Merge pull request #1477 from kaizen403/fix/boulder-agent-tracking

fix: track agent in boulder state to fix session continuation (fixes #927)
This commit is contained in:
YeonGyu-Kim
2026-02-05 17:41:05 +09:00
committed by GitHub
8 changed files with 234 additions and 15 deletions

View File

@@ -246,5 +246,33 @@ describe("boulder-state", () => {
expect(state.plan_name).toBe("auth-refactor")
expect(state.started_at).toBeDefined()
})
test("should include agent field when provided", () => {
//#given - plan path, session id, and agent type
const planPath = "/path/to/feature.md"
const sessionId = "ses-xyz789"
const agent = "atlas"
//#when - createBoulderState is called with agent
const state = createBoulderState(planPath, sessionId, agent)
//#then - state should include the agent field
expect(state.agent).toBe("atlas")
expect(state.active_plan).toBe(planPath)
expect(state.session_ids).toEqual([sessionId])
expect(state.plan_name).toBe("feature")
})
test("should allow agent to be undefined", () => {
//#given - plan path and session id without agent
const planPath = "/path/to/legacy.md"
const sessionId = "ses-legacy"
//#when - createBoulderState is called without agent
const state = createBoulderState(planPath, sessionId)
//#then - state should not have agent field (backward compatible)
expect(state.agent).toBeUndefined()
})
})
})

View File

@@ -139,12 +139,14 @@ export function getPlanName(planPath: string): string {
*/
export function createBoulderState(
planPath: string,
sessionId: string
sessionId: string,
agent?: string
): BoulderState {
return {
active_plan: planPath,
started_at: new Date().toISOString(),
session_ids: [sessionId],
plan_name: getPlanName(planPath),
...(agent !== undefined ? { agent } : {}),
}
}

View File

@@ -14,6 +14,8 @@ export interface BoulderState {
session_ids: string[]
/** Plan name derived from filename */
plan_name: string
/** Agent type to use when resuming (e.g., 'atlas') */
agent?: string
}
export interface PlanProgress {

View File

@@ -858,8 +858,8 @@ describe("atlas hook", () => {
expect(callArgs.body.parts[0].text).toContain("2 remaining")
})
test("should not inject when last agent is not Atlas", async () => {
// given - boulder state with incomplete plan, but last agent is NOT Atlas
test("should not inject when last agent does not match boulder agent", async () => {
// given - boulder state with incomplete plan, but last agent does NOT match
const planPath = join(TEST_DIR, "test-plan.md")
writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
@@ -868,10 +868,11 @@ describe("atlas hook", () => {
started_at: "2026-01-02T10:00:00Z",
session_ids: [MAIN_SESSION_ID],
plan_name: "test-plan",
agent: "atlas",
}
writeBoulderState(TEST_DIR, state)
// given - last agent is NOT Atlas
// given - last agent is NOT the boulder agent
cleanupMessageStorage(MAIN_SESSION_ID)
setupMessageStorage(MAIN_SESSION_ID, "sisyphus")
@@ -886,10 +887,44 @@ describe("atlas hook", () => {
},
})
// then - should NOT call prompt because agent is not Atlas
// then - should NOT call prompt because agent does not match
expect(mockInput._promptMock).not.toHaveBeenCalled()
})
test("should inject when last agent matches boulder agent even if non-Atlas", async () => {
// given - boulder state expects sisyphus and last agent is sisyphus
const planPath = join(TEST_DIR, "test-plan.md")
writeFileSync(planPath, "# Plan\n- [ ] Task 1\n- [ ] Task 2")
const state: BoulderState = {
active_plan: planPath,
started_at: "2026-01-02T10:00:00Z",
session_ids: [MAIN_SESSION_ID],
plan_name: "test-plan",
agent: "sisyphus",
}
writeBoulderState(TEST_DIR, state)
cleanupMessageStorage(MAIN_SESSION_ID)
setupMessageStorage(MAIN_SESSION_ID, "sisyphus")
const mockInput = createMockPluginInput()
const hook = createAtlasHook(mockInput)
// when
await hook.handler({
event: {
type: "session.idle",
properties: { sessionID: MAIN_SESSION_ID },
},
})
// then - should call prompt for sisyphus
expect(mockInput._promptMock).toHaveBeenCalled()
const callArgs = mockInput._promptMock.mock.calls[0][0]
expect(callArgs.body.agent).toBe("sisyphus")
})
test("should debounce rapid continuation injections (prevent infinite loop)", async () => {
// given - boulder state with incomplete plan
const planPath = join(TEST_DIR, "test-plan.md")

View File

@@ -26,6 +26,13 @@ function isSisyphusPath(filePath: string): boolean {
const WRITE_EDIT_TOOLS = ["Write", "Edit", "write", "edit"]
function getLastAgentFromSession(sessionID: string): string | null {
const messageDir = getMessageDir(sessionID)
if (!messageDir) return null
const nearest = findNearestMessageWithFields(messageDir)
return nearest?.agent?.toLowerCase() ?? null
}
const DIRECT_WORK_REMINDER = `
---
@@ -431,7 +438,7 @@ export function createAtlasHook(
return state
}
async function injectContinuation(sessionID: string, planName: string, remaining: number, total: number): Promise<void> {
async function injectContinuation(sessionID: string, planName: string, remaining: number, total: number, agent?: string): Promise<void> {
const hasRunningBgTasks = backgroundManager
? backgroundManager.getTasksByParentSession(sessionID).some(t => t.status === "running")
: false
@@ -477,7 +484,7 @@ export function createAtlasHook(
await ctx.client.session.prompt({
path: { id: sessionID },
body: {
agent: "atlas",
agent: agent ?? "atlas",
...(model !== undefined ? { model } : {}),
parts: [{ type: "text", text: prompt }],
},
@@ -549,8 +556,14 @@ export function createAtlasHook(
return
}
if (!isCallerOrchestrator(sessionID)) {
log(`[${HOOK_NAME}] Skipped: last agent is not Atlas`, { sessionID })
const requiredAgent = (boulderState.agent ?? "atlas").toLowerCase()
const lastAgent = getLastAgentFromSession(sessionID)
if (!lastAgent || lastAgent !== requiredAgent) {
log(`[${HOOK_NAME}] Skipped: last agent does not match boulder agent`, {
sessionID,
lastAgent: lastAgent ?? "unknown",
requiredAgent,
})
return
}
@@ -568,7 +581,7 @@ export function createAtlasHook(
state.lastContinuationInjectedAt = now
const remaining = progress.total - progress.completed
injectContinuation(sessionID, boulderState.plan_name, remaining, progress.total)
injectContinuation(sessionID, boulderState.plan_name, remaining, progress.total, boulderState.agent)
return
}

View File

@@ -352,6 +352,121 @@ describe("prometheus-md-only", () => {
})
})
describe("boulder state priority over message files (fixes #927)", () => {
const BOULDER_DIR = join(tmpdir(), `boulder-test-${randomUUID()}`)
const BOULDER_FILE = join(BOULDER_DIR, ".sisyphus", "boulder.json")
beforeEach(() => {
mkdirSync(join(BOULDER_DIR, ".sisyphus"), { recursive: true })
})
afterEach(() => {
rmSync(BOULDER_DIR, { recursive: true, force: true })
})
//#given session was started with prometheus (first message), but /start-work set boulder agent to atlas
//#when user types "continue" after interruption (memory cleared, falls back to message files)
//#then should use boulder state agent (atlas), not message file agent (prometheus)
test("should prioritize boulder agent over message file agent", async () => {
// given - prometheus in message files (from /plan)
setupMessageStorage(TEST_SESSION_ID, "prometheus")
// given - atlas in boulder state (from /start-work)
writeFileSync(BOULDER_FILE, JSON.stringify({
active_plan: "/test/plan.md",
started_at: new Date().toISOString(),
session_ids: [TEST_SESSION_ID],
plan_name: "test-plan",
agent: "atlas"
}))
const hook = createPrometheusMdOnlyHook({
client: {},
directory: BOULDER_DIR,
} as never)
const input = {
tool: "Write",
sessionID: TEST_SESSION_ID,
callID: "call-1",
}
const output = {
args: { filePath: "/path/to/code.ts" },
}
// when / then - should NOT block because boulder says atlas, not prometheus
await expect(
hook["tool.execute.before"](input, output)
).resolves.toBeUndefined()
})
test("should use prometheus from boulder state when set", async () => {
// given - atlas in message files (from some other agent)
setupMessageStorage(TEST_SESSION_ID, "atlas")
// given - prometheus in boulder state (edge case, but should honor it)
writeFileSync(BOULDER_FILE, JSON.stringify({
active_plan: "/test/plan.md",
started_at: new Date().toISOString(),
session_ids: [TEST_SESSION_ID],
plan_name: "test-plan",
agent: "prometheus"
}))
const hook = createPrometheusMdOnlyHook({
client: {},
directory: BOULDER_DIR,
} as never)
const input = {
tool: "Write",
sessionID: TEST_SESSION_ID,
callID: "call-1",
}
const output = {
args: { filePath: "/path/to/code.ts" },
}
// when / then - should block because boulder says prometheus
await expect(
hook["tool.execute.before"](input, output)
).rejects.toThrow("can only write/edit .md files")
})
test("should fall back to message files when session not in boulder", async () => {
// given - prometheus in message files
setupMessageStorage(TEST_SESSION_ID, "prometheus")
// given - boulder state exists but for different session
writeFileSync(BOULDER_FILE, JSON.stringify({
active_plan: "/test/plan.md",
started_at: new Date().toISOString(),
session_ids: ["other-session-id"],
plan_name: "test-plan",
agent: "atlas"
}))
const hook = createPrometheusMdOnlyHook({
client: {},
directory: BOULDER_DIR,
} as never)
const input = {
tool: "Write",
sessionID: TEST_SESSION_ID,
callID: "call-1",
}
const output = {
args: { filePath: "/path/to/code.ts" },
}
// when / then - should block because falls back to message files (prometheus)
await expect(
hook["tool.execute.before"](input, output)
).rejects.toThrow("can only write/edit .md files")
})
})
describe("without message storage", () => {
test("should handle missing session gracefully (no agent found)", async () => {
// given

View File

@@ -4,6 +4,7 @@ import { join, resolve, relative, isAbsolute } from "node:path"
import { HOOK_NAME, PROMETHEUS_AGENT, ALLOWED_EXTENSIONS, ALLOWED_PATH_PREFIX, BLOCKED_TOOLS, PLANNING_CONSULT_WARNING, PROMETHEUS_WORKFLOW_REMINDER } from "./constants"
import { findNearestMessageWithFields, findFirstMessageWithAgent, MESSAGE_STORAGE } from "../../features/hook-message-injector"
import { getSessionAgent } from "../../features/claude-code-session-state"
import { readBoulderState } from "../../features/boulder-state"
import { log } from "../../shared/logger"
import { SYSTEM_DIRECTIVE_PREFIX } from "../../shared/system-directive"
import { getAgentDisplayName } from "../../shared/agent-display-names"
@@ -70,8 +71,31 @@ function getAgentFromMessageFiles(sessionID: string): string | undefined {
return findFirstMessageWithAgent(messageDir) ?? findNearestMessageWithFields(messageDir)?.agent
}
function getAgentFromSession(sessionID: string): string | undefined {
return getSessionAgent(sessionID) ?? getAgentFromMessageFiles(sessionID)
/**
* Get the effective agent for the session.
* Priority order:
* 1. In-memory session agent (most recent, set by /start-work)
* 2. Boulder state agent (persisted across restarts, fixes #927)
* 3. Message files (fallback for sessions without boulder state)
*
* This fixes issue #927 where after interruption:
* - In-memory map is cleared (process restart)
* - Message files return "prometheus" (oldest message from /plan)
* - But boulder.json has agent: "atlas" (set by /start-work)
*/
function getAgentFromSession(sessionID: string, directory: string): string | undefined {
// Check in-memory first (current session)
const memoryAgent = getSessionAgent(sessionID)
if (memoryAgent) return memoryAgent
// Check boulder state (persisted across restarts) - fixes #927
const boulderState = readBoulderState(directory)
if (boulderState?.session_ids.includes(sessionID) && boulderState.agent) {
return boulderState.agent
}
// Fallback to message files
return getAgentFromMessageFiles(sessionID)
}
export function createPrometheusMdOnlyHook(ctx: PluginInput) {
@@ -80,7 +104,7 @@ export function createPrometheusMdOnlyHook(ctx: PluginInput) {
input: { tool: string; sessionID: string; callID: string },
output: { args: Record<string, unknown>; message?: string }
): Promise<void> => {
const agentName = getAgentFromSession(input.sessionID)
const agentName = getAgentFromSession(input.sessionID, ctx.directory)
if (agentName !== PROMETHEUS_AGENT) {
return

View File

@@ -102,7 +102,7 @@ All ${progress.total} tasks are done. Create a new plan with: /plan "your task"`
if (existingState) {
clearBoulderState(ctx.directory)
}
const newState = createBoulderState(matchedPlan, sessionId)
const newState = createBoulderState(matchedPlan, sessionId, "atlas")
writeBoulderState(ctx.directory, newState)
contextInfo = `
@@ -187,7 +187,7 @@ All ${plans.length} plan(s) are complete. Create a new plan with: /plan "your ta
} else if (incompletePlans.length === 1) {
const planPath = incompletePlans[0]
const progress = getPlanProgress(planPath)
const newState = createBoulderState(planPath, sessionId)
const newState = createBoulderState(planPath, sessionId, "atlas")
writeBoulderState(ctx.directory, newState)
contextInfo += `