> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentium.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Summaries

> Compressed recaps of older conversation, so long chats stay affordable without losing context.

# Summaries

## In plain terms

A **summary** is a short recap of the older parts of a conversation. When a chat gets long, keeping every word is expensive and eventually overflows the model's limit — so the oldest messages get compressed into a sentence or two and the verbatim text is dropped.

> **The analogy:** turning ten pages of meeting notes into a single sticky note. You lose the word-for-word detail but keep the gist.

Summaries are **on by default** — you get them for free with any `storage` backend. They're what lets a conversation continue for hours without the prompt ballooning.

## When to use it

* **Long-running conversations** — support cases, ongoing projects, multi-day threads. The agent remembers the arc of the discussion without carrying every message.
* **Cost control on chatty sessions** — instead of re-sending 200 messages each turn, the agent sends a compact recap plus the recent messages.

It's on by default, so for most agents you simply leave it alone.

## When to turn it off

* **Strictly short conversations** that never exceed `maxMessages` — there's nothing to summarize, so it's harmless either way, but you can disable it to skip the (rare) summarization LLM call:

```typescript theme={null}
memory: { storage, summaries: false }
```

* **When you need verbatim history** for audit/legal reasons — but note: summaries don't replace the raw transcript, they supplement it. The full session is still stored; summaries are an additional compact layer.

## Configuration

| Property    | Type     | Default | What it controls                                                      |
| ----------- | -------- | ------- | --------------------------------------------------------------------- |
| `maxCount`  | `number` | `10`    | How many recap snippets to keep per conversation. Oldest pruned first |
| `maxTokens` | `number` | `2000`  | Token budget for the summary text injected into the prompt each run   |

```typescript theme={null}
// Default (ON)
memory: { storage }

// Fewer, shorter summaries — leaner prompts, lower cost
memory: { storage, summaries: { maxCount: 5, maxTokens: 1000 } }

// Disable entirely
memory: { storage, summaries: false }
```

**Tuning guidance:**

* **`maxCount`** — each time the session overflows `maxMessages`, one summary is created. More summaries = the agent remembers more of the conversation's history, but old ones eventually drop. Raise it for threads that span days; lower it for short chats.
* **`maxTokens`** — directly affects cost, since these tokens are sent on every run. Lower it (`1000`) to save money; raise it (`4000`) when the conversation is rich and the agent needs more of its history to respond well.

## How it works

1. A conversation grows past `maxMessages` (see [Sessions](/memory/sessions)).
2. The oldest messages are handed to a model (use a cheap one via `memory.model`) which writes a short recap.
3. The recap is stored as a summary; the original messages are removed from the active thread.
4. On future runs, summaries are injected **newest-first** within the `maxTokens` budget — so the most recent context always survives if space is tight.

## Cross-references

* [Sessions & History](/memory/sessions) — where overflow comes from
* [Context Budget](/memory/budgeting) — how summaries compete with other memory for prompt space
* [Memory Overview](/memory/overview) — the full memory lifecycle