An agent that is saved but switched off is offered again when it's found on the computer, and choosing it turns it on, keeping its program and folder, instead of No coding agent was found staying on screen (refs #423).
Long lines in the feed's tool work stay inside the window: a tool-work row with no tool shows its note's first line, cut to fit, as its title, and the notes below wrap (refs #666).
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.
A program whose file is busy (just written, still open for writing in a child another thread is starting, so Linux says Text file busy) is tried again for about 0.3 s before its start fails. Fixes flaky test failures and a start just after an agent's CLI updates.
A build whose checks keep finding no working build stops after 10 in a row, across Try again presses, until a new request starts the count again (kept in craft.json as not_working_checks), and with app/ empty the builder is asked to write the project and show its build's output instead of fixing a build that doesn't exist (refs #736).
Supersedes #776.
Co-authored-by: Fábio Soares <fabiodev1123@gmail.com>
Chrome, Brave, Chromium and Edge installed as Flatpaks on Linux are found, and a Flatpak or Snap browser keeps its private profile in the home folder its sandbox shares, so it can start and its port can be read (fixes#747).
The README says Clean room isn't an operating-system sandbox, that installing dependencies runs code (and how to avoid npm's install scripts), and how to check that a Mac download is signed and notarized (refs #728).
Parser follow-ups to #722: Java reference searches keep earlier hits and report partial coverage, DEX signed LEB128 takes at most five bytes, legacy AAPT long strings recover within a shared budget, and ext indirect metadata is read within bounds.
The "Where is the program?" picker returned Antigravity.app on a Mac, and the path was saved
as the agent's command (#467). set_command now refuses a folder for a local agent, with a
message that names the command-line program to pick. A folder saved before that is not
started: the usual program name is used, as when none is chosen.
Co-Authored-By: Claude Haiku 5.5 <noreply@anthropic.com>
The keep-awake helper ends by itself once the app it serves is gone (Windows checks the process every 30 s, macOS uses caffeinate -w), so closing the window during a build no longer keeps the computer awake.
A program started by a relative path in another folder is looked up where it starts before it's reported as a path with no file (on Unix, a script there whose interpreter is missing).
A person's own project, edited in place with nothing to recreate, is checked by its own build and then its own tests, in any language a toolchain table knows (Rust, Node.js, Python, Go, .NET, Maven, Gradle, Make), instead of the checks made for a recreation (no --screenshot option, self-test or MECHANICS.md added to their code). A project with no tests, or one Craft Anything doesn't know how to build, isn't a failure and the note says so.
A project edited in place (Work on my project, or rebuild --existing edit) keeps the stack its own files use (an engine's project file, then Cargo.toml or package.json dependencies, then other project files), unless the request names another; a Godot folder no longer gets Unity from a request that reads as a game.
The pasted-picture test accepts a third paste that lands in the same millisecond as the first and takes its freed name, and checks the first paste's content is gone. Test only.
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).
Tool calls a local model writes as fenced JSON after a sentence, or several in one reply, are run when every one names an offered tool; words after the last call, other code or an unclosed fence keep the reply as text.
Send and Make's Start wait for the picture-size checks still running for their own destination, then go with the pictures, instead of leaving them for the next message or starting without them. A refused picture clears the wait, and editing Make meanwhile cancels the waiting Start.
A program started by its path (a saved agent program, say) with no file there says so and names the path, as possibly moved by an update, instead of "isn't installed or isn't on your PATH"; it stays a missing program, so builder turns aren't retried (refs #721).
Ghidra is found where people unzip it (Program Files, the home folder, Downloads, Desktop, /Applications, Homebrew's cask and the usual Linux folders), by folder name a set number of levels down, and the guided install uses a copy already on the computer instead of downloading it again (fixes#740).
When a server reports no input-token count, as local servers often don't, the system prompt and the tool schemas are counted from their text, so a conversation past its budget is trimmed (refs #731).
When a website build leaves app/ empty, the build check says the builder hasn't written the project, instead of only that no built site was found (refs #736).
On Windows, Antigravity's CLI (agy.exe) is also looked for straight in its Antigravity folder, where newer installers put it; the desktop app's own Antigravity.exe is never taken for it (fixes#737).
Leaving "Work on my project" forgets a folder it would edit in place, and a folder dialog that ends after leaving that door is dropped, so a version made on Make can't edit the person's own project. An address in that door's request stays part of the request instead of becoming an original to recreate. Follow-up to #686's review.
The prompt box can grow to two-fifths of the window's height, never less than its own limit, so a long prompt shows more of itself in a tall window (fixes#473).
Settings → AI has an "Another model" field beside the model list, so a newer model, a variant such as opusplan, or one another harness serves can be chosen without the CLI (fixes#470).
An agent's chosen program path that an update moved (Codex's bin/<build>/codex.exe) is found again in the newest build folder, else by its usual name on PATH, instead of failing every turn (refs #721).
* The build check says where a project made one folder down is, and the Rust steps say Cargo.toml goes in app/ itself
* Tick R5.4's nested project line and add the folder mix-up it showed
* Every missing-project note names a project one folder down; only app/ is told its files belong there
The Linux AppImage runs its bundled CLI with --cli as the first argument, or when started through a link named craft-anything-cli, so MCP clients can use it (fixes#723).
Unreal's readiness check finds Visual Studio's C++ tools installed outside Program Files, from the Visual Studio Installer's instance records and a developer shell's VSINSTALLDIR, VCINSTALLDIR or VCToolsInstallDir (fixes#669).
* A builder on a local model isn't told to call memory tools it isn't offered
* Record the first live local builds and what stops them
* Keep R5.3's API-key live check open: the stop was seen on a local build
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.
A picture over 20 MB is refused when it is added (prompt box, drag and drop, Make's picker) with a message, and copy_pictures refuses the whole list before copying anything, instead of dropping it silently when the message is sent.
What Detect found sits under two tabs with counts, Providers (an API key or a local model server) and Harnesses (an installed coding agent), so more providers don't push the coding agents off the screen.
Each paragraph of an agent's answer is laid out as one width-limited text block, keeping bold, inline code and glossary underlines, so a long file link after a glossary term no longer pushes messages under the sidebar (fixes#523).
Moonshot, DeepSeek, xAI, Groq, Mistral, Together, Fireworks and DeepInfra are offered by name when their key is set, from one table of base URLs, key variables and default models.
CRC cpio checksum work shares one byte allowance across a firmware scan and stops when the scan is cancelled; checksum fields must be eight hex digits, and skipped verification is reported (R3.12). Replays #676.
Co-authored-by: Afloat <132809511+Afloat16@users.noreply.github.com>
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.
bflatastic