# Memory correction

Correct a durable record through the versioned update path while preserving provenance and conflict signals.

- Canonical: https://docs.xmemo.dev/docs/concepts/memory-correction
- Locale: en-US
- Content-Locale: en-US
- Canonical-Content-Digest: 6f28d589cdd0ab6ac0d2145e0524ea5b88d6e3e81e8f0e634cd93aecc0865ef3
- Edition-Digest: 122580e9deaca1c80d6500106b573084e1ff184f8db7c849f294bfadf53e66e9
- Source-Revision: sha256:f7210d05c9e1bbd70c314abb60b434144f4220e0b1df97fb63073b6da3fd6873

## Correct the record, do not append a contradiction

A correction changes the existing memory through PATCH /v1/memories/{memory_id}. MemoryUpdateRequest makes every field optional and includes content, path, metadata, source, provenance, memory_type, status, expires_at, scope, and team_id. This keeps the correction attached to the same memory reference and lets the server apply its versioning path.

```http
PATCH /v1/memories/<memory-id>
X-API-Key: <your-assigned-api-key>
Content-Type: application/json

{
  "content": "The corrected deployment decision was verified on 2026-09-02.",
  "provenance": {
    "correction": "owner-confirmed"
  },
  "merge_provenance": true,
  "detect_conflicts": true
}
```

## Version and conflict controls are part of the request

The update contract includes merge_metadata, merge_provenance, and detect_conflicts, all defaulting to true, plus supersession_reason. The persistence path increments the memory version and keeps status/superseded_by/conflict evidence in the public memory contract; read the returned implementation data as the current result, while the OpenAPI response remains untyped.

- Merge metadata and provenance when the correction should retain existing evidence.
- Keep detect_conflicts enabled when concurrent edits or competing versions matter.
- Use supersession_reason when the correction intentionally supersedes an earlier version.

## Verify the corrected scope

After a correction, perform a scoped read and inspect the returned version, status, provenance, and conflict fields. Retrieval still follows the authenticated scope and memory status filters; a successful PATCH alone is not a proof that the intended scoped result is now visible.

```http
GET /v1/memories/search?query=corrected%20deployment%20decision&scope=memory-os&status=active&limit=5
X-API-Key: <your-assigned-api-key>
```

## ChatGPT user

Give ChatGPT durable access to your XMemo preferences, project facts, decisions, and TODOs without pasting bearer tokens into a chat.

Connect the hosted XMemo MCP server through the ChatGPT/OpenAI app OAuth flow, then approve the memory:read and memory:write grant for your XMemo account.

Save a synthetic preference or project note, start a new chat, then ask ChatGPT to recall it through XMemo before continuing work.

If OAuth fails or tools do not appear, sign out of the MCP server in the host app, reconnect the XMemo server URL, and retry before creating direct tokens.

## Copilot / Codex developer

Carry repo decisions, coding conventions, bug-fix notes, and task history between IDE and CLI agents.

Use OAuth for VS Code / GitHub Copilot and Gemini CLI when available. For Copilot CLI, Codex, Cursor, or other direct MCP clients, keep XMEMO_KEY in the local environment or secret store and set a stable XMEMO_AGENT_INSTANCE_ID.

Record a codebase decision or bug fix, then ask the next IDE or CLI agent to recall the relevant XMemo context before editing.

If recalls are empty, verify the selected MCP config path, the XMEMO_KEY environment variable for direct clients, and any stale OAuth credential in the host app.

## Team / enterprise pilot owner

Evaluate shared memory with account controls, source attribution, export/delete workflows, and reviewer-safe setup evidence.

Create or enter the protected XMemo workspace, invite approved users, then connect each client through OAuth or a scoped direct credential according to the readiness badges.

Have a pilot member save a synthetic team memory, confirm source attribution in XMemo, then review delete/export and support paths.

If a member cannot connect, check role permissions, OAuth approval, client readiness status, and support guidance before issuing a new token.

## Autonomous agent operator

Let headless or scheduled agents record progress, retrieve prior decisions, and keep a stable non-secret instance identity.

Fetch /api/v1/mcp/config/autonomous-agent. Prefer auth_modes.oauth when the runner supports OAuth + custom headers; use auth_modes.xmemo_key with XMEMO_KEY from a secret store only for fully headless runners.

Run one synthetic task that writes progress to XMemo, restart the runner, and confirm it recalls that progress using the same XMEMO_AGENT_INSTANCE_ID.

If attribution changes or recalls split across instances, persist XMEMO_AGENT_INSTANCE_ID outside git and verify the runner is not regenerating it on every start.