solvecraft/docs/agent-chat.md

Agent chat

Agent chat is a side panel where you talk to a coding agent you already use (Claude Code, Codex, Google Antigravity, OpenCode, Grok Build and others), or to a model behind an OpenAI-compatible or Anthropic-compatible endpoint you choose (Ollama or LM Studio on your computer, OpenAI, Anthropic, any other URL), and have it work on the design that's open. A coding agent runs on your computer under your own account with that agent: SolidCraft doesn't sell or proxy a model and needs no key for it. An endpoint's key, if it needs one, goes into your system keychain, never into SolidCraft's settings.

Desktop app only.

Turning it on and off

Everything about it is on one page: Preferences → AI.

• Show AI features (on by default) is the master switch. Turned off, SolidCraft shows nothing of it: no AI button, no shortcut, no menu entry, no panel, and nothing is looked for or started. The page stays, so you can turn it back on.
• Show Assistant button in application bar (on by default): the Assistant icon in the application bar row, which stays there however wide the window is. Turn it off to keep only the shortcut and the menu entry.
• Connect the last-used agent when SolidCraft starts (off by default): each launch starts the agent you connected last (the default one if you never connected), in the background, once SolidCraft has looked for the installed agents. The panel's header shows Starting…, then Ready, or Connection failed with Retry in place of Connect (the agent is missing, could not start, or ended while starting); the conversation says why. A design opened in place of the empty one SolidCraft starts with keeps the agent connected, as long as nothing was asked in that empty design's chat.
• Open the Assistant panel when SolidCraft starts (off by default): the panel (or its own window) is shown at each launch.

Neither applies when SolidCraft is started with --control for automation.

With AI features on, the panel opens from:

• the Assistant icon in the application bar;
• Ctrl+Shift+A (Cmd+Shift+A on a Mac), which also works from the chat's own text box;
• View settings (the last button of the navigation bar under the view) → Agent chat.

Nothing runs until you need it: SolidCraft looks for installed agents (a quick --version each, in the background) when the panel or the AI page first opens, and starts an agent only when you send a message or press Connect (or at launch, when you turned that on above).

The panel

In the floating layout, Assistant fills the viewport height in the shared rounded panel, with space around its edges. The compass and navigation bar move into the remaining space beside it. It overlays the model without changing the viewport projection; clicks and scrolling over the panel stay in the chat. The docked layout retains its side panel.

After clicking in Assistant, keyboard input stays in the chat, including when selecting text in an answer. Copy, Cut and Paste do not also operate on selected CAD geometry. Moving the pointer back over the model does not change this: click outside Assistant to return the keyboard to CAD. Closing or minimising the panel also releases it.

• Docking: on the left, Assistant is the first panel, before vertical history and the browser. The drag highlight shows the actual destination bounds. Drag the panel's header (the dotted grip and the title) to the other half of the window and let go. The side it would land on lights up while you drag. You can also pick Left or Right under Preferences → AI → Panel. SolidCraft remembers the side.
• Width: drag the panel's inner edge. SolidCraft remembers it.
• Its own window: the pop-out button in the header (a window with an arrow) moves the chat into a window of its own, named after the design, which you can move anywhere, including another screen. The window's own close button closes the chat, which opens there again next time; Dock (the same place in its header) puts it back in the side panel. You can also pick Own window under Preferences → AI → Panel. SolidCraft remembers where the window was and how big.
• Minimise (the line in the header) folds the panel into a small floating strip (a side strip in the docked layout) that keeps the chat icon, the agent's state, and a count of anything waiting for your answer. Click the icon to unfold it. Close (×) hides the panel. Neither stops the agent; Stop does.
• The agent switcher under the title picks the agent for this conversation; switching stops the one running. When an ACP agent reports configuration options (including OpenCode V2), a compact inline strip below it shows the agent's model, reasoning effort, mode, and any other supported select options, wrapping when space is tight. Hover a selector for its full label and description. Their names and choices come from the agent: not every model offers adjustable reasoning effort. Changing the model can change or remove the effort choices. A selection is shown as applied only after the agent reports it; a rejected change leaves the confirmed selection in place and shows an error.
• Older agents and API endpoints keep their model and mode drop-downs when they report those choices (an ACP agent's legacy model/mode lists, or an endpoint's /models). SolidCraft remembers the last model choice for each agent and puts it back on the next session when still available. An endpoint's agent also keeps it as its default model. An agent that reports no choices shows no drop-down. When these model lists include more than one provider (Hermes and OpenCode name each model Provider · model, or say Provider: … in its description), the picker groups the models under their providers, each a header with the count of its models that a click folds or opens: the provider of the model in use starts open and the others folded, a search opens every provider with a match, and a provider folded by hand stays folded until the picker closes. Models with no provider named are listed under Other. An endpoint whose listing names its models Vendor: Model under ids vendor/model (OpenRouter) is grouped by vendor the same way; its rows read the model's name, and the id stays in the tooltip and in the search.
• Picking a model. Every model picker opens on a search box over the list the agent or endpoint gave at this connection: SolidCraft has no list of its own. The search covers ids, names and descriptions, and Enter takes the exact match or the first one shown. A model that isn't listed can be typed: Use custom: … takes what is in the box, for an endpoint, an ACP agent with a model option, or an older agent that listed models. An endpoint takes it as it is and keeps it as its default model. An agent may refuse it: its model stays as it was and the chat says why. Only an endpoint keeps a typed model for the next session; an agent gets it back only if it then lists it. An endpoint that can't list its models (it has no such address, or refuses the key) still shows its configured model, and the popup says why there are no others.
• Reasoning effort is not permissions. The agent's thinking setting does not change SolidCraft's Ask / Edits / All approval policy. Reasoning options belong to the current session; changing them here does not rewrite OpenCode's configuration or another OpenCode session.

Messages use right-aligned user bubbles and plain assistant text. Consecutive tool calls share an activity group: click a row to inspect its output; failed calls have an error tint. Approval cards retain the agent’s permission choices, and SolidCraft’s own approvals offer Deny, Always allow and Allow once. The composer’s permission menu uses the same Ask / Edits / All policy as Preferences, for the selected agent, and shows the actual changes used against the configured turn limit. Queue, Send now and Stop keep their existing behavior.

Files and pictures

A message can carry up to eight files, to show the agent what you mean: a concept picture, a sketch, a brief, a part to fit around.

• + next to Send has Choose a file… (a file dialog for the types below) and Paste a picture (the picture on the clipboard).
• Drop files on the chat. Files dropped on the panel (or its folded strip) attach to the next message, and the app doesn't open them too. While files are dragged over the chat, it says so. The window gives no position while something is dragged, so the drop is the chat's when the pointer was last seen over the chat; + always works.
• The files show as chips above the text box: a picture's thumbnail, the name, and × to take the file off. A picture is read off the window thread, so a large one never stops the window: its chip shows a spinner meanwhile, and Send waits for it. Send sends files with no text.
• Pictures (PNG, JPEG, GIF, WebP) go to the agent as they are when they are at most 2048 px on the long side and 3.75 MB (a picture's base64 then stays under 5 MB, so eight still fit in a prompt). Otherwise they are scaled down to 2048 px and re-encoded: as PNG when that fits, as JPEG when the picture has no transparency, halved until it fits; a GIF goes as its first frame. BMP and TIFF go as PNG. HEIC can't be read: export it as JPEG or PNG first. An agent that takes no pictures gets none, and the message says which were left out.
• Text files (UTF-8, up to 256 KB: Markdown, plain text, JSON, CSV, YAML, TOML, XML, SVG…) go in the message's text, whole as far as the message's 100,000-character cap allows: past it a file is cut (and says how much is missing) or named only.
• CAD files (STEP, IGES, FreeCAD, Rhino, STL, 3MF, OBJ, glTF) are imported into the design at once, as components of their own. A file joins the message once its import is in (its chip shows a spinner meanwhile, and Send waits), and the message tells the agent it was added; a failed import says why and the agent is told nothing of it. Taking a part's chip off the message leaves the part in the design (Undo removes it).
• Every file is named in the message. In the conversation the attached pictures show under it as thumbnails (hold the pointer over one for a bigger preview, click it to open the viewer, where the file's name is shown and ‹ › step through the message's pictures, together with the picture of the view); the other files are listed by name. Pictures in any of the formats above are decoded in the background, with a spinner until they are in. A file that can't be attached says why.

Files stay with their message: one queued while the agent works keeps its files, and one sent again after a sign-in sends them again. When several queued messages go as one prompt, their files go with it, at most eight; the rest are named in the chat and not sent. New chat clears the files waiting on the chips too.

Typing while the agent works

Each design tab has its own conversation, agent session, draft, attachments and queued messages. A new tab starts with an empty chat and a session of its own; a sign-in the chat confirmed in one tab still counts in the others, so a new tab doesn't mark the agent as signed out. Switching away stops the current turn and keeps its completed changes in that design's undo history. Returning restores the conversation; queued messages wait for Send. Closing a design closes its conversation. Conversations are kept only while the tabs remain open.

When the agent itself creates a new design or opens a file, its conversation follows the new design and the same turn continues. Its completed changes stay in each design's own undo history. The original tab starts a fresh conversation if you return to it. Opening a file that is already in another tab returns an error instead of displacing that tab's conversation; select that tab yourself to continue there. Your own New, Open and tab switches still stop the current turn. Stop also cancels a file the agent is still opening.

The input stays enabled during a turn. Enter queues the message: it shows in the conversation as a Queued bubble that you can Edit or remove (×) until it is sent. Several queued messages go as one prompt, in order, when the turn ends normally.

• Send now (on the bubble, or Ctrl+Enter / Cmd+Enter in the input) stops the current step, waits for the agent to say it stopped, then sends the queue as the next prompt, with a short note that the agent's previous step was interrupted. What the interrupted message changed undoes as one step, like any other message.
• Stop (the square next to the input, or Esc in the input) stops the agent and keeps the queue: the bubbles wait for Send. If an external ACP agent does not finish its cancelled prompt within five seconds, SolidCraft disconnects it and stops its process in the background. Completed design changes stay undoable, and the queue stays put. Reconnect to start a new agent session.
• New chat (the header button, Ctrl+Shift+L / Cmd+Shift+L with the chat focused) stops what runs, clears the conversation, the queue and the files on the chips, and starts a fresh session on the same agent, keeping the agent and its mode. It asks first when a message is running or queued, or files are waiting. The design's undo history is untouched.

Agents

Preferences → AI → Agents lists every agent the chat can use, each with its kind (a program or an endpoint), version or model, whether it looks signed in, Test, Default (the one a new conversation starts with), its own permission setting, and Edit and Remove for the ones you added.

Found by themselves

SolidCraft looks for agents that speak the Agent Client Protocol on your PATH and in the usual install folders a desktop app's PATH often misses (npm's global folder, nvm, Volta, bun, ~/.local/bin, ~/.grok/bin, Homebrew, %APPDATA%\npm). For each one it shows its version (from --version, given three seconds) and whether a login was found. Version checks and agent sessions also use those folders on their PATH, so adapters can find runtimes such as Node when SolidCraft is opened from Finder or the Dock. Existing absolute PATH entries keep their order; no shell startup files are run. SolidCraft only checks whether the agent's own login file (~/.claude/.credentials.json, ~/.codex/auth.json, ~/.gemini/oauth_creds.json, …) or one of its key variables exists. It never reads the file and never starts the agent to find out. On macOS Claude Code keeps its login in the keychain, so SolidCraft doesn't guess there. A found login file may be expired: Test or a chat connection verifies it. A successful ACP connection shows signed in; an authentication rejection shows not signed in. These results apply to that agent until a newer connection result or Refresh, which checks the installed agents again. An unrelated connection error doesn't change the last known login state.

Agent	What to install
Claude Code	npm install -g @agentclientprotocol/claude-agent-acp (the ACP adapter for Claude Code)
Codex	npm install -g @agentclientprotocol/codex-acp
Google Antigravity	Google's ACP server, a separate download from Google's agy command (which has no ACP mode): take the zip for your system from the ACP registry, unzip it and put agy_acp_server.par (agy_acp_server.exe on Windows) on your PATH. The zip also holds localharness_external: leave the two together. It signs in itself (browser).
OpenCode	npm install -g opencode-ai (opencode acp)
XAI Grok	Grok Build installer, then grok login (grok agent stdio speaks ACP)
GitHub Copilot CLI, Qwen Code, goose	listed with their install command when missing

The panel lists agents that aren't installed with their install command and a Copy button. Refresh looks again after you install one. An agent whose program is there but fails its --version check without printing a version (an install that didn't finish, such as an npm install whose setup script didn't run, or a program built for another kind of computer) is still listed, marked does not start with the system's reason. Connecting to it first says why and gives its install command; reinstall it until --version works in a terminal, then press Refresh. A check that runs out of time is not counted as a failure. Test starts an agent briefly, asks it for a session and ends it again.

Flatpak

The Flatpak sandbox has no home-folder or network access by default. Agents installed through nvm or ~/.local/bin can therefore work in a terminal while SolidCraft reports that no agent was found. For Claude Code and its ACP adapter, run:

flatpak override --user io.tangencylabs.solidcraft --filesystem=~/.nvm:ro --filesystem=~/.local/bin:ro --filesystem=~/.local/share/claude:ro --filesystem=~/.claude --filesystem=~/.claude.json --share=network

These permissions apply to SolidCraft for your user account:

• ~/.nvm:ro exposes Node and globally installed npm adapters read-only.
• ~/.local/bin:ro exposes locally installed executables read-only.
• ~/.local/share/claude:ro exposes Claude Code's native installation read-only, including the targets of links in ~/.local/bin.
• ~/.claude and ~/.claude.json allow Claude Code to read and update its sign-in and configuration files.
• --share=network lets the adapter reach its service. It also gives SolidCraft network access, including making an enabled control server reachable from the host.

Restart SolidCraft after applying the override. Other agents or installation folders may need different filesystem permissions.

XAI Grok

Install Grok Build and run grok login in a terminal to sign in with your Grok account. In SolidCraft, open AI → Refresh, select XAI Grok, then Connect. You can make it the default under Preferences → AI → Agents.

SolidCraft reuses Grok Build's sign-in in ~/.grok/auth.json; it checks only whether that file exists and does not read or copy its tokens. If sign-in is needed, the panel offers Grok's own sign-in methods. You can also run grok login again and reconnect. Grok controls model access and usage limits for your account. This connection does not require an API key in SolidCraft. Grok Build also supports XAI_API_KEY for users who choose API authentication.

Add agent…

• Installed agent: your own entry for an installed agent, for example with other arguments.
• Custom command: any other program that speaks ACP on stdin and stdout, such as my-agent --acp. SolidCraft starts it directly, not through a shell.
• OpenAI-compatible API: a preset (Ollama http://localhost:11434/v1, LM Studio http://localhost:1234/v1, OpenClaw http://localhost:18789/v1, OpenAI, Mammouth AI https://api.mammouth.ai/v1, OpenCode Go https://opencode.ai/zen/go/v1, OpenRouter https://openrouter.ai/api/v1) or a custom URL, the model name, and an optional key. OpenCode Go models are routed to their endpoint by themselves (/responses, /messages or Gemini for those families, /chat/completions for the rest), each conversation request carrying the session header Go asks for, so one preset covers every model. A model the list does not know is retried on the next protocol when Go names the mismatch. For OpenClaw, turn on its chat endpoint (gateway.http.endpoints.chatCompletions.enabled in its config) and use its gateway token as the key; the models it lists are its agents, such as openclaw/default.
• Anthropic-compatible API: a preset (Anthropic) or a custom URL, for an endpoint that speaks the Anthropic Messages API ({base}/v1/messages). This covers Anthropic itself and providers that offer an Anthropic-compatible endpoint, such as DeepSeek and Qwen.
• The Model picker lists the endpoint's models, without a key where the endpoint allows that (OpenRouter does), once you leave the address and key fields; opening it asks again after a failure. You can also type a model.
• An endpoint's card under Preferences → AI → Agents has the same Model picker. While the agent isn't running, opening the picker lists the models (just viewing the page asks nothing), and a pick becomes the model for its next connection. While it runs, a pick changes the chat's model at once.
• The key goes into the system keychain (Keychain on macOS, Credential Manager on Windows, the Secret Service on Linux) and is only ever sent over HTTPS or to this computer. Test asks an OpenAI-compatible endpoint for its models; an Anthropic-compatible one gets a short message, because not every such endpoint lists models (Qwen's has no model list). For these agents SolidCraft runs the conversation itself, with the same tools, limits and questions as for a coding agent, and no cap on model requests per message (Stop ends it). Request timeout is how long one model request may take: 300 s by default, from 30 s to an hour. A slow local model (a large model on modest hardware, or a long message with many tool results) may need more; raise it here or in the endpoint's entry under Agents, where a change applies from the next request. A request that runs out of time ends the message with the limit it hit and where to raise it. Reasoning effort is optional and empty by default: nothing is sent and the provider's own default applies. When set, the value goes out as reasoning_effort on each /chat/completions request; accepted values differ per provider and model (for example low, high or max). A value you set is never replaced by SolidCraft: if the endpoint refuses it, the refusal is shown instead of being retried with none.

Edit on an agent you added opens the same dialog filled with its name and command, or its protocol, endpoint, model and request timeout, and Save changes it in place: it keeps its id, its permission setting and the tools you always allow for it. A stored key is never shown: leave the key field empty to keep it, or type a new one to replace it. A saved key still only goes to HTTPS or this computer, so moving an endpoint with a key to a plain http:// address elsewhere is refused. The running conversation takes a new request timeout at once; a new command, endpoint or model applies the next time the agent connects.

For Ollama, choosing a model checks its reported capabilities in the background. If its capabilities list lacks tools, a warning below the model picker explains that the model can only chat and suggests choosing one with tool support. Results are cached in memory per base URL and model, with a limit of 128 entries. SolidCraft recognises Ollama through /api/version at the endpoint's origin or the Ollama preset. Failed checks and older servers without a capabilities field show no warning. The check never blocks sending a message.

Local models

Choose a model that supports native tool calling to read or change the design. With Ollama, look for tools in the model's capabilities; a model that only supports chat cannot operate SolidCraft. Other OpenAI-compatible endpoints also need a model with native tool support.

If tools were available but a completed turn made no tool calls or changes, the panel shows a short notice when the reply was empty, or when an explicit edit request received only text. Ordinary answers to questions do not show it. Edit requests are recognised conservatively from English opening words such as “make”, “rename”, or “can you move”; other phrasing may stay quiet. Cancelled and failed turns keep their existing messages. Text describing a call is never run. A reply that stopped at its length limit, or that the model declined, says that instead of the tool-calling notice: an endpoint reports it as max_tokens or refusal (Anthropic), or as length, content_filter or a refusal (OpenAI-compatible). A tool call cut off at the length limit is not run.

An agent inside WSL (Windows)

An agent installed inside WSL keeps its own settings, skills and sign-in there. Add it as a Custom command that starts it through wsl.exe, for example:

wsl.exe -d Ubuntu -e bash -lc claude-agent-acp

bash -lc runs your login shell's setup, so the agent is found where your PATH puts it (npm, nvm, Volta). When the command's program is wsl or wsl.exe, SolidCraft gives the agent its working folder and the solidcraft-app server's program as WSL shows them (C:\Users\… becomes /mnt/c/Users/…). The server itself still runs on Windows and reaches the app at 127.0.0.1, so this works with WSL's default networking. If you moved WSL's drive mounts away from /mnt (automount.root in /etc/wsl.conf), those paths won't match and the agent can't start the server.

Signing in

If a coding agent isn't signed in, it says so and the panel shows Sign in to the agent with the agent's own ways to sign in:

• A command for a terminal, e.g. claude-agent-acp --cli auth login --claudeai, with a Copy button. Run it in a terminal, sign in there, then press I've signed in: connect again.
• A button for agents that sign in by themselves (Codex's ChatGPT login opens your browser).
• A variable to set for agents that take a key from the environment. The panel has no field for a coding agent's key, on purpose.

Whatever you typed before signing in is sent once the agent is ready.

What the agent can do

The agent reaches the open design only through SolidCraft's own tools (the MCP server), which SolidCraft hands it when the chat starts. That server is named solidcraft-app, so an MCP server you set up yourself under the name solidcraft (as in client configuration) doesn't take its place:

• Read the design: list commands, inspect features, sketches and parameters, measure, take pictures of the view.
• Change the design: run any modelling command, alone or in a batch. Changes show in the window as they happen.
• One undo per message: everything the agent changes while answering one message becomes a single undo step, named after your message. The conversation shows N changes, one undo step with Undo these changes while nothing else has happened since.
• Tool cards: each tool call shows as a card with its state; click it to see what it returned.
• Formatted text: the agent's answers show as Markdown: headings, lists, quotes, code blocks (with Copy), bold, italic, code and links (web links only; each link is a button that opens it in your browser). What you type, and the agent's thoughts, stay plain text.
• Attach view: tick it to send a picture of the current view with your message, for agents that take pictures. The picture is taken when the agent starts on the message and then shows as a small thumbnail under it. Hold the pointer over the thumbnail for a bigger preview that stays while you do; click it to open the viewer (the message's pictures one at a time, with ‹ and › or the arrow keys, closed with Esc or a click outside). A long message scrolls inside its box, so Send and the buttons beside it stay in view.
• Attach selection: tick it to send what is selected in the model with your message, so the agent knows what "this edge" or "that feature" is. The box shows how many things are selected, counted as you clicked them (the two halves of a rim you clicked once are one). Faces and edges go with the names and numbers the agent's tools take and with their size and place (so they can be found again after an edit), features with their name and kind, bodies with their name. The agent gets them as text after your message; the conversation shows your message as typed with the things as chips below it, grouped (Elements, Features, Bodies) with a count; hover a chip for what the agent was told about it. At most 64 things go with one message; the rest are counted ("+N more"), not dropped silently. The selection is read when you send, also for a message that waits in the queue.
• Pick context: press it to choose what the message is about on purpose. A picker opens with three lists, Elements (faces, edges, vertices), Features (steps of the timeline) and Bodies; click things in the model, the timeline or the browser to put them in the list that is active (click a list to make it active; click a picked thing again to take it out). OK puts them as chips above the message box, each with a ×; they go with the next message like an attached selection (and are shown the same way), and the box is empty again afterwards. Cancel keeps what was picked before.

Permissions

Preferences → AI → Permissions decides what the agent may do without asking, for every agent; each agent can have its own setting in its row.

• Ask every time: every change to the design and every file action waits for Allow, Always allow or Deny in the panel.
• Auto-allow model edits (the default): modelling commands run at once; saving, opening, exporting, importing, starting a new design, any command given a file name, and undoing past the start of your message still ask.
• Allow everything: nothing asks. The page warns you: the agent can then save, overwrite and replace your design.

Always allow remembers that command for that agent. The page lists what you allowed this way, per agent, with Reset.

These settings cover SolidCraft's tools. A coding agent's own tools (its shell, its file edits) follow the agent's own mode, which you pick in the panel's header. When an agent asks before using one of the chat's own SolidCraft tools and names it exactly as the Claude adapter does (mcp__solidcraft-app__batch), SolidCraft answers for you, since its own gate checks the call, and notes it in the chat as Auto-allowed. Any other question appears in the panel, including a SolidCraft tool an agent words differently and a SolidCraft MCP server you added to the agent yourself. With Allow everything, or after Always allow, those questions are answered the same way and noted too.

What counts as "a command given a file name": a parameter that holds a file or folder (file, dir, output, …), or path and source when the value reads like a file name (a separator, ~, a leading dot or a known extension), or any value of those in a command that exports, imports, saves, opens or inserts. A sweep's or pattern's path (curve ids) and an occurrence's path (ids) are geometry and run without a question.

What it can't do

• Files wait for you unless you chose Allow everything. Cancel or Stop declines everything that's waiting, and a question nobody answers is declined after four minutes. The MCP server's folder limits still apply after you allow: the design's folder, the recovery folder and the server's own scratch folder.
• An optional limit per message. There's none by default. Untick Unlimited on the AI page to cap the changes the agent may make per message (it starts at 24). Reading the design doesn't count. At the limit, it's told to stop and report what's left; send another message to let it carry on. Stop always works.
• No crash reports, whatever the permissions. Crash reports can hold other designs and file paths.
• Not the rest of the app. It can't click the interface, change settings, quit, or drive the chat itself.
• Its own tools stay off where we can turn them off. SolidCraft declares no file system and no terminal to the agent, runs it in an empty working folder of its own, and asks the Claude Code adapter to turn off its shell, file and web tools for the session.

When the panel's agent is stopped, another agent is picked, or SolidCraft quits, the agent and every program it started (the CLI it wraps, its MCP server) are stopped.

Privacy

Nothing goes anywhere except to the agent you run, or the endpoint you added. SolidCraft starts a coding agent as a program on your computer and talks to it over its standard input and output. What the agent sends to its own service, under your account and that service's terms, is between you and that service, exactly as when you use the agent in a terminal. SolidCraft never sees, stores or passes on a coding agent's password, token or key. An endpoint's key is kept in the system keychain and sent only to that endpoint. SolidCraft's own connection to the agent's tools uses a random per-launch token in a file only you can read, which never passes through the agent.

Trying it without an account

A scripted test agent is in the source tree. It makes a block, rounds it and measures it, with no model behind it:

cargo build --release -p solidcraft-ui-egui --example acp_test_agent

Then add it under Preferences → AI → Add agent… → Custom command with the path of target/release/examples/acp_test_agent. Put "save" in your message to see an Allow / Deny card, or "ask" to see the agent ask its own permission.

Benchmarking the Assistant

solidcraft-cli bench-assistant runs the eleven tasks of the standard model test (v1, #4851) against a desktop app that is already running with a control port, and checks each result on the design itself. Use it to see how well a local model drives SolidCraft before you post its results.

solidcraft --control 9271
# In another terminal:
solidcraft-cli bench-assistant --connect 127.0.0.1:9271 \
  --base-url http://localhost:11434/v1 --model qwen2.5:7b \
  --json results.json --markdown results.md

Each task replaces the open design with a new one, so save your work first. The command adds the endpoint as an API agent named "bench", starts a new chat with All permissions for every task, sends the prompt once, and waits for the turn to end. It runs only the setup the test prescribes (the box some tasks start from) and does none of the modelling itself. When it finishes it stops the agent and puts your permission setting back.

• The control token comes from --token, SOLIDCRAFT_CONTROL_TOKEN, or the app's token file, in that order.
• --tasks 1,2,5 runs only those tasks, --repeat N runs the test N times, and --timeout-s (default 300) is each turn's deadline; a turn that runs past it is stopped and fails as "timeout".
• A failed task gets one of the issue's failure categories ("wrote the call as text", "wrong or unknown command", "wrong arguments", "the endpoint refused tools", "an empty reply", "only talked", "gave up after errors", or "hit the request limit"), or "wrong result" when the calls worked but the design is not what the task asks for.
• --markdown writes the issue's comment template filled in; add the quantization, download size, and runtime before you post it. --json keeps each task's failed rules, conversation, and design before and after. Both files are rewritten after every task.

The show/hide shortcut defaults to Ctrl+Shift+A (Cmd+Shift+A on macOS). Change, clear or reset Toggle Assistant (ui.assistant) in Preferences → Shortcuts. The binding is saved with the other keyboard shortcuts; the assistant button tooltip follows it. Disabling AI features also disables the toggle.