@kingingwang/pi-linux-arm64 0.84.2 → 0.84.3

package/bin/CHANGELOG.md

@@ -1,5 +1,84 @@
 # Changelog
 
+## [0.84.3] - 2026-08-24
+
+### New Features
+
+- **PowerShell tool** — Use optional native PowerShell command execution on Windows. See [PowerShell Tool](docs/windows.md#powershell-tool).
+- **Safer managed updates** — Stage, verify, and atomically activate updates for installer-managed installations. See [Install and Manage](docs/packages.md#install-and-manage).
+- **Model and thinking controls** — Select thinking levels with `/thinking`, search defaults, keep selections session-scoped, and persist them explicitly with Ctrl+S. See [Models and Thinking](docs/keybindings.md#models-and-thinking).
+
+### Breaking Changes
+
+- Renamed the inherited `GoogleThinkingLevel` type to `GoogleApiThinkingLevel` and added `ResolvedGoogleThinkingLevel` for normalized adapter levels.
+
+### Added
+
+- Added an optional `powershell` tool for Windows, configurable through `defaultTools` and the SDK. See [PowerShell Tool](docs/windows.md#powershell-tool).
+- Added a `/thinking` selector and searchable default choices to the model and thinking selectors; Ctrl+S saves the selected model as the global default. See [Models and Thinking](docs/keybindings.md#models-and-thinking).
+- Added optional routing session IDs to exported compaction summary helpers so callers can preserve provider routing without enabling prompt cache writes.
+- Added transcript usage notices for compaction and branch summaries when cache miss notices are enabled.
+- Added `session_compact_failed` extension events so compaction failures and aborts expose their reason, retry state, source, and error message to handlers ([#8175](https://github.com/earendil-works/pi/issues/8175)).
+- Added inherited provider-neutral `toolChoice` support to simple stream requests.
+- Added inherited automatic Anthropic server-side refusal fallback for supported first-party models, including returned-model usage pricing ([#8017](https://github.com/earendil-works/pi/issues/8017)).
+- Added inherited configurable OpenAI-compatible thinking-token budget fields for vLLM, Qwen/SGLang, and llama.cpp servers. See [OpenAI Compatibility](docs/models.md#openai-compatibility) ([#8275](https://github.com/earendil-works/pi/pull/8275) by [@bnsd55](https://github.com/bnsd55)).
+- Added inherited China-specific ZAI Coding Plan models, including GLM-4.6V vision support and API-equivalent usage cost estimates ([#8220](https://github.com/earendil-works/pi/issues/8220)).
+- Added inherited `deepseek-v4-pro-0813` support to the Qwen Token Plan Individual catalog ([#8194](https://github.com/earendil-works/pi/issues/8194)).
+
+### Changed
+
+- Changed experimental installer-managed installations so `pi update` stages, verifies, and atomically activates the selected release in place. See [Install and Manage](docs/packages.md#install-and-manage).
+- Changed inherited built-in xAI models to use the Responses API with encrypted reasoning replay and made Grok 4.6 the default xAI model ([#8124](https://github.com/earendil-works/pi/pull/8124) by [@Jaaneek](https://github.com/Jaaneek)).
+- Changed inherited Anthropic, Azure OpenAI, Google, Mistral, and OpenAI adapters to send Pi's default `User-Agent` unless overridden ([#8305](https://github.com/earendil-works/pi/issues/8305)).
+- Changed Windows and WSL keybinding defaults to avoid terminal-reserved shortcuts for image paste, model cycling, editor undo, fullscreen transcript navigation and search, and message queueing ([#8372](https://github.com/earendil-works/pi/issues/8372)).
+- Changed Bun release archives to ship the native clipboard binary only inside the wrapper package, removing a duplicate platform package from each archive.
+- Changed package resource glob expansion to use Node.js's built-in implementation with deterministic visible-path matching, reducing the installed runtime dependency tree.
+- Changed the bundled Node.js runtime to load jiti only when importing an extension and Babel only when uncached source needs transformation, reducing CLI startup time and bundle size.
+- Changed syntax highlighting to initialize only twenty common languages eagerly and defer the remaining grammars until after the initial TUI render, reducing CLI startup time.
+- Changed the Node.js CLI and RPC entrypoints to load a bundled runtime, reducing startup filesystem reads while keeping the public library and legacy module paths on the modular runtime for normal dependency identity.
+- Changed session sharing to render clickable terminal links, display only the canonical Radius artifact URL, and include the current system prompt and active tool definitions in Radius session shares.
+
+### Fixed
+
+- Fixed failed extension factories leaving event subscriptions, provider registrations, and default flag state active ([#8424](https://github.com/earendil-works/pi/pull/8424) by [@acmerfight](https://github.com/acmerfight)).
+- Fixed `models.json` typings omitting the documented OpenAI-compatible `compat.supportsFinishReason` provider and model override ([#8487](https://github.com/earendil-works/pi/pull/8487) by [@petrroll](https://github.com/petrroll)).
+- Fixed `/model` and `/thinking` selections being persisted globally unless explicitly saved with Ctrl+S ([#5263](https://github.com/earendil-works/pi/issues/5263)).
+- Fixed JSON and RPC `toolcall_start` events omitting the tool call id and name ([#7953](https://github.com/earendil-works/pi/pull/7953) by [@christianklotz](https://github.com/christianklotz)).
+- Fixed extensions failing to load when the Node.js CLI runs as a single-executable application ([#8237](https://github.com/earendil-works/pi/issues/8237)).
+- Fixed nested Markdown skills inside `.agents/skills/` grouping directories not being discovered.
+- Fixed compaction and branch summarization requests exposing tools to providers.
+- Fixed single-object `edit` tool inputs failing validation by accepting them as one-edit arrays in both coding-agent and harness edit tools ([#7835](https://github.com/earendil-works/pi/issues/7835)).
+- Fixed root Markdown files such as `README.md` and `AGENTS.md` in skill directories being reported as broken skills unless they declare valid skill frontmatter ([#7805](https://github.com/earendil-works/pi/issues/7805)).
+- Fixed the default Cerebras model referencing an unavailable Z.AI model.
+- Fixed inherited OpenAI-compatible Chat Completions reasoning replay to preserve and resend assistant-level `reasoning_details` verbatim and in order ([#7994](https://github.com/earendil-works/pi/issues/7994)).
+- Fixed inherited Anthropic server-side fallback responses being priced with the requested model instead of the returned fallback model ([#8285](https://github.com/earendil-works/pi/issues/8285)).
+- Fixed inherited GitHub Copilot login triggering model-policy rate limits by limiting policy updates, retrying model discovery once, and honoring server retry delays ([#7850](https://github.com/earendil-works/pi/issues/7850)).
+- Fixed inherited Amazon Bedrock dropping and failing to replay opaque redacted reasoning from non-Anthropic models ([#8314](https://github.com/earendil-works/pi/pull/8314) by [@seiji](https://github.com/seiji)).
+- Fixed inherited Z.AI Coding Plan models deriving incomplete reasoning-effort metadata, including missing GLM-5.3 low, high, and max levels ([#8336](https://github.com/earendil-works/pi/issues/8336)).
+- Fixed inherited DeepSeek V4 Flash on OpenCode and OpenCode Go omitting its supported low thinking level ([#8181](https://github.com/earendil-works/pi/pull/8181) by [@tianshuang](https://github.com/tianshuang)).
+- Fixed inherited Azure OpenAI Responses ignoring `toolChoice` in provider-specific stream requests.
+- Fixed inherited Amazon Bedrock response hooks receiving only a synthesized request id instead of the raw response headers ([#8234](https://github.com/earendil-works/pi/issues/8234)).
+- Fixed inherited Kimi usage reporting so top-level `cached_tokens` count as cache reads instead of normal input tokens ([#8075](https://github.com/earendil-works/pi/issues/8075)).
+- Fixed inherited Google custom models ignoring `thinkingLevelMap`, which dropped extended thinking controls ([#8135](https://github.com/earendil-works/pi/issues/8135)).
+- Fixed writes to `auth.json` and `models-store.json` overriding administrator-managed file permissions and ACLs ([#7779](https://github.com/earendil-works/pi/issues/7779)).
+- Fixed UTF-8 BOM markers preventing frontmatter and user configuration files from loading ([#8337](https://github.com/earendil-works/pi/issues/8337)).
+- Fixed invalid settings files being easy to miss during interactive startup by rendering warnings with the file path inside the TUI ([#7829](https://github.com/earendil-works/pi/issues/7829)).
+- Fixed the subagent example repeatedly prompting before running project-local agents in trusted repositories ([#8261](https://github.com/earendil-works/pi/issues/8261)).
+- Fixed npm package update checks treating older registry versions as available updates, preventing `pi update` from downgrading already-newer installed packages ([#8226](https://github.com/earendil-works/pi/issues/8226)).
+- Fixed built-in llama.cpp models disappearing from `/model` when `/llama` refreshed a configured server under `PI_OFFLINE`, and included idle-slept `sleeping` router models in the selectable catalog ([#8167](https://github.com/earendil-works/pi/issues/8167)).
+- Fixed `pi.registerFlag()` accepting default values that do not match the declared flag type ([#8064](https://github.com/earendil-works/pi/issues/8064)).
+- Fixed Z.AI Coding Plan defaults referencing the removed GLM-5.1 model ([#8096](https://github.com/earendil-works/pi/issues/8096)).
+- Fixed repeated ambiguous truncated-response recovery being mislabeled as context overflow ([#8130](https://github.com/earendil-works/pi/issues/8130)).
+- Fixed duplicate fullscreen right-click paste in VS Code-based terminals on Windows ([#8186](https://github.com/earendil-works/pi/issues/8186)).
+- Fixed inherited padded text exceeding narrow terminal widths ([#8252](https://github.com/earendil-works/pi/issues/8252)).
+- Fixed inherited wrapped Markdown table links leaking color into borders and neighboring cells, including tables inside blockquotes ([#8335](https://github.com/earendil-works/pi/issues/8335)).
+- Fixed llama.cpp login guidance to direct users to `/llama` before `/model` when no local models are loaded ([#8203](https://github.com/earendil-works/pi/issues/8203)).
+- Fixed hung pi.dev model catalog requests consuming the entire refresh deadline without retrying ([#8198](https://github.com/earendil-works/pi/issues/8198)).
+- Fixed inherited Xiaomi model catalogs listing shut-down MiMo V2 models in `/model` and `--list-models` ([#8187](https://github.com/earendil-works/pi/issues/8187)).
+- Fixed branch summary entries recording the navigation destination in `fromId` instead of the pre-navigation source leaf.
+- Fixed threshold auto-compaction being skipped when providers omit streaming usage data ([#8328](https://github.com/earendil-works/pi/issues/8328)).
+- Fixed dash-prefixed prompts being parsed as options by supporting `--` as an end-of-options delimiter ([#7269](https://github.com/earendil-works/pi/issues/7269)).
+
 ## [0.84.2] - 2026-08-14
 
 ### New Features
@@ -30,6 +109,8 @@
 
 ### Fixed
 
+- Fixed root Markdown files such as `README.md` and `AGENTS.md` in skill directories being reported as broken skills unless they declare valid skill frontmatter ([#7805](https://github.com/earendil-works/pi/issues/7805)).
+- Fixed single-object `edit` tool inputs failing validation by accepting them as one-edit arrays in both coding-agent and harness edit tools ([#7835](https://github.com/earendil-works/pi/issues/7835)).
 - Fixed managed-tool downloads delaying TUI startup and hiding diagnostics in fullscreen mode by mounting the TUI first and showing download progress and warnings inside it.
 - Fixed opening a model selector immediately after startup cancelling and restarting the in-progress model catalog refresh.
 - Fixed inherited GitHub Copilot login triggering API rate limits while enabling model policies by limiting concurrent policy updates ([#6187](https://github.com/earendil-works/pi/issues/6187)).

package/bin/README.md

@@ -514,7 +514,7 @@ Read the [blog post](https://mariozechner.at/posts/2025-11-30-pi-coding-agent/)
 ## CLI Reference
 
 ```bash
-pi [options] [@files...] [messages...]
+pi [options] [--] [@files...] [messages...]
 ```
 
 ### Package Commands
@@ -584,7 +584,7 @@ cat README.md | pi -p "Summarize this text"
 | `--no-builtin-tools`, `-nbt` | Disable built-in tools by default but keep extension/custom tools enabled |
 | `--no-tools`, `-nt` | Disable all tools by default |
 
-Available built-in tools: `read`, `bash`, `edit`, `write`, `grep`, `find`, `ls`
+Available built-in tools: `read`, `bash`, `powershell` (Windows), `edit`, `write`, `grep`, `find`, `ls`
 
 ### Resource Options
 
@@ -613,6 +613,7 @@ Combine `--no-*` with explicit flags to load exactly what you need, ignoring set
 | `--verbose` | Force verbose startup |
 | `-a`, `--approve` | Trust project-local files for this run |
 | `-na`, `--no-approve` | Ignore project-local files for this run |
+| `--` | Stop option parsing; remaining arguments are prompts or `@file` inputs |
 | `-h`, `--help` | Show help |
 | `-v`, `--version` | Show version |
 
@@ -635,6 +636,9 @@ pi "List all .ts files in src/"
 # Non-interactive
 pi -p "Summarize this codebase"
 
+# Prompt beginning with a dash
+pi -p -- "- Summarize these points"
+
 # Non-interactive with piped stdin
 cat README.md | pi -p "Summarize this text"
 
@@ -678,7 +682,7 @@ pi --thinking high "Solve this complex problem"
 | `PI_CACHE_RETENTION` | Set to `long` for extended prompt cache (Anthropic: 1h, OpenAI: 24h) |
 | `VISUAL`, `EDITOR` | Fallback external editor for Ctrl+G when `externalEditor` is unset; defaults to Notepad on Windows and `nano` elsewhere |
 
-Commands run by the LLM-callable bash tool also receive current session metadata:
+Commands run by the LLM-callable `bash` and `powershell` tools also receive current session metadata:
 
 | Variable | Description |
 |----------|-------------|
@@ -688,7 +692,7 @@ Commands run by the LLM-callable bash tool also receive current session metadata
 | `PI_MODEL` | Currently selected model ID |
 | `PI_REASONING_LEVEL` | Current effective reasoning level |
 
-These values are resolved when each command starts. See [Environment Variables](docs/environment-variables.md#bash-tool-session-environment) for semantics, examples, and custom-tool opt-out.
+These values are resolved when each command starts. See [Environment Variables](docs/environment-variables.md#shell-tool-session-environment) for semantics, examples, and custom-tool opt-out.
 
 ---
 

package/bin/docs/compaction.md

@@ -346,6 +346,21 @@ pi.on("session_before_compact", async (event, ctx) => {
 
 See [custom-compaction.ts](../examples/extensions/custom-compaction.ts) for a complete example using a different model.
 
+### session_compact_failed
+
+Fired when manual or automatic compaction fails or is aborted. This is useful for telemetry extensions that need to pair `session_before_compact` attempts with terminal outcomes.
+
+```typescript
+pi.on("session_compact_failed", async (event, ctx) => {
+  const { reason, errorMessage, aborted, willRetry, fromExtension } = event;
+  // reason - "manual" (/compact), "threshold", or "overflow"
+  // errorMessage - present for non-abort failures
+  // aborted - true for cancelled/aborted compactions
+  // willRetry - whether the aborted turn would have retried after compaction
+  // fromExtension - whether extension-provided compaction content was being used
+});
+```
+
 ### session_before_tree
 
 Fired before `/tree` navigation. Always fires regardless of whether user chose to summarize. Can cancel navigation or provide custom summary.

package/bin/docs/custom-provider.md

@@ -752,8 +752,10 @@ interface ProviderModelConfig {
     requiresThinkingAsText?: boolean;
     requiresReasoningContentOnAssistantMessages?: boolean;
     thinkingFormat?: "openai" | "openrouter" | "deepseek" | "together" | "baseten" | "zai" | "qwen" | "chat-template" | "qwen-chat-template" | "string-thinking" | "ant-ling";
-    chatTemplateKwargs?: Record<string, string | number | boolean | null | { "$var": "thinking.enabled" | "thinking.effort"; omitWhenOff?: boolean }>;
-    chatTemplateArgs?: Record<string, string | number | boolean | null | { "$var": "thinking.enabled" | "thinking.effort"; omitWhenOff?: boolean }>;
+    chatTemplateKwargs?: Record<string, string | number | boolean | null | { "$var": "thinking.enabled" | "thinking.effort" | "thinking.budget"; omitWhenOff?: boolean }>;
+    chatTemplateArgs?: Record<string, string | number | boolean | null | { "$var": "thinking.enabled" | "thinking.effort" | "thinking.budget"; omitWhenOff?: boolean }>;
+    thinkingTokenBudgetField?: "thinking_token_budget" | "thinking_budget" | "thinking_budget_tokens";
+    supportsThinkingTokenBudget?: boolean;
     cacheControlFormat?: "anthropic";
     sessionAffinityFormat?: "openai" | "openai-nosession" | "openrouter";
     sendSessionAffinityHeaders?: boolean;
@@ -771,4 +773,5 @@ interface ProviderModelConfig {
 ```
 
 `openrouter` sends `reasoning: { effort }`. `deepseek` sends `thinking: { type: "enabled" | "disabled" }` and `reasoning_effort` when enabled. `together` sends `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking` and need `preserve_thinking`. Use `chat-template` for configurable `chat_template_kwargs`, for example DeepSeek V3.x behind vLLM with `chatTemplateKwargs: { "thinking": { "$var": "thinking.enabled" } }`. Use `thinkingFormat: "baseten"` with `chatTemplateArgs` when the provider expects toggle values under `chat_template_args` and optionally supports top-level `reasoning_effort`.
+`thinkingTokenBudgetField` sends a clamped per-level thinking budget as a top-level request field (`thinking_token_budget` on vLLM, `thinking_budget` on Qwen/SGLang, `thinking_budget_tokens` on llama.cpp). `supportsThinkingTokenBudget: true` is an alias for the vLLM field name. Do not combine it with `reasoning_effort` on DashScope Qwen models.
 `cacheControlFormat: "anthropic"` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and last user, assistant, or tool-result text content.

package/bin/docs/environment-variables.md

@@ -4,7 +4,7 @@ Pi uses environment variables in three ways:
 
 - Variables such as `PI_OFFLINE` configure the Pi process.
 - Pi sets process markers so child processes can identify Pi as the launching agent.
-- Commands run by the LLM-callable bash tool receive `PI_*` variables describing the current session.
+- Commands run by the LLM-callable shell tools receive `PI_*` variables describing the current session.
 
 Provider API-key variables are documented separately in [Providers](providers.md#environment-variables-or-auth-file).
 
@@ -17,9 +17,9 @@ The CLI and RPC entry points set two process markers:
 
 Child processes inherit both markers. They are not session-specific and are not set automatically when Pi is embedded through the SDK.
 
-## Bash Tool Session Environment
+## Shell Tool Session Environment
 
-Commands run by the bash tool receive the current Pi session state:
+Commands run by the `bash` and `powershell` tools receive the current Pi session state:
 
 | Variable | Description |
 |----------|-------------|
@@ -29,7 +29,7 @@ Commands run by the bash tool receive the current Pi session state:
 | `PI_MODEL` | Currently selected model ID |
 | `PI_REASONING_LEVEL` | Current effective reasoning level: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max` |
 
-The values are resolved when each command starts. Switching models or changing the reasoning level therefore affects the next bash command without restarting Pi. `PI_PROVIDER` and `PI_MODEL` identify the selected Pi model, not a different upstream model that a router may choose internally.
+The values are resolved when each command starts. Switching models or changing the reasoning level therefore affects the next shell command without restarting Pi. `PI_PROVIDER` and `PI_MODEL` identify the selected Pi model, not a different upstream model that a router may choose internally.
 
 When asked which model or provider is running, inspect these variables instead of inferring the answer from the system prompt:
 
@@ -46,11 +46,11 @@ if [ -n "$PI_SESSION_FILE" ]; then
 fi
 ```
 
-These variables are injected into the LLM-callable bash tool. They are not injected into user-entered `!` or `!!` commands.
+These variables are injected into the LLM-callable `bash` and `powershell` tools. They are not injected into user-entered `!` or `!!` commands.
 
-### Custom Bash Tools
+### Custom Shell Tools
 
-Bash tools created with `createBashTool()` expose the session environment by default when registered with Pi. Injection happens before `spawnHook`, so a hook receives the variables in `ctx.env`:
+Tools created with `createBashTool()` or `createPowerShellTool()` expose the session environment by default when registered with Pi. Injection happens before `spawnHook`, so a hook receives the variables in `ctx.env`:
 
 ```typescript
 const bashTool = createBashTool(cwd, {
@@ -64,7 +64,7 @@ const bashTool = createBashTool(cwd, {
 Disable session metadata independently of the spawn hook:
 
 ```typescript
-const bashTool = createBashTool(cwd, {
+const powershellTool = createPowerShellTool(cwd, {
   exposeSessionEnvironment: false,
   spawnHook: (ctx) => ctx,
 });

package/bin/docs/extensions.md

@@ -330,7 +330,8 @@ user sends another prompt ◄─────────────────
 
 /compact or auto-compaction
   ├─► session_before_compact (can cancel or customize)
-  └─► session_compact
+  ├─► session_compact (success)
+  └─► session_compact_failed (failure or abort)
 
 /tree navigation
   ├─► session_before_tree (can cancel or customize)
@@ -448,7 +449,7 @@ pi.on("session_before_fork", async (event, ctx) => {
 After a successful fork or clone, pi emits `session_shutdown` for the old extension instance, reloads and rebinds extensions for the new session, then emits `session_start` with `reason: "fork"` and `previousSessionFile`.
 Do cleanup work in `session_shutdown`, then reestablish any in-memory state in `session_start`.
 
-#### session_before_compact / session_compact
+#### session_before_compact / session_compact / session_compact_failed
 
 Fired on compaction. See [compaction.md](compaction.md) for details.
 
@@ -479,6 +480,14 @@ pi.on("session_compact", async (event, ctx) => {
   // event.reason - "manual" (/compact), "threshold", or "overflow"
   // event.willRetry - whether the aborted turn is retried after compaction (overflow recovery)
 });
+
+pi.on("session_compact_failed", async (event, ctx) => {
+  // event.reason - "manual" (/compact), "threshold", or "overflow"
+  // event.errorMessage - present for non-abort failures
+  // event.aborted - true for cancelled/aborted compactions
+  // event.willRetry - whether the aborted turn would have retried after compaction
+  // event.fromExtension - whether extension-provided compaction content was being used
+});
 ```
 
 #### session_before_tree / session_tree
@@ -2050,7 +2059,7 @@ pi.registerTool({
 
 ### Overriding Built-in Tools
 
-Extensions can override built-in tools (`read`, `bash`, `edit`, `write`, `grep`, `find`, `ls`) by registering a tool with the same name. Interactive mode displays a warning when this happens.
+Extensions can override built-in tools (`read`, `bash`, `powershell`, `edit`, `write`, `grep`, `find`, `ls`) by registering a tool with the same name. Interactive mode displays a warning when this happens.
 
 ```bash
 # Extension's read tool replaces built-in read
@@ -2074,6 +2083,7 @@ See [examples/extensions/tool-override.ts](../examples/extensions/tool-override.
 Built-in tool implementations:
 - [read.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/tools/read.ts) - `ReadToolDetails`
 - [bash.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/tools/bash.ts) - `BashToolDetails`
+- [powershell.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/tools/powershell.ts) - `PowerShellToolDetails`
 - [edit.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/tools/edit.ts)
 - [write.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/tools/write.ts)
 - [grep.ts](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/tools/grep.ts) - `GrepToolDetails`
@@ -2109,11 +2119,11 @@ pi.registerTool({
 });
 ```
 
-**Operations interfaces:** `ReadOperations`, `WriteOperations`, `EditOperations`, `BashOperations`, `LsOperations`, `GrepOperations`, `FindOperations`
+**Operations interfaces:** `ReadOperations`, `WriteOperations`, `EditOperations`, `BashOperations`, `PowerShellOperations`, `LsOperations`, `GrepOperations`, `FindOperations`
 
 For `user_bash`, extensions can reuse pi's local shell backend via `createLocalBashOperations()` instead of reimplementing local process spawning, shell resolution, and process-tree termination.
 
-The bash tool also supports a spawn hook to adjust the command, cwd, or env before execution:
+The `bash` and `powershell` tools also support a spawn hook to adjust the command, cwd, or env before execution:
 
 ```typescript
 import { createBashTool } from "@earendil-works/pi-coding-agent";
@@ -2127,7 +2137,7 @@ const bashTool = createBashTool(cwd, {
 });
 ```
 
-`createBashTool()` exposes the current session to commands through `PI_SESSION_ID`, `PI_SESSION_FILE`, `PI_PROVIDER`, `PI_MODEL`, and `PI_REASONING_LEVEL`. Injection happens before `spawnHook`, so hooks receive these values in `env` and preserve them when they spread the existing environment as above. Set `exposeSessionEnvironment: false` to disable them:
+`createBashTool()` and `createPowerShellTool()` expose the current session to commands through `PI_SESSION_ID`, `PI_SESSION_FILE`, `PI_PROVIDER`, `PI_MODEL`, and `PI_REASONING_LEVEL`. Injection happens before `spawnHook`, so hooks receive these values in `env` and preserve them when they spread the existing environment as above. Set `exposeSessionEnvironment: false` to disable them:
 
 ```typescript
 const bashTool = createBashTool(cwd, {
@@ -2135,7 +2145,7 @@ const bashTool = createBashTool(cwd, {
 });
 ```
 
-See [Bash tool session environment](environment-variables.md#bash-tool-session-environment) for variable semantics. See [examples/extensions/ssh.ts](../examples/extensions/ssh.ts) for a complete SSH example with `--ssh` flag.
+See [Shell tool session environment](environment-variables.md#shell-tool-session-environment) for variable semantics. See [examples/extensions/ssh.ts](../examples/extensions/ssh.ts) for a complete SSH example with `--ssh` flag.
 
 ### Output Truncation
 

package/bin/docs/json.md

@@ -15,12 +15,16 @@ except that streaming message updates omit cumulative snapshots:
 ```typescript
 type WithoutPartial<T> = T extends { partial: unknown } ? Omit<T, "partial"> : T;
 
+type JsonAssistantMessageEvent<T> = T extends { type: "toolcall_start"; partial: unknown }
+  ? WithoutPartial<T> & { id: string; toolName: string }
+  : WithoutPartial<T>;
+
 type JsonAgentSessionEvent =
   | Exclude<AgentSessionEvent, { type: "message_update" }>
   | {
       type: "message_update";
       usage: Usage;
-      assistantMessageEvent: WithoutPartial<AssistantMessageEvent>;
+      assistantMessageEvent: JsonAssistantMessageEvent<AssistantMessageEvent>;
     };
 ```
 
@@ -84,7 +88,8 @@ Followed by events as they occur:
 `assistantMessageEvent.partial` to keep stream size linear. The top-level `usage` field contains
 the latest cumulative provider-reported usage and may remain zero when a provider only reports
 usage at completion. Use `contentIndex` and `delta` to assemble live text, thinking, or tool-call
-arguments if needed. `message_end` contains the final authoritative message.
+arguments if needed. A `toolcall_start` event also includes the constant-sized `id` and `toolName`
+fields. `message_end` contains the final authoritative message.
 
 ## Example
 

package/bin/docs/keybindings.md

@@ -70,7 +70,7 @@ The dedicated history actions always change history entries, regardless of the c
 |--------|---------|-------------|
 | `tui.editor.yank` | `ctrl+y` | Paste most recently deleted text |
 | `tui.editor.yankPop` | `alt+y` | Cycle through deleted text after yank |
-| `tui.editor.undo` | `ctrl+-` | Undo last edit |
+| `tui.editor.undo` | `ctrl+-` (`ctrl+z` on Windows; `alt+z` on WSL) | Undo last edit |
 
 ### TUI Clipboard and Selection
 
@@ -107,9 +107,9 @@ This routing remains configurable through the ordinary action bindings. For exam
 | `tui.altScreen.halfPageDown` | *(none)* | Scroll the transcript down by half a page |
 | `tui.altScreen.lineUp` | *(none)* | Scroll the transcript up by one line |
 | `tui.altScreen.lineDown` | *(none)* | Scroll the transcript down by one line |
-| `tui.altScreen.previousPrompt` | `ctrl+shift+up` | Jump to the previous marked message |
-| `tui.altScreen.nextPrompt` | `ctrl+shift+down` | Jump to the next marked message |
-| `tui.altScreen.search` | `ctrl+shift+f` | Search the rendered transcript |
+| `tui.altScreen.previousPrompt` | `ctrl+shift+up`, `ctrl+up` (`ctrl+up` only on Windows and WSL) | Jump to the previous marked message |
+| `tui.altScreen.nextPrompt` | `ctrl+shift+down`, `ctrl+down` (`ctrl+down` only on Windows and WSL) | Jump to the next marked message |
+| `tui.altScreen.search` | `ctrl+shift+f` (`ctrl+f` on Windows and WSL) | Search the rendered transcript |
 | `tui.altScreen.searchNext` | `enter`, `ctrl+g` | Select the next search match while searching |
 | `tui.altScreen.searchPrevious` | `shift+enter`, `ctrl+shift+g` | Select the previous search match while searching |
 | `tui.altScreen.searchClose` | `escape` | Close transcript search |
@@ -125,7 +125,7 @@ This routing remains configurable through the ordinary action bindings. For exam
 | `app.exit` | `ctrl+d` | Exit (when editor empty) |
 | `app.suspend` | `ctrl+z` (none on Windows) | Suspend to background |
 | `app.editor.external` | `ctrl+g` | Open in external editor (`externalEditor`, `$VISUAL`, `$EDITOR`, Notepad on Windows, or `nano` elsewhere) |
-| `app.clipboard.pasteImage` | `ctrl+v` (`alt+v` on Windows) | Paste image or text from clipboard |
+| `app.clipboard.pasteImage` | `ctrl+v` (`alt+v` on Windows and WSL) | Paste image or text from clipboard |
 
 ### Sessions
 
@@ -148,7 +148,7 @@ This routing remains configurable through the ordinary action bindings. For exam
 |--------|---------|-------------|
 | `app.model.select` | `ctrl+l` | Open model selector |
 | `app.model.cycleForward` | `ctrl+p` | Cycle to next model |
-| `app.model.cycleBackward` | `shift+ctrl+p` | Cycle to previous model |
+| `app.model.cycleBackward` | `shift+ctrl+p` (`alt+p` on Windows and WSL) | Cycle to previous model |
 | `app.thinking.cycle` | `shift+tab` | Cycle thinking level |
 | `app.thinking.toggle` | `ctrl+t` | Collapse or expand thinking blocks |
 
@@ -158,8 +158,8 @@ This routing remains configurable through the ordinary action bindings. For exam
 |--------|---------|-------------|
 | `app.tools.expand` | `ctrl+o` | Collapse or expand tool output |
 | `app.message.copy` | `ctrl+x` | Copy the last assistant message, or the selected message in `/tree` |
-| `app.message.followUp` | `alt+enter` | Queue follow-up message |
-| `app.message.dequeue` | `alt+up` | Restore queued messages to editor |
+| `app.message.followUp` | `alt+enter` (`ctrl+q` on Windows and WSL) | Queue follow-up message |
+| `app.message.dequeue` | `alt+up` (`alt+q` on Windows and WSL) | Restore queued messages to editor |
 
 ### Tree Navigation
 

package/bin/docs/llama-cpp.md

@@ -53,6 +53,8 @@ Start Pi and configure the provider:
 
 Enter the router URL and optional API key. The default URL is `http://127.0.0.1:8080`.
 
+If you start the router with `--no-models-autoload`, `/login llama.cpp` only stores the connection. Run `/llama` to load a model, then `/model` to select the loaded model for the current session.
+
 Environment variables can configure the same values without `/login`:
 
 ```bash

package/bin/docs/models.md

@@ -254,6 +254,8 @@ Current behavior:
 
 Only OpenAI-compatible APIs apply it (`openai-completions`, `openai-responses`, `azure-openai-responses`); other APIs ignore it. Keys override pi's named request fields (for example a `temperature` key here beats the request-level temperature), so prefer it as the single source of sampling truth for a model. In `modelOverrides`, `samplingParams` merges per key with the base model's value.
 
+A constant thinking-token cap can go here too, but it will not follow `thinkingBudgets` or leave room for the answer. Prefer `compat.thinkingTokenBudgetField` (or the `supportsThinkingTokenBudget` alias) for that.
+
 ### Thinking Level Map
 
 Use `thinkingLevelMap` on a model to describe model-specific thinking controls. Keys are pi thinking levels: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`. Maps may contain holes; for example, a model can expose `high` and `max` without exposing `xhigh`.
@@ -467,8 +469,10 @@ For providers with partial OpenAI compatibility, use the `compat` field.
 | `requiresThinkingAsText` | Convert thinking blocks to plain text |
 | `requiresReasoningContentOnAssistantMessages` | Include empty `reasoning_content` on all replayed assistant messages when reasoning is enabled |
 | `thinkingFormat` | Use `reasoning_effort`, `openrouter`, `deepseek`, `together`, `baseten`, `zai`, `qwen`, `chat-template`, or `qwen-chat-template` thinking parameters |
-| `chatTemplateKwargs` | `chat_template_kwargs` values for `thinkingFormat: "chat-template"`; use `{ "$var": "thinking.enabled" }` or `{ "$var": "thinking.effort" }` for pi-controlled thinking values |
-| `chatTemplateArgs` | `chat_template_args` values for `thinkingFormat: "baseten"`; use `{ "$var": "thinking.enabled" }` or `{ "$var": "thinking.effort" }` for pi-controlled thinking values |
+| `chatTemplateKwargs` | `chat_template_kwargs` values for `thinkingFormat: "chat-template"`; use `{ "$var": "thinking.enabled" }`, `{ "$var": "thinking.effort" }`, or `{ "$var": "thinking.budget" }` for pi-controlled thinking values |
+| `chatTemplateArgs` | `chat_template_args` values for `thinkingFormat: "baseten"`; use `{ "$var": "thinking.enabled" }`, `{ "$var": "thinking.effort" }`, or `{ "$var": "thinking.budget" }` for pi-controlled thinking values |
+| `thinkingTokenBudgetField` | Top-level request field used to cap reasoning tokens from `thinkingBudgets`, clamped so at least 1024 tokens remain for the answer. `"thinking_token_budget"` (vLLM), `"thinking_budget"` (Qwen/DashScope/SGLang), `"thinking_budget_tokens"` (llama.cpp). Off by default; not set on the generated catalog. |
+| `supportsThinkingTokenBudget` | Alias for `thinkingTokenBudgetField: "thinking_token_budget"` (vLLM). Prefer `thinkingTokenBudgetField`. Default: `false`. |
 | `cacheControlFormat` | Use Anthropic-style `cache_control` markers on the system prompt, last tool definition, and last user, assistant, or tool-result text content. Currently only `anthropic` is supported. |
 | `sendSessionAffinityHeaders` | For `openai-completions`, send session-affinity headers from the session id when caching is enabled. Default: `false`. |
 | `sessionAffinityFormat` | For `openai-completions` and `openai-responses`, the session-affinity header format: `openai` sends `session_id`/`x-client-request-id` (completions also `x-session-affinity`), `openai-nosession` omits the underscore-containing `session_id` header, `openrouter` sends `x-session-id`. Does not affect the `prompt_cache_key` body param. Default: auto-detected. |
@@ -481,6 +485,8 @@ For providers with partial OpenAI compatibility, use the `compat` field.
 
 `openrouter` uses `reasoning: { effort }`. `together` uses `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` uses top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that require `chat_template_kwargs.enable_thinking` and `preserve_thinking`. Use `chat-template` for vLLM/Hugging Face chat templates that need configurable `chat_template_kwargs`, such as `chatTemplateKwargs: { "thinking": { "$var": "thinking.enabled" } }` for DeepSeek V3.x templates. Use `thinkingFormat: "baseten"` with `chatTemplateArgs` for providers that expose toggle controls through `chat_template_args` and optionally support top-level `reasoning_effort`.
 
+`thinkingTokenBudgetField` is independent of `thinkingFormat`. Do not enable it on the generated Qwen catalog: those models already send `reasoning_effort`, and DashScope rejects `thinking_budget` together with `reasoning_effort`.
+
 `cacheControlFormat: "anthropic"` is for OpenAI-compatible providers that expose Anthropic-style prompt caching through `cache_control` markers on text content and tool definitions.
 
 Example:

package/bin/docs/packages.md

@@ -38,7 +38,7 @@ pi update npm:@foo/bar      # update one package
 pi update --extension npm:@foo/bar
 ```
 
-These commands manage pi packages and `pi update` can update the pi CLI installation. To uninstall pi itself, see [Quickstart](quickstart.md#uninstall).
+These commands manage pi packages and `pi update` can update the pi CLI installation. For experimental installer-managed installations, `pi update` installs the exact checked version into a staged, lockfile-backed release and activates it only after verification, leaving the current release intact if the update fails. Managed installations do not support `--force`; rerun the installer to repair one. To uninstall pi itself, see [Quickstart](quickstart.md#uninstall).
 
 By default, `install` and `remove` write to user settings (`~/.pi/agent/settings.json`). Use `-l` to write to project settings (`.pi/settings.json`) instead. Project settings can be shared with your team, and pi installs any missing packages automatically on startup after the project is trusted.
 
@@ -130,7 +130,7 @@ Add a `pi` manifest to `package.json` or use conventional directories. Include t
 }
 ```
 
-Paths are relative to the package root. Arrays support glob patterns and `!exclusions`.
+Paths are relative to the package root. Arrays support glob patterns and `!exclusions`. Positive manifest globs discover visible paths in lexical order. List dot-prefixed paths directly. If a glob would need to continue through a symlink, list the symlinked resource root directly.
 
 ### Gallery Metadata
 

package/bin/docs/rpc.md

@@ -945,7 +945,7 @@ The `assistantMessageEvent` field contains one of these delta types:
 | `thinking_start` | Thinking block started |
 | `thinking_delta` | Thinking content chunk |
 | `thinking_end` | Thinking block ended |
-| `toolcall_start` | Tool call started |
+| `toolcall_start` | Tool call started (includes `id` and `toolName`) |
 | `toolcall_delta` | Tool call arguments chunk |
 | `toolcall_end` | Tool call ended (includes full `toolCall` object) |
 
@@ -960,11 +960,17 @@ Example streaming a text response:
 The top-level `usage` field contains the latest cumulative provider-reported usage. It may remain
 zero until completion when a provider does not report usage during streaming.
 
+Example starting a tool call:
+```json
+{"type":"message_update","usage":{...},"assistantMessageEvent":{"type":"toolcall_start","contentIndex":1,"id":"call_abc123","toolName":"write"}}
+```
+
 `message_update` intentionally omits the former cumulative `message` field and
 `assistantMessageEvent.partial`. Clients that need a live partial message must assemble it
 from `message_start` and subsequent events using `contentIndex`. Treat `message_end.message`
-as authoritative. For tool calls, buffer `toolcall_delta.delta`; `toolcall_end.toolCall`
-contains the completed call.
+as authoritative. For tool calls, `toolcall_start` provides the call `id` and `toolName`;
+buffer `toolcall_delta.delta` for arguments. `toolcall_end.toolCall` contains the completed
+call.
 
 ### bash_execution_update
 

package/bin/docs/sdk.md

@@ -519,7 +519,7 @@ const { session } = await createAgentSession({ resourceLoader: loader });
 
 Specify which built-in tools to enable:
 
-- Built-in tool names: `read`, `bash`, `edit`, `write`, `grep`, `find`, `ls`
+- Built-in tool names: `read`, `bash`, `powershell`, `edit`, `write`, `grep`, `find`, `ls`
 - Default built-ins: `read`, `bash`, `edit`, `write`
 - `noTools: "all"` disables all tools
 - `noTools: "builtin"` disables default built-ins while keeping extension and custom tools enabled
@@ -540,6 +540,11 @@ const { session } = await createAgentSession({
   tools: ["read", "bash", "grep"],
 });
 
+// Use PowerShell instead of Bash on Windows
+const { session } = await createAgentSession({
+  tools: ["read", "powershell", "edit", "write"],
+});
+
 // Disable one tool while keeping the rest available
 const { session } = await createAgentSession({
   excludeTools: ["ask_question"],
@@ -1196,7 +1201,7 @@ SettingsManager
 // Tool factories
 createCodingTools
 createReadOnlyTools
-createReadTool, createBashTool, createEditTool, createWriteTool
+createReadTool, createBashTool, createPowerShellTool, createEditTool, createWriteTool
 createGrepTool, createFindTool, createLsTool
 
 // Types

package/bin/docs/settings.md

@@ -31,8 +31,8 @@ Use `/trust` in interactive mode to save a project trust decision for future ses
 | `defaultModel` | string | - | Default model ID |
 | `defaultThinkingLevel` | string | - | `"off"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"` |
 | `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output |
-| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses |
-| `thinkingBudgets` | object | - | Custom token budgets per thinking level |
+| `showCacheMissNotices` | boolean | `false` | Show transcript notices for significant prompt-cache misses and compaction or branch-summary usage |
+| `thinkingBudgets` | object | - | Custom token budgets per thinking level. Anthropic, Google, and Bedrock use these natively. OpenAI-compatible models use them when `compat.thinkingTokenBudgetField` (or `supportsThinkingTokenBudget`) is set. |
 
 #### thinkingBudgets
 
@@ -227,7 +227,7 @@ Windows paths in JSON must use forward slashes or escaped backslashes:
 |---------|------|---------|-------------|
 | `defaultTools` | string[] | - | Built-in tools enabled initially. When omitted, Pi uses its standard defaults |
 
-`defaultTools` selects the built-in tools enabled at startup. Extension and SDK custom tools remain enabled:
+`defaultTools` selects the built-in tools enabled at startup. Extension and SDK custom tools remain enabled. Available built-ins are `read`, `bash`, `powershell`, `edit`, `write`, `grep`, `find`, and `ls`:
 
 ```json
 {
@@ -235,6 +235,14 @@ Windows paths in JSON must use forward slashes or escaped backslashes:
 }
 ```
 
+On Windows, select `powershell` instead of `bash`, or include both:
+
+```json
+{
+  "defaultTools": ["read", "powershell", "edit", "write"]
+}
+```
+
 An empty array starts with no built-in tools while preserving extension and SDK custom tools. `--tools` replaces this behavior with a strict allowlist for all tools, `--no-tools` disables all tools, and `--no-builtin-tools` disables the built-in defaults. `--exclude-tools` filters the resulting list. A project `defaultTools` array replaces the global array.
 
 ### Sessions

package/bin/docs/skills.md

@@ -34,9 +34,10 @@ Pi loads skills from:
 - CLI: `--skill <path>` (repeatable, additive even with `--no-skills`)
 
 Discovery rules:
-- In `~/.pi/agent/skills/` and `.pi/skills/`, direct root `.md` files are discovered as individual skills
+- In `~/.pi/agent/skills/` and `.pi/skills/`, direct root `.md` files are discovered as individual skills when they have valid skill frontmatter with a non-empty `description`
 - In all skill locations, directories containing `SKILL.md` are discovered recursively
-- In `~/.agents/skills/` and project `.agents/skills/`, root `.md` files are ignored
+- In `~/.agents/skills/` and project `.agents/skills/`, root `.md` files are ignored, but nested `.md` files in grouping folders are discovered when they declare skill frontmatter
+- Root Markdown files other than `SKILL.md` that do not look like skills are ignored silently
 
 Disable discovery with `--no-skills` (explicit `--skill` paths still load).
 
@@ -183,7 +184,7 @@ Pi validates skills against the Agent Skills standard. Most issues produce warni
 
 Unknown frontmatter fields are ignored.
 
-**Exception:** Skills with missing description are not loaded.
+Declared skills with missing descriptions are not loaded. Malformed `SKILL.md` files and `SKILL.md` files without a description produce warnings and are not loaded. Other Markdown files without valid skill frontmatter are ignored.
 
 Name collisions (same name from different locations) warn and keep the first skill found.
 

package/bin/docs/terminal-setup.md

@@ -120,7 +120,15 @@ Add to `keybindings.json`:
 
 ## Windows Terminal
 
-Add to `settings.json` (Ctrl+Shift+, or Settings → Open JSON file) to forward the modified Enter keys pi uses:
+Pi uses Windows-style keybindings when running natively on Windows or in WSL:
+
+- `Alt+V` pastes an image or clipboard text.
+- `Ctrl+F` searches the transcript in fullscreen mode, and `Ctrl+Up`/`Ctrl+Down` jump between marked messages.
+- `Alt+P` cycles to the previous model.
+- `Ctrl+Z` undoes editing on native Windows; WSL uses `Alt+Z` so `Ctrl+Z` can suspend pi.
+- `Ctrl+Q` queues a follow-up message and `Alt+Q` restores queued messages.
+
+Add to `settings.json` (Ctrl+Shift+, or Settings → Open JSON file) to forward `Shift+Enter` for inserting a new line:
 
 ```json
 {
@@ -128,20 +136,14 @@ Add to `settings.json` (Ctrl+Shift+, or Settings → Open JSON file) to forward
     {
       "command": { "action": "sendInput", "input": "\u001b[13;2u" },
       "keys": "shift+enter"
-    },
-    {
-      "command": { "action": "sendInput", "input": "\u001b[13;3u" },
-      "keys": "alt+enter"
     }
   ]
 }
 ```
 
-- `Shift+Enter` inserts a new line.
-- Windows Terminal binds `Alt+Enter` to fullscreen by default. That prevents pi from receiving `Alt+Enter` for follow-up queueing.
-- Remapping `Alt+Enter` to `sendInput` forwards the real key chord to pi instead.
+Windows Terminal binds `Alt+Enter` to fullscreen by default. To use it instead of pi's `Ctrl+Q` default for follow-up queueing, configure Windows Terminal to send the key and bind `app.message.followUp` to `alt+enter` in pi.
 
-If you already have an `actions` array, add the objects to it. If the old fullscreen behavior persists, fully close and reopen Windows Terminal.
+If you already have an `actions` array, add the object to it. Fully close and reopen Windows Terminal after changing its settings.
 
 ## xfce4-terminal, terminator
 

package/bin/docs/usage.md

@@ -142,7 +142,7 @@ If you use pi for open source work and want to publish sessions for model, promp
 ## CLI Reference
 
 ```bash
-pi [options] [@files...] [messages...]
+pi [options] [--] [@files...] [messages...]
 ```
 
 ### Package Commands
@@ -213,7 +213,7 @@ cat README.md | pi -p "Summarize this text"
 | `--no-builtin-tools`, `-nbt` | Disable built-in tools but keep extension/custom tools enabled |
 | `--no-tools`, `-nt` | Disable all tools |
 
-Built-in tools: `read`, `bash`, `edit`, `write`, `grep`, `find`, `ls`.
+Built-in tools: `read`, `bash`, `powershell` (Windows), `edit`, `write`, `grep`, `find`, `ls`.
 
 ### Resource Options
 
@@ -246,6 +246,7 @@ pi --no-extensions -e ./my-extension.ts
 | `--verbose` | Force verbose startup |
 | `-a`, `--approve` | Trust project-local files for this run |
 | `-na`, `--no-approve` | Ignore project-local files for this run |
+| `--` | Stop option parsing; remaining arguments are prompts or `@file` inputs |
 | `-h`, `--help` | Show help |
 | `-v`, `--version` | Show version |
 
@@ -272,6 +273,9 @@ pi "List all .ts files in src/"
 # Non-interactive
 pi -p "Summarize this codebase"
 
+# Prompt beginning with a dash
+pi -p -- "- Summarize these points"
+
 # Non-interactive with piped stdin
 cat README.md | pi -p "Summarize this text"
 

package/bin/docs/windows.md

@@ -1,6 +1,6 @@
 # Windows Setup
 
-Pi requires a bash shell on Windows. Checked locations (in order):
+Pi uses Git Bash by default on Windows. Checked locations (in order):
 
 1. Custom path from `~/.pi/agent/settings.json`
 2. Git Bash (`C:\Program Files\Git\bin\bash.exe`)
@@ -8,7 +8,29 @@ Pi requires a bash shell on Windows. Checked locations (in order):
 
 For most users, [Git for Windows](https://git-scm.com/download/win) is sufficient.
 
-## Custom Shell Path
+## PowerShell Tool
+
+The optional `powershell` tool runs commands through `pwsh.exe` when available, otherwise Windows PowerShell. It starts PowerShell with `-NoProfile -NonInteractive -ExecutionPolicy Bypass`. Administrator-enforced execution policies can still take precedence.
+
+Use `defaultTools` to replace the model-facing `bash` tool:
+
+```json
+{
+  "defaultTools": ["read", "powershell", "edit", "write"]
+}
+```
+
+Or enable both while comparing behavior:
+
+```json
+{
+  "defaultTools": ["read", "bash", "powershell", "edit", "write"]
+}
+```
+
+The `!` and `!!` editor commands still use Bash.
+
+## Custom Bash Path
 
 ```json
 {

package/bin/examples/extensions/border-status-editor.ts

@@ -92,7 +92,7 @@ export default function (pi: ExtensionAPI) {
 		activeTui?.requestRender();
 	});
 
-	pi.on("agent_end", () => {
+	pi.on("agent_settled", () => {
 		isWorking = false;
 		stopSpinner();
 		activeTui?.requestRender();

package/bin/examples/extensions/custom-provider-anthropic/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.84.2",
+  "version": "0.84.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.84.2",
+      "version": "0.84.3",
       "dependencies": {
         "@anthropic-ai/sdk": "^0.52.0"
       }

package/bin/examples/extensions/custom-provider-anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-anthropic",
   "private": true,
-  "version": "0.84.2",
+  "version": "0.84.3",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/bin/examples/extensions/custom-provider-gitlab-duo/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-gitlab-duo",
   "private": true,
-  "version": "0.84.2",
+  "version": "0.84.3",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/bin/examples/extensions/git-checkpoint.ts

@@ -46,8 +46,8 @@ export default function (pi: ExtensionAPI) {
 		}
 	});
 
-	pi.on("agent_end", async () => {
-		// Clear checkpoints after agent completes
+	pi.on("agent_settled", async () => {
+		// Clear checkpoints after the full agent run completes
 		checkpoints.clear();
 	});
 }

package/bin/examples/extensions/gondolin/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-gondolin",
-	"version": "0.84.2",
+	"version": "0.84.3",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-gondolin",
-			"version": "0.84.2",
+			"version": "0.84.3",
 			"dependencies": {
 				"@earendil-works/gondolin": "0.12.0"
 			}

package/bin/examples/extensions/gondolin/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-gondolin",
 	"private": true,
-	"version": "0.84.2",
+	"version": "0.84.3",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/bin/examples/extensions/notify.ts

@@ -49,7 +49,9 @@ function notify(title: string, body: string): void {
 }
 
 export default function (pi: ExtensionAPI) {
-	pi.on("agent_end", async () => {
+	// `agent_end` fires after each low-level run; Pi may still retry, compact,
+	// or continue with queued follow-ups. Notify only after the full run settles.
+	pi.on("agent_settled", async () => {
 		notify("Pi", "Ready for input");
 	});
 }

package/bin/examples/extensions/sandbox/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-sandbox",
-	"version": "1.14.2",
+	"version": "1.14.3",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-sandbox",
-			"version": "1.14.2",
+			"version": "1.14.3",
 			"dependencies": {
 				"@anthropic-ai/sandbox-runtime": "^0.0.26"
 			}

package/bin/examples/extensions/sandbox/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-sandbox",
 	"private": true,
-	"version": "1.14.2",
+	"version": "1.14.3",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/bin/examples/extensions/subagent/README.md

@@ -62,7 +62,7 @@ This tool executes a separate `pi` subprocess with a delegated system prompt and
 
 To enable project-local agents, pass `agentScope: "both"` (or `"project"`). Only do this for repositories you trust.
 
-When running interactively, the tool prompts for confirmation before running project-local agents. Set `confirmProjectAgents: false` to disable.
+When running interactively, the tool prompts for confirmation before running project-local agents in untrusted projects. Trusted projects skip the additional prompt. Set `confirmProjectAgents: false` to disable confirmation.
 
 ## Usage
 

package/bin/examples/extensions/subagent/index.ts

@@ -517,7 +517,12 @@ export default function (pi: ExtensionAPI) {
 				};
 			}
 
-			if ((agentScope === "project" || agentScope === "both") && confirmProjectAgents && ctx.hasUI) {
+			if (
+				(agentScope === "project" || agentScope === "both") &&
+				confirmProjectAgents &&
+				ctx.hasUI &&
+				!ctx.isProjectTrusted()
+			) {
 				const requestedAgentNames = new Set<string>();
 				if (params.chain) for (const step of params.chain) requestedAgentNames.add(step.agent);
 				if (params.tasks) for (const t of params.tasks) requestedAgentNames.add(t.agent);

package/bin/examples/extensions/titlebar-spinner.ts

@@ -48,7 +48,7 @@ export default function (pi: ExtensionAPI) {
 		startAnimation(ctx);
 	});
 
-	pi.on("agent_end", async (_event, ctx) => {
+	pi.on("agent_settled", async (_event, ctx) => {
 		stopAnimation(ctx);
 	});
 

package/bin/examples/extensions/with-deps/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-with-deps",
-  "version": "0.84.2",
+  "version": "0.84.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-with-deps",
-      "version": "0.84.2",
+      "version": "0.84.3",
       "dependencies": {
         "ms": "^2.1.3"
       },

package/bin/examples/extensions/with-deps/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-with-deps",
   "private": true,
-  "version": "0.84.2",
+  "version": "0.84.3",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/bin/examples/rpc-extension-ui.ts

@@ -576,7 +576,7 @@ async function main() {
 			return;
 		}
 
-		if (data.type === "agent_end") {
+		if (data.type === "agent_settled") {
 			isStreaming = false;
 			hideLoading();
 			outputLog.append("");

package/bin/examples/sdk/06-extensions.ts

@@ -71,7 +71,7 @@ export default function (pi: ExtensionAPI) {
 	});
 
 	pi.on("agent_end", async (event) => {
-		console.log(\`[Extension] Done, \${event.messages.length} messages\`);
+		console.log(\`[Extension] Low-level run ended, \${event.messages.length} messages\`);
 	});
 
 	// Register a custom tool

package/bin/examples/sdk/README.md

@@ -132,7 +132,7 @@ session.subscribe((event) => {
     case "tool_execution_end":
       console.log(`Result: ${event.result}`);
       break;
-    case "agent_end":
+    case "agent_settled":
       console.log("Done");
       break;
   }

package/bin/package.json

@@ -1,13 +1,13 @@
 {
 	"name": "@earendil-works/pi-coding-agent",
-	"version": "0.84.2",
+	"version": "0.84.3",
 	"description": "Coding agent CLI with read, bash, edit, write tools and session management",
 	"type": "module",
 	"piConfig": {
 		"configDir": ".pi"
 	},
 	"bin": {
-		"pi": "dist/cli.js"
+		"pi": "dist/bundle/cli.js"
 	},
 	"main": "./dist/index.js",
 	"types": "./dist/index.d.ts",
@@ -17,7 +17,7 @@
 			"import": "./dist/index.js"
 		},
 		"./rpc-entry": {
-			"import": "./dist/rpc-entry.js"
+			"import": "./dist/bundle/rpc-entry.js"
 		},
 		"./client": {
 			"types": "./dist/client/index.d.ts",
@@ -34,8 +34,9 @@
 	],
 	"scripts": {
 		"clean": "shx rm -rf dist",
-		"build": "tsgo -p tsconfig.build.json && shx chmod +x dist/cli.js dist/rpc-entry.js && npm run copy-assets",
-		"build:binary": "npm --prefix ../tui run build && npm --prefix ../telemetry run build && npm --prefix ../ai run build && npm --prefix ../agent run build && npm --prefix ../protocol run build && npm --prefix ../client run build && npm run build && bun build --compile --no-compile-autoload-bunfig ./dist/bun/cli.js ./src/utils/image-resize-worker.ts --outfile dist/pi && npm run copy-binary-assets",
+		"build": "npm run build:unbundled && node ../../scripts/build-coding-agent-bundle.mjs",
+		"build:unbundled": "tsgo -p tsconfig.build.json && shx chmod +x dist/cli.js dist/rpc-entry.js && npm run copy-assets",
+		"build:binary": "npm --prefix ../tui run build && npm --prefix ../telemetry run build && npm --prefix ../ai run build && npm --prefix ../agent run build && npm --prefix ../protocol run build && npm --prefix ../client run build && npm run build && bun build --compile --no-compile-autoload-bunfig ./src/bun/cli.ts ./src/utils/image-resize-worker.ts --outfile dist/pi && npm run copy-binary-assets",
 		"copy-assets": "shx mkdir -p dist/modes/interactive/theme && shx cp src/modes/interactive/theme/*.json dist/modes/interactive/theme/ && shx mkdir -p dist/modes/interactive/assets && shx cp src/modes/interactive/assets/*.png dist/modes/interactive/assets/ && shx mkdir -p dist/core/export-html/vendor && shx cp src/core/export-html/template.html src/core/export-html/template.css src/core/export-html/template.js dist/core/export-html/ && shx cp src/core/export-html/vendor/*.js dist/core/export-html/vendor/",
 		"copy-binary-assets": "shx cp package.json dist/ && shx cp README.md dist/ && shx cp CHANGELOG.md dist/ && shx mkdir -p dist/theme && shx cp src/modes/interactive/theme/*.json dist/theme/ && shx mkdir -p dist/assets && shx cp src/modes/interactive/assets/*.png dist/assets/ && shx mkdir -p dist/export-html/vendor && shx cp src/core/export-html/template.html dist/export-html/ && shx cp src/core/export-html/vendor/*.js dist/export-html/vendor/ && shx cp -r docs dist/ && shx cp -r examples dist/ && shx cp ../../node_modules/@silvia-odwyer/photon-node/photon_rs_bg.wasm dist/",
 		"test": "vitest --run",
@@ -43,16 +44,15 @@
 		"prepublishOnly": "npm run clean && npm run build && npm run shrinkwrap"
 	},
 	"dependencies": {
-		"@earendil-works/pi-agent-core": "^0.84.2",
-		"@earendil-works/pi-ai": "^0.84.2",
-		"@earendil-works/pi-client": "^0.84.2",
-		"@earendil-works/pi-protocol": "^0.84.2",
-		"@earendil-works/pi-tui": "^0.84.2",
+		"@earendil-works/pi-agent-core": "^0.84.3",
+		"@earendil-works/pi-ai": "^0.84.3",
+		"@earendil-works/pi-client": "^0.84.3",
+		"@earendil-works/pi-protocol": "^0.84.3",
+		"@earendil-works/pi-tui": "^0.84.3",
 		"@silvia-odwyer/photon-node": "0.3.4",
 		"chalk": "5.6.2",
 		"cross-spawn": "7.0.6",
 		"diff": "8.0.4",
-		"glob": "13.0.6",
 		"grok-mermaid": "0.2.2",
 		"highlight.js": "10.7.3",
 		"hosted-git-info": "9.0.3",
@@ -77,10 +77,8 @@
 	},
 	"devDependencies": {
 		"@types/cross-spawn": "6.0.6",
-		"@types/diff": "7.0.2",
 		"@types/hosted-git-info": "3.0.5",
-		"@types/ms": "2.1.0",
-		"@types/node": "24.12.4",
+		"@types/node": "22.19.19",
 		"@types/proper-lockfile": "4.1.4",
 		"@types/semver": "7.7.1",
 		"shx": "0.4.0",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kingingwang/pi-linux-arm64",
-  "version": "0.84.2",
+  "version": "0.84.3",
   "description": "Pi standalone binary for linux-arm64 (fork distribution)",
   "license": "MIT",
   "os": [

package/bin/node_modules/@mariozechner/clipboard-linux-arm64-gnu/README.md

@@ -1,3 +0,0 @@
-# `@mariozechner/clipboard-linux-arm64-gnu`
-
-This is the **aarch64-unknown-linux-gnu** binary for `@mariozechner/clipboard`

package/bin/node_modules/@mariozechner/clipboard-linux-arm64-gnu/package.json

@@ -1,25 +0,0 @@
-{
-  "name": "@mariozechner/clipboard-linux-arm64-gnu",
-  "version": "0.3.9",
-  "os": [
-    "linux"
-  ],
-  "cpu": [
-    "arm64"
-  ],
-  "main": "clipboard.linux-arm64-gnu.node",
-  "files": [
-    "clipboard.linux-arm64-gnu.node"
-  ],
-  "license": "MIT",
-  "engines": {
-    "node": ">= 10"
-  },
-  "libc": [
-    "glibc"
-  ],
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/badlogic/clipboard.git"
-  }
-}