feat(agent-core-v2): advertise model capabilities in the subagent model picker - #2591
Merged
Conversation
|
commit: |
mbuckaway
pushed a commit
to mbuckaway/kimi-code
that referenced
this pull request
Aug 4, 2026
…el picker (MoonshotAI#2591) * feat(agent-core-v2): advertise model capabilities in the subagent model picker * chore(agent-core-v2): follow header-only comment convention * docs(agent-core-v2): note the model catalog collaborator in the AgentSwarmTool header
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Related Issue
No linked issue — the problem is explained below.
Problem
With the
secondary-modelexperiment enabled, the subagent collaboration tools (Agent/AgentSwarm) advertise the routable models in theirmodelparameter descriptions — but only as bare model ids. The parent agent has no way to tell whether the secondary model supports images or thinking, so it can delegate a multimodal task to a text-only model; the engine then silently degrades (media tools unregistered, images replaced with placeholder text) without the parent ever knowing.What changed
Each advertised model line now carries a
capabilities: ...suffix derived from the model catalog's resolved capability flags (image_in,video_in,audio_in,thinking,tool_use,dynamically_loaded_tools), e.g.:secondarymodel configured via a patch recipe resolves capabilities from the derived entry the subagent would actually run on.max_context_tokens) are deliberately excluded — only the boolean ability array is advertised.secondary-modelexperiment flag (default off) is enabled, so nothing changes on shipped surfaces.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.