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)
This commit is contained in:
Kenneth Lien
2026-03-20 10:55:27 -07:00
parent 90accf6fd2
commit 1daff5f224

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'
@@ -593,9 +593,33 @@ 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
}
process.stderr.write(`telegram channel: polling failed: ${err}\n`)
return
}
}
})()