@astralyn/pi 0.83.0 → 0.84.0

package/docs/development.md

@@ -0,0 +1,83 @@
+# Development
+
+This repository is the standalone distribution of `@astralyn/pi`. It publishes one package and the `pi` executable; runtime source lives under `src/**`.
+
+## Requirements
+
+- Node.js `>=22.19`
+- npm
+
+The package consumes the published `@earendil-works/pi-ai`, `@earendil-works/pi-agent-core`, and `@earendil-works/pi-tui` dependencies. It does not recreate the upstream monorepo or vendor those packages.
+
+## Install and run
+
+Install dependencies without running lifecycle scripts:
+
+```bash
+npm install --ignore-scripts
+```
+
+Run the CLI directly from TypeScript source:
+
+```bash
+npm run dev
+```
+
+To run without provider credentials from the current environment:
+
+```bash
+npm run dev -- --no-env
+```
+
+Build the distributable package and assets:
+
+```bash
+npm run build
+```
+
+The compiled CLI is `dist/cli.js`. The package's executable is `pi`.
+
+## Verification
+
+Run the repository checks after code changes:
+
+```bash
+npm run check
+```
+
+This runs Biome, dependency and import checks, documentation-link validation, and TypeScript checks for source and examples.
+
+Run focused tests for changed behavior:
+
+```bash
+npx vitest run test/<changed-file>.test.ts
+```
+
+Run all tests in an isolated home and configuration directory:
+
+```bash
+npm run test:isolated
+```
+
+Validate the exact upstream release baseline and local deviations:
+
+```bash
+npm run diff:upstream -- --check
+```
+
+For interactive changes, also test in a real TTY, including pending and settled tool output, collapsed and expanded states, and relevant `/reload` or `/tree` flows.
+
+## Repository layout
+
+- `src/**` - runtime source
+- `src/extensions/**` - bundled extensions using the public Extension API
+- `test/**` - focused Vitest tests and fixtures
+- `docs/**` - published user and API documentation
+- `maintainers/**` - repository-only maintainer runbooks
+- `scripts/**` - development, verification, and release helpers
+
+## Boundaries
+
+Keep the upstream runtime contracts intact. Do not vendor or patch the AI, Agent core, or TUI dependencies. Preserve tool schemas, execution protocols, and result structures when changing display-only behavior. Keep direct dependencies pinned and regenerate `npm-shrinkwrap.json` intentionally when dependency metadata changes.
+
+Read the repository contract in `AGENTS.md` and the maintainer architecture and release guidance in `maintainers/README.md` before making changes.

package/docs/docs.json

@@ -39,13 +39,13 @@
           "title": "Keybindings",
           "path": "keybindings.md"
         },
-        {
-          "title": "Sessions",
-          "path": "sessions.md"
-        },
         {
           "title": "Compaction",
           "path": "compaction.md"
+        },
+        {
+          "title": "Development",
+          "path": "development.md"
         }
       ]
     },
@@ -56,6 +56,10 @@
           "title": "Overview",
           "path": "bundled/README.md"
         },
+        {
+          "title": "Biu",
+          "path": "bundled/extensions/biu.md"
+        },
         {
           "title": "DeepWiki",
           "path": "bundled/extensions/deepwiki.md"

package/docs/extensions.md

@@ -1584,6 +1584,27 @@ mode and would not execute if sent via `prompt`.
 
 Register a custom TUI renderer for custom messages with your `customType`. Custom messages are created with `pi.sendMessage()` and participate in LLM context. See [Custom UI](#custom-ui).
 
+### pi.registerMarkdownTransformer(transformer)
+
+Register a transformer for the Markdown in normal user text, assistant text, and thinking blocks. Transformers run in extension load order, and each transformer receives the Markdown returned by the previous transformer. After the chain finishes, Pi renders the transformed content with its built-in renderer.
+
+The transformer receives the Markdown string and a context with:
+
+- `messageType` — `"user"`, `"assistant"`, or `"assistant-thinking"`
+- `isStreaming` — `true` for partial assistant updates; `false` for user, finalized assistant, and restored messages
+- `availableWidth` — exact terminal columns available for the transformed Markdown content
+
+Return the transformed Markdown:
+
+```typescript
+pi.registerMarkdownTransformer((markdown, { messageType, isStreaming }) => {
+  if (isStreaming || messageType === "assistant-thinking") return markdown;
+  return markdown.replaceAll("-->", "→");
+});
+```
+
+If a transformer throws, Pi keeps the Markdown produced so far and continues with the next transformer. The hook is display-only: the original message remains unchanged in the session and model context. It runs for new user messages, assistant streaming updates, restored session messages, and terminal width changes, so transformers should remain synchronous and inexpensive.
+
 ### pi.registerEntryRenderer(customType, renderer)
 
 Register a custom TUI renderer for custom entries with your `customType`. Custom entries are created with `pi.appendEntry()` and do not participate in LLM context.
@@ -1708,7 +1729,9 @@ Register or override a model provider dynamically. Useful for proxies, custom en
 
 Calls made during the extension factory function are queued and applied once the runner initialises. Calls made after that — for example from a command handler following a user setup flow — take effect immediately without requiring a `/reload`.
 
-Dynamic providers can implement `refreshModels`. Pi calls it during model refresh, publishes the returned list synchronously through the provider, and passes the canonical credential/store/network/signal context. The extension decides whether to persist the catalog through `context.store`; live servers such as llama.cpp can ignore it.
+Dynamic providers can implement `refreshModels`. Pi calls it during model refresh, publishes the returned list synchronously through the provider, and passes the canonical credential/stored-catalog/network/signal context. The extension decides whether to persist catalog metadata through generation-checked `context.publish({ persist: entry })`; live servers such as llama.cpp can return models without persisting them.
+
+`context.signal` is always a concrete signal and provider callbacks must pass it to blocking I/O. Public `ModelRuntime.refresh()` and `ModelRegistry.refresh()` calls accept an optional signal and are unbounded when it is omitted; extensions and applications choose their own deadlines. Cancellation stops the caller waiting even if a provider ignores the signal, but cooperation is still required to stop the underlying work.
 
 Extensions that need native provider auth, filtering, refresh, or stream behavior can register a complete `Provider` from `@earendil-works/pi-ai`. The provider becomes the composition base and `models.json` overrides still apply above it.
 
@@ -1798,7 +1821,8 @@ pi.registerProvider("corporate-ai", {
       const code = await callbacks.onPrompt({ message: "Enter code:" });
       return { refresh: code, access: code, expires: Date.now() + 3600000 };
     },
-    async refreshToken(credentials) {
+    async refreshToken(credentials, signal) {
+      signal.throwIfAborted();
       // Refresh logic
       return credentials;
     },
@@ -1819,7 +1843,7 @@ The object form accepts a complete pi-ai `Provider`, including native `auth`, `g
 - `headers` - Custom headers to include in requests.
 - `authHeader` - If true, adds `Authorization: Bearer` header automatically.
 - `models` - Array of model definitions. If provided, replaces all existing models for this provider. Model definitions can set `baseUrl` to override the provider endpoint for that model.
-- `refreshModels` - Async dynamic discovery callback. Its returned models replace extension-provided models. Use the scoped `context.store` only when results should persist.
+- `refreshModels` - Async dynamic discovery callback. Its returned models replace extension-provided models. `context.stored` contains the persisted provider snapshot; use generation-checked `context.publish({ persist: entry })` only when updated catalog data should persist. Use `persist: null` to delete that snapshot.
 - `oauth` - OAuth provider config for `/login` support. When provided, the provider appears in the login menu.
 - `streamSimple` - Custom streaming implementation for non-standard APIs.
 

package/docs/json.md

@@ -8,7 +8,20 @@ Outputs all session events as JSON lines to stdout. Useful for integrating pi in
 
 ## Event Types
 
-Events are defined by `AgentSessionEvent`, exported from [`@astralyn/pi`](https://www.npmjs.com/package/@astralyn/pi):
+Wire events use `JsonAgentSessionEvent`, exported from [`@astralyn/pi`](https://www.npmjs.com/package/@astralyn/pi). It matches `AgentSessionEvent` except that streaming message updates omit cumulative snapshots:
+
+```typescript
+type WithoutPartial<T> = T extends { partial: unknown } ? Omit<T, "partial"> : T;
+
+type JsonAgentSessionEvent =
+  | Exclude<AgentSessionEvent, { type: "message_update" }>
+  | {
+      type: "message_update";
+      assistantMessageEvent: WithoutPartial<AssistantMessageEvent>;
+    };
+```
+
+Session events are defined by `AgentSessionEvent`:
 
 ```typescript
 type AgentSessionEvent =
@@ -29,6 +42,7 @@ type AgentSessionEvent =
   | { type: "summarization_retry_finished" }
   | { type: "bash_execution_update"; id?: string; delta: string };
 ```
+```
 
 `queue_update` emits the full pending steering and follow-up queues whenever they change. `compaction_start` and `compaction_end` cover both manual and automatic compaction.
 
@@ -79,12 +93,17 @@ Followed by events as they occur:
 {"type":"agent_start"}
 {"type":"turn_start"}
 {"type":"message_start","message":{"role":"assistant","content":[],...}}
-{"type":"message_update","message":{...},"assistantMessageEvent":{"type":"text_delta","delta":"Hello",...}}
+{"type":"message_update","assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":"Hello"}}
 {"type":"message_end","message":{...}}
 {"type":"turn_end","message":{...},"toolResults":[]}
 {"type":"agent_end","messages":[...],"willRetry":false}
 ```
 
+`message_update` records are delta-only. They omit both the cumulative `message` field and
+`assistantMessageEvent.partial` to keep stream size linear. Use `contentIndex` and `delta`
+to assemble live text, thinking, or tool-call arguments if needed. `message_end` contains
+the final authoritative message.
+
 ## Example
 
 ```bash

package/docs/keybindings.md

@@ -26,18 +26,22 @@ Modifier combinations: `ctrl+shift+x`, `alt+ctrl+x`, `ctrl+shift+alt+x`, `ctrl+1
 
 | Keybinding id | Default | Description |
 |--------|---------|-------------|
-| `tui.editor.cursorUp` | `up` | Move cursor up |
-| `tui.editor.cursorDown` | `down` | Move cursor down |
+| `tui.editor.cursorUp` | `up` | Move cursor up, browsing older history at the top |
+| `tui.editor.cursorDown` | `down` | Move cursor down, browsing newer history at the bottom |
+| `tui.editor.historyPrevious` | *(none)* | Select the previous prompt history entry |
+| `tui.editor.historyNext` | *(none)* | Select the next prompt history entry |
 | `tui.editor.cursorLeft` | `left`, `ctrl+b` | Move cursor left |
 | `tui.editor.cursorRight` | `right`, `ctrl+f` | Move cursor right |
 | `tui.editor.cursorWordLeft` | `alt+left`, `ctrl+left`, `alt+b` | Move cursor word left |
 | `tui.editor.cursorWordRight` | `alt+right`, `ctrl+right`, `alt+f` | Move cursor word right |
-| `tui.editor.cursorLineStart` | `home`, `ctrl+a` | Move to line start |
-| `tui.editor.cursorLineEnd` | `end`, `ctrl+e` | Move to line end |
+| `tui.editor.cursorLineStart` | `home`, `ctrl+home`, `ctrl+a` | Move to line start |
+| `tui.editor.cursorLineEnd` | `end`, `ctrl+end`, `ctrl+e` | Move to line end |
 | `tui.editor.jumpForward` | `ctrl+]` | Jump forward to character |
 | `tui.editor.jumpBackward` | `ctrl+alt+]` | Jump backward to character |
-| `tui.editor.pageUp` | `pageUp` | Scroll up by page |
-| `tui.editor.pageDown` | `pageDown` | Scroll down by page |
+| `tui.editor.pageUp` | `pageUp`, `ctrl+pageUp` | Scroll up by page |
+| `tui.editor.pageDown` | `pageDown`, `ctrl+pageDown` | Scroll down by page |
+
+The dedicated history actions always change history entries, regardless of the cursor position in a multiline prompt. Explicit history bindings take precedence over application actions while the main editor is focused, so binding `tui.editor.historyPrevious` to `ctrl+p` overrides model cycling in that context without changing `Ctrl+P` in selectors.
 
 ### TUI Editor Deletion
 
@@ -78,6 +82,30 @@ Modifier combinations: `ctrl+shift+x`, `alt+ctrl+x`, `ctrl+shift+alt+x`, `ctrl+1
 | `tui.select.confirm` | `enter` | Confirm selection |
 | `tui.select.cancel` | `escape`, `ctrl+c` | Cancel selection |
 
+### TUI Fullscreen Viewport
+
+These actions apply when interactive mode uses `--tui-mode fullscreen` and target the primary transcript scroll region. Two-finger trackpad and mouse-wheel input scroll the region under the pointer, falling back to the transcript over the fixed editor/status/footer dock. Clicking an OSC 8 hyperlink opens it in the default handler. Dragging with the primary mouse button selects text and copies it to the clipboard; holding at the transcript's top or bottom edge auto-scrolls into off-screen content.
+
+Fullscreen transcript bindings take precedence over editor bindings. The default unmodified navigation keys therefore control the transcript in fullscreen mode, while their `ctrl` variants continue to control the editor. Outside fullscreen mode, both variants control the editor.
+
+| Key | Default mode | Fullscreen mode |
+|-----|--------------|-----------------|
+| `home`, `end` | Editor | Transcript |
+| `ctrl+home`, `ctrl+end` | Editor | Editor |
+| `pageUp`, `pageDown` | Editor | Transcript |
+| `ctrl+pageUp`, `ctrl+pageDown` | Editor | Editor |
+
+This routing remains configurable through the ordinary action bindings. For example, `"tui.altScreen.pageUp": "ctrl+pageUp"` makes `pageUp` control the editor and `ctrl+pageUp` control the transcript in fullscreen mode. Setting `"tui.altScreen.pageUp": []` disables that transcript shortcut entirely. User bindings replace the defaults for that action.
+
+| Keybinding id | Default | Description |
+|--------|---------|-------------|
+| `tui.altScreen.pageUp` | `pageUp` | Scroll the transcript up by one page |
+| `tui.altScreen.pageDown` | `pageDown` | Scroll the transcript down by one page |
+| `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.top` | `home` | Scroll to the beginning of the transcript |
+| `tui.altScreen.bottom` | `end` | Scroll to the transcript end and follow new output |
+
 ### Application
 
 | Keybinding id | Default | Description |
@@ -158,8 +186,8 @@ Create `~/.pi/agent/keybindings.json`:
 
 ```json
 {
-  "tui.editor.cursorUp": ["up", "ctrl+p"],
-  "tui.editor.cursorDown": ["down", "ctrl+n"],
+  "tui.editor.historyPrevious": "ctrl+p",
+  "tui.editor.historyNext": "ctrl+n",
   "tui.editor.deleteWordBackward": ["ctrl+w", "alt+backspace"]
 }
 ```
@@ -172,8 +200,8 @@ On native Windows, `app.suspend` has no default binding because Windows terminal
 
 ```json
 {
-  "tui.editor.cursorUp": ["up", "ctrl+p"],
-  "tui.editor.cursorDown": ["down", "ctrl+n"],
+  "tui.editor.historyPrevious": "ctrl+p",
+  "tui.editor.historyNext": "ctrl+n",
   "tui.editor.cursorLeft": ["left", "ctrl+b"],
   "tui.editor.cursorRight": ["right", "ctrl+f"],
   "tui.editor.cursorWordLeft": ["alt+left", "alt+b"],

package/docs/models.md

@@ -244,6 +244,7 @@ A `models` entry supplies a complete custom model definition with useful default
 | `input` | No | `["text"]` | Supported input kinds: `text` and `image`. |
 | `contextWindow` | No | `128000` | Context window in tokens. |
 | `maxTokens` | No | `16384` | Maximum generated tokens. |
+| `samplingParams` | No | omitted | Free-form sampling parameters merged verbatim into every request body; see [Sampling Parameters](#sampling-parameters). |
 | `cost` | No | all rates `0` | Per-million-token rates and optional request-wide price tiers. |
 | `headers` | No | omitted | Model-specific request headers; see [Custom Headers](#custom-headers). |
 | `compat` | No | provider `compat` | Compatibility refinements merged with provider defaults. |
@@ -272,6 +273,23 @@ When `cost` is supplied on a `models` entry, it must contain all four base rates
 }
 ```
 
+### Sampling Parameters
+
+`samplingParams` is a free-form object merged verbatim into every request body for the model, after the fields pi sets itself, so its keys win. Use it to send sampling parameters pi does not model — including server-specific ones like llama.cpp's `min_p` or vLLM's `top_k`:
+
+```json
+{
+  "id": "deepseek-v4-flash",
+  "samplingParams": {
+    "temperature": 1.0,
+    "top_p": 0.95,
+    "top_k": 0,
+    "min_p": 0.0
+  }
+}
+```
+
+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.
 ### Thinking Level Map
 
 `thinkingLevelMap` uses these Pi levels: `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. It only affects a model with `reasoning: true`; a non-reasoning model exposes `off` only.
@@ -369,9 +387,7 @@ The built-in models remain. A new custom `id` is added, while a matching ID is r
 }
 ```
 
-An override supports `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, and `compat`. Its `cost` base rates are individually optional and retain omitted values; a supplied `tiers` array replaces the existing array. Thinking maps merge by level. `compat` merges by field, and its `openRouterRouting`, `vercelGatewayRouting`, and `chatTemplateKwargs` objects merge by key.
-
-If an override and a `models` entry use the same ID, the override still changes the final model. For headers only, the `models` entry wins on a duplicate header name as described in [Custom Headers](#custom-headers). Overrides also apply to matching extension-registered models; see [Custom Providers: Composition, Updates, and Removal](custom-provider.md#composition-updates-and-removal).
+An override supports `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost`, `contextWindow`, `maxTokens`, `samplingParams` (merged per key), `headers`, and `compat`. Its `cost` base rates are individually optional and retain omitted values; a supplied `tiers` array replaces the existing array. Thinking maps merge by level. `compat` merges by field, and its `openRouterRouting`, `vercelGatewayRouting`, and `chatTemplateKwargs` objects merge by key.
 
 Direct OpenAI GPT-5.6 Sol, Terra, and Luna default to a `272000` context window so requests remain within OpenAI's short-context pricing tier. To use the 1.05M context window, override each model you use:
 
@@ -450,6 +466,7 @@ For `api: "openai-completions"`, Pi auto-detects many defaults from the provider
 | `supportsDeveloperRole` | Uses `developer` rather than `system` for reasoning models. Default: URL-detected. |
 | `supportsReasoningEffort` | Accepts `reasoning_effort` when the selected thinking format uses it. Default: URL-detected. |
 | `supportsUsageInStreaming` | Accepts `stream_options: { "include_usage": true }`. Default: `true`. |
+| `supportsFinishReason` | Whether streamed responses include `finish_reason`. When `false`, Pi infers `stop` or `toolUse` when the stream ends. Default: `true`. |
 | `maxTokensField` | Selects `max_completion_tokens` or `max_tokens`. Default: URL-detected. |
 | `requiresToolResultName` | Requires `name` on tool-result messages. Default: URL-detected. |
 | `requiresAssistantAfterToolResult` | Requires an assistant message before a user message following tool results. Default: URL-detected. |
@@ -457,6 +474,7 @@ For `api: "openai-completions"`, Pi auto-detects many defaults from the provider
 | `requiresReasoningContentOnAssistantMessages` | Includes empty `reasoning_content` on replayed assistant messages when reasoning is enabled. Default: URL-detected. |
 | `thinkingFormat` | One of `openai`, `openrouter`, `deepseek`, `together`, `zai`, `qwen`, `chat-template`, `qwen-chat-template`, `string-thinking`, or `ant-ling`. Default: `openai` unless URL detection selects a known provider format. |
 | `chatTemplateKwargs` | `chat_template_kwargs` for `thinkingFormat: "chat-template"`. Values may be strings, numbers, booleans, `null`, or `{ "$var": "thinking.enabled" | "thinking.effort", "omitWhenOff"?: true }`. |
+| `chatTemplateArgs` | `chat_template_args` for `thinkingFormat: "baseten"`. Values may be strings, numbers, booleans, `null`, or `{ "$var": "thinking.enabled" | "thinking.effort", "omitWhenOff"?: true }`. |
 | `zaiToolStream` | Sends top-level `tool_stream: true` when tools are present. Default: `false`; use only for Z.AI-compatible endpoints that require it. |
 | `cacheControlFormat` | `anthropic` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and final text content when caching is enabled. |
 | `sendSessionAffinityHeaders` | Sends session-affinity headers from the session ID when caching is enabled. Default: `false`. |

package/docs/providers.md

@@ -92,6 +92,7 @@ pi
 | Hugging Face | `HF_TOKEN` | `huggingface` |
 | Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
 | Together AI | `TOGETHER_API_KEY` | `together` |
+| Baseten | `BASETEN_API_KEY` | `baseten` |
 | Kimi For Coding | `KIMI_API_KEY` | `kimi-coding` |
 | MiniMax | `MINIMAX_API_KEY` | `minimax` |
 | MiniMax (China) | `MINIMAX_CN_API_KEY` | `minimax-cn` |

package/docs/quickstart.md

@@ -100,6 +100,8 @@ Pi loads:
 - `~/.pi/agent/AGENTS.md` for global instructions
 - `AGENTS.md` or `CLAUDE.md` from parent directories and the current directory
 
+If a directory contains `AGENTS.override.md`, Pi loads it instead of `AGENTS.md` or `CLAUDE.md` from that directory.
+
 Restart pi, or run `/reload`, after changing context files.
 
 ## Common things to try

package/docs/rpc.md

@@ -949,17 +949,15 @@ Emitted when a message begins and completes. The `message` field contains an `Ag
 
 ### message_update (Streaming)
 
-Emitted during streaming of assistant messages. Contains both the partial message and a streaming delta event.
+Emitted during streaming of assistant messages. Contains a delta event without a cumulative message snapshot.
 
 ```json
 {
   "type": "message_update",
-  "message": {...},
   "assistantMessageEvent": {
     "type": "text_delta",
     "contentIndex": 0,
-    "delta": "Hello ",
-    "partial": {...}
+    "delta": "Hello "
   }
 }
 ```
@@ -968,7 +966,6 @@ The `assistantMessageEvent` field contains one of these delta types:
 
 | Type | Description |
 |------|-------------|
-| `start` | Message generation started |
 | `text_start` | Text content block started |
 | `text_delta` | Text content chunk |
 | `text_end` | Text content block ended |
@@ -978,17 +975,21 @@ The `assistantMessageEvent` field contains one of these delta types:
 | `toolcall_start` | Tool call started |
 | `toolcall_delta` | Tool call arguments chunk |
 | `toolcall_end` | Tool call ended (includes full `toolCall` object) |
-| `done` | Message complete (reason: `"stop"`, `"length"`, `"toolUse"`) |
-| `error` | Error occurred (reason: `"aborted"`, `"error"`) |
 
 Example streaming a text response:
 ```json
-{"type":"message_update","message":{...},"assistantMessageEvent":{"type":"text_start","contentIndex":0,"partial":{...}}}
-{"type":"message_update","message":{...},"assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":"Hello","partial":{...}}}
-{"type":"message_update","message":{...},"assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":" world","partial":{...}}}
-{"type":"message_update","message":{...},"assistantMessageEvent":{"type":"text_end","contentIndex":0,"content":"Hello world","partial":{...}}}
+{"type":"message_update","assistantMessageEvent":{"type":"text_start","contentIndex":0}}
+{"type":"message_update","assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":"Hello"}}
+{"type":"message_update","assistantMessageEvent":{"type":"text_delta","contentIndex":0,"delta":" world"}}
+{"type":"message_update","assistantMessageEvent":{"type":"text_end","contentIndex":0,"content":"Hello world"}}
 ```
 
+`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.
+
 ### bash_execution_update
 
 Emitted once for each output chunk from a direct `bash` command. `id` matches the command's `id`, allowing clients to associate output with the correct command.

package/docs/sdk.md

@@ -179,6 +179,33 @@ session = runtime.session;
 unsubscribe = session.subscribe(() => {});
 ```
 
+### Experimental Remote Sessions
+
+The `@astralyn/pi/client` subpath provides a lifecycle controller and transcript reducers for applications that connect to a remote Pi server. Transport and protocol primitives come from the exact `@earendil-works/pi-client` and `@earendil-works/pi-protocol` dependencies.
+
+```typescript
+import { PiClient } from "@earendil-works/pi-client";
+import { createUnixTransportFactory } from "@earendil-works/pi-client/unix";
+import { RemoteSession } from "@astralyn/pi/client";
+
+await using client = await PiClient.connect({
+  transportFactory: createUnixTransportFactory({ path: "/tmp/pi.sock" }),
+});
+await using session = await RemoteSession.create(client, {
+  cwd: "/workspace/project",
+});
+
+const unsubscribe = session.subscribe(({ lifecycle, snapshot, transcript }) => {
+  console.log(lifecycle.status, snapshot?.phase, transcript.length);
+});
+await session.submit("Inspect this project");
+unsubscribe();
+```
+
+Use `RemoteSession.open(client, sessionId)` to acquire an existing session. The controller serializes open/create/submit/model/thinking operations, selects prompt versus steering behavior from the remote phase, supports abort and reconnect, and releases its exclusive session lease on disposal. `createTranscriptState()`, `applyTranscriptSnapshot()`, `applyTranscriptProgress()`, and `selectTranscript()` are also exported for lower-level clients that manage transcript state directly.
+
+This API is experimental. Match client and server protocol versions, bound transport queues and frame sizes, authenticate the transport, and treat peers as untrusted.
+
 ### Prompting and Message Queueing
 
 `PromptOptions` controls prompt expansion, queueing behavior while streaming, and prompt preflight notifications:
@@ -479,6 +506,24 @@ const { session } = await createAgentSession({
 });
 ```
 
+`login()`, `logout()`, `setRuntimeApiKey()`, and `removeRuntimeApiKey()` resolve after the affected provider's cached/built-in catalog, composition, and availability snapshot are locally consistent. They do not wait for remote catalog freshness. If credentials were committed but local synchronization fails, they reject with the exported `CredentialSynchronizationError`; inspect its `providerId`, `operation`, `credential`, and `cause` fields instead of retrying the credential mutation blindly.
+
+Public model/auth operations and `ModelRuntime.create({ signal })` accept optional abort signals and are unbounded when omitted. SDK applications own deadline policy for remote catalog freshness:
+
+```typescript
+const signal = AbortSignal.timeout(15_000);
+const result = await modelRuntime.refresh({
+  providers: ["anthropic"],
+  signal,
+});
+if (result.aborted) console.warn("Catalog refresh timed out; using cached models");
+for (const [providerId, error] of result.errors) {
+  console.warn(`Could not refresh ${providerId}:`, error);
+}
+```
+
+A failed or timed-out network refresh does not undo a successful credential operation. `refresh()` starts a new provider generation, so it does not wait behind an older stalled refresh and stale generations cannot publish afterward.
+
 > See [examples/sdk/09-api-keys-and-oauth.ts](../examples/sdk/09-api-keys-and-oauth.ts)
 
 ### System Prompt
@@ -1086,6 +1131,7 @@ AgentSessionRuntime
 // Auth and Models
 ModelRuntime // implements pi-ai Models and owns credential storage
 ModelRegistry // synchronous extension compatibility facade
+CredentialSynchronizationError
 resolveCliModel
 resolveModelScopeWithDiagnostics
 

package/docs/security.md

@@ -24,7 +24,7 @@ Trusting a project allows pi to load project resources that require trust, inclu
 - missing project packages configured through project settings
 - project-local extensions and project package-managed extensions
 
-Declining trust skips protected resources. `AGENTS.md` and `CLAUDE.md` context files are loaded regardless of project trust unless context loading is disabled. Before trust is resolved, pi only loads context files, user/global extensions, and CLI `-e` extensions. User/global and CLI extensions can handle the `project_trust` event; the first extension that returns a yes/no decision owns the decision.
+Declining trust skips protected resources. Context files such as `AGENTS.override.md`, `AGENTS.md`, and `CLAUDE.md` are loaded regardless of project trust unless context loading is disabled. Before trust is resolved, pi only loads context files, user/global extensions, and CLI `-e` extensions. User/global and CLI extensions can handle the `project_trust` event; the first extension that returns a yes/no decision owns the decision.
 
 Non-interactive modes (`-p`, `--mode json`, and `--mode rpc`) do not show a trust prompt. Without an applicable saved trust decision, `defaultProjectTrust: "ask"` and `"never"` ignore such resources, while `"always"` trusts them. Use `--approve`/`-a` or `--no-approve`/`-na` to override project trust for one run.
 

package/docs/settings.md

@@ -65,6 +65,8 @@ Use `/trust` in interactive mode to save a project trust decision for future ses
 | `outputPad` | number | `1` | Horizontal padding for user messages, assistant messages, and thinking (0 or 1) |
 | `autocompleteMaxVisible` | number | `5` | Max visible items in autocomplete dropdown (3-20) |
 | `showHardwareCursor` | boolean | `false` | Show the terminal cursor while TUI positions it for IME support |
+| `tuiMode` | string | `"regular"` | Interactive TUI mode: `"regular"` or experimental `"fullscreen"`. Changes from `/settings` apply immediately; `--tui-mode` overrides this setting at startup |
+| `fullscreenScrollbar` | string | `"auto"` | Fullscreen transcript scrollbar: `"auto"` shows it temporarily while scrolling, `"always"` reserves the rightmost column and keeps it visible, and `"hidden"` hides it. Has no effect in regular TUI mode |
 
 For VS Code, include `--wait` so pi resumes after the editor exits:
 
@@ -178,7 +180,7 @@ Keep `retry.provider.maxRetries` at `0` unless provider-level retries are explic
 | `terminal.showImages` | boolean | `true` | Show images in terminal (if supported) |
 | `terminal.imageWidthCells` | number | `60` | Preferred inline image width in terminal cells |
 | `terminal.clearOnShrink` | boolean | `false` | Clear empty rows when content shrinks (can cause flicker) |
-| `images.autoResize` | boolean | `true` | Resize images to 2000x2000 max |
+| `images.autoResize` | boolean | `true` | Resize images to 2000x2000 max. Applies to `@file` attachments, `read`, and images returned by tools |
 | `images.blockImages` | boolean | `false` | Block all images from being sent to LLM |
 
 ### Shell
@@ -226,6 +228,7 @@ When multiple sources specify a session directory, precedence is `--session-dir`
 | Setting | Type | Default | Description |
 |---------|------|---------|-------------|
 | `markdown.codeBlockIndent` | string | `"  "` | Indentation for code blocks |
+| `markdown.mermaid` | string | `"streaming"` | Mermaid rendering mode: `"off"`, `"final"`, or `"streaming"` |
 
 ### Resources
 

package/docs/themes.md

@@ -52,7 +52,7 @@ vim ~/.pi/agent/themes/my-theme.json
 
 ```json
 {
-  "$schema": "https://raw.githubusercontent.com/earendil-works/pi/main/packages/coding-agent/src/modes/interactive/theme/theme-schema.json",
+  "$schema": "https://raw.githubusercontent.com/ming-kang/pi/main/src/modes/interactive/theme/theme-schema.json",
   "name": "my-theme",
   "vars": {
     "primary": "#00aaff",
@@ -71,6 +71,7 @@ vim ~/.pi/agent/themes/my-theme.json
     "text": "",
     "thinkingText": "secondary",
     "selectedBg": "#2d2d30",
+    "scrollbarThumb": "#555566",
     "userMessageBg": "#2d2d30",
     "userMessageText": "",
     "customMessageBg": "#2d2d30",
@@ -123,7 +124,7 @@ vim ~/.pi/agent/themes/my-theme.json
 
 ```json
 {
-  "$schema": "https://raw.githubusercontent.com/earendil-works/pi/main/packages/coding-agent/src/modes/interactive/theme/theme-schema.json",
+  "$schema": "https://raw.githubusercontent.com/ming-kang/pi/main/src/modes/interactive/theme/theme-schema.json",
   "name": "my-theme",
   "vars": {
     "blue": "#0066cc",
@@ -140,13 +141,13 @@ vim ~/.pi/agent/themes/my-theme.json
 
 - `name` is required, must be unique, and must not contain `/`.
 - `vars` is optional. Define reusable colors here, then reference them in `colors`.
-- `colors` must define all 51 required tokens. `thinkingMax` is optional and falls back to `thinkingXhigh`.
+- `colors` must define all 51 required tokens. `thinkingMax` is optional and falls back to `thinkingXhigh`; `scrollbarThumb` is optional and falls back to `selectedBg`.
 
 The `$schema` field enables editor auto-completion and validation.
 
 ## Color Tokens
 
-Every theme must define all 51 required color tokens. `thinkingMax` is optional for compatibility with existing themes; when omitted, it uses `thinkingXhigh`.
+Every theme must define all 51 required color tokens. `thinkingMax` and `scrollbarThumb` are optional for compatibility with existing themes; when omitted, they use `thinkingXhigh` and `selectedBg`, respectively.
 
 ### Core UI (11 colors)
 
@@ -164,11 +165,12 @@ Every theme must define all 51 required color tokens. `thinkingMax` is optional
 | `text` | Default text (usually `""`) |
 | `thinkingText` | Thinking block text |
 
-### Backgrounds & Content (11 colors)
+### Backgrounds & Content (11 required, 1 optional)
 
 | Token | Purpose |
 |-------|---------|
 | `selectedBg` | Selected line background |
+| `scrollbarThumb` | Fullscreen scrollbar thumb background; optional, falls back to `selectedBg` |
 | `userMessageBg` | User message background |
 | `userMessageText` | User message text |
 | `customMessageBg` | Extension message background |

package/docs/usage.md

@@ -37,6 +37,7 @@ Type `/` in the editor to open command completion. Extensions can register custo
 | Command | Description |
 |---------|-------------|
 | `/login`, `/logout` | Manage OAuth or API-key credentials |
+| [`/biu`](bundled/extensions/biu.md) | Toggle the TUI-only Biu workflow; inside the mode, open its menu |
 | [`/llama`](llama-cpp.md) | Download, load, and unload llama.cpp router models |
 | `/model` | Switch models |
 | `/scoped-models` | Enable/disable models for Ctrl+P cycling |
@@ -95,6 +96,8 @@ Pi loads `AGENTS.md` or `CLAUDE.md` at startup from:
 - parent directories, walking up from the current working directory
 - the current directory
 
+If a directory contains `AGENTS.override.md`, Pi loads it instead of `AGENTS.md` or `CLAUDE.md` from that directory. Context files from other directories still layer normally.
+
 Use context files for project conventions, commands, safety rules, and preferences. Disable loading with `--no-context-files` or `-nc`.
 
 ### System Prompt Files
@@ -231,12 +234,17 @@ pi --no-extensions -e ./my-extension.ts
 |--------|-------------|
 | `--system-prompt <text>` | Replace default prompt; context files and skills are still appended |
 | `--append-system-prompt <text>` | Append to system prompt |
+| `--tui-mode <mode>` | TUI mode: `regular` (default) or experimental `fullscreen` |
 | `--verbose` | Force verbose startup |
 | `-a`, `--approve` | Trust project-local files for this run |
 | `-na`, `--no-approve` | Ignore project-local files for this run |
 | `-h`, `--help` | Show help |
 | `-v`, `--version` | Show version |
 
+In `fullscreen` mode, the transcript scrolls inside the terminal viewport while queued messages, working status, extension widgets, editor, and footer remain fixed at the bottom. Mouse/trackpad input scrolls the region under the pointer; keyboard viewport actions always remain available. Inline images work in terminals that support the Kitty graphics protocol, including Kitty and Ghostty. In iTerm2 they render as text placeholders because its inline-image protocol cannot delete or crop placements during application-owned scrolling. In `regular` mode, pi uses the main screen and terminal-owned scrollback, and iTerm2 inline images continue to render normally.
+
+Set **TUI mode** in `/settings` to switch between `regular` and `fullscreen` immediately and choose the default for future sessions.
+
 ### File Arguments
 
 Prefix files with `@` to include them in the message: