@daniel156161/prism 0.2.76 → 0.2.78

package/node_modules/@earendil-works/pi-coding-agent/docs/custom-provider.md

@@ -331,8 +331,8 @@ pi.registerProvider("corporate-ai", {
       };
     },
 
-    async refreshToken(credentials: OAuthCredentials): Promise<OAuthCredentials> {
-      const tokens = await refreshAccessToken(credentials.refresh);
+    async refreshToken(credentials: OAuthCredentials, signal: AbortSignal): Promise<OAuthCredentials> {
+      const tokens = await refreshAccessToken(credentials.refresh, signal);
       return {
         refresh: tokens.refreshToken ?? credentials.refresh,
         access: tokens.accessToken,
@@ -688,7 +688,7 @@ interface ProviderConfig {
   oauth?: {
     name: string;
     login(callbacks: OAuthLoginCallbacks): Promise<OAuthCredentials>;
-    refreshToken(credentials: OAuthCredentials): Promise<OAuthCredentials>;
+    refreshToken(credentials: OAuthCredentials, signal: AbortSignal): Promise<OAuthCredentials>;
     getApiKey(credentials: OAuthCredentials): string;
   };
 }
@@ -743,6 +743,7 @@ interface ProviderModelConfig {
     supportsDeveloperRole?: boolean;
     supportsReasoningEffort?: boolean;
     supportsUsageInStreaming?: boolean;
+    supportsFinishReason?: boolean;
     supportsStrictMode?: boolean;
     supportsOpenAIGrammarTools?: boolean; // openai-completions/openai-responses; false falls back to normal function tools
     maxTokensField?: "max_completion_tokens" | "max_tokens";
@@ -750,8 +751,9 @@ interface ProviderModelConfig {
     requiresAssistantAfterToolResult?: boolean;
     requiresThinkingAsText?: boolean;
     requiresReasoningContentOnAssistantMessages?: boolean;
-    thinkingFormat?: "openai" | "openrouter" | "deepseek" | "together" | "zai" | "qwen" | "chat-template" | "qwen-chat-template" | "string-thinking" | "ant-ling";
+    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 }>;
     cacheControlFormat?: "anthropic";
     sessionAffinityFormat?: "openai" | "openai-nosession" | "openrouter";
     sendSessionAffinityHeaders?: boolean;
@@ -768,5 +770,5 @@ 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": { "$var": "thinking.enabled" } }`.
+`openrouter` sends `reasoning: { effort }`. `deepseek` sends `thinking: { type: "enabled" | "disabled" }` and `reasoning_effort` when enabled. `together` sends `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking` and need `preserve_thinking`. Use `chat-template` for configurable `chat_template_kwargs`, for example DeepSeek V3.x behind vLLM with `chatTemplateKwargs: { "thinking": { "$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`.
 `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/node_modules/@earendil-works/pi-coding-agent/docs/extensions.md

@@ -1562,6 +1562,27 @@ 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.
@@ -1686,7 +1707,9 @@ 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.
 
@@ -1776,7 +1799,8 @@ 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;
     },
@@ -1797,7 +1821,7 @@ 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/node_modules/@earendil-works/pi-coding-agent/docs/json.md

@@ -8,25 +8,25 @@ Outputs all session events as JSON lines to stdout. Useful for integrating pi in
 
 ## Event Types
 
-Events are defined in [`AgentSessionEvent`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/agent-session.ts#L102):
+Wire events use `JsonAgentSessionEvent`. It matches
+[`AgentSessionEvent`](https://github.com/earendil-works/pi-mono/blob/main/packages/coding-agent/src/core/agent-session.ts)
+except that streaming message updates omit cumulative snapshots:
 
 ```typescript
-type AgentSessionEvent =
-  | AgentEvent
-  | { type: "queue_update"; steering: readonly string[]; followUp: readonly string[] }
-  | { type: "compaction_start"; reason: "manual" | "threshold" | "overflow" }
-  | { type: "compaction_end"; reason: "manual" | "threshold" | "overflow"; result: CompactionResult | undefined; aborted: boolean; willRetry: boolean; errorMessage?: string }
-  | { type: "auto_retry_start"; attempt: number; maxAttempts: number; delayMs: number; errorMessage: string }
-  | { type: "auto_retry_end"; success: boolean; attempt: number; finalError?: string }
-  | { type: "summarization_retry_scheduled"; attempt: number; maxAttempts: number; delayMs: number; errorMessage: string }
-  | { type: "summarization_retry_attempt_start"; source: "branchSummary" }
-  | { type: "summarization_retry_attempt_start"; source: "compaction"; reason: "manual" | "threshold" | "overflow" }
-  | { type: "summarization_retry_finished" };
+type WithoutPartial<T> = T extends { partial: unknown } ? Omit<T, "partial"> : T;
+
+type JsonAgentSessionEvent =
+  | Exclude<AgentSessionEvent, { type: "message_update" }>
+  | {
+      type: "message_update";
+      assistantMessageEvent: WithoutPartial<AssistantMessageEvent>;
+    };
 ```
 
 `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.
 
-Base events from [`AgentEvent`](https://github.com/earendil-works/pi-mono/blob/main/packages/agent/src/types.ts#L179):
+Other base events come from
+[`AgentEvent`](https://github.com/earendil-works/pi-mono/blob/main/packages/agent/src/types.ts):
 
 ```typescript
 type AgentEvent =
@@ -73,12 +73,17 @@ 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":[...]}
 ```
 
+`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/node_modules/@earendil-works/pi-coding-agent/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/node_modules/@earendil-works/pi-coding-agent/docs/models.md

@@ -206,6 +206,7 @@ If your command is slow, expensive, rate-limited, or should keep using a previou
 | `input` | No | `["text"]` | Input types: `["text"]` or `["text", "image"]` |
 | `contextWindow` | No | `128000` | Context window size in tokens |
 | `maxTokens` | No | `16384` | Maximum output tokens |
+| `samplingParams` | No | omitted | Sampling parameters merged verbatim into every request body (see below) |
 | `cost` | No | all zeros | Per-million-token rates with optional request-wide input pricing tiers |
 | `compat` | No | provider `compat` | Provider compatibility overrides. Merged with provider-level `compat` when both are set. |
 
@@ -235,6 +236,24 @@ Current behavior:
 - `/model`, `--list-models`, and the interactive footer display entries by model `id`.
 - The configured `name` is used for model matching and secondary model detail text. It does not replace the footer/status-bar model id.
 
+### 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
 
 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`.
@@ -338,7 +357,7 @@ Use `modelOverrides` to customize built-in models and matching extension-registe
 }
 ```
 
-`modelOverrides` supports these fields per model: `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `headers`, `compat`.
+`modelOverrides` supports these fields per model: `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `samplingParams` (merged per key), `headers`, `compat`.
 
 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 opt into OpenAI's 1.05M context window, increase it for each model you use:
 
@@ -441,13 +460,15 @@ For providers with partial OpenAI compatibility, use the `compat` field.
 | `supportsDeveloperRole` | Use `developer` vs `system` role |
 | `supportsReasoningEffort` | Support for `reasoning_effort` parameter |
 | `supportsUsageInStreaming` | Supports `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` | Use `max_completion_tokens` or `max_tokens` |
 | `requiresToolResultName` | Include `name` on tool result messages |
 | `requiresAssistantAfterToolResult` | Insert an assistant message before a user message after tool results |
 | `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`, `zai`, `qwen`, `chat-template`, or `qwen-chat-template` thinking parameters |
+| `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 |
 | `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. |
@@ -458,7 +479,7 @@ For providers with partial OpenAI compatibility, use the `compat` field.
 | `openRouterRouting` | OpenRouter provider routing preferences. This object is sent as-is in the `provider` field of the [OpenRouter API request](https://openrouter.ai/docs/guides/routing/provider-selection). |
 | `vercelGatewayRouting` | Vercel AI Gateway routing config for provider selection (`only`, `order`) |
 
-`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": { "$var": "thinking.enabled" } }` for DeepSeek V3.x templates.
+`openrouter` uses `reasoning: { effort }`. `together` uses `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` uses top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that require `chat_template_kwargs.enable_thinking` and `preserve_thinking`. Use `chat-template` for vLLM/Hugging Face chat templates that need configurable `chat_template_kwargs`, such as `chatTemplateKwargs: { "thinking": { "$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`.
 
 `cacheControlFormat: "anthropic"` is for OpenAI-compatible providers that expose Anthropic-style prompt caching through `cache_control` markers on text content and tool definitions.
 

package/node_modules/@earendil-works/pi-coding-agent/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/node_modules/@earendil-works/pi-coding-agent/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/node_modules/@earendil-works/pi-coding-agent/docs/rpc.md

@@ -914,17 +914,15 @@ 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 "
   }
 }
 ```
@@ -933,7 +931,6 @@ 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 |
@@ -943,17 +940,21 @@ 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.
@@ -1362,6 +1363,7 @@ Source files:
 - [`packages/ai/src/types.ts`](../../ai/src/types.ts) - `Model`, `UserMessage`, `AssistantMessage`, `ToolResultMessage`
 - [`packages/agent/src/types.ts`](../../agent/src/types.ts) - `AgentMessage`, `AgentEvent`
 - [`src/core/messages.ts`](../src/core/messages.ts) - `BashExecutionMessage`
+- [`src/modes/json-event.ts`](../src/modes/json-event.ts) - `JsonAgentSessionEvent`
 - [`src/modes/rpc/rpc-types.ts`](../src/modes/rpc/rpc-types.ts) - RPC command/response types, extension UI request/response types
 
 ### Model

package/node_modules/@earendil-works/pi-coding-agent/docs/sdk.md

@@ -452,7 +452,7 @@ for (const provider of modelRuntime.getProviders()) {
 }
 
 // Runtime API key override (not persisted to disk)
-modelRuntime.setRuntimeApiKey("anthropic", "sk-my-temp-key");
+await modelRuntime.setRuntimeApiKey("anthropic", "sk-my-temp-key");
 
 // Custom credential and model locations
 const customRuntime = await ModelRuntime.create({
@@ -469,6 +469,24 @@ 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
@@ -938,7 +956,7 @@ const modelRuntime = await ModelRuntime.create({
   modelsPath: "/custom/agent/models.json",
 });
 if (process.env.MY_KEY) {
-  modelRuntime.setRuntimeApiKey("anthropic", process.env.MY_KEY);
+  await modelRuntime.setRuntimeApiKey("anthropic", process.env.MY_KEY);
 }
 
 // Inline tool
@@ -1144,6 +1162,7 @@ AgentSessionRuntime
 // Auth and Models
 ModelRuntime // implements pi-ai Models and owns credential storage
 ModelRegistry // synchronous extension compatibility facade
+CredentialSynchronizationError
 resolveCliModel
 resolveModelScopeWithDiagnostics
 

package/node_modules/@earendil-works/pi-coding-agent/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/node_modules/@earendil-works/pi-coding-agent/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/node_modules/@earendil-works/pi-coding-agent/docs/themes.md

@@ -71,6 +71,7 @@ vim ~/.pi/agent/themes/my-theme.json
     "text": "",
     "thinkingText": "secondary",
     "selectedBg": "#2d2d30",
+    "scrollbarThumb": "#555566",
     "userMessageBg": "#2d2d30",
     "userMessageText": "",
     "customMessageBg": "#2d2d30",
@@ -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/node_modules/@earendil-works/pi-coding-agent/docs/usage.md

@@ -103,6 +103,8 @@ 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
@@ -239,12 +241,17 @@ 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:

package/node_modules/@earendil-works/pi-coding-agent/examples/extensions/custom-compaction.ts

@@ -14,7 +14,6 @@
  */
 
 import { uuidv7 } from "@earendil-works/pi-ai";
-import { complete } from "@earendil-works/pi-ai/compat";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
 import { convertToLlm, serializeConversation } from "@earendil-works/pi-coding-agent";
 
@@ -32,17 +31,6 @@ export default function (pi: ExtensionAPI) {
 			return;
 		}
 
-		// Resolve request auth for the summarization model
-		const auth = await ctx.modelRegistry.getApiKeyAndHeaders(model);
-		if (!auth.ok) {
-			ctx.ui.notify(`Compaction auth failed: ${auth.error}`, "warning");
-			return;
-		}
-		if (!auth.apiKey) {
-			ctx.ui.notify(`No API key for ${model.provider}, using default compaction`, "warning");
-			return;
-		}
-
 		// Combine all messages for full summary
 		const allMessages = [...messagesToSummarize, ...turnPrefixMessages];
 
@@ -88,13 +76,10 @@ ${conversationText}
 
 		try {
 			// Pass signal to honor abort requests (e.g., user cancels compaction)
-			const response = await complete(
+			const response = await ctx.modelRegistry.complete(
 				model,
 				{ messages: summaryMessages },
 				{
-					apiKey: auth.apiKey,
-					headers: auth.headers,
-					env: auth.env,
 					maxTokens: 8192,
 					signal,
 					cacheRetention: "none",

package/node_modules/@earendil-works/pi-coding-agent/examples/extensions/custom-provider-anthropic/index.ts

@@ -124,7 +124,7 @@ async function loginAnthropic(callbacks: OAuthLoginCallbacks): Promise<OAuthCred
 	};
 }
 
-async function refreshAnthropicToken(credentials: OAuthCredentials): Promise<OAuthCredentials> {
+async function refreshAnthropicToken(credentials: OAuthCredentials, signal: AbortSignal): Promise<OAuthCredentials> {
 	const response = await fetch(TOKEN_URL, {
 		method: "POST",
 		headers: { "Content-Type": "application/json" },
@@ -133,6 +133,7 @@ async function refreshAnthropicToken(credentials: OAuthCredentials): Promise<OAu
 			client_id: CLIENT_ID,
 			refresh_token: credentials.refresh,
 		}),
+		signal,
 	});
 
 	if (!response.ok) {

package/node_modules/@earendil-works/pi-coding-agent/examples/extensions/custom-provider-anthropic/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.83.0",
+  "version": "0.84.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.83.0",
+      "version": "0.84.0",
       "dependencies": {
         "@anthropic-ai/sdk": "^0.52.0"
       }