feat(agent-core): enable Preserved Thinking by default for kimi models - #1417
Merged
Conversation
Default `thinking.keep` to "all" when Thinking is on so prior `reasoning_content` is kept across turns. Add `[thinking] keep` to config.toml and keep `KIMI_MODEL_THINKING_KEEP` as an override (env > config > default); off-values disable it.
🦋 Changeset detectedLatest commit: 4d34cea 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 |
commit: |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 tracking issue — implements a direct maintainer/user request to default Preserved Thinking on.
Problem
For Kimi thinking models, prior turns'
reasoning_contentwas not preserved across turns unless the user manually exportedKIMI_MODEL_THINKING_KEEP=all. Multi-turn reasoning therefore lost continuity by default.What changed
thinking.keepto"all"while Thinking is on, so previous turns' reasoning is preserved across turns (Preserved Thinking).[thinking] keepfield toconfig.toml(string, default"all"); an off-value (false/0/no/off/none/null) disables it.KIMI_MODEL_THINKING_KEEPas an override with precedence env > config > default. Applies to thekimiprovider only, and only while Thinking is on.Tests and bilingual docs (
config-files.md,env-vars.md) are updated, and a changeset is included.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.