> ## Documentation Index > Fetch the complete documentation index at: https://docs.gcaplabs.com/llms.txt > Use this file to discover all available pages before exploring further. # Conversations > How to create, manage, steer, and organize conversations in Headmaster. # Conversations A conversation is the basic unit of work in Headmaster. You type a message, the agent responds, and the exchange is saved as a session you can resume later. *** ## Creating a new conversation Click **New chat** in the sidebar. A fresh conversation starts with no context from previous chats. When you start a new conversation, you pick: 1. **An agent** — the built-in engine (default), or any detected CLI agent (Claude Code, Codex, Gemini CLI, etc.). Each agent has its own model list. 2. **A model** — from the agent's available models. Use the selector at the bottom-left of the composer. 3. **A specialist** (optional) — a pre-configured persona with rules and skills. See [Specialists](/specialists). The agent and model you pick are remembered for this conversation. New conversations start with your default agent and model. *** ## Streaming responses The agent's response streams into the chat window token by token. You see it being written in real time. While the agent is working, you can: * **Watch** the response as it streams. * **Scroll up** to review earlier parts while still generating. * **Interrupt** by clicking the stop button next to the composer. ### What appears in a response | Element | Description | | --------------------- | ---------------------------------------------------------------------------------------- | | **Text** | The agent's written answer. | | **Thinking** | The agent's reasoning process (collapsible block, for models that support it). | | **Tool calls** | Web searches, file reads, code execution, MCP calls — each shown as an expandable block. | | **File changes** | Files created or modified, shown as diff blocks. | | **Images** | Generated images appear inline. | | **Plans** | Step-by-step plan cards when the agent plans before acting. | | **Skill suggestions** | The agent may suggest enabling a skill for the conversation. | *** ## Follow-up messages After the agent responds, type a follow-up and press Enter. The agent has the full conversation context and responds accordingly. **Selection reply:** Select text in the agent's response and a reply button appears. Click it to quote the selected text in your follow-up — useful for asking about a specific part of the response. *** ## Editing and undo * **Edit your last message** — click the edit button on your most recent message. Edit it, re-send, and the conversation continues from the edited point. * **Undo** — click the undo button to back up one turn. Your message and the agent's response are removed. Undo multiple turns as needed. *** ## Interrupting and steering If the agent is going in a wrong direction, click the **stop** button. The agent stops and the partial response stays in the chat. Send a corrective message to redirect: ``` Actually, don't run that — just tell me the answer directly. ``` **Mid-run steering:** You can also redirect mid-task without breaking context. While the agent is working, type a new message and send it. The agent pauses, reads your instruction, and adjusts. *** ## Multiple conversations You can have many conversations open at once — each with independent memory, model, specialist, and project folder. Switch between them in the sidebar. Start a new one with **New chat**. ### Running tasks in parallel * Run a code review in one chat. * Generate a deck in another. * Research a topic in a third. All at the same time, all with their own context, with no bleed-through between conversations. *** ## Project (working folder) Open a folder as a project to give the agent scoped file access: Click the `+` button next to the composer and select **Open folder**. Choose a folder from the file dialog. The Workspace panel appears on the right with the folder tree. The agent can read and write files inside the project folder without per-access approval. Files outside the folder still require approval each time. A folder is locked per conversation. To work in a different folder, start a new chat. This prevents the agent from confusing two projects' file trees. ### Workspace panel The Workspace panel shows: * **File tree** — folder hierarchy with expand/collapse. * **File tabs** — open files in tabs, switch between them. * **Context menu** — right-click a file for options (open, rename, delete, copy path). * **File change list** — when the agent modifies files, a list of changes appears at the top. *** ## File upload Attach files to your message in several ways: * **Drag and drop** files directly into the composer. * **Click the `+` button** and choose files from disk. * **Paste** files from your clipboard. * **`@file:` mention syntax** — reference a file in your message: ``` Read @file:/path/to/config.yaml and tell me what's wrong with the database section. ``` **Supported file types:** text files, images, code files, PDFs, Office documents (`.docx`, `.xlsx`, `.pptx`), archives (`.zip`, `.tar.gz`), and more. *** ## Mention dropdown Type `@` in the composer to open the mention dropdown. It shows: * **Files** — files in your current project folder. * **Specialists** — available specialists to mention. * **Skills** — available skills to reference. *** ## Slash commands Type `/` in the composer to open the slash command menu: | Command | What it does | | -------------------- | ----------------------------------------------------------------------- | | `/council` | Start a Council session (routes to `/team/default`) | | `/specialist ` | Switch to a specific specialist | | `/mode ` | Switch mode (`work-along`, `run-it-yourself`, `hands-off`, `autopilot`) | | `/schedule` | Create a scheduled task from natural language | | `/remember` | Save the current message as a memory fact | | `/clear` | Clear the current conversation display (keeps the session) | *** ## Session persistence Conversations are saved automatically. When you close and reopen Headmaster, your conversation list is in the sidebar exactly as you left it. Click any conversation to resume — the agent picks up with the full context. Sessions are stored in `/sessions/`. Each session is a JSON file with the full transcript, tool call records, and metadata. *** ## Managing your conversation history The sidebar shows conversations most recent first. Each entry shows the first message (as a title), the date, the specialist used (if any), and whether the session was triggered by a scheduled task. You can: * **Search** conversations by typing in the search bar at the top of the sidebar. * **Pin** important conversations to keep them at the top. * **Rename** a conversation by clicking its title. * **Delete** a conversation — removes the session file permanently. * **Group** conversations by date (Today, Yesterday, This Week, Earlier). *** ## Stale session recovery If the runtime restarts while a conversation is mid-stream, the session becomes stale. Headmaster detects this and shows a **Recover** button. Click it to resume — the agent picks up where it left off with the full transcript preserved. *** How the agent remembers facts across conversations. Work Along, Run It Yourself, Hands-Off, and Autopilot explained.