mirror of
https://github.com/stablyai/orca.git
synced 2026-10-23 00:03:52 +00:00
9e4e6ddae5
* 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>
48 lines
2.0 KiB
TypeScript
48 lines
2.0 KiB
TypeScript
export type NativeChatTranscriptAgent = 'claude' | 'codex' | 'grok' | 'omp'
|
|
|
|
/** Agents whose transcripts the native chat view can parse and render. */
|
|
export const NATIVE_CHAT_SUPPORTED_AGENTS: ReadonlySet<string> = new Set([
|
|
'claude',
|
|
'openclaude',
|
|
'codex',
|
|
'grok',
|
|
'omp'
|
|
])
|
|
|
|
export function isNativeChatSupportedAgent(agent: string | null | undefined): boolean {
|
|
return agent != null && NATIVE_CHAT_SUPPORTED_AGENTS.has(agent)
|
|
}
|
|
|
|
/** Agents whose hook discloses no transcript path (`extractAgentProviderSession`),
|
|
* so native chat can only reach the session file by scanning a sessions root on
|
|
* a disk THIS process can read. Under Model-A SSH that disk is the wrong host,
|
|
* so the chat view must stay closed instead of loading forever. */
|
|
export function nativeChatRequiresLocalTranscript(agent: string | null | undefined): boolean {
|
|
const transcriptAgent = resolveNativeChatTranscriptAgent(agent)
|
|
return transcriptAgent === 'grok' || transcriptAgent === 'omp'
|
|
}
|
|
|
|
/** True when the agent renders a digit-commit question selector that ignores
|
|
* typed label text (pasting "Blue" + Enter commits the highlighted FIRST
|
|
* option — STA-1860): Claude's AskUserQuestion and Codex 0.145's
|
|
* request_user_input card both behave this way, so answers must be delivered
|
|
* as per-option keystrokes. Other agents commit a pasted answer. */
|
|
export function shouldStepNativeChatAskAnswer(agent: string | null | undefined): boolean {
|
|
const transcriptAgent = resolveNativeChatTranscriptAgent(agent)
|
|
return transcriptAgent === 'claude' || transcriptAgent === 'codex'
|
|
}
|
|
|
|
export function resolveNativeChatTranscriptAgent(
|
|
agent: string | null | undefined
|
|
): NativeChatTranscriptAgent | null {
|
|
// Why: OpenClaude writes the Claude transcript format and layout even though
|
|
// Orca preserves its distinct agent identity for launch and UI behavior.
|
|
if (agent === 'claude' || agent === 'openclaude') {
|
|
return 'claude'
|
|
}
|
|
if (agent === 'codex' || agent === 'grok' || agent === 'omp') {
|
|
return agent
|
|
}
|
|
return null
|
|
}
|