feat: support a configurable secondary model for subagents#2064
Open
7Sageer wants to merge 16 commits into
Open
feat: support a configurable secondary model for subagents#20647Sageer wants to merge 16 commits into
7Sageer wants to merge 16 commits into
Conversation
🦋 Changeset detectedLatest commit: 5a58ff1 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
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 |
7Sageer
force-pushed
the
feat-subagent-k27
branch
from
July 22, 2026 15:02
2dc8bf8 to
d2ce676
Compare
7Sageer
marked this pull request as ready for review
July 23, 2026 06:17
commit: |
…dary_model] The secondary model becomes a model-domain concept next to default_model so future consumers beyond subagents can share it: [secondary_model] model / effort in config.toml, KIMI_SECONDARY_MODEL / KIMI_SECONDARY_EFFORT env overrides, and the Agent / AgentSwarm per-spawn choice renamed from "subagent" to "secondary".
…aces State that [secondary_model], its env overrides, the Agent/AgentSwarm model parameter, and SYSTEM.md take effect only under kimi web and experimental kimi -p (the TUI ignores them), and that --agent / --agent-file are available only under experimental kimi -p. Also drop the SYSTEM.md claim of parity with --agent/--agent-file, which was inaccurate: SYSTEM.md is an agent-core-v2 app-domain feature and also applies under kimi web, while the flags are gated at the CLI.
- Drop the "cheaper" claim from the Agent/AgentSwarm model parameter descriptions and the advertised model list — the secondary model is not necessarily the cheaper one. - Downgrade the changeset to patch, note the kimi web / experimental kimi -p effective surface, and tighten the wording. - Remove the onWillRestore stub fields from two lifecycle stubs; they belong to upcoming lifecycle work, not to this change.
The model catalog's not-configured throw now carries details.model, and wrapSubagentModelError only decorates errors whose details.model matches the bound model. Malformed [models.*] entries and unrelated config.invalid failures during agent creation pass through untouched instead of being misattributed to an invalid secondary-model alias.
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
Signed-off-by: 7Sageer <12210216@mail.sustech.edu.cn>
Individual agents can override this via the new `model_preference` field in their agent file. Signed-off-by: 7Sageer <sag77r@hotmail.com>
The recipe is now `model` plus the flattened ModelOverride field set. With any patch field set, a config overlay synthesizes a derived registry entry (base copy, patch merged into overrides, aliases dropped) so subagent spawning rides the standard effectiveModelConfig merge; with none, subagents bind the pointed entry directly. `default_effort` replaces `effort` (KIMI_SECONDARY_EFFORT rebinds) and doubles as the explicit subagent thinking; unset, thinking resolves naturally instead of inheriting the caller. The overlay strips the derived entry (and any defaultModel pointer to it) from writes, and the kap-server GET /models route hides it from pickers.
rebuildEffective only committed the caller-named domains, so a ConfigEffectiveOverlay or section env binding that rewrote a sibling domain (setting [secondary_model] synthesizes a derived models entry; removing the recipe retracts it) left consumers of the models section stale. Widen the commit candidates with every domain the recompute actually changed; commit() deepEqual-guards each candidate, so the widening costs nothing.
7Sageer
force-pushed
the
feat-subagent-k27
branch
from
July 23, 2026 15:03
28f6027 to
5a58ff1
Compare
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 GitHub issue. This PR addresses the secondary-model behavior identified during design review.
Problem
Subagents currently inherit the caller model, so users cannot route routine delegated work to a separately configured model while keeping the primary model available for quality-sensitive tasks. A misconfigured secondary alias should also be rejected before this feature allocates an Agent, rather than introducing a persisted or live ghost Agent.
What changed
[secondary_model]model and effort configuration, withKIMI_SECONDARY_MODELandKIMI_SECONDARY_EFFORTenvironment overrides.AgentandAgentSwarmchoose the secondary or primary model for new spawns.model_preference: primary | secondaryto Agent files and apply this precedence: explicit tool argument, target profile preference, configured secondary-model default, then caller-model inheritance.onDidCreateordering remain unchanged.Verification
agent-core-v2affected suites: 10 files, 268 tests.kap-serveraffected suites: 2 files, 114 tests.git diff --checkpassed.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.