💭 feat: Require Explicit Auto-agent Enablement for Memories

[danny-avila]

Summary

• keep memory/manual personalization enabled without requiring a memory agent
• add explicit memory.agent.enabled: true opt-in for automatic memory-agent updates
• keep memory context primary-only by default; automatic opt-in preserves parallel-agent fan-out
• consolidate memory config helpers through @librechat/data-schemas and warn on old agent config without explicit enablement

Tests

• npm run build -w @librechat/data-schemas
• npm run build -w @librechat/api
• cd packages/api && npx jest src/memory/config.spec.ts src/app/permissions.spec.ts --runInBand
• cd api && npx jest server/controllers/agents/client.test.js --runInBand

[Copilot]

Pull request overview

Adjusts the memory feature so manual memories/personalization can remain enabled without implicitly enabling the legacy “automatic memory-agent” pipeline, requiring an explicit opt-in flag to run the memory agent and to fan memory context out to parallel agents.

Changes:

• Changes “memory enabled” semantics to only depend on memory.disabled, and adds isMemoryAgentEnabled() gated by memory.agent.enabled === true.
• Updates agent run context so memory context is primary-only by default; legacy opt-in restores parallel-agent memory fan-out.
• Updates schema, tests, and example YAML to document/verify the explicit enablement behavior.

Reviewed changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
packages/data-schemas/src/app/memory.ts	Updates enablement logic and introduces isMemoryAgentEnabled() for explicit auto-agent opt-in.
packages/data-schemas/src/app/interface.ts	Aligns UI-disable comment/logic with “explicitly disabled only” semantics.
packages/data-provider/src/config.ts	Extends memory.agent schema to accept optional enabled.
packages/api/src/memory/config.ts	Mirrors data-schemas memory enablement changes and adds isMemoryAgentEnabled().
packages/api/src/memory/config.spec.ts	Adds tests covering manual-memory enabled vs. auto-agent explicit opt-in behavior.
packages/api/src/app/permissions.ts	Updates wording to reflect “configured” vs. “valid agent” semantics.
packages/api/src/app/permissions.spec.ts	Updates expectations to match new “no agent required” memory config behavior.
librechat.example.yaml	Documents that auto memory-agent flow requires memory.agent.enabled: true.
api/server/controllers/agents/client.test.js	Updates/extends tests for primary-only memory context by default and legacy opt-in fan-out; adds getFormattedMemories mocking.
api/server/controllers/agents/client.js	Gates memory processing on isMemoryAgentEnabled; loads existing memories without auto-processing when not enabled; keeps memory context primary-only unless legacy opt-in.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

GitNexus: 🚀 deployed

The LibreChat-pr-12886 index is now live on the MCP server.
Deploy run

[danny-avila]

@codex review

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. Nice work!

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[github-actions]

GitNexus: 🚀 deployed

The LibreChat-pr-12886 index is now live on the MCP server.
Deploy run

[github-actions]

GitNexus: 🚀 deployed

The LibreChat-pr-12886 index is now live on the MCP server.
Deploy run