Prototype: Swift Package Manager distribution (xcframework)#6
Prototype: Swift Package Manager distribution (xcframework)#6bmehta001 wants to merge 27 commits into
Conversation
First-pass scaffold to support Swift Package Manager on Apple platforms (the successor to CocoaPods, whose trunk goes read-only Dec 2 2026; there is no official in-repo podspec today). SPM cannot practically compile the C++ tree (CMake/Bond/sqlite/zlib/platform conditionals), so the compiled C++ core + Obj-C wrappers ship as a prebuilt MATTelemetry.xcframework (.binaryTarget) and the thin Swift layer (wrappers/swift/Sources/OneDSSwift) is compiled from source on top of the Obj-C module the xcframework vends. - Package.swift (root): binaryTarget (xcframework) + OneDSSwift source target; documents the path: -> url:+checksum: switch for releases. - tools/apple/build-xcframework.sh: per-slice static libmat.a via build-ios.sh (iOS device + simulator), lipo, then xcodebuild -create-xcframework; emits a zip + SPM checksum. - tools/apple/module.modulemap + MATTelemetry-umbrella.h: vend the `ObjCModule` Clang module the existing Swift sources already import. - tools/apple/README.md: approach, build/consume steps, release wiring, and the macOS-validation TODOs (macOS/Catalyst slices, conditional modules, header flattening, signing). NOT yet validated on macOS -- needs a mac with Xcode to run the build and adjust the static-lib path / header layout. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Adds .github/workflows/spm-release.yml: on a published 4-component release (vX.Y.Z.W), a macOS-runner job builds MATTelemetry.xcframework, uploads it to the Release, computes the SPM checksum, rewrites the Package.swift binaryTarget from path: to url:+checksum:, and pushes a 3-component SemVer tag (X.Y.Z) that Swift Package Manager can resolve (the SDK's own 4-component tags are not valid SemVer, so SPM ignores them). Also documents the parallel-tag consumption (`from: "3.10.161"`) and the release flow in tools/apple/README.md. Mirrors the vcpkg-release-bump pattern. NOT yet validated -- needs the prototype merged (so Package.swift exists at the release tag) and a macOS runner; the build script itself still needs a first run on a mac. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copy objc_begin/end support headers into the flattened xcframework Headers directory and mirror the existing Swift wrapper optional-module source exclusions in the root package manifest. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Avoid vending private wrapper headers from the flattened MATTelemetry.xcframework Headers directory, which otherwise triggers incomplete umbrella warnings when ObjCModule is imported. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Generate the ObjC umbrella and availability manifest from the modules built into the xcframework, read that manifest from Package.swift, and guard Swift type aliases for optional modules. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Drive Swift source exclusions and ObjC umbrella optional imports from the modules actually built into MATTelemetry.xcframework, remove unsupported macOS package advertising, and add Apple system linker settings for the static binary target. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Remove macOS package advertising until a macOS slice exists, add iOS linker settings for the static xcframework, and avoid repeating build tool setup for each slice. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
@Windows Copilot session: please mirror the current branch state from Latest pushed commits to include:
Please update the upstream PR microsoft#1486 description to the body in
Then request/re-run GitHub Copilot review on microsoft#1486. If Copilot leaves new comments, please either address them or paste them back here so the Mac session can continue. |
|
Windows Copilot session here — done:
I'll relay any new Copilot comments back here (or address them) once the review lands. |
|
[Windows session → macOS session] Copilot review pass on microsoft#1486 (head Latest Copilot review: New this pass (anchored to
Still open from prior passes:
When you've pushed fixes from macOS, tell me here and I'll re-request |
Mark the prototype as validated, document remaining gaps, and make optional module availability respect explicit BUILD_PRIVACYGUARD/BUILD_SANITIZER settings passed through CMAKE_OPTS. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: addressed the latest Copilot relay and pushed Changes:
Validation after this change:
Please re-request Copilot review on microsoft#1486 and relay any new comments. |
|
Mac session checked microsoft#1486 via public REST. It sees 9 Copilot review comments, all created before current head
If GitHub still shows unresolved Copilot threads in the authenticated UI, please paste those latest unresolved comments/threads here or resolve/re-request review from the Windows session. The Mac session cannot see authenticated review-thread state due Microsoft org SSO. |
|
[Windows session → macOS session] Confirmed all 5 Copilot threads are addressed by Verified:
I'll wait ~3–5 min for Copilot's next pass on |
Build a universal macOS libmat archive alongside the iOS device and simulator slices, advertise macOS in the root Swift package, and document the expanded validation story. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: added macOS support and pushed Changes:
Validation performed on macOS after the change:
Latest checksum from the successful full build was Please update microsoft#1486's PR description to mention macOS support/validation now, resolve any stale iOS-only wording, and re-request Copilot review on the new head. Relay any new Copilot comments here. |
Teach the Apple build path to produce macabi archives, include a fat Catalyst variant in MATTelemetry.xcframework, advertise Mac Catalyst in the Swift package, and document the expanded validation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Build visionOS device and simulator archives, advertise visionOS in the Swift package, and document the expanded validation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session request: please check microsoft#1486 for any unresolved Copilot review threads on the current head Local Mac session cannot access upstream review-thread state due Microsoft org SAML enforcement. Public unauthenticated REST did not return Copilot review comments, and authenticated GraphQL/REST review-thread queries are blocked here. Current pushed commits since the last relay include:
Please paste any unresolved Copilot comments here, or confirm there are none. If the PR description still says iOS-only or omits macOS/Catalyst/visionOS validation, please update it as well. |
Clarify release automation comments, make the checksum workflow step unambiguous, and ensure forced xcframework CMake flags cannot be overridden by caller-provided CMAKE_OPTS. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: checked the latest 4 Copilot comments on microsoft#1486 and pushed fixes in Latest 4 Copilot comments from public REST:
Validation after the source fixes:
Please resolve/reply to the four Copilot threads as appropriate and re-request Copilot review on head |
Update the package comment for optional Swift sources, fail early for unsupported Apple platforms, and skip SPM tag publishing when the release tag already exists. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: checked the next 4 Copilot comments from review Comments addressed:
Validation after patch:
Please resolve/reply to those threads and re-request Copilot review on head |
Run SwiftPM and Xcode package builds for macOS, iOS Simulator, Mac Catalyst, and visionOS Simulator after producing the xcframework artifact. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Allow build-ios.sh callers to skip tgz package creation and set that flag from build-xcframework.sh so per-slice xcframework builds only produce the libmat archive they need. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: checked the newest Copilot review Newest comments:
Validation:
Please update the PR description and re-request Copilot review on head |
|
[Windows session → macOS session] Reworded microsoft#1486 and closed the loop on head PR name (was "Prototype: Swift Package Manager distribution (xcframework)") → now:
PR description — fully rewritten to drop all iOS-only framing and reflect current reality:
Review threads: the only unresolved Copilot thread was the recurring "description says iOS-only vs manifest declares macCatalyst/macOS/visionOS" ( Re-requested |
Refresh the prototype documentation to match the current multi-platform xcframework, release workflow, validation coverage, and remaining gaps. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Validate the Package.swift platform list with swift package dump-package before running the platform-specific package builds. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: handled the latest Copilot comment and pushed Comment addressed:
Validation:
Please resolve/reply to the Copilot thread and re-request review on head |
Remove a drifting line-number reference and keep section headings sequential. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: handled Copilot review Comments addressed in
Validation:
Please resolve/reply to those threads and re-request Copilot review on head |
Build each Apple slice from a clean CMake out directory, while preserving the build-tools marker, and restrict xcframework slice builds to the libmat archive target inputs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: handled Copilot review Valid comments addressed:
Validation:
Please resolve/reply to the two valid threads and re-request Copilot review on head |
Use POSIX '=' for the MATTELEMETRY_SKIP_PACKAGE check in build-ios.sh. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: handled Copilot review Valid comment addressed:
Validation:
Please resolve/reply to the thread and re-request Copilot review on head |
Addresses Copilot review on microsoft#1486 (CMakeLists.txt:70, :108): the new Apple-slice platform conditionals used unquoted ${IOS_PLAT} (and the adjacent ${IOS_ARCH}) inside if()/elseif(). If the variable is ever empty/undefined, `if(${IOS_PLAT} STREQUAL "...")` expands to `if( STREQUAL "...")`, which is a hard CMake parse error that aborts configuration. Quoting the expansion ("${IOS_PLAT}") keeps the compare well-formed (empty -> false) and matches the existing `if("${MAC_ARCH}" STREQUAL ...)` idiom already used in this file. Quoted all 7 ${IOS_PLAT} comparisons (lines 57/60/66/70/74/78/104) and the 3 ${IOS_ARCH} comparisons (84/88/92). ${CMAKE_SYSTEM_NAME} (line 313) is left as-is: it is always defined by CMake, so it cannot trigger the empty-expansion parse error. Verified with a minimal CMake repro: the quoted form configures cleanly with the variable undefined and still matches when set, whereas the old unquoted form errors out at configure time. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
[Windows session → macOS session] Addressed the 2 Copilot CMake comments on microsoft#1486 directly (pure CMake-syntax robustness, no macOS validation needed) and pushed Fix: quoted the variable expansions in the Apple-slice Validated with a minimal CMake repro: quoted form configures cleanly with the var undefined (evaluates false) and still matches when set; the old unquoted form fails at configure time with the exact parse error Copilot flagged. Replied + resolved both threads, and re-requested Copilot review on the new head |
The Obj-C wrapper module vended by MATTelemetry.xcframework (and the local wrappers/swift package) was named `ObjCModule` -- a generic name that consumers `import`. Once microsoft#1486 makes this module public via SPM, a generic name risks colliding with another binary/SPM package that also vends an `ObjCModule`, and pollutes the consumer's module namespace. Rename it to the namespaced `MATTelemetryObjC` while the name is still internal (the wrappers/swift package was never distributed), so it is collision-safe before first release. Renamed consistently across both build paths so the same Swift sources compile against both modulemaps: - tools/apple/module.modulemap (xcframework) and wrappers/swift/Modules/module.modulemap (local): `module MATTelemetryObjC`. - All 13 `import ObjCModule` -> `import MATTelemetryObjC` in wrappers/swift/Sources/OneDSSwift/*.swift. - Bridging header file renamed ObjCModule-Bridging-Header.h -> MATTelemetryObjC-Bridging-Header.h and its modulemap reference updated. - Comments/docs (Package.swift, build-xcframework.sh, tools/apple/README.md, examples/swift/README.md) updated. Pure rename; no behavioral change. Needs a macOS `swift build` (local wrappers path) + xcframework SPM build to confirm both paths still resolve the module -- I cannot run those on Windows. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
[Windows session → macOS session] Did #1 (module rename) per Bhagirath's call and pushed Rename: the generic public Clang module Changed consistently across both build paths (19 files, 25/25 lines, pure rename):
Please Re #2 (bundle sqlite/zlib into the xcframework): recommendation is don't. Apple builds link the system |
The SPM xcframework links the platform's libsqlite3/libz (Package.swift .linkedLibrary) rather than bundling them. Document why: bundling a private static sqlite3 would collide with any consumer that also uses SQLite (Core Data/GRDB/FMDB) -> duplicate symbols / two-instance state; system linking yields one shared copy. Notes the contrast with vcpkg (uses vcpkg packages) and Android (bundles, since the NDK has no system copy). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
[Windows session → macOS session] Pushed Two FYIs from a review pass (no action required unless you want it):
Please |
Every other PII-tagged public API in OneDSSwift (EventProperties, Logger, LogManager) already uses the `PIIKind` typealias; only SemanticContext.setUserID exposed the raw Obj-C `ODWPiiKind` in its signature/default. Switch it to `PIIKind` (same underlying type via the ObjCTypes.swift typealias) so consumers of the Swift API never need to reference the MATTelemetryObjC module name. Pure source-level alias swap; no behavioral change. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
setUserID accepted a piiKind argument but called the no-piiKind Obj-C overload `setUserId(_:)`, silently discarding the caller's PII classification for the user id. ODWSemanticContext exposes a `setUserId:piiKind:` overload (wrappers/obj-c/ODWSemanticContext.h:47-48) for exactly this. Route the argument through so the requested PII tag is actually applied. Privacy-relevant behavioral fix. Needs a macOS `swift build` to confirm the bridged selector (`setUserId(_:piiKind:)`); cannot run Swift on the Windows session. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
[Windows session → macOS session] Two commits on
Please |
Keep CommonDataContext available without PrivacyGuard, tighten Swift docs, and scope xcframework slice cleanup to the output directory. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
Mac session update: validated latest PR microsoft#1486 head after Windows pushes, addressed valid review comments, and pushed Synced through Windows commits up to
Valid comments addressed in
Please resolve/reply to those threads and re-request Copilot review on head |
1 participant
Prototype: Swift Package Manager distribution (xcframework)
First-pass scaffold to distribute the 1DS C++ SDK to Apple app developers via Swift Package Manager — the successor to CocoaPods (trunk goes read-only 2 Dec 2026). There is no official in-repo podspec today, and the existing
wrappers/swift/Package.swiftis a local-build skeleton rather than a distributable package.Approach
SPM cannot practically compile this C++ tree from source (CMake/Bond/sqlite/zlib/platform conditionals), so:
MATTelemetry.xcframework(.binaryTarget). The Obj-C wrappers compile intolibmat.aon Apple.wrappers/swift/Sources/OneDSSwift) is compiled from source on top of theObjCModulevended by the xcframework.Package.swiftadvertises.iOS(.v12)only until macOS / Catalyst / visionOS slices are added.What's here
Package.swift— distributable SPM manifest:binaryTarget+OneDSSwiftsource target.tools/apple/build-xcframework.sh— builds staticlibmat.aslices viabuild-ios.sh, combines simulator archs withlipo, and assemblesMATTelemetry.xcframeworkwithxcodebuild -create-xcframework.tools/apple/module.modulemap+MATTelemetry-umbrella.h— vend theObjCModuleClang module.tools/apple/MATTelemetryAvailability.json— generated by the xcframework build and read byPackage.swiftso Swift source exclusions match the optional modules actually built into the binary..github/workflows/spm-release.yml— on a publishedvX.Y.Z.Wrelease: build the xcframework on a macOS runner, upload it to the Release, pin thebinaryTargeturl:+checksum:, and push a 3-component SemVer tag (X.Y.Z) that SPM can resolve.tools/apple/README.md— approach, build/consume, release wiring, and remaining TODOs.Validation performed on macOS
Validated locally with Xcode on macOS:
./build-ios.sh clean release arm64 iphonesimulatorproducedout/lib/libmat.aas a static archive and included Obj-C wrapper symbols.tools/apple/build-xcframework.sh releasesucceeded.ios-arm64ios-arm64_x86_64-simulatorxcodebuild -scheme OneDSSwift -destination 'generic/platform=iOS Simulator' buildConsume after a release
Remaining TODOs
Package.swift.Package.swiftlives long-term, since it makes the repository an SPM package.Companion to the official vcpkg port (C++ consumers) — SPM serves Apple app developers; the two are complementary.