refactor!: overhaul thinking config and effort resolution#1132
Open
liruifengv wants to merge 15 commits into
Open
refactor!: overhaul thinking config and effort resolution#1132liruifengv wants to merge 15 commits into
liruifengv wants to merge 15 commits into
Conversation
- kimi provider: emit thinking.effort in the new wire format; keep reasoning_effort mirrored during the transition - model catalog: thread support_efforts / default_effort from oauth through to /models - config schema: add supportEfforts / defaultEffort on model aliases - TUI: multi-segment thinking control in /model, new /effort command, footer effort display - switch status uses displayName and distinguishes model vs effort-only changes
- thinking-effort-switching.md: implemented multi-level effort switching - thinking-model-overhaul.md: follow-up refactor plan for the thinking state model
Replace default_thinking and thinking.mode with a single [thinking] enabled/effort table. ThinkingEffort is now an open string ('off' | 'on' | model-declared effort); effort levels come from each model's support_efforts instead of a fixed enum.
Centralize default and always_thinking clamp logic in resolveThinkingEffort/defaultThinkingEffortFor, and honor an explicitly configured effort when an always_thinking model is forced back on.
TUI keeps a single thinkingEffort field instead of the boolean + level pair; 'on' is normalized to the model default at the UI boundary.
BREAKING CHANGE: default_thinking and thinking.mode are removed from config; migrate to [thinking] enabled/effort.
🦋 Changeset detectedLatest commit: bcea992 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: |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 04f3a6a3a2
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Rename comments, error messages, parameter names, the SetThinkingPayload wire field (level -> effort), and TUI local variables so the thinking effort naming is consistent throughout. No behavior change.
…fort Rename liveLevel/prevLevel/levelChanged/commitLevel/effectiveLevel to liveEffort/prevEffort/effortChanged/commitEffort/effectiveEffort in the TUI model picker and config commands.
…tests Rename levelLabel -> effortLabel, EffortSelectorOptions.levels -> efforts, and 'effort level(s)' / 'default level' / 'requested level' wording in comments, error messages, slash-command description, and test titles to effort. Also restore the withThinking(effort) parameter rename in the Kimi provider that was accidentally reverted.
- OpenAI thinkingEffortToReasoningEffort and Anthropic clampEffort now normalize 'on' / unrecognized efforts instead of throwing, so boolean non-Kimi models no longer crash on session start. - ACP resolveCurrentThinkingEnabled treats a non-empty thinking.effort as enabled, matching agent-core's resolveThinkingEffort. - REST promptThinkingSchema accepts any non-empty effort string so model-declared efforts are not rejected at the API boundary.
…_effort The kimi provider now sends reasoning_effort only when the model declares support_efforts; boolean models (no support_efforts) send only thinking.type. Update the kimi e2e tests to drop the stale reasoning_effort expectation for the boolean test model.
Add effort = "high" to the documented [thinking] table in the config parse test and assert config.thinking.effort is resolved, so the new [thinking] effort field has direct parse coverage.
Capture the explore agent's test coverage review for the thinking overhaul PR, including P1/P2 gaps and the two open design questions, for follow-up test additions.
The /models endpoint now returns effort levels under a nested think_efforts object ({ support, valid_efforts, default_effort }). Parse it preferentially in both managed-kimi-code and open-platform model parsing, falling back to the legacy flat support_efforts / default_effort fields for older servers.
Drop the legacy flat support_efforts / default_effort fallback. The think_efforts object is now the single source, and its support flag gates the whole object — when support is not true, valid_efforts and default_effort are ignored entirely.
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 issue — this implements the internal design at
plan/thinking-model-overhaul.md.Problem
The thinking on/off toggle and effort level were scattered across config, agent-core, SDK, TUI, and providers, accumulating redundancy:
default_thinking(boolean),thinking.mode(auto/on/off, whereautoandonwere equivalent), andthinking.effortoverlapped semantically.ThinkingEffortenum ('off' | 'low' | 'medium' | 'high' | 'xhigh' | 'max') hardcoded levels that should come from each model'ssupport_efforts, forcing provider-specific mappings likexhigh → highfor Kimi.'on'leaked across TUI → SDK → agent-core as a ghost level that was never in the enum.always_thinkingwas clamped in three separate places (UI, getter, ACP adapter).thinking: boolean+thinkingLevel?: string) with five duplicate fallbacks.What changed
[thinking] { enabled, effort }.default_thinkingandthinking.modeare removed.enabled = falsemeans off; otherwiseeffort(or the model default) is used.ThinkingEffortis now an open string ('off' | 'on' | (string & {})). Effort levels come from each model's declaredsupport_efforts; providers normalize any undeclared level to "no effort" instead of rejecting it. ThekimiEffort/wireEffortToThinkingEffortmappings are gone.resolveThinkingEffort/defaultThinkingEffortForderive the default from the model (default_effort→ middle ofsupport_efforts→'on'). Thealways_thinkingclamp lives in one place and now honors an explicitly configured effort instead of discarding it.thinkingEffortfield instead of the boolean + level pair.'on'is normalized to the model default at the UI boundary so it never leaks past the picker.thinkingEffort/resolveThinkingEffort/defaultThinkingEffortForacross the codebase.This is a breaking change: existing
default_thinkingandthinking.modeare no longer read, and are stripped on the next config write. Docs include a "Deprecated fields" section with the migration path and the version the new fields were added in.Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.