Support Codex subagent transcripts
This commit is contained in:
1 parent
7d9df5d572
commit
83b113ef0f
6 files changed
+557
-38
No files matched your search
+40
-14
@@ -1,9 +1,10 @@
|
||||
# Subagents
|
||||
|
||||
A session's subagents -- the helpers a Claude Code session starts through its
|
||||
Task tool -- each get a transcript of their own, listed under the session's
|
||||
card and readable in the same transcript view the session has. Designed
|
||||
2026-09-05; the decisions Bryan has not yet reviewed are in `DECISIONS.md`.
|
||||
A session's subagents -- helpers started by Claude Code's Task tool or Codex's
|
||||
collaboration tools -- each get a transcript of their own, listed under the
|
||||
session's card and readable in the same transcript view the session has.
|
||||
Designed 2026-09-05; extended to Codex's multiplexed app-server threads on
|
||||
2026-09-13. The decisions Bryan has not yet reviewed are in `DECISIONS.md`.
|
||||
|
||||
## What a subagent is here
|
||||
|
||||
@@ -14,24 +15,33 @@ own. Everything it shares with a session -- the transcript file format, the
|
||||
paging routes, the SSE stream, the phone's cache and rendering -- is reused
|
||||
by addressing, not by copying.
|
||||
|
||||
The CLI reports a subagent's messages on the parent's own stream-json
|
||||
output, each carrying `parent_tool_use_id` = the id of the Task `tool_use`
|
||||
that started it. Before this the translator dropped those lines
|
||||
Claude reports a subagent's messages on the parent's own stream-json output,
|
||||
each carrying `parent_tool_use_id` = the id of the Task `tool_use` that started
|
||||
it. Before this the translator dropped those lines
|
||||
(`subagent_events_are_not_duplicated_into_the_transcript`); now it routes
|
||||
them to that subagent's own translator and transcript. The parent's
|
||||
transcript still shows only the Task call itself.
|
||||
|
||||
Codex app-server multiplexes every thread in the session tree onto the root
|
||||
process's stdout. Its notifications carry `threadId`; `subAgentActivity`
|
||||
items name the child thread and its lifecycle, and `collabAgentToolCall`
|
||||
items carry the spawn prompt. The Codex translator routes a non-root
|
||||
`threadId` exactly as Claude routes a `parent_tool_use_id`. The child thread
|
||||
id is the subagent id on disk. An asynchronously delivered `agentMessage` is
|
||||
a `PeerMessage`, not assistant text from the recipient.
|
||||
|
||||
## Storage
|
||||
|
||||
Under the session directory:
|
||||
|
||||
```
|
||||
<session>/subagents/<tool_use_id>/meta.json {title, created}
|
||||
<session>/subagents/<tool_use_id>/transcript.jsonl same SeqEvent lines as the session's
|
||||
<session>/subagents/<subagent_id>/meta.json {title, created}
|
||||
<session>/subagents/<subagent_id>/transcript.jsonl same SeqEvent lines as the session's
|
||||
```
|
||||
|
||||
The id is the Task tool_use id (`toolu_…`), which is unique, stable across a
|
||||
backend restart, and already the key everything on the parent side uses.
|
||||
The id is Claude's Task tool_use id (`toolu_…`) or Codex's child thread id.
|
||||
Both are unique, stable across a backend restart, and already the key their
|
||||
parent-side lifecycle uses.
|
||||
Only ids matching `[A-Za-z0-9_-]+` are ever created or looked up, since the
|
||||
id becomes a path.
|
||||
|
||||
@@ -119,6 +129,16 @@ transcript is still being written to and its process is the session's to stop.
|
||||
precisely the one nothing in this process has touched -- and it would
|
||||
otherwise read `running` again every time its session was started.
|
||||
|
||||
For Codex the same lifecycle is expressed by app-server rather than Claude's
|
||||
task notices: `subAgentActivity.started` creates the child,
|
||||
`subAgentActivity.interacted` reopens it, and `completed` or `interrupted`
|
||||
finishes it. A child's own `turn/completed` is not its end; it remains running
|
||||
until that activity edge. The root's `turn/completed` reports `waiting` while
|
||||
the registry contains an open child, and the last activity completion reports
|
||||
`idle` if the root is between turns. Because the child thread id is also the
|
||||
on-disk id, an adopted driver can route and finish a child whose spawn record
|
||||
is already behind the durable stdout offset.
|
||||
|
||||
A subagent that was mid-flight when the backend restarted keeps working:
|
||||
the registry reopens the existing transcript on the next child line, and
|
||||
the file continues its sequence -- the same reopening #4 describes, whether
|
||||
@@ -127,9 +147,12 @@ the backend was down nothing recorded that until the next line arrives, so
|
||||
its last status stays `Running`, which the list reports as **unknown**
|
||||
rather than as running (see the wire shape) until then.
|
||||
|
||||
Title: the Task call's `description` input, then ` (<subagent_type>)` when
|
||||
one is given; falling back to the tool's name when the child arrives before
|
||||
(or without) the parent call being seen.
|
||||
Title: for Claude, the Task call's `description` input, then
|
||||
` (<subagent_type>)` when one is given; falling back to the tool's name when
|
||||
the child arrives before (or without) the parent call being seen. For Codex,
|
||||
the first lifecycle record uses the spawned thread's name or the last segment
|
||||
of `agentPath`, with underscores shown as spaces, then falls back to
|
||||
`subagent`.
|
||||
|
||||
## Server layout
|
||||
|
||||
@@ -142,6 +165,9 @@ one is given; falling back to the tool's name when the child arrives before
|
||||
- `session/claude/translate.rs` -- routes child lines by parent id, holds
|
||||
one child `Translator` per subagent, remembers pending Task calls'
|
||||
description/prompt/subagent_type.
|
||||
- `session/codex/translate.rs` -- routes multiplexed app-server notifications
|
||||
by thread id, remembers collaboration prompts, and translates activity
|
||||
edges into the same registry lifecycle.
|
||||
- `session/echo.rs` -- `/subagent [n]`: the test rig. Starts *n* (default 1)
|
||||
subagents at once, each named "helper k". Each writes the prompt as its
|
||||
user message, streams a few words of text, runs one `Bash` tool call, then
|
||||
|
||||
Reference in new issue
Block a user