Conversation
fix:CoWriterEditor scroll sync
* Core LLM hardening (slim): essential fixes and tests only * Add Anthropic and Local provider implementations
Feature/llm hardening core slim (#52)
Co-authored-by: Cursor <cursoragent@cursor.com>
feat: Add OpenRouter search provider
Restrict code execution scope and enforce import whitelist
feat/vision_slover
Merge the three core module rewrites from eval branch while preserving all existing dev features (chat, co_writer, guide, ideagen, research, API, frontend, Docker, etc.). Solve: Plan->ReAct->Write architecture (3 agents) with ToolRegistry for selective tool injection via YAML definitions. Question: Idea->Evaluate->Generate->Validate four-stage closed loop with coding question type and validator rejection mechanism. Personalization: Three ReAct agents (Reflection/Summary/Weakness) with TraceForest/TraceTree, event-driven integration with solve/question via EventBus (SOLVE_COMPLETE/QUESTION_COMPLETE) and MemoryReader. Also includes: benchmark pipeline, start.py CLI, shared module improvements (LLM client, RAG parsers, EventBus flush, etc.). Made-with: Cursor
Made-with: Cursor # Conflicts: # AGENTS.md # config/main.yaml # src/agents/question/agents/evaluator.py # src/agents/question/agents/idea_agent.py # src/agents/question/cli.py # src/agents/question/coordinator.py # src/agents/question/prompts/en/evaluator.yaml # src/agents/question/prompts/en/generator.yaml # src/agents/question/prompts/en/idea_agent.yaml # src/agents/question/prompts/en/validator.yaml # src/agents/question/prompts/zh/evaluator.yaml # src/agents/question/prompts/zh/generator.yaml # src/agents/question/prompts/zh/idea_agent.yaml # src/agents/question/prompts/zh/validator.yaml # src/agents/solve/agents/planner_agent.py # src/agents/solve/agents/solver_agent.py # src/agents/solve/agents/writer_agent.py # src/agents/solve/cli.py # src/agents/solve/context.md # src/agents/solve/main_solver.py # src/agents/solve/memory/scratchpad.py # src/agents/solve/prompts/en/planner_agent.yaml # src/agents/solve/prompts/en/solver_agent.yaml # src/agents/solve/prompts/en/writer_agent.yaml # src/agents/solve/prompts/zh/planner_agent.yaml # src/agents/solve/prompts/zh/solver_agent.yaml # src/agents/solve/prompts/zh/writer_agent.yaml # src/api/routers/question.py # src/config/settings.py # src/core/event_bus.py # src/personalization/__init__.py # src/tools/code_executor.py
The eval version of code_executor.py removed DEFAULT_SAFE_IMPORTS which is referenced by research_pipeline.py (from PR #196). Re-add the constant and apply it as default when no whitelist is provided. Made-with: Cursor
Keep evaluation code only on the eval branch. Made-with: Cursor
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
4 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.
Quick Summary
src/todeeptutor/+deeptutor_cli/with agent-native runtime (Tools + Capabilities).deeptutor), WebSocket API (/api/v1/ws), and Python SDK facade.chat,deep_solve,deep_question,deep_research,math_animator.rag,web_search,code_execution,reason,brainstorm,paper_search,geogebra_analysis.