459 Commits

Author	SHA1	Message	Date
enricobuehler	19c35de3d7	style(host): cargo fmt --all (rustfmt 1.9.0 drift) ... The CI image's rustfmt reformats these files (multi-line assert!/tracing! macros, match-arm and struct-variant wrapping) — pre-existing drift that the Format job caught. Reformat to match. Pure formatting; no logic change. main.rs also gets a blank line before a standalone comment so rustfmt stops mis-indenting it as a trailing-comment continuation. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 19:29:28 +00:00
enricobuehler	aa012c6b45	feat(vdisplay/mutter): pin the client's refresh by default; drop PUNKTFUNK_MUTTER_VIRTUAL_REFRESH ... The >60 Hz virtual-monitor path (RecordVirtual "modes" with the client's exact WxH@Hz) was gated behind PUNKTFUNK_MUTTER_VIRTUAL_REFRESH, default OFF, after a high-refresh virtual CRTC SIGSEGV'd gnome-shell on session teardown. That crash was since fixed by stopping the screencast before any monitor reconfig, so the gate is dead weight — and a silent footgun: every non-headless GNOME client was capped at Mutter's PipeWire-derived 60 Hz unless they knew the hidden flag. Make it the default: the custom-mode path now runs whenever mode.refresh_hz > 60 (≤60 Hz stays byte-identical to before — Mutter's 60 Hz default is already correct), and the virtual_refresh_enabled() env read is removed. Docs updated (configuration.md env table, vrr-plan.md reference). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 19:25:36 +00:00
enricobuehler	74c9e46faf	fix(vdisplay/windows): Windows clippy — per-block SAFETY comments + then_some ... The branch's Windows-host code never ran through the fleet Windows clippy (kept off CI); the merge to main exposed it. Fix the 4 -D warnings failures in cfg(windows) code: - manager.rs: 3 unsafe blocks (isolate_displays_ccd / force_extend_topology / set_virtual_primary_ccd) had one "both arms" SAFETY comment on the `match` line — clippy::undocumented_unsafe_blocks wants it immediately before each block. Split into per-block SAFETY comments. - win_display.rs: `.then(|| …)` on a POD u32 union read → `.then_some(…)` (eager is fine, discarded when false) for clippy::unnecessary_lazy_evaluations. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 19:04:06 +00:00
enricobuehler	334f36ce25	test(punktfunk1): serialize in-process-host tests (shared admission table) ... The reconnect-preempt (b53710d, preempt_same_identity) reads the process-global admission table and signals same-identity live sessions. The three in-process-host tests each bind a fixed loopback port and share that ONE table, so running them concurrently let one test's connection preempt + close another's live session — an intermittent `next_au: Closed` in c_abi_connection_roundtrip (surfaced under full-workspace load; a lucky pass hid it at b53710d). Serialize them on a poison-tolerant lock. Test-isolation only — in production a host is one process with unique client certs, so same-identity preempt is correct. Full workspace `cargo test` now green (18 suites, 3× clean). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 18:09:59 +00:00
enricobuehler	fc1e8a8a32	test(mgmt): display_settings_surface stays read-only (gaming-rig now accepted) ... The old `..._and_forever_rejected` asserted a 400 for keep_alive=forever; now that it's accepted, that PUT succeeded and WROTE gaming-rig into the process-global prefs, racing other tests. Rewrite read-only: assert the surface (5 presets, effective, enforced axes) and read gaming-rig=forever off the preset list — no write. Acceptance is covered on-glass (.116) + the pure policy tests. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 18:03:11 +00:00
enricobuehler	69f4c987f6	feat(tray): surface kept virtual displays in the tray tooltip ... Stage 8 polish. `GET /api/v1/local/summary` (the tray's loopback-only unauthenticated status source) gains `kept_displays` — the count of lingering/pinned virtual displays (held with no live session), over the already-validated `registry::snapshot()`. The tray shows it in the idle tooltip ("idle · 1 display kept"), so a user knows a display — and, under exclusive topology, their physical monitors — is being held (e.g. a gaming-rig `forever` pin). Release stays via the console: a state-changing release can't be an unauthenticated endpoint, and the non-elevated Windows tray can't read the SYSTEM-DACL'd mgmt token, so a tray release button isn't cleanly cross-platform. `#[serde(default)]` on the tray side keeps it compatible with an older host. Tray tests green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 17:54:44 +00:00
enricobuehler	04a397be84	fix(vdisplay/windows): drop an unused mut in isolate-retry (clippy -D warnings) ... `let (mut paths, mut modes)` — `modes` is only read (`modes.as_slice()`), never mutated. A pre-existing unused_mut (from 029d113) that the Linux CI never caught because win_display.rs is #[cfg(windows)]; surfaced by a manual .173 build. Would fail the release-gated Windows clippy. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 17:41:22 +00:00
enricobuehler	ccbd7e8880	feat(vdisplay): ship keep_alive=forever (gaming-rig) — Windows MgrState::Pinned ... Completes the last §6A-era preset. The Linux registry already resolved forever→Pinned (pure lifecycle machine); the blockers were the Windows manager, the mgmt reject, and the console tag: - Windows manager: new `MgrState::Pinned { mon }` — the last-released monitor under keep_alive=forever is kept indefinitely (like Lingering but the linger timer never fires). A reconnect preempts + recreates it (same as Lingering — a reused IddCx swap-chain is dead), snapshot reports "pinned", and `force_release` (POST /display/release, the §8 escape hatch) frees a pinned monitor. release() branches on the new `keep_alive_forever()`; all MgrState matches made exhaustive over Pinned. - mgmt PUT /display/settings: stop rejecting keep_alive=forever (now honored on both platforms with a release path). OpenAPI regenerated. - web: un-disable the gaming-rig preset (DISABLED_PRESETS now empty) — one-click applies. Linux paths + web/tsc/openapi green; 47 vdisplay tests pass. The Windows manager.rs is #[cfg(windows)] (not compilable on the Linux dev box) — build-verified + on-glass validation on .173 to follow. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 17:26:43 +00:00
enricobuehler	b53710da1a	feat(vdisplay): harden keep-alive reconnect — same-client preempt, quit-skips-linger, configurable idle ... On-glass testing (Test 2, KWin .116) surfaced that a reconnect within the QUIC idle-timeout window (~8s) lands on a fresh SECOND display instead of reusing the kept one: the old session was still Active (not yet Lingering), so the registry's keep-alive reuse (which only matches Lingering) skipped it and the old session kept streaming to nobody. Three fixes: #3 Same-client reconnect preempt (the real fix): admission::preempt_same_identity() lists a reconnecting client's OWN still-live session(s) (same cert fingerprint); serve_session signals their stop + waits the release grace BEFORE acquiring, so the zombie tears down → its display lingers → the reconnect REUSES it instead of making a second. Implements the "preempts downstream" the admission docs already promised. Independent of the mode_conflict policy; the pure core (same_identity_stops) is unit-tested. #2 Deliberate quit skips linger: a client that deliberately disconnects closes the QUIC connection with QUIT_CLOSE_CODE (0x51, shared in core::quic); the host reads the ApplicationClosed reason and tears the display down immediately (registry release() gained force_immediate → Linger::Immediate; multi-session-safe via the pure lifecycle machine), while a bare disconnect still lingers for reconnect. Threaded via a session quit flag → the DisplayLease. NativeClient::disconnect_quit() + punktfunk-probe --quit drive it; GameStream (Quit App / h_cancel) is a documented follow-up. #1 Configurable disconnect-detection latency: the QUIC control-connection idle timeout (stream_transport, 8s default) is host-tunable via --idle-timeout-ms / PUNKTFUNK_IDLE_TIMEOUT_MS, clamped >=1s with a keep-alive that scales to it so a live session never false-closes. Default unchanged (8s stays load-bearing for the Windows IDD-push reconnect flow). Workspace check + 63 core / 215 host / 47 vdisplay tests green; clippy clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 16:41:06 +00:00
enricobuehler	62e0367f4b	feat(punktfunk1): configurable data-plane UDP port (--data-port) ... The native data plane used a random ephemeral UDP port (hole-punched), which a strict firewall can't pre-open — so remote clients behind one couldn't connect. Add an optional fixed data port: - `Punktfunk1Options`/`NativeServe` gain `data_port`; `bind_data_socket` binds the fixed port (→ direct, no hole-punch) or falls back to a random port + hole-punch when unset or the fixed port is busy (a concurrent session already holds it). - `UdpTransport::from_socket`/`from_socket_punch` adopt an already-bound socket, so the host keeps the SAME data socket from handshake through streaming — no drop-then-rebind window in which a concurrent session could steal a fixed port. - `main.rs` wires the CLI flag through to `NativeServe`. - Firewall docs updated (troubleshooting.md + apt/pacman/bazzite READMEs): control plane is the fixed UDP 9777; the data plane is a separate random port that usually needs no rule, with the fixed-port option for strict firewalls. Unit-tested: default random+hole-punch, and fixed-port-then-fallback-when-busy. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 13:53:54 +00:00
enricobuehler	677a4f4cf5	perf(gamestream): move FEC packetization off the encode loop (3-stage pipeline) ... FEC/Reed-Solomon packetization ran inline on the encode loop (~3 ms/frame at 4K), serializing behind encode and capping the GameStream frame rate below what the encoder alone can sustain. Split it into a 3-stage pipeline, each stage on its own thread joined by a depth-2 bounded queue: encode loop → [raw AUs] → packetizer (FEC/RS) → [wire batch] → paced sender - `spawn_packetizer`: turns each `RawFrame`'s access units into wire datagrams via the stateful VideoPacketizer, off the encode loop. Above-normal priority (on the per-frame critical path). Tallies goodput (bytes to the wire) for the stats window. - Backpressure chains up: a slow sender blocks the packetizer, which fills the encode→packetizer queue, which makes the encode loop drop the NEWEST frame — encode itself never waits. - A dropped frame now consumes no client-visible frameIndex (packetization is downstream), so the host re-anchors the reference chain: a drop arms a keyframe on the next iteration (`recover_after_drop`), routed through the same coalesce gate as client IDR requests so a burst of drops (congestion) can't become an IDR storm. - Perf/stats relabeled: `pkt` = AU drain, `send` = enqueue to the pipeline (both should be near-zero now; nonzero = encode being stalled by pipeline backpressure). Goodput read from the packetizer's atomic at the 1 s stats boundary. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 13:53:43 +00:00
enricobuehler	87435e6547	feat(vdisplay): complete Stage 5 §6A group semantics — per-group restore, Mutter group-aware, gamescope groups ... Host-side completion of Stage 5 (§6A many-clients-as-monitors), all unit-tested; two-session on-glass validation still pending (no GPU on the dev VM): - Per-group topology restore (§6.1): the KWin `exclusive` restore no longer rides the per-session StopGuard (which re-enabled the physical the moment the FIRST of several exclusive sessions dropped, under a live sibling). KWin hands its restore to the registry as a closure (new trait `take_topology_restore`); the registry keeps it in the display group (`Entry.topology_restore`) and, on teardown, floats it to a surviving same-group sibling (`hand_off_restore`) or runs it when the group empties — outside the lock, before the last output's keepalive drops, so the compositor never sees zero outputs. All three teardown paths (lease drop / linger expiry / mgmt release) honor it. Single-display path byte-for-byte unchanged. Unit-tested: float / run-on-last / non-carrier-first / never-cross-backend. - Mutter group-aware (new trait `set_first_in_group`): the registry tells each backend whether it's the first display of its group; a non-first Mutter session EXTENDS into the already-exclusive desktop instead of re-applying a sole-monitor ApplyMonitorsConfig that would disable the first session's virtual. (Mutter connectors are un-nameable, so it can't build a keep-all-virtuals config; skipping is the safe equivalent.) Single-session unchanged. Residual APPLY_TEMPORARY revert documented. - gamescope groups (§6.1): `registry::group_key` makes each gamescope spawn its own group (independent nested session, no shared desktop) — never auto-rowed against or restore-/topology-grouped with another gamescope. Applied in both the /display/state assembly and the acquire-time position computation. Unit-tested. Remaining Stage 5: the web console arrangement table, on-glass validation, and the documented residuals (wlroots exclusive, Mutter APPLY_TEMPORARY). design doc updated. cargo build/test (214)/clippy --all-targets/fmt green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 13:26:25 +00:00
enricobuehler	e0f15822ae	feat(vdisplay): Stage 5 layout foundation — arrangement engine + /display/layout + group placement ... §6A layout, riding the Stages 1-3 registry with no protocol change: - vdisplay/layout.rs: pure arrangement engine — auto-row (left-to-right in acquire order, top-aligned) + manual (per-identity-slot offsets, auto-row fallback for unpinned members). Unit-tested. - Registry group model (Linux): group = backend (one desktop per compositor session). /display/state groups entries, orders by acquire (gen), and computes each member's position via the engine (pure `assemble_displays`, unit-tested). DisplayInfo carries group/display_index/position/identity_slot/topology. The backend reports its resolved slot via the new VirtualDisplay::last_identity_slot (KWin only), so the arrangement + state key on per-client identity. - Registry-driven position apply: new VirtualDisplay::apply_position(x,y) (default no-op; KWin drives kscreen-doctor). Right after create the registry computes the new display's position over its whole group (pure `position_for_new`, unit-tested) and applies it — one seam for BOTH deterministic auto-row AND manual placement. Guarded: the origin (0,0) is skipped, so a single-display / first-of-group session (and every non-KWin backend) issues no positioning — the historical single-display path is unchanged. On-glass-validation-pending. - PUT /api/v1/display/layout: persists the console's manual arrangement via the pure EffectivePolicy::with_manual_layout transform (locks current effective behavior into explicit Custom fields + sets a manual layout, so arranging is orthogonal to the other axes). OpenAPI regenerated. - /display/settings `enforced` now lists all five axes (keep_alive, topology, mode_conflict [Stage 4], identity [Stage 3], layout [Stage 5]) — was stale at keep_alive+topology; the console reads it to know which controls are live. Still Stage-5 TODO (design/display-management.md §11): Mutter/wlroots group-aware analogues, per-group topology restore, the web arrangement table, gamescope decline. cargo build/test/clippy/fmt green; OpenAPI in sync. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 12:59:04 +00:00
enricobuehler	eddcd91f48	feat(vdisplay/kwin): group-aware exclusive — never disable a sibling output (Stage 5 §6.1) ... The critical latent bug Stage 3 introduced: per-slot output names mean a 2nd exclusive session's other_enabled_outputs() (which disabled 'everything not named Virtual-punktfunk') would black out the 1st session's Virtual-punktfunk-<id> output. Fix: recognise the whole managed group by the shared Virtual-punktfunk prefix — exclusive now disables only NON-managed outputs (bootstrap/physical), never a group sibling. Plus first-slot-wins for the group primary (a_managed_output_is_primary): a later session joins as a secondary monitor of the shared desktop instead of stealing the shell off the first. Unit-tested. Start of Stage 5 (§6A many-clients-one-desktop). Remaining: Mutter/wlroots group-aware analogues, layout (auto-row/manual + /display/layout + console), per-group topology restore, gamescope groups. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 11:44:41 +00:00
enricobuehler	23446fa177	fix(vdisplay): Windows admission default is reject, not join (single-capturer limit) ... Two concurrent Windows sessions both drive the same pf-vdisplay monitor's single-capturer IDD-push channel (newest-delivery-wins), which freezes the live client and can wedge the driver (observed live: a concurrent-session test wedged .173 → Moonlight 'no video'; needed a reboot). True multi-session capture is §6.6/ Stage 7. So on Windows 'separate' (incl. the unconfigured default) now resolves to REJECT — a 2nd client gets a clean 503 and the live session is protected — instead of join (which would freeze it). join/steal stay explicit opt-ins; Linux keeps separate (real multi-view). Centralized as admission::effective_conflict(), shared by the native handshake + GameStream h_launch. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 11:32:52 +00:00
enricobuehler	980939ed6b	refactor(gamestream): extract + unit-test gamestream_admission (Stage 4) ... Pull the GameStream mode-conflict decision out of h_launch into a pure gamestream_admission(live, req_fp, policy) -> GsDecision so the 503/join/take-over logic is unit-tested (no live session / same-client → Serve; different client → Reject/Join/Serve per policy; anonymous requester treated as different) — the GameStream path can't be driven without a Moonlight client, so this covers the logic. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 10:43:08 +00:00
enricobuehler	cfad0cf7ee	feat(vdisplay): finish Stage 4 — typed reject, Windows join-default, GameStream 503 ... Completes the mode-conflict admission surface deferred from the initial Stage 4: - REJECT now delivers the reason to the client: punktfunk/1 closes the QUIC connection with a distinct BUSY code (0x42) + the 'host busy: streaming WxH@Hz to <client>' string, which the client reads from ApplicationClosed (validated on loopback: the probe logs 'closed by peer: host busy … (code 66)'). - Windows default: separate (incl. the unconfigured default) resolves to JOIN — the Windows native host admits a second client at the live mode instead of the old silent last-wins reconfigure of the shared monitor (release-note behavior fix; the reconfigure is now opt-in as steal). separate stays multi-view on Linux. - GameStream 503: h_launch tracks the session owner fp (LaunchSession.owner_fp, kept [u8;32] for Copy) and applies the policy when a DIFFERENT paired client launches — reject → 503 (Moonlight 'host busy'), join → serve the live mode, steal/separate → take over. Same-client re-launch is never a conflict. Native reject-reason loopback-validated; Windows join-default pending .173 rebuild; GameStream 503 pending a Moonlight client (can't drive /launch autonomously). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 10:34:49 +00:00
enricobuehler	42b1158ea7	feat(vdisplay): mode-conflict admission — separate/join/steal/reject (Stage 4) ... The mode_conflict policy is now enforced at ADMISSION, before the punktfunk/1 Welcome, when a DIFFERENT client connects while another client's session is live: - separate (default, unconfigured → no change): each client its own display. - join: admit at the live display's mode (honest-downgrade — the Welcome carries it). - steal: signal the victim session(s)' stop flags, wait the release grace, serve. - reject: refuse the handshake with a busy reason (live mode + client label). New vdisplay/admission.rs: the pure decide() (unit-tested — same-client never conflicts, anonymous clients each distinct, join targets the oldest session) + a live-session registry (identity + mode + stop flag) sessions register in once up. Wired into punktfunk1 serve_session: admit() before validate_dimensions, register after the data plane binds. A same-client reconnect never conflicts. Validated on loopback (two probes, distinct identities, differing modes) across all four policies: separate→own mode, join→live mode, steal→victim interrupted, reject→handshake refused. Remaining Stage-4 surface (deferred): GameStream 503 path, Windows-specific defaults (separate→join map, silent-reconfigure→steal), reject reason delivered to the client as a typed message (currently host-side log + connection close). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 10:21:28 +00:00
enricobuehler	029d1134a9	harden(vdisplay/windows): verify+retry exclusive isolation; pack primary layout ... Exclusive (topology=exclusive) was fire-and-forget — a field-reported bug had a physical monitor STAY ACTIVE. isolate_displays_ccd now re-queries after each apply and RETRIES (up to 4x) until count_other_active()==0, never trusting rc alone; logs SOLE-active on success, an error if a display survives all attempts. Secure desktop correctness depends on the lock screen not landing on a stray panel. Primary: drop the temporary per-path diagnostic; pack the kept displays left-to- right from the virtual's right edge instead of blindly shifting each by virt_width (which left a dead gap when extend already placed them right). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 09:55:13 +00:00
enricobuehler	e35b6991e2	fix(vdisplay/windows): topology=primary force-extends to reactivate the physical ... Root cause: on a headless box the IDD auto-activates as the SOLE display, so QueryDisplayConfig sees only the virtual — the physical is already deactivated before set_virtual_primary_ccd runs (no physical to keep). Force EXTEND first to reactivate every connected display alongside the virtual, then reposition to make the virtual primary, keeping the physical active. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 09:41:20 +00:00
enricobuehler	913f6ce659	diag(vdisplay/windows): log active paths in set_virtual_primary_ccd ... Temporary diagnostic — the physical monitor goes black in topology=primary despite rc=0; the SSH/session-0 view can't see the real interactive-session topology, so log the active paths the host actually operates on. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 09:36:53 +00:00
enricobuehler	d23bd9b0cf	fix(vdisplay/windows): DISPLAYCONFIG_PATH_SOURCE_INFO union field access ... modeInfoIdx lives in the Anonymous union (windows-rs), not directly on sourceInfo — set_virtual_primary_ccd now reads .Anonymous.modeInfoIdx. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 09:27:07 +00:00
enricobuehler	eda7cac78e	feat(vdisplay/windows): topology=primary — keep physicals active, virtual primary ... Implements the deferred Windows primary-only CCD (Stage 2). set_virtual_primary_ccd repositions the virtual output's source to (0,0) = primary and shifts the physical display(s) to its right, ALL kept active — one atomic CCD SetDisplayConfig (not GDI CDS_SET_PRIMARY, which storms MODE_CHANGE_IN_PROGRESS with another display live). The manager's should_isolate() becomes topology_action() (3-way): extend (skip), primary (set_virtual_primary_ccd), exclusive (isolate_displays_ccd). Restore-on-teardown covers both. Validates the user's two scenarios on a physical-monitor .173. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 09:17:41 +00:00
enricobuehler	d73951414c	feat(vdisplay): KWin per-slot output naming for persistent scaling (Stage 3) ... The KWin backend names its output Virtual-punktfunk-<id> from the client's stable identity slot, so KWin persists per-output config (scale/mode) by name in kwinoutputconfig.json and reapplies that client's scaling on reconnect — the KDE scaling ask. Also fixes the latent clash where two concurrent sessions both used Virtual-punktfunk (topology name-matching now uses the per-slot name). - identity::global() + resolve_slot(fp, mode, default) — the shared persisted map (Windows manager dropped its own field; both use the global — never same-process). Default identity is per-platform: PerClient on Windows, Shared on Linux, so unconfigured hosts keep today's behavior (Linux = single 'punktfunk' name). - KwinDisplay carries the client fp (set_client_identity), computes the per-slot name, threads it through the stream_virtual_output name + the topology helpers (set_custom_refresh / apply_virtual_primary[_only] / other_enabled_outputs). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 08:54:39 +00:00
enricobuehler	b150d79626	feat(vdisplay): platform-neutral identity map + per-client-mode (Stage 3) ... Generalize the Windows-only per-client stable-id map into vdisplay/identity.rs: - DisplayIdentityMap keyed on a composable string (identity_key: fingerprint, or fingerprint+resolution under per-client-mode); LRU at 15, persisted to display-identity.json (migrated from the legacy pf-vdisplay-identity.json). - Windows manager wired to it, picking the key from the identity policy. - Foundation for KWin per-slot output naming (persistent KDE scaling) — the KWin wiring is the next Stage-3 step (needs a KWin box). - Unit-tested (stable, per-client-mode split, LRU, key composition). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 08:40:18 +00:00
enricobuehler	cb7ddc0411	feat(vdisplay): topology decoupling — distinct primary level (Stage 2) ... The three topology levels become distinct behaviors (Stage 0 only did extend-vs-exclusive, faking primary): - vdisplay::effective_topology() -> the concrete level (console policy > legacy *_VIRTUAL_PRIMARY env > Auto default). Backends read it directly at create time; apply_session_env no longer writes the boolean env (one fewer connect- path env mutation). - Mutter: extend (no config), primary (virtual primary + physicals kept as secondaries — build_primary_keeping_physicals), exclusive (sole, physicals disabled). KWin: extend (no-op), primary (kscreen primary only), exclusive (primary + disable others). - Windows should_isolate treats primary as isolate (the primary-only CCD variant is a follow-up); wlroots exclusive + the physical-keep effect need a display-attached box (headless lab boxes can't observe primary vs exclusive). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-05 00:18:46 +00:00
enricobuehler	60816709c4	fix(vdisplay): call life.acquire() outside debug_assert (release no-op) ... The pooled entry's lifecycle transition was inside debug_assert_eq!, whose arguments don't evaluate in release builds — so acquire() never ran, the entry stayed Idle, and release saw Noop → immediate teardown (no keep-alive). Caught on-glass on the CachyOS box. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 23:45:36 +00:00
enricobuehler	783c52dfad	feat(vdisplay): Linux keep-alive pool — registry-owned display lifecycle (Stage 1b) ... The ownership split (design/display-management.md §3): the registry owns the per-session virtual-display lifecycle on Linux, so a display can outlive its session (keep-alive) and be reused on reconnect. - registry.rs: a Linux pool driven by the pure lifecycle machine. acquire() reuses a kept (lingering/pinned) display of the same backend+mode, else creates one and keeps the backend's keepalive so the compositor output (and its PipeWire node_id) survives the session. The session's capturer holds a gen-stamped DisplayLease instead of the real keepalive; its drop drives linger/teardown. Enabling fact: KWin/Mutter/gamescope put their node on the DEFAULT PipeWire daemon (remote_fd=None) — reconnect re-attaches by node_id, no fd re-open. wlroots (remote_fd=Some, xdpw portal) passes through unchanged (teardown-on-drop) pending the fresh-portal-capture re-attach. - Default (unconfigured) linger = Immediate → today's teardown-on-disconnect, so no behavior change without a keep-alive policy; concurrent sessions still each create their own output (reuse only matches LINGERING entries). - Wired build_pipeline (punktfunk1) + gamestream through registry::acquire; capture_virtual_output signature unchanged. Windows delegates to vd.create (the manager already leases) — unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 23:37:21 +00:00
enricobuehler	2dd17dda80	test(mgmt): display state/release endpoint smoke test ... Covers the idle path (empty /display/state + released:0 /display/release) on a unit-test host, exercising the wiring + auth without touching any global owner. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 21:27:52 +00:00
enricobuehler	87f0ce7997	feat(vdisplay): lifecycle state machine + display state/release API (Stage 1) ... Stage 1 of design/display-management.md — the lifecycle core + the display management surface: - vdisplay/lifecycle.rs: pure per-slot state machine (Idle/Active{refs}/ Lingering{until}/Pinned) with acquire/release/expiry/force-release transitions. No I/O, no OS types — the platform-neutral distillation of the Windows manager's model. Unit + a 200k-iteration seeded property walk (no leaks / double-frees / refcount underflow across arbitrary interleavings). - vdisplay/registry.rs: neutral snapshot/release facade over the per-OS lifecycle owners. Windows reads/controls the VirtualDisplayManager; Linux keep-alive (a per-session pool) lands in a following increment (needs GPU-box validation). - windows/manager.rs: additive snapshot() + force_release() (no behavior change to the on-glass-validated path). - mgmt: GET /api/v1/display/state (live/kept displays) + POST /api/v1/display/release (tear down lingering/pinned now; refuses active). OpenAPI regenerated. - web console: Virtual displays card gains a live-display list (polled) with per-row + release-all buttons and a linger countdown. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 20:32:03 +00:00
enricobuehler	bbd98241e4	feat(vdisplay): display-management policy surface (Stage 0) ... A user-configurable policy layer above the per-compositor VirtualDisplay backends: keep-alive, topology, conflict, identity, layout, max-displays — persisted to display-settings.json, editable from the web console, applied per connect. Design: design/display-management.md. Stage 0 stands up the surface and wires the two behaviors the existing code can already express — the Windows monitor linger duration and the "make the streamed output the sole desktop" topology — through it; every other option is stored + echoed but not yet enforced (later stages). An unconfigured host (no display-settings.json) keeps today's exact behavior. - vdisplay/policy.rs: pure DisplayPolicy + 5 presets + JSON store (gpu-settings pattern) + EffectivePolicy; 9 unit tests. - vdisplay.rs: resolve_topology(Auto); apply_session_env drives *_VIRTUAL_PRIMARY from the policy only when a settings file exists. - windows/manager.rs: linger_ms() + should_isolate() read the policy when configured. - mgmt: GET/PUT /api/v1/display/settings (bearer-only); PUT rejects keep_alive forever until the lifecycle stage. OpenAPI regenerated. - web console: Host → Virtual displays card (preset picker + custom fields); en+de. - docs-site: virtual-displays.md + configuration.md cross-links. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 19:44:18 +00:00
enricobuehler	7930d2f0f4	fix(core): split WIRE_VERSION from ABI_VERSION — new clients locked out of every deployed host ... ABI_VERSION was doing double duty: the embeddable C surface AND the punktfunk/1 Hello/Welcome version that hosts equality-check. The WoL feature's v3 bump added a client-local FFI function without changing a single wire byte — and every new client started refusing against every deployed host ("ABI mismatch: client 3 host 2", observed live Deck → Bazzite). The wire now carries its own WIRE_VERSION (still 2); ABI_VERSION stays 3 for the C header and the mgmt API's informational field. Bump WIRE_VERSION only when the handshake/planes actually change incompatibly. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 14:29:33 +00:00
enricobuehler	6c4ba77606	fix(wol): clippy + cfg-gate the Windows client module — main compiles again ... The Wake-on-LAN batch landed with lints that fail `clippy -D warnings` (doc continuation, char-array split, io::Error::other, redundant closure) and an ungated `mod wol;` in the Windows client, which pulls windows-only crates into the non-Windows stub build. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 12:02:45 +00:00
enricobuehler	7e6561aaa2	style: rustfmt the Wake-on-LAN modules ... Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 13:52:17 +02:00
enricobuehler	22c0d92f2e	feat(core,host): Wake-on-LAN sender + host MAC advertisement ... Add a runtime-free Wake-on-LAN sender in punktfunk-core (per-interface subnet-directed broadcast + 255.255.255.255 on ports 9/7, repeated, optional last-known-IP unicast) exposed both as a Rust fn and a punktfunk_wake_on_lan C-ABI (ABI v3), plus a parse_mac helper. The host enumerates its wake-capable NIC MAC(s) and advertises them in a new mDNS `mac` TXT record (routed NIC first), and best-effort detects & warns (never modifies) when the NIC isn't armed for WoL. MAC delivery is via the unauthenticated mDNS TXT rather than the connection handshake by design: a spoofed MAC only makes a wake fail (the packet is inert; the cert fingerprint still gates the connection), and it avoids threading through the hot connect path. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-04 13:39:44 +02:00
enricobuehler	90c2d8b3a0	fix(host): don't count punktfunk's own virtual Deck as a physical Steam controller ... The Steam-conflict gate scanned /sys/bus/hid/devices for non-virtual 28DE devices, but the usbip/gadget virtual Decks present a REAL USB device (vhci resolves through vhci_hcd, not /devices/virtual/) — so a just-ended session's pad still detaching, or a concurrent session's live one, read as "physical Steam controller attached" and degraded every back-to-back Deck session to DualSense (observed live on Bazzite). Exclude our pads by their PFDK… serial (HID_UNIQ), with the vhci_hcd path as belt and braces. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 11:14:24 +00:00
enricobuehler	5310176ab5	fix(client-linux,host): Deck video defaults to software decode + input-interception diagnostics ... Video (Deck): the VAAPI zero-copy path renders corrupt/gray/washed-out on the Deck — root-caused to Mesa >= 25.1 exporting radeonsi VCN decode surfaces TILED (the Flatpak runtime's Mesa 26 drives both the decoder and GTK's GL, and GTK's tiled-NV12 dmabuf import mishandles it; desktop Tier-1 validations ran distro Mesa with linear export). `auto` now resolves to software on a Deck (clean, correct-colour, easily handles 1280x800 HEVC); PUNKTFUNK_DECODER=vaapi still forces the hw path, with the descriptor modifier dump + GSK_RENDERER as the bisect levers. Also reserve extra_hw_frames=4 on the VAAPI decoder: the presenter pins mapped surfaces past receive_frame, and the fixed pool recycling a surface the renderer still samples is intermittent block corruption anywhere. Input (Deck): with Steam Input ON for Punktfunk, SDL sees only Steam's virtual X360 pad — the right trackpad arrives as a plain right stick and the left trackpad/paddles/gyro not at all, silently. The client now checks once the post-attach enumeration settles and raises a toast + warn naming the fix (disable Steam Input for the shortcut). The host logs a one-shot warning when InputPlumber is running (Bazzite default) since it can grab the virtual Deck pad and re-emit it under a different identity. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 09:56:06 +00:00
enricobuehler	00acf5e44e	fix(host/audio): WASAPI virtual mic — port the priming jitter buffer (crackling fix) ... Mac → Windows mic passthrough crackled heavily while the identical stream was clean on the Linux host. Cause: clients push mic audio in BURSTS on their own clock (the Mac input tap yields ~two 20 ms Opus packets every ~42 ms) while the WASAPI render loop pulled a block every ~10 ms device period and greedily drained whatever was queued, padding the rest with zeros — the queue sat near-empty and most periods inserted mid-stream silence. The Linux backend has absorbed this since day one with its priming jitter buffer; the WASAPI loop had none. Port the same semantics: emit silence until ~48 ms is buffered (covers the worst inter-burst gap), then play from the cushion (zero-filling only a momentary shortfall), re-prime only after a genuine full drain (client went quiet). Queue cap raised 80 → 120 ms for burst headroom; steady-state added latency ≈ the 48 ms cushion. Diagnosed live on .173: probe tone recording from CABLE Output proved the endpoint wiring, then the burst-vs-period math explained the crackle. Build-verified on Windows; on-glass listen pending. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 22:31:18 +00:00
enricobuehler	449a67ce8d	feat(protocol): per-AU host-timing plane (0xCF) — split host+network latency (stats phase 2) ... The unified-stats equation's host+network stage was one opaque number because the wire carried nothing but pts_ns. Now the host reports its own share per frame: when the client's Hello sets VIDEO_CAP_HOST_TIMING (0x08), the send thread emits a 13-byte 0xCF datagram — [tag][pts_ns u64][host_us u32] — right after the AU's last packet leaves the socket, so host_us = capture→fully-sent (capture read/convert, encode, FEC+seal, paced send) against the same anchor the wire pts carries. Clients correlate by pts_ns and derive network = (received + clock_offset − pts) − host_us; the two terms tile per frame by construction. Back-compat is free in all four combinations: old clients ignore unknown datagram tags, old hosts ignore unknown cap bits (client keeps the combined stage). The hardened data-plane format is untouched — this rides the established QUIC side-plane pattern (0xC8…0xCE). NativeClient ORs the bit in unconditionally and exposes next_host_timing(); the C ABI gains PunktfunkHostTiming + punktfunk_connection_next_host_timing (additive). The synthetic host emits 0xCF too, so pure-loopback protocol tests cover the plane. The probe reports the split (host_p50/p95_us · net_p50/p95_us) and is our direct analogue of Sunshine's "host processing latency" — ours additionally includes the paced send. Validated on loopback (synthetic host + probe, debug build): 240/240 AUs matched, host_p50 6.5 ms + net_p50 6.4 ms ≈ capture→received p50 13.0 ms. Core suite + new 0xCF roundtrip/truncation test green; host+core+probe clippy clean. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 21:22:12 +00:00
enricobuehler	09a5957c6d	feat(clients): unified stats vocabulary across every client + Moonlight comparison docs ... One stat model everywhere (design/stats-unification.md): four measurement points (capture/received/decoded/displayed), three stages that tile the interval exactly, and a HUD that shows the addition explicitly — end-to-end 14.2 ms p50 · 19.8 p95 · capture→on-glass = host+network 9.8 + decode 2.1 + display 2.3 replacing each client's ad-hoc mix of overlapping absolutes (the Apple HUD's three arrow lines that looked sequential but weren't), mean-vs-median decode times (Windows/Linux), missing same-host-clock flags (Windows/Linux), and three different names for the same capture→received measurement (probe's "reassembled", Apple/Android's "client", Windows/Linux's post-decode "lat"). Per client: Apple threads receivedNs through the VT decode via the frame refcon bit pattern so the decode stage exists at all (stage-1 fallback honestly degrades to a capture→received headline); Windows carries FrameTimes through the existing frame channel to the render thread and adds e2e p50/p95 post-Present; Linux stamps received at AU pop and rides decoded_ns on DecodedFrame to the paintable-set site; Android pairs receipt stamps with MediaCodec output buffers via the codec's pts round-trip (JNI stats array 14→16 doubles, indexes 0-13 unchanged). fps now uniformly counts received AUs; lost/(received+lost) per window, hidden at zero. docs-site gains "Understanding the Stats Overlay": what each line means, why the equation only approximately sums (percentiles), and a line-by-line Moonlight/Sunshine matrix — including that Moonlight has no end-to-end number and its "network latency" is an ENet control RTT, so punktfunk's headline must not be compared against any single Moonlight line. Verified here: linux client + probe + core check/clippy/fmt green, android native cargo-ndk arm64 check green. Pending: Windows CI + on-glass, swift test on the mac, on-device Android. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 21:01:29 +00:00
enricobuehler	c7630ff5dc	fix(host/audio): mic pump — open handshake on Linux + rapid-death backoff ... Found by a live boot-order test (host started before the user session's PipeWire): PwMicSource::open returned Ok before the daemon connection was attempted, so a PipeWire that wasn't running surfaced as an instantly-dead instance instead of an open failure — and the pump churned open→die→reopen at heartbeat rate (1 Hz "virtual mic ready" log spam) instead of backing off. - PwMicSource::open now has a bring-up handshake (mirrors the Windows backend): ready only after connect + stream connect succeed, so a down daemon is an open ERROR and the pump's backoff engages. - The pump triages deaths: an instance that lived >= 5 s (a one-off daemon restart) reopens immediately with the backoff reset; one that died right after opening counts as a failed open and backs off (2 s → 60 s cap). New pump test rapid_death_backs_off. Re-validated live: host started with PipeWire stopped → throttled "unavailable" warns, zero churn; daemon started → mic node up on the next retry; exactly one pump + one loop thread (no leak). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 20:58:06 +00:00
enricobuehler	2c7ded0f3c	fix(host/audio): rebuild mic passthrough — eager, self-healing virtual mic on both hosts ... Mic passthrough silently died on real hosts. Root causes, all fixed: - No liveness anywhere: a PipeWire restart (Linux) or any WASAPI device error (Windows) killed the backend worker; push() fed the dead queue for the rest of the host's life. VirtualMic now has a liveness contract (push -> bool, alive(), discard()) and the new shared audio::MicPump reopens with backoff, probing on an idle heartbeat so the mic heals BETWEEN sessions too. Validated live: systemctl restart pipewire -> node back in ~0.5 s, tone flows through the reopened backend. - Lazy creation: the mic device didn't exist until the first 0xCB frame, but games bind their capture device at launch and never re-follow. The pump opens eagerly at host start (node exists with zero clients, elected default source). - Windows headless dead-end: with VB-CABLE as the ONLY render endpoint (exactly what the installer ships), the anti-echo guard rejected the cable as the default render endpoint -> mic permanently dead. The new wiring_plan (pure, unit-tested on every platform) assigns the mic its endpoint FIRST (cable reserved for the mic), points the loopback at a DIFFERENT endpoint, and the capture side now yields (explicit endpoint or honest error) instead of the mic dying. Plan recomputed per (re)open — endpoints churn at boot/logon/driver installs. - Stale bursts: buffered audio from a previous session played into a newly-attached recorder (observed live). Timestamped chunks + a consumer-gap check in the process callback age everything past 1 s. The Linux node mechanism stays the stream-based Audio/Source with RT_PROCESS + priority.session: the canonical null-audio-sink adapter recipe was tested on this box (PipeWire 1.6.2) and never gets a clock (QUANT 0 -> pure silence), and WirePlumber reroutes a feeder targeting it to the default sink (echo). Decision documented in the module docs. Live-validated on this box (synthetic host + probe --mic-test, pw-record): eager node, both attach orderings, PipeWire-restart self-heal, post-session silence. Windows side compile/CI + on-glass validation pending. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 20:41:19 +00:00
enricobuehler	b7048446c4	fix(windows-host): IDD-push compose kick — idle desktop no longer fails the attach gate ... DWM presents a display only when something dirties it. On an idle desktop a perfectly healthy session sat at E_PENDING: the driver attached but no first frame ever landed, so wait_for_attach's 4 s gate failed the open (and a mid-session ring recreate hit the same stall against the 3 s recover-or-drop). A real client escaped only because its own input soon dirtied the desktop; a headless probe / input-less connect never did. kick_dwm_compose() injects two net-zero 1 px relative mouse moves via SendInput — pf-vdisplay has no hardware-cursor plane, so a cursor move is composited into the frame, a guaranteed real present onto the IDD swap-chain (the mechanism --input-test always relied on; the pointer ends where it started). Wired into wait_for_attach (first kick at 600 ms, then every 800 ms) and, rate-limited, into the GB1 recovery window. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 19:24:57 +00:00
enricobuehler	3f33ed30ae	fix(windows-host): claim the vdisplay single-instance guard eagerly at serve startup ... On-glass the lazy (first-session) claim let a second host started while the freshly-restarted service sat idle win the mutex and ADD a monitor on the real driver — priority backwards. The claim is now a process-global, retryable slot (a failed claim is not memoized, so it heals once the other instance exits), and `serve` claims it before any client can connect; ensure_device keeps the lazy claim for standalone punktfunk1-host runs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 18:57:47 +00:00
enricobuehler	7e31020c1c	fix(windows-host): second-host guard — classify ACCESS_DENIED on the instance mutex as in-use ... On-glass the SCM service creates Global\punktfunk-vdisplay-manager as SYSTEM, so a second elevated-admin host's CreateMutexW fails ACCESS_DENIED (the implicit open is checked against the SYSTEM DACL) before the ALREADY_EXISTS branch can fire — right refusal, wrong message. Map it to the same loud "another instance is live" error. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 18:53:54 +00:00
enricobuehler	fe54aff658	fix(windows-host): cross-plane IDD serialization, linger-expiry race, second-host guard ... Batch C of the audit's medium tier (M7+M8+M9): - M7: GameStream sessions now run the same begin_idd_setup dance as punktfunk/1 before creating the shared monitor. A GS connect could previously ADD/reconfigure the monitor while a native session was mid-build (and vice versa), and its sealed-channel delivery replaced the native ring (newest-wins) — each plane could freeze the other. GS has no cooperative stop plumbing, so it registers a flag nobody reads: a later session signals it, waits the 3 s grace, then force-preempts — the intended handover. - M8: the linger-expiry teardown now runs UNDER the state lock. Running it outside let a concurrent acquire see Idle and ADD+isolate while the old monitor's pinger-join / CCD-restore / REMOVE were still in flight — a failed or de-isolated session exactly at the expiry boundary. A racing acquire now waits the few teardown seconds instead. Lock order stays state → device everywhere; the pinger takes only the device lock. - M9: a named mutex (Global\punktfunk-vdisplay-manager) makes a SECOND host process fail its vdisplay open loudly instead of firing a startup CLEAR_ALL that razes the live host's monitors mid-stream (the admin footgun the shared watchdog then masked). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 17:28:22 +00:00
enricobuehler	20f0d2802f	feat(client/android): Snapdragon latency tuning — ADPF pipeline hints, game mode, max-clock decode ... Three levers to lower and steady decode latency on Snapdragon (Adreno) devices: - ADPF (Adaptive Performance Framework): a new dlsym-resolved hint session (native/src/adpf.rs; API-33+, resolved at runtime so there's no build-time link dependency and libpunktfunk_android.so still loads on API 31/32) tells the CPU governor the video pipeline runs a per-frame real-time workload, so it keeps those threads on fast cores at high clocks. It now covers all three latency-critical threads — the pf-decode feed/drain/present loop, the core data-plane pump (UDP receive + FEC reassembly), and the audio thread — via a new generic hot-thread registry on NativeClient (register_hot_thread / hot_thread_ids; the pump self-registers). The session is built lazily on the first presented frame, since ADPF createSession rejects a set containing any not-yet-live tid. - operating-rate -> Short.MAX ("as fast as possible"): pushes the Qualcomm decoder to run each frame at max clocks instead of merely sustaining the display rate at a power-saving clock that adds per-frame decode latency. - appCategory="game": makes the app eligible for OEM Game Mode / Game Dashboard performance profiles. The core registry is cross-platform (gettid on Linux/Android, a no-op elsewhere) — no Android-specific pollution of the shared core. Host workspace + 64 core tests green; Android arm64-v8a + x86_64 (platform 31) build + clippy clean. On-device Snapdragon validation pending. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-03 17:16:11 +00:00
enricobuehler	6f8fb15c9b	fix(windows-host): self-heal the hostless-zombie pf-vdisplay device (adapter cycle + re-probe) ... Fault-injection on-glass showed a killed/crashed WUDFHost leaves the devnode "started" but HOSTLESS: PnP Status OK, no WUDFHost process, zero device- interface instances — is_available() then fails every future session at the vdisplay::open gate (and a reopen inside VdisplayDriver::open finds nothing), until something cycles the device. Port reset-pf-vdisplay.ps1's adapter disable→enable step in-process (restart_vdisplay_device): the open gate now uses ensure_available() (cycle once + bounded re-probe; a genuinely uninstalled driver — no adapter devnode — still fails fast), and VdisplayDriver::open retries open_device over a short arrival window after a cycle, covering the manager's reopen path too. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 17:12:43 +00:00
enricobuehler	89455032a0	fix(windows-host): IDD-push resilience — driver-death recovery, reopenable control device, full interface discovery ... Batch A of the audit's medium tier (M1+M2+M3): - M1 driver-death detection: a dead WUDFHost stops publishing, which at the ring is indistinguishable from an idle desktop — SDR sessions streamed a frozen frame forever (next_frame's 20 s bail is unreachable once anything presented). The ChannelBroker's process handle now doubles as a liveness probe (SYNCHRONIZE at OpenProcess); while no fresh frame arrives, try_consume polls it (rate-limited) and fails the capturer, landing in the session's bounded in-place rebuild. - M2 reopenable control device: the manager's OnceLock-cached handle is now a retire/reopen DeviceSlot — a gone-classified IOCTL failure (driver upgrade / WUDFHost restart; pinger, create, or REMOVE) retires the handle and the next use reopens + re-handshakes. Retired handles are deliberately kept alive forever: bare-HANDLE holders (pinger, ChannelBroker) rely on never-closed, and a retired handle only fails IOCTLs. CLEAR_ALL runs on the FIRST open only (a reopen races live-ish sessions); acquire retries the monitor create once after a reopen. The JOIN path now probes the active monitor's WUDFHost pid and preempts a DEAD monitor instead of handing the rebuilding session its stale target — without this the whole recovery chain starved to the rebuild budget. - M3 interface discovery: enumerate ALL interface instances with an SPINT_ACTIVE filter (a Code-10 devnode at index 0 no longer shadows the live interface), HDEVINFO behind RAII (error paths leaked one per probe), the raw device handle wrapped before GET_INFO (leaked on handshake failure), and the detail-sizing result guarded before the cbSize write. - pf-driver-proto: SetFrameChannelRequest doc now states the real adopt-on-success contract (the old wording invited a driver-side close-on-error — a cross-process double-close against the host's reap). - install: pf_vdisplay_present() passes /connected so a phantom devnode can't suppress creating a live ROOT node. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 17:04:19 +00:00
enricobuehler	0da9d8ec10	fix(windows): IDD-push audit highs — keyed-mutex timeout, two per-frame leaks, IDD_PUSH knob, pooled-device threading ... Five verified findings from the IDD-push/pf-vdisplay deep audit: - Keyed-mutex acquire (BOTH endpoints): AcquireSync returns WAIT_TIMEOUT (0x102) / WAIT_ABANDONED (0x80) as SUCCESS-severity HRESULTs, which the windows-rs Result wrapper erases — a busy slot read as "acquired", so driver and host could race the same ring texture (torn frames) and the designed busy-skip backpressure was dead code. Both sides now classify the raw vtable HRESULT; WAIT_ABANDONED counts as acquired (ownership transfers — refusing it would wedge the slot forever). - Host SDR hot path leaked one ID3D11VideoProcessorInputView per converted frame: the D3D11_VIDEO_PROCESSOR_STREAM ManuallyDrop field suppressed the release after VideoProcessorBlt. Released by hand now, success or not. - Driver leaked IddCx's per-acquire surface reference (from_raw_borrowed on a TRANSFERRED reference — the MS sample Attach/Reset's it): the swap-chain surface set survived swap-chain destruction, the likely true root cause of the ~50 MB-per-reconnect VRAM loss that device pooling only mitigated. Now adopted via from_raw (publisher or not) and dropped pre-Finished. - PUNKTFUNK_IDD_PUSH removed: capture is unconditionally IDD-push, but the vdisplay manager still gated the lingering-monitor preempt (and render pin) on the knob, whose default was OFF — dev/CLI runs reused a lingering monitor whose IddCx swap-chain is dead (black reconnect). The preempt and the render-GPU pin are now unconditional; host.env comments no longer promise the removed DDA/WGC fallback. - Driver D3D device: dropped D3D11_CREATE_DEVICE_SINGLETHREADED (unsound since DEVICE_POOL shares one device across processors) and the pooled immediate context is now SetMultithreadProtected — two concurrent monitors' workers otherwise race an unlocked context (UB in the UMD). No wire-contract change (pf-driver-proto untouched); the driver fixes take effect on the next pf-vdisplay redeploy. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-03 16:27:13 +00:00