Skip to content

Commit c97167b

Browse files
axisrowclaude
andauthored
feat(ux): show resolved model/effort in the /codex:rescue launch line (closes #34) (#35)
The launch line for the codex:codex-rescue subagent showed only the topic (codex:codex-rescue(<topic>)) and never the model/effort Codex actually uses — painful in background runs where the companion's stderr announce is swallowed. The Agent-tool `description` is free-form text composed by the caller before the subagent selects the model, so instruct the caller (commands/rescue.md) to include the resolved model/effort there: `<topic> model=<…> effort=<…>`. Aliases resolve to full ids (spark→gpt-5.3-codex-spark, sol→gpt-5.6-sol, terra→gpt-5.6-terra, luna→gpt-5.6-luna); unset → `default`. No desync risk because codex-rescue selects the model only from explicit user flags. Companion unchanged — announceRun (#24) stays for foreground-stderr; the launch line is covered by the skill layer. Co-authored-by: axisrow <[email protected]> Co-authored-by: Claude <[email protected]>
1 parent ec6e98b commit c97167b

1 file changed

Lines changed: 11 additions & 0 deletions

File tree

‎plugins/codex/commands/rescue.md‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -8,6 +8,17 @@ Invoke the `codex:codex-rescue` subagent via the `Agent` tool (`subagent_type: "
88
`codex:codex-rescue` is a subagent, not a skill — do not call `Skill(codex:codex-rescue)` (no such skill) or `Skill(codex:rescue)` (that re-enters this command and hangs the session). The command runs inline so the `Agent` tool stays in scope; forked general-purpose subagents do not expose it.
99
The final user-visible response must be Codex's output verbatim.
1010

11+
Launch-line description:
12+
13+
The `Agent` tool `description` parameter is free-form text that becomes the parenthesized label on the launch line, e.g. `codex:codex-rescue(<description>)`. It is composed before the subagent selects the model, so include the resolved model and effort in it so the user can see which Codex configuration is running — especially for background runs where the companion's stderr announce is not visible.
14+
15+
Format the description as `<short topic> model=<model> effort=<effort>`, resolving aliases to full ids the way the companion does:
16+
17+
- `spark` → `gpt-5.3-codex-spark`, `sol` → `gpt-5.6-sol`, `terra` → `gpt-5.6-terra`, `luna` → `gpt-5.6-luna`. A concrete id (e.g. `gpt-5.4-mini`) passes through unchanged.
18+
- When the user did not specify `--model`, use `model=default`. When they did not specify `--effort`, use `effort=default`.
19+
20+
Example: a request about "issue #144" with `--model sol --effort xhigh` → description `Codex консультация по #144 model=gpt-5.6-sol effort=xhigh`.
21+
1122
Raw user request:
1223
$ARGUMENTS
1324

0 commit comments

Comments
 (0)