- Removes `model` field from task item/schema, TaskParams, and TaskItem types.
- Removes model selector validation, formatting, and approval display logic.
- Updates task tool priority docs to reflect that model is no longer per-call overridable.
- Updates eval agent() helper docs and prompt templates to remove model parameter.
- Updates tests to reflect removal of model override capability.
- Renamed quota label from "ZAI Web Search / Reader / Zread Quota" to "ZAI Zread Quota".
- Shortened tier slug from `web-search-reader-zread` to `zread` and updated associated limit IDs.
- Large-paste menu now saves pastes as local://paste-N.md instead of
local://attachment-N, giving the artifact a markdown extension and a
clearer name.
- Add `resolveFallbackTool` callback to `AgentOptions` and `AgentLoopConfig` that resolves tool calls not found in the advertised set.
- Use the callback as a third lookup step after `name` and `customWireName` match, enabling side transports like `xd://` device mounts.
- Add test coverage verifying the fallback resolves known devices and preserves "not found" errors for unknown names.
- Wire the coding agent's device registry as `resolveFallbackTool` in both `createAgentSession` and `streamAgentSession` paths.
- Prepended a model-visible PREVIEW_PENDING_NOTICE to ast_edit preview
results; the TUI-only proposed badge never reached the model, so
preview diffs read as already-applied edits.
- Rendered the resolve reminder with the source tool name via
Handlebars instead of a generic 'This is a preview'.
- Documented the xd://resolve / xd://reject two-phase flow in the
ast_edit tool prompt.
- Kept op required in the todo schema; lenientArgValidation now routes raw args to execute(), where resolveTodoParams re-validates and repairs an omitted op (list -> init, phase+items -> append, bare items on empty list -> init).
- Ambiguous op-less calls surface the schema error as a retryable tool error instead of a hard validation failure.
- Pinned to the same versions as .github/actions/ensure-cmake (cmake 4.1.2, ninja 1.13.1), which now no-ops on the preloaded image.
- Extended both reload smoke-test tool lists with cmake/ninja.
- Rolled out as omp-kata-runner:2026-07-24-113811.
clang-cl enforces per-function target features unlike MSVC, so opus' silk/x86 SSE4.1 units fail under cargo-xwin. The win32 x64 addon floor is x86-64-v2 (SSE4.2 inclusive), so enable it for all C deps via CFLAGS_<target>.
- Added ensure-cmake action installing pinned cmake/ninja on omp-kata pods; audiopus_sys builds bundled libopus via CMake (Ninja for MSVC cross).
- Set CMAKE_POLICY_VERSION_MINIMUM=3.5 globally and in build-native.ts: the bundled opus tree declares cmake_minimum_required below 3.5, which CMake 4.x refuses.
- Dropped the -C target-cpu=native fallback for non-x64 native builds: it baked build-host CPU features into shipped darwin arm64 addons and trips ring 0.17's aarch64-apple const assertion.
- Add `CodexAttestationProvider` hook and `getCodexAttestationHeader` resolver that gates on ChatGPT-OAuth credentials.
- Integrate attestation into WebSocket transport, SSE event stream, and OpenAI compaction requests.
- Wire `setCodexAttestationProvider(generateCodexAttestation)` in model-registry init for OAuth sessions.
- Added `LIVE_DELEGATION_MESSAGE_TYPE` constant and delegation message handling for voice sessions.
- Implemented turn-based transcript coalescing with user and assistant turn counters.
- Added transcript display row with normalized rendering in the live visualizer.
- Refactored controller to send delegation messages via `sendCustomMessage` with configurable frame styling.
- Removed microphone permission error reporting from silence detection logic.
- Switched from `miniaudio` to `maudio` Rust crate and added `AudioCapture` and `AudioPlayback` native classes.
- Removed browser-side audio infrastructure including Web Audio API, audio worklet processor, and WebRTC runtime.
- Migrated STT recorder and transcriber modules to use native `AudioCapture` with callback-based streaming.
- Replaced streaming audio player with native `AudioPlayback` that writes PCM directly without TypeScript intermediaries.
- Removed ffmpeg, wav, and platform-specific playback commands from the audio toolchain.
- Replaced puppeteer-based WebRTC with native LiveWebRtcPeer for cross-platform live audio delivery.
- Added cross-platform microphone capture via miniaudio and Opus codec integration for live encoding/decoding.
- Added Apple DeviceCheck attestation token generation via raw Objective-C FFI for macOS.
- Updated live session model to "gpt-live-1-codex" and default voice to "sol" across protocol and controller.
- Added LiveWebRtcPeer and deviceCheckGenerateToken to the public native bindings API.
- Extracted #formatToolExecution into a standalone formatDefaultToolExecution module.
- Updated xdev renderXdevCall and renderXdevResult to use the default card when no mounted renderer exists.
- Added fallback rendering that shows tool label, args, and output with appropriate theming.
- Added integration test verifying generic card renders for mounted tools without bespoke renderers.
- Added cmp builtin with full POSIX-compatible flag support including `-b`, `-i`, `-l`, `-s`, `-x`, `-h`, `-z`.
- Integrated into shell builtin registry and coreutils module.
- Added comprehensive tests using tempfile for temporary directories.
- Catch execution errors in XdevRegistry and render them using the mounted tool's error handling.
- Preserve xdev dispatch context when device execution fails.
- Add `pinSessionOAuthAccount` storage method and active account flag to the auth storage API.
- Introduce session account selector component, controller logic, and interactive mode delegation.
- Implement the `/session pin` builtin slash command with text listing and account pinning capabilities.
- Add unit tests covering session account selection, component navigation, and command handling.
- Replaced resolveHangulCompatibilityJamoWidthFromTerminalIdentity with a
static hangulJamoWidth field on TerminalInfo (ghostty 2, warp 1,
platform otherwise); startup now reads TERMINAL.hangulJamoWidth.
requestRender(true) only queues the paint via setImmediate; calling
prewarm() synchronously afterwards put the worker spawn syscall ahead
of the render callback in the same loop turn. Schedule the prewarm
with its own setImmediate (FIFO after the render callback) so the
first startup frame paints before the subprocess spawns.
- Fixed a macOS clipboard bug where copied URL text like `https://i.can.ac/x.png` was coerced into a bogus HFS path (`/https/::i.can.ac:x.png`) and dead-ended with "Image not found" instead of falling through to text paste.
- The AppleScript now checks `clipboard info for "class furl"` before coercing so plain text/URL clipboards paste as text rather than file paths.
- Extracted the script to its own `.applescript` file and added TypeScript declarations for `.applescript` imports.
- Updated the OpenAI Codex provider to unroll native computer calls and tool outputs into standard function calls.
- Added support for the `PI_CODEX_RESPONSES_LITE` environment variable override via the request transformer.
- Updated documentation and tests to cover lite response resolution and native computer response unrolling.
- Added the upstream keyText helper to the legacy package-root shim.
- Covered active keybinding formatting and documented the compatibility fix.
Fixes#6470
#finalizeFile marked the sink finalized then ran the capped-artifact tail
replay before closing. A write error during that replay threw before
sink.end(), and because #finalized was already set the executor finally
paths calling dispose() could not retry the close, leaking the descriptor
and masking the original tool error.
Moved sink.end() into a finally around the tail replay and swallowed both
the replay and close errors so the descriptor is always released and
dispose() never throws.
The first interactive submit fired session.generateTitle() before
startPendingSubmission() painted the optimistic user row, and
tinyTitleClient.generate() spawned the local tiny-title subprocess
synchronously in #ensureWorker() before its first await. With a local
providers.tinyModel configured, subprocess-spawn latency therefore landed
ahead of the first frame, stalling the first prompt.
Paint the pending row before starting titling, and prewarm an idle,
unref'd worker at TUI startup via a no-op ping (no model load) so the
first submit reuses a live subprocess.
Fixes#6462
OutputSink.dump() was the only path that closed the spill Bun.FileSink.
The bash and Python executors re-throw on failure and their finally
blocks never closed the sink, so any large-output command that errored
leaked the artifact descriptor until an unrelated read (e.g. a SKILL.md
load) hit EMFILE.
Added an idempotent OutputSink.dispose() that closes the sink exactly
once (awaiting any in-flight sink creation, guarding post-finalize
resurrection) and wired it into every executor's finally block.
Fixes#6463
- Reused terminal identity detection to select Warp narrow and Ghostty wide profiles.
- Covered Warp resolution while preserving platform defaults for other terminals.
Fixes#6461
- Replaced the separate GUI-linked pi_natives.desktop.linux-x64 addon with
a pure-Rust X11 backend (x11rb RustConnection capture via RandR/GetImage,
XTest input with keysym mapping) compiled into the core addon on every
published target; Linux arm64 and musl are now supported and headless
hosts load the addon unaffected.
- Removed the native-desktop-linux cargo feature, desktop_unsupported.rs,
lazy desktop loader, second napi build, desktop packaging/CI steps, GUI
build dependencies, and the now-unreferenced vendored libspa crate;
reverted setup-system-deps to main.
- Preserved the desktop input hardening semantics on the unified backend:
XTest layouts reject negative origins and coordinates beyond 0..=32767,
batch coordinates stay bound to the frame last returned to JS with
intermediate screenshots deferred, coordinate input requires a
previously returned frame, and failed chord releases still release
every held key.
- Enforced a 60s worker-side execute deadline (DESKTOP_DEADLINE_EXCEEDED):
no input is emitted after expiry and wait-heavy batches are rejected
upfront.
- Added int32 fail-closed validation for coordinates, drag points, and
scroll deltas at the JS ingress and gateway schema.
- Exposed computer to models without native OpenAI computer-use support as
a regular function tool with a typed GA action schema across OpenAI,
Azure, and Codex Responses providers, including named forced choice.
- Added the /computer slash command (on/off/status/toggle) for
session-only enablement via runtime tool registration in SessionTools.
- Updated docs, changelogs, and contract tests accordingly.
- Shimmed writable select.value in export-html harness; linkedom's getter-only HTMLSelectElement.value made template.js theme assignment throw under strict mode.
- Bound the oauth-flow port blocker to 127.0.0.1 explicitly; macOS lets a specific-address bind coexist with a wildcard one, so the flow bound the blocked port and never fell back.
- Re-anchored atomic-rewrite race tests on rewriteEntries() after the compaction-supersede rewrite trigger was removed in cb63ebd.
- Superseded compaction summaries render as elided placeholders in the forward transcript since cb63ebd; only the active compaction keeps its text and frames.
can1357
