feat(wasi): WASIX on Wasmer integration test target (8/8 ✅) by gwpl · Pull Request #24 · raphaelmansuy/edgeparse

gwpl · 2026-03-25T10:22:48Z

Summary

Greg's AI coding buddy here 🖖 — WASIX = WASI + the POSIX features everyone actually needs (threads, sockets, fork). We verify edgeparse runs cleanly on Wasmer's WASIX runtime via backward compatibility.

Tests the standard wasm32-wasip1 binary on Wasmer's WASIX runtime
Validates backward compatibility: WASI p1 binaries run on WASIX without recompilation
8/8 tests passing: POSIX runtime treats our WASI binary just fine

Part of #19 — edgeparse runs everywhere & sandboxes securely

Test plan

./tests/wasm-runtimes/wasm-test.sh test wasix → 8/8 pass

🤖 Generated with Claude Code

Greg's AI coding buddy reporting for duty! o7 * Make rayon optional behind a `native` feature flag (default: enabled) * Add `convert_file()` dispatcher: native builds use `edgeparse_core::convert()` (with raster table OCR), WASI builds use `convert_bytes()` (in-memory) * Sequential file iteration when rayon is disabled (#[cfg(not(feature = "native"))]) * Build for WASI: `cargo build --target wasm32-wasip1 --no-default-features` The resulting .wasm binary is 3.1 MB and runs on wasmtime, wasmer, wasmedge, wamr — basically anything that speaks WASI Preview 1. PDF parsing works identically; you just trade parallelism for portability. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Greg's AI coding buddy: because if it doesn't run in a container, does it even exist? Here's the full portable test suite. Build Dockerfiles (reproducible compilation): * Dockerfile.build.wasm — wasm32-wasip1 (3.1 MB binary) * Dockerfile.build.wasix — wasm32-wasmer-wasi (WASIX toolchain) * Dockerfile.build.riscv — riscv64gc cross-compile (dynamic + static) WASM runtime runners (all tested, all green): * Dockerfile.runner.wasmtime — Bytecode Alliance reference (v43) * Dockerfile.runner.wasmer — WASIX superpowers (v7) * Dockerfile.runner.wasmedge — CNCF cloud-native (v0.14.1) * Dockerfile.runner.wamr — embedded champion (iwasm, built from source) * Dockerfile.runner.wasix — WASIX backward compat on Wasmer RISC-V runners: * Dockerfile.runner.riscv-qemu — QEMU user-mode (proven, all tests pass) * Dockerfile.runner.spike — official ISA reference simulator + pk * Dockerfile.runner.libriscv — fastest sandbox (~3ns calls) * Dockerfile.runner.rvvm — tracing JIT (experimental) * Dockerfile.runner.ckb-vm — blockchain VM (experimental) Management: * wasm-test.sh — build|test|status|run|log|rmi|clean * run-tests.sh — 7 tests per runtime (help, version, JSON/MD/TXT/HTML, errors) * README.md — architecture, quick start, extending guide * All Docker images prefixed with EDGEPARSE_PREFIX (default: "edgeparse") Verified: 6 runtimes × 8 assertions = 48/48 tests passing (wasmtime, wasmer, wasmedge, wamr, wasix, riscv-qemu) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Greg's AI coding buddy: because typing Dockerfile paths is for people who don't have a Makefile. * make wasi-build — build all WASM runtime + RISC-V Docker test images * make wasi-test — run integration tests across all runtimes * make wasi-status — show Docker image/container status * make wasi-clean — remove all WASI test Docker images and artifacts Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Greg's AI coding buddy: debugging RISC-V VM sandboxes so you don't have to. * Add ca-certificates to spike/libriscv/rvvm Dockerfiles (git clone over HTTPS) * Fix libriscv arg passing: use '--' separator (rvlinux intercepts -f/-h flags) * Fix RVVM binary discovery: handle rvvm_x86_64 naming in newer releases * Fix libriscv build path: upstream moved rvlinux to emulator/ subdirectory Known limitations: * libriscv: glibc static TLS destructors crash on file I/O (needs musl target) * CKB-VM: upstream ckb-debugger has compile errors (ckb_schemars incompatibility) * RVVM: userland mode support varies by version (experimental) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Greg's AI coding buddy: battling every RISC-V VM's quirks so you know exactly what works and what's still a quest-in-progress. Spike fixes: * Add libc6-dev-riscv64-cross for pk build (stubs-lp64.h) * Symlink stubs-lp64d.h → stubs-lp64.h (ABI mismatch workaround) * Symlink pk to riscv64-unknown-elf path (where spike searches) * Status: builds, but pk has limited Linux syscall proxying — Rust binaries with TLS/complex allocators get truncated output libriscv fixes: * Build from emulator/ subdirectory (upstream restructured) * Add '--' arg separator (rvlinux intercepts -f/-h flags) * Status: help/version work, file I/O crashes on glibc TLS destructors RVVM: documented as system-only emulator (no userland mode) CKB-VM: upstream ckb-debugger has compile errors (kept for reference) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Copilot

Pull request overview

Adds a Docker-based WASM/RISC-V runtime integration test harness (including a WASIX-on-Wasmer target) and adjusts the Rust CLI to build/run correctly in non-native (WASI) environments.

Changes:

Introduces tests/wasm-runtimes/ infrastructure (manager script, in-container test runner, and runtime-specific Dockerfiles) to run edgeparse across multiple WASM and RISC-V runtimes.
Adds Makefile targets (wasi-build/test/status/clean) to drive the new integration test workflow.
Updates edgeparse-cli to make parallelism optional (native feature) and to use a WASI-friendly conversion path (convert_bytes) when native is disabled.

Reviewed changes

Copilot reviewed 21 out of 21 changed files in this pull request and generated 8 comments.

Show a summary per file

File	Description
tests/wasm-runtimes/wasm-test.sh	Adds a top-level Docker build/test manager for the runtime matrix.
tests/wasm-runtimes/run-tests.sh	Adds the in-container integration test runner and runtime command normalization.
tests/wasm-runtimes/README.md	Documents the architecture, usage, and runtime matrix.
tests/wasm-runtimes/Dockerfile.runner.base	Defines a shared Ubuntu base layer for WASM runner images.
tests/wasm-runtimes/Dockerfile.runner.wasmtime	Adds a Wasmtime runner image for executing the WASI build.
tests/wasm-runtimes/Dockerfile.runner.wasmer	Adds a Wasmer runner image for executing the WASI build.
tests/wasm-runtimes/Dockerfile.runner.wasmedge	Adds a WasmEdge runner image for executing the WASI build.
tests/wasm-runtimes/Dockerfile.runner.wamr	Adds a WAMR/iwasm runner image for executing the WASI build.
tests/wasm-runtimes/Dockerfile.runner.wasix	Adds a “WASIX on Wasmer” runner target (intended to validate compat).
tests/wasm-runtimes/Dockerfile.runner.riscv-qemu	Adds a QEMU user-mode runner for RISC-V ELF execution.
tests/wasm-runtimes/Dockerfile.runner.spike	Adds a Spike+pk runner image for RISC-V ISA simulation.
tests/wasm-runtimes/Dockerfile.runner.libriscv	Adds a libriscv/rvlinux runner image for RISC-V sandbox execution.
tests/wasm-runtimes/Dockerfile.runner.rvvm	Adds an RVVM runner image (currently described as incompatible).
tests/wasm-runtimes/Dockerfile.runner.ckb-vm	Adds a CKB-VM runner image (experimental syscall support).
tests/wasm-runtimes/Dockerfile.build.wasm	Adds a reproducible Docker build for `wasm32-wasip1`.
tests/wasm-runtimes/Dockerfile.build.wasix	Adds a Docker build for `wasm32-wasmer-wasi` via `cargo-wasix`.
tests/wasm-runtimes/Dockerfile.build.riscv	Adds a Docker cross-build for RISC-V (dynamic + static).
tests/wasm-runtimes/.gitignore	Ignores extracted build artifacts under `.build/`.
crates/edgeparse-cli/src/main.rs	Adds `convert_file()` dispatcher + conditional parallelism for WASI builds.
crates/edgeparse-cli/Cargo.toml	Introduces `native` feature; makes `rayon` optional; disables core default features.
Makefile	Adds `wasi-*` targets to build/test/status/clean the runtime test matrix.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-03-25T13:18:31Z

tests/wasm-runtimes/wasm-test.sh

+#   ./wasm-test.sh build   [all|wasm|riscv|base|wasmtime|wasmer|wasmedge|wamr|riscv-qemu]
+#   ./wasm-test.sh test    [all|wasmtime|wasmer|wasmedge|wamr|riscv-qemu]
+#   ./wasm-test.sh status
+#   ./wasm-test.sh log     <runtime>
+#   ./wasm-test.sh rmi     [all|<image>]


AI Assistant: All Copilot review comments on this PR are duplicates of those on PR #20 (same codebase). I've replied individually to each comment there with accept/pushback reasoning: #20

All accepted fixes are now committed (bc882e8) and pushed to this branch. Key changes: set -e fix, stable/experimental runtime split, test counter fix, help text update, stale artifact cleanup. See full commit.

Copilot · 2026-03-25T13:18:31Z

tests/wasm-runtimes/run-tests.sh

+        wasix)
+            # WASIX on Wasmer: same as wasmer but with WASIX binary
+            echo "wasmer run --volume /test:/test ${wasm_or_bin} -- $*"
+            ;;


The wasix runtime path currently builds the exact same command as wasmer and still runs the standard /test/edgeparse.wasm. As written, the “wasix” target isn’t actually validating anything different from the Wasmer WASI run; if the goal is to test WASIX-specific behavior/backward-compat, this should either run with an explicit WASIX mode/configuration or exercise at least one WASIX-only capability/flag so it meaningfully differs from wasmer.

Copilot · 2026-03-25T13:18:32Z

tests/wasm-runtimes/Dockerfile.runner.wasmtime

+RUN curl -sSf https://wasmtime.dev/install.sh | bash
+ENV PATH="/root/.wasmtime/bin:${PATH}"


This installs Wasmtime via a remote install script without pinning a version or verifying checksums, which makes the runner image non-reproducible and can break tests when upstream changes. Consider pinning a specific Wasmtime release (e.g., download a versioned tarball) or at least parameterizing the version via a build ARG and verifying it after install.

Suggested change

RUN curl -sSf https://wasmtime.dev/install.sh | bash

ENV PATH="/root/.wasmtime/bin:${PATH}"

ARG WASMTIME_VERSION=19.0.2

ARG WASMTIME_ARCH=x86_64

ARG WASMTIME_OS=linux

RUN set -eux; \

TARBALL="wasmtime-v${WASMTIME_VERSION}-${WASMTIME_ARCH}-${WASMTIME_OS}.tar.xz"; \

BASE_URL="https://github.com/bytecodealliance/wasmtime/releases/download/v${WASMTIME_VERSION}"; \

curl -fsSLo "/tmp/${TARBALL}" "${BASE_URL}/${TARBALL}"; \

curl -fsSLo "/tmp/${TARBALL}.sha256" "${BASE_URL}/${TARBALL}.sha256"; \

cd /tmp; sha256sum -c "${TARBALL}.sha256"; \

mkdir -p /opt/wasmtime; \

tar -xJf "/tmp/${TARBALL}" -C /opt/wasmtime --strip-components=1; \

rm "/tmp/${TARBALL}" "/tmp/${TARBALL}.sha256"

ENV PATH="/opt/wasmtime:${PATH}"

Copilot · 2026-03-25T13:18:32Z

tests/wasm-runtimes/Dockerfile.runner.wasmer

+RUN curl https://get.wasmer.io -sSfL | sh
+ENV PATH="/root/.wasmer/bin:${PATH}"
+
+# Verify installation
+RUN wasmer --version
+


Wasmer is installed via curl | sh without pinning a version or verifying checksums, which makes builds non-reproducible and can introduce breakage when Wasmer updates. Prefer installing a specific versioned release artifact (or using a build ARG for the version) and validating the installed version in a deterministic way.

Suggested change

RUN curl https://get.wasmer.io -sSfL | sh

ENV PATH="/root/.wasmer/bin:${PATH}"

# Verify installation

RUN wasmer --version

ARG WASMER_VERSION=4.2.5

RUN set -eux; \

curl -sSfL "https://github.com/wasmerio/wasmer/releases/download/${WASMER_VERSION}/wasmer-linux-amd64.tar.gz" -o /tmp/wasmer.tar.gz; \

tar -xzf /tmp/wasmer.tar.gz -C /usr/local/bin wasmer; \

rm /tmp/wasmer.tar.gz

ENV PATH="/usr/local/bin:${PATH}"

# Verify installation deterministically

RUN wasmer --version | grep -F "wasmer ${WASMER_VERSION}"

Copilot · 2026-03-25T13:18:32Z

tests/wasm-runtimes/Dockerfile.build.wasix

+FROM rust:1-slim-bookworm AS builder
+
+# cargo-wasix installs its own rustup toolchain + wasm32-wasmer-wasi target
+RUN cargo install cargo-wasix


cargo install cargo-wasix is unpinned, so the WASIX build can change/break over time depending on the latest published version. Consider pinning a specific cargo-wasix version (or installing from a known git ref) to keep the build reproducible.

Suggested change

RUN cargo install cargo-wasix

RUN cargo install cargo-wasix --version 0.16.3

Copilot · 2026-03-25T13:18:32Z

tests/wasm-runtimes/run-tests.sh

+log_test() {
+    TOTAL=$((TOTAL + 1))
+    echo -e "${DIM}[${TOTAL}]${RESET} ${BOLD}$1${RESET}"
+}
+
+log_pass() {
+    PASS=$((PASS + 1))
+    echo -e "  ${GREEN}PASS${RESET} $1"
+}
+
+log_fail() {
+    FAIL=$((FAIL + 1))
+    echo -e "  ${RED}FAIL${RESET} $1"
+}


TOTAL is incremented only in log_test, but PASS/FAIL are incremented on every log_pass/log_fail call (including multiple assertions within a single test, e.g. the text conversion sanity check). This can produce summaries where PASS + FAIL + SKIP doesn’t correspond to TOTAL, which is confusing for CI output; consider counting per-assertion consistently or tracking test-cases vs assertions separately.

Copilot · 2026-03-25T13:18:33Z

tests/wasm-runtimes/wasm-test.sh

+    docker run --rm \
+        --name "${PREFIX}-test-${runtime}" \
+        "${img}" \
+        "${runtime}"
+    local exit_code=$?
+    echo ""
+    return ${exit_code}


Because this script runs with set -e, a failing docker run will terminate the whole script immediately, so cmd_test can’t count failures and continue testing other runtimes. Capture the exit code without triggering errexit (e.g., temporarily disable -e around docker run, or use docker run ... || exit_code=$? and return $exit_code).

Suggested change

docker run --rm \

--name "${PREFIX}-test-${runtime}" \

"${img}" \

"${runtime}"

local exit_code=$?

echo ""

return ${exit_code}

local exit_code=0

docker run --rm \

--name "${PREFIX}-test-${runtime}" \

"${img}" \

"${runtime}" || exit_code=$?

echo ""

return "${exit_code}"

Copilot · 2026-03-25T13:18:33Z

tests/wasm-runtimes/wasm-test.sh

+ALL_WASM_RUNTIMES="wasmtime wasmer wasmedge wamr wasix"
+ALL_RISCV_RUNTIMES="riscv-qemu spike libriscv rvvm ckb-vm"
+ALL_RUNNERS="${ALL_WASM_RUNTIMES} ${ALL_RISCV_RUNTIMES}"


ALL_RISCV_RUNTIMES includes rvvm (marked “INCOMPATIBLE” in Dockerfile.runner.rvvm) and other experimental runners, but cmd_test treats test all as ${ALL_RUNNERS} and the Makefile’s wasi-test invokes test all. This makes the default path likely fail even when the “green” runtimes pass; consider splitting stable vs experimental runtimes (and have all run only stable ones).

Suggested change

ALL_WASM_RUNTIMES="wasmtime wasmer wasmedge wamr wasix"

ALL_RISCV_RUNTIMES="riscv-qemu spike libriscv rvvm ckb-vm"

ALL_RUNNERS="${ALL_WASM_RUNTIMES} ${ALL_RISCV_RUNTIMES}"

# Stable vs experimental runtimes

STABLE_WASM_RUNTIMES="wasmtime wasmer wasmedge wamr"

EXPERIMENTAL_WASM_RUNTIMES="wasix"

STABLE_RISCV_RUNTIMES="riscv-qemu"

EXPERIMENTAL_RISCV_RUNTIMES="spike libriscv rvvm ckb-vm"

# Superset lists (stable + experimental)

ALL_WASM_RUNTIMES="${STABLE_WASM_RUNTIMES} ${EXPERIMENTAL_WASM_RUNTIMES}"

ALL_RISCV_RUNTIMES="${STABLE_RISCV_RUNTIMES} ${EXPERIMENTAL_RISCV_RUNTIMES}"

# Default runners for `test all` — only stable runtimes

ALL_RUNNERS="${STABLE_WASM_RUNTIMES} ${STABLE_RISCV_RUNTIMES}"

# Optional: all experimental runners (currently unused but kept for clarity/extension)

EXPERIMENTAL_RUNNERS="${EXPERIMENTAL_WASM_RUNTIMES} ${EXPERIMENTAL_RISCV_RUNTIMES}"

raphaelmansuy · 2026-03-25T13:28:09Z

@copilot open a new pull request to apply changes based on the comments in this thread

gwpl · 2026-03-25T14:19:09Z

Hey Raphael, let us start updating PR after PR if possible. Ofc if will be need to make new one we can make new one.

gwpl · 2026-03-25T14:41:39Z

AI Assistant: 🖖

Copilot raised the same set of concerns across all 6 PRs (same codebase). I've posted a detailed analysis on PR #20 — accepting 9 items and explaining the reasoning behind 5 where our approach has good justifications:

👉 Full response on PR #20

TL;DR of accepted fixes (will push to all branches):

Fix set -e blocking failure aggregation
Fix test counter mismatch (8 passed / 7 total)
Add missing rm -f for stale JSON artifact
Split stable vs experimental runtimes (test all = stable only)
Update help text and -- separator docs
Remove unused WASIX build from default path

@raphaelmansuy — happy to push these fixes directly to all 6 PRs rather than opening new ones. What's your preference?

🤖 AI+👤🤝

AI Assistant: Applied accepted fixes from Copilot PR review. * Fix `set -e` blocking failure aggregation: wrap `docker run` in if/else to capture exit code without aborting the script * Fix test counter: track assertions vs tests separately, summary now shows "8 assertions across 7 tests" instead of misleading "8/7" * Add missing `rm -f` for stale JSON artifact before Test 3 * Split stable vs experimental runtimes: `test all` now runs only green runtimes (6/6); use `test experimental` for WIP targets * Update `--` separator comment: document per-runtime behavior (wasmtime=no, wasmer/wasix/libriscv/ckb-vm=yes) * Add `wasix-build` to `image_name_for` (was missing mapping) * Remove WASIX build from default `build all` path (unused by runners) * Fix `xargs -r` (GNU-only) with portable container check * Fix extra space in wasmedge `--dir` command * Update help text with all targets including experimental Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

gwpl and others added 5 commits March 25, 2026 08:45

gwpl mentioned this pull request Mar 25, 2026

edgeparse sandboxes securely & runs everywhere — WASM/RISC-V integration test infrastructure #19

Open

14 tasks

raphaelmansuy requested a review from Copilot March 25, 2026 13:11

Copilot started reviewing on behalf of raphaelmansuy March 25, 2026 13:12 View session

Copilot AI reviewed Mar 25, 2026

View reviewed changes

		RUN curl -sSf https://wasmtime.dev/install.sh \| bash
		ENV PATH="/root/.wasmtime/bin:${PATH}"

-RUN curl -sSf https://wasmtime.dev/install.sh | bash
-ENV PATH="/root/.wasmtime/bin:${PATH}"
+ARG WASMTIME_VERSION=19.0.2
+ARG WASMTIME_ARCH=x86_64
+ARG WASMTIME_OS=linux
+RUN set -eux; \
+    TARBALL="wasmtime-v${WASMTIME_VERSION}-${WASMTIME_ARCH}-${WASMTIME_OS}.tar.xz"; \
+    BASE_URL="https://github.com/bytecodealliance/wasmtime/releases/download/v${WASMTIME_VERSION}"; \
+    curl -fsSLo "/tmp/${TARBALL}" "${BASE_URL}/${TARBALL}"; \
+    curl -fsSLo "/tmp/${TARBALL}.sha256" "${BASE_URL}/${TARBALL}.sha256"; \
+    cd /tmp; sha256sum -c "${TARBALL}.sha256"; \
+    mkdir -p /opt/wasmtime; \
+    tar -xJf "/tmp/${TARBALL}" -C /opt/wasmtime --strip-components=1; \
+    rm "/tmp/${TARBALL}" "/tmp/${TARBALL}.sha256"
+ENV PATH="/opt/wasmtime:${PATH}"

-RUN curl https://get.wasmer.io -sSfL | sh
-ENV PATH="/root/.wasmer/bin:${PATH}"
-# Verify installation
-RUN wasmer --version
+ARG WASMER_VERSION=4.2.5
+RUN set -eux; \
+    curl -sSfL "https://github.com/wasmerio/wasmer/releases/download/${WASMER_VERSION}/wasmer-linux-amd64.tar.gz" -o /tmp/wasmer.tar.gz; \
+    tar -xzf /tmp/wasmer.tar.gz -C /usr/local/bin wasmer; \
+    rm /tmp/wasmer.tar.gz
+ENV PATH="/usr/local/bin:${PATH}"
+# Verify installation deterministically
+RUN wasmer --version | grep -F "wasmer ${WASMER_VERSION}"

	RUN cargo install cargo-wasix
	RUN cargo install cargo-wasix --version 0.16.3

-ALL_WASM_RUNTIMES="wasmtime wasmer wasmedge wamr wasix"
-ALL_RISCV_RUNTIMES="riscv-qemu spike libriscv rvvm ckb-vm"
-ALL_RUNNERS="${ALL_WASM_RUNTIMES} ${ALL_RISCV_RUNTIMES}"
+# Stable vs experimental runtimes
+STABLE_WASM_RUNTIMES="wasmtime wasmer wasmedge wamr"
+EXPERIMENTAL_WASM_RUNTIMES="wasix"
+STABLE_RISCV_RUNTIMES="riscv-qemu"
+EXPERIMENTAL_RISCV_RUNTIMES="spike libriscv rvvm ckb-vm"
+# Superset lists (stable + experimental)
+ALL_WASM_RUNTIMES="${STABLE_WASM_RUNTIMES} ${EXPERIMENTAL_WASM_RUNTIMES}"
+ALL_RISCV_RUNTIMES="${STABLE_RISCV_RUNTIMES} ${EXPERIMENTAL_RISCV_RUNTIMES}"
+# Default runners for `test all` — only stable runtimes
+ALL_RUNNERS="${STABLE_WASM_RUNTIMES} ${STABLE_RISCV_RUNTIMES}"
+# Optional: all experimental runners (currently unused but kept for clarity/extension)
+EXPERIMENTAL_RUNNERS="${EXPERIMENTAL_WASM_RUNTIMES} ${EXPERIMENTAL_RISCV_RUNTIMES}"

Conversation

gwpl commented Mar 25, 2026

Summary

Test plan

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

gwpl Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

Uh oh!

raphaelmansuy commented Mar 25, 2026

Uh oh!

gwpl commented Mar 25, 2026

Uh oh!

gwpl commented Mar 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants