refactor: migrate delegate_task to task tool with metadata fixes
- Rename delegate_task tool to task across codebase (100 files) - Update model references: claude-opus-4-6 → 4-5, gpt-5.3-codex → 5.2-codex - Add tool-metadata-store to restore metadata overwritten by fromPlugin() - Add session ID polling for BackgroundManager task sessions - Await async ctx.metadata() calls in tool executors - Add ses_ prefix guard to getMessageDir for performance - Harden BackgroundManager with idle deferral and error handling - Fix duplicate task key in sisyphus-junior test object literals - Fix unawaited showOutputToUser in ast_grep_replace - Fix background=true → run_in_background=true in ultrawork prompt - Fix duplicate task/task references in docs and comments
This commit is contained in:
YeonGyu-Kim
@@ -86,7 +86,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when - calling with undefined output
|
||||
const result = await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID: "session-123" },
|
||||
{ tool: "task", sessionID: "session-123" },
|
||||
undefined as unknown as { title: string; output: string; metadata: Record<string, unknown> }
|
||||
)
|
||||
|
||||
@@ -94,8 +94,8 @@ describe("atlas hook", () => {
|
||||
expect(result).toBeUndefined()
|
||||
})
|
||||
|
||||
test("should ignore non-delegate_task tools", async () => {
|
||||
// given - hook and non-delegate_task tool
|
||||
test("should ignore non-task tools", async () => {
|
||||
// given - hook and non-task tool
|
||||
const hook = createAtlasHook(createMockPluginInput())
|
||||
const output = {
|
||||
title: "Test Tool",
|
||||
@@ -138,7 +138,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
@@ -162,14 +162,14 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
// then - standalone verification reminder appended
|
||||
expect(output.output).toContain("Task completed successfully")
|
||||
expect(output.output).toContain("MANDATORY:")
|
||||
expect(output.output).toContain("delegate_task(session_id=")
|
||||
expect(output.output).toContain("task(session_id=")
|
||||
|
||||
cleanupMessageStorage(sessionID)
|
||||
})
|
||||
@@ -199,7 +199,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
@@ -208,7 +208,7 @@ describe("atlas hook", () => {
|
||||
expect(output.output).toContain("SUBAGENT WORK COMPLETED")
|
||||
expect(output.output).toContain("test-plan")
|
||||
expect(output.output).toContain("LIE")
|
||||
expect(output.output).toContain("delegate_task(session_id=")
|
||||
expect(output.output).toContain("task(session_id=")
|
||||
|
||||
cleanupMessageStorage(sessionID)
|
||||
})
|
||||
@@ -238,7 +238,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
@@ -275,7 +275,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
@@ -311,7 +311,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
@@ -348,7 +348,7 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
@@ -385,12 +385,12 @@ describe("atlas hook", () => {
|
||||
|
||||
// when
|
||||
await hook["tool.execute.after"](
|
||||
{ tool: "delegate_task", sessionID },
|
||||
{ tool: "task", sessionID },
|
||||
output
|
||||
)
|
||||
|
||||
// then - should include session_id instructions and verification
|
||||
expect(output.output).toContain("delegate_task(session_id=")
|
||||
expect(output.output).toContain("task(session_id=")
|
||||
expect(output.output).toContain("[x]")
|
||||
expect(output.output).toContain("MANDATORY:")
|
||||
|
||||
@@ -425,8 +425,8 @@ describe("atlas hook", () => {
|
||||
|
||||
// then
|
||||
expect(output.output).toContain("ORCHESTRATOR, not an IMPLEMENTER")
|
||||
expect(output.output).toContain("delegate_task")
|
||||
expect(output.output).toContain("delegate_task")
|
||||
expect(output.output).toContain("task")
|
||||
expect(output.output).toContain("task")
|
||||
})
|
||||
|
||||
test("should append delegation reminder when orchestrator edits outside .sisyphus/", async () => {
|
||||
|
||||
+10
-10
@@ -44,7 +44,7 @@ You just performed direct file modifications outside \`.sisyphus/\`.
|
||||
**You are an ORCHESTRATOR, not an IMPLEMENTER.**
|
||||
|
||||
As an orchestrator, you should:
|
||||
- **DELEGATE** implementation work to subagents via \`delegate_task\`
|
||||
- **DELEGATE** implementation work to subagents via \`task\`
|
||||
- **VERIFY** the work done by subagents
|
||||
- **COORDINATE** multiple tasks and ensure completion
|
||||
|
||||
@@ -54,7 +54,7 @@ You should NOT:
|
||||
- Implement features yourself
|
||||
|
||||
**If you need to make changes:**
|
||||
1. Use \`delegate_task\` to delegate to an appropriate subagent
|
||||
1. Use \`task\` to delegate to an appropriate subagent
|
||||
2. Provide clear instructions in the prompt
|
||||
3. Verify the subagent's work after completion
|
||||
|
||||
@@ -128,7 +128,7 @@ You (Atlas) are attempting to directly modify a file outside \`.sisyphus/\`.
|
||||
**THIS IS FORBIDDEN** (except for VERIFICATION purposes)
|
||||
|
||||
As an ORCHESTRATOR, you MUST:
|
||||
1. **DELEGATE** all implementation work via \`delegate_task\`
|
||||
1. **DELEGATE** all implementation work via \`task\`
|
||||
2. **VERIFY** the work done by subagents (reading files is OK)
|
||||
3. **COORDINATE** - you orchestrate, you don't implement
|
||||
|
||||
@@ -146,11 +146,11 @@ As an ORCHESTRATOR, you MUST:
|
||||
|
||||
**IF THIS IS FOR VERIFICATION:**
|
||||
Proceed if you are verifying subagent work by making a small fix.
|
||||
But for any substantial changes, USE \`delegate_task\`.
|
||||
But for any substantial changes, USE \`task\`.
|
||||
|
||||
**CORRECT APPROACH:**
|
||||
\`\`\`
|
||||
delegate_task(
|
||||
task(
|
||||
category="...",
|
||||
prompt="[specific single task with clear acceptance criteria]"
|
||||
)
|
||||
@@ -193,7 +193,7 @@ function buildVerificationReminder(sessionId: string): string {
|
||||
|
||||
**If ANY verification fails, use this immediately:**
|
||||
\`\`\`
|
||||
delegate_task(session_id="${sessionId}", prompt="fix: [describe the specific failure]")
|
||||
task(session_id="${sessionId}", prompt="fix: [describe the specific failure]")
|
||||
\`\`\``
|
||||
}
|
||||
|
||||
@@ -688,12 +688,12 @@ export function createAtlasHook(
|
||||
return
|
||||
}
|
||||
|
||||
// Check delegate_task - inject single-task directive
|
||||
if (input.tool === "delegate_task") {
|
||||
// Check task - inject single-task directive
|
||||
if (input.tool === "task") {
|
||||
const prompt = output.args.prompt as string | undefined
|
||||
if (prompt && !prompt.includes(SYSTEM_DIRECTIVE_PREFIX)) {
|
||||
output.args.prompt = `<system-reminder>${SINGLE_TASK_DIRECTIVE}</system-reminder>\n` + prompt
|
||||
log(`[${HOOK_NAME}] Injected single-task directive to delegate_task`, {
|
||||
log(`[${HOOK_NAME}] Injected single-task directive to task`, {
|
||||
sessionID: input.sessionID,
|
||||
})
|
||||
}
|
||||
@@ -732,7 +732,7 @@ export function createAtlasHook(
|
||||
return
|
||||
}
|
||||
|
||||
if (input.tool !== "delegate_task") {
|
||||
if (input.tool !== "task") {
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user