gsd-pi 2.58.0-dev.778d6ac → 2.58.0-dev.d63175c

package/packages/pi-coding-agent/src/core/retry-handler.test.ts

@@ -1,255 +0,0 @@
-/**
- * RetryHandler tests — long-context entitlement 429 error handling (#2803)
- *
- * Verifies that "Extra usage is required for long context requests" errors
- * are classified as quota_exhausted (not rate_limit) and trigger a model
- * downgrade from [1m] to base when no cross-provider fallback exists.
- */
-
-import { describe, it, beforeEach, mock, type Mock } from "node:test";
-import assert from "node:assert/strict";
-import { RetryHandler, type RetryHandlerDeps } from "./retry-handler.js";
-import type { Api, AssistantMessage, Model } from "@gsd/pi-ai";
-import type { FallbackResolver } from "./fallback-resolver.js";
-import type { ModelRegistry } from "./model-registry.js";
-import type { SettingsManager } from "./settings-manager.js";
-
-// ─── Helpers ────────────────────────────────────────────────────────────────
-
-function createMockModel(provider: string, id: string): Model<Api> {
-	return {
-		id,
-		name: id,
-		api: "anthropic" as Api,
-		provider,
-		baseUrl: "https://api.anthropic.com",
-		reasoning: false,
-		input: ["text"],
-		cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
-		contextWindow: 1_000_000,
-		maxTokens: 16384,
-	} as Model<Api>;
-}
-
-function errorMessage(msg: string): AssistantMessage {
-	return {
-		role: "assistant",
-		content: [],
-		api: "anthropic-messages",
-		provider: "anthropic",
-		model: "claude-opus-4-6[1m]",
-		usage: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, totalTokens: 0, cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 } },
-		stopReason: "error",
-		errorMessage: msg,
-		timestamp: Date.now(),
-	} as AssistantMessage;
-}
-
-interface MockDeps {
-	deps: RetryHandlerDeps;
-	emittedEvents: Array<Record<string, any>>;
-	continueFn: Mock<() => Promise<void>>;
-	onModelChangeFn: Mock<(model: Model<any>) => void>;
-	markUsageLimitReached: Mock<(...args: any[]) => boolean>;
-	findFallback: Mock<(...args: any[]) => Promise<any>>;
-	findModel: Mock<(provider: string, modelId: string) => Model<Api> | undefined>;
-}
-
-function createMockDeps(overrides?: {
-	model?: Model<Api>;
-	retryEnabled?: boolean;
-	markUsageLimitReachedResult?: boolean;
-	fallbackResult?: any;
-	findModelResult?: (provider: string, modelId: string) => Model<Api> | undefined;
-}): MockDeps {
-	const model = overrides?.model ?? createMockModel("anthropic", "claude-opus-4-6[1m]");
-	const emittedEvents: Array<Record<string, any>> = [];
-	const continueFn = mock.fn(async () => {});
-	const onModelChangeFn = mock.fn((_model: Model<any>) => {});
-	const markUsageLimitReached = mock.fn(
-		() => overrides?.markUsageLimitReachedResult ?? false,
-	);
-	const findFallback = mock.fn(async () => overrides?.fallbackResult ?? null);
-	const findModel = mock.fn(
-		overrides?.findModelResult ?? ((_provider: string, _modelId: string) => undefined),
-	);
-
-	const messages: Array<{ role: string } & Record<string, any>> = [];
-
-	const deps: RetryHandlerDeps = {
-		agent: {
-			continue: continueFn,
-			state: { messages },
-			setModel: mock.fn(),
-			replaceMessages: mock.fn((newMessages: any[]) => {
-				messages.length = 0;
-				messages.push(...newMessages);
-			}),
-		} as any,
-		settingsManager: {
-			getRetryEnabled: () => overrides?.retryEnabled ?? true,
-			getRetrySettings: () => ({
-				enabled: overrides?.retryEnabled ?? true,
-				maxRetries: 5,
-				baseDelayMs: 1000,
-				maxDelayMs: 30000,
-			}),
-		} as unknown as SettingsManager,
-		modelRegistry: {
-			authStorage: {
-				markUsageLimitReached,
-			},
-			find: findModel,
-		} as unknown as ModelRegistry,
-		fallbackResolver: {
-			findFallback,
-		} as unknown as FallbackResolver,
-		getModel: () => model,
-		getSessionId: () => "test-session",
-		emit: (event: any) => emittedEvents.push(event),
-		onModelChange: onModelChangeFn,
-	};
-
-	return { deps, emittedEvents, continueFn, onModelChangeFn, markUsageLimitReached, findFallback, findModel };
-}
-
-// ─── _classifyErrorType (tested via handleRetryableError behavior) ──────────
-
-describe("RetryHandler — long-context entitlement 429 (#2803)", () => {
-
-	describe("error classification", () => {
-		it("classifies 'Extra usage is required for long context requests' as quota_exhausted, not rate_limit", async () => {
-			// When the error is classified as quota_exhausted AND no alternate credentials
-			// AND no fallback, the handler should emit fallback_chain_exhausted and stop.
-			// If misclassified as rate_limit, it would enter the backoff loop instead.
-			const { deps, emittedEvents, findModel } = createMockDeps({
-				model: createMockModel("anthropic", "claude-opus-4-6[1m]"),
-				markUsageLimitReachedResult: false, // no alternate credentials
-				fallbackResult: null, // no cross-provider fallback
-				findModelResult: () => undefined, // no base model either
-			});
-
-			const handler = new RetryHandler(deps);
-			const msg = errorMessage(
-				'429 {"type":"error","error":{"type":"rate_limit_error","message":"Extra usage is required for long context requests."}}'
-			);
-
-			const result = await handler.handleRetryableError(msg);
-
-			// Should NOT retry (would be true if misclassified as rate_limit entering backoff)
-			assert.equal(result, false);
-
-			// Should emit fallback_chain_exhausted (quota_exhausted path), NOT auto_retry_start (backoff path)
-			const chainExhausted = emittedEvents.find((e) => e.type === "fallback_chain_exhausted");
-			assert.ok(chainExhausted, "Expected fallback_chain_exhausted event for entitlement error");
-
-			const retryStart = emittedEvents.find((e) => e.type === "auto_retry_start");
-			assert.equal(retryStart, undefined, "Should NOT emit auto_retry_start for entitlement error");
-		});
-
-		it("still classifies regular 429 rate limits as rate_limit", async () => {
-			// A normal "rate limit" 429 should still be classified as rate_limit
-			const { deps, emittedEvents } = createMockDeps({
-				model: createMockModel("anthropic", "claude-opus-4-6"),
-				markUsageLimitReachedResult: false,
-				fallbackResult: null,
-			});
-
-			const handler = new RetryHandler(deps);
-			const msg = errorMessage("429 Too Many Requests");
-
-			const result = await handler.handleRetryableError(msg);
-
-			// Should enter the backoff loop (rate_limit path, not quota_exhausted)
-			assert.equal(result, true);
-
-			const retryStart = emittedEvents.find((e) => e.type === "auto_retry_start");
-			assert.ok(retryStart, "Regular 429 should enter backoff retry");
-		});
-	});
-
-	describe("long-context model downgrade", () => {
-		it("downgrades from [1m] to base model when entitlement error and no fallback", async () => {
-			const baseModel = createMockModel("anthropic", "claude-opus-4-6");
-			const { deps, emittedEvents, onModelChangeFn, continueFn } = createMockDeps({
-				model: createMockModel("anthropic", "claude-opus-4-6[1m]"),
-				markUsageLimitReachedResult: false,
-				fallbackResult: null,
-				findModelResult: (provider: string, modelId: string) => {
-					if (provider === "anthropic" && modelId === "claude-opus-4-6") return baseModel;
-					return undefined;
-				},
-			});
-
-			const handler = new RetryHandler(deps);
-			const msg = errorMessage("Extra usage is required for long context requests.");
-
-			const result = await handler.handleRetryableError(msg);
-
-			assert.equal(result, true, "Should retry after downgrade");
-
-			// Should have called setModel with the base model
-			const setModelCalls = (deps.agent.setModel as any).mock.calls;
-			assert.equal(setModelCalls.length, 1);
-			assert.equal(setModelCalls[0].arguments[0].id, "claude-opus-4-6");
-
-			// Should have notified about model change
-			assert.equal(onModelChangeFn.mock.calls.length, 1);
-
-			// Should emit a fallback_provider_switch event indicating downgrade
-			const switchEvent = emittedEvents.find((e) => e.type === "fallback_provider_switch");
-			assert.ok(switchEvent, "Expected fallback_provider_switch event for downgrade");
-			assert.ok(switchEvent!.reason.includes("long context downgrade"), `reason should mention downgrade: ${switchEvent!.reason}`);
-		});
-
-		it("emits fallback_chain_exhausted when base model is also unavailable", async () => {
-			const { deps, emittedEvents } = createMockDeps({
-				model: createMockModel("anthropic", "claude-opus-4-6[1m]"),
-				markUsageLimitReachedResult: false,
-				fallbackResult: null,
-				findModelResult: () => undefined, // base model not found
-			});
-
-			const handler = new RetryHandler(deps);
-			const msg = errorMessage("Extra usage is required for long context requests.");
-
-			const result = await handler.handleRetryableError(msg);
-
-			assert.equal(result, false);
-			const chainExhausted = emittedEvents.find((e) => e.type === "fallback_chain_exhausted");
-			assert.ok(chainExhausted, "Expected fallback_chain_exhausted when base model unavailable");
-		});
-
-		it("does not attempt downgrade for non-[1m] models", async () => {
-			// When a regular model (no [1m] suffix) gets a quota_exhausted error
-			// with no fallback, it should just stop — no downgrade attempt.
-			const { deps, emittedEvents } = createMockDeps({
-				model: createMockModel("anthropic", "claude-opus-4-6"),
-				markUsageLimitReachedResult: false,
-				fallbackResult: null,
-			});
-
-			const handler = new RetryHandler(deps);
-			const msg = errorMessage("Extra usage is required for long context requests.");
-
-			const result = await handler.handleRetryableError(msg);
-
-			assert.equal(result, false);
-			const chainExhausted = emittedEvents.find((e) => e.type === "fallback_chain_exhausted");
-			assert.ok(chainExhausted);
-
-			// No downgrade switch should occur
-			const switchEvent = emittedEvents.find((e) => e.type === "fallback_provider_switch");
-			assert.equal(switchEvent, undefined, "Should not switch for non-[1m] models");
-		});
-	});
-
-	describe("isRetryableError", () => {
-		it("considers long-context entitlement error as retryable", () => {
-			const { deps } = createMockDeps();
-			const handler = new RetryHandler(deps);
-			const msg = errorMessage("Extra usage is required for long context requests.");
-			assert.equal(handler.isRetryableError(msg), true);
-		});
-	});
-});

package/packages/pi-coding-agent/src/core/tools/spawn-shell-windows.test.ts

@@ -1,92 +0,0 @@
-/**
- * spawn-shell-windows.test.ts — Regression test for Windows spawn ENOENT/EINVAL.
- *
- * On Windows, npm/npx/tsc and other tools are installed as .cmd batch scripts.
- * Node's `spawn()` without `shell: true` cannot execute .cmd files, resulting
- * in ENOENT or EINVAL errors. Every spawn site that may invoke a user-installed
- * binary (not `node` or a shell like `sh`/`bash`/`cmd`) must include
- * `shell: process.platform === "win32"` so the call is resolved through cmd.exe
- * on Windows while remaining a direct exec on POSIX.
- *
- * This test structurally scans all spawn sites and verifies the guard is present.
- *
- * Fixes: gsd-build/gsd-2#2854
- */
-
-import test from "node:test";
-import assert from "node:assert/strict";
-import { readFileSync } from "node:fs";
-import { join, dirname, relative } from "node:path";
-import { fileURLToPath } from "node:url";
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const coreDir = join(__dirname, "..");
-
-/**
- * Files that call `spawn()` with a user-facing binary (not `node`, `sh`, `bash`,
- * or `cmd`) and therefore need the Windows shell guard.
- *
- * If a file spawns only hardcoded system binaries (like `node` in rpc-client.ts),
- * it does not need the guard and should NOT appear here.
- */
-const SPAWN_FILES_NEEDING_SHELL_GUARD = [
-	// Extension's GSD client — spawns the `gsd` binary which is a .cmd on Windows
-	join(coreDir, "..", "..", "..", "vscode-extension", "src", "gsd-client.ts"),
-	// exec.ts — used by extensions to run arbitrary commands
-	join(coreDir, "exec.ts"),
-	// LSP index — spawns project-type commands (tsc, cargo, etc.)
-	join(coreDir, "lsp", "index.ts"),
-	// LSP client — spawns LSP server binaries (npx, etc.)
-	join(coreDir, "lsp", "client.ts"),
-	// LSP mux — spawns lspmux binary
-	join(coreDir, "lsp", "lspmux.ts"),
-	// Package manager — spawns npm/yarn/pnpm
-	join(coreDir, "package-manager.ts"),
-];
-
-test("all spawn sites that invoke user-facing binaries include shell: process.platform === 'win32'", () => {
-	const failures: string[] = [];
-
-	for (const file of SPAWN_FILES_NEEDING_SHELL_GUARD) {
-		let content: string;
-		try {
-			content = readFileSync(file, "utf-8");
-		} catch {
-			// File may not exist in this checkout — skip
-			continue;
-		}
-
-		const lines = content.split("\n");
-
-		// Find all spawn(..., { ... }) call sites and check each one
-		// for the presence of `shell: process.platform === "win32"` within
-		// 5 lines after the spawn call.
-		for (let i = 0; i < lines.length; i++) {
-			const line = lines[i]!;
-			// Skip comments
-			if (line.trim().startsWith("//") || line.trim().startsWith("*")) continue;
-
-			// Detect a spawn() call
-			if (/\bspawn\(/.test(line)) {
-				// Look ahead up to 8 lines for the shell guard
-				const lookahead = lines.slice(i, i + 8).join("\n");
-				const hasShellGuard =
-					/shell:\s*process\.platform\s*===\s*["']win32["']/.test(lookahead);
-
-				if (!hasShellGuard) {
-					const relPath = relative(join(coreDir, "..", ".."), file);
-					failures.push(`${relPath}:${i + 1}`);
-				}
-			}
-		}
-	}
-
-	assert.deepEqual(
-		failures,
-		[],
-		`The following spawn sites are missing 'shell: process.platform === "win32"':\n` +
-		failures.map(f => `  - ${f}`).join("\n") +
-		`\nOn Windows, .cmd wrapper scripts (npm, npx, tsc, gsd) require shell ` +
-		`resolution. Without this guard, spawn fails with ENOENT or EINVAL.`,
-	);
-});

package/src/resources/extensions/gsd/milestone-validation-gates.ts

@@ -1,56 +0,0 @@
-/**
- * Milestone validation quality gate persistence.
- *
- * #2945 Bug 4: validate-milestone was writing VALIDATION.md to disk and
- * inserting an assessment row, but never persisted structured quality_gates
- * records in the DB. This module inserts milestone-level validation gates
- * that correspond to the validation checks performed.
- *
- * Gate IDs for milestone validation:
- *   MV01 — Success criteria checklist
- *   MV02 — Slice delivery audit
- *   MV03 — Cross-slice integration
- *   MV04 — Requirement coverage
- *
- * These use the existing quality_gates table with scope "milestone".
- */
-
-import { _getAdapter } from "./gsd-db.js";
-
-/** Milestone validation gate IDs. */
-const MILESTONE_GATE_IDS = ["MV01", "MV02", "MV03", "MV04"] as const;
-
-/**
- * Insert milestone-level quality_gates records for a validation run.
- *
- * Each gate is inserted with status "complete" and a verdict derived
- * from the overall milestone validation verdict. Individual gate-level
- * verdicts are not available (the handler receives a single verdict),
- * so all gates share the overall verdict.
- */
-export function insertMilestoneValidationGates(
-  milestoneId: string,
-  sliceId: string,
-  verdict: string,
-  evaluatedAt: string,
-): void {
-  const db = _getAdapter();
-  if (!db) return;
-
-  const gateVerdict = verdict === "pass" ? "pass" : "flag";
-
-  for (const gateId of MILESTONE_GATE_IDS) {
-    db.prepare(
-      `INSERT OR REPLACE INTO quality_gates
-       (milestone_id, slice_id, gate_id, scope, task_id, status, verdict, rationale, findings, evaluated_at)
-       VALUES (:mid, :sid, :gid, 'milestone', '', 'complete', :verdict, :rationale, '', :evaluated_at)`,
-    ).run({
-      ":mid": milestoneId,
-      ":sid": sliceId,
-      ":gid": gateId,
-      ":verdict": gateVerdict,
-      ":rationale": `Milestone validation verdict: ${verdict}`,
-      ":evaluated_at": evaluatedAt,
-    });
-  }
-}

package/src/resources/extensions/gsd/tests/auto-mode-interactive-guard.test.ts

@@ -1,71 +0,0 @@
-/**
- * Test: auto-mode prompts must prohibit ask_user_questions / secure_env_collect
- *
- * Bug #2936: When the LLM calls ask_user_questions during auto-mode units
- * (plan-slice, execute-task, complete-slice), the interactive tool queues a
- * user response which causes the subsequent gsd_plan_slice / gsd_complete_task
- * call to fail with "Skipped due to queued user message." The canonical GSD
- * tool call is never recorded, verifyExpectedArtifact finds no artifact, and
- * the dispatch loop re-dispatches the same unit 2-4x.
- *
- * Fix: Each auto-mode prompt must contain an "Autonomous execution" guard
- * that explicitly prohibits ask_user_questions and secure_env_collect.
- */
-
-import test from "node:test";
-import assert from "node:assert/strict";
-import { readFileSync } from "node:fs";
-import { join, dirname } from "node:path";
-import { fileURLToPath } from "node:url";
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const promptsDir = join(__dirname, "..", "prompts");
-
-function loadPromptRaw(name: string): string {
-  return readFileSync(join(promptsDir, `${name}.md`), "utf-8");
-}
-
-const AUTO_MODE_PROMPTS = ["plan-slice", "execute-task", "complete-slice"];
-
-for (const promptName of AUTO_MODE_PROMPTS) {
-  test(`${promptName} prompt prohibits ask_user_questions in auto-mode`, () => {
-    const content = loadPromptRaw(promptName);
-
-    assert.ok(
-      content.includes("ask_user_questions"),
-      `${promptName}.md must mention ask_user_questions (to prohibit it)`,
-    );
-
-    assert.ok(
-      content.includes("secure_env_collect"),
-      `${promptName}.md must mention secure_env_collect (to prohibit it)`,
-    );
-
-    // The guard must clearly state this is autonomous / auto-mode
-    assert.ok(
-      content.toLowerCase().includes("auto-mode") || content.toLowerCase().includes("autonomous"),
-      `${promptName}.md must reference auto-mode or autonomous execution`,
-    );
-
-    // The guard must indicate no human is available
-    assert.ok(
-      content.includes("no human") || content.includes("no user"),
-      `${promptName}.md must state that no human/user is available to answer`,
-    );
-  });
-}
-
-test("auto-mode prompts contain autonomous guard before final tool call reminder", () => {
-  for (const promptName of AUTO_MODE_PROMPTS) {
-    const content = loadPromptRaw(promptName);
-
-    // The guard should appear before the final "MUST call" line
-    const guardIndex = content.indexOf("ask_user_questions");
-    const mustCallIndex = content.lastIndexOf("MUST call");
-
-    assert.ok(
-      guardIndex !== -1 && mustCallIndex !== -1 && guardIndex < mustCallIndex,
-      `${promptName}.md: autonomous guard (ask_user_questions prohibition) must appear before the final MUST call reminder`,
-    );
-  }
-});

package/src/resources/extensions/gsd/tests/cli-provider-rate-limit.test.ts

@@ -1,47 +0,0 @@
-/**
- * cli-provider-rate-limit.test.ts — Verify rate-limit backoff capping
- * for CLI-style providers (openai-codex, google-gemini-cli). (#2922)
- *
- * These providers use per-user quotas with shorter windows, so the
- * default 60s backoff should be capped at 30s to avoid leaving users
- * stuck in an apparent permanent "rate limit" state.
- */
-
-import test from "node:test";
-import assert from "node:assert/strict";
-import { readFileSync } from "node:fs";
-import { join, dirname } from "node:path";
-import { fileURLToPath } from "node:url";
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const RECOVERY_PATH = join(__dirname, "..", "bootstrap", "agent-end-recovery.ts");
-
-function getRecoverySource(): string {
-  return readFileSync(RECOVERY_PATH, "utf-8");
-}
-
-test("agent-end-recovery references openai-codex for rate-limit handling (#2922)", () => {
-  const src = getRecoverySource();
-  assert.ok(
-    src.includes("openai-codex"),
-    'agent-end-recovery.ts must reference "openai-codex" for CLI provider rate-limit handling (#2922)',
-  );
-});
-
-test("agent-end-recovery references google-gemini-cli for rate-limit handling (#2922)", () => {
-  const src = getRecoverySource();
-  assert.ok(
-    src.includes("google-gemini-cli"),
-    'agent-end-recovery.ts must reference "google-gemini-cli" for CLI provider rate-limit handling (#2922)',
-  );
-});
-
-test("agent-end-recovery caps rate-limit backoff for CLI providers (#2922)", () => {
-  const src = getRecoverySource();
-  // Must have a Math.min capping pattern for CLI provider rate-limit backoff
-  const cappingRe = /Math\.min\s*\(/;
-  assert.ok(
-    cappingRe.test(src),
-    'agent-end-recovery.ts must cap rate-limit backoff with Math.min for CLI providers (#2922)',
-  );
-});