feat: Add ZepGraphMemory to autogen example

[paul-paliychuk]

Important

Adds ZepGraphMemory and new tools for graph operations to Zep AutoGen integration, with updated documentation, examples, and tests.

• Memory Integration:
  • Adds ZepGraphMemory for graph-based memory storage and retrieval in graph_memory.py.
  • Updates ZepUserMemory to support thread context modes in memory.py.
• Tool Integration:
  • Adds create_search_graph_tool and create_add_graph_data_tool in tools.py for graph operations.
• Documentation:
  • Adds CLAUDE.md for detailed guidance on using Zep AutoGen integration.
  • Updates README.md to include new features and usage examples.
• Examples:
  • Adds autogen_graph.py, autogen_tools_full.py, and autogen_tools_search.py for demonstrating new functionalities.
• Tests:
  • Updates test_basic.py to test new memory and tool functionalities.
• Misc:
  • Bumps version to 1.1.0 in pyproject.toml.
  • Updates __init__.py to export new classes and functions.

^{This description was created by for b7f5e89. You can customize this summary. It will automatically update as commits are pushed.}

[ellipsis-dev]

Caution

Changes requested ❌

Reviewed everything up to 0a82286 in 1 minute and 59 seconds. Click for details.

• Reviewed 725 lines of code in 7 files
• Skipped 0 files when reviewing.
• Skipped posting 2 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. integrations/python/zep_autogen/src/zep_autogen/__init__.py:11

• Draft comment:
  The usage docstring still references ZepMemory; update it to ZepUserMemory for consistency.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

2. integrations/python/zep_autogen/tests/test_basic.py:20

• Draft comment:
  Update the test docstring to reference ZepUserMemory instead of ZepMemory.
• Reason this comment was not posted:
  Comment was on unchanged code.

Workflow ID: wflow_LQIA1mz5wAqjqqbj

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}

[ellipsis-dev]

Important

Looks good to me! 👍

Reviewed dcf615a in 1 minute and 6 seconds. Click for details.

• Reviewed 566 lines of code in 6 files
• Skipped 0 files when reviewing.
• Skipped posting 4 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. integrations/python/zep_autogen/src/zep_autogen/__init__.py:10

• Draft comment:
  Usage doc references 'ZepMemory' which isn’t exported. Update it to use 'ZepUserMemory' or provide an alias.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

2. integrations/python/zep_autogen/src/zep_autogen/graph_memory.py:289

• Draft comment:
  Avoid using print in production; use the logger (e.g., self._logger.debug) for graph context output.
• Reason this comment was not posted:
  Comment was on unchanged code.

3. integrations/python/zep_autogen/examples/autogen_graph.py:107

• Draft comment:
  Using 'await asyncio.sleep(50)' for demo purposes may be excessive; consider reducing or better explaining its purpose.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

4. integrations/python/zep_autogen/README.md:112

• Draft comment:
  Ensure documentation matches exported classes (e.g., ZepUserMemory and ZepGraphMemory) to avoid confusion.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50% This comment is asking the author to ensure that the documentation matches the exported classes. It is not a specific suggestion or a request for a test, and it doesn't point out a specific issue with the code. It is more of a general reminder, which violates the rule against asking the author to ensure things.

Workflow ID: wflow_R1PsVeG8ciYBlrqU

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}

[ellipsis-dev]

Caution

Changes requested ❌

Reviewed 838ec0a in 1 minute and 40 seconds. Click for details.

• Reviewed 742 lines of code in 4 files
• Skipped 0 files when reviewing.
• Skipped posting 5 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. integrations/python/zep_autogen/CLAUDE.md:1

• Draft comment:
  Comprehensive documentation with clear examples and proper grammar. No issues found.
• Reason this comment was not posted:
  Confidence changes required: 0% <= threshold 50% None

2. integrations/python/zep_autogen/examples/autogen_tools_full.py:71

• Draft comment:
  Consider parameterizing the indexing delay (sleep duration) to better adapt to different environments.
• Reason this comment was not posted:
  Confidence changes required: 33% <= threshold 50% None

3. integrations/python/zep_autogen/examples/autogen_tools_search.py:42

• Draft comment:
  Ensure the hard-coded indexing delay (await asyncio.sleep(30)) is appropriate; consider making it configurable.
• Reason this comment was not posted:
  Confidence changes required: 33% <= threshold 50% None

4. integrations/python/zep_autogen/src/zep_autogen/tools.py:212

• Draft comment:
  Consider simplifying the description string in the FunctionTool creation for better readability.
• Reason this comment was not posted:
  Confidence changes required: 33% <= threshold 50% None

5. integrations/python/zep_autogen/src/zep_autogen/tools.py:48

• Draft comment:
  The graph_id/user_id validation is repeated across functions; consider refactoring this into a helper to reduce duplication.
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50% None

Workflow ID: wflow_sKwgM7IOexWEqjsc

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}

[ellipsis-dev]

Important

Looks good to me! 👍

Reviewed f263a80 in 1 minute and 7 seconds. Click for details.

• Reviewed 95 lines of code in 4 files
• Skipped 0 files when reviewing.
• Skipped posting 4 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. integrations/python/zep_autogen/src/zep_autogen/__init__.py:1

• Draft comment:
  The package-level docstring and metadata (version, author, description) were removed. Ensure that user-facing documentation is maintained elsewhere if needed.
• Reason this comment was not posted:
  Comment looked like it was already resolved.

2. integrations/python/zep_autogen/src/zep_autogen/graph_memory.py:286

• Draft comment:
  Removed debug print statement from update_context. Good cleanup – consider using logger if debugging info is needed.
• Reason this comment was not posted:
  Comment looked like it was already resolved.

3. integrations/python/zep_autogen/src/zep_autogen/memory.py:77

• Draft comment:
  Updated the docstring parameter name from 'entry' to 'content' for clarity. This improves consistency with the parameter naming in the method signature.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50% This comment is purely informative, explaining a change that was made. It does not provide a suggestion, ask for confirmation, or point out a potential issue. According to the rules, purely informative comments should be removed.

4. integrations/python/zep_autogen/tests/test_basic.py:25

• Draft comment:
  Removed TestBasicFunctionality class that verified package metadata. Confirm that this removal aligns with the intended deprecation of the metadata in init.py.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50% The comment is asking for confirmation about the removal of a test class, which is not allowed according to the rules. It is not making a specific code suggestion or pointing out a specific issue that needs to be addressed.

Workflow ID: wflow_HJZyA65KPDYxkwxo

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}

[ellipsis-dev]

Important

Looks good to me! 👍

Reviewed b7f5e89 in 41 seconds. Click for details.

• Reviewed 44 lines of code in 2 files
• Skipped 0 files when reviewing.
• Skipped posting 4 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. integrations/python/zep_autogen/pyproject.toml:3

• Draft comment:
  Version bumped to 1.1.0. Ensure that the changelog and related documentation are updated to reflect this change.
• Reason this comment was not posted:
  Confidence changes required: 0% <= threshold 50% None

2. integrations/python/zep_autogen/pyproject.toml:15

• Draft comment:
  Updated dependency: zep-cloud now requires >=3.3.0. Confirm that this update matches the API changes expected in the integration.
• Reason this comment was not posted:
  Confidence changes required: 0% <= threshold 50% None

3. integrations/python/zep_autogen/src/zep_autogen/graph_memory.py:232

• Draft comment:
  Trimming the query using 'query = query[-400:]' preserves the most recent 400 characters. Verify that truncating mid-message does not remove critical context.
• Reason this comment was not posted:
  Confidence changes required: 33% <= threshold 50% None

4. integrations/python/zep_autogen/src/zep_autogen/graph_memory.py:267

• Draft comment:
  Updated call to 'compose_context_string' now includes an empty list as the third argument. Confirm this aligns with the new API requirements.
• Reason this comment was not posted:
  Confidence changes required: 33% <= threshold 50% None

Workflow ID: wflow_abUnj5maI9BM8clW

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}