killeros 1.4.2 → 1.4.5

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 All notable changes to KillerOS are documented here.
 
+## [1.4.5] - 2026-08-01
+
+### Fixed
+
+- Removed the child-budget extension, its read-tool budget, and the default 250,000-token/$5 quota.
+- Removed default child wall-time, JSONL-line, trace, stderr, returned-output, and model-output-length stops; role `timeoutMs` and other child guards are now opt-in.
+- Removed forced early-report prompt text so roles can finish their assigned work naturally.
+- Treat model stop reason `length` as a completed child process instead of inventing a KillerOS `limited` result.
+- Documented the child lifecycle contract: children complete naturally; explicit user interruptions, configured guards, and real child-process failures remain visible.
+
+## [1.4.3] - 2026-08-01
+
+### Fixed
+
+- Added child-runtime tool budgets for read-only roles, with a soft finalization nudge and hard blocking for read and web tools after 32 calls.
+- Added bounded child report instructions and kept read-tool budgets cumulative across steering restarts.
+- Lowered the default child quota to 250,000 tokens and $5, and exposed child tool-call counts in results.
+
 ## [1.4.2] - 2026-08-01
 
 ### Added

package/README.md

@@ -33,7 +33,7 @@ pi install git:github.com/KyrosHendrix/pi-KillerOS
 Pin an install to a release:
 
 ```bash
-pi install git:github.com/KyrosHendrix/pi-KillerOS@v1.4.1
+  pi install git:github.com/KyrosHendrix/pi-KillerOS@v1.4.5
 ```
 
 Add `-l` to either command for a project-only install. Restart Pi after installing.
@@ -47,7 +47,7 @@ Add `-l` to either command for a project-only install. Restart Pi after installi
 - Responsive footer with polished model/provider identity, plain-language context, and active goal state remaining; reasoning, Git branch, elapsed time, cost, and path cut down by available width
 - `/variants` selector and direct reasoning-level arguments
 - Codex-style `/goal` for durable long-running objectives with pause, resume, edit, clear, automatic continuation, and explicit completion
-- Pi-native `subagent` tool with named, inspectable child threads, Markdown roles, explicit read/write boundaries, parent controls, bounded resources, and cancellation propagation
+- Pi-native `subagent` tool with named, inspectable child threads, Markdown roles, explicit read/write boundaries, parent controls, natural completion, and cancellation propagation
 - Claude Code-style `/init` that scans the repository and generates a concise root `AGENTS.md` without setup questions
 - `question` tool with filtering, proposal previews, keyboard selection, custom answers, history, cancellation, and resize-safe rendering
 - Mid-prompt slash completion with current Pi `0.82.1` commands, extensions, prompts, and skills
@@ -89,7 +89,7 @@ KillerOS ships `planner`, `reviewer`, `scout`, and `security` as read-only roles
 | `scout` | read | Map unfamiliar code and return an evidence trail |
 | `security` | read | Audit trust boundaries and report concrete security findings |
 | `tester` | write | Add focused coverage and run deterministic verification |
-| `worker` | write | Execute a bounded repository change |
+| `worker` | write | Execute the assigned repository change |
 
 1. Bundled: `<killeros>/agents/*.md`
 2. Personal: `~/.pi/agent/agents/*.md`
@@ -103,7 +103,7 @@ The tool supports a single `agent` + `task`, parallel `tasks`, or a sequential `
 {"agent":"reviewer","task":"Review the change","model":"provider/model","thinking":"high"}
 ```
 
-Use the separate `model` and `thinking` fields for new configuration. The older `provider/model:thinking` model form remains accepted. Children run as ephemeral `pi --mode json -p --no-session` processes with explicit local tools plus `web_search`, `source_check`, `fetch_content`, and `get_search_content`. Each child explicitly loads `npm:pi-web-access`, discovers available skills, and keeps arbitrary extensions and prompt templates disabled; project-local skills load only when the parent project is trusted. Every bundled role is instructed to load the most relevant `SKILL.md` before work and to use web research when external evidence is needed. KillerOS allows at most eight tasks, four parallel readers, ten minutes, a 32 MiB JSONL line, 2 MiB retained trace, 64 KiB stderr, 50 KiB returned output, one million tokens, and $10 per child. Esc cancellation terminates active children and escalates after five seconds.
+Use the separate `model` and `thinking` fields for new configuration. The older `provider/model:thinking` model form remains accepted. Children run as ephemeral `pi --mode json -p --no-session` processes with explicit local tools plus `web_search`, `source_check`, `fetch_content`, and `get_search_content`. Each child explicitly loads `npm:pi-web-access`, discovers available skills, and keeps arbitrary extensions and prompt templates disabled; project-local skills load only when the parent project is trusted. Every bundled role is instructed to load the most relevant `SKILL.md` and report useful evidence. Children have no default token, dollar, turn, tool-call, research, wall-time, JSONL-line, trace, stderr, or returned-output quota. The parent still limits each request to eight tasks and four parallel readers and bounds role files, task input, and combined parent output. An embedding caller may opt into named child resource guards. Esc cancellation terminates active children and escalates after five seconds.
 
 ### Thread lifecycle
 
@@ -113,7 +113,7 @@ Threads move through `queued`, `active`, `done`, `failed`, `stopped`, and `close
 
 The parent can inspect a thread’s prompt, role, model, tools, trace, usage, and handoff; steer an active thread with one bounded follow-up; interrupt one child or all active children; collect a concise handoff into parent context; and close a finished or stopped thread. An interrupt preserves the partial trace, states the reason, and reports the handoff as partial rather than successful.
 
-A child completes naturally when it returns a final answer. Routine turn caps do not end useful work. Named resource guards still stop unsafe growth: wall time, output bytes, retained trace, stderr, quota, task count, and concurrency. A guard reports its cause and returns any partial work clearly. Esc cancellation terminates active children and escalates after five seconds.
+A child completes naturally when it returns a final answer. The default path has no per-child execution quota. Explicit embedding options can add wall-time, output, trace, stderr, JSONL, token, or cost guards; those guards report their cause and return partial work clearly. The parent still bounds task count, reader concurrency, role files, task input, and combined parent output. Explicit user interruptions and real child-process failures remain visible. Esc cancellation terminates active children and escalates after five seconds.
 
 The replacement lifecycle has nine phases:
 
@@ -123,7 +123,7 @@ The replacement lifecycle has nine phases:
 4. **Steer:** append a bounded parent follow-up to an active thread.
 5. **Interrupt:** stop one or all active children while preserving partial work.
 6. **Collect:** return a concise handoff while retaining the expanded trace.
-7. **Bound:** apply named resource guards instead of a routine turn stop.
+7. **Guard:** honor only explicitly configured child resource guards; do not impose a routine turn stop.
 8. **Close:** remove a finished or stopped thread from the workspace without deleting its result record.
 9. **Prove:** test identity, visibility, controls, natural completion, guards, partial handoffs, and closure.
 
@@ -163,7 +163,7 @@ The package manifest lists Pi’s built-in modules as peer dependencies, so npm
 
 The [`pi-package`](https://github.com/earendil-works/pi/blob/main/packages/coding-agent/docs/packages.md) keyword makes a published npm release visible in Pi’s package catalog.
 
-For the current unreleased `1.4.2`, publish after the validation checks pass:
+For release `1.4.5`, publish after the validation checks pass:
 
 ```bash
 npm login

package/agents/debugger.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, edit, write, bash, web_search, source_check, fetch_
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role

package/agents/documenter.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, edit, write, bash, web_search, source_check, fetch_
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role

package/agents/planner.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, web_search, source_check, fetch_content, get_search
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role

package/agents/reviewer.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, web_search, source_check, fetch_content, get_search
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role
@@ -39,7 +38,7 @@ If no concrete issue is found, report the reviewed scope, protections checked, a
 
 ## Boundaries
 
-Do not edit files or fix findings yourself. Do not report stylistic preferences as defects. Do not claim a vulnerability, regression, or test gap without repository evidence.
+Do not edit files or fix findings yourself. Do not report stylistic preferences as defects. Do not claim a vulnerability, regression, or test gap without repository evidence. Finish the assigned review when the evidence resolves its scope, report the findings or clean result, and do not chase unrelated work.
 
 ## Skills and web research
 

package/agents/scout.md

@@ -6,12 +6,11 @@ tools: read, grep, find, ls, web_search, source_check, fetch_content, get_search
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role
 
-You are the `scout` role, a fast and bounded repository investigator. Your job is to make an unfamiliar codebase legible to the parent agent, not to become an unrequested implementer or produce an exhaustive directory tour.
+You are the `scout` role, a focused repository investigator. Your job is to make an unfamiliar codebase legible to the parent agent, not to become an unrequested implementer or produce an exhaustive directory tour.
 
 ## Mission
 
@@ -23,7 +22,7 @@ Begin with the user’s actual question and define what evidence would answer it
 2. **Trace.** Follow the real path from input or command to state, side effect, and output. Follow callers and callees only when the current evidence requires it.
 3. **Compare.** Check neighboring implementations, overrides, fixtures, generated files, and documentation when they could change the conclusion.
 4. **Verify.** Record exact paths, symbols, commands, and conventions. Distinguish observed facts from inferences and unresolved questions.
-5. **Stop.** Once the parent’s question is closed by evidence, stop. Do not pad the report with unrelated files, generic architecture advice, or speculative fixes.
+5. **Finish.** Once evidence closes the parent’s question, report the findings and stop. Do not chase unrelated files, generic architecture advice, or speculative fixes.
 
 ## Report
 

package/agents/security.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, web_search, source_check, fetch_content, get_search
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role
@@ -35,7 +34,7 @@ Relevant lenses may include:
 
 ## Finding standard
 
-Every confirmed finding must name the severity, precondition or trigger, affected path or symbol, evidence, security impact, and smallest safe correction. Separate questions and blind spots from findings. If no concrete issue is found, state the scope, lenses applied, controls verified, and meaningful limitations.
+Every confirmed finding must name the severity, precondition or trigger, affected path or symbol, evidence, security impact, and smallest safe correction. Separate questions and blind spots from findings. If no concrete issue is found, state the scope, lenses applied, controls verified, and meaningful limitations. Finish the assigned review when the evidence resolves its scope, report the findings or clean result, and do not chase unrelated work.
 
 ## Skills and web research
 

package/agents/tester.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, edit, write, bash, web_search, source_check, fetch_
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role

package/agents/worker.md

@@ -6,7 +6,6 @@ tools: read, grep, find, ls, edit, write, bash, web_search, source_check, fetch_
 # Replace inherit with provider/model to pin this role; set thinking separately when needed.
 model: inherit
 thinking: inherit
-timeoutMs: 300000
 ---
 
 # Role

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "killeros",
-  "version": "1.4.2",
+  "version": "1.4.5",
   "description": "A production-hardened TUI and workflow extension for the Pi coding agent.",
   "type": "module",
   "keywords": [

package/subagent-process.ts

@@ -3,13 +3,6 @@ import { statSync } from "node:fs";
 import path from "node:path";
 
 export const SUBAGENT_PROCESS_LIMITS = {
-  wallTimeMs: 600_000,
-  jsonlLineBytes: 32 * 1024 * 1024,
-  traceBytes: 2 * 1024 * 1024,
-  stderrBytes: 64 * 1024,
-  outputBytes: 50 * 1024,
-  quotaTokens: 1_000_000,
-  quotaUsd: 10,
   killGraceMs: 5_000,
 } as const;
 
@@ -43,6 +36,7 @@ export interface SubagentProcessResult {
   output: string;
   outputBytes: number;
   outputTruncatedBytes: number;
+  toolCallCount: number;
   usage: SubagentProcessUsage;
   model?: string;
   stopReason?: string;
@@ -67,19 +61,20 @@ export interface SubagentProcessOptions {
   cwd: string;
   signal?: AbortSignal;
   limits?: Partial<SubagentProcessLimits>;
+  environment?: NodeJS.ProcessEnv;
   onUpdate?: (result: Readonly<SubagentProcessResult>) => void;
   /** Test or embed hook. It receives the exact Pi arguments supplied above. */
-  spawnProcess?: (args: string[], cwd: string) => SubagentProcessChild;
+  spawnProcess?: (args: string[], cwd: string, environment?: NodeJS.ProcessEnv) => SubagentProcessChild;
 }
 
 export interface SubagentProcessLimits {
-  wallTimeMs: number;
-  jsonlLineBytes: number;
-  traceBytes: number;
-  stderrBytes: number;
-  outputBytes: number;
-  quotaTokens: number;
-  quotaUsd: number;
+  wallTimeMs?: number;
+  jsonlLineBytes?: number;
+  traceBytes?: number;
+  stderrBytes?: number;
+  outputBytes?: number;
+  quotaTokens?: number;
+  quotaUsd?: number;
   killGraceMs: number;
 }
 
@@ -161,6 +156,11 @@ function textContent(message: any): string {
     .join("\n");
 }
 
+function toolCallCount(message: any): number {
+  if (!Array.isArray(message?.content)) return 0;
+  return message.content.filter((part: any) => part?.type === "toolCall").length;
+}
+
 function traceMessage(message: any): string[] {
   if (!Array.isArray(message?.content)) return [];
   const entries: string[] = [];
@@ -171,11 +171,11 @@ function traceMessage(message: any): string[] {
   return entries;
 }
 
-function appendTrace(result: SubagentProcessResult, entries: string[], maxBytes: number): boolean {
+function appendTrace(result: SubagentProcessResult, entries: string[], maxBytes: number | undefined): boolean {
   let truncated = false;
   for (const entry of entries) {
     const entryBytes = Buffer.byteLength(entry, "utf8");
-    const retained = truncateUtf8(entry, Math.max(0, maxBytes - result.traceBytes));
+    const retained = truncateUtf8(entry, maxBytes === undefined ? entryBytes : Math.max(0, maxBytes - result.traceBytes));
     if (retained.text) result.trace.push(retained.text);
     result.traceBytes += Buffer.byteLength(retained.text, "utf8");
     result.traceTruncatedBytes += entryBytes - Buffer.byteLength(retained.text, "utf8");
@@ -192,11 +192,11 @@ function normalizeLimits(overrides: Partial<SubagentProcessLimits> | undefined):
   const limits = { ...SUBAGENT_PROCESS_LIMITS, ...overrides };
   for (const name of ["wallTimeMs", "jsonlLineBytes", "traceBytes", "stderrBytes", "outputBytes", "killGraceMs"] as const) {
     const value = limits[name];
-    if (!Number.isSafeInteger(value) || value <= 0) throw new RangeError(`${name} must be a positive safe integer`);
+    if (value !== undefined && (!Number.isSafeInteger(value) || value <= 0)) throw new RangeError(`${name} must be a positive safe integer`);
   }
   for (const name of ["quotaTokens", "quotaUsd"] as const) {
     const value = limits[name];
-    if (!Number.isFinite(value) || value <= 0) throw new RangeError(`${name} must be a positive finite number`);
+    if (value !== undefined && (!Number.isFinite(value) || value <= 0)) throw new RangeError(`${name} must be a positive finite number`);
   }
   return limits;
 }
@@ -224,12 +224,12 @@ export function subagentProcessEnvironment(environment: NodeJS.ProcessEnv = proc
   return childEnvironment;
 }
 
-function defaultSpawnProcess(args: string[], cwd: string): SubagentProcessChild {
+function defaultSpawnProcess(args: string[], cwd: string, environment?: NodeJS.ProcessEnv): SubagentProcessChild {
   const invocation = getPiInvocation(args);
   return spawn(invocation.command, invocation.args, {
     cwd,
     detached: process.platform !== "win32",
-    env: subagentProcessEnvironment(),
+    env: subagentProcessEnvironment({ ...process.env, ...environment }),
     shell: false,
     stdio: ["ignore", "pipe", "pipe"],
     windowsHide: true,
@@ -263,7 +263,7 @@ function terminateProcess(child: SubagentProcessChild, force: boolean): void {
 
 /**
  * Run one isolated Pi JSON process. The caller owns all Pi arguments, including
- * model, tools, prompt, and extension flags. This runner never applies a turn cap.
+ * model, tools, prompt, and extension flags. Resource limits are opt-in.
  */
 export function runSubagentProcess(options: SubagentProcessOptions): SubagentProcessHandle {
   const args = [...options.args];
@@ -283,6 +283,7 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
     output: "",
     outputBytes: 0,
     outputTruncatedBytes: 0,
+    toolCallCount: 0,
     usage: emptyUsage(),
     exitCode: null,
     durationMs: 0,
@@ -323,9 +324,12 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
     if (requestedStatus) {
       state.status = requestedStatus;
       state.terminationReason = requestedReason;
-    } else if (code !== 0 || state.errorMessage || state.stopReason && state.stopReason !== "stop" && state.stopReason !== "toolUse") {
-      state.status = "failed";
+    } else if (code !== 0 || state.errorMessage || state.stopReason === "error" || state.stopReason === "aborted") {
+      state.status = state.stopReason === "aborted" ? "cancelled" : "failed";
       state.terminationReason ??= code === null ? "process_closed" : `exit_${code}`;
+    } else if (state.stopReason !== undefined && !["stop", "toolUse", "length"].includes(state.stopReason)) {
+      state.status = "failed";
+      state.terminationReason = state.stopReason;
     } else if (state.usage.turns === 0) {
       state.status = "failed";
       state.terminationReason = "missing_assistant_message";
@@ -373,9 +377,10 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
       }
       state.usage.turns += 1;
       addUsage(state.usage, { ...message.usage, turns: 0 });
-      if (state.usage.totalTokens > limits.quotaTokens) {
+      state.toolCallCount += toolCallCount(message);
+      if (limits.quotaTokens !== undefined && state.usage.totalTokens > limits.quotaTokens) {
         requestTermination("limited", "quota_tokens", `Child token usage exceeds ${limits.quotaTokens}`);
-      } else if (state.usage.cost.total > limits.quotaUsd) {
+      } else if (limits.quotaUsd !== undefined && state.usage.cost.total > limits.quotaUsd) {
         requestTermination("limited", "quota_cost", `Child cost exceeds $${limits.quotaUsd}`);
       }
       if (appendTrace(state, traceMessage(message), limits.traceBytes)) {
@@ -383,13 +388,13 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
       }
       const output = textContent(message);
       if (output) {
-        const capped = truncateUtf8(output, limits.outputBytes);
+        const capped = truncateUtf8(output, limits.outputBytes ?? Buffer.byteLength(output, "utf8"));
         state.output = capped.text;
         state.outputTruncatedBytes = capped.omittedBytes;
         outputBytesSeen += Buffer.byteLength(output, "utf8");
         state.outputBytes = outputBytesSeen;
-        state.outputTruncatedBytes = Math.max(state.outputTruncatedBytes, outputBytesSeen - limits.outputBytes);
-        if (outputBytesSeen > limits.outputBytes) requestTermination("limited", "output_limit", `Child output exceeds ${limits.outputBytes} bytes`);
+        state.outputTruncatedBytes = Math.max(state.outputTruncatedBytes, limits.outputBytes === undefined ? 0 : outputBytesSeen - limits.outputBytes);
+        if (limits.outputBytes !== undefined && outputBytesSeen > limits.outputBytes) requestTermination("limited", "output_limit", `Child output exceeds ${limits.outputBytes} bytes`);
       }
       if (typeof message.model === "string") state.model = message.provider ? `${message.provider}/${message.model}` : message.model;
       if (typeof message.stopReason === "string") {
@@ -398,7 +403,6 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
         else state.terminationReason = message.stopReason;
       }
       if (typeof message.errorMessage === "string") state.errorMessage = message.errorMessage;
-      if (message.stopReason === "length") requestTermination("limited", "model_output_limit");
       publish();
     } else if (event?.type === "tool_result_end" && event.message) {
       const name = typeof event.message.toolName === "string" ? event.message.toolName : "tool";
@@ -410,12 +414,14 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
   };
   const appendStdout = (fragment: Buffer): boolean => {
     const nextBytes = stdoutLineBytes + fragment.length;
-    if (nextBytes > limits.jsonlLineBytes) {
+    if (limits.jsonlLineBytes !== undefined && nextBytes > limits.jsonlLineBytes) {
       requestTermination("limited", "jsonl_line_limit", `Child JSONL line exceeds ${limits.jsonlLineBytes} bytes`);
       return false;
     }
     if (nextBytes > stdoutLine.length) {
-      const nextCapacity = Math.min(limits.jsonlLineBytes, Math.max(nextBytes, stdoutLine.length * 2, 4_096));
+      const nextCapacity = limits.jsonlLineBytes === undefined
+        ? Math.max(nextBytes, stdoutLine.length * 2, 4_096)
+        : Math.min(limits.jsonlLineBytes, Math.max(nextBytes, stdoutLine.length * 2, 4_096));
       const expanded = Buffer.allocUnsafe(nextCapacity);
       stdoutLine.copy(expanded, 0, 0, stdoutLineBytes);
       stdoutLine = expanded;
@@ -431,7 +437,9 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
     abortHandler();
   } else {
     try {
-      child = (options.spawnProcess ?? defaultSpawnProcess)(args, options.cwd);
+      child = options.spawnProcess
+        ? options.spawnProcess(args, options.cwd, options.environment)
+        : defaultSpawnProcess(args, options.cwd, options.environment);
       child.stdout.on("data", (chunk: Buffer | string) => {
         if (requestedStatus) return;
         const buffer = Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk);
@@ -450,14 +458,16 @@ export function runSubagentProcess(options: SubagentProcessOptions): SubagentPro
       });
       child.stderr.on("data", (chunk: Buffer | string) => {
         const buffer = Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk);
-        const retained = buffer.subarray(0, Math.max(0, limits.stderrBytes - stderr.length));
+        const retained = limits.stderrBytes === undefined
+          ? buffer
+          : buffer.subarray(0, Math.max(0, limits.stderrBytes - stderr.length));
         if (retained.length) stderr = Buffer.concat([stderr, retained]);
         state.stderrTruncatedBytes += buffer.length - retained.length;
         if (buffer.length > retained.length) requestTermination("limited", "stderr_limit", `Child stderr exceeds ${limits.stderrBytes} bytes`);
       });
       child.on("error", (error) => requestTermination("failed", "spawn_error", error.message));
       child.once("close", finish);
-      timeoutTimer = setTimeout(() => requestTermination("limited", "wall_time_limit"), limits.wallTimeMs);
+      if (limits.wallTimeMs !== undefined) timeoutTimer = setTimeout(() => requestTermination("limited", "wall_time_limit"), limits.wallTimeMs);
       options.signal?.addEventListener("abort", abortHandler, { once: true });
       if (options.signal?.aborted) abortHandler();
     } catch (error) {

package/subagent-ui.ts

@@ -120,14 +120,31 @@ function toRecord(item: ThreadListItem): ThreadRecord {
   };
 }
 
-export function formatThreadState(thread: Pick<ThreadRecord, "status" | "terminationReason">): ThreadStateView {
+function threadStatus(thread: Pick<ThreadRecord, "status" | "terminationReason">): ThreadStatus {
   const reason = thread.terminationReason;
-  if (thread.status === "complete") return { status: thread.status, label: "Complete" };
-  if (thread.status === "failed") return { status: thread.status, label: "Failed", reason, partialWork: "Failed before completion. Any saved output is partial work." };
-  if (thread.status === "cancelled") return { status: thread.status, label: "Stopped", reason, partialWork: "Stopped before completion. Any saved output is partial work." };
-  if (thread.status === "limited") return { status: thread.status, label: "Limited", reason, partialWork: "Stopped at a limit before completion. Any saved output is partial work." };
-  if (thread.status === "running") return { status: thread.status, label: "Running", reason };
-  return { status: thread.status, label: "Queued", reason };
+  if (thread.status === "failed" || reason === "error" || reason === "spawn_error" || reason === "process_closed" || reason === "missing_assistant_message" || reason === "malformed_jsonl" || reason === "invalid_usage" || reason?.startsWith("exit_")) return "failed";
+  if (thread.status === "cancelled" || reason === "abort" || reason === "interrupt") return "cancelled";
+  if (thread.status === "complete" || reason === "completed") return "complete";
+  return thread.status;
+}
+
+function threadReason(thread: Pick<ThreadRecord, "terminationReason" | "errorMessage">, status: ThreadStatus): string | undefined {
+  if (status === "cancelled" && thread.terminationReason === "interrupt") return "Interrupted by user.";
+  if (status === "cancelled" && thread.terminationReason === "abort") return "Cancelled by parent.";
+  if (status === "failed" && thread.errorMessage && thread.terminationReason) return `${thread.terminationReason}: ${thread.errorMessage}`;
+  if (status === "failed") return thread.errorMessage ?? thread.terminationReason ?? "Child process failed.";
+  return thread.terminationReason;
+}
+
+export function formatThreadState(thread: Pick<ThreadRecord, "status" | "terminationReason" | "errorMessage">): ThreadStateView {
+  const status = threadStatus(thread);
+  const reason = threadReason(thread, status);
+  if (status === "complete") return { status, label: "Complete" };
+  if (status === "failed") return { status, label: "Failed", reason, partialWork: "Failed before completion. Any saved output is partial work." };
+  if (status === "cancelled") return { status, label: "Stopped", reason, partialWork: "Stopped before completion. Any saved output is partial work." };
+  if (status === "limited") return { status, label: "Limited", reason, partialWork: "Stopped at a limit before completion. Any saved output is partial work." };
+  if (status === "running") return { status, label: "Running", reason };
+  return { status, label: "Queued", reason };
 }
 
 export function formatThreadUsage(usage: ThreadUsage): ThreadUsageView {
@@ -148,9 +165,9 @@ export function formatThreadTrace(thread: Pick<ThreadRecord, "trace" | "traceTru
   };
 }
 
-export function formatThreadHandoff(thread: Pick<ThreadRecord, "status" | "handoff" | "output">): ThreadHandoffView {
+export function formatThreadHandoff(thread: Pick<ThreadRecord, "status" | "terminationReason" | "handoff" | "output">): ThreadHandoffView {
   const text = thread.handoff ?? thread.output ?? "No handoff yet.";
-  return { label: "Handoff", text, isPartial: thread.status !== "complete" };
+  return { label: "Handoff", text, isPartial: threadStatus(thread) !== "complete" };
 }
 
 export function formatThreadControls(status: ThreadStatus): readonly ThreadBoardControl[] {

package/subagents.ts

@@ -22,15 +22,7 @@ import { formatThreadBoard, formatThreadInspection, type ThreadRecord as ThreadB
 export const SUBAGENT_LIMITS = {
   maxTasks: 8,
   maxReadConcurrency: 4,
-  defaultTimeoutMs: 300_000,
-  maxTimeoutMs: 600_000,
-  jsonlLineBytes: 32 * 1024 * 1024,
-  traceBytes: 2 * 1024 * 1024,
-  stderrBytes: 64 * 1024,
-  taskOutputBytes: 50 * 1024,
   toolOutputBytes: 50 * 1024,
-  quotaTokens: 1_000_000,
-  quotaUsd: 10,
   roleFileBytes: 64 * 1024,
   taskCharacters: 20_000,
   killGraceMs: 5_000,
@@ -58,7 +50,7 @@ export interface AgentRole {
   tools: string[];
   model?: string;
   thinking?: string;
-  timeoutMs: number;
+  timeoutMs?: number;
   prompt: string;
   source: AgentSource;
   filePath: string;
@@ -105,6 +97,7 @@ export interface SubagentTaskResult {
   output: string;
   outputBytes: number;
   outputTruncatedBytes: number;
+  toolCallCount: number;
   usage: SubagentUsage;
   durationMs: number;
   exitCode: number | null;
@@ -149,13 +142,21 @@ interface SpawnedProcess {
   once(event: "close", listener: (code: number | null) => void): this;
 }
 
-type SubagentLimits = { [Key in keyof typeof SUBAGENT_LIMITS]: number };
+type SubagentLimits = { [Key in keyof typeof SUBAGENT_LIMITS]: number } & {
+  wallTimeMs?: number;
+  jsonlLineBytes?: number;
+  traceBytes?: number;
+  stderrBytes?: number;
+  taskOutputBytes?: number;
+  quotaTokens?: number;
+  quotaUsd?: number;
+};
 
 export interface SubagentRuntimeOptions {
   bundledAgentsDir?: string;
   userAgentsDir?: string;
   webExtension?: string;
-  spawnProcess?: (args: string[], cwd: string) => SpawnedProcess;
+  spawnProcess?: (args: string[], cwd: string, environment?: NodeJS.ProcessEnv) => SpawnedProcess;
   limits?: Partial<SubagentLimits>;
 }
 
@@ -232,14 +233,15 @@ function optionalPositiveInteger(
   frontmatter: Record<string, unknown>,
   filePath: string,
   field: string,
-  fallback: number,
-  maximum: number,
-): number {
+  fallback?: number,
+  maximum?: number,
+): number | undefined {
   const value = frontmatter[field];
   if (value === undefined || value === "") return fallback;
   const parsed = typeof value === "number" ? value : typeof value === "string" ? Number(value) : Number.NaN;
-  if (!Number.isInteger(parsed) || parsed <= 0 || parsed > maximum) {
-    throw new AgentConfigurationError(filePath, field, `must be a positive integer no greater than ${maximum}`);
+  if (!Number.isInteger(parsed) || parsed <= 0 || maximum !== undefined && parsed > maximum) {
+    const bound = maximum === undefined ? "" : " no greater than " + maximum;
+    throw new AgentConfigurationError(filePath, field, `must be a positive integer${bound}`);
   }
   return parsed;
 }
@@ -296,7 +298,7 @@ function parseAgentFile(filePath: string, source: AgentSource, limits: SubagentL
     tools,
     model: typeof modelValue === "string" ? modelValue.trim() : undefined,
     thinking: typeof thinkingValue === "string" ? thinkingValue.trim() : undefined,
-    timeoutMs: optionalPositiveInteger(frontmatter, filePath, "timeoutMs", limits.defaultTimeoutMs, limits.maxTimeoutMs),
+    timeoutMs: optionalPositiveInteger(frontmatter, filePath, "timeoutMs"),
     prompt,
     source,
     filePath,
@@ -492,6 +494,7 @@ function makeQueuedResult(id: string, agent: string, task: string, step?: number
     output: "",
     outputBytes: 0,
     outputTruncatedBytes: 0,
+    toolCallCount: 0,
     usage: emptyUsage(),
     durationMs: 0,
     exitCode: null,
@@ -508,14 +511,14 @@ function cloneResult(result: SubagentTaskResult): SubagentTaskResult {
   };
 }
 
-function mergeTaskResults(previous: SubagentTaskResult | undefined, next: SubagentTaskResult, maxTraceBytes: number): SubagentTaskResult {
+function mergeTaskResults(previous: SubagentTaskResult | undefined, next: SubagentTaskResult, maxTraceBytes?: number): SubagentTaskResult {
   if (!previous) return cloneResult(next);
   const merged = cloneResult(next);
   const trace: string[] = [];
   let traceBytes = 0;
   let traceTruncatedBytes = previous.traceTruncatedBytes + next.traceTruncatedBytes;
   for (const entry of [...previous.trace, ...next.trace]) {
-    const retained = truncateUtf8(entry, Math.max(0, maxTraceBytes - traceBytes));
+    const retained = truncateUtf8(entry, maxTraceBytes === undefined ? Buffer.byteLength(entry, "utf8") : Math.max(0, maxTraceBytes - traceBytes));
     if (retained.text) trace.push(retained.text);
     const retainedBytes = Buffer.byteLength(retained.text, "utf8");
     traceBytes += retainedBytes;
@@ -530,6 +533,7 @@ function mergeTaskResults(previous: SubagentTaskResult | undefined, next: Subage
   merged.output = next.output || previous.output;
   merged.outputBytes = previous.outputBytes + next.outputBytes;
   merged.outputTruncatedBytes = previous.outputTruncatedBytes + next.outputTruncatedBytes;
+  merged.toolCallCount = previous.toolCallCount + next.toolCallCount;
   merged.usage = emptyUsage();
   addUsage(merged.usage, previous.usage);
   addUsage(merged.usage, next.usage);
@@ -557,7 +561,7 @@ interface RunTaskOptions {
   step?: number;
   model: ResolvedModel;
   signal?: AbortSignal;
-  spawnProcess: (args: string[], cwd: string) => SpawnedProcess;
+  spawnProcess: (args: string[], cwd: string, environment?: NodeJS.ProcessEnv) => SpawnedProcess;
   webExtension?: string;
   projectTrusted: boolean;
   limits: SubagentLimits;
@@ -582,6 +586,7 @@ function applyProcessResult(
   target.output = source.output;
   target.outputBytes = source.outputBytes;
   target.outputTruncatedBytes = source.outputTruncatedBytes;
+  target.toolCallCount = source.toolCallCount;
   target.usage = { ...source.usage, cost: { ...source.usage.cost } };
   target.model = source.model ?? target.model;
   target.terminationReason = source.terminationReason;
@@ -643,13 +648,13 @@ async function runTask(options: RunTaskOptions): Promise<SubagentTaskResult> {
       signal: options.signal,
       spawnProcess: options.spawnProcess,
       limits: {
-        wallTimeMs: options.timeoutMs ?? agent.timeoutMs,
-        jsonlLineBytes: limits.jsonlLineBytes,
-        traceBytes: limits.traceBytes,
-        stderrBytes: limits.stderrBytes,
-        outputBytes: limits.taskOutputBytes,
-        quotaTokens: limits.quotaTokens,
-        quotaUsd: limits.quotaUsd,
+        ...(options.timeoutMs === undefined ? {} : { wallTimeMs: options.timeoutMs }),
+        ...(limits.jsonlLineBytes === undefined ? {} : { jsonlLineBytes: limits.jsonlLineBytes }),
+        ...(limits.traceBytes === undefined ? {} : { traceBytes: limits.traceBytes }),
+        ...(limits.stderrBytes === undefined ? {} : { stderrBytes: limits.stderrBytes }),
+        ...(limits.taskOutputBytes === undefined ? {} : { outputBytes: limits.taskOutputBytes }),
+        ...(limits.quotaTokens === undefined ? {} : { quotaTokens: limits.quotaTokens }),
+        ...(limits.quotaUsd === undefined ? {} : { quotaUsd: limits.quotaUsd }),
         killGraceMs: limits.killGraceMs,
       },
       onUpdate: (next) => applyProcessResult(result, next, startedAt, options.onChange),
@@ -861,6 +866,7 @@ function threadResult(thread: SubagentThread, source?: SubagentTaskResult): Suba
       turns: thread.usage.turns,
     },
     output: thread.result ?? "",
+    toolCallCount: 0,
     terminationReason: thread.stopReason,
   };
 }
@@ -960,7 +966,9 @@ export function registerSubagentTool(pi: ExtensionAPI, options: SubagentRuntimeO
     const from = runtime?.traceCount ?? 0;
     let retainedTraceBytes = thread.trace.reduce((total, entry) => total + Buffer.byteLength(entry.message ?? "", "utf8"), 0);
     for (const entry of next.trace.slice(from)) {
-      const retained = truncateUtf8(entry, Math.max(0, limits.traceBytes - retainedTraceBytes));
+      const retained = truncateUtf8(entry, limits.traceBytes === undefined
+        ? Buffer.byteLength(entry, "utf8")
+        : Math.max(0, limits.traceBytes - retainedTraceBytes));
       if (retained.text) {
         threads.trace(threadId, { kind: "child", message: retained.text });
         retainedTraceBytes += Buffer.byteLength(retained.text, "utf8");
@@ -1238,33 +1246,34 @@ export function registerSubagentTool(pi: ExtensionAPI, options: SubagentRuntimeO
         try {
           while (true) {
             const aggregate = runtime.aggregate;
-            const remainingWallTimeMs = agent.timeoutMs - (Date.now() - runtime.startedAt);
+            const wallTimeMs = agent.timeoutMs ?? limits.wallTimeMs;
+            const remainingWallTimeMs = wallTimeMs === undefined ? undefined : wallTimeMs - (Date.now() - runtime.startedAt);
             const usedTraceBytes = aggregate?.traceBytes ?? 0;
             const usedStderrBytes = aggregate?.stderrBytes ?? 0;
             const usedOutputBytes = aggregate?.outputBytes ?? 0;
             const usedTokens = aggregate?.usage.totalTokens ?? 0;
             const usedCost = aggregate?.usage.cost.total ?? 0;
-            if (remainingWallTimeMs <= 0) {
-              stopForBudget("wall_time_limit", `Child thread exceeds ${agent.timeoutMs} ms`);
+            if (remainingWallTimeMs !== undefined && remainingWallTimeMs <= 0) {
+              stopForBudget("wall_time_limit", `Child thread exceeds ${wallTimeMs} ms`);
               break;
             }
-            if (usedTraceBytes >= limits.traceBytes || aggregate?.traceTruncatedBytes) {
+            if (limits.traceBytes !== undefined && (usedTraceBytes >= limits.traceBytes || aggregate?.traceTruncatedBytes)) {
               stopForBudget("trace_limit", `Child thread retains more than ${limits.traceBytes} trace bytes`);
               break;
             }
-            if (usedStderrBytes >= limits.stderrBytes || aggregate?.stderrTruncatedBytes) {
+            if (limits.stderrBytes !== undefined && (usedStderrBytes >= limits.stderrBytes || aggregate?.stderrTruncatedBytes)) {
               stopForBudget("stderr_limit", `Child thread emits more than ${limits.stderrBytes} stderr bytes`);
               break;
             }
-            if (usedOutputBytes >= limits.taskOutputBytes || aggregate?.outputTruncatedBytes) {
+            if (limits.taskOutputBytes !== undefined && (usedOutputBytes >= limits.taskOutputBytes || aggregate?.outputTruncatedBytes)) {
               stopForBudget("output_limit", `Child thread emits more than ${limits.taskOutputBytes} output bytes`);
               break;
             }
-            if (usedTokens >= limits.quotaTokens) {
+            if (limits.quotaTokens !== undefined && usedTokens >= limits.quotaTokens) {
               stopForBudget("quota_tokens", `Child thread exceeds ${limits.quotaTokens} tokens`);
               break;
             }
-            if (usedCost >= limits.quotaUsd) {
+            if (limits.quotaUsd !== undefined && usedCost >= limits.quotaUsd) {
               stopForBudget("quota_cost", `Child thread exceeds $${limits.quotaUsd}`);
               break;
             }
@@ -1282,11 +1291,11 @@ export function registerSubagentTool(pi: ExtensionAPI, options: SubagentRuntimeO
               spawnProcess,
               limits: {
                 ...limits,
-                traceBytes: limits.traceBytes - usedTraceBytes,
-                stderrBytes: limits.stderrBytes - usedStderrBytes,
-                taskOutputBytes: limits.taskOutputBytes - usedOutputBytes,
-                quotaTokens: limits.quotaTokens - usedTokens,
-                quotaUsd: limits.quotaUsd - usedCost,
+                ...(limits.traceBytes === undefined ? {} : { traceBytes: limits.traceBytes - usedTraceBytes }),
+                ...(limits.stderrBytes === undefined ? {} : { stderrBytes: limits.stderrBytes - usedStderrBytes }),
+                ...(limits.taskOutputBytes === undefined ? {} : { taskOutputBytes: limits.taskOutputBytes - usedOutputBytes }),
+                ...(limits.quotaTokens === undefined ? {} : { quotaTokens: limits.quotaTokens - usedTokens }),
+                ...(limits.quotaUsd === undefined ? {} : { quotaUsd: limits.quotaUsd - usedCost }),
               },
               timeoutMs: remainingWallTimeMs,
               onHandle: (handle) => { runtime.handle = handle; },