Add a knowledge base entry

Search knowledge base. Lexical FTS5 (or LIKE fallback) by default; set semantic=true / hybrid=true / search_mode=hybrid to use vector embeddings + RRF fusion (requires LORE_SEMANTIC_SEARCH=true).

Get full KB entry by ID

Fetch full content for multiple KB entries by ID. Use after kb_search to retrieve content without N+1 round trips.

List KB entries

Update existing KB entry content, title, topic, tags, verified state, and trust_score

Delete existing KB entry from database

Add an investigation entry (open or append to an ops investigation)

List investigations

Get a single investigation entry by ID

Log a structured experiment within an investigation (hypothesis, methodology, results, conclusion)

List logged investigation experiments

Hard-delete an investigation note by note_id (Issue #21). Requires confirm=True; in LORE_ENV=production also requires confirm_production=True.

Hard-delete an investigation experiment by experiment_id (Issue #21). Requires confirm=True; in LORE_ENV=production also requires confirm_production=True.

Append journal entry

List journal entries

Get journal entry

Full-text search across journal entry content (Issue #15)

Hard-delete a journal entry by entry_id (Issue #21). Requires confirm=True; in LORE_ENV=production also requires confirm_production=True.

Snapshot current config

Ingest single markdown file into KB with change detection

Batch ingest directory of markdown files

Check sync state between source docs and KB

Embed any KB entries that are missing or stale (model/content changed). Idempotent: skips entries whose stored content_hash still matches. Requires LORE_SEMANTIC_SEARCH=true.

Report embedding coverage: total entries, embedded count, missing count, current model, and per-model breakdown.

Scan all MCP servers and index their tools. By default, scans only configured servers (66% token savings).

Search for MCP tools by description/capability

Get all tools for a specific MCP server

Get detailed information about a specific tool

Force rebuild of entire MCP index (same as mcp_index_scan)

Search local files by content (lexical mode)

Search across corpus manifests (JSONL files)

Search transcript segments from Whisper outputs

Search across all configured sources simultaneously (KB, local files, transcripts, corpora) with a single query. Returns combined results from all available sources. For searching within a specific source only, use kb_search, search_local, search_transcripts, or search_corpora instead.

Remove duplicate search results based on text similarity

Groups search results by source_type (file extension, corpus, transcript). The cluster count is determined by the data, not by a parameter — Issue #22 removed the previously-misleading num_clusters/n_clusters knobs.

Score or annotate a prior kb_search result by its query_id (retrieval telemetry, issue #5). Supply user_feedback_score, required_requery, notes, or any combination; an omitted field is left unchanged (cannot be reset to null). No effect unless LORE_HARD_NEGATIVE_MINING=true on a PostgreSQL backend.

Read retrieval telemetry rows (issue #5). Selector precedence: query_id > session_id > topic > recent. Returns newest-first.

Aggregate retrieval telemetry stats (issue #5): totals, feedback coverage, requery count, average score, oldest/newest timestamps. Optionally scoped by session_id and/or topic.

Scan retrieval_telemetry for low-scored and requery signals, then upsert hard negative pairs into knowledge.hard_negative_pairs. Use since= for incremental refresh. dry_run=true returns counts without writing. Requires LORE_HARD_NEGATIVE_MINING=true.

Read hard negative (query, document) pairs from knowledge.hard_negative_pairs. Filter by signal_type (explicit/behavioral/all), doc_id, or query_text_like. Returns pairs sorted by occurrence_count DESC.

Backfill query_embedding column in retrieval_telemetry for rows that predate Phase 4a. Processes rows in batches. Set build_index=true to also create the HNSW index after backfill.