62448c1148
When user types '/start-work my-plan ultrawork', the hook now: 1. Extracts plan name from <user-request> section 2. Strips ultrawork/ulw keywords from the plan name 3. Searches for matching plan (exact then partial match) 4. Uses the matched plan instead of resuming stale boulder state This fixes the bug where '/start-work [PLAN] ultrawork' would: - Include 'ultrawork' as part of the plan name argument - Ignore the explicit plan and resume an old stale plan from boulder.json Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
384 lines
12 KiB
TypeScript
384 lines
12 KiB
TypeScript
import { describe, expect, test, beforeEach, afterEach } from "bun:test"
|
|
import { existsSync, mkdirSync, rmSync, writeFileSync } from "node:fs"
|
|
import { join } from "node:path"
|
|
import { tmpdir, homedir } from "node:os"
|
|
import { createStartWorkHook } from "./index"
|
|
import {
|
|
writeBoulderState,
|
|
clearBoulderState,
|
|
} from "../../features/boulder-state"
|
|
import type { BoulderState } from "../../features/boulder-state"
|
|
|
|
describe("start-work hook", () => {
|
|
const TEST_DIR = join(tmpdir(), "start-work-test-" + Date.now())
|
|
const SISYPHUS_DIR = join(TEST_DIR, ".sisyphus")
|
|
|
|
function createMockPluginInput() {
|
|
return {
|
|
directory: TEST_DIR,
|
|
client: {},
|
|
} as Parameters<typeof createStartWorkHook>[0]
|
|
}
|
|
|
|
beforeEach(() => {
|
|
if (!existsSync(TEST_DIR)) {
|
|
mkdirSync(TEST_DIR, { recursive: true })
|
|
}
|
|
if (!existsSync(SISYPHUS_DIR)) {
|
|
mkdirSync(SISYPHUS_DIR, { recursive: true })
|
|
}
|
|
clearBoulderState(TEST_DIR)
|
|
})
|
|
|
|
afterEach(() => {
|
|
clearBoulderState(TEST_DIR)
|
|
if (existsSync(TEST_DIR)) {
|
|
rmSync(TEST_DIR, { recursive: true, force: true })
|
|
}
|
|
})
|
|
|
|
describe("chat.message handler", () => {
|
|
test("should ignore non-start-work commands", async () => {
|
|
// #given - hook and non-start-work message
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [{ type: "text", text: "Just a regular message" }],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - output should be unchanged
|
|
expect(output.parts[0].text).toBe("Just a regular message")
|
|
})
|
|
|
|
test("should detect start-work command via session-context tag", async () => {
|
|
// #given - hook and start-work message
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: "<session-context>Some context here</session-context>",
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - output should be modified with context info
|
|
expect(output.parts[0].text).toContain("---")
|
|
})
|
|
|
|
test("should inject resume info when existing boulder state found", async () => {
|
|
// #given - existing boulder state with incomplete plan
|
|
const planPath = join(TEST_DIR, "test-plan.md")
|
|
writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [x] Task 2")
|
|
|
|
const state: BoulderState = {
|
|
active_plan: planPath,
|
|
started_at: "2026-01-02T10:00:00Z",
|
|
session_ids: ["session-1"],
|
|
plan_name: "test-plan",
|
|
}
|
|
writeBoulderState(TEST_DIR, state)
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [{ type: "text", text: "Start Sisyphus work session" }],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should show resuming status
|
|
expect(output.parts[0].text).toContain("RESUMING")
|
|
expect(output.parts[0].text).toContain("test-plan")
|
|
})
|
|
|
|
test("should replace $SESSION_ID placeholder", async () => {
|
|
// #given - hook and message with placeholder
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: "Start Sisyphus work session\nSession: $SESSION_ID",
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "ses-abc123" },
|
|
output
|
|
)
|
|
|
|
// #then - placeholder should be replaced
|
|
expect(output.parts[0].text).toContain("ses-abc123")
|
|
expect(output.parts[0].text).not.toContain("$SESSION_ID")
|
|
})
|
|
|
|
test("should replace $TIMESTAMP placeholder", async () => {
|
|
// #given - hook and message with placeholder
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: "Start Sisyphus work session\nTime: $TIMESTAMP",
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - placeholder should be replaced with ISO timestamp
|
|
expect(output.parts[0].text).not.toContain("$TIMESTAMP")
|
|
expect(output.parts[0].text).toMatch(/\d{4}-\d{2}-\d{2}T/)
|
|
})
|
|
|
|
test("should auto-select when only one incomplete plan among multiple plans", async () => {
|
|
// #given - multiple plans but only one incomplete
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
// Plan 1: complete (all checked)
|
|
const plan1Path = join(plansDir, "plan-complete.md")
|
|
writeFileSync(plan1Path, "# Plan Complete\n- [x] Task 1\n- [x] Task 2")
|
|
|
|
// Plan 2: incomplete (has unchecked)
|
|
const plan2Path = join(plansDir, "plan-incomplete.md")
|
|
writeFileSync(plan2Path, "# Plan Incomplete\n- [ ] Task 1\n- [x] Task 2")
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [{ type: "text", text: "Start Sisyphus work session" }],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should auto-select the incomplete plan, not ask user
|
|
expect(output.parts[0].text).toContain("Auto-Selected Plan")
|
|
expect(output.parts[0].text).toContain("plan-incomplete")
|
|
expect(output.parts[0].text).not.toContain("Multiple Plans Found")
|
|
})
|
|
|
|
test("should wrap multiple plans message in system-reminder tag", async () => {
|
|
// #given - multiple incomplete plans
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
const plan1Path = join(plansDir, "plan-a.md")
|
|
writeFileSync(plan1Path, "# Plan A\n- [ ] Task 1")
|
|
|
|
const plan2Path = join(plansDir, "plan-b.md")
|
|
writeFileSync(plan2Path, "# Plan B\n- [ ] Task 2")
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [{ type: "text", text: "Start Sisyphus work session" }],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should use system-reminder tag format
|
|
expect(output.parts[0].text).toContain("<system-reminder>")
|
|
expect(output.parts[0].text).toContain("</system-reminder>")
|
|
expect(output.parts[0].text).toContain("Multiple Plans Found")
|
|
})
|
|
|
|
test("should use 'ask user' prompt style for multiple plans", async () => {
|
|
// #given - multiple incomplete plans
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
const plan1Path = join(plansDir, "plan-x.md")
|
|
writeFileSync(plan1Path, "# Plan X\n- [ ] Task 1")
|
|
|
|
const plan2Path = join(plansDir, "plan-y.md")
|
|
writeFileSync(plan2Path, "# Plan Y\n- [ ] Task 2")
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [{ type: "text", text: "Start Sisyphus work session" }],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should prompt agent to ask user, not ask directly
|
|
expect(output.parts[0].text).toContain("Ask the user")
|
|
expect(output.parts[0].text).not.toContain("Which plan would you like to work on?")
|
|
})
|
|
|
|
test("should select explicitly specified plan name from user-request, ignoring existing boulder state", async () => {
|
|
// #given - existing boulder state pointing to old plan
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
// Old plan (in boulder state)
|
|
const oldPlanPath = join(plansDir, "old-plan.md")
|
|
writeFileSync(oldPlanPath, "# Old Plan\n- [ ] Old Task 1")
|
|
|
|
// New plan (user wants this one)
|
|
const newPlanPath = join(plansDir, "new-plan.md")
|
|
writeFileSync(newPlanPath, "# New Plan\n- [ ] New Task 1")
|
|
|
|
// Set up stale boulder state pointing to old plan
|
|
const staleState: BoulderState = {
|
|
active_plan: oldPlanPath,
|
|
started_at: "2026-01-01T10:00:00Z",
|
|
session_ids: ["old-session"],
|
|
plan_name: "old-plan",
|
|
}
|
|
writeBoulderState(TEST_DIR, staleState)
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: `Start Sisyphus work session
|
|
<user-request>
|
|
new-plan
|
|
</user-request>`,
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when - user explicitly specifies new-plan
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should select new-plan, NOT resume old-plan
|
|
expect(output.parts[0].text).toContain("new-plan")
|
|
expect(output.parts[0].text).not.toContain("RESUMING")
|
|
expect(output.parts[0].text).not.toContain("old-plan")
|
|
})
|
|
|
|
test("should strip ultrawork/ulw keywords from plan name argument", async () => {
|
|
// #given - plan with ultrawork keyword in user-request
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
const planPath = join(plansDir, "my-feature-plan.md")
|
|
writeFileSync(planPath, "# My Feature Plan\n- [ ] Task 1")
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: `Start Sisyphus work session
|
|
<user-request>
|
|
my-feature-plan ultrawork
|
|
</user-request>`,
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when - user specifies plan with ultrawork keyword
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should find plan without ultrawork suffix
|
|
expect(output.parts[0].text).toContain("my-feature-plan")
|
|
expect(output.parts[0].text).toContain("Auto-Selected Plan")
|
|
})
|
|
|
|
test("should strip ulw keyword from plan name argument", async () => {
|
|
// #given - plan with ulw keyword in user-request
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
const planPath = join(plansDir, "api-refactor.md")
|
|
writeFileSync(planPath, "# API Refactor\n- [ ] Task 1")
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: `Start Sisyphus work session
|
|
<user-request>
|
|
api-refactor ulw
|
|
</user-request>`,
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should find plan without ulw suffix
|
|
expect(output.parts[0].text).toContain("api-refactor")
|
|
expect(output.parts[0].text).toContain("Auto-Selected Plan")
|
|
})
|
|
|
|
test("should match plan by partial name", async () => {
|
|
// #given - user specifies partial plan name
|
|
const plansDir = join(TEST_DIR, ".sisyphus", "plans")
|
|
mkdirSync(plansDir, { recursive: true })
|
|
|
|
const planPath = join(plansDir, "2026-01-15-feature-implementation.md")
|
|
writeFileSync(planPath, "# Feature Implementation\n- [ ] Task 1")
|
|
|
|
const hook = createStartWorkHook(createMockPluginInput())
|
|
const output = {
|
|
parts: [
|
|
{
|
|
type: "text",
|
|
text: `Start Sisyphus work session
|
|
<user-request>
|
|
feature-implementation
|
|
</user-request>`,
|
|
},
|
|
],
|
|
}
|
|
|
|
// #when
|
|
await hook["chat.message"](
|
|
{ sessionID: "session-123" },
|
|
output
|
|
)
|
|
|
|
// #then - should find plan by partial match
|
|
expect(output.parts[0].text).toContain("2026-01-15-feature-implementation")
|
|
expect(output.parts[0].text).toContain("Auto-Selected Plan")
|
|
})
|
|
})
|
|
})
|