feat(config): per-bot thinking/effort configuration and /effort command#97
Closed
Shiien wants to merge 2 commits intoxvirobotics:mainfrom
Closed
feat(config): per-bot thinking/effort configuration and /effort command#97Shiien wants to merge 2 commits intoxvirobotics:mainfrom
Shiien wants to merge 2 commits intoxvirobotics:mainfrom
Conversation
…ommand Add configurable thinking and effort levels for Claude sessions: - Add `thinking` and `effort` fields to BotConfig (per-bot JSON and env) - Pass thinking/effort to Claude Agent SDK query options - Display model, thinking mode, and effort level in Feishu/Telegram card stats - Add `/effort` command for runtime effort level switching within a session - Add duplicate tool_result suppression in executor to prevent API 400 errors - Re-throw updateCard errors for proper error propagation - Improve card stats format (use · separator, add cost display) Defaults: thinking=adaptive, effort=max (configurable per bot in bots.json) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Contributor
|
Closing — these PRs are outdated as the codebase has diverged significantly. Thank you for the contribution! Feel free to open a fresh PR against the current main if you'd like to revisit. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Configurable thinking and effort levels for Claude sessions, with runtime switching via
/effortcommand.Why
Different use cases benefit from different reasoning levels. Quick questions need less thinking (lower cost, faster), while complex tasks benefit from maximum effort. This lets operators configure defaults per bot and users adjust on the fly.
How
Configuration:
thinking(object, e.g.{"type": "adaptive"}) andeffort(low/medium/high/max) toBotConfigbots.json, with defaults: thinking=adaptive, effort=maxquery()optionsRuntime command:
/effort <level>— Switch effort level for current session (low/medium/high/max)Card display:
·separator, add cost displaySafety:
tool_resultsuppression in executor (prevents API 400 errors when SDK and bridge both respond to the same tool)updateCarderrors for proper propagationChecklist
npx tsc --noEmit)npm test— 175 tests)npm run lint)npm run build)