[Fix] (Link, Async): carry the resolved gl_PointSize capture request into the SPIR-V handoff and let a deferred verdict name its own severity - the demotion read the request off a reflection slice phase A never fills it into, so its forced carrier was dead code, and its decline reason replayed at a level no shipped build keeps

MobileGL/MG_State/GLState/ProgramState/ProgramLinkTask.cpp

@@ -517,7 +517,9 @@ namespace MobileGL::MG_State::GLState {
         };
     } // namespace
 
-    void ProgramLinkTask::DeferLog(String line) { diagnostics.logLines.push_back(Move(line)); }
+    void ProgramLinkTask::DeferLog(String line, const Int level) {
+        diagnostics.logLines.push_back({level, Move(line)});
+    }
 
     void ProgramLinkTask::SubmitAfter(const Vector<SharedPtr<ShaderCompileTask>>& deps) {
         // +1 for the guard this function releases itself. Without it, a dependency that
@@ -855,6 +857,18 @@ namespace MobileGL::MG_State::GLState {
         spirvHandoff.reflection.uniformReflection = artifacts.uniformReflection;
         spirvHandoff.reflection.blockReflection = artifacts.blockReflection;
         spirvHandoff.reflection.tProgramBlockIndexToGl = artifacts.tProgramBlockIndexToGl;
+        // The capture set is NOT part of that slice (see the handoff's own comment), and the
+        // point-size demotion needs exactly one bit out of it: whether anything asked to
+        // capture gl_PointSize. Derived here, where ResolveTransformFeedbackVaryings has
+        // just filled artifacts.xfbVaryings and before the join moves them away, because a
+        // capture stage that only READS the built-in still has to declare the carrier the
+        // capture binds to - and phase B has no other way to learn that.
+        for (const ProgramObject::XfbVarying& varying : artifacts.xfbVaryings) {
+            if (varying.name == "gl_PointSize") {
+                spirvHandoff.captureRequestsPointSize = true;
+                break;
+            }
+        }
         // Phase B pairs this with its own SpirvArtifacts to insert the completed front end.
         // A COPY, because the GL-thread join moves `artifacts` out of this node before phase B
         // runs - and with the TProgram dropped, because a memo must never hold a glslang arena.

MobileGL/MG_State/GLState/ProgramState/ProgramLinkTask.h

@@ -117,6 +117,19 @@ namespace MobileGL::MG_State::GLState {
             // for phase B after the join has moved `artifacts` away.
             ProgramObject::LinkArtifacts reflection;
 
+            // Whether the RESOLVED transform-feedback capture set names gl_PointSize - the
+            // one fact about `artifacts.xfbVaryings` phase B needs, carried as a derived
+            // bool rather than by widening the slice above, which is deliberately the five
+            // (now eight) fields BuildGlobalUboRouting consumes and nothing else.
+            //
+            // It has to be here and cannot be re-derived: the point-size demotion forces the
+            // capture-capable stage to declare its carrier even when that stage never WRITES
+            // the built-in (ShaderCompiler::DemoteTessellationGeometryPointSizeForProgram's
+            // `captureRequestsPointSize`), and by phase B the only record of the request is
+            // this bit. No new L1 key material: the key already covers
+            // `requestedXfbVaryings`, of which this is a function.
+            Bool captureRequestsPointSize = false;
+
             // L1 shader-translation memo key for this program's SPIR-V (see
             // MG_Util/ShaderTranspiler/TranslationCache.h). Built HERE, at the tail of phase
             // A, and not by phase B - two reasons, both structural:
@@ -201,8 +214,10 @@ namespace MobileGL::MG_State::GLState {
         // Worker-side MGLOG replacement: appended to diagnostics.logLines and replayed by the
         // join, on the GL thread, where a serial implementation would have printed it.
         // Logging straight from a worker interleaves mid-line with the GL thread's output and
-        // lands out of order relative to the glLinkProgram that caused it.
-        void DeferLog(String line);
+        // lands out of order relative to the glLinkProgram that caused it. `level` is the
+        // severity the replay uses; DEBUG (the default) is compiled out of every shipped
+        // build, so a line that has to survive one names its own.
+        void DeferLog(String line, Int level = MOBILEGL_LOG_LEVEL_DEBUG);
 
         // Counts down to zero exactly once. Starts at deps + 1: the extra guard is released
         // by SubmitAfter itself, so a dependency that settles while the edges are still being

MobileGL/MG_State/GLState/ProgramState/ProgramSpirvTask.cpp

@@ -16,10 +16,29 @@
 #include <MG_Util/ShaderTranspiler/TranslationCache.h>
 #include <MG_Util/ShaderTranspiler/Types.h>
 
+#include <atomic>
 #include <cstring>
 
 namespace MobileGL::MG_State::GLState {
-    void ProgramSpirvTask::DeferLog(String line) { diagnostics.logLines.push_back(Move(line)); }
+    namespace {
+        // The MGLOG_*_ONCE latch, moved to the SOURCE of a deferred line. It cannot live at
+        // the replay: Async::ApplyDeferredDiagnostics is ONE site shared by every job in the
+        // tree, so a latch there would silence unrelated lines. And it has to exist: a shader
+        // pack hands the same refusal to program after program, and a per-program WARN on a
+        // path like that is exactly the repeated production logging the house rule forbids.
+        // First occurrence at WARN - the one a bug report needs - every later one back at
+        // DEBUG, which shipped builds compile out.
+        Int FirstTimeWarnLevel(std::atomic_flag& latch) {
+            return latch.test_and_set(std::memory_order_relaxed) ? MOBILEGL_LOG_LEVEL_DEBUG
+                                                                 : MOBILEGL_LOG_LEVEL_WARN;
+        }
+        std::atomic_flag g_pointSizeDeclineReported;
+        std::atomic_flag g_pointSizeOptimizerFailureReported;
+    } // namespace
+
+    void ProgramSpirvTask::DeferLog(String line, const Int level) {
+        diagnostics.logLines.push_back({level, Move(line)});
+    }
 
     void ProgramSpirvTask::SubmitAfter(const SharedPtr<ProgramLinkTask>& phaseA) {
         MOBILEGL_ASSERT(phaseA != nullptr, "ProgramSpirvTask::SubmitAfter: the phase-A node is missing");
@@ -285,13 +304,12 @@ namespace MobileGL::MG_State::GLState {
         // size in those stages - pays one module parse per stage and no rewrite.
         artifacts.pointSizeDemoted = false;
         if (allOptimized && (demoteTessellationPointSize || demoteGeometryPointSize)) {
-            Bool captureRequestsPointSize = false;
-            for (const auto& varying : handoff.reflection.xfbVaryings) {
-                if (varying.name == "gl_PointSize") {
-                    captureRequestsPointSize = true;
-                    break;
-                }
-            }
+            // Read off the HANDOFF's own derived bit, not off `handoff.reflection`: that
+            // field is the routing slice phase A fills with eight named members, and
+            // xfbVaryings is not one of them - reading it there answered "no capture ever
+            // asks for gl_PointSize" on every production link, which left a read-only
+            // capture stage without the carrier its capture binds to.
+            const Bool captureRequestsPointSize = handoff.captureRequestsPointSize;
             ShaderCompiler::PointSizeDemotionOutcome outcome;
             if (!ShaderCompiler::DemoteTessellationGeometryPointSizeForProgram(
                     artifacts.generatedSpirv, handoff.shaderTypes, demoteTessellationPointSize,
@@ -301,7 +319,8 @@ namespace MobileGL::MG_State::GLState {
                 // and the backends' existing refusals stay in charge - honest, just slower.
                 DeferLog(std::format("ProgramObject {}: point-size demotion failed in the optimizer; the "
                                      "program keeps its built-in and the device's declines apply",
-                                     externalIndex));
+                                     externalIndex),
+                         FirstTimeWarnLevel(g_pointSizeOptimizerFailureReported));
             } else if (outcome.demoted) {
                 artifacts.pointSizeDemoted = true;
                 DeferLog(std::format("ProgramObject {}: gl_PointSize demoted to an ordinary varying across "
@@ -309,9 +328,15 @@ namespace MobileGL::MG_State::GLState {
                                      "gl_in reads; rasterized size falls back to 1.0)",
                                      externalIndex));
             } else if (!outcome.declineDetail.empty()) {
+                // THE MOST VALUABLE LINE THIS FEATURE PRODUCES: which module shape the pass
+                // refused, and therefore why an affected device is still about to lose the
+                // program. Nothing else records it - `declineDetail` has no other runtime
+                // surface - so at the deferred channel's DEBUG default it was formatted and
+                // then dropped by every INFO build, i.e. every device and every CI artifact.
                 DeferLog(std::format("ProgramObject {}: point-size demotion declined ({}); the program "
                                      "keeps its built-in and the device's declines apply",
-                                     externalIndex, outcome.declineDetail));
+                                     externalIndex, outcome.declineDetail),
+                         FirstTimeWarnLevel(g_pointSizeDeclineReported));
             }
         }
     }

MobileGL/MG_State/GLState/ProgramState/ProgramSpirvTask.h

@@ -72,8 +72,9 @@ namespace MobileGL::MG_State::GLState {
         void BuildGlobalUboRouting(const ProgramLinkTask::SpirvHandoff& handoff, Uint externalIndex);
 
         // Worker-side MGLOG replacement, replayed by the join on the GL thread. Same reason as
-        // ProgramLinkTask::DeferLog.
-        void DeferLog(String line);
+        // ProgramLinkTask::DeferLog, and the same severity rule: DEBUG is compiled out of
+        // every shipped build, so a line that has to survive one names its own level.
+        void DeferLog(String line, Int level = MOBILEGL_LOG_LEVEL_DEBUG);
 
         SharedPtr<ProgramLinkTask> m_phaseA;
     };

MobileGL/MG_State/GLState/ProgramState/ShaderCompileTask.cpp

@@ -384,12 +384,15 @@ namespace MobileGL::MG_State::GLState {
             // the log, for every failing shader. The info log is what names the offending
             // line; the source is recoverable from the application.
             const SizeT firstLineEnd = artifacts.infoLog.find('\n');
-            diagnostics.logLines.push_back(std::format(
-                "ShaderCompileTask: shader {} (stage {}) failed to compile; compileStatus = false. "
-                "Preprocessed source: {} bytes. First log line: {}",
-                externalIndex, static_cast<Int>(stage), shared.preprocessedSource.length(),
-                artifacts.infoLog.substr(0, firstLineEnd == String::npos ? artifacts.infoLog.length()
-                                                                        : firstLineEnd)));
+            diagnostics.logLines.push_back(
+                {MOBILEGL_LOG_LEVEL_DEBUG,
+                 std::format(
+                     "ShaderCompileTask: shader {} (stage {}) failed to compile; compileStatus = false. "
+                     "Preprocessed source: {} bytes. First log line: {}",
+                     externalIndex, static_cast<Int>(stage), shared.preprocessedSource.length(),
+                     artifacts.infoLog.substr(0, firstLineEnd == String::npos
+                                                     ? artifacts.infoLog.length()
+                                                     : firstLineEnd))});
             if (shouldPopulateCache) {
                 fresh->outcome = ShaderPreprocessOutcome::ParseFailed;
                 fresh->infoLog = artifacts.infoLog;

MobileGL/MG_Test/Util/JobNodeTest.cpp

@@ -441,7 +441,7 @@ TEST(JobNodeException, AnExceptionEscapingABodyCancelsTheJobInsteadOfTerminating
     EXPECT_TRUE(job->IsCancelled());
     EXPECT_FALSE(job->IsComplete());
     ASSERT_EQ(job->diagnostics.logLines.size(), 1u);
-    EXPECT_NE(job->diagnostics.logLines[0].find("boom"), String::npos);
+    EXPECT_NE(job->diagnostics.logLines[0].text.find("boom"), String::npos);
 }
 
 TEST(JobNodeException, ANonStandardExceptionIsContainedToo) {

MobileGL/MG_Util/Async/JobNode.cpp

@@ -95,11 +95,13 @@ namespace MobileGL::MG_Util::Async {
             // which means std::terminate for the whole process. Every job boundary contains
             // it and reports the job as Cancelled; the joining GL thread then sees a node
             // that produced no result, which is the same shape as an abandoned node.
-            diagnostics.logLines.push_back(std::format("Job body threw: {}", e.what()));
+            diagnostics.logLines.push_back(
+                {MOBILEGL_LOG_LEVEL_DEBUG, std::format("Job body threw: {}", e.what())});
             TryTransition(JobState::Running, JobState::Cancelled);
             return;
         } catch (...) {
-            diagnostics.logLines.emplace_back("Job body threw a non-std exception");
+            diagnostics.logLines.push_back(
+                {MOBILEGL_LOG_LEVEL_DEBUG, String("Job body threw a non-std exception")});
             TryTransition(JobState::Running, JobState::Cancelled);
             return;
         }
@@ -162,10 +164,27 @@ namespace MobileGL::MG_Util::Async {
                         "being written");
 
         if (!node.diagnostics.logLines.empty()) {
-            Vector<String> lines;
+            Vector<DeferredLogLine> lines;
             lines.swap(node.diagnostics.logLines);
-            for (const String& line : lines) {
-                MGLOG_D("%s", line.c_str());
+            for (const DeferredLogLine& line : lines) {
+                // Per-line severity, because a shipped build compiles MGLOG_D away entirely
+                // and a verdict that only this channel records would vanish with it. The
+                // levels are the compile-time constants, so a suppressed one costs nothing
+                // beyond the string the worker already built.
+                switch (line.level) {
+                case MOBILEGL_LOG_LEVEL_INFO:
+                    MGLOG_I("%s", line.text.c_str());
+                    break;
+                case MOBILEGL_LOG_LEVEL_WARN:
+                    MGLOG_W("%s", line.text.c_str());
+                    break;
+                case MOBILEGL_LOG_LEVEL_ERROR:
+                    MGLOG_E("%s", line.text.c_str());
+                    break;
+                default:
+                    MGLOG_D("%s", line.text.c_str());
+                    break;
+                }
             }
         }
 

MobileGL/MG_Util/Async/JobNode.h

@@ -9,6 +9,7 @@
 #pragma once
 #include <Includes.h>
 #include <MG_Util/Types.h>
+#include <MG_Util/Debug/Log.h>
 #include <MG_State/GLState/ErrorState/ErrorCode.h>
 #include <MG_State/GLState/ErrorState/ErrorInfo.h>
 
@@ -35,9 +36,25 @@ namespace MobileGL::MG_Util::Async {
         UniquePtr<ErrorInfo> info;
     };
 
+    // One line of worker-side MGLOG text, with the severity the join replays it at.
+    //
+    // DEBUG is the default and stays the default: nearly every deferred line is per-program
+    // trace that a shipped build compiles out, which is the whole reason this channel could
+    // be a plain string vector for as long as it was. A line a SHIPPED build has to show -
+    // the reason a repair refused, which no other surface records - has to name its level
+    // here, or it is formatted on the worker and then thrown away at replay under the INFO
+    // level every device and CI build pins. Callers that sit on a repeated path latch at
+    // the SOURCE (a per-call-site atomic, exactly what MGLOG_*_ONCE does): the replay below
+    // is one shared site for every job in the tree, so a latch there would silence
+    // unrelated lines.
+    struct DeferredLogLine {
+        Int level = MOBILEGL_LOG_LEVEL_DEBUG;
+        String text;
+    };
+
     struct JobDiagnostics {
-        Vector<DeferredError> errors; // replayed, in ascending `sequence`, by the join
-        Vector<String> logLines;      // worker-side MGLOG text, flushed in order by the join
+        Vector<DeferredError> errors;      // replayed, in ascending `sequence`, by the join
+        Vector<DeferredLogLine> logLines;  // worker-side MGLOG text, flushed in order by the join
     };
 
     // The scheduling primitive every asynchronous compile and link is built on. A node owns