host: the last five text bounds in core/src/host still cut on UTF-16 units (steward, approvals, hooks, agents, schedules)

changelog.d/1993-p2-c5-remaining.fixed.md

@@ -0,0 +1 @@
+The last five text bounds in `core/src/host/` no longer cut on UTF-16 units ([#1993](https://github.com/ThinkFlowLab/FlyBot/issues/1993)): the quoted first line of a checkpoint's kept tail (80), an approval record's reason (500), a mention receipt's reason line (240), the title given to a DSH Agent's Session (80) and a schedule run's failure reason (200) used a bare `slice`, so a bound that landed between the halves of a surrogate pair stored a lone high surrogate — read as U+FFFD by any encoder. Each now goes through the shared `cut`, which keeps within the same budget the longest prefix that stops before a split pair; none of the five maxima changes.

core/src/host/agents.js

@@ -3,6 +3,7 @@
 // the whole dsh conversation surface and none of the team tools.
 import { randomUUID } from 'node:crypto'
 import { AGENT_NAME, AGENT_SESSION_TITLE_MAX, TEAM_TOOLS } from './constants.js'
+import { cut } from './text.js'
 
 export function install(rt) {
   const { ctx, state } = rt
@@ -166,7 +167,7 @@ export function install(rt) {
     const clean = String(title ?? '').trim()
     if (clean === '') throw new Error('A session needs a title')
     const agent_ = await rt.resolveAgent(sessionId)
-    await ctx.sessionTitle.rename(agent_.session, clean.slice(0, AGENT_SESSION_TITLE_MAX))
+    await ctx.sessionTitle.rename(agent_.session, cut(clean, AGENT_SESSION_TITLE_MAX).text)
   }
 
   async function removeAgent(agentId) {

core/src/host/approvals.js

@@ -5,6 +5,7 @@
 import { randomUUID } from 'node:crypto'
 import { EPHEMERAL_DENIED_TOOLS } from './tools.js'
 import { OWNER, settled } from './turn-origin.js'
+import { cut } from './text.js'
 
 const OUTCOMES = { allow: 'allowed-once', reject: 'rejected', 'always-bot': 'allowed-once', 'always-room': 'allowed-once' }
 const RUN_DENIED = new Set(EPHEMERAL_DENIED_TOOLS)
@@ -72,7 +73,7 @@ export function install(rt) {
       botId,
       ...(owner ? { roomId: owner.roomId } : {}),
       tool: String(request.toolName ?? ''),
-      reason: String(request.reason ?? '').slice(0, 500),
+      reason: cut(String(request.reason ?? ''), 500).text,
       detail: rt.callDetail?.(sessionId, request.callId) ?? {},
       at: Date.now(),
     }

core/src/host/hooks.js

@@ -1038,7 +1038,7 @@ export function install(rt) {
   // the room, posted as a relay role the room's round machinery does not answer (groups.js `opens`).
   async function mentionReceipt(sessionId, room, results, known) {
     if (room === undefined || results.length === 0) return
-    const line = value => String(value ?? '').replace(/[\u0000-\u001f\u007f-\u009f\u2028\u2029]/g, ' ').replace(/\s+/g, ' ').trim().slice(0, 240)
+    const line = value => cut(String(value ?? '').replace(/[\u0000-\u001f\u007f-\u009f\u2028\u2029]/g, ' ').replace(/\s+/g, ' ').trim(), 240).text
     const lines = results.map(({ handle, action, reason }) => {
       const name = cleanName(known.get(handle)?.name, handle)
       const why = line(reason)

core/src/host/schedules.js

@@ -31,7 +31,7 @@ import { randomUUID } from 'node:crypto'
 import { createUserMessage } from '@deepseek-ai/dsh-llm'
 import { quietHoursOf, inQuietHours, clockIn, quietError } from '../shared/quiet-hours.js'
 import { defineTool } from './tool-schema.js'
-import { codePoints, textOf } from './text.js'
+import { codePoints, cut, textOf } from './text.js'
 import { output } from './tools.js'
 import { retiredBot } from './store.js'
 
@@ -279,7 +279,7 @@ export function install(rt) {
     for (const id of entry.ids) {
       const run = runs()[id]
       if (run === undefined) continue
-      noteRun(id, { ...run, result: reason !== undefined ? 'failed' : aborted ? 'stopped' : 'ran', ...(reason !== undefined ? { reason: reason.slice(0, 200) } : {}) })
+      noteRun(id, { ...run, result: reason !== undefined ? 'failed' : aborted ? 'stopped' : 'ran', ...(reason !== undefined ? { reason: cut(reason, 200).text } : {}) })
     }
   }
   // A group round whose members' turns failed: the task's run in that group failed.

core/src/host/steward.js

@@ -6,7 +6,7 @@
 //
 // Every line follows the model. Its declared window, less the room its reply
 // needs, is the usable context; the check line is a share of that.
-import { estimateTokens } from './text.js'
+import { cut, estimateTokens } from './text.js'
 
 // For a model that declares no window.
 export const DEFAULT_WINDOW = 500_000
@@ -145,7 +145,7 @@ export function checkpointTailNote(tail) {
   const first = tail[0]
   const text = (Array.isArray(first?.content) ? first.content : [])
     .filter(block => block?.type === 'text').map(block => block.text).join(' ').replace(/\s+/g, ' ').trim()
-  const from = text === '' ? `from your ${first?.role === 'assistant' ? 'own step' : 'latest input'}` : `from the one that begins "${text.slice(0, 80)}"`
+  const from = text === '' ? `from your ${first?.role === 'assistant' ? 'own step' : 'latest input'}` : `from the one that begins "${cut(text, 80).text}"`
   return `The last ${tail.length === 1 ? 'message' : `${tail.length} messages`} above, ${from}, stay right after your summary, word for word. Count what they give as given: summarize only what comes before them, and do not copy them.`
 }
 

core/test/agents.test.js

@@ -153,6 +153,20 @@ test('agent-rename retitles an owned Session and refuses others', async (t) => {
   assert.equal((await call('agent-rename', { agentId: agent.id, sessionId: 'm1', title: 'x' })).ok, false)
 })
 
+test('P-1993: a Session title is cut on a code point at the 80-unit bound', async (t) => {
+  const { call, stop, renamed } = start(TEAM)
+  t.after(stop)
+  await call('state', {})
+  const agent = (await call('add-agent')).value
+  const head = 'a'.repeat(79)
+  assert.equal((await call('agent-rename', { agentId: agent.id, sessionId: agent.sessions[0], title: `${head}😀tail` })).ok, true)
+  assert.ok(renamed.at(-1).title.isWellFormed(), `the title is well formed: ${JSON.stringify(renamed.at(-1).title)}`)
+  assert.equal(renamed.at(-1).title, head, 'the pair at the bound is dropped whole, not split')
+  // Control: a title under the bound is stored word for word.
+  assert.equal((await call('agent-rename', { agentId: agent.id, sessionId: agent.sessions[0], title: '  Scratch  ' })).ok, true)
+  assert.equal(renamed.at(-1).title, 'Scratch')
+})
+
 test('remove-agent keeps the Agent with the Sessions it could not archive', async (t) => {
   const { call, stop, archived, failArchive } = start(TEAM)
   t.after(stop)

core/test/flybot.test.js

@@ -622,6 +622,36 @@ test('mentions in a group (#80, #81): the room gets a receipt — sent points to
   assert.equal((agents.get('b')?.calls ?? []).length, 0)
 })
 
+test('P-1993: a mention receipt\'s reason is cut on a code point at 240', async (t) => {
+  const { ctx, fb, stop, agents, grantTo } = await start({
+    rooms: { 'room-1': { id: 'room-1', name: 'Group', members: ['a', 'b'], admin: 'a', mode: 'admin', notice: '', createdAt: 1, createdBy: null } },
+  })
+  t.after(stop)
+  await grantTo('a', '@helper.friend.home')
+  fb.transports.add('bot-social', { send: async msg => ({ exchangeId: `r-${msg.to.handle}` }) })
+  fb.scope('social').remote.publish([{ handle: '@helper.friend.home', name: '助手', home: '@friend.home' }])
+  const head = 'a'.repeat(239)
+  fb.bot.send.use({ name: 'deny-long', handle: m => (m.target?.remote === true ? { action: 'deny', reason: /long/.test(m.text) ? `${head}😀tail` : 'no friendship' } : undefined) })
+  const receipts = () => (agents.get('room-1')?.calls ?? []).map(([, m]) => m.content.map(b => b.text).join('\n'))
+  const until = async (check) => {
+    const end = Date.now() + 2000
+    while (!check()) {
+      if (Date.now() > end) throw new Error('until: the condition did not hold within 2 s')
+      await delay(10)
+    }
+  }
+  const say = async (text, n) => {
+    ctx.emitArgs('session/event', { id: 'room-1' }, { type: 'user/message', seq: n, data: { source: { kind: 'user' }, content: [{ type: 'text', text }] } })
+    await until(() => receipts().length >= n)
+  }
+  await say('@helper.friend.home long one', 1)
+  assert.ok(receipts()[0].isWellFormed(), `the receipt is well formed: ${JSON.stringify(receipts()[0])}`)
+  assert.equal(receipts()[0], `助手: not sent — ${head}`, 'the pair at the bound is dropped whole, not split')
+  // Control: a reason under the bound is posted word for word.
+  await say('@helper.friend.home short one', 2)
+  assert.equal(receipts()[1], '助手: not sent — no friendship')
+})
+
 test('mentions (#143): a human line to a friend Bot already in the room stays in the room; Chief is not the sender', async (t) => {
   const { ctx, fb, stop, agents } = await start({
     rooms: {

core/test/group-status.test.js

@@ -132,6 +132,24 @@ test('a group Session\'s approval waits in the team view, frees the round, and t
   assert.equal(text(post), '[Group post from Writer]\nCopied the doc to E:/docs.')
 })
 
+test('P-1993: an approval record\'s reason is cut on a code point at 500', async (t) => {
+  const host = await start()
+  t.after(host.stop)
+  const head = 'a'.repeat(499)
+  const short = host.askApproval('gb', { callId: 'k1', reason: 'copy the doc' })
+  const [control] = (await host.call('state', {})).value.work.approvals
+  assert.equal(control.reason, 'copy the doc', 'a reason under the bound is stored word for word')
+  assert.equal((await host.call('approval-answer', { id: control.id, choice: 'allow' })).ok, true)
+  assert.equal(await short, 'allowed-once')
+
+  const long = host.askApproval('gb', { callId: 'k2', reason: `${head}😀tail` })
+  const [approval] = (await host.call('state', {})).value.work.approvals
+  assert.ok(approval.reason.isWellFormed(), `the stored reason is well formed: ${JSON.stringify(approval.reason)}`)
+  assert.equal(approval.reason, head, 'the pair at the bound is dropped whole, not split')
+  assert.equal((await host.call('approval-answer', { id: approval.id, choice: 'allow' })).ok, true)
+  assert.equal(await long, 'allowed-once')
+})
+
 // Both fields of a card go through a bound of their own: 300 for the description, 400 for the
 // command. A cut that splits a surrogate pair leaves a lone high half the card draws as U+FFFD.
 test('an approval card cuts its description and command at their bounds without splitting a pair', async (t) => {

core/test/schedules.test.js

@@ -628,6 +628,24 @@ test('a run fails only when its turn errors; a turn without an answer has run, a
   assert.equal(saved(), 'stopped')
 })
 
+test('P-1993: a failed run\'s reason is cut on a code point at 200', async (t) => {
+  const schedule = scheduleService()
+  const { ctx, home, call } = setup({ schedule })
+  t.after(async () => { await ctx.dispose(); rmSync(home, { recursive: true, force: true, maxRetries: 5 }) })
+  await call('schedule-create', { target: 'm1', title: 'Briefing', prompt: 'Sum up', when: DAILY })
+  const [id] = schedule.tasks.keys()
+  const message = { id: 'msg-1', content: [{ type: 'text', text: reminder(id, 'Sum up') }], source: { kind: 'schedule' } }
+  const head = `SERVER 503: ${'a'.repeat(187)}`
+  runTurn(ctx, 'm1', 1, message, { kind: 'error', error: { code: 'SERVER', status: 503, message: `${'a'.repeat(187)}😀tail` } })
+  const [[result, reason]] = await lastRuns(call)
+  assert.equal(result, 'failed')
+  assert.ok(reason.isWellFormed(), `the stored reason is well formed: ${JSON.stringify(reason)}`)
+  assert.equal(reason, head, 'the pair at the bound is dropped whole, not split')
+  // Control: a reason under the bound is stored word for word.
+  runTurn(ctx, 'm1', 2, { ...message, id: 'msg-2' }, { kind: 'error', error: { code: 'SERVER', status: 503, message: 'upstream busy' } })
+  assert.deepEqual(await lastRuns(call), [['failed', 'SERVER 503: upstream busy']])
+})
+
 test('Retry runs the same prompt once now in the Bot’s current part, and its turn is the task’s run', async (t) => {
   const schedule = scheduleService()
   const { ctx, home, call } = setup({ schedule })

core/test/steward.test.js

@@ -101,6 +101,17 @@ test('the checkpoint also reads the messages the backend keeps after it', () =>
   assert.ok(checkpointTailNote([say('user', '长'.repeat(300))]).includes(`"${'长'.repeat(80)}"`))
 })
 
+test('P-1993: the quoted first line of the kept tail is cut on a code point at 80', () => {
+  const say = (role, text) => ({ role, content: [{ type: 'text', text }] })
+  const head = 'a'.repeat(79)
+  const quoted = note => /begins "(.*)", stay right after your summary/.exec(note)[1]
+  const long = quoted(checkpointTailNote([say('user', `${head}😀tail`)]))
+  assert.ok(long.isWellFormed(), `the quoted line is well formed: ${JSON.stringify(long)}`)
+  assert.equal(long, head, 'the pair at the bound is dropped whole, not split')
+  // Control: a line under the bound is quoted word for word.
+  assert.equal(quoted(checkpointTailNote([say('user', 'Short line')])), 'Short line')
+})
+
 test('the checkpoint records unanswered requests as remaining, and does not answer them', () => {
   assert.match(CHECKPOINT_PROMPT, /every request not yet answered in your replies above/)
   assert.match(CHECKPOINT_PROMPT, /The user never sees this summary, so do not do any of the remaining work in it/)