agent/codex
1
0
Fork 0
mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[codex] Calm multi-agent v2 usage prompts (#27037)

Browse Source 
## Summary
- tighten the default multi-agent v2 root and subagent usage hints to
bias toward local work
- add a pre-call gate to the v2 spawn_agent description for independent,
bounded, parallelizable subtasks

## Validation
- just fmt
- started just test -p codex-core, but it was interrupted before
completion per follow-up request to commit and push immediately
This commit is contained in:
jif
2026-06-08 22:32:10 +02:00
committed by GitHub
Unverified
parent f3a8074975
commit f9a680b907
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/src/config/mod.rs
+2 -2
View File
@@ -202,7 +202,7 @@ All agents in the team, including the agents that you can assign tasks to, are e
You can use `spawn_agent` to create a new agent, `followup_task` to give an existing agent a new task and trigger a turn, and `send_message` to pass a message to a running agent without triggering a turn.
Child agents can also spawn their own sub-agents.
You can decide how much context you want to propagate to your sub-agents with the `fork_turns` parameter.
Use multi-agent capabilities only when there is a real reason to split the work; handle trivial or simple tasks directly.
Default to doing the work yourself. Spawn sub-agents only for concrete, bounded subtasks that can run independently alongside useful local work and are likely to materially shorten completion time. Do not delegate simple tasks, small edits, routine searches, or work you can complete quickly yourself.
You will receive messages in the analysis channel in the form:
```
@@ -219,7 +219,7 @@ You can spawn sub-agents to handle subtasks, and those sub-agents can spawn thei
You can use `spawn_agent` to create a new agent, `followup_task` to give an existing agent a new task and trigger a turn, and `send_message` to pass a message to a running agent.
Child agents can also spawn their own sub-agents.
Use multi-agent capabilities only when there is a real reason to split the work; handle trivial or simple tasks directly.
Default to doing the work yourself. Spawn sub-agents only for concrete, bounded subtasks that can run independently alongside useful local work and are likely to materially shorten completion time. Do not delegate simple tasks, small edits, routine searches, or work you can complete quickly yourself.
When you provide a response in the final channel, that content is immediately delivered back to your parent agent.
codex-rs/core/src/tools/handlers/multi_agents_spec.rs
+1
View File
@@ -741,6 +741,7 @@ fn spawn_agent_tool_description_v2(
You are then able to refer to this agent as `task_3` or `/root/task1/task_3` interchangeably. However an agent `/root/task2/task_3` would only be able to communicate with this agent via its canonical name `/root/task1/task_3`.
The spawned agent will have the same tools as you and the ability to spawn its own subagents.
{inherited_model_guidance}
Only call this tool for a concrete, bounded subtask that can run independently alongside useful local work; otherwise continue locally.
It will be able to send you and other running agents messages, and its final answer will be provided to you when it finishes.
The new agent's canonical task name will be provided to it along with the message.
{concurrency_guidance}"#