evalkeep 0.1.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- evalkeep/__init__.py +12 -0
- evalkeep/__main__.py +6 -0
- evalkeep/adapters/__init__.py +45 -0
- evalkeep/adapters/base.py +92 -0
- evalkeep/adapters/jsonl.py +164 -0
- evalkeep/adapters/langsmith.py +436 -0
- evalkeep/adapters/otlp.py +442 -0
- evalkeep/adapters/semconv.py +208 -0
- evalkeep/analysis.py +174 -0
- evalkeep/analysis_run.py +160 -0
- evalkeep/analyzers/__init__.py +52 -0
- evalkeep/analyzers/anthropic.py +145 -0
- evalkeep/analyzers/stub.py +34 -0
- evalkeep/cache.py +122 -0
- evalkeep/cli.py +1933 -0
- evalkeep/clustering.py +383 -0
- evalkeep/clusters.py +101 -0
- evalkeep/commands/__init__.py +1 -0
- evalkeep/commands/analyze_cmd.py +100 -0
- evalkeep/commands/compare_cmd.py +169 -0
- evalkeep/commands/dataset_cmd.py +182 -0
- evalkeep/commands/detect_cmd.py +154 -0
- evalkeep/commands/discover_cmd.py +274 -0
- evalkeep/commands/ingest_cmd.py +50 -0
- evalkeep/commands/init_cmd.py +151 -0
- evalkeep/commands/pipeline_cmd.py +156 -0
- evalkeep/commands/review_cmd.py +141 -0
- evalkeep/commands/run_cmd.py +131 -0
- evalkeep/commands/target_cmd.py +109 -0
- evalkeep/commands/trace_cmd.py +58 -0
- evalkeep/comparison.py +432 -0
- evalkeep/config.py +209 -0
- evalkeep/detection.py +94 -0
- evalkeep/detectors.py +182 -0
- evalkeep/discovery.py +208 -0
- evalkeep/embeddings/__init__.py +31 -0
- evalkeep/embeddings/base.py +32 -0
- evalkeep/embeddings/hashing.py +98 -0
- evalkeep/errors.py +42 -0
- evalkeep/examples/__init__.py +37 -0
- evalkeep/examples/langsmith/runs.jsonl +18 -0
- evalkeep/examples/opentelemetry/spans.json +898 -0
- evalkeep/examples/refund-agent/agents/baseline.py +66 -0
- evalkeep/examples/refund-agent/agents/candidate.py +66 -0
- evalkeep/examples/refund-agent/traces.jsonl +5 -0
- evalkeep/examples/tau-bench/prepare.py +230 -0
- evalkeep/exporters/__init__.py +45 -0
- evalkeep/exporters/generic.py +31 -0
- evalkeep/exporters/promptfoo.py +219 -0
- evalkeep/failures.py +95 -0
- evalkeep/generation.py +303 -0
- evalkeep/hashing.py +56 -0
- evalkeep/ingest.py +257 -0
- evalkeep/prompts.py +127 -0
- evalkeep/pseudonyms.py +82 -0
- evalkeep/py.typed +0 -0
- evalkeep/redaction.py +333 -0
- evalkeep/regression.py +409 -0
- evalkeep/review.py +309 -0
- evalkeep/runner.py +302 -0
- evalkeep/runs.py +185 -0
- evalkeep/storage/__init__.py +37 -0
- evalkeep/storage/clusters.py +163 -0
- evalkeep/storage/failures.py +254 -0
- evalkeep/storage/migrations.py +370 -0
- evalkeep/storage/regression.py +136 -0
- evalkeep/storage/runs.py +223 -0
- evalkeep/storage/store.py +429 -0
- evalkeep/targets.py +205 -0
- evalkeep/trace.py +238 -0
- evalkeep-0.1.0.dist-info/METADATA +221 -0
- evalkeep-0.1.0.dist-info/RECORD +75 -0
- evalkeep-0.1.0.dist-info/WHEEL +4 -0
- evalkeep-0.1.0.dist-info/entry_points.txt +3 -0
- evalkeep-0.1.0.dist-info/licenses/LICENSE +202 -0
|
@@ -0,0 +1,898 @@
|
|
|
1
|
+
{
|
|
2
|
+
"resourceSpans": [
|
|
3
|
+
{
|
|
4
|
+
"resource": {
|
|
5
|
+
"attributes": [
|
|
6
|
+
{
|
|
7
|
+
"key": "service.name",
|
|
8
|
+
"value": {
|
|
9
|
+
"stringValue": "shopping-agent"
|
|
10
|
+
}
|
|
11
|
+
}
|
|
12
|
+
]
|
|
13
|
+
},
|
|
14
|
+
"scopeSpans": [
|
|
15
|
+
{
|
|
16
|
+
"scope": {
|
|
17
|
+
"name": "openinference.instrumentation"
|
|
18
|
+
},
|
|
19
|
+
"spans": [
|
|
20
|
+
{
|
|
21
|
+
"traceId": "00000000000000000000000000000412",
|
|
22
|
+
"spanId": "0000000000000000",
|
|
23
|
+
"name": "RefundAgent",
|
|
24
|
+
"startTimeUnixNano": "1755000000000000000",
|
|
25
|
+
"endTimeUnixNano": "1755000005000000000",
|
|
26
|
+
"attributes": [
|
|
27
|
+
{
|
|
28
|
+
"key": "openinference.span.kind",
|
|
29
|
+
"value": {
|
|
30
|
+
"stringValue": "AGENT"
|
|
31
|
+
}
|
|
32
|
+
},
|
|
33
|
+
{
|
|
34
|
+
"key": "input.value",
|
|
35
|
+
"value": {
|
|
36
|
+
"stringValue": "Refund my latest order."
|
|
37
|
+
}
|
|
38
|
+
},
|
|
39
|
+
{
|
|
40
|
+
"key": "output.value",
|
|
41
|
+
"value": {
|
|
42
|
+
"stringValue": "I've refunded order order-A for $24.00."
|
|
43
|
+
}
|
|
44
|
+
}
|
|
45
|
+
],
|
|
46
|
+
"status": {
|
|
47
|
+
"code": 2,
|
|
48
|
+
"message": "refunded the oldest order, not the newest"
|
|
49
|
+
}
|
|
50
|
+
},
|
|
51
|
+
{
|
|
52
|
+
"traceId": "00000000000000000000000000000412",
|
|
53
|
+
"spanId": "0000000000000001",
|
|
54
|
+
"parentSpanId": "0000000000000000",
|
|
55
|
+
"name": "ChatCompletion",
|
|
56
|
+
"startTimeUnixNano": "1755000001000000000",
|
|
57
|
+
"endTimeUnixNano": "1755000002000000000",
|
|
58
|
+
"attributes": [
|
|
59
|
+
{
|
|
60
|
+
"key": "openinference.span.kind",
|
|
61
|
+
"value": {
|
|
62
|
+
"stringValue": "LLM"
|
|
63
|
+
}
|
|
64
|
+
},
|
|
65
|
+
{
|
|
66
|
+
"key": "llm.model_name",
|
|
67
|
+
"value": {
|
|
68
|
+
"stringValue": "demo-model-v3"
|
|
69
|
+
}
|
|
70
|
+
},
|
|
71
|
+
{
|
|
72
|
+
"key": "llm.input_messages.0.message.role",
|
|
73
|
+
"value": {
|
|
74
|
+
"stringValue": "user"
|
|
75
|
+
}
|
|
76
|
+
},
|
|
77
|
+
{
|
|
78
|
+
"key": "llm.input_messages.0.message.content",
|
|
79
|
+
"value": {
|
|
80
|
+
"stringValue": "Refund my latest order."
|
|
81
|
+
}
|
|
82
|
+
},
|
|
83
|
+
{
|
|
84
|
+
"key": "llm.output_messages.0.message.role",
|
|
85
|
+
"value": {
|
|
86
|
+
"stringValue": "assistant"
|
|
87
|
+
}
|
|
88
|
+
},
|
|
89
|
+
{
|
|
90
|
+
"key": "llm.output_messages.0.message.content",
|
|
91
|
+
"value": {
|
|
92
|
+
"stringValue": "I've refunded order order-A for $24.00."
|
|
93
|
+
}
|
|
94
|
+
},
|
|
95
|
+
{
|
|
96
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.name",
|
|
97
|
+
"value": {
|
|
98
|
+
"stringValue": "list_orders"
|
|
99
|
+
}
|
|
100
|
+
},
|
|
101
|
+
{
|
|
102
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.arguments",
|
|
103
|
+
"value": {
|
|
104
|
+
"stringValue": "{\"customer_id\": \"cust-77\"}"
|
|
105
|
+
}
|
|
106
|
+
},
|
|
107
|
+
{
|
|
108
|
+
"key": "llm.output_messages.0.message.tool_calls.1.tool_call.function.name",
|
|
109
|
+
"value": {
|
|
110
|
+
"stringValue": "refund_order"
|
|
111
|
+
}
|
|
112
|
+
},
|
|
113
|
+
{
|
|
114
|
+
"key": "llm.output_messages.0.message.tool_calls.1.tool_call.function.arguments",
|
|
115
|
+
"value": {
|
|
116
|
+
"stringValue": "{\"order_id\": \"order-A\"}"
|
|
117
|
+
}
|
|
118
|
+
}
|
|
119
|
+
],
|
|
120
|
+
"status": {
|
|
121
|
+
"code": 1
|
|
122
|
+
}
|
|
123
|
+
},
|
|
124
|
+
{
|
|
125
|
+
"traceId": "00000000000000000000000000000412",
|
|
126
|
+
"spanId": "0000000000000002",
|
|
127
|
+
"parentSpanId": "0000000000000000",
|
|
128
|
+
"name": "list_orders",
|
|
129
|
+
"startTimeUnixNano": "1755000003000000000",
|
|
130
|
+
"endTimeUnixNano": "1755000003500000000",
|
|
131
|
+
"attributes": [
|
|
132
|
+
{
|
|
133
|
+
"key": "openinference.span.kind",
|
|
134
|
+
"value": {
|
|
135
|
+
"stringValue": "TOOL"
|
|
136
|
+
}
|
|
137
|
+
},
|
|
138
|
+
{
|
|
139
|
+
"key": "tool.name",
|
|
140
|
+
"value": {
|
|
141
|
+
"stringValue": "list_orders"
|
|
142
|
+
}
|
|
143
|
+
},
|
|
144
|
+
{
|
|
145
|
+
"key": "tool.parameters",
|
|
146
|
+
"value": {
|
|
147
|
+
"stringValue": "{\"customer_id\": \"cust-77\"}"
|
|
148
|
+
}
|
|
149
|
+
},
|
|
150
|
+
{
|
|
151
|
+
"key": "output.value",
|
|
152
|
+
"value": {
|
|
153
|
+
"stringValue": "[{\"order_id\": \"order-A\", \"placed_at\": \"2026-06-01\", \"total\": \"24.00\"}, {\"order_id\": \"order-B\", \"placed_at\": \"2026-07-15\", \"total\": \"61.50\"}, {\"order_id\": \"order-C\", \"placed_at\": \"2026-08-12\", \"total\": \"18.99\"}]"
|
|
154
|
+
}
|
|
155
|
+
}
|
|
156
|
+
],
|
|
157
|
+
"status": {
|
|
158
|
+
"code": 1
|
|
159
|
+
}
|
|
160
|
+
},
|
|
161
|
+
{
|
|
162
|
+
"traceId": "00000000000000000000000000000412",
|
|
163
|
+
"spanId": "0000000000000003",
|
|
164
|
+
"parentSpanId": "0000000000000000",
|
|
165
|
+
"name": "refund_order",
|
|
166
|
+
"startTimeUnixNano": "1755000004000000000",
|
|
167
|
+
"endTimeUnixNano": "1755000004500000000",
|
|
168
|
+
"attributes": [
|
|
169
|
+
{
|
|
170
|
+
"key": "openinference.span.kind",
|
|
171
|
+
"value": {
|
|
172
|
+
"stringValue": "TOOL"
|
|
173
|
+
}
|
|
174
|
+
},
|
|
175
|
+
{
|
|
176
|
+
"key": "tool.name",
|
|
177
|
+
"value": {
|
|
178
|
+
"stringValue": "refund_order"
|
|
179
|
+
}
|
|
180
|
+
},
|
|
181
|
+
{
|
|
182
|
+
"key": "tool.parameters",
|
|
183
|
+
"value": {
|
|
184
|
+
"stringValue": "{\"order_id\": \"order-A\"}"
|
|
185
|
+
}
|
|
186
|
+
},
|
|
187
|
+
{
|
|
188
|
+
"key": "output.value",
|
|
189
|
+
"value": {
|
|
190
|
+
"stringValue": "{\"status\": \"refunded\", \"order_id\": \"order-A\"}"
|
|
191
|
+
}
|
|
192
|
+
}
|
|
193
|
+
],
|
|
194
|
+
"status": {
|
|
195
|
+
"code": 1
|
|
196
|
+
}
|
|
197
|
+
}
|
|
198
|
+
]
|
|
199
|
+
}
|
|
200
|
+
]
|
|
201
|
+
},
|
|
202
|
+
{
|
|
203
|
+
"resource": {
|
|
204
|
+
"attributes": [
|
|
205
|
+
{
|
|
206
|
+
"key": "service.name",
|
|
207
|
+
"value": {
|
|
208
|
+
"stringValue": "shopping-agent"
|
|
209
|
+
}
|
|
210
|
+
}
|
|
211
|
+
]
|
|
212
|
+
},
|
|
213
|
+
"scopeSpans": [
|
|
214
|
+
{
|
|
215
|
+
"scope": {
|
|
216
|
+
"name": "openinference.instrumentation"
|
|
217
|
+
},
|
|
218
|
+
"spans": [
|
|
219
|
+
{
|
|
220
|
+
"traceId": "00000000000000000000000000000413",
|
|
221
|
+
"spanId": "0000000000000010",
|
|
222
|
+
"name": "RefundAgent",
|
|
223
|
+
"startTimeUnixNano": "1755000060000000000",
|
|
224
|
+
"endTimeUnixNano": "1755000065000000000",
|
|
225
|
+
"attributes": [
|
|
226
|
+
{
|
|
227
|
+
"key": "openinference.span.kind",
|
|
228
|
+
"value": {
|
|
229
|
+
"stringValue": "AGENT"
|
|
230
|
+
}
|
|
231
|
+
},
|
|
232
|
+
{
|
|
233
|
+
"key": "input.value",
|
|
234
|
+
"value": {
|
|
235
|
+
"stringValue": "Please refund the order I placed most recently."
|
|
236
|
+
}
|
|
237
|
+
},
|
|
238
|
+
{
|
|
239
|
+
"key": "output.value",
|
|
240
|
+
"value": {
|
|
241
|
+
"stringValue": "Done - order-D has been refunded."
|
|
242
|
+
}
|
|
243
|
+
}
|
|
244
|
+
],
|
|
245
|
+
"status": {
|
|
246
|
+
"code": 2,
|
|
247
|
+
"message": "expected order-C, refunded order-D"
|
|
248
|
+
}
|
|
249
|
+
},
|
|
250
|
+
{
|
|
251
|
+
"traceId": "00000000000000000000000000000413",
|
|
252
|
+
"spanId": "0000000000000011",
|
|
253
|
+
"parentSpanId": "0000000000000010",
|
|
254
|
+
"name": "ChatCompletion",
|
|
255
|
+
"startTimeUnixNano": "1755000061000000000",
|
|
256
|
+
"endTimeUnixNano": "1755000062000000000",
|
|
257
|
+
"attributes": [
|
|
258
|
+
{
|
|
259
|
+
"key": "openinference.span.kind",
|
|
260
|
+
"value": {
|
|
261
|
+
"stringValue": "LLM"
|
|
262
|
+
}
|
|
263
|
+
},
|
|
264
|
+
{
|
|
265
|
+
"key": "llm.model_name",
|
|
266
|
+
"value": {
|
|
267
|
+
"stringValue": "demo-model-v3"
|
|
268
|
+
}
|
|
269
|
+
},
|
|
270
|
+
{
|
|
271
|
+
"key": "llm.input_messages.0.message.role",
|
|
272
|
+
"value": {
|
|
273
|
+
"stringValue": "user"
|
|
274
|
+
}
|
|
275
|
+
},
|
|
276
|
+
{
|
|
277
|
+
"key": "llm.input_messages.0.message.content",
|
|
278
|
+
"value": {
|
|
279
|
+
"stringValue": "Please refund the order I placed most recently."
|
|
280
|
+
}
|
|
281
|
+
},
|
|
282
|
+
{
|
|
283
|
+
"key": "llm.output_messages.0.message.role",
|
|
284
|
+
"value": {
|
|
285
|
+
"stringValue": "assistant"
|
|
286
|
+
}
|
|
287
|
+
},
|
|
288
|
+
{
|
|
289
|
+
"key": "llm.output_messages.0.message.content",
|
|
290
|
+
"value": {
|
|
291
|
+
"stringValue": "Done - order-D has been refunded."
|
|
292
|
+
}
|
|
293
|
+
},
|
|
294
|
+
{
|
|
295
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.name",
|
|
296
|
+
"value": {
|
|
297
|
+
"stringValue": "list_orders"
|
|
298
|
+
}
|
|
299
|
+
},
|
|
300
|
+
{
|
|
301
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.arguments",
|
|
302
|
+
"value": {
|
|
303
|
+
"stringValue": "{\"customer_id\": \"cust-91\"}"
|
|
304
|
+
}
|
|
305
|
+
},
|
|
306
|
+
{
|
|
307
|
+
"key": "llm.output_messages.0.message.tool_calls.1.tool_call.function.name",
|
|
308
|
+
"value": {
|
|
309
|
+
"stringValue": "refund_order"
|
|
310
|
+
}
|
|
311
|
+
},
|
|
312
|
+
{
|
|
313
|
+
"key": "llm.output_messages.0.message.tool_calls.1.tool_call.function.arguments",
|
|
314
|
+
"value": {
|
|
315
|
+
"stringValue": "{\"order_id\": \"order-D\"}"
|
|
316
|
+
}
|
|
317
|
+
}
|
|
318
|
+
],
|
|
319
|
+
"status": {
|
|
320
|
+
"code": 1
|
|
321
|
+
}
|
|
322
|
+
},
|
|
323
|
+
{
|
|
324
|
+
"traceId": "00000000000000000000000000000413",
|
|
325
|
+
"spanId": "0000000000000012",
|
|
326
|
+
"parentSpanId": "0000000000000010",
|
|
327
|
+
"name": "list_orders",
|
|
328
|
+
"startTimeUnixNano": "1755000063000000000",
|
|
329
|
+
"endTimeUnixNano": "1755000063500000000",
|
|
330
|
+
"attributes": [
|
|
331
|
+
{
|
|
332
|
+
"key": "openinference.span.kind",
|
|
333
|
+
"value": {
|
|
334
|
+
"stringValue": "TOOL"
|
|
335
|
+
}
|
|
336
|
+
},
|
|
337
|
+
{
|
|
338
|
+
"key": "tool.name",
|
|
339
|
+
"value": {
|
|
340
|
+
"stringValue": "list_orders"
|
|
341
|
+
}
|
|
342
|
+
},
|
|
343
|
+
{
|
|
344
|
+
"key": "tool.parameters",
|
|
345
|
+
"value": {
|
|
346
|
+
"stringValue": "{\"customer_id\": \"cust-91\"}"
|
|
347
|
+
}
|
|
348
|
+
},
|
|
349
|
+
{
|
|
350
|
+
"key": "output.value",
|
|
351
|
+
"value": {
|
|
352
|
+
"stringValue": "[{\"order_id\": \"order-A\", \"placed_at\": \"2026-06-01\", \"total\": \"24.00\"}, {\"order_id\": \"order-B\", \"placed_at\": \"2026-07-15\", \"total\": \"61.50\"}, {\"order_id\": \"order-C\", \"placed_at\": \"2026-08-12\", \"total\": \"18.99\"}]"
|
|
353
|
+
}
|
|
354
|
+
}
|
|
355
|
+
],
|
|
356
|
+
"status": {
|
|
357
|
+
"code": 1
|
|
358
|
+
}
|
|
359
|
+
},
|
|
360
|
+
{
|
|
361
|
+
"traceId": "00000000000000000000000000000413",
|
|
362
|
+
"spanId": "0000000000000013",
|
|
363
|
+
"parentSpanId": "0000000000000010",
|
|
364
|
+
"name": "refund_order",
|
|
365
|
+
"startTimeUnixNano": "1755000064000000000",
|
|
366
|
+
"endTimeUnixNano": "1755000064500000000",
|
|
367
|
+
"attributes": [
|
|
368
|
+
{
|
|
369
|
+
"key": "openinference.span.kind",
|
|
370
|
+
"value": {
|
|
371
|
+
"stringValue": "TOOL"
|
|
372
|
+
}
|
|
373
|
+
},
|
|
374
|
+
{
|
|
375
|
+
"key": "tool.name",
|
|
376
|
+
"value": {
|
|
377
|
+
"stringValue": "refund_order"
|
|
378
|
+
}
|
|
379
|
+
},
|
|
380
|
+
{
|
|
381
|
+
"key": "tool.parameters",
|
|
382
|
+
"value": {
|
|
383
|
+
"stringValue": "{\"order_id\": \"order-D\"}"
|
|
384
|
+
}
|
|
385
|
+
},
|
|
386
|
+
{
|
|
387
|
+
"key": "output.value",
|
|
388
|
+
"value": {
|
|
389
|
+
"stringValue": "{\"status\": \"refunded\"}"
|
|
390
|
+
}
|
|
391
|
+
}
|
|
392
|
+
],
|
|
393
|
+
"status": {
|
|
394
|
+
"code": 1
|
|
395
|
+
}
|
|
396
|
+
}
|
|
397
|
+
]
|
|
398
|
+
}
|
|
399
|
+
]
|
|
400
|
+
},
|
|
401
|
+
{
|
|
402
|
+
"resource": {
|
|
403
|
+
"attributes": [
|
|
404
|
+
{
|
|
405
|
+
"key": "service.name",
|
|
406
|
+
"value": {
|
|
407
|
+
"stringValue": "shopping-agent"
|
|
408
|
+
}
|
|
409
|
+
}
|
|
410
|
+
]
|
|
411
|
+
},
|
|
412
|
+
"scopeSpans": [
|
|
413
|
+
{
|
|
414
|
+
"scope": {
|
|
415
|
+
"name": "openinference.instrumentation"
|
|
416
|
+
},
|
|
417
|
+
"spans": [
|
|
418
|
+
{
|
|
419
|
+
"traceId": "0000000000000000000000000000041b",
|
|
420
|
+
"spanId": "0000000000000020",
|
|
421
|
+
"name": "RefundAgent",
|
|
422
|
+
"startTimeUnixNano": "1755000120000000000",
|
|
423
|
+
"endTimeUnixNano": "1755000125000000000",
|
|
424
|
+
"attributes": [
|
|
425
|
+
{
|
|
426
|
+
"key": "openinference.span.kind",
|
|
427
|
+
"value": {
|
|
428
|
+
"stringValue": "AGENT"
|
|
429
|
+
}
|
|
430
|
+
},
|
|
431
|
+
{
|
|
432
|
+
"key": "input.value",
|
|
433
|
+
"value": {
|
|
434
|
+
"stringValue": "Cancel and refund order-B."
|
|
435
|
+
}
|
|
436
|
+
},
|
|
437
|
+
{
|
|
438
|
+
"key": "output.value",
|
|
439
|
+
"value": {
|
|
440
|
+
"stringValue": "I have refunded every order on your account."
|
|
441
|
+
}
|
|
442
|
+
}
|
|
443
|
+
],
|
|
444
|
+
"status": {
|
|
445
|
+
"code": 1
|
|
446
|
+
}
|
|
447
|
+
},
|
|
448
|
+
{
|
|
449
|
+
"traceId": "0000000000000000000000000000041b",
|
|
450
|
+
"spanId": "0000000000000021",
|
|
451
|
+
"parentSpanId": "0000000000000020",
|
|
452
|
+
"name": "ChatCompletion",
|
|
453
|
+
"startTimeUnixNano": "1755000121000000000",
|
|
454
|
+
"endTimeUnixNano": "1755000122000000000",
|
|
455
|
+
"attributes": [
|
|
456
|
+
{
|
|
457
|
+
"key": "openinference.span.kind",
|
|
458
|
+
"value": {
|
|
459
|
+
"stringValue": "LLM"
|
|
460
|
+
}
|
|
461
|
+
},
|
|
462
|
+
{
|
|
463
|
+
"key": "llm.model_name",
|
|
464
|
+
"value": {
|
|
465
|
+
"stringValue": "demo-model-v3"
|
|
466
|
+
}
|
|
467
|
+
},
|
|
468
|
+
{
|
|
469
|
+
"key": "llm.input_messages.0.message.role",
|
|
470
|
+
"value": {
|
|
471
|
+
"stringValue": "user"
|
|
472
|
+
}
|
|
473
|
+
},
|
|
474
|
+
{
|
|
475
|
+
"key": "llm.input_messages.0.message.content",
|
|
476
|
+
"value": {
|
|
477
|
+
"stringValue": "Cancel and refund order-B."
|
|
478
|
+
}
|
|
479
|
+
},
|
|
480
|
+
{
|
|
481
|
+
"key": "llm.output_messages.0.message.role",
|
|
482
|
+
"value": {
|
|
483
|
+
"stringValue": "assistant"
|
|
484
|
+
}
|
|
485
|
+
},
|
|
486
|
+
{
|
|
487
|
+
"key": "llm.output_messages.0.message.content",
|
|
488
|
+
"value": {
|
|
489
|
+
"stringValue": "I have refunded every order on your account."
|
|
490
|
+
}
|
|
491
|
+
},
|
|
492
|
+
{
|
|
493
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.name",
|
|
494
|
+
"value": {
|
|
495
|
+
"stringValue": "refund_order"
|
|
496
|
+
}
|
|
497
|
+
},
|
|
498
|
+
{
|
|
499
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.arguments",
|
|
500
|
+
"value": {
|
|
501
|
+
"stringValue": "{\"order_id\": \"order-A\"}"
|
|
502
|
+
}
|
|
503
|
+
},
|
|
504
|
+
{
|
|
505
|
+
"key": "llm.output_messages.0.message.tool_calls.1.tool_call.function.name",
|
|
506
|
+
"value": {
|
|
507
|
+
"stringValue": "refund_order"
|
|
508
|
+
}
|
|
509
|
+
},
|
|
510
|
+
{
|
|
511
|
+
"key": "llm.output_messages.0.message.tool_calls.1.tool_call.function.arguments",
|
|
512
|
+
"value": {
|
|
513
|
+
"stringValue": "{\"order_id\": \"order-B\"}"
|
|
514
|
+
}
|
|
515
|
+
},
|
|
516
|
+
{
|
|
517
|
+
"key": "llm.output_messages.0.message.tool_calls.2.tool_call.function.name",
|
|
518
|
+
"value": {
|
|
519
|
+
"stringValue": "refund_order"
|
|
520
|
+
}
|
|
521
|
+
},
|
|
522
|
+
{
|
|
523
|
+
"key": "llm.output_messages.0.message.tool_calls.2.tool_call.function.arguments",
|
|
524
|
+
"value": {
|
|
525
|
+
"stringValue": "{\"order_id\": \"order-C\"}"
|
|
526
|
+
}
|
|
527
|
+
}
|
|
528
|
+
],
|
|
529
|
+
"status": {
|
|
530
|
+
"code": 1
|
|
531
|
+
}
|
|
532
|
+
},
|
|
533
|
+
{
|
|
534
|
+
"traceId": "0000000000000000000000000000041b",
|
|
535
|
+
"spanId": "0000000000000022",
|
|
536
|
+
"parentSpanId": "0000000000000020",
|
|
537
|
+
"name": "refund_order",
|
|
538
|
+
"startTimeUnixNano": "1755000123000000000",
|
|
539
|
+
"endTimeUnixNano": "1755000123500000000",
|
|
540
|
+
"attributes": [
|
|
541
|
+
{
|
|
542
|
+
"key": "openinference.span.kind",
|
|
543
|
+
"value": {
|
|
544
|
+
"stringValue": "TOOL"
|
|
545
|
+
}
|
|
546
|
+
},
|
|
547
|
+
{
|
|
548
|
+
"key": "tool.name",
|
|
549
|
+
"value": {
|
|
550
|
+
"stringValue": "refund_order"
|
|
551
|
+
}
|
|
552
|
+
},
|
|
553
|
+
{
|
|
554
|
+
"key": "tool.parameters",
|
|
555
|
+
"value": {
|
|
556
|
+
"stringValue": "{\"order_id\": \"order-A\"}"
|
|
557
|
+
}
|
|
558
|
+
},
|
|
559
|
+
{
|
|
560
|
+
"key": "output.value",
|
|
561
|
+
"value": {
|
|
562
|
+
"stringValue": "{\"status\": \"refunded\"}"
|
|
563
|
+
}
|
|
564
|
+
}
|
|
565
|
+
],
|
|
566
|
+
"status": {
|
|
567
|
+
"code": 1
|
|
568
|
+
}
|
|
569
|
+
},
|
|
570
|
+
{
|
|
571
|
+
"traceId": "0000000000000000000000000000041b",
|
|
572
|
+
"spanId": "0000000000000023",
|
|
573
|
+
"parentSpanId": "0000000000000020",
|
|
574
|
+
"name": "refund_order",
|
|
575
|
+
"startTimeUnixNano": "1755000124000000000",
|
|
576
|
+
"endTimeUnixNano": "1755000124500000000",
|
|
577
|
+
"attributes": [
|
|
578
|
+
{
|
|
579
|
+
"key": "openinference.span.kind",
|
|
580
|
+
"value": {
|
|
581
|
+
"stringValue": "TOOL"
|
|
582
|
+
}
|
|
583
|
+
},
|
|
584
|
+
{
|
|
585
|
+
"key": "tool.name",
|
|
586
|
+
"value": {
|
|
587
|
+
"stringValue": "refund_order"
|
|
588
|
+
}
|
|
589
|
+
},
|
|
590
|
+
{
|
|
591
|
+
"key": "tool.parameters",
|
|
592
|
+
"value": {
|
|
593
|
+
"stringValue": "{\"order_id\": \"order-B\"}"
|
|
594
|
+
}
|
|
595
|
+
},
|
|
596
|
+
{
|
|
597
|
+
"key": "output.value",
|
|
598
|
+
"value": {
|
|
599
|
+
"stringValue": "{\"status\": \"refunded\"}"
|
|
600
|
+
}
|
|
601
|
+
}
|
|
602
|
+
],
|
|
603
|
+
"status": {
|
|
604
|
+
"code": 1
|
|
605
|
+
}
|
|
606
|
+
},
|
|
607
|
+
{
|
|
608
|
+
"traceId": "0000000000000000000000000000041b",
|
|
609
|
+
"spanId": "0000000000000024",
|
|
610
|
+
"parentSpanId": "0000000000000020",
|
|
611
|
+
"name": "refund_order",
|
|
612
|
+
"startTimeUnixNano": "1755000125000000000",
|
|
613
|
+
"endTimeUnixNano": "1755000125500000000",
|
|
614
|
+
"attributes": [
|
|
615
|
+
{
|
|
616
|
+
"key": "openinference.span.kind",
|
|
617
|
+
"value": {
|
|
618
|
+
"stringValue": "TOOL"
|
|
619
|
+
}
|
|
620
|
+
},
|
|
621
|
+
{
|
|
622
|
+
"key": "tool.name",
|
|
623
|
+
"value": {
|
|
624
|
+
"stringValue": "refund_order"
|
|
625
|
+
}
|
|
626
|
+
},
|
|
627
|
+
{
|
|
628
|
+
"key": "tool.parameters",
|
|
629
|
+
"value": {
|
|
630
|
+
"stringValue": "{\"order_id\": \"order-C\"}"
|
|
631
|
+
}
|
|
632
|
+
},
|
|
633
|
+
{
|
|
634
|
+
"key": "output.value",
|
|
635
|
+
"value": {
|
|
636
|
+
"stringValue": "{\"status\": \"refunded\"}"
|
|
637
|
+
}
|
|
638
|
+
}
|
|
639
|
+
],
|
|
640
|
+
"status": {
|
|
641
|
+
"code": 1
|
|
642
|
+
}
|
|
643
|
+
}
|
|
644
|
+
]
|
|
645
|
+
}
|
|
646
|
+
]
|
|
647
|
+
},
|
|
648
|
+
{
|
|
649
|
+
"resource": {
|
|
650
|
+
"attributes": [
|
|
651
|
+
{
|
|
652
|
+
"key": "service.name",
|
|
653
|
+
"value": {
|
|
654
|
+
"stringValue": "shopping-agent"
|
|
655
|
+
}
|
|
656
|
+
}
|
|
657
|
+
]
|
|
658
|
+
},
|
|
659
|
+
"scopeSpans": [
|
|
660
|
+
{
|
|
661
|
+
"scope": {
|
|
662
|
+
"name": "openinference.instrumentation"
|
|
663
|
+
},
|
|
664
|
+
"spans": [
|
|
665
|
+
{
|
|
666
|
+
"traceId": "00000000000000000000000000000424",
|
|
667
|
+
"spanId": "0000000000000030",
|
|
668
|
+
"name": "RefundAgent",
|
|
669
|
+
"startTimeUnixNano": "1755000180000000000",
|
|
670
|
+
"endTimeUnixNano": "1755000185000000000",
|
|
671
|
+
"attributes": [
|
|
672
|
+
{
|
|
673
|
+
"key": "openinference.span.kind",
|
|
674
|
+
"value": {
|
|
675
|
+
"stringValue": "AGENT"
|
|
676
|
+
}
|
|
677
|
+
},
|
|
678
|
+
{
|
|
679
|
+
"key": "input.value",
|
|
680
|
+
"value": {
|
|
681
|
+
"stringValue": "What is the status of order-C?"
|
|
682
|
+
}
|
|
683
|
+
},
|
|
684
|
+
{
|
|
685
|
+
"key": "output.value",
|
|
686
|
+
"value": {
|
|
687
|
+
"stringValue": "order-C shipped on 2026-08-13 and arrives Friday."
|
|
688
|
+
}
|
|
689
|
+
}
|
|
690
|
+
],
|
|
691
|
+
"status": {
|
|
692
|
+
"code": 1
|
|
693
|
+
}
|
|
694
|
+
},
|
|
695
|
+
{
|
|
696
|
+
"traceId": "00000000000000000000000000000424",
|
|
697
|
+
"spanId": "0000000000000031",
|
|
698
|
+
"parentSpanId": "0000000000000030",
|
|
699
|
+
"name": "ChatCompletion",
|
|
700
|
+
"startTimeUnixNano": "1755000181000000000",
|
|
701
|
+
"endTimeUnixNano": "1755000182000000000",
|
|
702
|
+
"attributes": [
|
|
703
|
+
{
|
|
704
|
+
"key": "openinference.span.kind",
|
|
705
|
+
"value": {
|
|
706
|
+
"stringValue": "LLM"
|
|
707
|
+
}
|
|
708
|
+
},
|
|
709
|
+
{
|
|
710
|
+
"key": "llm.model_name",
|
|
711
|
+
"value": {
|
|
712
|
+
"stringValue": "demo-model-v3"
|
|
713
|
+
}
|
|
714
|
+
},
|
|
715
|
+
{
|
|
716
|
+
"key": "llm.input_messages.0.message.role",
|
|
717
|
+
"value": {
|
|
718
|
+
"stringValue": "user"
|
|
719
|
+
}
|
|
720
|
+
},
|
|
721
|
+
{
|
|
722
|
+
"key": "llm.input_messages.0.message.content",
|
|
723
|
+
"value": {
|
|
724
|
+
"stringValue": "What is the status of order-C?"
|
|
725
|
+
}
|
|
726
|
+
},
|
|
727
|
+
{
|
|
728
|
+
"key": "llm.output_messages.0.message.role",
|
|
729
|
+
"value": {
|
|
730
|
+
"stringValue": "assistant"
|
|
731
|
+
}
|
|
732
|
+
},
|
|
733
|
+
{
|
|
734
|
+
"key": "llm.output_messages.0.message.content",
|
|
735
|
+
"value": {
|
|
736
|
+
"stringValue": "order-C shipped on 2026-08-13 and arrives Friday."
|
|
737
|
+
}
|
|
738
|
+
},
|
|
739
|
+
{
|
|
740
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.name",
|
|
741
|
+
"value": {
|
|
742
|
+
"stringValue": "get_order"
|
|
743
|
+
}
|
|
744
|
+
},
|
|
745
|
+
{
|
|
746
|
+
"key": "llm.output_messages.0.message.tool_calls.0.tool_call.function.arguments",
|
|
747
|
+
"value": {
|
|
748
|
+
"stringValue": "{\"order_id\": \"order-C\"}"
|
|
749
|
+
}
|
|
750
|
+
}
|
|
751
|
+
],
|
|
752
|
+
"status": {
|
|
753
|
+
"code": 1
|
|
754
|
+
}
|
|
755
|
+
},
|
|
756
|
+
{
|
|
757
|
+
"traceId": "00000000000000000000000000000424",
|
|
758
|
+
"spanId": "0000000000000032",
|
|
759
|
+
"parentSpanId": "0000000000000030",
|
|
760
|
+
"name": "get_order",
|
|
761
|
+
"startTimeUnixNano": "1755000183000000000",
|
|
762
|
+
"endTimeUnixNano": "1755000183500000000",
|
|
763
|
+
"attributes": [
|
|
764
|
+
{
|
|
765
|
+
"key": "openinference.span.kind",
|
|
766
|
+
"value": {
|
|
767
|
+
"stringValue": "TOOL"
|
|
768
|
+
}
|
|
769
|
+
},
|
|
770
|
+
{
|
|
771
|
+
"key": "tool.name",
|
|
772
|
+
"value": {
|
|
773
|
+
"stringValue": "get_order"
|
|
774
|
+
}
|
|
775
|
+
},
|
|
776
|
+
{
|
|
777
|
+
"key": "tool.parameters",
|
|
778
|
+
"value": {
|
|
779
|
+
"stringValue": "{\"order_id\": \"order-C\"}"
|
|
780
|
+
}
|
|
781
|
+
},
|
|
782
|
+
{
|
|
783
|
+
"key": "output.value",
|
|
784
|
+
"value": {
|
|
785
|
+
"stringValue": "{\"order_id\": \"order-C\", \"status\": \"shipped\"}"
|
|
786
|
+
}
|
|
787
|
+
}
|
|
788
|
+
],
|
|
789
|
+
"status": {
|
|
790
|
+
"code": 1
|
|
791
|
+
}
|
|
792
|
+
}
|
|
793
|
+
]
|
|
794
|
+
}
|
|
795
|
+
]
|
|
796
|
+
},
|
|
797
|
+
{
|
|
798
|
+
"resource": {
|
|
799
|
+
"attributes": [
|
|
800
|
+
{
|
|
801
|
+
"key": "service.name",
|
|
802
|
+
"value": {
|
|
803
|
+
"stringValue": "shopping-agent"
|
|
804
|
+
}
|
|
805
|
+
}
|
|
806
|
+
]
|
|
807
|
+
},
|
|
808
|
+
"scopeSpans": [
|
|
809
|
+
{
|
|
810
|
+
"scope": {
|
|
811
|
+
"name": "openinference.instrumentation"
|
|
812
|
+
},
|
|
813
|
+
"spans": [
|
|
814
|
+
{
|
|
815
|
+
"traceId": "00000000000000000000000000000425",
|
|
816
|
+
"spanId": "0000000000000040",
|
|
817
|
+
"name": "RefundAgent",
|
|
818
|
+
"startTimeUnixNano": "1755000240000000000",
|
|
819
|
+
"endTimeUnixNano": "1755000245000000000",
|
|
820
|
+
"attributes": [
|
|
821
|
+
{
|
|
822
|
+
"key": "openinference.span.kind",
|
|
823
|
+
"value": {
|
|
824
|
+
"stringValue": "AGENT"
|
|
825
|
+
}
|
|
826
|
+
},
|
|
827
|
+
{
|
|
828
|
+
"key": "input.value",
|
|
829
|
+
"value": {
|
|
830
|
+
"stringValue": "Do you ship to Portugal?"
|
|
831
|
+
}
|
|
832
|
+
},
|
|
833
|
+
{
|
|
834
|
+
"key": "output.value",
|
|
835
|
+
"value": {
|
|
836
|
+
"stringValue": "Yes, we ship to Portugal."
|
|
837
|
+
}
|
|
838
|
+
}
|
|
839
|
+
],
|
|
840
|
+
"status": {
|
|
841
|
+
"code": 1
|
|
842
|
+
}
|
|
843
|
+
},
|
|
844
|
+
{
|
|
845
|
+
"traceId": "00000000000000000000000000000425",
|
|
846
|
+
"spanId": "0000000000000041",
|
|
847
|
+
"parentSpanId": "0000000000000040",
|
|
848
|
+
"name": "ChatCompletion",
|
|
849
|
+
"startTimeUnixNano": "1755000241000000000",
|
|
850
|
+
"endTimeUnixNano": "1755000242000000000",
|
|
851
|
+
"attributes": [
|
|
852
|
+
{
|
|
853
|
+
"key": "openinference.span.kind",
|
|
854
|
+
"value": {
|
|
855
|
+
"stringValue": "LLM"
|
|
856
|
+
}
|
|
857
|
+
},
|
|
858
|
+
{
|
|
859
|
+
"key": "llm.model_name",
|
|
860
|
+
"value": {
|
|
861
|
+
"stringValue": "demo-model-v3"
|
|
862
|
+
}
|
|
863
|
+
},
|
|
864
|
+
{
|
|
865
|
+
"key": "llm.input_messages.0.message.role",
|
|
866
|
+
"value": {
|
|
867
|
+
"stringValue": "user"
|
|
868
|
+
}
|
|
869
|
+
},
|
|
870
|
+
{
|
|
871
|
+
"key": "llm.input_messages.0.message.content",
|
|
872
|
+
"value": {
|
|
873
|
+
"stringValue": "Do you ship to Portugal?"
|
|
874
|
+
}
|
|
875
|
+
},
|
|
876
|
+
{
|
|
877
|
+
"key": "llm.output_messages.0.message.role",
|
|
878
|
+
"value": {
|
|
879
|
+
"stringValue": "assistant"
|
|
880
|
+
}
|
|
881
|
+
},
|
|
882
|
+
{
|
|
883
|
+
"key": "llm.output_messages.0.message.content",
|
|
884
|
+
"value": {
|
|
885
|
+
"stringValue": "Yes, we ship to Portugal."
|
|
886
|
+
}
|
|
887
|
+
}
|
|
888
|
+
],
|
|
889
|
+
"status": {
|
|
890
|
+
"code": 1
|
|
891
|
+
}
|
|
892
|
+
}
|
|
893
|
+
]
|
|
894
|
+
}
|
|
895
|
+
]
|
|
896
|
+
}
|
|
897
|
+
]
|
|
898
|
+
}
|