROM A AS p INNER JOIN B AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id), __resource_filter_C AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), C AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_C) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_D AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), D AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_D) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), C_DIR_DESC_D AS (SELECT p.* FROM C AS p INNER JOIN D AS c ON p.trace_id = c.trace_id AND p.span_id = c.parent_span_id), A_DIR_DESC_B_AND_C_DIR_DESC_D AS (SELECT l.* FROM A_DIR_DESC_B AS l INNER JOIN C_DIR_DESC_D AS r ON l.trace_id = r.trace_id) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM A_DIR_DESC_B_AND_C_DIR_DESC_D ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "frontend", "%service.name%", "%service.name\":\"frontend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "backend", "%service.name%", "%service.name\":\"backend%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "auth", "%service.name%", "%service.name\":\"auth%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "database", "%service.name%", "%service.name\":\"database%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 5},
},
expectedErr: nil,
@@ -434,7 +434,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B AS (WITH RECURSIVE up AS (SELECT d.trace_id, d.span_id, d.parent_span_id, 0 AS depth FROM B AS d UNION ALL SELECT p.trace_id, p.span_id, p.parent_span_id, up.depth + 1 FROM all_spans AS p JOIN up ON p.trace_id = up.trace_id AND p.span_id = up.parent_span_id WHERE up.depth < 100) SELECT DISTINCT a.* FROM A AS a GLOBAL INNER JOIN (SELECT DISTINCT trace_id, span_id FROM up WHERE depth > 0 ) AS ancestors ON ancestors.trace_id = a.trace_id AND ancestors.span_id = a.span_id), __return_from_B AS (SELECT * FROM B WHERE trace_id IN (SELECT DISTINCT trace_id FROM A_INDIR_DESC_B)) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM __return_from_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B AS (WITH RECURSIVE up AS (SELECT d.trace_id, d.span_id, d.parent_span_id, 0 AS depth FROM B AS d UNION ALL SELECT p.trace_id, p.span_id, p.parent_span_id, up.depth + 1 FROM all_spans AS p JOIN up ON p.trace_id = up.trace_id AND p.span_id = up.parent_span_id WHERE up.depth < 100) SELECT DISTINCT a.* FROM A AS a GLOBAL INNER JOIN (SELECT DISTINCT trace_id, span_id FROM up WHERE depth > 0 ) AS ancestors ON ancestors.trace_id = a.trace_id AND ancestors.span_id = a.span_id), __return_from_B AS (SELECT * FROM B WHERE trace_id IN (SELECT DISTINCT trace_id FROM A_INDIR_DESC_B)) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM __return_from_B ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "gateway", "%service.name%", "%service.name\":\"gateway%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "database", "%service.name%", "%service.name\":\"database%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,
@@ -476,7 +476,7 @@ func TestTraceOperatorStatementBuilder(t *testing.T) {
},
},
expected: qbtypes.Statement{
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B AS (WITH RECURSIVE up AS (SELECT d.trace_id, d.span_id, d.parent_span_id, 0 AS depth FROM B AS d UNION ALL SELECT p.trace_id, p.span_id, p.parent_span_id, up.depth + 1 FROM all_spans AS p JOIN up ON p.trace_id = up.trace_id AND p.span_id = up.parent_span_id WHERE up.depth < 100) SELECT DISTINCT a.* FROM A AS a GLOBAL INNER JOIN (SELECT DISTINCT trace_id, span_id FROM up WHERE depth > 0 ) AS ancestors ON ancestors.trace_id = a.trace_id AND ancestors.span_id = a.span_id), __resource_filter_C AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), C AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_C) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B_AND_C AS (SELECT l.* FROM A_INDIR_DESC_B AS l INNER JOIN C AS r ON l.trace_id = r.trace_id), __return_from_C AS (SELECT * FROM C WHERE trace_id IN (SELECT DISTINCT trace_id FROM A_INDIR_DESC_B_AND_C)) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes, scope FROM __return_from_C ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Query: "WITH toDateTime64(1747947419000000000, 9) AS t_from, toDateTime64(1747983448000000000, 9) AS t_to, 1747945619 AS bucket_from, 1747983448 AS bucket_to, all_spans AS (SELECT *, resource_string_service$$name AS `service.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_A AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), A AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_A) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), __resource_filter_B AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), B AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_B) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B AS (WITH RECURSIVE up AS (SELECT d.trace_id, d.span_id, d.parent_span_id, 0 AS depth FROM B AS d UNION ALL SELECT p.trace_id, p.span_id, p.parent_span_id, up.depth + 1 FROM all_spans AS p JOIN up ON p.trace_id = up.trace_id AND p.span_id = up.parent_span_id WHERE up.depth < 100) SELECT DISTINCT a.* FROM A AS a GLOBAL INNER JOIN (SELECT DISTINCT trace_id, span_id FROM up WHERE depth > 0 ) AS ancestors ON ancestors.trace_id = a.trace_id AND ancestors.span_id = a.span_id), __resource_filter_C AS (SELECT fingerprint FROM signoz_traces.distributed_traces_v3_resource WHERE (simpleJSONExtractString(labels, 'service.name') = ? AND labels LIKE ? AND labels LIKE ?) AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ? GROUP BY fingerprint), C AS (SELECT * FROM signoz_traces.distributed_signoz_index_v3 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter_C) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ?), A_INDIR_DESC_B_AND_C AS (SELECT l.* FROM A_INDIR_DESC_B AS l INNER JOIN C AS r ON l.trace_id = r.trace_id), __return_from_C AS (SELECT * FROM C WHERE trace_id IN (SELECT DISTINCT trace_id FROM A_INDIR_DESC_B_AND_C)) SELECT timestamp, trace_id, span_id, name, duration_nano, parent_span_id, trace_state AS `__SELECT_KEY_3_trace_state`, flags AS `__SELECT_KEY_5_flags`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_is_remote`, attributes_string, attributes_number, attributes_bool, resources_string, attributes FROM __return_from_C ORDER BY timestamp DESC LIMIT ? SETTINGS distributed_product_mode='allow', max_memory_usage=10000000000",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "gateway", "%service.name%", "%service.name\":\"gateway%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "database", "%service.name%", "%service.name\":\"database%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), "auth", "%service.name%", "%service.name\":\"auth%", uint64(1747945619), uint64(1747983448), "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
expectedErr: nil,

View File

@@ -46,7 +46,6 @@ const (
SpanAttributesColumn = "attributes"
SpanAttributesPromotedColumn = "attributes_promoted"
SpanResourcesStringColumn = "resources_string"
SpanScopeColumn = "scope"
)
var (
@@ -456,7 +455,6 @@ var (
SpanAttributesBoolColumn,
SpanResourcesStringColumn,
SpanAttributesColumn,
SpanScopeColumn,
}
DefaultFields = map[string]telemetrytypes.TelemetryFieldKey{

View File

@@ -121,10 +121,13 @@ func (f *formatting) messages() {
// OpenRouter's answer object or an Anthropic response beside the OpenAI chat request it answers is one
// format, not a mix: an Anthropic request without system and without Anthropic-only blocks reads as an
// OpenAI chat request.
// OpenAI chat request. A side kept as generic already warned, and a side read from OpenInference's
// buckets beside the raw payload of the other is the documented fallback.
func (f *formatting) warnMixedFormats(inputLabel, outputLabel string) {
switch {
case inputLabel == "" || outputLabel == "" || outputLabel == inputLabel:
case inputLabel == FormatterGeneric || outputLabel == FormatterGeneric:
case inputLabel == FormatterOpenInference || outputLabel == FormatterOpenInference:
case inputLabel == FormatterOpenAIChat && (outputLabel == FormatterOpenRouter || outputLabel == FormatterAnthropic):
default:
f.warn("output formatted as %s, input as %s", outputLabel, inputLabel)
@@ -183,11 +186,16 @@ func (f *formatting) side(value any, role Role) (OutputMessages, string) {
return f.semconv(v), FormatterSemconv
case isAnthropicMessages(v):
return f.anthropicMessages(v), FormatterAnthropic
case isResponsesItems(v):
return foldAssistant(f.responsesItems(v)), FormatterOpenAIResponses
case first["role"] != nil:
return f.openAIChatMessages(v), FormatterOpenAIChat
}
}
case map[string]any:
if inner, ok := superJSON(v); ok {
return f.side(decode(inner), role)
}
switch {
case isLangChainRun(v):
return f.langChainRun(v), FormatterLangChain
@@ -214,6 +222,9 @@ func (f *formatting) side(value any, role Role) (OutputMessages, string) {
if messages, ok := v["messages"].([]any); ok {
return f.openAIChatMessages(messages), FormatterOpenAIChat
}
if (v["role"] != nil && hasKeys(v, "content")) || v["tool_calls"] != nil {
return OutputMessages{f.openAIChatSingle(v)}, FormatterOpenAIChat
}
case string:
if v == "" {
return OutputMessages{}, FormatterText
@@ -309,6 +320,23 @@ func foldAssistant(msgs OutputMessages) OutputMessages {
return out
}
// superJSON unwraps {json, meta?}, the envelope superjson, the transformer tRPC apps serialise with,
// puts around a value; a Langfuse generation records it around the request when the app passes the
// serialised form:
// https://github.com/flightcontrolhq/superjson/blob/aaa65e36e8e31da740265a56b27c965ca1c7b754/README.md
func superJSON(m map[string]any) (any, bool) {
inner, ok := m["json"]
if !ok {
return nil, false
}
for key := range m {
if key != "json" && key != "meta" {
return nil, false
}
}
return inner, true
}
// decode parses a JSON-encoded attribute value, twice when an SDK encoded the string again.
// Anything that is not JSON is returned as is.
func decode(value any) any {

View File

@@ -4,8 +4,9 @@ import (
"strings"
)
// Format: OpenAI Chat Completions, a request {messages}, a response {choices}, or a bare message list.
// Written by: bifrost, openrouter requests, the raw OpenAI calls OpenInference records.
// Format: OpenAI Chat Completions, a request {messages}, a response {choices}, a bare message list, or a
// single message.
// Written by: bifrost, openrouter requests, the raw OpenAI calls OpenInference records, the Langfuse SDK.
// Handled: string and block content, tool_calls nested or flattened, tool messages, refusal,
// reasoning_content, finish reasons.
// Not yet: streaming delta chunks, legacy completions choices[].text, audio output.
@@ -88,6 +89,19 @@ func (f *formatting) openAIChatMessage(m map[string]any) OutputMessage {
return msg
}
// openAIChatSingle converts a message recorded outside a list: the first choice's message the Langfuse
// OpenAI wrapper writes as the output, or the additional_kwargs of a LangChain AIMessage, {tool_calls}
// without a role, which the Langfuse LangChain handler writes for a tool-calling turn:
// https://github.com/langfuse/langfuse-python/blob/18baf80450dd5f9c1f85916eb2d1b3c72d2052e1/langfuse/openai.py#L446
// https://github.com/langfuse/langfuse-python/blob/18baf80450dd5f9c1f85916eb2d1b3c72d2052e1/langfuse/langchain/CallbackHandler.py#L1558
func (f *formatting) openAIChatSingle(m map[string]any) OutputMessage {
msg := f.openAIChatMessage(m)
if msg.Role.IsZero() {
msg.Role = RoleAssistant
}
return msg
}
// toolCallPart reads {id, function: {name, arguments}}; a gateway may flatten it to {id, name, arguments|args}.
func toolCallPart(c map[string]any) Part {
call := ToolCallRequestPart{Type: PartTypeToolCall, ID: optionalString(c["id"]), Name: stringOf(c["name"])}

View File

@@ -205,6 +205,30 @@ func TestFormat_OpenAIChat(t *testing.T) {
]`,
wantOutput: `[]`,
},
{
// Langfuse SDK generation: the history as a list, the first choice's message as the output
name: "SingleMessageOutput_AssistantMessage",
input: `[{"role": "system", "content": "You are a support agent on a phone call."}, {"role": "user", "content": "Hello?"}]`,
output: `{"role": "assistant", "content": "Hi, this is a courtesy call about your order. Do you have a minute?"}`,
wantInput: `[{"role": "system", "parts": [{"type": "text", "content": "You are a support agent on a phone call."}]}, {"role": "user", "parts": [{"type": "text", "content": "Hello?"}]}]`,
wantOutput: `[{"role": "assistant", "parts": [{"type": "text", "content": "Hi, this is a courtesy call about your order. Do you have a minute?"}]}]`,
},
{
// a structured output that happens to carry a role key is not a message
name: "ObjectWithRoleKeyButNoContent_KeptAsGeneric",
output: `{"role": "admin", "permissions": ["read", "write"]}`,
warnings: []string{"message format not recognised, kept as generic"},
wantInput: `[]`,
wantOutput: `[{"role": "", "parts": [{"type": "generic", "content": "{\"permissions\":[\"read\",\"write\"],\"role\":\"admin\"}"}]}]`,
},
{
// Langfuse LangChain handler: the additional_kwargs of the AIMessage, without a role, as the output
// of a tool-calling turn
name: "RolelessToolCallsOutput_AssistantToolCallPart",
output: `{"tool_calls": [{"id": "call_1", "type": "function", "function": {"name": "get_weather", "arguments": "{\"city\": \"Oslo\"}"}}], "refusal": null}`,
wantInput: `[]`,
wantOutput: `[{"role": "assistant", "parts": [{"type": "tool_call", "name": "get_weather", "id": "call_1", "arguments": {"city": "Oslo"}}]}]`,
},
{
name: "ResponseWithScalarChoice_KeptAsGeneric",
output: `{"choices":["oops",{"finish_reason":"stop","index":1,"message":{"role":"assistant","content":"hi"}}]}`,

View File

@@ -2,13 +2,15 @@ package aiobservabilitytypes
import "strings"
// Format: OpenAI Responses, a request {input, instructions} or a response {output, status} of items:
// Format: OpenAI Responses, a request {input, instructions}, a response {output, status} or a bare list
// of items:
// https://github.com/openai/openai-openapi/blob/aeb6a041dc56c011ca9f12127ec898f911100aa0/openapi.yaml#L47597
// https://github.com/openai/openai-openapi/blob/aeb6a041dc56c011ca9f12127ec898f911100aa0/openapi.yaml#L69691
// https://github.com/openai/openai-openapi/blob/aeb6a041dc56c011ca9f12127ec898f911100aa0/openapi.yaml#L53834
// https://github.com/openai/openai-openapi/blob/aeb6a041dc56c011ca9f12127ec898f911100aa0/openapi.yaml#L57596
// Written by: gateways recording raw Responses bodies, and the raw calls OpenInference records for the
// Responses API and the OpenAI Agents SDK when its flattened messages are absent.
// Written by: gateways recording raw Responses bodies, the raw calls OpenInference records for the
// Responses API and the OpenAI Agents SDK when its flattened messages are absent, and LiteLLM's
// langfuse_otel callback, the function_call items of a tool-calling turn as a bare list.
// Handled: message items with input_text, output_text, refusal, input_image and input_file content;
// function_call and custom_tool_call with their outputs; reasoning summaries; compaction; every other
// *_call item as a server tool call and *_output item as its response; the status and incomplete_details
@@ -32,6 +34,19 @@ func isResponsesRequest(m map[string]any) bool {
return isItem
}
// isResponsesItems looks for an item only the Responses API has, a tool call or its output, a reasoning
// or compaction item, all without a role; a list of messages has none.
func isResponsesItems(list []any) bool {
for _, item := range list {
m, _ := item.(map[string]any)
typ := stringOf(m["type"])
if m["role"] == nil && (typ == "reasoning" || typ == "compaction" || typ == "mcp_approval_response" || strings.HasSuffix(typ, "_call") || strings.HasSuffix(typ, "_output")) {
return true
}
}
return false
}
func isResponsesResponse(m map[string]any) bool {
if _, ok := m["output"].([]any); !ok {
return false

View File

@@ -73,6 +73,23 @@ func TestFormat_OpenAIResponses(t *testing.T) {
wantInput: `[{"role": "system", "parts": [{"type": "text", "content": "Be brief."}]}, {"role": "user", "parts": [{"type": "text", "content": "Say hi"}]}]`,
wantOutput: `[]`,
},
{
// LiteLLM langfuse_otel: the function_call items of a tool-calling turn as a bare list
name: "BareFunctionCallItems_OneAssistantMessage",
output: `[{"id": "chatcmpl-1", "name": "set_stage", "call_id": "call_7", "type": "function_call", "arguments": {"fields": {"stage": "consent"}}}]`,
wantInput: `[]`,
wantOutput: `[{"role": "assistant", "parts": [{"type": "tool_call", "name": "set_stage", "id": "call_7", "arguments": {"fields": {"stage": "consent"}}}]}]`,
},
{
name: "BareItemsWithMessage_ToolRound",
input: `[{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Weather in Oslo?"}]}, {"type": "function_call", "call_id": "call_9", "name": "get_weather", "arguments": "{\"city\":\"Oslo\"}"}, {"type": "function_call_output", "call_id": "call_9", "output": "4C, cloudy"}]`,
wantInput: `[
{"role": "user", "parts": [{"type": "text", "content": "Weather in Oslo?"}]},
{"role": "assistant", "parts": [{"type": "tool_call", "name": "get_weather", "id": "call_9", "arguments": {"city": "Oslo"}}]},
{"role": "tool", "parts": [{"type": "tool_call_response", "id": "call_9", "response": "4C, cloudy"}]}
]`,
wantOutput: `[]`,
},
{
// openinference capture, CreateEmbeddings span: an embeddings request also has input and model
name: "EmbeddingsRequest_NotResponses_KeptAsGeneric",

View File

@@ -4,8 +4,9 @@ import "github.com/SigNoz/signoz/pkg/valuer"
// Format: the flattened llm.input_messages.N.message.* and llm.output_messages.N.message.* keys, the
// provider-neutral copy of the conversation the OpenInference instrumentations write on LLM spans. A side
// without them falls back to the raw provider payload the mapper moved onto gen_ai.*.messages; pipecat
// streams the reply into output.value alone.
// without them, or whose buckets hold no message, falls back to the raw provider payload the mapper moved
// onto gen_ai.*.messages; pipecat streams the reply into output.value alone, LiteLLM's OpenInference mode
// leaves the output bucket empty on a tool-calling turn.
// https://github.com/Arize-ai/openinference/blob/12f2cc035edfb00b60b656d977f07abfb7a69900/spec/semantic_conventions.md#L77
// https://github.com/Arize-ai/openinference/blob/12f2cc035edfb00b60b656d977f07abfb7a69900/spec/tool_calling.md#L37
// https://github.com/Arize-ai/openinference/blob/12f2cc035edfb00b60b656d977f07abfb7a69900/spec/multimodal_attributes.md#L35
@@ -28,15 +29,14 @@ func (f *formatting) openInference() bool {
return false
}
inputLabel, outputLabel := FormatterOpenInference, FormatterOpenInference
if len(input) > 0 {
f.out.Input = inputMessages(openInferenceMessages(input))
if msgs := openInferenceMessages(input); len(msgs) > 0 {
f.out.Input = inputMessages(msgs)
} else if raw := attribute(f.attributes, GenAIInputMessages); raw != nil {
var msgs OutputMessages
msgs, inputLabel = f.side(decode(raw), RoleUser)
f.out.Input = inputMessages(msgs)
}
if len(output) > 0 {
f.out.Output = openInferenceMessages(output)
if msgs := openInferenceMessages(output); len(msgs) > 0 {
f.out.Output = msgs
if fr := finishReason(stringOf(attribute(f.attributes, openInferenceFinishReason))); fr != nil {
for i := range f.out.Output {
f.out.Output[i].FinishReason = fr

View File

@@ -160,16 +160,30 @@ func TestFormat_OpenInference(t *testing.T) {
// which the mapper moves onto gen_ai.output.messages
// https://github.com/Arize-ai/openinference/blob/12f2cc035edfb00b60b656d977f07abfb7a69900/python/instrumentation/openinference-instrumentation-pipecat/src/openinference/instrumentation/pipecat/_attributes.py#L430
// https://github.com/Arize-ai/openinference/blob/12f2cc035edfb00b60b656d977f07abfb7a69900/python/instrumentation/openinference-instrumentation-pipecat/src/openinference/instrumentation/pipecat/_observer.py#L628
name: "OutputKeysAbsent_RawOutputFormatted_Warns",
name: "OutputKeysAbsent_RawOutputFormatted",
attributes: map[string]any{
"llm.input_messages.0.message.role": "user",
"llm.input_messages.0.message.content": "hi",
GenAIOutputMessages: "Hello there.",
},
warnings: []string{"bare assistant text, role assumed", "output formatted as text, input as openinference"},
warnings: []string{"bare assistant text, role assumed"},
wantInput: `[{"role": "user", "parts": [{"type": "text", "content": "hi"}]}]`,
wantOutput: `[{"role": "assistant", "parts": [{"type": "text", "content": "Hello there."}]}]`,
},
{
// LiteLLM's OpenInference mode leaves the output bucket empty on a tool-calling turn; the calls are
// the Langfuse output the mapper moved onto gen_ai.output.messages
name: "EmptyOutputBucket_RawOutputFormatted",
attributes: map[string]any{
"llm.input_messages.0.message.role": "user",
"llm.input_messages.0.message.content": "Yes, go ahead.",
"llm.output_messages.0.message.role": "assistant",
"llm.output_messages.0.message.content": "",
GenAIOutputMessages: `[{"id": "chatcmpl-2", "name": "set_stage", "call_id": "call_8", "type": "function_call", "arguments": {"fields": {"stage": "email"}}}]`,
},
wantInput: `[{"role": "user", "parts": [{"type": "text", "content": "Yes, go ahead."}]}]`,
wantOutput: `[{"role": "assistant", "parts": [{"type": "tool_call", "name": "set_stage", "id": "call_8", "arguments": {"fields": {"stage": "email"}}}]}]`,
},
{
// message.role left unset by some instrumentors: tool_call_id, tool_calls or neither decide it,
// as the collector-contrib normalizer does

View File

@@ -122,6 +122,31 @@ So, the ball costs 5 cents.`,
wantInput: `[]`,
wantOutput: `[]`,
},
{
// Langfuse SDK generation: the app passes the request through superjson, the output is the parsed
// structured output
name: "SuperJSONEnvelope_Unwrapped_StructuredOutputGeneric",
input: `{"json": {"model": "gpt-4o-mini", "messages": [{"role": "system", "content": "Extract the main article of the page as JSON."}, {"role": "user", "content": "# Council approves new bike lanes"}], "temperature": 0}}`,
output: `{"hasArticle": true, "article": {"title": "Council approves new bike lanes"}}`,
warnings: []string{"message format not recognised, kept as generic"},
wantInput: `[{"role": "system", "parts": [{"type": "text", "content": "Extract the main article of the page as JSON."}]}, {"role": "user", "parts": [{"type": "text", "content": "# Council approves new bike lanes"}]}]`,
wantOutput: `[{"role": "", "parts": [{"type": "generic", "content": "{\"article\":{\"title\":\"Council approves new bike lanes\"},\"hasArticle\":true}"}]}]`,
},
{
name: "SuperJSONEnvelopeWithMeta_Unwrapped",
input: `{"json": {"messages": [{"role": "user", "content": "What time is it in Oslo?"}]}, "meta": {"values": {"messages.0.at": ["Date"]}}}`,
output: `{"json": {"choices": [{"finish_reason": "stop", "message": {"role": "assistant", "content": "It is 14:05 in Oslo."}}]}, "meta": {"values": {}}}`,
wantInput: `[{"role": "user", "parts": [{"type": "text", "content": "What time is it in Oslo?"}]}]`,
wantOutput: `[{"role": "assistant", "parts": [{"type": "text", "content": "It is 14:05 in Oslo."}], "finish_reason": "stop"}]`,
},
{
// a json key beside others is a payload of its own, not the envelope
name: "JSONKeyBesideOthers_NotUnwrapped_Generic",
input: `{"json": {"messages": []}, "schema": "v1"}`,
warnings: []string{"message format not recognised, kept as generic"},
wantInput: `[{"role": "", "parts": [{"type": "generic", "content": "{\"json\":{\"messages\":[]},\"schema\":\"v1\"}"}]}]`,
wantOutput: `[]`,
},
{
name: "NoMessageAttributes_EmptyLists",
attributes: map[string]any{GenAIRequestModel: "gpt-4o", GenAIToolName: "get_weather"},

View File

@@ -17,7 +17,6 @@ type FlamegraphSpan struct {
Events []Event `json:"event" required:"true" nullable:"false"`
Attributes map[string]any `json:"attributes" required:"true" nullable:"false"`
Resource map[string]string `json:"resource" required:"true" nullable:"false"`
Scope Scope `json:"scope" required:"true" nullable:"false"`
Children []*FlamegraphSpan `json:"-"` // internal tree use only
}
@@ -67,13 +66,11 @@ func NewFlamegraphSpanFromStorable(s *StorableSpan, level int64, selectFields []
Events: s.UnmarshalledEvents(),
Attributes: make(map[string]any),
Resource: make(map[string]string),
Scope: Scope{},
}
if len(selectFields) == 0 {
return span
}
var attributes map[string]any
var scopeFields []string
for _, field := range selectFields {
switch field.FieldContext {
case telemetrytypes.FieldContextResource:
@@ -87,13 +84,8 @@ func NewFlamegraphSpanFromStorable(s *StorableSpan, level int64, selectFields []
if v, ok := attributes[field.Name]; ok {
span.Attributes[field.Name] = v
}
case telemetrytypes.FieldContextScope:
scopeFields = append(scopeFields, field.Name)
}
}
if len(scopeFields) > 0 {
span.Scope = NewSelectedScope(s.Scope.Flatten(), scopeFields)
}
return span
}
@@ -104,7 +96,6 @@ func NewMissingParentFlamegraphSpan(node *FlamegraphSpan) *FlamegraphSpan {
Timestamp: node.Timestamp,
DurationNano: node.DurationNano,
Events: []Event{},
Scope: Scope{},
Children: []*FlamegraphSpan{node},
}
}

View File

@@ -1,11 +1,9 @@
package spantypes
import (
"encoding/json"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
)
@@ -17,7 +15,6 @@ func TestNewFlamegraphSpanFromStorable_SelectFields(t *testing.T) {
selectFields []telemetrytypes.TelemetryFieldKey
wantAttrs map[string]any
wantResource map[string]string
wantScope Scope
}{
{
name: "JSONColumn_ResolvesDottedPaths",
@@ -29,7 +26,6 @@ func TestNewFlamegraphSpanFromStorable_SelectFields(t *testing.T) {
},
wantAttrs: map[string]any{"http.route": "/orders", "http.retry.count": float64(2)},
wantResource: map[string]string{},
wantScope: Scope{},
},
{
name: "LegacyMaps_Resolve",
@@ -41,7 +37,6 @@ func TestNewFlamegraphSpanFromStorable_SelectFields(t *testing.T) {
},
wantAttrs: map[string]any{"http.route": "/cart", "cache.hit": true},
wantResource: map[string]string{},
wantScope: Scope{},
},
{
name: "ResourceFields_EmptyValueSkipped",
@@ -52,30 +47,6 @@ func TestNewFlamegraphSpanFromStorable_SelectFields(t *testing.T) {
},
wantAttrs: map[string]any{},
wantResource: map[string]string{"service.name": "checkout"},
wantScope: Scope{},
},
{
name: "ScopeFields_DeclaredPathsAndAttributes",
span: StorableSpan{Scope: scopeColumn("io.opentelemetry.http", "1.2.0", map[string]any{"lib.lang": "go", "team": "payments"})},
selectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "scope.name", FieldContext: telemetrytypes.FieldContextScope},
{Name: "lib.lang", FieldContext: telemetrytypes.FieldContextScope},
{Name: "missing", FieldContext: telemetrytypes.FieldContextScope},
},
wantAttrs: map[string]any{},
wantResource: map[string]string{},
wantScope: Scope{"name": "io.opentelemetry.http", "attributes": map[string]any{"lib.lang": "go"}},
},
{
name: "ScopeFields_UnsetSelection_Empty",
span: StorableSpan{Scope: scopeColumn("io.opentelemetry.grpc", "", map[string]any{"rpc.system": "grpc"})},
selectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "scope.version", FieldContext: telemetrytypes.FieldContextScope},
{Name: "absent", FieldContext: telemetrytypes.FieldContextScope},
},
wantAttrs: map[string]any{},
wantResource: map[string]string{},
wantScope: Scope{},
},
}
for _, testCase := range testCases {
@@ -83,15 +54,6 @@ func TestNewFlamegraphSpanFromStorable_SelectFields(t *testing.T) {
span := NewFlamegraphSpanFromStorable(&testCase.span, 0, testCase.selectFields)
assert.Equal(t, testCase.wantAttrs, span.Attributes)
assert.Equal(t, testCase.wantResource, span.Resource)
assert.Equal(t, testCase.wantScope, span.Scope)
})
}
}
func TestNewMissingParentFlamegraphSpan_EmptyScope(t *testing.T) {
span := NewMissingParentFlamegraphSpan(&FlamegraphSpan{SpanID: "child", ParentSpanID: "parent"})
raw, err := json.Marshal(span)
require.NoError(t, err)
assert.Contains(t, string(raw), `"scope":{}`)
}

View File

@@ -1,72 +0,0 @@
package spantypes
import (
"strings"
"github.com/swaggest/jsonschema-go"
)
const (
scopeName = "name"
scopeVersion = "version"
scopeAttributes = "attributes"
)
var _ jsonschema.Preparer = Scope{}
// Scope is a span's instrumentation scope holding only the fields that are set: name, version and
// attributes, a flat bag of dotted keys like the span attributes.
type Scope map[string]any
// NewScope builds a Scope from the flattened scope column, where an unset declared path reads back
// as its zero value (name and version as empty strings).
func NewScope(column map[string]any) Scope {
scope := Scope{}
if name, _ := column[scopeName].(string); name != "" {
scope[scopeName] = name
}
if version, _ := column[scopeVersion].(string); version != "" {
scope[scopeVersion] = version
}
if attributes, _ := column[scopeAttributes].(map[string]any); len(attributes) > 0 {
scope[scopeAttributes] = attributes
}
return scope
}
// NewSelectedScope builds a Scope with only the selected fields from the flattened scope column:
// scope.name and scope.version select the declared paths, any other name a scope attribute.
func NewSelectedScope(column map[string]any, names []string) Scope {
attributes, _ := column[scopeAttributes].(map[string]any)
selected := map[string]any{}
selectedAttributes := map[string]any{}
for _, name := range names {
switch name {
case "scope.name":
selected[scopeName] = column[scopeName]
case "scope.version":
selected[scopeVersion] = column[scopeVersion]
default:
name = strings.TrimPrefix(name, "attribute.")
if v, ok := attributes[name]; ok {
selectedAttributes[name] = v
}
}
}
selected[scopeAttributes] = selectedAttributes
return NewScope(selected)
}
// PrepareJSONSchema types the map's fields. Scope is a map rather than a struct so unset fields are
// left out instead of sent empty; omitempty would do that but decodes back with nil fields.
func (Scope) PrepareJSONSchema(schema *jsonschema.Schema) error {
attributes := jsonschema.Schema{}
attributes.WithType(jsonschema.Object.Type())
attributes.WithAdditionalProperties(jsonschema.SchemaOrBool{TypeObject: &jsonschema.Schema{}})
schema.AdditionalProperties = nil
schema.WithPropertiesItem(scopeName, jsonschema.String.ToSchemaOrBool())
schema.WithPropertiesItem(scopeVersion, jsonschema.String.ToSchemaOrBool())
schema.WithPropertiesItem(scopeAttributes, attributes.ToSchemaOrBool())
return nil
}

View File

@@ -1,58 +0,0 @@
package spantypes
import (
"testing"
"github.com/ClickHouse/clickhouse-go/v2/lib/chcol"
"github.com/stretchr/testify/assert"
"github.com/SigNoz/signoz/pkg/types/telemetrystoretypes"
)
// scopeColumn mirrors the driver's scan of the scope column: declared String paths as plain strings and the
// declared attributes path as a nested *chcol.JSON.
func scopeColumn(name, version string, attributes map[string]any) telemetrystoretypes.JSONValue {
j := chcol.NewJSON()
j.SetValueAtPath("name", name)
j.SetValueAtPath("version", version)
attrs := chcol.NewJSON()
for path, value := range attributes {
attrs.SetValueAtPath(path, value)
}
j.SetValueAtPath("attributes", attrs)
return telemetrystoretypes.NewJSONValue(*j)
}
func TestNewScope(t *testing.T) {
testCases := []struct {
name string
column telemetrystoretypes.JSONValue
want Scope
}{
{
name: "AttributesStayDotted",
column: scopeColumn("io.opentelemetry.http", "1.2.0", map[string]any{"lib.lang": "go", "lib.lang.version": "1.22", "retry": int64(3)}),
want: Scope{"name": "io.opentelemetry.http", "version": "1.2.0", "attributes": map[string]any{"lib.lang": "go", "lib.lang.version": "1.22", "retry": float64(3)}},
},
{
name: "DropsNullAttributePaths_UnsetVersion",
column: scopeColumn("checkout", "", map[string]any{"team": "payments", "absent": chcol.Variant{}}),
want: Scope{"name": "checkout", "attributes": map[string]any{"team": "payments"}},
},
{
name: "UnsetDeclaredPaths_Empty",
column: scopeColumn("", "", nil),
want: Scope{},
},
{
name: "EmptyColumn",
column: telemetrystoretypes.JSONValue{},
want: Scope{},
},
}
for _, testCase := range testCases {
t.Run(testCase.name, func(t *testing.T) {
assert.Equal(t, testCase.want, NewScope(testCase.column.Flatten()))
})
}
}

View File

@@ -64,7 +64,6 @@ type WaterfallSpan struct {
Name string `json:"name"`
ParentSpanID string `json:"parent_span_id"`
Resource map[string]string `json:"resource"`
Scope Scope `json:"scope"`
SpanID string `json:"span_id"`
TimeUnix uint64 `json:"time_unix"`
TraceID string `json:"trace_id"`
@@ -114,7 +113,6 @@ type StorableSpan struct {
AttributesBool map[string]bool `ch:"attributes_bool"`
AttributesJSON telemetrystoretypes.JSONValue `ch:"attributes"`
ResourcesString map[string]string `ch:"resources_string"`
Scope telemetrystoretypes.JSONValue `ch:"scope"`
Events []string `ch:"events"`
StatusMessage string `ch:"status_message"`
StatusCodeString string `ch:"status_code_string"`
@@ -155,7 +153,6 @@ func (item *MinimalSpan) ToWaterfallSpan(traceID string) *WaterfallSpan {
HasError: item.HasError,
ServiceName: item.ServiceName,
Resource: map[string]string{"service.name": item.ServiceName},
Scope: Scope{},
Children: make([]*WaterfallSpan, 0),
Attributes: make(map[string]any),
Events: make([]Event, 0),
@@ -185,7 +182,6 @@ func NewMissingWaterfallSpan(spanID, traceID string, timeUnixNano, durationNano
Children: make([]*WaterfallSpan, 0),
Attributes: make(map[string]any),
Resource: make(map[string]string),
Scope: Scope{},
}
}
@@ -340,7 +336,6 @@ func (item *StorableSpan) ToWaterfallSpan(traceID string) *WaterfallSpan {
Name: item.Name,
ParentSpanID: item.ParentSpanID,
Resource: resources,
Scope: NewScope(item.Scope.Flatten()),
ResponseStatusCode: item.ResponseStatusCode,
SpanID: item.SpanID,
StatusCode: item.StatusCode,

View File

@@ -39,7 +39,7 @@ func (v JSONValue) Flatten() map[string]any {
if isNull(value) {
continue
}
flat[path] = flatObject(value)
flat[path] = value
}
return unwrap(flat)
}
@@ -57,15 +57,6 @@ func (v JSONValue) MarshalJSON() ([]byte, error) {
return json.Marshal(v.Flatten())
}
// flatObject renders a declared JSON sub-path, which the driver scans as a nested chcol.JSON (such as
// scope.attributes), as a flat attribute bag.
func flatObject(value any) any {
if object, ok := value.(*chcol.JSON); ok && object != nil {
return JSONValue{column: *object}
}
return value
}
func isNull(value any) bool {
if value == nil {
return true

View File

@@ -50,7 +50,6 @@ ALL_SELECT_FIELDS = [
# all contextual columns (merged in response layer)
"attributes",
"resource",
"scope",
]

View File

@@ -545,7 +545,7 @@ def test_traces_list_response_shape_values(
now = datetime.now(tz=UTC).replace(microsecond=0)
trace_id = TraceIdGenerator.trace_id()
def span(marker: str, *, kind: TracesKind, status_code: TracesStatusCode = TracesStatusCode.STATUS_CODE_UNSET, status_message: str = "", flags: int = 0, attributes: dict[str, Any], scope: dict[str, Any] | None = None) -> Traces:
def span(marker: str, *, kind: TracesKind, status_code: TracesStatusCode = TracesStatusCode.STATUS_CODE_UNSET, status_message: str = "", flags: int = 0, attributes: dict[str, Any]) -> Traces:
return Traces(
timestamp=now - timedelta(seconds=1),
duration=timedelta(seconds=1),
@@ -558,11 +558,10 @@ def test_traces_list_response_shape_values(
flags=flags,
resources={"service.name": "shape-service", **extra_resources},
attributes={"marker": marker, **attributes, **extra_attrs},
scope=scope or {},
)
spans = [
span("error", kind=TracesKind.SPAN_KIND_SERVER, status_code=TracesStatusCode.STATUS_CODE_ERROR, status_message="boom", attributes={"str_a": "x", "num_a": 7.5, "bool_a": True}, scope={"name": "io.signoz.shape", "version": "0.1.0", "attributes": {"lib.lang": "go"}}),
span("error", kind=TracesKind.SPAN_KIND_SERVER, status_code=TracesStatusCode.STATUS_CODE_ERROR, status_message="boom", attributes={"str_a": "x", "num_a": 7.5, "bool_a": True}),
span("client", kind=TracesKind.SPAN_KIND_CLIENT, attributes={"http.url": "https://api.example.com/v1/orders", "http.request.method": "GET"}),
span("db", kind=TracesKind.SPAN_KIND_CLIENT, attributes={"db.name": "orders_db", "db.operation": "SELECT"}),
span("host", kind=TracesKind.SPAN_KIND_PRODUCER, attributes={"server.address": "payments.internal:8080"}),
@@ -623,7 +622,6 @@ def test_traces_list_response_shape_values(
"is_remote": span_obj.is_remote,
"attributes": {**span_obj.attribute_string, **span_obj.attributes_number, **span_obj.attributes_bool},
"resource": span_obj.resources_string,
"scope": {k: v for k, v in span_obj.scope_json.items() if v},
}
# `==` treats True/1 and 7.5/7.5 as equal regardless of type, so pin the
# string/number/bool type preservation for the error span explicitly.
@@ -1156,7 +1154,6 @@ def test_traces_list_span_scope(
"is_remote": x[3].is_remote,
"attributes": {**x[3].attribute_string, **x[3].attributes_number, **x[3].attributes_bool},
"resource": x[3].resources_string,
"scope": {k: v for k, v in x[3].scope_json.items() if v},
},
id="order_timestamp_full_shape",
),
@@ -1194,7 +1191,6 @@ def test_traces_list_span_scope(
"is_remote": x[3].is_remote,
"attributes": {**x[3].attribute_string, **x[3].attributes_number, **x[3].attributes_bool},
"resource": x[3].resources_string,
"scope": {k: v for k, v in x[3].scope_json.items() if v},
},
id="order_attribute_timestamp_full_shape",
),

View File

@@ -21,13 +21,12 @@ def test_waterfall_and_flamegraph_read_each_attribute_home(
trace_id = TraceIdGenerator.trace_id()
legacy_id, json_id, dual_id = (TraceIdGenerator.span_id() for _ in range(3))
resources = {"service.name": "tracedetail-attribute-homes"}
scope = {"name": "io.opentelemetry.http", "version": "1.2.0", "attributes": {"lib.lang": "go"}}
insert_traces(
[
Traces(timestamp=now - timedelta(seconds=10), duration=timedelta(seconds=9), trace_id=trace_id, span_id=legacy_id, name="GET /legacy", kind=TracesKind.SPAN_KIND_SERVER, resources=resources, attributes={"http.route": "/legacy", "http.retry.count": 1, "cache.hit": True}, attribute_write_mode="legacy_only"),
Traces(timestamp=now - timedelta(seconds=8), trace_id=trace_id, span_id=json_id, parent_span_id=legacy_id, name="db call", resources=resources, attributes={"http.route": "/json", "db.function": "node_refresh", "db.function.arg_count": 2}, attribute_write_mode="json_only"),
Traces(timestamp=now - timedelta(seconds=6), trace_id=trace_id, span_id=dual_id, parent_span_id=legacy_id, name="GET /dual", resources=resources, attributes={"http.route": "/dual"}, scope=scope),
Traces(timestamp=now - timedelta(seconds=6), trace_id=trace_id, span_id=dual_id, parent_span_id=legacy_id, name="GET /dual", resources=resources, attributes={"http.route": "/dual"}),
]
)
@@ -41,14 +40,11 @@ def test_waterfall_and_flamegraph_read_each_attribute_home(
timeout=10,
)
assert response.status_code == HTTPStatus.OK, response.text
spans = {span["span_id"]: span for span in response.json()["data"]["spans"]}
waterfall = {span_id: span["attributes"] for span_id, span in spans.items()}
waterfall = {span["span_id"]: span["attributes"] for span in response.json()["data"]["spans"]}
assert waterfall[legacy_id] == {"http.route": "/legacy", "http.retry.count": 1, "cache.hit": True}
# a key stored at both a scalar and an object path stays two flat keys
assert waterfall[json_id] == {"http.route": "/json", "db.function": "node_refresh", "db.function.arg_count": 2}
assert waterfall[dual_id] == {"http.route": "/dual"}
assert spans[dual_id]["scope"] == scope
assert spans[legacy_id]["scope"] == {}
response = requests.post(
signoz.self.host_configs["8080"].get(f"/api/v3/traces/{trace_id}/flamegraph"),
@@ -58,8 +54,6 @@ def test_waterfall_and_flamegraph_read_each_attribute_home(
{"name": "http.route", "fieldContext": "attribute"},
{"name": "db.function.arg_count", "fieldContext": "attribute"},
{"name": "service.name", "fieldContext": "resource"},
{"name": "scope.name", "fieldContext": "scope"},
{"name": "lib.lang", "fieldContext": "scope"},
],
},
headers=headers,
@@ -71,5 +65,3 @@ def test_waterfall_and_flamegraph_read_each_attribute_home(
assert flamegraph[json_id]["attributes"] == {"http.route": "/json", "db.function.arg_count": 2}
assert flamegraph[dual_id]["attributes"] == {"http.route": "/dual"}
assert all(span["resource"] == resources for span in flamegraph.values())
assert flamegraph[dual_id]["scope"] == {"name": "io.opentelemetry.http", "attributes": {"lib.lang": "go"}}
assert flamegraph[json_id]["scope"] == {}