GitHub Release: can1357/oh-my-pi v18.3.3 (27.09.2026)

@oh-my-pi/pi-agent-core

Added

• Added live steering support, allowing models to receive and act on user steering messages during an active stream.

@oh-my-pi/pi-coding-agent

Added

• Added a unified predictive text engine with N-gram, SmolLM2, and macOS native providers, including cross-engine blending, background model downloads, and a cross-process prediction daemon.


• Added the omp predict command for evaluating completion performance and support for ingesting existing Claude Code and Codex prompt histories to bootstrap predictions on new installations.


• Added omp skill list [dir] [--json] to report skills resolved for a session directory, including discovery warnings in JSON output.


• Added a centralized progress display for background tool and model downloads, including support for downloading the SmolLM2-135M word-completion model.


• Added dynamic evaluation guidance through hidden session notices.


• Added a required complexity rationale to the task tool to improve automatic thinking-depth selection.


• Agents using task or bash now receive the wait tool for background-process coordination, and subagents can receive it when explicitly requested.


• Added context-aware suggestions to empty composers based on agent activity and effort.


• Added optional global or per-project memory scopes to the retain and learn tools when Mnemopi scoping is enabled.


• Added /btw to focused subagent views for asking questions about that agent's transcript with separate side-conversation history.

Changed

• Completion behavior now uses the N-gram engine for standard auto completion across platforms, with blended N-gram and SmolLM confidence scoring where applicable; the SmolLM2 model uses a 145 MB GGUF (Q8_0) download and is prefetched only when explicitly activated.


• Updated spelling.autocomplete to use an enum-based engine configuration.


• Completion ghost text is now preserved through manual keystrokes.


• Window input actions now default to background execution; set takeover: true to opt into foreground activation, with clarified cross-platform coordinate and activation behavior.


• omp tiny-models download can now download the word-completion model.


• Updated /play help, read-tool summaries, platform-aware shortcut labels, and other UI hints for clearer interaction guidance.


• Updated the empty-submit behavior to account for live-steered messages and surface pending live-steering status in the UI.


• ps --all now includes exited global services, while the default view shows live global services.


• Orchestrator task documentation now follows a Target/Change/Acceptance format.


• Slash-command and hint usage tracking is now persistent and namespaced.

Fixed

• Preserved MCP structuredContent in live tool-result details so evaluation callers can consume server data without reparsing model-facing JSON; spilled results continue to retain an artifact reference without duplicating the payload in session history.


• Fixed Collab hosts becoming unable to reclaim a room after a brief network interruption; hosts now retry room recovery without losing guests or queued updates.


• Fixed one-shot commands that stopped before completing, such as omp config set on a fresh Windows profile, incorrectly exiting successfully without output; they now report failure with diagnostic guidance.

@oh-my-pi/pi-mnemopi

Fixed

• Fixed recall search matching query terms inside unrelated words, improving result relevance and ensuring exact matches are prioritized.


• Fixed sleep summaries replacing shortened terms within larger words, preventing unintended word corruption.

@oh-my-pi/pi-natives

Added

• Added a TextPredictor N-API binding for managing the high-performance ghost-text completion engine.

Changed

• Updated desktop input-control capabilities to use a unified takeover setting, including takeover: true for forced foreground pointer interaction.

@oh-my-pi/pi-tui

Added

• Added responsive ghost-text word completion with pluggable backend providers, context-aware prose filtering, and feedback support.


• Improved autocomplete responsiveness for high-latency file discovery by showing interim suggestions and a searching state while results are refreshed.

Changed

• Improved word-completion acceptance and persistence when typing through existing ghost text, including more natural handling of trailing spaces and punctuation.


• Made keyboard labels across the TUI platform-aware so shortcuts are displayed using the appropriate key names for the user's operating system.


• Updated the process monitor to distinguish target scope from current and global scope in its labels.

Fixed

• Fixed autocomplete submission so Enter commits the current input correctly while suggestions are still loading.


• Fixed the background tint for truncated skip lines.

Removed

• Removed the legacy TinyTitleDownloadProgress overlay in favor of the centralized agent HUD.

What's Changed

• fix(collab): reclaim a host room the relay still holds after a drop by @alphastorm in #13355


• fix(cli): exit non-zero when a command ends before completing by @alphastorm in #13373


• ci: second set of CI uplifts by @H4vC in #13391


• fix(mnemopi): match AAAK word substitutions on whole words only by @alphastorm in #13320


• fix(mnemopi): require token boundaries for lexical recall matches by @alphastorm in #13322


• feat(coding-agent): let retain and learn write to the shared memory bank by @alphastorm in #13324


• fix(mcp): preserve structured results in tool details by @shawnkoh in #13398


• feat(coding-agent): allow /btw in focused subagent views by @H4vC in #13412


• fix(web-search): prioritize GPT-6 Luna over GPT-5.6 Luna by @anatoli-tsinovoy in #13442


• fix(coding-agent): serialized codex saved resets across sessions by @roboomp in #13439


• fix(collab): re-applied auto-start after a room ended on its own by @roboomp in #13446


• fix(task): kept latest value for repeated scalar yield sections by @roboomp in #13449


• ci: release-time uplifts and green main (no native rebuild on bump, win32-arm64 cross-build, fresh bazel lock) by @H4vC in #13450


• fix(coding-agent): scope focused /btw history and keep it rendering after leaving the view by @H4vC in #13431


• spinner fix by @H4vC in #13453


• feat(cli): add omp skills command for machine-readable skill listings by @andrebrait in #12273


• fix(catalog): narrowed llama.cpp pre-3.8 qwen effort ladder by @roboomp in #13456


• fix(session): preserved batched tool results after rewind by @roboomp in #13459

Full Changelog: v18.3.2...v18.3.3