Cloud memdb #764
Merged
Cloud memdb #764
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ike pricing and features. Update CodeAssistantCaps to use this new struct for the metadata field. This change enhances metadata management and provides clearer structure and serialization.
- Introduce `load_customization_compiled_in` function to load YAML customizations. - Add logic to send and search memories using a remote server via HTTP requests. - Remove unused `reset_memory` option from command-line arguments. - Update system prompts to include workspace and extra instructions. - Revise knowledge instructions in YAML to streamline learning and recording processes. - Simplify `create_knowledge` tool parameters by removing non-essential fields. - Ensure project-specific paths are utilized during memory searches.
…d storage - Delete outdated memory test files: test07_memories.py, test13_choredb.py, test14_choredb_observe.py, and test15_memdb_subevents.py. - Remove memory-related functions from vdb_highlev.rs and vdb_structs.rs. - Introduce memories.rs to handle memory additions and searches with the new cloud-based system. - Update tools and commands (tool_create_knowledge.rs, tool_knowledge.rs, at_knowledge.rs) to utilize the new memory module. - Revise background_tasks.rs and main.rs to accommodate the migration process for existing local memories to the cloud.
JegernOUTT
force-pushed
the
cloud_mem_chores
branch
from
1aa702f to
eb45fca
Compare
…d command modules
Introduce new API route `/set_active_workspace_id` that updates the active workspace ID in the global context. Implement the handler function `handle_v1_set_active_workspace_id` for processing incoming requests and storing the workspace ID. Update the `memories.rs` file to utilize the active workspace ID for API requests, ensuring that it is set before proceeding. Remove redundant error handling in `at_knowledge.rs` for empty memory searches.
- Enhance chat prompt with core memories integration - Simplify memory migration by removing project name parameter - Update memory add function to determine project info dynamically - Modify memory search to return Vec<MemoRecord> instead of a structured result - Introduce `memories_get_core` for fetching core memories - Ensure URLs do not have credentials in git operations - Remove unused structures and imports for cleaner codebase
# Conflicts: # refact-agent/engine/src/http/routers/v1/status.rs # refact-agent/engine/src/tools/mod.rs # refact-agent/engine/src/tools/tool_relevant_files.rs # refact-agent/engine/src/tools/tools_description.rs # refact-agent/engine/src/yaml_configs/customization_compiled_in.yaml
…lite.rs` and suppress dead code warning in `chat_based_handlers.rs`
Update the memory API request URL and simplify the request body. Change the method to discover a Git repository instead of opening it directly for better flexibility in locating repository roots.
olegklimov
approved these changes
May 20, 2025
- Change `active_workspace_id` to `active_group_id` in global context and related structs. - Update HTTP routes with endpoints for group ID operations, including setting and getting active group candidates. - Adjust memory functions and remote calls to utilize the new group ID parameter, ensuring consistent functionality with cloud server interactions.
# Conflicts: # refact-agent/engine/Cargo.toml
- Introduce `CLOUD_URL` constant for consistent API endpoint base URL. - Change `iknow_id` type from `i64` to `String` for better ID handling. - Simplify URL formatting by using the new constant across API calls. - Add new JSON fields `group_id` and `knowledge_goal` in request bodies to enhance request data structure.
- Replace `iknow_type` and `iknow_origin` fields with `iknow_tags` as a vector of strings in `MemoRecord`. - Disable memory migration temporarily. - Update SQL queries to exclude `m_origin` and adapt the retrieval logic. - Remove `m_origin` parameter from `memories_add` function calls. - Adjust related function signatures and code paths to reflect these changes.
…ponents structure
…accept onUpdate callback to parse all data without batching
…tate directly in IDE with preselected group if any & tests adjusted
…stead of always defined clients
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.