fix(agent-core-v2): project support_efforts and default_effort in the model catalog - #1677
Merged
Merged
Conversation
… model catalog Align toProtocolModel with the v1 projection and the protocol wire schema by applying effectiveModelConfig and emitting support_efforts / default_effort, so clients of the v2 /models endpoint see thinking-effort levels again.
🦋 Changeset detectedLatest commit: 23a37b6 The changes in this PR will be included in the next version bump. This PR includes changesets to release 3 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
commit: |
Merged
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The v2 backend's model catalog (
/models) response dropssupport_effortsanddefault_effort, even though the protocol wire schema defines both fields and models declare them in config (e.g.support_efforts = ["low","high","max"],default_effort = "max"). Clients connected to the v2 backend — the web UI or any non-TUI consumer — receiveundefinedfor the effort fields and cannot render thinking-effort selection (the web UI falls back to a plain on/off toggle). The v1 catalog projection emits both fields, so this is a v1/v2 parity gap on a surface that claims wire compatibility.What changed
packages/agent-core-v2/src/app/modelCatalog/modelCatalog.ts:toProtocolModelnow applieseffectiveModelConfig(the v2 counterpart of v1'seffectiveModelAlias, which merges configoverrides) and projectssupport_efforts/default_effortalongside the existing fields, matching the v1 projection field-for-field.packages/agent-core-v2/test/app/modelCatalog/modelCatalog.test.ts: two new projection tests — effort fields declared directly on the model config, and effective effort values whenoverridesreplace them.@moonshot-ai/agent-core-v2patch.Verified:
lint:domain,typecheck, and the full agent-core-v2 test suite (3337 tests) pass.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.