Added reversible private-use glyph tokenization for Claude-compatible provider requests, including prompt notices, streamed response decoding, and safe handling of unresolved model-authored glyph tokens. Added model capability metadata for reversible private-use glyph tokenization on Claude-compatible models, so provider request handling can apply the compatibility layer without inferring from transport details. Added the `omp render` command to replay session threads and benchmark transcript pipeline performance. Added configurable typo detection (`Ctrl+.` suggestions), Tab word completion, and opt-in autocorrect to the macOS prompt editor. Added a live benchmark dashboard to `omp bench` with real-time performance estimates, p50/p95 statistics, distinct input/output throughput metrics, cost tracking, mixed challenge suites by default, and a `--prefill-bytes` option for synthetic prefill benchmarks. Added the `/shake thinking` command to strip model reasoning blocks from session history. Added icon support and usage-frequency ranking to slash-command autocomplete suggestions. Enhanced the edit tool to support `+`-prefixed line insertions, unified diff formats, bare selection replacements, and robust recovery for common syntax variations and ambiguous match spans. Startup composer now renders immediately using cached session and theme data, allowing typing before session initialization finishes without dropping keystrokes. Added the `tui.resizeScrollback` setting (default `append`) controlling how a settled width resize refreshes pane scrollback when the terminal repaints in place (tmux/screen/Zellij panes, in-place direct terminals). Multiplexers rewrap old output naively on width changes, leaving history hard-broken at the old width; `append` re-emits the transcript at the new width below it (one fresh copy per settled resize), `rebuild` clears pane history first so it holds exactly one current-width copy (needs a host that honors ED3, like tmux; erases pre-session scrollback), and `preserve` keeps the old-width history untouched with zero growth ([#8193](https://github.com/can1357/oh-my-pi/issues/8193)). Added native macOS spellchecker APIs (`macOSAutocorrectWord`, `macOSCheckSpelling`, `macOSCompleteWord`, `macOSSpellingGuesses`, and `macOSSpellCheckerAvailable`) that run asynchronously without blocking the JavaScript thread. Added `HighlightStream`, a stateful incremental syntax highlighter that supports chunked highlighting while maintaining parser state. Added `TtyWriter`, an off-thread terminal output writer that performs non-blocking writes and tracks backlog metrics for renderer frame skipping. Added `EditorTextAssistProvider` with spelling suggestion support (`ctrl+.`), word replacement choices, and async autocorrection handling. Added `Terminal.pendingOutputBytes` and an output-backpressure render gate to drop stale frames on slow terminals. Added `deferInput` startup option and `enableInput()` across `Terminal`, `TUI`, and `TUIStartOptions` to improve startup responsiveness. Added icon support and customizable theming to autocomplete and select lists. Added `MarkdownTheme.createHighlightStream` for incremental syntax highlighting of completed lines in streaming Markdown code blocks. Added `maxDescriptionRows` option to `SelectList` layouts to truncate wrapped descriptions with an ellipsis. Added `commandUsage` ranking callback support to `CombinedAutocompleteProvider` to prioritize frequently used slash commands. Added `Editor.viewportRowsProvider` to constrain autocomplete dropdowns within the available terminal height. Added `Editor.setTheme()` to dynamically change themes without recreating the editor or losing draft content. Added `setResizeScrollback()` / `ResizeScrollbackMode` (`PI_TUI_RESIZE_SCROLLBACK` env initializer) controlling what a settled in-place width resize does to native scrollback, which the host rewraps naively at the old width: `append` replays the transcript at the settled width below the old-wrap history, `rebuild` clears pane history first (ED3) so it holds exactly one current-width copy, and `preserve` repaints the viewport only with zero history growth. The raw engine defaults to `preserve`; the coding agent's `tui.resizeScrollback` setting (default `append`) governs interactive sessions. Added Amazon Bedrock Converse guardrail configuration with provider-scoped identifier, version, and trace settings. Fixed `google-gemini-cli` model refresh returning only bundled models for Gemini Code Assist Standard accounts, whose credential is not authorized for the Antigravity `fetchAvailableModels` endpoint (HTTP 403). Discovery now falls back to the account's own `retrieveUserQuota` list on Cloud Code Assist, surfacing models such as `gemini-3.5-flash` ([#9315](https://github.com/can1357/oh-my-pi/issues/9315)). Added Amazon Bedrock guardrail metadata to model definitions for Converse requests. Plan review can save a plan to a chosen path and start a new session. Edit results now warn when an edit leaves a previously parsing file unparseable, independent of the `edit.blackbox.enabled` recorder. Added provider-wide Amazon Bedrock guardrail settings to models configuration, including custom models. Added the `/pin` slash command to pin and unpin sessions so they stay at the top of the `--resume` picker UI. Optional edit parse-regression capture appends the before/after content, model, variant, and arguments to `~/.omp/agent/edit-blackbox.jsonl` when `edit.blackbox.enabled` is enabled. Collapsed individual skill commands into a `/skill:` namespace entry to declutter suggestions Added `TUI.renderNow()` for terminal-safe synchronous priority frames that retain resize debounce, output-backlog, and image deferral safeguards. Added opt-in edit auto-repair (`edit.autoRepair.enabled`): when an edit breaks a file's AST parse, the smol model repairs the broken region in place — validated by re-parse, revert-rejected, and surfaced as a diff in the tool result — instead of only warning. Added update channels: `omp update --canary` installs canary prereleases from the npm `canary` dist-tag and `omp update --stable` switches back; the chosen channel persists and drives the startup update check. Added the `omp git` command (and `/git` slash command): an interactive, fullscreen repository TUI featuring a split/inline/hunk diff viewer with minimap scrollbar, syntax highlighting, a staging sidebar with line-level staging, commit composer with amend support, and author avatars. Supports keyboard navigation, full mouse interaction, and pinning views to specific commits via `omp git `. Overhauled the `/extensions` Extension Control Center into a fullscreen alternate-screen dashboard with mouse support, tab navigation, unified inspector views across extension types, live MCP connection management, and expandable details (`Ctrl+O`). Added support for live syntax highlighting in streaming markdown code blocks. Added an immediately editable startup composer for interactive launches, preserving drafts typed while session initialization is in progress. Exported `getAvatarCacheDir` to resolve the avatar cache directory path. Added browser-based Sign in with OpenRouter using OAuth PKCE, while retaining support for pasted OpenRouter API keys and redirect URLs for remote sessions. Added `/login` API-key authentication for DeepInfra and Yolo-Auto, including validation against each provider before the credentials are accepted. Added built-in DeepInfra provider support (`deepinfra`, `DEEPINFRA_API_KEY`) with live model discovery, including chat models, context windows, pricing, cache-read pricing, vision input, and reasoning-effort capabilities. Added built-in Yolo-Auto provider support with the flat-rate `deepseek-flash-v4` model and live model discovery. Added append-only transcript declarations and stable-row APIs for components with immutable history prefixes. Added the `:img` read selector to rasterize local SVG and SVGZ files for vision input. Added side-by-side image and SVG previews to `omp git`, including Git LFS object resolution and clear placeholders for unavailable or unsupported binary content. Added the `omp if-bench` command for zero-tool instruction-following and working-memory benchmarking across models, with live progress and ranked results. Added `q` to quit the git TUI. Added advanced whitespace filtering to the git TUI, including formatting-only changes and import-only changes in TypeScript, JavaScript, Rust, and Go. Improved the git TUI sidebar by compressing single-child directory chains and separating new or untracked files from tracked changes. Added Yolo-Auto to `/login` and documented the `YOLO_AUTO_API_KEY` environment variable. Updated the OpenRouter `/login` flow to support browser-based sign-in and automatic API-key provisioning, while retaining support for pasted `sk-or-…` keys. Added DeepInfra support for the `image_gen` and `tts` tools, including provider selection and MP3 or WAV output for text-to-speech. Added asynchronous, size-bounded SVG-to-PNG rasterization for terminal media previews. Added the `DiffStream` API for processing text and byte input incrementally, opening files asynchronously, reporting stable-prefix progress, generating exact unified diffs, and warming syntax grammars asynchronously. Loader messages can now be provided as a function, allowing dynamic labels such as live countdowns to update on each spinner tick while preserving the existing behavior for static strings. Added `stableStringifyJson` for deterministic serialization of nested JSON-shaped data. Added the `backgroundIdleMs` option to customize how long background auth-broker activity remains active before automatically parking. Added fast, cached conventional commit message generation to the git TUI and `omp commit --legacy`, including automatic handling of whitespace-only changes, clearer commit scopes, and improved grammar and tense in generated summaries. The git TUI sidebar now supports collapsing and expanding the Unstaged and Staged sections, with keyboard shortcuts to stage or unstage an entire section. Long streaming thinking and reasoning output now continues into terminal scrollback during a turn instead of remaining clipped to the viewport. Added `Markdown.getLastRenderStableText()` to expose the stable prefix of streamed Markdown text for append-only transcript publication. Added conventional commit generation with support for dependency, security, configuration, UX, and infrastructure commit types, plus configurable caching and large-diff analysis behavior. Added application-level usage attribution for billing and usage reporting, with per-application aggregation and automatic client identification. Applications can set their label with `OMP_APP_NAME` (default: `omp`); update the broker before clients to support the new usage reports. Added cached background refresh from the shared models.dev catalog so newly published models for known providers can appear without a new OMP release, while bundled models remain the offline fallback. Added nonblocking shared model-catalog refresh with cached startup hydration and source freshness diagnostics, allowing newly published models for known providers to appear without a binary release. Added `omp usage clients` to report per-client token usage recorded by the auth broker, including the machine and application responsible for usage by provider. Supports `--days` and `--json` output. Added `math-delimiters`, the LaTeX span/block delimiter grammar (`mathStartIndex`, `mathOpenerAt`, `mathSpanAt`, `mathBlockAt`) shared by every Markdown renderer: pandoc's anti-currency rules for `$…$`, own-line display blocks, and delimiters matched by backslash parity, so an escaped `\$x$` stays literal and a TeX row break cannot end a span early. Added `RequestError.sessionBusy(message, data)` to represent ACP session-busy errors (`-32003`) through the shared JSON-RPC transport. Exported `getComposerCacheDir` for resolving the per-project Composer cache directory, including support for `XDG_CACHE_HOME`. Added Z.AI GLM Coding Plan usage tracking: credit-based `CREDIT_LIMIT` windows (5h + weekly) now surface in `omp usage` and the status line with the plan tier (`plan: lite/pro/max`). Transcript usage rows now show the total prompt-to-yield time (Δ + clock, including tool calls) after the turn timestamp, opt-in via `display.showTurnTime` (off by default). `omp usage` now shows Z.AI GLM Coding Plan credit quotas (5h + weekly) with the subscribed plan tier. The usage status line now labels untiered quota windows with the report's plan tier, surfacing Z.AI Coding Plan (`pro`) and Codex plan names next to the 5h/7d percentages. Transcript Markdown now renders LaTeX: `$…$` and `\(…\)` inline, `$$…$$` and `\[…\]` in display mode, plus own-line `$$`/`\[` blocks. Currency ("$5 and $10"), escaped dollars, and code spans stay literal, and half-streamed delimiters stay visible until the equation closes. Note: parity with the TUI covers these delimited forms only. Bare `\begin{…}…\end{…}` environments without `$$`/`\[` fences remain literal here (the TUI typesets them); web support is a follow-up. `ProcessTerminal` accepts a `conpty` option to force ConPTY-hosted behavior on or off, keeping terminal tests hermetic on WSL where live env detection would otherwise flip kitty-keyboard flags and write chunking ([#9887](https://github.com/can1357/oh-my-pi/issues/9887)). Added the Linux `subreaper` spawn option to retain reparented descendants for process-tree cleanup. Added Z.AI GLM-5.3-Flash to the bundled GLM Coding Plan catalog, with a 1M-token context window, 131,072-token output limit, native image input, and low/high/max thinking levels. It is now available through model discovery and the model picker. Added portable repository discovery and read operations through `VcsRepo`, `repo()`, and `require()`, with support for Git and Jujutsu and explicit capability checks for staged and revision diffs. Added the `Vcs*` API for repository operations across Git and Jujutsu, including repository discovery, refs and status, diffs, staging, commits, branches, worktrees, patch application, stash, cherry-pick, and CLI-backed push, fetch, and clone operations with cancellation support. Exported TuiDebugServer for programmatic headless control Added debug demonstration script to examples Added an `OMP_TUI_DEBUG` Unix socket for headless TUI driving and structured inspection. Added support for continuing interrupted agent runs with pending tool calls, allowing those calls to be retried before requesting the next model response. Added the Sharpshooter memory backend for tracking friction-earned project decisions, with `/memory queue` and `/memory sync` controls. Added `/restart` to relaunch omp with its original launch flags and resume the current session in place. Added the `band` composer shape, a flush powerline status band above the prompt; it is now the default while existing `composer.shape` settings remain unchanged. Added in-place retry for interrupted or failed tool calls: use F5, Alt+R (`app.retry`), or `/retry` to replay an intact failed batch without an additional model round trip. Improved the working status display with a timed braille spinner, streamed intent, session accent colors across relevant status elements, and theme-aware session accent generation. Updated the `unicode` and `ascii` symbol presets to use `π`/`pi` for the brand icon, avoiding tofu on fonts without the nerd-font glyph. Added native process replacement support for the CLI’s `/restart` command. Added `VcsGitRepo.mergeBase(a, b)` to find the best common ancestor of two Git revisions, returning `null` when the histories are unrelated. Press the Right Arrow at the end of a line to accept autocomplete suggestions, inline ghost-text completions, and spelling corrections, just like Tab. Added a smooth brand-color transition and an elapsed turn timer to the status line while the agent is working. Added a full-width “band” composer style for flush status lines. Added `postmortem.drainStdout` to flush buffered standard output before process exit or exec-replacement. Added an `exitOnly` option to `postmortem.register` for resources that should remain available during keep-alive cleanup and be released only on actual process exit. Added `hexToOklch` and `oklchToHex` color conversion utilities with sRGB gamut mapping that reduces chroma when necessary. Added `checkpointWal` to checkpoint committed SQLite WAL frames without blocking concurrent readers. Added gallery previews for composer and status-line components, with CLI filters for browsing by surface, composer, or segment. Added `setTerminalHyperlinks()` to let hosts control OSC 8 hyperlink behavior in rendered Markdown links. Added an optional `completeSimple` callback that observes every result, including results from internal thinking-loop retries. Added compatibility options for Anthropic-compatible proxies that reject `context_management` and OpenAI Responses proxies that provide incomplete reasoning-summary streams. Added ClinePass API-key authentication via the official `CLINE_API_KEY` environment variable, with account validation, actionable subscription and quota errors, support for eligible ClinePass model rosters, and rolling quota-window reporting in `omp usage`. Added Devin router-model support, including assignment of the concrete model before each request, routed-model metadata, credit usage reporting, and plan, quota-window, and account details through `omp usage`. Added GitLab Duo model support. Added provider support for Llama.cpp, LM Studio, and Minimax. Added catalog entries for Qwen 3.8 27B, Granite 4.2 8B, Abliterated variants, GLM 5.3, and Qwen 3.8 Flash Next. Added compatibility metadata for context management and reasoning summaries on supported provider-compatible model endpoints. Added the native ClinePass provider with live model discovery, subscription and free-tier model listings, current limits and pricing, model modalities, and per-model reasoning controls. Subscription models display API-equivalent pricing while free-tier models display as free. Added native Devin provider discovery with current Cascade model capabilities, pricing, limits, reasoning controls, selector aliases, and model descriptions and recommendation/beta metadata. Added static SWE-1.6 defaults so the provider can resolve a default model before account-scoped discovery completes. Added per-tier model pricing and long-context pricing support, along with expanded catalog metadata for model limits, API routes, input modalities, and provider-specific model aliases. Added the `/trace` slash command to display session trace URLs in the stats dashboard. Added support for OpenAI-compatible gateways whose model-list endpoint is rooted at a versioned URL, with an `injectV1: false` discovery option to request `{baseUrl}/models` directly. Added provider-reported credits and concrete routed-model counts to `/session` statistics. Added `CLINE_API_KEY` to CLI environment help for native ClinePass subscription inference. Expanded Devin model selection to support native CLI aliases, dotted upstream model names, and raw effort-route identifiers. Added provider-supplied model metadata to `/models`, including new, beta, and recommended badges plus model descriptions. Standalone `CLAUDE.md` files in project and ancestor directories are now loaded as context alongside `AGENTS.md`, while preserving config-directory precedence. Added an Activity view to Agent Hub with searchable and filterable timelines spanning live progress and persisted transcripts; `/hub` is now the live-operations entry point while `/agents` retains Control Center behavior. Added an `icon.advisorClosed` symbol-theme token: the advisor eye in the status line now closes once the advisor has finished reviewing and will not add further comments. Added a declarative compatibility rules system for consistent model identification, capabilities, policies, and provider-specific behavior across model classes, families, and revisions. Added the compat-compiler CLI for managing model identity and capability rules through KDL configuration files. Added API for daily activity tracking, including cost, requests, and token usage aggregates Added a Traces dashboard for detailed session analysis, including an interactive timeline, searchable and filterable transcripts, token and cost summaries, and aggregate tool-usage and timing insights. Added `postmortem.fatal` for terminal-safe top-level failure reporting. Added thinking controls for Amazon Bedrock models. Added dynamic mid-conversation updates for Anthropic system prompts, tools, and reasoning effort. Added deferred tool loading and prompt caching for Anthropic models. Added configurable handling for invalid Anthropic thinking blocks through `anthropicPrefixMismatchBehavior`. Added support for turn-scoped system messages, changing tools during a conversation, and setting effort on individual messages. Added support for Claude Fable 5.1 models, with improved thinking-prefix handling across supported Claude models. Added DeepSeek V4 Flash Vision Exp, Mercury 2.5 Preview, and Xiaomi MiMo V2.5 Pro UltraSpeed models. Recover stray payloads emitted as plain text into real edit tool calls, with support for disabling this behavior through the edit.recoverInlineEdits setting. Advisors now receive context from the active memory backend, including project decisions and recalled instructions; advisors also gain the recall tool when supported by the backend. Added support for Claude Fable 5.1 Added `/login abliteration` with API key validation against `/v1/models`, supporting the `ABLITERATION_API_KEY` and `ABLIT_KEY` environment variables. Added the Abliteration (abliteration.ai) provider, including its documented abliterated-model catalog and live model discovery. Added the GLM 5.3 Promo 50 model. Added computer-use capability metadata to model configurations. Added declarative provider authentication policies covering login, refresh, environment-key, and credential behavior, with generated compatibility data and typed accessors. Added Abliteration provider support to `/login`, including `ABLITERATION_API_KEY` configuration and help text. Added clone-first Git worktree support that carries over ignored build artifacts when creating worktrees, with a configurable `worktree.clone` setting and fallback to a standard checkout. This is supported by `github pr_checkout`, `omp worktree add`, and `git worktree add` commands entered through the Bash tool. Added the `omp worktree add` command with Git-compatible branch, detach, path, and commit options. Added `/wt` (alias `/worktree`) to create a linked worktree with uncommitted changes and move the current session into it while leaving the original checkout untouched. Added `TerminalQueryResponder` to `@oh-my-pi/pi-utils/vterm`, enabling headless PTY consumers to answer common terminal queries for cursor position, device status and attributes, and foreground/background colors without maintaining a screen buffer. Added support for streaming tool argument updates, providing more responsive tool-call progress. Added Amazon Bedrock `requestMetadata` support for cost and usage attribution in AWS invocation logs. Added catalog-delivered model intelligence scores and estimated output throughput to help compare model capabilities and performance. Added agent reactions: a reply that opens with a lone emoji line shows the emoji as a badge on your message bubble instead of in the text; toggle the prompt invitation with the tui.reactions setting. Added video attachment and reading support through ffmpeg, including preview grids with metadata and timestamp/frame selectors such as :412 and :1h5m42s. Enhanced the model picker with intelligence indicators, catalog TPS estimates, provider-aware ranking, and provider-supplied badges and descriptions. Added detailed, non-summarized findings for scout agents through the report definition field, and subagent result relay so read-only agents can return data to their originating agent. Added agent-scoped rules using an agents frontmatter field with glob matching, including support for inspecting applicable rules with omp ttsr list and omp ttsr test --agent. Added non-interrupting extension messages through deliverAs: "aside" for pi.sendMessage and pi.sendUserMessage. Added copy and open controls for rendered blocks and links, including /copy link and the /open command. Added option-click cursor positioning in the prompt entry box. Added the configurable opencode display layout, with a corresponding first-run and upgrade setup option. Added the skillful prompt setting and /skillful command to control whether available skills are listed in the system prompt. Added Firecrawl as an optional providers.fetch backend for URL reading, configurable with FIRECRAWL_API_KEY and FIRECRAWL_BASE_URL. Added provider request metadata configuration for usage and cost attribution, including Amazon Bedrock request headers and User-Agent customization. Added the :-N read selector for reading the last N lines from files, directories, archives, artifacts, internal URLs, and web URLs, including combinations such as :raw:-60. Added an opt-in extension status-line segment for displaying custom statuses inline. Added injectV1: false to openai-models-list discovery for OpenAI-compatible gateways whose model endpoint is rooted at a versioned URL. Added provider-reported credits and routed-model counts to /session statistics. Added CLINE_API_KEY to the CLI environment help for native ClinePass subscription inference. Expanded Devin model selectors to support native CLI aliases, dotted upstream names, and dynamic effort-route identifiers. Standalone CLAUDE.md files in the project root and ancestor directories are now loaded as project context alongside AGENTS.md files. Added edit-session and edit-store types and utilities for managing edit states, snapshots, hashline operations, edit modes, edit descriptions, editable notebook text, and inline sloppy regions. Added cross-platform sleep inhibition to `PowerAssertion` on Linux and Windows. Added `IncomingDoc` (`@oh-my-pi/pi-utils/incoming-json`) for incrementally reading path-addressed JSON data as text arrives, including string chunks and lines, array elements, and keyed object values, with structured errors for missing, incomplete, aborted, malformed, or mismatched data. Added `Serial` for running asynchronous operations sequentially in call order. Added asynchronous eval agent and completion handles with status, cancellation, messaging, waiting, and automatic result delivery for unwaited background work. Added eval workpools for queueing items onto the least context-loaded keep-alive subagent with configurable concurrency; the pool name is its async-job ID for `hub wait`, `.peek()` gives a non-consuming snapshot, per-item `{key, data|error}` yields finish batches incrementally, and `eval.workpool.freshAgents` opts into a new agent per item. Added support for defining eval tools in Python with @tool or JavaScript with tool(fn, schema), and exposing them to subagents through task, agent, and workpool calls. Configure availability with eval.tools.enabled. Added native Windows ARM64 binaries with architecture-aware installation and updates. Added an MLX backend for running local tiny models on Apple silicon. Configure providers.tinyModelDevice=mlx, or use PI_TINY_DEVICE=mlx or metal, to run title generation, memory tasks, and automatic thinking classification with MLX models, with an ONNX CPU fallback when Python is unavailable. Added Qwen3 1.7B as a local memory and thinking-classification model for the MLX backend. Added Windows ARM64 native addon support, including platform-specific npm packages. Added the public `getTinyWorkerRuntimeDir()` utility, which returns the standard `~/.omp/run/tiny` directory for tiny-worker runtime data. Added GPT-6 Astra support for preserving prompt caching when changing the thinking level during a conversation across the OpenAI and OpenAI Codex providers. Added GPT-6 Astra to the OpenAI Codex model catalog, including support for configuration updates and requests using the freeform `apply_patch` tool. Added recoverable native custom-scheme OAuth callbacks for macOS, Linux desktops, and Windows, with a manual fallback for unavailable or remote sessions. Added the `delegation-bias` capability for tuning how agents delegate work to subagents. Bash now extracts Kitty and Sixel terminal graphics as image results for foreground, failed, manual, and background executions. Markdown links to existing local files and resources are now clickable while preserving their displayed URLs. Added `/switch ` for session-only model changes, with the same model selectors and completions supported by `--model`; ACP `/model ` accepts these selectors as well. Added the `worktree.cleanSource` setting to reset and clean the original checkout when creating a worktree with `/wt`. Expanded the computer JavaScript/Python evaluation prelude with direct desktop, window, screenshot, accessibility, and element interaction helpers, while keeping `computer.run` available for multi-step scripts. Added native Sixel-to-PNG decoding for terminal graphics returned by shell commands. Added transactional native OAuth callback registration with one-shot callback delivery on macOS, Linux desktops, and Windows. Added Markdown hyperlink target resolution while preserving the displayed URL text. Added the `retry.waitForUsageReset` setting: when a provider reports usage-limit exhaustion with a reset time (5-hour or weekly quota windows on any provider), the session sleeps until the reset instead of failing fast past `retry.maxDelayMs`. Added opt-in `bash.allowCompoundCommands` approval for conservative literal `&&` chains, with ordered per-segment rules and normal bash policy fallback for unmatched segments. The opt-in requires a positively classified POSIX-quoting shell; incompatible and unknown shells retain legacy approval. Whole-chain denies take precedence over earlier prompts. Added Muse Code subscription sign-in, credential refresh, inference, and quota reporting in `/usage`, with durable rate-limit backoff so quota refresh recovers instead of repeatedly retrying. Added Muse Code as a provider with Muse Spark models and live account-scoped discovery. Muse Code subscriptions now resolve a compact edit-prompt variant, cutting recurring per-request tool bytes without touching other providers. Added Meta's new `max` reasoning effort tier to Muse Spark 1.3 (standard) on the Meta Model API and Muse Code. Added `advisor.maxNotesPerUpdate` setting and `WATCHDOG.yml` configuration (default `4`): allows reasoning verifiers to batch findings in a single review update without being rate-limited. Headless browser tabs now freeze when a turn settles so idle animated/WebGL pages stop burning CPU/GPU, resuming automatically on next use; tabs idle past `browser.idleCloseSec` (default 30 minutes) are closed. `persist: true` on `browser.open` opts a tab out of both ([#8246](https://github.com/can1357/oh-my-pi/issues/8246) by [@H4vC](https://github.com/H4vC)). `/rename` without a title now generates a session name from recent conversation using the configured tiny model. Added opt-in experimental notes-backed context windows with persistent branch-local notes, searchable original session history, retained latest user requests, and a model-callable rollover tool, including in Code Mode. `/loop` accepts `--until ''` / `--while ''` to gate each iteration on a shell command's exit status, so a loop can stop on real project state instead of only a count or duration. ([#10858](https://github.com/can1357/oh-my-pi/pull/10858) by [@andyhite](https://github.com/andyhite)) Added DeepSeek cost estimates that follow published peak/off-peak rates. Added dated, announced price changes to the catalog, so rates switch on their effective date (e.g. DeepSeek Pro moving to Flash rates). Added Command Code as a built-in provider with API-key login, live model discovery, per-model pricing, native OpenAI/Anthropic-compatible routing, cache-aware token usage, and TTFT metrics ([#11391](https://github.com/can1357/oh-my-pi/pull/11391) by [@CherkaSSH](https://github.com/CherkaSSH)). Unsent prompts cleared with Ctrl+C can now be recalled with Up, including pastes and images; disable Recall Cleared Drafts in settings to discard future clears instead ([#11524](https://github.com/can1357/oh-my-pi/pull/11524) by [@camjac251](https://github.com/camjac251)). Added `tui.vimMode`, an opt-in modal editing layer for the prompt, off by default ([#3299](https://github.com/can1357/oh-my-pi/issues/3299)). Escape leaves Insert; Normal mode has `hjkl`, `0`, `^`, `$`, `w`, `b`, `e`, `gg`, `G`, count prefixes, `x`/`D`/`C`, `dd`/`yy`, `p`/`P` and `u`; `v`/`V` start a Visual selection that `y` copies and `d` deletes. Added a `vim` status-line segment showing the current Vim mode (`NORMAL`/`INSERT`/`VISUAL`/`V-LINE`), the half-typed command beside it (Vim's `showcmd`, e.g. `2d`), and the Visual selection height (`V-LINE 4L`). Included in every built-in preset and hidden entirely unless `tui.vimMode` is on; `custom` preset users can add `"vim"` to `statusLine.leftSegments`. The cursor now changes shape with the Vim mode: block in Normal/Visual, thin/underline in Insert. Applies to the software cursor, and to the real terminal cursor (DECSCUSR) when `PI_HARDWARE_CURSOR` is set. Added the `tui.vimModeDisplay` setting (`text` / `icon` / `none`) controlling how the Vim mode appears in the status line: the full mode name, a single glyph per mode, or nothing. Shown in `/settings` only while Vim mode is on. Added `icon.vimNormal`, `icon.vimInsert`, `icon.vimVisual`, and `icon.vimVisualLine` symbols, so the Vim mode icons follow the active symbol preset like every other status-line icon — Nerd Font (fa-square / fa-pencil / fa-eye / fa-bars), Unicode (`■` `▎` `◉` `≡`), or ascii (`N`/`I`/`V`/`L`) — and can be overridden per theme via the `symbols` map. Added peak `↑` / off-peak `↓` indicators to the cost display for models with scheduled pricing (DeepSeek), refreshed automatically when the tariff changes. Added plan autosave: enable `plan.autosave` to automatically save approved plans to `/.omp/plans/` when plan mode completes (customize with `plan.autosaveDir`, which accepts `~`, absolute, and cwd-relative paths) ([#11599](https://github.com/can1357/oh-my-pi/pull/11599) by [@H4vC](https://github.com/H4vC)). Editor history can retain local draft snapshots with their paste expansions and host-owned attachment restoration, without writing them to persistent history ([#11524](https://github.com/can1357/oh-my-pi/pull/11524) by [@camjac251](https://github.com/camjac251)). Added an optional Vim-style modal editing layer to `Editor`, off unless `setVimMode(true)` is called: Insert, Normal, and Visual/Visual-Line with motions, count prefixes, and operators. `j`/`k` keep Vim's desired column, so passing over a shorter line does not collapse it, and `$` sticks to end-of-line. `p`/`P` paste from an internal register; yanks are surfaced to the host through `onYank` so it can route them to the system clipboard. Vim mode now exposes its chrome to hosts: `Editor.vimEnabled`, `Editor.vimPending` (the half-typed command, e.g. `2d`), and `Editor.vimSelectedLines` (Visual selection height). `onVimModeChange` additionally fires when the pending command or selection size changes, not only on mode switches. Vim mode now understands text objects: `iw`/`aw` (and `W`), quotes `i"`/`a'`/`` a` ``, bracket pairs `i(`/`a{`/`i[`/`a<` (nesting-aware and multi-line), and paragraphs `ip`/`ap`. They work under an operator (`diw`, `ca(`) and in Visual mode (`viw`), with counts (`d2aw`). Previously `i` after an operator fell through to Insert mode, so `diw` typed text instead of deleting a word. Vim mode's `c` operator now actually enters Insert mode (`cw`, `cip`, `c` in Visual); it also follows Vim's `cw`-acts-like-`ce` quirk and parks the cursor correctly when the changed range is empty (`ci"` between bare quotes). Added `Terminal.setCursorShape()` (DECSCUSR), restored to the terminal's configured shape on teardown and crash cleanup. Anthropic server-side compaction as a `remote` compaction backend: model lines the beta supports (`compat.supportsServerCompaction`, rule-owned in the catalog: Opus 4.6+, Sonnet 4.6+, Fable/Mythos 5) on the official endpoint, resolved the way the provider routes requests, plus Anthropic-compatible routes with `remoteCompaction.enabled`, compact by re-issuing the live turn's own request — same system prompt, tools, and history, so it reads the prompt cache the last turn wrote — with the `compact_20260112` edit paused after the summary and the harness summary prompt as `instructions`. The instructions name where the retained tail begins so the summary covers only the history the rebuilt context drops. The API's summary is stored as the entry text and as `preserveData.anthropicCompaction`, replayed natively on later Anthropic requests and read as plain text by every other provider; the retained tail comes from session entries as with a local summary. Contexts below 55k tokens (the API trigger floor plus margin) keep summarizing locally, and a response without a summary is a native failure, like the OpenAI lanes. An aborted compaction response is the abort (a cancellation, never a native failure) and an error response keeps its HTTP status, so auth and timeout classification match the OpenAI lanes; the block's opaque `encrypted_content` is persisted as `preserveData.anthropicCompaction.encryptedContent` and replayed verbatim. Anthropic server-side compaction (`compact-2026-01-12` beta): `anthropicCompaction` on `StreamOptions` sends the `compact_20260112` context-management edit, the streamed `compaction` block is surfaced as an `anthropicCompaction` provider payload, the `compaction` stop reason is a normal stop tagged in `stopDetails` (exempt from the empty-completion retry), and usage sums `usage.iterations` whenever a compaction iteration ran. A user-role compaction summary carrying that payload replays as a leading assistant `compaction` block — folded into the retained assistant turn when one follows — with the beta and a never-firing strategy attached automatically; other providers keep reading the summary text. Everything compaction-related is gated on the model line (`compat.supportsServerCompaction`, rule-owned in the catalog) and on the endpoint the request actually reaches (`supportsAnthropicCompaction`: the official API for the first-party provider, resolved through Foundry / `ANTHROPIC_BASE_URL` reroutes, or an explicit `remoteCompaction.enabled` opt-in), so a rerouted session or an older model line falls back to the text summary instead of sending a block the API rejects. Caller-owned clients are gated on their own endpoint (the client's `baseURL`, or an explicit `remoteCompaction.enabled` opt-in when it exposes none) and receive the compaction beta per request, like the effort and control betas. A block held by its originating assistant message — a caller that appends the compacting response itself — replays at the head of that turn. The block's opaque `encrypted_content` is captured from the stream, kept on the payload as `encryptedContent`, and replayed verbatim. A compacting turn is priced per sampling iteration (like a server-side fallback turn), so a long-context tier applies only to an iteration whose own prompt crosses the threshold, never to the summed totals. Added historical decimation prompt-cache breakpoints every 15 user turns on Anthropic requests, so long conversations retain stable cached prefixes during branching, rewinds, and session resume ([#11665](https://github.com/can1357/oh-my-pi/pull/11665) by [@camjac251](https://github.com/camjac251)). `supports-server-compaction` compat axis (`compat.supportsServerCompaction`): whether a model line accepts Anthropic server-side compaction (`compact-2026-01-12`). Class rules enable it for Opus 4.6+, Sonnet 4.6+, and Fable/Mythos 5 on every Anthropic-messages host; the default is `false`. Enable `tui.mouse` to focus live subagent cards and jump-list rows by clicking them, with a hover highlight on the target; native selection becomes Shift+drag while on ([#11737](https://github.com/can1357/oh-my-pi/pull/11737) by [@H4vC](https://github.com/H4vC)). The pinned `Subagents` block now lists every live agent, collapsed to a few rows with a click expander by default; `display.pinnedAgents` switches it to `full` or `off` ([#11737](https://github.com/can1357/oh-my-pi/pull/11737) by [@H4vC](https://github.com/H4vC)). The `remote` compaction method now covers Claude: Anthropic server-side compaction (`compact-2026-01-12` beta) runs behind the existing `compaction.methodOrder` / `compaction.remoteEnabled` gates for first-party Anthropic models, persists its plain-text summary with a native replay payload that later Anthropic turns send back as a `compaction` block, and falls through to the next configured method on failure like OpenAI server compaction. Added `Agent.getPendingToolResults()` for reconstructing live displays before buffered tool results are persisted ([#11868](https://github.com/can1357/oh-my-pi/pull/11868) by [@serverinspector](https://github.com/serverinspector)). Added opt-in host authorization and exact-once streamed child execution for discard-safe local reads. Charm Hyper accounts now report their remaining prepaid credit balance in `/usage` ([#11656](https://github.com/can1357/oh-my-pi/pull/11656) by [@oldschoola](https://github.com/oldschoola)). Added Charm Hyper as a built-in provider with API-key login, live model discovery, and per-model pricing, effort ladders, and limits read straight from its catalog ([#11656](https://github.com/can1357/oh-my-pi/pull/11656) by [@oldschoola](https://github.com/oldschoola)). Added default-off speculative execution for validated local reads, including reads projected from nested JavaScript and Python eval cells. `/usage` now shows prepaid credit balances (e.g. Charm Hyper's `100 credits left`) on the provider cards and account summaries instead of `no data` ([#11656](https://github.com/can1357/oh-my-pi/pull/11656) by [@oldschoola](https://github.com/oldschoola)). Retry fallback chains now support per-model reasoning efforts: a fallback entry may carry an explicit thinking suffix (`"default": ["openai/gpt-5-mini:low"]`), and pressing `t` on a fallback row in `/models` sets or clears it. Bare entries keep inheriting the failing turn's effort. ([#11842](https://github.com/can1357/oh-my-pi/pull/11842) by [@H4vC](https://github.com/H4vC)). Added `task.agentServiceTierOverrides` for sparse exact-name service-tier overrides on task/eval agents, so selected agents can use priority/Fast mode without accelerating every subagent ([#9668](https://github.com/can1357/oh-my-pi/pull/9668) by [@alphastorm](https://github.com/alphastorm)). Added session-local `/btw` history with persistent answers and follow-ups; bare `/btw` reopens history, Escape cancels running answers before closing, and new questions no longer replace an in-progress answer. Added `f follow up` in BTW history to continue a selected side conversation with an English input prompt, persistent multi-turn history, and no changes to the main conversation. Completed inline BTW answers now support `f follow up` directly; history uses `Tab` for pane navigation and `Enter` or `f` to start a follow-up. Codex web search now accepts valid email-only OAuth credentials without requiring or fabricating a `ChatGPT-Account-Id` header ([#11847](https://github.com/can1357/oh-my-pi/pull/11847) by [@nguyennguyenit](https://github.com/nguyennguyenit)). Sessions now stay alive when their working directory is removed instead of crashing while preparing shell tools ([#11828](https://github.com/can1357/oh-my-pi/issues/11828)). MCP tool calls spelled with the Claude Code doubled separator (`mcp__server__tool`) now reach their registered tool ([#11516](https://github.com/can1357/oh-my-pi/issues/11516) by [@oldschoola](https://github.com/oldschoola)). MCP HTTP reconnects now release obsolete tool generations instead of growing session memory on every reconnect ([#11784](https://github.com/can1357/oh-my-pi/issues/11784)). `/debug` memory reports now keep large heap snapshots out of JavaScript strings and reject empty snapshots instead of saving zero-byte files ([#11785](https://github.com/can1357/oh-my-pi/issues/11785)). Sloppy-mode edits now drop a copied `[N more lines in ...]` read notice the same way they already drop the other read-metadata rows, so a pasted projection can no longer leak into the matched pattern or the written text ([#11797](https://github.com/can1357/oh-my-pi/pull/11797) by [@vasyza](https://github.com/vasyza)). `/usage` now honors a provider's configured `baseUrl` when checking credentials before any model has been discovered, so a proxy-scoped API key is no longer sent to the provider's canonical host ([#11656](https://github.com/can1357/oh-my-pi/pull/11656) by [@oldschoola](https://github.com/oldschoola)). Added public `acquireFileLock()` and `FileLockHandle` APIs for holding and explicitly releasing exclusive OS-backed file locks. Added `collab.autoStart` (`off` | `view` | `control`): every local interactive session hosts itself as it starts and rotates its room on `/new`, `/resume`, fork, or branch, so a phone or dashboard can reach any running session without running `/collab` first ([#11908](https://github.com/can1357/oh-my-pi/pull/11908) by [@alphastorm](https://github.com/alphastorm) and [@sorphwer](https://github.com/sorphwer)). Added `omp collab list [--json]` and `/collab list` to enumerate every live local Collab host (instance, generation, session, cwd, model, participants, relay/attention state, access) without exposing links, plus `omp collab link [--view]` to fetch one generation-bound browser URL from a private per-room Unix socket/named pipe registry; room keys, write tokens, and URLs never touch disk ([#6099](https://github.com/can1357/oh-my-pi/issues/6099); [#11908](https://github.com/can1357/oh-my-pi/pull/11908) by [@alphastorm](https://github.com/alphastorm) and [@sorphwer](https://github.com/sorphwer)). Added `getBrowserProfilesDir()` (`~/.omp/browser-profiles`; XDG: `$XDG_STATE_HOME/omp/browser-profiles`) for profiles of Chromium browsers spawned by the browser tool. Enabled assistant prefill support for Ollama models Added a privacy warning to memory reports reminding users to review data for secrets before sharing `omp git` / `/git`: `delete` discards the selected file's changes (press twice to confirm) — in the sidebar on a file or whole directory, in the diff pane on the shown file; untracked files are removed, staged files reset to HEAD Assistant turns from Anthropic-compatible hosts (direct, or via OpenRouter's `reasoning_details`) carry `upstreamModel`, the serving model id recovered from the signed thinking block, so callers can detect a router substituting a different model than requested. Added support for DeepInfra, LiteLLM, Qwen Portal, SiliconFlow, and SiliconFlow-CN providers Added support for Gemini 3.8 Flash models Added `ollama` web search provider using Ollama's hosted web search API (`POST https://ollama.com/api/web_search`), authenticated via `OLLAMA_CLOUD_API_KEY` ([#3791](https://github.com/can1357/oh-my-pi/issues/3791)). Added `readUrl` support for Ollama model pages (`ollama.com/` and `ollama.com/library/`), extracting descriptions, tags, and architecture metadata. `@upstream` routing selectors accept tiered OpenRouter slugs (`openrouter/google/gemini-3.8-flash@google-ai-studio/priority`), and `omp bench` labels each routed model with its upstream. `/skill:` in the composer becomes an atomic skill chip (icon + name, linked to its SKILL.md) once you finish typing it or accept it from autocomplete — it deletes as one unit and survives draft restores, like image chips. The transcript now flags a gateway serving a different Claude model than requested: a `⚠ served claude-haiku-4-5-20251001 · requested claude-opus-5 · via openrouter/Amazon Bedrock` divider under the first affected turn, shown once per substitution per session. Added `Editor.textRevision` for content-dependent render caches, including undo and draft restoration. Added collapseToAtom method to compress text spans into UI-friendly atoms Added `relativePathWithinNormalizedRoot()` for reusing canonical paths across containment checks. Added `sleepLong()` and `MAX_TIMER_DELAY_MS`: an abortable sleep that chunks delays past the signed 32-bit timer ceiling so day-scale provider waits elapse instead of overflowing the timer. Added optional queued-message preparation with cancellation-safe delivery and appended context ([#11835](https://github.com/can1357/oh-my-pi/pull/11835) by [@andrebrait](https://github.com/andrebrait)). Added support for Cerebras Qwen 3.8-27b with improved reasoning effort control Added optional host browser-session callbacks for Perplexity SSO login, keeping browser automation out of pi-ai and preserving email and authenticator-code login. DeepSeek V4.1 Flash (`deepseek-flash`) now accepts image inputs and resolves its reasoning metadata, name, and effort ladder from upstream instead of shipping as a text-only row without them. Added keyless Parallel web search when the provider is explicitly selected ([#9770](https://github.com/can1357/oh-my-pi/pull/9770) by [@georgeatparallel](https://github.com/georgeatparallel)). Sloppy edits support `` to insert new lines after an anchor without repeating or replacing it. Fixed eligible full OpenAI Responses request-body timeouts by retrying once after conservative local tool-result elision, while preserving assistant/user history, unsafe partial output, and existing stateful retries ([#11878](https://github.com/can1357/oh-my-pi/pull/11878) by [@hellofrommorgan](https://github.com/hellofrommorgan)). User append instructions (`APPEND_SYSTEM.md`, `--append-system-prompt`) now render under their own `## User Instructions` heading whenever generated blocks precede them, instead of trailing the `## MCP Server Instructions` section and reading as server-supplied, unverified content ([#11832](https://github.com/can1357/oh-my-pi/pull/11832) by [@iacore](https://github.com/iacore)). Prewalk now arms for a hand-off target served by a `models.yml` `discovery:` provider (e.g. `openai-models-list`): `buildSessionOptions` runs a cache-aware refresh for the provider named by the selector and retries, instead of disabling prewalk with a `Model "…" not found` warning for ids `omp models` lists ([#11820](https://github.com/can1357/oh-my-pi/issues/11820)). Non-throwing tool failures now retain their error status through extension result rewrites and eval-defined subagent tools ([#11585](https://github.com/can1357/oh-my-pi/issues/11585)). Session rewrites now refuse to replace a file changed by another process, preserving durable turns from concurrent terminals ([#11496](https://github.com/can1357/oh-my-pi/issues/11496)). Goal mode now idles after repeated continuations return identical tool evidence instead of re-waking indefinitely ([#11819](https://github.com/can1357/oh-my-pi/issues/11819)). Cycling models with Ctrl+P no longer injects a spurious tool-roster notice that made the model believe still-callable tools had been removed; a prompt rebuild now discards the queued delta it already reflects ([#11824](https://github.com/can1357/oh-my-pi/issues/11824)). Subagent `yield` no longer fails a run with `SYSTEM WARNING: Subagent called yield with null data.` when a data-less `useLastTurn` finalize (e.g. `{type:"result"}`) lands on a thinking-only turn with no text; the tool now rejects it at the boundary so the child is reminded to resubmit with `data` ([#11150](https://github.com/can1357/oh-my-pi/issues/11150)). `--continue` no longer treats a merely-missing breadcrumb cwd as a project move. Re-root now requires the continue directory to be the same device+inode the breadcrumb recorded (`git worktree move` / same-filesystem `mv`). A cross-filesystem `mv` (copy+unlink, new inode) is intentionally not re-rooted: the session stays in the original bucket, `header.cwd` is not rewritten, and a warn is logged ([#11565](https://github.com/can1357/oh-my-pi/issues/11565)). Cold-revived persisted subagents now anchor wake-turn artifacts to their own transcript directory rather than the live root session's, so nested-depth and post-`/new` revivals no longer write `.md` outside the revived agent's tree ([#11563](https://github.com/can1357/oh-my-pi/issues/11563)). Legacy `settings.json` → `config.yml` migration now writes the YAML first and only then archives the JSON, surfaces failures instead of swallowing them, and recovers from an orphaned `settings.json.bak` when `config.yml` is missing ([#11569](https://github.com/can1357/oh-my-pi/issues/11569)). Legacy `settings.json` → `config.yml` migration now writes the YAML first and only then archives the JSON, and surfaces failures instead of swallowing them ([#11569](https://github.com/can1357/oh-my-pi/issues/11569)). MCP server names may now contain spaces, so human-friendly display labels like `MaaS Slack` survive `/mcp reauth` write-back instead of being rejected by the config writer ([#11731](https://github.com/can1357/oh-my-pi/issues/11731)). File paths in the compact grouped `Read (N)` tree are now clickable OSC 8 hyperlinks, matching standalone Read rows; delimited reads carry a resolved link target per row so both live output and rebuilt transcripts link correctly ([#11732](https://github.com/can1357/oh-my-pi/issues/11732)). Added server-name autocomplete for `/mcp` commands (`enable`, `disable`, `test`, `remove`, `reconnect`, `reauth`, `unauth`) using configured and runtime-discovered MCP servers. Added `CUT` and `PASTE` ops to the hashline edit tool for moving code without retyping it: `CUT N.=M` (and `.BLK` block forms) capture lines into a clipboard register, and `PASTE` operations insert them. The register flows across sections within a patch (cross-file moves) and persists across edit calls per session. Added `--from-claude` and `--from-codex` session imports (including compaction state for Codex), also available from `/resume @claude` and `/resume @codex`. Added interactive Exa API-key onboarding through `/login exa`, opening the official key dashboard and saving pasted keys for authenticated web search while preserving `EXA_API_KEY` and explicit-selection public MCP fallback behavior ([#1798](https://github.com/can1357/oh-my-pi/issues/1798)). Added `ExtensionContext.getAsyncJobSnapshot()` so extensions can read the owning session's async-job state without relying on process-global job-manager identity Added opt-in `tui.codexResetFireworks` celebrations for unscheduled Codex weekly usage resets and newly banked saved resets, shown in a theme-aware top-third modal until Escape ([#6858](https://github.com/can1357/oh-my-pi/pull/6858) by [@joshrzemien](https://github.com/joshrzemien)). The Cursor exec bridge serves the seven modern Pi tool frames, mapping each to its local equivalent: `pi_read`/`pi_ls` → `read`, `pi_bash` → `bash`, `pi_edit` → `edit`, `pi_write` → `write`, `pi_grep` → `grep`, and `pi_find` → `glob`. The frames are a separate wire family from the legacy args, not aliases, so each mapping is a real translation — `pi_grep`'s `ignore_case` is the inverse of the local tool's case-sensitivity flag, `pi_find` searches filenames rather than contents, and `pi_edit`'s replacements are renamed to the local snake_case pairs. `providers.autoThinkingMaxEffort` (`xhigh` | `max`, default `xhigh`) raises the ceiling of the `auto` thinking classifier. `max` became a first-class effort tier after the classifier prompt was written, so `auto` could never reach it on models that expose the tier — only the `ultrathink` keyword could. Opting in adds `max` to the classifier's vocabulary, gated on the target model actually supporting it; the default keeps today's prompt byte-for-byte. The ceiling is enforced inside the effort clamp rather than on the classifier's answer, so a sparse ladder cannot snap an excluded request back up, and the Low floor is still resolved against the model's own ladder. The on-device 3-bucket classifier stays capped at `xhigh` regardless of the setting. The ceiling governs what `auto` resolves: a ladder with nothing underneath it yields no auto level, and a `thinking.requiresEffort` model still gets its lowest supported effort from the transport. Added omp cleanse, a new command that automatically detects language-ecosystem checkers, parses diagnostics (such as Cargo Clippy JSON), distributes repair workloads across concurrent subagents, and runs verification checks with a live progress bar. Added the bundled `ts-no-local-is-record` TTSR rule, which catches local `isRecord` function and lambda definitions and directs agents to shared guards plus explicit shape validation. A `tool_call` handler (extension or hook) can now return `input` to revise the arguments a tool executes with, not just `block` it. The returned object is the raw execution input passed to the tool (ignored when `block` is set, and not applied to `computer` tool calls), enabling wrappers that normalize or rewrite a built-in's arguments without reimplementing the tool. For model-issued calls the event fires at arg-prep time in the agent loop, so a revision is revalidated against the tool schema and is what concurrency scheduling, `tool_execution_start`/transcripts, the persisted assistant message, and the approval gate all observe — the user approves exactly what runs, and a revision that changes a tool's functional concurrency (e.g. bash `pty`) schedules correctly. A revised nested `write xd://` device dispatch forfeits the outer write gate's approval and faces the full prompt again ([#6681](https://github.com/can1357/oh-my-pi/pull/6681) by [@psyrendust](https://github.com/psyrendust)). Added a parser for macOS `sample`(1) call-tree reports to the read tool: `*.sample.txt` reads now return a compact bottleneck summary — per-thread hot paths with on-CPU sample counts (blocked syscall time excluded), demangled Rust v0/legacy symbols, flattened direct recursion, merged call-site siblings, idle-thread classification, and a process-wide top-functions-by-self-samples table. `:raw` still reads the original report, and files that merely carry the extension fall back to plain text. Added V8 `.cpuprofile` support to the read tool (Node/Bun `--cpu-prof`, Chrome DevTools, CDP `Profiler.stop` output): reads now return a compact bottleneck summary — hot-path call tree with on-CPU milliseconds (`(idle)` time excluded), collapsed pass-through chains, flattened direct recursion, shortened file URLs, and a top-functions-by-self-time table. `:raw` still reads the original JSON, and files that merely carry the extension fall back to plain text. Added separate Advisor cost visibility to the status line, rendering primary and Advisor spend as `$2.67 (sub) + $0.41 (adv)` while keeping already-incurred Advisor cost across runtime disablement and same-session history rewrites. Added a configurable per-request timeout for the `inspect_image` tool (`inspect_image.timeoutMs`, default 5 minutes; set to 0 to disable) so a stalled vision-model provider fails fast with a clear error instead of blocking until manual abort ([#4165](https://github.com/can1357/oh-my-pi/issues/4165)). Added `maxBytes` to `VcsGitRepo.diffText` options: rendering stops and the call rejects with an `OutputTooLarge` VcsError once the patch crosses the cap, so callers can bound the memory a large change set may consume ([#11454](https://github.com/can1357/oh-my-pi/pull/11454) by [@sjawhar](https://github.com/sjawhar)). Native addon embedding now rejects stale release binaries before standalone builds can package them ([#11831](https://github.com/can1357/oh-my-pi/issues/11831)). Fixed git repository discovery treating an unpopulated `.git` directory (no `HEAD`) as a checkout, which made `/wt` and isolated tasks fail with a raw "No such file or directory (os error 2)" instead of reporting that no Git repository was found. Discovery now skips such entries and keeps walking toward the root, matching `git rev-parse`. Added `vcsDiscoverForDisplay` (`repoForDisplay`): like repository discovery, but equal-root jj+git ties prefer Jujutsu for the status line and footer. Git-safe automation must keep using `vcsDiscover` ([#11071](https://github.com/can1357/oh-my-pi/issues/11071), [#11325](https://github.com/can1357/oh-my-pi/pull/11325) by [@boazy](https://github.com/boazy)). Shell and PTY command output on Windows now falls back from UTF-8 to the system ANSI code page (e.g. GBK on Chinese locales) instead of emitting replacement characters. Added `trim()`, `superRefine()`, and one-argument `record()` support to the Zod compatibility facade ([#12011](https://github.com/can1357/oh-my-pi/pull/12011) by [@bnivanov](https://github.com/bnivanov)). `Editor.deleteCharForward()` exposes the `tui.editor.deleteCharForward` operation to hosts that resolve the chord themselves, applying the same transient-state teardown the key dispatch does (pending character jump, spelling-assist popup) and routing through Vim's `x` in Normal and Visual modes. Added the public `postmortem.exitProcess()` utility for host-owned hard exits that must bypass temporary process-exit guards ([#11789](https://github.com/can1357/oh-my-pi/issues/11789)). Added `readSseJsonOrText`: like `readSseJson`, but a `data:` frame that is not valid JSON is yielded as its raw text instead of raising a `SyntaxError`, so a consumer can classify a reverse proxy's plain-text throttle page (`429 Too Many Requests`) that arrives after the stream headers were already sent. `readSseJson` is unchanged and shares the framing with it. Added configurable `baseUrl` support for `bedrock-converse-stream` requests, enabling Amazon Bedrock providers and compatible custom providers to use VPC or PrivateLink endpoints, FIPS hosts, and internal gateways, including endpoints mounted under a path or authenticated with query parameters. OpenAI-compatible model discovery now fills in reasoning-effort tiers for unrecognized models using the shared catalog’s published reasoning options, while preserving explicit discovery metadata and reviewed model rules. Expanded built-in secret obfuscation to detect credentials in connection URLs regardless of environment-variable name, including PostgreSQL, MongoDB, MySQL, Redis, AMQP, and other supported schemes. Expanded built-in secret obfuscation to cover AWS access keys, Google API keys, Slack, npm, Stripe secret/restricted keys and webhook secrets, Hugging Face and SendGrid tokens, JWTs, Bearer tokens, and PEM private keys. Added the `tui.titleSpinner` setting to choose the terminal-title working-state animation (`braille`, `dots`, `line`, or `pulse`), alongside the existing `tui.titleState` toggle. Added asynchronous and synchronous SQLite database opening APIs with path-attributed errors, optional corruption recovery that preserves private database and sidecar backups, and automatic retries for transient busy errors during asynchronous opens. `stream()` and `streamSimple()` support asynchronous model header resolution for each request attempt, including authentication retries and cancellation. Provider login prompts can request masked entry with `secret: true`. Models can carry deferred request-header resolvers, and model managers can reconstruct omitted cached headers from authoritative local configuration without persisting credentials. Type `^` to tag a model for delegation, with atomic display-name chips and session-persisted `m1`, `m2`, … agents available to task and eval. Provider login and setup support masked secret prompts; RPC rejects secret prompts rather than requesting ordinary input. Editors support whitespace-delimited `^` mention autocomplete and expose registered atoms for host-defined chip rendering. Added the `judgment` module for typed questions over JSON state, including choice, yes/no, and score judgments through the `Judge` interface. Added `TypeSafeJudge` support with TypeSafe System One authentication, credential rotation on unauthorized responses, and retry-aware backoff. Added `TextJudge` and `chatTextBackend` for model-based judgments, with structured state rendering and safeguards that prevent embedded requests from being executed. Added automatic format-correction retries to `TextJudge` when models return malformed output. Added the `guardState` option to `TextBackend` to control whether safety guidance is included in prompts. Added `typesafe` authentication for TypeSafe System One judgments via the `TYPESAFE_API_KEY` configuration and API-key validation against the TypeSafe models endpoint. Added an optional live generation speed readout via `composer.tokenRate`, showing smoothed tokens-per-second output in the working row and keeping the rate visible between turns. Added TypeSafe provider support through `/login typesafe` or `TYPESAFE_API_KEY`. TypeSafe can power thinking-level detection, unexpected-stop detection, and AI-assisted git staging with calibrated judgment probabilities; configure `providers.judgmentProvider` as `auto`, `typesafe`, or `llm` to select the judgment backend. Added the `judge(state, questions)` evaluation helper for Python and JavaScript cell code, supporting typed choice, boolean, and score judgments. It returns a handle whose `.wait()` method provides answers and probabilities, using TypeSafe when configured and available or a fallback chat model otherwise. Added support for templating and custom base and authentication URLs in OAuth flows. Added the `stencil` authentication provider for `omp stream`, supporting OAuth code + PKCE sign-in with `auth.stencil.so`, configurable via `STENCIL_API_KEY`, `STENCIL_AUTH_URL`, and `STENCIL_BASE_URL`. This is an authentication-only provider, not a model provider; OAuth-code login configuration also supports `base-url` and `auth-url` nodes with `{base}` and `{auth}` URL placeholders. Added `omp stream` for livestreaming terminal sessions at `live.omp.sh/`, with viewer chat, pane-per-session display for sessions in the same directory, screen redaction, and configurable `stream.serverUrl` and `stream.redactPatterns` settings. Use `--server` to override the stream server, `--title` to set a title, and `--no-tui` to retain the line-based log interface. Added Stencil account support to `/login`. `omp stream` uses a signed-in Stencil account or `STENCIL_API_KEY` for channel ownership and authentication. Sensitive environment, dotenv, `secrets.yml`, credential-shaped, and configured pattern-matching values are redacted before screen data is transmitted. Added faster keyless web search fallback by prioritizing the default keyless Parallel provider ahead of Perplexity. Added the full coding-agent terminal UI to the package, including themed rendering primitives, shared chrome, tool renderers, chat transcripts, overlays and hubs, status lines, prompt and autocomplete controls, setup flows, and standalone utilities such as the Git TUI, process viewer, debug viewers, boards, and pickers. Added reusable terminal UI components for forms, menus, split layouts, disclosures, tree views, tool cards, data widgets, fullscreen hubs, scrollable overlay navigation, and interactive footer chips. Added live viewer counts to the status line and exposed paint observers through `TUIOptions.onPaint` and `TUI.setPaintListener` for hosts that need to track committed scrollback and viewport rows. Added details and notes fields to todo items, plus an interactive task-list renderer for managing subtasks. Added inline summaries for structured task outputs. Added image input validation with automatic conversion of unsupported formats and support for video previews in chat. Added the MCP Add Wizard for streamlined server configuration. Added an `autoresearch` tool renderer for tracking experiments. Added side-by-side diff rendering for merge conflicts and improved presentation of GitHub Actions workflow jobs and runs. Added the `dark-celestial` built-in theme with a twilight palette and pink, coral, purple, cyan, and peach accents. Added utilities for reading dotenv-sourced environment values, customizing filtered child-shell environment values, converting color palettes to RGB, cleaning trailing spaces from YAML block headers, and counting newlines in text. Added the `omp stream` wire contract (`@oh-my-pi/pi-wire/stream`) for pane screen updates, viewer snapshots and chat, channel metadata, and `live.omp.sh` stream routes. Added authentication support for stencil.so streams, including user identity in welcome messages, channel ownership metadata, and explicit unauthorized and forbidden close codes. Added model-kind and grounded-search capability metadata, along with catalogs for local inference and search-engine models. Added OpenRouter image-model discovery and live TypeSafe judge-model discovery. Added the `buildDiscoveredModel` helper for defining custom providers. Added glob-based patterns for identity overrides. Added `find` tool for semantic workspace searching, allowing agents to locate behaviors and symbols using natural language Added `find` CLI command for performing semantic workspace searches Added batch evaluation with judge_batch(states, questions) / judgeBatch(...), including bounded background execution, incremental result and status access, per-item failure reporting, and the ability to wait for or reattach to jobs across turns or after a reset. Added the jevify magic keyword to have the agent establish an evaluation rubric before classifying bulk items and inspect only items flagged by the judge. Added omp web-search as an alias for omp search. Added tui.titleSpinner configuration to select the terminal-title working-state spinner (braille, dots, or line). Added Handlebars-based system prompt templates through SYSTEM_TEMPLATE.md, --system-prompt-template, and the SDK, with access to live settings and tool data. Added configurable image, web, speech, dictation, judge, and memory model roles with ordered fallbacks, legacy backend-setting migration, and omp models --kind filtering. Added native OpenRouter image generation, model-selected web-plugin search, and live discovery of TypeSafe judge models. Added `renderMermaidAscii`, a native Mermaid-to-ASCII/Unicode renderer supporting flowcharts, state, sequence, class, ER, and xychart diagrams with color modes, themes, and direction overrides. Added a `default` package export condition so CommonJS consumers, including bytecode bundles, can load the native bindings. Added `find` tool renderer to display search results with hit ranking and score visualization Supported collapsing/expanding search hit details and range snippets Enabled file hyperlinking for navigation to absolute paths in search results Added streaming progress display for incomplete find tool operations Added Glyph Protocol support for rendering icons without requiring patched fonts Added `setMagicKeywords` for dynamic configuration of highlightable magic keywords Added support for text embeddings, document reranking, video generation, image generation across multiple providers, audio speech synthesis, and audio transcription services. Added support for the System One judgment API, including configurable request headers for proxy routing and custom authentication. Expanded OpenRouter provider support with embedding, reranking, video generation, text-to-speech, and speech-to-text capabilities, including five new speech-to-text models. Added speech-to-text support to the OpenAI provider. Added comprehensive browser automation tools for accessibility auditing, React inspection, console and network monitoring, performance tracing, semantic DOM queries, tab management, screen recording with cursor overlays, downloads, custom initialization scripts, persistent storage, and WebMCP cross-frame tool discovery. Added support for buffered cloud transcription with OpenAI-compatible models. Added visual change detection for video processing, including FFMPEG analysis and SVG overlays. Added support for declaring native judges through custom providers using the `typesafe` and `openrouter-decisions` API values, with configurable base URLs, API keys, and headers. Added Claude saved-reset discovery and redemption, including session-only resets, grant eligibility, expiry, and safe retry handling. Added live benchmark results table with real-time model ranking and per-kind performance metrics Added dedicated prefill throughput reporting for prefill-focused benchmarks Added `/record` slash command to capture terminal sessions as replayable `.ompcast` files Added `omp play` CLI for terminal-based playback of session recordings Added intent descriptions to judgment batching Added live progress tracking for judgment batches in the TUI Added Claude saved resets to usage views and `/usage reset`, with automatic blocked-limit recovery and expiring-reset redemption controlled by `claudeResets`. Added support for searching embedded harness documentation with `find` and `omp find` using `omp://` scopes, including file-specific searches and `:start-end` selectors; results open directly through canonical `omp://` URLs. Added Claude and Codex saved-reset counts, availability, and expiry to usage views, with provider-specific confirmation and uniquely identified account options. Added terminal detection and capability support for otty and rio, including Kitty graphics and true-color support where available, plus otty hyperlinks and notifications. Added the public `stripTerminalSequences` export for extensions that need to remove terminal control sequences. Added built-in StepFun provider support for the step-5-preview model, including live model discovery. Added a Skills section to the settings. Enabled OSC 8 hyperlinks in rio. Added public API contract and authentication schemas for the Skillshare registry. Added support for documenting agent tools on demand through the new `AgentTool.docTopics` method. Added `TOOL_INTERRUPT_ABORT_REASON` so interruptible tools can distinguish queued steering, peer messages, or background completions from a full run abort. Added support for Anthropic User Profiles, including schema-validated API responses. Added support for Apple Foundation Models running on-device, including tool calling and vision capabilities. Added multi-account authentication and authorization for Codex cyber access programs, including automatic request replay after access-program rejections. Added credential-aware authentication routing with per-account OAuth policies, deterministic account selection, protected quota reserves, persistent rate-limit tracking, automatic recovery, and sticky session-to-credential affinity. Added deprecated `getApiKey` and `reload` methods for backward compatibility. Added compaction support for the `claude-mythos-preview` model. Added provider and authentication rule definitions for on-device Apple Foundation Models. Added per-account discovery of Codex cyber access entitlements. Added `org-scoped-identity` and `oauth-token-env` authentication rules for providers. Added `omp://` documentation scopes for `find` and `omp find`. Search all embedded harness documentation with `omp://` or a specific document with `omp://.md`; results are returned as canonical URLs that `read` can open, including range selectors. Added extension support for ephemeral, `/btw`-style side turns through `ctx.runEphemeralTurn()`, with optional tool suppression and output/context limits without adding the turn to session history. Added background job and service management through the `wait` tool and `proc://` URLs, including supervised services in `bash` and direct agent messaging through `agent://` write targets. Added `*** Insert Before` and `*** Insert After` edit operations for adding lines without replacing existing code. Added the `toks` command for offline token counting, including support for Jev (TypeSafe Jev 1.13) encodings. Added automatic discovery of Apple Foundation Models on supported Apple silicon devices. Added `/changelog last [N]` for viewing the latest release or a selected number of recent releases. Added terminal-based OAuth authentication with `omp login`, including browser-assisted login, account and organization details, and automatic model discovery refresh. Added provider support for `org-scoped-identity`, `oauth-token-env`, and per-account OAuth priority/reserve policies through `auth.accountPolicies`, with policy state shown by `omp usage`. Added the `daybreak` badge to `omp usage` for enabled accounts. Added `/export` and `/usage` to focused subagent views for exporting a focused transcript and viewing account usage without returning to the main session. Pasted clipboard images are now saved in the session artifact directory, allowing agents to read, copy, or upload them by file path. Added `/annotate` for attaching notes to diffs, replies, session messages, files, or quoted text and inserting or sending those notes in prompts and reviews. Added configurable MCP startup behavior through `MCP_STARTUP_TIMEOUT_MS`/`mcp.startupTimeoutMs` and `OMP_MCP_REQUIRE_READY=1`, allowing headless runs to require MCP servers to become ready before the first turn. Added native judgment usage reporting, including error stop reasons and messages, and added `openrouter/~typesafe/jev-latest` as a native judge candidate. Added support for rendering coordinated job and messaging views through the `wait` tool. Added native bindings for Apple Foundation Models availability checks, text generation, and cancellation. Added offline token counting support for TypeSafe Jev 1.13 `state` inputs via `Encoding.Jev` (excluding the request frame). Added proc:// and agent:// URI support for interacting with processes and agents. Added support for xd:// documentation topic URLs. Added rendering for background job state and peer-to-peer messages from the wait tool. Added supervised bash service rendering with status, readiness, and output information. Added a fullscreen annotation overlay for diffs and text, including multi-line notes, editing, deletion, and undo ([#12601](https://github.com/can1357/oh-my-pi/pull/12601) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added Daybreak-enabled account listings to the usage dashboard. Added live steering support for Codex WebSocket transports, allowing users to provide input while a response is in progress. Added passive tool-call context support, allowing hooks and tools to supply additional context for subsequent model processing. Improved context-window handling by automatically adjusting output-token limits and supporting models that truncate output at the context-window limit. Added live steering support for GPT-6 models, allowing queued user messages to be delivered during an active streaming response. Added the `anthropicSlowMode` stream option for first-party Claude OAuth requests, enabling slow-mode rate-limit handling, per-account rate-limit reporting, and server-paced retries during capacity limits. Added support for capturing and redeeming Anthropic fallback credit tokens, including prompt-cache repricing for classifier refusals. Added Vercel AI Gateway app attribution by sending `http-referer: https://omp.sh/` and `x-title: omp` by default; user-provided header values take precedence. Added compatibility flags for models that stop output at the context-window limit and models that support steering, including defaults for Claude 4.5+ and GPT-6+ models. Added native filesystem support for `local://` and `omp://` URLs across file-search, content-search, AST, shell, and related tools, including support for virtual working directories. Added a native `cp` builtin for filesystem copy operations. Added IDA Pro integration for opening executables and IDA databases, browsing pseudocode, assembly, imports, exports, strings, and cross-references, and performing database-aware actions such as renaming, commenting, type editing, function creation, saving, and persistent Python execution. Added shared, project-scoped IDA database access with broker-managed host processes, configurable concurrency and idle cleanup via `ida.maxOpen` and `ida.idleCloseSec`, automatic autosaving, and universal Mach-O architecture selection with `:@` syntax and host-architecture detection. IDA features can be configured with `ida.enabled`, `ida.python`, and `ida.installDir`. Added the `/slow [on|off|status]` command for opting into lower-priority service tiers on OpenAI, Google, and Anthropic subscription sessions, including automatic continuation when Anthropic session limits are reached. Added the `providers.openaiLiveSteering` setting to control whether input can be delivered while a response is in progress. Added session-wide approval for configuration changes through an `Always for this session` option in `cfg://` prompts, with clear timeout handling for unanswered prompts. Added the `cfg://` protocol and a configuration registry for reading, modifying, unsetting, and reactively managing layered agent settings with approval and precedence feedback. Added paged reading for large files, with metadata that allows clients to recover and continue displaying results. Added per-agent compaction thresholds for task and evaluation subagents, configurable as percentages or fixed token limits without changing the main session threshold. Added trusted additional context for extension and hook tool results, including `ctx.addAdditionalContext()`, allowing instructions to reach the model without altering displayed tool results. Added dictation support to `/btw` follow-up input. Added support for multiple simultaneous browser instances, including concurrent Chrome and Edge connections. Added detailed benchmark phases for measuring single-user throughput, parallel scaling, and prefill performance, with automatic prefill sizing based on model context limits. Added opt-in CUDA support to the Nix package for tiny-model inference through ONNX Runtime. Added reliable RPC prompt lifecycle reporting with `prompt_result`, structured provider errors, session-settled state, prompt identifiers, event filtering, and `--no-ui` support for non-interactive hosts. Added RPC session management through `open_session`, plus corresponding TypeScript and Python client APIs including `openSession`, `setEventFilter`, `onPromptResult`, `onSessionSettled`, and `waitForSettled`. Added `attachment://` and `conflict://` resource URL handlers. Added a per-server MCP `instructions: false` option to keep a server's guidance out of the system prompt while retaining its tools. Added support for asynchronous file I/O and custom filesystem providers in native shell execution, including resolving arbitrary `scheme://` paths through native operation options. Added push-to-talk dictation to `Input`, with live transcription and `cursorOverride` support. Added visual indicators for live-steered user messages and paginated content in read-tool results. Added transcript support for `cfg://` configuration read and write tool calls. Added an Anthropic slow-mode badge to the status-line model segment, showing the priority state, end time, and remaining request percentage when available. Added `ctx.agent` to the extension context, reporting whether the session is the top-level agent or a subagent, plus its registry id, agent definition name, task depth and parent id, so handlers rebound to subagent sessions can tell which agent they serve ([#13314](https://github.com/can1357/oh-my-pi/pull/13314) by [@andrebrait](https://github.com/andrebrait)) Added tracking of Anthropic's usage-limit wrap-up allowance for Claude subscription accounts: after the 5-hour or weekly limit is reached, the status line and `/slow status` show `limit reached · wrapping up · resets HH:MM`, and the agent is told to wrap up when neither low priority nor extra usage will continue the work ([#13340](https://github.com/can1357/oh-my-pi/pull/13340) by [@H4vC](https://github.com/H4vC)) Added live steering support, allowing models to receive and act on user steering messages during an active stream. 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. Added a `TextPredictor` N-API binding for managing the high-performance ghost-text completion engine. 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. Added the `openai` web-search grounding for OpenAI API models that support Responses web search (`gpt-5.5`, `gpt-5.6-luna`, `gpt-6-astra`, `gpt-6-luna`) ([#13467](https://github.com/can1357/oh-my-pi/pull/13467) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added `Model.promptCache`, per-retention-tier prompt-cache entry lifetimes in seconds (`short` / `long`), declared per provider through the `prompt-cache` KDL rule (bundled: direct Anthropic, 5 min / 1 h). Custom models and `modelOverrides` opt in with the models.yml `promptCache` key ([#12699](https://github.com/can1357/oh-my-pi/pull/12699) by [@KamijoToma](https://github.com/KamijoToma)). Added API-key-billed OpenAI Responses web search (`openai/gpt-6-luna`, then `openai/gpt-5.6-luna`), tried after every Codex entry in the default search fallback chain so ChatGPT-subscription search is exhausted before any API usage is billed ([#13467](https://github.com/can1357/oh-my-pi/pull/13467) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added prompt-cache warming, ported from [earendil-works/pi](https://github.com/earendil-works/pi): shortly before a prompt-cache entry expires, the main agent loop replays its last request and cuts the replay off at the first generated token, so idle gaps no longer force a full-prefix cache re-write. A refresh fires only when the expected avoided-miss cost clears its cost by $0.05, and warming stops as soon as a refresh misses the cache. Controlled by `providers.cacheWarming` (`off` / `streaming` / `idle`, default `idle`); idle warming covers 5-minute entries only, and models without a declared `promptCache` lifetime are never warmed. Extensions can override each decision through the `cache_warming_decision` event ([#12699](https://github.com/can1357/oh-my-pi/pull/12699) by [@KamijoToma](https://github.com/KamijoToma)). Added an "OpenAI API" option to the setup wizard's web-search step; the existing ChatGPT-OAuth option is now labeled "OpenAI Codex" ([#13467](https://github.com/can1357/oh-my-pi/pull/13467) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added image metadata to hosted OpenAI image-generation results, including the model used and each generated image’s dimensions and quality. Added the `telemetry.otlpExportEnabled` setting under Settings → Providers → Privacy to disable OTLP trace, log, and metric export even when `OTEL_*` endpoints are configured; exporting remains enabled by default. Added a first-launch warning when Python evaluation is enabled but no working Python interpreter is available, with guidance for configuring `python.interpreter` and checking the installation with `omp setup python --check`. Added Windows path utilities for converting between long and 8.3 short path spellings without resolving symlinks or junctions. Import them from `@oh-my-pi/pi-natives/path`. Added `resolveCatalogAxes` to `compat/resolve`, which resolves a model's catalog-axis policy without computing its full compat and thinking policy; context-window and catalog-policy lookups now use it, reducing model-catalog load time. Added tool_execution_end events that fire as each tool call settles for live UI updates The shell's `cp` builtin accepts macOS's `-c` (clone where possible, else copy; same as `--reflink=auto`). Added `summarizeCodeAsync` for non-blocking source structure summarization on the libuv thread pool Added cloneJsonTree to provide a high-performance deep copy utility for JSON-shaped object trees Added `transformAssistantMessagePreservesToolCalls`, letting stream speculation and direct speculative candidates run under a `transformAssistantMessage` that never rewrites streamed tool calls Added `authorizeLaunch` to the speculative execution host and coordinator so tool stream sessions can start host-approved effectful work (e.g. subagents) before their call dispatches Added Command Code usage limits (5-hour, weekly, and credit balance) to /usage and the status line ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty)) Added Command Code's typesafe/jev decision model for the judge role ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty)) Added Command Code's DeepSeek V4.1 Flash Fast model ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty)) Added Command Code's Claude Sonnet 5.5 model ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty)) Added `trust-forbidden=#true` for optional login `validate` checks, so a key check that answers 403 keeps the pasted key instead of rejecting it ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty)) `hosted-image #false` and `image-model #false` now remove a hosted image flag or image model that a class rule grants ([#13666](https://github.com/can1357/oh-my-pi/pull/13666) by [@riicodespretty](https://github.com/riicodespretty)) Added support for Claude Sonnet 5.5 model with image and text inputs Added new compatibility rules for Anthropic Sonnet family enabling mid‑conversation system features and disabling forced tool choice Added the `web-search-model`, `hosted-image`, and `image-model` catalog axes (`Model.webSearchModel`, `hostedImage`, `imageModel`). `web-search` now comes from the model's lineage and API (GPT-5+ Responses, Claude 4+ Messages, Gemini 2+), so proxies and gateways that expose these models inherit it. Batch `task` calls now start each subagent as soon as its `tasks[]` item finishes streaming instead of waiting for the whole call; launched agents are aborted if the finished call is invalid, blocked, or changed. Controlled by `task.speculativeLaunch` (default on; requires auto-allowed task approval and no extension tool lifecycle handlers) Set `PI_SMART_GIT=1` to have every `git worktree add` in the bash tool — including inside compound commands, functions, and loops — copy-on-write clone the checkout (APFS, btrfs/XFS reflink, ReFS) instead of checking out every file, so new worktrees start with ignored build caches (`target/`, `node_modules/`) already in place; every `worktree add` option except `--orphan`, `--no-checkout`, `--track`, and `--relative-paths` is handled, and anything else still runs real git. Added an optional `onDone` callback to `readSseJsonOrText` that reports the `[DONE]` sentinel without attaching a raw-event observer ([#13650](https://github.com/can1357/oh-my-pi/pull/13650) by [@H4vC](https://github.com/H4vC)). Added `Agent.replaceQueue()` to replace one pending queue without changing the other queue ([#11872](https://github.com/can1357/oh-my-pi/pull/11872) by [@andrebrait](https://github.com/andrebrait)). Added queued-message grouping so owned companion records and their user prompt are dequeued together in `one-at-a-time` mode ([#11872](https://github.com/can1357/oh-my-pi/pull/11872) by [@andrebrait](https://github.com/andrebrait)). Added `Agent.onQueueChange()`, a listener called whenever a steering/follow-up queue mutator (enqueue, dequeue on delivery, clear, or restore) runs, so hosts can observe queue changes without polling ([#11872](https://github.com/can1357/oh-my-pi/pull/11872) by [@andrebrait](https://github.com/andrebrait)). Added the `ultrafast` service tier. It is sent to the OpenAI API as-is, and to Codex only for models that list it in their discovered service tiers; other providers never receive it. On Codex websockets, switching into or out of `ultrafast` starts a new response chain instead of reusing `previous_response_id`, matching the Codex CLI. Ultrafast turns are costed at standard rates because no Ultrafast price is published yet ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)). Added `compat.bedrockMessagesApi` for `anthropic-messages` models: detected from a Bedrock `/anthropic` base URL under any provider id, it drops tool `strict`, fits `metadata.user_id` to Bedrock's pattern, and enables on-demand compaction; set it in `models.yml` to opt a proxy or an `ANTHROPIC_BASE_URL` reroute in, or `false` to opt out ([#13311](https://github.com/can1357/oh-my-pi/pull/13311)). Added GPT-6.1 Sol pricing for `openai-codex` (`gpt-6.1-sol`, `gpt-6.1-sol-wm`: $2 input, $10 output, $0.10 cached input), so Codex usage shows cost instead of $0 ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)). Added `Model.serviceTiers`, the service tiers a provider advertises for a model; Codex discovery fills it from `service_tiers` (e.g. `priority`, `ultrafast`) ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)). Added the documented 922K input maximum for `openai-codex/gpt-6.1-sol` with extended context on (Codex reports a stale 872K), matching GPT-6 Astra; the default window stays 272K ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)). Added `compat.bedrockMessagesApi` to `models.yml`, so Claude reached through a proxy or an `ANTHROPIC_BASE_URL` reroute to Bedrock's `/anthropic` API gets Bedrock request shaping and on-demand compaction; `false` opts a Bedrock URL out ([#13311](https://github.com/can1357/oh-my-pi/pull/13311)). Submitting exactly `exit`, `quit`, or `q` (any case, no leading `/`, nothing else in the input) in a session with no messages now quits; turn off with `input.bareExitOnEmptySession` ([#13755](https://github.com/can1357/oh-my-pi/pull/13755) by [@H4vC](https://github.com/H4vC)) Added the opt-in `input.bareSlashCommands` setting (Interaction > Input): submitting exactly a command name without the leading `/` (e.g. `model`, `compact`, a skill or extension command) runs that slash command. Before the first message it runs at once; after that, the first Enter asks for confirmation and a second Enter runs it (a leading space sends the word as a message) ([#13780](https://github.com/can1357/oh-my-pi/pull/13780) by [@H4vC](https://github.com/H4vC)) Extensions can now rewrite finalized assistant-message text through the awaited `assistant_message` hook before it reaches context, history, and `message_end` ([#13769](https://github.com/can1357/oh-my-pi/pull/13769) by [@NaC-L](https://github.com/nac-l)) In Tern (`TERM_PROGRAM=tern`), omp reports its session file to the terminal (OSC 1337 user variable `omp_session_file`) at start and whenever the session changes, so an agent pane Tern's daemon restores after a crash or restart resumes the same session with `--resume` Added `additionalContext` to extension and hook `tool_result` results, so success- and failure-specific post-tool guidance reaches the model through the trusted developer channel instead of altering tool output ([#13267](https://github.com/can1357/oh-my-pi/pull/13267) by [@andrebrait](https://github.com/andrebrait)). The `ask` tool's custom-answer and note prompts accept pasted images, which reach the model with the answer ([#13774](https://github.com/can1357/oh-my-pi/pull/13774) by [@DrFaustus-vic](https://github.com/DrFaustus-vic)) Added `/fast ultra` to select OpenAI's Ultrafast service tier on models that offer it (OpenAI API with preview access, or Codex models that advertise it, such as GPT-6.1 Sol once Ultrafast rolls out); `/fast off` clears it and `/fast status` reports `ultra`. `ultrafast` is also accepted by `tier.openai`, `tier.subagent`, `tier.advisor`, and `--service-tier` ([#13782](https://github.com/can1357/oh-my-pi/pull/13782) by [@H4vC](https://github.com/H4vC)). RPC clients can now cancel one pending steering or follow-up message with `remove_queued_message`, including its hidden attachment context, without aborting the turn or changing other queued work ([#11872](https://github.com/can1357/oh-my-pi/pull/11872) by [@andrebrait](https://github.com/andrebrait)). Added typed queued-message removal to the official Python RPC client, including validated success and refusal results ([#11872](https://github.com/can1357/oh-my-pi/pull/11872) by [@andrebrait](https://github.com/andrebrait)). RPC clients can now render the actual pending-message queue instead of tracking it themselves: `get_state` reports a `queuedMessages` snapshot and a new `queue_update` event reports it live as steering/follow-up messages are queued, delivered, removed, or cleared ([#11872](https://github.com/can1357/oh-my-pi/pull/11872) by [@andrebrait](https://github.com/andrebrait)). Added per-instance `polyphonicRecall` and `enhancedRecall` options to `Mnemopi` and `BeamMemory`, so memories opened side by side can use different recall policies; `configureRecallFeatures` remains the process-wide default and the env vars still win Added the `printStatsSummary` export, shared by `omp-stats --sync` and `omp stats --summary`. Added Tern Surface Protocol (TSP) integration for native terminal rendering Redesigned transcript, chat, dashboard, and picker UI components for native wire representation `HookEditorComponent` accepts pasted images when constructed with `acceptImages`; the ask dialog returns them as `customInputImages` / `noteImages` ([#13774](https://github.com/can1357/oh-my-pi/pull/13774) by [@DrFaustus-vic](https://github.com/DrFaustus-vic)) Added `formatFileMatches` and `FileMatchSection` to `tools/grouped-file-output` for rendering per-file grep/ast-grep matches in grouped or flat mode. Added `normalizePremiumRequests` (also still exported from `@oh-my-pi/pi-tui`). Added the Tern Surface Protocol wire contract (`@oh-my-pi/pi-wire`): message framing constants, the component vocabulary, document ops, frames, the handshake and terminal events that let omp render natively in terminals that speak it Added Factory Droid OAuth, HTTP streaming across Anthropic, OpenAI and Gemini protocols, and pool-aware usage reporting ([#8577](https://github.com/can1357/oh-my-pi/pull/8577) by [@will-bogusz](https://github.com/will-bogusz), continued in [#13276](https://github.com/can1357/oh-my-pi/pull/13276) by [@DusKing1](https://github.com/DusKing1)). `AuthStorage.keys.setConfig(provider, value, { fallback: true })` registers a key that is used only when no stored OAuth or `/login` credential exists, instead of overriding them; `removeConfig`/`clearConfig` also clear these fallbacks ([#13815](https://github.com/can1357/oh-my-pi/pull/13815) by [@H4vC](https://github.com/H4vC)) Cursor turns now fall back to Cursor's HTTP/1 streaming transport when HTTP/2 is unavailable, surface Cursor's structured service errors, and resume from the last safe server checkpoint after a dropped stream ([#11613](https://github.com/can1357/oh-my-pi/pull/11613) by [@will-bogusz](https://github.com/will-bogusz)). Added the hand-maintained Factory Droid catalog with account policy and regional discovery, upstream-specific reasoning controls, and base credit rates ([#8577](https://github.com/can1357/oh-my-pi/pull/8577) by [@will-bogusz](https://github.com/will-bogusz), continued in [#13276](https://github.com/can1357/oh-my-pi/pull/13276) by [@DusKing1](https://github.com/DusKing1)). Added Factory Droid login and model selection with base credit badges and account-matched regional discovery ([#8577](https://github.com/can1357/oh-my-pi/pull/8577) by [@will-bogusz](https://github.com/will-bogusz), continued in [#13276](https://github.com/can1357/oh-my-pi/pull/13276) by [@DusKing1](https://github.com/DusKing1)). Added `HELMCODE_API_KEY` to the environment variables listed in `omp --help` ([#13630](https://github.com/can1357/oh-my-pi/pull/13630) by [@alexcerezo](https://github.com/alexcerezo)). RPC hosts can send `messageUpdates: "delta"` with `set_event_filter` to receive `message_update` frames without the accumulated message snapshots (`message` shrinks to `{ role }` and `assistantMessageEvent.partial` is omitted); the response echoes the active mode ([#13716](https://github.com/can1357/oh-my-pi/pull/13716) by [@alphastorm](https://github.com/alphastorm)) RPC hosts can follow each cache-warming refresh through `cache_warming_start` and `cache_warming_end` events (also written by `--mode json`), which report the outcome and the recorded usage, and can set the session's warming mode with `set_cache_warming` without changing `config.yml`; the Python client gains `set_cache_warming()` ([#13717](https://github.com/can1357/oh-my-pi/pull/13717) by [@alphastorm](https://github.com/alphastorm)) The `/review` and `/annotate code-review` menus have a "Review a specific PR" option that lists the repository's open pull requests, with server-side search and a `#123` shortcut ([#12399](https://github.com/can1357/oh-my-pi/pull/12399) by [@abilliontokens](https://github.com/abilliontokens)) Pinned Subagents rows can show each agent's current (or most recent) tool call with a one-line detail and an elapsed marker; enable with `display.subagentLivePreview` (off by default) ([#3821](https://github.com/can1357/oh-my-pi/pull/3821) by [@abilliontokens](https://github.com/abilliontokens)) Model presets: save every role assignment plus the default thinking level under a name and switch between them with `/modelpreset save|switch|delete|list`, pick one interactively with `/modelpreset`, or press `s` in the `/models` Roles view to save the current setup ([#5253](https://github.com/can1357/oh-my-pi/pull/5253) by [@abilliontokens](https://github.com/abilliontokens)) Subagent tool previews name the files a freeform edit (`apply_patch`, sloppy, hashline) touches ([#11210](https://github.com/can1357/oh-my-pi/pull/11210) by [@DarkPhilosophy](https://github.com/DarkPhilosophy)). Added Factory Droid base-credit badges; models without a dollar-price reference no longer appear free ([#8577](https://github.com/can1357/oh-my-pi/pull/8577) by [@will-bogusz](https://github.com/will-bogusz), continued in [#13276](https://github.com/can1357/oh-my-pi/pull/13276) by [@DusKing1](https://github.com/DusKing1)). Added APIs for improving agent follow-up and steering workflow management, including moving queued follow-ups into steering with a single queue-change notification. Added support for trusted post-tool guidance via `afterToolCall` results, allowing additional context to be included in the next provider request, including after tool failures. Added configurable catalog cache-warming lifetimes for cache-capable Claude models on Amazon Bedrock Converse, Bedrock Runtime, and Mantle, with 5-minute defaults and a 1-hour Converse option where supported. Added a live Background Jobs view that lets you monitor running background jobs without interrupting the transcript. Added agent lineage navigation, making it easy to move between subagents and the main session from the composer header. Added queued-message controls to the RPC clients and session API, including promotion of queued follow-ups to steering messages without duplicating text or losing attachments, plus explicit steering or follow-up behavior for prompts sent while the agent is busy. Added support for keeping Claude prompt caches warm on Amazon Bedrock and Bedrock Mantle according to configured model cache lifetimes and retention settings. In Tern terminals, the effort indicator now visualizes the selected thinking level and becomes a fireball at the maximum level. Added a full-page transcript replay experience for Rewind in native terminals, with branching navigation through the conversation. Added agent lineage navigation, including headers and links for moving between a subagent and its ancestors or returning to the main session. Added a Jobs overlay for viewing background jobs. Added OSC 877 protocol support for native TUI surfaces in Windows ConPTY environments. Added customizable native screen layouts through Component.describeScreen and programmatic scrolling for native nodes. Added native-terminal text editing support for selections in the composer and single-line inputs, including undoable host edits and safe handling of stale or token-spanning ranges. Added optional dismissal handling for error banners, including a Dismiss button in native terminal strips. Added the `TspMeterMark` component for marking a position on a meter track with a custom icon and a total value that defines the full span of the track. Added an optional `terminal` section to theme JSON (`background`, `foreground`, `chrome`, `widget`, 16 `ansi` colors) naming the terminal a theme was made for, for hosts that paint the terminal themselves; the built-in themes ported from known schemes (GitHub, Nord, Dracula, Catppuccin, Solarized, Gruvbox, Tokyo Night, One, Monokai, Rosé Pine, Poimandres, Celestial) carry their scheme's. Added opt-in stale-session garbage collection with `omp gc --stale` or `gc.stale`, removing orphaned session markers and terminal breadcrumbs and expiring old debug reports and collaboration replicas according to configurable retention limits. Added RPC controls to cancel or steer individual foreground and background subagents without aborting the session. Added RPC word-completion commands so web and IDE hosts can provide the same ghost-text completion available in the terminal editor. Added an opt-in RPC ask-dialog mode that lets hosts render all questions together with checkbox or radio-button controls and submit their answers in one response. Added SDK notifications when a session moves to a new persistence file, including the previous and new paths. Added SDK APIs to inspect and cancel background jobs, including their command, working directory, process IDs, exit status, and captured output. Added `readTextFromClipboard()` for reading plain text from the system clipboard without starting a subprocess. Added `Shell.pids()` to retrieve the IDs of still-running processes spawned by an in-flight shell command. Exported `wordCompletionQuery()` so hosts outside the editor can apply the same prose eligibility rules used by ghost-text word completion. Added a full-featured Background jobs view with selectable jobs, live status and elapsed time, working directory, process IDs, exit code, command, tailing output, and cancellation for running jobs. Added `tryAcquireFileLock`, a non-blocking file-lock helper that returns `null` when the lock is already held. Added an `unref` option to `AsyncDrain`, allowing applications to use long batch windows without keeping the process alive. Added terminal scrolling support through the TSP scroll operation, allowing keyboard scrolling of the terminal scroller when supported. Added a terminal focus event for requesting keyboard focus on editors and inputs, or returning focus to the preferences sheet. Added global and per-advisor review cadence, including final-yield reviews and intervals that accumulate skipped transcript updates ([#12385](https://github.com/can1357/oh-my-pi/pull/12385) by [@olegpulatov](https://github.com/olegpulatov)). Added per-advisor catch-up policy and cancellable `strict` waiting, so asynchronous turn reviewers can run beside synchronous final reviewers ([#12385](https://github.com/can1357/oh-my-pi/pull/12385) by [@olegpulatov](https://github.com/olegpulatov)). Added `/jobs full` to show each background bash job's full command line; plain `/jobs` still shortens it to fit the terminal ([#13980](https://github.com/can1357/oh-my-pi/pull/13980) by [@rickythefox](https://github.com/rickythefox)) Added ContextUsageView.setBreakdown to refresh usage card without recreating it Added support for change events with flexible values in native TUI Added `startFrom(src, from)` to inline Markdown tokenizer extensions: a start hint that returns the first match at or after `from` (or `undefined`), so long paragraphs stay linear ([#13961](https://github.com/can1357/oh-my-pi/pull/13961) by [@sjawhar](https://github.com/sjawhar)). Added `this.source` and `this.end` for inline Markdown tokenizer extensions: the whole inline source and where the text being lexed ends in it, with one `this` per source that the link labels and emphasis inside it share, so a tokenizer can remember what it already scanned ([#13961](https://github.com/can1357/oh-my-pi/pull/13961) by [@sjawhar](https://github.com/sjawhar)). Added `mathSpanInContext` and `MathSpans` to `math-delimiters`, which find math spans without rescanning a run of unclosed openers ([#13961](https://github.com/can1357/oh-my-pi/pull/13961) by [@sjawhar](https://github.com/sjawhar)). Added goal management for RPC hosts and optional automatic goal continuation via `goal.continuationModes: ["rpc"]`. RPC clients can create, inspect, pause, resume, and remove goals, and view the current goal in `get_state`. Added `--goal ` for interactive launches to begin a new session in goal mode without requiring the `/goal` command. Added periodic completion estimates for running subagents, with configurable polling through `task.completionProbeMs` and progress displayed in wait and task views. Added the RPC `fork` command (`RpcClient.fork(entryId?)`, Python `fork(entry_id=None)`): it moves an RPC session onto a new session file holding the history up to and including any message entry (and the tool results answering a cut tool-call batch), together with the session's artifacts, or a copy of the whole session when `entryId` is omitted ([#14077](https://github.com/can1357/oh-my-pi/pull/14077) by [@andrebrait](https://github.com/andrebrait)). Added `reason` (`"branch"`, `"fork"` or `"btw"`) to the `session_before_branch` and `session_branch` extension and hook events, so handlers can tell whether `entryId` is dropped (`branch`) or kept ([#14077](https://github.com/can1357/oh-my-pi/pull/14077) by [@andrebrait](https://github.com/andrebrait)). Added subagent completion percentages to the agent tree, task, and wait views. Added XDG-aware utility paths for skill descriptions and prediction state, with automatic adoption of legacy data when XDG locations are first resolved. Added support for agent completion estimates in the wire protocol. Added `createAuthGatewayRouter`, the auth-gateway's routes without the HTTP listener, and `serveAuthGatewayStdio`, which serves them as JSON lines (`{"id", "path", "body"}` in, `{"id", "status", "body"}` out) for a parent process. Added `omp auth-gateway stdio`: a long-lived inference server for other programs speaking JSON lines on stdin/stdout (`{"id", "path": "/v1/chat/completions", "body"}` in, `{"id", "status", "body"}` out) with your own sign-ins; a request's `model` takes any `--model` selector (`@smol`, `sonnet`, `@commit,@smol`) and falls back along `retry.fallbackChains` when an attempt fails. Added `closeModelCache()` (`@oh-my-pi/pi-catalog/model-cache`) to release the shared default `models.db` handle so an agent directory can be deleted on Windows; the next cache access reopens it `/dump all` writes a zip to the temp directory with the main transcript, the LLM request JSON, and one file per subagent transcript (nested subagents included, killed ones marked aborted); the TUI copies the archive path to the clipboard. Plain `/dump` is unchanged ([#13908](https://github.com/can1357/oh-my-pi/pull/13908) by [@H4vC](https://github.com/H4vC)) Added `/effort [level]` to set the thinking level without switching models: bare `/effort` opens a picker, and completions offer only the current model's levels within the session effort ceiling. Its description includes thinking and intelligence so either term finds it; `Shift+Tab` still cycles levels ([#12222](https://github.com/can1357/oh-my-pi/pull/12222) by [@Xytronix](https://github.com/Xytronix), [#14113](https://github.com/can1357/oh-my-pi/pull/14113) by [@andrebrait](https://github.com/andrebrait)). Added a per-call `model` selector to task items, eval `agent()`, and `workpool()`: a `provider/model[:level]` pattern or role alias, or an ordered array of them, that takes precedence over `task.agentModelOverrides` and the agent definition. Selection is an ordered preference — requested candidates are tried before configured fallbacks — and the spawn fails at preflight instead of silently routing elsewhere when the selector is the ambiguous literal `default`/`inherit` with or without a `:level` suffix (use `@default`), is blank or comma-only, carries an invalid thinking suffix, matches no available model, or sits on the batch container instead of a `tasks[]` item. A requested model without working credentials fails the spawn instead of running on the parent's model, and the error tells the caller to report the unavailable model rather than substitute another. A pool applies its selector to each worker's first turn and reuses that worker's session afterwards ([#12229](https://github.com/can1357/oh-my-pi/pull/12229) by [@Xytronix](https://github.com/Xytronix), [#13669](https://github.com/can1357/oh-my-pi/pull/13669) by [@andrebrait](https://github.com/andrebrait)). Added `ReportPanel`, a read-only command report: a `/btw`-style titled box with an Esc hint in text mode (above the editor, or as a full-screen page whose body scrolls on the arrow/page/Home/End keys and the wheel), and natively a `/usage`-style sheet whose body the terminal scrolls once it is long, with a Close button ([#14136](https://github.com/can1357/oh-my-pi/pull/14136) by [@H4vC](https://github.com/H4vC)). Added `contextUsageHead()`, the `/context` title naming the model and its window ([#14136](https://github.com/can1357/oh-my-pi/pull/14136) by [@H4vC](https://github.com/H4vC)). Added `Composer.rowsBelow()`, the rows the chrome under a below-transcript root took in the last frame ([#14136](https://github.com/can1357/oh-my-pi/pull/14136) by [@H4vC](https://github.com/H4vC)). Added `Composer.pinInputToBottom()`, which keeps the input on the bottom row after chrome above the editor closes when rows it displaced went to scrollback ([#14136](https://github.com/can1357/oh-my-pi/pull/14136) by [@H4vC](https://github.com/H4vC)). Added a repeatable native `reveal` (`{ at, n }`): a described node scrolls into view again whenever its `n` changes, without being re-added. Added the public `getSessionOwnersDir()` utility, which returns the profile-independent `~/.omp/run/session-owners` directory that names session ownership leases ([#14095](https://github.com/can1357/oh-my-pi/pull/14095) by [@andrebrait](https://github.com/andrebrait)) Added provider-reported usage cost, the unnormalized provider ID, and the requested model ID to CostEstimatorContext, allowing cost estimators to use the cost already recorded for a request instead of recomputing it from token counts. Added support for listing models from Codex-compatible gateways through openaiCodexModelManagerOptions.baseUrl, with discovery caches isolated per endpoint. Exposed the max reasoning-effort tier for Muse Spark 1.3 contributor models on Meta and Muse Code providers. Added RPC support for GPT live voice sessions bound to the RPC session, including live start, stop, mute, phase, level, transcript, and end events; closing stdin also stops an active live session. Published a machine-readable RPC wire schema and added generated-client support for Python, Rust, and Go RPC clients, including protocol v2 negotiation, prompt-result handling, host tools, and host URIs. The Python client is now distributed from the SDK package location. Added the read-only `archive` eval global for browsing projects and past sessions, viewing idle recaps and recap journals, opening session prompts, and searching prompt history. It is enabled by default with `archive.enabled`. Added native terminal support for submitting explicit composer prompts atomically, preserving displaced drafts and attachments for local recall. Added progress percentages to subagent entries in the agent tree, task, and wait views. Added a `Rebuilding…` indicator for lengthy tmux resize redraws without flashing it for quick updates. Added `writeTerminalSequence()` for sending supported terminal escape sequences through the active terminal output stream, with stdout fallback when no terminal is active. Added utilities for detecting and scanning own-line display-math blocks in growing text, including identifying possible openers and closers efficiently. Added an option to `TerminalQueryResponder` that lets PTY hosts provide cursor-position reports themselves. Added `refreshShellConfigCache()` to rebuild the cached shell spawn environment from the current process environment. Added support for submitting explicit prompts to live editable composers without simulating keyboard input. The `/models` Roles view shows which saved model preset is in effect, and Ctrl+←/→ (or `p`/`P` on the role rows, for macOS where Ctrl+←/→ switches Spaces) switches to the next or previous one, in Tern and text mode ([#14210](https://github.com/can1357/oh-my-pi/pull/14210) by [@H4vC](https://github.com/H4vC)) Added `Agent.setOnModelCallSystemPrompt`, called with the exact system prompt each model call is built from ([#14338](https://github.com/can1357/oh-my-pi/pull/14338) by [@will-bogusz](https://github.com/will-bogusz)) Added per-model `compat.statefulResponses` to enable or disable stored Responses chaining (`previous_response_id` with `store: true`) for one endpoint without the official-only request fields that `compat.officialEndpoint` implies ([#13686](https://github.com/can1357/oh-my-pi/pull/13686) by [@alphastorm](https://github.com/alphastorm)). Added Snowflake Cortex with browser OAuth, token refresh, PAT environment authentication, and streaming Claude/OpenAI models with local tool execution ([#14507](https://github.com/can1357/oh-my-pi/pull/14507) by [@jorgoose](https://github.com/jorgoose)). `AuthStorage.health.check()` accepts `excludeProviders` to skip credentials of providers the caller does not serve ([#14234](https://github.com/can1357/oh-my-pi/pull/14234) by [@will-bogusz](https://github.com/will-bogusz)) Added an optional `statefulResponses` compat field for OpenAI Responses models, kept through OpenRouter's Responses dispatch ([#13686](https://github.com/can1357/oh-my-pi/pull/13686) by [@alphastorm](https://github.com/alphastorm)). Added 15 Snowflake Cortex models with account-specific endpoints, Cortex compatibility rules, and estimated account-billed pricing ([#14507](https://github.com/can1357/oh-my-pi/pull/14507) by [@jorgoose](https://github.com/jorgoose)). Added the `image-tokenization` axis, which declares how GPT-5.2+, Claude and Gemini 3 lines bill input images on every host, with wire-API fallback rules for other models, plus `imageTokens()` to price one image ([#14286](https://github.com/can1357/oh-my-pi/pull/14286) by [@will-bogusz](https://github.com/will-bogusz)). Added an agents HUD pill counting running subagents, opening the agent hub on click In Tern the thinking level shows as the composer model chip's icon instead of a separate chip, still cycling on click, while `statusLine.compactThinkingLevel` (Compact Thinking Level, on by default) is on Added `computer.zoom()` and window-local `zoom()` in JavaScript and Python Eval, with native-detail region captures that preserve full-screenshot click coordinates. Added window menus, combined `observe()`, native application discovery/launch, live display handles, bounded input holds, human-approved task control, and macOS Space helpers in both Eval languages. RPC `open_session` and `switch_session` accept an optional `provider`/`modelId` pair that binds the session to that model instead of its saved one, as `--model` does at startup; `RpcClient.openSession()`/`switchSession()` and the Python client's `open_session()`/`switch_session()` take it too ([#13689](https://github.com/can1357/oh-my-pi/pull/13689) by [@alphastorm](https://github.com/alphastorm)) Added `compat.statefulResponses` to `models.yml`, so a provider or model can opt into or out of stored Responses chaining without the process-wide `PI_OPENAI_STATEFUL` ([#13686](https://github.com/can1357/oh-my-pi/pull/13686) by [@alphastorm](https://github.com/alphastorm)). Added the `app.stt.pushToTalk` keybinding, defaulting to `Space`, so push-to-talk can be remapped or disabled independently from speech-to-text and `app.stt.toggle` ([#6592](https://github.com/can1357/oh-my-pi/pull/6592) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added an `expandThinkingBlocks` setting that keeps finished thinking blocks expanded in Tern instead of collapsing them at turn end ([#14519](https://github.com/can1357/oh-my-pi/pull/14519) by [@H4vC](https://github.com/H4vC)) RPC clients can show and toggle `/slow`: `get_state` reports `slowModeSupported`, `slowModeEnabled`, and a provider-neutral `usageLimit` (wrap-up or low-priority stage, with reset times for the client's timezone), and the new `set_slow_mode` command turns it on or off; the TypeScript client and the generated Python, Go, and Rust SDKs gain a matching `setSlowMode`/`set_slow_mode`/`SetSlowMode` method ([#14153](https://github.com/can1357/oh-my-pi/pull/14153) by [@andrebrait](https://github.com/andrebrait)) RPC clients can now stop a turn the way Esc does in the TUI with `abort_and_restore_queue`: queued steering and follow-up messages are taken back and returned for the editor instead of running in a new turn after the abort ([#14179](https://github.com/can1357/oh-my-pi/pull/14179) by [@andrebrait](https://github.com/andrebrait)) RPC `remove_queued_message` now returns the removed message's images, so clients can put an edited queued message back in the editor with its attachments ([#14179](https://github.com/can1357/oh-my-pi/pull/14179) by [@andrebrait](https://github.com/andrebrait)) Added `/btw` side questions for RPC hosts: `btw` asks one (or a follow-up in an earlier topic) while the main turn keeps running, the answer streams as `btw_delta` / `btw_record` frames, `btw_cancel` stops it, and `get_btw_history` lists the session's BTW history shared with the TUI ([#14110](https://github.com/can1357/oh-my-pi/pull/14110) by [@andrebrait](https://github.com/andrebrait)) Added the `providers.muse-code.storeResponses` setting (off by default; `PI_MUSE_STORE_RESPONSES` overrides it) to store Muse Code results on Meta's servers, so a turn whose connection drops is recovered instead of re-run ([#14534](https://github.com/can1357/oh-my-pi/pull/14534) by [@abilliontokens](https://github.com/abilliontokens)). Added `encodeSixelAsync` and `decodeSixelToPngAsync`, which encode and decode SIXEL off the JavaScript thread ([#14529](https://github.com/can1357/oh-my-pi/pull/14529) by [@H4vC](https://github.com/H4vC)) Added `warmBlockParse`, which parses a file for block context off the JavaScript thread so later block-context lookups answer from the cache; files over 4 MiB, which the cache does not keep, are skipped ([#14520](https://github.com/can1357/oh-my-pi/pull/14520) by [@H4vC](https://github.com/H4vC)) Added native screenshot region capture without replacing the full-frame coordinate reference, native cancellation generations, and cross-process input/focus ownership. Added operation-scoped physical Escape cancellation on macOS. Added native application discovery/launch, background menus, combined image/AX observations, display targets, bounded held input, task control ownership, and macOS Space movement. Added `frameBilling`, `frameTokens` and `frameBillingKey`, which price a rendered frame at what the model reading it is billed ([#14291](https://github.com/can1357/oh-my-pi/pull/14291) by [@will-bogusz](https://github.com/will-bogusz)) `ComposerNativeState.rate` shows a tok/s readout in the native composer bar after the effort chip, and `ComposerNativeState.thinkingInModel` draws the thinking level as the model chip's icon instead of a separate chip `formatTooltipKey` formats a key for a native tooltip: unicode keycap glyphs whatever the symbol preset, `esc` for Escape `ImageOptions.requestRender` repaints an image without an image budget once its SIXEL encode lands ([#14529](https://github.com/can1357/oh-my-pi/pull/14529) by [@H4vC](https://github.com/H4vC)) `AssistantMessageComponent` can keep finished thinking sections expanded via `setExpandThinkingBlocks()`; sections folded by hand stay folded ([#14519](https://github.com/can1357/oh-my-pi/pull/14519) by [@H4vC](https://github.com/H4vC)) Added `getOAuthCredentialProvider()` to resolve login aliases, such as `openai-codex-device`, to the provider where their credentials are stored. Added Mistral Large 4 with reasoning support, image input, a 1M-token context window, and preview pricing. Added configurable thinking levels from low through maximum for MiniMax-M3.1-Flash-Preview; because the model always reasons, requests that disable thinking use the low level. Added Google Antigravity pricing and model support for Claude Opus 5.5 and Sonnet 5.5. Added last-chance consumption of eligible banked Codex and Claude resets expiring within five minutes when auto-redeem is enabled, even with low usage or reserved credits. Added inline rendering of agent-generated SVG diagrams, charts, and mockups, with theme-aware colors and a `tui.renderSvg` setting to disable it. Added automatic chart generation for numeric tables, configurable with `tui.autoGraph` (`always`, `smart`, or `off`). The agent now chooses suitable visual formats—including charts, Mermaid, SVG, tables, or prose—based on the content. Charts and this guidance apply to the main TUI session only, not to subagents, print, RPC, or ACP. Added first-class JSON and JSONL querying to the `read` tool with `?q=`, including in-process filtering, raw or compact output, and offset/limit pagination for efficient large-file access. Added `/prewalk off` to cancel a pending model handoff without changing the active model, saved prewalk setting, or continuation history. Added logout support to RPC clients through `get_logout_accounts` and `logout`, with matching methods in the TypeScript, Python, Go, and Rust SDKs. Added custom model-kind declarations for providers and extensions, allowing image, speech, embedding, judge, and other supported model roles to be registered and routed correctly. Added working-directory reporting for Tern terminal sessions so the native composer bar can display the current folder. Enhanced `rasterizeSvg` with optional scaling and terminal-cell padding, allowing SVGs to render larger while preserving 1:1 display in terminals. Added `OMP_NATIVE_FEATURES` for passing extra Cargo features to local native addon builds; Bazel builds ignore this setting. Added support for cross-compiling macOS native addons from Linux hosts. Assistant SVG code blocks now render as inline, theme-colored images on terminals with graphics support, updating as responses stream and adapting to terminal width; SVG that cannot be rendered remains available as code. Numeric tables in assistant responses can now include automatically selected, themed charts based on the table’s structure and units. Write-tool previews now render as files stream: SVG files appear as images, and Mermaid files (`.mmd` and `.mermaid`) appear as diagrams. Tern also previews supported 3D model formats (`.obj`, `.ply`, `.wrl`, `.x3dv`, `.stl`, `.gltf`, and `.usda`) and renders SVG writes as SVG figures. Added the `title.icons` setting to show session title cards with a Nerd Font glyph and emoji fallback (`nf+emoji`, default), always the emoji (`emoji`), or as plain titles (`boring`). Added the `title.generator` setting to name sessions from a fork of the reply (`fork`, default) or with the title model only (`tiny`). SVG and Mermaid files now render as images or diagrams beneath their file cards, with SVG previews updating while the file streams and Mermaid previews appearing when the file is complete. Native tool cards can open expanded regardless of the transcript’s expansion state; the todo checklist uses this behavior. Added `ZipPackage` to `@oh-my-pi/pi-utils/ar` for lazily reading ZIP-based document packages with a configurable total-inflation limit, plus `DocxImage.readBytes()` for accessing raw DOCX image data. Added the public `validateAgentToolArguments()` API for consistent, lenient-aware validation of agent tool arguments across agent and coding-agent workflows. Added session restrictions for OAuth account pools via `AuthStorage.sessions.restrict`, limiting selection, fallback, rotation, and authentication to specified accounts until the returned lease is released with `sessions.unrestrict`. API keys and other accounts are not used when a session is restricted. Exported `resolveCredentialIdentityKey` for determining the identity key used to match credentials with broker account pools and session restrictions. Added account pools for task agents, allowing an agent and its related work—including advisors, title generation, subagents, and resumed sessions—to use only specified OAuth accounts and fail rather than fall back to another account or an API key. Added `omp usage accounts` to list OAuth account provider and identity keys without exposing tokens, making account-pool configuration easier. Added the `PI_NATIVES_DIR` configuration option to control where compiled native addons are extracted. The version-specific subdirectory remains appended, allowing separate `HOME` environments to share the same native addon copy without sharing other data. Added `PI_NATIVES_DIR` support to `getNativesDir()` for configuring the native addon directory. Added `ZipPackage` for lazily reading ZIP-based document packages with a total decompressed-size limit, along with `DocxImage.readBytes()` for accessing raw DOCX image data. Added `OAuthRefreshUnavailableError`, a retryable error that `keys.getWithCredential` and `oauth.access` reject with when every usable OAuth credential failed to refresh transiently; `keys.get` resolves `undefined` instead so availability probes move on to their next candidate ([#14843](https://github.com/can1357/oh-my-pi/pull/14843) by [@H4vC](https://github.com/H4vC)) Added Claude Haiku 5.5 with adaptive thinking (low through max effort), image input, a 1M-token context window, 128K output, and its tiered pricing above 100K input tokens. Auth gateway route option `excludeProviders` leaves those providers' accounts out of `/v1/usage` and `/v1/credentials/check` ([#14755](https://github.com/can1357/oh-my-pi/pull/14755) by [@will-bogusz](https://github.com/will-bogusz)) `oauth.refresh(id, signal, { reason: "auth-recovery" })` forwards provider-401 recovery intent to a delegated (auth broker) refresh, and `AuthStorageOptions.refreshOAuthCredentialMints` marks a `refreshOAuthCredential` hook that exchanges tokens itself so its tokens are reused for auth recovery ([#14752](https://github.com/can1357/oh-my-pi/pull/14752) by [@will-bogusz](https://github.com/will-bogusz)) `SessionsApi.inherit` accepts an optional filter, called with each provider and whether the source's affinity is an explicit user pin, to copy only the affinities it accepts ([#14749](https://github.com/can1357/oh-my-pi/pull/14749) by [@will-bogusz](https://github.com/will-bogusz)) Added per-model auto-compaction points: the `/models` preview shows where each model compacts, and in the Roles view `k` (or the **Compaction limit** button) sets it for the selected role's or fallback's model (`90000`, `90k`, `1M`, `80%`; empty resets). Also configurable as `compaction.modelThresholds` with `provider/model-id` or `provider/*` keys ([#14952](https://github.com/can1357/oh-my-pi/pull/14952) by [@H4vC](https://github.com/H4vC)) Added a **Compacts at** fact to the model hub preview and a Roles-view **Compaction limit** action (`k`) that edits the selected row's model limit through the new `ModelBrowserSource.compactionPointFor` and `ModelHubCallbacks.onCompactionPointChange` hooks ([#14952](https://github.com/can1357/oh-my-pi/pull/14952) by [@H4vC](https://github.com/H4vC)) Added support for warm-cache-aware conversation pruning, keeping pruned history within the model’s prompt-cache lookback window while preserving Anthropic prompt-cache efficiency. Added `AgentLoopConfig.hasQueuedAsides` (also available on `Agent`) to allow interruptible waits to detect queued asides without consuming them or signaling other tools. Added prompt-cache lookback support for Claude models across all hosts, including the public `prompt-cache-lookback` catalog axis and `resolvePromptCacheLookback` API. Added per-session Git worktree support with `worktree.onStart` and `worktree.onExit` settings to create an isolated worktree for each session and clean it up when the session ends. Expanded xAI web search with X post search, including X-only and author-specific queries, author exclusions, date and recency filters, and automatic xAI routing when credentials are available. Added xAI-powered reading of X posts, threads and replies, profiles, searches, and hashtags when logged in, replacing the unavailable Nitter mirrors. Added routing-session cleanup for OpenAI Responses and Codex while preserving shared provider fallbacks ([#14334](https://github.com/can1357/oh-my-pi/pull/14334) by [@iliaal](https://github.com/iliaal)). Added built-in CoralBricks support with `/login`, live model discovery, per-model reasoning levels and off controls, and bundled offline fallbacks. ([#14146](https://github.com/can1357/oh-my-pi/pull/14146) by [@ryan-brosas](https://github.com/ryan-brosas)) Added `gen:models --provider ` to update one provider without changing other providers' catalog snapshots. ([#14146](https://github.com/can1357/oh-my-pi/pull/14146) by [@ryan-brosas](https://github.com/ryan-brosas)) Added automated release binary publication to build.stencil.so Added OSC 7501 program status reporting: terminals and agent inboxes that support it now show whether omp is working, waiting on your answer or approval (with the question), done, or failed (with the error), without parsing the window title. Turn it off with `terminal.programStatus`. Added title cards (icon and short code) to `/rename`: the title model picks one for a title you type, or for a generated title when the session has no card yet; `title.icons: boring` keeps renamed titles plain. Grammars for less common languages (Kotlin, Swift, Ruby, PHP, Haskell, Verilog, and others) are now downloaded on first use for code summaries, block context, `ast_grep`, `ast_edit`, and TTSR rules; offline, files in those languages are skipped with a note instead of failing. `PI_GRAMMARS_URL` overrides the download location. Added `bash.gitGuard` (default off) for checkouts shared by concurrent agents: the bash tool refuses `git stash`, `git reset --hard` or to another commit, and `git checkout`/`switch`/`restore` that would overwrite working-tree files unless a merge or rebase conflict is being resolved; unstaging stays allowed, and commands are judged as they actually run, including inside substitutions, functions, and after `cd`. Added `wasmGrammarFor` for tree-sitter grammars loaded as WebAssembly on demand from `/grammars`, and `missingGrammars` on `astGrep`/`astEdit` results naming languages skipped because their grammar is not installed. Added cache-release hooks for TUI components and tool cards, allowing extensions to discard derived render data without rebuilding content ([#13632](https://github.com/can1357/oh-my-pi/pull/13632) by [@iliaal](https://github.com/iliaal)). Added `getNativeGrammarsDir()`, where the native addon loads downloaded tree-sitter grammars from (`~/.omp/natives/grammars`). Added `Agent.setModelResolver()` to fit every model an agent adopts (via `setModel`, starting with the current one) before it is used ([#15048](https://github.com/can1357/oh-my-pi/pull/15048) by [@H4vC](https://github.com/H4vC)) Added `CompactionSettings.baseWindowTokens`: when set, `resolveThresholdTokens()` scales its percentage or reserve-based threshold from that base instead of the full context window ([#15065](https://github.com/can1357/oh-my-pi/pull/15065) by [@H4vC](https://github.com/H4vC)) Added the `connection-bound-native-history` rule axis for Responses hosts that reject native history items from an earlier connection, set for GitHub Copilot ([#15148](https://github.com/can1357/oh-my-pi/pull/15148) by [@will-bogusz](https://github.com/will-bogusz)) Added `/jobs kill |all` to cancel a running background job (or every one this session owns) from the command line, even while the agent is busy ([#14160](https://github.com/can1357/oh-my-pi/pull/14160) by [@KanwarGill](https://github.com/KanwarGill)) Added `omp anonymize [session] [-o dir]` to write a shareable copy of a session and its subagent transcripts: only an explicit allowlist of omp metadata (ids, timestamps, models, usage, built-in tool names and options) is kept; message, thinking, and tool-output text become size-annotated `[redacted …]` markers; tool-call paths become mock paths (`/home/seg3/seg4/src/seg9.ts:10-20`), shell commands keep known programs and flags, other literals such as a grep pattern become `PLACEHOLDER_N`, and extension or MCP payloads are redacted whole, with the same original always mapping to the same token across files ([#15077](https://github.com/can1357/oh-my-pi/pull/15077) by [@H4vC](https://github.com/H4vC)) Added `/dump anon`, which writes the same anonymized session and subagent JSONL to a zip in the temp directory and copies its path ([#15077](https://github.com/can1357/oh-my-pi/pull/15077) by [@H4vC](https://github.com/H4vC)) Added message times to `/dump` transcripts (assistant turns also show request duration and time to first token), and live status, last activity, pending tool calls, and the partially streamed turn to `/dump all` files for subagents still running, so a stuck subagent can be diagnosed from the archive ([#15121](https://github.com/can1357/oh-my-pi/pull/15121) by [@H4vC](https://github.com/H4vC)) Added `contextFiles.extra` to load extra instruction files, such as `AGENTS.local.md`, beside the usual context file ([#15147](https://github.com/can1357/oh-my-pi/pull/15147) by [@Shadorain](https://github.com/Shadorain)). `/annotate` opens the note you are writing, a file or typed-prompt source, or (for local diff reviews) the current working-tree file in `$VISUAL` or `$EDITOR` with the external-editor key (Ctrl+G by default); a file source is saved back and its notes follow the edited text ([#15151](https://github.com/can1357/oh-my-pi/pull/15151) by [@Shadorain](https://github.com/Shadorain)) Added an `inline` option to `HookSelectorComponent` that keeps a selector in the composer slot in Tern instead of opening it as a sheet over the screen ([#15058](https://github.com/can1357/oh-my-pi/pull/15058) by [@H4vC](https://github.com/H4vC)) Added `ModelHubCallbacks.previewCompactionPoint`, whose line the compaction limit field shows while you type instead of the input syntax ([#15065](https://github.com/can1357/oh-my-pi/pull/15065) by [@H4vC](https://github.com/H4vC)) Added Vim find and till motions (`f`, `F`, `t`, `T`) in the prompt editor, with `;` and `,` to repeat them ([#15100](https://github.com/can1357/oh-my-pi/pull/15100) by [@Shadorain](https://github.com/Shadorain)) Added Vim replace (`r`, `R`) in the prompt editor ([#15100](https://github.com/can1357/oh-my-pi/pull/15100) by [@Shadorain](https://github.com/Shadorain)) Added Vim bracket and quote matching (`%`), paragraph motions (`{`, `}`), line join (`J`), and indent (`>>`, `<<`) in the prompt editor ([#15100](https://github.com/can1357/oh-my-pi/pull/15100) by [@Shadorain](https://github.com/Shadorain)) Added an external-editor key (Ctrl+G by default) to the annotation overlay for the note draft and, when the host provides `onExternalEditor`, the source being annotated; an edited text source is returned as `editedText` on the paste result ([#15151](https://github.com/can1357/oh-my-pi/pull/15151) by [@Shadorain](https://github.com/Shadorain)) Added `TUI.releaseHeldInput()`: on a terminal expected to speak TSP, a `deferInput` start now holds keystrokes (TSP events and the cell-size reply still apply; Ctrl+C/Ctrl+D release early) until the app calls it once its session is wired; such terminals also skip the sixel probe ([#15120](https://github.com/can1357/oh-my-pi/pull/15120) by [@H4vC](https://github.com/H4vC)) Added `TUI.replaceHeldFocus(previous, next)`, which `Composer.setEditor()` calls so a swapped-in editor inherits held startup keys; only keys for the start-time focus owner are now held, and a dialog that takes focus gets its input live ([#15122](https://github.com/can1357/oh-my-pi/pull/15122) by [@H4vC](https://github.com/H4vC)) Added `RenderResultOptions.elapsedMs` and `cancelled`, `NativeToolHead.command` and `NativeToolView.preview: "children"` for native describe hooks Added `TspToolProps.command` (the command line Copy command copies), `TspToolProps.preview: "children"` (the collapsed body stays whole while its children clamp) and `TspCodeProps.preview` Added capability-driven extension terminal launches for tmux, Zellij, Herdr, and CMUX, with consolidated multiplexer detection, provider/shell capability feedback, and required POSIX-shell confirmation for shell-input launches; CMUX shell input preserves non-ASCII arguments and pane working directories ([#13620](https://github.com/can1357/oh-my-pi/pull/13620) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added `/fork pane|window|tab` to open a fork of the session in a new multiplexer pane or window while this session keeps running; bare `/fork` still forks in place ([#13620](https://github.com/can1357/oh-my-pi/pull/13620) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). Added Orca CLI-based launches for `/fork pane|window|tab` and `ctx.ui.openTerminal()`, with POSIX-shell confirmation; when Orca can only start a tab as a background terminal, the launch reports a warning instead of a visible tab ([#13620](https://github.com/can1357/oh-my-pi/pull/13620) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). `classifyTerminalMultiplexer()` reports `"orca"` inside Orca terminals while `isInsideTerminalMultiplexer()` stays false there, so Orca keeps the direct-terminal render path; `TERMINAL_MULTIPLEXER_ENV_KEYS` lists every environment variable multiplexer detection reads ([#13620](https://github.com/can1357/oh-my-pi/pull/13620) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)) Added `terminalMultiplexerSessions()`, `terminalMultiplexerForTerm()`, `classifyTerminalMultiplexerModule()`, and `routeTerminalMultiplexerNotification()`, driven by one multiplexer registry that now owns notification routing and per-multiplexer capability overrides ([#13620](https://github.com/can1357/oh-my-pi/pull/13620) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)) Added `change` and `progress` table-chart kinds with `ChartSpec.baseline` and `TableColumn.scores`: a before/after table whose rows have their own units charts each metric as a factor of the baseline column (rows without two numbers are named in the caption), and `analyzeTable` reads whole-number scores (`12/12`, `154/160`) as the percent of their total, keeping `a / b` pairs and lists as written Added `hueDistance`, the angular distance between two OKLCH hues Exported `matchesReplacementCredential` and `isSameOAuthAccount` to help identify credential replacement and account ownership. Added `AuthStorage.sessions.permits(provider, sessionId, credentialId)` for checking whether a stored account may serve a session restricted to an account pool. Added `judgeQuestions()` for loading judge questions from JSON with inferred choice labels and answer types, plus `renderQuestion()` for templated instructions. Added browser target discovery and control, allowing agents to list the user's available pages and operate an already-open Tern browser block instead of opening a new view. Added the `ctx.annotations` extension API for submitting and collecting `/annotate` feedback on text and diffs. Added configurable Extra Context Files under `/settings` → Context, allowing custom instruction filenames without editing YAML. Added optional composer predictions via `composer.predictions`, which suggest the user's next message as ghost text after each turn and support Tab or Right to accept the suggestion. Predictions use an additional model request and are included in session usage and `/stats`. Added structured async job metadata exposing native job status and child-agent identity alongside the job ID. Enhanced `tui.autoGraph: smart` with data-aware chart recommendations, including labels, grouping, ordering, shading, reference rows, measure direction, and suitable chart types. Added `retry.fallbackOn` to restrict model fallback to quota errors (`usage-limit`) or to non-quota errors (`except-usage-limit`), while retaining `any` as the default. Added `omp usage reset` commands to list saved Codex and Claude rate-limit resets and redeem a selected reset from the CLI, scripts, or auth-broker clients. Added warnings for saved Codex and Claude resets that are nearing expiry, including affected accounts and redemption targets; interactive sessions also show a one-time conversation warning. On macOS, the `computer` tool now keeps the display awake while operating and reports when the screen is locked or asleep. Tern browser open results now indicate when a page is not currently visible, helping agents direct users to hidden picture-in-picture or omp-tab views. Exported `clipRecallContent` for applications that need to format content consistently with Mnemopi recall previews. Added `applyBinaryPatch(oldPath, patchPath, outPath)` for applying HDiffPatch single-stream delta patches, including zstd-compressed patches, to files. macOS desktop sessions now keep the display awake while in use and expose screen-lock and display-sleep state through capabilities, `screenState`, and screen captures. Added opt-in JSON editing for free-form array settings while keeping credential values masked; settings editors now surface submission and validation errors. Added ghost-text predictions to the editor via the new `Editor.prediction` callback. Press Tab or Right at the end of a line to accept the suggested text without submitting. Expanded table-chart support with stacked, waterfall, timeline, dots, range, slope, butterfly, bullet, ladder, histogram, and stat charts, including error whiskers, share bars, status matrices, and richer before/after visualizations. Added richer table-chart planning and presentation controls, including titles, ordering, grouping, shading, normalization, reference lines, polarity, rivals, focus rows, and model-driven selection for smart mode. Charts now identify key findings, highlight best values and changes, and adapt scales and labels for clearer comparisons. Added the optional `assistantMessageText` theme token for coloring assistant reply prose while preserving the terminal default when unset or empty. Added optional status-line support for showing saved usage resets that expire soon and warning once per conversation when a reset expires within 24 hours. Added `withLoopPhase(label, fn)` for attributing synchronous work to a named loop phase, with automatic cleanup even when the callback throws. Added `compat.supportsThinkingBindingControls` for Bedrock Converse: setting it to `false` stops prefix-bound Claude requests from sending `thinking.block_binding`, the `thinking-binding-controls-2026-08-01` beta and the `/input_transformations` response path, for gateways or regions that reject them ([#15316](https://github.com/can1357/oh-my-pi/pull/15316) by [@harshaygadekar](https://github.com/harshaygadekar)) Added the `supports-thinking-binding-controls` axis to Bedrock Converse models (on by default) so a rule or `models.yml` override can turn off Claude thinking-binding controls on hosts that reject them ([#15316](https://github.com/can1357/oh-my-pi/pull/15316) by [@harshaygadekar](https://github.com/harshaygadekar)) Added `supportsThinkingBindingControls` to Bedrock `compat` in `models.yml`, so a Bedrock gateway or region that rejects Claude thinking-binding controls can turn them off ([#15316](https://github.com/can1357/oh-my-pi/pull/15316) by [@harshaygadekar](https://github.com/harshaygadekar)) Added native judge support for OpenAI’s Decisions API and Cloudflare Workers AI decision models, including the `openai-decisions` and `workers-ai-systemone` APIs. The auth gateway’s System One route supports both providers. Added `createNativeJudge(model, { apiKey, headers, fetch })` for creating judges from catalog models with their configured request model IDs and question limits. Added Cloudflare Workers AI authentication with `loginCloudflareWorkersAi`, storing the API token and account ID; logging in again with the same token replaces the existing credential. Added automatic question batching to `NativeJudge` for endpoints with question limits, with up to four concurrent batches and merged answers and usage reporting. Usage from successful batches is reported through partial-usage callbacks and both session and auth-gateway usage ledgers, even if another batch fails. Added native TSP rendering support for Tern terminal sessions running inside tmux, with automatic session detection and safe title-setting behavior. Added `/fork` support for creating a new Tern pane while a turn is streaming, preserving the original session Added `omp session pack`, `omp session unpack` and `omp session moved` to move a session with its artifacts to another machine and continue it there; resuming the copy left behind forks it instead of continuing it Added `omp auth export` and `omp auth import` to carry model sign-ins to another machine Added hiding a pending `ask` question without answering it: `Alt+H` (`app.ask.hide`) or the Hide button in Tern collapses the dialog to one line; the same key, `Enter`, or Show brings it back ([#15400](https://github.com/can1357/oh-my-pi/pull/15400) by [@H4vC](https://github.com/H4vC)) Added `IpcServer`, `IpcConnection`, and `ipcEndpoint`: a local IPC transport over Unix sockets and Windows named pipes with owner-only access, single-instance binding, stale-endpoint takeover, and newline framing. Added the `app.ask.hide` keybinding (default `Alt+H`) and Hide/Show actions on `AskDialogComponent`, which collapse the dialog to a single line while its question stays pending ([#15400](https://github.com/can1357/oh-my-pi/pull/15400) by [@H4vC](https://github.com/H4vC)) Added `getMnemopiEmbedRuntimeDir()` for the shared mnemopi embedding server endpoints and logs. Added a Copy button that leads the turn footer under an answer in Tern (`⧉ · 2m13s · 71K tok · $0.85 this turn`, in place of the clock), which copies that answer `AssistantMessageComponent`'s native turn footer leads with a Copy icon (`omp.turn.copy`) and a dot instead of the clock icon; it copies the answer's text and shows when the host handles transcript actions Added `AgentLoopConfig.onDetachedToolUpdate`: a tool's `onUpdate` frames that arrive after its run's event stream ended (a returned call whose background job keeps reporting) reach it instead of being dropped; `Agent` forwards them to its subscribers as `tool_execution_update` events Added support for `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` on the `anthropic` provider: when set, requests omit pre-release fields (`context_management`, beta tool fields such as `strict` and `defer_loading`, task budgets, structured-output format, `thinking.block_binding`, and Anthropic server compaction) along with their beta headers, so `ANTHROPIC_BASE_URL` gateways that reject them keep working ([#15458](https://github.com/can1357/oh-my-pi/pull/15458) by [@H4vC](https://github.com/H4vC)) Added the `honors-claude-code-beta-kill-switch` axis (`compat.honorsClaudeCodeBetaKillSwitch`), on for the `anthropic` provider, so a rule or `models.yml` override decides which providers honor `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` ([#15458](https://github.com/can1357/oh-my-pi/pull/15458) by [@H4vC](https://github.com/H4vC)) Added `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` support: set it to stop Anthropic requests sending experimental beta fields that a company `ANTHROPIC_BASE_URL` gateway rejects, such as the Sonnet 5.5 `thinking.adaptive.block_binding` 400 ([#15458](https://github.com/can1357/oh-my-pi/pull/15458) by [@H4vC](https://github.com/H4vC)) Added the `task.structured` setting (default off) for structured task results: when on, the task tool accepts `outputSchema`/`schemaMode` and subagents return results through `yield` as before Added in-process `env`, `du`, `chmod`, `fold`, `rmdir`, `od`, `df`, `uptime`, `id`, and `dd` shell builtins matching GNU coreutils 9.x options, output, and exit codes (`chmod` and `id` on Unix only; `dd` is disabled with the destructive set by `PI_DISABLE_UUTILS_DESTRUCTIVE`). Added an in-process `nl` shell builtin (ported from uutils coreutils 0.8.0, matching GNU `nl`), with header/body/footer numbering styles including `pBRE` regex styles, logical-page section delimiters, `-l` blank-line grouping, and `ln`/`rn`/`rz` number formats. Added opt-in `/tree` branch navigation across visible branches and nested fork depths; bind `app.tree.previousBranch` / `app.tree.nextBranch` (e.g. to `Shift+Left` / `Shift+Right`) in `keybindings.yml` ([#12623](https://github.com/can1357/oh-my-pi/pull/12623) by [@azain47](https://github.com/azain47)). Added `TspPickerMark.icon`: an icon a picker mark draws instead of its initials when the terminal has it (`provider:` names a model provider's logo) Added `withoutUnverifiedThinking` utility to filter reasoning capability from models when no effort is requested Added `reachesOfficialEndpoint(model)`: whether a request to the model reaches the official endpoint its compat was built for, following `ANTHROPIC_BASE_URL` and Foundry's `FOUNDRY_BASE_URL` reroutes of first-party Anthropic models ([#15434](https://github.com/can1357/oh-my-pi/pull/15434) by [@will-bogusz](https://github.com/will-bogusz)) Added `AssistantMessage.elidedOutputTokens`, the visible output tokens a history rewrite (shake) has removed from the turn, which `usage.output` still counts ([#15446](https://github.com/can1357/oh-my-pi/pull/15446) by [@will-bogusz](https://github.com/will-bogusz)) Exported `shouldDropTruncatedThinkingOnlyAssistant` from `providers/transform-messages`, `isColdReplayableResponsesTurn` from `providers/openai-shared` and the new `openAIResponsesReplaysNativeHistory` from `providers/openai-responses`, so local token estimates can follow which turns replay drops and whether a session replays native history ([#15447](https://github.com/can1357/oh-my-pi/pull/15447) by [@will-bogusz](https://github.com/will-bogusz)) Added Muse Wonder (`muse-wonder-1.0`) to Meta and Muse Code with its `minimal`–`max` effort ladder and pricing Added the `thinking-unverified` rule axis: on hosts whose model list carries no capability metadata (Meta, Muse Code), unrecognized models now offer an opt-in thinking ladder (`ThinkingConfig.unverified`) instead of none Added `thinking-unverified` axis for offering reasoning ladders on unclassified model IDs Added `Muse Wonder 1.0` model definition to Meta provider Added the opt-in `snapcompact-image-reads` axis: snapcompact images a fresh `read` result only for readers whose rule sets it; Claude Opus 5.5 and later opt in ([#14249](https://github.com/can1357/oh-my-pi/pull/14249) by [@will-bogusz](https://github.com/will-bogusz)) Added the `image-count-budget` rule for how many images one request may carry (Anthropic 90, Codex 200, other hosts unchanged) and the `official-image-count-budget` override that applies only on the official endpoint: Anthropic 600 (100 on 200k-window Claude models), Codex 2,000 ([#15434](https://github.com/can1357/oh-my-pi/pull/15434) by [@will-bogusz](https://github.com/will-bogusz)) Added a 24 MB inline-image byte budget for the Codex backend, which now counts as its official endpoint at its default URL and at paths under it such as `/codex/responses` ([#15434](https://github.com/can1357/oh-my-pi/pull/15434) by [@will-bogusz](https://github.com/will-bogusz)) Added `isOfficialCodexApiUrl` to `wire/codex`, moved from pi-ai ([#15434](https://github.com/can1357/oh-my-pi/pull/15434) by [@will-bogusz](https://github.com/will-bogusz)) Added `verified` to `image-tokenization` rules, marking the Claude 4.7+ high-res tier and the GPT-5.5 to 6.1 and gpt-6-astra rules as matching measured provider billing ([#15442](https://github.com/can1357/oh-my-pi/pull/15442) by [@will-bogusz](https://github.com/will-bogusz)) Added the `image-max-edge` axis and `resolveImageMaxEdge()` for hosts that shrink images before the model reads them; Cursor's Claude and GPT models and its `default` (Auto) route fit 1024×1024 ([#15448](https://github.com/can1357/oh-my-pi/pull/15448) by [@will-bogusz](https://github.com/will-bogusz)) Added the `thinking-replay-tokens` axis; Claude lines set it to `output` on every host, since a replayed signed thinking block bills the turn's full reasoning, not the signature's bytes ([#15446](https://github.com/can1357/oh-my-pi/pull/15446) by [@will-bogusz](https://github.com/will-bogusz)) Added a KDL opt-in for sibling subagent prompt-cache sharing, enabled for Muse Code's Spark 1.3, Wonder 1.0, and Wonder Full 1.0 variants over the Responses API ([#15467](https://github.com/can1357/oh-my-pi/pull/15467) by [@iliaal](https://github.com/iliaal)) Added `task.agentSoftRequestBudget` to give named subagents their own soft request budget, so a long-running agent can get more requests (or `0` for no guard) while scout, sonic and other agents keep theirs ([#15419](https://github.com/can1357/oh-my-pi/pull/15419) by [@will-bogusz](https://github.com/will-bogusz)) Added `o200k` as a `tokenizer` value for custom models and overrides in `models.yml` ([#15447](https://github.com/can1357/oh-my-pi/pull/15447) by [@will-bogusz](https://github.com/will-bogusz)) Added `plannedFrameTokens` and `Shape.frameTokensVerified`: archive sizing charges a frame its own price when the reader's `image-tokenization` rule is `verified`, and at least `FRAME_TOKEN_ESTIMATE` otherwise ([#15442](https://github.com/can1357/oh-my-pi/pull/15442) by [@will-bogusz](https://github.com/will-bogusz)) `AgentTool.formatApprovalDetails` receives `ApprovalDetailsOptions`; `compact: true` asks for untruncated bodies so a compact approval prompt can count their lines ([#15550](https://github.com/can1357/oh-my-pi/pull/15550) by [@H4vC](https://github.com/H4vC)) Added Muse Code's subscription-only Muse Wonder Full and Wonder contributor tiers with the `max` effort, recording API-equivalent cost instead of $0: Wonder Full at Muse Wonder's $4 input / $0.20 cached / $20 output per 1M tokens, contributor tiers at the measured $1.60 / $0.08 / $8 ([#15522](https://github.com/can1357/oh-my-pi/pull/15522) by [@eggpeat](https://github.com/eggpeat)) Added the `classifier-cot-extraction` rule axis, set for Claude, marking models whose classifier refuses earlier reasoning quoted back into their input ([#15436](https://github.com/can1357/oh-my-pi/pull/15436) by [@will-bogusz](https://github.com/will-bogusz)) Added Gemini 4 Argon pricing on Cursor ($2 input / $0.10 cached / $10 output per 1M tokens) and Google Antigravity, which now uses Google's first-party rate instead of showing $0 ([#15620](https://github.com/can1357/oh-my-pi/pull/15620) by [@eggpeat](https://github.com/eggpeat)) Added scheduled list-price changes to `cost-patch`, as `cost-fallback` already allowed: a dated `effective-rates` card sets the price from its date, and each request is priced at the card in force when it was made, even on models loaded before the change, on rebuilt models, and on Cursor lanes priced from a sibling's card. A malformed dated card now fails the model build instead of silently keeping the old price. `getEffectiveTokenCost` returns that card for price displays, and `hasRecurringTariff` tells these dated-only schedules apart from peak/off-peak tariffs, which alone show a status-line arrow ([#15620](https://github.com/can1357/oh-my-pi/pull/15620) by [@eggpeat](https://github.com/eggpeat)) Extensions can observe and answer the interactive plan review, including refinement feedback and save-and-quit ([#14250](https://github.com/can1357/oh-my-pi/pull/14250) by [@rlfleming93](https://github.com/rlfleming93)) Added opt-in `omp gc --compress` (or `gc.compress`), which stores sessions idle for `gc.compressAfterDays` (default 7) with filesystem transparent compression (APFS, NTFS); they stay resumable and searchable ([#15600](https://github.com/can1357/oh-my-pi/pull/15600) by [@wolfiesch](https://github.com/wolfiesch)) Extensions can reopen a dismissed plan review while the session is idle (`ctx.openPlanReview()`) and pick the execution tier on `ctx.resolvePlanReview` (`input.role`); `plan_review_requested` now reports the slider's tiers ([#15552](https://github.com/can1357/oh-my-pi/pull/15552) by [@Shadorain](https://github.com/Shadorain)) Added `viewWithoutThinking()`, `textWithoutThinking()`, `readerIncludesThinking()` and an optional `Archive.withoutThinking` variant, so an archive rendered with reasoning can be read by a model that must not see it; without a stored variant the view keeps only reasoning-free text and no frames ([#15436](https://github.com/can1357/oh-my-pi/pull/15436) by [@will-bogusz](https://github.com/will-bogusz)) Added `ApprovalDialogComponent` and the `app.approval.approve` keybinding (default `Ctrl+Enter`, `Ctrl+Q`) ([#15548](https://github.com/can1357/oh-my-pi/pull/15548) by [@H4vC](https://github.com/H4vC)) Plan review overlay can take a remote answer: it shows the remotely chosen execution tier and locks further input like a terminal approval ([#15552](https://github.com/can1357/oh-my-pi/pull/15552) by [@Shadorain](https://github.com/Shadorain)) `AgentTool.delegationGuidance`: instructions a same-name extension replacement inherits in its description when it delegates to the native tool ([#15477](https://github.com/can1357/oh-my-pi/pull/15477) by [@iliaal](https://github.com/iliaal)) `CompactionPreparation.lastSummarizedEntryId` and `CompactionResult.providerReplayThroughEntryId`: a remote compaction that could only fit the history before the kept tail reports the last entry its native history covers; later entries replay normally ([#15712](https://github.com/can1357/oh-my-pi/pull/15712) by [@H4vC](https://github.com/H4vC)) Added `local/nemotron-streaming-en-0.6b` for local streaming English dictation ([#15759](https://github.com/can1357/oh-my-pi/pull/15759) by [@daaximus](https://github.com/daaximus)). Added SambaNova Cloud (`sambanova`) as a provider: `/login sambanova` with an API key, and the live `/v1/models` roster with its prices, reasoning models, and Gemma 4 image input ([#14986](https://github.com/can1357/oh-my-pi/pull/14986) by [@rjuez00](https://github.com/rjuez00)) Added a microphone button beside Send in Tern: click to record, click Stop to finish, then review and submit the transcription yourself. Clicking while it says **Starting…** cancels a slow first model load ([#15759](https://github.com/can1357/oh-my-pi/pull/15759) by [@daaximus](https://github.com/daaximus)). Added local Nemotron streaming dictation: words appear while you speak, and the microphone waits for the recognizer to be ready before recording ([#15759](https://github.com/can1357/oh-my-pi/pull/15759) by [@daaximus](https://github.com/daaximus)). Added agent frontmatter `structured: true`: that agent's task spawns keep the `yield` tool and its `output` schema validation while `task.structured` is off ([#15717](https://github.com/can1357/oh-my-pi/pull/15717) by [@alphastorm](https://github.com/alphastorm)) The composer stays usable while a tool approval is pending: sending a message denies the call and steers the turn with it, so the agent knows why it was denied ([#15642](https://github.com/can1357/oh-my-pi/pull/15642) by [@H4vC](https://github.com/H4vC)) Session entries record which omp build wrote them, so a transcript shows whether a fix was live even in a session left open across an upgrade: the version, plus commit, branch, and uncommitted-diff hash when run from a source checkout, and `OMP_BUILD_LABEL` when set. `/session` lists the builds that wrote the session ([#15680](https://github.com/can1357/oh-my-pi/pull/15680) by [@will-bogusz](https://github.com/will-bogusz)) Added native composer microphone controls with visible starting, recording and transcription states; a start still loading its model can be cancelled, and Enter and Send wait while dictation is recording or transcribing into the draft ([#15759](https://github.com/can1357/oh-my-pi/pull/15759) by [@daaximus](https://github.com/daaximus)). `ApprovalDialogComponent` takes a `draft` option that routes typing to the composer beneath it, so a message can be written while a tool call waits ([#15642](https://github.com/can1357/oh-my-pi/pull/15642) by [@H4vC](https://github.com/H4vC)) `ApprovalDialogComponent` takes a `fullPrompt` option that the expand key (`app.tools.expand`) or a Details button swaps in for the summarized prompt; it replaces `wrapDetails` ([#15642](https://github.com/can1357/oh-my-pi/pull/15642) by [@H4vC](https://github.com/H4vC)) `Tokenizer.countLatestTurn`: counts a message as the transcript's latest assistant turn, which an Anthropic Messages replay keeps byte-for-byte ([#15791](https://github.com/can1357/oh-my-pi/pull/15791) by [@will-bogusz](https://github.com/will-bogusz)) `Agent.prioritizeSteering`: moves given pending steering messages ahead of older ones so one-at-a-time delivery takes them first ([#15642](https://github.com/can1357/oh-my-pi/pull/15642)) Added image support for native OpenAI Decisions and Workers AI judgments, prompted vision chat, and auth-gateway System One requests; images exceeding a judgment API's documented caps (e.g. Clef's 4 images, 4 MiB each) are rejected locally ([#15471](https://github.com/can1357/oh-my-pi/pull/15471) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)). `isSurvivingAssistant` in `providers/transform-messages`: whether an assistant turn reaches a replay, malformed tool calls dropped first, so callers outside `transformMessages` pick the same latest turn ([#15791](https://github.com/can1357/oh-my-pi/pull/15791) by [@will-bogusz](https://github.com/will-bogusz)) Added image attachments to single and batch eval `judge()`/`judge_batch()` calls (local paths or embedded images); image judgments skip candidates without image support and fail explicitly instead of dropping images ([#15471](https://github.com/can1357/oh-my-pi/pull/15471) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)) Added a job tree to `/jobs`, `/jobs full` and the jobs pill's sheet, in the terminal UI and over ACP: subagents' background jobs now appear nested under the task that runs them, with the busiest branches listed first; only your own jobs offer Cancel ([#15854](https://github.com/can1357/oh-my-pi/pull/15854) by [@H4vC](https://github.com/H4vC)) Added `ctx.ui.getEditorComponent()` so extensions can wrap the active custom editor factory instead of replacing it ([#8655](https://github.com/can1357/oh-my-pi/pull/8655) by [@jovi-tsx](https://github.com/jovi-tsx)) Added `listWorkspace({ reportDirectoryErrors })`: an unreadable root fails the scan and unreadable subdirectories are returned in `unreadableDirectories` instead of being silently skipped ([#15769](https://github.com/can1357/oh-my-pi/issues/15769)). Added a tree layout to the background jobs sheet: subagents' jobs nest under the task job that runs them, busiest branches first, and Cancel appears only on the viewing agent's own jobs ([#15854](https://github.com/can1357/oh-my-pi/pull/15854) by [@H4vC](https://github.com/H4vC)) `agent_start` carries `resumedToolCallIds` when a continued run first executes the calls of an unpaired assistant tail Added scoped clients to `startAuthGateway` (`clients`, `setClients`): each client bearer is limited to its own models and OAuth accounts, with no fallback to other accounts or API keys, and request log lines name the client and the credential a request started on ([#5098](https://github.com/can1357/oh-my-pi/issues/5098), [#15900](https://github.com/can1357/oh-my-pi/pull/15900) by [@alphastorm](https://github.com/alphastorm)) Added experimental native image judgments for TypeSafe Jev's `jev-latest`, `jev-preview`, `jev-1.13.0`, and `jev-1.14.0`, plus OpenRouter's `typesafe/jev-1.13`, `typesafe/jev-1.14`, and `~typesafe/jev-latest` models; images outside Jev's documented size bounds fall through to a vision chat judge instead of failing ([#15887](https://github.com/can1357/oh-my-pi/pull/15887) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)) Added `keep-bundled-names` catalog attribute to preserve static model display names during discovery Updated `openai-codex` provider configuration to prevent model name regressions during live discovery Added `lsp.requestTimeout` setting to configure wait durations for language server diagnostics and requests Added `omp auth-gateway serve --clients=`: per-client bearer tokens, each limited to listed models and broker OAuth accounts with no fallback to other accounts or API keys, re-read while serving ([#5098](https://github.com/can1357/oh-my-pi/issues/5098), [#15900](https://github.com/can1357/oh-my-pi/pull/15900) by [@alphastorm](https://github.com/alphastorm)) Added `parseCodeStatus` to check code syntax and its resolved language without generating a summary ([#15904](https://github.com/can1357/oh-my-pi/pull/15904) by [@iliaal](https://github.com/iliaal)). Added `DesktopSession.holdDisplayUntilReleased()` and `releaseDisplayAwake()` to keep the display awake until the caller releases it, rather than for 5 minutes after the last request ([#15762](https://github.com/can1357/oh-my-pi/pull/15762) by [@will-bogusz](https://github.com/will-bogusz)) Exported `sqliteFileIdentity()`, so a caller holding a long-lived SQLite connection can tell when its path now names a different file (e.g. after a corrupt store was quarantined and replaced) ([#14361](https://github.com/can1357/oh-my-pi/pull/14361) by [@F0Rextasy](https://github.com/F0Rextasy)) Added `slugify()`, the shared lowercase ASCII kebab-case helper with an optional `maxLength` ([#14283](https://github.com/can1357/oh-my-pi/pull/14283) by [@jaredlyon](https://github.com/jaredlyon)) `prepareQueuedMessages` receives which queue (`steering` or `followUp`) a batch came from ([#16026](https://github.com/can1357/oh-my-pi/pull/16026)) Added `imageCountBudget` to custom models and `modelOverrides` in models.yml, so a custom gateway can state its host's image limit instead of the default of 5; past that limit the oldest images were dropped on every new image, which rewrote the provider's prompt cache ([#15002](https://github.com/can1357/oh-my-pi/issues/15002), [#15969](https://github.com/can1357/oh-my-pi/pull/15969) by [@aramalipoor](https://github.com/aramalipoor)) The status line names the active profile next to the `π` brand (`π-work`), so sessions from different profiles are distinguishable at a glance; the default profile is unchanged ([#15622](https://github.com/can1357/oh-my-pi/pull/15622) by [@matthewrball](https://github.com/matthewrball)) Added opt-in `prewalk.auto` (`off`, `suggest`, or `on`): the native judge decides per task whether to arm a prewalk handoff to `prewalk.autoTarget`, and the next task starts back on the planning model ([#16026](https://github.com/can1357/oh-my-pi/pull/16026) by [@taibenvenuti](https://github.com/taibenvenuti)) Added `/seance` and the task `seance` agent: consult a saved session read-only, in place, without resuming it or copying its artifacts; pick the source and an optional model from pickers, and send follow-ups to the consultant ([#15036](https://github.com/can1357/oh-my-pi/pull/15036) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)) Added selection-only session and model picker actions for `/seance`, so choosing a source or model leaves the active session and model unchanged ([#15036](https://github.com/can1357/oh-my-pi/pull/15036) by [@anatoli-tsinovoy](https://github.com/anatoli-tsinovoy)) Added `ThinkingContent.narration`, set on Anthropic and Bedrock thinking blocks whose signature marks them as between-tool narration, and `presentNarrationAsAnswer(message)` to show those blocks as reply text while replay keeps them as signed thinking Added `keys.peek(provider, { includeExpired: true })` to name the stored account behind an expired OAuth token for reads that never send it, such as keying an offline model-cache lookup ([#16061](https://github.com/can1357/oh-my-pi/pull/16061) by [@gchai](https://github.com/gchai)) Added `prewarmModelConnection(model)` (`providers/connection-prewarm`), which opens the model's API connection ahead of a request using the same transport and TLS settings so the request reuses it instead of paying the connection handshake ([#16086](https://github.com/can1357/oh-my-pi/pull/16086) by [@H4vC](https://github.com/H4vC)) Added the `request-encodings`, `request-encoding-rejection`, and `endpoint-hosts` rule axes, `resolveRequestCompression(model, url)`, and `isCatalogEndpointUrl(model, url)`, declaring which providers' own endpoints decode compressed request bodies: official Anthropic API (gzip), Codex backend (zstd), and GitHub Copilot's API hosts (zstd, then gzip); Moonshot's China host counts as its own endpoint ([#16086](https://github.com/can1357/oh-my-pi/pull/16086) by [@H4vC](https://github.com/H4vC)) Added `statusLine.segmentOptions.pi.showProfile`: set it to `false` to hide the profile name next to the `π` brand, for example when each profile already has its own theme ([#16063](https://github.com/can1357/oh-my-pi/pull/16063) by [@shgew](https://github.com/shgew)) Added `sharpshooter.minPromptLength` (default 16, minimum 2) to control the shortest prompt Sharpshooter extracts decisions from ([#16043](https://github.com/can1357/oh-my-pi/pull/16043) by [@bigHippoZz](https://github.com/bigHippoZz)) Added `pi.showProfile` to `StatusLineSegmentOptions`: `false` keeps the `pi` segment's bare glyph under a named profile, in the rendered bar and in `describe` ([#16063](https://github.com/can1357/oh-my-pi/pull/16063) by [@shgew](https://github.com/shgew)) Added `sanitizeTextDeep()`, which applies `sanitizeText()` to every string in a JSON-shaped value without mutating it ([#15963](https://github.com/can1357/oh-my-pi/issues/15963)) Added `advisor.continueSeverity` (`nit`, `concern`, `blocker`) to choose the minimum advisor note severity that wakes the agent after it finished with a final answer; lower-severity notes stay as a card at the end of the transcript Printed DataFrames/Series render as tables, large dicts/lists and objects as JSON trees, and Markdown objects as Markdown for the user, while the model sees the printed text Printing a figure or image in eval attaches the image to the result Added `nativeJudgmentImageBounds()`: the image bounds a native judge enforces, its wire's transport limits tightened by the catalog's model bounds Added Box judgment questions (`BoxQuestion`/`BoxAnswer`, TypeSafe Jev 1.14+ direct or through OpenRouter): each names the request image it searches by `image` index, and comes back as that image's edges as 0–1 fractions; text, OpenAI Decisions, and Workers AI judges reject them Added `computer.backgroundFallback` (`takeover` by default, or `refuse`): when a `computer` window input call has no background route, the tool reruns that one call in takeover, hands focus back to your app and says so in its result; `refuse` fails the call instead and also refuses the agent's own foreground requests (`takeover: true`, `raise()`, an activating `apps.open`, desktop input, and on macOS menus and `AXOpen`) ([#15191](https://github.com/can1357/oh-my-pi/pull/15191) by [@will-bogusz](https://github.com/will-bogusz)) Added DeepSeek as a web search engine (`web/deepseek`), using DeepSeek's new Search API with your existing `DEEPSEEK_API_KEY` or stored `deepseek` credential Added `el.selectText(text, { prefix?, suffix?, select? })` to the macOS `computer` tool: it selects text (or places a caret) in a background app's text field without taking focus, moving the pointer or sending keys, so typing into that field replaces it ([#15175](https://github.com/can1357/oh-my-pi/pull/15175) by [@will-bogusz](https://github.com/will-bogusz)) Added `{ takeover: true }` to computer-use `win.move`, so a hover that a window refuses in the background can be retried in the foreground ([#15173](https://github.com/can1357/oh-my-pi/pull/15173) by [@will-bogusz](https://github.com/will-bogusz)) Added a `menu` option to the `computer` tool's `win.click`, `el.click`, `el.press` and `el.perform`, so on macOS the call that opens a menu also chooses its item, e.g. `menu: ["Add to", "Fonts"]` ([#15185](https://github.com/can1357/oh-my-pi/pull/15185) by [@will-bogusz](https://github.com/will-bogusz)) Added `el.type(text)` and `el.press(chord)` to the `computer` tool, which send text and keys to that element instead of wherever its window's focus is; on macOS and Windows nothing is sent when the element cannot be addressed without taking your focus ([#15563](https://github.com/can1357/oh-my-pi/pull/15563) by [@will-bogusz](https://github.com/will-bogusz)) Added: pressing Escape during takeover input now stops computer use for the rest of the turn, and that session's later `computer` calls are refused, unsent, until your next message ([#15564](https://github.com/can1357/oh-my-pi/pull/15564) by [@will-bogusz](https://github.com/will-bogusz)) Added the `computer` tool's `UserIntervened` error on macOS: input into an app you have used since the agent last read its window fails without sending, and the agent is told to read the window again and keep your edits ([#15562](https://github.com/can1357/oh-my-pi/pull/15562) by [@will-bogusz](https://github.com/will-bogusz)) Added `tui.completeScrollback`: rows a growing HUD or dialog pushes off screen go straight to scrollback instead of missing from it until it shrinks ([#15692](https://github.com/can1357/oh-my-pi/pull/15692) by [@Ilm-Alan](https://github.com/Ilm-Alan)) Added a `refuseMenu` option to `click`, `drag` and `holdMouse`: a macOS background left click on a menu button or popup button, or a drag or hold starting on one, throws `BackgroundUnavailable` before anything is sent ([#15191](https://github.com/can1357/oh-my-pi/pull/15191) by [@will-bogusz](https://github.com/will-bogusz)) Added a `returnFocus` option for window input with `takeover`: on macOS the takeover hands focus back to your app even if you clicked meanwhile, and only a third app you switched to keeps focus ([#15191](https://github.com/can1357/oh-my-pi/pull/15191) by [@will-bogusz](https://github.com/will-bogusz)) Added `DesktopSession.axSelectText` (macOS) to select text in an accessibility element's value by UTF-16 range, refusing missing or ambiguous matches and returning the selection read back ([#15175](https://github.com/can1357/oh-my-pi/pull/15175) by [@will-bogusz](https://github.com/will-bogusz)) Added a `menu` item path to `click` options and `axPerform`: a macOS click or action that opens a menu chooses that item, submenus included, and leaves no menu open ([#15185](https://github.com/can1357/oh-my-pi/pull/15185) by [@will-bogusz](https://github.com/will-bogusz)) Added `DesktopSession.axType` and `axKeyChord`, which type into or press keys in one accessibility element; on macOS a field that does not report keyboard focus gets nothing and the error names what has focus; on Windows background input goes straight to the element's own control window and refuses a windowless element ([#15563](https://github.com/can1357/oh-my-pi/pull/15563) by [@will-bogusz](https://github.com/will-bogusz)) Added `DesktopSession.escapeStops` and `desktopEscapeStops(key)`, counting takeover input you stopped with physical Escape on macOS, Windows and X11, apart from host cancels ([#15564](https://github.com/can1357/oh-my-pi/pull/15564) by [@will-bogusz](https://github.com/will-bogusz)) Added `UserIntervened` on macOS: keys and clicks stop at your first key or click in the app they go to, and input to an app you used since it was last read waits up to 5 s for you to pause, then fails without sending (needs Input Monitoring) ([#15562](https://github.com/can1357/oh-my-pi/pull/15562) by [@will-bogusz](https://github.com/will-bogusz)) Added `ComposerPreferences.completeScrollback` (default `false`): rows a growing HUD or dialog pushes off screen go straight to scrollback instead of being held back until it shrinks ([#15692](https://github.com/can1357/oh-my-pi/pull/15692) by [@Ilm-Alan](https://github.com/Ilm-Alan)) Added `readSalvageableRows()` to read the rows of a damaged SQLite table that are still readable, skipping only the damaged pages ([#15751](https://github.com/can1357/oh-my-pi/pull/15751) by [@Shadorain](https://github.com/Shadorain)) `AgentTool` gained the optional `approvalCacheTargets` hook, which the `always-ask-cached` approval mode uses to check and record per-file grants ([#16049](https://github.com/can1357/oh-my-pi/pull/16049) by [@Peribunt](https://github.com/Peribunt)) Added `validateToolArguments(tool, call, { keepUnknownRootKeys: true })` to keep unknown root keys that a closed schema would otherwise drop during argument repair ([#16317](https://github.com/can1357/oh-my-pi/issues/16317)) Added the **Ask and remember** approval mode (`tools.approvalMode: always-ask-cached`, `--approval-mode always-ask-cached`): it also asks before file reads, and file prompts can remember the folder or the file, for this session or across sessions, through `approval-cache.db` ([#16049](https://github.com/can1357/oh-my-pi/pull/16049) by [@Peribunt](https://github.com/Peribunt)) Added `/forget-approvals` to forget every file and folder approval Ask and remember has recorded ([#16049](https://github.com/can1357/oh-my-pi/pull/16049) by [@Peribunt](https://github.com/Peribunt)) Extension `ui.approve()` hosts can render the new `prompt.grants` choices and answer `{ grant, always }`; hosts that ignore them keep answering `once`/`session`/`deny` ([#16049](https://github.com/can1357/oh-my-pi/pull/16049) by [@Peribunt](https://github.com/Peribunt)) Extension and custom tools can declare `approvalCacheTargets` to take part in Ask and remember grants ([#16049](https://github.com/can1357/oh-my-pi/pull/16049) by [@Peribunt](https://github.com/Peribunt)) Added `proc:///streams` for bash jobs: it lists the command's pipes, and `proc:///streams/` shows what has crossed pipe `n` so far, so `cmd | tail -5` can be followed live without rerunning `cmd` Background job widgets are designed per job by the new `widget` model role (resolves like `smol` until you assign it): one request writes rules that read the job's output and its pipes (`cmd | tail` included), and every later update is computed locally with no further model calls or messages to the agent; a subagent gets a widget only once it says which output shows its progress, and a job with nothing worth charting gets none; turn them off with `async.widgets: false` Running subagents now show their current step, in their own words, on the task card; the periodic completion check also asks the subagent which output shows its progress, so the job widget knows what to chart The `wait` card shows the watched jobs as a row of tiles, each with its status, name (a subagent's in full), what it is doing, and its headline figure and live widget when it has one (a throughput chart with its target line, per-model bars, CI job status, trial progress), and a subagent's own completion estimate as a ring that turns from blue to green as it fills (hover the tile for the percentage); the HUD jobs pill shows the freshest job's headline and a mini chart, and hovering it opens a card with the running jobs as tiles; the jobs sheet shows the selected job's widget above its output, and the terminal status line appends the headline to the jobs count Added a `hiddenContent` option to `htmlToMarkdown`: `"drop"` (default) omits hidden content, `"reachable"` keeps content the page can reveal such as collapsed sections and inactive tab panels, and `"all"` also keeps `