Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
PlateerLab
xgen-cli
Repository navigation
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
More
items
도구 검색·조회·GET 실행 연결과 실제 모델 평가
- #89
#89
Merged
SonAIengine
merged 22 commits into
main
PlateerLab/xgen-cli:main
from
feat/live-tool-selection-evaluation
PlateerLab/xgen-cli:feat/live-tool-selection-evaluation
Copy head branch name to clipboard
Oct 13, 2026
Conversation
Commits
22
(22)
Checks
Files changed
Merged
도구 검색·조회·GET 실행 연결과 실제 모델 평가
#89
SonAIengine
merged 22 commits into
main
PlateerLab/xgen-cli:main
from
feat/live-tool-selection-evaluation
PlateerLab/xgen-cli:feat/live-tool-selection-evaluation
Copy head branch name to clipboard
Commits
Commits on Oct 5, 2026
실제 모델 계획 크기 비교의 prompt 충돌과 비용 측정 계약 조사
SonAIengine
committed
8f73803
View commit details
Copy full SHA for 8f73803
Browse repository at this point
평가용 공통 planning profile에 Step 상한 1·4를 결합하고 초과 응답을 거절
SonAIengine
committed
1bc2f07
View commit details
Copy full SHA for 1bc2f07
Browse repository at this point
계획 크기 pilot runner에 실제 driver·독립 oracle·비용 사전 예약을 연결하고 18회 계약 검증
SonAIengine
committed
250fe39
View commit details
Copy full SHA for 250fe39
Browse repository at this point
DeepSeek 개발 smoke 18회 결과와 120회 사전 등록을 고정하고 model·fingerprint·입력 변경을 차단
SonAIengine
committed
24f1f49
View commit details
Copy full SHA for 24f1f49
Browse repository at this point
DeepSeek 계획 크기 120회 비교와 최종 응답 계약 실패 기록
SonAIengine
committed
4625d15
View commit details
Copy full SHA for 4625d15
Browse repository at this point
최종 응답 schema와 Receipt 기반 실행 기록을 추가하고 24회 검증
Show description for 8feaa1d
SonAIengine
committed
8feaa1d
View commit details
Copy full SHA for 8feaa1d
Browse repository at this point
최신 검증 Receipt를 완료 조건으로 연결하고 32개 시나리오 검증
Show description for d04322f
SonAIengine
committed
d04322f
View commit details
Copy full SHA for d04322f
Browse repository at this point
완료 검증 40회 비교와 틀린 완료 차단·비용 증가 증거 보존
SonAIengine
committed
a129bd2
View commit details
Copy full SHA for a129bd2
Browse repository at this point
검증 실패 JSON 진단과 수정·재검증 경로 검증 및 16회 비교 보존
SonAIengine
committed
9703233
View commit details
Copy full SHA for 9703233
Browse repository at this point
검증 진단의 현재 digest 전달과 16회 비교에서 성공 4건에서 8건 확인
SonAIengine
committed
d05fa3b
View commit details
Copy full SHA for d05fa3b
Browse repository at this point
graph-tool-call 내부 검색을 연결하고 두 명세와 실제 도구 1108개 수집 검증
SonAIengine
committed
4c5f6b1
View commit details
Copy full SHA for 4c5f6b1
Browse repository at this point
agent loop에 도구 검색·명세 조회를 연결하고 snapshot·입력·Receipt 검증 172개 통과
SonAIengine
committed
6206815
View commit details
Copy full SHA for 6206815
Browse repository at this point
연결된 GET 도구 실행과 인증 분리를 구현하고 두 API의 Receipt·재개를 검증
SonAIengine
committed
885b1af
View commit details
Copy full SHA for 885b1af
Browse repository at this point
도구 품질 실패의 책임 판정 기준을 정리하고 저장소별 TODO를 분리
SonAIengine
committed
429a4e6
View commit details
Copy full SHA for 429a4e6
Browse repository at this point
32개 조회 요청의 검색·전달을 분리 평가하고 큰 명세 실패 14건의 책임을 구분
SonAIengine
committed
e7d96f3
View commit details
Copy full SHA for e7d96f3
Browse repository at this point
대형 도구 명세의 전달 실패 14건을 제한된 조회와 원본 검증 분리로 해결
SonAIengine
committed
7cf69ff
View commit details
Copy full SHA for 7cf69ff
Browse repository at this point
실제 모델 120회로 검색어 생성과 도구 선택을 분리 평가하고 정답 기준 한계 기록
SonAIengine
committed
e2e6870
View commit details
Copy full SHA for e2e6870
Browse repository at this point
Commits on Oct 8, 2026
graph-tool-call 0.47.0으로 고정을 올리고 이전 버전 collection 오류를 구분
Show description for ee5c63e
SonAIengine
and
claude
committed
ee5c63e
View commit details
Copy full SHA for ee5c63e
Browse repository at this point
Commits on Oct 10, 2026
Merge pull request #84 from PlateerLab/feat/graph-tool-call-0.47
SonAIengine
authored
d395df5
View commit details
Copy full SHA for d395df5
Browse repository at this point
graph-tool-call이 없는 CI에서 worker 의존 Python 테스트 5개를 건너뛰도록 수정
Show description for 41c9008
SonAIengine
and
claude
committed
41c9008
View commit details
Copy full SHA for 41c9008
Browse repository at this point
Merge pull request #85 from PlateerLab/fix/python-tests-skip-without-gtc
SonAIengine
authored
78e9ca0
View commit details
Copy full SHA for 78e9ca0
Browse repository at this point
Commits on Oct 13, 2026
Merge branch 'main' into feat/live-tool-selection-evaluation
SonAIengine
authored
c20ecff
View commit details
Copy full SHA for c20ecff
Browse repository at this point
You can’t perform that action at this time.
