Search development memory
search_dev_memorySearch agent transcripts, changesets, and shared development memory to retrieve evidence relevant to a question, enabling reuse of prior context before editing or reviewing code.
Instructions
Purpose: Search imported agent transcripts, changesets, and shared development memory for evidence relevant to a question. When to use: use this before editing, reviewing, or explaining repo behavior so the agent can reuse prior context. Inputs: query is the natural-language search text; mode selects keyword, vector, or hybrid retrieval; filters scope the search by workspace or source; rerank can improve ranking. Side effects: records an MCP audit event. Output: compact search hits with snippets, scores, sources, and evidence references. Failure modes: invalid mode raises an error; vector or hybrid search requires an embedding provider and database connectivity.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Retrieval mode: keyword for lexical search, vector for embeddings, hybrid for both. | keyword |
| limit | No | Maximum number of search results to return. | |
| query | Yes | Natural-language question or keywords to search for in shared memory. | |
| rerank | No | Reranking strategy: none, local, or api depending on configured providers. | none |
| source | No | Optional imported source filter such as codex, vscode, claude-code, or manus. | |
| workspace_uri | No | Optional workspace root URI used to restrict results to one repo. | |
| candidate_limit | No | Optional number of pre-rerank candidates to retrieve before trimming to limit. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |