Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: CastError
Message: Couldn't cast
_meta: struct<generator: string, config: struct<seed: int64, model: string, sessions: int64, turns: int64, (... 309 chars omitted)
child 0, generator: string
child 1, config: struct<seed: int64, model: string, sessions: int64, turns: int64, system_tokens: int64, tools: int64 (... 274 chars omitted)
child 0, seed: int64
child 1, model: string
child 2, sessions: int64
child 3, turns: int64
child 4, system_tokens: int64
child 5, tools: int64
child 6, tool_burst_min: int64
child 7, tool_burst_max: int64
child 8, retry_rate: double
child 9, faults: struct<F1: double, F2: double, F3: double, F4: double, F5: double, F6: double, F7: double, F8: doubl (... 2 chars omitted)
child 0, F1: double
child 1, F2: double
child 2, F3: double
child 3, F4: double
child 4, F5: double
child 5, F6: double
child 6, F7: double
child 7, F8: double
child 10, chars_per_token: double
child 11, session_gap_s: double
child 12, step_gap_s: double
child 13, client_tool_order: string
messages: null
tools: null
request_index: int64
request_id: string
session_id: string
fault: string
scope: string
reference_request_id: string
location: struct<element: string, section: string, detail: string, tool_index: int64, role: string>
child 0, element: string
child 1, section: string
child 2, detail: string
child 3, tool_index: int64
child 4, role: string
timestamp: string
model: string
to
{'request_id': Value('string'), 'session_id': Value('string'), 'timestamp': Value('string'), 'model': Value('string'), 'messages': List(Json(decode=True)), 'tools': List({'type': Value('string'), 'function': {'name': Value('string'), 'description': Value('string'), 'parameters': {'type': Value('string'), 'properties': Json(decode=True), 'required': List(Value('string'))}}})}
because column names don't match
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1835, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 621, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 361, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2381, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2309, in cast_table_to_schema
raise CastError(
...<3 lines>...
)
datasets.table.CastError: Couldn't cast
_meta: struct<generator: string, config: struct<seed: int64, model: string, sessions: int64, turns: int64, (... 309 chars omitted)
child 0, generator: string
child 1, config: struct<seed: int64, model: string, sessions: int64, turns: int64, system_tokens: int64, tools: int64 (... 274 chars omitted)
child 0, seed: int64
child 1, model: string
child 2, sessions: int64
child 3, turns: int64
child 4, system_tokens: int64
child 5, tools: int64
child 6, tool_burst_min: int64
child 7, tool_burst_max: int64
child 8, retry_rate: double
child 9, faults: struct<F1: double, F2: double, F3: double, F4: double, F5: double, F6: double, F7: double, F8: doubl (... 2 chars omitted)
child 0, F1: double
child 1, F2: double
child 2, F3: double
child 3, F4: double
child 4, F5: double
child 5, F6: double
child 6, F7: double
child 7, F8: double
child 10, chars_per_token: double
child 11, session_gap_s: double
child 12, step_gap_s: double
child 13, client_tool_order: string
messages: null
tools: null
request_index: int64
request_id: string
session_id: string
fault: string
scope: string
reference_request_id: string
location: struct<element: string, section: string, detail: string, tool_index: int64, role: string>
child 0, element: string
child 1, section: string
child 2, detail: string
child 3, tool_index: int64
child 4, role: string
timestamp: string
model: string
to
{'request_id': Value('string'), 'session_id': Value('string'), 'timestamp': Value('string'), 'model': Value('string'), 'messages': List(Json(decode=True)), 'tools': List({'type': Value('string'), 'function': {'name': Value('string'), 'description': Value('string'), 'parameters': {'type': Value('string'), 'properties': Json(decode=True), 'required': List(Value('string'))}}})}
because column names don't match
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1379, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 956, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
request_id string | session_id string | timestamp string | model string | messages list | tools list |
|---|---|---|---|---|---|
sess-0000-r000 | sess-0000 | 2026-01-15T09:00:00.000Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r001 | sess-0000 | 2026-01-15T09:00:06.339Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r002 | sess-0000 | 2026-01-15T09:00:08.562Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r003 | sess-0000 | 2026-01-15T09:00:12.624Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r004 | sess-0000 | 2026-01-15T09:00:18.528Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467698\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r000 | sess-0001 | 2026-01-15T09:00:20.406Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r005 | sess-0000 | 2026-01-15T09:00:20.875Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467698\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r006 | sess-0000 | 2026-01-15T09:00:24.563Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467780\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r001 | sess-0001 | 2026-01-15T09:00:24.848Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r002 | sess-0001 | 2026-01-15T09:00:28.196Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r007 | sess-0000 | 2026-01-15T09:00:30.189Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467780\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0000-r008 | sess-0000 | 2026-01-15T09:00:32.681Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467780\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r003 | sess-0001 | 2026-01-15T09:00:32.852Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r004 | sess-0001 | 2026-01-15T09:00:35.477Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r005 | sess-0001 | 2026-01-15T09:00:36.907Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r006 | sess-0001 | 2026-01-15T09:00:38.238Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
sess-0001-r007 | sess-0001 | 2026-01-15T09:00:43.145Z | agent-model | [
{
"role": "system",
"content": "You are Forge Agent, an autonomous software engineering assistant.\n\nEpoch: 1768467692\n\nYou are assisting Ingrid Dubois from the mobile team.\n\nIn server result code task should that write only tool package. In code of commit step cache shard query config this project you... | [
{
"type": "function",
"function": {
"name": "build_service",
"description": "Then path verify agent this server will path when review version record code index service stream.",
"parameters": {
"type": "object",
"properties": {
"schema_name": {
"type":... |
End of preview.
AgentLoad synthetic agent traces
Synthetic OpenAI-compatible chat-completion request logs of tool-using agent sessions, with ground-truth
labels of injected prefix-cache fragmentation (F1–F8). Generated by prefixanvil gen (PrefixAnvil AgentLoad);
fully reproducible from a small JSON config and a seed. No real user data. The traces are generated by
PrefixAnvil — https://github.com/NagaYu/prefixanvil
License
This dataset is made publicly visible solely so it can be read and evaluated. It is All Rights Reserved — no license is granted beyond viewing and downloading for evaluation. Licensing or transfer inquiries: https://nagayu-portfolio.nagayu.workers.dev/en
Files
| file | content |
|---|---|
bench_main.jsonl |
377 requests, 40 sessions, all eight fragmentation types injected at 6% each |
bench_main.labels.jsonl |
one line per injected event: request_index, request_id, fault (F1–F8), scope (within/cross session), reference_request_id, location |
bench_xsession.jsonl |
155 requests, 30 sessions, no faults; each session's client lists the same tools in its own order |
configs/*.json |
the exact generator configs (seeds included) |
Each request line: request_id, session_id, timestamp, model, messages, tools.
How it was generated
prefixanvil gen --config fixtures/bench/bench_main.json --out bench_main.jsonl
prefixanvil gen --config fixtures/bench/bench_xsession.json --out bench_xsession.jsonl
Byte-identical output for the same config (pure-Python RNG; checked in CI). File sha256 of the four .jsonl
files in this folder:
| file | sha256 |
|---|---|
bench_main.jsonl |
cee5445df3364b3fc0a2af4a1f906356d537076857a5c4059ce96a6b800ef000 |
bench_main.labels.jsonl |
5b114c0cf4547eadb77454313d82249e1fdccd869118d72864a31c16415b623a |
bench_xsession.jsonl |
271a8a6f3c2a61e9ae4b0878285e65ac96e17bf0b08202b415bff2c3a2f819df |
bench_xsession.labels.jsonl |
ec1431b9afd077cdc20026ca7886c5169f821ff4f0ec3224bba81a73d9af0b39 |
Fragmentation types
F1 volatile values (timestamps, UUIDs, run ids) · F2 non-deterministic JSON serialization · F3 tool-set churn · F4 per-user interpolation · F5 conditional system sections · F6 whitespace/format drift · F7 retrieved context inserted before stable instructions · F8 rewritten history. At most one event per request/reference pair, so the cause of each first divergence is unambiguous.
Benchmark headline
Measured on Kaggle 2 × Tesla T4 (free tier) with Qwen2.5-7B-Instruct-AWQ and vLLM 0.33.0, replaying these
traces at concurrency 1 (run t4-20261111-0408). Hit rate and prefill are determined by the cache algorithm,
not the GPU; TTFT/GPU-seconds (in BENCH.md) are T4 reference values only.
| trace | policy | token-weighted hit rate | recomputed prefill tokens |
|---|---|---|---|
| bench_main | raw | 74.71% | 241,640 |
| bench_main | L1 canonicalization | 81.79% | 172,268 (−28.7%) |
| bench_main | L2 relocation (reference) | 83.61% | 155,068 (−35.8%) |
| bench_xsession | raw | 86.63% | 50,120 |
| bench_xsession | L1 session-stable (deployed policy) | 86.69% | 49,273 |
| bench_xsession | L1 stateless name-sort (ceiling) | 95.31% | 17,369 |
L1/L2 are prompt transforms; identical generated text is not guaranteed (Phase 3 sampled L1-vs-raw match 10/18,
L2-vs-raw 4/6, against an 18/18 raw-vs-raw control). Full numbers, fidelity and the NVIDIA Dynamo trial are in
BENCH.md.
Limitations
Synthetic text (word-salad sentences), synthetic tools, open-loop (assistant turns are generated, not model outputs). Useful for measuring prefix-cache behaviour, not for training or evaluating language quality.
- Downloads last month
- 42