orca/src/main/native-chat/transcript-tail-reader.ts

import { readOpenCodeNativeChatTranscriptTail } from './transcript-opencode'
import { isENOENT } from '../ipc/filesystem/filesystem-path-containment'
import type {
  AgentType,
  NativeChatMessage,
  NativeChatTurnLifecycle
} from '../../shared/native-chat-types'
import { resolveNativeChatTranscriptAgent } from '../../shared/native-chat/native-chat-agent-support'
import { resolveSessionFilePath, type ResolveSessionFileOptions } from './session-file-resolver'
import {
  decodeClaudeTranscriptLine,
  decodeCodexTranscriptLine,
  decodeGrokTranscriptLine,
  decodeOmpTranscriptLine
} from './transcript-line-decoders'
import { transcriptFallbackId } from './transcript-fallback-id'
import { inTranscriptFileOrder } from './transcript-file-order'
import { extendTranscriptBoundary } from './transcript-file-version'
import {
  nativeChatTurnLifecycleDecoderForAgent,
  type NativeChatTurnLifecycleDecoder
} from './transcript-turn-lifecycle'
import {
  findLastCompleteLineEnd,
  readTranscriptByteAt,
  TAIL_CHUNK_BYTES
} from './transcript-tail-boundary'
import {
  closeTranscriptHandle,
  openTranscriptFile,
  readTranscriptFile,
  transcriptFileStat
} from './wsl-transcript-fs-access'
import { wslTranscriptFsRefusal } from './wsl-transcript-fs-gate'

export const MAX_NATIVE_CHAT_TRANSCRIPT_RECORD_BYTES = 2 * 1024 * 1024

export type NativeChatLineDecoder = (line: string, fallbackId: string) => NativeChatMessage | null

export function nativeChatLineDecoderForAgent(agent: AgentType): NativeChatLineDecoder | null {
  const transcriptAgent = resolveNativeChatTranscriptAgent(agent)
  if (transcriptAgent === 'claude') {
    return decodeClaudeTranscriptLine
  }
  if (transcriptAgent === 'codex') {
    return decodeCodexTranscriptLine
  }
  if (transcriptAgent === 'grok') {
    return decodeGrokTranscriptLine
  }
  if (transcriptAgent === 'omp') {
    return decodeOmpTranscriptLine
  }
  return null
}

export async function readNativeChatTranscriptTailFile(
  filePath: string,
  limit: number,
  decode: NativeChatLineDecoder,
  includeTrailingLine = false,
  endOffset?: number,
  decodeLifecycle?: NativeChatTurnLifecycleDecoder | null,
  signal?: AbortSignal,
  onConsumedBoundary?: (boundary: Buffer) => void,
  sourceOrder = false
): Promise<{
  messages: NativeChatMessage[]
  lifecycle?: NativeChatTurnLifecycle
  consumedTo: number
  hasMore: boolean
  beforeOffset: number
  latestTimestamp?: number
  malformedRecordCount?: number
  oversizedRecordCount?: number
}> {
  signal?.throwIfAborted()
  const end = Math.min(
    (await transcriptFileStat(filePath, 'exact', signal)).size,
    endOffset ?? Number.MAX_SAFE_INTEGER
  )
  signal?.throwIfAborted()
  if (end === 0) {
    return { messages: [], consumedTo: 0, hasMore: false, beforeOffset: 0 }
  }
  const handle = await openTranscriptFile(filePath, 'exact', signal)
  const lineParts: Buffer[] = []
  let lineBytes = 0
  let lineOversized = false
  let lifecycle: NativeChatTurnLifecycle | undefined
  let malformedRecordCount = 0
  let oversizedRecordCount = 0
  let ignoreNextMalformedRecord = false
  try {
    signal?.throwIfAborted()
    const consumedTo = includeTrailingLine
      ? end
      : await findLastCompleteLineEnd(handle, filePath, end, signal)
    if (consumedTo === 0) {
      return { messages: [], consumedTo: 0, hasMore: false, beforeOffset: 0 }
    }
    const newestFirst: { message: NativeChatMessage; offset: number }[] = []
    const finalByte = await readTranscriptByteAt(handle, filePath, consumedTo - 1, signal)
    if (finalByte === null) {
      return { messages: [], consumedTo: 0, hasMore: false, beforeOffset: 0 }
    }
    ignoreNextMalformedRecord = finalByte !== 0x0a
    let cursor = consumedTo - (finalByte === 0x0a ? 1 : 0)
    const finalBoundaryByte = finalByte === 0x0a ? Buffer.from([finalByte]) : Buffer.alloc(0)
    let boundaryCaptured = false
    if (cursor === 0) {
      onConsumedBoundary?.(finalBoundaryByte)
    }
    while (cursor > 0 && newestFirst.length <= limit) {
      signal?.throwIfAborted()
      const start = Math.max(0, cursor - TAIL_CHUNK_BYTES)
      const buffer = Buffer.allocUnsafe(cursor - start)
      const { bytesRead } = await readTranscriptFile(
        handle,
        filePath,
        buffer,
        0,
        buffer.length,
        start,
        'exact',
        signal
      )
      signal?.throwIfAborted()
      // Short reads mean shrink; never stitch non-adjacent bytes into a record.
      if (bytesRead < buffer.length) {
        break
      }
      if (!boundaryCaptured && onConsumedBoundary) {
        onConsumedBoundary(extendTranscriptBoundary(buffer, finalBoundaryByte))
        boundaryCaptured = true
      }
      let segmentEnd = bytesRead
      for (let index = bytesRead - 1; index >= 0 && newestFirst.length <= limit; index--) {
        if (buffer[index] !== 0x0a) {
          continue
        }
        retainPart(buffer.subarray(index + 1, segmentEnd))
        if (!lineOversized) {
          decodeLine(start + index + 1, newestFirst)
        }
        resetLine()
        segmentEnd = index
      }
      if (segmentEnd > 0) {
        retainPart(buffer.subarray(0, segmentEnd))
      }
      cursor = start
    }
    if (cursor === 0 && lineParts.length > 0 && newestFirst.length <= limit) {
      decodeLine(0, newestFirst)
    }
    let latest = Number.NEGATIVE_INFINITY
    const chronological = newestFirst.toReversed().map((entry) => {
      const ordered = inTranscriptFileOrder(
        entry.message,
        latest,
        sourceOrder ? entry.offset : undefined
      )
      latest = ordered.latest
      return { message: ordered.message, offset: entry.offset }
    })
    // slice(-0) returns everything; non-positive limits must explicitly select nothing.
    const selected = limit > 0 ? chronological.slice(Math.max(0, chronological.length - limit)) : []
    return {
      messages: selected.map((entry) => entry.message),
      ...(lifecycle ? { lifecycle } : {}),
      consumedTo,
      hasMore: limit > 0 && chronological.length > limit,
      beforeOffset: selected[0]?.offset ?? end,
      ...(Number.isFinite(latest) ? { latestTimestamp: latest } : {}),
      ...(malformedRecordCount > 0 ? { malformedRecordCount } : {}),
      ...(oversizedRecordCount > 0 ? { oversizedRecordCount } : {})
    }
  } finally {
    await closeTranscriptHandle(handle, filePath)
  }

  function retainPart(part: Buffer): void {
    if (lineOversized) {
      return
    }
    lineBytes += part.length
    if (lineBytes > MAX_NATIVE_CHAT_TRANSCRIPT_RECORD_BYTES) {
      lineParts.length = 0
      lineOversized = true
      oversizedRecordCount++
      return
    }
    lineParts.push(part)
  }

  function resetLine(): void {
    lineParts.length = 0
    lineBytes = 0
    lineOversized = false
  }

  function decodeLine(
    lineOffset: number,
    messages: { message: NativeChatMessage; offset: number }[]
  ): void {
    // Positional reads own their buffers; only split records require a reverse-order join.
    const bytes = lineParts.length === 1 ? lineParts[0] : Buffer.concat(lineParts.toReversed())
    let line = bytes.toString('utf8')
    if (line.endsWith('\r')) {
      line = line.slice(0, -1)
    }
    if (!line) {
      return
    }
    try {
      JSON.parse(line)
    } catch {
      if (ignoreNextMalformedRecord) {
        ignoreNextMalformedRecord = false
        return
      }
      malformedRecordCount++
      return
    }
    ignoreNextMalformedRecord = false
    const fallbackId = transcriptFallbackId(filePath, lineOffset)
    // Use provider lifecycle records from the same window; visible assistant text cannot prove completion.
    lifecycle ??= decodeLifecycle?.(line, fallbackId) ?? undefined
    const message = decode(line, fallbackId)
    if (message) {
      messages.push({ message, offset: lineOffset })
    }
  }
}

export async function readNativeChatTranscriptTail(
  args: ResolveSessionFileOptions & {
    agent: AgentType
    sessionId: string
    transcriptPath?: string
    filePath?: string
    limit: number
    beforeOffset?: number
    sourceOrder?: boolean
  },
  signal?: AbortSignal
): Promise<
  | {
      messages: NativeChatMessage[]
      lifecycle?: NativeChatTurnLifecycle
      hasMore: boolean
      beforeOffset: number
    }
  | { error: string; notFound?: true }
> {
  if (resolveNativeChatTranscriptAgent(args.agent) === 'opencode') {
    return readOpenCodeNativeChatTranscriptTail(
      { ...args, agent: args.agent === 'zcode' ? 'zcode' : undefined },
      {},
      signal
    )
  }
  const decode = nativeChatLineDecoderForAgent(args.agent)
  const decodeLifecycle = nativeChatTurnLifecycleDecoderForAgent(args.agent)
  if (!decode) {
    return { error: 'Transcript unavailable' }
  }
  let filePath: string | null
  try {
    filePath =
      args.filePath ?? (await resolveSessionFilePath(args.agent, args.sessionId, args, signal))
  } catch (error) {
    signal?.throwIfAborted()
    // Gate refusal is unavailable, never proof of a missing transcript.
    return { error: wslTranscriptFsRefusal(error).message }
  }
  signal?.throwIfAborted()
  // Session IDs can arrive before the first flush; missing paths stay retryable.
  if (!filePath) {
    return { error: 'Transcript unavailable', notFound: true }
  }
  try {
    const result = await readNativeChatTranscriptTailFile(
      filePath,
      args.limit,
      decode,
      true,
      args.beforeOffset,
      decodeLifecycle,
      signal,
      undefined,
      args.sourceOrder
    )
    signal?.throwIfAborted()
    return {
      messages: result.messages,
      // Historical pages cannot rewind live lifecycle; only the current tail describes present turn state.
      ...(args.beforeOffset === undefined && result.lifecycle
        ? { lifecycle: result.lifecycle }
        : {}),
      hasMore: result.hasMore,
      beforeOffset: result.beforeOffset
    }
  } catch (error) {
    signal?.throwIfAborted()
    const message = error instanceof Error ? error.message : String(error)
    return isENOENT(error) ? { error: message, notFound: true } : { error: message }
  }
}