> ## Documentation Index > Fetch the complete documentation index at: https://www.rumus.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Conversation management > Auto-naming, automatic summarization, and task lists — how Rumus keeps your AI threads coherent over time. A long agentic conversation can pile up a lot of context — tool calls, intermediate results, half-finished plans. Rumus has a few quiet behaviors that keep things readable and within the model's context window. ## Auto-naming When you start a new conversation, the AI generates a short 3–7 word title from the first exchange. This is what shows up in the chat history list in the AI sidebar. | Setting | Where | Default | | --------------------------- | ----------------------- | ------- | | **Auto-name conversations** | Settings → AI → General | On | When **off**, the title is just the first message truncated to \~50 characters. The first-message fallback is also used if auto-naming fails or times out (30s) — your conversations always end up with *some* title. Titles are generated in the **language of your message** — if you write in Chinese, the title comes out in Chinese. You can rename a conversation any time from its row menu in the history list. ## Automatic summarization Long conversations would eventually exceed the model's context window. Rumus heads that off by **summarizing older parts of the conversation** automatically — the agent compresses the older portion into a 150–300 word summary that preserves decisions, context, actions, and pending tasks, and keeps the most recent few messages verbatim. You don't trigger this manually; it happens whenever the conversation crosses an internal threshold (currently around 10+ new messages and rising). When it does, you'll see a **Summary block** in the conversation marking where the compaction happened. The summary preserves: * **Decisions made** — "we chose option A because of X." * **Context discovered** — "the host was running Ubuntu 22.04, not 24.04 as assumed." * **Actions taken** — "ran the migration script; it succeeded." * **Pending tasks** — "still need to deploy to staging." This means even very long conversations stay coherent — the agent can reach back into the summary for context that would otherwise have aged out. There's no toggle for summarization — it's automatic and driven by token-count logic. If you want a fresh start, start a new conversation. ## Task lists For multi-step jobs, the agent can render a **Todo list** inside the conversation — a checkbox list of tasks it's tracking. This is separate from [plan mode](/docs/ai/plan-mode); it's a lighter-weight progress tracker that shows up alongside ordinary tool calls. | Setting | Where | Default | | ------------- | --------------------------------------- | ------- | | **Todo list** | Settings → AI → Conversation → Behavior | On | When on, the agent decides whether the conversation benefits from a task list and creates one when useful. It checks items off as it makes progress and appears as a single block in the conversation that updates in place. The task list is conversation-scoped — it doesn't persist across conversations and isn't a global todo system. Use [skills](/docs/ai/rules-skills) for procedures you want to reuse. ## Picking a model per conversation The model picker remembers your last choice **per conversation**. Switching models on one thread doesn't affect any other thread. This makes it cheap to maintain parallel conversations on different models — say, a long debugging thread on a strong reasoning model and a high-volume routine ops thread on a faster, cheaper one. ## Token info per message Click the small info icon on any AI message to see: * **Input tokens** — what was sent to the model (prompt + history + tool results). * **Output tokens** — what the model generated. * **Cached input tokens** — input served from prompt cache, billed cheaper. * **Reasoning tokens** — internal "thinking" tokens, when the model exposes them. * **Cost** — dollar value charged for built-in models. Useful for spotting which messages are dominating your spend. ## Other related toggles A few smaller behaviors you can tweak: * **Auto-collapse tool calls** — keeps the conversation tidy by collapsing tool blocks once they finish. On by default. * **Max mode** — a per-conversation toggle that uses the model's full context length rather than a default safety margin. Useful for long-context work; off by default to avoid the cost spikes from filling a 1M-token window. Both live under **Settings → AI → Conversation**. ## Tips * **Start a fresh conversation when the topic changes.** Summarization preserves a lot, but completely new topics are easier to follow as a clean thread. * **Star important conversations.** The history view's favorites filter makes them easy to find later — especially handy for long-running debugging where you keep coming back. * **Auto-naming + good first messages.** A descriptive first message produces a descriptive title. *"Why is nginx returning 502 for /api?"* gives a title that means something later. ## Next steps Multi-step plans rendered as a checklist with status icons. Define reusable procedures the agent invokes by name.