memory_recall
Read-onlyIdempotent
Recall stored memories by matching a natural-language cue. Retrieves relevant hits and anti-hits with validity dates for context-aware memory access.
Instructions
Recall verbatim memories by cue. Returns hits + anti_hits with derived valid_from/valid_to. Read-only.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cue | Yes | Natural-language query to match against stored memories. Embedded server-side via bge-small-en-v1.5 (384d) unless `cue_embedding` is supplied. | |
| budget_tokens | No | Soft token budget for the response (default 1500). Hits are appended until the next would exceed this budget; at least one hit is always returned. | |
| session_id | No | Current session id; gets written into every recalled record's provenance. Omit to use '-'. | |
| cue_embedding | No | Optional pre-computed embedding vector for the cue (EMBED_DIM=384 floats; bge-small-en-v1.5). When omitted, the daemon embeds the cue server-side. Used by memory_contradict and tests that need byte-stable embeddings. | |
| language | No | Optional ISO-639-1 language hint for the sleep-suggestion path (8 supported: en/ru/ja/ar/de/fr/es/zh). Defaults to 'en' when omitted. Hot-path retrieval is language-agnostic; this key only affects the sleep-suggestion regex pre-screen. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| hits | No | ||
| anti_hits | No | ||
| activation_trace | No | ||
| budget_used | No | ||
| hints | No | ||
| cue_mode | No | ||
| patterns_observed | No |