2. ตั้งค่าและปรับแต่งผู้ช่วยในแบบของคุณ [GA]

เปิดใช้ API - ผู้ดูแลระบบ Bumble จะเป็นผู้ดำเนินการในส่วนนี้ โปรดทราบว่าการดำเนินการนี้ไม่ได้มีไว้สำหรับผู้เข้าร่วม เนื่องจากผู้เข้าร่วมอาจไม่มีสิทธิ์เข้าถึงคอนโซล Google Cloud

ต้องเพิ่มข้อกำหนดเบื้องต้นนี้ในเวิร์กช็อปเพื่อให้ผู้ดูแลระบบคลาวด์ดำเนินการให้เสร็จสมบูรณ์

กำหนดค่าการปรับเปลี่ยนในแบบของคุณ

"การพัฒนาซอฟต์แวร์สำหรับผู้บริโภคและแอปบนอุปกรณ์เคลื่อนที่" ไม่อยู่ในเมนูแบบเลื่อนลง ดังนั้นผู้ใช้จึงต้องเลือก "กำหนดเอง" แล้วเพิ่มข้อความนี้

จากนั้นก็ต้องปิดป๊อปอัปนั้น

3. กำหนดค่าตัวเชื่อมต่อข้อมูล [GA]

โดยผู้ดูแลระบบ Gemini Enterprise จะเป็นผู้ดำเนินการ ไม่ใช่ผู้เข้าร่วม ดังนั้นโปรดระบุข้อกำหนดเบื้องต้นนี้สำหรับเวิร์กช็อป

4. การโต้ตอบพื้นฐานกับตัวเชื่อมต่อ Jira [GA]

ก่อนอื่น คุณต้องให้สิทธิ์ตัวเชื่อมต่อเพื่อให้ผู้เข้าร่วมแต่ละคนใช้ตัวเชื่อมต่อ Jira และ GitHub ได้ โดยภาพหน้าจอสำหรับขั้นตอนนี้จะอยู่ด้านล่าง

image-1-jira-authozie.png

image-2-jira-authoziation-page.png

image-3-after-jira-authoziation.png

ทำเช่นเดียวกันกับ github

นอกจากนี้ ให้ขอปิดใช้ Google Search เมื่อทำงานในตัวเชื่อมต่อ Jira หรือ GitHub

image-4-disable-google-search.png

1. ค้นหาคีย์โปรเจ็กต์ Jira - ให้คำแนะนำเกี่ยวกับวิธีเปิดแชทเพื่อถาม Gemini โดยภาพหน้าจอด้านล่างนี้ใช้เพื่ออ้างอิง

Image-5-jira-list-projects.png

ให้ทำแบบเดียวกันกับการทดสอบอื่นๆ ด้วย เช่น สร้างงาน แสดงความคิดเห็น อัปเดตสถานะ ฯลฯ นอกจากนี้ เรายังได้อัปเดตภาพหน้าจอที่เกี่ยวข้องให้สอดคล้องกันด้วย

image-6-jira-create-projects-1.png

image-7-jira-create-projects-2.png

image-8-jira-create-projects-3.png

image-9-jira-comment-1.png

image-10-jira-comment-2.png

image-11-jira-comment-3.png

image-12-jira-status-1.png

image-13-jira-status-2.png

image-14-jira-status-3.png

5. การโต้ตอบพื้นฐานกับตัวเชื่อมต่อ GitHub [GA]

หากต้องการคอมมิตรายการสิ่งที่ต้องทำ คุณต้องทราบชื่อที่เก็บ ดังนั้นเรามาใช้พรอมต์แบบด้านล่างเพื่อรับชื่อที่เก็บกัน

ก่อนที่จะเรียกใช้คำสั่งนี้ คุณต้องบอกให้ผู้เข้าร่วมปิดใช้ตัวเชื่อมต่ออื่นๆ และใช้เฉพาะ GitHub

สำหรับการทดสอบทั้งหมด ให้รับรูปภาพที่เกี่ยวข้องและเพิ่มตามนั้น ด้านล่างนี้คือชื่อไฟล์ภาพหน้าจอ

image-15-github-enable-1.png

image-16-github-list-repo-2.png

image-17-github-list-commit-3.png

image-18-github-list-pull-request-4.png

image-19-github-list-pull-request-summary-5.png

6. ตรวจสอบเพื่อเปรียบเทียบเอกสารประกอบกับการดำเนินการ [GA]

ในขั้นตอนที่ 2 ของส่วน "เอกสารข้อกำหนดในการอัปโหลด" ควรทำ "อัปโหลดไฟล์ชื่อ requirements.txt พร้อมเนื้อหาต่อไปนี้" ก่อน เพื่อให้ผู้เข้าร่วมมีไฟล์ที่สร้างไว้ในแล็ปท็อปของตนเอง หากต้องการสร้างไฟล์ .txt ใน Mac ให้ใช้แอป TextEdit ในตัว เปิด TextEdit ไปที่เมนูด้านบน แล้วคลิกรูปแบบ > สร้างข้อความธรรมดา พิมพ์ข้อความ คลิกไฟล์ > บันทึก ตั้งชื่อไฟล์ (ตรวจสอบว่าลงท้ายด้วย .txt) เลือกตำแหน่ง แล้วคลิก ระบุวิธีการที่คล้ายกันสำหรับแล็ปท็อปอื่นๆ

นอกจากนี้ "ในอินเทอร์เฟซแชทของ Gemini Enterprise ให้คลิกไอคอน + (บวก) หรือลากและวางไฟล์เพื่ออัปโหลด" ยังไม่เกี่ยวข้องในขั้นตอนนี้

หลังจากสร้างข้อความข้อกำหนดแล้ว ให้เปิดหน้าต่างแชทใหม่ ปิดใช้ตัวเชื่อมต่ออื่นๆ และเปิดใช้เฉพาะ Jira จากนั้นสร้างข้อมูลตัวอย่างโดยใช้ Gemini แล้วเรียกใช้การวิเคราะห์ จากนั้นผู้ใช้จะต้องอัปโหลดไฟล์ txt ไปยังแอป Gemini ดูภาพหน้าจอของการทดสอบนี้ด้านล่าง ซึ่งเป็นชื่อไฟล์ของภาพหน้าจอตามลำดับ

image-20-jira-req-txt-1.png

รูปภาพสำหรับสร้างข้อมูลตัวอย่างโดยใช้ Gemini

image-21-jira-create-ticket-2.png

image-22-jira-create-ticket-confirmation-3.png

image-23-jira-create-ticket-done-status-confirmation-4.png

image-24-jira-create-ticket-confirmation-5.png

image-25-jira-create-ticket-inprogress-status-confirmation-6.png

image-26-jira-create-ticket-created-6.png

image-27-jira-create-tinjira-portal-7.png

รูปภาพสำหรับเรียกใช้การวิเคราะห์

image-28-jira-run-analysis-1.png

image-29-jira-run-analysis-output-2.png

หมายเหตุ "คลิกการอ้างอิงที่ระบุไว้ในคำตอบเพื่อยืนยันว่า Gemini อ้างอิงส่วนใดของไฟล์หรือคำขอ Jira" แต่ฉันไม่เห็นการอ้างอิงจริงๆ

7. วิเคราะห์งานค้างของสปรินต์ด้วย NotebookLM [GA]

ในทำนองเดียวกัน ในการสร้างไฟล์ txt เป็นครั้งแรกนี้ ให้ระบุวิธีการสำหรับไฟล์นั้น แล้วคลิกสร้าง Notebook ใหม่ จากนั้นอัปโหลดไฟล์ชื่อ retro.txt พร้อมบันทึกจำลองต่อไปนี้

ให้คำสั่งเพื่อสร้างข้อมูลเชิงลึกเกี่ยวกับสิ่งที่ต้องคลิก

นี่คือไฟล์รูปภาพของภาพหน้าจอดังกล่าว

image-30-notebook-lm-output.png

image-31-notebook-lm-mindmap.png

ตรวจสอบภาพหน้าจอของการทดสอบจริงและอัปเดตวิธีการหากมีสิ่งใดขาดหายไป ชื่อไฟล์ของรูปภาพภาพหน้าจอ นอกจากนี้ ให้ระบุว่าการดำเนินการเหล่านี้ต้องใช้เวลาสักครู่ ดังนั้นให้ทริกเกอร์และไปยัง Lab ถัดไปจนกว่าจะพร้อม นอกจากนี้ ให้ระบุรายละเอียดเกี่ยวกับสิ่งที่ต้องตรวจสอบในรายงาน ตรวจสอบเกี่ยวกับ

deep-research-1.png

deep-research-2.png

deep-research-3.png

9. ระดมความคิดด้วยการสร้างไอเดีย [ตัวอย่างแบบสาธารณะ]

ตรวจสอบภาพหน้าจอของการทดสอบจริงและอัปเดตวิธีการหากมีสิ่งใดขาดหายไป ชื่อไฟล์ของรูปภาพภาพหน้าจอ นอกจากนี้ ให้ระบุว่าการดำเนินการเหล่านี้ต้องใช้เวลาสักครู่ ดังนั้นให้ทริกเกอร์และไปยัง Lab ถัดไปจนกว่าจะพร้อม นอกจากนี้ ให้ระบุรายละเอียดเกี่ยวกับสิ่งที่ต้องตรวจสอบในรายงาน ตรวจสอบเกี่ยวกับ

idea-agent-1

idea-agent-2

idea-agent-3

idea-agent-4

idea-agent-5

10. สร้างผู้ช่วย Scrum Master แบบหลายขั้นตอน [เวอร์ชันตัวอย่างแบบสาธารณะ]

ขั้นตอนแรกคือคลิก "แชทกับตัวแทน" เมื่อเลือก "ตัวแทนใหม่" เนื่องจากเรามีตัวเลือกการแสดงตัวอย่างภายใต้ตัวแทนใหม่สำหรับ "ตัวแทนเวิร์กโฟลว์" ซึ่งเราไม่ได้กล่าวถึงในส่วนนี้

ดูรูปภาพ scrum-master-1.png

หากต้องการเปลี่ยนชื่อ Agent คุณต้องคลิกช่องกลางเพื่อเปิดแผงด้านข้าง โปรดดูรูปภาพ scrum-master-3.png และ scrum-master-4.png

ดูรูปภาพสำหรับขั้นตอนถัดไปในการระบุพรอมต์ - scrum-master-5.png

สำหรับขั้นตอนที่ 3 ให้ทำตามวิธีการต่อไปนี้ ซึ่งจะสร้างเอเจนต์โดยเปิดใช้ Google Search และเปลี่ยนชื่อเอเจนต์เป็น "Lead Scrum Master" ดูรูปภาพ scrum-master-6.png ดังนั้น เรามานำขั้นตอนที่ 2 ออกเพื่อเปลี่ยนชื่อเอเจนต์เป็น "Bumble-Lead-Scrum-Master" เนื่องจากพรอมต์เปลี่ยนชื่อให้แล้ว แต่ต้องตรวจสอบว่าพรอมต์ตั้งชื่อเป็น "Lead Scrum Master" เสมอ

นอกจากนี้ ในพรอมต์ ให้ขอให้ใช้เฉพาะตัวเชื่อมต่อ Jira และ GitHub เท่านั้น ไม่ต้องใช้ Google Search

นอกจากนี้ ให้อัปเดตวิธีการที่เหลือด้วยชื่อเอเจนต์ปัจจุบันแทน "Bumble-Lead-Scrum-Master"

เพิ่มตัวแทนย่อยเฉพาะทาง

ขั้นตอนที่ 1

ในวิธีการ ให้ระบุว่าก่อนหน้านี้มีการค้นหาคีย์โปรเจ็กต์ใน 4 การโต้ตอบพื้นฐานกับ Jira Connector [GA] ขั้นตอนที่ 1 ในห้องทดลอง

ยกเลิกการเลือก Google Search และเลือกเฉพาะ Jira
ดูรูปภาพด้านล่างและตรวจสอบว่าได้อัปเดตตามวิธีการแล้ว

scrum-master-7.png

Scrum-master-8.png

ขั้นตอนที่ 2

ในวิธีการ ให้ระบุว่าก่อนหน้านี้มีการค้นหาชื่อที่เก็บในขั้นตอนที่ 5 การโต้ตอบพื้นฐานกับตัวเชื่อมต่อ GitHub [GA] ขั้นตอนที่ 1

ยกเลิกการเลือก Google Search และเลือกเฉพาะ GitHub
ดูรูปภาพด้านล่างและตรวจสอบว่าได้อัปเดตตามวิธีการแล้ว

scrum-master-9.png

scrum-master-10.png

scrum-master-11.png

พรอมต์นี้ค้นหาใน GitHub สาธารณะและแสดงผลลัพธ์ "สร้างการอัปเดตที่มีลำดับความสำคัญสูงสำหรับโปรเจ็กต์ Bumble ในช่วง 24 ชั่วโมงที่ผ่านมา" ซึ่งไม่ถูกต้อง เอเจนต์ควรค้นหาข้อมูลจากโปรเจ็กต์ Jira และที่เก็บ GitHub ที่ฉันให้ไว้เท่านั้น ไม่แน่ใจว่าทำไม

ดูภาพหน้าจอนี้เพื่อดูเอาต์พุตที่เราได้รับ - scrum-master-12.png เอาต์พุตจริงแสดงอยู่ด้านล่าง

โปรดอัปเดตวิธีการอย่างถูกต้องเพื่อให้ค้นหาเฉพาะโปรเจ็กต์ Jira และรายงาน GitHub ที่กำหนดค่าไว้ในตัวแทน

Generate the high-priority update for the Bumble project for the past 24 hours.
Response complete
Gemini replied
Here is the high-priority daily update for the Bumble project ecosystem over the past 24 hours. [107, 109, 928, 934]
-
🚀 Overall Progress Summary
The past 24 hours saw significant progress in integrating Google’s Bumble Bluetooth stack across downstream tools, notably introducing native Windows support for NXBT 

 and adding optional BLE pairing transports to smpclient [107]. Additionally, core refactoring in Bumble's AVDTP (Audio/Video Distribution) layers has successfully eliminated resource-locking bugs [928]. Meanwhile, the community is actively tackling high-priority Classic Bluetooth pairing failures and Windows boot-up driver issues [59, 934].
-
✨ Key Achievements & Code Progress (GitHub)
Repository / Project
Contribution
Details
intercreate/smpclient
BLE Transport with Pairing (PR #107)
Added an optional bumble extra (smpclient[bumble]) providing SMPBumbleTransport [107]. This BLE transport drives external HCI USB controllers, supporting secure scanning, pairing PIN flows, and stored LTK encryption [107].
google/bumble
AVDTP In-Use Management (PR #928)
Merged! Avoids explicit stream in_use flag management by delegating to a dynamic property checking if stream state is IDLE [928]. This resolves previous edge-case resource leaks [923].
typenoob/nxbt
Native Windows Support (Issue #4)
Announced a major integration with Bumble enabling native Windows support for NXBT controllers via hci-socket and usb (WinUSB) transports 

 .
badoo/codeisok
Security Hardening (PR #109)
Enabled the secure flag for authentication cookies in the Login controller to prevent unencrypted session token transmission [109].
 
-
⚠️ Current Blockers & High-Priority Issues
While no tracking issues were found in Jira for "Bumble", the following high-priority issues are currently impeding progress in the GitHub ecosystem:
Classic Bluetooth Pairing Failures (Issue #59 - kindle-hid-passthrough) [59]
Status: Active / Investigation [59]
Impact: Classic-only Bluetooth HID devices (such as the Logitech K811 keyboard) fail during Simple Secure Pairing (SSP) with an AUTHENTICATION_FAILURE_ERROR (0x05) [59]. Bumble appears to bypass the user pairing delegate entirely [59].
Next Steps: Testing a speculative fix on feature/brcm-bt-support that relaxes pairing config constraints for BR/EDR [59].
Windows Startup Power-On Failures (Issue #934 - google/bumble) [934]
Status: Open [934]
Impact: Bluetooth USB dongles fail to power on during the very first boot on Windows systems [934]. The Intel driver receives a disallowed error (HCI_COMMAND_DISALLOWED_ERROR) during the initial HCI_RESET_COMMAND [934].
-
Would you like me to draft any replies to these active issues or prepare a Confluence summary document of the Windows workarounds?
give me the link for this repo intercreate/smpclient
Response complete
Gemini replied
The link for the intercreate/smpclient repository is:
👉 https://github.com/intercreate/smpclient
intercreate/smpclient repo is not in my repo in mumanoha/gemini-code-review-agent-demo. intercreate/smpclient is a public repo why are you getting me all the public repo
Response complete
Gemini replied
I retrieved results from public repositories because the search query for "Bumble" was executed globally across all of GitHub rather than being restricted to your specific repository (mumanoha/gemini-code-review-agent-demo).
When I initially searched your internal Jira projects and repositories for the project "Bumble", it returned no matches. To ensure I didn't miss any relevant information, my search query broadened its scope to look for any active issues or pull requests containing the keyword "Bumble" globally, which pulled in these public repositories (like Google's bumble library and intercreate/smpclient).
-
🔍 Filtering to Your Specific Repository
If "Bumble" is a branch, a specific folder, or a topic within your repository, I can narrow down the search.
Would you like me to run a targeted analysis specifically on mumanoha/gemini-code-review-agent-demo for any updates or commits made in the past 24 hours instead?

หากฉันใช้พรอมต์ "สร้างการอัปเดตที่มีลำดับความสำคัญสูงสำหรับโปรเจ็กต์ของฉันในช่วง 24 ชั่วโมงที่ผ่านมา" ฉันจะได้รับเอาต์พุตด้านล่าง

ดูรูปภาพ scrum-master-13.png

Generate the high-priority update for the my projects for the past 24 hours.
Response complete
Gemini replied
📊 Daily Project Status Report (Past 24 Hours)
-
🚀 Overall Progress Overview
Currently, the projects are focused on resolving critical infrastructure blockers on Google Cloud Platform while maintaining a steady baseline on application services. While there has been no new code merged or committed in the last 24 hours, the active development continues to center around service integration, and the infrastructure pipeline is currently held back by two newly updated high-priority Jira issues 

 .
-
🛠️ Code Progress & Achievements (GitHub)
There are no new commits or merged pull requests to report for the past 24 hours. The primary active work-in-progress remains:
Repository / PR
Status
Description
mumanoha/gemini-code-review-agent-demo PR #1: feat: Add menu-service application
🟡 Open
This pull request introduces the core menu-service application to the repository.
 
-
⚠️ Blockers & High-Priority Issues (Jira)
The following high-priority infrastructure issues were updated in the past 24 hours under the ge-bugs project and require immediate attention to prevent further deployment delays on the GCP Migration Strategy 

 :
Key
Priority
Status
Summary
Impact
GB-5
🔴 High
To Do
IAM permission shadowing in VPC
Conflicting IAM policies between the VPC and GKE cluster are causing intermittent permission denied errors for active services 

 .
GB-4
🔴 High
To Do
GKE node pool auto-scaling timeout
The GKE node pool is failing to auto-scale automatically, leading to pod scheduling failures under load 

 .
 
-
Let me know if you would like me to help assign these blockers or draft a follow-up message to the infrastructure team!

นอกจากนี้ ฉันยังไม่แน่ใจว่าต้องเพิ่มตัวเชื่อมต่อใน Agent รูทหรือไม่ ฉันได้นำตัวเชื่อมต่อในเอเจนต์รูทออกแล้ว และทดสอบแล้ว ผลลัพธ์ที่ได้คือ การกำหนดค่าที่ถูกต้องคืออะไร ฉันไม่แน่ใจว่าจะให้คุณตัดสินใจเกี่ยวกับการกำหนดค่าที่ถูกต้อง


ดูรูปภาพ - scrum-master-14.png

Generate the high-priority update for the my projects for the past 24 hours.
Response complete
Gemini replied
High-Priority Update: Project GB (ge-bugs)
Here is the summary of P0/P1 (Highest/High priority) issues and blocked tickets in Project GB (ge-bugs) along with their current impact:
1. P0/P1 Issues (High Priority)
GB-4: GKE node pool auto-scaling timeout
Priority: High (P1) 

Impact: The GKE node pool is failing to auto-scale dynamically under load. This results directly in pod scheduling failures, threatening application reliability and performance during high traffic 

 .
GB-5: IAM permission shadowing in VPC
Priority: High (P1)
Impact: Conflicting IAM policies between the VPC and the GKE cluster are causing intermittent "permission denied" errors for services, leading to unstable internal communication 

 .
2. Blocked Tickets
GB-7: Fix database latency issues
Priority: Medium
Status: Blocked 

Impact: Progress on resolving database latency is halted. The ticket is currently blocked while waiting for the infrastructure team to increase IOPS 

 .
-
I will now hand control back to the root agent to synthesize this update into your unified daily report. Let's make sure this progress is tracked.
I have checked the open Pull Requests in the mumanoha/gemini-code-review-agent-demo repository:
Open Pull Requests:
PR #1: feat: Add menu-service application
State: Open
Review Status: There is currently one review submitted by gemini-code-assist[bot], which has a status of COMMENTED (not CHANGES_REQUESTED). The reviewer provided general code quality, testing, and dependency cleanup suggestions but did not block the PR with an explicit changes-requested status.
Therefore, there are no Pull Requests currently in the "Changes Requested" state.
I will now transfer control back to the root_agent to compile the complete update.Here is your unified daily report for the past 24 hours, highlighting the high-priority Jira blockers and active code progress on GitHub.
I, Gemini Enterprise, have analyzed your active projects and compiled the most critical updates to keep you and your team aligned.
-
🚨 High-Priority Jira Issues & Blockers
There are currently two high-priority bugs active in Project GB (ge-bugs), along with one blocked issue that requires infrastructure intervention.
Issue
Priority
Status
Description & Impact
GB-4: GKE node pool auto-scaling timeout
High
To Do
The GKE node pool is failing to auto-scale under load, resulting in active pod scheduling failures.
GB-5: IAM permission shadowing in VPC
High
To Do
Conflicting IAM policies between the VPC and GKE cluster are causing intermittent service permission errors.
GB-7: Fix database latency issues
Medium
🛑 Blocked
Progress is currently halted. The team is waiting on the infrastructure team to increase IOPS.
 
-
💻 GitHub Code Progress
Active progress continues on the gemini-code-review-agent-demo repository with one open pull request. There are currently no PRs blocked under a "Changes Requested" status.
PR # & Title
State
Review Status
Key Highlights
#1: feat: Add menu-service application
Open
Commented
Adds the menu-service Quarkus application. gemini-code-assist[bot] provided recommendations to clean up pom.xml, improve JPA mapping, utilize Panache's active record pattern, and expand test coverage.
 
-
Would you like me to help you draft a follow-up message to the infrastructure team to expedite the IOPS increase for GB-7, or would you like to dive deeper into any of these updates?

11. สร้างเอเจนต์ตัววิเคราะห์ผลกระทบของทรัพยากร [ตัวอย่างแบบสาธารณะ]

ขั้นตอนแรกคือคลิก "แชทกับตัวแทน" เมื่อเลือก "ตัวแทนใหม่" เนื่องจากเรามีตัวเลือกการแสดงตัวอย่างภายใต้ตัวแทนใหม่สำหรับ "ตัวแทนเวิร์กโฟลว์" ซึ่งเราไม่ได้กล่าวถึงในส่วนนี้

ดูรูปภาพ scrum-master-1.png

แทนที่จะเป็นสร้าง Agent ใหม่ > ไปที่เครื่องมือสร้าง มาป้อนพรอมต์ในแชทกัน ดูภาพหน้าจอนี้ resource-impact-1.png

เมื่อเอเจนต์สร้างโปรเจ็กต์แล้ว คุณจะต้องยกเลิกการเลือกตัวเชื่อมต่อ Google แล้วคลิกแสดงตัวอย่างเพื่อทดสอบพรอมต์ "สมาชิกในทีม "Muthu" ลาพักร้อน 3 วัน ผลกระทบคืออะไร"

ดูรูปภาพและตรวจสอบว่าได้อัปเดตวิธีการตามนั้นแล้ว
resource-impact-2.png & resource-impact-3.png

เมื่อทดสอบแล้ว ให้คลิกสร้างเพื่อเผยแพร่เอเจนต์

12. ขั้นสูง: สร้างและติดตั้งใช้งานด้วย ADK [เวอร์ชันตัวอย่างแบบสาธารณะ]

เราได้ถ่ายภาพหน้าจอของขั้นตอนเหล่านี้ โปรดตรวจสอบรูปภาพภาพหน้าจอเพื่อให้แน่ใจว่าคำสั่งถูกต้อง และอัปเดตภาพหน้าจอสำหรับแต่ละขั้นตอนเพื่อให้ชัดเจน

ขั้นตอนที่ 1: ตั้งค่าสภาพแวดล้อม

agent-cli-1.png

ขั้นตอนที่ 2: การตรวจสอบสิทธิ์และการตั้งค่า

agent-cli-2.png
agent-cli-3.png - this steps a long time
agent-cli-4.png -

ระบุในวิธีการว่า CLI จะขอสิทธิ์ในการเรียกใช้คำสั่ง ให้เลือก "อนุญาตครั้งเดียว"

ตัวเลือก ข: วิธีใช้ Gemini CLI (ภาษาธรรมชาติ)

ดูรูปภาพเพื่ออัปเดตวิธีการอย่างถูกต้องตามสิ่งที่เกิดขึ้นจริงในคอนโซล อัปเดต Codelab ด้วยภาพหน้าจอเหล่านี้ตามความเหมาะสมและพร้อมวิธีการที่เกี่ยวข้อง

รูปภาพที่จะตรวจสอบ - agent-cli-5.png ถึง agent-cli-9.png

ด้านล่างนี้คือเอาต์พุตใน CLI

ฉันได้สร้าง Agent Bumble-Ops-Assistant ให้คุณโดยใช้ Agent Development Kit (ADK)

1. การติดตั้งใช้งาน Agent
Agent อยู่ใน bumble-ops-assistant/app/agent.py ซึ่งรวมถึงเครื่องมือ check_build_health ที่แสดงสถานะ "GREEN" ที่ฮาร์ดโค้ดไว้สำหรับทุกสภาพแวดล้อม

1 def check\_build\_health(environment: str) \-\> str:                                                                                                                          
2     """Checks the build health for a given environment.                                                                                                                   
3                                                                                                                                                                           
4     Args:                                                                                                                                                                 
5         environment: The environment to check (e.g., 'prod', 'staging').                                                                                                  
6                                                                                                                                                                           
7     Returns:                                                                                                                                                              
8         The health status of the build.                                                                                                                                   
9     """                                                                                                                                                                   

10 return "GREEN"
11
12 root_agent = Agent(
13 name="Bumble_Ops_Assistant",
14 # ...
15 instruction="You are Bumble-Ops-Assistant, an operations assistant. คุณสามารถตรวจสอบความสมบูรณ์ของบิลด์สำหรับสภาพแวดล้อมการผลิตและการจัดเตรียมได้",
16 tools=[check_build_health],
17 )

2. การทดสอบแบบ Smoke Testing
ฉันทำการทดสอบแบบ Smoke Testing 2 ประเภท ดังนี้

* การทดสอบหน่วย: ฉันสร้างและเรียกใช้การทดสอบหน่วยใน bumble-ops-assistant/tests/unit/test_health_tool.py เพื่อยืนยันตรรกะของเครื่องมือโดยตรง
* ผลลัพธ์: ผ่าน 2 รายการใน 3.03 วินาที
* การทดสอบแบบเร็วเพื่อประเมิน: ฉันสร้างชุดการประเมินอย่างง่ายใน bumble-ops-assistant/tests/eval/evalsets/smoke_test.evalset.json เพื่อทดสอบการโต้ตอบของเอเจนต์
* หมายเหตุ: การเรียกใช้การประเมินพบข้อผิดพลาด PERMISSION_DENIED เนื่องจากไม่ได้เปิดใช้ aiplatform.googleapis.com API ในโปรเจ็กต์ cloudshell-gca และฉันไม่มี
สิทธิ์ในการเปิดใช้

agent-cli-10.png - แสดงเมื่อคลิกที่ "เปิดเอดิเตอร์" และขอให้ผู้เข้าร่วมตรวจสอบไฟล์เพื่อดูว่า Agent CLI สร้างอะไรขึ้นมาบ้าง และอธิบายไฟล์แต่ละไฟล์ที่ Agent CLI สร้างขึ้น โปรดดูรายละเอียดในเอกสารประกอบ
การทดสอบ Playground - ระบุขั้นตอนเหล่านั้นก่อนที่จะติดตั้งใช้งานและเผยแพร่
ดูรูปภาพเหล่านี้เพื่อดูการทดสอบและสร้างวิธีการตามนั้น
รูปภาพ - agent-cli-11.png ถึง agent-cli-15.png

ฉันพยายามขอให้ Agent CLI สร้าง Playground และทดสอบ แต่พบปัญหา
ไม่พบเซสชัน: f681747b-c55d-42d6-9324-77f394d0ecb8 กำหนดค่า Runner ด้วยชื่อแอป "bumble_ops_assistant" แต่โหลดเอเจนต์รูทจาก "/home/admin_/bumble-ops-assistant/app" ซึ่งหมายถึงชื่อแอป "app" ตรวจสอบว่า app_name ของแอป Runner ตรงกับไดเรกทอรีนั้น หรือส่ง app_name อย่างชัดเจนเมื่อสร้าง Runner ความไม่ตรงกันจะป้องกันไม่ให้ผู้เรียกใช้ค้นหาเซสชัน หากต้องการสร้างเซสชันโดยอัตโนมัติเมื่อไม่มี ให้ตั้งค่า auto_create_session=True เมื่อสร้าง Runner

หลังจากขอให้ตัวแทนแก้ไขแล้ว ปัญหาเกี่ยวกับสิทธิ์ก็ได้รับการแก้ไขและทุกอย่างก็เริ่มทำงาน

13. ติดตั้งใช้งานและเผยแพร่ไปยัง Gemini Enterprise [เวอร์ชันตัวอย่างแบบสาธารณะ]

ฉันต้องการใช้ภาษาธรรมชาติเพื่อติดตั้งใช้งานและเผยแพร่ไปยัง GE
ดังนั้นโปรดเก็บทั้ง 2 ตัวเลือกไว้ ไม่ว่าจะเป็นวิธีแบบแมนนวลหรือวิธีภาษาธรรมชาติ

ฉันขอให้ติดตั้งใช้งาน Agent และระบบก็ติดตั้งใช้งานใน Agent Engine ดูรูปภาพเพื่อทำความเข้าใจขั้นตอนและสร้างวิธีการที่เกี่ยวข้อง
รูปภาพ - agent-cli-deploy-1.png ถึง agent-cli-deploy-4.png

ฉันขอให้ Gemini CLI เผยแพร่ไปยังแอป GE

ฉันใช้ - เผยแพร่ไปยังแอป Gemini Enterprise bumble-workshop-lab-test-1_1778167389086
ดูรูปภาพด้านล่างเพื่อทำความเข้าใจวิธีดำเนินการนี้และสร้างวิธีการตามนั้น

agent-cli-publish-1.png ถึง agent-cli-publish-7.png