feat: update dedupe backfill script to filter by issue number

Replace date-based filtering with issue number filtering to only process issues older than #4050. This provides more precise control over which issues are processed for duplicate detection backfill.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

.github/workflows/log-issue-events.yml

@@ -1,40 +1,176 @@
-name: Log Issue Events to Statsig
+name: Log GitHub Issue Events
 
 on:
   issues:
-    types: [opened]
+    types: [opened, closed]
 
 jobs:
-  log-to-statsig:
+  log-issue-created:
+    if: github.event.action == 'opened'
     runs-on: ubuntu-latest
+    timeout-minutes: 5
     permissions:
+      contents: read
       issues: read
+
     steps:
       - name: Log issue creation to Statsig
         env:
           STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
-          ISSUE_NUMBER: ${{ github.event.issue.number }}
-          REPO: ${{ github.repository }}
-          ISSUE_TITLE: ${{ github.event.issue.title }}
-          AUTHOR: ${{ github.event.issue.user.login }}
-          CREATED_AT: ${{ github.event.issue.created_at }}
         run: |
-          # All values are now safely passed via environment variables
-          # No direct templating in the shell script to prevent injection attacks
+          ISSUE_NUMBER=${{ github.event.issue.number }}
+          REPO=${{ github.repository }}
+          ISSUE_TITLE=$(echo '${{ github.event.issue.title }}' | sed "s/'/'\\\\''/g")
+          AUTHOR="${{ github.event.issue.user.login }}"
+          CREATED_AT="${{ github.event.issue.created_at }}"
           
-          curl -X POST "https://events.statsigapi.net/v1/log_event" \
-            -H "Content-Type: application/json" \
-            -H "statsig-api-key: $STATSIG_API_KEY" \
-            -d '{
-              "events": [{
-                "eventName": "github_issue_created",
-                "metadata": {
-                  "issue_number": "'"$ISSUE_NUMBER"'",
-                  "repository": "'"$REPO"'",
-                  "title": "'"$(echo "$ISSUE_TITLE" | sed "s/\"/\\\\\"/g")"'",
-                  "author": "'"$AUTHOR"'",
-                  "created_at": "'"$CREATED_AT"'"
+          if [ -z "$STATSIG_API_KEY" ]; then
+            echo "STATSIG_API_KEY not found, skipping Statsig logging"
+            exit 0
+          fi
+          
+          # Prepare the event payload
+          EVENT_PAYLOAD=$(jq -n \
+            --arg issue_number "$ISSUE_NUMBER" \
+            --arg repo "$REPO" \
+            --arg title "$ISSUE_TITLE" \
+            --arg author "$AUTHOR" \
+            --arg created_at "$CREATED_AT" \
+            '{
+              events: [{
+                eventName: "github_issue_created",
+                value: 1,
+                metadata: {
+                  repository: $repo,
+                  issue_number: ($issue_number | tonumber),
+                  issue_title: $title,
+                  issue_author: $author,
+                  created_at: $created_at
                 },
-                "time": '"$(date +%s)000"'
+                time: (now | floor | tostring)
               }]
-            }'
+            }')
+          
+          # Send to Statsig API
+          echo "Logging issue creation to Statsig for issue #${ISSUE_NUMBER}"
+          
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
+            -H "Content-Type: application/json" \
+            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
+            -d "$EVENT_PAYLOAD")
+          
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+          
+          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
+            echo "Successfully logged issue creation for issue #${ISSUE_NUMBER}"
+          else
+            echo "Failed to log issue creation for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
+          fi
+
+  log-issue-closed:
+    if: github.event.action == 'closed'
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      contents: read
+      issues: read
+
+    steps:
+      - name: Log issue closure to Statsig
+        env:
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          ISSUE_NUMBER=${{ github.event.issue.number }}
+          REPO=${{ github.repository }}
+          ISSUE_TITLE=$(echo '${{ github.event.issue.title }}' | sed "s/'/'\\\\''/g")
+          CLOSED_BY="${{ github.event.issue.closed_by.login }}"
+          CLOSED_AT="${{ github.event.issue.closed_at }}"
+          STATE_REASON="${{ github.event.issue.state_reason }}"
+          
+          if [ -z "$STATSIG_API_KEY" ]; then
+            echo "STATSIG_API_KEY not found, skipping Statsig logging"
+            exit 0
+          fi
+          
+          # Get additional issue data via GitHub API
+          echo "Fetching additional issue data for #${ISSUE_NUMBER}"
+          ISSUE_DATA=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${REPO}/issues/${ISSUE_NUMBER}")
+          
+          COMMENTS_COUNT=$(echo "$ISSUE_DATA" | jq -r '.comments')
+          
+          # Get reactions data
+          REACTIONS_DATA=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${REPO}/issues/${ISSUE_NUMBER}/reactions")
+          
+          REACTIONS_COUNT=$(echo "$REACTIONS_DATA" | jq '. | length')
+          
+          # Check if issue was closed automatically (by checking if closed_by is a bot)
+          CLOSED_AUTOMATICALLY="false"
+          if [[ "$CLOSED_BY" == *"[bot]"* ]]; then
+            CLOSED_AUTOMATICALLY="true"
+          fi
+          
+          # Check if closed as duplicate by state_reason
+          CLOSED_AS_DUPLICATE="false"
+          if [ "$STATE_REASON" = "duplicate" ]; then
+            CLOSED_AS_DUPLICATE="true"
+          fi
+          
+          # Prepare the event payload
+          EVENT_PAYLOAD=$(jq -n \
+            --arg issue_number "$ISSUE_NUMBER" \
+            --arg repo "$REPO" \
+            --arg title "$ISSUE_TITLE" \
+            --arg closed_by "$CLOSED_BY" \
+            --arg closed_at "$CLOSED_AT" \
+            --arg state_reason "$STATE_REASON" \
+            --arg comments_count "$COMMENTS_COUNT" \
+            --arg reactions_count "$REACTIONS_COUNT" \
+            --arg closed_automatically "$CLOSED_AUTOMATICALLY" \
+            --arg closed_as_duplicate "$CLOSED_AS_DUPLICATE" \
+            '{
+              events: [{
+                eventName: "github_issue_closed",
+                value: 1,
+                metadata: {
+                  repository: $repo,
+                  issue_number: ($issue_number | tonumber),
+                  issue_title: $title,
+                  closed_by: $closed_by,
+                  closed_at: $closed_at,
+                  state_reason: $state_reason,
+                  comments_count: ($comments_count | tonumber),
+                  reactions_count: ($reactions_count | tonumber),
+                  closed_automatically: ($closed_automatically | test("true")),
+                  closed_as_duplicate: ($closed_as_duplicate | test("true"))
+                },
+                time: (now | floor | tostring)
+              }]
+            }')
+          
+          # Send to Statsig API
+          echo "Logging issue closure to Statsig for issue #${ISSUE_NUMBER}"
+          
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
+            -H "Content-Type: application/json" \
+            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
+            -d "$EVENT_PAYLOAD")
+          
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+          
+          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
+            echo "Successfully logged issue closure for issue #${ISSUE_NUMBER}"
+            echo "Closed by: $CLOSED_BY"
+            echo "Comments: $COMMENTS_COUNT"
+            echo "Reactions: $REACTIONS_COUNT"
+            echo "Closed automatically: $CLOSED_AUTOMATICALLY"
+            echo "Closed as duplicate: $CLOSED_AS_DUPLICATE"
+          else
+            echo "Failed to log issue closure for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
+          fi

CHANGELOG.md

@@ -1,13 +1,5 @@
 # Changelog
 
-## 1.0.82
-
-- SDK: Add request cancellation support
-- SDK: New additionalDirectories option to search custom paths, improved slash command processing
-- Settings: Validation prevents invalid fields in .claude/settings.json files
-- MCP: Improve tool name consistency
-- Bash: Fix crash when Claude tries to automatically read large files
-
 ## 1.0.81
 
 - Released output styles, including new built-in educational output styles "Explanatory" and "Learning". Docs: https://docs.anthropic.com/en/docs/claude-code/output-styles

scripts/backfill-duplicate-comments.ts

@@ -82,46 +82,61 @@ Usage:
 Environment Variables:
   GITHUB_TOKEN - GitHub personal access token with repo and actions permissions (required)
   DRY_RUN - Set to "false" to actually trigger workflows (default: true for safety)
-  DAYS_BACK - How many days back to look for old issues (default: 90)`);
+  MAX_ISSUE_NUMBER - Only process issues with numbers less than this value (default: 4050)`);
   }
   console.log("[DEBUG] GitHub token found");
 
   const owner = "anthropics";
   const repo = "claude-code";
   const dryRun = process.env.DRY_RUN !== "false";
-  const daysBack = parseInt(process.env.DAYS_BACK || "90", 10);
+  const maxIssueNumber = parseInt(process.env.MAX_ISSUE_NUMBER || "4050", 10);
+  const minIssueNumber = parseInt(process.env.MIN_ISSUE_NUMBER || "1", 10);
   
   console.log(`[DEBUG] Repository: ${owner}/${repo}`);
   console.log(`[DEBUG] Dry run mode: ${dryRun}`);
-  console.log(`[DEBUG] Looking back ${daysBack} days`);
+  console.log(`[DEBUG] Looking at issues between #${minIssueNumber} and #${maxIssueNumber}`);
 
-  const cutoffDate = new Date();
-  cutoffDate.setDate(cutoffDate.getDate() - daysBack);
-
-  console.log(`[DEBUG] Fetching issues created since ${cutoffDate.toISOString()}...`);
+  console.log(`[DEBUG] Fetching issues between #${minIssueNumber} and #${maxIssueNumber}...`);
   const allIssues: GitHubIssue[] = [];
   let page = 1;
   const perPage = 100;
   
   while (true) {
     const pageIssues: GitHubIssue[] = await githubRequest(
-      `/repos/${owner}/${repo}/issues?state=all&per_page=${perPage}&page=${page}&since=${cutoffDate.toISOString()}`,
+      `/repos/${owner}/${repo}/issues?state=all&per_page=${perPage}&page=${page}&sort=created&direction=desc`,
       token
     );
     
     if (pageIssues.length === 0) break;
     
-    allIssues.push(...pageIssues);
+    // Filter to only include issues within the specified range
+    const filteredIssues = pageIssues.filter(issue => 
+      issue.number >= minIssueNumber && issue.number < maxIssueNumber
+    );
+    allIssues.push(...filteredIssues);
+    
+    // If the oldest issue in this page is still above our minimum, we need to continue
+    // but if the oldest issue is below our minimum, we can stop
+    const oldestIssueInPage = pageIssues[pageIssues.length - 1];
+    if (oldestIssueInPage && oldestIssueInPage.number >= maxIssueNumber) {
+      console.log(`[DEBUG] Oldest issue in page #${page} is #${oldestIssueInPage.number}, continuing...`);
+    } else if (oldestIssueInPage && oldestIssueInPage.number < minIssueNumber) {
+      console.log(`[DEBUG] Oldest issue in page #${page} is #${oldestIssueInPage.number}, below minimum, stopping`);
+      break;
+    } else if (filteredIssues.length === 0 && pageIssues.length > 0) {
+      console.log(`[DEBUG] No issues in page #${page} are in range #${minIssueNumber}-#${maxIssueNumber}, continuing...`);
+    }
+    
     page++;
     
     // Safety limit to avoid infinite loops
-    if (page > 100) {
+    if (page > 200) {
       console.log("[DEBUG] Reached page limit, stopping pagination");
       break;
     }
   }
   
-  console.log(`[DEBUG] Found ${allIssues.length} issues from the last ${daysBack} days`);
+  console.log(`[DEBUG] Found ${allIssues.length} issues between #${minIssueNumber} and #${maxIssueNumber}`);
 
   let processedCount = 0;
   let candidateCount = 0;