feat(agents): add GPT-5.2 optimized prompt for sisyphus-junior
Restructure sisyphus-junior agent to use model-specific prompts: - GPT models: GPT-5.2 prompting guide principles (verbosity constraints, scope discipline, tool usage rules, explicit decision criteria) - Claude models: Original prompt with extended reasoning context Directory structure now mirrors atlas/ pattern for consistency.
This commit is contained in:
YeonGyu-Kim
@@ -0,0 +1,360 @@
|
||||
import { describe, expect, test } from "bun:test"
|
||||
import {
|
||||
createSisyphusJuniorAgentWithOverrides,
|
||||
SISYPHUS_JUNIOR_DEFAULTS,
|
||||
getSisyphusJuniorPromptSource,
|
||||
buildSisyphusJuniorPrompt,
|
||||
} from "./index"
|
||||
|
||||
describe("createSisyphusJuniorAgentWithOverrides", () => {
|
||||
describe("honored fields", () => {
|
||||
test("applies model override", () => {
|
||||
// given
|
||||
const override = { model: "openai/gpt-5.2" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.model).toBe("openai/gpt-5.2")
|
||||
})
|
||||
|
||||
test("applies temperature override", () => {
|
||||
// given
|
||||
const override = { temperature: 0.5 }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.temperature).toBe(0.5)
|
||||
})
|
||||
|
||||
test("applies top_p override", () => {
|
||||
// given
|
||||
const override = { top_p: 0.9 }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.top_p).toBe(0.9)
|
||||
})
|
||||
|
||||
test("applies description override", () => {
|
||||
// given
|
||||
const override = { description: "Custom description" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.description).toBe("Custom description")
|
||||
})
|
||||
|
||||
test("applies color override", () => {
|
||||
// given
|
||||
const override = { color: "#FF0000" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.color).toBe("#FF0000")
|
||||
})
|
||||
|
||||
test("appends prompt_append to base prompt", () => {
|
||||
// given
|
||||
const override = { prompt_append: "Extra instructions here" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.prompt).toContain("You work ALONE")
|
||||
expect(result.prompt).toContain("Extra instructions here")
|
||||
})
|
||||
})
|
||||
|
||||
describe("defaults", () => {
|
||||
test("uses default model when no override", () => {
|
||||
// given
|
||||
const override = {}
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.model).toBe(SISYPHUS_JUNIOR_DEFAULTS.model)
|
||||
})
|
||||
|
||||
test("uses default temperature when no override", () => {
|
||||
// given
|
||||
const override = {}
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.temperature).toBe(SISYPHUS_JUNIOR_DEFAULTS.temperature)
|
||||
})
|
||||
})
|
||||
|
||||
describe("disable semantics", () => {
|
||||
test("disable: true causes override block to be ignored", () => {
|
||||
// given
|
||||
const override = {
|
||||
disable: true,
|
||||
model: "openai/gpt-5.2",
|
||||
temperature: 0.9,
|
||||
}
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then - defaults should be used, not the overrides
|
||||
expect(result.model).toBe(SISYPHUS_JUNIOR_DEFAULTS.model)
|
||||
expect(result.temperature).toBe(SISYPHUS_JUNIOR_DEFAULTS.temperature)
|
||||
})
|
||||
})
|
||||
|
||||
describe("constrained fields", () => {
|
||||
test("mode is forced to subagent", () => {
|
||||
// given
|
||||
const override = { mode: "primary" as const }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.mode).toBe("subagent")
|
||||
})
|
||||
|
||||
test("prompt override is ignored (discipline text preserved)", () => {
|
||||
// given
|
||||
const override = { prompt: "Completely new prompt that replaces everything" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.prompt).toContain("You work ALONE")
|
||||
expect(result.prompt).not.toBe("Completely new prompt that replaces everything")
|
||||
})
|
||||
})
|
||||
|
||||
describe("tool safety (task/delegate_task blocked, call_omo_agent allowed)", () => {
|
||||
test("task and delegate_task remain blocked, call_omo_agent is allowed via tools format", () => {
|
||||
// given
|
||||
const override = {
|
||||
tools: {
|
||||
task: true,
|
||||
delegate_task: true,
|
||||
call_omo_agent: true,
|
||||
read: true,
|
||||
},
|
||||
}
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
const tools = result.tools as Record<string, boolean> | undefined
|
||||
const permission = result.permission as Record<string, string> | undefined
|
||||
if (tools) {
|
||||
expect(tools.task).toBe(false)
|
||||
expect(tools.delegate_task).toBe(false)
|
||||
// call_omo_agent is NOW ALLOWED for subagents to spawn explore/librarian
|
||||
expect(tools.call_omo_agent).toBe(true)
|
||||
expect(tools.read).toBe(true)
|
||||
}
|
||||
if (permission) {
|
||||
expect(permission.task).toBe("deny")
|
||||
expect(permission.delegate_task).toBe("deny")
|
||||
// call_omo_agent is NOW ALLOWED for subagents to spawn explore/librarian
|
||||
expect(permission.call_omo_agent).toBe("allow")
|
||||
}
|
||||
})
|
||||
|
||||
test("task and delegate_task remain blocked when using permission format override", () => {
|
||||
// given
|
||||
const override = {
|
||||
permission: {
|
||||
task: "allow",
|
||||
delegate_task: "allow",
|
||||
call_omo_agent: "allow",
|
||||
read: "allow",
|
||||
},
|
||||
} as { permission: Record<string, string> }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override as Parameters<typeof createSisyphusJuniorAgentWithOverrides>[0])
|
||||
|
||||
// then - task/delegate_task blocked, but call_omo_agent allowed for explore/librarian spawning
|
||||
const tools = result.tools as Record<string, boolean> | undefined
|
||||
const permission = result.permission as Record<string, string> | undefined
|
||||
if (tools) {
|
||||
expect(tools.task).toBe(false)
|
||||
expect(tools.delegate_task).toBe(false)
|
||||
expect(tools.call_omo_agent).toBe(true)
|
||||
}
|
||||
if (permission) {
|
||||
expect(permission.task).toBe("deny")
|
||||
expect(permission.delegate_task).toBe("deny")
|
||||
expect(permission.call_omo_agent).toBe("allow")
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe("prompt composition", () => {
|
||||
test("base prompt contains discipline constraints", () => {
|
||||
// given
|
||||
const override = {}
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.prompt).toContain("Sisyphus-Junior")
|
||||
expect(result.prompt).toContain("You work ALONE")
|
||||
})
|
||||
|
||||
test("Claude model uses default prompt with BLOCKED ACTIONS section", () => {
|
||||
// given
|
||||
const override = { model: "anthropic/claude-sonnet-4-5" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.prompt).toContain("BLOCKED ACTIONS")
|
||||
expect(result.prompt).not.toContain("<blocked_actions>")
|
||||
})
|
||||
|
||||
test("GPT model uses GPT-optimized prompt with blocked_actions section", () => {
|
||||
// given
|
||||
const override = { model: "openai/gpt-5.2" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
expect(result.prompt).toContain("<blocked_actions>")
|
||||
expect(result.prompt).toContain("<output_verbosity_spec>")
|
||||
expect(result.prompt).toContain("<scope_and_design_constraints>")
|
||||
})
|
||||
|
||||
test("prompt_append is added after base prompt", () => {
|
||||
// given
|
||||
const override = { prompt_append: "CUSTOM_MARKER_FOR_TEST" }
|
||||
|
||||
// when
|
||||
const result = createSisyphusJuniorAgentWithOverrides(override)
|
||||
|
||||
// then
|
||||
const baseEndIndex = result.prompt!.indexOf("Dense > verbose.")
|
||||
const appendIndex = result.prompt!.indexOf("CUSTOM_MARKER_FOR_TEST")
|
||||
expect(baseEndIndex).not.toBe(-1)
|
||||
expect(appendIndex).toBeGreaterThan(baseEndIndex)
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe("getSisyphusJuniorPromptSource", () => {
|
||||
test("returns 'gpt' for OpenAI models", () => {
|
||||
// given
|
||||
const model = "openai/gpt-5.2"
|
||||
|
||||
// when
|
||||
const source = getSisyphusJuniorPromptSource(model)
|
||||
|
||||
// then
|
||||
expect(source).toBe("gpt")
|
||||
})
|
||||
|
||||
test("returns 'gpt' for GitHub Copilot GPT models", () => {
|
||||
// given
|
||||
const model = "github-copilot/gpt-4o"
|
||||
|
||||
// when
|
||||
const source = getSisyphusJuniorPromptSource(model)
|
||||
|
||||
// then
|
||||
expect(source).toBe("gpt")
|
||||
})
|
||||
|
||||
test("returns 'default' for Claude models", () => {
|
||||
// given
|
||||
const model = "anthropic/claude-sonnet-4-5"
|
||||
|
||||
// when
|
||||
const source = getSisyphusJuniorPromptSource(model)
|
||||
|
||||
// then
|
||||
expect(source).toBe("default")
|
||||
})
|
||||
|
||||
test("returns 'default' for undefined model", () => {
|
||||
// given
|
||||
const model = undefined
|
||||
|
||||
// when
|
||||
const source = getSisyphusJuniorPromptSource(model)
|
||||
|
||||
// then
|
||||
expect(source).toBe("default")
|
||||
})
|
||||
})
|
||||
|
||||
describe("buildSisyphusJuniorPrompt", () => {
|
||||
test("GPT model prompt contains GPT-5.2 specific sections", () => {
|
||||
// given
|
||||
const model = "openai/gpt-5.2"
|
||||
|
||||
// when
|
||||
const prompt = buildSisyphusJuniorPrompt(model, false)
|
||||
|
||||
// then
|
||||
expect(prompt).toContain("<identity>")
|
||||
expect(prompt).toContain("<output_verbosity_spec>")
|
||||
expect(prompt).toContain("<scope_and_design_constraints>")
|
||||
expect(prompt).toContain("<tool_usage_rules>")
|
||||
})
|
||||
|
||||
test("Claude model prompt contains Claude-specific sections", () => {
|
||||
// given
|
||||
const model = "anthropic/claude-sonnet-4-5"
|
||||
|
||||
// when
|
||||
const prompt = buildSisyphusJuniorPrompt(model, false)
|
||||
|
||||
// then
|
||||
expect(prompt).toContain("<Role>")
|
||||
expect(prompt).toContain("<Critical_Constraints>")
|
||||
expect(prompt).toContain("BLOCKED ACTIONS")
|
||||
})
|
||||
|
||||
test("useTaskSystem=true includes Task_Discipline for GPT", () => {
|
||||
// given
|
||||
const model = "openai/gpt-5.2"
|
||||
|
||||
// when
|
||||
const prompt = buildSisyphusJuniorPrompt(model, true)
|
||||
|
||||
// then
|
||||
expect(prompt).toContain("<task_discipline_spec>")
|
||||
expect(prompt).toContain("TaskCreate")
|
||||
})
|
||||
|
||||
test("useTaskSystem=false includes Todo_Discipline for Claude", () => {
|
||||
// given
|
||||
const model = "anthropic/claude-sonnet-4-5"
|
||||
|
||||
// when
|
||||
const prompt = buildSisyphusJuniorPrompt(model, false)
|
||||
|
||||
// then
|
||||
expect(prompt).toContain("<Todo_Discipline>")
|
||||
expect(prompt).toContain("todowrite")
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user