-
Notifications
You must be signed in to change notification settings - Fork 19
docs: rewrite memory-lifecycle.md to reflect actual server-controlled implementation #66
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
… implementation - Remove client-controlled forgetting APIs that don't exist - Document background task system using Docket - Clarify server autonomy over memory lifecycle management - Update configuration examples to match actual implementation - Add best practices for robust client design Co-authored-by: Andrew Brookins <abrookins@users.noreply.github.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR fixes critical discrepancies between the documentation and the actual implementation by rewriting the memory lifecycle documentation to accurately reflect the server-controlled memory management system.
- Removed non-existent client-controlled forgetting APIs and replaced with server-side background process documentation
- Added comprehensive coverage of the Docket-based background task system for memory lifecycle operations
- Updated configuration examples and client usage patterns to match the actual implementation
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
docs/memory-lifecycle.md
Outdated
| for i in range(0, len(memory_ids), batch_size): | ||
| batch_ids = memory_ids[i:i + batch_size] | ||
| await client.delete_memories(batch_ids) | ||
| await client.delete_long_term_memories(batch_ids) # Correct method name |
Copilot
AI
Sep 5, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
[nitpick] The comment 'Correct method name' should be removed as it's not providing value to readers and appears to be a note from the documentation rewrite process.
docs/memory-lifecycle.md
Outdated
| memory_ids = [mem.id for mem in topic_memories.memories] | ||
| if memory_ids: | ||
| await client.delete_memories(memory_ids) | ||
| await client.delete_long_term_memories(memory_ids) # Correct method name |
Copilot
AI
Sep 5, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
[nitpick] The comment 'Correct method name' should be removed as it's not providing value to readers and appears to be a note from the documentation rewrite process.
| else: | ||
| return get_default_preference(preference_key) | ||
| # Bad: Assuming specific memories will always exist |
Copilot
AI
Sep 5, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The commented code example references get_memory_by_id() method which may not exist in the actual API. Consider using a method that's documented elsewhere in the codebase or clarify that this is a hypothetical example.
| # Bad: Assuming specific memories will always exist | |
| # Bad: Assuming specific memories will always exist | |
| # Hypothetical: get_memory_by_id() does not exist in the real API |
|
@claude Tighten the language in this PR: no need to reinforce that forgetting is “not controlled by the client.” Just talk about how it works. |
|
Claude finished @abrookins's task —— View job Tasks
Changes MadeTightened the language throughout the memory lifecycle documentation: Key improvements:
Examples of changes:
The documentation now focuses on how the system works rather than what it doesn't allow, making it more actionable and less defensive. |
- Remove unnecessary reinforcement about client control limitations
- Focus on positive descriptions of how the system works
- Clean up leftover editing comments ('Correct method name')
- Address review feedback for cleaner, more direct language
Co-authored-by: Andrew Brookins <abrookins@users.noreply.github.com>
|
@claude Fix the linting and make sure you use "pre-commit" |
|
Claude finished @abrookins's task —— View job Claude finished @abrookins's task —— View job Tasks
Changes MadeSuccessfully fixed linting issues and ensured pre-commit compliance: Linting fixes applied:
Pre-commit hooks verified:
The documentation is now properly formatted and all automated code quality checks are passing. The commit includes the fixes and has been pushed to the PR branch. |
- Remove trailing whitespace from multiple lines - Apply code formatting with ruff - Ensure all pre-commit hooks pass Co-authored-by: Andrew Brookins <abrookins@users.noreply.github.com>
This PR fixes discrepancies between the memory lifecycle documentation and the actual implementation.
Changes
Closes #65
Generated with Claude Code