multi-agent: move concurrency guidance into v2 usage hints - #27569
Conversation
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 168cddddc1
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: fe04e86efa
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 92644c48f2
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e13920ef12
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
For the record we won't support backward compatibility so it's not a big deal |
Why
Native Codex currently teaches multi-agent concurrency through the
spawn_agenttool description, while bridge-driven evals frame the same limit as a shared pool of active agent slots. That mismatch makes the model-facing story harder to reason about, especially because the tool-level wording does not make it explicit that the limit covers the whole agent team, including the current agent.This change gives native Codex the same mental model: tell the root agent and subagents how many active slots exist, and remove the separate
spawn_agentlimit wording.What changed
multi_agent_v2root and subagent usage hints with shared-slot guidance derived from the resolvedmax_concurrent_threads_per_sessionvalue.MultiAgentV2Configso initial context and forked histories consume the same canonical strings.spawn_agentdescription text and remove the now-unused limit plumbing from the tool spec path.Testing
just test -p codex-core usage_hintjust test -p codex-core multi_agent_v2_default_session_thread_cap_counts_rootjust test -p codex-core multi_agent_v2_default_usage_hints_use_configured_thread_capjust test -p codex-core spawn_agent_tool_v2_requires_task_name_and_lists_visible_modelsjust test -p codex-core multi_agent_feature_selects_one_agent_tool_family