feat(encode): RGB-direct (EFC) is now the DEFAULT on capable hosts — gated by a session cursor-blend hint

B2 default-on (design/vulkan-rgb-direct-encode.md): wherever the probe
passes, Vulkan Video sessions now take the EFC RGB source by default —
direct import on aligned modes, padded-copy staging on unaligned ones
(1080p). PUNKTFUNK_VULKAN_RGB_DIRECT becomes the override: =0 disables,
=1 forces, unset = the default below.

The one session class that must NOT default on: cursor-as-metadata
captures (every non-gamescope compositor), where the CSC shader's blend
IS the visible pointer — the EFC cannot composite, and defaulting there
would silently drop the cursor from the stream. The hint rides the
existing plumbing:

- SessionPlan gains cursor_blend, resolved once where the compositor is
  known (gamescope embeds the pointer itself → false; kwin/mutter/
  wlroots/hyprland → true), and shows up in the logged plan line.
- open_video/open_video_backend thread it through (native pump: all
  three encoder-open sites read plan.cursor_blend; GameStream monitor
  capture: true — it negotiates metadata cursor; spike: false).
- VulkanVideoEncoder::open resolves: env override, else ON iff the
  session never hands us cursor bitmaps. The warn-once for a cursor on
  an RGB session (forced via =1) stays.

Verified on-hw box (Linux): pf-encode + punktfunk-host compile, clippy
clean, unit suite green. The GPU paths themselves are unchanged from the
smoke-validated 96e19986 — this commit only changes which sessions
select them by default.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

crates/pf-encode/src/enc/linux/vulkan_video.rs

@@ -69,12 +69,19 @@ fn quality_request() -> u32 {
         .unwrap_or(0)
 }
 
-/// `PUNKTFUNK_VULKAN_RGB_DIRECT=1` opts into the RGB-direct encode source (B1,
-/// design/vulkan-rgb-direct-encode.md): the captured RGB frame is handed to the encoder as-is
-/// and the VCN EFC front-end does the 709-narrow CSC inline — no compute CSC, no plane copies,
-/// one queue submit per frame. Default OFF until the color/latency A/B graduates it (B2).
-fn rgb_request() -> bool {
-    std::env::var("PUNKTFUNK_VULKAN_RGB_DIRECT").is_ok_and(|v| v == "1")
+/// `PUNKTFUNK_VULKAN_RGB_DIRECT` override for the RGB-direct encode source
+/// (design/vulkan-rgb-direct-encode.md): the captured RGB frame is the encode source and the
+/// VCN EFC front-end does the 709-narrow CSC inline — no compute CSC, no plane copies, one
+/// queue submit per frame (unaligned modes go through the padded-copy staging blit). B2
+/// default: ON wherever the probe passes, EXCEPT sessions that may need the CSC's cursor
+/// blend (see [`VulkanVideoEncoder::open`]). `=0` disables outright; `=1` forces it even on
+/// cursor-blend sessions (the pointer will be missing from the stream); unset = the default.
+fn rgb_request() -> Option<bool> {
+    match std::env::var("PUNKTFUNK_VULKAN_RGB_DIRECT") {
+        Ok(v) if v == "0" => Some(false),
+        Ok(_) => Some(true),
+        Err(_) => None,
+    }
 }
 
 /// Live RGB-direct session config: the chroma-siting bits the session was created with
@@ -408,9 +415,21 @@ pub struct VulkanVideoEncoder {
 unsafe impl Send for VulkanVideoEncoder {}
 
 impl VulkanVideoEncoder {
-    /// Signature mirrors the other Linux backends' `open` (see `nvenc_cuda::NvencCudaEncoder::open`).
-    pub fn open(codec: Codec, width: u32, height: u32, fps: u32, bitrate_bps: u64) -> Result<Self> {
-        Self::open_opts(codec, width, height, fps, bitrate_bps, rgb_request())
+    /// Signature mirrors the other Linux backends' `open` plus `cursor_blend`: the session may
+    /// hand this encoder cursor bitmaps to composite (cursor-as-metadata captures — every
+    /// non-gamescope compositor). The EFC cannot blend, so such sessions default to the CSC
+    /// path; everywhere else the RGB-direct source is the DEFAULT wherever the probe passes
+    /// (B2). `PUNKTFUNK_VULKAN_RGB_DIRECT` overrides both ways (see [`rgb_request`]).
+    pub fn open(
+        codec: Codec,
+        width: u32,
+        height: u32,
+        fps: u32,
+        bitrate_bps: u64,
+        cursor_blend: bool,
+    ) -> Result<Self> {
+        let want_rgb = rgb_request().unwrap_or(!cursor_blend);
+        Self::open_opts(codec, width, height, fps, bitrate_bps, want_rgb)
     }
 
     /// `open` with the RGB-direct request explicit instead of read from the env — the smoke
@@ -563,7 +582,9 @@ impl VulkanVideoEncoder {
                 (_, _, Some(RgbDirect { padded: true, .. })) =>
                     "active(padded-copy: mode is not 64x16-aligned — staging blit + edge \
                      duplication instead of the direct import)",
-                (Ok(_), false, None) => "available(off; set PUNKTFUNK_VULKAN_RGB_DIRECT=1)",
+                (Ok(_), false, None) =>
+                    "available(off: PUNKTFUNK_VULKAN_RGB_DIRECT=0, or a cursor-blend session \
+                     — =1 forces)",
                 (Err(e), _, None) => e,
                 // (Ok, wanted) always builds Some above.
                 (Ok(_), true, None) => unreachable!("rgb gate and cfg disagree"),

crates/pf-encode/src/lib.rs

@@ -129,6 +129,9 @@ pub fn open_video(
     cuda: bool,
     bit_depth: u8,
     chroma: ChromaFormat,
+    // The session may hand this encoder cursor bitmaps to composite (cursor-as-metadata
+    // captures). Backends whose fast path can't blend (Vulkan EFC RGB-direct) key off it.
+    cursor_blend: bool,
 ) -> Result<Box<dyn Encoder>> {
     let (inner, backend) = open_video_backend(
         codec,
@@ -140,6 +143,7 @@ pub fn open_video(
         cuda,
         bit_depth,
         chroma,
+        cursor_blend,
     )?;
     // Record what this session encodes on (the mgmt API's "currently used GPU"): the backend label
     // is reported by `open_video_backend` from the branch that ACTUALLY opened — not re-derived by
@@ -264,7 +268,9 @@ fn open_video_backend(
     cuda: bool,
     bit_depth: u8,
     chroma: ChromaFormat,
+    cursor_blend: bool,
 ) -> Result<(Box<dyn Encoder>, &'static str)> {
+    let _ = cursor_blend; // consumed only by the Linux vulkan-encode arm below
     validate_dimensions(codec, width, height)?;
     // Refresh/fps must be positive and sane: fps feeds the encoder time_base (`Rational(1, fps)`)
     // and the pts→ns conversion (`pts * 1e9 / fps`), so 0 builds a 1/0 rational / divides by zero.
@@ -322,8 +328,14 @@ fn open_video_backend(
                 && vulkan_encode_enabled()
                 && !(bit_depth == 10 && format.is_hdr_rgb10())
             {
-                match vulkan_video::VulkanVideoEncoder::open(codec, width, height, fps, bitrate_bps)
-                {
+                match vulkan_video::VulkanVideoEncoder::open(
+                    codec,
+                    width,
+                    height,
+                    fps,
+                    bitrate_bps,
+                    cursor_blend,
+                ) {
                     Ok(e) => {
                         tracing::info!(
                             codec = ?codec,
@@ -376,8 +388,15 @@ fn open_video_backend(
                             "the Vulkan Video encoder supports HEVC + AV1; the session negotiated {codec:?}"
                         );
                     }
-                    vulkan_video::VulkanVideoEncoder::open(codec, width, height, fps, bitrate_bps)
-                        .map(|e| (Box::new(e) as Box<dyn Encoder>, "vulkan"))
+                    vulkan_video::VulkanVideoEncoder::open(
+                        codec,
+                        width,
+                        height,
+                        fps,
+                        bitrate_bps,
+                        cursor_blend,
+                    )
+                    .map(|e| (Box::new(e) as Box<dyn Encoder>, "vulkan"))
                 }
                 #[cfg(not(feature = "vulkan-encode"))]
                 {

crates/punktfunk-host/src/gamestream/stream.rs

@@ -658,6 +658,9 @@ fn stream_body(
         // GameStream/Moonlight stays 4:2:0 — stock Moonlight clients can't decode 4:4:4, and the
         // Windows IDD-push capturer can't yet deliver full-chroma frames. 4:4:4 is punktfunk/1-native only.
         encode::ChromaFormat::Yuv420,
+        // Desktop monitor capture negotiates cursor-as-metadata where available — the encoder
+        // may be handed cursor bitmaps to composite.
+        true,
     )
     .context("open video encoder for stream")?;
     // FEC overhead percent (Sunshine default 20). Override with PUNKTFUNK_FEC_PCT (0 = data-only).
@@ -811,6 +814,7 @@ fn stream_body(
                     frame.is_cuda(),
                     gs_bit_depth(frame.format),
                     encode::ChromaFormat::Yuv420, // GameStream stays 4:2:0
+                    true,                         // metadata-cursor capture — see the first open
                 )
                 .context("reopen encoder after rebuild")?;
                 supports_rfi = enc.caps().supports_rfi;

crates/punktfunk-host/src/native/stream.rs

@@ -983,7 +983,12 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
     // path now reads this typed `SessionPlan` instead of re-deriving from config at each dispatch site
     // (the latent "capture and encode disagree on the backend" hazard, plan §2.4). `bit_depth` is the
     // only per-session input — capture/topology/encoder are otherwise pure functions of `HostConfig`.
-    let mut plan = crate::session_plan::SessionPlan::resolve(ctx.bit_depth, ctx.chroma, ctx.codec);
+    let mut plan = crate::session_plan::SessionPlan::resolve(
+        ctx.bit_depth,
+        ctx.chroma,
+        ctx.codec,
+        ctx.compositor != pf_vdisplay::Compositor::Gamescope,
+    );
     // PyroWave rides the datagram-aligned wire mode (§4.4): every encoder this session opens
     // packetizes at the negotiated shard payload, so a lost datagram costs blocks, not frames.
     if ctx.codec == crate::encode::Codec::PyroWave {
@@ -1632,6 +1637,7 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
                     frame.is_cuda(),
                     bit_depth,
                     plan.chroma,
+                    plan.cursor_blend,
                 ) {
                     Ok(mut new_enc) => {
                         tracing::info!(
@@ -2551,6 +2557,7 @@ fn try_inplace_resize(
         new_frame.is_cuda(),
         bit_depth,
         plan.chroma,
+        plan.cursor_blend,
     ) {
         Ok(e) => e,
         Err(e) => {
@@ -2619,7 +2626,12 @@ pub(super) fn prepare_display(
     // Same plan resolution as `virtual_stream` (pure in these inputs + host config), including
     // PyroWave's datagram-aligned wire mode — `Session::shard_payload()` echoes the negotiated
     // Welcome value passed here.
-    let mut plan = crate::session_plan::SessionPlan::resolve(bit_depth, chroma, codec);
+    let mut plan = crate::session_plan::SessionPlan::resolve(
+        bit_depth,
+        chroma,
+        codec,
+        compositor != pf_vdisplay::Compositor::Gamescope,
+    );
     if codec == crate::encode::Codec::PyroWave {
         plan.wire_chunk = Some(shard_payload as usize);
     }
@@ -2871,6 +2883,7 @@ fn build_pipeline(
         frame.is_cuda(),
         bit_depth,
         plan.chroma,
+        plan.cursor_blend,
     )
     .context("open video encoder")?;
     if let Some(t) = trace {

crates/punktfunk-host/src/session_plan.rs

@@ -103,6 +103,11 @@ pub struct SessionPlan {
     /// PyroWave session — applied to EVERY encoder this plan opens (initial + all rebuilds) so
     /// AUs stay shard-aligned across mode/bitrate/stall rebuilds. `None` for the H.26x codecs.
     pub wire_chunk: Option<usize>,
+    /// The session may hand the encoder cursor bitmaps to composite (cursor-as-metadata
+    /// captures — every non-gamescope compositor; gamescope embeds the pointer itself).
+    /// Encoders whose fast path cannot blend (the Vulkan EFC RGB-direct source) stay on their
+    /// blending path when this is set, so the pointer never silently vanishes from the stream.
+    pub cursor_blend: bool,
 }
 
 impl SessionPlan {
@@ -112,6 +117,7 @@ impl SessionPlan {
         bit_depth: u8,
         chroma: crate::encode::ChromaFormat,
         codec: crate::encode::Codec,
+        cursor_blend: bool,
     ) -> Self {
         SessionPlan {
             capture: CaptureBackend::resolve(),
@@ -122,6 +128,7 @@ impl SessionPlan {
             chroma,
             codec,
             wire_chunk: None,
+            cursor_blend,
         }
     }
 

crates/punktfunk-host/src/spike.rs

@@ -147,6 +147,7 @@ pub fn run(opts: Options) -> Result<()> {
         first.is_cuda(),
         8,                            // spike synthetic harness: 8-bit
         encode::ChromaFormat::Yuv420, // ...and 4:2:0
+        false,                        // synthetic frames carry no cursor
     )
     .context("open encoder")?;