search_similar
Retrieve cached solutions from cross-project memory by describing your current problem. Check if a known solution already exists before building a new one.
Instructions
Search the cross-project memory for solutions similar to the current problem.
Call this FIRST before reasoning about a problem from scratch. If similarity ≥ threshold a cached solution is returned — check edge_cases to see if any known limitations apply to the current context. If no match is found, solve normally and then call confirm_solution.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| problem | Yes | Describe the problem you are trying to solve. | |
| category | No | Problem domain. One of: ci_cd, containers, infrastructure, cloud, networking, observability, auth_security, data_pipeline, ml_training, model_serving, experiment_tracking, llm_rag, llm_api, vector_db, agents, database, api, async_concurrency, dependencies, performance, testing, architecture, other. Use 'other' when unsure. | other |
| tags | No | Optional keywords to narrow the search — library names, framework, error type, tool name. E.g. ['kubernetes','oom','python']. | |
| language | No | Programming language if relevant, e.g. 'python', 'typescript'. | |
| threshold | No | Minimum similarity (0–1). Defaults to similarity_threshold in config.toml (default 0.85). |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |