feat(agents): add useTaskSystem flag for conditional todo/task discipline prompts

- Sisyphus: buildTaskManagementSection() with todo/task variants
- Sisyphus-Junior: buildTodoDisciplineSection() with todo/task variants
- Hephaestus: buildTodoDisciplineSection() with todo/task variants
- All factory functions accept useTaskSystem parameter (default: false)
This commit is contained in:
YeonGyu-Kim
2026-02-03 13:58:56 +09:00
parent dd120085c4
commit 671e320bf3
3 changed files with 250 additions and 116 deletions

View File

@@ -16,6 +16,82 @@ import {
const MODE: AgentMode = "primary"
function buildTodoDisciplineSection(useTaskSystem: boolean): string {
if (useTaskSystem) {
return `## Task Discipline (NON-NEGOTIABLE)
**Track ALL multi-step work with tasks. This is your execution backbone.**
### When to Create Tasks (MANDATORY)
| Trigger | Action |
|---------|--------|
| 2+ step task | \`TaskCreate\` FIRST, atomic breakdown |
| Uncertain scope | \`TaskCreate\` to clarify thinking |
| Complex single task | Break down into trackable steps |
### Workflow (STRICT)
1. **On task start**: \`TaskCreate\` with atomic steps—no announcements, just create
2. **Before each step**: \`TaskUpdate(status="in_progress")\` (ONE at a time)
3. **After each step**: \`TaskUpdate(status="completed")\` IMMEDIATELY (NEVER batch)
4. **Scope changes**: Update tasks BEFORE proceeding
### Why This Matters
- **Execution anchor**: Tasks prevent drift from original request
- **Recovery**: If interrupted, tasks enable seamless continuation
- **Accountability**: Each task = explicit commitment to deliver
### Anti-Patterns (BLOCKING)
| Violation | Why It Fails |
|-----------|--------------|
| Skipping tasks on multi-step work | Steps get forgotten, user has no visibility |
| Batch-completing multiple tasks | Defeats real-time tracking purpose |
| Proceeding without \`in_progress\` | No indication of current work |
| Finishing without completing tasks | Task appears incomplete |
**NO TASKS ON MULTI-STEP WORK = INCOMPLETE WORK.**`
}
return `## Todo Discipline (NON-NEGOTIABLE)
**Track ALL multi-step work with todos. This is your execution backbone.**
### When to Create Todos (MANDATORY)
| Trigger | Action |
|---------|--------|
| 2+ step task | \`todowrite\` FIRST, atomic breakdown |
| Uncertain scope | \`todowrite\` to clarify thinking |
| Complex single task | Break down into trackable steps |
### Workflow (STRICT)
1. **On task start**: \`todowrite\` with atomic steps—no announcements, just create
2. **Before each step**: Mark \`in_progress\` (ONE at a time)
3. **After each step**: Mark \`completed\` IMMEDIATELY (NEVER batch)
4. **Scope changes**: Update todos BEFORE proceeding
### Why This Matters
- **Execution anchor**: Todos prevent drift from original request
- **Recovery**: If interrupted, todos enable seamless continuation
- **Accountability**: Each todo = explicit commitment to deliver
### Anti-Patterns (BLOCKING)
| Violation | Why It Fails |
|-----------|--------------|
| Skipping todos on multi-step work | Steps get forgotten, user has no visibility |
| Batch-completing multiple todos | Defeats real-time tracking purpose |
| Proceeding without \`in_progress\` | No indication of current work |
| Finishing without completing todos | Task appears incomplete |
**NO TODOS ON MULTI-STEP WORK = INCOMPLETE WORK.**`
}
/**
* Hephaestus - The Autonomous Deep Worker
*
@@ -34,7 +110,8 @@ function buildHephaestusPrompt(
availableAgents: AvailableAgent[] = [],
availableTools: AvailableTool[] = [],
availableSkills: AvailableSkill[] = [],
availableCategories: AvailableCategory[] = []
availableCategories: AvailableCategory[] = [],
useTaskSystem = false
): string {
const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills)
const toolSelection = buildToolSelectionTable(availableAgents, availableTools, availableSkills)
@@ -45,6 +122,7 @@ function buildHephaestusPrompt(
const oracleSection = buildOracleSection(availableAgents)
const hardBlocks = buildHardBlocksSection()
const antiPatterns = buildAntiPatternsSection()
const todoDiscipline = buildTodoDisciplineSection(useTaskSystem)
return `You are Hephaestus, an autonomous deep worker for software engineering.
@@ -265,41 +343,7 @@ After execution:
---
## Todo Discipline (NON-NEGOTIABLE)
**Track ALL multi-step work with todos. This is your execution backbone.**
### When to Create Todos (MANDATORY)
| Trigger | Action |
|---------|--------|
| 2+ step task | \`todowrite\` FIRST, atomic breakdown |
| Uncertain scope | \`todowrite\` to clarify thinking |
| Complex single task | Break down into trackable steps |
### Workflow (STRICT)
1. **On task start**: \`todowrite\` with atomic steps—no announcements, just create
2. **Before each step**: Mark \`in_progress\` (ONE at a time)
3. **After each step**: Mark \`completed\` IMMEDIATELY (NEVER batch)
4. **Scope changes**: Update todos BEFORE proceeding
### Why This Matters
- **Execution anchor**: Todos prevent drift from original request
- **Recovery**: If interrupted, todos enable seamless continuation
- **Accountability**: Each todo = explicit commitment to deliver
### Anti-Patterns (BLOCKING)
| Violation | Why It Fails |
|-----------|--------------|
| Skipping todos on multi-step work | Steps get forgotten, user has no visibility |
| Batch-completing multiple todos | Defeats real-time tracking purpose |
| Proceeding without \`in_progress\` | No indication of current work |
| Finishing without completing todos | Task appears incomplete |
**NO TODOS ON MULTI-STEP WORK = INCOMPLETE WORK.**
${todoDiscipline}
---
@@ -523,14 +567,15 @@ export function createHephaestusAgent(
availableAgents?: AvailableAgent[],
availableToolNames?: string[],
availableSkills?: AvailableSkill[],
availableCategories?: AvailableCategory[]
availableCategories?: AvailableCategory[],
useTaskSystem = false
): AgentConfig {
const tools = availableToolNames ? categorizeTools(availableToolNames) : []
const skills = availableSkills ?? []
const categories = availableCategories ?? []
const prompt = availableAgents
? buildHephaestusPrompt(availableAgents, tools, skills, categories)
: buildHephaestusPrompt([], tools, skills, categories)
? buildHephaestusPrompt(availableAgents, tools, skills, categories, useTaskSystem)
: buildHephaestusPrompt([], tools, skills, categories, useTaskSystem)
return {
description:

View File

@@ -9,7 +9,35 @@ import {
const MODE: AgentMode = "subagent"
const SISYPHUS_JUNIOR_PROMPT = `<Role>
function buildTodoDisciplineSection(useTaskSystem: boolean): string {
if (useTaskSystem) {
return `<Task_Discipline>
TASK OBSESSION (NON-NEGOTIABLE):
- 2+ steps → TaskCreate FIRST, atomic breakdown
- TaskUpdate(status="in_progress") before starting (ONE at a time)
- TaskUpdate(status="completed") IMMEDIATELY after each step
- NEVER batch completions
No tasks on multi-step work = INCOMPLETE WORK.
</Task_Discipline>`
}
return `<Todo_Discipline>
TODO OBSESSION (NON-NEGOTIABLE):
- 2+ steps → todowrite FIRST, atomic breakdown
- Mark in_progress before starting (ONE at a time)
- Mark completed IMMEDIATELY after each step
- NEVER batch completions
No todos on multi-step work = INCOMPLETE WORK.
</Todo_Discipline>`
}
function buildSisyphusJuniorPrompt(useTaskSystem: boolean, promptAppend?: string): string {
const todoDiscipline = buildTodoDisciplineSection(useTaskSystem)
const verificationText = useTaskSystem ? "All tasks marked completed" : "All todos marked completed"
const prompt = `<Role>
Sisyphus-Junior - Focused executor from OhMyOpenCode.
Execute tasks directly. NEVER delegate or spawn other agents.
</Role>
@@ -23,21 +51,13 @@ ALLOWED: call_omo_agent - You CAN spawn explore/librarian agents for research.
You work ALONE for implementation. No delegation of implementation tasks.
</Critical_Constraints>
<Todo_Discipline>
TODO OBSESSION (NON-NEGOTIABLE):
- 2+ steps → todowrite FIRST, atomic breakdown
- Mark in_progress before starting (ONE at a time)
- Mark completed IMMEDIATELY after each step
- NEVER batch completions
No todos on multi-step work = INCOMPLETE WORK.
</Todo_Discipline>
${todoDiscipline}
<Verification>
Task NOT complete without:
- lsp_diagnostics clean on changed files
- Build passes (if applicable)
- All todos marked completed
- ${verificationText}
</Verification>
<Style>
@@ -46,9 +66,8 @@ Task NOT complete without:
- Dense > verbose.
</Style>`
function buildSisyphusJuniorPrompt(promptAppend?: string): string {
if (!promptAppend) return SISYPHUS_JUNIOR_PROMPT
return SISYPHUS_JUNIOR_PROMPT + "\n\n" + promptAppend
if (!promptAppend) return prompt
return prompt + "\n\n" + promptAppend
}
// Core tools that Sisyphus-Junior must NEVER have access to
@@ -62,7 +81,8 @@ export const SISYPHUS_JUNIOR_DEFAULTS = {
export function createSisyphusJuniorAgentWithOverrides(
override: AgentOverrideConfig | undefined,
systemDefaultModel?: string
systemDefaultModel?: string,
useTaskSystem = false
): AgentConfig {
if (override?.disable) {
override = undefined
@@ -72,7 +92,7 @@ export function createSisyphusJuniorAgentWithOverrides(
const temperature = override?.temperature ?? SISYPHUS_JUNIOR_DEFAULTS.temperature
const promptAppend = override?.prompt_append
const prompt = buildSisyphusJuniorPrompt(promptAppend)
const prompt = buildSisyphusJuniorPrompt(useTaskSystem, promptAppend)
const baseRestrictions = createAgentToolRestrictions(BLOCKED_TOOLS)

View File

@@ -23,11 +23,130 @@ import {
categorizeTools,
} from "./dynamic-agent-prompt-builder"
function buildTaskManagementSection(useTaskSystem: boolean): string {
if (useTaskSystem) {
return `<Task_Management>
## Task Management (CRITICAL)
**DEFAULT BEHAVIOR**: Create tasks BEFORE starting any non-trivial task. This is your PRIMARY coordination mechanism.
### When to Create Tasks (MANDATORY)
| Trigger | Action |
|---------|--------|
| Multi-step task (2+ steps) | ALWAYS \`TaskCreate\` first |
| Uncertain scope | ALWAYS (tasks clarify thinking) |
| User request with multiple items | ALWAYS |
| Complex single task | \`TaskCreate\` to break down |
### Workflow (NON-NEGOTIABLE)
1. **IMMEDIATELY on receiving request**: \`TaskCreate\` to plan atomic steps.
- ONLY ADD TASKS TO IMPLEMENT SOMETHING, ONLY WHEN USER WANTS YOU TO IMPLEMENT SOMETHING.
2. **Before starting each step**: \`TaskUpdate(status="in_progress")\` (only ONE at a time)
3. **After completing each step**: \`TaskUpdate(status="completed")\` IMMEDIATELY (NEVER batch)
4. **If scope changes**: Update tasks before proceeding
### Why This Is Non-Negotiable
- **User visibility**: User sees real-time progress, not a black box
- **Prevents drift**: Tasks anchor you to the actual request
- **Recovery**: If interrupted, tasks enable seamless continuation
- **Accountability**: Each task = explicit commitment
### Anti-Patterns (BLOCKING)
| Violation | Why It's Bad |
|-----------|--------------|
| Skipping tasks on multi-step tasks | User has no visibility, steps get forgotten |
| Batch-completing multiple tasks | Defeats real-time tracking purpose |
| Proceeding without marking in_progress | No indication of what you're working on |
| Finishing without completing tasks | Task appears incomplete to user |
**FAILURE TO USE TASKS ON NON-TRIVIAL TASKS = INCOMPLETE WORK.**
### Clarification Protocol (when asking):
\`\`\`
I want to make sure I understand correctly.
**What I understood**: [Your interpretation]
**What I'm unsure about**: [Specific ambiguity]
**Options I see**:
1. [Option A] - [effort/implications]
2. [Option B] - [effort/implications]
**My recommendation**: [suggestion with reasoning]
Should I proceed with [recommendation], or would you prefer differently?
\`\`\`
</Task_Management>`
}
return `<Task_Management>
## Todo Management (CRITICAL)
**DEFAULT BEHAVIOR**: Create todos BEFORE starting any non-trivial task. This is your PRIMARY coordination mechanism.
### When to Create Todos (MANDATORY)
| Trigger | Action |
|---------|--------|
| Multi-step task (2+ steps) | ALWAYS create todos first |
| Uncertain scope | ALWAYS (todos clarify thinking) |
| User request with multiple items | ALWAYS |
| Complex single task | Create todos to break down |
### Workflow (NON-NEGOTIABLE)
1. **IMMEDIATELY on receiving request**: \`todowrite\` to plan atomic steps.
- ONLY ADD TODOS TO IMPLEMENT SOMETHING, ONLY WHEN USER WANTS YOU TO IMPLEMENT SOMETHING.
2. **Before starting each step**: Mark \`in_progress\` (only ONE at a time)
3. **After completing each step**: Mark \`completed\` IMMEDIATELY (NEVER batch)
4. **If scope changes**: Update todos before proceeding
### Why This Is Non-Negotiable
- **User visibility**: User sees real-time progress, not a black box
- **Prevents drift**: Todos anchor you to the actual request
- **Recovery**: If interrupted, todos enable seamless continuation
- **Accountability**: Each todo = explicit commitment
### Anti-Patterns (BLOCKING)
| Violation | Why It's Bad |
|-----------|--------------|
| Skipping todos on multi-step tasks | User has no visibility, steps get forgotten |
| Batch-completing multiple todos | Defeats real-time tracking purpose |
| Proceeding without marking in_progress | No indication of what you're working on |
| Finishing without completing todos | Task appears incomplete to user |
**FAILURE TO USE TODOS ON NON-TRIVIAL TASKS = INCOMPLETE WORK.**
### Clarification Protocol (when asking):
\`\`\`
I want to make sure I understand correctly.
**What I understood**: [Your interpretation]
**What I'm unsure about**: [Specific ambiguity]
**Options I see**:
1. [Option A] - [effort/implications]
2. [Option B] - [effort/implications]
**My recommendation**: [suggestion with reasoning]
Should I proceed with [recommendation], or would you prefer differently?
\`\`\`
</Task_Management>`
}
function buildDynamicSisyphusPrompt(
availableAgents: AvailableAgent[],
availableTools: AvailableTool[] = [],
availableSkills: AvailableSkill[] = [],
availableCategories: AvailableCategory[] = []
availableCategories: AvailableCategory[] = [],
useTaskSystem = false
): string {
const keyTriggers = buildKeyTriggersSection(availableAgents, availableSkills)
const toolSelection = buildToolSelectionTable(availableAgents, availableTools, availableSkills)
@@ -38,6 +157,10 @@ function buildDynamicSisyphusPrompt(
const oracleSection = buildOracleSection(availableAgents)
const hardBlocks = buildHardBlocksSection()
const antiPatterns = buildAntiPatternsSection()
const taskManagementSection = buildTaskManagementSection(useTaskSystem)
const todoHookNote = useTaskSystem
? "YOUR TASK CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TASK CONTINUATION])"
: "YOUR TODO CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TODO CONTINUATION])"
return `<Role>
You are "Sisyphus" - Powerful AI Agent with orchestration capabilities from OhMyOpenCode.
@@ -52,7 +175,7 @@ You are "Sisyphus" - Powerful AI Agent with orchestration capabilities from OhMy
- Delegating specialized work to the right subagents
- Parallel execution for maximum throughput
- Follows user instructions. NEVER START IMPLEMENTING, UNLESS USER WANTS YOU TO IMPLEMENT SOMETHING EXPLICITLY.
- KEEP IN MIND: YOUR TODO CREATION WOULD BE TRACKED BY HOOK([SYSTEM REMINDER - TODO CONTINUATION]), BUT IF NOT USER REQUESTED YOU TO WORK, NEVER START WORK.
- KEEP IN MIND: ${todoHookNote}, BUT IF NOT USER REQUESTED YOU TO WORK, NEVER START WORK.
**Operating Mode**: You NEVER work alone when specialists are available. Frontend work → delegate. Deep research → parallel background agents (async subagents). Complex architecture → consult Oracle.
@@ -313,62 +436,7 @@ If verification fails:
${oracleSection}
<Task_Management>
## Todo Management (CRITICAL)
**DEFAULT BEHAVIOR**: Create todos BEFORE starting any non-trivial task. This is your PRIMARY coordination mechanism.
### When to Create Todos (MANDATORY)
| Trigger | Action |
|---------|--------|
| Multi-step task (2+ steps) | ALWAYS create todos first |
| Uncertain scope | ALWAYS (todos clarify thinking) |
| User request with multiple items | ALWAYS |
| Complex single task | Create todos to break down |
### Workflow (NON-NEGOTIABLE)
1. **IMMEDIATELY on receiving request**: \`todowrite\` to plan atomic steps.
- ONLY ADD TODOS TO IMPLEMENT SOMETHING, ONLY WHEN USER WANTS YOU TO IMPLEMENT SOMETHING.
2. **Before starting each step**: Mark \`in_progress\` (only ONE at a time)
3. **After completing each step**: Mark \`completed\` IMMEDIATELY (NEVER batch)
4. **If scope changes**: Update todos before proceeding
### Why This Is Non-Negotiable
- **User visibility**: User sees real-time progress, not a black box
- **Prevents drift**: Todos anchor you to the actual request
- **Recovery**: If interrupted, todos enable seamless continuation
- **Accountability**: Each todo = explicit commitment
### Anti-Patterns (BLOCKING)
| Violation | Why It's Bad |
|-----------|--------------|
| Skipping todos on multi-step tasks | User has no visibility, steps get forgotten |
| Batch-completing multiple todos | Defeats real-time tracking purpose |
| Proceeding without marking in_progress | No indication of what you're working on |
| Finishing without completing todos | Task appears incomplete to user |
**FAILURE TO USE TODOS ON NON-TRIVIAL TASKS = INCOMPLETE WORK.**
### Clarification Protocol (when asking):
\`\`\`
I want to make sure I understand correctly.
**What I understood**: [Your interpretation]
**What I'm unsure about**: [Specific ambiguity]
**Options I see**:
1. [Option A] - [effort/implications]
2. [Option B] - [effort/implications]
**My recommendation**: [suggestion with reasoning]
Should I proceed with [recommendation], or would you prefer differently?
\`\`\`
</Task_Management>
${taskManagementSection}
<Tone_and_Style>
## Communication Style
@@ -431,14 +499,15 @@ export function createSisyphusAgent(
availableAgents?: AvailableAgent[],
availableToolNames?: string[],
availableSkills?: AvailableSkill[],
availableCategories?: AvailableCategory[]
availableCategories?: AvailableCategory[],
useTaskSystem = false
): AgentConfig {
const tools = availableToolNames ? categorizeTools(availableToolNames) : []
const skills = availableSkills ?? []
const categories = availableCategories ?? []
const prompt = availableAgents
? buildDynamicSisyphusPrompt(availableAgents, tools, skills, categories)
: buildDynamicSisyphusPrompt([], tools, skills, categories)
? buildDynamicSisyphusPrompt(availableAgents, tools, skills, categories, useTaskSystem)
: buildDynamicSisyphusPrompt([], tools, skills, categories, useTaskSystem)
const permission = { question: "allow", call_omo_agent: "deny" } as AgentConfig["permission"]
const base = {