Solution

# Your context window fills and the agent forgets the morning. *Keep working in one session.*

Context Mode keeps older work word for word in an archive and sends the model recent work plus an index. In a paired run on a 200K window: no compactions, 9 of 10 early details exact, 37.6% lower cost.

[Get started free](https://console.context-mode.com/login) [Read the docs](https://context-mode.com/docs/recall)

One workday

Cost Compactions Early details Early rule Terminal

The same 30 steps on a 200K window, run twice.

Without Context Mode **$4.86** Context Mode **$3.04**

37.6% lower per session. Cheaper in 3 of 3 pairs, Claude Opus 5.5.

How often the session compacted.

Without Context Mode **3** Context Mode **0**

Through Context Mode the session never compacted.

After the work, 10 questions about early details.

Without Context Mode **4 of 10** Context Mode **9 of 10**

Exact answers. Task checks 8 of 8 in both arms.

Early on you said: keep the refund window at 14 days.

After compaction

- In the summary only if the summary kept it
- In other words, not yours
- The agent may ask again

With Recall

- In the index, word for word
- Listed as a decision the agent must not reopen

An example of the mechanism, from the Recall docs.

What you see when Recall acts.

```
⚡ context-mode · picked up after a 2 h pause, nothing compacted
⚡ context-mode · recalled 2 items from 2 days ago (a decision, src/billing/quota.ts)
```

Each line shows once. The console lists each lookup.

The problem

## The window sets your day. *Not your work.*

**The session ends early**

Close to the window, your agent compacts: it swaps older history for a summary. From then on it works from the summary, not from your morning.

**You answer twice**

The summary drops exact lines and early rules. The agent asks the same question again, or makes the other choice.

**The bill grows each hour**

Until it compacts, every request sends the whole history again. Each request costs more than the one before.

How it works

## Set a limit once. *Work all day.*

1. 01 **Pick a size** Choose 200K, 500K or 1M in Active Context. Each thread stays under it.
2. 02 **Older work goes to the archive** Word for word, before it leaves the model's view. The model gets recent work and an index of the rest.
3. 03 **The agent looks it up** It fetches an early detail by id, or finds it by search. You do not type it again.

Want to see it step by step? [One session, from hour one to hour six →](https://context-mode.com/use-cases/all-day-session)

Proof

## The same workday, *run twice.*

**37.6% lower cost** per session on a 200K window, $4.86 to $3.04 **0 compactions** through Context Mode. Without it, the session compacted 3 times. **9 of 10** exact answers about early details, against 4 of 10 without Context Mode

3 pre-registered pairs on 2026-10-04, mean of 3 pairs. Claude Code on Claude Opus 5.5, the same 30 steps in both arms. Cheaper in 3 of 3 pairs. Task checks 8 of 8 in both. [Method and sources →](https://context-mode.com/docs/benchmarks#long-session-200k-r2-detail)

Products used

## What this *uses.*

**[Recall](https://context-mode.com/recall)**

Recent work and an index go to the model. Older work stays in the archive, word for word.

**[Active Context](https://context-mode.com/active-context)**

Pick 200K, 500K or 1M once. Each thread stays under it.

**[Search](https://context-mode.com/search)**

Find any prompt, command or tool output from past sessions, in the console or from your agent.

Related: [All-day session, step by step](https://context-mode.com/use-cases/all-day-session) · [All-day sessions without compaction](https://context-mode.com/blog/recall-all-day-sessions-without-compaction) · [Session resume](https://context-mode.com/session-resume) · [Recall docs](https://context-mode.com/docs/recall)

## One session, *all day.*

*npx @context-mode/cli* connects your agents. 1,000 requests free, no card.

[Get started free →](https://console.context-mode.com/login) [Read the docs →](https://context-mode.com/docs/recall)