- Implemented in-house, zero-dependency utility modules in `pi-utils` covering DOM manipulation, markdown parsing, templating, browser automation helpers, and terminal buffers.
- Migrated packages across the repository to consume the new internal utilities and `omptype` schema validators instead of external dependencies.
- Removed multiple external runtime and development dependencies including Zod, Marked, LRU cache, Turndown, and Puppeteer browser packages.
Reported compositor-limited per-window input before reaching the AT-SPI focus path and stopped advertising foreground delivery on Wayland.
Removed the obsolete AT-SPI window-raise helper and updated public recovery guidance.
Fixes#7702
WaylandBackend::capabilities() hardcoded capture:true, but the PipeWire
screencast path is compiled only under the wayland-pipewire feature, which
is off by default and excluded from shipped Bazel addons (crate_features=[]).
Released builds therefore advertised capture the binary could never do:
every capture() call returned CaptureFailed, and callers trusting
capabilities() retried into a guaranteed failure.
Gate the capture flag and capture_permission on cfg!(feature =
"wayland-pipewire") so the report matches the compiled-in path, and align
docs/computer-use.md with what shipped builds actually support.
Fixes#7700
The Claude/Cursor/Gemini/Windsurf importers appended user entries before
project entries, so a project `enabled: false` could not claim its dedupe key
ahead of a same-named user server and the disable was silently ignored. Load
project entries first, matching the native/Codex loaders, so a project disable
suppresses a same-named user server.
Updated docs/mcp-config.md to reflect the project-first precedence and added
compound regression coverage.
Fixes#7652
Completes the maintainer's removal of per-call model selection from
subagent spawns (9f8aa87dbf removed it from the task tool and the
model-facing agent() docs/prompt, but the eval agent() runtime and all
four preludes still accepted and forwarded a per-call model).
Subagents now always resolve through the selected agent's frontmatter
model and settings, so an explicit model: "default" can no longer
silently route children onto the parent session model.
- agent-bridge: drops "model?" from agentArgsSchema and the request
forward; adds "+": "delete" so a legacy model argument is stripped
(same contract as the task wire schemas).
- JS/Python/Ruby/Julia preludes: remove the model parameter from
agent(); completion()'s tier selector is unchanged.
- docs (tools/eval.md, python-repl.md) updated to the removed surface.
Refs #6438
- Introduce `@oh-my-pi/omptype` as a new ArkType-compatible schema validation package featuring a lazy JIT runtime, JSON Schema emission, and compatibility adapters.
- Replace `arktype` across workspace packages and test utilities with `@oh-my-pi/omptype`.
- Add benchmark suites, tests, and documentation for the new validation engine and adapters.
- Update workspace build, test runner, and release configurations to include the new package.
Retained pending pipeline state across blank and comment-only continuation
lines, and parsed Bash's |& operator as a single pipe boundary. Added
regression coverage for both forms and aligned the Bash interceptor docs.
Fixes#7496
The 17.2.2 compound-fragment matching splits commands on every unquoted
operator including `|`, so a downstream pipe stage like `grep x` in
`printf 'x\n' | grep x` became a standalone interception candidate and was
routed to the `grep` tool, which searches paths and cannot consume the
previous stage's stdout.
`extractFlatShellCommandSegments` now flags each segment that receives piped
stdin from a single unquoted `|`, and `interceptionCandidates` skips those:
a stdin-consuming stage cannot be replaced by a path-based dedicated tool.
Standalone (`grep pattern path`), first-stage (`grep x file | wc`), and
`&&`/`||`/`;`-sequenced commands still match.
Fixes#7496
- Added window discovery, targeting, and frame validation for macOS, Windows, and Linux platforms.
- Updated computer tool and protocol definitions to support listing and targeting specific application windows.
- Refactored native computer tool exposure to function-only representation across models.
- Updated documentation and test suites to reflect window-scoped computer control capabilities.
- Added `ensureSharedBrowser` and shared browser acquisition to manage project-shared broker-owned Chromium instances.
- Implemented concurrent duplicate daemon start prevention and single-flight `pendingOpens` deduplication.
- Updated browser handle disposal to disconnect from shared daemons rather than closing them.
- Updated browser documentation and launch specifications to support shared and local headless runs.
Added the active Kitty Unicode placeholder overrides to the canonical environment-variable reference, including tmux placement behavior and the unsupported-terminal caveat.
Fixes#7172
Match interceptor regexes against conservative, raw shell command segments
in addition to the complete command, so anchored rules can detect commands
after &&, ||, ;, |, &, and newlines without treating quoted or escaped text
as commands.
Add extractFlatShellCommandSegments() to preserve source text for
user-configured regexes, unlike the token-based approval matcher.
Add skipShellWord() and environment-assignment stripping so rules can match
commands prefixed with NAME=value assignments. Preserve the original command
in interception errors after extracting a leading cd command.
html-to-markdown-rs 2.30 could recurse through pathological HTML until
a native stack overflow aborted the entire OMP process. Upstream 3.9.2
bounds those traversals and reports omitted subtrees as a
machine-readable DepthLimitExceeded warning.
Upgrade html-to-markdown-rs to 3.9.2. Upstream treats a depth-limited
conversion as a successful partial Markdown result plus a warning;
deliberately promote that warning to a rejected `htmlToMarkdown`
promise, allowing the Read tool to fall back without terminating OMP.
Normal conversions and unrelated warnings keep their existing behavior.
Add a rejection-contract test plus a child-process regression proving
OMP survives deeply nested and malformed input.
- Add the `app.live.toggle` keybinding defaulted to `Ctrl+L` to start or stop live voice mode.
- Remap the default display-reset action (`app.display.reset`) from `Ctrl+L` to `Alt+L`.
- Update the live visualizer to listen for stop keys so the toggle chord terminates active sessions.
- Added the coding-agent changelog entry the review flagged as missing.
- Updated docs/extensions.md: the ACP UI-context surface note still listed
editor among the stubbed no-op methods after it was wired through
elicitFromAcpClient.
Addresses PR review. The initial version put invokeTool on AgentToolContext
via ToolContextStore, but the extension execute path (RegisteredToolAdapter)
builds its own ExtensionContext and never saw it, so the documented
registerTool wrapper use case did not work. It also allowed arbitrary
cross-tool targets (bypassing the target's approval policy), used a
session-global recursion counter that tripped on concurrent independent
delegations, and missed discoverable built-ins that xdev partitioning moves
out of the tool array.
Rework:
- Move invokeTool onto ExtensionContext, and bind it in RegisteredToolAdapter
to the tool's own name, so a re-registered built-in actually receives it.
- Make delegation same-tool only: invokeTool takes just (params, options) and
runs the native built-in of the caller's own name. It cannot reach an
arbitrary target, so it cannot escalate past the approval already granted
for the call, and the native call is not re-gated.
- Track recursion depth per call chain (threaded through invokeNativeTool and
createContext) instead of session-global state, so concurrent delegations
do not interfere.
- Seed the native resolver from the xdev registry when present (it retains
discoverable built-ins like browser), else the built-in registry.
Replaces the ToolContextStore-level unit test with an end-to-end test that
registers a built-in wrapper through the extension/session path and asserts
the native tool runs the wrapper's delegated input.
A tool's execute context now carries invokeTool(name, params, options?),
which runs the native built-in of `name` and returns its result. A tool
that re-registers a built-in (e.g. wrapping write to add logging or a
policy check) can delegate to the original instead of reimplementing it.
The native implementation is captured before extension re-registration
replaces the registry entry and before the ExtensionToolWrapper pass, so
invokeTool reaches the unwrapped native execute: it does not recurse into
the caller's own wrapper, and it inherits the caller's already-granted
approval rather than re-running the gate. Delegation depth is guarded
against accidental self-recursion, and it resolves to undefined when no
native tool of that name exists.
Wired through ToolContextStore with a lazy native-tool resolver, so it is
coding-agent-only (no agent-loop change) and sees the fully-assembled
built-in set at call time.
Under a rootless XWayland session (the GNOME/KDE/sway default) the X11
root window has no backing pixmap, so core `GetImage` on the root returns
`BadMatch`. The computer tool advertised Wayland support yet failed every
screenshot with a raw X11 protocol dump, and coordinate actions stayed
gated behind a capture that could never succeed.
- `Monitor::all` now probes a 1x1 root `GetImage` at initialization and,
on a `Match`/`Drawable` error, fails fast with an actionable
`DESKTOP_BACKEND_UNAVAILABLE` message naming the rootless-XWayland
constraint via the new `root_capture_error` classifier.
- `capture_image` routes its `GetImage` failure through the same
classifier so any surviving path yields the actionable message rather
than a raw protocol dump; unrelated errors stay verbatim.
- Corrected the module doc premise and `docs/computer-use.md` to list
rootless XWayland as unsupported (capture needs a rooted/rootful X
server, which only exposes X11 clients).
Fixes#7085
can1357