fix: apply output cap during compaction

[ktwu01]

Related Issue

Fixes #476

Problem

Normal model requests pass the configured model maxOutputSize into completion budget resolution, but full compaction requests only passed the reserved-context fallback. For models with a very large context window and a smaller output cap, compaction could therefore send a completion cap based on context size rather than the model output limit.

What changed

• Pass this.agent.config.maxOutputSize into full compaction's completion budget resolution.
• Added a regression test that patches the resolved runtime provider with a model output cap and verifies compaction sends that cap.
• Added a changeset for @moonshot-ai/agent-core and the CLI bundle.

Validation

• pnpm --filter @moonshot-ai/agent-core exec vitest run test/agent/compaction/full.test.ts
• pnpm --filter @moonshot-ai/agent-core typecheck
• pnpm --filter @moonshot-ai/kimi-code typecheck
• pnpm exec oxlint --type-aware packages/agent-core/src/agent/compaction/full.ts packages/agent-core/test/agent/compaction/full.test.ts
• Read-only staged diff audit for internal identifiers and secrets: clean

Checklist

• I have read the CONTRIBUTING document.
• I have linked a related issue, or explained the problem above.
• I have added tests that prove my feature works.
• Ran gen-changesets skill, or this PR needs no changeset.
• Ran gen-docs skill, or this PR needs no doc update.

[changeset-bot]

🦋 Changeset detected

Latest commit: a7b66d6

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 2 packages

Name	Type
@moonshot-ai/agent-core	Patch
@moonshot-ai/kimi-code	Patch

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

[liruifengv]

Thanks for contributing. This PR appears to be part of a batch generated by AI scanning the issue list, and we are not accepting this kind of bulk PR, so it is being closed.