[Feat] code_generate 도구 구현#12
Open
haein45 wants to merge 4 commits into
Open
Conversation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughOpenRouter 기반 LLM 클라이언트 캐싱, SSE 이벤트 스트리밍 인프라, 그리고 이를 통합한 ChangesLLM 클라이언트 및 SSE 스트리밍 인프라 추가
Sequence Diagram(s)sequenceDiagram
participant Caller
participant Tool as code_generate Tool
participant Emitter as SSEEmitter
participant LLMClient as get_llm(flash)
participant Queue as asyncio.Queue
Caller->>Tool: code_generate(problem, approach)
alt SSE emitter available
Tool->>Emitter: emit(tool_start, {name, input})
Emitter->>Queue: put(SSEEvent)
end
Tool->>LLMClient: request ChatOpenRouter instance
LLMClient->>LLMClient: check/create cached instance
LLMClient->>Tool: return ChatOpenRouter
Tool->>Tool: invoke LLM with system prompt
alt SSE emitter available
Tool->>Emitter: emit(tool_result, {output})
Emitter->>Queue: put(SSEEvent)
end
Tool->>Caller: return code string
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Collaborator
Author
|
@coderabbitai 리뷰 ㄱ |
|
✅ Actions performedReview triggered.
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
src/proovy_agent/graph/tools/code_generate.py (1)
27-44: ⚡ Quick winLLM 호출 실패 시 SSE 종료 이벤트를 보강해 주세요.
현재는 예외가 나면
tool_start만 발행되고 결과/오류 이벤트가 빠질 수 있습니다.try/except에서error이벤트를 emit하면 UI 상태가 안정적입니다.제안 diff
emitter = current_emitter.get() if emitter: await emitter.emit( "tool_start", {"name": "code_generate", "label": "🔧 검증 코드 생성 중..."} ) - llm = get_llm("flash") - messages = [ - {"role": "system", "content": _SYSTEM_PROMPT}, - {"role": "user", "content": f"문제: {problem}\n\n풀이 방향: {approach}"}, - ] - response = await llm.ainvoke(messages) - code = response.content.strip() + try: + llm = get_llm("flash") + messages = [ + {"role": "system", "content": _SYSTEM_PROMPT}, + {"role": "user", "content": f"문제: {problem}\n\n풀이 방향: {approach}"}, + ] + response = await llm.ainvoke(messages) + code = response.content.strip() + except Exception as exc: + if emitter: + await emitter.emit( + "error", + {"name": "code_generate", "message": str(exc)}, + ) + raise if emitter: await emitter.emit("tool_result", {"name": "code_generate", "output": code})🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@src/proovy_agent/graph/tools/code_generate.py` around lines 27 - 44, The code_generate function emits "tool_start" but doesn't emit a follow-up event if the LLM call fails; wrap the LLM invocation and result emission in a try/except and on exception call emitter.emit with an error event (e.g., "tool_error" or "tool_result" with an error payload) including the exception message and the tool name "code_generate", then re-raise or return an appropriate value so the UI gets a terminal event; ensure you reference current_emitter.get(), emitter.emit("tool_start", ...), llm.ainvoke(...), and emitter.emit("tool_result", ...) and add emitter.emit("tool_error", {"name":"code_generate", "error": str(e)}) in the except block.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/proovy_agent/common/sse/emitter.py`:
- Around line 22-28: Add the missing return type annotation to the async
generator method stream: change its signature in the Emitter class (async def
stream(self)) to specify AsyncIterator[dict[str, str]] so the function is
declared as returning an AsyncIterator of dict[str, str]; ensure you import
AsyncIterator from typing if not already imported.
In `@src/proovy_agent/graph/tools/code_generate.py`:
- Around line 38-40: The code assumes response.content is always a string;
change the extraction to use the LangChain-standard content_blocks on the
response from llm.ainvoke so it handles string, list, or dict formats: fetch
response.content_blocks, join or pick the primary textual block and then strip
it (with a safe fallback if content_blocks is missing or empty) instead of
calling response.content.strip(); update the logic around the response variable
returned by llm.ainvoke to use content_blocks and a fallback text to avoid
AttributeError.
---
Nitpick comments:
In `@src/proovy_agent/graph/tools/code_generate.py`:
- Around line 27-44: The code_generate function emits "tool_start" but doesn't
emit a follow-up event if the LLM call fails; wrap the LLM invocation and result
emission in a try/except and on exception call emitter.emit with an error event
(e.g., "tool_error" or "tool_result" with an error payload) including the
exception message and the tool name "code_generate", then re-raise or return an
appropriate value so the UI gets a terminal event; ensure you reference
current_emitter.get(), emitter.emit("tool_start", ...), llm.ainvoke(...), and
emitter.emit("tool_result", ...) and add emitter.emit("tool_error",
{"name":"code_generate", "error": str(e)}) in the except block.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 1228a28e-5f9e-42ef-ae14-f628397fa846
📒 Files selected for processing (5)
src/proovy_agent/common/llm/client.pysrc/proovy_agent/common/sse/context.pysrc/proovy_agent/common/sse/emitter.pysrc/proovy_agent/common/sse/events.pysrc/proovy_agent/graph/tools/code_generate.py
haein45
force-pushed
the
feat/10-code-generate
branch
2 times, most recently
from
6841430 to
64cb051
Compare
response.content가 list인 경우 .strip() 호출 시 AttributeError 발생하므로 isinstance 분기로 안전하게 텍스트 추출 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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.
📌 관련 이슈
🏷️ PR 타입
📝 작업 내용
src/proovy_agent/graph/tools/code_generate.py구현src/proovy_agent/common/sse/context.py구현 —ContextVar기반 SSE emitter 전달@tool로 정의,problem과approach를 입력받아 실행 가능한 Python 코드 반환get_llm("flash")사용으로 코드 생성current_emitterContextVar로 tool 내부에서 SSEtool_start/tool_result이벤트 발행📸 스크린샷
✅ 체크리스트
📎 기타 참고사항
ChatOpenRouter) 의존으로 단위 테스트 미작성current_emitterContextVar는 CoreSolver 노드가 실행 전set(), tool 내부에서get()으로 참조하는 방식Summary by CodeRabbit
릴리스 노트