update: issue triage workflows tags duplicate issues (#5868)

2 files changed, 250 insertions, 0 deletions

diff --git a/.github/workflows/gemini-automated-issue-triage.yml b/.github/workflows/gemini-automated-issue-triage.yml
index 74904d4c..950d11e8 100644
--- a/.github/workflows/gemini-automated-issue-triage.yml
+++ b/.github/workflows/gemini-automated-issue-triage.yml
@@ -28,6 +28,7 @@ permissions:
   id-token: 'write'
   issues: 'write'
   statuses: 'write'
+  packages: 'read'
 
 jobs:
   triage-issue:
@@ -201,3 +202,149 @@ jobs:
               issue_number: '${{ github.event.issue.number }}',
               body: 'There is a problem with the Gemini CLI issue triaging. Please check the [action logs](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}) for details.'
             })
+
+  deduplicate-issues:
+    if: >
+      github.repository == 'google-gemini/gemini-cli' &&
+      vars.TRIAGE_DEDUPLICATE_ISSUES != '' &&
+      (github.event_name == 'issues' ||
+       github.event_name == 'workflow_dispatch' ||
+       (github.event_name == 'issue_comment' &&
+       contains(github.event.comment.body, '@gemini-cli /deduplicate') &&
+       (github.event.comment.author_association == 'OWNER' ||
+        github.event.comment.author_association == 'MEMBER' ||
+        github.event.comment.author_association == 'COLLABORATOR')))
+
+    timeout-minutes: 20
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Checkout repository'
+        uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683'
+
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        uses: 'actions/create-github-app-token@df432ceedc7162793a195dd1713ff69aefc7379e'
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: 'Run Gemini Issue Deduplication'
+        uses: 'google-github-actions/run-gemini-cli@20351b5ea2b4179431f1ae8918a246a0808f8747'
+        id: 'gemini_issue_deduplication'
+        env:
+          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          ISSUE_TITLE: '${{ github.event.issue.title }}'
+          ISSUE_BODY: '${{ github.event.issue.body }}'
+          ISSUE_NUMBER: '${{ github.event.issue.number }}'
+          REPOSITORY: '${{ github.repository }}'
+          FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
+        with:
+          gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
+          gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
+          gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
+          gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
+          use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
+          settings: |-
+            {
+              "mcpServers": {
+                "issue_deduplication": {
+                  "command": "docker",
+                  "args": [
+                    "run",
+                    "-i",
+                    "--rm",
+                    "--network", "host",
+                    "-e", "GITHUB_TOKEN",
+                    "-e", "GEMINI_API_KEY",
+                    "-e", "DATABASE_TYPE",
+                    "-e", "FIRESTORE_DATABASE_ID",
+                    "-e", "GCP_PROJECT",
+                    "-e", "GOOGLE_APPLICATION_CREDENTIALS=/app/gcp-credentials.json",
+                    "-v", "${GOOGLE_APPLICATION_CREDENTIALS}:/app/gcp-credentials.json",
+                    "ghcr.io/google-gemini/gemini-cli-issue-triage@sha256:e3de1523f6c83aabb3c54b76d08940a2bf42febcb789dd2da6f95169641f94d3"
+                  ],
+                  "env": {
+                    "GITHUB_TOKEN": "${GITHUB_TOKEN}",
+                    "GEMINI_API_KEY": "${{ secrets.GEMINI_API_KEY }}",
+                    "DATABASE_TYPE":"firestore",
+                    "GCP_PROJECT": "${FIRESTORE_PROJECT}",
+                    "FIRESTORE_DATABASE_ID": "(default)",
+                    "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}"
+                  },
+                  "enabled": true,
+                  "timeout": 600000
+                }
+              },
+              "maxSessionTurns": 25,
+              "coreTools": [
+                "run_shell_command(echo)",
+                "run_shell_command(gh issue comment)",
+                "run_shell_command(gh issue view)",
+                "run_shell_command(gh issue edit)"
+              ],
+              "telemetry": {
+                "enabled": true,
+                "target": "gcp"
+              }
+            }
+          prompt: |-
+            ## Role
+            You are an issue de-duplication assistant. Your goal is to find
+            duplicate issues, label the current issue as a duplicate, and notify
+            the user by commenting on the current issue, while avoiding
+            duplicate comments.
+            ## Steps
+            1.  **Find Potential Duplicates:**
+                - The repository is ${{ github.repository }} and the issue number is ${{ github.event.issue.number }}.
+                - Use the `duplicates` tool with the `repo` and `issue_number` to find potential duplicates for the current issue. Do not use the `threshold` parameter.
+                - If no duplicates are found, you are done.
+                - Print the JSON output from the `duplicates` tool to the logs.
+            2.  **Refine Duplicates List (if necessary):**
+                - If the `duplicates` tool returns between 1 and 14 results, you must refine the list.
+                - For each potential duplicate issue, run `gh issue view <issue-number> --json title,body,comments` to fetch its content.
+                - Also fetch the content of the original issue: `gh issue view "${ISSUE_NUMBER}" --json title,body,comments`.
+                - Carefully analyze the content (title, body, comments) of the original issue and all potential duplicates.
+                - It is very important if the comments on either issue mention that they are not duplicates of each other, to treat them as not duplicates.
+                - Based on your analysis, create a final list containing only the issues you are highly confident are actual duplicates.
+                - If your final list is empty, you are done.
+                - Print to the logs if you omitted any potential duplicates based on your analysis.
+                - If the `duplicates` tool returned 15+ results, use the top 15 matches (based on descending similarity score value) to perform this step.
+            3.  **Format Final Duplicates List:**
+                Format the final list of duplicates into a markdown string.
+                The format should be:
+                "Found possible duplicate issues:\n\n- #${issue_number}\n\nIf you believe this is not a duplicate, please remove the `status/possible-duplicate` label."
+                Add an HTML comment to the end for identification: `<!-- gemini-cli-deduplication -->`
+            4.  **Check for Existing Comment:**
+                - Run `gh issue view "${ISSUE_NUMBER}" --json comments` to get all
+                  comments on the issue.
+                - Look for a comment made by a bot (the author's login often ends in `[bot]`) that contains `<!-- gemini-cli-deduplication -->`.
+                - If you find such a comment, store its `id` and `body`.
+            5.  **Decide Action:**
+                - **If an existing comment is found:**
+                    - Compare the new list of duplicate issues with the list from the existing comment's body.
+                    - If they are the same, do nothing.
+                    - If they are different, edit the existing comment. Use
+                      `gh issue comment "${ISSUE_NUMBER}" --edit-comment <comment-id> --body "..."`.
+                      The new body should be the new list of duplicates, but with the header "Found possible duplicate issues (updated):".
+                - **If no existing comment is found:**
+                    - Create a new comment with the list of duplicates.
+                    - Use `gh issue comment "${ISSUE_NUMBER}" --body "..."`.
+            6.  **Add Duplicate Label:**
+                - If you created or updated a comment in the previous step, add the `duplicate` label to the current issue.
+                - Use `gh issue edit "${ISSUE_NUMBER}" --add-label "status/possible-duplicate"`.
+            ## Guidelines
+            - Only use the `duplicates` and `run_shell_command` tools.
+            - The `run_shell_command` tool can be used with `gh issue view`, `gh issue comment`, and `gh issue edit`.
+            - Do not download or read media files like images, videos, or links. The `--json` flag for `gh issue view` will prevent this.
+            - Do not modify the issue content or status.
+            - Only comment on and label the current issue.
+            - Reference all shell variables as "${VAR}" (with quotes and braces).
diff --git a/.github/workflows/gemini-scheduled-issue-triage.yml b/.github/workflows/gemini-scheduled-issue-triage.yml
index 97a81332..c6553706 100644
--- a/.github/workflows/gemini-scheduled-issue-triage.yml
+++ b/.github/workflows/gemini-scheduled-issue-triage.yml
@@ -18,6 +18,7 @@ permissions:
   id-token: 'write'
   issues: 'write'
   statuses: 'write'
+  packages: 'read'
 
 jobs:
   triage-issues:
@@ -223,3 +224,105 @@ jobs:
               - could also pertain to latency,
               - other general software performance like, memory usage, CPU consumption, and algorithmic efficiency.
               - Switching models from one to the other unexpectedly.
+
+  refresh-embeddings:
+    if: |-
+      ${{ vars.TRIAGE_DEDUPLICATE_ISSUES != '' && github.repository == 'google-gemini/gemini-cli' }}
+    timeout-minutes: 20
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Checkout repository'
+        uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683'
+
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        uses: 'actions/create-github-app-token@df432ceedc7162793a195dd1713ff69aefc7379e'
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: 'Run Gemini Issue Deduplication Refresh'
+        uses: 'google-github-actions/run-gemini-cli@20351b5ea2b4179431f1ae8918a246a0808f8747'
+        id: 'gemini_refresh_embeddings'
+        env:
+          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          ISSUE_TITLE: '${{ github.event.issue.title }}'
+          ISSUE_BODY: '${{ github.event.issue.body }}'
+          ISSUE_NUMBER: '${{ github.event.issue.number }}'
+          REPOSITORY: '${{ github.repository }}'
+          FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
+        with:
+          gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
+          gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
+          gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
+          gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
+          use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
+          settings: |-
+            {
+              "mcpServers": {
+                "issue_deduplication": {
+                  "command": "docker",
+                  "args": [
+                    "run",
+                    "-i",
+                    "--rm",
+                    "--network", "host",
+                    "-e", "GITHUB_TOKEN",
+                    "-e", "GEMINI_API_KEY",
+                    "-e", "DATABASE_TYPE",
+                    "-e", "FIRESTORE_DATABASE_ID",
+                    "-e", "GCP_PROJECT",
+                    "-e", "GOOGLE_APPLICATION_CREDENTIALS=/app/gcp-credentials.json",
+                    "-v", "${GOOGLE_APPLICATION_CREDENTIALS}:/app/gcp-credentials.json",
+                    "ghcr.io/google-gemini/gemini-cli-issue-triage@sha256:e3de1523f6c83aabb3c54b76d08940a2bf42febcb789dd2da6f95169641f94d3"
+                  ],
+                  "env": {
+                    "GITHUB_TOKEN": "${GITHUB_TOKEN}",
+                    "GEMINI_API_KEY": "${{ secrets.GEMINI_API_KEY }}",
+                    "DATABASE_TYPE":"firestore",
+                    "GCP_PROJECT": "${FIRESTORE_PROJECT}",
+                    "FIRESTORE_DATABASE_ID": "(default)",
+                    "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}"
+                  },
+                  "enabled": true,
+                  "timeout": 600000
+                }
+              },
+              "maxSessionTurns": 25,
+              "coreTools": [
+                "run_shell_command(echo)"
+              ],
+              "telemetry": {
+                "enabled": true,
+                "target": "gcp"
+              }
+            }
+          prompt: |-
+            ## Role
+
+            You are a database maintenance assistant for a GitHub issue deduplication system.
+
+            ## Goal
+
+            Your sole responsibility is to refresh the embeddings for all open issues in the repository to ensure the deduplication database is up-to-date.
+
+            ## Steps
+
+            1.  **Extract Repository Information:** The repository is ${{ github.repository }}.
+            2.  **Refresh Embeddings:** Call the `refresh` tool with the correct `repo`. Do not use the `force` parameter.
+            3.  **Log Output:** Print the JSON output from the `refresh` tool to the logs.
+
+            ## Guidelines
+
+            - Only use the `refresh` tool.
+            - Do not attempt to find duplicates or modify any issues.
+            - Your only task is to call the `refresh` tool and log its output.