Merge Ψ-W2-T2: a bit-identical capture collapses to one lossless mono channel

# Conflicts:
#	src/shell/capture/CLAUDE.md
#	src/shell/capture/capture.cpp
#	src/shell/capture/capture.h

src/core/capture/CLAUDE.md

@@ -45,7 +45,7 @@ Detail specific to these pure modules:
 
 ## Modules
 
-- `wav_codec` — chunk walker + layout parse + float32 build + size-field patch + content hashes; the single pure RIFF/WAV owner (`wav_trim` is retired; `wav_codec` is the sole owner).
+- `wav_codec` — chunk walker + layout parse + float32 build + size-field patch + the lossless mono collapse + content hashes; the single pure RIFF/WAV owner (`wav_trim` is retired; `wav_codec` is the sole owner).
 - `capture_realtime` (`core/capture`, **renamed from `realtime_record` in Q-W3** — the Q-9 naming rider: pure module takes the stem, the shell takes the suffix, matching `drag_out`/`drag_out_win`) — the M8 realtime-record pure logic: capture scope + FX-tap point → `I_RECMODE`/`I_RECMODE_FLAGS` values, wet/dry → tap point, the recorded-file → `Sample` mapping, and the async record-phase state machine. Depends on `bank_model` for the plain `Sample`/`SourceMode` types. The transport/temp-track/send recipe lives in the shell (`shell/capture/capture_realtime_shell.cpp` + `capture_realtime_finalize.cpp`).
 - `batch_capture` — pure batch-capture planner: maps source ranges to capture units and aggregates results.
 - `capture_paths` — the REAPER-free path arithmetic behind offline capture: bank-subfolder + unique-filename derivation (`deriveBankPaths`, forward-slash form, no filesystem touch), the absolute-render-dir vs. project-relative-index-path split (`BankPaths`), the persist-side inverse (`resolveBankFile`, `projectDirOfRpp`), the Save-As bank-relocation plan (`deriveRelocationPlan`), and the GUID-primary project-identity classifier (`classifyProjectTransition` → `NoOp`/`Load`/`SaveAsRelocate`) the persist-poll timer drives.
@@ -82,6 +82,22 @@ Detail specific to these pure modules:
 - `kRenderPreFaderStems` (&8192) is deliberately **not** used — REAPER offline
   render has no true pre-FX "dry" bit; FX scoping is done entirely by the
   FX-bypass-around-render mechanism, never by a render bit.
+- **The mono collapse changes a capture's content identity, by design.**
+  `hashWavContent` covers the `fmt ` body plus the `data` payload, and the collapse
+  rewrites both — so a collapsed capture does NOT hash-dedup against a stereo twin of
+  the same audio already in the bank. Accepted: the predicate is deterministic over
+  deterministic bytes, so repeats of the same request still dedup against each other,
+  which is what the bit-identical-repeats invariant actually asks for. Do not "fix"
+  this by hashing pre-collapse — that would make two entries with different audio
+  layouts share one identity.
+- **The collapse's minimal rebuild also drops `bext`/iXML/LIST — a source-position
+  consequence, not only a hashing one.** REAPER's renderer writes a `bext` time
+  reference, and REAPER's own import paths can position an item at that BWF timestamp,
+  so a collapsed capture loses it while a declined (non-collapsed) capture from the same
+  action keeps it — two captures from one action behave differently on re-import.
+  `shell/capture/insert.cpp` is unaffected (it drives `SetEditCurPos` + `InsertMedia`
+  rather than reading BWF), so this is not a defect in the shipped insert path.
+  Accepted, not verified against a DAW re-import: `[verify — DAW]`.
 - `tail_control`'s `kDefaultManualTailMs`/`kManualStepMs` and
   `render_settings`'s `kMaxTailMs`/`kAutoTrimThresholdDb` are separate constants
   in separate files by design (panel-facing default/step vs. runaway-guard cap)

src/core/capture/wav_codec.cpp

@@ -257,6 +257,49 @@ std::vector<std::uint8_t> buildFloat32Wav(int nch, std::uint32_t rate,
     return out;
 }
 
+MonoCollapse collapseToMono(const std::vector<std::uint8_t>& bytes) {
+    MonoCollapse out;
+
+    const WavLayout layout = parseWavLayout(bytes);
+    if (!layout.valid || layout.channelCount < 2) return out;
+
+    const std::size_t frames = layout.frameCount();
+    if (frames == 0) return out;
+
+    const std::size_t stride = layout.channelCount;
+    const std::vector<AudioSample> pcm = extractFloatFrames(bytes, layout, 0, frames);
+    if (pcm.size() != frames * stride) return out;  // short read -> decline, never guess
+
+    // Bit patterns, not values: see the header. memcpy is the only defined float->bits
+    // read, and it compiles to a register move.
+    auto bitsOf = [](AudioSample s) {
+        std::uint32_t bits = 0;
+        std::memcpy(&bits, &s, 4u);
+        return bits;
+    };
+    for (std::size_t f = 0; f < frames; ++f) {
+        const std::uint32_t first = bitsOf(pcm[f * stride]);
+        for (std::size_t c = 1; c < stride; ++c) {
+            if (bitsOf(pcm[f * stride + c]) != first) return out;
+        }
+    }
+
+    // float -> double -> float round-trips exactly for every finite value and for
+    // +-0/+-infinity (double represents every float bit pattern in those classes), so
+    // channel 0 reaches the rebuilt file unaltered. The one hole: a signaling NaN is
+    // quieted by the float->double promotion, so an identical-bit sNaN pair could
+    // collapse to a different bit pattern than it started with. Not reachable from
+    // REAPER-rendered audio, but the bit-identical predicate above admits NaN inputs,
+    // so this rebuild is not exempt from the claim it makes.
+    std::vector<double> mono(frames);
+    for (std::size_t f = 0; f < frames; ++f)
+        mono[f] = static_cast<double>(pcm[f * stride]);
+
+    out.collapsed = true;
+    out.bytes = buildFloat32Wav(1, layout.sampleRate, frames, mono);
+    return out;
+}
+
 std::string hashBytes(const std::uint8_t* data, std::size_t len) {
     // FNV-1a 64-bit: deterministic, no dependencies, adequate for dedup identity.
     std::uint64_t h = kFnvOffsetBasis;

src/core/capture/wav_codec.h

@@ -90,6 +90,33 @@ std::vector<std::uint8_t> buildFloat32Wav(int nch, std::uint32_t rate,
                                           std::size_t frameCount,
                                           const std::vector<double>& interleaved);
 
+// --- Lossless mono collapse ---------------------------------------------------
+
+// The outcome of the bit-identical mono collapse. `collapsed == false` means the
+// caller must leave the source file exactly as it is — it writes nothing.
+struct MonoCollapse {
+    bool collapsed = false;
+    std::vector<std::uint8_t> bytes;  // the rebuilt 1-channel WAV; empty unless collapsed
+};
+
+// Collapses a multi-channel float32 WAV to one channel when EVERY channel of EVERY
+// frame carries the identical float BIT PATTERN. Bit equality, never an epsilon and
+// never `==` on floats: +0.0/-0.0 and two NaNs with differing payloads are NOT
+// identical and are never folded. Frame count, sample rate and bit depth are
+// preserved — only the interleave stride changes — so the collapse cannot lose
+// information, and a lossy downmix (summing differing channels) is not something
+// this can express.
+//
+// Declines for: bytes that do not parse; a file already at one channel; a zero-frame
+// file (no frame of evidence to act on); any differing channel pair.
+//
+// The rebuild is a canonical minimal WAV, so non-audio chunks (a renderer's `bext`
+// timestamp, iXML, LIST) do not survive it. That much hashWavContent already skips —
+// but the collapse rewrites the `fmt ` body and the `data` payload too, which moves
+// the file's content identity; see this directory's CLAUDE.md for what that costs,
+// including the bext/source-position consequence beyond hashing.
+MonoCollapse collapseToMono(const std::vector<std::uint8_t>& bytes);
+
 // --- Content identity (dedup hashes) -----------------------------------------
 
 // Deterministic FNV-1a 64-bit content hash over `len` bytes, as 16-char lowercase

src/core/model/bank_model.h

@@ -88,6 +88,11 @@ struct Sample {
 
     double wetDry = 1.0;            // 1.0 = fully wet, 0.0 = fully dry
 
+    // Channels in the file this entry names — equal to its `fmt ` count by
+    // construction on every path that measures it, which is what makes the
+    // instrument's mono/stereo-toggle default agree with the audio (the waveform
+    // lane count reads the decoded file directly, not this field). 0 = unknown —
+    // a pre-field entry, or a capture whose file could not be parsed to measure it.
     int    channelCount = 0;
     int    sampleRate   = 0;
 

src/shell/capture/CLAUDE.md

@@ -51,7 +51,7 @@ detail not covered there:
 
 ## Modules
 
-- `capture` — two CONCRETE backends with deliberately different lifecycles (no shared interface — the former `ICaptureBackend` was deleted in Q-W3, T4-26: one deriver, zero polymorphic call sites): `OfflineRenderBackend` (deterministic default, synchronous) and `RealtimeRecordBackend` (async begin/tick/abort). Input: `CaptureRequest`. Output: finished file + populated `Sample` handed to `bank_model`.
+- `capture` — two CONCRETE backends with deliberately different lifecycles (no shared interface — the former `ICaptureBackend` was deleted in Q-W3, T4-26: one deriver, zero polymorphic call sites): `OfflineRenderBackend` (deterministic default, synchronous) and `RealtimeRecordBackend` (async begin/tick/abort). Input: `CaptureRequest`. Output: finished file + populated `Sample` handed to `bank_model`. It also owns the two file-side steps both backends share, in this order: `collapseCapturedFileToMono` (the lossless mono collapse, applied to the landed file) and `stampCaptureSample`, which measures the channel count off that same file so the entry and the audio cannot disagree. And `captureNameFor` — the impure local-clock read the entry points call to build a request's label + stem, kept out of the pure `core/capture/capture_name` composition it feeds.
 - `scope_resolve` (`shell/capture`) — scope/source resolution shared by every capture entry point (Q-W3 hoist out of `main.cpp`): razor-else-time range inference, selected-track/selected-item-owning-track collection with canonical GUIDs, and the M10 provenance-assembly inputs (read BEFORE the FX-bypass guard neutralizes the in-scope chain). Also the one place a source track's NAME is read (`trackName`, via `GetTrackName` — chosen over `P_NAME` because it already answers REAPER's `"Track N"` convention for an unnamed track), landed on `ResolvedSource::trackNames` parallel to `sourceTracks` and composed into the capture's label + stem by the pure `core/capture/capture_name`.
 - `render_selection` (`shell/capture`) — the transient track selection a selected-tracks render (`&128`) requires, as a stack RAII guard: REAPER prints whatever tracks are selected, so `renderOffline` makes the request's own tracks BE the selection for the render's duration and restores the user's set on every exit path. Engaged ONLY for that source mode, which leaves a stated residual: a `&32` selected-items render still prints whatever ITEMS the user has selected. Live captures are unaffected (that selection is the source), but a recipe replay of a `SelectedItems` capture renders against whatever happens to be selected then — the recipe stores tracks and a range, never item GUIDs, so this guard cannot close it. Filed in `docs/TODO.md`.
 - `render_isolation` (`shell/capture`) — the transient upstream silencing a ranged ITEM render needs, as a stack RAII guard alongside the two above: the selected-tracks source prints everything flowing INTO the track, so each direct folder child's `B_MAINSEND` and each of the track's receives' `B_MUTE` are cut for the render and restored on every exit path. Direct children only — a grandchild reaches the track through the child that owns it. The child-set walk is pure (`core/capture/track_topology`).
@@ -61,7 +61,7 @@ detail not covered there:
 - `realtime_lifecycle` (`shell/capture`) — the in-flight realtime-capture state machine + globals (Q-W3 hoist): the action starts it, `OnTimer` drives it per tick via `DriveRealtimeCapture` (a single-pointer-test idle fast path — load-bearing hot-path guardrail), `CommitRealtimeResult` lands a finished capture in the bank, `AbortRealtimeCaptureForUnload` tears down cleanly on extension unload.
 - `capture_realtime_shell` (`shell/capture`) — the async realtime-record backend surface (Q-W6 split of the former fat `capture.h`): `RealtimeRecordBackend::begin`/`tick`/`abort`, transport-driven across timer ticks (a realtime record cannot block REAPER's UI for its own duration). Deliberately shares NO interface with the offline backend — the lifecycles genuinely differ (the former `ICaptureBackend` interface was deleted in Q-W3, T4-26).
 - `capture_realtime_finalize` (`shell/capture`) — the file-side half of the realtime-record shell (Q-W3, T4-08): discovers the file REAPER actually recorded, moves it into the bank, runs the Auto-tail PCM decay-scan trim, and populates the finished `Sample`.
-- `insert` — placement via `InsertMedia`. **Conform-to-project-tempo is an explicit opt-in flag, never silent stretching.**
+- `insert` — placement via `InsertMedia`. **Conform-to-project-tempo is an explicit opt-in flag, never silent stretching.** The mono collapse needs no change here: `insert.cpp` passes only a path to `InsertMedia`, and REAPER derives the item's channel count from the file itself — a 1-channel WAV yields a mono item for free.
 - `provenance_shell` — FX-chain identity queries via `TrackFX_*`/`TakeFX_*` APIs; feeds the pure `provenance` fingerprint builder. Stamps `Sample.provenance` on capture; ambiguous/mixed cases record nothing conservatively.
 - `track_guid` — shared `MediaTrack*` → canonical GUID-string formatter; single source of truth for membership keys.
 - `item_read` — the ONE place a `MediaItem*` is read for its canonical GUID string (`itemGuid`) and for the durable `P_LANENAME` of the fixed lane it sits on (`itemLaneName`); extracted from previously-duplicated `itemGuid`/`itemLaneName` pairs in `view.cpp` and `bank_panel.cpp` — the item-read analog of `track_guid`'s single `MediaTrack*`→GUID-key formatter. Callers must already know the track is fixed-lane (`I_FREEMODE==2`) before calling `itemLaneName`; the pure `isOnManualLane` predicate handles the non-fixed-lane case separately.

src/shell/capture/capture.cpp

@@ -1,5 +1,6 @@
 // REAPER-facing offline-render backend (OfflineRenderBackend) plus the shared
-// backend helpers (makeUniqueTag / stampCaptureSample).
+// backend helpers (makeUniqueTag / captureNameFor / collapseCapturedFileToMono /
+// stampCaptureSample).
 //
 // Includes reaper_plugin_functions.h WITHOUT REAPERAPI_IMPLEMENT — main.cpp is
 // the one TU that defines the API pointers; here they are extern.
@@ -31,7 +32,7 @@
 #include <vector>
 
 #include "core/capture/capture_paths.h"
-#include "core/capture/wav_codec.h"   // hashWavContent — the one WAV/RIFF owner
+#include "core/capture/wav_codec.h"   // hashWavContent / collapseToMono — the one WAV/RIFF owner
 #include "core/util/file_bytes.h"
 #include "core/capture/render_settings.h"
 #include "core/capture/render_window.h"  // frameCountFor — the exact-bounds number
@@ -227,13 +228,54 @@ CaptureName captureNameFor(const std::vector<std::string>& sourceNames,
     return composeCaptureName(in);
 }
 
+bool collapseCapturedFileToMono(const std::string& absolutePath) {
+    const std::vector<std::uint8_t> bytes = util::readFileBytes(absolutePath);
+    if (bytes.empty()) return false;
+
+    const MonoCollapse collapse = collapseToMono(bytes);
+    if (!collapse.collapsed) return false;
+
+    // Sibling temp + rename, NOT an in-place truncating write: this runs unconditionally
+    // on the deterministic offline path (which never reopened its render for write before
+    // this step existed), so a mid-write failure here must not land a truncated file that
+    // stampCaptureSample then hashes as a false CaptureStatus::Ok. rename() replaces the
+    // destination in one step, so the original bytes are never destroyed until the
+    // replacement is known-complete; a failed write or rename leaves the original file
+    // untouched and self-cleans the temp rather than littering it.
+    const std::string tempPath = absolutePath + ".moncollapse.tmp";
+    {
+        std::ofstream out(tempPath, std::ios::binary | std::ios::trunc);
+        if (!out) return false;
+        out.write(reinterpret_cast<const char*>(collapse.bytes.data()),
+                  static_cast<std::streamsize>(collapse.bytes.size()));
+        const bool wroteOk = static_cast<bool>(out);
+        out.close();
+        if (!wroteOk) {
+            std::error_code ec;
+            std::filesystem::remove(tempPath, ec);
+            return false;
+        }
+    }
+    std::error_code ec;
+    std::filesystem::rename(tempPath, absolutePath, ec);
+    if (ec) {
+        std::filesystem::remove(tempPath, ec);  // don't leave litter on a failed rename
+        return false;
+    }
+    return true;
+}
+
 void stampCaptureSample(Sample& s, const CaptureRequest& req,
                         ReaProject* rateProj, ReaProject* timeSigProj,
                         const std::string& absolutePath) {
-    // Track GUIDs + channel count: echoed from the request (the caller resolved
-    // the selection; the backends stay source-agnostic).
+    // Track GUIDs echoed from the request (the caller resolved the selection; the
+    // backends stay source-agnostic). channelCount starts at 0 (unknown, the same
+    // sentinel bank_model already uses for a pre-field entry) rather than the
+    // request's value — the request always asks for 2, so echoing it would claim a
+    // measurement that never happened for the unparseable-file case below. The
+    // produced FILE overrides it below whenever it parses.
     s.trackGuids   = req.trackGuids;
-    s.channelCount = req.channelCount;
+    s.channelCount = 0;
 
     // PROJECT_SRATE can read 0 on a project that never pinned a rate — stays 0
     // (honest "unknown") rather than a bogus literal.
@@ -264,6 +306,10 @@ void stampCaptureSample(Sample& s, const CaptureRequest& req,
         const std::vector<std::uint8_t> fileBytes = util::readFileBytes(absolutePath);
         if (!fileBytes.empty()) {
             s.contentHash = hashWavContent(fileBytes);
+            // The one authority for the entry's channel count is the file's own `fmt`
+            // — never the render request, which asks for 2 on every capture path.
+            const WavLayout layout = parseWavLayout(fileBytes);
+            if (layout.valid) s.channelCount = static_cast<int>(layout.channelCount);
         }
     }
 
@@ -473,6 +519,14 @@ CaptureResult OfflineRenderBackend::capture(const CaptureRequest& request) {
         }
     }
 
+    // Lossless mono collapse, deliberately AFTER the bounds gate: the gate measures
+    // REAPER's own render against the requested window, so nothing of ours may sit
+    // between the render and that measurement, and a refusal must delete the
+    // renderer's file rather than one this step had already rewritten. The collapse
+    // preserves the frame count, so the two are order-independent in outcome — only
+    // in what each is measuring.
+    const bool collapsedToMono = collapseCapturedFileToMono(expectedPath);
+
     // Record the request's own bounds (exact) rather than re-measuring the file.
     Sample s;
     // Same uniqueTag that named the file — calling makeUniqueTag() again could
@@ -499,7 +553,8 @@ CaptureResult OfflineRenderBackend::capture(const CaptureRequest& request) {
     result.message = "Captured [" +
                      std::to_string(request.startSeconds) + "s, " +
                      std::to_string(request.endSeconds) + "s] -> " +
-                     paths.relativePath;
+                     paths.relativePath +
+                     (collapsedToMono ? " (collapsed to mono)" : "");
     return result;
 }
 

src/shell/capture/capture.h

@@ -1,6 +1,7 @@
 #pragma once
 // The shared capture seam: CaptureRequest/CaptureResult (types both backends
-// speak), OfflineRenderBackend, and the makeUniqueTag/stampCaptureSample helpers.
+// speak), OfflineRenderBackend, and the helpers both backends share (naming, the
+// mono collapse, the Sample stamp).
 // Realtime's async begin/tick/abort surface lives in capture_realtime_shell.h.
 //
 // REAPER-free on purpose (bank_model only) so callers can depend on the seam
@@ -54,6 +55,9 @@ struct CaptureRequest {
 
     // 0 sampleRate => follow project rate.
     int         sampleRate   = 0;
+    // What the RENDER is asked for (RENDER_CHANNELS / the realtime record mode), not
+    // what the capture lands as: a dual-mono render is collapsed to 1 channel after
+    // the fact, and the Sample's count comes from the produced file.
     int         channelCount = 2;
     WavBitDepth bitDepth      = WavBitDepth::Float32;
 
@@ -118,9 +122,19 @@ std::string makeUniqueTag(const std::string& prefix);
 CaptureName captureNameFor(const std::vector<std::string>& sourceNames,
                            int ordinal, const std::string& fallback);
 
-// Stamps the metadata shared by both backends onto `s`: trackGuids + channelCount
-// (echoed from the request), resolved sampleRate (request rate, else PROJECT_SRATE
-// from `rateProj`), captureTempo, the capture-start time signature
+// Rewrites a just-captured WAV in place as a 1-channel file when its channels are
+// bit-identical (the pure `collapseToMono` decides). Every other file is left
+// untouched, byte for byte, so the not-collapsed path is exactly what the backend
+// produced. Must run BEFORE stampCaptureSample, which measures the landed file.
+// Returns whether the file was actually rewritten (collapsed AND the write landed) —
+// callers use it to make the collapse observable in the reported CaptureResult.
+bool collapseCapturedFileToMono(const std::string& absolutePath);
+
+// Stamps the metadata shared by both backends onto `s`: trackGuids (echoed from the
+// request) + channelCount (measured from the produced file's `fmt`; 0/unknown as the
+// fallback for a file that cannot be parsed — never the request's value, which is
+// always 2 and was never actually measured), resolved sampleRate (request rate,
+// else PROJECT_SRATE from `rateProj`), captureTempo, the capture-start time signature
 // (TimeMap_GetTimeSigAtTime against `timeSigProj` — offline passes nullptr for the
 // active project, realtime pins the record's own project), the WAV-aware
 // contentHash of `absolutePath` (left empty when unreadable), and createdTimestamp.

src/shell/capture/capture_realtime_finalize.cpp

@@ -184,6 +184,10 @@ CaptureResult finalizeRecording(ReaProject* proj, MediaTrack* temp,
                                                 request.endSeconds);
     }
 
+    // Channel-domain rewrite, after the frame-domain trim so it acts on the final
+    // frame set; it preserves the frame count, so the trimmed length above still holds.
+    const bool collapsedToMono = collapseCapturedFileToMono(destPath);
+
     // Pure recorded-capture -> Sample mapping (identity, bounds echo, tier).
     RecordedCapture cap;
     cap.relativePath = paths.relativePath;
@@ -194,7 +198,9 @@ CaptureResult finalizeRecording(ReaProject* proj, MediaTrack* temp,
     cap.wetDry       = request.wetDry;
     cap.displayName  = request.label();
     cap.trackGuids   = request.trackGuids;
-    cap.channelCount = request.channelCount;
+    // channelCount deliberately left unset here: stampCaptureSample measures it from
+    // the file below. Echoing the request was this path's own defect — it parsed the
+    // recorded layout for the trim and still reported the requested 2.
 
     result.status  = CaptureStatus::Ok;
     result.sample  = sampleFromRecordedCapture(cap);
@@ -219,7 +225,8 @@ CaptureResult finalizeRecording(ReaProject* proj, MediaTrack* temp,
                      std::to_string(request.startSeconds) + "s, " +
                      std::to_string(request.endSeconds) + "s] (recorded " +
                      std::to_string(result.sample.lengthSeconds) + "s) -> " +
-                     paths.relativePath;
+                     paths.relativePath +
+                     (collapsedToMono ? " (collapsed to mono)" : "");
     return result;
 }
 

src/shell/instrument/processor_reload.cpp

@@ -148,8 +148,9 @@ std::string ReaSamplerProcessor::reloadInstrument() {
     //    no-play — no crash, no retry loop.
     if (const SelectedSample* sel = findRef(refs, selId)) {
         // Auto-default: channelModeFor computes the mode from the loaded capture's channel
-        // count (always 2 for extension captures; mono only for ingest-imported mono files).
-        // An unknown count (0) or explicit user choice keeps the mode.
+        // count — 1 for an ingested mono file or a capture whose channels came out
+        // bit-identical and collapsed, 2 otherwise. An unknown count (0) or an explicit
+        // user choice keeps the mode.
         {
             std::lock_guard<std::mutex> cm(channelModeMutex_);
             channelMode_ = channelModeFor(sel->channelCount, channelMode_,