@astralyn/pi 0.87.6 → 0.99.0

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

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

package/examples/extensions/debug-provider.ts

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

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

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-gondolin",
-	"version": "0.87.1",
+	"version": "0.99.1",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-gondolin",
-			"version": "0.87.1",
+			"version": "0.99.1",
 			"dependencies": {
 				"@earendil-works/gondolin": "0.12.0"
 			}

package/examples/extensions/gondolin/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "pi-extension-gondolin",
 	"private": true,
-	"version": "0.87.1",
+	"version": "0.99.1",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

package/examples/extensions/jev-router.ts

@@ -0,0 +1,113 @@
+/**
+ * Jev router - a virtual model that plans on a strong model and implements on a cheap one.
+ *
+ * Registers `jev/auto`, which routes between three OpenAI Codex models:
+ *
+ * - Planning: GPT-5.6 Sol for complex work, GPT-5.6 Terra otherwise. The Jev classifier rates the
+ *   first user message; planning stays on the chosen model.
+ * - Implementation: GPT-5.6 Luna.
+ *
+ * The planning model explores, plans, and makes the first edit. After the first successful `edit`
+ * or `write` tool call, the next request of the same turn goes to Luna, and the session stays
+ * there. A session therefore switches models once and accepts a single prompt-cache miss.
+ *
+ * The phase is router state: Pi stores it on the session branch, so it follows the session tree
+ * and survives compaction. The selected thinking level passes through as the reasoning effort of
+ * the chosen model. Requests outside the agent loop, such as compaction summaries, go to Luna.
+ *
+ * Requires TypeSafe credentials (TYPESAFE_API_KEY) and an OpenAI Codex login.
+ * Usage: pi -e ./jev-router.ts --model jev/auto
+ */
+
+import type { Message } from "@earendil-works/pi-ai";
+import type { ExtensionAPI, ExtensionContext, ModelRoute, ModelRouteRequest } from "@earendil-works/pi-coding-agent";
+
+const PROVIDER = "openai-codex";
+const SOL = "gpt-5.6-sol";
+const TERRA = "gpt-5.6-terra";
+const LUNA = "gpt-5.6-luna";
+
+/** Tools whose successful result means implementation has started. */
+const EDIT_TOOLS = new Set(["edit", "write"]);
+
+interface JevState {
+	phase: "planning" | "implementation";
+	/** OpenAI Codex model for this phase. */
+	model: string;
+}
+
+type JevRequest = ModelRouteRequest<JevState>;
+
+function routeTo(request: JevRequest, ctx: ExtensionContext, id: string, state?: JevState): ModelRoute<JevState> {
+	const model = ctx.modelRegistry.find(PROVIDER, id);
+	if (!model) throw new Error(`Model ${PROVIDER}/${id} is not in the catalog`);
+	return { model, thinkingLevel: request.thinkingLevel, state };
+}
+
+function lastUserText(messages: readonly Message[]): string {
+	const content = messages.filter((message) => message.role === "user").at(-1)?.content ?? "";
+	if (typeof content === "string") return content;
+	return content.flatMap((block) => (block.type === "text" ? [block.text] : [])).join("\n");
+}
+
+/** Whether a tool call since the last user message edited a file successfully. */
+function editedThisTurn(messages: readonly Message[]): boolean {
+	const lastUser = messages.findLastIndex((message) => message.role === "user");
+	return messages
+		.slice(lastUser + 1)
+		.some((message) => message.role === "toolResult" && EDIT_TOOLS.has(message.toolName) && !message.isError);
+}
+
+/** Planning model for a new session: Sol for complex work, Terra otherwise or when Jev is unavailable. */
+async function choosePlanningModel(request: JevRequest, ctx: ExtensionContext): Promise<string> {
+	// Keep a planning model the session already uses, so switching to jev/auto costs no cache miss.
+	const previous = request.previous?.model;
+	if (previous?.provider === PROVIDER && (previous.id === SOL || previous.id === TERRA)) return previous.id;
+
+	const jev = ctx.modelRegistry.findOfType("classifier", "typesafe", "jev-latest");
+	if (!jev) return TERRA;
+	const result = await ctx.modelRegistry.classify(
+		jev,
+		{
+			state: { prompt: lastUserText(request.messages).slice(0, 16_000) },
+			questions: {
+				complexity: {
+					type: "choice",
+					instructions: "How demanding is the software engineering work requested in `prompt`?",
+					criteria: {
+						standard: "Ordinary features, fixes, reviews, or questions",
+						complex: "Subtle design, cross-cutting changes, or hard debugging",
+					},
+				},
+			},
+		},
+		{ signal: request.signal },
+	);
+	const answer = result.stopReason === "stop" ? result.answers.complexity : undefined;
+	return answer?.type === "choice" && (answer.probabilities.complex ?? 0) >= 0.5 ? SOL : TERRA;
+}
+
+export default function (pi: ExtensionAPI) {
+	pi.registerVirtualModel<JevState>({
+		provider: "jev",
+		id: "auto",
+		name: "Auto (Jev)",
+		thinkingLevels: ["low", "medium", "high", "xhigh"],
+		// Shared by all three models; shown before the first response.
+		contextWindow: 272_000,
+		maxTokens: 128_000,
+		async route(request, ctx) {
+			if (request.reason === "direct") return routeTo(request, ctx, LUNA);
+			const state = request.state;
+			if (!state) {
+				const model = await choosePlanningModel(request, ctx);
+				return routeTo(request, ctx, model, { phase: "planning", model });
+			}
+			// The planning model made the first edit: hand the rest of the work to Luna.
+			if (state.phase === "planning" && editedThisTurn(request.messages)) {
+				return routeTo(request, ctx, LUNA, { phase: "implementation", model: LUNA });
+			}
+			return routeTo(request, ctx, state.model);
+		},
+	});
+}

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

@@ -1,12 +1,12 @@
 {
 	"name": "pi-extension-sandbox",
-	"version": "1.17.1",
+	"version": "0.99.1",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "pi-extension-sandbox",
-			"version": "1.17.1",
+			"version": "0.99.1",
 			"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": "1.17.1",
+	"version": "0.99.1",
 	"type": "module",
 	"scripts": {
 		"clean": "echo 'nothing to clean'",

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

@@ -1,12 +1,12 @@
 {
   "name": "pi-extension-with-deps",
-  "version": "0.87.1",
+  "version": "0.99.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pi-extension-with-deps",
-      "version": "0.87.1",
+      "version": "0.99.1",
       "dependencies": {
         "ms": "^2.1.3"
       },

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

@@ -1,7 +1,7 @@
 {
   "name": "pi-extension-with-deps",
   "private": true,
-  "version": "0.87.1",
+  "version": "0.99.1",
   "type": "module",
   "scripts": {
     "clean": "echo 'nothing to clean'",

package/examples/rpc-client.ts

@@ -2,7 +2,7 @@
  * Run one prompt through a Pi RPC child process.
  *
  * Build the coding-agent package first, then run:
- * npx tsx examples/rpc-client.ts "Explain this repository"
+ * node examples/rpc-client.ts "Explain this repository"
  */
 
 import { dirname, join } from "node:path";

package/examples/rpc-extension-ui.ts

@@ -5,7 +5,7 @@
  * Demonstrates how to build a custom UI on top of the RPC protocol,
  * including handling extension UI requests (select, confirm, input, editor).
  *
- * Usage: npx tsx examples/rpc-extension-ui.ts
+ * Usage: node examples/rpc-extension-ui.ts
  *
  * Slash commands:
  *   /select  - demo select dialog

package/examples/sdk/14-codemode-mcp.ts

@@ -0,0 +1,61 @@
+/**
+ * Codemode, Tool Search, and MCP
+ *
+ * The CLI loads `codemode`, `tool_search`, and MCP as built-in extensions. SDK sessions add
+ * them to the resource loader's extension factories.
+ *
+ * `codemode` and `tool_search` are registered inactive. Enable them through the `defaultTools` setting
+ * (`tools` would also restrict the session to the named tools, which hides MCP tools), or let the
+ * MCP extension activate them: `codemode` for servers with `codemode` or `codemode-deferred` exposure,
+ * `tool_search` for servers with `deferred` exposure.
+ */
+
+import {
+	createAgentSession,
+	createCodemodeExtension,
+	createMcpExtension,
+	createToolSearchExtension,
+	DefaultResourceLoader,
+	getAgentDir,
+	SessionManager,
+	SettingsManager,
+} from "@earendil-works/pi-coding-agent";
+
+const cwd = process.cwd();
+
+const resourceLoader = new DefaultResourceLoader({
+	cwd,
+	agentDir: getAgentDir(),
+	extensionFactories: [
+		createCodemodeExtension({ mode: "on" }),
+		createToolSearchExtension(),
+		// Reads mcp.json from the agent directory and the trusted project, like the CLI.
+		createMcpExtension(),
+	],
+});
+await resourceLoader.reload();
+
+const settingsManager = SettingsManager.create(cwd);
+// `+name` adds to the configured default tools instead of replacing them.
+settingsManager.applyOverrides({ defaultTools: ["+codemode", "+tool_search"] });
+
+const { session } = await createAgentSession({
+	resourceLoader,
+	settingsManager,
+	sessionManager: SessionManager.inMemory(),
+});
+
+try {
+	// Emits session_start, which connects the MCP servers in the background.
+	await session.bindExtensions({});
+	console.log("Active tools:", session.getActiveToolNames().join(", "));
+	session.subscribe((event) => {
+		if (event.type === "message_update" && event.assistantMessageEvent.type === "text_delta") {
+			process.stdout.write(event.assistantMessageEvent.delta);
+		}
+	});
+	await session.prompt("Use codemode to count the TypeScript files in src/ and list the three largest.");
+	console.log();
+} finally {
+	session.dispose();
+}

package/examples/sdk/README.md

@@ -21,6 +21,7 @@ The runtime example shows how to build a recreate function that closes over proc
 | `11-sessions.ts` | In-memory, persistent, continue, list sessions |
 | `12-full-control.ts` | Replace everything, no discovery |
 | `13-session-runtime.ts` | Manage runtime-backed session replacement |
+| `14-codemode-mcp.ts` | Add the `codemode`, `tool_search`, and MCP extensions |
 
 ## Running