Add stale issue management workflows

- Add stale-issue-manager.yml to check and manage inactive issues daily
- Add remove-autoclose-label.yml to remove autoclose label when users comment
- Issues get warning after 30 days of inactivity
- Issues auto-close after 60 days (30 days after warning)
- User comments reset the stale timer by removing autoclose label

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

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

.claude/commands/commit-push-pr.md

@@ -0,0 +1,19 @@
+---
+allowed-tools: Bash(git checkout --branch:*), Bash(git add:*), Bash(git status:*), Bash(git push:*), Bash(git commit:*), Bash(gh pr create:*)
+description: Commit, push, and open a PR
+---
+
+## Context
+
+- Current git status: !`git status`
+- Current git diff (staged and unstaged changes): !`git diff HEAD`
+- Current branch: !`git branch --show-current`
+
+## Your task
+
+Based on the above changes:
+1. Create a new branch if on main
+2. Create a single commit with an appropriate message
+3. Push the branch to origin
+4. Create a pull request using `gh pr create`
+5. You have the capability to call multiple tools in a single response. You MUST do all of the above in a single message. Do not use any other tools or do anything else. Do not send any other text or messages besides these tool calls.

.claude/commands/dedupe.md

@@ -0,0 +1,38 @@
+---
+allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh api:*), Bash(gh issue comment:*)
+description: Find duplicate GitHub issues
+---
+
+Find up to 3 likely duplicate issues for a given GitHub issue.
+
+To do this, follow these steps precisely:
+
+1. Use an agent to check if the Github issue (a) is closed, (b) does not need to be deduped (eg. because it is broad product feedback without a specific solution, or positive feedback), or (c) already has a duplicates comment that you made earlier. If so, do not proceed.
+2. Use an agent to view a Github issue, and ask the agent to return a summary of the issue
+3. Then, launch 5 parallel agents to search Github for duplicates of this issue, using diverse keywords and search approaches, using the summary from #1
+4. Next, feed the results from #1 and #2 into another agent, so that it can filter out false positives, that are likely not actually duplicates of the original issue. If there are no duplicates remaining, do not proceed.
+5. Finally, comment back on the issue with a list of up to three duplicate issues (or zero, if there are no likely duplicates)
+
+Notes (be sure to tell this to your agents, too):
+
+- Use `gh` to interact with Github, rather than web fetch
+- Do not use other tools, beyond `gh` (eg. don't use other MCP servers, file edit, etc.)
+- Make a todo list first
+- For your comment, follow the following format precisely (assuming for this example that you found 3 suspected duplicates):
+
+---
+
+Found 3 possible duplicate issues:
+
+1. <link to issue>
+2. <link to issue>
+3. <link to issue>
+
+This issue will be automatically closed as a duplicate in 3 days.
+
+- If your issue is a duplicate, please close it and 👍 the existing issue instead
+- To prevent auto-closure, add a comment or 👎 this comment
+
+🤖 Generated with [Claude Code](https://claude.ai/code)
+
+---

.devcontainer/Dockerfile

@@ -3,8 +3,11 @@ FROM node:20
 ARG TZ
 ENV TZ="$TZ"
 
+ARG CLAUDE_CODE_VERSION=latest
+
 # Install basic development tools and iptables/ipset
-RUN apt update && apt install -y less \
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  less \
   git \
   procps \
   sudo \
@@ -19,7 +22,10 @@ RUN apt update && apt install -y less \
   iproute2 \
   dnsutils \
   aggregate \
-  jq
+  jq \
+  nano \
+  vim \
+  && apt-get clean && rm -rf /var/lib/apt/lists/*
 
 # Ensure default node user has access to /usr/local/share
 RUN mkdir -p /usr/local/share/npm-global && \
@@ -42,9 +48,11 @@ RUN mkdir -p /workspace /home/node/.claude && \
 
 WORKDIR /workspace
 
-RUN wget https://github.com/dandavison/delta/releases/download/0.18.2/git-delta_0.18.2_arm64.deb && \
-  sudo dpkg -i git-delta_0.18.2_arm64.deb && \
-  rm git-delta_0.18.2_arm64.deb
+ARG GIT_DELTA_VERSION=0.18.2
+RUN ARCH=$(dpkg --print-architecture) && \
+  wget "https://github.com/dandavison/delta/releases/download/${GIT_DELTA_VERSION}/git-delta_${GIT_DELTA_VERSION}_${ARCH}.deb" && \
+  sudo dpkg -i "git-delta_${GIT_DELTA_VERSION}_${ARCH}.deb" && \
+  rm "git-delta_${GIT_DELTA_VERSION}_${ARCH}.deb"
 
 # Set up non-root user
 USER node
@@ -53,11 +61,16 @@ USER node
 ENV NPM_CONFIG_PREFIX=/usr/local/share/npm-global
 ENV PATH=$PATH:/usr/local/share/npm-global/bin
 
-# Set the default shell to bash rather than sh
-ENV SHELL /bin/zsh
+# Set the default shell to zsh rather than sh
+ENV SHELL=/bin/zsh
+
+# Set the default editor and visual
+ENV EDITOR nano
+ENV VISUAL nano
 
 # Default powerline10k theme
-RUN sh -c "$(wget -O- https://github.com/deluan/zsh-in-docker/releases/download/v1.2.0/zsh-in-docker.sh)" -- \
+ARG ZSH_IN_DOCKER_VERSION=1.2.0
+RUN sh -c "$(wget -O- https://github.com/deluan/zsh-in-docker/releases/download/v${ZSH_IN_DOCKER_VERSION}/zsh-in-docker.sh)" -- \
   -p git \
   -p fzf \
   -a "source /usr/share/doc/fzf/examples/key-bindings.zsh" \
@@ -66,8 +79,8 @@ RUN sh -c "$(wget -O- https://github.com/deluan/zsh-in-docker/releases/download/
   -x
 
 # Install Claude
-# TODO(ben): Add this back in when we have a public release
-# RUN npm install -g @anthropic-ai/claude-code
+RUN npm install -g @anthropic-ai/claude-code@${CLAUDE_CODE_VERSION}
+
 
 # Copy and set up firewall script
 COPY init-firewall.sh /usr/local/bin/

.devcontainer/devcontainer.json

@@ -3,7 +3,10 @@
   "build": {
     "dockerfile": "Dockerfile",
     "args": {
-      "TZ": "${localEnv:TZ:America/Los_Angeles}"
+      "TZ": "${localEnv:TZ:America/Los_Angeles}",
+      "CLAUDE_CODE_VERSION": "latest",
+      "GIT_DELTA_VERSION": "0.18.2",
+      "ZSH_IN_DOCKER_VERSION": "1.2.0"
     }
   },
   "runArgs": [
@@ -38,10 +41,10 @@
   },
   "remoteUser": "node",
   "mounts": [
-    "source=claude-code-bashhistory,target=/commandhistory,type=volume",
-    "source=claude-code-config,target=/home/node/.claude,type=volume"
+    "source=claude-code-bashhistory-${devcontainerId},target=/commandhistory,type=volume",
+    "source=claude-code-config-${devcontainerId},target=/home/node/.claude,type=volume"
   ],
-  "remoteEnv": {
+  "containerEnv": {
     "NODE_OPTIONS": "--max-old-space-size=4096",
     "CLAUDE_CONFIG_DIR": "/home/node/.claude",
     "POWERLEVEL9K_DISABLE_GITSTATUS": "true"

.devcontainer/init-firewall.sh

@@ -2,6 +2,9 @@
 set -euo pipefail  # Exit on error, undefined vars, and pipeline failures
 IFS=$'\n\t'       # Stricter word splitting
 
+# 1. Extract Docker DNS info BEFORE any flushing
+DOCKER_DNS_RULES=$(iptables-save -t nat | grep "127\.0\.0\.11" || true)
+
 # Flush existing rules and delete existing ipsets
 iptables -F
 iptables -X
@@ -11,6 +14,16 @@ iptables -t mangle -F
 iptables -t mangle -X
 ipset destroy allowed-domains 2>/dev/null || true
 
+# 2. Selectively restore ONLY internal Docker DNS resolution
+if [ -n "$DOCKER_DNS_RULES" ]; then
+    echo "Restoring Docker DNS rules..."
+    iptables -t nat -N DOCKER_OUTPUT 2>/dev/null || true
+    iptables -t nat -N DOCKER_POSTROUTING 2>/dev/null || true
+    echo "$DOCKER_DNS_RULES" | xargs -L 1 iptables -t nat
+else
+    echo "No Docker DNS rules to restore"
+fi
+
 # First allow DNS and localhost before any restrictions
 # Allow outbound DNS
 iptables -A OUTPUT -p udp --dport 53 -j ACCEPT
@@ -58,7 +71,7 @@ for domain in \
     "statsig.anthropic.com" \
     "statsig.com"; do
     echo "Resolving $domain..."
-    ips=$(dig +short A "$domain")
+    ips=$(dig +noall +answer A "$domain" | awk '$4 == "A" {print $5}')
     if [ -z "$ips" ]; then
         echo "ERROR: Failed to resolve $domain"
         exit 1
@@ -88,7 +101,6 @@ echo "Host network detected as: $HOST_NETWORK"
 iptables -A INPUT -s "$HOST_NETWORK" -j ACCEPT
 iptables -A OUTPUT -d "$HOST_NETWORK" -j ACCEPT
 
-# Set default policies to DROP first
 # Set default policies to DROP first
 iptables -P INPUT DROP
 iptables -P FORWARD DROP

.gitattributes

@@ -0,0 +1,2 @@
+* text=auto eol=lf
+*.sh text eol=lf

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,34 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: '[BUG] '
+labels: bug
+assignees: ''
+---
+
+## Environment
+- Platform (select one):
+  - [ ] Anthropic API
+  - [ ] AWS Bedrock
+  - [ ] Google Vertex AI
+  - [ ] Other: <!-- specify -->
+- Claude CLI version: <!-- output of `claude --version` -->
+- Operating System: <!-- e.g. macOS 14.3, Windows 11, Ubuntu 22.04 -->
+- Terminal:  <!-- e.g. iTerm2, Terminal App -->
+
+## Bug Description
+<!-- A clear and concise description of the bug -->
+
+## Steps to Reproduce
+1. <!-- First step -->
+2. <!-- Second step -->
+3. <!-- And so on... -->
+
+## Expected Behavior
+<!-- What you expected to happen -->
+
+## Actual Behavior
+<!-- What actually happened -->
+
+## Additional Context
+<!-- Add any other context about the problem here, such as screenshots, logs, etc. -->

.github/workflows/auto-close-duplicates.yml

@@ -0,0 +1,31 @@
+name: Auto-close duplicate issues
+description: Auto-closes issues that are duplicates of existing issues
+on:
+  schedule:
+    - cron: "0 9 * * *"
+  workflow_dispatch:
+
+jobs:
+  auto-close-duplicates:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Auto-close duplicate issues
+        run: bun run scripts/auto-close-duplicates.ts
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
+          GITHUB_REPOSITORY_NAME: ${{ github.event.repository.name }}
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}

.github/workflows/backfill-duplicate-comments.yml

@@ -0,0 +1,44 @@
+name: Backfill Duplicate Comments
+description: Triggers duplicate detection for old issues that don't have duplicate comments
+
+on:
+  workflow_dispatch:
+    inputs:
+      days_back:
+        description: 'How many days back to look for old issues'
+        required: false
+        default: '90'
+        type: string
+      dry_run:
+        description: 'Dry run mode (true to only log what would be done)'
+        required: false
+        default: 'true'
+        type: choice
+        options:
+          - 'true'
+          - 'false'
+
+jobs:
+  backfill-duplicate-comments:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    permissions:
+      contents: read
+      issues: read
+      actions: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      
+      - name: Backfill duplicate comments
+        run: bun run scripts/backfill-duplicate-comments.ts
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          DAYS_BACK: ${{ inputs.days_back }}
+          DRY_RUN: ${{ inputs.dry_run }}

.github/workflows/claude-dedupe-issues.yml

@@ -0,0 +1,80 @@
+name: Claude Issue Dedupe
+description: Automatically dedupe GitHub issues using Claude Code
+on:
+  issues:
+    types: [opened]
+  workflow_dispatch:
+    inputs:
+      issue_number:
+        description: 'Issue number to process for duplicate detection'
+        required: true
+        type: string
+
+jobs:
+  claude-dedupe-issues:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Run Claude Code slash command
+        uses: anthropics/claude-code-base-action@beta
+        with:
+          prompt: "/dedupe ${{ github.repository }}/issues/${{ github.event.issue.number || inputs.issue_number }}"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          claude_env: |
+            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Log duplicate comment event to Statsig
+        if: always()
+        env:
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
+        run: |
+          ISSUE_NUMBER=${{ github.event.issue.number || inputs.issue_number }}
+          REPO=${{ github.repository }}
+          
+          if [ -z "$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 "$REPO" \
+            --arg triggered_by "${{ github.event_name }}" \
+            '{
+              events: [{
+                eventName: "github_duplicate_comment_added",
+                value: 1,
+                metadata: {
+                  repository: $repo,
+                  issue_number: ($issue_number | tonumber),
+                  triggered_by: $triggered_by,
+                  workflow_run_id: "${{ github.run_id }}"
+                },
+                time: (now | floor | tostring)
+              }]
+            }')
+          
+          # Send to Statsig API
+          echo "Logging duplicate comment event 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 duplicate comment event for issue #${ISSUE_NUMBER}"
+          else
+            echo "Failed to log duplicate comment event for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
+          fi

.github/workflows/claude-issue-triage.yml

@@ -0,0 +1,106 @@
+name: Claude Issue Triage
+description: Automatically triage GitHub issues using Claude Code
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  triage-issue:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Create triage prompt
+        run: |
+          mkdir -p /tmp/claude-prompts
+          cat > /tmp/claude-prompts/triage-prompt.txt << 'EOF'
+          You're an issue triage assistant for GitHub issues. Your task is to analyze the issue and select appropriate labels from the provided list.
+
+          IMPORTANT: Don't post any comments or messages to the issue. Your only action should be to apply labels.
+
+          Issue Information:
+          - REPO: ${{ github.repository }}
+          - ISSUE_NUMBER: ${{ github.event.issue.number }}
+
+          TASK OVERVIEW:
+
+          1. First, fetch the list of labels available in this repository by running: `gh label list`. Run exactly this command with nothing else.
+
+          2. Next, use the GitHub tools to get context about the issue:
+             - You have access to these tools:
+               - mcp__github__get_issue: Use this to retrieve the current issue's details including title, description, and existing labels
+               - mcp__github__get_issue_comments: Use this to read any discussion or additional context provided in the comments
+               - mcp__github__update_issue: Use this to apply labels to the issue (do not use this for commenting)
+               - mcp__github__search_issues: Use this to find similar issues that might provide context for proper categorization and to identify potential duplicate issues
+               - mcp__github__list_issues: Use this to understand patterns in how other issues are labeled
+             - Start by using mcp__github__get_issue to get the issue details
+
+          3. Analyze the issue content, considering:
+             - The issue title and description
+             - The type of issue (bug report, feature request, question, etc.)
+             - Technical areas mentioned
+             - Severity or priority indicators
+             - User impact
+             - Components affected
+
+          4. Select appropriate labels from the available labels list provided above:
+             - Choose labels that accurately reflect the issue's nature
+             - Be specific but comprehensive
+             - Select priority labels if you can determine urgency (high-priority, med-priority, or low-priority)
+             - Consider platform labels (android, ios) if applicable
+             - If you find similar issues using mcp__github__search_issues, consider using a "duplicate" label if appropriate. Only do so if the issue is a duplicate of another OPEN issue.
+
+          5. Apply the selected labels:
+             - Use mcp__github__update_issue to apply your selected labels
+             - DO NOT post any comments explaining your decision
+             - DO NOT communicate directly with users
+             - If no labels are clearly applicable, do not apply any labels
+
+          IMPORTANT GUIDELINES:
+          - Be thorough in your analysis
+          - Only select labels from the provided list above
+          - DO NOT post any comments to the issue
+          - Your ONLY action should be to apply labels using mcp__github__update_issue
+          - It's okay to not add any labels if none are clearly applicable
+          EOF
+
+      - name: Setup GitHub MCP Server
+        run: |
+          mkdir -p /tmp/mcp-config
+          cat > /tmp/mcp-config/mcp-servers.json << 'EOF'
+          {
+            "mcpServers": {
+              "github": {
+                "command": "docker",
+                "args": [
+                  "run",
+                  "-i",
+                  "--rm",
+                  "-e",
+                  "GITHUB_PERSONAL_ACCESS_TOKEN",
+                  "ghcr.io/github/github-mcp-server:sha-7aced2b"
+                ],
+                "env": {
+                  "GITHUB_PERSONAL_ACCESS_TOKEN": "${{ secrets.GITHUB_TOKEN }}"
+                }
+              }
+            }
+          }
+          EOF
+
+      - name: Run Claude Code for Issue Triage
+        uses: anthropics/claude-code-base-action@beta
+        with:
+          prompt_file: /tmp/claude-prompts/triage-prompt.txt
+          allowed_tools: "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"
+          timeout_minutes: "5"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          mcp_config: /tmp/mcp-config/mcp-servers.json
+          claude_env: |
+            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/claude.yml

@@ -0,0 +1,37 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683  # v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+

.github/workflows/lock-closed-issues.yml

@@ -0,0 +1,92 @@
+name: "Lock Stale Issues"
+
+on:
+  schedule:
+    # 8am Pacific = 1pm UTC (2pm UTC during DST)
+    - cron: "0 14 * * *"
+  workflow_dispatch:
+
+permissions:
+  issues: write
+
+concurrency:
+  group: lock-threads
+
+jobs:
+  lock-closed-issues:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Lock closed issues after 7 days of inactivity
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const sevenDaysAgo = new Date();
+            sevenDaysAgo.setDate(sevenDaysAgo.getDate() - 7);
+
+            const lockComment = `This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.`;
+
+            let page = 1;
+            let hasMore = true;
+            let totalLocked = 0;
+
+            while (hasMore) {
+              // Get closed issues (pagination)
+              const { data: issues } = await github.rest.issues.listForRepo({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                state: 'closed',
+                sort: 'updated',
+                direction: 'asc',
+                per_page: 100,
+                page: page
+              });
+              
+              if (issues.length === 0) {
+                hasMore = false;
+                break;
+              }
+              
+              for (const issue of issues) {
+                // Skip if already locked
+                if (issue.locked) continue;
+                
+                // Skip pull requests
+                if (issue.pull_request) continue;
+                
+                // Check if updated more than 7 days ago
+                const updatedAt = new Date(issue.updated_at);
+                if (updatedAt > sevenDaysAgo) {
+                  // Since issues are sorted by updated_at ascending, 
+                  // once we hit a recent issue, all remaining will be recent too
+                  hasMore = false;
+                  break;
+                }
+                
+                try {
+                  // Add comment before locking
+                  await github.rest.issues.createComment({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    body: lockComment
+                  });
+                  
+                  // Lock the issue
+                  await github.rest.issues.lock({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    lock_reason: 'resolved'
+                  });
+                  
+                  totalLocked++;
+                  console.log(`Locked issue #${issue.number}: ${issue.title}`);
+                } catch (error) {
+                  console.error(`Failed to lock issue #${issue.number}: ${error.message}`);
+                }
+              }
+              
+              page++;
+            }
+
+            console.log(`Total issues locked: ${totalLocked}`);

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

@@ -0,0 +1,40 @@
+name: Log Issue Events to Statsig
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  log-to-statsig:
+    runs-on: ubuntu-latest
+    permissions:
+      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
+          
+          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": "'"$CREATED_AT"'"
+                },
+                "time": '"$(date +%s)000"'
+              }]
+            }'

.github/workflows/remove-autoclose-label.yml

@@ -0,0 +1,42 @@
+name: "Remove Autoclose Label on Activity"
+
+on:
+  issue_comment:
+    types: [created]
+
+permissions:
+  issues: write
+
+jobs:
+  remove-autoclose:
+    # Only run if the issue has the autoclose label
+    if: |
+      github.event.issue.state == 'open' &&
+      contains(github.event.issue.labels.*.name, 'autoclose') &&
+      github.event.comment.user.login != 'github-actions[bot]'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Remove autoclose label
+        uses: actions/github-script@v7
+        with:
+          script: |
+            console.log(`Removing autoclose label from issue #${context.issue.number} due to new comment from ${context.payload.comment.user.login}`);
+            
+            try {
+              // Remove the autoclose label
+              await github.rest.issues.removeLabel({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.issue.number,
+                name: 'autoclose'
+              });
+              
+              console.log(`Successfully removed autoclose label from issue #${context.issue.number}`);
+            } catch (error) {
+              // If the label was already removed or doesn't exist, that's fine
+              if (error.status === 404) {
+                console.log(`Autoclose label was already removed from issue #${context.issue.number}`);
+              } else {
+                throw error;
+              }
+            }

.github/workflows/stale-issue-manager.yml

@@ -0,0 +1,157 @@
+name: "Manage Stale Issues"
+
+on:
+  schedule:
+    # 2am Pacific = 9am UTC (10am UTC during DST)
+    - cron: "0 10 * * *"
+  workflow_dispatch:
+
+permissions:
+  issues: write
+
+concurrency:
+  group: stale-issue-manager
+
+jobs:
+  manage-stale-issues:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Manage stale issues
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const oneMonthAgo = new Date();
+            oneMonthAgo.setDate(oneMonthAgo.getDate() - 30);
+
+            const twoMonthsAgo = new Date();
+            twoMonthsAgo.setDate(twoMonthsAgo.getDate() - 60);
+
+            const warningComment = `This issue has been inactive for 30 days. If the issue is still occurring, please comment to let us know. Otherwise, this issue will be automatically closed in 30 days for housekeeping purposes.`;
+
+            const closingComment = `This issue has been automatically closed due to 60 days of inactivity. If you're still experiencing this issue, please open a new issue with updated information.`;
+
+            let page = 1;
+            let hasMore = true;
+            let totalWarned = 0;
+            let totalClosed = 0;
+            let totalLabeled = 0;
+
+            while (hasMore) {
+              // Get open issues sorted by last updated (oldest first)
+              const { data: issues } = await github.rest.issues.listForRepo({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                state: 'open',
+                sort: 'updated',
+                direction: 'asc',
+                per_page: 100,
+                page: page
+              });
+              
+              if (issues.length === 0) {
+                hasMore = false;
+                break;
+              }
+              
+              for (const issue of issues) {
+                // Skip if already locked
+                if (issue.locked) continue;
+                
+                // Skip pull requests
+                if (issue.pull_request) continue;
+                
+                // Check if updated more recently than 30 days ago
+                const updatedAt = new Date(issue.updated_at);
+                if (updatedAt > oneMonthAgo) {
+                  // Since issues are sorted by updated_at ascending, 
+                  // once we hit a recent issue, all remaining will be recent too
+                  hasMore = false;
+                  break;
+                }
+                
+                // Check if issue has autoclose label
+                const hasAutocloseLabel = issue.labels.some(label => 
+                  typeof label === 'object' && label.name === 'autoclose'
+                );
+                
+                try {
+                  // Get comments to check for existing warning
+                  const { data: comments } = await github.rest.issues.listComments({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    per_page: 100
+                  });
+                  
+                  // Find the last comment from github-actions bot
+                  const botComments = comments.filter(comment => 
+                    comment.user && comment.user.login === 'github-actions[bot]' &&
+                    comment.body && comment.body.includes('inactive for 30 days')
+                  );
+                  
+                  const lastBotComment = botComments[botComments.length - 1];
+                  
+                  if (lastBotComment) {
+                    // Check if the bot comment is older than 30 days (total 60 days of inactivity)
+                    const botCommentDate = new Date(lastBotComment.created_at);
+                    if (botCommentDate < oneMonthAgo) {
+                      // Close the issue - it's been stale for 60+ days
+                      console.log(`Closing issue #${issue.number} (stale for 60+ days): ${issue.title}`);
+                      
+                      // Post closing comment
+                      await github.rest.issues.createComment({
+                        owner: context.repo.owner,
+                        repo: context.repo.repo,
+                        issue_number: issue.number,
+                        body: closingComment
+                      });
+                      
+                      // Close the issue
+                      await github.rest.issues.update({
+                        owner: context.repo.owner,
+                        repo: context.repo.repo,
+                        issue_number: issue.number,
+                        state: 'closed',
+                        state_reason: 'not_planned'
+                      });
+                      
+                      totalClosed++;
+                    }
+                    // If bot comment exists but is recent, issue already has warning
+                  } else if (updatedAt < oneMonthAgo) {
+                    // No bot warning yet, issue is 30+ days old
+                    console.log(`Warning issue #${issue.number} (stale for 30+ days): ${issue.title}`);
+                    
+                    // Post warning comment
+                    await github.rest.issues.createComment({
+                      owner: context.repo.owner,
+                      repo: context.repo.repo,
+                      issue_number: issue.number,
+                      body: warningComment
+                    });
+                    
+                    totalWarned++;
+                    
+                    // Add autoclose label if not present
+                    if (!hasAutocloseLabel) {
+                      await github.rest.issues.addLabels({
+                        owner: context.repo.owner,
+                        repo: context.repo.repo,
+                        issue_number: issue.number,
+                        labels: ['autoclose']
+                      });
+                      totalLabeled++;
+                    }
+                  }
+                } catch (error) {
+                  console.error(`Failed to process issue #${issue.number}: ${error.message}`);
+                }
+              }
+              
+              page++;
+            }
+
+            console.log(`Summary:`);
+            console.log(`- Issues warned (30 days stale): ${totalWarned}`);
+            console.log(`- Issues labeled with autoclose: ${totalLabeled}`);
+            console.log(`- Issues closed (60 days stale): ${totalClosed}`);

CHANGELOG.md

@@ -0,0 +1,599 @@
+# Changelog
+
+## 1.0.88
+
+- Fixed issue causing "OAuth authentication is currently not supported"
+- Status line input now includes `exceeds_200k_tokens`
+- Fixed incorrect usage tracking in /cost.
+- Introduced `ANTHROPIC_DEFAULT_SONNET_MODEL` and `ANTHROPIC_DEFAULT_OPUS_MODEL` for controlling model aliases opusplan, opus, and sonnet.
+- Bedrock: Updated default Sonnet model to Sonnet 4
+
+## 1.0.86
+
+- Added /context to help users self-serve debug context issues
+- SDK: Added UUID support for all SDK messages
+- SDK: Added `--replay-user-messages` to replay user messages back to stdout
+
+## 1.0.85
+
+- Status line input now includes session cost info
+- Hooks: Introduced SessionEnd hook
+
+## 1.0.84
+
+- Fix tool_use/tool_result id mismatch error when network is unstable
+- Fix Claude sometimes ignoring real-time steering when wrapping up a task
+- @-mention: Add ~/.claude/\* files to suggestions for easier agent, output style, and slash command editing
+- Use built-in ripgrep by default; to opt out of this behavior, set USE_BUILTIN_RIPGREP=0
+
+## 1.0.83
+
+- @-mention: Support files with spaces in path
+- New shimmering spinner
+
+## 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
+- Agents: Fix custom agent loading when agent files are unparsable
+
+## 1.0.80
+
+- UI improvements: Fix text contrast for custom subagent colors and spinner rendering issues
+
+## 1.0.77
+
+- Bash tool: Fix heredoc and multiline string escaping, improve stderr redirection handling
+- SDK: Add session support and permission denial tracking
+- Fix token limit errors in conversation summarization
+- Opus Plan Mode: New setting in `/model` to run Opus only in plan mode, Sonnet otherwise
+
+## 1.0.73
+
+- MCP: Support multiple config files with `--mcp-config file1.json file2.json`
+- MCP: Press Esc to cancel OAuth authentication flows
+- Bash: Improved command validation and reduced false security warnings
+- UI: Enhanced spinner animations and status line visual hierarchy
+- Linux: Added support for Alpine and musl-based distributions (requires separate ripgrep installation)
+
+## 1.0.72
+
+- Ask permissions: have Claude Code always ask for confirmation to use specific tools with /permissions
+
+## 1.0.71
+
+- Background commands: (Ctrl-b) to run any Bash command in the background so Claude can keep working (great for dev servers, tailing logs, etc.)
+- Customizable status line: add your terminal prompt to Claude Code with /statusline
+
+## 1.0.70
+
+- Performance: Optimized message rendering for better performance with large contexts
+- Windows: Fixed native file search, ripgrep, and subagent functionality
+- Added support for @-mentions in slash command arguments
+
+## 1.0.69
+
+- Upgraded Opus to version 4.1
+
+## 1.0.68
+
+- Fix incorrect model names being used for certain commands like `/pr-comments`
+- Windows: improve permissions checks for allow / deny tools and project trust. This may create a new project entry in `.claude.json` - manually merge the history field if desired.
+- Windows: improve sub-process spawning to eliminate "No such file or directory" when running commands like pnpm
+- Enhanced /doctor command with CLAUDE.md and MCP tool context for self-serve debugging
+- SDK: Added canUseTool callback support for tool confirmation
+- Added `disableAllHooks` setting
+- Improved file suggestions performance in large repos
+
+## 1.0.65
+
+- IDE: Fixed connection stability issues and error handling for diagnostics
+- Windows: Fixed shell environment setup for users without .bashrc files
+
+## 1.0.64
+
+- Agents: Added model customization support - you can now specify which model an agent should use
+- Agents: Fixed unintended access to the recursive agent tool
+- Hooks: Added systemMessage field to hook JSON output for displaying warnings and context
+- SDK: Fixed user input tracking across multi-turn conversations
+- Added hidden files to file search and @-mention suggestions
+
+## 1.0.63
+
+- Windows: Fixed file search, @agent mentions, and custom slash commands functionality
+
+## 1.0.62
+
+- Added @-mention support with typeahead for custom agents. @<your-custom-agent> to invoke it
+- Hooks: Added SessionStart hook for new session initialization
+- /add-dir command now supports typeahead for directory paths
+- Improved network connectivity check reliability
+
+## 1.0.61
+
+- Transcript mode (Ctrl+R): Changed Esc to exit transcript mode rather than interrupt
+- Settings: Added `--settings` flag to load settings from a JSON file
+- Settings: Fixed resolution of settings files paths that are symlinks
+- OTEL: Fixed reporting of wrong organization after authentication changes
+- Slash commands: Fixed permissions checking for allowed-tools with Bash
+- IDE: Added support for pasting images in VSCode MacOS using ⌘+V
+- IDE: Added `CLAUDE_CODE_AUTO_CONNECT_IDE=false` for disabling IDE auto-connection
+- Added `CLAUDE_CODE_SHELL_PREFIX` for wrapping Claude and user-provided shell commands run by Claude Code
+
+## 1.0.60
+
+- You can now create custom subagents for specialized tasks! Run /agents to get started
+
+## 1.0.59
+
+- SDK: Added tool confirmation support with canUseTool callback
+- SDK: Allow specifying env for spawned process
+- Hooks: Exposed PermissionDecision to hooks (including "ask")
+- Hooks: UserPromptSubmit now supports additionalContext in advanced JSON output
+- Fixed issue where some Max users that specified Opus would still see fallback to Sonnet
+
+## 1.0.58
+
+- Added support for reading PDFs
+- MCP: Improved server health status display in 'claude mcp list'
+- Hooks: Added CLAUDE_PROJECT_DIR env var for hook commands
+
+## 1.0.57
+
+- Added support for specifying a model in slash commands
+- Improved permission messages to help Claude understand allowed tools
+- Fix: Remove trailing newlines from bash output in terminal wrapping
+
+## 1.0.56
+
+- Windows: Enabled shift+tab for mode switching on versions of Node.js that support terminal VT mode
+- Fixes for WSL IDE detection
+- Fix an issue causing awsRefreshHelper changes to .aws directory not to be picked up
+
+## 1.0.55
+
+- Clarified knowledge cutoff for Opus 4 and Sonnet 4 models
+- Windows: fixed Ctrl+Z crash
+- SDK: Added ability to capture error logging
+- Add --system-prompt-file option to override system prompt in print mode
+
+## 1.0.54
+
+- Hooks: Added UserPromptSubmit hook and the current working directory to hook inputs
+- Custom slash commands: Added argument-hint to frontmatter
+- Windows: OAuth uses port 45454 and properly constructs browser URL
+- Windows: mode switching now uses alt + m, and plan mode renders properly
+- Shell: Switch to in-memory shell snapshot to fix file-related errors
+
+## 1.0.53
+
+- Updated @-mention file truncation from 100 lines to 2000 lines
+- Add helper script settings for AWS token refresh: awsAuthRefresh (for foreground operations like aws sso login) and awsCredentialExport (for background operation with STS-like response).
+
+## 1.0.52
+
+- Added support for MCP server instructions
+
+## 1.0.51
+
+- Added support for native Windows (requires Git for Windows)
+- Added support for Bedrock API keys through environment variable AWS_BEARER_TOKEN_BEDROCK
+- Settings: /doctor can now help you identify and fix invalid setting files
+- `--append-system-prompt` can now be used in interactive mode, not just --print/-p.
+- Increased auto-compact warning threshold from 60% to 80%
+- Fixed an issue with handling user directories with spaces for shell snapshots
+- OTEL resource now includes os.type, os.version, host.arch, and wsl.version (if running on Windows Subsystem for Linux)
+- Custom slash commands: Fixed user-level commands in subdirectories
+- Plan mode: Fixed issue where rejected plan from sub-task would get discarded
+
+## 1.0.48
+
+- Fixed a bug in v1.0.45 where the app would sometimes freeze on launch
+- Added progress messages to Bash tool based on the last 5 lines of command output
+- Added expanding variables support for MCP server configuration
+- Moved shell snapshots from /tmp to ~/.claude for more reliable Bash tool calls
+- Improved IDE extension path handling when Claude Code runs in WSL
+- Hooks: Added a PreCompact hook
+- Vim mode: Added c, f/F, t/T
+
+## 1.0.45
+
+- Redesigned Search (Grep) tool with new tool input parameters and features
+- Disabled IDE diffs for notebook files, fixing "Timeout waiting after 1000ms" error
+- Fixed config file corruption issue by enforcing atomic writes
+- Updated prompt input undo to Ctrl+\_ to avoid breaking existing Ctrl+U behavior, matching zsh's undo shortcut
+- Stop Hooks: Fixed transcript path after /clear and fixed triggering when loop ends with tool call
+- Custom slash commands: Restored namespacing in command names based on subdirectories. For example, .claude/commands/frontend/component.md is now /frontend:component, not /component.
+
+## 1.0.44
+
+- New /export command lets you quickly export a conversation for sharing
+- MCP: resource_link tool results are now supported
+- MCP: tool annotations and tool titles now display in /mcp view
+- Changed Ctrl+Z to suspend Claude Code. Resume by running `fg`. Prompt input undo is now Ctrl+U.
+
+## 1.0.43
+
+- Fixed a bug where the theme selector was saving excessively
+- Hooks: Added EPIPE system error handling
+
+## 1.0.42
+
+- Added tilde (`~`) expansion support to `/add-dir` command
+
+## 1.0.41
+
+- Hooks: Split Stop hook triggering into Stop and SubagentStop
+- Hooks: Enabled optional timeout configuration for each command
+- Hooks: Added "hook_event_name" to hook input
+- Fixed a bug where MCP tools would display twice in tool list
+- New tool parameters JSON for Bash tool in `tool_decision` event
+
+## 1.0.40
+
+- Fixed a bug causing API connection errors with UNABLE_TO_GET_ISSUER_CERT_LOCALLY if `NODE_EXTRA_CA_CERTS` was set
+
+## 1.0.39
+
+- New Active Time metric in OpenTelemetry logging
+
+## 1.0.38
+
+- Released hooks. Special thanks to community input in https://github.com/anthropics/claude-code/issues/712. Docs: https://docs.anthropic.com/en/docs/claude-code/hooks
+
+## 1.0.37
+
+- Remove ability to set `Proxy-Authorization` header via ANTHROPIC_AUTH_TOKEN or apiKeyHelper
+
+## 1.0.36
+
+- Web search now takes today's date into context
+- Fixed a bug where stdio MCP servers were not terminating properly on exit
+
+## 1.0.35
+
+- Added support for MCP OAuth Authorization Server discovery
+
+## 1.0.34
+
+- Fixed a memory leak causing a MaxListenersExceededWarning message to appear
+
+## 1.0.33
+
+- Improved logging functionality with session ID support
+- Added prompt input undo functionality (Ctrl+Z and vim 'u' command)
+- Improvements to plan mode
+
+## 1.0.32
+
+- Updated loopback config for litellm
+- Added forceLoginMethod setting to bypass login selection screen
+
+## 1.0.31
+
+- Fixed a bug where ~/.claude.json would get reset when file contained invalid JSON
+
+## 1.0.30
+
+- Custom slash commands: Run bash output, @-mention files, enable thinking with thinking keywords
+- Improved file path autocomplete with filename matching
+- Added timestamps in Ctrl-r mode and fixed Ctrl-c handling
+- Enhanced jq regex support for complex filters with pipes and select
+
+## 1.0.29
+
+- Improved CJK character support in cursor navigation and rendering
+
+## 1.0.28
+
+- Slash commands: Fix selector display during history navigation
+- Resizes images before upload to prevent API size limit errors
+- Added XDG_CONFIG_HOME support to configuration directory
+- Performance optimizations for memory usage
+- New attributes (terminal.type, language) in OpenTelemetry logging
+
+## 1.0.27
+
+- Streamable HTTP MCP servers are now supported
+- Remote MCP servers (SSE and HTTP) now support OAuth
+- MCP resources can now be @-mentioned
+- /resume slash command to switch conversations within Claude Code
+
+## 1.0.25
+
+- Slash commands: moved "project" and "user" prefixes to descriptions
+- Slash commands: improved reliability for command discovery
+- Improved support for Ghostty
+- Improved web search reliability
+
+## 1.0.24
+
+- Improved /mcp output
+- Fixed a bug where settings arrays got overwritten instead of merged
+
+## 1.0.23
+
+- Released TypeScript SDK: import @anthropic-ai/claude-code to get started
+- Released Python SDK: pip install claude-code-sdk to get started
+
+## 1.0.22
+
+- SDK: Renamed `total_cost` to `total_cost_usd`
+
+## 1.0.21
+
+- Improved editing of files with tab-based indentation
+- Fix for tool_use without matching tool_result errors
+- Fixed a bug where stdio MCP server processes would linger after quitting Claude Code
+
+## 1.0.18
+
+- Added --add-dir CLI argument for specifying additional working directories
+- Added streaming input support without require -p flag
+- Improved startup performance and session storage performance
+- Added CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR environment variable to freeze working directory for bash commands
+- Added detailed MCP server tools display (/mcp)
+- MCP authentication and permission improvements
+- Added auto-reconnection for MCP SSE connections on disconnect
+- Fixed issue where pasted content was lost when dialogs appeared
+
+## 1.0.17
+
+- We now emit messages from sub-tasks in -p mode (look for the parent_tool_use_id property)
+- Fixed crashes when the VS Code diff tool is invoked multiple times quickly
+- MCP server list UI improvements
+- Update Claude Code process title to display "claude" instead of "node"
+
+## 1.0.11
+
+- Claude Code can now also be used with a Claude Pro subscription
+- Added /upgrade for smoother switching to Claude Max plans
+- Improved UI for authentication from API keys and Bedrock/Vertex/external auth tokens
+- Improved shell configuration error handling
+- Improved todo list handling during compaction
+
+## 1.0.10
+
+- Added markdown table support
+- Improved streaming performance
+
+## 1.0.8
+
+- Fixed Vertex AI region fallback when using CLOUD_ML_REGION
+- Increased default otel interval from 1s -> 5s
+- Fixed edge cases where MCP_TIMEOUT and MCP_TOOL_TIMEOUT weren't being respected
+- Fixed a regression where search tools unnecessarily asked for permissions
+- Added support for triggering thinking non-English languages
+- Improved compacting UI
+
+## 1.0.7
+
+- Renamed /allowed-tools -> /permissions
+- Migrated allowedTools and ignorePatterns from .claude.json -> settings.json
+- Deprecated claude config commands in favor of editing settings.json
+- Fixed a bug where --dangerously-skip-permissions sometimes didn't work in --print mode
+- Improved error handling for /install-github-app
+- Bugfixes, UI polish, and tool reliability improvements
+
+## 1.0.6
+
+- Improved edit reliability for tab-indented files
+- Respect CLAUDE_CONFIG_DIR everywhere
+- Reduced unnecessary tool permission prompts
+- Added support for symlinks in @file typeahead
+- Bugfixes, UI polish, and tool reliability improvements
+
+## 1.0.4
+
+- Fixed a bug where MCP tool errors weren't being parsed correctly
+
+## 1.0.1
+
+- Added `DISABLE_INTERLEAVED_THINKING` to give users the option to opt out of interleaved thinking.
+- Improved model references to show provider-specific names (Sonnet 3.7 for Bedrock, Sonnet 4 for Console)
+- Updated documentation links and OAuth process descriptions
+
+## 1.0.0
+
+- Claude Code is now generally available
+- Introducing Sonnet 4 and Opus 4 models
+
+## 0.2.125
+
+- Breaking change: Bedrock ARN passed to `ANTHROPIC_MODEL` or `ANTHROPIC_SMALL_FAST_MODEL` should no longer contain an escaped slash (specify `/` instead of `%2F`)
+- Removed `DEBUG=true` in favor of `ANTHROPIC_LOG=debug`, to log all requests
+
+## 0.2.117
+
+- Breaking change: --print JSON output now returns nested message objects, for forwards-compatibility as we introduce new metadata fields
+- Introduced settings.cleanupPeriodDays
+- Introduced CLAUDE_CODE_API_KEY_HELPER_TTL_MS env var
+- Introduced --debug mode
+
+## 0.2.108
+
+- You can now send messages to Claude while it works to steer Claude in real-time
+- Introduced BASH_DEFAULT_TIMEOUT_MS and BASH_MAX_TIMEOUT_MS env vars
+- Fixed a bug where thinking was not working in -p mode
+- Fixed a regression in /cost reporting
+- Deprecated MCP wizard interface in favor of other MCP commands
+- Lots of other bugfixes and improvements
+
+## 0.2.107
+
+- CLAUDE.md files can now import other files. Add @path/to/file.md to ./CLAUDE.md to load additional files on launch
+
+## 0.2.106
+
+- MCP SSE server configs can now specify custom headers
+- Fixed a bug where MCP permission prompt didn't always show correctly
+
+## 0.2.105
+
+- Claude can now search the web
+- Moved system & account status to /status
+- Added word movement keybindings for Vim
+- Improved latency for startup, todo tool, and file edits
+
+## 0.2.102
+
+- Improved thinking triggering reliability
+- Improved @mention reliability for images and folders
+- You can now paste multiple large chunks into one prompt
+
+## 0.2.100
+
+- Fixed a crash caused by a stack overflow error
+- Made db storage optional; missing db support disables --continue and --resume
+
+## 0.2.98
+
+- Fixed an issue where auto-compact was running twice
+
+## 0.2.96
+
+- Claude Code can now also be used with a Claude Max subscription (https://claude.ai/upgrade)
+
+## 0.2.93
+
+- Resume conversations from where you left off from with "claude --continue" and "claude --resume"
+- Claude now has access to a Todo list that helps it stay on track and be more organized
+
+## 0.2.82
+
+- Added support for --disallowedTools
+- Renamed tools for consistency: LSTool -> LS, View -> Read, etc.
+
+## 0.2.75
+
+- Hit Enter to queue up additional messages while Claude is working
+- Drag in or copy/paste image files directly into the prompt
+- @-mention files to directly add them to context
+- Run one-off MCP servers with `claude --mcp-config <path-to-file>`
+- Improved performance for filename auto-complete
+
+## 0.2.74
+
+- Added support for refreshing dynamically generated API keys (via apiKeyHelper), with a 5 minute TTL
+- Task tool can now perform writes and run bash commands
+
+## 0.2.72
+
+- Updated spinner to indicate tokens loaded and tool usage
+
+## 0.2.70
+
+- Network commands like curl are now available for Claude to use
+- Claude can now run multiple web queries in parallel
+- Pressing ESC once immediately interrupts Claude in Auto-accept mode
+
+## 0.2.69
+
+- Fixed UI glitches with improved Select component behavior
+- Enhanced terminal output display with better text truncation logic
+
+## 0.2.67
+
+- Shared project permission rules can be saved in .claude/settings.json
+
+## 0.2.66
+
+- Print mode (-p) now supports streaming output via --output-format=stream-json
+- Fixed issue where pasting could trigger memory or bash mode unexpectedly
+
+## 0.2.63
+
+- Fixed an issue where MCP tools were loaded twice, which caused tool call errors
+
+## 0.2.61
+
+- Navigate menus with vim-style keys (j/k) or bash/emacs shortcuts (Ctrl+n/p) for faster interaction
+- Enhanced image detection for more reliable clipboard paste functionality
+- Fixed an issue where ESC key could crash the conversation history selector
+
+## 0.2.59
+
+- Copy+paste images directly into your prompt
+- Improved progress indicators for bash and fetch tools
+- Bugfixes for non-interactive mode (-p)
+
+## 0.2.54
+
+- Quickly add to Memory by starting your message with '#'
+- Press ctrl+r to see full output for long tool results
+- Added support for MCP SSE transport
+
+## 0.2.53
+
+- New web fetch tool lets Claude view URLs that you paste in
+- Fixed a bug with JPEG detection
+
+## 0.2.50
+
+- New MCP "project" scope now allows you to add MCP servers to .mcp.json files and commit them to your repository
+
+## 0.2.49
+
+- Previous MCP server scopes have been renamed: previous "project" scope is now "local" and "global" scope is now "user"
+
+## 0.2.47
+
+- Press Tab to auto-complete file and folder names
+- Press Shift + Tab to toggle auto-accept for file edits
+- Automatic conversation compaction for infinite conversation length (toggle with /config)
+
+## 0.2.44
+
+- Ask Claude to make a plan with thinking mode: just say 'think' or 'think harder' or even 'ultrathink'
+
+## 0.2.41
+
+- MCP server startup timeout can now be configured via MCP_TIMEOUT environment variable
+- MCP server startup no longer blocks the app from starting up
+
+## 0.2.37
+
+- New /release-notes command lets you view release notes at any time
+- `claude config add/remove` commands now accept multiple values separated by commas or spaces
+
+## 0.2.36
+
+- Import MCP servers from Claude Desktop with `claude mcp add-from-claude-desktop`
+- Add MCP servers as JSON strings with `claude mcp add-json <n> <json>`
+
+## 0.2.34
+
+- Vim bindings for text input - enable with /vim or /config
+
+## 0.2.32
+
+- Interactive MCP setup wizard: Run "claude mcp add" to add MCP servers with a step-by-step interface
+- Fix for some PersistentShell issues
+
+## 0.2.31
+
+- Custom slash commands: Markdown files in .claude/commands/ directories now appear as custom slash commands to insert prompts into your conversation
+- MCP debug mode: Run with --mcp-debug flag to get more information about MCP server errors
+
+## 0.2.30
+
+- Added ANSI color theme for better terminal compatibility
+- Fixed issue where slash command arguments weren't being sent properly
+- (Mac-only) API keys are now stored in macOS Keychain
+
+## 0.2.26
+
+- New /approved-tools command for managing tool permissions
+- Word-level diff display for improved code readability
+- Fuzzy matching for slash commands
+
+## 0.2.21
+
+- Fuzzy matching for /commands

LICENSE.md

@@ -1,3 +1 @@
-Claude Code is a Beta research preview per our [Commercial Terms of Service](https://www.anthropic.com/legal/commercial-terms). When you use Claude Code, we collect Feedback, which includes usage data such as code acceptance or rejections, as well as associated conversation data. We may use this Feedback to improve our products, although we will not train models using your Feedback from Claude Code.
-
 © Anthropic PBC. All rights reserved. Use is subject to Anthropic's [Commercial Terms of Service](https://www.anthropic.com/legal/commercial-terms).

README.md

@@ -1,48 +1,38 @@
-# Claude Code (Research Preview)
+# Claude Code
 
-![](https://img.shields.io/badge/Node.js-18%2B-brightgreen?style=flat-square)
+![](https://img.shields.io/badge/Node.js-18%2B-brightgreen?style=flat-square) [![npm]](https://www.npmjs.com/package/@anthropic-ai/claude-code)
 
-Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
+[npm]: https://img.shields.io/npm/v/@anthropic-ai/claude-code.svg?style=flat-square
 
-Some of its key capabilities include:
+Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands. Use it in your terminal, IDE, or tag @claude on Github.
 
-- Edit files and fix bugs across your codebase
-- Answer questions about your code's architecture and logic
-- Execute and fix tests, lint, and other commands
-- Search through git history, resolve merge conflicts, and create commits and PRs
+**Learn more in the [official documentation](https://docs.anthropic.com/en/docs/claude-code/overview)**.
 
-**Learn more in the [official documentation](https://docs.anthropic.com/en/docs/agents/claude-code/introduction)**.
+<img src="./demo.gif" />
 
 ## Get started
 
-<ol>
-  <li>
-    Run the following command in your terminal: <br />
-    <code>npm install -g @anthropic-ai/claude-code</code>
-  </li>
-  <li>
-    Navigate to your project directory and run <code>claude</code>
-  </li>
-  <li>
-    Complete the one-time OAuth process with your Anthropic Console account.
-  </li>
-</ol>
+1. Install Claude Code:
 
-### Research Preview
+```sh
+npm install -g @anthropic-ai/claude-code
+```
 
-We're launching Claude Code as a beta product in research preview to learn directly from developers about their experiences collaborating with AI agents. Our aim is to learn more about how developers prefer to collaborate with AI tools, which development workflows benefit most from working with the agent, and how we can make the agent experience more intuitive.
+2. Navigate to your project directory and run `claude`.
 
-This is an early version of the product experience, and it's likely to evolve as we learn more about developer preferences. Claude Code is an early look into what's possible with agentic coding, and we know there are areas to improve. We plan to enhance tool execution reliability, support for long-running commands, terminal rendering, and Claude's self-knowledge of its capabilities -- as well as many other product experiences -- over the coming weeks.
+## Reporting Bugs
 
-### Reporting Bugs
+We welcome your feedback. Use the `/bug` command to report issues directly within Claude Code, or file a [GitHub issue](https://github.com/anthropics/claude-code/issues).
 
-We welcome feedback during this beta period. Use the `/bug` command to report issues directly within Claude Code, or file a [GitHub issue](https://github.com/anthropics/claude-code/issues).
+## Connect on Discord
 
-### Data collection, usage, and retention
+Join the [Claude Developers Discord](https://anthropic.com/discord) to connect with other developers using Claude Code. Get help, share feedback, and discuss your projects with the community.
+
+## Data collection, usage, and retention
 
 When you use Claude Code, we collect feedback, which includes usage data (such as code acceptance or rejections), associated conversation data, and user feedback submitted via the `/bug` command.
 
-#### How we use your data
+### How we use your data
 
 We may use feedback to improve our products and services, but we will not train generative models using your feedback from Claude Code. Given their potentially sensitive nature, we store user feedback transcripts for only 30 days.
 

SECURITY.md

@@ -0,0 +1,12 @@
+# Security Policy
+Thank you for helping us keep Claude Code secure!
+
+## Reporting Security Issues
+
+The security of our systems and user data is Anthropic's top priority. We appreciate the work of security researchers acting in good faith in identifying and reporting potential vulnerabilities.
+
+Our security program is managed on HackerOne and we ask that any validated vulnerability in this functionality be reported through their [submission form](https://hackerone.com/anthropic-vdp/reports/new?type=team&report_type=vulnerability).
+
+## Vulnerability Disclosure Program
+
+Our Vulnerability Program Guidelines are defined on our [HackerOne program page](https://hackerone.com/anthropic-vdp).

Script/run_devcontainer_claude_code.ps1

@@ -0,0 +1,148 @@
+<#
+.SYNOPSIS
+    Automates the setup and connection to a DevContainer environment using either Docker or Podman on Windows.
+
+.DESCRIPTION
+    This script automates the process of initializing, starting, and connecting to a DevContainer
+    using either Docker or Podman as the container backend. It must be executed from the root
+    directory of your project and assumes the script is located in a 'Script' subdirectory.
+
+.PARAMETER Backend
+    Specifies the container backend to use. Valid values are 'docker' or 'podman'.
+
+.EXAMPLE
+    .\Script\run_devcontainer_claude_code.ps1 -Backend docker
+    Uses Docker as the container backend.
+
+.EXAMPLE
+    .\Script\run_devcontainer_claude_code.ps1 -Backend podman
+    Uses Podman as the container backend.
+
+.NOTES
+    Project Structure:
+    Project/
+    ├── .devcontainer/
+    └── Script/
+        └── run_devcontainer_claude_code.ps1
+#>
+
+[CmdletBinding()]
+param(
+    [Parameter(Mandatory=$true)]
+    [ValidateSet('docker','podman')]
+    [string]$Backend
+)
+
+# Notify script start
+Write-Host "--- DevContainer Startup & Connection Script ---"
+Write-Host "Using backend: $($Backend)"
+
+# --- Prerequisite Check ---
+Write-Host "Checking for required commands..."
+try {
+    Get-Command $Backend -ErrorAction Stop | Out-Null
+    Write-Host "- $($Backend) command found."
+    Get-Command devcontainer -ErrorAction Stop | Out-Null
+    Write-Host "- devcontainer command found."
+}
+catch {
+    Write-Error "A required command is not installed or not in your PATH."
+    Write-Error "Please ensure '$($_.Exception.Message.Split(':')[0])' and 'devcontainer' are installed and accessible."
+    exit 1
+}
+
+
+# --- Backend-Specific Initialization ---
+if ($Backend -eq 'podman') {
+    Write-Host "--- Podman Backend Initialization ---"
+
+    # --- Step 1a: Initialize Podman machine ---
+    Write-Host "Initializing Podman machine 'claudeVM'..."
+    try {
+        & podman machine init claudeVM
+        Write-Host "Podman machine 'claudeVM' initialized or already exists."
+    } catch {
+        Write-Error "Failed to initialize Podman machine: $($_.Exception.Message)"
+        exit 1 # Exit script on error
+    }
+
+    # --- Step 1b: Start Podman machine ---
+    Write-Host "Starting Podman machine 'claudeVM'..."
+    try {
+        & podman machine start claudeVM -q
+        Write-Host "Podman machine started or already running."
+    } catch {
+        Write-Error "Failed to start Podman machine: $($_.Exception.Message)"
+        exit 1
+    }
+
+    # --- Step 2: Set default connection ---
+    Write-Host "Setting default Podman connection to 'claudeVM'..."
+    try {
+        & podman system connection default claudeVM
+        Write-Host "Default connection set."
+    } catch {
+        Write-Warning "Failed to set default Podman connection (may be already set or machine issue): $($_.Exception.Message)"
+    }
+
+} elseif ($Backend -eq 'docker') {
+    Write-Host "--- Docker Backend Initialization ---"
+
+    # --- Step 1 & 2: Check Docker Desktop ---
+    Write-Host "Checking if Docker Desktop is running and docker command is available..."
+    try {
+        docker info | Out-Null
+        Write-Host "Docker Desktop (daemon) is running."
+    } catch {
+        Write-Error "Docker Desktop is not running or docker command not found."
+        Write-Error "Please ensure Docker Desktop is running."
+        exit 1
+    }
+}
+
+# --- Step 3: Bring up DevContainer ---
+Write-Host "Bringing up DevContainer in the current folder..."
+try {
+    $arguments = @('up', '--workspace-folder', '.')
+    if ($Backend -eq 'podman') {
+        $arguments += '--docker-path', 'podman'
+    }
+    & devcontainer @arguments
+    Write-Host "DevContainer startup process completed."
+} catch {
+    Write-Error "Failed to bring up DevContainer: $($_.Exception.Message)"
+    exit 1
+}
+
+# --- Step 4: Get DevContainer ID ---
+Write-Host "Finding the DevContainer ID..."
+$currentFolder = (Get-Location).Path
+
+try {
+    $containerId = (& $Backend ps --filter "label=devcontainer.local_folder=$currentFolder" --format '{{.ID}}').Trim()
+} catch {
+    $displayCommand = "$Backend ps --filter `"label=devcontainer.local_folder=$currentFolder`" --format '{{.ID}}'"
+    Write-Error "Failed to get container ID (Command: $displayCommand): $($_.Exception.Message)"
+    exit 1
+}
+
+if (-not $containerId) {
+    Write-Error "Could not find DevContainer ID for the current folder ('$currentFolder')."
+    Write-Error "Please check if 'devcontainer up' was successful and the container is running."
+    exit 1
+}
+Write-Host "Found container ID: $containerId"
+
+# --- Step 5 & 6: Execute command and enter interactive shell inside container ---
+Write-Host "Executing 'claude' command and then starting zsh session inside container $($containerId)..."
+try {
+    & $Backend exec -it $containerId zsh -c 'claude; exec zsh'
+    Write-Host "Interactive session ended."
+} catch {
+    $displayCommand = "$Backend exec -it $containerId zsh -c 'claude; exec zsh'"
+    Write-Error "Failed to execute command inside container (Command: $displayCommand): $($_.Exception.Message)"
+    exit 1
+}
+
+# Notify script completion
+Write-Host "--- Script completed ---"

examples/hooks/bash_command_validator_example.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""
+Claude Code Hook: Bash Command Validator
+=========================================
+This hook runs as a PreToolUse hook for the Bash tool.
+It validates bash commands against a set of rules before execution.
+In this case it changes grep calls to using rg.
+
+Read more about hooks here: https://docs.anthropic.com/en/docs/claude-code/hooks
+
+Make sure to change your path to your actual script.
+
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python3 /path/to/claude-code/examples/hooks/bash_command_validator_example.py"
+          }
+        ]
+      }
+    ]
+  }
+}
+
+"""
+
+import json
+import re
+import sys
+
+# Define validation rules as a list of (regex pattern, message) tuples
+_VALIDATION_RULES = [
+    (
+        r"^grep\b(?!.*\|)",
+        "Use 'rg' (ripgrep) instead of 'grep' for better performance and features",
+    ),
+    (
+        r"^find\s+\S+\s+-name\b",
+        "Use 'rg --files | rg pattern' or 'rg --files -g pattern' instead of 'find -name' for better performance",
+    ),
+]
+
+
+def _validate_command(command: str) -> list[str]:
+    issues = []
+    for pattern, message in _VALIDATION_RULES:
+        if re.search(pattern, command):
+            issues.append(message)
+    return issues
+
+
+def main():
+    try:
+        input_data = json.load(sys.stdin)
+    except json.JSONDecodeError as e:
+        print(f"Error: Invalid JSON input: {e}", file=sys.stderr)
+        # Exit code 1 shows stderr to the user but not to Claude
+        sys.exit(1)
+
+    tool_name = input_data.get("tool_name", "")
+    if tool_name != "Bash":
+        sys.exit(0)
+
+    tool_input = input_data.get("tool_input", {})
+    command = tool_input.get("command", "")
+
+    if not command:
+        sys.exit(0)
+
+    issues = _validate_command(command)
+    if issues:
+        for message in issues:
+            print(f"• {message}", file=sys.stderr)
+        # Exit code 2 blocks tool call and shows stderr to Claude
+        sys.exit(2)
+
+
+if __name__ == "__main__":
+    main()

scripts/auto-close-duplicates.ts

@@ -0,0 +1,277 @@
+#!/usr/bin/env bun
+
+declare global {
+  var process: {
+    env: Record<string, string | undefined>;
+  };
+}
+
+interface GitHubIssue {
+  number: number;
+  title: string;
+  user: { id: number };
+  created_at: string;
+}
+
+interface GitHubComment {
+  id: number;
+  body: string;
+  created_at: string;
+  user: { type: string; id: number };
+}
+
+interface GitHubReaction {
+  user: { id: number };
+  content: string;
+}
+
+async function githubRequest<T>(endpoint: string, token: string, method: string = 'GET', body?: any): Promise<T> {
+  const response = await fetch(`https://api.github.com${endpoint}`, {
+    method,
+    headers: {
+      Authorization: `Bearer ${token}`,
+      Accept: "application/vnd.github.v3+json",
+      "User-Agent": "auto-close-duplicates-script",
+      ...(body && { "Content-Type": "application/json" }),
+    },
+    ...(body && { body: JSON.stringify(body) }),
+  });
+
+  if (!response.ok) {
+    throw new Error(
+      `GitHub API request failed: ${response.status} ${response.statusText}`
+    );
+  }
+
+  return response.json();
+}
+
+function extractDuplicateIssueNumber(commentBody: string): number | null {
+  // Try to match #123 format first
+  let match = commentBody.match(/#(\d+)/);
+  if (match) {
+    return parseInt(match[1], 10);
+  }
+  
+  // Try to match GitHub issue URL format: https://github.com/owner/repo/issues/123
+  match = commentBody.match(/github\.com\/[^\/]+\/[^\/]+\/issues\/(\d+)/);
+  if (match) {
+    return parseInt(match[1], 10);
+  }
+  
+  return null;
+}
+
+
+async function closeIssueAsDuplicate(
+  owner: string,
+  repo: string,
+  issueNumber: number,
+  duplicateOfNumber: number,
+  token: string
+): Promise<void> {
+  await githubRequest(
+    `/repos/${owner}/${repo}/issues/${issueNumber}`,
+    token,
+    'PATCH',
+    {
+      state: 'closed',
+      state_reason: 'duplicate',
+      labels: ['duplicate']
+    }
+  );
+
+  await githubRequest(
+    `/repos/${owner}/${repo}/issues/${issueNumber}/comments`,
+    token,
+    'POST',
+    {
+      body: `This issue has been automatically closed as a duplicate of #${duplicateOfNumber}.
+
+If this is incorrect, please re-open this issue or create a new one.
+
+🤖 Generated with [Claude Code](https://claude.ai/code)`
+    }
+  );
+
+}
+
+async function autoCloseDuplicates(): Promise<void> {
+  console.log("[DEBUG] Starting auto-close duplicates script");
+
+  const token = process.env.GITHUB_TOKEN;
+  if (!token) {
+    throw new Error("GITHUB_TOKEN environment variable is required");
+  }
+  console.log("[DEBUG] GitHub token found");
+
+  const owner = process.env.GITHUB_REPOSITORY_OWNER || "anthropics";
+  const repo = process.env.GITHUB_REPOSITORY_NAME || "claude-code";
+  console.log(`[DEBUG] Repository: ${owner}/${repo}`);
+
+  const threeDaysAgo = new Date();
+  threeDaysAgo.setDate(threeDaysAgo.getDate() - 3);
+  console.log(
+    `[DEBUG] Checking for duplicate comments older than: ${threeDaysAgo.toISOString()}`
+  );
+
+  console.log("[DEBUG] Fetching open issues created more than 3 days ago...");
+  const allIssues: GitHubIssue[] = [];
+  let page = 1;
+  const perPage = 100;
+  
+  while (true) {
+    const pageIssues: GitHubIssue[] = await githubRequest(
+      `/repos/${owner}/${repo}/issues?state=open&per_page=${perPage}&page=${page}`,
+      token
+    );
+    
+    if (pageIssues.length === 0) break;
+    
+    // Filter for issues created more than 3 days ago
+    const oldEnoughIssues = pageIssues.filter(issue => 
+      new Date(issue.created_at) <= threeDaysAgo
+    );
+    
+    allIssues.push(...oldEnoughIssues);
+    page++;
+    
+    // Safety limit to avoid infinite loops
+    if (page > 20) break;
+  }
+  
+  const issues = allIssues;
+  console.log(`[DEBUG] Found ${issues.length} open issues`);
+
+  let processedCount = 0;
+  let candidateCount = 0;
+
+  for (const issue of issues) {
+    processedCount++;
+    console.log(
+      `[DEBUG] Processing issue #${issue.number} (${processedCount}/${issues.length}): ${issue.title}`
+    );
+
+    console.log(`[DEBUG] Fetching comments for issue #${issue.number}...`);
+    const comments: GitHubComment[] = await githubRequest(
+      `/repos/${owner}/${repo}/issues/${issue.number}/comments`,
+      token
+    );
+    console.log(
+      `[DEBUG] Issue #${issue.number} has ${comments.length} comments`
+    );
+
+    const dupeComments = comments.filter(
+      (comment) =>
+        comment.body.includes("Found") &&
+        comment.body.includes("possible duplicate") &&
+        comment.user.type === "Bot"
+    );
+    console.log(
+      `[DEBUG] Issue #${issue.number} has ${dupeComments.length} duplicate detection comments`
+    );
+
+    if (dupeComments.length === 0) {
+      console.log(
+        `[DEBUG] Issue #${issue.number} - no duplicate comments found, skipping`
+      );
+      continue;
+    }
+
+    const lastDupeComment = dupeComments[dupeComments.length - 1];
+    const dupeCommentDate = new Date(lastDupeComment.created_at);
+    console.log(
+      `[DEBUG] Issue #${
+        issue.number
+      } - most recent duplicate comment from: ${dupeCommentDate.toISOString()}`
+    );
+
+    if (dupeCommentDate > threeDaysAgo) {
+      console.log(
+        `[DEBUG] Issue #${issue.number} - duplicate comment is too recent, skipping`
+      );
+      continue;
+    }
+    console.log(
+      `[DEBUG] Issue #${
+        issue.number
+      } - duplicate comment is old enough (${Math.floor(
+        (Date.now() - dupeCommentDate.getTime()) / (1000 * 60 * 60 * 24)
+      )} days)`
+    );
+
+    const commentsAfterDupe = comments.filter(
+      (comment) => new Date(comment.created_at) > dupeCommentDate
+    );
+    console.log(
+      `[DEBUG] Issue #${issue.number} - ${commentsAfterDupe.length} comments after duplicate detection`
+    );
+
+    if (commentsAfterDupe.length > 0) {
+      console.log(
+        `[DEBUG] Issue #${issue.number} - has activity after duplicate comment, skipping`
+      );
+      continue;
+    }
+
+    console.log(
+      `[DEBUG] Issue #${issue.number} - checking reactions on duplicate comment...`
+    );
+    const reactions: GitHubReaction[] = await githubRequest(
+      `/repos/${owner}/${repo}/issues/comments/${lastDupeComment.id}/reactions`,
+      token
+    );
+    console.log(
+      `[DEBUG] Issue #${issue.number} - duplicate comment has ${reactions.length} reactions`
+    );
+
+    const authorThumbsDown = reactions.some(
+      (reaction) =>
+        reaction.user.id === issue.user.id && reaction.content === "-1"
+    );
+    console.log(
+      `[DEBUG] Issue #${issue.number} - author thumbs down reaction: ${authorThumbsDown}`
+    );
+
+    if (authorThumbsDown) {
+      console.log(
+        `[DEBUG] Issue #${issue.number} - author disagreed with duplicate detection, skipping`
+      );
+      continue;
+    }
+
+    const duplicateIssueNumber = extractDuplicateIssueNumber(lastDupeComment.body);
+    if (!duplicateIssueNumber) {
+      console.log(
+        `[DEBUG] Issue #${issue.number} - could not extract duplicate issue number from comment, skipping`
+      );
+      continue;
+    }
+
+    candidateCount++;
+    const issueUrl = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
+    
+    try {
+      console.log(
+        `[INFO] Auto-closing issue #${issue.number} as duplicate of #${duplicateIssueNumber}: ${issueUrl}`
+      );
+      await closeIssueAsDuplicate(owner, repo, issue.number, duplicateIssueNumber, token);
+      console.log(
+        `[SUCCESS] Successfully closed issue #${issue.number} as duplicate of #${duplicateIssueNumber}`
+      );
+    } catch (error) {
+      console.error(
+        `[ERROR] Failed to close issue #${issue.number} as duplicate: ${error}`
+      );
+    }
+  }
+
+  console.log(
+    `[DEBUG] Script completed. Processed ${processedCount} issues, found ${candidateCount} candidates for auto-close`
+  );
+}
+
+autoCloseDuplicates().catch(console.error);
+
+// Make it a module
+export {};

scripts/backfill-duplicate-comments.ts

@@ -0,0 +1,198 @@
+#!/usr/bin/env bun
+
+declare global {
+  var process: {
+    env: Record<string, string | undefined>;
+  };
+}
+
+interface GitHubIssue {
+  number: number;
+  title: string;
+  state: string;
+  state_reason?: string;
+  user: { id: number };
+  created_at: string;
+  closed_at?: string;
+}
+
+interface GitHubComment {
+  id: number;
+  body: string;
+  created_at: string;
+  user: { type: string; id: number };
+}
+
+async function githubRequest<T>(endpoint: string, token: string, method: string = 'GET', body?: any): Promise<T> {
+  const response = await fetch(`https://api.github.com${endpoint}`, {
+    method,
+    headers: {
+      Authorization: `Bearer ${token}`,
+      Accept: "application/vnd.github.v3+json",
+      "User-Agent": "backfill-duplicate-comments-script",
+      ...(body && { "Content-Type": "application/json" }),
+    },
+    ...(body && { body: JSON.stringify(body) }),
+  });
+
+  if (!response.ok) {
+    throw new Error(
+      `GitHub API request failed: ${response.status} ${response.statusText}`
+    );
+  }
+
+  return response.json();
+}
+
+async function triggerDedupeWorkflow(
+  owner: string,
+  repo: string,
+  issueNumber: number,
+  token: string,
+  dryRun: boolean = true
+): Promise<void> {
+  if (dryRun) {
+    console.log(`[DRY RUN] Would trigger dedupe workflow for issue #${issueNumber}`);
+    return;
+  }
+
+  await githubRequest(
+    `/repos/${owner}/${repo}/actions/workflows/claude-dedupe-issues.yml/dispatches`,
+    token,
+    'POST',
+    {
+      ref: 'main',
+      inputs: {
+        issue_number: issueNumber.toString()
+      }
+    }
+  );
+}
+
+async function backfillDuplicateComments(): Promise<void> {
+  console.log("[DEBUG] Starting backfill duplicate comments script");
+
+  const token = process.env.GITHUB_TOKEN;
+  if (!token) {
+    throw new Error(`GITHUB_TOKEN environment variable is required
+
+Usage:
+  GITHUB_TOKEN=your_token bun run scripts/backfill-duplicate-comments.ts
+
+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)`);
+  }
+  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);
+  
+  console.log(`[DEBUG] Repository: ${owner}/${repo}`);
+  console.log(`[DEBUG] Dry run mode: ${dryRun}`);
+  console.log(`[DEBUG] Looking back ${daysBack} days`);
+
+  const cutoffDate = new Date();
+  cutoffDate.setDate(cutoffDate.getDate() - daysBack);
+
+  console.log(`[DEBUG] Fetching issues created since ${cutoffDate.toISOString()}...`);
+  const allIssues: GitHubIssue[] = [];
+  let page = 1;
+  const perPage = 100;
+  
+  while (true) {
+    const pageIssues: GitHubIssue[] = await githubRequest(
+      `/repos/${owner}/${repo}/issues?state=all&per_page=${perPage}&page=${page}&since=${cutoffDate.toISOString()}`,
+      token
+    );
+    
+    if (pageIssues.length === 0) break;
+    
+    allIssues.push(...pageIssues);
+    page++;
+    
+    // Safety limit to avoid infinite loops
+    if (page > 100) {
+      console.log("[DEBUG] Reached page limit, stopping pagination");
+      break;
+    }
+  }
+  
+  console.log(`[DEBUG] Found ${allIssues.length} issues from the last ${daysBack} days`);
+
+  let processedCount = 0;
+  let candidateCount = 0;
+  let triggeredCount = 0;
+
+  for (const issue of allIssues) {
+    processedCount++;
+    console.log(
+      `[DEBUG] Processing issue #${issue.number} (${processedCount}/${allIssues.length}): ${issue.title}`
+    );
+
+    console.log(`[DEBUG] Fetching comments for issue #${issue.number}...`);
+    const comments: GitHubComment[] = await githubRequest(
+      `/repos/${owner}/${repo}/issues/${issue.number}/comments`,
+      token
+    );
+    console.log(
+      `[DEBUG] Issue #${issue.number} has ${comments.length} comments`
+    );
+
+    // Look for existing duplicate detection comments (from the dedupe bot)
+    const dupeDetectionComments = comments.filter(
+      (comment) =>
+        comment.body.includes("Found") &&
+        comment.body.includes("possible duplicate") &&
+        comment.user.type === "Bot"
+    );
+
+    console.log(
+      `[DEBUG] Issue #${issue.number} has ${dupeDetectionComments.length} duplicate detection comments`
+    );
+
+    // Skip if there's already a duplicate detection comment
+    if (dupeDetectionComments.length > 0) {
+      console.log(
+        `[DEBUG] Issue #${issue.number} already has duplicate detection comment, skipping`
+      );
+      continue;
+    }
+
+    candidateCount++;
+    const issueUrl = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
+    
+    try {
+      console.log(
+        `[INFO] ${dryRun ? '[DRY RUN] ' : ''}Triggering dedupe workflow for issue #${issue.number}: ${issueUrl}`
+      );
+      await triggerDedupeWorkflow(owner, repo, issue.number, token, dryRun);
+      
+      if (!dryRun) {
+        console.log(
+          `[SUCCESS] Successfully triggered dedupe workflow for issue #${issue.number}`
+        );
+      }
+      triggeredCount++;
+    } catch (error) {
+      console.error(
+        `[ERROR] Failed to trigger workflow for issue #${issue.number}: ${error}`
+      );
+    }
+
+    // Add a delay between workflow triggers to avoid overwhelming the system
+    await new Promise(resolve => setTimeout(resolve, 1000));
+  }
+
+  console.log(
+    `[DEBUG] Script completed. Processed ${processedCount} issues, found ${candidateCount} candidates without duplicate comments, ${dryRun ? 'would trigger' : 'triggered'} ${triggeredCount} workflows`
+  );
+}
+
+backfillDuplicateComments().catch(console.error);
+
+// Make it a module
+export {};