A CLI integer option stripped the 0x prefix and parsed the rest with from_str_radix, which accepts a leading '+', so --addr 0x+10 was read as 16. The text after 0x must now be non-empty hex digits; anything else gives the existing "expects a number" error.
An API backend's `tools` setting (auto, lean or full) could only be changed by editing config.toml. Settings → AI now has a "Builder's tools" choice per API backend, with a caption saying what Auto works out to for that AI, and `ai tools <name> [auto|lean|full]` shows or sets it from the CLI. Auto is saved as no setting; agent apps are refused, as they choose their own tools.
* Let Claude Code use the model its own settings name by default
Claude Code runs are no longer passed a hardcoded --model: with no choice
saved, the agent uses whatever its own settings name (a custom model, an
alias, opusplan…), and `ai model --default` clears a saved override back
to that. The Settings → AI picker lists "Default (its own settings)" first
for Claude Code (saved as `claude-code` or `claude`), choosing it clears
the saved model, and the typed "Another model" field is gone since the
list carries the choice. effort_levels detects Claude Code by adapter id
so the `claude` agent id gets every effort level too.
* Translate "Default (its own settings)" in the remaining eight catalogs
The i18n gate requires every catalog to carry the same key set; the
first commit only added the new picker label to six of them.
An API backend's requests per minute could only be set by editing config.toml. Settings → AI now has a field for it on each API backend, and the CLI has ai request-rate <name> [n]; zero removes the limit. Agent apps send their own requests, so they have no such setting. The save runs on a worker through the hub's usual save path.
Agents over ACP report context use, not a turn's tokens, so their turns now say the token count is unknown instead of 0, in the CLI, the build's activity and the app. Project and session totals keep what was reported: "Unknown" when nothing was, and a lower bound such as "1.9M+" when some turns had no count. usage.json gains `tokens_incomplete`; older files read as before.
The Effort setting in Settings → AI appeared only for the Claude API and Claude Code. OpenAI, OpenRouter, Gemini and OpenAI-compatible AIs now offer OpenAI's levels (none to xhigh), starting at default, which sends nothing; once a level is picked, requests carry reasoning_effort (OpenRouter: reasoning.effort), and craft-anything-cli ai effort lists and sets the same levels. Claude no longer accepts none or minimal. Refs #1813.
* feat(updates): add manual release checks and verified native updates
* chore: bump version to 0.6.1
* fix(flatpak): honor the launcher version choices
* fix(updates): report restart outcomes without UI process side effects
* fix(i18n): translate updater controls in the complete catalogs
* test: document native updater startup as UI plumbing
Since #987, picking a folder that already holds a project attaches to it, but the create path then overwrote its saved builder, asset budget, generated-assets choice and stack, replaced its conversation, and dropped the typed request. An attached project now keeps everything the person set and its saved conversation, and the request is added as its follow-up, in the app and the CLI; the CLI refuses --build-with, --generate-assets and --existing for such a folder with a fix to use instead.
A number option parsed with f64, which accepts NaN, inf and infinity; JSON can't hold those, so the value silently became null. The CLI now refuses non-finite numbers with its usual "expects a number" error, and a test covers NaN, inf, -inf and infinity.
A key saved in the app silently wins over the one in the environment, so a rotated key stayed hidden behind the old one unless the backend was removed or the keychain edited by hand. Settings → AI now shows for every API backend whether a key is saved; a saved one can be forgotten, so the environment's is used again, and a new one saved in its place, without removing the backend. The CLI does the same with ai key <name> (--key-env, --key-stdin or --forget), and never prints the key. A new key is read back after saving, and a forget that a locked or failing keychain can't confirm says so instead of reporting success.
Refs #1358
A coding agent's turn killed mid-turn leaves a record of its session, which was removed only at the next agent turn or on uninstall; meanwhile the agent's own background service could carry on a session nobody was watching. The desktop app now sweeps those records when it starts, on a background thread, with the same rules as any sweep: a record a running turn holds is left alone, and a delete that fails is kept for the next sweep.
OpenCode Go backends that weren't added through Settings (from an older version, or found from an environment key) had no saved session id, so each run sent a new one. The app and the CLI now save one at startup for any OpenCode Go backend that has none, before any session lock is taken, and keep it across restarts. An OpenCode error that comes without a message now shows its name, HTTP status and the start of the response body instead of "no error details".
Refs #1225
Devin can be added as a coding agent. Builds talk to `devin acp`, which takes our tool server and sends its permission requests to the approval policy; since Devin doesn't use its own CLI sign-in over ACP, the session authenticates with the key stored for that backend, sent only to the local process and only when Devin offers that method. The key is looked up only for agents that authenticate this way, so other agents never touch the keychain. One-off questions use `devin -p`, and `craft-anything-cli ai add --acp` sets an agent to ACP.
A stopped, failed or timed-out OpenCode turn deletes the session it started, so OpenCode's own service can't resume it later. A turn records its session while it runs, so one left by a killed app is deleted at the next turn or by doctor, on this computer or over SSH.
Part of #1115. Includes #1176.
The two start guard tests share the process-wide held mark, so one's opened() could drop the other's lock mid-test and fail main now and then. They now take a shared test lock.
A note sent while a build runs now carries the latest Just ask answers its mode may show, including through Claude Code's note hook, and they count as told only once the builder has them. A Clean room run never gets Deep answers.
`rebuild --continue-in`, `rebuild_start` on a project and `rebuild_question_ask` now say which AI works when the saved one is off or gone, as the app does.
A project can allow, ask about or refuse each kind of builder action (web, commands, outside files, publishing, deletes outside the project, system changes, other tools); a kind it hasn't chosen follows Auto mode as before. `project_approvals_set` sets them, and an agent can only make a kind stricter, including through our CLI from its own shell. "Always" on a push, delete or system card allows that whole kind, and pushes are read word by word in every shell form.
A Windows start that can't draw moves on through DX12, WARP, Vulkan and OpenGL and keeps the one that works; a start still under way is not a failed one. The Claude desktop hint covers the SSH-only case and the Store package folder. Closes#794.
`mcp --restricted` leaves out tools that act on the machine or reach the network, going by what each declares; `--allow-web` and `--allow-capture` turn on their own groups. Closes#855. Closes #856.\n\nCo-authored-by: Dev Maktuporia <devmaktuporia@gmail.com>
The Mac window keeps its native buttons and frame, the bar keeps its size when zoomed, and room is reserved for the buttons in full screen too.\n\nCo-authored-by: Sanket Dofe <dofesanket@gmail.com>
`rebuild --backend <name>` uses a configured backend of that name as it is, and registers an installed agent whose name matches when it is not added yet; an unknown name adds nothing. Follow-up to #819 (R5.5).
`rebuild` looks for and saves a coding agent only when no enabled AI can build, so a run with an API backend no longer adds Claude Code to the settings; a refused command changes nothing (R5.5).
Tests for both start-panic decisions (passed through, turned into a start error before the window showed, resumed after), now in a module CI runs on every platform. An early panic is reported as an internal error rather than a graphics failure, since it can be any bug in the first moments. Follow-up to #786.
On macOS the system menu bar has the app's actions with the usual Mac shortcuts (Settings ⌘, · New project ⌘N · Open ⌘O · Command palette ⌘K · Quit ⌘Q, the Simple/Advanced and Clean room/Deep choices, and Help links to this repository), through muda. Other systems are unchanged.
Supersedes #791.
Co-authored-by: sanketdofe <46375884+sanketdofe@users.noreply.github.com>
When the Claude desktop app is installed but Claude Code isn't, the setup card and ai detect say so and how to install Claude Code (refs #259).
Supersedes #781.
Co-authored-by: FuryNocturn <28540819+FuryNocturn@users.noreply.github.com>
When the graphics can't start the window, the app shows why in the start-failure dialog instead of crashing: a panic before the first frames were shown is reported like any other start failure.
The window opens on Macs whose Metal compiler rejects the shader language version wgpu takes from the macOS version: a patched wgpu-hal 30.0.1 (identical to the released crate except for this probe) compiles a tiny kernel with each version up to the OS's and keeps the first one accepted. A lost device on a Mac no longer points at the Windows-only software renderer setting (fixes#742).
Each Claude Code AI can have its own folder (CLAUDE_CONFIG_DIR) in Settings → AI or with craft-anything-cli ai folder, so each can use a different account; the sign-in check, runs and sessions use that folder.
GitHub Copilot CLI can be a coding agent over ACP, with its models chosen through the shared agent model catalogue; options that could bypass the app's tool restrictions are refused, and agents share investigation findings safely.
On Linux a switched-off screen (a closed laptop lid) no longer counts as the one the GPU drives, and PCI ids pick a card only when no other card shares them (follow-up to #659).
On Linux the window is drawn on the GPU that drives the screen (the built-in panel's, or the only one with displays), so laptops with two GPUs open fast and don't lag; WGPU_ADAPTER_NAME and WGPU_POWER_PREF still decide (fixes#571). Replays #578.
Co-authored-by: Thân Minh Nghĩa <thanminhnghia3@gmail.com>
Replays #576, #577, #581, #589, #624, #625 and #628. Builder steps stop after 25 failed builds in a row, OpenRouter tool requests ask for a provider that supports tools, a start that never opened a window draws in software next time, spinners stop redrawing every frame, local builders get a lean tool list, lldb call observation works and reports failures, and LM Studio is found on other ports.
Co-authored-by: Fábio Soares <fabiodev1123@gmail.com>
Supersedes #216. A prompt brought back with Up keeps the pictures it was sent with. feed.json moves to version 3: a User item with pictures is saved as {text, pictures}, one without stays a plain string, so older files read as before. Picture paths are absolute, so they don't come back after the project is moved.
Co-authored-by: muraa-p <muraa-p@users.noreply.github.com>
runtime_captures_compare's left and right parameters are declared as a string or an object instead of a boolean schema, which made Claude Code drop every tool from the MCP server; on the command line a JSON object passed to them stays an object.
Fixes#522. On Windows the app draws with the DX12 shader compiler that ships with Windows (FXC) unless WGPU_DX12_COMPILER says otherwise, and a lost graphics device says how to draw without the graphics card (CRAFT_ANYTHING_RENDERER=software).
On Windows the app starts only DX12 by default, since starting Vulkan crashed on some Intel drivers before any window opened; WGPU_BACKEND still picks others. Fixes#394.
Claude's effort goes up to xhigh and max. A model without a level gets the nearest one below it. The level is chosen in Settings → AI or with craft-anything-cli ai effort, and over SSH it reaches the other computer. R2.9.
`craft-anything-cli capabilities` lists each tool with `available`, `needs_target` and `reason`. To show target tools as usable before anything is open, it marked every target tool available and dropped its reason. That also covered tools Clean room refuses, so in Clean room `native_function_pseudocode` read as available with no reason, though the engine refuses it.
Only the "nothing is open yet" refusal is waived now. A target tool the mode refuses keeps `available: false` and its Clean room reason, with `needs_target: true` as before. In Deep mode nothing changes.
**Verified:** a new CLI test runs `capabilities` in Clean room (the tool is unavailable with a reason) and with `--deep` (available, no reason). `cargo test -p craft-anything-cli` and clippy pass.
Fixes#249
The adapter ranking is (GL last, fastest device first, DX12 before Vulkan), so a GPU offered over both backends starts on DX12, out of reach of Vulkan overlays, while a real Vulkan GPU still beats Windows' software renderer.
eframe starts every wgpu backend before an adapter is picked, and starting GL loads the system's OpenGL driver; Intel's ig9icd64.dll crashed in it (0xc0000005), so the app vanished with no window or error box. Windows now starts the primary backends only (DX12 with WARP, Vulkan); WGPU_BACKEND still decides when set.
Fixes#196
When the window can't start, the app shows an error box with the reason, a hint to update the graphics driver and where desktop.log is, instead of exiting with nothing on screen. For #166, #104, #74 and #33.
Settings → AI shows each AI's model with Change…, listing the API's own models or Claude's models for Claude Code; craft-anything-cli ai model <name> [model] lists or sets it. Fixes#123 and #127.
Settings → AI gets an Add an AI by its address form; AiHub::add_server asks the server for its models before adding it and picks one that can chat when none is named; ai add --kind openai_compatible --base-url without --model does the same. Fixes#54, #98 and #128.
On macOS the window gets an empty icon, which keeps the bundle's icon (padded to Apple's icon grid) instead of replacing it with the full tile. Fixes#102.