fix: supervisor race condition, store.ts error handling#32
Open
Chasen-Liao wants to merge 20 commits into
Open
fix: supervisor race condition, store.ts error handling#32Chasen-Liao wants to merge 20 commits into
Chasen-Liao wants to merge 20 commits into
Conversation
…claude dir - Add scheduleLock to SubAgentSupervisor to prevent concurrent queue processing which could cause race conditions where max concurrent agents was exceeded - Add try/catch error handling to ShortTermMemory.saveToDisk() to gracefully handle file write failures instead of crashing - Add .claude/ to .gitignore to prevent skill documentation from being committed - Update yaml dependency version Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add MiniMax LLM provider that uses the Anthropic SDK format with base URL https://api.minimaxi.com/anthropic. Includes full integration with provider registry, configuration flow, and API key validation. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add missing minimax provider configuration in getDefaultConfig() with environment variable support MINIMAX_API_KEY, MINIMAX_BASE_URL, MINIMAX_MODEL, and MINIMAX_ENABLED. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Remove redundant await in MiniMaxProvider.streamText() - Ensure scheduleLock is released in SubAgentSupervisor error path Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add MINIMAX_PREFERRED_MODELS constant and add minimax to preferredByProvider records in provider-models.ts. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The correct endpoint is https://api.minimaxi.com/anthropic/v1/messages Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add fetchMiniMaxModels function to fetch available models from MiniMax API /v1/models endpoint during setup. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Fix Node.js version to 18+ in architecture section - Add exponential backoff crash recovery description to daemon mode - Expand contributing section with Agentic Expertise principles, code quality guidelines, getting started steps, and PR guidelines
- Add Feishu access state and config helpers in config.ts - Add FeishuChannel adapter using @larksuiteoapi/node-sdk - Add channel-routing.ts with pickOutboundChannelType helper - Add Feishu setup wizard prompts in CLI setup flow - Update README with Feishu documentation - Add Feishu CLI commands: list, approve, reject, remove, promote, demote, reset - Fix review feedback: JSON.parse validation, non-null assertions, WebSocket error handling - Add tests for Feishu config helpers and adapter functions
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.
Summary
scheduleLocktoSubAgentSupervisorto prevent concurrent queue processing that could exceed max concurrent agentsShortTermMemory.saveToDisk()for graceful file write failure handling.claude/to.gitignoreto prevent skill documentation from being committedTest plan
🤖 Generated with Claude Code