claude-converter 1.0.0__tar.gz

claude_converter-1.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 Aquiles-ai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

claude_converter-1.0.0/PKG-INFO

@@ -0,0 +1,282 @@
+Metadata-Version: 2.4
+Name: claude-converter
+Version: 1.0.0
+Summary: A zero-dependency Python module for inspecting and converting Claude Code session files '.jsonl' into the 'messages' format expected by Hugging Face Transformers.
+Author-email: Fredy Rivera <fredyriveraacevedo13@gmail.com>
+License: Apache License 2.0
+Project-URL: Homepage, https://github.com/FredyRivera-dev/claude_converter
+Project-URL: Issues, https://github.com/FredyRivera-dev/claude_converter/issues
+Keywords: ai,claude,transformers
+Classifier: Development Status :: 4 - Beta
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Environment :: Web Environment
+Classifier: Topic :: Software Development :: Build Tools
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: isort; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Dynamic: license-file
+
+# claude_converter
+
+A zero-dependency Python module for inspecting and converting [Claude Code](https://www.anthropic.com/claude-code) session files (`.jsonl`) into the `messages` format expected by Hugging Face Transformers.
+
+Claude Code stores every session as a JSONL file on disk under `~/.claude/projects/<encoded-project-path>/<session-uuid>.jsonl`. Each line is a JSON record containing the full message history — user prompts, assistant responses, tool calls, tool results, and extended thinking blocks. This module parses that format and flattens it into the simple `[{"role": ..., "content": ...}]` list that `tokenizer.apply_chat_template()` consumes directly.
+
+## Why this exists
+
+The conversion pipeline has two stages that are often conflated:
+
+```
+Claude Code JSONL  →  [claude_converter]  →  messages[]  →  apply_chat_template()  →  tokens
+                         (this module)                        (transformers handles this)
+```
+
+`apply_chat_template()` handles stage 2 (turning a `messages` list into model-specific token sequences), but it knows nothing about Claude Code's JSONL format. This module handles stage 1.
+
+## Installation
+
+```bash
+uv pip install claude-converter
+```
+
+## Quick start
+
+```python
+from claude_converter import session_to_messages
+
+messages = session_to_messages("path/to/session.jsonl")
+```
+
+`messages` is ready for `apply_chat_template()`.
+
+## API reference
+
+### `load_session(path)`
+
+Loads a Claude Code `.jsonl` file and returns the raw list of record dicts — one per line.
+
+```python
+from claude_converter import load_session
+
+records = load_session("session.jsonl")
+# [{"type": "user", "uuid": "...", "message": {...}, ...}, ...]
+```
+
+Raises `FileNotFoundError` if the file doesn't exist, `ValueError` if the extension is not `.jsonl` or `.json`, or if the file contains no valid records.
+
+### `session_to_messages(path, output=None)`
+
+Loads a session and converts it to a `messages` list in one call. Optionally saves the result to a JSON file.
+
+```python
+from claude_converter import session_to_messages
+
+# In-memory only
+messages = session_to_messages("session.jsonl")
+
+# Save to disk too
+messages = session_to_messages("session.jsonl", output="messages.json")
+```
+
+Returns `list[{"role": str, "content": str}]`. Content blocks (`tool_use`, `tool_result`, `thinking`, `text`) are flattened to plain text using XML-style tags so the conversation structure is preserved.
+
+### `records_to_messages(records)`
+
+Converts an already-loaded list of records into the messages format. Useful when you want to load once and run multiple transformations without re-reading the file.
+
+```python
+from claude_converter import load_session, records_to_messages
+
+records  = load_session("session.jsonl")
+messages = records_to_messages(records)
+```
+
+### `inspect_session(path, show_flow=False, show_blocks=False, show_raw=False)`
+
+Prints a color-coded report of a session: record type counts, content block breakdown by role, and token usage totals. The conversation flow is optional and off by default.
+
+```python
+from claude_converter import inspect_session
+
+# Stats only (default)
+inspect_session("session.jsonl")
+
+# Stats + timestamped conversation flow
+inspect_session("session.jsonl", show_flow=True)
+
+# Flow + content of every block inline
+inspect_session("session.jsonl", show_flow=True, show_blocks=True)
+
+# Full report: flow, blocks, and raw record structure examples
+inspect_session("session.jsonl", show_flow=True, show_blocks=True, show_raw=True)
+```
+
+Example output (default):
+
+```
+══════════════════════════════════════════════════════════════════════
+  CLAUDE CODE SESSION INSPECTOR
+══════════════════════════════════════════════════════════════════════
+  File    : session.jsonl
+  Size    : 3.6 KB
+  Lines   : 9
+  Session : abc-123
+  CWD     : /home/user/myproject
+  Branch  : main
+══════════════════════════════════════════════════════════════════════
+
+  RECORD TYPES
+  user         4  ████
+  assistant    4  ████
+  system       1  █
+
+  CONTENT BLOCKS (by record type)
+  assistant
+    · text                 3
+    · tool_use             2
+    · thinking             1
+  user
+    · text                 2
+    · tool_result          2
+
+  TOKEN USAGE
+  Input       : 2,617
+  Output      : 147
+  Cache read  : 1,700
+  Cache write :   482
+  Total       : 2,764
+```
+
+## Using the output with Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from claude_converter import session_to_messages
+
+MODEL_ID = "your-model-id"
+
+messages  = session_to_messages("session.jsonl", output="messages.json")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+tokens = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_dict=True,
+    return_tensors="pt",
+)
+```
+
+## Fine-tuning local models
+
+Claude Code sessions are a natural source of training data: they capture
+real coding conversations (tool calls, reasoning traces, multi-turn edits)
+in a format that maps directly to the `messages` list expected by every major
+fine-tuning framework.
+
+### Preprocessing recommendations
+
+Before training, filter the messages list for your target model:
+
+- **Strip tool blocks**: most local models don't understand `<tool_use>` /
+  `<tool_result>` tags. Remove or replace them unless you are training a
+  tool-calling model.
+- **Strip thinking blocks**: `<thinking>` blocks leak chain-of-thought that
+  may not generalize. Keep them only if you are distilling reasoning behavior.
+- **Drop short or empty turns**: single-word assistant replies and empty
+  user turns add noise.
+
+```python
+def clean_messages(messages, keep_tool_calls=False, keep_thinking=False):
+    import re
+    cleaned = []
+    for msg in messages:
+        content = msg["content"]
+        if not keep_thinking:
+            content = re.sub(r"<thinking>.*?</thinking>", "", content, flags=re.DOTALL)
+        if not keep_tool_calls:
+            content = re.sub(r"<tool_use.*?>.*?</tool_use>", "", content, flags=re.DOTALL)
+            content = re.sub(r"<tool_result>.*?</tool_result>", "", content, flags=re.DOTALL)
+        content = content.strip()
+        if content:
+            cleaned.append({"role": msg["role"], "content": content})
+    return cleaned
+```
+
+### TRL / SFTTrainer example
+
+```python
+from datasets import Dataset
+from trl import SFTTrainer, SFTConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from claude_converter import session_to_messages
+import glob
+
+MODEL_ID = "your-model-id"
+
+all_messages = []
+for path in glob.glob("~/.claude/projects/**/*.jsonl", recursive=True):
+    msgs = session_to_messages(path)
+    msgs = clean_messages(msgs)
+    if len(msgs) >= 2:
+        all_messages.append({"messages": msgs})
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model     = AutoModelForCausalLM.from_pretrained(MODEL_ID)
+dataset   = Dataset.from_list(all_messages)
+
+trainer = SFTTrainer(
+    model=model,
+    args=SFTConfig(output_dir="./output", max_seq_length=4096),
+    train_dataset=dataset,
+    processing_class=tokenizer,
+)
+trainer.train()
+```
+
+### Axolotl / LLaMA-Factory
+
+Both frameworks accept a `sharegpt` format, which is structurally identical to
+the `messages` list this module produces. Save the cleaned messages list with
+`output="messages.json"` and point your framework config at that file.
+
+## Content block mapping
+
+Claude Code sessions contain several block types that have no direct equivalent in the Transformers `messages` format. This module flattens them as follows:
+
+| Claude Code block | Flattened as |
+|---|---|
+| `text` | plain text, as-is |
+| `thinking` | `<thinking>...</thinking>` |
+| `tool_use` | `<tool_use name='...'>{input JSON}</tool_use>` |
+| `tool_result` | `<tool_result>...</tool_result>` |
+| `system` records | skipped (not included in messages output) |
+
+Records with an empty content string after flattening are also skipped.
+
+## Where Claude Code stores sessions
+
+```
+~/.claude/projects/
+└── <url-encoded-project-path>/
+    └── <session-uuid>.jsonl
+```
+
+The project path is URL-encoded: `/home/user/myapp` becomes `-home-user-myapp`. Each session is a separate file, append-only, one JSON object per line.
+
+## Limitations
+
+- **Graph structure**: Claude Code sessions are directed acyclic graphs linked by `parentUuid`. This module reads lines in file order (linear), which is correct for the vast majority of sessions. Branched or multi-agent sessions may need custom traversal.
+- **Tool call fidelity**: Most local models don't natively understand `<tool_use>` or `<tool_result>` tags. For inference-only use cases, consider stripping those blocks before passing to `apply_chat_template()`.
+- **No streaming**: The module loads the full file into memory. For very large sessions, use `load_session()` and process records in batches.
+- **Data quality for fine-tuning**: Sessions include failed attempts, retries, and exploratory tool calls. Blindly training on raw sessions will teach the model bad habits. Filter aggressively: keep only sessions where the final assistant turn solves the stated problem, and prefer sessions with a high ratio of `text` blocks to `tool_use` blocks unless tool-calling is your training target.