Dataset Preview
Duplicate
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed because of a cast error
Error code:   DatasetGenerationCastError
Exception:    DatasetGenerationCastError
Message:      An error occurred while generating the dataset

All the data files must have the same columns, but at some point there are 8 new columns ({'total_output_tokens', 'sessions', 'total_input_tokens', 'models', 'exported_at', 'projects', 'skipped', 'redactions'}) and 8 missing columns ({'session_id', 'stats', 'project', 'model', 'start_time', 'messages', 'git_branch', 'end_time'}).

This happened while the json dataset builder was generating data using

hf://datasets/parani01/dataclaw-parani01/metadata.json (at revision 98a7d6ffad5b3ea5272df4aab890e4d7ac87976f), [/tmp/hf-datasets-cache/medium/datasets/36531242505508-config-parquet-and-info-parani01-dataclaw-parani0-22f9b3e8/hub/datasets--parani01--dataclaw-parani01/snapshots/98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/conversations.jsonl (origin=hf://datasets/parani01/dataclaw-parani01@98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/conversations.jsonl), /tmp/hf-datasets-cache/medium/datasets/36531242505508-config-parquet-and-info-parani01-dataclaw-parani0-22f9b3e8/hub/datasets--parani01--dataclaw-parani01/snapshots/98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/metadata.json (origin=hf://datasets/parani01/dataclaw-parani01@98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/metadata.json)]

Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
                  writer.write_table(table)
                File "/usr/local/lib/python3.12/site-packages/datasets/arrow_writer.py", line 675, in write_table
                  pa_table = table_cast(pa_table, self._schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2272, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2218, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              sessions: int64
              skipped: int64
              redactions: int64
              models: struct<claude-opus-4-6: int64>
                child 0, claude-opus-4-6: int64
              projects: list<item: string>
                child 0, item: string
              total_input_tokens: int64
              total_output_tokens: int64
              exported_at: string
              to
              {'session_id': Value('string'), 'model': Value('string'), 'git_branch': Value('string'), 'start_time': Value('string'), 'end_time': Value('string'), 'messages': List({'role': Value('string'), 'content': Value('string'), 'timestamp': Value('string'), 'tool_uses': List({'tool': Value('string'), 'input': Value('string')}), 'thinking': Value('string')}), 'stats': {'user_messages': Value('int64'), 'assistant_messages': Value('int64'), 'tool_uses': Value('int64'), 'input_tokens': Value('int64'), 'output_tokens': Value('int64'), 'skipped_lines': Value('int64')}, 'project': Value('string')}
              because column names don't match
              
              During handling of the above exception, another exception occurred:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1347, in compute_config_parquet_and_info_response
                  parquet_operations = convert_to_parquet(builder)
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 980, in convert_to_parquet
                  builder.download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 884, in download_and_prepare
                  self._download_and_prepare(
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 947, in _download_and_prepare
                  self._prepare_split(split_generator, **prepare_split_kwargs)
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1736, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1889, in _prepare_split_single
                  raise DatasetGenerationCastError.from_cast_error(
              datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
              
              All the data files must have the same columns, but at some point there are 8 new columns ({'total_output_tokens', 'sessions', 'total_input_tokens', 'models', 'exported_at', 'projects', 'skipped', 'redactions'}) and 8 missing columns ({'session_id', 'stats', 'project', 'model', 'start_time', 'messages', 'git_branch', 'end_time'}).
              
              This happened while the json dataset builder was generating data using
              
              hf://datasets/parani01/dataclaw-parani01/metadata.json (at revision 98a7d6ffad5b3ea5272df4aab890e4d7ac87976f), [/tmp/hf-datasets-cache/medium/datasets/36531242505508-config-parquet-and-info-parani01-dataclaw-parani0-22f9b3e8/hub/datasets--parani01--dataclaw-parani01/snapshots/98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/conversations.jsonl (origin=hf://datasets/parani01/dataclaw-parani01@98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/conversations.jsonl), /tmp/hf-datasets-cache/medium/datasets/36531242505508-config-parquet-and-info-parani01-dataclaw-parani0-22f9b3e8/hub/datasets--parani01--dataclaw-parani01/snapshots/98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/metadata.json (origin=hf://datasets/parani01/dataclaw-parani01@98a7d6ffad5b3ea5272df4aab890e4d7ac87976f/metadata.json)]
              
              Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

session_id
string
model
string
git_branch
string
start_time
string
end_time
string
messages
list
stats
dict
project
string
487062a1-9362-4218-b1c9-a263fd0c18f9
claude-opus-4-6
HEAD
2026-02-11T09:06:24.244Z
2026-02-11T09:09:36.855Z
[ { "role": "user", "content": "<ide_opened_file>The user opened the file /user_6f6789bd/check.py in the IDE. This may or may not be related to the current task.</ide_opened_file>\ncan you run and install dependecises and run the information", "timestamp": "2026-02-11T09:06:24.244Z", "tool_uses": null...
{ "user_messages": 1, "assistant_messages": 10, "tool_uses": 4, "input_tokens": 194460, "output_tokens": 33, "skipped_lines": 0 }
~home
77b97807-13ec-46a9-b323-b02787e5887f
claude-opus-4-6
HEAD
2026-02-26T01:18:33.858Z
2026-02-26T01:29:11.667Z
[ { "role": "user", "content": "Help me export my Claude Code, Codex, and Gemini CLI conversation history to Hugging Face using DataClaw.\nInstall it, set up the skill, then walk me through the process.\n\nSTEP 1 — INSTALL\n pip install dataclaw\n If that fails: git clone https://github.com/banodoco/datacla...
{ "user_messages": 4, "assistant_messages": 64, "tool_uses": 36, "input_tokens": 1747211, "output_tokens": 5643, "skipped_lines": 0 }
~home
457d34f1-af77-4a73-9180-9f4e8440d8e4
claude-opus-4-6
main
2026-02-10T16:35:47.445Z
2026-02-11T04:39:22.737Z
[ { "role": "user", "content": "[Request interrupted by user for tool use]", "timestamp": "2026-02-10T16:35:47.445Z", "tool_uses": null, "thinking": null }, { "role": "user", "content": "Implement the following plan:\n\n# Portfolio Rebuild Plan: React + Vite + Dark Minimal Theme\n\n## ...
{ "user_messages": 4, "assistant_messages": 118, "tool_uses": 89, "input_tokens": 4656392, "output_tokens": 27092, "skipped_lines": 0 }
baranidharan27-github-io
457d34f1-af77-4a73-9180-9f4e8440d8e4
claude-opus-4-6
main
2026-02-10T16:19:14.672Z
2026-02-10T16:34:36.480Z
[ { "role": "user", "content": "hey hi how are you", "timestamp": "2026-02-10T16:19:14.672Z", "tool_uses": null, "thinking": null }, { "role": "assistant", "content": "Hey! I'm doing well, thanks. How can I help you today?", "timestamp": "2026-02-10T16:19:17.495Z", "tool_uses":...
{ "user_messages": 3, "assistant_messages": 27, "tool_uses": 10, "input_tokens": 992852, "output_tokens": 7334, "skipped_lines": 0 }
baranidharan27-github-io
d6d538dd-3efb-4b6a-a84f-34f0c8782a43
claude-opus-4-6
main
2026-02-12T15:01:03.429Z
2026-02-13T11:47:04.486Z
[ { "role": "user", "content": "bro can you make thie even more good not dark theme a light theme with good colours ", "timestamp": "2026-02-12T15:01:03.429Z", "tool_uses": null, "thinking": null }, { "role": "assistant", "content": null, "timestamp": "2026-02-12T15:01:06.660Z", ...
{ "user_messages": 6, "assistant_messages": 147, "tool_uses": 101, "input_tokens": 9765388, "output_tokens": 29381, "skipped_lines": 0 }
baranidharan27-github-io
null
null
null
null
null
null
null
null

Claude Code Conversation Logs

Exported with DataClaw.

Tag: dataclawBrowse all DataClaw datasets

Stats

Metric Value
Sessions 5
Projects 2
Input tokens 17.4M
Output tokens 69K
Last updated 2026-02-26

Models

Model Sessions
claude-opus-4-6 5

Schema

Each line in conversations.jsonl is one conversation session:

{
  "session_id": "uuid",
  "project": "my-project",
  "model": "claude-opus-4-6",
  "git_branch": "main",
  "start_time": "2025-01-15T10:00:00+00:00",
  "end_time": "2025-01-15T10:30:00+00:00",
  "messages": [
    {"role": "user", "content": "Fix the login bug", "timestamp": "..."},
    {
      "role": "assistant",
      "content": "I'll investigate the login flow.",
      "thinking": "The user wants me to...",
      "tool_uses": [{"tool": "Read", "input": "src/auth.py"}],
      "timestamp": "..."
    }
  ],
  "stats": {
    "user_messages": 5,
    "assistant_messages": 8,
    "tool_uses": 20,
    "input_tokens": 50000,
    "output_tokens": 3000
  }
}

Privacy

  • Paths anonymized to project-relative; usernames hashed
  • No tool outputs — only tool call inputs (summaries)

Load

from datasets import load_dataset
ds = load_dataset("parani01/dataclaw-parani01", split="train")

Export your own

pip install dataclaw
dataclaw
Downloads last month
181