feat(v2): v2 architecture migration — single long-lived branch (GAP 01-04 done; 05-09 to come)#494
Open
sanchitmonga22 wants to merge 481 commits into
Open
feat(v2): v2 architecture migration — single long-lived branch (GAP 01-04 done; 05-09 to come)#494sanchitmonga22 wants to merge 481 commits into
sanchitmonga22 wants to merge 481 commits into
Conversation
Contributor
|
Too many files changed for review. ( |
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
📝 WalkthroughWalkthroughThis PR implements a unified engine plugin system architecture with protocol-buffer based IDL schemas and multi-language code generation. It introduces plugin registration/discovery, hardware-aware engine routing, dynamic/static plugin loading, CI drift-checking for generated artifacts, and corresponding language SDK updates to bridge proto-generated types. Changes
Sequence Diagram(s)sequenceDiagram
participant Frontend as Frontend/App
participant Router as EngineRouter<br/>(CPU: Intel, GPU: Metal)
participant Registry as Plugin Registry
participant Backend as Engine Backend<br/>(e.g., LLama.cpp)
Frontend->>Router: route(primitive=GENERATE_TEXT,<br/>preferred_runtime=Metal)
activate Router
Router->>Router: score(LlamaCPP vtable)<br/>priority=50, Metal support=false<br/>score=-1000
Router->>Router: score(MetalRT vtable)<br/>priority=60, Metal support=true<br/>score=70 (60+Metal bonus)
Router->>Registry: find(GENERATE_TEXT)
activate Registry
Registry-->>Router: [MetalRT, LlamaCPP] (sorted by score)
deactivate Registry
Router-->>Frontend: RouteResult(vtable=MetalRT,<br/>score=70)
deactivate Router
Frontend->>Backend: llm_ops->generate(...)
activate Backend
Backend-->>Frontend: result
deactivate Backend
sequenceDiagram
participant Loader as rac_registry_load_plugin()
participant SO as Shared Library<br/>(dlopen/LoadLibrary)
participant Entry as Plugin Entry Point<br/>(rac_plugin_entry_*)
participant Registry as Plugin Registry<br/>(rac_plugin_register)
participant App as App Runtime
Loader->>SO: dlopen("/path/to/librunanywhere_onnx.so")
activate SO
SO-->>Loader: handle
deactivate SO
Loader->>Entry: dlsym(handle, "rac_plugin_entry_onnx")
activate Entry
Entry-->>Loader: function pointer
deactivate Entry
Loader->>Entry: rac_plugin_entry_onnx()
activate Entry
Entry-->>Loader: rac_engine_vtable_t*<br/>(metadata.abi_version=2,<br/>stt_ops, tts_ops, vad_ops)
deactivate Entry
Loader->>Registry: rac_plugin_register(vtable)
activate Registry
Registry->>Registry: validate ABI version<br/>matches RAC_PLUGIN_API_VERSION
Registry->>Registry: insert into primitive buckets<br/>(TRANSCRIBE, SYNTHESIZE,<br/>DETECT_VOICE)
Registry-->>Loader: RAC_SUCCESS
deactivate Registry
Loader->>SO: store dl handle
Loader-->>App: RAC_SUCCESS
App->>Registry: rac_plugin_find(TRANSCRIBE)
Registry-->>App: onnx vtable (priority-sorted)
Estimated code review effort🎯 4 (Complex) | ⏱️ ~90 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Poem
✨ Finishing Touches🧪 Generate unit tests (beta)
|
Closed
9 tasks
sanchitmonga22
added a commit
that referenced
this pull request
Apr 22, 2026
Per review request — all v2 architecture work lives on the one `feat/v2-architecture` branch tracked by PR #494, instead of fragmenting into per-wave sub-branches. Updates `docs/wave_roadmap.md` to encode this contract for future contributors: - Branch: `feat/v2-architecture` (single, long-lived). - PR: #494 (stays open and grows commit-by-commit). - Cadence: one commit per phase, message prefix `feat(gapXX-phaseN)`. - Per-wave milestone: checked-in `docs/gap0X_final_gate_report.md`. - Merge to main: only when GAP 01-08 are all done (GAP 05 opt-in). Refresh the title from "Post-Wave-A roadmap" to "v2 architecture roadmap" to match the broader scope. Note Wave A is now MERGED INTO the branch (not "this branch"). No code changes. Made-with: Cursor
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Comment on lines
+37
to
+100
| name: Verify generated code matches IDL | ||
| runs-on: macos-14 | ||
| timeout-minutes: 15 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
|
|
||
| - name: Cache Homebrew | ||
| uses: actions/cache@v4 | ||
| with: | ||
| path: | | ||
| /usr/local/Homebrew | ||
| /opt/homebrew | ||
| ~/Library/Caches/Homebrew | ||
| key: ${{ runner.os }}-brew-protoc-${{ hashFiles('scripts/setup-toolchain.sh') }} | ||
|
|
||
| - name: Install protoc + swift-protobuf (Homebrew) | ||
| run: | | ||
| brew install protobuf swift-protobuf | ||
|
|
||
| - name: Install wire-compiler (best-effort — Gradle Wire plugin is the fallback) | ||
| run: | | ||
| brew install wire || echo "wire bottle unavailable; Gradle Wire plugin will handle Kotlin codegen" | ||
|
|
||
| - name: Install Dart plugin (protoc-gen-dart) | ||
| run: | | ||
| if command -v dart >/dev/null 2>&1; then | ||
| dart pub global activate protoc_plugin 21.1.2 | ||
| echo "$HOME/.pub-cache/bin" >> "$GITHUB_PATH" | ||
| else | ||
| echo "::warning::dart not found on macos-14 runner; Dart codegen skipped" | ||
| fi | ||
|
|
||
| - name: Install ts-proto (npm) | ||
| run: | | ||
| npm install -g ts-proto@1.181.1 protobufjs | ||
|
|
||
| - name: Install Python protobuf | ||
| run: | | ||
| python3 -m pip install --upgrade "protobuf>=4.25,<5" grpcio-tools | ||
|
|
||
| - name: Dump toolchain versions (debug) | ||
| run: | | ||
| echo "protoc: $(protoc --version)" | ||
| echo "protoc-gen-swift: $(protoc-gen-swift --version 2>/dev/null || echo 'not present')" | ||
| echo "wire-compiler: $(wire-compiler --version 2>/dev/null || echo 'not present')" | ||
| echo "protoc-gen-dart: $(protoc-gen-dart --version 2>/dev/null || echo 'present or skipped')" | ||
| echo "node: $(node --version)" | ||
| echo "python3: $(python3 --version)" | ||
|
|
||
| - name: Regenerate all bindings | ||
| run: ./idl/codegen/generate_all.sh | ||
|
|
||
| - name: Fail on drift | ||
| run: | | ||
| if ! git diff --exit-code --stat; then | ||
| echo "::error::IDL-generated code is out of sync with .proto sources." | ||
| echo "" | ||
| echo "To fix locally:" | ||
| echo " ./scripts/setup-toolchain.sh" | ||
| echo " ./idl/codegen/generate_all.sh" | ||
| echo " git add -A && git commit -m 'chore(codegen): regenerate bindings'" | ||
| exit 1 | ||
| fi | ||
| echo "✓ No drift detected." |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 20
Note
Due to the large number of review comments, Critical, Major severity comments were prioritized as inline comments.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (7)
sdk/runanywhere-commons/src/backends/whisperkit_coreml/CMakeLists.txt (1)
15-25:⚠️ Potential issue | 🟡 MinorAdd RAC_WHISPERKIT_COREML_BUILDING compile definition to match peer backends.
The WhisperKit CMakeLists.txt does not define a backend-specific
RAC_WHISPERKIT_COREML_BUILDINGmacro, unlike ONNX, LlamaCPP, and MetalRT. While the public callback functions useRAC_API(which has unconditionalvisibility("default")), the plugin entry pointrac_plugin_entry_whisperkit_coremlhas no explicit visibility attribute and relies on default behavior. Add the definition to maintain consistency and ensure robust symbol visibility:target_compile_definitions(rac_backend_whisperkit_coreml PRIVATE RAC_WHISPERKIT_COREML_BUILDING)Then create
rac_backend_whisperkit_coreml.hwith the visibility wrapper pattern used by peer backends, or annotate the entry symbol explicitly if it needs special handling in shared builds.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/whisperkit_coreml/CMakeLists.txt` around lines 15 - 25, Add a compile definition and visibility wrapper for the WhisperKit backend: update the CMake target rac_backend_whisperkit_coreml to call target_compile_definitions(... PRIVATE RAC_WHISPERKIT_COREML_BUILDING) so the backend-specific macro is defined for shared builds, and add a new header rac_backend_whisperkit_coreml.h that mirrors the visibility wrapper pattern used by ONNX/LlamaCPP/MetalRT (define RAC_WHISPERKIT_COREML_BUILDING to export symbols via RAC_API and annotate the plugin entry function rac_plugin_entry_whisperkit_coreml or include the header in that source to ensure the entry symbol has the correct visibility in shared builds).sdk/runanywhere-commons/src/backends/whisperkit_coreml/rac_backend_whisperkit_coreml_register.cpp (1)
91-98:⚠️ Potential issue | 🔴 Critical
g_whisperkit_coreml_stt_opshas internal linkage and cannot be accessed via extern from another translation unit.The symbol is defined inside the unnamed
namespace {block (opened at line 24, closed at line 174) at line 91. Names declared in an unnamed namespace have internal linkage per C++ [basic.link], so the extern declaration inrac_plugin_entry_whisperkit_coreml.cppline 19 cannot resolve to this symbol at link time.Move the definition outside the anonymous namespace with
extern "C":Fix
namespace { const char* LOG_CAT = "WhisperKitCoreML"; // ... vtable functions ... +} // namespace + +extern "C" const rac_stt_service_ops_t g_whisperkit_coreml_stt_ops = { -const rac_stt_service_ops_t g_whisperkit_coreml_stt_ops = { .initialize = whisperkit_coreml_stt_vtable_initialize, .transcribe = whisperkit_coreml_stt_vtable_transcribe, .transcribe_stream = whisperkit_coreml_stt_vtable_transcribe_stream, .get_info = whisperkit_coreml_stt_vtable_get_info, .cleanup = whisperkit_coreml_stt_vtable_cleanup, .destroy = whisperkit_coreml_stt_vtable_destroy, }; + +namespace {🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/whisperkit_coreml/rac_backend_whisperkit_coreml_register.cpp` around lines 91 - 98, The symbol g_whisperkit_coreml_stt_ops is defined inside an unnamed namespace so it has internal linkage and cannot satisfy the extern in rac_plugin_entry_whisperkit_coreml.cpp; move the definition of g_whisperkit_coreml_stt_ops out of the anonymous namespace to global scope and give it external C linkage (e.g., declare/define it as extern "C" const rac_stt_service_ops_t g_whisperkit_coreml_stt_ops) so the extern in the other TU can link to it, keeping the existing initializer and references to whisperkit_coreml_stt_vtable_* functions unchanged.sdk/runanywhere-commons/src/backends/llamacpp/rac_backend_llamacpp_register.cpp (1)
156-179:⚠️ Potential issue | 🔴 CriticalMove
g_llamacpp_opsoutside the anonymous namespace — currently it cannot be resolved by plugin entry extern declarations.
g_llamacpp_opsis defined at line 162 inside thenamespace {block (opened at line 27, closed at line 291), yetrac_plugin_entry_llamacpp.cppattempts toexternit. Per C++ [basic.link], names in an unnamed namespace have internal linkage regardless of whetherstaticis used, so the extern declaration will fail to link.Similarly, all five backend register files have identical issues:
rac_backend_whisperkit_coreml_register.cpp: namespace 24–174,g_whisperkit_coreml_stt_opsat line 91rac_backend_whispercpp_register.cpp: namespace 23–188,g_whispercpp_stt_opsat line 106rac_backend_onnx_register.cpp: namespace 39–538, multiple ops structs insiderac_backend_metalrt_register.cpp: namespace 79–499,g_metalrt_llm_opsat line 159Move each ops struct (and referenced vtable functions, or forward-declare them) outside its anonymous namespace, or define the unified plugin entry in the same TU.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/llamacpp/rac_backend_llamacpp_register.cpp` around lines 156 - 179, The ops struct g_llamacpp_ops is inside an unnamed namespace so it has internal linkage and cannot be extern'd by rac_plugin_entry_llamacpp.cpp; move the declaration/definition of g_llamacpp_ops out of the anonymous namespace (or remove the extern use by placing the plugin entry in the same TU), and ensure any vtable functions it references (llamacpp_vtable_initialize, llamacpp_vtable_generate, etc.) are either forward-declared at namespace-scope or also defined outside the anonymous namespace; apply the same fix for the other backends' ops structs (g_whisperkit_coreml_stt_ops, g_whispercpp_stt_ops, the ops in rac_backend_onnx_register.cpp, g_metalrt_llm_ops) so the plugin entry externs can link them.sdk/runanywhere-commons/src/backends/whispercpp/rac_backend_whispercpp_register.cpp (1)
23-188:⚠️ Potential issue | 🔴 CriticalCritical:
g_whispercpp_stt_opshas internal linkage and cannot be referenced externally.The vtable definition at line 106 sits inside the anonymous namespace (
namespace {}, lines 23–188). Per C++[basic.link], names in unnamed namespaces have internal linkage regardless of thestatickeyword. The extern declaration inrac_plugin_entry_whispercpp.cpp:14will fail to link.Move
g_whispercpp_stt_opsoutside the anonymous namespace. Keep helper functions (convert_int16_to_float32, vtable implementations) insidenamespace {}.Proposed fix
namespace { const char* LOG_CAT = "WhisperCPP"; /** * Convert Int16 PCM audio to Float32 normalized to [-1.0, 1.0]. */ static std::vector<float> convert_int16_to_float32(const void* int16_data, size_t byte_count) { // ... implementation ... } // Vtable function implementations static rac_result_t whispercpp_stt_vtable_initialize(void* impl, const char* model_path) { /* ... */ } static rac_result_t whispercpp_stt_vtable_transcribe(void* impl, const void* audio_data, /* ... */ ) { /* ... */ } static rac_result_t whispercpp_stt_vtable_transcribe_stream(void* impl, /* ... */ ) { /* ... */ } static rac_result_t whispercpp_stt_vtable_get_info(void* impl, rac_stt_info_t* out_info) { /* ... */ } static rac_result_t whispercpp_stt_vtable_cleanup(void* impl) { /* ... */ } static void whispercpp_stt_vtable_destroy(void* impl) { /* ... */ } const char* const MODULE_ID = "whispercpp"; const char* const STT_PROVIDER_NAME = "WhisperCPPSTTService"; rac_bool_t whispercpp_stt_can_handle(const rac_service_request_t* request, void* user_data) { /* ... */ } rac_handle_t whispercpp_stt_create(const rac_service_request_t* request, void* user_data) { /* ... */ } bool g_registered = false; } // namespace // Externally-visible vtable extern "C" const rac_stt_service_ops_t g_whispercpp_stt_ops = { .initialize = whispercpp_stt_vtable_initialize, .transcribe = whispercpp_stt_vtable_transcribe, .transcribe_stream = whispercpp_stt_vtable_transcribe_stream, .get_info = whispercpp_stt_vtable_get_info, .cleanup = whispercpp_stt_vtable_cleanup, .destroy = whispercpp_stt_vtable_destroy, };🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/whispercpp/rac_backend_whispercpp_register.cpp` around lines 23 - 188, The g_whispercpp_stt_ops vtable is defined inside the anonymous namespace so it has internal linkage and cannot be referenced from rac_plugin_entry_whispercpp.cpp; move the definition of g_whispercpp_stt_ops out of the anonymous namespace (leaving helper functions like convert_int16_to_float32 and the vtable implementation functions whispercpp_stt_vtable_initialize/transcribe/transcribe_stream/get_info/cleanup/destroy inside the anonymous namespace) so the symbol has external linkage, and ensure its declaration matches the extern usage in rac_plugin_entry_whispercpp.cpp.sdk/runanywhere-commons/src/backends/llamacpp/rac_backend_llamacpp_vlm_register.cpp (1)
25-240:⚠️ Potential issue | 🔴 CriticalCritical:
g_llamacpp_vlm_opsremains internally-linked — unnamed namespace prevents external linkage.The definition at lines 114–124 is enclosed by the anonymous namespace (opened line 25, closed line 240). Per C++
[basic.link], names in an unnamed namespace have internal linkage; removing thestatickeyword does not change this. The comment on lines 114–115 is incorrect: simply making the variable non-staticdoes not allow external linkage from within an unnamed namespace.The plugin entry TU (
rac_plugin_entry_llamacpp_vlm.cppline 19) declaresextern const rac_vlm_service_ops_t g_llamacpp_vlm_ops;, which will not resolve to this definition and will cause a linker error.Hoist
g_llamacpp_vlm_opsand its vtable function pointers out of the anonymous namespace to give them external linkage. (Same issue and fix pattern asrac_backend_whispercpp_register.cpp.)🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/llamacpp/rac_backend_llamacpp_vlm_register.cpp` around lines 25 - 240, The exported vtable g_llamacpp_vlm_ops is currently inside an unnamed namespace so it has internal linkage and cannot satisfy the extern in rac_plugin_entry_llamacpp_vlm.cpp; move the vtable and its related vtable functions out of the anonymous namespace to give them external linkage. Specifically, take the const rac_vlm_service_ops_t g_llamacpp_vlm_ops definition and the functions it references (llamacpp_vlm_vtable_initialize, llamacpp_vlm_vtable_process, llamacpp_vlm_vtable_process_stream, llamacpp_vlm_vtable_get_info, llamacpp_vlm_vtable_cancel, llamacpp_vlm_vtable_cleanup, llamacpp_vlm_vtable_destroy) out of the anonymous namespace (keep other helper types like VLMStreamAdapter or registry state inside if desired), ensure the symbol names remain unchanged and visible at global scope, and keep the signature matching the extern declaration so the linker can resolve g_llamacpp_vlm_ops.sdk/runanywhere-commons/src/backends/metalrt/rac_backend_metalrt_register.cpp (1)
159-322:⚠️ Potential issue | 🔴 CriticalThe vtable symbols cannot be referenced via
externdeclarations while inside an anonymous namespace.
g_metalrt_llm_ops(line 159),g_metalrt_stt_ops(line 209),g_metalrt_tts_ops(line 254), andg_metalrt_vlm_ops(line 314) are all defined within the anonymous namespace (lines 79–499). Per the C++ standard, names in an unnamed namespace have internal linkage—externdeclarations inrac_plugin_entry_metalrt.cpp(lines 22–25) cannot bind to these definitions. This will produce either a linker error (unresolved symbol) or silent dispatch to the wrong definition.To export these vtables so
rac_plugin_entry_metalrt.cppcan reference them, move the fourg_metalrt_*_opsdefinitions outside the anonymous namespace, or expose them via accessor functions that reside outside the namespace.Note: The ONNX backend (
rac_backend_onnx_register.cpp) exhibits the same pattern (ops inside anonymous namespace at lines 39–538, referenced viaexterninrac_plugin_entry_onnx.cpp), which suggests this issue may be systemic.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/metalrt/rac_backend_metalrt_register.cpp` around lines 159 - 322, The four vtable symbols g_metalrt_llm_ops, g_metalrt_stt_ops, g_metalrt_tts_ops, and g_metalrt_vlm_ops are currently defined inside an anonymous namespace so external extern declarations cannot bind to them; fix by moving each of those const rac_*_service_ops_t definitions out of the unnamed namespace (place them at namespace scope with external linkage) or alternatively add and export simple accessor functions (e.g., get_metalrt_llm_ops(), get_metalrt_stt_ops(), get_metalrt_tts_ops(), get_metalrt_vlm_ops()) defined outside the anonymous namespace that return pointers/references to the corresponding ops, and update rac_plugin_entry_metalrt.cpp to use those accessors instead of extern symbols.sdk/runanywhere-commons/src/backends/onnx/rac_backend_onnx_register.cpp (1)
147-384:⚠️ Potential issue | 🔴 CriticalLinkage error: service ops defined in anonymous namespace cannot be externally linked.
g_onnx_stt_ops(line ~147),g_onnx_tts_ops(line ~213), andg_onnx_vad_ops(line ~376) are defined inside the anonymous namespace (lines 39–538). By C++ standard, symbols in unnamed namespaces have internal linkage. Whenrac_plugin_entry_onnx.cppdeclaresextern const rac_stt_service_ops_t g_onnx_stt_ops;etc., the linker cannot resolve these symbols because they are not visible outside their translation unit.Removing
staticalone will not help—the anonymous namespace already enforces internal linkage. Move the three definitions outside the anonymous namespace, or expose them via accessor functions in theextern "C"block below.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/onnx/rac_backend_onnx_register.cpp` around lines 147 - 384, The service ops objects g_onnx_stt_ops, g_onnx_tts_ops, and g_onnx_vad_ops are currently defined inside an unnamed (anonymous) namespace which gives them internal linkage, so extern declarations in rac_plugin_entry_onnx.cpp cannot link to them; fix this by moving the three definitions (g_onnx_stt_ops, g_onnx_tts_ops, g_onnx_vad_ops) out of the anonymous namespace into global scope (or alternatively add extern "C" accessor functions that return pointers to these objects and call those from rac_plugin_entry_onnx.cpp), ensuring the objects remain non-static and globally visible.
♻️ Duplicate comments (1)
.github/workflows/idl-drift-check.yml (1)
35-40:⚠️ Potential issue | 🟡 MinorAdd an explicit
permissions:block.CodeQL has already flagged this. A
contents: readdefault is sufficient for a drift check that only reads the repo.🔒 Suggested change
jobs: check: name: Verify generated code matches IDL runs-on: macos-14 timeout-minutes: 15 + permissions: + contents: read steps:🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/idl-drift-check.yml around lines 35 - 40, Add an explicit permissions block to the workflow so the job has only the repo read permission; update the workflow (job "check" in .github/workflows/idl-drift-check.yml) to include a top-level permissions: entry with contents: read to satisfy CodeQL and limit token scope for the verify generated code job.
🟡 Minor comments (18)
idl/codegen/ci-drift-check.sh-24-31 (1)
24-31:⚠️ Potential issue | 🟡 MinorDrift check misses newly generated (untracked) files.
git diff --exit-code --statonly reports modifications to tracked files. Ifgenerate_all.shcreates a brand-new output file (e.g., when a new.protois added and its first-time generated binding isn't committed yet), the file shows up as untracked and the drift check passes silently.Consider staging everything first, or explicitly checking for untracked files:
🔧 Proposed fix
-# Fail loud on any drift. -if ! git diff --exit-code --stat; then +# Fail loud on any drift (modifications or new untracked outputs). +git add -A -N . # intent-to-add so untracked files show up in diff +if ! git diff --exit-code --stat; then echo "" >&2 echo "::error::IDL-generated code is out of sync with .proto sources." >&2Or equivalently, assert
git status --porcelainis empty.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@idl/codegen/ci-drift-check.sh` around lines 24 - 31, The current drift check uses "git diff --exit-code --stat" which ignores untracked files so newly generated files (from generate_all.sh) can be missed; modify the script to first run a check for any workspace changes including untracked files (for example by running "git status --porcelain" and failing if its output is non-empty) or alternatively stage all changes and compare the index (e.g., "git add -A" then "git diff --cached --exit-code --stat"); update the block that currently runs "git diff --exit-code --stat" to use one of these approaches so untracked generated files cause the check to fail.docs/gap04_final_gate_report.md-41-49 (1)
41-49:⚠️ Potential issue | 🟡 MinorBroken placeholder link in a gate-closure document.
Line 44 points the "execution wave plan" reference to
https://example.invalid/plan, which is not a real target. Sinceexample.invalidis the reserved RFC 2606 TLD, this is clearly a placeholder that slipped through. Either link to the actual file in-repo (e.g., a relative path underv2_gap_specs/ordocs/) or remove the hyperlink.Minor nit on line 9: "iOS17 ANE run" reads better as "iOS 17 ANE run".
✍️ Proposed fix
-Wave A (GAP 03 + GAP 04) ships the dynamic-loader + hardware-aware router on top of the GAP 02 plugin ABI. Subsequent waves per -[`gap03_gap04_execution_wave_08047ae8.plan.md`](https://example.invalid/plan): +Wave A (GAP 03 + GAP 04) ships the dynamic-loader + hardware-aware router on top of the GAP 02 plugin ABI. Subsequent waves per +[`gap03_gap04_execution_wave_08047ae8.plan.md`](../path/to/gap03_gap04_execution_wave_08047ae8.plan.md):🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/gap04_final_gate_report.md` around lines 41 - 49, The placeholder link to https://example.invalid/plan (referenced as `gap03_gap04_execution_wave_08047ae8.plan.md`) in docs/gap04_final_gate_report.md is invalid; replace the hyperlink with either the correct in-repo relative path (e.g., the actual file under v2_gap_specs/ or docs/) or remove the link and keep plain text, ensuring the reference text `gap03_gap04_execution_wave_08047ae8.plan.md` matches the real filename; also fix the minor typo by changing the phrase "iOS17 ANE run" to "iOS 17 ANE run".idl/codegen/generate_kotlin.sh-21-29 (1)
21-29:⚠️ Potential issue | 🟡 MinorFix the Wire output root to align directory structure with package paths.
The current configuration generates files at
.../com/runanywhere/sdk/generated/ai/runanywhere/proto/v1/with package declarationai.runanywhere.proto.v1. This creates a mismatch: the directory path includescom/runanywhere/sdk/generatedbut the package does not.Wire treats
--kotlin_outas a source root and appends the package directory structure from the protojava_packageoption. Since the proto files specifyoption java_package = "ai.runanywhere.proto.v1", change the output root tosdk/runanywhere-kotlin/src/commonMain/kotlinso files are generated at the correct structure matching their package names.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@idl/codegen/generate_kotlin.sh` around lines 21 - 29, Update the OUT_DIR used in generate_kotlin.sh so the Wire compiler's --kotlin_out points to the Kotlin source root instead of embedding "com/runanywhere/sdk/generated"; change the OUT_DIR variable (and the mkdir -p target) from the current "${REPO_ROOT}/sdk/runanywhere-kotlin/src/commonMain/kotlin/com/runanywhere/sdk/generated" to "${REPO_ROOT}/sdk/runanywhere-kotlin/src/commonMain/kotlin" and ensure the wire-compiler invocation continues to use "--kotlin_out=\"${OUT_DIR}\"" so generated files follow the package path from the proto java_package option.sdk/runanywhere-commons/tests/test_static_registration.cpp-27-29 (1)
27-29:⚠️ Potential issue | 🟡 MinorNarrowing:
0xFEEDFACEdoes not fit inint.
0xFEEDFACE= 4,276,993,774, which exceedsINT_MAX(2,147,483,647) on all common platforms. Initializingconst intfrom it is a narrowing/implementation-defined conversion and will warn (or fail under-Wnarrowing/-Werror). Use an unsigned or wider type — it's just a sentinel pointer value, so unsigned is fine.🛡️ Proposed fix
namespace { -const int k_sentinel_static = 0xFEEDFACE; +const unsigned int k_sentinel_static = 0xFEEDFACEu; }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/tests/test_static_registration.cpp` around lines 27 - 29, k_sentinel_static is declared as const int but initialized with 0xFEEDFACE which exceeds INT_MAX and causes a narrowing/implementation-defined conversion; change its type to an unsigned or wider integer type (e.g., constexpr unsigned int, uint32_t, or uintptr_t) and use an unsigned literal (0xFEEDFACEu) so the sentinel value is represented without narrowing in the anonymous namespace.sdk/runanywhere-commons/src/backends/whisperkit_coreml/rac_plugin_entry_whisperkit_coreml.cpp-34-37 (1)
34-37:⚠️ Potential issue | 🟡 MinorUse protobuf enum symbols instead of magic numbers for model formats.
The hardcoded values
6and8will silently drift if new enum values are inserted beforeMODEL_FORMAT_COREMLorMODEL_FORMAT_MLPACKAGEinidl/model_types.proto. Include the generated protobuf header and reference the enum symbols directly.Proposed fix
+#include "rac/plugin/rac_engine_vtable.h" +#include "rac/plugin/rac_plugin_entry.h" +#include "rac/features/stt/rac_stt_service.h" +#include "rac/core/rac_error.h" +#include "rac/generated/proto/model_types.pb.h" extern "C" { extern const rac_stt_service_ops_t g_whisperkit_coreml_stt_ops; static rac_result_t whisperkit_coreml_capability_check(void) { `#if` defined(__APPLE__) return RAC_SUCCESS; `#else` return RAC_ERROR_CAPABILITY_UNSUPPORTED; `#endif` } static const rac_runtime_id_t k_whisperkit_coreml_runtimes[] = { RAC_RUNTIME_COREML, RAC_RUNTIME_ANE, }; static const uint32_t k_whisperkit_coreml_formats[] = { - 6, /* MODEL_FORMAT_COREML */ - 8, /* MODEL_FORMAT_MLPACKAGE */ + static_cast<uint32_t>(MODEL_FORMAT_COREML), + static_cast<uint32_t>(MODEL_FORMAT_MLPACKAGE), };🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/whisperkit_coreml/rac_plugin_entry_whisperkit_coreml.cpp` around lines 34 - 37, Replace the magic numeric literals in k_whisperkit_coreml_formats with the generated protobuf enum symbols and include the generated protobuf header: add an `#include` for the model_types protobuf header (e.g., the generated idl/model_types.pb.h) at the top of the file and change the array entries to use MODEL_FORMAT_COREML and MODEL_FORMAT_MLPACKAGE (the protobuf enum symbols referenced in idl/model_types.proto) so the code uses the canonical enum values instead of hardcoded numbers.idl/CMakeLists.txt-26-43 (1)
26-43:⚠️ Potential issue | 🟡 MinorRemove dead
_RAC_IDL_GEN_DIRvariable and dead include directive.
protobuf_generate_cpp()emits files directly to${CMAKE_CURRENT_BINARY_DIR}, not to${_RAC_IDL_GEN_DIR}. Thefile(MAKE_DIRECTORY)call and the secondtarget_include_directories()targeting${_RAC_IDL_GEN_DIR}are unused. Also, the comment on lines 39–40 incorrectly claims consumers will include"runanywhere/idl/model_types.pb.h"— they will actually include"model_types.pb.h"(no prefix) because the include root is the binary dir.Simplest fix: delete lines 27–29 and lines 39–42, and wrap the first
target_include_directories()argument in$<BUILD_INTERFACE:>.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@idl/CMakeLists.txt` around lines 26 - 43, Remove the dead _RAC_IDL_GEN_DIR setup and the unused include directive: delete the file(MAKE_DIRECTORY ${_RAC_IDL_GEN_DIR}) and the _RAC_IDL_GEN_DIR variable usage plus the second target_include_directories(...) that references it; keep protobuf_generate_cpp(...) as-is (it emits into ${CMAKE_CURRENT_BINARY_DIR}), and change the existing target_include_directories(rac_idl PUBLIC ${CMAKE_CURRENT_BINARY_DIR}) to wrap the include in $<BUILD_INTERFACE:...> so it reads target_include_directories(rac_idl PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_BINARY_DIR}>); leave target_link_libraries(rac_idl PUBLIC ${Protobuf_LIBRARIES}) and the add_library(rac_idl STATIC ...) intact.sdk/runanywhere-commons/src/plugin/plugin_registry_internal.h-40-46 (1)
40-46:⚠️ Potential issue | 🟡 MinorDocstring doesn't match the signature of
rac_plugin_registry_snapshot_names.The comment says "Returns the count via
out_count" and "Caller passes the desired count cap; the registry truncates if it has more", but the declared signature has neither anout_countparameter nor a cap input — it returnssize_tdirectly and takes onlyout_names. Either the doc is stale or the signature is missing parameters; whichever is intended, they disagree, and the loader TU will be coded against one or the other.🛠️ If the return-value form is the intended one
/** * Snapshot the names of every currently-registered plugin into `out_names` * (heap-allocated `strdup`s, caller frees with `free()` per entry + `free()` - * on the array). Returns the count via `out_count`. Caller passes the desired - * count cap; the registry truncates if it has more. + * on the array). Returns the number of entries written to `*out_names`. */ size_t rac_plugin_registry_snapshot_names(const char*** out_names);🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/plugin/plugin_registry_internal.h` around lines 40 - 46, The docstring and the declaration for rac_plugin_registry_snapshot_names disagree: either update the comment to match the current signature or change the function signature/implementation to match the documented API. Fix option A (preferred if return-value style is intended): change the comment on rac_plugin_registry_snapshot_names to state that the function returns the count as its size_t return value, that it allocates an array of strdup'd C-strings into the out_names pointer (caller must free each entry and the array), and remove references to out_count and a caller-provided cap. Fix option B (if the doc is correct): change the declaration/implementation of rac_plugin_registry_snapshot_names to accept a size_t cap and a size_t* out_count (e.g., size_t rac_plugin_registry_snapshot_names(const char*** out_names, size_t cap, size_t* out_count)), and update all callers to pass a cap and receive out_count; preserve the strdup/ownership semantics noted in the comment.docs/engine_plugin_authoring.md-86-90 (1)
86-90:⚠️ Potential issue | 🟡 MinorUpdate
RAC_PLUGIN_API_VERSIONversion number in documentation from "1" to "2".Lines 86–90 document
RAC_PLUGIN_API_VERSIONas "currently 1", but the actual definition insdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry.h:58is2u. Plugin authors following this outdated documentation will hardcode the wrong version and encounterRAC_ERROR_ABI_VERSION_MISMATCHat runtime.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/engine_plugin_authoring.md` around lines 86 - 90, The doc text incorrectly states RAC_PLUGIN_API_VERSION is "currently 1"; update the documentation so it reflects the actual ABI value 2 (i.e., change the phrase "currently 1" to "currently 2" or, better, reference the constant symbol RAC_PLUGIN_API_VERSION directly), ensuring the rule describing metadata.abi_version explicitly requires equality with RAC_PLUGIN_API_VERSION (now 2) to prevent authors from hardcoding the wrong value and triggering RAC_ERROR_ABI_VERSION_MISMATCH.sdk/runanywhere-kotlin/src/commonMain/kotlin/com/runanywhere/sdk/core/types/ComponentTypes.kt-82-95 (1)
82-95:⚠️ Potential issue | 🟡 MinorAdd
else → nullfallback to handle forward-compatibility as new proto enum values are added.The
whenexpression covers all current enum values but lacks an explicit fallback. UnlikeInferenceFramework.fromProto(line 248), which useselse → UNKNOWN, this function implicitly returnsnullfor unknown values. Make this intent explicit by addingelse → nullto match the pattern in the generated proto'sfromValuehelper and improve clarity for future maintainers.Suggested fix
fun audioFormatFromProto(proto: ai.runanywhere.proto.v1.AudioFormat): AudioFormat? = when (proto) { ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_PCM -> AudioFormat.PCM ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_WAV -> AudioFormat.WAV ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_MP3 -> AudioFormat.MP3 ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_OPUS -> AudioFormat.OPUS ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_AAC -> AudioFormat.AAC ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_FLAC -> AudioFormat.FLAC ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_OGG -> AudioFormat.OGG ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_PCM_S16LE -> AudioFormat.PCM_16BIT ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_M4A -> null ai.runanywhere.proto.v1.AudioFormat.AUDIO_FORMAT_UNSPECIFIED -> null + else -> null }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-kotlin/src/commonMain/kotlin/com/runanywhere/sdk/core/types/ComponentTypes.kt` around lines 82 - 95, The when-expression in audioFormatFromProto currently lists all known ai.runanywhere.proto.v1.AudioFormat cases but lacks an explicit fallback; update the audioFormatFromProto function to include an else → null branch so any future/unknown ai.runanywhere.proto.v1.AudioFormat values are handled explicitly and return null (matching the intended forward-compatibility behavior).sdk/runanywhere-commons/src/backends/llamacpp/rac_plugin_entry_llamacpp_vlm.cpp-28-44 (1)
28-44:⚠️ Potential issue | 🟡 MinorReplace magic format numbers with proto enum constants to prevent silent drift.
The vtable architecture explicitly documents that format values must be proto-encoded
runanywhere.v1.ModelFormatvalues. The current hardcoded values (1, 5) are correct, but lack abstraction—if the proto enum reorders or renumbers, they will silently mismatch. Use the named constants from the generated header:♻️ Suggested change
+#include "rac/infrastructure/proto_wrapper.h" // or appropriate proto header path + static const uint32_t k_llamacpp_vlm_formats[] = { - 1, /* MODEL_FORMAT_GGUF */ - 5, /* MODEL_FORMAT_BIN — vision projector / mmproj files */ + static_cast<uint32_t>(runanywhere::v1::MODEL_FORMAT_GGUF), + static_cast<uint32_t>(runanywhere::v1::MODEL_FORMAT_BIN), };(Adjust include path to match your proto header location.)
This pattern affects all backend plugins (
whispercpp,llamacpp,onnx,whisperkit_coreml,metalrt); consider applying uniformly.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/llamacpp/rac_plugin_entry_llamacpp_vlm.cpp` around lines 28 - 44, The static array k_llamacpp_vlm_formats currently uses magic numbers (1, 5); replace those numeric literals with the proto enum constants from the generated runanywhere v1 header (e.g., MODEL_FORMAT_GGUF and MODEL_FORMAT_BIN from the runanywhere::v1 proto enum) and add the appropriate `#include` for that generated header; update g_llamacpp_vlm_engine_vtable (formats/formats_count) only by changing k_llamacpp_vlm_formats contents so semantics remain the same and compile-time enum names prevent future drift.sdk/runanywhere-commons/tests/test_engine_vtable.cpp-161-167 (1)
161-167:⚠️ Potential issue | 🟡 MinorScenario (9) does not actually exercise
RAC_STATIC_PLUGIN_REGISTER.The file header and scenario list both promise a static-registration smoke check, but this block only asserts
rac_plugin_count() == 0. Either invokeRAC_STATIC_PLUGIN_REGISTERin this TU (or verify a statically-registered plugin from another TU is present before the test-local cleanups) to match the documented contract, or update the comment/header to stop advertising that coverage.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/tests/test_engine_vtable.cpp` around lines 161 - 167, The test block claims to exercise static-registration but never uses RAC_STATIC_PLUGIN_REGISTER; update the test to actually invoke the macro in this translation unit and verify its effect: call RAC_STATIC_PLUGIN_REGISTER(...) with a simple test plugin identifier at the start of the scenario, assert rac_plugin_count() increases (e.g., >0) to show the static registration was observed, then perform the existing cleanup and assert rac_plugin_count() == 0 afterward; locate the checks around rac_plugin_count() in the same test block and add the macro invocation and the intermediate assertion there (or alternatively, remove/adjust the comment if you prefer not to exercise the macro).sdk/runanywhere-commons/src/backends/onnx/rac_plugin_entry_onnx.cpp-50-50 (1)
50-50:⚠️ Potential issue | 🟡 Minor
engine_versionset tonullptr.Other plugins (e.g., the test fixture) set a version string here. If any consumer (logs, router telemetry,
display_nameformatting) callsstrlen/printf("%s", …)onengine_versionwithout a null check, this will crash. Recommend populating with the ONNX Runtime version (or"unknown") for safety and parity with other backends.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/backends/onnx/rac_plugin_entry_onnx.cpp` at line 50, Replace the null engine_version in the plugin descriptor (.engine_version = nullptr) with a stable C-string containing the ONNX Runtime version (or a fallback like "unknown") so callers can safely call strlen/printf without null checks; ensure you use a statically-allocated string or a string with process lifetime (e.g., a literal or the result of the runtime/version API) when setting engine_version in the rac_plugin_entry_onnx plugin descriptor.docs/plugin_loader_authoring.md-46-69 (1)
46-69:⚠️ Potential issue | 🟡 MinorExample vtable metadata doesn't match the actual struct layout.
The example initializes
.reserved_0/.reserved_1but omits.runtimes,.runtimes_count,.formats,.formats_count— the opposite of what the realrac_engine_metadata_texposes inrac_test_plugin.cpp(lines 45-48) andrac_plugin_entry_onnx.cpp(lines 53-56). A copy-paste of this snippet won't compile. Please sync the example with the current metadata struct (dropreserved_*, add the runtimes/formats fields).🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/plugin_loader_authoring.md` around lines 46 - 69, The g_myonnx_vtable metadata block does not match the current rac_engine_metadata_t layout; update the static const rac_engine_vtable_t g_myonnx_vtable initialization to remove the obsolete .reserved_0/.reserved_1 fields and instead include the current fields .runtimes, .runtimes_count, .formats, and .formats_count in the metadata sub-struct (and ensure their order/presence matches rac_engine_metadata_t as used in rac_test_plugin.cpp and rac_plugin_entry_onnx.cpp); leave other vtable members (capability_check, on_unload, g_myonnx_llm_ops, etc.) as-is.sdk/runanywhere-commons/tests/CMakeLists.txt-82-97 (1)
82-97:⚠️ Potential issue | 🟡 MinorPlugin entry symbol won't export on MSVC due to CMake visibility preset.
The fixture manually adds
__attribute__((visibility("default")))beforeRAC_PLUGIN_ENTRY_DEF(test_plugin), butRAC_PLUGIN_ENTRY_DEFexpands to just a function declaration with no visibility attribute. WithC_VISIBILITY_PRESET hiddenandCXX_VISIBILITY_PRESET hidden, MSVC will hide the symbol (the GCC/Clang visibility attribute is ignored).dlsym()will fail to findrac_plugin_entry_test_pluginon Windows, causing the loader tests to fail.Update
RAC_PLUGIN_ENTRY_DEFinrac_plugin_entry.hto use a portable export macro (following the pattern ofRAC_APIinrac_types.h:__declspec(dllexport)on MSVC,__attribute__((visibility("default")))on GCC/Clang), then remove the manual visibility attribute from the fixture.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/tests/CMakeLists.txt` around lines 82 - 97, The plugin entry symbol is hidden on MSVC because C_VISIBILITY_PRESET/CXX_VISIBILITY_PRESET hide symbols and the fixture's GCC visibility attribute is ignored; update rac_plugin_entry.h so RAC_PLUGIN_ENTRY_DEF uses a portable export macro (follow RAC_API in rac_types.h) that expands to __declspec(dllexport) on MSVC and __attribute__((visibility("default"))) on GCC/Clang, then apply that macro to the RAC_PLUGIN_ENTRY_DEF declaration (so rac_plugin_entry_test_plugin is exported) and remove the manual __attribute__((visibility("default"))) from the test fixture.sdk/runanywhere-commons/src/router/rac_hardware_profile.cpp-94-108 (1)
94-108:⚠️ Potential issue | 🟡 MinorProbe vs. documented contract drift: CUDA/Vulkan only check that the loader is present, not that a device exists.
The header contract for these flags reads:
has_cuda→ "NVIDIA CUDA driver + at least 1 device node."has_vulkan→ "Vulkan loader + at least 1 physical device."
detect_cuda_linuxdoes gate on/dev/nvidiactlexisting, which approximates the "device node" claim, butdetect_vulkan_linuxonly callsdlopen("libvulkan.so.1", ...)— a present loader does not imply a usable physical device (common on CI containers and headless VMs shipping the Vulkan loader but zero adapters). The "conservative, prefer false-negative" philosophy in the file header is violated here: a box with only the loader will reporthas_vulkan=trueand the router will cheerfully route Vulkan-preferring plugins to it.Two low-cost options:
- Weaken the header doc to match the probe ("Vulkan loader present" only), or
- Extend the probe: after
dlopen,dlsymvkCreateInstance/vkEnumeratePhysicalDevices, create a throwaway instance, and verifyphysicalDeviceCount > 0before returning true.Either is fine; keeping the header contract authoritative makes (2) the preferable fix. Same consideration applies to the NNAPI / QNN
dlopen-only probes in the Android block — those at least combine a device-node stat for QNN, but NNAPI is loader-only.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/router/rac_hardware_profile.cpp` around lines 94 - 108, The current detect_vulkan_linux() only checks for the Vulkan loader via dlopen which violates the header contract that requires "Vulkan loader + at least 1 physical device"; update detect_vulkan_linux() to, after dlopen("libvulkan.so.1"), use dlsym to load vkCreateInstance and vkEnumeratePhysicalDevices, create a temporary VkInstance (use minimal VkApplicationInfo/VkInstanceCreateInfo), call vkEnumeratePhysicalDevices to get the device count, and only return true if count > 0; ensure proper cleanup (destroy instance if created, dlclose the library) and treat any failure or missing symbols as false. Also review detect_cuda_linux() for consistency (it already stats /dev/nvidiactl but ensure it still returns false on dlopen/dlsym failures) so both functions match the documented "loader + device" semantics.sdk/runanywhere-flutter/packages/runanywhere/lib/core/types/model_types.dart-166-190 (1)
166-190:⚠️ Potential issue | 🟡 Minor
ModelCategory.fromProtosilently coercesUNSPECIFIEDand future proto cases toaudio.The fallback after the
MODEL_CATEGORY_EMBEDDINGcheck returnsModelCategory.audiofor any value that didn't match above. The comment documents the AUDIO+VAD collapse, but the same branch is also hit by:
MODEL_CATEGORY_UNSPECIFIED(proto3 default for unset fields) — an un-initializedcategoryfield on the wire becomes "Audio Processing", which is misleading (and likely undesirable for a language/vision catalog row).- Any future
ModelCategoryvalue added tomodel_types.protobefore the Dart enum catches up.The Dart
ModelCategoryenum has nounknowncase (unlikeModelFormat/InferenceFramework), so pick a safer default and handleUNSPECIFIEDexplicitly, e.g.:🩹 Proposed fix
static ModelCategory fromProto(pb.ModelCategory proto) { + if (proto == pb.ModelCategory.MODEL_CATEGORY_UNSPECIFIED) { + // Proto default / unset — fall back to the most common category rather + // than silently labeling the row as audio. + return ModelCategory.language; + } if (proto == pb.ModelCategory.MODEL_CATEGORY_LANGUAGE) { return ModelCategory.language; } ... - // AUDIO + VAD both map to the Dart audio case + // AUDIO + VAD both map to the Dart audio case; any future proto case + // added upstream also lands here until this bridge is updated. return ModelCategory.audio; }Long-term: consider adding a
ModelCategory.unknowncase for symmetry with the other bridges — that would also remove the need to pick an arbitrary fallback here.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-flutter/packages/runanywhere/lib/core/types/model_types.dart` around lines 166 - 190, ModelCategory.fromProto currently falls through to ModelCategory.audio for any unmatched proto value, causing MODEL_CATEGORY_UNSPECIFIED and future proto additions to be misclassified; update the mapping to explicitly handle pb.ModelCategory.MODEL_CATEGORY_UNSPECIFIED (return a new Dart enum case ModelCategory.unknown) and map only pb.ModelCategory.MODEL_CATEGORY_AUDIO and pb.ModelCategory.MODEL_CATEGORY_VAD to ModelCategory.audio, then add ModelCategory.unknown to the Dart ModelCategory enum so unmatched/future proto values map to unknown instead of audio; adjust any callers/serializers that assume the old enum shape accordingly.sdk/runanywhere-commons/src/plugin/plugin_loader.cpp-74-88 (1)
74-88:⚠️ Potential issue | 🟡 Minor
entry_symbol_from_pathusesfind('.')— breaks on versioned dylibs and dotted plugin names.After
last_sep,sis just the basename (no directory), but the extension strip uses the first dot, not the last. That gives the wrong symbol whenever the basename contains more than one dot:
Input basename Current result Expected libfoo.sorac_plugin_entry_foorac_plugin_entry_foo✅libfoo.1.dylibrac_plugin_entry_foorac_plugin_entry_foo.1❌ (should strip only.dylib)libfoo.1.2.3.dylibrac_plugin_entry_foorac_plugin_entry_foo.1.2.3❌libruntime.plugin.sorac_plugin_entry_runtimerac_plugin_entry_runtime.plugin❌macOS in particular ships versioned dylibs with this exact layout (
libllama.1.0.dylib), and Linux symlinked.so.Nvariants are common. Either switch to stripping by the well-known extension set, or use the last dot:🩹 Quick fix
- // Drop file extension. - auto dot = s.find('.'); - if (dot != std::string::npos) s.erase(dot); + // Drop file extension — use the last dot so versioned names like + // "libfoo.1.0.dylib" strip only ".dylib". + auto dot = s.rfind('.'); + if (dot != std::string::npos) s.erase(dot);For full robustness against
libfoo.so.1(trailing version after the extension on Linux SONAMEs), consider a small loop / a known-suffix list (.so,.dylib,.dll,.so.<N>).🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/src/plugin/plugin_loader.cpp` around lines 74 - 88, The basename-to-symbol logic in entry_symbol_from_path incorrectly strips at the first dot (variable 'dot'), which drops version segments and dotted plugin names; change the extension removal to either find the last dot (use s.find_last_of('.') instead of s.find('.')) or implement suffix-aware stripping that removes known extensions (e.g., ".so", ".dylib", ".dll") and optional trailing version components (like ".so.1" or multiple ".N" segments) while preserving any prior dot-separated parts (so s retains "foo.1.2.3" for "libfoo.1.2.3.dylib"); update the code around variables s, last_sep and dot (or replace 'dot' logic) accordingly and ensure tests cover names like "libfoo.1.dylib", "libfoo.so.1", and "libruntime.plugin.so".sdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry.h-123-166 (1)
123-166:⚠️ Potential issue | 🟡 MinorFix MSVC linker symbol name in documentation to match macro export.
Line 125 instructs users to use
/INCLUDE:_g_rac_plugin_autoreg_<name>, but the macro on line 166 exportsrac_plugin_static_marker_##name. Users following the current documentation on MSVC would fail to prevent static plugin TUs from being stripped.Documentation fix
- * - MSVC: add `/INCLUDE:_g_rac_plugin_autoreg_<name>` per plugin + * - MSVC: add `/INCLUDE:rac_plugin_static_marker_<name>` per plugin🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@sdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry.h` around lines 123 - 166, Update the MSVC linker instruction to reference the actual exported symbol from the macro: replace `/INCLUDE:_g_rac_plugin_autoreg_<name>` with `/INCLUDE:rac_plugin_static_marker_<name>` (matching the extern "C" symbol produced by the RAC_STATIC_PLUGIN_REGISTER macro, i.e., rac_plugin_static_marker_##name). Ensure the documentation text around RAC_STATIC_PLUGIN_REGISTER and the example uses the corrected symbol name so MSVC users can force-include the TU.
Comment on lines
+60
to
+67
| - name: Install Dart plugin (protoc-gen-dart) | ||
| run: | | ||
| if command -v dart >/dev/null 2>&1; then | ||
| dart pub global activate protoc_plugin 21.1.2 | ||
| echo "$HOME/.pub-cache/bin" >> "$GITHUB_PATH" | ||
| else | ||
| echo "::warning::dart not found on macos-14 runner; Dart codegen skipped" | ||
| fi |
There was a problem hiding this comment.
Drift check silently passes when Dart is unavailable.
macos-14 runners do not ship with dart preinstalled, so this step emits a warning and generate_dart.sh is never invoked by generate_all.sh. Because the committed Dart bindings under sdk/runanywhere-flutter/packages/runanywhere/lib/generated/** are not regenerated, git diff --exit-code on line 91 reports no drift even when a contributor edits idl/*.proto without regenerating Dart (or hand-edits a generated Dart file). The gate advertised in the workflow header ("any .proto … without regenerating the committed language bindings … this job fails") does not hold for Dart.
Either install Dart unconditionally (e.g., dart-lang/setup-dart@v1) or fail the job when dart is missing rather than warning — the drift guarantee is only as strong as its weakest language.
🛡️ Suggested change
- - name: Install Dart plugin (protoc-gen-dart)
- run: |
- if command -v dart >/dev/null 2>&1; then
- dart pub global activate protoc_plugin 21.1.2
- echo "$HOME/.pub-cache/bin" >> "$GITHUB_PATH"
- else
- echo "::warning::dart not found on macos-14 runner; Dart codegen skipped"
- fi
+ - uses: dart-lang/setup-dart@v1
+ with:
+ sdk: stable
+ - name: Install Dart plugin (protoc-gen-dart)
+ run: |
+ dart pub global activate protoc_plugin 21.1.2
+ echo "$HOME/.pub-cache/bin" >> "$GITHUB_PATH"🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.github/workflows/idl-drift-check.yml around lines 60 - 67, The macos step
that conditionally skips Dart makes the drift check unsound; modify the "Install
Dart plugin (protoc-gen-dart)" step so Dart is guaranteed (either install Dart
using dart-lang/setup-dart@v1 before activating protoc_plugin, or replace the
current else warning with an explicit exit 1), ensuring generate_all.sh will
invoke generate_dart.sh and that protoc_plugin (protoc-gen-dart) activation runs
on macos; update the run block that currently checks `command -v dart` to
perform a setup action or fail the job when dart is missing.
Comment on lines
+13
to
+16
| # The generated headers live inside sdk/runanywhere-commons so the C ABI shim | ||
| # layer can `#include "runanywhere/idl/model_types.pb.h"` for | ||
| # proto-encoded wire conversions. CMake's `idl/CMakeLists.txt` generates the | ||
| # same files at build time for the `rac_idl` library; this script keeps a |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Check whether committed/generated headers and consumers agree on the include path.
set -euo pipefail
echo "Generated C++ proto headers:"
fd '.*\.pb\.h$' sdk/runanywhere-commons/src/generated/proto || true
echo
echo "C++ proto include sites:"
rg -n '#include\s+["<].*\.pb\.h[">]' sdk/runanywhere-commons || trueRepository: RunanywhereAI/runanywhere-sdks
Length of output: 728
🏁 Script executed:
cat -n idl/codegen/generate_cpp.sh | head -50Repository: RunanywhereAI/runanywhere-sdks
Length of output: 1587
🏁 Script executed:
# Check the protoc command invocations to understand output path structure
rg -A 5 'protoc.*--cpp_out' idl/codegen/generate_cpp.shRepository: RunanywhereAI/runanywhere-sdks
Length of output: 268
🏁 Script executed:
# Find C ABI shim layer and files referencing the documented include path
rg -r '#include.*runanywhere/idl' --type cpp --type c || true
echo "---"
# Also check for any usage of the documented include path
rg 'runanywhere/idl/.*\.pb\.h' || trueRepository: RunanywhereAI/runanywhere-sdks
Length of output: 649
🏁 Script executed:
# Look for C ABI shim layer files
fd -i 'abi|shim' sdk/runanywhere-commons --type f | head -20Repository: RunanywhereAI/runanywhere-sdks
Length of output: 139
🏁 Script executed:
# Check CMakeLists.txt for include path configuration
find . -name CMakeLists.txt -exec grep -l 'runanywhere-commons\|proto\|idl' {} \; | head -5Repository: RunanywhereAI/runanywhere-sdks
Length of output: 522
🏁 Script executed:
cat idl/CMakeLists.txtRepository: RunanywhereAI/runanywhere-sdks
Length of output: 1819
🏁 Script executed:
cat sdk/runanywhere-commons/tests/test_plugin_loader_abi_mismatch.cppRepository: RunanywhereAI/runanywhere-sdks
Length of output: 1837
🏁 Script executed:
# Search for actual consumer code that links against rac_idl or uses the proto headers
rg 'target_link_libraries.*rac_idl|link_libraries.*rac_idl' --type cmakeRepository: RunanywhereAI/runanywhere-sdks
Length of output: 152
🏁 Script executed:
# Check test CMakeLists.txt to see how tests consume the proto headers
head -100 sdk/runanywhere-commons/tests/CMakeLists.txt | grep -A 5 -B 5 'rac_idl\|model_types'Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
Align the generated C++ include path with the documented consumer interface.
The script documents that consumers use #include "runanywhere/idl/model_types.pb.h", but the protoc invocation with --proto_path="${REPO_ROOT}/idl" and --cpp_out="${OUT_DIR}" (where ${OUT_DIR} is sdk/runanywhere-commons/src/generated/proto) generates headers directly at that output directory without the runanywhere/idl/ prefix. The CMakeLists.txt target_include_directories() configuration only exposes the bare filenames (e.g., #include "model_types.pb.h"), not the documented path. Any consumer following the documented include path will fail to compile.
Either adjust the protoc invocation to generate files under a runanywhere/idl/ subdirectory, or update the documentation to reflect the actual include paths used in the build.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@idl/codegen/generate_cpp.sh` around lines 13 - 16, The generated C++ headers
are emitted directly into ${OUT_DIR} but the docs and consumers expect `#include`
"runanywhere/idl/model_types.pb.h"; update the protoc invocation in
generate_cpp.sh (the line invoking protoc with --proto_path="${REPO_ROOT}/idl"
and --cpp_out="${OUT_DIR}") to emit files under a runanywhere/idl/ subdirectory
(so generated headers match the documented include path), or alternatively
update the documentation/CMake target_include_directories() notes to document
the bare include names (e.g., "model_types.pb.h"); modify whichever is simpler
to keep the protoc/OUT_DIR behavior and documented include path consistent.
Comment on lines
+49
to
+51
| // Barge-in behavior. | ||
| bool enable_barge_in = 8; // default true | ||
| int32 barge_in_threshold_ms = 9; // default 200 |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
rg -n 'enable_barge_in|optional bool enable_barge_in|disable_barge_in' idl
rg -n 'proto3_optional|has_.*enable_barge_in|hasEnableBargeIn|enableBargeIn.*case' .Repository: RunanywhereAI/runanywhere-sdks
Length of output: 273
🏁 Script executed:
cat -n idl/solutions.proto | sed -n '40,60p'Repository: RunanywhereAI/runanywhere-sdks
Length of output: 902
🏁 Script executed:
# Check if the field is already optional
rg -A 3 -B 3 'enable_barge_in' idl/solutions.protoRepository: RunanywhereAI/runanywhere-sdks
Length of output: 258
🏁 Script executed:
# Check if other generated files also have presence tracking
find . -name "*.pb.*" -type f | head -20 | xargs grep -l "hasEnableBargeIn\|EnableBargeIn" 2>/dev/null | head -10Repository: RunanywhereAI/runanywhere-sdks
Length of output: 213
🏁 Script executed:
# Check C++ generated code
rg -A 5 -B 5 'enable_barge_in' ./sdk/runanywhere-commons/src/generated/proto/solutions.pb.h | head -40Repository: RunanywhereAI/runanywhere-sdks
Length of output: 1197
🏁 Script executed:
# Check Dart generated code more thoroughly
rg -A 10 -B 10 'hasEnableBargeIn' ./sdk/runanywhere-flutter/packages/runanywhere/lib/generated/solutions.pb.dartRepository: RunanywhereAI/runanywhere-sdks
Length of output: 725
🏁 Script executed:
# Check if other bool fields also have has methods in Dart
rg 'has[A-Z][a-zA-Z]*\(\) => \$_has' ./sdk/runanywhere-flutter/packages/runanywhere/lib/generated/solutions.pb.dart | head -20Repository: RunanywhereAI/runanywhere-sdks
Length of output: 935
Make the default-true barge-in flag representable across all generators.
A plain proto3 bool defaults to false and lacks presence semantics, preventing the core (C++) from distinguishing "unset, use default true" from "caller explicitly set false." Although Dart's protoc plugin auto-generates presence tracking, C++ does not, creating inconsistency. Use optional bool to ensure all generators properly preserve presence.
Proposed proto change
- bool enable_barge_in = 8; // default true
+ optional bool enable_barge_in = 8; // default true when unset📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| // Barge-in behavior. | |
| bool enable_barge_in = 8; // default true | |
| int32 barge_in_threshold_ms = 9; // default 200 | |
| // Barge-in behavior. | |
| optional bool enable_barge_in = 8; // default true when unset | |
| int32 barge_in_threshold_ms = 9; // default 200 |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@idl/solutions.proto` around lines 49 - 51, Change the plain proto3 bool field
enable_barge_in in idl/solutions.proto to an optional bool so presence is
preserved across all language generators (allowing the C++ core to distinguish
"unset (use default true)" from "explicitly false"); keep the semantic default
(documented comment "default true" / leave barge_in_threshold_ms as-is) and
update any server/client code that reads enable_barge_in to check presence
before applying the default behavior.
Comment on lines
+38
to
+43
| PROTOC_EXPECTED_MAJOR="25" | ||
| SWIFT_PROTOBUF_EXPECTED="1.27" | ||
| WIRE_EXPECTED="4.9" | ||
| PROTOC_PLUGIN_DART_EXPECTED="21.1.2" | ||
| TS_PROTO_EXPECTED="1.181" | ||
| PYTHON_PROTOBUF_EXPECTED="4.25" |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Show declared expected versions and whether they are actually compared.
rg -n -C2 'EXPECTED|npm install -g|pip install|rc=1|--version|protoc-gen' scripts/setup-toolchain.sh
# ShellCheck already points at the same symptom for several expected-version vars.
# This command is read-only and only reports if shellcheck is available.
if command -v shellcheck >/dev/null 2>&1; then
shellcheck scripts/setup-toolchain.sh || true
fiRepository: RunanywhereAI/runanywhere-sdks
Length of output: 3564
🏁 Script executed:
# First, let's examine the complete setup-toolchain.sh file to understand its structure
wc -l scripts/setup-toolchain.sh && echo "---" && head -50 scripts/setup-toolchain.shRepository: RunanywhereAI/runanywhere-sdks
Length of output: 1577
🏁 Script executed:
# Search for all references to the expected version variables to confirm usage
rg -n 'PROTOC_EXPECTED_MAJOR|SWIFT_PROTOBUF_EXPECTED|WIRE_EXPECTED' scripts/setup-toolchain.shRepository: RunanywhereAI/runanywhere-sdks
Length of output: 160
🏁 Script executed:
# Check if these variables are exported or used by external scripts
git ls-files | xargs rg -l 'PROTOC_EXPECTED_MAJOR|SWIFT_PROTOBUF_EXPECTED|WIRE_EXPECTED'Repository: RunanywhereAI/runanywhere-sdks
Length of output: 283
🏁 Script executed:
# Examine the check_versions() function more carefully to see exit code behavior
sed -n '130,170p' scripts/setup-toolchain.shRepository: RunanywhereAI/runanywhere-sdks
Length of output: 1375
🏁 Script executed:
# Check install functions to verify version pinning behavior
sed -n '57,128p' scripts/setup-toolchain.shRepository: RunanywhereAI/runanywhere-sdks
Length of output: 2318
🏁 Script executed:
# Verify the exact versions being installed vs expected
rg -A2 'npm install|pip install|brew install|dart pub' scripts/setup-toolchain.shRepository: RunanywhereAI/runanywhere-sdks
Length of output: 861
Enforce the pinned tool versions instead of only declaring them.
The script claims byte-identical codegen, but three expected versions (PROTOC_EXPECTED_MAJOR, SWIFT_PROTOBUF_EXPECTED, WIRE_EXPECTED) are unused, and remaining pinned versions allow floating resolution instead of exact matches:
brew/aptinstall unpinned (protoc, swift-protobuf, wire-compiler)npm install "ts-proto@^${TS_PROTO_EXPECTED}"uses caret range, not exact versionpip install "protobuf>=${PYTHON_PROTOBUF_EXPECTED},<5"allows 4.25–4.99.x range, not exact versioncheck_versions()only fails on missingprotoc, not on missing or mismatched protoc-gen-swift, protoc-gen-dart, or ts-proto
Local regeneration can silently drift from CI. --check should validate exact versions and fail consistently on any missing codegen tool.
Suggested direction
+PROTOC_EXPECTED_MAJOR="25"
+SWIFT_PROTOBUF_EXPECTED="1.27"
+WIRE_EXPECTED="4.9"
PROTOC_PLUGIN_DART_EXPECTED="21.1.2"
TS_PROTO_EXPECTED="1.181"
PYTHON_PROTOBUF_EXPECTED="4.25"
+
+version_has_prefix() {
+ case "$1" in
+ "$2"*) return 0 ;;
+ *) return 1 ;;
+ esac
+}
+
+mark_version_mismatch() {
+ echo "$1: expected $2.x, got $3" >&2
+ return 1
+}
@@
- npm install -g "ts-proto@^${TS_PROTO_EXPECTED}" protobufjs
+ npm install -g "ts-proto@${TS_PROTO_EXPECTED}" protobufjs
@@
- python3 -m pip install --user --upgrade "protobuf>=${PYTHON_PROTOBUF_EXPECTED},<5" grpcio-tools
+ python3 -m pip install --user --upgrade "protobuf>=${PYTHON_PROTOBUF_EXPECTED},<4.26" grpcio-tools
@@
if have protoc; then
- echo "protoc: $(protoc --version)"
+ local protoc_version
+ protoc_version="$(protoc --version | awk '{print $2}')"
+ echo "protoc: ${protoc_version}"
+ version_has_prefix "${protoc_version}" "${PROTOC_EXPECTED_MAJOR}." || {
+ mark_version_mismatch "protoc" "${PROTOC_EXPECTED_MAJOR}" "${protoc_version}"
+ rc=1
+ }
@@
if have protoc-gen-swift; then
echo "protoc-gen-swift: $(protoc-gen-swift --version 2>/dev/null || echo 'present')"
else
echo "protoc-gen-swift: MISSING (Swift codegen will fail)" >&2
+ rc=1
@@
if have protoc-gen-dart; then
echo "protoc-gen-dart: present"
else
echo "protoc-gen-dart: MISSING (Dart codegen will fail)" >&2
+ rc=1
@@
if have npm && [ -x "$(npm root -g 2>/dev/null)/ts-proto/protoc-gen-ts_proto" ]; then
echo "ts-proto: present"
else
echo "ts-proto: MISSING (TS codegen will fail)" >&2
+ rc=1
@@
if have python3 && python3 -c "import google.protobuf" >/dev/null 2>&1; then
echo "python-protobuf: present"
else
echo "python-protobuf: MISSING (Python codegen will fail)" >&2
+ rc=1🧰 Tools
🪛 Shellcheck (0.11.0)
[warning] 38-38: PROTOC_EXPECTED_MAJOR appears unused. Verify use (or export if used externally).
(SC2034)
[warning] 39-39: SWIFT_PROTOBUF_EXPECTED appears unused. Verify use (or export if used externally).
(SC2034)
[warning] 40-40: WIRE_EXPECTED appears unused. Verify use (or export if used externally).
(SC2034)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@scripts/setup-toolchain.sh` around lines 38 - 43, The script currently only
declares expected versions (PROTOC_EXPECTED_MAJOR, SWIFT_PROTOBUF_EXPECTED,
WIRE_EXPECTED, TS_PROTO_EXPECTED, PYTHON_PROTOBUF_EXPECTED) and uses loose
install specifiers and incomplete checks; update it to enforce exact pinned
versions: use the variables (PROTOC_EXPECTED_MAJOR, SWIFT_PROTOBUF_EXPECTED,
WIRE_EXPECTED, PROTOC_PLUGIN_DART_EXPECTED, TS_PROTO_EXPECTED,
PYTHON_PROTOBUF_EXPECTED) in installer commands so package managers install
exact versions (avoid caret/ranges, e.g. install ts‑proto@<exact> and pip
install protobuf==<exact>), change any apt/brew install invocations to target
specific releases or download exact binaries, and extend check_versions() to
verify exact versions for protoc (major match and ideally exact if available),
protoc-gen-swift, protoc-gen-dart, protoc-gen-dart plugin name
(protoc-gen-dart), ts-proto (ts-proto), swift-protobuf (swift-protobuf/wire
compiler as WIRE_EXPECTED) and fail with non-zero exit when any tool is missing
or version-mismatched; also ensure the previously unused constants
(PROTOC_EXPECTED_MAJOR, SWIFT_PROTOBUF_EXPECTED, WIRE_EXPECTED) are referenced
by these checks/installs so the script enforces byte-identical codegen.
Comment on lines
+259
to
+267
| auto* arr = static_cast<const char**>(std::malloc(n * sizeof(const char*))); | ||
| if (arr == nullptr) { | ||
| *out_names = nullptr; | ||
| return 0; | ||
| } | ||
| size_t i = 0; | ||
| for (auto& kv : s.by_name) { | ||
| arr[i++] = strdup(kv.first.c_str()); | ||
| } |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
rg -nP '\bstrdup\s*\(' --glob '*.{c,cc,cpp,cxx,h,hpp}' sdk/runanywhere-commons
rg -n 'MSVC|WIN32|_WIN32|_strdup' sdk/runanywhere-commons -C 2Repository: RunanywhereAI/runanywhere-sdks
Length of output: 50386
🏁 Script executed:
head -n 280 sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cpp | tail -n 30Repository: RunanywhereAI/runanywhere-sdks
Length of output: 1065
🏁 Script executed:
rg -n 'strdup' sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cpp -B 2 -A 2Repository: RunanywhereAI/runanywhere-sdks
Length of output: 217
🏁 Script executed:
grep -n 'rac_strdup' sdk/runanywhere-commons/include/rac/core/rac_types.h -A 5Repository: RunanywhereAI/runanywhere-sdks
Length of output: 170
🏁 Script executed:
rg -n 'rac_strdup' sdk/runanywhere-commons/src -A 3 | head -50Repository: RunanywhereAI/runanywhere-sdks
Length of output: 4397
🏁 Script executed:
find sdk/runanywhere-commons -name "rac_memory.cpp" -o -name "*memory*" | grep -E '\.(cpp|c)$'Repository: RunanywhereAI/runanywhere-sdks
Length of output: 121
🏁 Script executed:
grep -r 'char\*\*' sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cpp -B 5 -A 10 | head -60Repository: RunanywhereAI/runanywhere-sdks
Length of output: 724
🏁 Script executed:
cat sdk/runanywhere-commons/src/core/rac_memory.cpp | head -100Repository: RunanywhereAI/runanywhere-sdks
Length of output: 1035
🏁 Script executed:
grep -n 'rac_strdup' sdk/runanywhere-commons/src/core/rac_memory.cpp -A 8Repository: RunanywhereAI/runanywhere-sdks
Length of output: 336
🏁 Script executed:
grep -n 'for.*strdup\|for.*malloc' sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cpp -B 3 -A 5Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
🏁 Script executed:
rg 'strdup' sdk/runanywhere-commons/src/plugin/ -lRepository: RunanywhereAI/runanywhere-sdks
Length of output: 194
🏁 Script executed:
rg 'strdup' sdk/runanywhere-commons/src/plugin/plugin_registry_internal.h -B 2 -A 2Repository: RunanywhereAI/runanywhere-sdks
Length of output: 363
🏁 Script executed:
sed -n '250,280p' sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cppRepository: RunanywhereAI/runanywhere-sdks
Length of output: 1134
🏁 Script executed:
grep -n 'snapshot_names' sdk/runanywhere-commons/include -r -A 5 -B 2Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
🏁 Script executed:
find sdk/runanywhere-commons/include -name "*.h" | xargs grep -l 'plugin_registry'Repository: RunanywhereAI/runanywhere-sdks
Length of output: 135
🏁 Script executed:
grep -n 'snapshot_names\|plugin_registry' sdk/runanywhere-commons/include/rac/plugin/*.h 2>/dev/null | head -30Repository: RunanywhereAI/runanywhere-sdks
Length of output: 214
🏁 Script executed:
grep -n 'snapshot_names' sdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry.h -B 3 -A 8Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
🏁 Script executed:
grep -n 'free\|strdup' sdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry.h | head -20Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
🏁 Script executed:
grep -n 'rac_plugin_registry_snapshot_names' sdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry.h -B 3 -A 10Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
🏁 Script executed:
grep -n 'rac_plugin_registry_snapshot_names' sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cpp -B 5 | head -20Repository: RunanywhereAI/runanywhere-sdks
Length of output: 237
🏁 Script executed:
sed -n '240,275p' sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cppRepository: RunanywhereAI/runanywhere-sdks
Length of output: 1141
🏁 Script executed:
rg 'extern.*snapshot_names|RAC_API.*snapshot_names' sdk/runanywhere-commons -A 2Repository: RunanywhereAI/runanywhere-sdks
Length of output: 56
Replace POSIX strdup with portable malloc+memcpy and add cleanup on allocation failure.
strdup is not available on MSVC (Windows), and the current code has no error handling if allocation fails mid-loop—it would return a partially-invalid snapshot as if all names were copied. Use the proposed portable approach with proper cleanup.
Portable allocation fix
size_t i = 0;
for (auto& kv : s.by_name) {
- arr[i++] = strdup(kv.first.c_str());
+ const std::string& name = kv.first;
+ auto* copy = static_cast<char*>(std::malloc(name.size() + 1));
+ if (copy == nullptr) {
+ for (size_t j = 0; j < i; ++j) {
+ std::free(const_cast<char*>(arr[j]));
+ }
+ std::free(arr);
+ *out_names = nullptr;
+ return 0;
+ }
+ std::memcpy(copy, name.c_str(), name.size() + 1);
+ arr[i++] = copy;
}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@sdk/runanywhere-commons/src/plugin/rac_plugin_registry.cpp` around lines 259
- 267, The loop that uses strdup to copy keys from s.by_name into arr must be
made portable and robust: replace strdup(kv.first.c_str()) with allocating len =
kv.first.size() + 1 bytes via malloc, memcpy (or memcpy/memmove) the bytes
including the terminating NUL, then assign to arr[i]; after each malloc check
for NULL and on any failure free all previously allocated arr[j] strings and
free arr, set *out_names = nullptr and return 0; on success set *out_names = arr
and return the count. Ensure you reference and update arr, s.by_name, out_names
and the loop that currently uses strdup so no partial snapshot is returned and
code is MSVC-portable.
Comment on lines
+92
to
+134
| RouteResult EngineRouter::route(const RouteRequest& req) const { | ||
| auto candidates = snapshot_for_primitive(req.primitive); | ||
| if (candidates.empty()) { | ||
| return RouteResult{nullptr, -1, "no plugin serves this primitive"}; | ||
| } | ||
|
|
||
| /* Score every candidate. */ | ||
| struct Scored { | ||
| int score; | ||
| const rac_engine_vtable_t* vt; | ||
| }; | ||
| std::vector<Scored> scored; | ||
| scored.reserve(candidates.size()); | ||
| for (auto* vt : candidates) { | ||
| if (vt == nullptr) continue; | ||
| int s = score(*vt, req); | ||
| if (s > -1000) { | ||
| scored.push_back({s, vt}); | ||
| } | ||
| } | ||
| if (scored.empty()) { | ||
| if (!req.pinned_engine.empty() && req.no_fallback) { | ||
| return RouteResult{nullptr, -1, | ||
| std::string("pinned engine '") + | ||
| std::string(req.pinned_engine) + | ||
| "' not registered; no_fallback=true"}; | ||
| } | ||
| return RouteResult{nullptr, -1, "no eligible plugin (all hard-rejected)"}; | ||
| } | ||
|
|
||
| /* Stable sort: score desc, priority desc (tiebreak), name asc (final tiebreak). | ||
| * Determinism is required by the spec — same RouteRequest in same process | ||
| * MUST yield same winner across 1000 calls. */ | ||
| std::sort(scored.begin(), scored.end(), | ||
| [](const Scored& a, const Scored& b) { | ||
| if (a.score != b.score) return a.score > b.score; | ||
| if (a.vt->metadata.priority != b.vt->metadata.priority) { | ||
| return a.vt->metadata.priority > b.vt->metadata.priority; | ||
| } | ||
| return std::strcmp(a.vt->metadata.name, b.vt->metadata.name) < 0; | ||
| }); | ||
|
|
||
| return RouteResult{scored.front().vt, scored.front().score, {}}; |
There was a problem hiding this comment.
Pin plugin lifetime while routing.
route() snapshots raw vtable pointers, then dereferences them after the registry lock is gone. A concurrent unregister/dynamic unload can invalidate vt->metadata while scoring or tie-breaking. Hold a registry read lock through scoring, or return a snapshot that ref-counts/pins the plugin handle until routing completes.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@sdk/runanywhere-commons/src/router/rac_engine_router.cpp` around lines 92 -
134, EngineRouter::route currently grabs raw vtable pointers from
snapshot_for_primitive and then dereferences vt->metadata after the registry
lock may have been released, risking use-after-unload; fix by ensuring the
plugin lifetime is pinned while scoring/sorting: either have
snapshot_for_primitive return a snapshot of ref-counted/pinned plugin handles
(not raw rac_engine_vtable_t*), or acquire and hold the registry read-lock for
the entire scoring and std::sort phase inside EngineRouter::route; update the
loop that builds scored (and the comparator that reads vt->metadata) to use the
pinned handle type or to run while holding the lock so vt->metadata cannot be
invalidated concurrently.
Comment on lines
+53
to
+68
| /* (4) RAC_FORCE_RUNTIME=cpu zeroes every has_* flag. */ | ||
| setenv("RAC_FORCE_RUNTIME", "cpu", 1); | ||
| HardwareProfile::refresh(); | ||
| const HardwareProfile& d = HardwareProfile::cached(); | ||
| bool any_accel = d.has_metal || d.has_ane || d.has_coreml || d.has_cuda || | ||
| d.has_vulkan || d.has_qnn || d.has_nnapi || d.has_webgpu; | ||
| if (any_accel) { | ||
| std::fprintf(stderr, " FAIL: RAC_FORCE_RUNTIME=cpu but accelerators detected\n"); ++fails; | ||
| } else { | ||
| std::fprintf(stdout, " ok: RAC_FORCE_RUNTIME=cpu disables every accelerator\n"); | ||
| } | ||
| if (!d.supports_runtime(RAC_RUNTIME_CPU)) { | ||
| std::fprintf(stderr, " FAIL: CPU still not supported under FORCE\n"); ++fails; | ||
| } | ||
| unsetenv("RAC_FORCE_RUNTIME"); | ||
| HardwareProfile::refresh(); /* leave cache in normal state for any later tests */ |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify whether this test is registered for all platforms or platform-gated.
set -euo pipefail
rg -n -C3 'test_hardware_profile|add_executable|add_test' sdk/runanywhere-commons/testsRepository: RunanywhereAI/runanywhere-sdks
Length of output: 24754
🏁 Script executed:
# Check if Commons supports Windows builds and look for WIN32 conditionals
rg -n "WIN32|_WIN32|MSVC" sdk/runanywhere-commons/tests/CMakeLists.txtRepository: RunanywhereAI/runanywhere-sdks
Length of output: 430
🏁 Script executed:
# Check the actual test file to confirm setenv/unsetenv usage
head -70 sdk/runanywhere-commons/tests/test_hardware_profile.cpp | tail -30Repository: RunanywhereAI/runanywhere-sdks
Length of output: 1498
🏁 Script executed:
# Search for existing environment variable portability patterns in the codebase
rg -n "setenv|unsetenv|_putenv" sdk/runanywhere-commons --type cpp --type hRepository: RunanywhereAI/runanywhere-sdks
Length of output: 269
Guard environment variable access with platform-specific wrapper.
setenv/unsetenv are POSIX-only APIs. This test is marked as "always built" (line 43 of CMakeLists.txt) without WIN32 guards, so it will fail to compile under the Windows/MSVC Commons build. Wrap the environment variable access in a small platform-conditional helper function.
Portable test helper
+#if defined(_WIN32)
+#include <cstdlib>
+static void set_env(const char* name, const char* value) {
+ _putenv_s(name, value);
+}
+static void unset_env(const char* name) {
+ _putenv_s(name, "");
+}
+#else
+static void set_env(const char* name, const char* value) {
+ setenv(name, value, 1);
+}
+static void unset_env(const char* name) {
+ unsetenv(name);
+}
+#endif
+
/* (4) RAC_FORCE_RUNTIME=cpu zeroes every has_* flag. */
- setenv("RAC_FORCE_RUNTIME", "cpu", 1);
+ set_env("RAC_FORCE_RUNTIME", "cpu");
HardwareProfile::refresh();
@@
- unsetenv("RAC_FORCE_RUNTIME");
+ unset_env("RAC_FORCE_RUNTIME");📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| /* (4) RAC_FORCE_RUNTIME=cpu zeroes every has_* flag. */ | |
| setenv("RAC_FORCE_RUNTIME", "cpu", 1); | |
| HardwareProfile::refresh(); | |
| const HardwareProfile& d = HardwareProfile::cached(); | |
| bool any_accel = d.has_metal || d.has_ane || d.has_coreml || d.has_cuda || | |
| d.has_vulkan || d.has_qnn || d.has_nnapi || d.has_webgpu; | |
| if (any_accel) { | |
| std::fprintf(stderr, " FAIL: RAC_FORCE_RUNTIME=cpu but accelerators detected\n"); ++fails; | |
| } else { | |
| std::fprintf(stdout, " ok: RAC_FORCE_RUNTIME=cpu disables every accelerator\n"); | |
| } | |
| if (!d.supports_runtime(RAC_RUNTIME_CPU)) { | |
| std::fprintf(stderr, " FAIL: CPU still not supported under FORCE\n"); ++fails; | |
| } | |
| unsetenv("RAC_FORCE_RUNTIME"); | |
| HardwareProfile::refresh(); /* leave cache in normal state for any later tests */ | |
| `#if` defined(_WIN32) | |
| `#include` <cstdlib> | |
| static void set_env(const char* name, const char* value) { | |
| _putenv_s(name, value); | |
| } | |
| static void unset_env(const char* name) { | |
| _putenv_s(name, ""); | |
| } | |
| `#else` | |
| static void set_env(const char* name, const char* value) { | |
| setenv(name, value, 1); | |
| } | |
| static void unset_env(const char* name) { | |
| unsetenv(name); | |
| } | |
| `#endif` | |
| /* (4) RAC_FORCE_RUNTIME=cpu zeroes every has_* flag. */ | |
| set_env("RAC_FORCE_RUNTIME", "cpu"); | |
| HardwareProfile::refresh(); | |
| const HardwareProfile& d = HardwareProfile::cached(); | |
| bool any_accel = d.has_metal || d.has_ane || d.has_coreml || d.has_cuda || | |
| d.has_vulkan || d.has_qnn || d.has_nnapi || d.has_webgpu; | |
| if (any_accel) { | |
| std::fprintf(stderr, " FAIL: RAC_FORCE_RUNTIME=cpu but accelerators detected\n"); ++fails; | |
| } else { | |
| std::fprintf(stdout, " ok: RAC_FORCE_RUNTIME=cpu disables every accelerator\n"); | |
| } | |
| if (!d.supports_runtime(RAC_RUNTIME_CPU)) { | |
| std::fprintf(stderr, " FAIL: CPU still not supported under FORCE\n"); ++fails; | |
| } | |
| unset_env("RAC_FORCE_RUNTIME"); | |
| HardwareProfile::refresh(); /* leave cache in normal state for any later tests */ |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@sdk/runanywhere-commons/tests/test_hardware_profile.cpp` around lines 53 -
68, The test uses POSIX setenv/unsetenv directly (lines calling
setenv("RAC_FORCE_RUNTIME", ...) and unsetenv(...)), which breaks MSVC/Windows
builds; add a small platform-conditional helper (e.g., SetTestEnv(const char*
name, const char* value) and UnsetTestEnv(const char* name)) that on POSIX calls
setenv/unsetenv and on Windows calls _putenv_s (or _putenv/_putenv_s semantics)
and then update the test to call SetTestEnv("RAC_FORCE_RUNTIME","cpu") and
UnsetTestEnv("RAC_FORCE_RUNTIME") around
HardwareProfile::refresh()/HardwareProfile::cached() usage so the test builds on
both platforms.
Comment on lines
+33
to
+42
| /// Decode from the IDL-generated Wire enum. Unknown → development. | ||
| static SDKEnvironment fromProto(pb.SDKEnvironment proto) { | ||
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_STAGING) { | ||
| return SDKEnvironment.staging; | ||
| } | ||
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_PRODUCTION) { | ||
| return SDKEnvironment.production; | ||
| } | ||
| return SDKEnvironment.development; | ||
| } |
There was a problem hiding this comment.
Use a safe fallback for unknown proto environments.
Mapping unknown or unspecified wire values to development can disable auth/sync and enable dev behavior in production flows. Prefer an explicit development match and default unknowns to production or throw.
Safer fallback
static SDKEnvironment fromProto(pb.SDKEnvironment proto) {
+ if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT) {
+ return SDKEnvironment.development;
+ }
if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_STAGING) {
return SDKEnvironment.staging;
}
if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_PRODUCTION) {
return SDKEnvironment.production;
}
- return SDKEnvironment.development;
+ return SDKEnvironment.production;
}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| /// Decode from the IDL-generated Wire enum. Unknown → development. | |
| static SDKEnvironment fromProto(pb.SDKEnvironment proto) { | |
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_STAGING) { | |
| return SDKEnvironment.staging; | |
| } | |
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_PRODUCTION) { | |
| return SDKEnvironment.production; | |
| } | |
| return SDKEnvironment.development; | |
| } | |
| /// Decode from the IDL-generated Wire enum. Unknown → production. | |
| static SDKEnvironment fromProto(pb.SDKEnvironment proto) { | |
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT) { | |
| return SDKEnvironment.development; | |
| } | |
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_STAGING) { | |
| return SDKEnvironment.staging; | |
| } | |
| if (proto == pb.SDKEnvironment.SDK_ENVIRONMENT_PRODUCTION) { | |
| return SDKEnvironment.production; | |
| } | |
| return SDKEnvironment.production; | |
| } |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In
`@sdk/runanywhere-flutter/packages/runanywhere/lib/public/configuration/sdk_environment.dart`
around lines 33 - 42, The current SDKEnvironment.fromProto maps any
non-staging/non-production proto to development, which can enable dev behavior
in real deployments; change fromProto to explicitly check for
pb.SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT and return
SDKEnvironment.development only in that case, return SDKEnvironment.production
for any unknown/unspecified values (or alternatively throw) so unknown wire
values do not default to development; update the function handling in
SDKEnvironment.fromProto accordingly, referencing
pb.SDKEnvironment.SDK_ENVIRONMENT_DEVELOPMENT, SDKEnvironment.development, and
SDKEnvironment.production.
sanchitmonga22
added a commit
that referenced
this pull request
Apr 23, 2026
Closes Wave F (GAP 11 legacy cleanup) — the final wave of the v2 architecture migration program. PR #494 ready to merge to main after this commit. Phase 29 — deprecate the legacy service registry surface: - sdk/runanywhere-commons/include/rac/core/rac_core.h: 4 entry points (rac_service_register_provider, rac_service_unregister_provider, rac_service_create, rac_service_list_providers) annotated with the new `RAC_DEPRECATED_LEGACY_SVC` macro. Macro expands to C++14 `[[deprecated]]` for clang/g++/MSVC with appropriate fallbacks. - sdk/runanywhere-commons/src/infrastructure/registry/service_registry.cpp: added `rac_legacy_warn_once(fn_name)` helper that emits a single RAC_LOG_WARNING per entry point on first invocation, thread-safe via std::atomic<bool> in a guarded map. Inserted into all 4 entry points. - docs/engine_plugin_authoring.md: new §"Migrating off the legacy service registry (GAP 11 Phase 29)" with the call-site translation table — every legacy call has its `rac_plugin_*` replacement. Phase 30 — audit the residue: - docs/gap11_audit_repoint.md NEW. `rg -c rac_service_*` across the monorepo found 88 references in 30 files: 4 in SDK frontends (Swift bridge + Flutter FFI), 56 in commons (incl. the 21 in the impl file itself, scheduled for `git rm` in v3), and 22 in engine plugins (dual-path bridges + JNI thunks). Per-call-site mechanical translation documented; physical repoint scheduled for v3 because each caller needs per-platform behavioral verification. Phase 31 — final v2 gate: - docs/gap11_final_gate_report.md NEW. All 7 spec Success Criteria addressed. 5 OK, 2 OK partial (the actual `git rm` + RAC_PLUGIN_API_VERSION bump are layout-incompatible struct removals by convention deferred to v3 — same pattern as Square Wire 3.x→4.x and gRPC Server→aio.server migrations). - docs/v2_migration_complete.md NEW. Comprehensive post-mortem covering all 33 phases across 6 waves. Includes the full architecture-as-built tree diagram, wave/GAP scoreboard with LOC delta per gap, "what v2 unlocks" summary, and the v3 deferral list. Verified: - service_registry.cpp compiles clean with -Wno-deprecated-declarations. - All 4 rac_service_* entry points reachable both at compile-time (with warning) and at runtime (with one-time log). - Migration table in engine_plugin_authoring.md cross-checked against the actual API in rac/plugin/rac_plugin_entry.h + rac/router/rac_route.h. Wave F complete. v2 architecture migration: done. Ready to merge to main as PR #494. What's deferred to v3 (per gap11_final_gate_report.md): - git rm service_registry.cpp + rac_capability_t / rac_service_provider_t - RAC_PLUGIN_API_VERSION 2u → 3u - Physical delete of Wave D orchestration bodies (~3,040 LOC) - Per-call-site repoint of 30 files (per gap11_audit_repoint.md) - Wave E (GAP 05 DAG runtime primitives) — gated on a second pipeline Made-with: Cursor
sanchitmonga22
added a commit
that referenced
this pull request
Apr 23, 2026
Three independent agents audited the branch on Wave-F-final HEAD, cross-referencing v2_gap_specs/* with docs/gap0*_final_gate_report.md and the actual code state. Findings converged on: - Waves A, B, C are substantively shipped: IDL + codegen, plugin ABI + dynamic loading + router, root CMake + presets + engines/ reorg, streaming adapter contracts in all 5 SDKs. - Wave D (GAP 08 frontend deletion) and Wave F (GAP 11 legacy removal) shipped *deprecation pressure*, not the *physical deletes* the gate prose initially described. The orchestration bodies marked @deprecated still execute; service_registry.cpp is still on disk; RAC_PLUGIN_API_VERSION is still 2u. The Kotlin streamVoiceSession function (the largest single Wave D target) lacks even the marker. - Two GAP 08 LOC ceilings are violated today: runanywhere.dart : 2,688 LOC (spec ≤ 500) VoiceSessionHandle.ts : 636 LOC (spec ≤ 250) - Aggregate diff vs branch start (8d1f851): 127 files, +3,845 / −6,095, net −2,250 LOC. The deletes are the 10 legacy build-*.sh scripts from GAP 07 Phase 7, not Wave D's ~3,040 LOC of orchestration (which is scheduled, not shipped). - No v2_gap_specs/GAP_11_*.md exists in the repo — gate report cites a missing spec; criteria reverse-engineered from the gate. - GAP 05 deferred per Wave E (no second pipeline yet). This commit: 1. wave_roadmap.md - Replaces the "all five waves done" framing with a per-wave spec-vs-reality table. - Adds an "Audit snapshot" section near the top so reviewers don't miss the deferral story. - Points at the new v2_remaining_work.md for the action list. 2. v2_remaining_work.md NEW - Single prioritized list (P0 build sanity → P1 streaming E2E → P2 Wave D physical deletes (10 platform-specific PRs) → P3 v3 cut-over → P4 spec-drift cleanups → P5 optional Wave E). - Each item cites the spec criterion + files + effort estimate pulled from the original plan budget. - Includes the audit methodology so the report is reproducible. 3. v2_migration_complete.md - Reframed from "Complete" tagline to "Status & Post-Mortem" ("not yet shippable as v2"). - Adds an "Audit reality check" section with a what-is-real vs what-is-deferred table. - Adds release-planning guidance: PR #494 = v2-foundation PR, v2 ship tag waits on Priority 2, v3 tag is Priority 3. Why now: the user asked for a current-state assessment + an updated view of remaining work. This commit is doc-only; no code changes. Audit transcript: 3 agents on feat/v2-architecture HEAD, cross-checking spec criteria against gate reports against actual files. All three converged on the same picture. Made-with: Cursor
sanchitmonga22
added a commit
that referenced
this pull request
Apr 23, 2026
…s flips Phase 16. Closes the v2 close-out program. All 16 phases complete on the single feat/v2-architecture branch (PR #494). What ships in this commit: 1. docs/v2_closeout_results.md NEW — comprehensive results report: - Per-file LOC delta table (10 in-place targets + 3 git-rm'd files) - Branch diff vs Phase 0 baseline e81fae3: 66 files, +6,028 / -6,772, net -744 LOC - Wave D total delete: -6,247 LOC across 13 files (3 full delete + 10 in-place shrink). 22% over the spec's 5,100±500 target, driven by the 3 zero-caller Kotlin files that the audit underestimated. - GAP 09 spec-criteria status flips: #1, #3, #4, #5, #6, #7, #8, #9 all moved from MISSING/PARTIAL to OK. - GAP 08 spec-criteria status flips: #1, #3, #5, #6, #7, #10 moved to OK; #4 (runanywhere.dart ≤500) stays DEFERRED with explicit rationale. - 8 bugs found + fixed during execution (CMakePresets schema, 5min vs 60s auth drift, grpc-swift v2 plugin name, grpc-swift v2 flag rename, 88-vs-131 orphan count, 3 zero-caller Kotlin files, AlamofireDownloadService already thin, EventBus no legacy block). - Tests passing: 9 + 10 + 8 across the 3 v2-closeout test suites. 2. docs/gap08_final_gate_report.md updated: - Added "POST-CLOSE-OUT UPDATE" callout pointing at v2_closeout_results.md. - Marker-only criteria are now backed by real deletes. 3. docs/gap09_final_gate_report.md updated: - Added "POST-CLOSE-OUT UPDATE" callout listing the specific phase-by-phase work that closed the previously-PARTIAL/MISSING criteria. 4. docs/wave_roadmap.md "Audit snapshot" table updated: - GAP 08 row: "Markers + audits only" → "−6,247 LOC actually deleted in v2 close-out Phases 6-14". - GAP 09 row: "Shipped partial" → "Shipped. All 9 spec criteria OK or OK-by-design". 5. docs/v2_remaining_work.md status banner: - "STATUS UPDATE (post-v2-closeout): P0, P1, P2 are DONE. What remains: P3 (v3 cut-over), P4 (spec-drift cleanups), P5 (Wave E — optional)." 6. docs/v2_migration_complete.md tagline flipped: - "READY TO SHIP as v2" (was "not yet shippable as v2" per the post-Wave-F audit). What's deferred to follow-up PRs (acknowledged honestly): - Dart runanywhere.dart (2,688 → ≤500): per-feature extension extraction across 79 methods. Multi-day Dart-specific refactor. - Kotlin CppBridgeAuth.kt (181 LOC remain) → 0: needs rac_auth_* JNI thunks; sequenced for safety per docs/v2_closeout_phase5_cabis.md. - Kotlin orphan natives (~95 declarations across 21 surviving CppBridge*.kt files): per-bridge cleanup PRs. - Per-platform behavioral verification: 60-sec auth refresh (Android), voice barge-in latency (iOS), download resume smoke check. All scheduled in docs/v2_closeout_device_verification.md. - Sample-app smoke automation: separate v2.x workstream. Verified locally: - All 3 v2-closeout test suites green: test_proto_event_dispatch (9/9), test_llm_thinking (10/10), parity_test_cpp (8/8 events match golden). - cmake --preset macos-release configures clean. - cmake --build --preset macos-release --target rac_commons builds clean (only intentional GAP 11 deprecated-warnings). The v2 architecture program is closed. Total v2-closeout commit count: 17 commits across 16 phases on feat/v2-architecture, all on a single branch / single PR. Made-with: Cursor
Comment on lines
+54
to
+63
| runs-on: ubuntu-22.04 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: ./.github/actions/setup-toolchain | ||
| with: | ||
| platform: sdk-only | ||
| - name: Setup Android SDK | ||
| uses: android-actions/setup-android@v3 | ||
| - name: Gradle build (no test) | ||
| working-directory: sdk/runanywhere-kotlin | ||
| run: ./gradlew build -x test --no-daemon || echo "::warning::Kotlin gradle build failed — non-blocking on PR" | ||
| - name: Install ninja + protobuf | ||
| run: sudo apt-get update && sudo apt-get install -y ninja-build libprotobuf-dev protobuf-compiler | ||
| - run: cmake --preset linux-debug | ||
| - run: cmake --build --preset linux-debug | ||
| - run: ctest --preset linux-debug | ||
|
|
||
| sdk_web: | ||
| needs: [detect, native_web] | ||
| if: | | ||
| always() && ( | ||
| needs.detect.outputs.sdk_web == 'true' || | ||
| needs.native_web.result == 'success' | ||
| ) | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 20 | ||
| linux-asan: |
Comment on lines
+64
to
+72
| runs-on: ubuntu-22.04 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: ./.github/actions/setup-toolchain | ||
| with: | ||
| platform: sdk-only | ||
| - name: Install web deps | ||
| working-directory: sdk/runanywhere-web | ||
| run: npm install | ||
| - name: Build TS (core then llamacpp then onnx) | ||
| working-directory: sdk/runanywhere-web | ||
| # build:ts must run before typecheck because llamacpp/onnx packages | ||
| # import from `@runanywhere/web`; tsc can only resolve those imports | ||
| # once the core package has produced its `dist/` (with .d.ts files). | ||
| run: npm run build:ts | ||
| - name: Typecheck (now that dist/ exists) | ||
| working-directory: sdk/runanywhere-web | ||
| run: npm run typecheck | ||
| - run: sudo apt-get update && sudo apt-get install -y ninja-build libprotobuf-dev protobuf-compiler | ||
| - run: cmake --preset linux-asan | ||
| - run: cmake --build --preset linux-asan | ||
| - run: ctest --preset linux-asan | ||
|
|
||
| sdk_flutter: | ||
| # Flutter consumes BOTH iOS and Android natives, so fire whenever either | ||
| # native-build job succeeded on this run, OR when Flutter SDK paths changed. | ||
| needs: [detect, native_ios, native_android] | ||
| if: | | ||
| always() && ( | ||
| needs.detect.outputs.sdk_flutter == 'true' || | ||
| needs.native_ios.result == 'success' || | ||
| needs.native_android.result == 'success' | ||
| ) | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 25 | ||
| ios-device: |
Comment on lines
+73
to
+80
| runs-on: macos-14 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: subosito/flutter-action@v2 | ||
| with: | ||
| channel: stable | ||
| - name: Flutter analyze (each package) | ||
| working-directory: sdk/runanywhere-flutter | ||
| run: | | ||
| for pkg in packages/*/; do | ||
| if [ -f "$pkg/pubspec.yaml" ]; then | ||
| echo "=== Analyzing $pkg ===" | ||
| (cd "$pkg" && flutter pub get && flutter analyze) || echo "::warning::flutter analyze failed in $pkg" | ||
| fi | ||
| done | ||
| - run: brew install protobuf | ||
| - run: cmake --preset ios-device | ||
| - run: cmake --build --preset ios-device --config Release | ||
|
|
||
| sdk_react_native: | ||
| # React Native consumes BOTH iOS and Android natives, so fire whenever either | ||
| # native-build job succeeded on this run, OR when RN SDK paths changed. | ||
| needs: [detect, native_ios, native_android] | ||
| if: | | ||
| always() && ( | ||
| needs.detect.outputs.sdk_react_native == 'true' || | ||
| needs.native_ios.result == 'success' || | ||
| needs.native_android.result == 'success' | ||
| ) | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 25 | ||
| android-arm64: |
Comment on lines
+81
to
+99
| runs-on: ubuntu-22.04 | ||
| env: | ||
| ANDROID_NDK_HOME: ${{ github.workspace }}/android-ndk-r27c | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: ./.github/actions/setup-toolchain | ||
| with: | ||
| platform: sdk-only | ||
| - name: Enable Corepack (for yarn@3.6.1 declared in packageManager) | ||
| run: corepack enable | ||
| - name: Install RN workspace | ||
| working-directory: sdk/runanywhere-react-native | ||
| - name: Install Android NDK | ||
| run: | | ||
| # The RN SDK uses yarn workspaces + yarn@3.6.1 via Corepack; fall | ||
| # back to npm install only as a last resort for older checkouts. | ||
| if [ -f yarn.lock ] || grep -q '"packageManager": "yarn@' package.json 2>/dev/null; then | ||
| yarn install --immutable || yarn install | ||
| else | ||
| npm install --legacy-peer-deps | ||
| fi | ||
| - name: Typecheck packages | ||
| working-directory: sdk/runanywhere-react-native | ||
| run: | | ||
| for pkg in packages/*/; do | ||
| if [ -f "$pkg/tsconfig.json" ]; then | ||
| echo "=== Typechecking $pkg ===" | ||
| (cd "$pkg" && npx tsc --noEmit) || echo "::warning::tsc failed in $pkg" | ||
| fi | ||
| done | ||
|
|
||
| # --------------------------------------------------------------------------- | ||
| # Lint jobs — fast, parallel, symmetric across all 5 SDKs. | ||
| # Each runs independently of the native builds and can fail a PR on its own. | ||
| # Path-filtered so a Swift-only PR doesn't run Kotlin/Web/Flutter/RN lints. | ||
| # --------------------------------------------------------------------------- | ||
|
|
||
| lint_swift: | ||
| needs: detect | ||
| if: needs.detect.outputs.sdk_swift == 'true' || needs.detect.outputs.workflows == 'true' | ||
| curl -sSL -o ndk.zip https://dl.google.com/android/repository/android-ndk-r27c-linux.zip | ||
| unzip -q ndk.zip | ||
| mv android-ndk-r27c "${ANDROID_NDK_HOME}" | ||
| - run: sudo apt-get update && sudo apt-get install -y ninja-build | ||
| - run: cmake --preset android-arm64 | ||
| - run: cmake --build --preset android-arm64 | ||
|
|
||
| # ============================================================================= | ||
| # Per-SDK frontend builds (call wrapper scripts, which internally drive cmake) | ||
| # ============================================================================= | ||
|
|
||
| swift-spm: |
Comment on lines
+111
to
+127
| runs-on: ubuntu-22.04 | ||
| needs: [android-arm64] | ||
| env: | ||
| ANDROID_NDK_HOME: ${{ github.workspace }}/android-ndk-r27c | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: ./.github/actions/setup-toolchain | ||
| with: | ||
| platform: sdk-only | ||
| - name: Lint Kotlin SDK (detekt + ktlint) | ||
| working-directory: sdk/runanywhere-kotlin | ||
| run: ./gradlew detekt ktlintCheck --no-daemon | ||
| - name: Lint Android example (detekt + ktlint) | ||
| working-directory: examples/android/RunAnywhereAI | ||
| run: ./gradlew detekt ktlintCheck --no-daemon | ||
| - run: | | ||
| curl -sSL -o ndk.zip https://dl.google.com/android/repository/android-ndk-r27c-linux.zip | ||
| unzip -q ndk.zip | ||
| mv android-ndk-r27c "${ANDROID_NDK_HOME}" | ||
| - run: sudo apt-get update && sudo apt-get install -y ninja-build | ||
| - name: Build Android JNI libs | ||
| run: ./scripts/build-core-android.sh | ||
| - name: gradle assembleDebug | ||
| run: ./gradlew :runanywhere-kotlin:assembleDebug | ||
|
|
||
| lint_web: | ||
| needs: detect | ||
| if: needs.detect.outputs.sdk_web == 'true' || needs.detect.outputs.workflows == 'true' | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 10 | ||
| flutter-pubget: |
Comment on lines
+128
to
+135
| runs-on: ubuntu-22.04 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: ./.github/actions/setup-toolchain | ||
| with: | ||
| platform: sdk-only | ||
| - name: Install deps | ||
| working-directory: sdk/runanywhere-web | ||
| run: npm install | ||
| - name: Build core (so llamacpp/onnx can resolve types) | ||
| working-directory: sdk/runanywhere-web | ||
| run: npm run build -w packages/core | ||
| - name: Lint | ||
| working-directory: sdk/runanywhere-web | ||
| run: npm run lint | ||
| - uses: subosito/flutter-action@v2 | ||
| with: { flutter-version: '3.38.x' } | ||
| - run: cd sdk/runanywhere-flutter/packages/runanywhere && flutter pub get && flutter analyze --no-fatal-infos lib | ||
|
|
||
| lint_rn: | ||
| needs: detect | ||
| if: needs.detect.outputs.sdk_react_native == 'true' || needs.detect.outputs.workflows == 'true' | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 15 | ||
| rn-typecheck: |
Comment on lines
+136
to
+144
| runs-on: ubuntu-22.04 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: ./.github/actions/setup-toolchain | ||
| with: | ||
| platform: sdk-only | ||
| - name: Enable Corepack (yarn@3.6.1) | ||
| run: corepack enable | ||
| - name: Install RN SDK deps | ||
| working-directory: sdk/runanywhere-react-native | ||
| run: yarn install --immutable || yarn install | ||
| - name: Prepare core (nitrogen + build for llamacpp/onnx) | ||
| working-directory: sdk/runanywhere-react-native | ||
| run: yarn core:prepare || true | ||
| - name: Lint RN SDK | ||
| working-directory: sdk/runanywhere-react-native | ||
| run: yarn lint | ||
| - uses: actions/setup-node@v4 | ||
| with: { node-version: '20' } | ||
| - run: cd sdk/runanywhere-react-native && yarn install --immutable | ||
| - run: cd sdk/runanywhere-react-native/packages/core && yarn typecheck | ||
|
|
||
| lint_flutter: | ||
| needs: detect | ||
| if: needs.detect.outputs.sdk_flutter == 'true' || needs.detect.outputs.workflows == 'true' | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 15 | ||
| web-typecheck: |
Comment on lines
+145
to
+150
| runs-on: ubuntu-22.04 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - uses: subosito/flutter-action@v2 | ||
| with: | ||
| channel: stable | ||
| - name: Flutter analyze — SDK packages | ||
| working-directory: sdk/runanywhere-flutter | ||
| run: | | ||
| set -e | ||
| # Generate pubspec_overrides.yaml for each sub-package so that | ||
| # `flutter pub get` resolves `runanywhere` from the local monorepo | ||
| # instead of the published version on pub.dev (which lags behind). | ||
| for pkg in packages/runanywhere_genie packages/runanywhere_llamacpp packages/runanywhere_onnx; do | ||
| if [ -f "$pkg/pubspec.yaml" ]; then | ||
| printf 'dependency_overrides:\n runanywhere:\n path: ../runanywhere\n' \ | ||
| > "$pkg/pubspec_overrides.yaml" | ||
| fi | ||
| done | ||
| for pkg in packages/runanywhere packages/runanywhere_genie packages/runanywhere_llamacpp packages/runanywhere_onnx; do | ||
| if [ -f "$pkg/pubspec.yaml" ]; then | ||
| echo "=== Analyzing $pkg ===" | ||
| (cd "$pkg" && flutter pub get && flutter analyze) | ||
| fi | ||
| done | ||
| - name: Flutter analyze — example app | ||
| working-directory: examples/flutter/RunAnywhereAI | ||
| run: flutter pub get && flutter analyze | ||
|
|
||
| # --------------------------------------------------------------------------- | ||
| # summary: depends on every other job so the PR check shows an aggregate result | ||
| # --------------------------------------------------------------------------- | ||
| summary: | ||
| if: always() | ||
| needs: | ||
| - detect | ||
| - native_ios | ||
| - native_android | ||
| - native_linux | ||
| - native_windows | ||
| - native_web | ||
| - sdk_swift | ||
| - sdk_kotlin | ||
| - sdk_web | ||
| - sdk_flutter | ||
| - sdk_react_native | ||
| - lint_swift | ||
| - lint_kotlin | ||
| - lint_web | ||
| - lint_rn | ||
| - lint_flutter | ||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - name: Print job results | ||
| run: | | ||
| echo "::group::Job results" | ||
| echo "native_ios = ${{ needs.native_ios.result }}" | ||
| echo "native_android = ${{ needs.native_android.result }}" | ||
| echo "native_linux = ${{ needs.native_linux.result }}" | ||
| echo "native_windows = ${{ needs.native_windows.result }}" | ||
| echo "native_web = ${{ needs.native_web.result }}" | ||
| echo "sdk_swift = ${{ needs.sdk_swift.result }}" | ||
| echo "sdk_kotlin = ${{ needs.sdk_kotlin.result }}" | ||
| echo "sdk_web = ${{ needs.sdk_web.result }}" | ||
| echo "sdk_flutter = ${{ needs.sdk_flutter.result }}" | ||
| echo "sdk_react_native = ${{ needs.sdk_react_native.result }}" | ||
| echo "lint_swift = ${{ needs.lint_swift.result }}" | ||
| echo "lint_kotlin = ${{ needs.lint_kotlin.result }}" | ||
| echo "lint_web = ${{ needs.lint_web.result }}" | ||
| echo "lint_rn = ${{ needs.lint_rn.result }}" | ||
| echo "lint_flutter = ${{ needs.lint_flutter.result }}" | ||
| echo "::endgroup::" | ||
| - name: Fail on hard failures | ||
| run: | | ||
| # 'failure' = job ran and failed. 'cancelled'/'skipped' don't fail the PR. | ||
| for r in \ | ||
| "${{ needs.native_ios.result }}" \ | ||
| "${{ needs.native_android.result }}" \ | ||
| "${{ needs.native_linux.result }}" \ | ||
| "${{ needs.native_windows.result }}" \ | ||
| "${{ needs.native_web.result }}" \ | ||
| "${{ needs.lint_swift.result }}" \ | ||
| "${{ needs.lint_kotlin.result }}" \ | ||
| "${{ needs.lint_web.result }}" \ | ||
| "${{ needs.lint_rn.result }}" \ | ||
| "${{ needs.lint_flutter.result }}"; do | ||
| if [ "$r" = "failure" ]; then | ||
| echo "::error::A build or lint job failed." | ||
| exit 1 | ||
| fi | ||
| done | ||
| - uses: actions/setup-node@v4 | ||
| with: { node-version: '20' } | ||
| - run: cd sdk/runanywhere-web/packages/core && npm install --no-audit --no-fund && npx tsc --noEmit |
Comment on lines
+32
to
+75
| runs-on: ubuntu-latest | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
|
|
||
| - name: Install build deps | ||
| run: | | ||
| sudo apt-get update | ||
| sudo apt-get install -y ninja-build cmake libprotobuf-dev protobuf-compiler libabsl-dev python3 | ||
|
|
||
| - name: Configure | ||
| run: cmake --preset linux-debug -DRAC_BUILD_TESTS=ON | ||
|
|
||
| - name: Build streaming targets | ||
| run: | | ||
| cmake --build --preset linux-debug --target parity_test_cpp | ||
| cmake --build --preset linux-debug --target perf_producer | ||
| cmake --build --preset linux-debug --target cancel_producer | ||
|
|
||
| - name: Run parity check (C++ golden producer) | ||
| run: ctest --test-dir build/linux-debug -R parity_test_cpp_check --output-on-failure | ||
|
|
||
| - name: Run perf producer | ||
| run: ctest --test-dir build/linux-debug -R perf_producer_cpp --output-on-failure | ||
|
|
||
| - name: Run cancel producer | ||
| run: ctest --test-dir build/linux-debug -R cancel_producer_cpp --output-on-failure | ||
|
|
||
| - name: Aggregate perf percentiles (no per-SDK logs => harness sanity only) | ||
| run: ctest --test-dir build/linux-debug -R perf_aggregate --output-on-failure || true | ||
|
|
||
| - name: Aggregate cancel traces | ||
| run: ctest --test-dir build/linux-debug -R cancel_aggregate --output-on-failure || true | ||
|
|
||
| - name: Upload perf-bench fixture | ||
| uses: actions/upload-artifact@v4 | ||
| with: | ||
| name: perf-bench-fixture | ||
| path: build/linux-debug/tests/streaming/perf_bench/ | ||
|
|
||
| - name: Upload cancel-parity fixture | ||
| uses: actions/upload-artifact@v4 | ||
| with: | ||
| name: cancel-parity-fixture | ||
| path: build/linux-debug/tests/streaming/cancel_parity/ |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 3 potential issues.
Bugbot Autofix prepared fixes for all 3 issues found in the latest run.
- ✅ Fixed: Dev toggle
useLocalNatives = truecommitted to repo- Set
useLocalNativesback tofalseinPackage.swiftso external SPM consumers use release binaries by default.
- Set
- ✅ Fixed: NDK
mvfails: source and destination are identical- Removed the redundant
mv android-ndk-r27c "${ANDROID_NDK_HOME}"lines from both Android workflow jobs so NDK install no longer fails on self-move.
- Removed the redundant
- ✅ Fixed: Generator expressions in
message()print literal strings- Replaced generator expressions in the CMake summary with configure-time
if()-computed variables somessage()prints real mode values.
- Replaced generator expressions in the CMake summary with configure-time
Or push these changes by commenting:
@cursor push f30a17ede9
Preview (f30a17ede9)
diff --git a/.github/workflows/pr-build.yml b/.github/workflows/pr-build.yml
--- a/.github/workflows/pr-build.yml
+++ b/.github/workflows/pr-build.yml
@@ -87,7 +87,6 @@
run: |
curl -sSL -o ndk.zip https://dl.google.com/android/repository/android-ndk-r27c-linux.zip
unzip -q ndk.zip
- mv android-ndk-r27c "${ANDROID_NDK_HOME}"
- run: sudo apt-get update && sudo apt-get install -y ninja-build
- run: cmake --preset android-arm64
- run: cmake --build --preset android-arm64
@@ -117,7 +116,6 @@
- run: |
curl -sSL -o ndk.zip https://dl.google.com/android/repository/android-ndk-r27c-linux.zip
unzip -q ndk.zip
- mv android-ndk-r27c "${ANDROID_NDK_HOME}"
- run: sudo apt-get update && sudo apt-get install -y ninja-build
- name: Build Android JNI libs
run: ./scripts/build-core-android.sh
diff --git a/CMakeLists.txt b/CMakeLists.txt
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -152,8 +152,18 @@
message(STATUS "RunAnywhere SDKs — root CMake configured")
message(STATUS "============================================")
message(STATUS "Version : ${RAC_VERSION}")
-message(STATUS "Build mode : $<IF:$<BOOL:${RAC_BUILD_SHARED}>,SHARED,STATIC>")
-message(STATUS "Plugin mode : $<IF:$<BOOL:${RAC_STATIC_PLUGINS}>,STATIC (linked into commons),SHARED (dlopen-loaded)>")
+if(RAC_BUILD_SHARED)
+ set(RAC_BUILD_MODE_SUMMARY "SHARED")
+else()
+ set(RAC_BUILD_MODE_SUMMARY "STATIC")
+endif()
+if(RAC_STATIC_PLUGINS)
+ set(RAC_PLUGIN_MODE_SUMMARY "STATIC (linked into commons)")
+else()
+ set(RAC_PLUGIN_MODE_SUMMARY "SHARED (dlopen-loaded)")
+endif()
+message(STATUS "Build mode : ${RAC_BUILD_MODE_SUMMARY}")
+message(STATUS "Plugin mode : ${RAC_PLUGIN_MODE_SUMMARY}")
message(STATUS "Sanitizer : ${RAC_SANITIZER}")
message(STATUS "Tests : ${RAC_BUILD_TESTS}")
message(STATUS "Server (HTTP) : ${RAC_BUILD_SERVER}")
diff --git a/Package.swift b/Package.swift
--- a/Package.swift
+++ b/Package.swift
@@ -40,7 +40,7 @@
// the same — it's been renamed to `useLocalNatives` for consistency with the
// equivalent toggle in the other client SDKs (Kotlin, Flutter, React Native).
// =============================================================================
-let useLocalNatives = true // Toggle: true for local dev, false for release
+let useLocalNatives = false // Toggle: true for local dev, false for release
// Version for remote XCFrameworks (used when useLocalNatives = false)
// Updated automatically by CI/CD during releases.You can send follow-ups to the cloud agent here.
Comment @cursor review or bugbot run to trigger another review on this PR
Reviewed by Cursor Bugbot for commit 801cac4. Configure here.
| // equivalent toggle in the other client SDKs (Kotlin, Flutter, React Native). | ||
| // ============================================================================= | ||
| let useLocalNatives = false // Toggle: true for local dev, false for release | ||
| let useLocalNatives = true // Toggle: true for local dev, false for release |
There was a problem hiding this comment.
Dev toggle useLocalNatives = true committed to repo
High Severity
useLocalNatives was flipped from false to true. The inline comment says "true for local dev, false for release" and the full documentation block (lines 28-37) explicitly marks false as PRODUCTION. When this merges to main, external SPM consumers will get the local-dev path that expects XCFrameworks at sdk/runanywhere-swift/Binaries/ — which don't exist in a fresh clone — instead of downloading from GitHub Releases. This breaks all external Swift Package Manager resolution.
Reviewed by Cursor Bugbot for commit 801cac4. Configure here.
| if: needs.detect.outputs.sdk_swift == 'true' || needs.detect.outputs.workflows == 'true' | ||
| curl -sSL -o ndk.zip https://dl.google.com/android/repository/android-ndk-r27c-linux.zip | ||
| unzip -q ndk.zip | ||
| mv android-ndk-r27c "${ANDROID_NDK_HOME}" |
There was a problem hiding this comment.
NDK mv fails: source and destination are identical
High Severity
ANDROID_NDK_HOME is set to ${{ github.workspace }}/android-ndk-r27c. The unzip extracts the NDK into the default working directory, which is also github.workspace. The subsequent mv android-ndk-r27c "${ANDROID_NDK_HOME}" resolves to moving a directory onto itself, which fails with exit code 1 and breaks both the android-arm64 and kotlin-android CI jobs. The mv line is unnecessary since the NDK is already at the correct path after unzip.
Additional Locations (1)
Reviewed by Cursor Bugbot for commit 801cac4. Configure here.
| message(STATUS "============================================") | ||
| message(STATUS "Version : ${RAC_VERSION}") | ||
| message(STATUS "Build mode : $<IF:$<BOOL:${RAC_BUILD_SHARED}>,SHARED,STATIC>") | ||
| message(STATUS "Plugin mode : $<IF:$<BOOL:${RAC_STATIC_PLUGINS}>,STATIC (linked into commons),SHARED (dlopen-loaded)>") |
There was a problem hiding this comment.
Generator expressions in message() print literal strings
Low Severity
The configuration summary uses CMake generator expressions ($<IF:$<BOOL:...>,...,...>) inside message(STATUS ...). Generator expressions are only evaluated during build-system generation for target-related commands — message() runs at configure time and prints the literal unexpanded string. The "Build mode" and "Plugin mode" lines will display something like $<IF:$<BOOL:OFF>,SHARED,STATIC> instead of the intended STATIC or SHARED.
Reviewed by Cursor Bugbot for commit 801cac4. Configure here.
Comment on lines
+13
to
+38
| runs-on: ubuntu-latest | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - name: Fail if removed legacy files reappear | ||
| shell: bash | ||
| run: | | ||
| set -euo pipefail | ||
| blocked=( | ||
| "sdk/runanywhere-react-native/packages/core/src/Features/VoiceSession/VoiceSessionHandle.ts" | ||
| "sdk/runanywhere-react-native/packages/core/src/Public/Extensions/RunAnywhere+VoiceSession.ts" | ||
| "sdk/runanywhere-react-native/scripts/build-react-native.sh" | ||
| "sdk/runanywhere-web/packages/core/src/Public/Extensions/RunAnywhere+VoiceAgent.ts" | ||
| "sdk/runanywhere-web/scripts/build-web.sh" | ||
| ) | ||
|
|
||
| found=0 | ||
| for path in "${blocked[@]}"; do | ||
| if [[ -e "$path" ]]; then | ||
| echo "Blocked legacy file reintroduced: $path" | ||
| found=1 | ||
| fi | ||
| done | ||
|
|
||
| if [[ "$found" -ne 0 ]]; then | ||
| exit 1 | ||
| fi |
|
|
||
| const canRemoveDocuments = RAG.capabilities().documentRemoval; | ||
| listEl.innerHTML = documents.map((doc) => ` | ||
| <li class="docs-item" data-id="${escapeHtml(doc.id)}"> |
| <div class="docs-item-title">${escapeHtml(doc.name)}</div> | ||
| <div class="docs-item-meta">${doc.chunkCount} chunk${doc.chunkCount === 1 ? '' : 's'}</div> | ||
| </div> | ||
| ${canRemoveDocuments ? `<button class="btn btn-icon docs-item-delete" data-id="${escapeHtml(doc.id)}" aria-label="Remove"> |
…nalize helpers (CPP-04) Construct RAGBackend directly from proto bytes in rac_rag_proto_abi.cpp; hoist rac_rag_session_*_proto / rac_rag_ingest_proto / rac_rag_query_proto / rac_rag_clear_proto / rac_rag_stats_proto declarations to rac_rag.h. Deleted (commons): - include/rac/features/rag/rac_rag_pipeline.h (~314 LOC) - src/features/rag/rac_rag_pipeline.cpp (~340 LOC) - rac_rag_config_to/from_proto, rac_rag_query_to/from_proto, rac_search_result_to/from_proto, rac_rag_result_to/from_proto (unused after proto ABI refactor; ~143 LOC in proto_adapters.cpp + 25 decls in .h) Deleted (RN): - packages/core/cpp/bridges/RAGBridge.cpp (~298 LOC) - packages/core/cpp/bridges/RAGBridge.hpp (~40 LOC) ModelRegistryBridge + CompatibilityBridge retained (comment blocks mark getHandle/checkCompatibility as internal adapter glue still reached from Registry/Storage/Lifecycle extensions; blocker: rac_model_compatibility_*_proto ABI does not yet exist on commons; tracked under react-native.md CPP-RN-RAG-BRIDGE-PURGE). Validation: - cmake --preset macos-debug -DRAC_BUILD_BACKENDS=ON configures clean - cmake --build build/macos-debug --target rac_commons succeeds - cmake --build build/macos-debug --target runanywhere_commons_jni succeeds - ctest -R "advanced_modality_proto_abi_tests|rag_service_proto_abi_tests" both pass (100%, 2/2) - cd sdk/runanywhere-react-native && yarn typecheck passes Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…EB-01) Flips the Emscripten force-disable gates on engines/onnx, engines/sherpa, and runtimes/onnxrt to EXISTS-guarded disables keyed on the vendored WASM static archives under sdk/runanywhere-commons/third_party/. Once the archives land (CPP-13-VENDOR / WEB-01-VENDOR), the engines turn on automatically and commons WASM ships _rac_backend_onnx_register + _rac_backend_sherpa_register. Changes: - engines/onnx/CMakeLists.txt: EXISTS gate for onnxruntime-wasm static lib. - engines/sherpa/CMakeLists.txt: EXISTS gate + new elseif(EMSCRIPTEN) prebuilt-discovery branch creating STATIC IMPORTED targets for every libsherpa-onnx-*.a + libkaldi-*.a + libkissfft-*.a (+ optional Piper TTS deps) under third_party/sherpa-onnx-wasm/lib/. - runtimes/onnxrt/CMakeLists.txt: mirror the same EXISTS gate. - sdk/runanywhere-commons/cmake/FetchONNXRuntime.cmake: Emscripten branch now creates a STATIC IMPORTED onnxruntime target when the archive is present; falls back to INTERFACE-only otherwise. - sdk/runanywhere-web/wasm/CMakeLists.txt: adds _rac_backend_sherpa_register / _unregister to RAC_EXPORTED_FUNCTIONS and links rac_backend_sherpa into runanywhere_wasm when the target exists. Updated FATAL_ERROR explains the vendoring dependency; sherpa target absence downgrades to STATUS warning instead of fail-fast. Residual (follow-up row): staging the ONNX Runtime WASM + Sherpa-ONNX WASM static archives under sdk/runanywhere-commons/third_party/. Build recipes live in the banners at the top of engines/onnx and engines/sherpa CMakeLists.txt plus the .gitkeep sentinels under the vendored directories (directories themselves are gitignored by sdk/runanywhere-commons/.gitignore:44). Validation: - macOS reconfigure green (cmake --preset macos-debug): Configuring ONNX backend + Configuring Sherpa-ONNX backend both still logged; no non-EMSCRIPTEN path regressed. - rac_commons target builds clean (no changes affected macOS code). - Existing racommons-llamacpp.wasm + racommons-llamacpp-webgpu.wasm artifacts untouched (vendored archives not yet present → engines still skip on Emscripten; pre-existing unrelated RAG header break in wasm_exports.cpp is separate, tracked elsewhere). Cross-links: - thoughts/shared/plans/wasm_onnx_unblock.md (9-step plan, Steps 2-4+6 landed here; Steps 1+5 are CPP-13-VENDOR follow-up). - gaps/gaps/inconsistencies/cpp-layer.md § CPP-13 - gaps/gaps/inconsistencies/web.md § WEB-01 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…s (CPP-04 follow-up) CPP-04 (commit 8958b8e) deleted rac_rag_pipeline.{h,cpp} but the WASM entry point at sdk/runanywhere-web/wasm/src/wasm_exports.cpp:83 still included the deleted header. Remove the include; no RAG functions are actually referenced in wasm_exports.cpp so no replacement is needed. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…TE-LLAMA-load_model) The rac_llm_llamacpp_load_model function was a documented no-op since LlamaCPP loads the model during rac_llm_llamacpp_create(). It was called in only two places: - The llamacpp_vtable_initialize callback (inlined to RAC_SUCCESS return) - A reload test path (removed — reload via destroy/recreate instead) Delete the function definition, public header declaration, Swift-side runtime shim declaration, and the WASM exports list entry. Update the test to stop attempting a reload through this removed API. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…a (ENG-LLAMA-04)
Both engines declared their own `enum class DeviceType` in their
backend headers with overlapping numeric codes and divergent value
sets. Consolidate into a single shared internal header under
engines/common/ — union of all values (CPU/GPU/NEURAL_ENGINE/
METAL/CUDA/WEBGPU) in a single `runanywhere::DeviceType`.
- New: engines/common/rac_engine_device_type.h
- Update llamacpp_backend.h + sherpa_backend.h to include the shared
header and remove their local duplicates.
- Add `${CMAKE_CURRENT_SOURCE_DIR}/..` (engines/) to each backend's
include path so the shared header resolves via `common/*.h`.
Closes ENG-LLAMA-04 / DUP-04 (active-backend slice).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…ter + static shims (ENG-SHERPA-03)
Unify the plugin-registration contract across the three active backends so all
of llamacpp / sherpa / onnx ship the same two entry points:
1. Explicit `rac_backend_<name>_register()` for dynamic-link hosts
(Android / Linux / macOS dev).
2. `rac_static_register_<name>.cpp` shim expanding
`RAC_STATIC_PLUGIN_REGISTER(<name>)` for static-link hosts (iOS / WASM,
`RAC_STATIC_PLUGINS=ON`).
Changes:
- Delete the ELF `__attribute__((constructor))` auto-register block at the
bottom of `engines/sherpa/rac_plugin_entry_sherpa.cpp`.
- Add `rac_backend_sherpa_register()` / `rac_backend_sherpa_unregister()` to
`engines/sherpa/rac_backend_sherpa_register.cpp` (mirrors the onnx shape).
- Publish `sdk/runanywhere-commons/include/rac/plugin/rac_plugin_entry_sherpa.h`
declaring the entry point + register functions (parallel to llamacpp / onnx).
- Add `engines/sherpa/rac_static_register_sherpa.cpp` +
`engines/onnx/rac_static_register_onnx.cpp` shims; wire them into each
engine's CMakeLists with the same `if(RAC_STATIC_PLUGINS)` branching as
`engines/llamacpp/CMakeLists.txt`.
- Teach the ONNX JNI bridge to dlsym `rac_backend_sherpa_register` at
`nativeRegister` time so Android / JVM hosts that dlopen
`librac_backend_sherpa.so` keep registering sherpa without a dedicated
sherpa JNI bridge.
Validation: macos-debug rebuilds `rac_commons`, `rac_backend_sherpa`,
`rac_backend_onnx`, `runanywhere_sherpa`, `runanywhere_onnx` clean. The
pre-existing ggml-metal upstream compile failure on `rac_backend_llamacpp` is
unrelated to this refactor.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…-ONNX-02)
Relocate onnx_embedding_provider.{h,cpp} and rac_onnx_embeddings_register.cpp
from sdk/runanywhere-commons/src/features/rag/ into engines/onnx/ so the ONNX
engine plugin fully owns its embedding primitive. Replaces the cross-module
CMake RAG_DIR tweak (engines/onnx/CMakeLists.txt) with plain local sources
and updates comment references in the embeddings service header, RAG
CMakeLists, plugin entry, and placeholder tokenizer test. The files are
still gated by RAC_BACKEND_RAG because the RAG pipeline is the sole
consumer of the embeddings primitive today.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…tions from onnx backend (ENG-ONNX-05) Audited commons for consumers of rac_storage_strategy_register / rac_download_strategy_register: no live caller exists. The wrappers rac_model_strategy_find_path / _detect / _is_valid / _prepare_download / _get_download_dest / _post_process all fall through to the default path-resolution behavior (rac_model_paths_resolve_artifact + default extraction) when no per-framework strategy is registered. Framework gating for ONNX is already carried by g_onnx_engine_vtable.metadata per the plugin-entry TU, making RAC_FRAMEWORK_ONNX strategy registration redundant pre-v3 machinery. Deleted from engines/onnx/rac_backend_onnx_register.cpp: - rac_storage_strategy_register(RAC_FRAMEWORK_ONNX, ...) - rac_download_strategy_register(RAC_FRAMEWORK_ONNX, ...) - rac_model_strategy_unregister(RAC_FRAMEWORK_ONNX) - 8 dead strategy callbacks (onnx_storage_find_model_path, onnx_storage_detect_model, onnx_storage_is_valid, onnx_storage_get_patterns, onnx_download_prepare, onnx_download_get_dest, onnx_download_post_process, onnx_download_cleanup) + their static strategy structs - Unused includes: rac_model_strategy.h, rac_model_types.h, cstdint, cstdio, cstdlib, cstring, vector The entire strategy-registry machinery in commons now has zero live registrants and is dead code - tracked as CPP-STRATEGY-CLEANUP in gaps/gaps/inconsistencies/cpp-layer.md for a follow-up row removing the register/lookup/wrapper APIs and the rac_model_strategy.h header entirely. Validation: - cmake --preset macos-debug (green) - cmake --build build/macos-debug --target rac_backend_onnx (green) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…herpa copy (DUP-01) Sherpa's `convert_int16_to_float32` wrapper now routes through the shared `rac::audio::rac_audio_pcm16_to_float32` helper in `sdk/runanywhere-commons/include/rac/audio/rac_audio_convert.h`, eliminating the duplicated inner loop. The sherpa-only `std::vector<float>`-returning wrapper is kept as a thin adapter since both transcribe paths still require the allocate-and-return shape. Validated: `cmake --build build/macos-debug --target rac_backend_sherpa` green. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…gnment (DUP-07) Extract the duplicated `target_link_options(... --gc-sections, max-page-size=16384, common-page-size=16384)` block into a shared `rac_apply_android_page_alignment()` helper in `cmake/plugins.cmake`. Replace 8 copy-pasted occurrences across the 3 active engines (llamacpp, sherpa, onnx) with single-line calls. The helper is a no-op on non-Android platforms so callers don't need a RAC_PLATFORM_ANDROID guard at the call site. Deferred engines (whispercpp, genie) keep the raw block until they are un-parked. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…e scaffolds (DUP-03)
The per-primitive `<name>_<primitive>_create_impl` functions on each backend
were 7-line copy-pasted forwards onto `rac_<primitive>_<name>_create`. Factor
the scaffold into a single macro `RAC_DEFINE_CREATE_ADAPTER(primitive, name)`
in `rac_plugin_entry.h`.
Migrated: sherpa STT, sherpa TTS, sherpa VAD (net -32 LOC in
`engines/sherpa/rac_backend_sherpa_register.cpp`). Sherpa VAD loses a dead
RAC_LOG_ERROR + null-handle recovery branch that `rac_vad_sherpa_create`
never actually triggers — it asserts out_handle internally on failure.
Not migrated (scoped out with note in the tracked gap doc):
- llamacpp LLM `create_impl`: 45-line body wraps `LlamaCppRuntimeImpl`
around a CPU-runtime session — cannot be expressed as a 7-line forward.
- onnx embeddings `create_impl`: try/catch + std::make_unique +
is_ready()-after-init check diverges from the scaffold shape.
Build verified: `cmake --build build/macos-debug --target rac_backend_sherpa`
links cleanly. The llamacpp register.cpp.o also builds; the pre-existing
vendored ggml-metal .m compile failure against current Xcode SDK is
unrelated to this change.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…ates (DUP-05)
Factor the duplicated {callback, user_data} stream adapter struct used by
engines/llamacpp's LLM and VLM vtable TUs into a shared template header at
sdk/runanywhere-commons/include/rac/plugin/rac_stream_adapter.h.
Both llamacpp TUs now use `rac::plugin::StreamAdapter<CallbackT>` via a
`using` alias parameterized on their respective `rac_*_stream_callback_fn`
typedef. Per-primitive C trampolines remain intentionally per-TU because
each still needs to discard its own `is_final` arg; the win is the
removed struct body.
Validation: `cmake --build build/macos-debug --target rac_backend_llamacpp`
recompiles `rac_backend_llamacpp_register.cpp.o` and
`rac_backend_llamacpp_vlm_register.cpp.o` clean. The pre-existing
ggml-metal obj-c compile errors in _deps/llamacpp-src are unrelated.
Updated gaps/gaps/inconsistencies/engines.md: DUP-05 marked resolved.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…lete per-backend duplicates (DUP-06)
Lifted rac_event_track("*.backend.created", ...) emission into the commons
service layer so future backends inherit it automatically and can't silently
drop the event.
Commons emits (each reads backend name from vt->metadata.name, so the JSON
payload is correct regardless of which plugin the router picked):
- sdk/runanywhere-commons/src/features/llm/rac_llm_service.cpp (rac_llm_create)
- sdk/runanywhere-commons/src/features/stt/rac_stt_service.cpp (rac_stt_create)
- sdk/runanywhere-commons/src/features/tts/rac_tts_service.cpp (rac_tts_create)
- sdk/runanywhere-commons/src/features/vad/vad_component.cpp (rac_vad_component_load_model)
Deleted per-backend firings that are now duplicates:
- engines/llamacpp/rac_llm_llamacpp.cpp (was line 114)
- engines/sherpa/rac_stt_sherpa.cpp (was line 97)
- engines/sherpa/rac_tts_sherpa.cpp (was line 74)
- engines/sherpa/rac_vad_sherpa.cpp (was line 78)
Validation: rac_commons + rac_backend_sherpa compile clean under
'cmake --build build/macos-debug'. engines/whispercpp retains its own emit
(deferred to Iteration-I; will be cleaned up when whispercpp is reactivated).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
… + ONNXRT (DUP-RT-01) Replace inlined release_tensor implementations in CPU and ONNXRT runtimes with calls to the shared rac::runtime::rac_runtime_release_tensor helper. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…ONNXRT (DUP-RT-02) Replaces the inlined offset/bounds check + memmove in cpu_copy_buffer and onnxrt_copy_buffer with a call into the shared rac::runtime::rac_runtime_copy_buffer helper declared in sdk/runanywhere-commons/include/rac/runtime/rac_runtime_helpers.h. Both runtimes already include the helpers header (DUP-RT-01 wave); this migration removes the remaining duplicated body. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
After adding the `protobuf` pip dep, the next generator in the chain (`generate_swift_modality_abi.py`) bailed with: error: PyYAML not installed. Run `python3 -m pip install pyyaml` or use the toolchain installed by scripts/setup-toolchain.sh. Bundle pyyaml into the same install step so both groups of generators have their Python deps ready. Co-authored-by: Cursor <cursoragent@cursor.com>
idl-drift-check finally got through every codegen step (mint, dart, python protobuf+pyyaml, ts-proto, generate_all.sh) and bailed at the proto-ts build: npm error code EUNSUPPORTEDPROTOCOL npm error Unsupported URL Type "workspace:": workspace:* Same root cause we already fixed for pr-build.yml web-typecheck (commit 086170b): npm walks up from sdk/shared/proto-ts, hits the root Yarn workspace package.json with `workspace:*` deps it can't parse, and bails. Add `--workspaces=false` so npm treats this directory as standalone for the install. Co-authored-by: Cursor <cursoragent@cursor.com>
…cframework script
- .github/workflows/pr-build.yml (kotlin-android): explicit
`actions/setup-java@v4` step pinned to Temurin 17. The ubuntu-22.04
runner default JDK is 11, which AGP 8.13.0 rejects:
> Android Gradle plugin requires Java 17 to run.
> You are currently using Java 11.
- scripts/build-core-xcframework.sh: rename the expected static
archive from `libcommon.a` → `libllama-common.a` to match the
llama.cpp b9180 target rename that we already fixed in
engines/llamacpp/CMakeLists.txt's LINK_LIBRARIES list (commit
6d24629). Without this swift-spm fails the final libtool merge
with:
error: required archive not found:
build/ios-device/_deps/llamacpp-build/common/Release-iphoneos/libcommon.a
Co-authored-by: Cursor <cursoragent@cursor.com>
…stacks Closes out the second-pass review of PR #494 (v2 architecture migration). 50 review agents staged 124 deduped findings (3 blocker, 42 major, 69 minor, 10 nit) against current HEAD; 15 cross-SDK follow-ups were spawned during the fix waves. Final state: 139/139 records FIXED with real code changes, zero FIXED-PARTIAL or RESOLVED-NO-CODE-CHANGE remaining. Blockers fixed - Cross-SDK UAF window in modality stream dispatchers (LLM/STT/TTS/VAD/VLM/ Diffusion): lifted voice_agent's in_flight atomic counter + spinwait quiesce pattern to all six dispatchers; new rac_vlm_proto_quiesce() public symbol and per-modality unset/destroy spinwait close the Swift/Flutter/RN UAF - Apple RAC_API exports completed: 479 missing core symbols added, RACommons.exports split into core + 3 backend-conditional sibling files (rag / onnx_embeddings / whisperkit_coreml) concatenated at CMake configure time, stale rac_vad_{start,stop,reset} decls removed (1003/1003 covered) - Web @runanywhere/web-onnx package no longer auto-installs the standalone Sherpa provider whose wasm/ glob was excluded from published files Major fixes — Commons + IDL - Tool-calling: tool_choice/forced_tool_name (proto fields 7/8) added to ToolCallingSessionCreateRequest, plumbed through build_options_snapshot, run-loop and session paths. New cancel ABI: rac_tool_calling_session_cancel _proto, rac_tool_calling_run_loop_with_handle_proto, rac_tool_calling_run_ loop_cancel_proto + JNI shim + Swift/Kotlin/Flutter/RN/Web adapter plumbing - LLMStreamEvent.tool_call (proto field 18): producer wired for both libprotobuf and WASM hand-encoded paths in rac_llm_stream.cpp; consumer wiring in Swift/Kotlin/Flutter/RN/Web event types - structured_output: typed validation failures (INVALID_FORMAT / VALIDATION_ FAILED) now surface through StructuredOutputResult instead of transport err - Runtime registry: rac_runtime_register eviction now single-critical-section; destroy/dlclose run on locally-captured locals after lock release - Tool-calling tool_choice=NONE follow-up turn now preserves tool_results - Cross-thread error propagation in SolutionRunner (mutex-guarded operator- error slot drained on wait()); built-in 'retrieve' operator stand-in; download orchestrator UB guard on empty-plan path Major fixes — Swift SDK - HandleStreamAdapter.tearDown rewritten lock-then-release (no recursive-lock deadlock); new tests for terminal-event teardown + sync-unregister-during- teardown invariants - Generated ModalityProtoABI streams now pass onCancel: through to native cancel (LLM + StructuredOutput); generator updated to emit it - RunAnywhere+ToolCalling: toolChoice/forcedToolName/validateCalls public params; withTaskCancellationHandler wires AbortSignal-equivalent cancel - SDKException.fieldPath + validationFailed(fieldPath:message:underlying:) factory (cross-SDK ValidationError parity) - Real SHA-256 checksums for all 4 Package.swift remote binaryTargets (RACommons, LlamaCPP, ONNX, Sherpa) + Binaries/checksums.txt sidecar - CRACommons LoRA 4-arg prototypes stripped; bundled xcframework Headers/ copies synced with current commons ABI - README v2 migration; CppBridge+StructuredOutput.generate dead-code removed Major fixes — Kotlin SDK - HandleStreamAdapter: Channel.UNLIMITED (Swift AsyncStream parity); 2-phase install state machine appends collector before native register, calls register outside per-fan-out lock (no lost-first-event) - ComponentActor unit tests (5 cases); fan-out tests for cancel-one-of-N mid-stream + post-detach delivery - RAConvenience.kt regenerated: zero-literal-by-type (Long==0L etc.), else->"" branches for fully-annotated enums - README/Documentation/ARCHITECTURE/CLAUDE.md migrated from v1 to v2 API - SDKException.validationFailed(fieldPath, message, cause) factory - Tool-calling cancel via Job.invokeOnCompletion → racToolCallingSessionCancel Major fixes — Flutter SDK - Real bridge stream-drain test (injection seam on DartBridgeTTS, fake FFI override) replaces the previous generic StreamController contract test - kStreamDrainMaxMicrotasks shared constant + drainPendingStreamCallbacks helper (deduplicates 4 magic-number sites across TTS/VLM/STT/LLM) - ToolCallingOptions.toolChoice / forcedToolName plumbed through proto request - LLMStreamEvent.toolCall consumed end-to-end (Wire decode auto-forwards) - ONNX bindings: hardcoded lookupFunction<Concrete,Concrete> per symbol (replaces unsafe generic _lookup helper) - VAD callback API removal documented in CHANGELOG; reset() docstring fixed - Centralization gate parser tolerates pubspec-driven registry post-syn-121 Major fixes — React Native SDK - HybridRunAnywhereCore.resetAllGlobalComponentHandles: documented destruction ordering invariant tying voice_agent destroy-before-leaves to owns_components =false contract - RunAnywhere+ToolCalling: toolChoice/forcedToolName/validateCalls + Abort- Signal cancel + validation-failure logger.warning - RunAnywhere+TextGeneration: toolCall accumulator on LLMGenerationResult - proto-ts dist regenerated (was stale; root cause of pass-2 typecheck failure) - nitro peer ranges aligned to 0.33.9 (matches versions.json SoT) - App.tsx awaits + boolean-gates ONNX.register() (parity with LlamaCPP path) Major fixes — Web SDK - TS tool-calling run loop REPLACED with WASM session-driver: calls _rac_tool_ calling_session_{create,step_with_result,destroy,cancel}_proto via Module. addFunction trampoline; loop iteration now lives in commons; addFunction trampoline handles executor callback; cancel wiring via AbortSignal - T6.1 Worker pipeline: @internal @experimental contract; shutdown tears it down (OffscreenRuntimeBridge.disposeShared + setStreamWorkerFactory(null) + setStreamWorkerInit(null)); 10s handshake timeout; modality-aware cancel routing; structured-clone → transferable on init + per-token paths - EventBus.onCategory/eventsFor APIs (Swift/Kotlin/RN/Flutter parity) - StandaloneSherpa: VAD reset/drainSegments per call (Silero state leak fixed); stageDirectoryFromCommons no longer creates phantom directory at basename; STT/TTS destroy capture-into-local before async free (UAF + heap leak fixes) - RACErrors.ts canonical RAC error-code module (no more -401 dup) - Hardcoded /Users/sanchitmonga absolute paths replaced with REPO_ROOT-relative in 7 browser specs; RA_RUN_SPEECH_E2E gate added to 4 specs - LifecycleVLMProvider category guard (no LLM-as-VLM routing) Major fixes — IDL + codegen - Kotlin convenience generator: zero_literal_for_required helper fixes compile-breaking `Long == 0` comparisons (INT64/FLOAT/DOUBLE/INT32 typed zeros); else->"" emitted on all enum accessors; _convenience_common shared helpers imported (deletes ~120 LOC of dup in Dart + TS generators) - TS convenience generator: emits only annotated fields (matches Kotlin/Dart/ Swift); BOOL rac_required behavior aligned; LangProfile extended with DART_PROFILE / TS_PROFILE + int64_wrap callable - generate_swift_modality_abi.py emits onCancel: closures; swift-modality-abi .yaml LoRA modality-level handle key removed - generate_streams.sh source_proto derivation (njk template parameterized); stale attribution to deleted generate_{rn,web}_streams.sh removed - idl/codegen/tests/ smoke harness: test_options.proto fixture + runner + swift/kotlin/dart/ts golden files Major fixes — Native engines + runtimes - WhisperKit-CoreML + MetalRT static-register shims (engines/*/rac_static_ register_*.cpp): plugin registers now actually run at static-init time - Sherpa VAD configure rebuilds with full VADConfig snapshot (not just threshold); TTS synthesize() mutex serializes concurrent calls; STT per-language recognizer cache (LRU cap 3) eliminates the rebuild cliff - llamacpp VLM plugin entry annotated with RAC_API for explicit visibility - Diffusion CoreML loadable registration path (mirrors llamacpp pattern) Major fixes — Example apps + build/CI - Web example: Voice Agent preflight, RAG bootstrap clearer-error wrapping, Documents/Vision provider activation, web-sdk-test-suite.md realignment - iOS example CLAUDE.md scrubbed of deferred WhisperKit/Diffusion sections; Package.swift platform floor bumped to .iOS("17.5")/.macOS("14.5") - Android example System TTS registration documented; ModelBootstrap full baseline catalog parity with iOS/Flutter - RN example: scripts/pod-install.sh runs `bundle install` before `bundle exec pod install` (no chicken-and-egg) - release.yml: publish gate flipped to == 'success', if-no-files-found: error, manifest-content assertion; validate_consumer_* jobs added to publish.needs with continue-on-error removed; validate_consumer_flutter gets actions/checkout + native artifact download - pr-build.yml + release.yml Flutter version centralized via VERSIONS + setup-toolchain (was hardcoded 3.27.0 in 3 places) - scripts/sync-versions.sh extended to bump proto-ts/package.json, @runanywhere/proto-ts caret deps in RN+Web, per-SDK SDKConstants - scripts/setup-toolchain.sh sources VERSIONS for codegen pins (Wire, swift-protobuf, ts-proto) — closes the 3-way version fork - .syncpackrc.json nitro aligned to 0.33.9 (matches versions.json) - New centralization gates wired to pr-build.yml (T4 premise now defended) - Brewfile + requirements-codegen.txt pin codegen toolchain externals - renovate.json customManagers cover dependencies/versions.json + VERSIONS Regression tests + guards - Voice agent pipeline-mutex concurrency stress (4 writers + 2 readers + 2 resetters under TSAN-friendly conditions) - HTTP-200-ignore-Range resume fallback test (mid-stream failure + retry) - LoRA proto-ABI negative-input cases (malformed buffer, NULL pointer, missing vtable slot, double-clear idempotency, unknown-id remove) - Download orchestrator path-traversal rejection (8 malicious paths + hand-built plan validation) - HandleStreamAdapter Swift tests: terminal-event teardown + sync-unregister - ComponentActor Kotlin tests: atomic loadModel critical section, concurrent serialization, destroy-during-load ordering - OkHttpHttpTransport Kotlin resume contract test (Range header + marker) - check_no_pii_logging.sh CI guard (URL+path INFO logging fingerprint) - no-llm-stream-adapter regression guard (fs.existsSync) Verification — all 6 stacks PASS - C++ Commons: cmake configure + 442/442 build targets + 135/135 ctest + clang-format clean + RAC_API exports 1003/1003 covered - Swift: swift build + 24/24 swift test + swiftlint 0 violations + smoke OK - Kotlin: assemble + 39 jvmTest + 25 testDebugUnitTest + ktlint + detekt + Android example assembleDebug - Flutter: dart analyze (0 err/warn) + 48/48 flutter test + centralization gate + example pub get + analyze - React Native: typecheck across 4 packages + lint + nitrogen current + example typecheck - Web SDK: npm typecheck + lint + 48/48 Vitest + vite build + WASM rebuilt with the 7 new tool-calling session exports embedded + example vite build - IDL: toolchain check + regen idempotent + convenience generator goldens match across swift/kotlin/dart/ts + all 3 centralization gates + PII gate + deprecated-surface gate WASM artifacts - racommons-llamacpp.{js,wasm} rebuilt; new exports: _rac_tool_calling_session _{create,step_with_result,destroy,cancel}_proto + _rac_tool_calling_run_loop _{with_handle,cancel,proto} (7 new symbols total) - wasm/CMakeLists.txt POST_BUILD made tolerant of Emscripten 5.x bundled- worker output (no separate .worker.js) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
… improved dependency management - Updated the label for local workspace packages in .syncpackrc.json to clarify the handling of @runanywhere/proto-ts. - Added new pinned dependencies for @runanywhere/proto-ts, react-native, react, @eslint/js, and tsd to ensure consistent versioning across SDKs. - Adjusted the default and exact range labels in .syncpackrc.json to better reflect dependency management strategies. - Enhanced the descriptions in versions.json for react-native-nitro-modules and nitrogen to clarify their interdependencies and versioning strategy. These changes aim to streamline dependency management and improve clarity for future contributors.
Updates stale `CLAUDE.md` references in source/docs/config to point at
the renamed `AGENTS.md` files. Follow-up to the bulk rename commit that
moved each CLAUDE.md to AGENTS.md across the monorepo.
Per-file changes:
- .gitleaks.toml: allowlist regex `CLAUDE\.md$` → `AGENTS\.md$`
- Package.swift / sdk/runanywhere-swift/Package.swift: comment refs
- sdk/runanywhere-{commons,swift}/ARCHITECTURE.md: doc cross-refs
- sdk/runanywhere-commons/src/core/internal/platform_compat.h
- sdk/runanywhere-swift/Sources/.../{CppBridge*,HandleStreamAdapter,
RunAnywhere+Solutions}.swift: NSLock policy comments
- sdk/runanywhere-flutter/packages/runanywhere_genie/lib/genie.dart
- scripts/validation/check_gradle_centralization.sh
- 4 AGENTS.md title lines (commons, web sdk, flutter sdk, web example)
Vendored CLAUDE.md files in build-*/ and SPM checkouts are left
untouched (not project-owned).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…restore Recovers RN ProtoWire/Hermes proto helpers, Metro bufbuild wiring, Flutter registry fixes, iOS xcframework packaging flags, web lane Playwright scripts, and pod-install Xcode settings that were discarded by git restore. Co-authored-by: Cursor <cursoragent@cursor.com>
Unblock Flutter lanes, harden commons for RAG-off builds and WASM tar.gz extraction, and fix Web/RN model-load and HTTP paths identified by the 20260520 matrix run. Co-authored-by: Cursor <cursoragent@cursor.com>
…ate, device noise) - Commons download_orchestrator: idempotent rac_download_start_proto rejects duplicate starts for an in-flight model and returns the existing task instead of cancelling the first one (CLUSTER-02 / SWIFT-IOS-001 double-tap-Get bug). - Commons device manager: downgrade noisy LOGE to LOGD when callbacks bind after the first register_if_needed call — Web SDK init order makes this benign (WEB-DEVICE-CB-NOISE-001). - Web RunAnywhere.hydrateModelRegistry: emit models.hydrated event on every patch (WEB-OPFS-HYDRATE-UI-001), and reconcile registry when OPFS bytes are missing so re-download is triggered instead of no-op (WEB-REDOWNLOAD-WAIT-001). Co-authored-by: Cursor <cursoragent@cursor.com>
…po, drop make refs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Workflow contract for this branch
main.feat/v2-architecture— nofeat/v2-gap0Xsub-branches.docs/gap0X_final_gate_report.mdto make the merge-time review easier.main, this PR squash-merges (or merge-commits, depending on team preference) the whole thing.What's in this PR today
GAP 01-04 already implemented (Wave A). Per-gap breakdown below.
18 commits, 202 files changed, +62,471 / −589 LOC (most additions are committed proto-generated code across 6 languages).
GAP 01 — IDL + Codegen
idl/directory with 4 proto schemas (model_types,voice_events,pipeline,solutions) + 7 codegen scripts underidl/codegen/..github/workflows/idl-drift-check.yml) that fails any PR where committed generated code drifts from.protosources.toProto()/fromProto()bridges (Kotlin / Dart / TS RN / TS Web).AudioFormatand 1SDKEnvironment(the duplicates were the original motivation for GAP 01).docs/gap01_final_gate_report.md.GAP 02 — Unified Engine Plugin ABI
rac/plugin/headers:rac_primitive.h,rac_engine_vtable.h(8 active + 10 reserved primitive slots),rac_plugin_entry.h(withRAC_PLUGIN_API_VERSION+RAC_STATIC_PLUGIN_REGISTERmacro).src/plugin/rac_plugin_registry.cpp— ABI validation +capability_check+ dedup-by-name + priority sort.llamacpp,llamacpp_vlm,onnx,whispercpp,whisperkit_coreml,metalrt.docs/engine_plugin_authoring.md.docs/gap02_final_gate_report.md.GAP 03 — Dynamic Plugin Loading
rac_plugin_loader.h+plugin_loader.cpp— POSIX (dlopen | RTLD_NOW | RTLD_LOCAL) + Win32 (LoadLibraryA) loader. Symbol resolution:librunanywhere_<name>.so→rac_plugin_entry_<name>.RAC_STATIC_PLUGINSCMake option — forced ON for iOS + Emscripten, default OFF elsewhere. Static path usesRAC_STATIC_PLUGIN_REGISTERwith__attribute__((used))+ per-plugin extern marker so Apple's linker keeps the TU.rac_commonsor the standalonelibrunanywhere_llamacpp.so.docs/plugin_loader_authoring.md.docs/gap03_final_gate_report.md.GAP 04 — Engine Router + Hardware Profile
rac_runtime_id_tenum (CPU / Metal / CoreML / ANE / CUDA / Vulkan / QNN / NNAPI / WebGPU / WASM_SIMD + 7 reserved).rac::router::HardwareProfilewith per-platform probes (Apple chip-gen via sysctl, Androidro.hardware+ QNN/NNAPI dlopen, Linux CUDA/Vulkan dlopen). HonorsRAC_FORCE_RUNTIME=cpuenv override.rac::router::EngineRouterwith deterministic scoring: hard rejects + pinned-name (+10000) + priority ++30runtime match ++10format match + tiebreak by name.rac_plugin_route()C ABI wrapper for non-C++ frontends.rac_engine_metadata_textended withruntimes[]+formats[]arrays; all 6 in-tree backends updated.docs/gap04_final_gate_report.md.Forward roadmap
docs/wave_roadmap.mdoutlines Waves B-E with scope, expected deliverables, dependencies, and likely todo decomposition so the next batch of work starts from a known baseline.Commit log (18 commits, designed for per-phase review)
Backwards compatibility
rac_service_register_provider()+rac_service_create()continue to work for unmigrated callers.rac_plugin_*andrac_router_*APIs are parallel surfaces; sample apps + frontend SDKs see no public-API change.RAC_PLUGIN_API_VERSIONbumps are explicit (1u in GAP 02, 2u in GAP 04). Plugins compiled against an older version are rejected at register time withRAC_ERROR_ABI_VERSION_MISMATCH+ a single specific log line.Test plan
idl-drift-check.yml) green on Ubuntu 22.04 + macOS 14.swift build --target RunAnywheregreen (verified locally)../gradlew :runanywhere-kotlin:compileKotlinJvm+compileDebugKotlinAndroidgreen (verified locally).dart analyze sdk/runanywhere-flutter/packages/runanywhere/libclean (verified locally).tsc --noEmitgreen on bothsdk/runanywhere-react-native/packages/coreandsdk/runanywhere-web/packages/core(verified locally).test_engine_vtable,test_plugin_entry_*,test_legacy_coexistence,test_static_registration,test_plugin_loader{,_abi_mismatch,_double_load},test_engine_router,test_hardware_profile).RAC_STATIC_PLUGINS=ONandrac_registry_plugin_count() > 0at launch.librunanywhere_llamacpp.so; loading viarac_registry_load_plugin()round-trips clean.Risks
1u → 2u) rebuilds every in-tree backend in the same commit; out-of-tree plugins compiled against the older header would be rejected. Safe outcome by design.-force_load/--whole-archive. Thecmake/plugins.cmakehelper that wraps these flags lands in Wave B (GAP 07).LlamaCPPRuntimeSwift target header drift between the binaryRACommons.xcframeworkand the committedCRACommonsheaders is unrelated to this PR (confirmed by building pristinemain).Source-of-truth specs
v2_gap_specs/GAP_01_IDL_AND_CODEGEN.mdv2_gap_specs/GAP_02_UNIFIED_ENGINE_PLUGIN_ABI.mdv2_gap_specs/GAP_03_DYNAMIC_PLUGIN_LOADING.mdv2_gap_specs/GAP_04_ENGINE_ROUTER.mdMade with Cursor
Summary by CodeRabbit
Release Notes
New Features
Documentation
Build & Infrastructure
Tests
Note
Medium Risk
Moderate risk because it replaces the PR CI build workflow and introduces a new root CMake/preset-based build entrypoint that could break cross-platform builds if presets or helper macros diverge from existing scripts.
Overview
Build/CI overhaul for the v2 migration. Adds a root
CMakeLists.txt+CMakePresets.jsonas the single native build entrypoint, plus new shared CMake helpers (cmake/platform.cmake,cmake/plugins.cmake,cmake/protobuf.cmake,cmake/sanitizers.cmake) to standardize platform detection, plugin target creation/force-load, protobuf detection/codegen, and sanitizer flags.GitHub Actions changes. Replaces the previous path-filtered, script-driven
pr-build.ymlwith a smaller preset-based matrix (macOS/Linux/iOS/Android + per-SDK wrapper checks), addsidl-drift-check.ymlto regenerate bindings and fail on drift, and addsstreaming-perf.ymlto build/run streaming parity/perf fixtures and upload artifacts.SDK/tooling + docs updates. Marks generated binding trees as
linguist-generatedin.gitattributes, updates Swift SPM to depend onswift-protobufand exclude unused generated*.grpc.swiftstubs (plus flipsuseLocalNativestotrue), makes Android NDK path configurable viaracNdkVersion, and adds/updates several architecture/migration/release documents and SDK docs to reflect proto-stream voice agent usage and current package versions.Reviewed by Cursor Bugbot for commit 801cac4. Configure here.