docs: drop legacy secondary-model content and unify subagent terminology - #2891
Conversation
- Remove the legacy-engine secondary-model recipe section, the KIMI_SECONDARY_MODEL / KIMI_SECONDARY_EFFORT env entries, and the model_preference agent-file field: the default engine never reads them and the legacy engine is deprecated. - Remove the backward-compat note for a lone [secondary_model] model key; the code still reads it, but the docs now only document the current pool scheme. - Reframe the secondary_model section around the subagent model pool instead of a singular secondary model. - Unify zh terminology: 子 Agent -> subagent, 主 Agent -> main agent, covering prose, headings, anchors, the sidebar label, and the docs/AGENTS.md term table.
|
|
@codex review |
commit: |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ce13e15f03
ℹ️ About Codex in GitHub
Codex has been enabled to automatically 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 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| @@ -1,47 +1,47 @@ | |||
| # Agent 与子 Agent | |||
| # Agent 与 subagent | |||
There was a problem hiding this comment.
This changes the H1 of an existing docs page as part of the terminology cleanup, and the matching sidebar label was changed as well. The docs guide explicitly says not to change H1 titles or nav/sidebar labels, so this page title should stay stable and the terminology update should be limited to body text unless that docs rule is intentionally changed.
AGENTS.md reference: docs/AGENTS.md:L56-L56
Useful? React with 👍 / 👎.
2 participants
Related Issue
No linked issue — the problem is explained below.
Problem
The
[secondary_model]documentation taught two configuration systems at once: the current subagent model pool (default engine) and the legacy engine's "secondary-model recipe" (separate keys, patch fields, env overrides, amodel_preferenceprofile field). The legacy engine is deprecated, so the dual presentation — plus backward-compat notes for a legacymodelkey — is pure cognitive load for readers. The Chinese docs also translated the agent terms (子 Agent / 主 Agent) while the English docs use subagent / main agent, and the zh side had drifted into three competing renderings (子 Agent / 子代理).What changed
Documentation only; no code or behavior changes.
KIMI_SECONDARY_MODEL/KIMI_SECONDARY_EFFORTenv entries, and themodel_preferenceagent-file field. Verified against the agent-core-v2 source that the default engine never reads them.[secondary_model] modelkey. The code still reads it, so old configs keep working; the docs now only document the current pool scheme.secondary_modelsection around the subagent model pool instead of a singular "secondary model" concept.Checklist
gen-changesetsskill, or this PR needs no changeset. (No changeset: docs-only change.)gen-docsskill, or this PR needs no doc update. (This PR is the doc update.)