@code-yeongyu/senpi-codemode 2026.9.3 → 2026.9.4

package/CHANGELOG.md

@@ -12,6 +12,44 @@
 
 ### Removed
 
+## [2026.9.4] - 2026-09-04
+
+### Breaking Changes
+
+### Added
+
+### Changed
+
+### Fixed
+
+### Removed
+
+## [2026.9.3-3] - 2026-09-03
+
+### Breaking Changes
+
+### Added
+
+### Changed
+
+### Fixed
+
+### Removed
+
+## [2026.9.3-2] - 2026-09-03
+
+### Breaking Changes
+
+### Added
+
+### Changed
+
+### Fixed
+
+- JavaScript eval cells no longer leak child-process output onto the host terminal under Bun: `Bun.$` commands awaited without `.quiet()`/`.text()` and `Bun.spawn` children with the default stderr now route their output into the cell's stdout/stderr streams instead of the inherited fd 1/2 that the interactive TUI owns.
+
+### Removed
+
 ## [2026.9.3] - 2026-09-03
 
 ### Breaking Changes

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/senpi-codemode",
-	"version": "2026.9.3",
+	"version": "2026.9.4",
 	"description": "Source-only senpi extension package for codemode evaluation tools",
 	"type": "module",
 	"main": "./src/index.ts",
@@ -30,14 +30,14 @@
 	},
 	"dependencies": {
 		"@babel/parser": "8.0.4",
-		"@earendil-works/pi-ai": "npm:@code-yeongyu/senpi-ai@2026.9.3",
+		"@earendil-works/pi-ai": "npm:@code-yeongyu/senpi-ai@2026.9.4",
 		"typebox": "1.3.18"
 	},
 	"peerDependencies": {
-		"@code-yeongyu/senpi": "2026.9.3"
+		"@code-yeongyu/senpi": "2026.9.4"
 	},
 	"devDependencies": {
-		"@code-yeongyu/senpi": "2026.9.3"
+		"@code-yeongyu/senpi": "2026.9.4"
 	},
 	"keywords": [
 		"senpi",

package/src/index.ts

@@ -64,6 +64,15 @@ export interface SenpiCodemodeOptions {
 	readonly now?: () => number;
 }
 
+/** Whether the session registry holds `monitor`; false when the runtime cannot be read yet. */
+function monitorIsRegistered(pi: CodemodeExtensionAPI): boolean {
+	try {
+		return pi.getAllTools().some((tool) => tool.name === "monitor");
+	} catch {
+		return false;
+	}
+}
+
 export default function senpiCodemode(pi: CodemodeExtensionAPI, options: SenpiCodemodeOptions = {}): void {
 	const manager = new SessionManagerProxy();
 	const complete = options.complete ?? ((request, ctx) => createCompletionHandler()(ctx)(request));
@@ -108,6 +117,11 @@ export default function senpiCodemode(pi: CodemodeExtensionAPI, options: SenpiCo
 			pi.rpc?.emit(EVAL_EXECUTION_EVENT, toEvalExecutionRpcPayload(payload));
 			pi.events?.emit(EVAL_EXECUTION_EVENT, payload);
 		};
+		// `listTools` below survives because it is lazy; this read is eager, and the loader's
+		// action methods throw while extensions are still loading (the bundled codemode path
+		// reaches this before the runtime is bound). An unreadable registry means "do not teach
+		// a tool we cannot confirm"; session_start / model_select re-register once it is live.
+		const monitor = monitorIsRegistered(pi);
 		pi.registerTool(
 			createEvalTool({
 				enabledLanguages: runtime.enabledLanguages,
@@ -122,6 +136,7 @@ export default function senpiCodemode(pi: CodemodeExtensionAPI, options: SenpiCo
 				executionTracker: manager,
 				onCellSettled,
 				renderers,
+				monitor,
 				spawns: runtime.spawns,
 				spawnDefaultAgent: runtime.settings.taskTools.task,
 				hostLine: hostLine(),
@@ -159,6 +174,8 @@ export default function senpiCodemode(pi: CodemodeExtensionAPI, options: SenpiCo
 			}),
 			executionTracker: manager,
 			renderers,
+			// The baseline tool is registered before extensions such as monitor load.
+			monitor: false,
 			hostLine: hostLine(),
 			runtimes: { js: jsRuntimeInfo() },
 			...(bunSkillPath === undefined ? {} : { bunSkillPath }),

package/src/kernels/js/worker-runtime.js

@@ -3,6 +3,7 @@ import { mkdir, readFile, stat, writeFile } from "node:fs/promises";
 import { dirname, isAbsolute, join, normalize, resolve, sep } from "node:path";
 import { inspect } from "node:util";
 import { awaitMaybePromise, indirectEval, wrapUserCode } from "./worker-indirect-eval.js";
+import { installShellCapture } from "./worker-shell-capture.js";
 
 const PREPARED_CELL_PREFIX = "/*senpi:prepared-cell*/";
 const INTERNAL_URL = /^([a-z][a-z0-9+.-]*):\/\/(.*)$/iu;
@@ -84,11 +85,16 @@ export class JsWorkerRuntime {
 		process.stderr.write = routeWrite(process.stderr, originalStderrWrite, "stderr");
 		console.log = (...values) => this.#emitText("stdout", `${values.map(formatValue).join(" ")}\n`);
 		console.error = (...values) => this.#emitText("stderr", `${values.map(formatValue).join(" ")}\n`);
+		const restoreShellCapture = installShellCapture({
+			isActive: () => this.#hooks !== null,
+			emitText: (stream, data) => this.#emitText(stream, data),
+		});
 		globalThis.__senpi_restore_console__ = () => {
 			console.log = originalLog;
 			console.error = originalError;
 			process.stdout.write = originalStdoutWrite;
 			process.stderr.write = originalStderrWrite;
+			restoreShellCapture();
 		};
 	}
 

package/src/kernels/js/worker-shell-capture.d.ts

@@ -0,0 +1,10 @@
+export type ShellCaptureStream = "stdout" | "stderr";
+
+export type ShellCaptureRestore = () => void;
+
+export interface ShellCaptureOptions {
+	readonly isActive: () => boolean;
+	readonly emitText: (stream: ShellCaptureStream, data: string) => void;
+}
+
+export function installShellCapture(options: ShellCaptureOptions): ShellCaptureRestore;

package/src/kernels/js/worker-shell-capture.js

@@ -0,0 +1,126 @@
+const SHELL_CONFIG_METHODS = ["env", "cwd", "nothrow", "throws"];
+const SHELL_READ_METHODS = ["text", "json", "lines", "arrayBuffer", "bytes", "blob"];
+
+export function installShellCapture(options) {
+	const bun = globalThis.Bun;
+	if (!isBunRuntime(bun)) return () => {};
+	const originalShell = bun.$;
+	const originalSpawn = bun.spawn;
+	bun.$ = capturedShell(originalShell, options);
+	bun.spawn = capturedSpawn(originalSpawn, options);
+	return () => {
+		bun.$ = originalShell;
+		bun.spawn = originalSpawn;
+	};
+}
+
+function isBunRuntime(bun) {
+	return bun !== null && typeof bun === "object" && typeof bun.$ === "function" && typeof bun.spawn === "function";
+}
+
+function capturedShell(originalShell, options) {
+	const shell = (strings, ...expressions) => {
+		const promise = originalShell(strings, ...expressions);
+		return options.isActive() ? captureShellPromise(promise, options.emitText) : promise;
+	};
+	for (const key of Object.keys(originalShell)) shell[key] = originalShell[key];
+	for (const method of SHELL_CONFIG_METHODS) {
+		shell[method] = (...args) => {
+			originalShell[method](...args);
+			return shell;
+		};
+	}
+	return shell;
+}
+
+function captureShellPromise(promise, emitText) {
+	const prototype = Object.getPrototypeOf(promise);
+	let echo = true;
+	const echoOnce = (output) => {
+		if (!echo) return;
+		echo = false;
+		emitShellOutput(output, emitText);
+	};
+	prototype.quiet.call(promise);
+	promise.quiet = function quiet() {
+		echo = false;
+		return prototype.quiet.call(this);
+	};
+	for (const method of SHELL_READ_METHODS) {
+		if (typeof prototype[method] !== "function") continue;
+		promise[method] = function read(...args) {
+			echo = false;
+			return prototype[method].apply(this, args);
+		};
+	}
+	promise.then = function then(onFulfilled, onRejected) {
+		return prototype.then.call(
+			this,
+			(output) => {
+				echoOnce(output);
+				return onFulfilled ? onFulfilled(output) : output;
+			},
+			(error) => {
+				echoOnce(error);
+				if (onRejected) return onRejected(error);
+				throw error;
+			},
+		);
+	};
+	return promise;
+}
+
+function emitShellOutput(output, emitText) {
+	if (output === null || typeof output !== "object") return;
+	const stdout = outputText(output.stdout);
+	if (stdout) emitText("stdout", stdout);
+	const stderr = outputText(output.stderr);
+	if (stderr) emitText("stderr", stderr);
+}
+
+function outputText(value) {
+	if (value instanceof Uint8Array) return new TextDecoder().decode(value);
+	return typeof value === "string" ? value : "";
+}
+
+function capturedSpawn(originalSpawn, options) {
+	return (...args) => {
+		if (!options.isActive()) return originalSpawn(...args);
+		const [first, second] = args;
+		if (Array.isArray(first)) {
+			const spawnOptions = second === undefined ? {} : second;
+			if (!needsStderrCapture(spawnOptions)) return originalSpawn(...args);
+			return drainStderr(originalSpawn(first, { ...spawnOptions, stderr: "pipe" }), options.emitText);
+		}
+		if (!needsStderrCapture(first)) return originalSpawn(...args);
+		return drainStderr(originalSpawn({ ...first, stderr: "pipe" }), options.emitText);
+	};
+}
+
+function needsStderrCapture(spawnOptions) {
+	return (
+		spawnOptions !== null &&
+		typeof spawnOptions === "object" &&
+		spawnOptions.stdio === undefined &&
+		spawnOptions.stderr === undefined
+	);
+}
+
+function drainStderr(child, emitText) {
+	const stream = child?.stderr;
+	if (!(stream instanceof ReadableStream)) return child;
+	void readStream(stream, emitText).catch((error) => {
+		emitText("stderr", `[spawn stderr capture failed: ${String(error)}]\n`);
+	});
+	return child;
+}
+
+async function readStream(stream, emitText) {
+	const decoder = new TextDecoder();
+	for await (const chunk of stream) {
+		const text = decoder.decode(chunk, { stream: true });
+		if (text) emitText("stderr", text);
+	}
+	const tail = decoder.decode();
+	if (tail) emitText("stderr", tail);
+}

package/src/prompt/eval-prompt.ts

@@ -15,6 +15,8 @@ export interface EvalPromptParts {
 
 export interface EvalPromptOptions {
 	readonly spawns: boolean;
+	/** Whether the session registry exposes the monitor tool through eval. */
+	readonly monitor?: boolean;
 	readonly spawnDefaultAgent?: string;
 	/** Active model id; selects the emphasis dialect of the batching guidance. */
 	readonly modelId?: string;
@@ -105,21 +107,26 @@ Work incrementally: imports in one call, define in the next, test, then use —
 \`eval\` is your default execution surface: if a step needs more than one tool call, write ONE cell that performs the whole step — never issue the calls one at a time.
 - Enumerate every lookup the step needs, then run all independent ones simultaneously with \`parallel(thunks)\` inside the cell; keep calls sequential only when one result feeds the next.
 - Write real code around the calls: loop or comprehend over file sets with \`read()\`/stdlib, branch per case, and wrap risky calls in try/except so one failure degrades only its item — recover or retry inside the cell, keep the batch alive.
-- Post-process \`tool.<name>()\` results programmatically and return distilled facts, not raw dumps.
+- Post-process \`tool.<name>()\` results programmatically — filter, join, aggregate — and return distilled facts, not raw dumps.
+{{#if monitor}}- Start long-running work (build, test run, deploy, or watch) through \`tool.monitor({ command, filter })\`, putting the decisive-line filter inside the same cell, then keep working until its event wakes the turn; sleeping, timed retries, and repeated status reads are not waiting.{{/if}}
 </eval_first_batching>{{/if}}{{#if styleGpt}}<gpt_eval_dialect>
 GPT eval: compose multi-tool work inside one cell with \`tool.<name>(args)\` and \`parallel(thunks)\`; do not split a planned step into serial tool calls.
 - Long pure-compute cells detach on timeout and notify on completion. Do not poll or re-run them; use \`eval({ action: "peek"|"stop", cell_id })\` only to inspect or stop a detached cell.
-- Reduce tool results in the cell and return only decision-relevant facts.
+- Filter, join, and aggregate tool results in the cell; return only decision-relevant facts.
+{{#if monitor}}- For long-running build, test run, deploy, or watch work, start \`tool.monitor({ command, filter })\` with the decisive-line filter in the same cell; keep working while its event wakes the turn; sleeping, timed retries, and repeated status reads are not waiting.{{/if}}
 </gpt_eval_dialect>{{/if}}{{#if styleCodex}}Route multi-call steps through eval: one cell per step, independent lookups dispatched together via \`parallel(thunks)\`; keep work sequential only when one result determines the next action.
-- Loop or comprehend over file sets with \`read()\`/stdlib instead of reading files one call at a time; post-process \`tool.<name>()\` results programmatically.
+- Loop or comprehend over file sets with \`read()\`/stdlib instead of reading files one call at a time; post-process \`tool.<name>()\` results programmatically — filter, join, aggregate.
 - Wrap failable calls in try/except inside the cell; a failed item degrades only itself. After two distinct failed strategies for the same fact, fall back to direct tool calls.
-- Reduce large results in-kernel to the facts the task needs before returning.{{/if}}{{#if styleKimi}}**EVAL IS YOUR SUPERPOWER — MAKE IT YOUR DEFAULT WAY TO ACT.** Before any step, think: "how do I execute this WHOLE step in ONE parallelized cell?" — then write that ONE cell.
+- Reduce large results in-kernel to the facts the task needs before returning.
+{{#if monitor}}- Long-running build/test/deploy/watch work: start \`tool.monitor({ command, filter })\` with the decisive-line filter inside the same cell, then continue working; its event wakes the turn — sleeping, timed retries, and repeated status reads are not waiting.{{/if}}{{/if}}{{#if styleKimi}}**EVAL IS YOUR SUPERPOWER — MAKE IT YOUR DEFAULT WAY TO ACT.** Before any step, think: "how do I execute this WHOLE step in ONE parallelized cell?" — then write that ONE cell.
 - **BATCH EVERYTHING AT ONCE:** enumerate EVERY independent lookup the step needs and dispatch them ALL simultaneously with \`parallel(thunks)\` in that cell; keep calls sequential only when one result feeds the next.
 - **WRITE REAL CODE, NOT CALL CHAINS:** loop or comprehend over file sets with \`read()\`/stdlib, post-process \`tool.<name>()\` results programmatically, and put try/except around each risky call so the rest of the batch completes.
-- **DISTILL IN-KERNEL:** filter and aggregate results in code, then return ONLY the distilled facts.{{/if}}{{#if styleDefault}}**EVAL IS YOUR PRIMARY EXECUTION SURFACE.** Any step that needs MORE THAN ONE tool call MUST be written as ONE cell — NEVER as a chain of single tool calls.
+- **DISTILL IN-KERNEL:** filter, join, and aggregate \`tool.<name>()\` results in code, then return ONLY the distilled facts.
+{{#if monitor}}- **DO start long-running build, test run, deploy, or watch work with \`tool.monitor({ command, filter })\`, put the decisive-line filter INSIDE THE SAME CELL, and KEEP WORKING until its event wakes the turn; sleeping, timed retries, and repeated status reads are not waiting.**{{/if}}{{/if}}{{#if styleDefault}}**EVAL IS YOUR PRIMARY EXECUTION SURFACE.** Any step that needs MORE THAN ONE tool call MUST be written as ONE cell — NEVER as a chain of single tool calls.
 - **PLAN THE WHOLE STEP, THEN BATCH IT.** Enumerate every read/search/lookup the step needs and dispatch ALL independent ones through \`parallel(thunks)\` in one cell.
 - **WRITE REAL CODE, NOT CALL LISTS.** Loop or comprehend over file sets with \`read()\`/stdlib, branch \`if\`/\`else\` per case, post-process \`tool.<name>()\` results programmatically, and wrap EVERY risky call in try/except so ONE failure NEVER kills the batch.
-- **DISTILL IN-KERNEL.** Filter, diff, and aggregate in code before returning; return facts, NOT dumps.{{/if}}
+- **DISTILL IN-KERNEL.** Filter, join, diff, and aggregate in code before returning; return facts, NOT dumps.
+{{#if monitor}}- **LONG-RUNNING build, test run, deploy, or watch work MUST start with \`tool.monitor({ command, filter })\`, with the decisive-line filter INSIDE THE SAME CELL; KEEP WORKING until its event wakes the turn — SLEEPING, TIMED RETRIES, AND REPEATED STATUS READS ARE NOT WAITING.**{{/if}}{{/if}}
 {{#if hostLine}}
 Host: {{hostLine}} — cells execute here. Size \`parallel(thunks)\` pools to its cores; \`tool.<name>()\` shell commands must fit this platform, even when the code you are writing targets another machine.
 {{/if}}
@@ -211,6 +218,7 @@ export function buildEvalPrompt(
 		rb: enabled.rb,
 		jl: enabled.jl,
 		spawns: options.spawns,
+		monitor: options.monitor === true,
 		spawnDefaultAgent,
 		styleClaude: style === "claude",
 		styleCodex: style === "codex",

package/src/tool/eval-tool-options.ts

@@ -36,6 +36,8 @@ export interface CreateEvalToolOptions {
 	readonly proxyExecutor?: (params: EvalToolInput, signal?: AbortSignal) => Promise<AgentToolResult<EvalToolDetails>>;
 	readonly renderers?: Pick<ToolDefinition<EvalInputSchema, EvalToolDetails>, "renderCall" | "renderResult">;
 	readonly spawns?: boolean;
+	/** Whether the session registry exposes the monitor tool through eval. */
+	readonly monitor?: boolean;
 	readonly spawnDefaultAgent?: string;
 	readonly modelId?: string;
 	readonly hostLine?: string;

package/src/tool/eval-tool.ts

@@ -28,6 +28,7 @@ export function createEvalTool(options: CreateEvalToolOptions): ToolDefinition<E
 	const parameters = createEvalInputSchema(options.enabledLanguages);
 	const prompt = buildEvalPrompt(options.enabledLanguages, {
 		spawns: options.spawns ?? false,
+		monitor: options.monitor,
 		...(options.spawnDefaultAgent === undefined ? {} : { spawnDefaultAgent: options.spawnDefaultAgent }),
 		...(options.modelId === undefined ? {} : { modelId: options.modelId }),
 		...(options.hostLine === undefined ? {} : { hostLine: options.hostLine }),