conversations listlengths 2 74 | agent stringclasses 1
value | model stringclasses 1
value | model_provider stringclasses 1
value | date stringlengths 27 27 | task stringlengths 17 17 | episode stringclasses 36
values | run_id stringclasses 1
value | trial_name stringlengths 26 26 | result stringclasses 4
values | instruction stringlengths 10 944 ⌀ | verifier_output stringlengths 88 29.4k ⌀ | prompt_token_ids listlengths 0 32 | completion_token_ids listlengths 0 32 | logprobs listlengths 0 32 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
{
"content": "",
"role": "user"
},
{
"content": "<think>I need to understand the test requirements and existing project structure before implementing the solution.\n</think>\n\n\n\n<tool_call>\n{\"name\": \"read\", \"arguments\": {\"filePath\": \"/tests/TestSolution.java\"}}\n</tool_call>\n<tool_cal... | opencode | vllm/1747708670135088 | vllm | 2026-07-06T03:38:39.737833Z | methods2test-4667 | episode-1 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4667__zHi7n6v | AgentTimeoutError | null | null | [] | [] | [] |
[
{
"content": "",
"role": "user"
},
{
"content": "<think>I need to analyze the test file and understand what classes and interfaces need to be implemented to make it pass.\n</think>\n\n\n\n<tool_call>\n{\"name\": \"read\", \"arguments\": {\"filePath\": \"/tests/TestSolution.java\"}}\n</tool_call>\n<t... | opencode | vllm/1747708670135088 | vllm | 2026-07-06T10:36:46.014111Z | methods2test-4189 | episode-6 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4189__zSCZdNi | AgentTimeoutError | The files don't exist yet. Based on the task description, I need to create the project structure. Let me analyze what's needed:
1. The test uses `AsyncMethodCallback`, `client`, `iface`, `Solution`, and static methods like `doAnswer`, `when`, `any`, `assertThat`, `verify`, `eq`
2. These are Mockito and Hamcrest patter... | null | [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>I need to understand the test requirements first by(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T15:22:54.472593Z | methods2test-3885 | episode-15 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-3885__L7xudED | AgentTimeoutError | "Based on the task description, I need to create the project structure from scratch. Let me set up t(...TRUNCATED) | null | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[40,1144,310,3418,279,1228,8242,1118,539,5122,279,1228,999,321,28523,8756,310,1436,1092,17210,1144,(...TRUNCATED) | [[-0.22695708274841309,-8.344598427356686e-6,-7.510143404942937e-6,-0.7316544055938721,-0.0265869703(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>I need to understand the test requirements and impl(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T15:58:42.930670Z | methods2test-3841 | episode-9 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-3841__YPJzAUN | NonZeroAgentExitCodeError | "Based on the task description, I need to create the necessary Java source files and Maven configura(...TRUNCATED) | Compiling and running tests...
v3 verifier: runner_rc=0 tests_run=0 failures=0 errors=0
| [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>I need to first understand the test file and pom.xm(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T04:12:58.141502Z | methods2test-4635 | episode-6 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4635__t558CU2 | AgentTimeoutError | "The files don't exist yet. Based on the task description, I need to:\n1. Create the test file at `/(...TRUNCATED) | null | [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>Let me start by understanding the task. I need to i(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T02:39:34.777563Z | methods2test-4716 | episode-22 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4716__GKVajTp | 0.0 | "The test file and pom.xml don't exist yet. Based on the task description, I need to create:\n\n1. `(...TRUNCATED) | "Compiling and running tests...\n[\u001b[1;31mERROR\u001b[m] COMPILATION ERROR : \n[\u001b[1;31mERRO(...TRUNCATED) | [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>I need to implement a BitStream class that the test(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T06:48:23.829717Z | methods2test-4473 | episode-15 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4473__wVhwxEh | 0.0 | "Based on the task description, I need to implement a `BitStream` class that:\n1. Takes an integer s(...TRUNCATED) | "Compiling and running tests...\n[\u001b[1;31mERROR\u001b[m] COMPILATION ERROR : \n[\u001b[1;31mERRO(...TRUNCATED) | [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>I need to understand the test requirements and impl(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T10:42:55.492097Z | methods2test-4184 | episode-3 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4184__vG39NAP | AgentTimeoutError | "The test file and pom.xml don't exist yet. Based on the task description, I need to create the enti(...TRUNCATED) | null | [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>Let me analyze the task:\n\n1. I need to implement (...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T04:49:07.621507Z | methods2test-4602 | episode-23 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4602__HuGrxXM | AgentTimeoutError | "The test file and pom.xml don't exist yet. Based on the task description, I need to create the enti(...TRUNCATED) | null | [] | [] | [] |
[{"content":"","role":"user"},{"content":"<think>I need to read the test file and pom.xml to underst(...TRUNCATED) | opencode | vllm/1747708670135088 | vllm | 2026-07-06T13:53:13.581397Z | methods2test-4020 | episode-3 | 3b996477-0a9c-4ba3-936a-e651eae48722 | methods2test-4020__nm9BsZZ | AgentTimeoutError | "The test file and directories don't exist yet. Based on the task description, I need to create the (...TRUNCATED) | Compiling and running tests...
v3 verifier: runner_rc=0 tests_run=0 failures=0 errors=0
| [] | [] | [] |
End of preview. Expand in Data Studio
Agent trace dataset
Decoding the literal token IDs
The prompt_token_ids / completion_token_ids / logprobs columns are the
verbatim tokens the serving engine emitted, stored PER AGENT STEP as a
list-of-lists (one inner list per turn). To turn them back into text you MUST
use the exact tokenizer the model was served with — a generic same-family
tokenizer will decode word tokens to garbage.
Served model / tokenizer source: Qwen/Qwen3.5-122B-A10B-FP8
from transformers import AutoTokenizer
# Use the served model's own tokenizer (pull from the ref above; if it is a
# gs:// mirror, copy tokenizer.json/tokenizer_config.json/vocab.json/merges.txt
# locally first and point AutoTokenizer at that dir).
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-122B-A10B-FP8")
# token_ids are list-of-lists (one list per turn) — decode each turn:
text = [tok.decode(turn, skip_special_tokens=False) for turn in completion_token_ids]
Engine-reported served model name: 1747708670135088
See tokenizer_provenance.json for a machine-readable version.
- Downloads last month
- 119