Compare commits

..

2 Commits

Author SHA1 Message Date
Kenneth Lien
3d8042f259 Silently return when bot.stop() aborts the setup phase
If bot.stop() is called while bot.start() is still in setup (deleteWebhook/
getMe), grammy rejects with 'Aborted delay'. Expected, not an error.
2026-03-20 11:07:05 -07:00
Kenneth Lien
1daff5f224 telegram: retry on 409 Conflict instead of crashing
During /mcp reload or when a zombie from a previous session still holds
the polling slot, the new process gets 409 Conflict on its first
getUpdates and dies immediately. Retry with backoff until the slot
frees — typically within a second or two.

Also handles the two-sessions case: the second Claude Code instance
keeps retrying (with a clear message about what's happening) and takes
over when the first one exits.

Fixes #804 #794, partial #788 (issue 4)
2026-03-20 10:55:27 -07:00

View File

@@ -15,7 +15,7 @@ import {
ListToolsRequestSchema, ListToolsRequestSchema,
CallToolRequestSchema, CallToolRequestSchema,
} from '@modelcontextprotocol/sdk/types.js' } from '@modelcontextprotocol/sdk/types.js'
import { Bot, InputFile, type Context } from 'grammy' import { Bot, GrammyError, InputFile, type Context } from 'grammy'
import type { ReactionTypeEmoji } from 'grammy/types' import type { ReactionTypeEmoji } from 'grammy/types'
import { randomBytes } from 'crypto' import { randomBytes } from 'crypto'
import { readFileSync, writeFileSync, mkdirSync, readdirSync, rmSync, statSync, renameSync, realpathSync, chmodSync } from 'fs' import { readFileSync, writeFileSync, mkdirSync, readdirSync, rmSync, statSync, renameSync, realpathSync, chmodSync } from 'fs'
@@ -304,7 +304,7 @@ function checkApprovals(): void {
} }
} }
if (!STATIC) setInterval(checkApprovals, 5000).unref() if (!STATIC) setInterval(checkApprovals, 5000)
// Telegram caps messages at 4096 chars. Split long replies, preferring // Telegram caps messages at 4096 chars. Split long replies, preferring
// paragraph boundaries when chunkMode is 'newline'. // paragraph boundaries when chunkMode is 'newline'.
@@ -507,24 +507,6 @@ mcp.setRequestHandler(CallToolRequestSchema, async req => {
await mcp.connect(new StdioServerTransport()) await mcp.connect(new StdioServerTransport())
// When Claude Code closes the MCP connection, stdin gets EOF. Without this
// the bot keeps polling forever as a zombie, holding the token and blocking
// the next session with 409 Conflict.
let shuttingDown = false
function shutdown(): void {
if (shuttingDown) return
shuttingDown = true
process.stderr.write('telegram channel: shutting down\n')
// bot.stop() signals the poll loop to end; the current getUpdates request
// may take up to its long-poll timeout to return. Force-exit after 2s.
setTimeout(() => process.exit(0), 2000)
void Promise.resolve(bot.stop()).finally(() => process.exit(0))
}
process.stdin.on('end', shutdown)
process.stdin.on('close', shutdown)
process.on('SIGTERM', shutdown)
process.on('SIGINT', shutdown)
bot.on('message:text', async ctx => { bot.on('message:text', async ctx => {
await handleInbound(ctx, ctx.message.text, undefined) await handleInbound(ctx, ctx.message.text, undefined)
}) })
@@ -611,9 +593,35 @@ async function handleInbound(
}) })
} }
void bot.start({ // 409 Conflict = another getUpdates consumer is still active (zombie from a
onStart: info => { // previous session, or a second Claude Code instance). Retry with backoff
botUsername = info.username // until the slot frees up instead of crashing on the first rejection.
process.stderr.write(`telegram channel: polling as @${info.username}\n`) void (async () => {
}, for (let attempt = 1; ; attempt++) {
}) try {
await bot.start({
onStart: info => {
botUsername = info.username
process.stderr.write(`telegram channel: polling as @${info.username}\n`)
},
})
return // bot.stop() was called — clean exit from the loop
} catch (err) {
if (err instanceof GrammyError && err.error_code === 409) {
const delay = Math.min(1000 * attempt, 15000)
const detail = attempt === 1
? ' — another instance is polling (zombie session, or a second Claude Code running?)'
: ''
process.stderr.write(
`telegram channel: 409 Conflict${detail}, retrying in ${delay / 1000}s\n`,
)
await new Promise(r => setTimeout(r, delay))
continue
}
// bot.stop() mid-setup rejects with grammy's "Aborted delay" — expected, not an error.
if (err instanceof Error && err.message === 'Aborted delay') return
process.stderr.write(`telegram channel: polling failed: ${err}\n`)
return
}
}
})()