@earendil-works/pi-coding-agent 0.83.0 → 0.84.1

package/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/docs/providers.md

@@ -92,10 +92,12 @@ 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` |
-| Qwen Token Plan | `QWEN_TOKEN_PLAN_API_KEY` | `qwen-token-plan` |
+| Qwen Token Plan (existing catalog) | `QWEN_TOKEN_PLAN_API_KEY` | `qwen-token-plan` |
+| Qwen Token Plan (Individual) | `QWEN_TOKEN_PLAN_API_KEY` | `qwen-token-plan-individual` |
 | Qwen Token Plan (China) | `QWEN_TOKEN_PLAN_CN_API_KEY` | `qwen-token-plan-cn` |
 | Xiaomi MiMo | `XIAOMI_API_KEY` | `xiaomi` |
 | Xiaomi MiMo Token Plan (China) | `XIAOMI_TOKEN_PLAN_CN_API_KEY` | `xiaomi-token-plan-cn` |
@@ -120,6 +122,7 @@ Store credentials in `~/.pi/agent/auth.json`:
   "opencode-go": { "type": "api_key", "key": "..." },
   "together": { "type": "api_key", "key": "..." },
   "qwen-token-plan":  { "type": "api_key", "key": "sk-sp-..." },
+  "qwen-token-plan-individual": { "type": "api_key", "key": "sk-sp-..." },
   "qwen-token-plan-cn": { "type": "api_key", "key": "sk-sp-..." },
   "xiaomi": { "type": "api_key", "key": "..." },
   "xiaomi-token-plan-cn":  { "type": "api_key", "key": "..." },
@@ -128,6 +131,11 @@ Store credentials in `~/.pi/agent/auth.json`:
 }
 ```
 
+`qwen-token-plan-individual` uses the same international endpoint and `QWEN_TOKEN_PLAN_API_KEY` as
+`qwen-token-plan`, but limits the picker to the models documented for Individual subscriptions. The existing
+provider keeps its broader catalog for backward compatibility. When using `auth.json`, store the
+credential under the provider you select; an environment variable is shared by both international providers.
+
 The file is created with `0600` permissions (user read/write only). Auth file credentials take priority over environment variables.
 
 API key credentials can also include provider-scoped environment values. These values are used before process environment variables when resolving the credential key, provider/model headers, and provider configuration such as Cloudflare account IDs, Azure OpenAI settings, Vertex project/location, Bedrock settings, `PI_CACHE_RETENTION`, and `HTTP_PROXY`/`HTTPS_PROXY`.

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

@@ -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/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/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

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

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-custom-provider",
-  "version": "0.83.0",
+  "version": "0.84.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-custom-provider",
-      "version": "0.83.0",
+      "version": "0.84.1",
       "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": "0.83.0",
+  "version": "0.84.1",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

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

@@ -274,7 +274,7 @@ async function loginGitLab(callbacks: OAuthLoginCallbacks): Promise<OAuthCredent
 	};
 }
 
-async function refreshGitLabToken(credentials: OAuthCredentials): Promise<OAuthCredentials> {
+async function refreshGitLabToken(credentials: OAuthCredentials, signal: AbortSignal): Promise<OAuthCredentials> {
 	const response = await fetch(`${GITLAB_COM_URL}/oauth/token`, {
 		method: "POST",
 		headers: { "Content-Type": "application/x-www-form-urlencoded" },
@@ -283,6 +283,7 @@ async function refreshGitLabToken(credentials: OAuthCredentials): Promise<OAuthC
 			grant_type: "refresh_token",
 			refresh_token: credentials.refresh,
 		}).toString(),
+		signal,
 	});
 	if (!response.ok) throw new Error(`Token refresh failed: ${await response.text()}`);
 	const data = (await response.json()) as {

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

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-custom-provider-gitlab-duo",
   "private": true,
-  "version": "0.83.0",
+  "version": "0.84.1",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/extensions/doom-overlay/wad-finder.ts

@@ -1,11 +1,12 @@
 import { existsSync, writeFileSync } from "node:fs";
 import { dirname, join, resolve } from "node:path";
 import { fileURLToPath } from "node:url";
+import { gunzipSync } from "node:zlib";
 
 // Get the bundled WAD path (relative to this module)
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const BUNDLED_WAD = join(__dirname, "doom1.wad");
-const WAD_URL = "https://distro.ibiblio.org/slitaz/sources/packages/d/doom1.wad";
+const WAD_URL = "https://www.gamers.org/pub/idgames/idstuff/doom/doom-1.8.wad.gz";
 
 const DEFAULT_WAD_PATHS = ["./doom1.wad", "./DOOM1.WAD", "~/doom1.wad", "~/.doom/doom1.wad"];
 
@@ -42,8 +43,11 @@ export async function ensureWadFile(): Promise<string | null> {
 		if (!response.ok) {
 			throw new Error(`HTTP ${response.status}`);
 		}
-		const buffer = await response.arrayBuffer();
-		writeFileSync(BUNDLED_WAD, Buffer.from(buffer));
+		const wad = gunzipSync(Buffer.from(await response.arrayBuffer()));
+		if (wad.subarray(0, 4).toString("ascii") !== "IWAD") {
+			throw new Error("Downloaded file is not a valid IWAD");
+		}
+		writeFileSync(BUNDLED_WAD, wad);
 		return BUNDLED_WAD;
 	} catch {
 		return null;

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

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-gondolin",
-	"version": "0.83.0",
+	"version": "0.84.1",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-gondolin",
-			"version": "0.83.0",
+			"version": "0.84.1",
 			"dependencies": {
 				"@earendil-works/gondolin": "0.12.0"
 			}

package/examples/extensions/gondolin/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-gondolin",
 	"private": true,
-	"version": "0.83.0",
+	"version": "0.84.1",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/handoff.ts

@@ -13,8 +13,7 @@
  */
 
 import type { AgentMessage } from "@earendil-works/pi-agent-core";
-import { uuidv7 } from "@earendil-works/pi-ai";
-import { complete, type Message } from "@earendil-works/pi-ai/compat";
+import { type Message, uuidv7 } from "@earendil-works/pi-ai";
 import type { ExtensionAPI, SessionEntry } from "@earendil-works/pi-coding-agent";
 import { BorderedLoader, convertToLlm, serializeConversation } from "@earendil-works/pi-coding-agent";
 
@@ -118,11 +117,6 @@ export default function (pi: ExtensionAPI) {
 				loader.onAbort = () => done(null);
 
 				const doGenerate = async () => {
-					const auth = await ctx.modelRegistry.getApiKeyAndHeaders(ctx.model!);
-					if (!auth.ok || !auth.apiKey) {
-						throw new Error(auth.ok ? `No API key for ${ctx.model!.provider}` : auth.error);
-					}
-
 					const userMessage: Message = {
 						role: "user",
 						content: [
@@ -134,13 +128,10 @@ export default function (pi: ExtensionAPI) {
 						timestamp: Date.now(),
 					};
 
-					const response = await complete(
+					const response = await ctx.modelRegistry.complete(
 						ctx.model!,
 						{ systemPrompt: SYSTEM_PROMPT, messages: [userMessage] },
 						{
-							apiKey: auth.apiKey,
-							headers: auth.headers,
-							env: auth.env,
 							signal: loader.signal,
 							cacheRetention: "none",
 							sessionId: uuidv7(),

package/examples/extensions/qna.ts

@@ -7,7 +7,7 @@
  * 3. Loads the result into the editor for user to fill in answers
  */
 
-import { complete, type UserMessage } from "@earendil-works/pi-ai/compat";
+import type { UserMessage } from "@earendil-works/pi-ai";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
 import { BorderedLoader } from "@earendil-works/pi-coding-agent";
 
@@ -77,20 +77,16 @@ export default function (pi: ExtensionAPI) {
 
 				// Do the work
 				const doExtract = async () => {
-					const auth = await ctx.modelRegistry.getApiKeyAndHeaders(ctx.model!);
-					if (!auth.ok || !auth.apiKey) {
-						throw new Error(auth.ok ? `No API key for ${ctx.model!.provider}` : auth.error);
-					}
 					const userMessage: UserMessage = {
 						role: "user",
 						content: [{ type: "text", text: lastAssistantText! }],
 						timestamp: Date.now(),
 					};
 
-					const response = await complete(
+					const response = await ctx.modelRegistry.complete(
 						ctx.model!,
 						{ systemPrompt: SYSTEM_PROMPT, messages: [userMessage] },
-						{ apiKey: auth.apiKey, headers: auth.headers, env: auth.env, signal: loader.signal },
+						{ signal: loader.signal },
 					);
 
 					if (response.stopReason === "aborted") {

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

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-sandbox",
-	"version": "1.13.0",
+	"version": "1.14.1",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-sandbox",
-			"version": "1.13.0",
+			"version": "1.14.1",
 			"dependencies": {
 				"@anthropic-ai/sandbox-runtime": "^0.0.26"
 			}

package/examples/extensions/sandbox/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-sandbox",
 	"private": true,
-	"version": "1.13.0",
+	"version": "1.14.1",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",