pi-usereq 0.7.0 → 0.10.0

package/pi.dev-src/pi-mono/ai/test/anthropic-tool-name-normalization.test.ts

@@ -0,0 +1,205 @@
+import { Type } from "typebox";
+import { describe, expect, it } from "vitest";
+import { getModel } from "../src/models.js";
+import { stream } from "../src/stream.js";
+import type { Context, Tool } from "../src/types.js";
+import { resolveApiKey } from "./oauth.js";
+
+const oauthToken = await resolveApiKey("anthropic");
+
+/**
+ * Tests for Anthropic OAuth tool name normalization.
+ *
+ * When using Claude Code OAuth, tool names must match CC's canonical casing.
+ * The normalization should:
+ * 1. Convert tool names that match CC tools (case-insensitive) to CC casing on outbound
+ * 2. Convert tool names back to the original casing on inbound
+ *
+ * This is a simple case-insensitive lookup, NOT a mapping of different names.
+ * e.g., "todowrite" -> "TodoWrite" -> "todowrite" (round-trip works)
+ *
+ * The old `find -> Glob` mapping was WRONG because:
+ * - Outbound: "find" -> "Glob"
+ * - Inbound: "Glob" -> ??? (no tool named "glob" in context.tools, only "find")
+ * - Result: tool call has name "Glob" but no tool exists with that name
+ */
+describe.skipIf(!oauthToken)("Anthropic OAuth tool name normalization", () => {
+	const model = getModel("anthropic", "claude-sonnet-4-20250514");
+
+	it("should normalize user-defined tool matching CC name (todowrite -> TodoWrite -> todowrite)", async () => {
+		// User defines a tool named "todowrite" (lowercase)
+		// CC has "TodoWrite" - this should round-trip correctly
+		const todoTool: Tool = {
+			name: "todowrite",
+			description: "Write a todo item",
+			parameters: Type.Object({
+				task: Type.String({ description: "The task to add" }),
+			}),
+		};
+
+		const context: Context = {
+			systemPrompt: "You are a helpful assistant. Use the todowrite tool when asked to add todos.",
+			messages: [
+				{
+					role: "user",
+					content: "Add a todo: buy milk. Use the todowrite tool.",
+					timestamp: Date.now(),
+				},
+			],
+			tools: [todoTool],
+		};
+
+		const s = stream(model, context, { apiKey: oauthToken });
+		let toolCallName: string | undefined;
+
+		for await (const event of s) {
+			if (event.type === "toolcall_end") {
+				const toolCall = event.partial.content[event.contentIndex];
+				if (toolCall.type === "toolCall") {
+					toolCallName = toolCall.name;
+				}
+			}
+		}
+
+		const response = await s.result();
+		expect(response.stopReason, `Error: ${response.errorMessage}`).toBe("toolUse");
+
+		// The tool call should come back with the ORIGINAL name "todowrite", not "TodoWrite"
+		expect(toolCallName).toBe("todowrite");
+	});
+
+	it("should handle pi's built-in tools (read, write, edit, bash)", async () => {
+		// Pi's tools use lowercase names, CC uses PascalCase
+		const readTool: Tool = {
+			name: "read",
+			description: "Read a file",
+			parameters: Type.Object({
+				path: Type.String({ description: "File path" }),
+			}),
+		};
+
+		const context: Context = {
+			systemPrompt: "You are a helpful assistant. Use the read tool to read files.",
+			messages: [
+				{
+					role: "user",
+					content: "Read the file /tmp/test.txt using the read tool.",
+					timestamp: Date.now(),
+				},
+			],
+			tools: [readTool],
+		};
+
+		const s = stream(model, context, { apiKey: oauthToken });
+		let toolCallName: string | undefined;
+
+		for await (const event of s) {
+			if (event.type === "toolcall_end") {
+				const toolCall = event.partial.content[event.contentIndex];
+				if (toolCall.type === "toolCall") {
+					toolCallName = toolCall.name;
+				}
+			}
+		}
+
+		const response = await s.result();
+		expect(response.stopReason, `Error: ${response.errorMessage}`).toBe("toolUse");
+
+		// The tool call should come back with the ORIGINAL name "read", not "Read"
+		expect(toolCallName).toBe("read");
+	});
+
+	it("should NOT map find to Glob - find is not a CC tool name", async () => {
+		// Pi has a "find" tool, CC has "Glob" - these are DIFFERENT tools
+		// The old code incorrectly mapped find -> Glob, which broke the round-trip
+		// because there's no tool named "glob" in context.tools
+		const findTool: Tool = {
+			name: "find",
+			description: "Find files by pattern",
+			parameters: Type.Object({
+				pattern: Type.String({ description: "Glob pattern" }),
+			}),
+		};
+
+		const context: Context = {
+			systemPrompt: "You are a helpful assistant. Use the find tool to search for files.",
+			messages: [
+				{
+					role: "user",
+					content: "Find all .ts files using the find tool.",
+					timestamp: Date.now(),
+				},
+			],
+			tools: [findTool],
+		};
+
+		const s = stream(model, context, { apiKey: oauthToken });
+		let toolCallName: string | undefined;
+
+		for await (const event of s) {
+			if (event.type === "toolcall_end") {
+				const toolCall = event.partial.content[event.contentIndex];
+				if (toolCall.type === "toolCall") {
+					toolCallName = toolCall.name;
+				}
+			}
+		}
+
+		const response = await s.result();
+		expect(response.stopReason, `Error: ${response.errorMessage}`).toBe("toolUse");
+
+		// With the BROKEN find -> Glob mapping:
+		// - Sent as "Glob" to Anthropic
+		// - Received back as "Glob"
+		// - fromClaudeCodeName("Glob", tools) looks for tool.name.toLowerCase() === "glob"
+		// - No match (tool is named "find"), returns "Glob"
+		// - Test fails: toolCallName is "Glob" instead of "find"
+		//
+		// With the CORRECT implementation (no find->Glob mapping):
+		// - Sent as "find" to Anthropic (no CC tool named "Find")
+		// - Received back as "find"
+		// - Test passes: toolCallName is "find"
+		expect(toolCallName).toBe("find");
+	});
+
+	it("should handle custom tools that don't match any CC tool names", async () => {
+		// A completely custom tool should pass through unchanged
+		const customTool: Tool = {
+			name: "my_custom_tool",
+			description: "A custom tool",
+			parameters: Type.Object({
+				input: Type.String({ description: "Input value" }),
+			}),
+		};
+
+		const context: Context = {
+			systemPrompt: "You are a helpful assistant. Use my_custom_tool when asked.",
+			messages: [
+				{
+					role: "user",
+					content: "Use my_custom_tool with input 'hello'.",
+					timestamp: Date.now(),
+				},
+			],
+			tools: [customTool],
+		};
+
+		const s = stream(model, context, { apiKey: oauthToken });
+		let toolCallName: string | undefined;
+
+		for await (const event of s) {
+			if (event.type === "toolcall_end") {
+				const toolCall = event.partial.content[event.contentIndex];
+				if (toolCall.type === "toolCall") {
+					toolCallName = toolCall.name;
+				}
+			}
+		}
+
+		const response = await s.result();
+		expect(response.stopReason, `Error: ${response.errorMessage}`).toBe("toolUse");
+
+		// Custom tool names should pass through unchanged
+		expect(toolCallName).toBe("my_custom_tool");
+	});
+});

package/pi.dev-src/pi-mono/ai/test/azure-utils.ts

@@ -0,0 +1,28 @@
+/**
+ * Utility functions for Azure OpenAI tests
+ */
+
+function parseDeploymentNameMap(value: string | undefined): Map<string, string> {
+	const map = new Map<string, string>();
+	if (!value) return map;
+	for (const entry of value.split(",")) {
+		const trimmed = entry.trim();
+		if (!trimmed) continue;
+		const [modelId, deploymentName] = trimmed.split("=", 2);
+		if (!modelId || !deploymentName) continue;
+		map.set(modelId.trim(), deploymentName.trim());
+	}
+	return map;
+}
+
+export function hasAzureOpenAICredentials(): boolean {
+	const hasKey = !!process.env.AZURE_OPENAI_API_KEY;
+	const hasBaseUrl = !!(process.env.AZURE_OPENAI_BASE_URL || process.env.AZURE_OPENAI_RESOURCE_NAME);
+	return hasKey && hasBaseUrl;
+}
+
+export function resolveAzureDeploymentName(modelId: string): string | undefined {
+	const mapValue = process.env.AZURE_OPENAI_DEPLOYMENT_NAME_MAP;
+	if (!mapValue) return undefined;
+	return parseDeploymentNameMap(mapValue).get(modelId);
+}

package/pi.dev-src/pi-mono/ai/test/bedrock-endpoint-resolution.test.ts

@@ -0,0 +1,131 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
+
+const bedrockMock = vi.hoisted(() => ({
+	constructorCalls: [] as Array<Record<string, unknown>>,
+}));
+
+vi.mock("@aws-sdk/client-bedrock-runtime", () => {
+	class BedrockRuntimeServiceException extends Error {}
+
+	class BedrockRuntimeClient {
+		constructor(config: Record<string, unknown>) {
+			bedrockMock.constructorCalls.push(config);
+		}
+
+		send(): Promise<never> {
+			return Promise.reject(new Error("mock send"));
+		}
+	}
+
+	class ConverseStreamCommand {
+		readonly input: unknown;
+
+		constructor(input: unknown) {
+			this.input = input;
+		}
+	}
+
+	return {
+		BedrockRuntimeClient,
+		BedrockRuntimeServiceException,
+		ConverseStreamCommand,
+		StopReason: {
+			END_TURN: "end_turn",
+			STOP_SEQUENCE: "stop_sequence",
+			MAX_TOKENS: "max_tokens",
+			MODEL_CONTEXT_WINDOW_EXCEEDED: "model_context_window_exceeded",
+			TOOL_USE: "tool_use",
+		},
+		CachePointType: { DEFAULT: "default" },
+		CacheTTL: { ONE_HOUR: "ONE_HOUR" },
+		ConversationRole: { ASSISTANT: "assistant", USER: "user" },
+		ImageFormat: { JPEG: "jpeg", PNG: "png", GIF: "gif", WEBP: "webp" },
+		ToolResultStatus: { ERROR: "error", SUCCESS: "success" },
+	};
+});
+
+import { getModel } from "../src/models.js";
+import { streamBedrock } from "../src/providers/amazon-bedrock.js";
+import type { Context, Model } from "../src/types.js";
+
+const context: Context = {
+	messages: [{ role: "user", content: "hello", timestamp: Date.now() }],
+};
+
+const originalAwsRegion = process.env.AWS_REGION;
+const originalAwsDefaultRegion = process.env.AWS_DEFAULT_REGION;
+const originalAwsProfile = process.env.AWS_PROFILE;
+
+beforeEach(() => {
+	bedrockMock.constructorCalls.length = 0;
+	delete process.env.AWS_REGION;
+	delete process.env.AWS_DEFAULT_REGION;
+	delete process.env.AWS_PROFILE;
+});
+
+afterEach(() => {
+	if (originalAwsRegion === undefined) {
+		delete process.env.AWS_REGION;
+	} else {
+		process.env.AWS_REGION = originalAwsRegion;
+	}
+
+	if (originalAwsDefaultRegion === undefined) {
+		delete process.env.AWS_DEFAULT_REGION;
+	} else {
+		process.env.AWS_DEFAULT_REGION = originalAwsDefaultRegion;
+	}
+
+	if (originalAwsProfile === undefined) {
+		delete process.env.AWS_PROFILE;
+	} else {
+		process.env.AWS_PROFILE = originalAwsProfile;
+	}
+});
+
+async function captureClientConfig(model: Model<"bedrock-converse-stream">): Promise<Record<string, unknown>> {
+	await streamBedrock(model, context, { cacheRetention: "none" }).result();
+	expect(bedrockMock.constructorCalls).toHaveLength(1);
+	return bedrockMock.constructorCalls[0];
+}
+
+describe("bedrock endpoint resolution", () => {
+	it("assigns eu-central-1 runtime URLs to built-in EU inference profiles", () => {
+		const model = getModel("amazon-bedrock", "eu.anthropic.claude-sonnet-4-5-20250929-v1:0");
+
+		expect(model.baseUrl).toBe("https://bedrock-runtime.eu-central-1.amazonaws.com");
+	});
+
+	it("does not pin standard AWS endpoints when AWS_REGION is configured", async () => {
+		process.env.AWS_REGION = "us-east-2";
+		const model = getModel("amazon-bedrock", "us.anthropic.claude-opus-4-7");
+
+		const config = await captureClientConfig(model);
+
+		expect(config.region).toBe("us-east-2");
+		expect(config.endpoint).toBeUndefined();
+	});
+
+	it("derives region from a built-in EU endpoint when no region or profile is configured", async () => {
+		const model = getModel("amazon-bedrock", "eu.anthropic.claude-sonnet-4-5-20250929-v1:0");
+
+		const config = await captureClientConfig(model);
+
+		expect(config.endpoint).toBe("https://bedrock-runtime.eu-central-1.amazonaws.com");
+		expect(config.region).toBe("eu-central-1");
+	});
+
+	it("still passes custom Bedrock endpoints through to the SDK client", async () => {
+		process.env.AWS_REGION = "us-west-2";
+		const baseModel = getModel("amazon-bedrock", "us.anthropic.claude-opus-4-7");
+		const model: Model<"bedrock-converse-stream"> = {
+			...baseModel,
+			baseUrl: "https://bedrock-vpc.example.com",
+		};
+
+		const config = await captureClientConfig(model);
+
+		expect(config.endpoint).toBe("https://bedrock-vpc.example.com");
+		expect(config.region).toBe("us-west-2");
+	});
+});

package/pi.dev-src/pi-mono/ai/test/bedrock-models.test.ts

@@ -0,0 +1,66 @@
+/**
+ * A test suite to ensure all configured Amazon Bedrock models are usable.
+ *
+ * This is here to make sure we got correct model identifiers from models.dev and other sources.
+ * Because Amazon Bedrock requires cross-region inference in some models,
+ * plain model identifiers are not always usable and it requires tweaking of model identifiers to use cross-region inference.
+ * See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html#inference-profiles-support-system for more details.
+ *
+ * This test suite is not enabled by default unless AWS credentials and `BEDROCK_EXTENSIVE_MODEL_TEST` environment variables are set.
+ * This test suite takes ~2 minutes to run. Because not all models are available in all regions,
+ * it's recommended to use `us-west-2` region for best coverage for running this test suite.
+ *
+ * You can run this test suite with:
+ * ```bash
+ * $ AWS_REGION=us-west-2 BEDROCK_EXTENSIVE_MODEL_TEST=1 AWS_PROFILE=... npm test -- ./test/bedrock-models.test.ts
+ * ```
+ */
+
+import { describe, expect, it } from "vitest";
+import { getModels } from "../src/models.js";
+import { complete } from "../src/stream.js";
+import type { Context } from "../src/types.js";
+import { hasBedrockCredentials } from "./bedrock-utils.js";
+
+describe("Amazon Bedrock Models", () => {
+	const models = getModels("amazon-bedrock");
+
+	it("should get all available Bedrock models", () => {
+		expect(models.length).toBeGreaterThan(0);
+		console.log(`Found ${models.length} Bedrock models`);
+	});
+
+	if (hasBedrockCredentials() && process.env.BEDROCK_EXTENSIVE_MODEL_TEST) {
+		for (const model of models) {
+			it(`should make a simple request with ${model.id}`, { timeout: 10_000 }, async () => {
+				const context: Context = {
+					systemPrompt: "You are a helpful assistant. Be extremely concise.",
+					messages: [
+						{
+							role: "user",
+							content: "Reply with exactly: 'OK'",
+							timestamp: Date.now(),
+						},
+					],
+				};
+
+				const response = await complete(model, context);
+
+				expect(response.role).toBe("assistant");
+				expect(response.content).toBeTruthy();
+				expect(response.content.length).toBeGreaterThan(0);
+				expect(response.usage.input + response.usage.cacheRead).toBeGreaterThan(0);
+				expect(response.usage.output).toBeGreaterThan(0);
+				expect(response.errorMessage).toBeFalsy();
+
+				const textContent = response.content
+					.filter((b) => b.type === "text")
+					.map((b) => (b.type === "text" ? b.text : ""))
+					.join("")
+					.trim();
+				expect(textContent).toBeTruthy();
+				console.log(`${model.id}: ${textContent.substring(0, 100)}`);
+			});
+		}
+	}
+});

package/pi.dev-src/pi-mono/ai/test/bedrock-thinking-payload.test.ts

@@ -0,0 +1,107 @@
+import { describe, expect, it } from "vitest";
+import { getModel } from "../src/models.js";
+import { type BedrockOptions, streamBedrock } from "../src/providers/amazon-bedrock.js";
+import type { Context, Model } from "../src/types.js";
+
+interface BedrockThinkingPayload {
+	additionalModelRequestFields?: {
+		thinking?: { type: string; budget_tokens?: number; display?: string };
+		output_config?: { effort?: string };
+		anthropic_beta?: string[];
+	};
+}
+
+function makeContext(): Context {
+	return {
+		messages: [{ role: "user", content: "Hello", timestamp: Date.now() }],
+	};
+}
+
+async function capturePayload(
+	model: Model<"bedrock-converse-stream">,
+	options?: BedrockOptions,
+): Promise<BedrockThinkingPayload> {
+	let capturedPayload: BedrockThinkingPayload | undefined;
+	const s = streamBedrock(model, makeContext(), {
+		...options,
+		reasoning: options?.reasoning ?? "high",
+		signal: AbortSignal.abort(),
+		onPayload: (payload) => {
+			capturedPayload = payload as BedrockThinkingPayload;
+			return payload;
+		},
+	});
+
+	for await (const event of s) {
+		if (event.type === "error") {
+			break;
+		}
+	}
+
+	if (!capturedPayload) {
+		throw new Error("Expected Bedrock payload to be captured before request abort");
+	}
+
+	return capturedPayload;
+}
+
+describe("Bedrock thinking payload", () => {
+	it("uses adaptive thinking for Claude Opus 4.7 when reasoning is enabled", async () => {
+		const baseModel = getModel("amazon-bedrock", "global.anthropic.claude-opus-4-6-v1");
+		const model: Model<"bedrock-converse-stream"> = {
+			...baseModel,
+			id: "global.anthropic.claude-opus-4-7-v1",
+			name: "Claude Opus 4.7 (Global)",
+		};
+
+		const payload = await capturePayload(model);
+
+		expect(payload.additionalModelRequestFields?.thinking).toEqual({ type: "adaptive", display: "summarized" });
+		expect(payload.additionalModelRequestFields?.output_config).toEqual({ effort: "high" });
+		expect(payload.additionalModelRequestFields?.anthropic_beta).toBeUndefined();
+	});
+
+	it("maps xhigh reasoning to effort=xhigh for Claude Opus 4.7", async () => {
+		const baseModel = getModel("amazon-bedrock", "global.anthropic.claude-opus-4-6-v1");
+		const model: Model<"bedrock-converse-stream"> = {
+			...baseModel,
+			id: "global.anthropic.claude-opus-4-7-v1",
+			name: "Claude Opus 4.7 (Global)",
+		};
+
+		const payload = await capturePayload(model, { reasoning: "xhigh" });
+
+		expect(payload.additionalModelRequestFields?.thinking).toEqual({ type: "adaptive", display: "summarized" });
+		expect(payload.additionalModelRequestFields?.output_config).toEqual({ effort: "xhigh" });
+		expect(payload.additionalModelRequestFields?.anthropic_beta).toBeUndefined();
+	});
+
+	it("omits display for GovCloud model ids on non-adaptive Claude thinking", async () => {
+		const baseModel = getModel("amazon-bedrock", "us.anthropic.claude-sonnet-4-5-20250929-v1:0");
+		const model: Model<"bedrock-converse-stream"> = {
+			...baseModel,
+			id: "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0",
+			name: "Claude Sonnet 4.5 (GovCloud)",
+		};
+
+		const payload = await capturePayload(model);
+
+		expect(payload.additionalModelRequestFields?.thinking).toEqual({ type: "enabled", budget_tokens: 16384 });
+		expect(payload.additionalModelRequestFields?.anthropic_beta).toEqual(["interleaved-thinking-2025-05-14"]);
+	});
+
+	it("omits display for GovCloud regions on adaptive Claude thinking", async () => {
+		const baseModel = getModel("amazon-bedrock", "global.anthropic.claude-opus-4-6-v1");
+		const model: Model<"bedrock-converse-stream"> = {
+			...baseModel,
+			id: "global.anthropic.claude-opus-4-7-v1",
+			name: "Claude Opus 4.7 (Global)",
+		};
+
+		const payload = await capturePayload(model, { region: "us-gov-west-1" });
+
+		expect(payload.additionalModelRequestFields?.thinking).toEqual({ type: "adaptive" });
+		expect(payload.additionalModelRequestFields?.output_config).toEqual({ effort: "high" });
+		expect(payload.additionalModelRequestFields?.anthropic_beta).toBeUndefined();
+	});
+});

package/pi.dev-src/pi-mono/ai/test/bedrock-utils.ts

@@ -0,0 +1,18 @@
+/**
+ * Utility functions for Amazon Bedrock tests
+ */
+
+/**
+ * Check if any valid AWS credentials are configured for Bedrock.
+ * Returns true if any of the following are set:
+ * - AWS_PROFILE (named profile from ~/.aws/credentials)
+ * - AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY (IAM keys)
+ * - AWS_BEARER_TOKEN_BEDROCK (Bedrock API key)
+ */
+export function hasBedrockCredentials(): boolean {
+	return !!(
+		process.env.AWS_PROFILE ||
+		(process.env.AWS_ACCESS_KEY_ID && process.env.AWS_SECRET_ACCESS_KEY) ||
+		process.env.AWS_BEARER_TOKEN_BEDROCK
+	);
+}