You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Memory-off /v1 turns: memory_remember's answer can echo the user's name and stored memories #547
Found while testing #479 (OpenAI-compatible API) on a real engine.
What happens. In a /v1 turn with "Let connected apps use my memories" off (openai_api.allow_memory: false), the memory read tools are gone (as designed, Agent.memory_allowed, #529), but memory_remember stays so the app can still suggest facts for review. Its answer goes back to the model, and through the model to the app, and it can carry things the turn isn't supposed to see:
The user's name.FactStore.remember runs name_the_user (Memory save stores "the user" instead of the user's name ("Priya, the user's sister, lives in Mumbai") #475) before saving, and the tool returns the rewritten text. In the real test, a helper started from a memory-off /v1 turn called memory_remember("The user works at a tech startup in Bangalore.") and got back {"action": "ADD", "content": "Maya works at a tech startup in Bangalore.", "status": "pending", ...}. The turn's prompt leaves the configured name out, so this is the only way the app learned it.
An existing memory's text._hold (sentient/memory/facts.py) answers a near-duplicate with {"action": "SKIP", "id": <existing id>, "content": <the existing fact's text>}. An app can guess a fact close to a stored one and read the stored wording back. The bar is memory.duplicate_similarity (0.98) plus same_subject, so it's a narrow oracle, but Hindi memories get merged into the wrong facts on the default local models #339 shows short facts in one script can score that close with real embedding models.
Suggested fix. When ctx.memory_allowed is false, memory_remember answers without stored content: the fact as the app gave it (not renamed), and no id or text of another fact (for example {"saved": "for review", "status": "pending"}, or {"status": "skipped"} for a duplicate). Same for helpers the turn starts (they inherit the decision). A test in tests/test_openai_api.py next to the existing memory-off tests.
Not a blocker for #479: the memory switch is off by default and the key is made by the user for apps on their own computer, but the switch should mean what it says.
Activity
hskl18 commentedon Nov 2, 2026
/assign
github-actions commentedon Nov 2, 2026
@hskl18 Assigned to you. Open a PR within a week or comment if you need more time.