search_shared_memory
Retrieve relevant shared discoveries from agent memory using full-text, semantic, or hybrid queries. Filter by tags, agent, and scope to find prior decisions, fixes, or insights before acting.
Instructions
Primary workflow name for memory search; implemented by knowledge(action='search').
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Tags (action=store, note); for action=search an exact any-of filter in every search mode. | |
| limit | No | Max results (for action=search: min 1, values above 100 are capped, 0 or negative is rejected) | |
| query | No | Search query (for action=search) | |
| scope | No | KG audit scope for action=audit | |
| top_n | No | Maximum stale entries returned by action=audit | |
| topic | No | Synthesize just this one tag/topic (for action=synthesize). Omit to sweep the densest topics. | |
| length | No | Maximum details characters returned for action=details | |
| offset | No | Character offset for action=details pagination | |
| status | No | Status filter/update value (open, resolved, archived, superseded) | |
| dry_run | No | Dry run mode (for action=cleanup, synthesize) | |
| use_llm | No | Use the local LLM for the rollup narrative (for action=synthesize, default true; falls back to deterministic when unreachable) | |
| agent_id | No | Filter by agent (for action=get, search; omit when using discovery_id readback) | |
| operator | No | Boolean operator for multi-term FTS queries | |
| semantic | No | Legacy action=search toggle to force or skip semantic retrieval when supported | |
| severity | No | Severity: low, medium, high, critical (for action=store or action=update) | |
| use_model | No | Use the local model to assess stale entries for action=audit | |
| confidence | No | Writer-supplied confidence for action=store, validated to 0-1; not independently verified or adjusted by governance metrics | |
| epoch_scope | No | Stats/list scope: current epoch only or all epochs | |
| min_members | No | Minimum discoveries a topic needs before it is rolled up (for action=synthesize, default 3) | |
| search_mode | No | Force retrieval mode for action=search. 'semantic' and 'hybrid' fail honestly when unsupported by the active backend. | |
| include_cold | No | Include cold-storage (long-term) discoveries in search results (default: excluded) | |
| closure_class | No | Closing standard for action=update: fix_verified | unobserved | not_reproducible | obsolete | duplicate. 'fix_verified' needs a deployed change whose effect was observed. | |
| response_mode | No | Read-envelope mode. Default lean: one-line digests; compact adds diagnostics, full adds raw_governance. | lean |
| discovery_type | No | action=store; one of architectural_decision, learning, pattern, bug_fix, refactoring, documentation, experiment, question, note, rule, insight, bug_found, bug, improvement, exploration, observation. | |
| including_cold | No | Include cold-storage discoveries in action=list raw status aggregates | |
| memory_context | No | S22 provenance: memory/KG/transcript surfaces visible to the writer | |
| min_similarity | No | Minimum cosine similarity for semantic retrieval modes | |
| include_details | No | Expand results inline only with response_mode='full'; otherwise open one with knowledge(action='details'). | |
| max_chain_depth | No | Maximum response-chain traversal depth for action=details | |
| closure_evidence | No | Evidence for closure_class. Required keys: fix_verified needs {deployed, observed}; unobserved needs {window, instrument_check}. | |
| continuity_token | No | Ownership proof from onboard()/identity(), for same-live-process rebinds only. Not a cross-process resume credential. | |
| include_archived | No | Include archived discoveries in search results (default: excluded) | |
| client_session_id | No | In-session binding id from start_session()/identity(); pass it on same-process calls. Not a cross-process proof. | |
| include_provenance | No | Include provenance and lineage chain fields in search/details results | |
| exclude_agent_labels | No | Omit search results whose writer display label matches one of these values | |
| include_response_chain | No | Include typed response chain for action=details |