Settings · AI behavior
Context memory
Control which conversation messages AI models receive in the Playground and explore context and token usage.
Updated October 19, 2026
Context Memory lets you control which parts of a chat's context the EidoStack AI Playground sends with your next prompt. The choice affects continuity, token usage, and the available context window. Use it to maintain an ongoing conversation, reduce unnecessary history, or explore how a model responds with different amounts of context.
Choose a context strategy
EidoStack provides five strategies in Settings > Context Memory and in the Context Memory control of each chat.
| Strategy | Request behavior | Best starting point |
|---|---|---|
| None | Sends only the current prompt, without a system prompt, history, or retrieved messages. | Isolated prompts where you want no chat context. |
| System Prompt Only | Sends the configured system prompt, if any, and the current prompt. Omits history and memory. | Tasks that need fixed instructions without earlier conversation turns. |
| Full History | Sends the conversation history with the new prompt. | Tasks where all prior turns are relevant and the context remains manageable. |
| Recent Messages | Sends a selected window of messages from the start or end of the chat. | Ongoing tasks where recency matters more than the entire record. |
| Semantic Memory | Retrieves saved messages related to the current prompt. | Long chats where only relevant earlier details should be recalled. |
A context strategy changes which chat context is included in the next model request; it does not delete messages from your saved chat. Two requests can therefore produce different responses even when the visible conversation is unchanged.
Set defaults for new chats
- Open workspace settings and select Context Memory.
- Select None, System Prompt Only, Full History, Recent Messages, or Semantic Memory.
- Adjust the controls revealed for the selected strategy.
- Create a new chat to use those values as its starting point.
The settings page defines defaults for future chats. Each existing chat has its own Context Memory button in the prompt toolbar, where changes are saved to that chat without rewriting the workspace default.
Tune Recent Messages
Select Recent Messages to reveal Message Limit and Selection Direction.
- Message Limit sets the number of messages to include. The control supports 1 to 1,000 messages and defaults to 20.
- First starts collecting from the oldest messages in the chat.
- Last starts collecting from the most recent messages, which is the default and is usually the practical choice for an active conversation.
Use a smaller window to reduce input tokens and keep attention on the recent task. Use a larger window only when the earlier turns genuinely affect the answer. A window is measured in messages, not in tokens, so a few long messages can still consume substantial context capacity.
Tune Semantic Memory
Select Semantic Memory to reveal Search Precision. Its value runs from 0.00 to 1.00:
- A lower value permits broader associations and is useful when relevant information may be phrased differently.
- A higher value requires stricter matches and reduces the chance that loosely related history is included.
Semantic Memory retrieves related saved messages from the current chat using the new prompt. It cannot guarantee that every important detail will be retrieved, so compare the model's answers with other strategies when the missing context would matter for your task.
Watch context capacity and cost
The chat’s context control shows an estimated capacity meter for the selected model. The usage button also shows the model’s context-window capacity and input tokens from the last API response. Green, amber, and red states indicate increasing use of that capacity.
Treat the meter as a guide to context capacity, not a measure of response quality. A short history can omit important details even when plenty of tokens remain. Try the same prompt under different context strategies in the Playground to see how the answer and token usage change.
Use System prompts to configure instructions sent alongside the chosen context. None omits configured system prompts as well as conversation history, while System Prompt Only sends those instructions without conversation history. To evaluate how these settings affect a model on a specific workload, follow Evaluate a model.