Gladdonilli 0fb765732a
fix: improve background task completion detection and message extraction (#638)
* fix: background task completion detection and silent notifications

- Fix TS2742 by adding explicit ToolDefinition type annotations
- Add stability detection (3 consecutive stable polls after 10s minimum)
- Remove early continue when sessionStatus is undefined
- Add silent notification system via tool.execute.after hook injection
- Change task retention from 200ms to 5 minutes for background_output retrieval
- Fix formatTaskResult to sort messages by time descending

Fixes hanging background tasks that never complete due to missing sessionStatus.

* fix: improve background task completion detection and message extraction

- Add stability-based completion detection (10s min + 3 stable polls)
- Fix message extraction to recognize 'reasoning' parts from thinking models
- Switch from promptAsync() to prompt() for proper agent initialization
- Remove model parameter from prompt body (use agent's configured model)
- Add fire-and-forget prompt pattern for sisyphus_task sync mode
- Add silent notification via tool.execute.after hook injection
- Fix indentation issues in manager.ts and index.ts

Incorporates fixes from:
- PR #592: Stability detection mechanism
- PR #610: Model parameter passing (partially)
- PR #628: Completion detection improvements

Known limitation: Thinking models (e.g. claude-*-thinking-*) cause
JSON Parse errors in child sessions. Use non-thinking models for
background agents until OpenCode core resolves this.

* fix: add tool_result handling and pendingByParent tracking for resume/external tasks

Addresses code review feedback from PR #638:

P1: Add tool_result type to validateSessionHasOutput() to prevent
    false negatives for tool-only background tasks that would otherwise
    timeout after 30 minutes despite having valid results.

P2: Add pendingByParent tracking to resume() and registerExternalTask()
    to prevent premature 'ALL COMPLETE' notifications when mixing
    launched and resumed tasks.

* fix: address code review feedback - log messages, model passthrough, sorting, race condition

- Fix misleading log messages: 'promptAsync' -> 'prompt (fire-and-forget)'
- Restore model passthrough in launch() for Sisyphus category configs
- Fix call-omo-agent sorting: use time.created number instead of String(time)
- Fix race condition: check promptError inside polling loop, not just after 100ms
2026-01-10 14:00:25 +09:00

234 lines
8.6 KiB
TypeScript

import { tool, type PluginInput, type ToolDefinition } from "@opencode-ai/plugin"
import { ALLOWED_AGENTS, CALL_OMO_AGENT_DESCRIPTION } from "./constants"
import type { CallOmoAgentArgs } from "./types"
import type { BackgroundManager } from "../../features/background-agent"
import { log } from "../../shared/logger"
type ToolContextWithMetadata = {
sessionID: string
messageID: string
agent: string
abort: AbortSignal
metadata?: (input: { title?: string; metadata?: Record<string, unknown> }) => void
}
export function createCallOmoAgent(
ctx: PluginInput,
backgroundManager: BackgroundManager
): ToolDefinition {
const agentDescriptions = ALLOWED_AGENTS.map(
(name) => `- ${name}: Specialized agent for ${name} tasks`
).join("\n")
const description = CALL_OMO_AGENT_DESCRIPTION.replace("{agents}", agentDescriptions)
return tool({
description,
args: {
description: tool.schema.string().describe("A short (3-5 words) description of the task"),
prompt: tool.schema.string().describe("The task for the agent to perform"),
subagent_type: tool.schema
.enum(ALLOWED_AGENTS)
.describe("The type of specialized agent to use for this task (explore or librarian only)"),
run_in_background: tool.schema
.boolean()
.describe("REQUIRED. true: run asynchronously (use background_output to get results), false: run synchronously and wait for completion"),
session_id: tool.schema.string().describe("Existing Task session to continue").optional(),
},
async execute(args: CallOmoAgentArgs, toolContext) {
const toolCtx = toolContext as ToolContextWithMetadata
log(`[call_omo_agent] Starting with agent: ${args.subagent_type}, background: ${args.run_in_background}`)
if (!ALLOWED_AGENTS.includes(args.subagent_type as typeof ALLOWED_AGENTS[number])) {
return `Error: Invalid agent type "${args.subagent_type}". Only ${ALLOWED_AGENTS.join(", ")} are allowed.`
}
if (args.run_in_background) {
if (args.session_id) {
return `Error: session_id is not supported in background mode. Use run_in_background=false to continue an existing session.`
}
return await executeBackground(args, toolCtx, backgroundManager)
}
return await executeSync(args, toolCtx, ctx)
},
})
}
async function executeBackground(
args: CallOmoAgentArgs,
toolContext: ToolContextWithMetadata,
manager: BackgroundManager
): Promise<string> {
try {
const task = await manager.launch({
description: args.description,
prompt: args.prompt,
agent: args.subagent_type,
parentSessionID: toolContext.sessionID,
parentMessageID: toolContext.messageID,
})
toolContext.metadata?.({
title: args.description,
metadata: { sessionId: task.sessionID },
})
return `Background agent task launched successfully.
Task ID: ${task.id}
Session ID: ${task.sessionID}
Description: ${task.description}
Agent: ${task.agent} (subagent)
Status: ${task.status}
The system will notify you when the task completes.
Use \`background_output\` tool with task_id="${task.id}" to check progress:
- block=false (default): Check status immediately - returns full status info
- block=true: Wait for completion (rarely needed since system notifies)`
} catch (error) {
const message = error instanceof Error ? error.message : String(error)
return `Failed to launch background agent task: ${message}`
}
}
async function executeSync(
args: CallOmoAgentArgs,
toolContext: ToolContextWithMetadata,
ctx: PluginInput
): Promise<string> {
let sessionID: string
if (args.session_id) {
log(`[call_omo_agent] Using existing session: ${args.session_id}`)
const sessionResult = await ctx.client.session.get({
path: { id: args.session_id },
})
if (sessionResult.error) {
log(`[call_omo_agent] Session get error:`, sessionResult.error)
return `Error: Failed to get existing session: ${sessionResult.error}`
}
sessionID = args.session_id
} else {
log(`[call_omo_agent] Creating new session with parent: ${toolContext.sessionID}`)
const createResult = await ctx.client.session.create({
body: {
parentID: toolContext.sessionID,
title: `${args.description} (@${args.subagent_type} subagent)`,
},
})
if (createResult.error) {
log(`[call_omo_agent] Session create error:`, createResult.error)
return `Error: Failed to create session: ${createResult.error}`
}
sessionID = createResult.data.id
log(`[call_omo_agent] Created session: ${sessionID}`)
}
toolContext.metadata?.({
title: args.description,
metadata: { sessionId: sessionID },
})
log(`[call_omo_agent] Sending prompt to session ${sessionID}`)
log(`[call_omo_agent] Prompt text:`, args.prompt.substring(0, 100))
try {
await ctx.client.session.prompt({
path: { id: sessionID },
body: {
agent: args.subagent_type,
tools: {
task: false,
call_omo_agent: false,
sisyphus_task: false,
},
parts: [{ type: "text", text: args.prompt }],
},
})
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error)
log(`[call_omo_agent] Prompt error:`, errorMessage)
if (errorMessage.includes("agent.name") || errorMessage.includes("undefined")) {
return `Error: Agent "${args.subagent_type}" not found. Make sure the agent is registered in your opencode.json or provided by a plugin.\n\n<task_metadata>\nsession_id: ${sessionID}\n</task_metadata>`
}
return `Error: Failed to send prompt: ${errorMessage}\n\n<task_metadata>\nsession_id: ${sessionID}\n</task_metadata>`
}
log(`[call_omo_agent] Prompt sent, fetching messages...`)
const messagesResult = await ctx.client.session.messages({
path: { id: sessionID },
})
if (messagesResult.error) {
log(`[call_omo_agent] Messages error:`, messagesResult.error)
return `Error: Failed to get messages: ${messagesResult.error}`
}
const messages = messagesResult.data
log(`[call_omo_agent] Got ${messages.length} messages`)
// Include both assistant messages AND tool messages
// Tool results (grep, glob, bash output) come from role "tool"
// eslint-disable-next-line @typescript-eslint/no-explicit-any
const relevantMessages = messages.filter(
(m: any) => m.info?.role === "assistant" || m.info?.role === "tool"
)
if (relevantMessages.length === 0) {
log(`[call_omo_agent] No assistant or tool messages found`)
log(`[call_omo_agent] All messages:`, JSON.stringify(messages, null, 2))
return `Error: No assistant or tool response found\n\n<task_metadata>\nsession_id: ${sessionID}\n</task_metadata>`
}
log(`[call_omo_agent] Found ${relevantMessages.length} relevant messages`)
// Sort by time ascending (oldest first) to process messages in order
// eslint-disable-next-line @typescript-eslint/no-explicit-any
const sortedMessages = [...relevantMessages].sort((a: any, b: any) => {
const timeA = a.info?.time?.created ?? 0
const timeB = b.info?.time?.created ?? 0
return timeA - timeB
})
// Extract content from ALL messages, not just the last one
// Tool results may be in earlier messages while the final message is empty
const extractedContent: string[] = []
for (const message of sortedMessages) {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
for (const part of (message as any).parts ?? []) {
// Handle both "text" and "reasoning" parts (thinking models use "reasoning")
if ((part.type === "text" || part.type === "reasoning") && part.text) {
extractedContent.push(part.text)
} else if (part.type === "tool_result") {
// Tool results contain the actual output from tool calls
const toolResult = part as { content?: string | Array<{ type: string; text?: string }> }
if (typeof toolResult.content === "string" && toolResult.content) {
extractedContent.push(toolResult.content)
} else if (Array.isArray(toolResult.content)) {
// Handle array of content blocks
for (const block of toolResult.content) {
if ((block.type === "text" || block.type === "reasoning") && block.text) {
extractedContent.push(block.text)
}
}
}
}
}
}
const responseText = extractedContent
.filter((text) => text.length > 0)
.join("\n\n")
log(`[call_omo_agent] Got response, length: ${responseText.length}`)
const output =
responseText + "\n\n" + ["<task_metadata>", `session_id: ${sessionID}`, "</task_metadata>"].join("\n")
return output
}