Chat modes & controls
Three modes share the same engine — they differ in policy, not power. Pair the right mode with the right approval setting and the agent does exactly as much as you want it to, no more.
Chat, Ask and Agent
| Mode | Best for | Tools? | Edits files? |
|---|---|---|---|
| Chat | Normal conversation, lightweight grounded help, follow-ups | Sometimes — lightweight, non-mutating tools when policy selects them | No |
| Ask | Explanations, planning, summaries, attachment questions, read-only repo inspection | Yes — read-only inspect/report tools when needed | No |
| Agent | Inspecting, editing, running tests/lint, web research, multi-step work | Yes — full tool use | Yes, when approval allows |
Use Chat for back-and-forth, Ask for grounded help that never touches files, and Agent when you want the system to do the work. Mode is just a flag — the same code paths handle all three.
You don’t need command-like phrasing. In Agent mode, plain requests such as “rename this function and update its callers” work fine. Casual, speech-style requests are classified semantically, so you’re not limited to exact trigger words.
Forcing read-only
Explicit no-edit wording is always respected. Say “no editing”, “do not edit”, “read-only”, “inspect only” or “report only” and coding, test and lint requests switch to an inspect-and-report workflow with read-only tools. Web and image search can still run, because those tools don’t change project files.
The Tools chip — approval mode
Right next to the mode chip is the approval control. It decides whether risky tool calls pause for your yes.
| Setting | Behaviour |
|---|---|
| Confirm | Medium and high-risk tools pause for human approval before they run |
| Autopilot | Risky tools run without asking — the automatic review of edits and the test/lint verification still apply; only your approval click is gone |
This is not an on/off switch for agent capability — it’s the approval mode for tool runs. And it’s live: flip it while the agent is working and it takes effect on the next tool. The full safety model is on the Approvals & Undo page.
The Models panel
The Models button on the composer opens the slot selectors and the context-window size. Most users never need to touch these — the defaults are tuned for an 8 GB GPU.
| Control | What it sets |
|---|---|
| Planner | The model used for planning, replies, Ask mode and finalising |
| Executor | The model used for fast code and tool execution |
| Thinking | Auto, Adaptive, On or Off — see below |
| Context | The chat context window — 8K to 48K (default 16K). Bigger means more history and recall, but more VRAM. Applied after a server restart |
You can also tick Use chat-specific models to save a model choice to just the current chat. By default both Planner and Executor use the same installed model, which keeps memory use low on an 8 GB GPU. To run a different or larger model, see Models & Hardware.
Thinking mode
Whether the model emits extended <think> reasoning is a single setting, gated by what the model can actually do:
| Setting | Behaviour |
|---|---|
| off | Never think — fastest |
| on | Think on every reasoner step — maximum quality, slowest |
| adaptive | Think only when it’s likely to help — on hard, multi-step problems — and stay fast otherwise |
| auto | Let the model’s own default apply (the panel labels this “Auto (model default)”) |
Thinking only applies to thinking-capable models, and Chat mode never thinks. When the model does reason, the trail appears in a collapsible “thinking” card, kept separate from the answer.
The context window
A local model has a limited context window — the chat default is 16K tokens, selectable up to 48K in the model panel. Riverforge manages that budget for you so a small window still handles large tasks: it keeps the most relevant material in view and pulls older details back when they’re needed. The context ring on the composer shows the estimated usage for your next turn — click it for a breakdown of what’s taking up space. More on how the memory works on the Memory & Identity page.
Slash commands
Slash commands are shortcuts, not a requirement — you can always just talk normally. They’re handy when you want to be explicit, and they run through the server so any future client gets the same behaviour.
| Command | Use |
|---|---|
/help | Show chat / tool help |
/tools | List available tools and presets |
/map | Map the repository |
/web query | Research with real web pages |
/images query | Search images and show cards |
/run command | Run an allowed local command |
/test · /lint | Run the configured / default test or lint command |
/diff | Summarise git changes |
/ai-comments | Scan source comments marked AI, AI? or AI! |
/reset | Start fresh for the next answer |
Tool slash commands automatically run as tool-enabled Agent requests. The full catalog and a set of copy-paste recipes are on the Tools & Commands page.