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

# Get Memory Conflict

> Retrieve full details of a single memory conflict

```
GET /openapi/memorylake/api/v2/projects/{id}/memories/conflicts/{conflictId}
```

Returns the full record for one conflict. You always get the memory snapshots captured at detection time. For memory-vs-document (`m2d`) conflicts, you also get the document excerpts that contradict the memory — excerpts whose source document has since been removed from the project are dropped.

<Note>
  **Permission required:** [`project:mem_read`](/features/team-collaboration/permission-reference#read-a-fact’s-content) · `instance`
</Note>

### Path Parameters

<ParamField path="id" type="string" required>
  Project ID
</ParamField>

<ParamField path="conflictId" type="string" required>
  Conflict ID
</ParamField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X GET 'https://app.memorylake.ai/openapi/memorylake/api/v2/projects/proj-a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6/memories/conflicts/conf-abc123' \
    -H 'Authorization: Bearer sk_xxxxxx'
  ```
</RequestExample>

### Response

<ResponseField name="data" type="object">
  <Expandable title="Conflict">
    <ResponseField name="id" type="string">Conflict ID</ResponseField>
    <ResponseField name="name" type="string">Short title</ResponseField>
    <ResponseField name="description" type="string">Longer explanation of the contradiction</ResponseField>
    <ResponseField name="category" type="string">`m2m` (memory vs memory) or `m2d` (memory vs document)</ResponseField>

    <ResponseField name="conflict_type" type="string">
      What kind of inconsistency:

      * `logical` — contradiction or tension between statements.
      * `knowledge` — disagreement about facts or what was cited.
    </ResponseField>

    <ResponseField name="resolved" type="boolean">Whether the conflict has been resolved</ResponseField>

    <ResponseField name="resolve" type="object">
      Resolution record — present only when `resolved` is `true`.

      <Expandable title="Resolution">
        <ResponseField name="id" type="string">Resolution record ID</ResponseField>
        <ResponseField name="strategy" type="string">Strategy applied: `keep_memory`, `trust_memory`, `trust_document`, or `dismiss`</ResponseField>
        <ResponseField name="keep_memory_id" type="string">Memory kept when the strategy required a choice</ResponseField>
        <ResponseField name="forgotten_memory_ids" type="array">Memories forgotten as part of resolution</ResponseField>
        <ResponseField name="resolved_by" type="string">Actor that resolved the conflict</ResponseField>
        <ResponseField name="created_at" type="string">When the conflict was resolved</ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="stale" type="boolean">Whether underlying content has changed since detection</ResponseField>
    <ResponseField name="memory_ids" type="array">Memories involved in the conflict</ResponseField>

    <ResponseField name="memory_snapshots" type="array">
      Snapshots of each memory's text at the moment the conflict was detected

      <Expandable title="Memory snapshot">
        <ResponseField name="memory_id" type="string">Memory identifier</ResponseField>
        <ResponseField name="memory_history_id" type="string">History revision ID, if any</ResponseField>
        <ResponseField name="memory_text" type="string">Memory text at detection time</ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="file_chunks" type="array">
      Document excerpts — non-empty when `category` is `m2d`

      <Expandable title="File chunk">
        <ResponseField name="document_id" type="string">ID of the project document</ResponseField>
        <ResponseField name="document_name" type="string">Display name of the document</ResponseField>

        <ResponseField name="chunk" type="object">
          Matched text span from the document

          <Expandable title="Chunk">
            <ResponseField name="type" type="string">`text`</ResponseField>
            <ResponseField name="text" type="string">Plain text content</ResponseField>
            <ResponseField name="range" type="string">Optional location hint (e.g. page or cell range)</ResponseField>
          </Expandable>
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="event_id" type="string">ID of the event that triggered detection</ResponseField>
    <ResponseField name="created_at" type="string">First detected at</ResponseField>
    <ResponseField name="updated_at" type="string">Last updated at</ResponseField>
  </Expandable>
</ResponseField>

<ResponseExample>
  ```json Success (200) theme={null}
  {
    "success": true,
    "data": {
      "id": "conf-abc123",
      "name": "Contradicting restaurant preferences",
      "description": "An earlier memory says the user prefers spicy food; a later one says they avoid it.",
      "category": "m2m",
      "conflict_type": "logical",
      "resolved": false,
      "stale": false,
      "memory_ids": ["mem-001", "mem-002"],
      "memory_snapshots": [
        {
          "memory_id": "mem-001",
          "memory_text": "User prefers spicy food"
        },
        {
          "memory_id": "mem-002",
          "memory_text": "User avoids spicy food"
        }
      ],
      "file_chunks": [],
      "event_id": "evt-xyz",
      "created_at": "2024-01-15T10:30:00Z",
      "updated_at": "2024-01-15T10:30:00Z"
    }
  }
  ```
</ResponseExample>

<Tip>
  Once you have the conflict detail, apply a decision with [Resolve Memory Conflict](/features/memorylake/api-reference/memories/resolve-memory-conflict). The returned `forgotten_memory_ids` tells you which memories were removed so your UI can stay in sync.
</Tip>