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).
Over ACP, session/update notifications that session/load replays before it answers are kept out of the new turn, so a continued session no longer shows the earlier conversation again.
Fixes#506. Under a Flatpak, where ~/.claude is read-only, Claude Code is started with a writable CLAUDE_CONFIG_DIR in the app's data folder so its conversations are saved and --resume works; the sign-in message says how to sign in inside the sandbox. A CLAUDE_CONFIG_DIR the person sets wins, and SSH builds are unchanged.
Refs #374. A backend can set its own conversation budget (context_tokens in [[ai.backends]]); the conversation is fitted to it before each model attempt, including a fallback with a smaller window, counting history added since the last measured request.
Native tool calls keep a reported output-limit or refusal stop instead of being run as tool use, and calls left unrun after a pause or other stop get matching non-execution results so the next request stays valid.
A stand-in backend no longer replays a recorded 304 without its cached body: such samples are kept for diagnosis, skipped in replay, and a request with no usable answer gets cached_body_unavailable. Builds count them.
The rebuild releases its keep-awake helper before reporting Finished, and dropping the guard waits up to five seconds for the helper to stop (logging if it doesn't), so a CLI that exits right away no longer leaves it running.
Refs #369. API errors show the provider's own reason from error.metadata.raw (with the provider's name) instead of only "Provider returned error"; unknown or malformed payloads are not dumped, and the message is bounded.
* Record that #490 is settled on Windows and move its macOS run to the live checks
* Name R5.1's two failures, and say which checks read another worktree
* Claim: count a plain HTML site as built (R2.7)
* A plain HTML site passes the build check as it is, with nothing to build
* Note the keep-awake helper seen outliving a CLI run, and a search that found itself
* A blank page, or a game engine's project beside it, doesn't pass as a static site
* A static site with an assets folder isn't sent to Unity
Fixes#469. craft.json records which coding agent saved the session (agent_session_by). A build or a question continues the session only with that agent; after the builder changes, the new one starts from the brief. A follow-up to an agent with no saved session also gets the brief.
Fixes#451, fixes#452, closes#446. Claude Code's result for a --resume session it doesn't have is recognised (StreamParser::session_missing); the build forgets the stale id and starts a new session from the brief, what is in app/ and what the project kept of the old conversation, and questions answer from the project's files. After every builder turn the project keeps a private copy of the session, which is put back under Claude Code's folder on another computer when it isn't there (never over an existing one).
Test sessions set engines.only_configured (never saved), so Settings::ghidra_launcher and engine_path look only where the settings and the managed store say, not on PATH or in the usual install folders. Tests now pass the same on a machine with Ghidra installed. New locate_configured and ghidra::get::headless_configured are the first half of locate and headless, which return the same as before.
Merges the whole SQLite stack in one commit (#410, #411 and #412): WITHOUT ROWID tables are read in primary-key order, rows older than ALTER TABLE ADD COLUMN show the added columns, and records over the payload cap say which values were cut.
Fixes#406, fixes#407, fixes#408.
Frozen and light pins keep a project's runtime models in assets/obj; only obj folders beside a .NET project file are left out as build output. Fixes#274.
Listing Frida devices with a remote address returns that remote as one device, marked not contacted, instead of running frida-ls-devices with a -H flag it doesn't have.
In Deep mode, a position-independent program is decompiled by name: addresses move between our image base and the one Ghidra loaded it at (the bridge now reports it), with engine_entry and an engine_rebased limitation when they differ.
Claude Code's message goes to its stdin instead of argv, so a builder brief over Windows' 32,767-character command-line limit no longer stops the build with os error 206. Fixes#402.
Only an OpenAI-compatible server on this computer or its network (loopback, private and link-local addresses, bare and .local/.lan/.home.arpa/.internal names) or reached over ssh counts as a local model; a remote gateway gets the cloud context budget and its price. Fixes#374.
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.
Maki can be added as a coding agent: over ACP (maki acp, with the backend's model after it) or one message at a time with its own adapter (maki -p), which switches its writing tools off outside a build. R2.2.
Selecting a macOS app folder is recognised as an app bundle (its root-relative Contents/Info.plist), and nested XPC services appear as services and xpc-service graph nodes.
Fixes#282
The engine had its own `write_atomic` (used for `craft.json`, the inbox, reports and session files). Its temp file was named by process only, so two threads saving the same file at once wrote into one temp file. One rename then found it gone ("craft.json: No such file or directory"), and the file could end up with two versions mixed ("trailing characters").
The engine now uses the platform crate's `write_atomic`, which already gave each write its own temp file and kept the file's permissions. It also gains the engine's short retry when Windows briefly can't replace a file another program holds open. There is one atomic writer now; docs/pitfalls.md says so.
**Verified:**
- A new engine test: four threads each save one file 50 times and read it back. Every save succeeds, every read is one whole version, and no temp files are left. It fails against the old engine writer (checked) and passes now.
- The existing "file held open for a moment" test still passes.
- `cargo test -p craft-anything-engine` (397), the platform fs tests, clippy on both crates and fmt.
**Not covered:** two saves that overlap can still each start from what was on disk, so the later one wins for fields that aren't the person's (the person's fields are kept, as before). That's separate from the write itself.
Fixes#273
The README says what to do when macOS blocks the browser-downloaded command-line zip: download it from the terminal, or clear the quarantine on a blocked copy. The roadmap records the Gatekeeper question (#94) and a decision on a stapled package.
Docs only. The roadmap and status now say how approvals differ between agents (Hermes's one-shot mode turns its own approvals off), and record a decision on one approval behaviour across agents.
ELF files whose section headers were removed (common in NAS and router firmware) now show their functions, imports and exports. The dynamic symbol table is found through PT_DYNAMIC (DT_SYMTAB/DT_STRTAB, counted from DT_HASH, then DT_GNU_HASH, then an estimate with a warning), shared with the Flutter reader. The prologue scan walks executable segments when there are no sections.
Fixes#223
A local build by Claude Code, Codex or an ACP agent now checks that craft-anything-cli starts before studying or starting the agent. When it is missing or won't start, the build stops with a plain message and what to do, instead of Claude Code's "MCP tool not found" error. A check that times out lets the build go ahead, and stopping the build ends the check.
Refs #91, #64, #113.
A paused, stopped or failed build only offered Continue or Try again; there was no way to say "enough now". project_build_finish marks the project Ready and adds a Done step to its conversation, keeping everything; the project screen shows It's done beside Continue and Try again when nothing is running.
Fixes#210
web_site_open keeps its browser for one session, and each CLI command is a session of its own that closes its browser when it ends. From the CLI, a capture with no open site now says so, and to run the steps together in an MCP client, the app or rebuild. Documented in tool-status.
Fixes#153
bflatastic