subagent transcript

You are working on the FreeCAD -> WebAssembly port. Ground EVERYTHING in the real code; do not guess. - Source tree: /home/magik6k/lcad-wasm/freecad-port/FreeCAD (git branch wasm-port). CMake build dir (out-of-source, already configured): /opt/toolchains/src/freecad-gui-build — read /opt/toolchains/src/freecad-gui-build/CMakeCache.txt for BUILD_* flags and dep paths. Build binary: bin/FreeCAD.wasm (~180 MB). - Toolchain: emscripten, ASYNCIFY + JS exceptions (-fexceptions), SINGLE-THREADED (no pthreads). Static CPython 3.14 + static Qt 6.11 (wasm) + static OCCT + static Coin3D. Everything is statically linked; there is NO dlopen — Python C-extension modules are registered statically via PyImport_AppendInittab in the generated file src/Main/WasmInittab.cpp / WasmInittabGui.cpp (see also freecadWasmRegisterInittab in src/Main/MainGui.cpp). - CRITICAL wasm constraints you MUST check for and design around: (1) THREADING HANGS: any std::thread ctor / std::async(default or async policy) / QThreadPool / QtConcurrent / QThread worker HANGS or throws (no pthreads). Fix pattern: force synchronous/deferred on __EMSCRIPTEN__ (e.g. std::launch::deferred), or #ifndef FC_OS_WASM guard the worker and run inline. Example already in-tree: Mod/Sketcher/App/planegcs/GCS.cpp forced std::launch::deferred; App/Application.cpp guards _recomputeThread with #ifndef FC_OS_WASM; Gui/ProgressBar.cpp skips qApp->processEvents() on __EMSCRIPTEN__. (2) MODAL DIALOGS / NESTED EVENT LOOPS: QDialog::exec()/QMessageBox::exec()/QEventLoop::exec() may deadlock under asyncify when driven from outside the main loop. Task-panel (docked, non-modal) dialogs are preferred. (3) Reentrant ccalls from JS during asyncify suspend corrupt state — a QTimer command-pump (/fc-cmd.py) exists for JS->Python. QtWebEngine has NO wasm port (Web workbench / in-app help / real Start page can't use it). (4) Wasm guards used in-tree: __EMSCRIPTEN__ (compiler-provided) and FC_OS_WASM (FreeCAD-defined) — both are defined on wasm. - Built modules today: Part, Sketcher, Material, Start (+ kernel). Everything else is OFF (see BUILD_* in CMakeCache). - PySide/shiboken: FREECAD_USE_PYSIDE=OFF, FREECAD_USE_SHIBOKEN=OFF, PySide6_DIR/Shiboken6_DIR NOTFOUND. Python 'PySide'/'shiboken6' import fails at runtime ("Cannot load shiboken6"). Many workbenches (Draft, BIM, most task dialogs) are Python+PySide and cannot function without it. DELIVERABLES — do BOTH: 1) Write a thorough, concrete, ready-to-apply plan to /home/magik6k/lcad-wasm/porting/<SLUG>/plan.md — include: exact CMake flags/edits, exact source edits (file + before/after or unified-diff snippets precise enough to apply), any NEW files (full contents), external-dependency build recipes (how to build each dep for this emscripten/asyncify toolchain), a threading-hazard list (grep the real files, give file:line + the exact construct + the exact fix), a modal-dialog-hazard list, the PyImport_AppendInittab lines to add, an ordered step list, and an effort/risk estimate. Put any patch files or new-file contents as separate files in that dir too. 2) Return the structured summary (the schema). Keep summary fields concise; the depth goes in plan.md. Your returned text IS the structured object. Be exhaustive and correct — token cost is not a concern. Verify claims against the actual files (use grep/read). If a dependency has no known wasm port, say so plainly and estimate the porting effort. === SYNTHESIS === You have 16 per-item analysis reports (summaries below; full plans are in the listed files, which you should READ for the details that matter): - [pyside-recipe] needs-code | order 60 | 1-2 weeks | Buildable with on-box tools but bespoke: PySide has no upstream wasm path, so drive raw CMake for a dlopen-less static link; libshiboken/libpyside are already thread-safe for single-thread asyncify. (plan: /home/magik6k/lcad-wasm/porting/pyside-recipe/plan.md) - [pyside-integrate] needs-dep-port | order 50 | weeks+ | FreeCAD-side wiring is small and fully specified (2 flags, 2 DIRs, ~5 inittab lines, 3 patches, 2 package shims), but it is blocked on static PySide6/shiboken6 wasm libs that DO NOT EXIST in the toolchain and have never been ported to static+asyncify+no-pthreads — that dependency port is weeks of research-grade work. (plan: /home/magik6k/lcad-wasm/porting/pyside-integrate/plan.md) - [partdesign] config-only | order 1 | hours | Cheapest workbench yet: the wasm build was pre-wired for BUILD_PART_DESIGN (auto inittab + auto link, only requires BUILD_SKETCHER which is ON); zero C++ changes, no threading, and the one real edit is a try/except guard in InitGui.py so the PySide gear/sprocket imports don't abort activation. (plan: /home/magik6k/lcad-wasm/porting/partdesign/plan.md) - [draft] needs-dep-port | order 50 | weeks+ | The 2 C++ files build fine and all 242 .py package trivially, but Draft is unusable (even headless import fails) until PySide6/shiboken and pivy _coin are ported to wasm. (plan: /home/magik6k/lcad-wasm/porting/draft/plan.md) - [measure] config-only | order 1 | hours | Flip BUILD_MEASURE=ON (all wasm inittab/link plumbing already exists) plus a two-line PySide QT_TRANSLATE_NOOP fallback in two Python files; no new deps, no threading/modal hazards. (plan: /home/magik6k/lcad-wasm/porting/measure/plan.md) - [spreadsheet-surface] config-only | order 2 | 1-2 days | Both are C++ workbenches (no PySide, no threads, no dep porting) — enabling them is a CMake/config change: flip two BUILD flags, remove a bogus BUILD_DRAFT gate for Spreadsheet, and add a Surface inittab block. (plan: /home/magik6k/lcad-wasm/porting/spreadsheet-surface/plan.md) - [import-io] config-only | order 2 | hours | Best-case port: OCCT's STEP/IGES/glTF data-exchange toolkits are already built for the wasm/asyncify toolchain and the Import module has zero threading/network/subprocess code, so enabling it is one small CMake dependency patch + inittab registration + reusing the existing /fc-cmd.py file-picker pump …