Oracle chat

1. Your birth details load your saju profile from the engine: pillars, traits, and timing readings.
2. When you ask about your chart, Oracle has to fetch the answer. That may be your birth reading, your glyph, a day, a month, a year, a decade, a friend pairing, or a public figure pairing. Each one is a separate request to the engine. The engine is the only place those numbers exist.
3. Your glyph card is the one part we can promise outright. The app adds it to the answer afterwards, so the portrait, number, and archetype are read from your chart, not written by the AI.
4. Personal memory (when signed in) carries preferences you have mentioned across chats. It shapes the wording. It is never a source of chart facts.
5. Your likes and dislikes on Daily luck, and your votes on the timeline, can steer the tone. Again, that changes only the wording, not the substance.

Everything above is how the app is built, not a promise we can check sentence by sentence. Oracle is asked to answer only from what the engine returned, and it is given no other way to reach your chart. But no automatic check reads a finished answer back and confirms every number in it. If something Oracle says does not match what you see on the Chart screen, the Chart screen is the one to trust.

Asking your own questions is part of Plus. Without it, the Oracle screen still opens and still reads your chart. But you pick from a fixed set of questions instead of writing your own, and nothing is saved between visits.

Chat asks your permission before the first question. To write the answer, it has to send your question and the engine's findings to Google. If you decline, every other part of the app works exactly as before: the fixed-question screen sends nothing.

Plus comes with a monthly question allowance. Once you are down to ten, the message box starts telling you how many are left, so the limit is never a surprise. The count resets on your own subscription date: subscribe on the 20th and the questions come back on the 20th, not the 1st. The allowance is monthly rather than daily on purpose. People often ask four questions in one sitting and none for a week, and a daily cap punished exactly that.

Your chats are saved to your account and listed in the left drawer. Each chat is separate. You can delete the one you have open from the Oracle screen, or all of them at once from the account sheet at the foot of the drawer. Clearing chats does not clear what the Oracle remembers about you. That is a second control in the same sheet, Clear Oracle memory. It empties the summary on your account and on this device, and leaves your saved chats alone. The Profile screen has the same control. Neither one touches your resonance feedback. Clearing the memory also does not stop the Oracle building a new summary from your next conversation.

Oracle can read a pairing two ways, and they differ on consent. Friends are people who accepted your invite or whose invite you accepted, so the pairing rests on something they did. Public figures are read from our own catalog of well-known people. They have not agreed to anything, just as when you compare yourself with a celebrity on the Match screen. Oracle cannot reach anyone else. It has no way to read a person you have only described to it, and it does not guess a chart from a name.