fix: prevent agents from duplicating delegated subagent work
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
This commit is contained in:
YeonGyu-Kim
@@ -0,0 +1,118 @@
|
||||
import { describe, test, expect } from "bun:test"
|
||||
import { ATLAS_SYSTEM_PROMPT } from "./default"
|
||||
import { ATLAS_GPT_SYSTEM_PROMPT } from "./gpt"
|
||||
import { ATLAS_GEMINI_SYSTEM_PROMPT } from "./gemini"
|
||||
|
||||
describe("Atlas prompts auto-continue policy", () => {
|
||||
test("default variant should forbid asking user for continuation confirmation", () => {
|
||||
// given
|
||||
const prompt = ATLAS_SYSTEM_PROMPT
|
||||
|
||||
// when
|
||||
const lowerPrompt = prompt.toLowerCase()
|
||||
|
||||
// then
|
||||
expect(lowerPrompt).toContain("auto-continue policy")
|
||||
expect(lowerPrompt).toContain("never ask the user")
|
||||
expect(lowerPrompt).toContain("should i continue")
|
||||
expect(lowerPrompt).toContain("proceed to next task")
|
||||
expect(lowerPrompt).toContain("approval-style")
|
||||
expect(lowerPrompt).toContain("auto-continue immediately")
|
||||
})
|
||||
|
||||
test("gpt variant should forbid asking user for continuation confirmation", () => {
|
||||
// given
|
||||
const prompt = ATLAS_GPT_SYSTEM_PROMPT
|
||||
|
||||
// when
|
||||
const lowerPrompt = prompt.toLowerCase()
|
||||
|
||||
// then
|
||||
expect(lowerPrompt).toContain("auto-continue policy")
|
||||
expect(lowerPrompt).toContain("never ask the user")
|
||||
expect(lowerPrompt).toContain("should i continue")
|
||||
expect(lowerPrompt).toContain("proceed to next task")
|
||||
expect(lowerPrompt).toContain("approval-style")
|
||||
expect(lowerPrompt).toContain("auto-continue immediately")
|
||||
})
|
||||
|
||||
test("gemini variant should forbid asking user for continuation confirmation", () => {
|
||||
// given
|
||||
const prompt = ATLAS_GEMINI_SYSTEM_PROMPT
|
||||
|
||||
// when
|
||||
const lowerPrompt = prompt.toLowerCase()
|
||||
|
||||
// then
|
||||
expect(lowerPrompt).toContain("auto-continue policy")
|
||||
expect(lowerPrompt).toContain("never ask the user")
|
||||
expect(lowerPrompt).toContain("should i continue")
|
||||
expect(lowerPrompt).toContain("proceed to next task")
|
||||
expect(lowerPrompt).toContain("approval-style")
|
||||
expect(lowerPrompt).toContain("auto-continue immediately")
|
||||
})
|
||||
|
||||
test("all variants should require immediate continuation after verification passes", () => {
|
||||
// given
|
||||
const prompts = [ATLAS_SYSTEM_PROMPT, ATLAS_GPT_SYSTEM_PROMPT, ATLAS_GEMINI_SYSTEM_PROMPT]
|
||||
|
||||
// when / then
|
||||
for (const prompt of prompts) {
|
||||
const lowerPrompt = prompt.toLowerCase()
|
||||
expect(lowerPrompt).toMatch(/auto-continue immediately after verification/)
|
||||
expect(lowerPrompt).toMatch(/immediately delegate next task/)
|
||||
}
|
||||
})
|
||||
|
||||
test("all variants should define when user interaction is actually needed", () => {
|
||||
// given
|
||||
const prompts = [ATLAS_SYSTEM_PROMPT, ATLAS_GPT_SYSTEM_PROMPT, ATLAS_GEMINI_SYSTEM_PROMPT]
|
||||
|
||||
// when / then
|
||||
for (const prompt of prompts) {
|
||||
const lowerPrompt = prompt.toLowerCase()
|
||||
expect(lowerPrompt).toMatch(/only pause.*truly blocked/)
|
||||
expect(lowerPrompt).toMatch(/plan needs clarification|blocked by external/)
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe("Atlas prompts plan path consistency", () => {
|
||||
test("default variant should use .sisyphus/plans/{plan-name}.md path", () => {
|
||||
// given
|
||||
const prompt = ATLAS_SYSTEM_PROMPT
|
||||
|
||||
// when / then
|
||||
expect(prompt).toContain(".sisyphus/plans/{plan-name}.md")
|
||||
expect(prompt).not.toContain(".sisyphus/tasks/{plan-name}.yaml")
|
||||
expect(prompt).not.toContain(".sisyphus/tasks/")
|
||||
})
|
||||
|
||||
test("gpt variant should use .sisyphus/plans/{plan-name}.md path", () => {
|
||||
// given
|
||||
const prompt = ATLAS_GPT_SYSTEM_PROMPT
|
||||
|
||||
// when / then
|
||||
expect(prompt).toContain(".sisyphus/plans/{plan-name}.md")
|
||||
expect(prompt).not.toContain(".sisyphus/tasks/")
|
||||
})
|
||||
|
||||
test("gemini variant should use .sisyphus/plans/{plan-name}.md path", () => {
|
||||
// given
|
||||
const prompt = ATLAS_GEMINI_SYSTEM_PROMPT
|
||||
|
||||
// when / then
|
||||
expect(prompt).toContain(".sisyphus/plans/{plan-name}.md")
|
||||
expect(prompt).not.toContain(".sisyphus/tasks/")
|
||||
})
|
||||
|
||||
test("all variants should read plan file after verification", () => {
|
||||
// given
|
||||
const prompts = [ATLAS_SYSTEM_PROMPT, ATLAS_GPT_SYSTEM_PROMPT, ATLAS_GEMINI_SYSTEM_PROMPT]
|
||||
|
||||
// when / then
|
||||
for (const prompt of prompts) {
|
||||
expect(prompt).toMatch(/read[\s\S]*?\.sisyphus\/plans\//)
|
||||
}
|
||||
})
|
||||
})
|
||||
@@ -100,6 +100,29 @@ Every \`task()\` prompt MUST include ALL 6 sections:
|
||||
**If your prompt is under 30 lines, it's TOO SHORT.**
|
||||
</delegation_system>
|
||||
|
||||
<auto_continue>
|
||||
## AUTO-CONTINUE POLICY (STRICT)
|
||||
|
||||
**CRITICAL: NEVER ask the user "should I continue", "proceed to next task", or any approval-style questions between plan steps.**
|
||||
|
||||
**You MUST auto-continue immediately after verification passes:**
|
||||
- After any delegation completes and passes verification → Immediately delegate next task
|
||||
- Do NOT wait for user input, do NOT ask "should I continue"
|
||||
- Only pause or ask if you are truly blocked by missing information, an external dependency, or a critical failure
|
||||
|
||||
**The only time you ask the user:**
|
||||
- Plan needs clarification or modification before execution
|
||||
- Blocked by an external dependency beyond your control
|
||||
- Critical failure prevents any further progress
|
||||
|
||||
**Auto-continue examples:**
|
||||
- Task A done → Verify → Pass → Immediately start Task B
|
||||
- Task fails → Retry 3x → Still fails → Document → Move to next independent task
|
||||
- NEVER: "Should I continue to the next task?"
|
||||
|
||||
**This is NOT optional. This is core to your role as orchestrator.**
|
||||
</auto_continue>
|
||||
|
||||
<workflow>
|
||||
## Step 0: Register Tracking
|
||||
|
||||
|
||||
@@ -117,6 +117,29 @@ Every \`task()\` prompt MUST include ALL 6 sections:
|
||||
**Minimum 30 lines per delegation prompt. Under 30 lines = the subagent WILL fail.**
|
||||
</delegation_system>
|
||||
|
||||
<auto_continue>
|
||||
## AUTO-CONTINUE POLICY (STRICT)
|
||||
|
||||
**CRITICAL: NEVER ask the user "should I continue", "proceed to next task", or any approval-style questions between plan steps.**
|
||||
|
||||
**You MUST auto-continue immediately after verification passes:**
|
||||
- After any delegation completes and passes verification → Immediately delegate next task
|
||||
- Do NOT wait for user input, do NOT ask "should I continue"
|
||||
- Only pause or ask if you are truly blocked by missing information, an external dependency, or a critical failure
|
||||
|
||||
**The only time you ask the user:**
|
||||
- Plan needs clarification or modification before execution
|
||||
- Blocked by an external dependency beyond your control
|
||||
- Critical failure prevents any further progress
|
||||
|
||||
**Auto-continue examples:**
|
||||
- Task A done → Verify → Pass → Immediately start Task B
|
||||
- Task fails → Retry 3x → Still fails → Document → Move to next independent task
|
||||
- NEVER: "Should I continue to the next task?"
|
||||
|
||||
**This is NOT optional. This is core to your role as orchestrator.**
|
||||
</auto_continue>
|
||||
|
||||
<workflow>
|
||||
## Step 0: Register Tracking
|
||||
|
||||
|
||||
+25
-1
@@ -40,9 +40,10 @@ Implementation tasks are the means. Final Wave approval is the goal.
|
||||
</scope_and_design_constraints>
|
||||
|
||||
<uncertainty_and_ambiguity>
|
||||
- If a task is ambiguous or underspecified:
|
||||
- During initial plan analysis, if a task is ambiguous or underspecified:
|
||||
- Ask 1-3 precise clarifying questions, OR
|
||||
- State your interpretation explicitly and proceed with the simplest approach.
|
||||
- Once execution has started, do NOT stop to ask for continuation or approval between steps.
|
||||
- Never fabricate task details, file paths, or requirements.
|
||||
- Prefer language like "Based on the plan..." instead of absolute claims.
|
||||
- When unsure about parallelization, default to sequential execution.
|
||||
@@ -126,6 +127,29 @@ Every \`task()\` prompt MUST include ALL 6 sections:
|
||||
**Minimum 30 lines per delegation prompt.**
|
||||
</delegation_system>
|
||||
|
||||
<auto_continue>
|
||||
## AUTO-CONTINUE POLICY (STRICT)
|
||||
|
||||
**CRITICAL: NEVER ask the user "should I continue", "proceed to next task", or any approval-style questions between plan steps.**
|
||||
|
||||
**You MUST auto-continue immediately after verification passes:**
|
||||
- After any delegation completes and passes verification → Immediately delegate next task
|
||||
- Do NOT wait for user input, do NOT ask "should I continue"
|
||||
- Only pause or ask if you are truly blocked by missing information, an external dependency, or a critical failure
|
||||
|
||||
**The only time you ask the user:**
|
||||
- Plan needs clarification or modification before execution
|
||||
- Blocked by an external dependency beyond your control
|
||||
- Critical failure prevents any further progress
|
||||
|
||||
**Auto-continue examples:**
|
||||
- Task A done → Verify → Pass → Immediately start Task B
|
||||
- Task fails → Retry 3x → Still fails → Document → Move to next independent task
|
||||
- NEVER: "Should I continue to the next task?"
|
||||
|
||||
**This is NOT optional. This is core to your role as orchestrator.**
|
||||
</auto_continue>
|
||||
|
||||
<workflow>
|
||||
## Step 0: Register Tracking
|
||||
|
||||
|
||||
Reference in New Issue
Block a user