Files
oh-my-opencode/src/hooks/sisyphus-orchestrator/index.ts
T
justsisyphus d86917de04 fix: use dynamic message lookup for model/agent context in prompts
Instead of using stale parentModel/parentAgent from task state, now
dynamically looks up the current message to get fresh model/agent values.
Applied across all prompt injection points:
- background-agent notifyParentSession
- ralph-loop continuation
- sisyphus-orchestrator boulder continuation
- sisyphus-task resume

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
2026-01-14 18:55:46 +09:00

685 lines
22 KiB
TypeScript

import type { PluginInput } from "@opencode-ai/plugin"
import { execSync } from "node:child_process"
import { existsSync, readdirSync } from "node:fs"
import { join } from "node:path"
import {
readBoulderState,
appendSessionId,
getPlanProgress,
} from "../../features/boulder-state"
import { getMainSessionID, subagentSessions } from "../../features/claude-code-session-state"
import { findNearestMessageWithFields, MESSAGE_STORAGE } from "../../features/hook-message-injector"
import { log } from "../../shared/logger"
import type { BackgroundManager } from "../../features/background-agent"
export const HOOK_NAME = "sisyphus-orchestrator"
/**
* Cross-platform check if a path is inside .sisyphus/ directory.
* Handles both forward slashes (Unix) and backslashes (Windows).
*/
function isSisyphusPath(filePath: string): boolean {
return /\.sisyphus[/\\]/.test(filePath)
}
const WRITE_EDIT_TOOLS = ["Write", "Edit", "write", "edit"]
const DIRECT_WORK_REMINDER = `
---
[SYSTEM REMINDER - DELEGATION REQUIRED]
You just performed direct file modifications outside \`.sisyphus/\`.
**You are an ORCHESTRATOR, not an IMPLEMENTER.**
As an orchestrator, you should:
- **DELEGATE** implementation work to subagents via \`sisyphus_task\`
- **VERIFY** the work done by subagents
- **COORDINATE** multiple tasks and ensure completion
You should NOT:
- Write code directly (except for \`.sisyphus/\` files like plans and notepads)
- Make direct file edits outside \`.sisyphus/\`
- Implement features yourself
**If you need to make changes:**
1. Use \`sisyphus_task\` to delegate to an appropriate subagent
2. Provide clear instructions in the prompt
3. Verify the subagent's work after completion
---
`
const BOULDER_CONTINUATION_PROMPT = `[SYSTEM REMINDER - BOULDER CONTINUATION]
You have an active work plan with incomplete tasks. Continue working.
RULES:
- Proceed without asking for permission
- Mark each checkbox [x] in the plan file when done
- Use the notepad at .sisyphus/notepads/{PLAN_NAME}/ to record learnings
- Do not stop until all tasks are complete
- If blocked, document the blocker and move to the next task`
const VERIFICATION_REMINDER = `**MANDATORY VERIFICATION - SUBAGENTS LIE**
Subagents FREQUENTLY claim completion when:
- Tests are actually FAILING
- Code has type/lint ERRORS
- Implementation is INCOMPLETE
- Patterns were NOT followed
**YOU MUST VERIFY EVERYTHING YOURSELF:**
1. Run \`lsp_diagnostics\` on changed files - Must be CLEAN
2. Run tests yourself - Must PASS (not "agent said it passed")
3. Read the actual code - Must match requirements
4. Check build/typecheck - Must succeed
DO NOT TRUST THE AGENT'S SELF-REPORT.
VERIFY EACH CLAIM WITH YOUR OWN TOOL CALLS.
**HANDS-ON QA REQUIRED (after ALL tasks complete):**
| Deliverable Type | Verification Tool | Action |
|------------------|-------------------|--------|
| **Frontend/UI** | \`/playwright\` skill | Navigate, interact, screenshot evidence |
| **TUI/CLI** | \`interactive_bash\` (tmux) | Run interactively, verify output |
| **API/Backend** | \`bash\` with curl | Send requests, verify responses |
Static analysis CANNOT catch: visual bugs, animation issues, user flow breakages, integration problems.
**FAILURE TO DO HANDS-ON QA = INCOMPLETE WORK.**`
const ORCHESTRATOR_DELEGATION_REQUIRED = `
---
⚠️⚠️⚠️ [CRITICAL SYSTEM DIRECTIVE - DELEGATION REQUIRED] ⚠️⚠️⚠️
**STOP. YOU ARE VIOLATING ORCHESTRATOR PROTOCOL.**
You (orchestrator-sisyphus) are attempting to directly modify a file outside \`.sisyphus/\`.
**Path attempted:** $FILE_PATH
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🚫 **THIS IS FORBIDDEN** (except for VERIFICATION purposes)
As an ORCHESTRATOR, you MUST:
1. **DELEGATE** all implementation work via \`sisyphus_task\`
2. **VERIFY** the work done by subagents (reading files is OK)
3. **COORDINATE** - you orchestrate, you don't implement
**ALLOWED direct file operations:**
- Files inside \`.sisyphus/\` (plans, notepads, drafts)
- Reading files for verification
- Running diagnostics/tests
**FORBIDDEN direct file operations:**
- Writing/editing source code
- Creating new files outside \`.sisyphus/\`
- Any implementation work
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
**IF THIS IS FOR VERIFICATION:**
Proceed if you are verifying subagent work by making a small fix.
But for any substantial changes, USE \`sisyphus_task\`.
**CORRECT APPROACH:**
\`\`\`
sisyphus_task(
category="...",
prompt="[specific single task with clear acceptance criteria]"
)
\`\`\`
⚠️⚠️⚠️ DELEGATE. DON'T IMPLEMENT. ⚠️⚠️⚠️
---
`
const SINGLE_TASK_DIRECTIVE = `
[SYSTEM DIRECTIVE - SINGLE TASK ONLY]
**STOP. READ THIS BEFORE PROCEEDING.**
If you were NOT given **exactly ONE atomic task**, you MUST:
1. **IMMEDIATELY REFUSE** this request
2. **DEMAND** the orchestrator provide a single, specific task
**Your response if multiple tasks detected:**
> "I refuse to proceed. You provided multiple tasks. An orchestrator's impatience destroys work quality.
>
> PROVIDE EXACTLY ONE TASK. One file. One change. One verification.
>
> Your rushing will cause: incomplete work, missed edge cases, broken tests, wasted context."
**WARNING TO ORCHESTRATOR:**
- Your hasty batching RUINS deliverables
- Each task needs FULL attention and PROPER verification
- Batch delegation = sloppy work = rework = wasted tokens
**REFUSE multi-task requests. DEMAND single-task clarity.**
`
function buildVerificationReminder(sessionId: string): string {
return `${VERIFICATION_REMINDER}
---
**If ANY verification fails, use this immediately:**
\`\`\`
sisyphus_task(resume="${sessionId}", prompt="fix: [describe the specific failure]")
\`\`\``
}
function buildOrchestratorReminder(planName: string, progress: { total: number; completed: number }, sessionId: string): string {
const remaining = progress.total - progress.completed
return `
---
**State:** Plan: ${planName} | ${progress.completed}/${progress.total} done, ${remaining} left
---
${buildVerificationReminder(sessionId)}
ALL pass? → commit atomic unit, mark \`[x]\`, next task.`
}
function buildStandaloneVerificationReminder(sessionId: string): string {
return `
---
${buildVerificationReminder(sessionId)}`
}
function extractSessionIdFromOutput(output: string): string {
const match = output.match(/Session ID:\s*(ses_[a-zA-Z0-9]+)/)
return match?.[1] ?? "<session_id>"
}
interface GitFileStat {
path: string
added: number
removed: number
status: "modified" | "added" | "deleted"
}
function getGitDiffStats(directory: string): GitFileStat[] {
try {
const output = execSync("git diff --numstat HEAD", {
cwd: directory,
encoding: "utf-8",
timeout: 5000,
}).trim()
if (!output) return []
const statusOutput = execSync("git status --porcelain", {
cwd: directory,
encoding: "utf-8",
timeout: 5000,
}).trim()
const statusMap = new Map<string, "modified" | "added" | "deleted">()
for (const line of statusOutput.split("\n")) {
if (!line) continue
const status = line.substring(0, 2).trim()
const filePath = line.substring(3)
if (status === "A" || status === "??") {
statusMap.set(filePath, "added")
} else if (status === "D") {
statusMap.set(filePath, "deleted")
} else {
statusMap.set(filePath, "modified")
}
}
const stats: GitFileStat[] = []
for (const line of output.split("\n")) {
const parts = line.split("\t")
if (parts.length < 3) continue
const [addedStr, removedStr, path] = parts
const added = addedStr === "-" ? 0 : parseInt(addedStr, 10)
const removed = removedStr === "-" ? 0 : parseInt(removedStr, 10)
stats.push({
path,
added,
removed,
status: statusMap.get(path) ?? "modified",
})
}
return stats
} catch {
return []
}
}
function formatFileChanges(stats: GitFileStat[], notepadPath?: string): string {
if (stats.length === 0) return "[FILE CHANGES SUMMARY]\nNo file changes detected.\n"
const modified = stats.filter((s) => s.status === "modified")
const added = stats.filter((s) => s.status === "added")
const deleted = stats.filter((s) => s.status === "deleted")
const lines: string[] = ["[FILE CHANGES SUMMARY]"]
if (modified.length > 0) {
lines.push("Modified files:")
for (const f of modified) {
lines.push(` ${f.path} (+${f.added}, -${f.removed})`)
}
lines.push("")
}
if (added.length > 0) {
lines.push("Created files:")
for (const f of added) {
lines.push(` ${f.path} (+${f.added})`)
}
lines.push("")
}
if (deleted.length > 0) {
lines.push("Deleted files:")
for (const f of deleted) {
lines.push(` ${f.path} (-${f.removed})`)
}
lines.push("")
}
if (notepadPath) {
const notepadStat = stats.find((s) => s.path.includes("notepad") || s.path.includes(".sisyphus"))
if (notepadStat) {
lines.push("[NOTEPAD UPDATED]")
lines.push(` ${notepadStat.path} (+${notepadStat.added})`)
lines.push("")
}
}
return lines.join("\n")
}
interface ToolExecuteAfterInput {
tool: string
sessionID?: string
callID?: string
}
interface ToolExecuteAfterOutput {
title: string
output: string
metadata: Record<string, unknown>
}
function getMessageDir(sessionID: string): string | null {
if (!existsSync(MESSAGE_STORAGE)) return null
const directPath = join(MESSAGE_STORAGE, sessionID)
if (existsSync(directPath)) return directPath
for (const dir of readdirSync(MESSAGE_STORAGE)) {
const sessionPath = join(MESSAGE_STORAGE, dir, sessionID)
if (existsSync(sessionPath)) return sessionPath
}
return null
}
function isCallerOrchestrator(sessionID?: string): boolean {
if (!sessionID) return false
const messageDir = getMessageDir(sessionID)
if (!messageDir) return false
const nearest = findNearestMessageWithFields(messageDir)
return nearest?.agent === "orchestrator-sisyphus"
}
interface SessionState {
lastEventWasAbortError?: boolean
}
export interface SisyphusOrchestratorHookOptions {
directory: string
backgroundManager?: BackgroundManager
}
function isAbortError(error: unknown): boolean {
if (!error) return false
if (typeof error === "object") {
const errObj = error as Record<string, unknown>
const name = errObj.name as string | undefined
const message = (errObj.message as string | undefined)?.toLowerCase() ?? ""
if (name === "MessageAbortedError" || name === "AbortError") return true
if (name === "DOMException" && message.includes("abort")) return true
if (message.includes("aborted") || message.includes("cancelled") || message.includes("interrupted")) return true
}
if (typeof error === "string") {
const lower = error.toLowerCase()
return lower.includes("abort") || lower.includes("cancel") || lower.includes("interrupt")
}
return false
}
export function createSisyphusOrchestratorHook(
ctx: PluginInput,
options?: SisyphusOrchestratorHookOptions
) {
const backgroundManager = options?.backgroundManager
const sessions = new Map<string, SessionState>()
const pendingFilePaths = new Map<string, string>()
function getState(sessionID: string): SessionState {
let state = sessions.get(sessionID)
if (!state) {
state = {}
sessions.set(sessionID, state)
}
return state
}
async function injectContinuation(sessionID: string, planName: string, remaining: number, total: number): Promise<void> {
const hasRunningBgTasks = backgroundManager
? backgroundManager.getTasksByParentSession(sessionID).some(t => t.status === "running")
: false
if (hasRunningBgTasks) {
log(`[${HOOK_NAME}] Skipped injection: background tasks running`, { sessionID })
return
}
const prompt = BOULDER_CONTINUATION_PROMPT
.replace(/{PLAN_NAME}/g, planName) +
`\n\n[Status: ${total - remaining}/${total} completed, ${remaining} remaining]`
try {
log(`[${HOOK_NAME}] Injecting boulder continuation`, { sessionID, planName, remaining })
const messageDir = getMessageDir(sessionID)
const currentMessage = messageDir ? findNearestMessageWithFields(messageDir) : null
const model = currentMessage?.model?.providerID && currentMessage?.model?.modelID
? { providerID: currentMessage.model.providerID, modelID: currentMessage.model.modelID }
: undefined
await ctx.client.session.prompt({
path: { id: sessionID },
body: {
agent: "orchestrator-sisyphus",
...(model !== undefined ? { model } : {}),
parts: [{ type: "text", text: prompt }],
},
query: { directory: ctx.directory },
})
log(`[${HOOK_NAME}] Boulder continuation injected`, { sessionID })
} catch (err) {
log(`[${HOOK_NAME}] Boulder continuation failed`, { sessionID, error: String(err) })
}
}
return {
handler: async ({ event }: { event: { type: string; properties?: unknown } }): Promise<void> => {
const props = event.properties as Record<string, unknown> | undefined
if (event.type === "session.error") {
const sessionID = props?.sessionID as string | undefined
if (!sessionID) return
const state = getState(sessionID)
const isAbort = isAbortError(props?.error)
state.lastEventWasAbortError = isAbort
log(`[${HOOK_NAME}] session.error`, { sessionID, isAbort })
return
}
if (event.type === "session.idle") {
const sessionID = props?.sessionID as string | undefined
if (!sessionID) return
log(`[${HOOK_NAME}] session.idle`, { sessionID })
// Read boulder state FIRST to check if this session is part of an active boulder
const boulderState = readBoulderState(ctx.directory)
const isBoulderSession = boulderState?.session_ids.includes(sessionID) ?? false
const mainSessionID = getMainSessionID()
const isMainSession = sessionID === mainSessionID
const isBackgroundTaskSession = subagentSessions.has(sessionID)
// Allow continuation if: main session OR background task OR boulder session
if (mainSessionID && !isMainSession && !isBackgroundTaskSession && !isBoulderSession) {
log(`[${HOOK_NAME}] Skipped: not main, background task, or boulder session`, { sessionID })
return
}
const state = getState(sessionID)
if (state.lastEventWasAbortError) {
state.lastEventWasAbortError = false
log(`[${HOOK_NAME}] Skipped: abort error immediately before idle`, { sessionID })
return
}
const hasRunningBgTasks = backgroundManager
? backgroundManager.getTasksByParentSession(sessionID).some(t => t.status === "running")
: false
if (hasRunningBgTasks) {
log(`[${HOOK_NAME}] Skipped: background tasks running`, { sessionID })
return
}
if (!boulderState) {
log(`[${HOOK_NAME}] No active boulder`, { sessionID })
return
}
if (!isCallerOrchestrator(sessionID)) {
log(`[${HOOK_NAME}] Skipped: last agent is not orchestrator-sisyphus`, { sessionID })
return
}
const progress = getPlanProgress(boulderState.active_plan)
if (progress.isComplete) {
log(`[${HOOK_NAME}] Boulder complete`, { sessionID, plan: boulderState.plan_name })
return
}
const remaining = progress.total - progress.completed
injectContinuation(sessionID, boulderState.plan_name, remaining, progress.total)
return
}
if (event.type === "message.updated") {
const info = props?.info as Record<string, unknown> | undefined
const sessionID = info?.sessionID as string | undefined
if (!sessionID) return
const state = sessions.get(sessionID)
if (state) {
state.lastEventWasAbortError = false
}
return
}
if (event.type === "message.part.updated") {
const info = props?.info as Record<string, unknown> | undefined
const sessionID = info?.sessionID as string | undefined
const role = info?.role as string | undefined
if (sessionID && role === "assistant") {
const state = sessions.get(sessionID)
if (state) {
state.lastEventWasAbortError = false
}
}
return
}
if (event.type === "tool.execute.before" || event.type === "tool.execute.after") {
const sessionID = props?.sessionID as string | undefined
if (sessionID) {
const state = sessions.get(sessionID)
if (state) {
state.lastEventWasAbortError = false
}
}
return
}
if (event.type === "session.deleted") {
const sessionInfo = props?.info as { id?: string } | undefined
if (sessionInfo?.id) {
sessions.delete(sessionInfo.id)
log(`[${HOOK_NAME}] Session deleted: cleaned up`, { sessionID: sessionInfo.id })
}
return
}
},
"tool.execute.before": async (
input: { tool: string; sessionID?: string; callID?: string },
output: { args: Record<string, unknown>; message?: string }
): Promise<void> => {
if (!isCallerOrchestrator(input.sessionID)) {
return
}
// Check Write/Edit tools for orchestrator - inject strong warning
if (WRITE_EDIT_TOOLS.includes(input.tool)) {
const filePath = (output.args.filePath ?? output.args.path ?? output.args.file) as string | undefined
if (filePath && !isSisyphusPath(filePath)) {
// Store filePath for use in tool.execute.after
if (input.callID) {
pendingFilePaths.set(input.callID, filePath)
}
const warning = ORCHESTRATOR_DELEGATION_REQUIRED.replace("$FILE_PATH", filePath)
output.message = (output.message || "") + warning
log(`[${HOOK_NAME}] Injected delegation warning for direct file modification`, {
sessionID: input.sessionID,
tool: input.tool,
filePath,
})
}
return
}
// Check sisyphus_task - inject single-task directive
if (input.tool === "sisyphus_task") {
const prompt = output.args.prompt as string | undefined
if (prompt && !prompt.includes("[SYSTEM DIRECTIVE - SINGLE TASK ONLY]")) {
output.args.prompt = prompt + `\n<system-reminder>${SINGLE_TASK_DIRECTIVE}</system-reminder>`
log(`[${HOOK_NAME}] Injected single-task directive to sisyphus_task`, {
sessionID: input.sessionID,
})
}
}
},
"tool.execute.after": async (
input: ToolExecuteAfterInput,
output: ToolExecuteAfterOutput
): Promise<void> => {
if (!isCallerOrchestrator(input.sessionID)) {
return
}
if (WRITE_EDIT_TOOLS.includes(input.tool)) {
let filePath = input.callID ? pendingFilePaths.get(input.callID) : undefined
if (input.callID) {
pendingFilePaths.delete(input.callID)
}
if (!filePath) {
filePath = output.metadata?.filePath as string | undefined
}
if (filePath && !isSisyphusPath(filePath)) {
output.output = (output.output || "") + DIRECT_WORK_REMINDER
log(`[${HOOK_NAME}] Direct work reminder appended`, {
sessionID: input.sessionID,
tool: input.tool,
filePath,
})
}
return
}
if (input.tool !== "sisyphus_task") {
return
}
const outputStr = output.output && typeof output.output === "string" ? output.output : ""
const isBackgroundLaunch = outputStr.includes("Background task launched") || outputStr.includes("Background task resumed")
if (isBackgroundLaunch) {
return
}
if (output.output && typeof output.output === "string") {
const gitStats = getGitDiffStats(ctx.directory)
const fileChanges = formatFileChanges(gitStats)
const subagentSessionId = extractSessionIdFromOutput(output.output)
const boulderState = readBoulderState(ctx.directory)
if (boulderState) {
const progress = getPlanProgress(boulderState.active_plan)
if (input.sessionID && !boulderState.session_ids.includes(input.sessionID)) {
appendSessionId(ctx.directory, input.sessionID)
log(`[${HOOK_NAME}] Appended session to boulder`, {
sessionID: input.sessionID,
plan: boulderState.plan_name,
})
}
// Preserve original subagent response - critical for debugging failed tasks
const originalResponse = output.output
output.output = `
## SUBAGENT WORK COMPLETED
${fileChanges}
---
**Subagent Response:**
${originalResponse}
<system-reminder>
${buildOrchestratorReminder(boulderState.plan_name, progress, subagentSessionId)}
</system-reminder>`
log(`[${HOOK_NAME}] Output transformed for orchestrator mode (boulder)`, {
plan: boulderState.plan_name,
progress: `${progress.completed}/${progress.total}`,
fileCount: gitStats.length,
})
} else {
output.output += `\n<system-reminder>\n${buildStandaloneVerificationReminder(subagentSessionId)}\n</system-reminder>`
log(`[${HOOK_NAME}] Verification reminder appended for orchestrator`, {
sessionID: input.sessionID,
fileCount: gitStats.length,
})
}
}
},
}
}