Files
crewAI/lib/crewai/tests/cassettes/test_disabled_memory.yaml
João Moura 18d266c8e7
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled
New Unified Memory System (#4420)
* chore: update memory management and dependencies

- Enhance the memory system by introducing a unified memory API that consolidates short-term, long-term, entity, and external memory functionalities.
- Update the `.gitignore` to exclude new memory-related files and blog directories.
- Modify `conftest.py` to handle missing imports for vcr stubs more gracefully.
- Add new development dependencies in `pyproject.toml` for testing and memory management.
- Refactor the `Crew` class to utilize the new unified memory system, replacing deprecated memory attributes.
- Implement memory context injection in `LiteAgent` to improve memory recall during agent execution.
- Update documentation to reflect changes in memory usage and configuration.

* feat: introduce Memory TUI for enhanced memory management

- Add a new command to the CLI for launching a Textual User Interface (TUI) to browse and recall memories.
- Implement the MemoryTUI class to facilitate user interaction with memory scopes and records.
- Enhance the unified memory API by adding a method to list records within a specified scope.
- Update `pyproject.toml` to include the `textual` dependency for TUI functionality.
- Ensure proper error handling for missing dependencies when accessing the TUI.

* feat: implement consolidation flow for memory management

- Introduce the ConsolidationFlow class to handle the decision-making process for inserting, updating, or deleting memory records based on new content.
- Add new data models: ConsolidationAction and ConsolidationPlan to structure the actions taken during consolidation.
- Enhance the memory types with new fields for consolidation thresholds and limits.
- Update the unified memory API to utilize the new consolidation flow for managing memory records.
- Implement embedding functionality for new content to facilitate similarity checks.
- Refactor existing memory analysis methods to integrate with the consolidation process.
- Update translations to include prompts for consolidation actions and user interactions.

* feat: enhance Memory TUI with Rich markup and improved UI elements

- Update the MemoryTUI class to utilize Rich markup for better visual representation of memory scope information.
- Introduce a color palette for consistent branding across the TUI interface.
- Refactor the CSS styles to improve the layout and aesthetics of the memory browsing experience.
- Enhance the display of memory entries, including better formatting for records and importance ratings.
- Implement loading indicators and error messages with Rich styling for improved user feedback during recall operations.
- Update the action bindings and navigation prompts for a more intuitive user experience.

* feat: enhance Crew class memory management and configuration

- Update the Crew class to allow for more flexible memory configurations by accepting Memory, MemoryScope, or MemorySlice instances.
- Refactor memory initialization logic to support custom memory configurations while maintaining backward compatibility.
- Improve documentation for memory-related fields to clarify usage and expectations.
- Introduce a recall oversample factor to optimize memory recall processes.
- Update related memory types and configurations to ensure consistency across the memory management system.

* chore: update dependency overrides and enhance memory management

- Added an override for the 'rich' dependency to allow compatibility with 'textual' requirements.
- Updated the 'pyproject.toml' and 'uv.lock' files to reflect the new dependency specifications.
- Refactored the Crew class to simplify memory configuration handling by allowing any type for the memory attribute.
- Improved error messages in the CLI for missing 'textual' dependency to guide users on installation.
- Introduced new packages and dependencies in the project to enhance functionality and maintain compatibility.

* refactor: enhance thread safety in flow management

- Updated LockedListProxy and LockedDictProxy to subclass list and dict respectively, ensuring compatibility with libraries requiring strict type checks.
- Improved documentation to clarify the purpose of these proxies and their thread-safe operations.
- Ensured that all mutations are protected by locks while reads delegate to the underlying data structures, enhancing concurrency safety.

* chore: update dependency versions and improve Python compatibility

- Downgraded 'vcrpy' dependency to version 7.0.0 for compatibility.
- Enhanced 'uv.lock' to include more granular resolution markers for Python versions and implementations, ensuring better compatibility across different environments.
- Updated 'urllib3' and 'selenium' dependencies to specify versions based on Python implementation, improving stability and performance.
- Removed deprecated resolution markers for 'fastembed' and streamlined its dependencies for better clarity.

* fix linter

* chore: update uv.lock for improved dependency management and memory management enhancements

- Incremented revision number in uv.lock to reflect changes.
- Added a new development dependency group in uv.lock, specifying versions for tools like pytest, mypy, and pre-commit to streamline development workflows.
- Enhanced error handling in CLI memory functions to provide clearer feedback on missing dependencies.
- Refactored memory management classes to improve type hints and maintainability, ensuring better compatibility with future updates.

* fix tests

* refactor: remove obsolete RAGStorage tests and clean up error handling

- Deleted outdated tests for RAGStorage that were no longer relevant, including tests for client failures, save operation failures, and reset failures.
- Cleaned up the test suite to focus on current functionality and improve maintainability.
- Ensured that remaining tests continue to validate the expected behavior of knowledge storage components.

* fix test

* fix texts

* fix tests

* forcing new commit

* fix: add location parameter to Google Vertex embedder configuration for memory integration tests

* debugging CI

* adding debugging for CI

* refactor: remove unnecessary logging for memory checks in agent execution

- Eliminated redundant logging statements related to memory checks in the Agent and CrewAgentExecutor classes.
- Simplified the memory retrieval logic by directly checking for available memory without logging intermediate states.
- Improved code readability and maintainability by reducing clutter in the logging output.

* udpating desp

* feat: enhance thread safety in LockedListProxy and LockedDictProxy

- Added equality comparison methods (__eq__ and __ne__) to LockedListProxy and LockedDictProxy to allow for safe comparison of their contents.
- Implemented consistent locking mechanisms to prevent deadlocks during comparisons.
- Improved the overall robustness of these proxy classes in multi-threaded environments.

* feat: enhance memory functionality in Flows documentation and memory system

- Added a new section on memory usage within Flows, detailing built-in methods for storing and recalling memories.
- Included an example of a Research and Analyze Flow demonstrating the integration of memory for accumulating knowledge over time.
- Updated the Memory documentation to clarify the unified memory system and its capabilities, including adaptive-depth recall and composite scoring.
- Introduced a new configuration parameter, `recall_oversample_factor`, to improve the effectiveness of memory retrieval processes.

* update docs

* refactor: improve memory record handling and pagination in unified memory system

- Simplified the `get_record` method in the Memory class by directly accessing the storage's `get_record` method.
- Enhanced the `list_records` method to include an `offset` parameter for pagination, allowing users to skip a specified number of records.
- Updated documentation for both methods to clarify their functionality and parameters, improving overall code clarity and usability.

* test: update memory scope assertions in unified memory tests

- Modified assertions in `test_lancedb_list_scopes_get_scope_info` and `test_memory_list_scopes_info_tree` to check for the presence of the "/team" scope instead of the root scope.
- Clarified comments to indicate that `list_scopes` returns child scopes rather than the root itself, enhancing test clarity and accuracy.

* feat: integrate memory tools for agents and crews

- Added functionality to inject memory tools into agents during initialization, enhancing their ability to recall and remember information mid-task.
- Implemented a new `_add_memory_tools` method in the Crew class to facilitate the addition of memory tools when memory is available.
- Introduced `RecallMemoryTool` and `RememberTool` classes in a new `memory_tools.py` file, providing agents with active recall and memory storage capabilities.
- Updated English translations to include descriptions for the new memory tools, improving user guidance on their usage.

* refactor: streamline memory recall functionality across agents and tools

- Removed the 'depth' parameter from memory recall calls in LiteAgent and Agent classes, simplifying the recall process.
- Updated the MemoryTUI to use 'deep' depth by default for more comprehensive memory retrieval.
- Enhanced the MemoryScope and MemorySlice classes to default to 'deep' depth, improving recall accuracy.
- Introduced a new 'recall_queries' field in QueryAnalysis to optimize semantic vector searches with targeted phrases.
- Updated documentation and comments to reflect changes in memory recall behavior and parameters.

* refactor: optimize memory management in flow classes

- Enhanced memory auto-creation logic in Flow class to prevent unnecessary Memory instance creation for internal flows (RecallFlow, ConsolidationFlow) by introducing a _skip_auto_memory flag.
- Removed the deprecated time_hints field from QueryAnalysis and replaced it with a more flexible time_filter field to better handle time-based queries.
- Updated documentation and comments to reflect changes in memory handling and query analysis structure, improving clarity and usability.

* updates tests

* feat: introduce EncodingFlow for enhanced memory encoding pipeline

- Added a new EncodingFlow class to orchestrate the encoding process for memory, integrating LLM analysis and embedding.
- Updated the Memory class to utilize EncodingFlow for saving content, improving the overall memory management and conflict resolution.
- Enhanced the unified memory module to include the new EncodingFlow in its public API, facilitating better memory handling.
- Updated tests to ensure proper functionality of the new encoding flow and its integration with existing memory features.

* refactor: optimize memory tool integration and recall flow

- Streamlined the addition of memory tools in the Agent class by using list comprehension for cleaner code.
- Enhanced the RecallFlow class to build task lists more efficiently with list comprehensions, improving readability and performance.
- Updated the RecallMemoryTool to utilize list comprehensions for formatting memory results, simplifying the code structure.
- Adjusted test assertions in LiteAgent to reflect the default behavior of memory recall depth, ensuring clarity in expected outcomes.

* Potential fix for pull request finding 'Empty except'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* chore: gen missing cassette

* fix

* test: enhance memory extraction test by mocking recall to prevent LLM calls

Updated the test for memory extraction to include a mock for the recall method, ensuring that the test focuses on the save path without invoking external LLM calls. This improves test reliability and clarity.

* refactor: enhance memory handling by adding agent role parameter

Updated memory storage methods across multiple classes to include an optional `agent_role` parameter, improving the context of stored memories. Additionally, modified the initialization of several flow classes to suppress flow events, enhancing performance and reducing unnecessary event triggers.

* feat: enhance agent memory functionality with recall and save mechanisms

Implemented memory context injection during agent kickoff, allowing for memory recall before execution and passive saving of results afterward. Added new methods to handle memory saving and retrieval, including error handling for memory operations. Updated the BaseAgent class to support dynamic memory resolution and improved memory record structure with source and privacy attributes for better provenance tracking.

* test

* feat: add utility method to simplify tools field in console formatter

Introduced a new static method `_simplify_tools_field` in the console formatter to transform the 'tools' field from full tool objects to a comma-separated string of tool names. This enhancement improves the readability of tool information in the output.

* refactor: improve lazy initialization of LLM and embedder in Memory class

Refactored the Memory class to implement lazy initialization for the LLM and embedder, ensuring they are only created when first accessed. This change enhances the robustness of the Memory class by preventing initialization failures when constructed without an API key. Additionally, updated error handling to provide clearer guidance for users on resolving initialization issues.

* refactor: consolidate memory saving methods for improved efficiency

Refactored memory handling across multiple classes to replace individual memory saving calls with a batch method, `remember_many`, enhancing performance and reducing redundancy. Updated related tools and schemas to support single and multiple item memory operations, ensuring a more streamlined interface for memory interactions. Additionally, improved documentation and test coverage for the new functionality.

* feat: enhance MemoryTUI with improved layout and entry handling

Updated the MemoryTUI class to incorporate a new vertical layout, adding an OptionList for displaying entries and enhancing the detail view for selected records. Introduced methods for populating entry and recall lists, improving user interaction and data presentation. Additionally, refined CSS styles for better visual organization and focus handling.

* fix test

* feat: inject memory tools into LiteAgent for enhanced functionality

Added logic to the LiteAgent class to inject memory tools if memory is configured, ensuring that memory tools are only added if they are not already present. This change improves the agent's capability to utilize memory effectively during execution.

* feat: add synchronous execution method to ConsolidationFlow for improved integration

Introduced a new `run_sync()` method in the ConsolidationFlow class to facilitate procedural execution of the consolidation pipeline without relying on asynchronous event loops. Updated the EncodingFlow class to utilize this method for conflict resolution, ensuring compatibility within its async context. This change enhances the flow's ability to manage memory records effectively during nested executions.

* refactor: update ConsolidationFlow and EncodingFlow for improved async handling

Removed the synchronous `run_sync()` method from ConsolidationFlow and refactored the consolidate method in EncodingFlow to be asynchronous. This change allows for direct awaiting of the ConsolidationFlow's kickoff method, enhancing compatibility within the async event loop and preventing nested asyncio.run() issues. Additionally, updated the execution plan to listen for multiple paths, streamlining the consolidation process.

* fix: update flow documentation and remove unused ConsolidationFlow

Corrected the comment in Flow class regarding internal flows, replacing "ConsolidationFlow" with "EncodingFlow". Removed the ConsolidationFlow class as it is no longer needed, streamlining the memory handling process. Updated related imports and ensured that the memory module reflects these changes, enhancing clarity and maintainability.

* feat: enhance memory handling with background saving and query analysis optimization

Implemented a background saving mechanism in the Memory class to allow non-blocking memory operations, improving performance during high-load scenarios. Added a query analysis threshold to skip LLM calls for short queries, optimizing recall efficiency. Updated related methods and documentation to reflect these changes, ensuring a more responsive and efficient memory management system.

* fix test

* fix test

* fix: handle synchronous fallback for save operations in Memory class

Updated the Memory class to implement a synchronous fallback mechanism for save operations when the background thread pool is shut down. This change ensures that late save requests still succeed, improving reliability in memory management during shutdown scenarios.

* feat: implement HITL learning features in human feedback decorator

Added support for learning from human feedback in the human feedback decorator. Introduced parameters to enable lesson distillation and pre-review of outputs based on past feedback. Updated related tests to ensure proper functionality of the learning mechanism, including memory interactions and default LLM usage.

---------

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-02-13 21:34:37 -03:00

193 lines
8.8 KiB
YAML

interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1541'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 24 Sep 2024 21:45:11 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert in research and you love to learn new things.\nYour personal goal
is: You research about math.\nTo give my best complete final answer to the task
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!"}, {"role": "user", "content": "\nCurrent Task: Research a topic to teach
a kid aged 6 about math.\n\nThis is the expect criteria for your final answer:
A topic, explanation, angle, and examples.\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '902'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-AB7dDZV5HxzvFLtaeW3yh3f43Bx3k\",\n \"object\"\
: \"chat.completion\",\n \"created\": 1727214307,\n \"model\": \"gpt-4o-2024-05-13\"\
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \
\ \"role\": \"assistant\",\n \"content\": \"Thought: I now can\
\ give a great answer\\nFinal Answer: \\n### Topic: Basic Addition\\n\\n###\
\ Explanation:\\nAddition is one of the most fundamental concepts in math.\
\ It involves combining two or more numbers to find their total. Think of\
\ addition as putting things together. When we add, we are simply counting\
\ how many items we have in total.\\n\\n### Angle:\\nTo make it easy and fun\
\ for a 6-year-old, let's use everyday objects and relatable scenarios. Using\
\ toys, fruits, or even fingers can help them visualize and understand the\
\ concept better. We'll also use simple and engaging language.\\n\\n### Examples:\\\
n\\n1. **Using Toys**:\\n - Imagine you have 2 toy cars and your friend\
\ gives you 3 more toy cars. How many toy cars do you have now? \\n - **Calculation**:\
\ 2 + 3 = 5\\n - **Explanation**: You can count the toy cars one by one.\
\ First, there are 2 cars, then you add 3 more. So, 1, 2, 3, 4, 5. You have\
\ 5 toy cars in total.\\n\\n2. **Using Fingers**:\\n - Hold up 3 fingers\
\ on one hand and 2 fingers on the other. Now, count all the fingers you are\
\ holding up.\\n - **Calculation**: 3 + 2 = 5\\n - **Explanation**: Start\
\ counting from 1 to 3 on one hand, then continue from 4 to 5 on the other\
\ hand. How many fingers did you count? Five!\\n\\n3. **Using Fruits**:\\\
n - Imagine you have 1 apple and you buy 4 more apples. How many apples\
\ do you have now? \\n - **Calculation**: 1 + 4 = 5\\n - **Explanation**:\
\ Picture having 1 apple first. Then, you add 4 more apples to your first\
\ apple. Counting them all together gives you 5 apples.\\n\\n4. **Story Time**:\
\ \\n - **Scenario**: There were 2 birds sitting on a tree. Then, 3 more\
\ birds came and joined them. How many birds are there on the tree now?\\\
n - **Calculation**: 2 + 3 = 5\\n - **Explanation**: First, count the\
\ original 2 birds, then add the 3 new birds. In total, 1, 2, 3, 4, 5. Five\
\ birds are now sitting on the tree.\\n\\nBy using these examples and making\
\ the learning fun and interactive, a child can easily grasp the concept of\
\ basic addition through visualization and practical experience.\",\n \
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\"\
: \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 181,\n \
\ \"completion_tokens\": 544,\n \"total_tokens\": 725,\n \"completion_tokens_details\"\
: {\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\"\
: \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f5a988a51cf3-GRU
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:45:15 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '8050'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999785'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d45d03d42785ee4b16aca0e37911929d
status:
code: 200
message: OK
version: 1