Add feature request: Enable auto-mode option in permission dialogs

When auto mode gets disabled, users face an avalanche of permission
requests without an easy way to re-enable auto mode. This feature
request proposes adding an 'Enable auto-mode' option to permission
dialogs that would approve the current request and re-enable auto
mode for the session.

This addresses the UX pain point where users need uninterrupted time
to manually re-enable auto mode while being bombarded with prompts.

.claude/commands/dedupe.md

@@ -13,7 +13,7 @@ To do this, follow these steps precisely:
 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, use the comment script to post duplicates:
    ```
-   ./scripts/comment-on-duplicates.sh --base-issue <issue-number> --potential-duplicates <dup1> <dup2> <dup3>
+   ./scripts/comment-on-duplicates.sh --potential-duplicates <dup1> <dup2> <dup3>
    ```
 
 Notes (be sure to tell this to your agents, too):

.claude/commands/triage-issue.md

@@ -20,7 +20,7 @@ TOOLS:
   - `./scripts/gh.sh issue list --state open --limit 20` — list issues
   - `./scripts/gh.sh search issues "query"` — find similar or duplicate issues
   - `./scripts/gh.sh search issues "query" --limit 10` — search with limit
-- `./scripts/edit-issue-labels.sh --issue NUMBER --add-label LABEL --remove-label LABEL` — add or remove labels
+- `./scripts/edit-issue-labels.sh --add-label LABEL --remove-label LABEL` — add or remove labels (issue number is read from the workflow event)
 
 TASK:
 
@@ -48,15 +48,15 @@ TASK:
    The goal is to avoid issues lingering without a clear next step.
 
 7. Apply all selected labels:
-   `./scripts/edit-issue-labels.sh --issue ISSUE_NUMBER --add-label "label1" --add-label "label2"`
+   `./scripts/edit-issue-labels.sh --add-label "label1" --add-label "label2"`
 
 **If EVENT is "issue_comment" (comment on existing issue):**
 
 4. Evaluate lifecycle labels based on the full conversation:
    - If the issue has `stale` or `autoclose`, remove the label — a new human comment means the issue is still active:
-     `./scripts/edit-issue-labels.sh --issue ISSUE_NUMBER --remove-label "stale" --remove-label "autoclose"`
+     `./scripts/edit-issue-labels.sh --remove-label "stale" --remove-label "autoclose"`
    - If the issue has `needs-repro` or `needs-info` and the missing information has now been provided, remove the label:
-     `./scripts/edit-issue-labels.sh --issue ISSUE_NUMBER --remove-label "needs-repro"`
+     `./scripts/edit-issue-labels.sh --remove-label "needs-repro"`
    - If the issue doesn't have lifecycle labels but clearly needs them (e.g., a maintainer asked for repro steps or more details), add the appropriate label.
    - Comments like "+1", "me too", "same here", or emoji reactions are NOT the missing information. Only remove `needs-repro` or `needs-info` when substantive details are actually provided.
    - Do NOT add or remove category labels (bug, enhancement, etc.) on comment events.

.github/FEATURE_REQUEST_auto_mode_permission.md

@@ -0,0 +1,80 @@
+# Feature Request: Add "Enable auto-mode" to permission request options
+
+## Problem Statement
+
+When auto mode gets turned off (for various reasons like encountering a tool that requires explicit permission), users face an avalanche of back-to-back permission requests. This makes it very difficult to get the 2 seconds of uninterrupted time needed to navigate to settings and re-enable auto mode.
+
+Currently, users must either:
+1. Manually approve each permission request one-by-one, or
+2. Try to find a brief pause to navigate away and re-enable auto mode
+
+This creates a frustrating user experience, especially when multiple permission requests queue up rapidly.
+
+## Proposed Solution
+
+Add "Enable auto-mode" as a new option in permission request dialogs, alongside the existing options like:
+- Yes, allow
+- Yes, allow for this session  
+- Always allow
+- No, deny
+
+The new option would:
+1. Approve the current permission request
+2. Enable auto-mode for the remainder of the session
+3. Allow subsequent permission requests to be handled automatically by the auto-mode classifier
+
+### User Experience
+
+When a permission prompt appears, users would see something like:
+
+```
+Claude wants to run: npm test
+
+  > Yes, allow
+    Yes, allow for this session
+    Always allow
+    Enable auto-mode (approve this and future requests automatically)
+    No, deny
+```
+
+Selecting "Enable auto-mode" would:
+1. Immediately approve the current pending request
+2. Switch the session to auto-mode
+3. Continue processing any queued requests using auto-mode
+
+## Technical Context
+
+Based on CHANGELOG analysis, the relevant code areas include:
+- Permission prompt component (React/Ink-based UI)
+- `setPermissionMode` function for changing modes
+- Auto-mode classifier system
+- Session state management for permission modes
+
+The existing infrastructure supports:
+- `value:"allow_all"` for session-wide permissions
+- `value:"yes-accept-edits"` for auto-accepting edits
+- Mode transitions via keyboard shortcuts (Shift+Tab in plan mode)
+
+## Priority
+
+High - This is a significant impact on productivity, especially for users who rely on auto-mode for their workflow.
+
+## Feature Category
+
+Interactive mode (TUI)
+
+## Use Case Example
+
+1. User is working with auto-mode enabled
+2. A tool triggers that auto-mode can't classify (e.g., a sensitive operation)
+3. Auto-mode gets disabled, prompting for explicit permission
+4. User approves the operation
+5. Multiple follow-up tool calls also need permission
+6. Instead of approving each one, user selects "Enable auto-mode"
+7. Current request is approved and auto-mode handles the rest
+
+## Additional Context
+
+- Slack thread: https://anthropic.slack.com/archives/C07VBSHV7EV/p1774978648891819?thread_ts=1774978537.133329&cid=C07VBSHV7EV
+- Requested by Mark Christian
+- Related to improving the permission request UX when auto-mode is interrupted

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

@@ -26,6 +26,7 @@ jobs:
         uses: anthropics/claude-code-action@v1
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          CLAUDE_CODE_SCRIPT_CAPS: '{"comment-on-duplicates.sh":1}'
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           allowed_non_write_users: "*"

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

@@ -29,6 +29,7 @@ jobs:
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           GH_REPO: ${{ github.repository }}
+          CLAUDE_CODE_SCRIPT_CAPS: '{"edit-issue-labels.sh":2}'
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           allowed_non_write_users: "*"

CHANGELOG.md

@@ -1,49 +1,5 @@
 # Changelog
 
-## 2.1.88
-
-- Added `CLAUDE_CODE_NO_FLICKER=1` environment variable to opt into flicker-free alt-screen rendering with virtualized scrollback
-- Added `PermissionDenied` hook that fires after auto mode classifier denials — return `{retry: true}` to tell the model it can retry
-- Added named subagents to `@` mention typeahead suggestions
-- Fixed prompt cache misses in long sessions caused by tool schema bytes changing mid-session
-- Fixed nested CLAUDE.md files being re-injected dozens of times in long sessions that read many files
-- Fixed Edit/Write tools doubling CRLF on Windows and stripping Markdown hard line breaks (two trailing spaces)
-- Fixed `StructuredOutput` schema cache bug causing ~50% failure rate in workflows with multiple schemas
-- Fixed memory leak where large JSON inputs were retained as LRU cache keys in long-running sessions
-- Fixed a potential out-of-memory crash when the Edit tool was used on very large files (>1 GiB)
-- Fixed a crash when removing a message from very large session files (over 50MB)
-- Fixed `--resume` crash when transcript contains a tool result from an older CLI version or interrupted write
-- Fixed misleading "Rate limit reached" message when the API returned an entitlement error — now shows the actual error with actionable hints
-- Fixed LSP server zombie state after crash — server now restarts on next request instead of failing until session restart
-- Fixed hooks `if` condition filtering not matching compound commands (`ls && git push`) or commands with env-var prefixes (`FOO=bar git push`)
-- Fixed prompt history entries containing CJK or emoji being silently dropped when they fall on a 4KB boundary in `~/.claude/history.jsonl`
-- Fixed `/stats` losing historical data beyond 30 days when the stats cache format changes
-- Fixed `/stats` undercounting tokens by excluding subagent/fork usage
-- Fixed scrollback disappearing when scrolling up in long sessions
-- Fixed collapsed search/read group badges duplicating in terminal scrollback during heavy parallel tool use
-- Fixed notification `invalidates` not clearing the currently-displayed notification immediately
-- Fixed prompt briefly disappearing after submit when background messages arrived during processing
-- Fixed long `/btw` responses being clipped with no way to scroll — responses now render in a scrollable viewport
-- Fixed Devanagari and other combining-mark text being truncated in assistant output
-- Fixed rendering artifacts on main-screen terminals after layout shifts
-- Fixed voice mode failing to request microphone permission on macOS Apple Silicon
-- Fixed voice push-to-talk not activating for some modifier-combo bindings
-- Fixed voice mode on Windows failing with "WebSocket upgrade rejected with HTTP 101"
-- Fixed Shift+Enter submitting instead of inserting a newline on Windows Terminal Preview 1.25
-- Fixed periodic UI jitter during streaming in iTerm2 when running inside tmux
-- Fixed PowerShell tool incorrectly reporting failures when commands like `git push` wrote progress to stderr on Windows PowerShell 5.1
-- Fixed SDK error result messages (`error_during_execution`, `error_max_turns`) to correctly set `is_error: true` with descriptive messages
-- Fixed task notifications being lost when backgrounding a session with Ctrl+B
-- Fixed PreToolUse/PostToolUse hooks not providing `file_path` as an absolute path for Write/Edit/Read tools
-- Improved PowerShell tool prompt with version-appropriate syntax guidance (5.1 vs 7+)
-- Thinking summaries are no longer generated by default in interactive sessions — set `showThinkingSummaries: true` in settings to restore
-- Auto mode denied commands now show a notification and appear in `/permissions` → Recent tab
-- `/env` now applies to PowerShell tool commands (previously only affected Bash)
-- `/usage` now hides redundant "Current week (Sonnet only)" bar for Pro and Enterprise plans
-- Collapsed tool summary now shows "Listed N directories" for ls/tree/du instead of "Read N files"
-- Image paste no longer inserts a trailing space
-- Pasting `!command` into an empty prompt now enters bash mode, matching typed `!` behavior
-
 ## 2.1.87
 
 - Fixed messages in Cowork Dispatch not getting delivered

scripts/comment-on-duplicates.sh

@@ -1,22 +1,28 @@
 #!/usr/bin/env bash
 #
 # Comments on a GitHub issue with a list of potential duplicates.
-# Usage: ./comment-on-duplicates.sh --base-issue 123 --potential-duplicates 456 789 101
+# Usage: ./comment-on-duplicates.sh --potential-duplicates 456 789 101
+#
+# The base issue number is read from the workflow event payload.
 #
 
 set -euo pipefail
 
 REPO="anthropics/claude-code"
-BASE_ISSUE=""
+
+# Read from event payload so the issue number is bound to the triggering event.
+# Falls back to workflow_dispatch inputs for manual runs.
+BASE_ISSUE=$(jq -r '.issue.number // .inputs.issue_number // empty' "${GITHUB_EVENT_PATH:?GITHUB_EVENT_PATH not set}")
+if ! [[ "$BASE_ISSUE" =~ ^[0-9]+$ ]]; then
+  echo "Error: no issue number in event payload" >&2
+  exit 1
+fi
+
 DUPLICATES=()
 
 # Parse arguments
 while [[ $# -gt 0 ]]; do
   case $1 in
-    --base-issue)
-      BASE_ISSUE="$2"
-      shift 2
-      ;;
     --potential-duplicates)
       shift
       while [[ $# -gt 0 && ! "$1" =~ ^-- ]]; do
@@ -25,23 +31,12 @@ while [[ $# -gt 0 ]]; do
       done
       ;;
     *)
-      echo "Unknown option: $1" >&2
+      echo "Error: unknown argument (only --potential-duplicates is accepted)" >&2
       exit 1
       ;;
   esac
 done
 
-# Validate base issue
-if [[ -z "$BASE_ISSUE" ]]; then
-  echo "Error: --base-issue is required" >&2
-  exit 1
-fi
-
-if ! [[ "$BASE_ISSUE" =~ ^[0-9]+$ ]]; then
-  echo "Error: --base-issue must be a number, got: $BASE_ISSUE" >&2
-  exit 1
-fi
-
 # Validate duplicates
 if [[ ${#DUPLICATES[@]} -eq 0 ]]; then
   echo "Error: --potential-duplicates requires at least one issue number" >&2

scripts/edit-issue-labels.sh

@@ -1,22 +1,27 @@
 #!/usr/bin/env bash
 #
 # Edits labels on a GitHub issue.
-# Usage: ./edit-issue-labels.sh --issue 123 --add-label bug --add-label needs-triage --remove-label untriaged
+# Usage: ./edit-issue-labels.sh --add-label bug --add-label needs-triage --remove-label untriaged
+#
+# The issue number is read from the workflow event payload.
 #
 
 set -euo pipefail
 
-ISSUE=""
+# Read from event payload so the issue number is bound to the triggering event.
+# Falls back to workflow_dispatch inputs for manual runs.
+ISSUE=$(jq -r '.issue.number // .inputs.issue_number // empty' "${GITHUB_EVENT_PATH:?GITHUB_EVENT_PATH not set}")
+if ! [[ "$ISSUE" =~ ^[0-9]+$ ]]; then
+  echo "Error: no issue number in event payload" >&2
+  exit 1
+fi
+
 ADD_LABELS=()
 REMOVE_LABELS=()
 
 # Parse arguments
 while [[ $# -gt 0 ]]; do
   case $1 in
-    --issue)
-      ISSUE="$2"
-      shift 2
-      ;;
     --add-label)
       ADD_LABELS+=("$2")
       shift 2
@@ -26,20 +31,12 @@ while [[ $# -gt 0 ]]; do
       shift 2
       ;;
     *)
+      echo "Error: unknown argument (only --add-label and --remove-label are accepted)" >&2
       exit 1
       ;;
   esac
 done
 
-# Validate issue number
-if [[ -z "$ISSUE" ]]; then
-  exit 1
-fi
-
-if ! [[ "$ISSUE" =~ ^[0-9]+$ ]]; then
-  exit 1
-fi
-
 if [[ ${#ADD_LABELS[@]} -eq 0 && ${#REMOVE_LABELS[@]} -eq 0 ]]; then
   exit 1
 fi