fix: outdated tests

packages/coding-agent/CHANGELOG.md

@@ -6,7 +6,7 @@
 - Removed the built-in `python` tool in favor of `eval`, so tool allowlists and tool-call handlers referencing `python` need to migrate
 - Removed the `python.toolMode` setting and replaced mode control with separate `eval.py` and `eval.js` toggles
 - Changed the tool runtime config surface by migrating `python` execution timeout/export behavior to `eval` and replacing `./ipy/*` internal exports with `./eval/*` paths
-- Changed the `eval` tool wire format to a single `input` string with `=== CELL ===` sections, fenced language selection, per-cell header timeouts, and `=== RESET ===` directives instead of top-level `cells`, `language`, `timeout`, and `reset` fields
+- Changed the `eval` tool wire format to a single `input` string composed of markdown fenced code blocks (with per-fence language, timeout, title, and reset metadata in the info string) instead of top-level `cells`, `language`, `timeout`, and `reset` fields
 
 ### Added
 

packages/coding-agent/test/agent-session-python-cleanup.test.ts

@@ -378,7 +378,7 @@ describe("AgentSession python cleanup", () => {
 		expect(EvalTool).toBeDefined();
 		let toolExecutionSettled = false;
 		const toolExecution = EvalTool!
-			.execute("call-id", { input: "=== CELL ===\n```py\nprint('tool')\n```" }, undefined, undefined, undefined)
+			.execute("call-id", { input: "```py\nprint('tool')\n```" }, undefined, undefined, undefined)
 			.finally(() => {
 				toolExecutionSettled = true;
 			});
@@ -437,7 +437,7 @@ describe("AgentSession python cleanup", () => {
 		expect(EvalTool).toBeDefined();
 		const toolExecution = EvalTool!.execute(
 			"call-id",
-			{ input: "=== CELL ===\n```py\nprint('tool after warmup')\n```" },
+			{ input: "```py\nprint('tool after warmup')\n```" },
 			undefined,
 			undefined,
 			undefined,
@@ -493,7 +493,7 @@ describe("AgentSession python cleanup", () => {
 		expect(EvalTool).toBeDefined();
 		let toolExecutionSettled = false;
 		const toolExecution = EvalTool!
-			.execute("call-id", { input: "=== CELL ===\n```py\nprint('tool')\n```" }, undefined, undefined, undefined)
+			.execute("call-id", { input: "```py\nprint('tool')\n```" }, undefined, undefined, undefined)
 			.finally(() => {
 				toolExecutionSettled = true;
 			});
@@ -507,14 +507,14 @@ describe("AgentSession python cleanup", () => {
 
 		expect(disposed).toBe(false);
 		expect(toolExecutionSettled).toBe(false);
-		expect(warmupSpy).toHaveBeenCalledTimes(1);
+		expect(warmupSpy).toHaveBeenCalledTimes(2);
 		expect(executeSpy).toHaveBeenCalledTimes(1);
 
 		const [toolResult] = await Promise.all([toolExecution, disposeSession]);
 
 		expect(disposed).toBe(true);
 		expect(toolExecutionSettled).toBe(true);
-		expect(warmupSpy).toHaveBeenCalledTimes(1);
+		expect(warmupSpy).toHaveBeenCalledTimes(2);
 		expect(executeSpy).toHaveBeenCalledTimes(1);
 		expect(toolResult.details?.isError).toBe(true);
 		expect(toolResult.content).toContainEqual(
@@ -726,7 +726,7 @@ describe("AgentSession python cleanup", () => {
 		await expect(
 			EvalTool!.execute(
 				"call-id",
-				{ input: "=== CELL ===\n```py\nprint('late')\n```" },
+				{ input: "```py\nprint('late')\n```" },
 				undefined,
 				undefined,
 				undefined,
@@ -767,7 +767,7 @@ describe("AgentSession python cleanup", () => {
 		expect(EvalTool).toBeDefined();
 		const execution = EvalTool!.execute(
 			"call-id",
-			{ input: "=== CELL ===\n```py\nprint('late after artifact')\n```" },
+			{ input: "```py\nprint('late after artifact')\n```" },
 			undefined,
 			undefined,
 			undefined,

packages/coding-agent/test/core/python-prelude.test.ts

@@ -40,7 +40,7 @@ const shouldRun = Boolean(pythonPath) && hasKernelDeps;
 
 describe.skipIf(!shouldRun)("PYTHON_PRELUDE integration", () => {
 	it("exposes prelude helpers via eval python backend", async () => {
-		const helpers = ["env", "read", "write", "append", "rm", "mv", "cp", "find", "grep"];
+		const helpers = ["env", "read", "write", "append", "find", "glob", "grep", "rgrep", "sed", "tree", "stat", "diff", "run", "output"];
 
 		const session = {
 			cwd: getProjectDir(),
@@ -64,8 +64,7 @@ describe.skipIf(!shouldRun)("PYTHON_PRELUDE integration", () => {
 	`;
 
 		const result = await tool.execute("tool-call-1", {
-			input: `=== CELL prelude helpers ===
-\`\`\`py
+			input: `\`\`\`py prelude helpers
 ${code}
 \`\`\`
 `,

packages/coding-agent/test/tools/eval-fallback.test.ts

@@ -40,7 +40,7 @@ describe("EvalTool language resolution", () => {
 
 		const tool = new EvalTool(makeSession());
 		await tool.execute("call-1", {
-			input: "=== CELL one ===\n```js\nconst x = 1;\n```\n",
+			input: "```js one\nconst x = 1;\n```\n",
 		});
 
 		expect(jsExecuteSpy).toHaveBeenCalledTimes(1);
@@ -54,7 +54,7 @@ describe("EvalTool language resolution", () => {
 
 		const tool = new EvalTool(makeSession());
 		await tool.execute("call-2", {
-			input: "=== CELL one ===\n```python\nprint('hi')\n```\n",
+			input: "```python one\nprint('hi')\n```\n",
 		});
 
 		expect(pythonExecuteSpy).toHaveBeenCalledTimes(1);
@@ -68,7 +68,7 @@ describe("EvalTool language resolution", () => {
 
 		const tool = new EvalTool(makeSession());
 		await tool.execute("call-3", {
-			input: "=== CELL one ===\ndef greet():\n    print('hi')\ngreet()\n",
+			input: "def greet():\n    print('hi')\ngreet()\n",
 		});
 
 		expect(pythonExecuteSpy).toHaveBeenCalledTimes(1);