Files
orca/src/main/native-chat/transcript-tail-reader.ts
T
9e4e6ddae5 feat(native-chat): render omp transcripts (#11523)
* feat(native-chat): render omp transcripts

omp already ships as a first-class launchable agent with session_id resume, but
its transcripts had no decoder, so native chat could not render it — the agent
runs and the conversation stays a raw terminal. This adds the decoder and wires
it through the same path Claude, Codex and Grok use.

omp writes one envelope per line, `{ type, id, parentId, timestamp, … }`, where
conversation turns are `type: 'message'` and the rest is session bookkeeping.
Reasoning arrives as a `thinking` content block inside the assistant turn, so
the mapping follows Claude rather than Codex: thinking becomes a text block on
an assistant message, where Codex and Grok emit a separate reasoning role only
because their transcripts carry dedicated reasoning records.

  - toolCall -> tool-call, arguments passed through as the object omp writes
  - toolResult -> tool role, isError preserved
  - developer -> system, matching the Codex non-user/non-assistant fallback
  - blob-handle images drop, as the Claude mapper drops an image record with
    neither path nor url
  - bookkeeping and unrecognized types skip rather than throw

Session files are `<ISO timestamp>_<session id>.jsonl` under a per-cwd directory,
so the resolver matches the id as a base-name suffix the way Codex rollout files
are matched, and honors OMP_CODING_AGENT_DIR through normalizeAgentSessionsDir
so it stays consistent with the AI Vault scanner.

omp records no interruption or abort event, so unlike Claude and Codex there is
no NATIVE_CHAT_INTERRUPTED_STATUS_TEXT path.

Verified against 94,603 lines of real omp transcripts across four sessions:
50,546 records decoded, zero malformed, zero thrown.

* fix(native-chat): complete omp record coverage and gate remote transcripts

Review fixes on the omp transcript decoder.

omp writes several record types with no `content` field, so they decoded
to zero blocks and disappeared from the chat view entirely:

- `bashExecution` / `pythonExecution`: TUI `!command` runs, now a tool turn
- `fileMention`: `@path` attachments, listed by path (never `files[].content`,
  which is an auto-read dump)
- `custom_message` and legacy `custom` / `hookMessage` rows, gated on
  `display` the way omp's own renderer gates them

Also:

- `stopReason: 'aborted'` turns now surface as the interrupted row, matching
  the Claude and Codex decoders. An abort carrying partial content keeps it.
- A cancelled command cell now reads as errored. Every omp cancel path emits
  `exitCode: undefined`, which JSON drops, so an `exitCode !== 0` check read a
  cancelled run as a clean success.
- omp joins Grok in requiring a locally readable transcript. Its hook reports
  no transcript path, so under Model-A SSH the chat view opened against a disk
  this process cannot read and never loaded. Applies on mobile too, which
  shares the same allowlist.
- The session-file walk prunes omp's per-session subagent artifact
  directories, matching the AI Vault scanner. It was returning a subagent
  transcript instead of the parent session, and cost a full recursive readdir
  on every resolve.

* style(native-chat): apply oxfmt to the omp review fixes

Mobile CI gates `oxfmt --check`; the two root files were unformatted too,
just ungated there. Line wrapping only, no behavior change.

---------

Co-authored-by: plotarmordev <299844489+plotarmordev@users.noreply.github.com>
Co-authored-by: Brennan Benson <79079362+brennanb2025@users.noreply.github.com>
2026-08-07 00:58:29 -07:00

254 lines
8.1 KiB
TypeScript

import { open, stat } from 'node:fs/promises'
import type {
AgentType,
NativeChatMessage,
NativeChatTurnLifecycle
} from '../../shared/native-chat-types'
import { resolveNativeChatTranscriptAgent } from '../../shared/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 {
nativeChatTurnLifecycleDecoderForAgent,
type NativeChatTurnLifecycleDecoder
} from './transcript-turn-lifecycle'
export const MAX_NATIVE_CHAT_TRANSCRIPT_RECORD_BYTES = 2 * 1024 * 1024
const TAIL_CHUNK_BYTES = 64 * 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
): Promise<{
messages: NativeChatMessage[]
lifecycle?: NativeChatTurnLifecycle
consumedTo: number
hasMore: boolean
beforeOffset: number
malformedRecordCount?: number
oversizedRecordCount?: number
}> {
const end = Math.min((await stat(filePath)).size, endOffset ?? Number.MAX_SAFE_INTEGER)
if (end === 0) {
return { messages: [], consumedTo: 0, hasMore: false, beforeOffset: 0 }
}
const handle = await open(filePath, 'r')
const lineParts: Buffer[] = []
let lineBytes = 0
let lineOversized = false
let lifecycle: NativeChatTurnLifecycle | undefined
let malformedRecordCount = 0
let oversizedRecordCount = 0
let ignoreNextMalformedRecord = false
try {
const consumedTo = includeTrailingLine ? end : await findLastCompleteLineEnd(handle, end)
if (consumedTo === 0) {
return { messages: [], consumedTo: 0, hasMore: false, beforeOffset: 0 }
}
const newestFirst: { message: NativeChatMessage; offset: number }[] = []
const finalByte = Buffer.allocUnsafe(1)
await handle.read(finalByte, 0, 1, consumedTo - 1)
ignoreNextMalformedRecord = finalByte[0] !== 0x0a
let cursor = consumedTo - (finalByte[0] === 0x0a ? 1 : 0)
while (cursor > 0 && newestFirst.length <= limit) {
const start = Math.max(0, cursor - TAIL_CHUNK_BYTES)
const buffer = Buffer.allocUnsafe(cursor - start)
const { bytesRead } = await handle.read(buffer, 0, buffer.length, start)
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)
}
const chronological = newestFirst.toReversed()
// Why: slice(-0) returns the whole array, so a non-positive limit must
// window to nothing explicitly rather than leak every buffered record.
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,
...(malformedRecordCount > 0 ? { malformedRecordCount } : {}),
...(oversizedRecordCount > 0 ? { oversizedRecordCount } : {})
}
} finally {
await handle.close()
}
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 {
let line = Buffer.concat([...lineParts].toReversed()).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)
// Why: scan the same bounded JSONL window for provider-authored lifecycle
// records so reconnect snapshots can replay completion without guessing
// from the last visible assistant message.
lifecycle ??= decodeLifecycle?.(line, fallbackId) ?? undefined
const message = decode(line, fallbackId)
if (message) {
messages.push({ message, offset: lineOffset })
}
}
}
async function findLastCompleteLineEnd(
handle: Awaited<ReturnType<typeof open>>,
end: number
): Promise<number> {
const lastByte = Buffer.allocUnsafe(1)
await handle.read(lastByte, 0, 1, end - 1)
if (lastByte[0] === 0x0a) {
return end
}
let cursor = end
while (cursor > 0) {
const start = Math.max(0, cursor - TAIL_CHUNK_BYTES)
const buffer = Buffer.allocUnsafe(cursor - start)
const { bytesRead } = await handle.read(buffer, 0, buffer.length, start)
const newline = buffer.subarray(0, bytesRead).lastIndexOf(0x0a)
if (newline >= 0) {
return start + newline + 1
}
cursor = start
}
return 0
}
export async function readNativeChatTranscriptTail(
args: ResolveSessionFileOptions & {
agent: AgentType
sessionId: string
transcriptPath?: string
filePath?: string
limit: number
beforeOffset?: number
}
): Promise<
| {
messages: NativeChatMessage[]
lifecycle?: NativeChatTurnLifecycle
hasMore: boolean
beforeOffset: number
}
| { error: string; notFound?: true }
> {
const decode = nativeChatLineDecoderForAgent(args.agent)
const decodeLifecycle = nativeChatTurnLifecycleDecoderForAgent(args.agent)
const filePath = args.filePath ?? (await resolveSessionFilePath(args.agent, args.sessionId, args))
if (!decode) {
return { error: 'Transcript unavailable' }
}
// Why: a new agent session can report its id before the first JSONL flush;
// callers keep that miss in loading/retry rather than showing a false error.
if (!filePath) {
return { error: 'Transcript unavailable', notFound: true }
}
try {
const result = await readNativeChatTranscriptTailFile(
filePath,
args.limit,
decode,
true,
args.beforeOffset,
decodeLifecycle
)
return {
messages: result.messages,
// Why: an older pagination page must not rewind the live lifecycle; only
// the current transcript tail can authoritatively describe turn state.
...(args.beforeOffset === undefined && result.lifecycle
? { lifecycle: result.lifecycle }
: {}),
hasMore: result.hasMore,
beforeOffset: result.beforeOffset
}
} catch (error) {
const message = error instanceof Error ? error.message : String(error)
return (error as NodeJS.ErrnoException | null)?.code === 'ENOENT'
? { error: message, notFound: true }
: { error: message }
}
}