`runtime_ui_read` with `screenshot: true` returns one on-screen window of the pid as a PNG on macOS 14+, restricted by `window_id` when given. Missing permission, a missing window or a failed capture is a limitation with partial coverage, and no permission dialog opens.
Fixes#248
The DeepSeek Harness row says the macOS run renamed an existing craft-anything MCP registration, because the generated overlay uses the same server name.
`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.
The preamble and task go on stdin instead of the command line, so a multi-line or long task no longer fails in the Windows desktop app's batch launcher.
A saved AI that was turned off or removed no longer gets replaced silently: a notice says which AI builds instead, so a build can't quietly use one the person didn't choose.
The installed skill says that `setup --yes` writes the plain `mcp` command and so drops an `--all-tools` already in an entry; keeping the person's arguments is on the roadmap.
A move that can't pass gives the lock back and says why, tested with a release that works and one that doesn't, and a second reason no longer repeats "could not start Ghidra".
Ubuntu's /usr/bin/chromium-browser is a script that hands over to the snap; the snap is now started directly, with a profile it can use, so a website build gets past Study.
Closes#1054.
A refused move is only waited on when it may pass, and a timeout says what kept it waiting; a lock that can't be released ends the attempt with the reason.
Someone signed in with `grok login` can build with their installed `grok` through ACP, with our approver deciding permission requests. Clean room, deep chat and questions are refused before it starts, because Grok can't keep to them; only Grok's sessions send `"type": "stdio"`.
A new build taking over a stale lock moves the project folder aside rather than deleting it, and waits if the move is refused because another Ghidra still has it open.
Closes#951.
Two tests in the ai crate start the craft-anything-cli helper, which `cargo test -p craft-anything-ai` does not build; AGENTS.md now says to build it first.
Closes#1041.
When a server refuses a request and says how big its window is, the agent keeps that size for the backend, makes room to three quarters of it, measured with the server's own count, and asks once more; the error says how to give the model more context.
Closes#962.
Tool calls made natively before a switch to the text protocol are written as `Action:` lines, and a turn with nothing left is dropped, so providers such as Kimi no longer refuse the conversation.
Closes#849.
* A command of several kinds needs each allowed, and an inbox path split by quotes is still the inbox
* A Windows inbox path split by quotes is still the inbox
* A relative path into the inbox, from the project folder or app/, is a system change
* An inbox path written as a PowerShell parameter or with Bash escapes is still the inbox
A saved bare `claude`, or a saved path to the desktop app's own file, goes through the same lookup as the usual name: the real Claude Code when there is one, else a plain error.
The test that a stopped launch takes its descendants with it uses a parent and child started without a shell, so it runs the same on Unix and Windows, and a failed start still stops what it launched.
An Approvals menu beside the builder's-questions switch offers Default, Allow, Ask or Refuse for each kind of action, and `/approvals <kind> <choice>` does the same from the prompt box without sending anything to the builder.
The check for the project's records reads a command with quotes and escapes taken out, as the shell joins them, and any mention of `CRAFT_ANYTHING_AGENT` counts as a system change. docs/claude-code.md says these raise the bar and aren't a wall.
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 valid fenced tool call followed by a summary still isn't run, but the model is now told why and how to send it again, so the build doesn't stop with nothing written.
Without Screen Recording the capture is refused before the program starts, with where to allow it. The name fallback matches whole words and never the system's own windows, and a window that's late gets up to 10 more seconds.
Ghidra's public downloads leave out macOS's native programs, so a Deep build analysed for many minutes and then decompiled nothing. It now stops at once and says which command builds one; an install laid out in a way we don't recognise is left to Ghidra.
The block table parser checks every compressed block against the data region's size, so blocks can't reach into a trailing table or bytes after the declared bundle end.
The OpenCode remote setup test no longer expects one exit code from `command -v` for a missing helper, and runs with private PATH folders so a helper installed on the machine can't hide the failure.
STATUS.md no longer says the project feed, engine installs and launching exist only in the desktop app; it describes the shared tools and their limits.
A saved program path that's gone now goes through the same filtered lookup as every other path, and when only the desktop app's `claude` is on the search path the run stops with a plain error and how to install Claude Code.
The AppImage build uses pinned releases of appimagetool and the runtime, checks each against its SHA-256 and hands appimagetool the checked runtime, so it downloads nothing itself. The four hashes match GitHub's digests for those release assets.