> ## Documentation Index
> Fetch the complete documentation index at: https://docs.compose.market/llms.txt
> Use this file to discover all available pages before exploring further.

# Layers

> Reference for working, scene, graph, patterns, archives, and vectors.

Layer search lives in `runtime/src/manowar/memory/layers.ts`. Each layer has its own source and filter shape. `searchMemoryLayers()` runs selected layers concurrently and returns raw hits plus per-layer totals.

## Layer reference

| Layer      | Source                              | Query behavior                                                                      | Scope                     |
| ---------- | ----------------------------------- | ----------------------------------------------------------------------------------- | ------------------------- |
| `working`  | `sessions.workingMemory.context`    | Substring match over recent working context, newest first.                          | Thread-scoped.            |
| `scene`    | `session_transcripts`               | Substring match over transcript messages or summary, newest first.                  | Thread-scoped.            |
| `graph`    | `memory` rows with `source: "fact"` | Vector search over durable facts, then decay, rerank, and MMR.                      | Durable agent/user scope. |
| `patterns` | `patterns`                          | Substring match over pattern summary or trigger, sorted by success rate.            | Durable agent/user scope. |
| `archives` | `archives`                          | Substring match over summary or content, newest first.                              | Durable agent/user scope. |
| `vectors`  | `memory` rows                       | Atlas vector search over semantic rows, then ranking unless graph is also selected. | Durable agent/user scope. |

If `layers` is omitted, Manowar searches all six layers.

## Working

`working` is the hot session buffer. `rememberSessionMessages()` appends user and assistant messages to `workingMemory.context`, ignores system and tool messages, and keeps only the last `MEMORY_SESSION_CONTEXT_LIMIT` entries. The default limit is `12`.

The session row also stores `entities`, `state`, metadata, `lastAccessedAt`, and an `expiresAt` date. MongoDB deletes expired rows through the `idx_session_ttl` index.

## Scene

`scene` is the transcript layer. `storeTranscript()` upserts a `session_transcripts` row by `sessionId`, including messages, summary, token count, model metadata, and scope fields.

Scene retrieval does not embed the whole transcript on every read. It searches recent scoped transcript rows and keeps rows whose message text or summary contains the query.

## Graph

`graph` stores durable facts. Facts land in the same `memory` collection as vectors, with:

```json theme={null}
{
  "source": "fact",
  "metadata": {
    "layer": "graph",
    "factType": "preference",
    "confidence": 0.92
  }
}
```

Fact extraction is asynchronous on `post_turn`. Explicit saves through `remember` bypass extraction and index the supplied fact directly.

Allowed fact types are:

| Type           | Use                                    |
| -------------- | -------------------------------------- |
| `preference`   | Stable user preferences.               |
| `identity`     | Durable identity facts about the user. |
| `context`      | Durable situational context.           |
| `skill`        | User or agent skill facts.             |
| `relationship` | Stable relationship facts.             |
| `event`        | Dated or durable events.               |

Unknown explicit fact types default to `context`.

## Patterns

`patterns` stores procedural memory extracted from transcripts. `extractExecutionPatterns()` looks for repeated tool-call sequences, counts occurrences, assigns confidence from frequency, and stores `tool_sequence` patterns when they pass the configured threshold.

Pattern validation requires:

| Condition       | Threshold |
| --------------- | --------- |
| Execution count | `>= 2`    |
| Success rate    | `>= 0.55` |
| Confidence      | `>= 0.2`  |

Validated patterns can become learned skills through `promotePatternToSkill()`.

## Archives

`archives` is cold memory. `createMemoryArchive()` collects vector rows for an agent and date range, serializes them into JSON, compresses the payload by default, and stores it in `archives`.

`syncArchiveToPinata()` can pin an archive payload to IPFS through Pinata and store the returned CID as `ipfsCid`.

## Vectors

`vectors` is the general semantic layer. It covers session summaries, knowledge rows, pattern rows, archive rows, and fact rows. Retrieval embeds the query with `input_type: "query"` and searches Atlas `$vectorSearch`.

When both `graph` and `vectors` are requested, the vector layer disables local ranking options for `vectors`. The graph layer already calls the ranked vector pipeline for facts, so the combined result avoids double-ranking the same candidate family.

## Filters

Memory filters are intentionally allowlisted. The runtime accepts primitive values or arrays of primitive values for:

| Input path                                                                                  | Stored path       |
| ------------------------------------------------------------------------------------------- | ----------------- |
| `appId`, `app_id`                                                                           | `metadata.app_id` |
| `hai_id`                                                                                    | `haiId`           |
| `user_id`                                                                                   | `userAddress`     |
| `thread_id`                                                                                 | `threadId`        |
| `agentWallet`, `userAddress`, `threadId`, `mode`, `haiId`, `scopeKind`, `scopeId`, `source` | Same path.        |
| `metadata.*`                                                                                | Same path.        |
| `workingMemory.state.*`                                                                     | Same path.        |
| `workingMemory.entities.*`                                                                  | Same path.        |

Other paths are ignored. Retrieval filters stay predictable, and callers cannot turn arbitrary document fields into query controls.

## Related

* [Retrieval and ranking](/manowar/memory/retrieval-ranking)
* [Memory flows](/manowar/memory/flows)
* [Operations](/manowar/memory/operations)