@astralyn/pi 0.87.6 → 1.0.0

package/docs/settings.md

@@ -77,9 +77,9 @@ Selecting a model or thinking level with Enter changes only the current session.
 
 | Setting | Type | Default | Description |
 |---------|------|---------|-------------|
-| `theme` | string | `"dark"` | Theme name (`"dark"`, `"light"`, or custom) |
+| `theme` | string | `"system"` | Theme name (`"system"`, `"dark"`, `"light"`, bundled ice-cream themes, or custom) |
 | `externalEditor` | string | `$VISUAL`, then `$EDITOR`, then Notepad on Windows or `nano` elsewhere | Command for Ctrl+G external editor; takes precedence over environment variables |
-| `quietStartup` | boolean | `false` | Hide startup header |
+| `quietStartup` | boolean | `"header"` | `false` | `true` hides the startup header and loaded-resource listing. `"header"` keeps the header (version and key hints) but hides the model scope line and loaded-resource listing |
 | `defaultProjectTrust` | string | `"ask"` | Fallback project trust behavior: `"ask"`, `"always"`, or `"never"`. Global setting only |
 | `collapseChangelog` | boolean | `false` | Show condensed changelog after updates |
 | `enableInstallTelemetry` | boolean | `true` | Legacy setting name for optional provider attribution headers. This does not control update checks |
@@ -285,7 +285,7 @@ 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. Available built-ins are `read`, `bash`, `powershell`, `edit`, `write`, `grep`, `find`, and `ls`:
+`defaultTools` selects tools enabled at startup; plain names replace the selection, while `+name` and `-name` modify it. It can also activate `codemode`, `tool_search`, and other inactive extension tools. Extension and SDK custom tools remain enabled. Available built-ins are `read`, `bash`, `powershell`, `edit`, `write`, `grep`, `find`, and `ls`:
 
 ```json
 {
@@ -427,3 +427,29 @@ Project settings (`.pi/settings.json`) override global settings. Nested objects
   "compaction": { "enabled": true, "triggerPercent": 70 }
 }
 ```
+
+## Codemode and tool selection
+
+A list of only `+name` and `-name` entries changes the inherited selection instead of replacing it. For example, this enables `codemode` next to the default tools:
+
+```json
+{
+  "defaultTools": ["+codemode"]
+}
+```
+
+This replaces `bash` with `powershell` and enables `grep`: `["-bash", "+powershell", "+grep"]`. Project settings apply on top of user settings: a project list with only `+name` and `-name` entries changes the user's selection, and a project list with a plain name replaces it. In one list, plain names form the selection, and `+name` and `-name` then apply in order.
+
+`/reload` enables tools newly added to `defaultTools`. It does not disable tools removed from it or re-enable unchanged tools you turned off. `--tools`, `--no-tools`, and `--no-builtin-tools` override `defaultTools`, also on reload.
+
+CLI tool options override this setting for one invocation; `--tools` does not accept `+name` or `-name`. See [Command Line](usage.md#tools).
+
+| Setting | Default | Meaning |
+|---|---|---|
+| `codemode.mode` | `"on"` | `on` keeps direct tool declarations and appends a note on calling them from scripts; `only` hides callable tools from direct model access and lists them in codemode. See [Codemode](codemode.md) |
+| `codemode.inlineBudget` | `3000` | Estimated tokens for inline tool declarations; scripts discover the rest with `searchTools()` |
+| `fullscreenWheelScrollLines` | `"auto"` | 1–100 lines per wheel event, or automatic acceleration; Alt+wheel moves five times as far |
+
+Built-in extensions can be disabled in `pi config` or with `"extensions": ["-builtin:mcp"]`. Project `+builtin:<name>` and `-builtin:<name>` entries override user settings. `--no-extensions` disables built-ins too; `-e builtin:mcp` loads one explicitly.
+
+MCP servers live in `~/.pi/agent/mcp.json` or trusted project `.pi/mcp.json`; see [MCP Servers](mcp.md).

package/docs/themes.md

@@ -18,7 +18,7 @@ Themes are JSON files that define colors for the TUI.
 
 Pi loads themes from:
 
-- Built-in: `dark`, `light`, `ice-cream-dark`, `ice-cream-light`
+- Built-in: `system`, `dark`, `light`, `ice-cream-dark`, `ice-cream-light`
 - Global: `~/.pi/agent/themes/*.json`
 - Project: `.pi/themes/*.json` (only after the project is trusted)
 - Packages: `themes/` directories or `pi.themes` entries in `package.json`
@@ -37,7 +37,7 @@ Select a theme via `/settings` or in `settings.json`:
 }
 ```
 
-On first run, pi detects your terminal background and defaults to `dark` or `light`.
+Without a saved theme setting, Pi uses `system`, which follows the terminal palette and appearance.
 
 ### Initial Theme
 
@@ -158,7 +158,8 @@ vim ~/.pi/agent/themes/my-theme.json
 }
 ```
 
-- `name` is required, must be unique, and must not contain `/`.
+- `name` is required, must be unique, must not contain `/`, and cannot be `system`.
+- `appearance` is optional: `"dark"` or `"light"`. Pi detects it from the colors when omitted.
 - `vars` is optional. Define reusable colors here, then reference them in `colors`.
 - `colors` must define all 51 required tokens. `thinkingMax`, `scrollbarThumb`, and the two search highlight tokens are optional and use the fallbacks listed below.
 
@@ -276,11 +277,13 @@ The `export` section controls colors for `/export` HTML output. If omitted, colo
 
 ## Color Values
 
-Four formats are supported:
+Six formats are supported:
 
 | Format | Example | Description |
 |--------|---------|-------------|
-| Hex | `"#ff0000"` | 6-digit hex RGB |
+| Hex | `"#f00"` or `"#ff0000"` | 3- or 6-digit hex RGB |
+| OKLCH | `"oklch(62% 0.1 200)"` | Perceptual lightness, chroma, and hue |
+| OKHSL | `"okhsl(250 60% 55%)"` | Hue, saturation, and lightness within the sRGB gamut |
 | 256-color | `39` | xterm 256-color palette index (0-255) |
 | Variable | `"primary"` | Reference to a `vars` entry |
 | Default | `""` | Terminal's default color |
@@ -318,3 +321,22 @@ echo $COLORTERM  # Should output "truecolor" or "24bit"
 The built-in themes are selected by name: `dark`, `light`, `ice-cream-dark`, and `ice-cream-light`. When inspecting an installed package, their JSON assets are under `node_modules/@astralyn/pi/dist/modes/interactive/theme/` (the global-install equivalent is under Pi's npm package directory).
 
 The ice-cream palette and bundled design notes are documented in [Bundled themes](bundled/themes.md).
+
+## Use your terminal's colors
+
+The `system` theme is the default. It builds Pi's colors from your terminal's theme, so Pi matches the terminal instead of bringing its own palette:
+
+- Pi queries the terminal's default foreground and background colors and its 16 ANSI colors.
+- Each Pi color takes its hue from one ANSI color, for example errors from red and links from blue.
+- Pi sets each color's lightness so that it stands out from the background by a minimum contrast. Body text keeps at least a 4.5:1 WCAG contrast ratio on the background and every panel.
+- When the terminal switches between light and dark, Pi queries the colors again and rebuilds the theme.
+
+The theme adapts to what the terminal reports:
+
+| Terminal reports | Result |
+|---|---|
+| Background and ANSI colors | Colors from the terminal palette, placed for the actual background. |
+| Background only | Pi's own hues, placed for the actual background. |
+| Nothing | ANSI color indices and the terminal's default colors, which the terminal renders itself. Secondary text is faint, and panels have no background color. |
+
+Pi asks the terminal for its colors when it starts. Terminals usually answer within a few milliseconds, and Pi waits at most 100 ms before showing the startup header. If the terminal does not answer in time, Pi uses the ANSI color fallback, and it still applies the colors if they arrive later, for example over a slow SSH connection. `system` is a reserved name: a custom theme with that name is ignored.

package/docs/tui.md

@@ -828,4 +828,24 @@ PI_TUI_WRITE_LOG=/tmp/tui-ansi.log pi
 ## Additional examples
 
 - **Game loop and disposal:** [examples/extensions/snake.ts](../examples/extensions/snake.ts)
-- **Custom tool rendering:** [examples/extensions/todo.ts](../examples/extensions/todo.ts)
+- **Custom tool rendering:** [examples/extensions/built-in-tool-renderer.ts](../examples/extensions/built-in-tool-renderer.ts)
+
+## Combined theme styles
+
+Use `theme.style()` to combine foreground and background colors with text attributes:
+
+```typescript
+return new Text(
+  theme.style("Done!", {
+    fg: "success",
+    bg: "toolSuccessBg",
+    bold: true,
+  }),
+  0,
+  0,
+);
+```
+
+A style color can be a semantic theme token or a concrete `Color`. Foreground tokens are accepted as `fg` and background tokens as `bg`; to use a token's color in the other position, pass its concrete color, for example `{ fg: theme.colors.userMessageBg }`. Access concrete colors through `theme.colors` and use utilities such as `mixColors()` from `@earendil-works/pi-tui` when color math is needed. Tokens that a theme sets to the terminal default render with the terminal's own color; `theme.colors` reports the color the terminal announced for them, or a guess when it did not. Use `theme.appearance` (`"dark"` or `"light"`) to decide, for example, whether to lighten or darken a color. Pi converts the result to truecolor or 256-color output based on terminal capabilities. Theme tokens are converted once per theme; compute concrete colors outside the render path when possible.
+
+The existing `theme.fg()` and `theme.bg()` helpers remain available for applying one semantic color.

package/docs/usage.md

@@ -38,6 +38,7 @@ Type `/` in the editor to open command completion. Extensions can register custo
 |---------|-------------|
 | `/login`, `/logout` | Manage OAuth or API-key credentials |
 | [`/llama`](llama-cpp.md) | Download, load, and unload llama.cpp router models |
+| [`/mcp`](mcp.md) | Manage MCP servers, authentication, tools, and resources |
 | [`/btw [question]`](bundled/extensions/btw.md) | Open a temporary side conversation using the current context |
 | `/model` | Switch models; Ctrl+S in the picker saves the startup default |
 | `/thinking` | Switch thinking level; Ctrl+S in the picker saves the startup default |
@@ -185,7 +186,7 @@ cat README.md | pi -p "Summarize this text"
 
 | Option | Description |
 |--------|-------------|
-| `--provider <name>` | Provider, such as `anthropic`, `openai`, or `google` |
+| `--provider <name>` | Provider to search for `--model`, such as `anthropic` or `openai`; requires `--model` |
 | `--model <pattern>` | Model pattern or ID; supports `provider/id` and optional `:<thinking>` |
 | `--api-key <key>` | API key, overriding environment variables |
 | `--thinking <level>` | `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max` |
@@ -219,8 +220,8 @@ Built-in tools: `read`, `bash`, `powershell` (Windows), `edit`, `write`, `grep`,
 
 | Option | Description |
 |--------|-------------|
-| `-e`, `--extension <source>` | Load an extension from path, npm, or git; repeatable |
-| `--no-extensions` | Disable extension discovery |
+| `-e`, `--extension <source>` | Load an extension from path, npm, git, or `builtin:<name>`; repeatable |
+| `--no-extensions` | Disable discovered, configured, and built-in extensions; explicit `-e` entries still load |
 | `--skill <path>` | Load a skill; repeatable |
 | `--no-skills` | Disable skill discovery |
 | `--prompt-template <path>` | Load a prompt template; repeatable |
@@ -305,6 +306,53 @@ pi --exclude-tools ask_question
 
 Pi keeps the core small and pushes workflow-specific behavior into extensions, skills, prompt templates, and packages.
 
-This distribution ships selected workflows as hidden built-in extensions, including sub-agents, to-dos, and background bash tasks. It does not include built-in MCP or permission popups. You can build or install additional workflows as extensions or packages, or use external tools such as containers and tmux.
+Upstream Pi provides the llama.cpp integration, codemode, MCP, and tool search. This distribution adds Tasks, BTW, other workflow extensions, and its native tool presentation. See the [feature catalog](bundled/README.md) for their origins and usage. You can build or install additional workflows as extensions or packages.
 
 For the full rationale, read the [blog post](https://mariozechner.at/posts/2025-11-30-pi-coding-agent/).
+
+## Codemode and tool search
+
+Codemode and tool search are built-in extensions from [upstream Pi](https://github.com/earendil-works/pi), included in `@astralyn/pi`. Both tools are inactive by default; enable them explicitly or let the MCP extension activate them when needed.
+
+### Enable codemode
+
+To turn on `codemode` for every session, add it to the default tools in `~/.pi/agent/settings.json` or a project's `.pi/settings.json`:
+
+```json
+{
+  "defaultTools": ["+codemode"]
+}
+```
+
+This keeps `read`, `bash`, `edit`, and `write` and adds `codemode`. For one invocation, list every tool, since `--tools` replaces the selection:
+
+```sh
+pi --tools read,bash,edit,write,codemode
+```
+
+Codemode is useful without MCP: scripts can run several tool calls in parallel, filter large output before it reaches the model, call classifier models such as TypeSafe's Jev through `models.classify()` (see [Classifier models](models.md#use-classifier-models)), and generate images through `models.generateImages()` (see [Image models](models.md#use-image-models)).
+
+### How codemode works
+
+Scripts run in a QuickJS sandbox and reach the other tools through `tools.<name>(args)`. [Codemode](codemode.md) describes the script API, how tools are listed and found, the `store()` and `models` globals, and the limits.
+
+### Tool search
+
+`tool_search` is off by default; enable it with `"defaultTools": ["+tool_search"]` or `--tools`. It uses the same ranking as `searchTools()` over tools that are not declared yet and declares the matches for the next model call. Loaded tools are recorded in the session like other tool changes, so they stay declared on that branch.
+
+## MCP commands
+
+These commands work outside a session, so agents can run them through `bash`. See [MCP Servers](mcp.md).
+
+| Command | Description |
+|---|---|
+| `pi mcp add <server> [options] -- <command> [args...]` | Add or replace a stdio server in `mcp.json`; `--env KEY=VALUE` (repeatable) and `--cwd <dir>` set its environment and working directory. Arguments after the command are passed to it |
+| `pi mcp add <server> [options] --url <url>` | Add or replace a streamable HTTP server; `--header KEY=VALUE` (repeatable), `--bearer-token-env-var <NAME>` (sends `Authorization: Bearer ${NAME}`), `--oauth-client-id`, `--oauth-client-secret`, `--oauth-callback-port`, and `--oauth-client-name` configure authentication |
+| `pi mcp remove <server>` | Remove a server from `mcp.json`; stored OAuth credentials are kept |
+| `pi mcp list [--json]` | Connect to every enabled server and print its state, tools, and errors; exit with `1` when a config entry is invalid or an enabled server is not connected |
+| `pi mcp login <server> [--timeout <seconds>]` | Sign in to an OAuth server: open the authorization page and wait for the browser (default 300 seconds); a terminal also accepts the pasted redirect URL |
+| `pi mcp logout <server>` | Delete the stored OAuth credentials of a server |
+
+`add` and `remove` change `~/.pi/agent/mcp.json`, or `.pi/mcp.json` in the current directory with `--local` (`-l`). `add` also takes `--exposure <mode>` (see [Exposure](mcp.md#exposure)) and `--description <text>` and does not connect; run `pi mcp list` to check the server.
+
+Project `.pi/mcp.json` files are only read for projects that are already trusted.

package/docs/virtual-models.md

@@ -0,0 +1,114 @@
+# Virtual Models
+
+A virtual model is a selectable model that picks a physical model for each request. Use one to route by task, cost, or conversation state. For example, a router can send quick questions to a small model and hard problems to a large one, while the user selects a single model.
+
+Register virtual models from an [extension](extensions.md). They appear in `/model`, `--model`, scoped models, and settings like any other model. A virtual model can be listed under any provider, including one with physical models, such as `openai-codex/auto`.
+
+## Selection and dispatch
+
+A virtual model selects a model and a thinking level. A router maps that pair to a physical pair for each request:
+
+```
+selected (virtual model, virtual level)  ->  dispatched (physical model, physical level)
+jev/auto:low                             ->  anthropic/claude-sonnet-4-5:high
+```
+
+The virtual thinking level is an input to the router. Its meaning is up to the router; it need not correspond to a reasoning budget.
+
+Pi keeps the two pairs apart:
+
+| | Selection | Dispatch |
+|---|---|---|
+| Recorded in | `model_change` and `thinking_level_change` entries | Each assistant message: `provider`, `api`, `model`, `thinkingLevel` |
+| Visible as | `ctx.model`, `ctx.thinkingLevel`, `PI_MODEL`, `PI_REASONING_LEVEL`, `/model` | The assistant message of each response |
+
+Providers only receive physical models. Assistant messages name the physical model, so replaying a conversation across different physical models works the same as after a manual model switch. Resuming a session restores the virtual selection from its latest `model_change` entry. If the virtual model is no longer registered, Pi falls back to the physical model that answered last.
+
+In interactive mode, the footer shows the routed model next to the selection, for example `auto • high → gpt-5.6-luna • medium`. `/session` lists the cost for each physical model.
+
+Context usage uses the limits of the physical model that produced the latest response, even if that response came before switching to the virtual model. Without such a response, it uses the limits declared on the virtual model, if any. Compaction checks the same limits, and again the limits of the model each request is routed to. If that model's context window is too small for the conversation, Pi compacts before sending the request; the route stays as the router chose it.
+
+## Register a virtual model
+
+```typescript
+import type { ExtensionAPI } from "@astralyn/pi";
+
+export default function (pi: ExtensionAPI) {
+  pi.registerVirtualModel({
+    provider: "router",
+    id: "auto",
+    name: "Auto",
+    thinkingLevels: ["low", "high"],
+    route(request, ctx) {
+      // Tool follow-ups and retries stay on the model that handled the turn.
+      const sticky = request.failed ?? request.previous;
+      if (request.reason !== "user" && sticky) {
+        return { model: sticky.model, thinkingLevel: sticky.thinkingLevel ?? "medium" };
+      }
+      const id = request.thinkingLevel === "high" ? "claude-sonnet-4-5" : "claude-haiku-4-5";
+      return { model: ctx.modelRegistry.find("anthropic", id)!, thinkingLevel: "medium" };
+    },
+  });
+}
+```
+
+- `provider` is the provider the model is listed under. It can be any provider ID. A provider can list several virtual models next to its physical ones. On a physical provider, the virtual model is available when that provider has credentials. Under an ID that no provider uses, it is always available.
+- `id` must not be the ID of a physical model of that provider. If a catalog refresh later adds a physical model with the same ID, the virtual model hides it.
+- `thinkingLevels` lists the levels offered for selection. It defaults to `["off"]`.
+- `contextWindow` and `maxTokens` are shown before the first response. Unset limits are unknown.
+- `input` lists the input types offered for selection. It defaults to text and images; physical models without image support receive placeholders.
+
+Registration follows the same queuing and reload rules as `pi.registerProvider()`. Registering the same provider and ID again replaces the virtual model. `pi.unregisterVirtualModel(provider, id)` removes it; `pi.unregisterProvider()` does not. SDK code can register one without an extension: `modelRuntime.registerVirtualModel(definition)`.
+
+## Route requests
+
+`route(request, ctx)` runs before every request made with the virtual model and returns `{ model, thinkingLevel }`. The model can be any physical model in the catalog whose provider has credentials; look it up with `ctx.modelRegistry`. A virtual model cannot route to another virtual model. Pi clamps the thinking level to the returned model.
+
+| Field | Meaning |
+|---|---|
+| `model`, `thinkingLevel` | The selected virtual model and level |
+| `reason` | Why the request is made, see below |
+| `previous` | Physical model and thinking level of the latest successful response in `messages` |
+| `failed` | For `retry`: physical model, thinking level, and assistant `message` of the failed request, which `messages` no longer contains. The message carries `stopReason` and `errorMessage`. Absent when routing itself failed |
+| `state` | Router state last returned on this session branch, see below |
+| `messages` | The conversation for this request, including system messages |
+| `signal` | Abort signal of the request |
+
+| `reason` | Request |
+|---|---|
+| `user` | First request after a message the user wrote, including steering and follow-up messages |
+| `continuation` | Any other request in the agent loop, such as after tool results or extension messages |
+| `retry` | Automatic retry after a failed request, including after compaction for a context overflow |
+| `direct` | Request made outside the agent loop, such as a compaction summary or an extension calling `ctx.modelRegistry.streamSimple()` |
+
+Returning `previous` for `continuation` and `failed` for `retry` keeps prompt caches and thinking signatures valid. Switching models between turns is allowed but loses the prompt cache. A retry can also switch to another model, for example when `failed.message.errorMessage` reports that a provider is overloaded or the context overflowed.
+
+If `route()` throws, or returns a virtual model or a model without credentials, the request ends with an error response.
+
+## Keep routing state
+
+`route()` can return `state` next to the model. Pi stores it on the session branch and passes it back as `request.state` on later requests. Use it for decisions the transcript does not record, such as classifier results or a routing phase:
+
+```typescript
+pi.registerVirtualModel<{ phase: "plan" | "build" }>({
+  provider: "router",
+  id: "phased",
+  name: "Phased",
+  route(request, ctx) {
+    const state = request.state ?? { phase: "plan" };
+    const id = state.phase === "plan" ? "claude-opus-4-5" : "claude-haiku-4-5";
+    return { model: ctx.modelRegistry.find("anthropic", id)!, thinkingLevel: "medium", state };
+  },
+});
+```
+
+- State must be JSON-serializable. Returning `undefined` or `request.state` itself keeps the current state.
+- Pi stores any other returned object as new state, before the request is sent, even when it equals the current state. Return a new object only when the state changes. The state stays stored if the request later fails.
+- State follows the session tree, so forks and `/tree` navigation see the state of their branch. It survives compaction.
+- `direct` requests have no state, and Pi ignores state they return.
+
+The transcript already records the selection and every dispatched model, and `ctx.sessionManager.getBranch()` exposes both.
+
+Routers can call other models through `ctx.modelRegistry`, for example `ctx.modelRegistry.classify()` with a classifier model from `ctx.modelRegistry.findOfType("classifier", provider, id)`. The call adds latency before the first token of the turn.
+
+See [`jev-router.ts`](../examples/extensions/jev-router.ts) for a complete router. It plans on a strong OpenAI Codex model chosen by the Jev classifier, lets that model make the first edit, and then switches once to a cheaper model, accepting a single prompt-cache miss. It keeps the phase as router state.

package/docs/windows.md

@@ -37,3 +37,5 @@ The `!` and `!!` editor commands still use Bash.
   "shellPath": "C:\\cygwin64\\bin\\bash.exe"
 }
 ```
+
+`"defaultTools": ["-bash", "+powershell"]` replaces Bash while preserving other configured default tools.

package/examples/README.md

@@ -10,7 +10,7 @@ Runs one prompt through a Pi RPC child process with the typed `RpcClient`: it st
 Build the package before running it from a repository checkout:
 
 ```bash
-npx tsx examples/rpc-client.ts "Explain this repository"
+node examples/rpc-client.ts "Explain this repository"
 ```
 
 ### [rpc-extension-ui.ts](rpc-extension-ui.ts)
@@ -24,7 +24,7 @@ Programmatic usage via `createAgentSession()`. Shows how to customize models, pr
 ### [extensions/](extensions/)
 Example extensions demonstrating:
 - Lifecycle event handlers (tool interception, safety gates, context modifications)
-- Custom tools (todo lists, questions, output truncation)
+- Custom tools (questions, output truncation)
 - Commands and keyboard shortcuts
 - Custom UI (footers, headers, editors, overlays)
 - Git integration (checkpoints, auto-commit)

package/examples/extensions/README.md

@@ -30,7 +30,6 @@ cp permission-gate.ts ~/.pi/agent/extensions/
 
 | Extension | Description |
 |-----------|-------------|
-| `todo.ts` | Todo list tool + `/todos` command with custom rendering and state persistence |
 | `hello.ts` | Minimal custom tool example |
 | `question.ts` | Demonstrates `ctx.ui.select()` for asking the user questions with custom UI |
 | `questionnaire.ts` | Multi-question input with tab bar navigation between questions |
@@ -113,6 +112,7 @@ cp permission-gate.ts ~/.pi/agent/extensions/
 |-----------|-------------|
 | `message-renderer.ts` | Custom message rendering with colors and expandable details via `registerMessageRenderer` |
 | `entry-renderer.ts` | TUI-only session entry rendering via `appendEntry` and `registerEntryRenderer` |
+| `debug-provider.ts` | Toggle raw provider stream capture with `/debug-provider` and inspect each assistant message in a TUI-only session entry |
 | `event-bus.ts` | Inter-extension communication via `pi.events` |
 
 ### Session Metadata
@@ -128,6 +128,7 @@ cp permission-gate.ts ~/.pi/agent/extensions/
 |-----------|-------------|
 | `custom-provider-anthropic/` | Custom Anthropic provider with OAuth support and custom streaming implementation |
 | `custom-provider-gitlab-duo/` | GitLab Duo provider using pi-ai's built-in Anthropic/OpenAI streaming via proxy |
+| `jev-router.ts` | Virtual model via `registerVirtualModel` that plans on Codex Sol or Terra (picked by the Jev classifier) and switches to Luna after the first edit |
 
 ### External Dependencies
 
@@ -197,7 +198,7 @@ action: Type.Union([Type.Literal("list"), Type.Literal("add")])
 // Store state in tool result details for proper forking support
 return {
   content: [{ type: "text", text: "Done" }],
-  details: { todos: [...todos], nextId },  // Persisted in session
+  details: { items: [...items], nextId },  // Persisted in session
 };
 
 // Reconstruct on session events

package/examples/extensions/built-in-tool-renderer.ts

@@ -12,8 +12,8 @@
  *
  * How it works:
  * - registerTool() with the same name as a built-in replaces it entirely
- * - We create instances of the original tools via createReadTool(), etc.
- *   and delegate execute() to them
+ * - We create the original definitions via createReadToolDefinition(), etc.
+ *   and override only their renderers
  * - renderCall() controls what's shown when the tool is invoked
  * - renderResult() controls what's shown after execution completes
  * - renderShell: "self" lets a tool render its own outer shell instead of
@@ -26,23 +26,21 @@
  */
 
 import type { BashToolDetails, EditToolDetails, ExtensionAPI, ReadToolDetails } from "@earendil-works/pi-coding-agent";
-import { createBashTool, createEditTool, createReadTool, createWriteTool } from "@earendil-works/pi-coding-agent";
+import {
+	createBashToolDefinition,
+	createEditToolDefinition,
+	createReadToolDefinition,
+	createWriteToolDefinition,
+} from "@earendil-works/pi-coding-agent";
 import { Text } from "@earendil-works/pi-tui";
 
 export default function (pi: ExtensionAPI) {
 	const cwd = process.cwd();
 
 	// --- Read tool: show path and line count ---
-	const originalRead = createReadTool(cwd);
+	const originalRead = createReadToolDefinition(cwd);
 	pi.registerTool({
-		name: "read",
-		label: "read",
-		description: originalRead.description,
-		parameters: originalRead.parameters,
-
-		async execute(toolCallId, params, signal, onUpdate) {
-			return originalRead.execute(toolCallId, params, signal, onUpdate);
-		},
+		...originalRead,
 
 		renderCall(args, theme, _context) {
 			let text = theme.fg("toolTitle", theme.bold("read "));
@@ -92,16 +90,9 @@ export default function (pi: ExtensionAPI) {
 	});
 
 	// --- Bash tool: show command and exit code ---
-	const originalBash = createBashTool(cwd);
+	const originalBash = createBashToolDefinition(cwd);
 	pi.registerTool({
-		name: "bash",
-		label: "bash",
-		description: originalBash.description,
-		parameters: originalBash.parameters,
-
-		async execute(toolCallId, params, signal, onUpdate) {
-			return originalBash.execute(toolCallId, params, signal, onUpdate);
-		},
+		...originalBash,
 
 		renderCall(args, theme, _context) {
 			let text = theme.fg("toolTitle", theme.bold("$ "));
@@ -151,17 +142,9 @@ export default function (pi: ExtensionAPI) {
 	});
 
 	// --- Edit tool: show path and diff stats ---
-	const originalEdit = createEditTool(cwd);
+	const originalEdit = createEditToolDefinition(cwd);
 	pi.registerTool({
-		name: "edit",
-		label: "edit",
-		description: originalEdit.description,
-		parameters: originalEdit.parameters,
-		renderShell: "self",
-
-		async execute(toolCallId, params, signal, onUpdate) {
-			return originalEdit.execute(toolCallId, params, signal, onUpdate);
-		},
+		...originalEdit,
 
 		renderCall(args, theme, _context) {
 			let text = theme.fg("toolTitle", theme.bold("edit "));
@@ -216,16 +199,9 @@ export default function (pi: ExtensionAPI) {
 	});
 
 	// --- Write tool: show path and size ---
-	const originalWrite = createWriteTool(cwd);
+	const originalWrite = createWriteToolDefinition(cwd);
 	pi.registerTool({
-		name: "write",
-		label: "write",
-		description: originalWrite.description,
-		parameters: originalWrite.parameters,
-
-		async execute(toolCallId, params, signal, onUpdate) {
-			return originalWrite.execute(toolCallId, params, signal, onUpdate);
-		},
+		...originalWrite,
 
 		renderCall(args, theme, _context) {
 			let text = theme.fg("toolTitle", theme.bold("write "));

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

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.87.1",
+  "version": "1.0.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.87.1",
+      "version": "1.0.0",
       "dependencies": {
         "@anthropic-ai/sdk": "^0.52.0"
       }

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

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-anthropic",
   "private": true,
-  "version": "0.87.1",
+  "version": "1.0.0",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

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

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-gitlab-duo",
   "private": true,
-  "version": "0.87.1",
+  "version": "1.0.0",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/custom-provider-gitlab-duo/test.ts

@@ -1,11 +1,11 @@
 /**
  * Test script for GitLab Duo extension
- * Run: npx tsx test.ts [model-id] [--thinking]
+ * Run: node test.ts [model-id] [--thinking]
  *
  * Examples:
- *   npx tsx test.ts                              # Test default (claude-sonnet-4-5-20250929)
- *   npx tsx test.ts gpt-5-codex                  # Test GPT-5 Codex
- *   npx tsx test.ts claude-sonnet-4-5-20250929 --thinking
+ *   node test.ts                              # Test default (claude-sonnet-4-5-20250929)
+ *   node test.ts gpt-5-codex                  # Test GPT-5 Codex
+ *   node test.ts claude-sonnet-4-5-20250929 --thinking
  */
 
 import { getAgentDir } from "@astralyn/pi";

package/examples/extensions/debug-provider.ts

@@ -0,0 +1,90 @@
+/**
+ * Raw provider event viewer.
+ *
+ * Usage: /debug-provider [on|off]
+ * With no argument, the command toggles capture. Captured events are persisted
+ * as expandable custom entries.
+ */
+
+import { type ExtensionAPI, keyHint } from "@earendil-works/pi-coding-agent";
+import { Box, Text } from "@earendil-works/pi-tui";
+
+const ENTRY_TYPE = "debug-provider-events";
+const STATUS_KEY = "debug-provider";
+
+interface ProviderDebugEntry {
+	provider: string;
+	api: string;
+	model: string;
+	events: unknown[];
+}
+
+export default function (pi: ExtensionAPI) {
+	let enabled = false;
+	let activeEvents: unknown[] | undefined;
+	let completedEntry: ProviderDebugEntry | undefined;
+
+	pi.registerEntryRenderer<ProviderDebugEntry>(ENTRY_TYPE, (entry, { expanded }, theme) => {
+		const data = entry.data;
+		if (!data) return new Text(theme.fg("warning", "[provider debug] Missing event data"), 0, 0);
+
+		const box = new Box(1, 1, (text) => theme.bg("customMessageBg", text));
+		const count = `${data.events.length} event${data.events.length === 1 ? "" : "s"}`;
+		const expandHint = expanded ? "" : ` (${keyHint("app.tools.expand", "to view events")})`;
+		box.addChild(
+			new Text(
+				`${theme.fg("accent", "[provider debug]")} ${data.provider}/${data.model} (${data.api}) · ${count}${expandHint}`,
+				0,
+				0,
+			),
+		);
+		if (expanded) {
+			box.addChild(new Text(JSON.stringify(data.events, null, 2), 0, 0));
+		}
+		return box;
+	});
+
+	pi.registerCommand("debug-provider", {
+		description: "Toggle capture of raw provider stream events",
+		handler: async (args, ctx) => {
+			const requestedState = args.trim().toLowerCase();
+			if (requestedState !== "" && requestedState !== "on" && requestedState !== "off") {
+				ctx.ui.notify("Usage: /debug-provider [on|off]", "warning");
+				return;
+			}
+
+			enabled = requestedState === "" ? !enabled : requestedState === "on";
+			if (!enabled) {
+				activeEvents = undefined;
+				completedEntry = undefined;
+			}
+			ctx.ui.setStatus(STATUS_KEY, enabled ? "provider debug" : undefined);
+			ctx.ui.notify(`Provider event capture ${enabled ? "enabled" : "disabled"}`, "info");
+		},
+	});
+
+	pi.on("turn_start", () => {
+		activeEvents = enabled ? [] : undefined;
+	});
+
+	pi.on("provider_stream_event", (event) => {
+		activeEvents?.push(structuredClone(event.data));
+	});
+
+	pi.on("message_end", (event) => {
+		if (event.message.role !== "assistant" || !activeEvents) return;
+		completedEntry = {
+			provider: event.message.provider,
+			api: event.message.api,
+			model: event.message.model,
+			events: activeEvents,
+		};
+		activeEvents = undefined;
+	});
+
+	pi.on("turn_end", () => {
+		if (!completedEntry) return;
+		pi.appendEntry<ProviderDebugEntry>(ENTRY_TYPE, completedEntry);
+		completedEntry = undefined;
+	});
+}