@leing2021/super-pi 0.20.0 → 0.21.0

package/README.md

@@ -91,7 +91,7 @@ Breaks requirements into implementation units, each following strict **RED → G
 
 ### 03-work: Build Right
 
-**Parallel execution**: `task_splitter` uses a Union-Find algorithm to analyze file dependencies, feeds conflict-free units to `parallel_subagent` for concurrent execution.
+**Parallel execution**: `task_splitter` uses a Union-Find algorithm to analyze file dependencies, feeds conflict-free units to `subagent` (parallel mode, via pi-subagents) for concurrent execution.
 
 **Checkpoint resume**: After each unit, a checkpoint is saved. Interrupted? Next startup auto-loads, skips completed work, continues from the breakpoint. Failed? `fail` records the error → `retry` suggests a recovery strategy (timeout? extend timeout. Permission issue? check permissions first. Code error? fix then retry).
 
@@ -161,7 +161,7 @@ This ensures your stage-specific models and thinking levels are used when CE Age
 |-------|-----------|-----------|
 | `01-brainstorm` | Deep requirements mining in three modes | `brainstorm_dialog` |
 | `02-plan` | Break into units, TDD gates, incremental updates | `plan_diff` |
-| `03-work` | Parallel execution, checkpoint resume, error recovery | `session_checkpoint`, `task_splitter`, `parallel_subagent` |
+| `03-work` | Parallel execution, checkpoint resume, error recovery | `session_checkpoint`, `task_splitter`, `subagent` (pi-subagents) |
 | `04-review` | Persona-routed review + live browser testing | `review_router` |
 | `05-learn` | Pattern extraction → knowledge card compounding | `pattern_extractor` |
 | `06-next` | Not sure what to do next? Ask this | `workflow_state`, `session_history` |
@@ -177,7 +177,7 @@ This ensures your stage-specific models and thinking levels are used when CE Age
 | `task_splitter` | Union-Find algorithm analyzes file dependencies, auto-groups parallel-safe units |
 | `session_checkpoint` | JSON-persisted checkpoints with save/load/fail/retry operations |
 | `plan_diff` | Incremental plans: compare detects diffs, patch applies changes |
-| `parallel_subagent` | `Promise.allSettled`-style parallel subagent execution with context slimming |
+| `subagent` | Parallel & serial subagent execution via pi-subagents (async, TUI, agent CRUD) |
 | `review_router` | Auto-assign reviewer personas from diff metadata |
 | `pattern_extractor` | Extract and categorize patterns from artifacts |
 | `brainstorm_dialog` | Multi-round dialog state machine (start → refine × N → summarize) |
@@ -421,6 +421,14 @@ Not a fork. Not a wrapper. Methodologies extracted and rebuilt with Pi's native
 
 ## Changelog
 
+### 0.21.0 — Delegate subagent tools to pi-subagents
+- Removed `subagent` and `parallel_subagent` tool registrations from `ce-core` extension.
+- Subagent capabilities (serial, parallel, chain, async, TUI, agent CRUD) now provided by the `pi-subagents` package.
+- Removed `AsyncMutex`, `subagent-depth-guard` exports — no longer needed in this package.
+- Added `pi-subagents` as a peer dependency in `package.json`.
+- Updated `03-work` skill, `ce-worker` agent, and all README references from `parallel_subagent` to `subagent` (pi-subagents).
+- Renamed internal `path` variable to `filePath` in read-output-filter to avoid shadowing.
+
 ### 0.20.0 — Extension API migration + v0.19.7 rework
 - Migrated `super-pi-extension` from legacy `export default { load() }` object format to Pi-native factory function `(pi: ExtensionAPI) => void`.
 - Replaced hardcoded `ExtensionContext` import with `ExtensionAPI`-only — context now provided via event handler.
@@ -530,7 +538,7 @@ Not a fork. Not a wrapper. Methodologies extracted and rebuilt with Pi's native
 - New session_checkpoint tool
 
 ### 0.5.0 — Parallel execution
-- New parallel_subagent tool
+- New parallel_subagent tool (now delegated to pi-subagents)
 
 ### 0.4.0 — Smart review
 - New review_router tool

package/extensions/ce-core/index.ts

@@ -4,11 +4,9 @@ import type { ExtensionAPI } from "@mariozechner/pi-coding-agent"
 import { Type } from "typebox"
 import { createArtifactHelperTool, type ArtifactType } from "./tools/artifact-helper"
 import { createAskUserQuestionTool } from "./tools/ask-user-question"
-import { createSubagentTool } from "./tools/subagent"
 import { createWorkflowStateTool } from "./tools/workflow-state"
 import { createWorktreeManagerTool } from "./tools/worktree-manager"
 import { createReviewRouterTool } from "./tools/review-router"
-import { createParallelSubagentTool } from "./tools/parallel-subagent"
 import { createSessionCheckpointTool } from "./tools/session-checkpoint"
 import { createTaskSplitterTool } from "./tools/task-splitter"
 import { createBrainstormDialogTool } from "./tools/brainstorm-dialog"
@@ -18,10 +16,11 @@ import { createPatternExtractorTool } from "./tools/pattern-extractor"
 import { filterBashOutput } from "./tools/bash-output-filter"
 import { filterReadOutput } from "./tools/read-output-filter"
 import { COMPACTION_FOCUS_INSTRUCTIONS } from "./tools/compaction-optimizer"
-import { AsyncMutex } from "./tools/async-mutex"
-import type { SubagentExecOptions, SubagentRunner } from "./tools/subagent"
 
-const _subagentEnvMutex = new AsyncMutex()
+// NOTE: subagent and parallel_subagent tool registration removed.
+// Subagent capabilities are provided by the pi-subagents package.
+// super-pi focuses on CE-specific tools only.
+
 const PIPELINE_STAGE_KEYS = new Set([
   "01-brainstorm",
   "02-plan",
@@ -82,47 +81,6 @@ function parseModelRef(
   }
 }
 
-/**
- * Create a subagent runner that handles env injection with mutex protection
- * for concurrency safety when multiple parallel subagents share the process.
- */
-function createSubagentRunner(
-  pi: ExtensionAPI,
-  signal?: AbortSignal,
-): SubagentRunner {
-  return async (prompt: string, options?: SubagentExecOptions) => {
-    const args = ["--no-session", ...(options?.extraFlags ?? []), "-p", prompt]
-    const release = await _subagentEnvMutex.acquire()
-    const savedEnv: Record<string, string | undefined> = {}
-    const extraEnv = options?.extraEnv ?? {}
-    for (const [key, value] of Object.entries(extraEnv)) {
-      savedEnv[key] = process.env[key]
-      process.env[key] = value
-    }
-    try {
-      const execResult = await pi.exec("pi", args, {
-        signal,
-        timeout: 10 * 60 * 1000,
-      })
-
-      if (execResult.code !== 0) {
-        throw new Error(execResult.stderr || execResult.stdout || `Subagent failed for prompt: ${prompt}`)
-      }
-
-      return (execResult.stdout || "").trim()
-    } finally {
-      for (const [key, oldValue] of Object.entries(savedEnv)) {
-        if (oldValue === undefined) {
-          delete process.env[key]
-        } else {
-          process.env[key] = oldValue
-        }
-      }
-      release()
-    }
-  }
-}
-
 const artifactHelperParams = Type.Object({
   repoRoot: Type.String({ description: "Repository root where workflow artifacts should be created" }),
   artifactType: Type.Union([
@@ -145,18 +103,6 @@ const askUserQuestionParams = Type.Object({
   allowCustom: Type.Optional(Type.Boolean({ description: "Allow a custom answer when options are present" })),
 })
 
-const subagentTaskSchema = Type.Object({
-  agent: Type.String({ description: "Skill name to invoke via /skill:<name>" }),
-  task: Type.String({ description: "Task text passed to the subagent" }),
-})
-
-const subagentParams = Type.Object({
-  agent: Type.Optional(Type.String({ description: "Single subagent skill name" })),
-  task: Type.Optional(Type.String({ description: "Single subagent task" })),
-  chain: Type.Optional(Type.Array(subagentTaskSchema, { description: "Serial subagent chain with optional {previous} placeholder" })),
-  inheritSkills: Type.Optional(Type.Boolean({ description: "Whether the subagent should inherit skills. Default: true" })),
-})
-
 const workflowStateParams = Type.Object({
   repoRoot: Type.String({ description: "Repository root to scan for workflow artifacts" }),
 })
@@ -179,19 +125,6 @@ const reviewRouterParams = Type.Object({
   deletions: Type.Number({ description: "Number of lines removed" }),
 })
 
-const parallelSubagentTaskSchema = Type.Object({
-  agent: Type.String({ description: "Skill name to invoke via /skill:<name>" }),
-  task: Type.String({ description: "Task text passed to the subagent" }),
-})
-
-const parallelSubagentParams = Type.Object({
-  tasks: Type.Union([
-    Type.Array(parallelSubagentTaskSchema),
-    Type.String({ description: "JSON stringified array of tasks" }),
-  ], { description: "Array of independent tasks to run concurrently (can be a JSON string)" }),
-  inheritSkills: Type.Optional(Type.Boolean({ description: "Whether subagents should inherit skills. Default: false" })),
-})
-
 const sessionCheckpointParams = Type.Object({
   operation: Type.Union([
     Type.Literal("save"),
@@ -342,11 +275,9 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
 
   const artifactHelper = createArtifactHelperTool()
   const askUserQuestion = createAskUserQuestionTool()
-  const subagent = createSubagentTool()
   const workflowState = createWorkflowStateTool()
   const worktreeManager = createWorktreeManagerTool()
   const reviewRouter = createReviewRouterTool()
-  const parallelSubagent = createParallelSubagentTool()
   const sessionCheckpoint = createSessionCheckpointTool()
   const taskSplitter = createTaskSplitterTool()
   const brainstormDialog = createBrainstormDialogTool()
@@ -419,29 +350,6 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     },
   })
 
-  pi.registerTool({
-    name: subagent.name,
-    label: "Subagent",
-    description: "Run a single skill-based subagent or a serial chain in an isolated Pi process.",
-    parameters: subagentParams,
-    async execute(_toolCallId, params, signal, _onUpdate, ctx) {
-      const result = await subagent.execute(
-        {
-          agent: params.agent,
-          task: params.task,
-          chain: params.chain,
-          inheritSkills: params.inheritSkills,
-        },
-        createSubagentRunner(pi, signal),
-      )
-
-      return {
-        content: [{ type: "text", text: result.outputs[result.outputs.length - 1] ?? "" }],
-        details: result,
-      }
-    },
-  })
-
   pi.registerTool({
     name: workflowState.name,
     label: "Workflow State",
@@ -513,39 +421,6 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     },
   })
 
-  pi.registerTool({
-    name: parallelSubagent.name,
-    label: "Parallel Subagent",
-    description: "Run multiple skill-based subagent tasks concurrently. IMPORTANT: Provide 'tasks' as a clean JSON array object. If the environment forces a string, provide a valid JSON array string.",
-    parameters: parallelSubagentParams,
-    async execute(_toolCallId, params, signal) {
-      let tasks: any[]
-      if (typeof params.tasks === "string") {
-        try {
-          const cleaned = params.tasks.replace(/^```json\s*|```$/g, "").trim()
-          tasks = JSON.parse(cleaned)
-        } catch (e) {
-          throw new Error(`Failed to parse tasks string as JSON: ${e instanceof Error ? e.message : String(e)}`)
-        }
-      } else {
-        tasks = params.tasks
-      }
-
-      const result = await parallelSubagent.execute(
-        {
-          tasks,
-          inheritSkills: params.inheritSkills,
-        },
-        createSubagentRunner(pi, signal),
-      )
-
-      return {
-        content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
-        details: result,
-      }
-    },
-  })
-
   pi.registerTool({
     name: sessionCheckpoint.name,
     label: "Session Checkpoint",
@@ -712,8 +587,8 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     if (event.toolName !== "read") return undefined
 
     // Extract path from input
-    const path = (event.input as any)?.path ?? ""
-    if (!path) return undefined
+    const filePath = (event.input as any)?.path ?? ""
+    if (!filePath) return undefined
 
     // Extract text content from tool result
     const textBlocks = (event.content as Array<any>)?.filter((b: any) => b.type === "text") ?? []
@@ -723,7 +598,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     const isImage = (event.content as Array<any>)?.some((b: any) => b.type === "image") ?? false
 
     const result = filterReadOutput({
-      path,
+      path: filePath,
       output,
       isError: event.isError ?? false,
       isImage,
@@ -756,13 +631,9 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
 
 export { createArtifactHelperTool } from "./tools/artifact-helper"
 export { createAskUserQuestionTool } from "./tools/ask-user-question"
-export { createSubagentTool } from "./tools/subagent"
-export { checkSubagentDepth, getChildDepthEnv, DEFAULT_MAX_SUBAGENT_DEPTH } from "./tools/subagent-depth-guard"
-export { AsyncMutex } from "./tools/async-mutex"
 export { createWorkflowStateTool } from "./tools/workflow-state"
 export { createWorktreeManagerTool } from "./tools/worktree-manager"
 export { createReviewRouterTool } from "./tools/review-router"
-export { createParallelSubagentTool } from "./tools/parallel-subagent"
 export { createSessionCheckpointTool } from "./tools/session-checkpoint"
 export { createTaskSplitterTool } from "./tools/task-splitter"
 export { createBrainstormDialogTool } from "./tools/brainstorm-dialog"

package/extensions/super-pi-extension/agents/ce-worker.md

@@ -43,7 +43,7 @@ defaultProgress: true
 - 不写任何生产代码直到有 RED 测试失败证据
 - 不跳过验证步骤
 - 每次完成都要有命令输出证据
-- 优先使用 `parallel_subagent` 执行独立单元
+- 优先使用 `subagent` (parallel mode, via pi-subagents) 执行独立单元
 
 ### 进度记录格式
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@leing2021/super-pi",
-  "version": "0.20.0",
+  "version": "0.21.0",
   "private": false,
   "type": "module",
   "description": "Pi-native Compound Engineering package for iterative development workflows",
@@ -36,6 +36,7 @@
   },
   "peerDependencies": {
     "@mariozechner/pi-coding-agent": "*",
+    "pi-subagents": "*",
     "typebox": "*"
   },
   "devDependencies": {

package/skills/03-work/SKILL.md

@@ -18,11 +18,11 @@ See [shared pipeline instructions](../references/pipeline-config.md) for model r
   4. If the task involves frontend/browser concerns, also load `rules/web/` files
 - Distinguish between a **plan path** input and a **bare prompt** input before doing work.
 - Prefer deriving execution tasks from plan **implementation units**.
-- Use **serial subagents** for tasks with dependencies.
-- Use **`parallel_subagent`** for independent tasks that can run concurrently.
+- Use **serial subagents** (via `subagent` tool from pi-subagents) for tasks with dependencies.
+- Use **`subagent` tool in parallel mode** (via pi-subagents) for independent tasks that can run concurrently.
 - Use **`session_checkpoint`** to track plan execution progress. On start, load the checkpoint and skip completed units. After each unit, save the checkpoint.
 - On execution failure, use `session_checkpoint` `fail` to record the error, then `retry` to get a retry strategy. Follow the suggested strategy to recover.
-- Use **`task_splitter`** to analyze implementation units for file-level dependencies before execution. Run independent units via `parallel_subagent` and dependent units serially.
+- Use **`task_splitter`** to analyze implementation units for file-level dependencies before execution. Run independent units via parallel subagents and dependent units serially.
 - If inside a **worktree** (created via `07-worktree`), execute within it. Otherwise, consider recommending `07-worktree` for isolation.
 - End by recommending `04-review`.