revert: package-lock.json changes

revert: remove heredoc mandate from legacy system prompt
feat(core): append write_file suggestion when shell commands with heredocs fail
2026-07-23 08:10:57 -07:00 · 2026-03-28 04:14:09 +00:00 · 2026-03-28 04:13:21 +00:00 · 2026-03-28 04:13:21 +00:00 · 2026-03-28 04:13:20 +00:00
457 changed files with 6555 additions and 20705 deletions
@@ -1,9 +1,9 @@
 {
  "experimental": {
+    "plan": true,
    "extensionReloading": true,
    "modelSteering": true,
-    "memoryManager": false,
-    "topicUpdateNarration": true
+    "memoryManager": true
  },
  "general": {
    "devtools": true
@@ -1,194 +1,190 @@
 #!/bin/bash

 notify() {
-  local title="${1}"
-  local message="${2}"
-  local pr="${3}"
+  local title="$1"
+  local message="$2"
+  local pr="$3"
  # Terminal escape sequence
-  printf "\e]9;%s | PR #%s | %s\a" "${title}" "${pr}" "${message}"
+  printf "\e]9;%s | PR #%s | %s\a" "$title" "$pr" "$message"
  # Native macOS notification
-  os_type="$(uname || true)"
-  if [[ "${os_type}" == "Darwin" ]]; then
-    osascript -e "display notification \"${message}\" with title \"${title}\" subtitle \"PR #${pr}\""
+  if [[ "$(uname)" == "Darwin" ]]; then
+    osascript -e "display notification \"$message\" with title \"$title\" subtitle \"PR #$pr\""
  fi
 }

-pr_number="${1}"
-if [[ -z "${pr_number}" ]]; then
+pr_number=$1
+if [[ -z "$pr_number" ]]; then
  echo "Usage: async-review <pr_number>"
  exit 1
 fi

-base_dir="$(git rev-parse --show-toplevel 2>/dev/null || true)"
-if [[ -z "${base_dir}" ]]; then
+base_dir=$(git rev-parse --show-toplevel 2>/dev/null)
+if [[ -z "$base_dir" ]]; then
  echo "❌ Must be run from within a git repository."
  exit 1
 fi

 # Use the repository's local .gemini/tmp directory for ephemeral worktrees and logs
-pr_dir="${base_dir}/.gemini/tmp/async-reviews/pr-${pr_number}"
-target_dir="${pr_dir}/worktree"
-log_dir="${pr_dir}/logs"
+pr_dir="$base_dir/.gemini/tmp/async-reviews/pr-$pr_number"
+target_dir="$pr_dir/worktree"
+log_dir="$pr_dir/logs"

-cd "${base_dir}" || exit 1
+cd "$base_dir" || exit 1

-mkdir -p "${log_dir}"
-rm -f "${log_dir}/setup.exit" "${log_dir}/final-assessment.exit" "${log_dir}/final-assessment.md"
+mkdir -p "$log_dir"
+rm -f "$log_dir/setup.exit" "$log_dir/final-assessment.exit" "$log_dir/final-assessment.md"

-echo "🧹 Cleaning up previous worktree if it exists..." | tee -a "${log_dir}/setup.log"
-git worktree remove -f "${target_dir}" >> "${log_dir}/setup.log" 2>&1 || true
-git branch -D "gemini-async-pr-${pr_number}" >> "${log_dir}/setup.log" 2>&1 || true
-git worktree prune >> "${log_dir}/setup.log" 2>&1 || true
+echo "🧹 Cleaning up previous worktree if it exists..." | tee -a "$log_dir/setup.log"
+git worktree remove -f "$target_dir" >> "$log_dir/setup.log" 2>&1 || true
+git branch -D "gemini-async-pr-$pr_number" >> "$log_dir/setup.log" 2>&1 || true
+git worktree prune >> "$log_dir/setup.log" 2>&1 || true

-echo "📡 Fetching PR #${pr_number}..." | tee -a "${log_dir}/setup.log"
-if ! git fetch origin -f "pull/${pr_number}/head:gemini-async-pr-${pr_number}" >> "${log_dir}/setup.log" 2>&1; then
-  echo 1 > "${log_dir}/setup.exit"
-  echo "❌ Fetch failed. Check ${log_dir}/setup.log"
-  notify "Async Review Failed" "Fetch failed." "${pr_number}"
+echo "📡 Fetching PR #$pr_number..." | tee -a "$log_dir/setup.log"
+if ! git fetch origin -f "pull/$pr_number/head:gemini-async-pr-$pr_number" >> "$log_dir/setup.log" 2>&1; then
+  echo 1 > "$log_dir/setup.exit"
+  echo "❌ Fetch failed. Check $log_dir/setup.log"
+  notify "Async Review Failed" "Fetch failed." "$pr_number"
  exit 1
 fi

-if [[ ! -d "${target_dir}" ]]; then
-  echo "🧹 Pruning missing worktrees..." | tee -a "${log_dir}/setup.log"
-  git worktree prune >> "${log_dir}/setup.log" 2>&1
-  echo "🌿 Creating worktree in ${target_dir}..." | tee -a "${log_dir}/setup.log"
-  if ! git worktree add "${target_dir}" "gemini-async-pr-${pr_number}" >> "${log_dir}/setup.log" 2>&1; then
-    echo 1 > "${log_dir}/setup.exit"
-    echo "❌ Worktree creation failed. Check ${log_dir}/setup.log"
-    notify "Async Review Failed" "Worktree creation failed." "${pr_number}"
+if [[ ! -d "$target_dir" ]]; then
+  echo "🧹 Pruning missing worktrees..." | tee -a "$log_dir/setup.log"
+  git worktree prune >> "$log_dir/setup.log" 2>&1
+  echo "🌿 Creating worktree in $target_dir..." | tee -a "$log_dir/setup.log"
+  if ! git worktree add "$target_dir" "gemini-async-pr-$pr_number" >> "$log_dir/setup.log" 2>&1; then
+    echo 1 > "$log_dir/setup.exit"
+    echo "❌ Worktree creation failed. Check $log_dir/setup.log"
+    notify "Async Review Failed" "Worktree creation failed." "$pr_number"
    exit 1
  fi
 else
-  echo "🌿 Worktree already exists." | tee -a "${log_dir}/setup.log"
+  echo "🌿 Worktree already exists." | tee -a "$log_dir/setup.log"
 fi
-echo 0 > "${log_dir}/setup.exit"
+echo 0 > "$log_dir/setup.exit"

-cd "${target_dir}" || exit 1
+cd "$target_dir" || exit 1

-echo "🚀 Launching background tasks. Logs saving to: ${log_dir}"
+echo "🚀 Launching background tasks. Logs saving to: $log_dir"

 echo "  ↳ [1/5] Grabbing PR diff..."
-rm -f "${log_dir}/pr-diff.exit"
-{ gh pr diff "${pr_number}" > "${log_dir}/pr-diff.diff" 2>&1; echo $? > "${log_dir}/pr-diff.exit"; } &
+rm -f "$log_dir/pr-diff.exit"
+{ gh pr diff "$pr_number" > "$log_dir/pr-diff.diff" 2>&1; echo $? > "$log_dir/pr-diff.exit"; } &

 echo "  ↳ [2/5] Starting build and lint..."
-rm -f "${log_dir}/build-and-lint.exit"
-{ { npm run clean && npm ci && npm run format && npm run build && npm run lint:ci && npm run typecheck; } > "${log_dir}/build-and-lint.log" 2>&1; echo $? > "${log_dir}/build-and-lint.exit"; } &
+rm -f "$log_dir/build-and-lint.exit"
+{ { npm run clean && npm ci && npm run format && npm run build && npm run lint:ci && npm run typecheck; } > "$log_dir/build-and-lint.log" 2>&1; echo $? > "$log_dir/build-and-lint.exit"; } &

 # Dynamically resolve gemini binary (fallback to your nightly path)
-GEMINI_CMD="$(command -v gemini || echo "${HOME}/.gcli/nightly/node_modules/.bin/gemini")"
-# shellcheck disable=SC2312
+GEMINI_CMD=$(which gemini || echo "$HOME/.gcli/nightly/node_modules/.bin/gemini")
 POLICY_PATH="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/policy.toml"

 echo "  ↳ [3/5] Starting Gemini code review..."
-rm -f "${log_dir}/review.exit"
-{ "${GEMINI_CMD}" --policy "${POLICY_PATH}" -p "/review-frontend ${pr_number}" > "${log_dir}/review.md" 2>&1; echo $? > "${log_dir}/review.exit"; } &
+rm -f "$log_dir/review.exit"
+{ "$GEMINI_CMD" --policy "$POLICY_PATH" -p "/review-frontend $pr_number" > "$log_dir/review.md" 2>&1; echo $? > "$log_dir/review.exit"; } &

 echo "  ↳ [4/5] Starting automated tests (waiting for build and lint)..."
-rm -f "${log_dir}/npm-test.exit"
+rm -f "$log_dir/npm-test.exit"
 { 
-  while [[ ! -f "${log_dir}/build-and-lint.exit" ]]; do sleep 1; done
-  read -r build_exit < "${log_dir}/build-and-lint.exit" || build_exit=""
-  if [[ "${build_exit}" == "0" ]]; then
-    gh pr checks "${pr_number}" > "${log_dir}/ci-checks.log" 2>&1
+  while [ ! -f "$log_dir/build-and-lint.exit" ]; do sleep 1; done
+  if [ "$(cat "$log_dir/build-and-lint.exit")" == "0" ]; then
+    gh pr checks "$pr_number" > "$log_dir/ci-checks.log" 2>&1
    ci_status=$?
    
-    if [[ "${ci_status}" -eq 0 ]]; then
-      echo "CI checks passed. Skipping local npm tests." > "${log_dir}/npm-test.log"
-      echo 0 > "${log_dir}/npm-test.exit"
-    elif [[ "${ci_status}" -eq 8 ]]; then
-      echo "CI checks are still pending. Skipping local npm tests to avoid duplicate work. Please check GitHub for final results." > "${log_dir}/npm-test.log"
-      echo 0 > "${log_dir}/npm-test.exit"
+    if [ "$ci_status" -eq 0 ]; then
+      echo "CI checks passed. Skipping local npm tests." > "$log_dir/npm-test.log"
+      echo 0 > "$log_dir/npm-test.exit"
+    elif [ "$ci_status" -eq 8 ]; then
+      echo "CI checks are still pending. Skipping local npm tests to avoid duplicate work. Please check GitHub for final results." > "$log_dir/npm-test.log"
+      echo 0 > "$log_dir/npm-test.exit"
    else
-      echo "CI checks failed. Failing checks:" > "${log_dir}/npm-test.log"
-      gh pr checks "${pr_number}" --json name,bucket -q '.[] | select(.bucket=="fail") | .name' >> "${log_dir}/npm-test.log" 2>&1
+      echo "CI checks failed. Failing checks:" > "$log_dir/npm-test.log"
+      gh pr checks "$pr_number" --json name,bucket -q '.[] | select(.bucket=="fail") | .name' >> "$log_dir/npm-test.log" 2>&1
      
-      echo "Attempting to extract failing test files from CI logs..." >> "${log_dir}/npm-test.log"
-      pr_branch="$(gh pr view "${pr_number}" --json headRefName -q '.headRefName' 2>/dev/null || true)"
-      run_id="$(gh run list --branch "${pr_branch}" --workflow ci.yml --json databaseId -q '.[0].databaseId' 2>/dev/null || true)"
+      echo "Attempting to extract failing test files from CI logs..." >> "$log_dir/npm-test.log"
+      pr_branch=$(gh pr view "$pr_number" --json headRefName -q '.headRefName' 2>/dev/null)
+      run_id=$(gh run list --branch "$pr_branch" --workflow ci.yml --json databaseId -q '.[0].databaseId' 2>/dev/null)
      
      failed_files=""
-      if [[ -n "${run_id}" ]]; then
-        failed_files="$(gh run view "${run_id}" --log-failed 2>/dev/null | grep -o -E '(packages/[a-zA-Z0-9_-]+|integration-tests|evals)/[a-zA-Z0-9_/-]+\.test\.ts(x)?' | sort | uniq || true)"
+      if [[ -n "$run_id" ]]; then
+        failed_files=$(gh run view "$run_id" --log-failed 2>/dev/null | grep -o -E '(packages/[a-zA-Z0-9_-]+|integration-tests|evals)/[a-zA-Z0-9_/-]+\.test\.ts(x)?' | sort | uniq)
      fi
      
-      if [[ -n "${failed_files}" ]]; then
-        echo "Found failing test files from CI:" >> "${log_dir}/npm-test.log"
-        for f in ${failed_files}; do echo "  - ${f}" >> "${log_dir}/npm-test.log"; done
-        echo "Running ONLY failing tests locally..." >> "${log_dir}/npm-test.log"
+      if [[ -n "$failed_files" ]]; then
+        echo "Found failing test files from CI:" >> "$log_dir/npm-test.log"
+        for f in $failed_files; do echo "  - $f" >> "$log_dir/npm-test.log"; done
+        echo "Running ONLY failing tests locally..." >> "$log_dir/npm-test.log"
        
        exit_code=0
-        for file in ${failed_files}; do
-           if [[ "${file}" == packages/* ]]; then
-             ws_dir="$(echo "${file}" | cut -d'/' -f1,2)"
+        for file in $failed_files; do
+           if [[ "$file" == packages/* ]]; then
+             ws_dir=$(echo "$file" | cut -d'/' -f1,2)
           else
-             ws_dir="$(echo "${file}" | cut -d'/' -f1)"
+             ws_dir=$(echo "$file" | cut -d'/' -f1)
           fi
-           rel_file="${file#"${ws_dir}"/}"
+           rel_file=${file#$ws_dir/}
           
-           echo "--- Running ${rel_file} in workspace ${ws_dir} ---" >> "${log_dir}/npm-test.log"
-           if ! npm run test:ci -w "${ws_dir}" -- "${rel_file}" >> "${log_dir}/npm-test.log" 2>&1; then
+           echo "--- Running $rel_file in workspace $ws_dir ---" >> "$log_dir/npm-test.log"
+           if ! npm run test:ci -w "$ws_dir" -- "$rel_file" >> "$log_dir/npm-test.log" 2>&1; then
             exit_code=1
           fi
        done
-        echo "${exit_code}" > "${log_dir}/npm-test.exit"
+        echo $exit_code > "$log_dir/npm-test.exit"
      else
-        echo "Could not extract specific failing files. Skipping full local test suite as it takes too long. Please check CI logs manually." >> "${log_dir}/npm-test.log"
-        echo 1 > "${log_dir}/npm-test.exit"
+        echo "Could not extract specific failing files. Skipping full local test suite as it takes too long. Please check CI logs manually." >> "$log_dir/npm-test.log"
+        echo 1 > "$log_dir/npm-test.exit"
      fi
    fi
  else
-    echo "Skipped due to build-and-lint failure" > "${log_dir}/npm-test.log"
-    echo 1 > "${log_dir}/npm-test.exit"
+    echo "Skipped due to build-and-lint failure" > "$log_dir/npm-test.log"
+    echo 1 > "$log_dir/npm-test.exit"
  fi
 } &

 echo "  ↳ [5/5] Starting Gemini test execution (waiting for build and lint)..."
-rm -f "${log_dir}/test-execution.exit"
+rm -f "$log_dir/test-execution.exit"
 { 
-  while [[ ! -f "${log_dir}/build-and-lint.exit" ]]; do sleep 1; done
-  read -r build_exit < "${log_dir}/build-and-lint.exit" || build_exit=""
-  if [[ "${build_exit}" == "0" ]]; then
-    "${GEMINI_CMD}" --policy "${POLICY_PATH}" -p "Analyze the diff for PR ${pr_number} using 'gh pr diff ${pr_number}'. Instead of running the project's automated test suite (like 'npm test'), physically exercise the newly changed code in the terminal (e.g., by writing a temporary script to call the new functions, or testing the CLI command directly). Verify the feature's behavior works as expected. IMPORTANT: Do NOT modify any source code to fix errors. Just exercise the code and log the results, reporting any failures clearly. Do not ask for user confirmation." > "${log_dir}/test-execution.log" 2>&1; echo $? > "${log_dir}/test-execution.exit"
+  while [ ! -f "$log_dir/build-and-lint.exit" ]; do sleep 1; done
+  if [ "$(cat "$log_dir/build-and-lint.exit")" == "0" ]; then
+    "$GEMINI_CMD" --policy "$POLICY_PATH" -p "Analyze the diff for PR $pr_number using 'gh pr diff $pr_number'. Instead of running the project's automated test suite (like 'npm test'), physically exercise the newly changed code in the terminal (e.g., by writing a temporary script to call the new functions, or testing the CLI command directly). Verify the feature's behavior works as expected. IMPORTANT: Do NOT modify any source code to fix errors. Just exercise the code and log the results, reporting any failures clearly. Do not ask for user confirmation." > "$log_dir/test-execution.log" 2>&1; echo $? > "$log_dir/test-execution.exit"
  else
-    echo "Skipped due to build-and-lint failure" > "${log_dir}/test-execution.log"
-    echo 1 > "${log_dir}/test-execution.exit"
+    echo "Skipped due to build-and-lint failure" > "$log_dir/test-execution.log"
+    echo 1 > "$log_dir/test-execution.exit"
  fi
 } &

 echo "✅ All tasks dispatched!"
-echo "You can monitor progress with: tail -f ${log_dir}/*.log"
-echo "Read your review later at: ${log_dir}/review.md"
+echo "You can monitor progress with: tail -f $log_dir/*.log"
+echo "Read your review later at: $log_dir/review.md"

 # Polling loop to wait for all background tasks to finish
 tasks=("pr-diff" "build-and-lint" "review" "npm-test" "test-execution")
 log_files=("pr-diff.diff" "build-and-lint.log" "review.md" "npm-test.log" "test-execution.log")

 declare -A task_done
-for t in "${tasks[@]}"; do task_done[${t}]=0; done
+for t in "${tasks[@]}"; do task_done[$t]=0; done

 all_done=0
-while [[ "${all_done}" -eq 0 ]]; do
+while [[ $all_done -eq 0 ]]; do
  clear
  echo "=================================================="
-  echo "🚀 Async PR Review Status for PR #${pr_number}"
+  echo "🚀 Async PR Review Status for PR #$pr_number"
  echo "=================================================="
  echo ""
  
  all_done=1
  for i in "${!tasks[@]}"; do
-    t="${tasks[${i}]}"
+    t="${tasks[$i]}"
    
-    if [[ -f "${log_dir}/${t}.exit" ]]; then
-      read -r task_exit < "${log_dir}/${t}.exit" || task_exit=""
-      if [[ "${task_exit}" == "0" ]]; then
-        echo "  ✅ ${t}: SUCCESS"
+    if [[ -f "$log_dir/$t.exit" ]]; then
+      exit_code=$(cat "$log_dir/$t.exit")
+      if [[ "$exit_code" == "0" ]]; then
+        echo "  ✅ $t: SUCCESS"
      else
-        echo "  ❌ ${t}: FAILED (exit code ${task_exit})"
+        echo "  ❌ $t: FAILED (exit code $exit_code)"
      fi
-      task_done[${t}]=1
+      task_done[$t]=1
    else
-      echo "  ⏳ ${t}: RUNNING"
+      echo "  ⏳ $t: RUNNING"
      all_done=0
    fi
  done
@@ -199,47 +195,47 @@ while [[ "${all_done}" -eq 0 ]]; do
  echo "=================================================="
  
  for i in "${!tasks[@]}"; do
-    t="${tasks[${i}]}"
-    log_file="${log_files[${i}]}"
+    t="${tasks[$i]}"
+    log_file="${log_files[$i]}"
    
-    if [[ "${task_done[${t}]}" -eq 0 ]]; then
-      if [[ -f "${log_dir}/${log_file}" ]]; then
+    if [[ ${task_done[$t]} -eq 0 ]]; then
+      if [[ -f "$log_dir/$log_file" ]]; then
        echo ""
-        echo "--- ${t} ---"
-        tail -n 5 "${log_dir}/${log_file}"
+        echo "--- $t ---"
+        tail -n 5 "$log_dir/$log_file"
      fi
    fi
  done
  
-  if [[ "${all_done}" -eq 0 ]]; then
+  if [[ $all_done -eq 0 ]]; then
    sleep 3
  fi
 done

 clear
 echo "=================================================="
-echo "🚀 Async PR Review Status for PR #${pr_number}"
+echo "🚀 Async PR Review Status for PR #$pr_number"
 echo "=================================================="
 echo ""
 for t in "${tasks[@]}"; do
-  read -r task_exit < "${log_dir}/${t}.exit" || task_exit=""
-  if [[ "${task_exit}" == "0" ]]; then
-    echo "  ✅ ${t}: SUCCESS"
+  exit_code=$(cat "$log_dir/$t.exit")
+  if [[ "$exit_code" == "0" ]]; then
+    echo "  ✅ $t: SUCCESS"
  else
-    echo "  ❌ ${t}: FAILED (exit code ${task_exit})"
+    echo "  ❌ $t: FAILED (exit code $exit_code)"
  fi
 done
 echo ""

 echo "⏳ Tasks complete! Synthesizing final assessment..."
-if ! "${GEMINI_CMD}" --policy "${POLICY_PATH}" -p "Read the review at ${log_dir}/review.md, the automated test logs at ${log_dir}/npm-test.log, and the manual test execution logs at ${log_dir}/test-execution.log. Summarize the results, state whether the build and tests passed based on ${log_dir}/build-and-lint.exit and ${log_dir}/npm-test.exit, and give a final recommendation for PR ${pr_number}." > "${log_dir}/final-assessment.md" 2>&1; then
-  echo $? > "${log_dir}/final-assessment.exit"
+if ! "$GEMINI_CMD" --policy "$POLICY_PATH" -p "Read the review at $log_dir/review.md, the automated test logs at $log_dir/npm-test.log, and the manual test execution logs at $log_dir/test-execution.log. Summarize the results, state whether the build and tests passed based on $log_dir/build-and-lint.exit and $log_dir/npm-test.exit, and give a final recommendation for PR $pr_number." > "$log_dir/final-assessment.md" 2>&1; then
+  echo $? > "$log_dir/final-assessment.exit"
  echo "❌ Final assessment synthesis failed!"
-  echo "Check ${log_dir}/final-assessment.md for details."
-  notify "Async Review Failed" "Final assessment synthesis failed." "${pr_number}"
+  echo "Check $log_dir/final-assessment.md for details."
+  notify "Async Review Failed" "Final assessment synthesis failed." "$pr_number"
  exit 1
 fi

-echo 0 > "${log_dir}/final-assessment.exit"
-echo "✅ Final assessment complete! Check ${log_dir}/final-assessment.md"
-notify "Async Review Complete" "Review and test execution finished successfully." "${pr_number}"
+echo 0 > "$log_dir/final-assessment.exit"
+echo "✅ Final assessment complete! Check $log_dir/final-assessment.md"
+notify "Async Review Complete" "Review and test execution finished successfully." "$pr_number"
@@ -1,22 +1,22 @@
 #!/bin/bash
-pr_number="${1}"
+pr_number=$1

-if [[ -z "${pr_number}" ]]; then
+if [[ -z "$pr_number" ]]; then
  echo "Usage: check-async-review <pr_number>"
  exit 1
 fi

-base_dir="$(git rev-parse --show-toplevel 2>/dev/null || true)"
-if [[ -z "${base_dir}" ]]; then
+base_dir=$(git rev-parse --show-toplevel 2>/dev/null)
+if [[ -z "$base_dir" ]]; then
  echo "❌ Must be run from within a git repository."
  exit 1
 fi

-log_dir="${base_dir}/.gemini/tmp/async-reviews/pr-${pr_number}/logs"
+log_dir="$base_dir/.gemini/tmp/async-reviews/pr-$pr_number/logs"

-if [[ ! -d "${log_dir}" ]]; then
+if [[ ! -d "$log_dir" ]]; then
  echo "STATUS: NOT_FOUND"
-  echo "❌ No logs found for PR #${pr_number} in ${log_dir}"
+  echo "❌ No logs found for PR #$pr_number in $log_dir"
  exit 0
 fi

@@ -34,32 +34,32 @@ all_done=true
 echo "STATUS: CHECKING"

 for task_info in "${tasks[@]}"; do
-  IFS="|" read -r task_name log_file <<< "${task_info}"
+  IFS="|" read -r task_name log_file <<< "$task_info"
  
-  file_path="${log_dir}/${log_file}"
-  exit_file="${log_dir}/${task_name}.exit"
+  file_path="$log_dir/$log_file"
+  exit_file="$log_dir/$task_name.exit"

-  if [[ -f "${exit_file}" ]]; then
-    read -r exit_code < "${exit_file}" || exit_code=""
-    if [[ "${exit_code}" == "0" ]]; then
-      echo "✅ ${task_name}: SUCCESS"
+  if [[ -f "$exit_file" ]]; then
+    exit_code=$(cat "$exit_file")
+    if [[ "$exit_code" == "0" ]]; then
+      echo "✅ $task_name: SUCCESS"
    else
-      echo "❌ ${task_name}: FAILED (exit code ${exit_code})"
-      echo "   Last lines of ${file_path}:"
-      tail -n 3 "${file_path}" | sed 's/^/      /' || true
+      echo "❌ $task_name: FAILED (exit code $exit_code)"
+      echo "   Last lines of $file_path:"
+      tail -n 3 "$file_path" | sed 's/^/      /'
    fi
-  elif [[ -f "${file_path}" ]]; then
-    echo "⏳ ${task_name}: RUNNING"
+  elif [[ -f "$file_path" ]]; then
+    echo "⏳ $task_name: RUNNING"
    all_done=false
  else
-    echo "➖ ${task_name}: NOT STARTED"
+    echo "➖ $task_name: NOT STARTED"
    all_done=false
  fi
 done

-if [[ "${all_done}" == "true" ]]; then
+if $all_done; then
  echo "STATUS: COMPLETE"
-  echo "LOG_DIR: ${log_dir}"
+  echo "LOG_DIR: $log_dir"
 else
  echo "STATUS: IN_PROGRESS"
-fi
+fi
@@ -175,9 +175,7 @@ runs:
          --dry-run="${INPUTS_DRY_RUN}" \
          --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
          --no-tag
-        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
-        fi
+        npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false

    - name: '🔗 Install latest core package'
      working-directory: '${{ inputs.working-directory }}'
@@ -195,7 +193,7 @@ runs:
        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'

    - name: '📦 Prepare bundled CLI for npm release'
-      if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/'"
+      if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/' && inputs.npm-tag != 'latest'"
      working-directory: '${{ inputs.working-directory }}'
      shell: 'bash'
      run: |
@@ -250,9 +248,7 @@ runs:
          --dry-run="${INPUTS_DRY_RUN}" \
          --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
          --no-tag
-          if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
-          fi
+        npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false

    - name: '🔬 Verify NPM release by version'
      uses: './.github/actions/verify-release'
@@ -291,25 +287,8 @@ runs:
        INPUTS_PREVIOUS_TAG: '${{ inputs.previous-tag }}'
      shell: 'bash'
      run: |
-        rm -f gemini-cli-bundle.zip
-        (cd bundle && chmod +x gemini.js && zip -r ../gemini-cli-bundle.zip .)
-
-        echo "Testing the generated bundle archive..."
-        rm -rf test-bundle
-        mkdir -p test-bundle
-        unzip -q gemini-cli-bundle.zip -d test-bundle
-
-        # Verify it runs and outputs a version
-        BUNDLE_VERSION=$(node test-bundle/gemini.js --version | xargs)
-        echo "Bundle version output: ${BUNDLE_VERSION}"
-        if [[ -z "${BUNDLE_VERSION}" ]]; then
-          echo "Error: Bundle failed to execute or return version."
-          exit 1
-        fi
-        rm -rf test-bundle
-
        gh release create "${INPUTS_RELEASE_TAG}" \
-          gemini-cli-bundle.zip \
+          bundle/gemini.js \
          --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
          --title "Release ${INPUTS_RELEASE_TAG}" \
          --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \
@@ -18,13 +18,6 @@ runs:
      env:
        JSON_INPUTS: '${{ toJSON(inputs) }}'
      run: 'echo "$JSON_INPUTS"'
-    - name: 'Install system dependencies'
-      if: "runner.os == 'Linux'"
-      run: |
-        sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq bubblewrap
-        # Ubuntu 24.04+ requires this to allow bwrap to function in CI
-        sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
-      shell: 'bash'
    - name: 'Run Tests'
      env:
        GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
@@ -0,0 +1,69 @@
+name: 'Evals: PR Guidance'
+
+on:
+  pull_request:
+    paths:
+      - 'packages/core/src/**/*.ts'
+      - '!**/*.test.ts'
+      - '!**/*.test.tsx'
+
+permissions:
+  pull-requests: 'write'
+  contents: 'read'
+
+jobs:
+  provide-guidance:
+    name: 'Model Steering Guidance'
+    runs-on: 'ubuntu-latest'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Detect Steering Changes'
+        id: 'detect'
+        run: |
+          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
+          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
+
+      - name: 'Analyze PR Content'
+        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
+        id: 'analysis'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          # Check for behavioral eval changes
+          EVAL_CHANGES=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep "^evals/" || true)
+          if [ -z "$EVAL_CHANGES" ]; then
+            echo "MISSING_EVALS=true" >> "$GITHUB_OUTPUT"
+          fi
+
+          # Check if user is a maintainer (has write/admin access)
+          USER_PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/${{ github.actor }}/permission --jq '.permission')
+          if [[ "$USER_PERMISSION" == "admin" || "$USER_PERMISSION" == "write" ]]; then
+            echo "IS_MAINTAINER=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: 'Post Guidance Comment'
+        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
+        uses: 'thollander/actions-comment-pull-request@65f9e5c9a1f2cd378bd74b2e057c9736982a8e74' # ratchet:thollander/actions-comment-pull-request@v3
+        with:
+          comment-tag: 'eval-guidance-bot'
+          message: |
+            ### 🧠 Model Steering Guidance
+
+            This PR modifies files that affect the model's behavior (prompts, tools, or instructions).
+
+            ${{ steps.analysis.outputs.MISSING_EVALS == 'true' && '- ⚠️ **Consider adding Evals:** No behavioral evaluations (`evals/*.eval.ts`) were added or updated in this PR. Consider adding a test case to verify the new behavior and prevent regressions.' || '' }}
+            ${{ steps.analysis.outputs.IS_MAINTAINER == 'true' && '- 🚀 **Maintainer Reminder:** Please ensure that these changes do not regress results on benchmark evals before merging.' || '' }}
+
+            ---
+            *This is an automated guidance message triggered by steering logic signatures.*
@@ -1,137 +0,0 @@
-name: 'Evals: PR Evaluation & Regression'
-
-on:
-  pull_request:
-    types: ['opened', 'synchronize', 'reopened', 'ready_for_review']
-    paths:
-      - 'packages/core/src/prompts/**'
-      - 'packages/core/src/tools/**'
-      - 'packages/core/src/agents/**'
-      - 'evals/**'
-      - '!**/*.test.ts'
-      - '!**/*.test.tsx'
-  workflow_dispatch:
-
-# Prevents multiple runs for the same PR simultaneously (saves tokens)
-concurrency:
-  group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
-  cancel-in-progress: true
-
-permissions:
-  pull-requests: 'write'
-  contents: 'read'
-  actions: 'read'
-
-jobs:
-  pr-evaluation:
-    name: 'Evaluate Steering & Regressions'
-    runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name != 'pull_request' || (github.event.pull_request.draft == false && github.event.pull_request.head.repo.full_name == github.repository))"
-    # External contributors' PRs will wait for approval in this environment
-    environment: |-
-      ${{ (github.event.pull_request.head.repo.full_name == github.repository) && 'internal' || 'external-evals' }}
-    env:
-      # CENTRALIZED MODEL LIST
-      MODEL_LIST: 'gemini-3-flash-preview'
-
-    steps:
-      - name: 'Checkout'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: 'Set up Node.js'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
-        with:
-          node-version-file: '.nvmrc'
-          cache: 'npm'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-
-      - name: 'Build project'
-        run: 'npm run build'
-
-      - name: 'Detect Steering Changes'
-        id: 'detect'
-        run: |
-          SHOULD_RUN=$(node scripts/changed_prompt.js)
-          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
-          echo "SHOULD_RUN=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
-          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
-
-      - name: 'Analyze PR Content (Guidance)'
-        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
-        id: 'analysis'
-        env:
-          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-        run: |
-          # Check for behavioral eval changes
-          EVAL_CHANGES=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep "^evals/" || true)
-          if [ -z "$EVAL_CHANGES" ]; then
-            echo "MISSING_EVALS=true" >> "$GITHUB_OUTPUT"
-          fi
-
-          # Check if user is a maintainer
-          USER_PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/${{ github.actor }}/permission --jq '.permission')
-          if [[ "$USER_PERMISSION" == "admin" || "$USER_PERMISSION" == "write" ]]; then
-            echo "IS_MAINTAINER=true" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: 'Execute Regression Check'
-        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
-        env:
-          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          MODEL_LIST: '${{ env.MODEL_LIST }}'
-        run: |
-          # Run the regression check loop. The script saves the report to a file.
-          node scripts/run_eval_regression.js
-
-          # Use the generated report file if it exists
-          if [[ -f eval_regression_report.md ]]; then
-            echo "REPORT_FILE=eval_regression_report.md" >> "$GITHUB_ENV"
-          fi
-
-      - name: 'Post or Update PR Comment'
-        if: "always() && steps.detect.outputs.STEERING_DETECTED == 'true'"
-        env:
-          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-        run: |
-          # 1. Build the full comment body
-          {
-            if [[ -f eval_regression_report.md ]]; then
-              cat eval_regression_report.md
-              echo ""
-            fi
-            echo "### 🧠 Model Steering Guidance"
-            echo ""
-            echo "This PR modifies files that affect the model's behavior (prompts, tools, or instructions)."
-            echo ""
-
-            if [[ "${{ steps.analysis.outputs.MISSING_EVALS }}" == "true" ]]; then
-              echo "- ⚠️ **Consider adding Evals:** No behavioral evaluations (\`evals/*.eval.ts\`) were added or updated in this PR. Consider [adding a test case](https://github.com/google-gemini/gemini-cli/blob/main/evals/README.md#creating-an-evaluation) to verify the new behavior and prevent regressions."
-            fi
-
-            if [[ "${{ steps.analysis.outputs.IS_MAINTAINER }}" == "true" ]]; then
-              echo "- 🚀 **Maintainer Reminder:** Please ensure that these changes do not regress results on benchmark evals before merging."
-            fi
-
-            echo ""
-            echo "---"
-            echo "*This is an automated guidance message triggered by steering logic signatures.*"
-            echo "<!-- eval-pr-report -->"
-          } > full_comment.md
-
-          # 2. Find if a comment with our unique tag already exists
-          # We extract the numeric ID from the URL to ensure compatibility with the REST API
-          COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-pr-report -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
-
-          # 3. Update or Create the comment
-          if [ -n "$COMMENT_ID" ]; then
-            echo "Updating existing comment $COMMENT_ID via API..."
-            gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body=@full_comment.md
-          else
-            echo "Creating new PR comment..."
-            gh pr comment ${{ github.event.pull_request.number }} --body-file full_comment.md
-          fi
@@ -346,11 +346,9 @@ npm run lint

 - Please adhere to the coding style, patterns, and conventions used throughout
  the existing codebase.
- Consult
-  [GEMINI.md](https://github.com/google-gemini/gemini-cli/blob/main/GEMINI.md)
-  (typically found in the project root) for specific instructions related to
-  AI-assisted development, including conventions for React, comments, and Git
-  usage.
+- Consult [GEMINI.md](../GEMINI.md) (typically found in the project root) for
+  specific instructions related to AI-assisted development, including
+  conventions for React, comments, and Git usage.
 - **Imports:** Pay special attention to import paths. The project uses ESLint to
  enforce restrictions on relative imports between packages.

@@ -507,9 +505,8 @@ code.

 ### Documentation structure

-Our documentation is organized using
-[sidebar.json](https://github.com/google-gemini/gemini-cli/blob/main/docs/sidebar.json)
-as the table of contents. When adding new documentation:
+Our documentation is organized using [sidebar.json](/docs/sidebar.json) as the
+table of contents. When adding new documentation:

 1. Create your markdown file **in the appropriate directory** under `/docs`.
 2. Add an entry to `sidebar.json` in the relevant section.
@@ -30,7 +30,7 @@ Learn all about Gemini CLI in our [documentation](https://geminicli.com/docs/).
 ## 📦 Installation

 See
-[Gemini CLI installation, execution, and releases](https://www.geminicli.com/docs/get-started/installation)
+[Gemini CLI installation, execution, and releases](./docs/get-started/installation.md)
 for recommended system specifications and a detailed installation guide.

 ### Quick Install
@@ -71,9 +71,9 @@ conda activate gemini_env
 npm install -g @google/gemini-cli
 ```

-## Release Channels
+## Release Cadence and Tags

-See [Releases](https://www.geminicli.com/docs/changelogs) for more details.
+See [Releases](./docs/releases.md) for more details.

 ### Preview

@@ -209,7 +209,7 @@ gemini
 ```

 For Google Workspace accounts and other authentication methods, see the
-[authentication guide](https://www.geminicli.com/docs/get-started/authentication).
+[authentication guide](./docs/get-started/authentication.md).

 ## 🚀 Getting Started

@@ -278,64 +278,59 @@ gemini

 ### Getting Started

- [**Quickstart Guide**](https://www.geminicli.com/docs/get-started) - Get up
-  and running quickly.
- [**Authentication Setup**](https://www.geminicli.com/docs/get-started/authentication) -
-  Detailed auth configuration.
- [**Configuration Guide**](https://www.geminicli.com/docs/reference/configuration) -
-  Settings and customization.
- [**Keyboard Shortcuts**](https://www.geminicli.com/docs/reference/keyboard-shortcuts) -
+- [**Quickstart Guide**](./docs/get-started/index.md) - Get up and running
+  quickly.
+- [**Authentication Setup**](./docs/get-started/authentication.md) - Detailed
+  auth configuration.
+- [**Configuration Guide**](./docs/reference/configuration.md) - Settings and
+  customization.
+- [**Keyboard Shortcuts**](./docs/reference/keyboard-shortcuts.md) -
  Productivity tips.

 ### Core Features

- [**Commands Reference**](https://www.geminicli.com/docs/reference/commands) -
-  All slash commands (`/help`, `/chat`, etc).
- [**Custom Commands**](https://www.geminicli.com/docs/cli/custom-commands) -
-  Create your own reusable commands.
- [**Context Files (GEMINI.md)**](https://www.geminicli.com/docs/cli/gemini-md) -
-  Provide persistent context to Gemini CLI.
- [**Checkpointing**](https://www.geminicli.com/docs/cli/checkpointing) - Save
-  and resume conversations.
- [**Token Caching**](https://www.geminicli.com/docs/cli/token-caching) -
-  Optimize token usage.
+- [**Commands Reference**](./docs/reference/commands.md) - All slash commands
+  (`/help`, `/chat`, etc).
+- [**Custom Commands**](./docs/cli/custom-commands.md) - Create your own
+  reusable commands.
+- [**Context Files (GEMINI.md)**](./docs/cli/gemini-md.md) - Provide persistent
+  context to Gemini CLI.
+- [**Checkpointing**](./docs/cli/checkpointing.md) - Save and resume
+  conversations.
+- [**Token Caching**](./docs/cli/token-caching.md) - Optimize token usage.

 ### Tools & Extensions

- [**Built-in Tools Overview**](https://www.geminicli.com/docs/reference/tools)
-  - [File System Operations](https://www.geminicli.com/docs/tools/file-system)
-  - [Shell Commands](https://www.geminicli.com/docs/tools/shell)
-  - [Web Fetch & Search](https://www.geminicli.com/docs/tools/web-fetch)
- [**MCP Server Integration**](https://www.geminicli.com/docs/tools/mcp-server) -
-  Extend with custom tools.
- [**Custom Extensions**](https://geminicli.com/docs/extensions/writing-extensions) -
-  Build and share your own commands.
+- [**Built-in Tools Overview**](./docs/reference/tools.md)
+  - [File System Operations](./docs/tools/file-system.md)
+  - [Shell Commands](./docs/tools/shell.md)
+  - [Web Fetch & Search](./docs/tools/web-fetch.md)
+- [**MCP Server Integration**](./docs/tools/mcp-server.md) - Extend with custom
+  tools.
+- [**Custom Extensions**](./docs/extensions/index.md) - Build and share your own
+  commands.

 ### Advanced Topics

- [**Headless Mode (Scripting)**](https://www.geminicli.com/docs/cli/headless) -
-  Use Gemini CLI in automated workflows.
- [**IDE Integration**](https://www.geminicli.com/docs/ide-integration) - VS
-  Code companion.
- [**Sandboxing & Security**](https://www.geminicli.com/docs/cli/sandbox) - Safe
-  execution environments.
- [**Trusted Folders**](https://www.geminicli.com/docs/cli/trusted-folders) -
-  Control execution policies by folder.
- [**Enterprise Guide**](https://www.geminicli.com/docs/cli/enterprise) - Deploy
-  and manage in a corporate environment.
- [**Telemetry & Monitoring**](https://www.geminicli.com/docs/cli/telemetry) -
-  Usage tracking.
- [**Tools reference**](https://www.geminicli.com/docs/reference/tools) -
-  Built-in tools overview.
- [**Local development**](https://www.geminicli.com/docs/local-development) -
-  Local development tooling.
+- [**Headless Mode (Scripting)**](./docs/cli/headless.md) - Use Gemini CLI in
+  automated workflows.
+- [**IDE Integration**](./docs/ide-integration/index.md) - VS Code companion.
+- [**Sandboxing & Security**](./docs/cli/sandbox.md) - Safe execution
+  environments.
+- [**Trusted Folders**](./docs/cli/trusted-folders.md) - Control execution
+  policies by folder.
+- [**Enterprise Guide**](./docs/cli/enterprise.md) - Deploy and manage in a
+  corporate environment.
+- [**Telemetry & Monitoring**](./docs/cli/telemetry.md) - Usage tracking.
+- [**Tools reference**](./docs/reference/tools.md) - Built-in tools overview.
+- [**Local development**](./docs/local-development.md) - Local development
+  tooling.

 ### Troubleshooting & Support

- [**Troubleshooting Guide**](https://www.geminicli.com/docs/resources/troubleshooting) -
-  Common issues and solutions.
- [**FAQ**](https://www.geminicli.com/docs/resources/faq) - Frequently asked
-  questions.
+- [**Troubleshooting Guide**](./docs/resources/troubleshooting.md) - Common
+  issues and solutions.
+- [**FAQ**](./docs/resources/faq.md) - Frequently asked questions.
 - Use `/bug` command to report issues directly from the CLI.

 ### Using MCP Servers
@@ -349,9 +344,8 @@ custom tools:
 > @database Run a query to find inactive users
 ```

-See the
-[MCP Server Integration guide](https://www.geminicli.com/docs/tools/mcp-server)
-for setup instructions.
+See the [MCP Server Integration guide](./docs/tools/mcp-server.md) for setup
+instructions.

 ## 🤝 Contributing

@@ -372,8 +366,7 @@ for planned features and priorities.
 ## 📖 Resources

 - **[Official Roadmap](./ROADMAP.md)** - See what's coming next.
- **[Changelog](https://www.geminicli.com/docs/changelogs)** - See recent
-  notable updates.
+- **[Changelog](./docs/changelogs/index.md)** - See recent notable updates.
 - **[NPM Package](https://www.npmjs.com/package/@google/gemini-cli)** - Package
  registry.
 - **[GitHub Issues](https://github.com/google-gemini/gemini-cli/issues)** -
@@ -383,14 +376,13 @@ for planned features and priorities.

 ### Uninstall

-See the [Uninstall Guide](https://www.geminicli.com/docs/resources/uninstall)
-for removal instructions.
+See the [Uninstall Guide](./docs/resources/uninstall.md) for removal
+instructions.

 ## 📄 Legal

 - **License**: [Apache License 2.0](LICENSE)
- **Terms of Service**:
-  [Terms & Privacy](https://www.geminicli.com/docs/resources/tos-privacy)
+- **Terms of Service**: [Terms & Privacy](./docs/resources/tos-privacy.md)
 - **Security**: [Security Policy](SECURITY.md)

 ---
@@ -1,6 +1,6 @@
-# Latest stable release: v0.35.3
+# Latest stable release: v0.35.2

-Released: March 28, 2026
+Released: March 26, 2026

 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -29,9 +29,6 @@ npm install -g @google/gemini-cli

 ## What's Changed

- fix(patch): cherry-pick 765fb67 to release/v0.35.2-pr-24055 [CONFLICTS] by
-  @gemini-cli-robot in
-  [#24063](https://github.com/google-gemini/gemini-cli/pull/24063)
 - fix(core): allow disabling environment variable redaction by @galz10 in
  [#23927](https://github.com/google-gemini/gemini-cli/pull/23927)
 - fix(a2a-server): A2A server should execute ask policies in interactive mode by
@@ -388,4 +385,4 @@ npm install -g @google/gemini-cli
  [#23585](https://github.com/google-gemini/gemini-cli/pull/23585)

 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.34.0...v0.35.3
+https://github.com/google-gemini/gemini-cli/compare/v0.34.0...v0.35.2
@@ -1,6 +1,6 @@
-# Preview release: v0.36.0-preview.8
+# Preview release: v0.36.0-preview.5

-Released: April 01, 2026
+Released: March 27, 2026

 Our preview release includes the latest, new, and experimental features. This
 release may not be as stable as our [latest weekly release](latest.md).
@@ -31,10 +31,6 @@ npm install -g @google/gemini-cli@preview

 ## What's Changed

- fix(patch): cherry-pick 765fb67 to release/v0.36.0-preview.5-pr-24055 to patch
-  version v0.36.0-preview.5 and create version 0.36.0-preview.6 by
-  @gemini-cli-robot in
-  [#24061](https://github.com/google-gemini/gemini-cli/pull/24061)
 - fix(a2a-server): A2A server should execute ask policies in interactive mode by
  @kschaab in [#23831](https://github.com/google-gemini/gemini-cli/pull/23831)
 - docs(core): document agent_card_json string literal options for remote agents
@@ -390,4 +386,4 @@ npm install -g @google/gemini-cli@preview
  [#23666](https://github.com/google-gemini/gemini-cli/pull/23666)

 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.35.0-preview.5...v0.36.0-preview.8
+https://github.com/google-gemini/gemini-cli/compare/v0.35.0-preview.5...v0.36.0-preview.5
@@ -52,7 +52,7 @@ These commands are available within the interactive REPL.
 | `--prompt-interactive`           | `-i`  | string  | -         | Execute prompt and continue in interactive mode                                                                                                                        |
 | `--worktree`                     | `-w`  | string  | -         | Start Gemini in a new git worktree. If no name is provided, one is generated automatically. Requires `experimental.worktrees: true` in settings.                       |
 | `--sandbox`                      | `-s`  | boolean | `false`   | Run in a sandboxed environment for safer execution                                                                                                                     |
-| `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`, `plan`                                                                                      |
+| `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`                                                                                              |
 | `--yolo`                         | `-y`  | boolean | `false`   | **Deprecated.** Auto-approve all actions. Use `--approval-mode=yolo` instead.                                                                                          |
 | `--experimental-acp`             | -     | boolean | -         | Start in ACP (Agent Code Pilot) mode. **Experimental feature.**                                                                                                        |
 | `--experimental-zed-integration` | -     | boolean | -         | Run in Zed editor integration mode. **Experimental feature.**                                                                                                          |
@@ -39,9 +39,7 @@ To start Plan Mode while using Gemini CLI:
  the rotation when Gemini CLI is actively processing or showing confirmation
  dialogs.

- **Command:** Type `/plan [goal]` in the input box. The `[goal]` is optional;
-  for example, `/plan implement authentication` will switch to Plan Mode and
-  immediately submit the prompt to the model.
+- **Command:** Type `/plan` in the input box.

 - **Natural Language:** Ask Gemini CLI to "start a plan for...". Gemini CLI
  calls the
@@ -56,21 +54,19 @@ Gemini CLI takes action.

 1.  **Provide a goal:** Start by describing what you want to achieve. Gemini CLI
    will then enter Plan Mode (if it's not already) to research the task.
-2.  **Discuss and agree on strategy:** As Gemini CLI analyzes your codebase, it
-    will discuss its findings and proposed strategy with you to ensure
-    alignment. It may ask you questions or present different implementation
-    options using [`ask_user`](../tools/ask-user.md). **Gemini CLI will stop and
-    wait for your confirmation** before drafting the formal plan. You should
-    reach an informal agreement on the approach before proceeding.
-3.  **Review the plan:** Once you've agreed on the strategy, Gemini CLI creates
-    a detailed implementation plan as a Markdown file in your plans directory.
+2.  **Review research and provide input:** As Gemini CLI analyzes your codebase,
+    it may ask you questions or present different implementation options using
+    [`ask_user`](../tools/ask-user.md). Provide your preferences to help guide
+    the design.
+3.  **Review the plan:** Once Gemini CLI has a proposed strategy, it creates a
+    detailed implementation plan as a Markdown file in your plans directory.
    - **View:** You can open and read this file to understand the proposed
      changes.
    - **Edit:** Press `Ctrl+X` to open the plan directly in your configured
      external editor.

 4.  **Approve or iterate:** Gemini CLI will present the finalized plan for your
-    formal approval.
+    approval.
    - **Approve:** If you're satisfied with the plan, approve it to start the
      implementation immediately: **Yes, automatically accept edits** or **Yes,
      manually accept edits**.
@@ -123,7 +119,6 @@ These are the only allowed tools:
  [`glob`](../tools/file-system.md#4-glob-findfiles)
 - **Search:** [`grep_search`](../tools/file-system.md#5-grep_search-searchtext),
  [`google_web_search`](../tools/web-search.md),
-  [`web_fetch`](../tools/web-fetch.md) (requires explicit confirmation),
  [`get_internal_docs`](../tools/internal-docs.md)
 - **Research Subagents:**
  [`codebase_investigator`](../core/subagents.md#codebase-investigator),
@@ -30,7 +30,6 @@ they appear in the UI.
 | Default Approval Mode   | `general.defaultApprovalMode`      | The default approval mode for tool execution. 'default' prompts for approval, 'auto_edit' auto-approves edit tools, and 'plan' is read-only mode. YOLO mode (auto-approve all actions) can only be enabled via command line (--yolo or --approval-mode=yolo). | `"default"` |
 | Enable Auto Update      | `general.enableAutoUpdate`         | Enable automatic updates.                                                                                                                                                                                                                                     | `true`      |
 | Enable Notifications    | `general.enableNotifications`      | Enable run-event notifications for action-required prompts and session completion.                                                                                                                                                                            | `false`     |
-| Enable Plan Mode        | `general.plan.enabled`             | Enable Plan Mode for read-only safety during planning.                                                                                                                                                                                                        | `true`      |
 | Plan Directory          | `general.plan.directory`           | The directory where planning artifacts are stored. If not specified, defaults to the system temporary directory. A custom directory requires a policy to allow write access in Plan Mode.                                                                     | `undefined` |
 | Plan Model Routing      | `general.plan.modelRouting`        | Automatically switch between Pro and Flash models based on Plan Mode status. Uses Pro for the planning phase and Flash for the implementation phase.                                                                                                          | `true`      |
 | Retry Fetch Errors      | `general.retryFetchErrors`         | Retry on "exception TypeError: fetch failed sending request" errors.                                                                                                                                                                                          | `true`      |
@@ -47,39 +46,38 @@ they appear in the UI.

 ### UI

-| UI Label                             | Setting                                | Description                                                                                                                                                       | Default |
-| ------------------------------------ | -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
-| Auto Theme Switching                 | `ui.autoThemeSwitching`                | Automatically switch between default light and dark themes based on terminal background color.                                                                    | `true`  |
-| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval` | Interval in seconds to poll the terminal background color.                                                                                                        | `60`    |
-| Hide Window Title                    | `ui.hideWindowTitle`                   | Hide the window title bar                                                                                                                                         | `false` |
-| Inline Thinking                      | `ui.inlineThinkingMode`                | Display model thinking inline: off or full.                                                                                                                       | `"off"` |
-| Show Thoughts in Title               | `ui.showStatusInTitle`                 | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false` |
-| Dynamic Window Title                 | `ui.dynamicWindowTitle`                | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`  |
-| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`  |
-| Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                          | `true`  |
-| Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                       | `false` |
-| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                         | `false` |
-| Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`  |
-| Compact Tool Output                  | `ui.compactToolOutput`                 | Display tool outputs (like directory listings and file reads) in a compact, structured format.                                                                    | `false` |
-| Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                       | `false` |
-| Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false` |
-| Hide CWD                             | `ui.footer.hideCWD`                    | Hide the current working directory in the footer.                                                                                                                 | `false` |
-| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`          | Hide the sandbox status indicator in the footer.                                                                                                                  | `false` |
-| Hide Model Info                      | `ui.footer.hideModelInfo`              | Hide the model name and context usage in the footer.                                                                                                              | `false` |
-| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`      | Hides the context window usage percentage.                                                                                                                        | `true`  |
-| Hide Footer                          | `ui.hideFooter`                        | Hide the footer from the UI                                                                                                                                       | `false` |
-| Show Memory Usage                    | `ui.showMemoryUsage`                   | Display memory usage information in the UI                                                                                                                        | `false` |
-| Show Line Numbers                    | `ui.showLineNumbers`                   | Show line numbers in the chat.                                                                                                                                    | `true`  |
-| Show Citations                       | `ui.showCitations`                     | Show citations for generated text in the chat.                                                                                                                    | `false` |
-| Show Model Info In Chat              | `ui.showModelInfoInChat`               | Show the model name in the chat for each model turn.                                                                                                              | `false` |
-| Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                        | `true`  |
-| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false` |
-| Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                       | `true`  |
-| Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`  |
-| Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`  |
-| Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, all, or off.                                                                                       | `"off"` |
-| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                       | `"low"` |
-| Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                   | `false` |
+| UI Label                             | Setting                                | Description                                                                                                                                                       | Default  |
+| ------------------------------------ | -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- |
+| Auto Theme Switching                 | `ui.autoThemeSwitching`                | Automatically switch between default light and dark themes based on terminal background color.                                                                    | `true`   |
+| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval` | Interval in seconds to poll the terminal background color.                                                                                                        | `60`     |
+| Hide Window Title                    | `ui.hideWindowTitle`                   | Hide the window title bar                                                                                                                                         | `false`  |
+| Inline Thinking                      | `ui.inlineThinkingMode`                | Display model thinking inline: off or full.                                                                                                                       | `"off"`  |
+| Show Thoughts in Title               | `ui.showStatusInTitle`                 | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false`  |
+| Dynamic Window Title                 | `ui.dynamicWindowTitle`                | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`   |
+| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`   |
+| Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                          | `true`   |
+| Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                       | `false`  |
+| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                         | `false`  |
+| Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`   |
+| Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                       | `false`  |
+| Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false`  |
+| Hide CWD                             | `ui.footer.hideCWD`                    | Hide the current working directory in the footer.                                                                                                                 | `false`  |
+| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`          | Hide the sandbox status indicator in the footer.                                                                                                                  | `false`  |
+| Hide Model Info                      | `ui.footer.hideModelInfo`              | Hide the model name and context usage in the footer.                                                                                                              | `false`  |
+| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`      | Hides the context window usage percentage.                                                                                                                        | `true`   |
+| Hide Footer                          | `ui.hideFooter`                        | Hide the footer from the UI                                                                                                                                       | `false`  |
+| Show Memory Usage                    | `ui.showMemoryUsage`                   | Display memory usage information in the UI                                                                                                                        | `false`  |
+| Show Line Numbers                    | `ui.showLineNumbers`                   | Show line numbers in the chat.                                                                                                                                    | `true`   |
+| Show Citations                       | `ui.showCitations`                     | Show citations for generated text in the chat.                                                                                                                    | `false`  |
+| Show Model Info In Chat              | `ui.showModelInfoInChat`               | Show the model name in the chat for each model turn.                                                                                                              | `false`  |
+| Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                        | `true`   |
+| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false`  |
+| Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                       | `true`   |
+| Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`   |
+| Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`   |
+| Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, both, or nothing.                                                                                  | `"tips"` |
+| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                       | `"low"`  |
+| Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                   | `false`  |

 ### IDE

@@ -153,20 +151,25 @@ they appear in the UI.

 | UI Label                          | Setting                        | Description                                   | Default |
 | --------------------------------- | ------------------------------ | --------------------------------------------- | ------- |
-| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits | `true`  |
+| Auto Configure Max Old Space Size | `advanced.autoConfigureMemory` | Automatically configure Node.js memory limits | `false` |

 ### Experimental

-| UI Label                  | Setting                             | Description                                                                                                                                               | Default |
-| ------------------------- | ----------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
-| Enable Git Worktrees      | `experimental.worktrees`            | Enable automated Git worktree management for parallel work.                                                                                               | `false` |
-| Use OSC 52 Paste          | `experimental.useOSC52Paste`        | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
-| Use OSC 52 Copy           | `experimental.useOSC52Copy`         | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
-| Model Steering            | `experimental.modelSteering`        | Enable model steering (user hints) to guide the model during tool execution.                                                                              | `false` |
-| Direct Web Fetch          | `experimental.directWebFetch`       | Enable web fetch behavior that bypasses LLM summarization.                                                                                                | `false` |
-| Memory Manager Agent      | `experimental.memoryManager`        | Replace the built-in save_memory tool with a memory manager subagent that supports adding, removing, de-duplicating, and organizing memories.             | `false` |
-| Enable Context Management | `experimental.contextManagement`    | Enable logic for context management.                                                                                                                      | `false` |
-| Topic & Update Narration  | `experimental.topicUpdateNarration` | Enable the experimental Topic & Update communication model for reduced chattiness and structured progress reporting.                                      | `false` |
+| UI Label                           | Setting                                        | Description                                                                                                                                               | Default |
+| ---------------------------------- | ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Enable Tool Output Masking         | `experimental.toolOutputMasking.enabled`       | Enables tool output masking to save tokens.                                                                                                               | `true`  |
+| Enable Git Worktrees               | `experimental.worktrees`                       | Enable automated Git worktree management for parallel work.                                                                                               | `false` |
+| Use OSC 52 Paste                   | `experimental.useOSC52Paste`                   | Use OSC 52 for pasting. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
+| Use OSC 52 Copy                    | `experimental.useOSC52Copy`                    | Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it). | `false` |
+| Plan                               | `experimental.plan`                            | Enable Plan Mode.                                                                                                                                         | `true`  |
+| Model Steering                     | `experimental.modelSteering`                   | Enable model steering (user hints) to guide the model during tool execution.                                                                              | `false` |
+| Direct Web Fetch                   | `experimental.directWebFetch`                  | Enable web fetch behavior that bypasses LLM summarization.                                                                                                | `false` |
+| Memory Manager Agent               | `experimental.memoryManager`                   | Replace the built-in save_memory tool with a memory manager subagent that supports adding, removing, de-duplicating, and organizing memories.             | `false` |
+| Agent History Truncation           | `experimental.agentHistoryTruncation`          | Enable truncation window logic for the Agent History Provider.                                                                                            | `false` |
+| Agent History Truncation Threshold | `experimental.agentHistoryTruncationThreshold` | The maximum number of messages before history is truncated.                                                                                               | `30`    |
+| Agent History Retained Messages    | `experimental.agentHistoryRetainedMessages`    | The number of recent messages to retain after truncation.                                                                                                 | `15`    |
+| Agent History Summarization        | `experimental.agentHistorySummarization`       | Enable summarization of truncated content via a small model for the Agent History Provider.                                                               | `false` |
+| Topic & Update Narration           | `experimental.topicUpdateNarration`            | Enable the experimental Topic & Update communication model for reduced chattiness and structured progress reporting.                                      | `false` |

 ### Skills

@@ -19,7 +19,6 @@ using the `/theme` command within Gemini CLI:
  - `Holiday`
  - `Shades Of Purple`
  - `Solarized Dark`
-  - `Tokyo Night`
 - **Light themes:**
  - `ANSI Light`
  - `Ayu Light`
@@ -253,10 +252,6 @@ identify their source, for example: `shades-of-green (green-extension)`.

 <img src="/docs/assets/theme-solarized-dark.png" alt="Solarized Dark theme" width="600">

-### Tokyo Night
-
-<img src="/docs/assets/theme-tokyonight-dark.png" alt="Tokyo Night theme" width="600">
-
 ## Light themes

 ### ANSI Light
@@ -7,8 +7,8 @@ requests sent from `packages/cli`. For a general overview of Gemini CLI, see the

 ## Navigating this section

- **[Sub-agents](./subagents.md):** Learn how to create and use specialized
-  sub-agents for complex tasks.
+- **[Sub-agents (experimental)](./subagents.md):** Learn how to create and use
+  specialized sub-agents for complex tasks.
 - **[Core tools reference](../reference/tools.md):** Information on how tools
  are defined, registered, and used by the core.
 - **[Memory Import Processor](../reference/memport.md):** Documentation for the
@@ -1,16 +1,20 @@
-# Subagents
+# Subagents (experimental)

 Subagents are specialized agents that operate within your main Gemini CLI
 session. They are designed to handle specific, complex tasks—like deep codebase
 analysis, documentation lookup, or domain-specific reasoning—without cluttering
 the main agent's context or toolset.

-Subagents are enabled by default. To disable them, set `enableAgents` to `false`
-in your `settings.json`:
+<!-- prettier-ignore -->
+> [!NOTE]
+> Subagents are currently an experimental feature.
+> 
+To use custom subagents, you must ensure they are enabled in your
+`settings.json` (enabled by default):

 ```json
 {
-  "experimental": { "enableAgents": false }
+  "experimental": { "enableAgents": true }
 }
 ```

@@ -222,65 +226,19 @@ the `click_at` tool for precise, coordinate-based interactions.
 > The visual agent requires API key or Vertex AI authentication. It is
 > not available when using "Sign in with Google".

-#### Sandbox support
-
-The browser agent adjusts its behavior automatically when running inside a
-sandbox.
-
-##### macOS seatbelt (`sandbox-exec`)
-
-When the CLI runs under the macOS seatbelt sandbox, `persistent` and `isolated`
-session modes are forced to `isolated` with `headless` enabled. This avoids
-permission errors caused by seatbelt file-system restrictions on persistent
-browser profiles. If `sessionMode` is set to `existing`, no override is applied.
-
-##### Container sandboxes (Docker / Podman)
-
-Chrome is not available inside the container, so the browser agent is
-**disabled** unless `sessionMode` is set to `"existing"`. When enabled with
-`existing` mode, the agent automatically connects to Chrome on the host via the
-resolved IP of `host.docker.internal:9222` instead of using local pipe
-discovery. Port `9222` is currently hardcoded and cannot be customized.
-
-To use the browser agent in a Docker sandbox:
-
-1. Start Chrome on the host with remote debugging enabled:
-
-   ```bash
-   # Option A: Launch Chrome from the command line
-   google-chrome --remote-debugging-port=9222
-
-   # Option B: Enable in Chrome settings
-   # Navigate to chrome://inspect/#remote-debugging and enable
-   ```
-
-2. Configure `sessionMode` and allowed domains in your project's
-   `.gemini/settings.json`:
-
-   ```json
-   {
-     "agents": {
-       "overrides": {
-         "browser_agent": { "enabled": true }
-       },
-       "browser": {
-         "sessionMode": "existing",
-         "allowedDomains": ["example.com"]
-       }
-     }
-   }
-   ```
-
-3. Launch the CLI with port forwarding:
-
-   ```bash
-   GEMINI_SANDBOX=docker SANDBOX_PORTS=9222 gemini
-   ```
-
 ## Creating custom subagents

 You can create your own subagents to automate specific workflows or enforce
-specific personas.
+specific personas. To use custom subagents, you must enable them in your
+`settings.json`:
+
+```json
+{
+  "experimental": {
+    "enableAgents": true
+  }
+}
+```

 ### Agent definition files

@@ -332,7 +290,6 @@ it yourself; just report it.
 | `description`  | string | Yes      | Short description of what the agent does. This is visible to the main agent to help it decide when to call this subagent.                                                                                     |
 | `kind`         | string | No       | `local` (default) or `remote`.                                                                                                                                                                                |
 | `tools`        | array  | No       | List of tool names this agent can use. Supports wildcards: `*` (all tools), `mcp_*` (all MCP tools), `mcp_server_*` (all tools from a server). **If omitted, it inherits all tools from the parent session.** |
-| `mcpServers`   | object | No       | Configuration for inline Model Context Protocol (MCP) servers isolated to this specific agent.                                                                                                                |
 | `model`        | string | No       | Specific model to use (e.g., `gemini-3-preview`). Defaults to `inherit` (uses the main session model).                                                                                                        |
 | `temperature`  | number | No       | Model temperature (0.0 - 2.0). Defaults to `1`.                                                                                                                                                               |
 | `max_turns`    | number | No       | Maximum number of conversation turns allowed for this agent before it must return. Defaults to `30`.                                                                                                          |
@@ -360,78 +317,6 @@ Each subagent runs in its own isolated context loop. This means:
  subagents **cannot** call other subagents. If a subagent is granted the `*`
  tool wildcard, it will still be unable to see or invoke other agents.

-## Subagent tool isolation
-
-Subagent tool isolation moves Gemini CLI away from a single global tool
-registry. By providing isolated execution environments, you can ensure that
-subagents only interact with the parts of the system they are designed for. This
-prevents unintended side effects, improves reliability by avoiding state
-contamination, and enables fine-grained permission control.
-
-With this feature, you can:
-
- **Specify tool access:** Define exactly which tools an agent can access using
-  a `tools` list in the agent definition.
- **Define inline MCP servers:** Configure Model Context Protocol (MCP) servers
-  (which provide a standardized way to connect AI models to external tools and
-  data sources) directly in the subagent's markdown frontmatter, isolating them
-  to that specific agent.
- **Maintain state isolation:** Ensure that subagents only interact with their
-  own set of tools and servers, preventing side effects and state contamination.
- **Apply subagent-specific policies:** Enforce granular rules in your
-  [Policy Engine](../reference/policy-engine.md) TOML configuration based on the
-  executing subagent's name.
-
-### Configuring isolated tools and servers
-
-You can configure tool isolation for a subagent by updating its markdown
-frontmatter. This allows you to explicitly state which tools the subagent can
-use, rather than relying on the global registry.
-
-Add an `mcpServers` object to define inline MCP servers that are unique to the
-agent.
-
-**Example:**
-
-```yaml
---
-name: my-isolated-agent
-tools:
-  - grep_search
-  - read_file
-mcpServers:
-  my-custom-server:
-    command: 'node'
-    args: ['path/to/server.js']
---
-```
-
-### Subagent-specific policies
-
-You can enforce fine-grained control over subagents using the
-[Policy Engine's](../reference/policy-engine.md) TOML configuration. This allows
-you to grant or restrict permissions specifically for an agent, without
-affecting the rest of your CLI session.
-
-To restrict a policy rule to a specific subagent, add the `subagent` property to
-the `[[rules]]` block in your `policy.toml` file.
-
-**Example:**
-
-```toml
-[[rules]]
-name = "Allow pr-creator to push code"
-subagent = "pr-creator"
-description = "Permit pr-creator to push branches automatically."
-action = "allow"
-toolName = "run_shell_command"
-commandPrefix = "git push"
-```
-
-In this configuration, the policy rule only triggers if the executing subagent's
-name matches `pr-creator`. Rules without the `subagent` property apply
-universally to all agents.
-
 ## Managing subagents

 You can manage subagents interactively using the `/agents` command or
@@ -521,11 +406,15 @@ If you need to further tune your subagent, you can do so by selecting the model
 to optimize for with `/model` and then asking the model why it does not think
 that your subagent was called with a specific prompt and the given description.

-## Remote subagents (Agent2Agent)
+## Remote subagents (Agent2Agent) (experimental)

 Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent
 (A2A) protocol.

+<!-- prettier-ignore -->
+> [!NOTE]
+> Remote subagents are currently an experimental feature.
+
 See the [Remote Subagents documentation](remote-agents) for detailed
 configuration, authentication, and usage instructions.

@@ -17,6 +17,8 @@ Slash commands provide meta-level control over the CLI itself.
 ### `/agents`

 - **Description:** Manage local and remote subagents.
+- **Note:** This command is experimental and requires
+  `experimental.enableAgents: true` in your `settings.json`.
 - **Sub-commands:**
  - **`list`**:
    - **Description:** Lists all discovered agents, including built-in, local,
@@ -303,7 +305,7 @@ Slash commands provide meta-level control over the CLI itself.
 - **Description:** Switch to Plan Mode (read-only) and view the current plan if
  one has been generated.
  - **Note:** This feature is enabled by default. It can be disabled via the
-    `general.plan.enabled` setting in your configuration.
+    `experimental.plan` setting in your configuration.
 - **Sub-commands:**
  - **`copy`**:
    - **Description:** Copy the currently approved plan to your clipboard.
@@ -141,11 +141,6 @@ their corresponding top-level category object in your `settings.json` file.
  - **Default:** `false`
  - **Requires restart:** Yes

- **`general.plan.enabled`** (boolean):
-  - **Description:** Enable Plan Mode for read-only safety during planning.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 - **`general.plan.directory`** (string):
  - **Description:** The directory where planning artifacts are stored. If not
    specified, defaults to the system temporary directory. A custom directory
@@ -262,11 +257,6 @@ their corresponding top-level category object in your `settings.json` file.
  - **Description:** Show the "? for shortcuts" hint above the input.
  - **Default:** `true`

- **`ui.compactToolOutput`** (boolean):
-  - **Description:** Display tool outputs (like directory listings and file
-    reads) in a compact, structured format.
-  - **Default:** `false`
-
 - **`ui.hideBanner`** (boolean):
  - **Description:** Hide the application banner
  - **Default:** `false`
@@ -354,8 +344,8 @@ their corresponding top-level category object in your `settings.json` file.

 - **`ui.loadingPhrases`** (enum):
  - **Description:** What to show while the model is working: tips, witty
-    comments, all, or off.
-  - **Default:** `"off"`
+    comments, both, or nothing.
+  - **Default:** `"tips"`
  - **Values:** `"tips"`, `"witty"`, `"all"`, `"off"`

 - **`ui.errorVerbosity`** (enum):
@@ -1376,14 +1366,6 @@ their corresponding top-level category object in your `settings.json` file.
  - **Default:** `true`
  - **Requires restart:** Yes

- **`tools.shell.backgroundCompletionBehavior`** (enum):
-  - **Description:** Controls what happens when a background shell command
-    finishes. 'silent' (default): quietly exits in background. 'inject':
-    automatically returns output to agent. 'notify': shows brief message in
-    chat.
-  - **Default:** `"silent"`
-  - **Values:** `"silent"`, `"inject"`, `"notify"`
-
 - **`tools.shell.pager`** (string):
  - **Description:** The pager command to use for shell output. Defaults to
    `cat`.
@@ -1565,7 +1547,7 @@ their corresponding top-level category object in your `settings.json` file.

 - **`advanced.autoConfigureMemory`** (boolean):
  - **Description:** Automatically configure Node.js memory limits
-  - **Default:** `true`
+  - **Default:** `false`
  - **Requires restart:** Yes

 - **`advanced.dnsResolutionOrder`** (string):
@@ -1587,9 +1569,26 @@ their corresponding top-level category object in your `settings.json` file.

 #### `experimental`

- **`experimental.adk.agentSessionNoninteractiveEnabled`** (boolean):
-  - **Description:** Enable non-interactive agent sessions.
-  - **Default:** `false`
+- **`experimental.toolOutputMasking.enabled`** (boolean):
+  - **Description:** Enables tool output masking to save tokens.
+  - **Default:** `true`
+  - **Requires restart:** Yes
+
+- **`experimental.toolOutputMasking.toolProtectionThreshold`** (number):
+  - **Description:** Minimum number of tokens to protect from masking (most
+    recent tool outputs).
+  - **Default:** `50000`
+  - **Requires restart:** Yes
+
+- **`experimental.toolOutputMasking.minPrunableTokensThreshold`** (number):
+  - **Description:** Minimum prunable tokens required to trigger a masking pass.
+  - **Default:** `30000`
+  - **Requires restart:** Yes
+
+- **`experimental.toolOutputMasking.protectLatestTurn`** (boolean):
+  - **Description:** Ensures the absolute latest turn is never masked,
+    regardless of token count.
+  - **Default:** `true`
  - **Requires restart:** Yes

 - **`experimental.enableAgents`** (boolean):
@@ -1630,7 +1629,7 @@ their corresponding top-level category object in your `settings.json` file.

 - **`experimental.jitContext`** (boolean):
  - **Description:** Enable Just-In-Time (JIT) context loading.
-  - **Default:** `false`
+  - **Default:** `true`
  - **Requires restart:** Yes

 - **`experimental.useOSC52Paste`** (boolean):
@@ -1645,6 +1644,11 @@ their corresponding top-level category object in your `settings.json` file.
    configured to allow it).
  - **Default:** `false`

+- **`experimental.plan`** (boolean):
+  - **Description:** Enable Plan Mode.
+  - **Default:** `true`
+  - **Requires restart:** Yes
+
 - **`experimental.taskTracker`** (boolean):
  - **Description:** Enable task tracker tools.
  - **Default:** `false`
@@ -1690,8 +1694,25 @@ their corresponding top-level category object in your `settings.json` file.
  - **Default:** `false`
  - **Requires restart:** Yes

- **`experimental.contextManagement`** (boolean):
-  - **Description:** Enable logic for context management.
+- **`experimental.agentHistoryTruncation`** (boolean):
+  - **Description:** Enable truncation window logic for the Agent History
+    Provider.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
+- **`experimental.agentHistoryTruncationThreshold`** (number):
+  - **Description:** The maximum number of messages before history is truncated.
+  - **Default:** `30`
+  - **Requires restart:** Yes
+
+- **`experimental.agentHistoryRetainedMessages`** (number):
+  - **Description:** The number of recent messages to retain after truncation.
+  - **Default:** `15`
+  - **Requires restart:** Yes
+
+- **`experimental.agentHistorySummarization`** (boolean):
+  - **Description:** Enable summarization of truncated content via a small model
+    for the Agent History Provider.
  - **Default:** `false`
  - **Requires restart:** Yes

@@ -1786,69 +1807,6 @@ their corresponding top-level category object in your `settings.json` file.
    prioritize available tools dynamically.
  - **Default:** `[]`

-#### `contextManagement`
-
- **`contextManagement.historyWindow.maxTokens`** (number):
-  - **Description:** The number of tokens to allow before triggering
-    compression.
-  - **Default:** `150000`
-  - **Requires restart:** Yes
-
- **`contextManagement.historyWindow.retainedTokens`** (number):
-  - **Description:** The number of tokens to always retain.
-  - **Default:** `40000`
-  - **Requires restart:** Yes
-
- **`contextManagement.messageLimits.normalMaxTokens`** (number):
-  - **Description:** The target number of tokens to budget for a normal
-    conversation turn.
-  - **Default:** `2500`
-  - **Requires restart:** Yes
-
- **`contextManagement.messageLimits.retainedMaxTokens`** (number):
-  - **Description:** The maximum number of tokens a single conversation turn can
-    consume before truncation.
-  - **Default:** `12000`
-  - **Requires restart:** Yes
-
- **`contextManagement.messageLimits.normalizationHeadRatio`** (number):
-  - **Description:** The ratio of tokens to retain from the beginning of a
-    truncated message (0.0 to 1.0).
-  - **Default:** `0.25`
-  - **Requires restart:** Yes
-
- **`contextManagement.tools.distillation.maxOutputTokens`** (number):
-  - **Description:** Maximum tokens to show to the model when truncating large
-    tool outputs.
-  - **Default:** `10000`
-  - **Requires restart:** Yes
-
- **`contextManagement.tools.distillation.summarizationThresholdTokens`**
-  (number):
-  - **Description:** Threshold above which truncated tool outputs will be
-    summarized by an LLM.
-  - **Default:** `20000`
-  - **Requires restart:** Yes
-
- **`contextManagement.tools.outputMasking.protectionThresholdTokens`**
-  (number):
-  - **Description:** Minimum number of tokens to protect from masking (most
-    recent tool outputs).
-  - **Default:** `50000`
-  - **Requires restart:** Yes
-
- **`contextManagement.tools.outputMasking.minPrunableThresholdTokens`**
-  (number):
-  - **Description:** Minimum prunable tokens required to trigger a masking pass.
-  - **Default:** `30000`
-  - **Requires restart:** Yes
-
- **`contextManagement.tools.outputMasking.protectLatestTurn`** (boolean):
-  - **Description:** Ensures the absolute latest turn is never masked,
-    regardless of token count.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 #### `admin`

 - **`admin.secureModeEnabled`** (boolean):
@@ -127,13 +127,6 @@ available combinations.
 | `background.unfocusList`    | Move focus from background shell list to Gemini.                   | `Tab`       |
 | `background.unfocusWarning` | Show warning when trying to move focus away from background shell. | `Tab`       |

-#### Extension Controls
-
-| Command            | Action                                      | Keys |
-| ------------------ | ------------------------------------------- | ---- |
-| `extension.update` | Update the current extension if available.  | `I`  |
-| `extension.link`   | Link the current extension to a local path. | `L`  |
-
 <!-- KEYBINDINGS-AUTOGEN:END -->

 ## Customizing Keybindings
@@ -29,12 +29,13 @@ To create your first policy:
    ```toml
    [[rule]]
    toolName = "run_shell_command"
-    commandPrefix = "rm -rf"
-    decision = "deny"
+    commandPrefix = "git status"
+    decision = "allow"
    priority = 100
    ```
 3.  **Run a command** that triggers the policy (e.g., ask Gemini CLI to
-    `rm -rf /`). The tool will now be blocked automatically.
+    `git status`). The tool will now execute automatically without prompting for
+    confirmation.

 ## Core concepts

@@ -142,26 +143,25 @@ engine transforms this into a final priority using the following formula:

 This system guarantees that:

- Admin policies always override User, Workspace, and Default policies (defined
-  in policy TOML files).
+- Admin policies always override User, Workspace, and Default policies.
 - User policies override Workspace and Default policies.
 - Workspace policies override Default policies.
 - You can still order rules within a single tier with fine-grained control.

 For example:

- A `priority: 50` rule in a Default policy TOML becomes `1.050`.
- A `priority: 10` rule in a Workspace policy TOML becomes `2.010`.
- A `priority: 100` rule in a User policy TOML becomes `3.100`.
- A `priority: 20` rule in an Admin policy TOML becomes `4.020`.
+- A `priority: 50` rule in a Default policy file becomes `1.050`.
+- A `priority: 10` rule in a Workspace policy policy file becomes `2.010`.
+- A `priority: 100` rule in a User policy file becomes `3.100`.
+- A `priority: 20` rule in an Admin policy file becomes `4.020`.

 ### Approval modes

 Approval modes allow the policy engine to apply different sets of rules based on
-the CLI's operational mode. A rule in a TOML policy file can be associated with
-one or more modes (e.g., `yolo`, `autoEdit`, `plan`). The rule will only be
-active if the CLI is running in one of its specified modes. If a rule has no
-modes specified, it is always active.
+the CLI's operational mode. A rule can be associated with one or more modes
+(e.g., `yolo`, `autoEdit`, `plan`). The rule will only be active if the CLI is
+running in one of its specified modes. If a rule has no modes specified, it is
+always active.

 - `default`: The standard interactive mode where most write tools require
  confirmation.
@@ -179,8 +179,8 @@ outcome.

 A rule matches a tool call if all of its conditions are met:

-1.  **Tool name**: The `toolName` in the TOML rule must match the name of the
-    tool being called.
+1.  **Tool name**: The `toolName` in the rule must match the name of the tool
+    being called.
    - **Wildcards**: You can use wildcards like `*`, `mcp_server_*`, or
      `mcp_*_toolName` to match multiple tools. See [Tool Name](#tool-name) for
      details.
@@ -264,7 +264,7 @@ toolName = "run_shell_command"

 # (Optional) The name of a subagent. If provided, the rule only applies to tool
 # calls made by this specific subagent.
-subagent = "codebase_investigator"
+subagent = "generalist"

 # (Optional) The name of an MCP server. Can be combined with toolName
 # to form a composite FQN internally like "mcp_mcpName_toolName".
@@ -419,6 +419,20 @@ decision = "ask_user"
 priority = 10
 ```

+**4. Targeting a tool name across all servers**
+
+Use `mcpName = "*"` with a specific `toolName` to target that operation
+regardless of which server provides it.
+
+```toml
+# Allow the `search` tool across all connected MCP servers
+[[rule]]
+mcpName = "*"
+toolName = "search"
+decision = "allow"
+priority = 50
+```
+
 ## Default policies

 The Gemini CLI ships with a set of default policies to provide a safe
@@ -115,10 +115,10 @@ each tool.

 ### Web

-| Tool                                          | Kind     | Description                                                                                                                                                                                                                                                              |
-| :-------------------------------------------- | :------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [`google_web_search`](../tools/web-search.md) | `Search` | Performs a Google Search to find up-to-date information.                                                                                                                                                                                                                 |
-| [`web_fetch`](../tools/web-fetch.md)          | `Fetch`  | Retrieves and processes content from specific URLs. **Warning:** This tool can access local and private network addresses (e.g., localhost), which may pose a security risk if used with untrusted prompts. In Plan Mode, this tool requires explicit user confirmation. |
+| Tool                                          | Kind     | Description                                                                                                                                                                                                 |
+| :-------------------------------------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [`google_web_search`](../tools/web-search.md) | `Search` | Performs a Google Search to find up-to-date information.                                                                                                                                                    |
+| [`web_fetch`](../tools/web-fetch.md)          | `Fetch`  | Retrieves and processes content from specific URLs. **Warning:** This tool can access local and private network addresses (e.g., localhost), which may pose a security risk if used with untrusted prompts. |

 ## Under the hood

@@ -138,10 +138,12 @@
          { "label": "Plan mode", "slug": "docs/cli/plan-mode" },
          {
            "label": "Subagents",
+            "badge": "🔬",
            "slug": "docs/core/subagents"
          },
          {
            "label": "Remote subagents",
+            "badge": "🔬",
            "slug": "docs/core/remote-agents"
          },
          { "label": "Rewind", "slug": "docs/cli/rewind" },
@@ -32,9 +32,7 @@ and planning.
 ## 2. `exit_plan_mode` (ExitPlanMode)

 `exit_plan_mode` signals that the planning phase is complete. It presents the
-finalized plan to the user and requests formal approval to start the
-implementation. The agent MUST reach an informal agreement with the user in the
-chat regarding the proposed strategy BEFORE calling this tool.
+finalized plan to the user and requests approval to start the implementation.

 - **Tool name:** `exit_plan_mode`
 - **Display name:** Exit Plan Mode
@@ -46,7 +44,7 @@ chat regarding the proposed strategy BEFORE calling this tool.
 - **Behavior:**
  - Validates that the `plan_path` is within the allowed directory and that the
    file exists and has content.
-  - Presents the plan to the user for formal review.
+  - Presents the plan to the user for review.
  - If the user approves the plan:
    - Switches the CLI's approval mode to the user's chosen approval mode (
      `DEFAULT` or `AUTO_EDIT`).
@@ -58,5 +56,5 @@ chat regarding the proposed strategy BEFORE calling this tool.
  - On approval: A message indicating the plan was approved and the new approval
    mode.
  - On rejection: A message containing the user's feedback.
- **Confirmation:** Yes. Shows the finalized plan and asks for user formal
-  approval to proceed with implementation.
+- **Confirmation:** Yes. Shows the finalized plan and asks for user approval to
+  proceed with implementation.
@@ -17,9 +17,6 @@ specific operations like summarization or extraction.
 ## Technical behavior

 - **Confirmation:** Triggers a confirmation dialog showing the converted URLs.
- **Plan Mode:** In [Plan Mode](../cli/plan-mode.md), `web_fetch` is available
-  but always requires explicit user confirmation (`ask_user`) due to security
-  implications of accessing external or private network addresses.
 - **Processing:** Uses the Gemini API's `urlContext` for retrieval.
 - **Fallback:** If API access fails, the tool attempts to fetch raw content
  directly from your local machine.
@@ -13,7 +13,7 @@ import { wasmLoader } from 'esbuild-plugin-wasm';
 let esbuild;
 try {
  esbuild = (await import('esbuild')).default;
-} catch {
+} catch (_error) {
  console.error('esbuild not available - cannot build bundle');
  process.exit(1);
 }
@@ -41,11 +41,6 @@ const commonRestrictedSyntaxRules = [
    message:
      'Do not use typeof to check object properties. Define a TypeScript interface and a type guard function instead.',
  },
-  {
-    selector: 'CatchClause > Identifier[name=/^_/]',
-    message:
-      'Do not use underscored identifiers in catch blocks. If the error is unused, use "catch {}". If it is used, remove the underscore.',
-  },
 ];

 export default tseslint.config(
@@ -134,7 +129,7 @@ export default tseslint.config(
        {
          argsIgnorePattern: '^_',
          varsIgnorePattern: '^_',
-          caughtErrors: 'all',
+          caughtErrorsIgnorePattern: '^_',
        },
      ],
      // Prevent async errors from bypassing catch handlers
@@ -341,7 +336,7 @@ export default tseslint.config(
        {
          argsIgnorePattern: '^_',
          varsIgnorePattern: '^_',
-          caughtErrors: 'all',
+          caughtErrorsIgnorePattern: '^_',
        },
      ],
    },
@@ -365,7 +360,7 @@ export default tseslint.config(
        {
          argsIgnorePattern: '^_',
          varsIgnorePattern: '^_',
-          caughtErrors: 'all',
+          caughtErrorsIgnorePattern: '^_',
        },
      ],
    },
@@ -427,7 +422,7 @@ export default tseslint.config(
        {
          argsIgnorePattern: '^_',
          varsIgnorePattern: '^_',
-          caughtErrors: 'all',
+          caughtErrorsIgnorePattern: '^_',
        },
      ],
    },
@@ -212,56 +212,6 @@ The nightly workflow executes the full evaluation suite multiple times
 (currently 3 attempts) to account for non-determinism. These results are
 aggregated into a **Nightly Summary** attached to the workflow run.

-## Regression Check Scripts
-
-The project includes several scripts to automate high-signal regression checking
-in Pull Requests. These can also be run locally for debugging.
-
- **`scripts/get_trustworthy_evals.js`**: Analyzes nightly history to identify
-  stable tests (80%+ aggregate pass rate).
- **`scripts/run_regression_check.js`**: Runs a specific set of tests using the
-  "Best-of-4" logic and "Dynamic Baseline Verification".
- **`scripts/run_eval_regression.js`**: The main orchestrator that loops through
-  models and generates the final PR report.
-
-### Running Regression Checks Locally
-
-You can simulate the PR regression check locally to verify your changes before
-pushing:
-
-```bash
-# Run the full regression loop for a specific model
-MODEL_LIST=gemini-3-flash-preview node scripts/run_eval_regression.js
-```
-
-To debug a specific failing test with the same logic used in CI:
-
-```bash
-# 1. Get the Vitest pattern for trustworthy tests
-OUTPUT=$(node scripts/get_trustworthy_evals.js "gemini-3-flash-preview")
-
-# 2. Run the regression logic for those tests
-node scripts/run_regression_check.js "gemini-3-flash-preview" "$OUTPUT"
-```
-
-### The Regression Quality Bar
-
-Because LLMs are non-deterministic, the PR regression check uses a high-signal
-probabilistic approach rather than a 100% pass requirement:
-
-1.  **Trustworthiness (60/80 Filter):** Only tests with a proven track record
-    are run. A test must score at least **60% (2/3)** every single night and
-    maintain an **80% aggregate** pass rate over the last 6 days.
-2.  **The 50% Pass Rule:** In a PR, a test is considered a **Pass** if the model
-    correctly performs the behavior at least half the time (**2 successes** out
-    of up to 4 attempts).
-3.  **Dynamic Baseline Verification:** If a test fails in a PR (e.g., 0/3), the
-    system automatically checks the `main` branch. If it fails there too, it is
-    marked as **Pre-existing** and cleared for the PR, ensuring you are only
-    blocked by regressions caused by your specific changes.
-
-## Fixing Evaluations
-
 #### How to interpret the report:

 - **Pass Rate (%)**: Each cell represents the percentage of successful runs for
@@ -15,9 +15,7 @@ import {
 describe('plan_mode', () => {
  const TEST_PREFIX = 'Plan Mode: ';
  const settings = {
-    general: {
-      plan: { enabled: true },
-    },
+    experimental: { plan: true },
  };

  const getWriteTargets = (logs: any[]) =>
@@ -174,8 +172,7 @@ describe('plan_mode', () => {
    params: {
      settings,
    },
-    prompt:
-      'I agree with the strategy to use a JWT-based login. Create a plan for a new login feature.',
+    prompt: 'Create a plan for a new login feature.',
    assert: async (rig, result) => {
      await rig.waitForTelemetryReady();
      const toolLogs = rig.readToolLogs();
@@ -212,7 +209,7 @@ describe('plan_mode', () => {
        'import { sum } from "./mathUtils";\nconsole.log(sum(1, 2));',
    },
    prompt:
-      'I want to refactor our math utilities. I agree with the strategy to move the `sum` function from `src/mathUtils.ts` to a new file `src/basicMath.ts` and update `src/main.ts`. Please create a detailed implementation plan first, then execute it.',
+      'I want to refactor our math utilities. Move the `sum` function from `src/mathUtils.ts` to a new file `src/basicMath.ts` and update `src/main.ts` to use the new file. Please create a detailed implementation plan first, then execute it.',
    assert: async (rig, result) => {
      const enterPlanCalled = await rig.waitForToolCall('enter_plan_mode');
      expect(
@@ -284,80 +281,4 @@ describe('plan_mode', () => {
      assertModelHasOutput(result);
    },
  });
-
-  evalTest('ALWAYS_PASSES', {
-    name: 'should transition from plan mode to normal execution and create a plan file from scratch',
-    params: {
-      settings,
-    },
-    prompt:
-      'Enter plan mode and plan to create a new module called foo. The plan should be saved as foo-plan.md. Then, exit plan mode.',
-    assert: async (rig, result) => {
-      const enterPlanCalled = await rig.waitForToolCall('enter_plan_mode');
-      expect(
-        enterPlanCalled,
-        'Expected enter_plan_mode tool to be called',
-      ).toBe(true);
-
-      const exitPlanCalled = await rig.waitForToolCall('exit_plan_mode');
-      expect(exitPlanCalled, 'Expected exit_plan_mode tool to be called').toBe(
-        true,
-      );
-
-      await rig.waitForTelemetryReady();
-      const toolLogs = rig.readToolLogs();
-
-      // Check if the plan file was written successfully
-      const planWrite = toolLogs.find(
-        (log) =>
-          log.toolRequest.name === 'write_file' &&
-          log.toolRequest.args.includes('foo-plan.md'),
-      );
-
-      expect(
-        planWrite,
-        'Expected write_file to be called for foo-plan.md',
-      ).toBeDefined();
-
-      expect(
-        planWrite?.toolRequest.success,
-        `Expected write_file to succeed, but got error: ${planWrite?.toolRequest.error}`,
-      ).toBe(true);
-
-      assertModelHasOutput(result);
-    },
-  });
-
-  evalTest('USUALLY_PASSES', {
-    name: 'should not exit plan mode or draft before informal agreement',
-    approvalMode: ApprovalMode.PLAN,
-    params: {
-      settings,
-    },
-    prompt: 'I need to build a new login feature. Please plan it.',
-    assert: async (rig, result) => {
-      await rig.waitForTelemetryReady();
-      const toolLogs = rig.readToolLogs();
-
-      const exitPlanCall = toolLogs.find(
-        (log) => log.toolRequest.name === 'exit_plan_mode',
-      );
-      expect(
-        exitPlanCall,
-        'Should NOT call exit_plan_mode before informal agreement',
-      ).toBeUndefined();
-
-      const planWrite = toolLogs.find(
-        (log) =>
-          log.toolRequest.name === 'write_file' &&
-          log.toolRequest.args.includes('/plans/'),
-      );
-      expect(
-        planWrite,
-        'Should NOT draft the plan file before informal agreement',
-      ).toBeUndefined();
-
-      assertModelHasOutput(result);
-    },
-  });
 });
@@ -13,21 +13,8 @@ import { evalTest, TEST_AGENTS } from './test-helper.js';

 const INDEX_TS = 'export const add = (a: number, b: number) => a + b;\n';

-// A minimal package.json is used to provide a realistic workspace anchor.
-// This prevents the agent from making incorrect assumptions about the environment
-// and helps it properly navigate or act as if it is in a standard Node.js project.
-const MOCK_PACKAGE_JSON = JSON.stringify(
-  {
-    name: 'subagent-eval-project',
-    version: '1.0.0',
-    type: 'module',
-  },
-  null,
-  2,
-);
-
 function readProjectFile(
-  rig: { testDir: string | null },
+  rig: { testDir?: string },
  relativePath: string,
 ): string {
  return fs.readFileSync(path.join(rig.testDir!, relativePath), 'utf8');
@@ -130,7 +117,15 @@ describe('subagent eval test cases', () => {
    files: {
      ...TEST_AGENTS.TESTING_AGENT.asFile(),
      'index.ts': INDEX_TS,
-      'package.json': MOCK_PACKAGE_JSON,
+      'package.json': JSON.stringify(
+        {
+          name: 'subagent-eval-project',
+          version: '1.0.0',
+          type: 'module',
+        },
+        null,
+        2,
+      ),
    },
    assert: async (rig, _result) => {
      const toolLogs = rig.readToolLogs() as Array<{
@@ -169,7 +164,15 @@ describe('subagent eval test cases', () => {
      ...TEST_AGENTS.TESTING_AGENT.asFile(),
      'index.ts': INDEX_TS,
      'README.md': 'TODO: update the README.\n',
-      'package.json': MOCK_PACKAGE_JSON,
+      'package.json': JSON.stringify(
+        {
+          name: 'subagent-eval-project',
+          version: '1.0.0',
+          type: 'module',
+        },
+        null,
+        2,
+      ),
    },
    assert: async (rig, _result) => {
      const toolLogs = rig.readToolLogs() as Array<{
@@ -187,105 +190,4 @@ describe('subagent eval test cases', () => {
      );
    },
  });
-
-  /**
-   * Checks that the main agent can correctly select the appropriate subagent
-   * from a large pool of available subagents (10 total).
-   */
-  evalTest('USUALLY_PASSES', {
-    name: 'should select the correct subagent from a pool of 10 different agents',
-    prompt: 'Please add a new SQL table migration for a user profile.',
-    files: {
-      ...TEST_AGENTS.DOCS_AGENT.asFile(),
-      ...TEST_AGENTS.TESTING_AGENT.asFile(),
-      ...TEST_AGENTS.DATABASE_AGENT.asFile(),
-      ...TEST_AGENTS.CSS_AGENT.asFile(),
-      ...TEST_AGENTS.I18N_AGENT.asFile(),
-      ...TEST_AGENTS.SECURITY_AGENT.asFile(),
-      ...TEST_AGENTS.DEVOPS_AGENT.asFile(),
-      ...TEST_AGENTS.ANALYTICS_AGENT.asFile(),
-      ...TEST_AGENTS.ACCESSIBILITY_AGENT.asFile(),
-      ...TEST_AGENTS.MOBILE_AGENT.asFile(),
-      'package.json': MOCK_PACKAGE_JSON,
-    },
-    assert: async (rig, _result) => {
-      const toolLogs = rig.readToolLogs() as Array<{
-        toolRequest: { name: string };
-      }>;
-      await rig.expectToolCallSuccess(['database-agent']);
-
-      // Ensure the generalist and other irrelevant specialists were not invoked
-      const uncalledAgents = [
-        'generalist',
-        TEST_AGENTS.DOCS_AGENT.name,
-        TEST_AGENTS.TESTING_AGENT.name,
-        TEST_AGENTS.CSS_AGENT.name,
-        TEST_AGENTS.I18N_AGENT.name,
-        TEST_AGENTS.SECURITY_AGENT.name,
-        TEST_AGENTS.DEVOPS_AGENT.name,
-        TEST_AGENTS.ANALYTICS_AGENT.name,
-        TEST_AGENTS.ACCESSIBILITY_AGENT.name,
-        TEST_AGENTS.MOBILE_AGENT.name,
-      ];
-
-      for (const agentName of uncalledAgents) {
-        expect(toolLogs.some((l) => l.toolRequest.name === agentName)).toBe(
-          false,
-        );
-      }
-    },
-  });
-
-  /**
-   * Checks that the main agent can correctly select the appropriate subagent
-   * from a large pool of available subagents, even when many irrelevant MCP tools are present.
-   *
-   * This test includes stress tests the subagent delegation with ~80 tools.
-   */
-  evalTest('USUALLY_PASSES', {
-    name: 'should select the correct subagent from a pool of 10 different agents with MCP tools present',
-    prompt: 'Please add a new SQL table migration for a user profile.',
-    setup: async (rig) => {
-      rig.addTestMcpServer('workspace-server', 'google-workspace');
-    },
-    files: {
-      ...TEST_AGENTS.DOCS_AGENT.asFile(),
-      ...TEST_AGENTS.TESTING_AGENT.asFile(),
-      ...TEST_AGENTS.DATABASE_AGENT.asFile(),
-      ...TEST_AGENTS.CSS_AGENT.asFile(),
-      ...TEST_AGENTS.I18N_AGENT.asFile(),
-      ...TEST_AGENTS.SECURITY_AGENT.asFile(),
-      ...TEST_AGENTS.DEVOPS_AGENT.asFile(),
-      ...TEST_AGENTS.ANALYTICS_AGENT.asFile(),
-      ...TEST_AGENTS.ACCESSIBILITY_AGENT.asFile(),
-      ...TEST_AGENTS.MOBILE_AGENT.asFile(),
-      'package.json': MOCK_PACKAGE_JSON,
-    },
-    assert: async (rig, _result) => {
-      const toolLogs = rig.readToolLogs() as Array<{
-        toolRequest: { name: string };
-      }>;
-      await rig.expectToolCallSuccess(['database-agent']);
-
-      // Ensure the generalist and other irrelevant specialists were not invoked
-      const uncalledAgents = [
-        'generalist',
-        TEST_AGENTS.DOCS_AGENT.name,
-        TEST_AGENTS.TESTING_AGENT.name,
-        TEST_AGENTS.CSS_AGENT.name,
-        TEST_AGENTS.I18N_AGENT.name,
-        TEST_AGENTS.SECURITY_AGENT.name,
-        TEST_AGENTS.DEVOPS_AGENT.name,
-        TEST_AGENTS.ANALYTICS_AGENT.name,
-        TEST_AGENTS.ACCESSIBILITY_AGENT.name,
-        TEST_AGENTS.MOBILE_AGENT.name,
-      ];
-
-      for (const agentName of uncalledAgents) {
-        expect(toolLogs.some((l) => l.toolRequest.name === agentName)).toBe(
-          false,
-        );
-      }
-    },
-  });
 });
@@ -61,10 +61,6 @@ export async function internalEvalTest(evalCase: EvalCase) {
    try {
      rig.setup(evalCase.name, evalCase.params);

-      if (evalCase.setup) {
-        await evalCase.setup(rig);
-      }
-
      if (evalCase.files) {
        await setupTestFiles(rig, evalCase.files);
      }
@@ -375,7 +371,6 @@ export interface EvalCase {
  prompt: string;
  timeout?: number;
  files?: Record<string, string>;
-  setup?: (rig: TestRig) => Promise<void> | void;
  /** Conversation history to pre-load via --resume. Each entry is a message object with type, content, etc. */
  messages?: Record<string, unknown>[];
  /** Session ID for the resumed session. Auto-generated if not provided. */
@@ -113,21 +113,4 @@ describe('tracker_mode', () => {
      assertModelHasOutput(result);
    },
  });
-
-  evalTest('USUALLY_PASSES', {
-    name: 'should correctly identify the task tracker storage location from the system prompt',
-    params: {
-      settings: { experimental: { taskTracker: true } },
-    },
-    prompt:
-      'Where is my task tracker storage located? Please provide the absolute path in your response.',
-    assert: async (rig, result) => {
-      // The rig sets GEMINI_CLI_HOME to rig.homeDir
-      const homeDir = rig.homeDir!;
-      // The response should contain the dynamic path which includes the home directory
-      // and follows the .gemini/tmp/.../tracker structure.
-      expect(result).toContain(homeDir);
-      expect(result).toMatch(/\.gemini\/tmp\/.*\/tracker/);
-    },
-  });
 });
@@ -1,116 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { describe, expect } from 'vitest';
-import { evalTest } from './test-helper.js';
-
-describe('update_topic_behavior', () => {
-  // Constants for tool names and params for robustness
-  const UPDATE_TOPIC_TOOL_NAME = 'update_topic';
-
-  /**
-   * Verifies the desired behavior of the update_topic tool. update_topic is used by the
-   * agent to share periodic, concise updates about what the agent is working on, independent
-   * of the regular model output and/or thoughts. This tool is expected to be called at least
-   * at the start and end of the session, and typically at least once in the middle, but no
-   * more than 1/4 turns.
-   */
-  evalTest('USUALLY_PASSES', {
-    name: 'update_topic should be used at start, end and middle for complex tasks',
-    prompt: `Create a simple users REST API using Express. 
-1. Initialize a new npm project and install express.
-2. Create src/app.ts as the main entry point.
-3. Create src/routes/userRoutes.ts for user routes.
-4. Create src/controllers/userController.ts for user logic.
-5. Implement GET /users, POST /users, and GET /users/:id using an in-memory array.
-6. Add a 'start' script to package.json.
-7. Finally, run a quick grep to verify the routes are in src/app.ts.`,
-    files: {
-      'package.json': JSON.stringify(
-        {
-          name: 'users-api',
-          version: '1.0.0',
-          private: true,
-        },
-        null,
-        2,
-      ),
-      '.gemini/settings.json': JSON.stringify({
-        experimental: {
-          topicUpdateNarration: true,
-        },
-      }),
-    },
-    assert: async (rig, result) => {
-      const toolLogs = rig.readToolLogs();
-      const topicCalls = toolLogs.filter(
-        (l) => l.toolRequest.name === UPDATE_TOPIC_TOOL_NAME,
-      );
-
-      // 1. Assert that update_topic is called at least 3 times (start, middle, end)
-      expect(
-        topicCalls.length,
-        `Expected at least 3 update_topic calls, but found ${topicCalls.length}`,
-      ).toBeGreaterThanOrEqual(3);
-
-      // 2. Assert update_topic is called at the very beginning (first tool call)
-      expect(
-        toolLogs[0].toolRequest.name,
-        'First tool call should be update_topic',
-      ).toBe(UPDATE_TOPIC_TOOL_NAME);
-
-      // 3. Assert update_topic is called near the end
-      const lastTopicCallIndex = toolLogs
-        .map((l) => l.toolRequest.name)
-        .lastIndexOf(UPDATE_TOPIC_TOOL_NAME);
-      expect(
-        lastTopicCallIndex,
-        'Expected update_topic to be used near the end of the task',
-      ).toBeGreaterThanOrEqual(toolLogs.length * 0.7);
-
-      // 4. Assert there is at least one update_topic call in the middle (between start and end phases)
-      const middleTopicCalls = topicCalls.slice(1, -1);
-
-      expect(
-        middleTopicCalls.length,
-        'Expected at least one update_topic call in the middle of the task',
-      ).toBeGreaterThanOrEqual(1);
-
-      // 5. Turn Ratio Assertion: update_topic should be <= 1/2 of total turns.
-      // We only enforce this for tasks that take more than 5 turns, as shorter tasks
-      // naturally have a higher ratio when following the "start, middle, end" rule.
-      const uniquePromptIds = new Set(
-        toolLogs
-          .map((l) => l.toolRequest.prompt_id)
-          .filter((id) => id !== undefined),
-      );
-      const totalTurns = uniquePromptIds.size;
-
-      if (totalTurns > 5) {
-        const topicTurns = new Set(
-          topicCalls
-            .map((l) => l.toolRequest.prompt_id)
-            .filter((id) => id !== undefined),
-        );
-        const topicTurnCount = topicTurns.size;
-
-        const ratio = topicTurnCount / totalTurns;
-
-        expect(
-          ratio,
-          `update_topic was used in ${topicTurnCount} out of ${totalTurns} turns (${(ratio * 100).toFixed(1)}%). Expected <= 50%.`,
-        ).toBeLessThanOrEqual(0.5);
-
-        // Ideal ratio is closer to 1/5 (20%). We log high usage as a warning.
-        if (ratio > 0.25) {
-          console.warn(
-            `[Efficiency Warning] update_topic usage is high: ${(ratio * 100).toFixed(1)}% (Goal: ~20%)`,
-          );
-        }
-      }
-    },
-  });
-});
@@ -1 +1 @@
-{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Part 1. "}],"role":"model"},"index":0}]},{"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":10,"totalTokenCount":110}},{"candidates":[{"content":{"parts":[{"text":"Part 2."}],"role":"model"},"index":0,"finishReason":"STOP"}]}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Part 1. "}],"role":"model"},"index":0}]},{"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":10,"totalTokenCount":110}},{"candidates":[{"content":{"parts":[{"text":"Part 2."}],"role":"model"},"index":0}],"finishReason":"STOP"}]}
@@ -10,13 +10,8 @@ import { dirname, join } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { execSync } from 'node:child_process';
 import { existsSync, writeFileSync, readFileSync, mkdirSync } from 'node:fs';
-import { env } from 'node:process';
 import stripAnsi from 'strip-ansi';

-// Browser agent Chrome DevTools MCP connection is flaky in Docker sandbox.
-// See: https://github.com/google-gemini/gemini-cli/issues/24382
-const isDockerSandbox = env['GEMINI_SANDBOX'] === 'docker';
-
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = dirname(__filename);

@@ -64,146 +59,122 @@ describe.skipIf(!chromeAvailable)('browser-policy', () => {
    await rig.cleanup();
  });

-  it.skipIf(isDockerSandbox)(
-    'should skip confirmation when "Allow all server tools for this session" is chosen',
-    async () => {
-      rig.setup('browser-policy-skip-confirmation', {
-        fakeResponsesPath: join(__dirname, 'browser-policy.responses'),
-        settings: {
-          agents: {
-            overrides: {
-              browser_agent: {
-                enabled: true,
-              },
-            },
-            browser: {
-              headless: true,
-              sessionMode: 'isolated',
-              allowedDomains: ['example.com'],
+  it('should skip confirmation when "Allow all server tools for this session" is chosen', async () => {
+    rig.setup('browser-policy-skip-confirmation', {
+      fakeResponsesPath: join(__dirname, 'browser-policy.responses'),
+      settings: {
+        agents: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
            },
          },
+          browser: {
+            headless: true,
+            sessionMode: 'isolated',
+            allowedDomains: ['example.com'],
+          },
        },
-      });
+      },
+    });

-      // Manually trust the folder to avoid the dialog and enable option 3
-      const geminiDir = join(rig.homeDir!, '.gemini');
-      mkdirSync(geminiDir, { recursive: true });
+    // Manually trust the folder to avoid the dialog and enable option 3
+    const geminiDir = join(rig.homeDir!, '.gemini');
+    mkdirSync(geminiDir, { recursive: true });

-      // Write to trustedFolders.json
-      const trustedFoldersPath = join(geminiDir, 'trustedFolders.json');
-      const trustedFolders = {
-        [rig.testDir!]: 'TRUST_FOLDER',
-      };
-      writeFileSync(
-        trustedFoldersPath,
-        JSON.stringify(trustedFolders, null, 2),
-      );
+    // Write to trustedFolders.json
+    const trustedFoldersPath = join(geminiDir, 'trustedFolders.json');
+    const trustedFolders = {
+      [rig.testDir!]: 'TRUST_FOLDER',
+    };
+    writeFileSync(trustedFoldersPath, JSON.stringify(trustedFolders, null, 2));

-      // Force confirmation for browser agent.
-      // NOTE: We don't force confirm browser tools here because "Allow all server tools"
-      // adds a rule with ALWAYS_ALLOW_PRIORITY (3.9x) which would be overshadowed by
-      // a rule in the user tier (4.x) like the one from this TOML.
-      // By removing the explicit mcp rule, the first MCP tool will still prompt
-      // due to default approvalMode = 'default', and then "Allow all" will correctly
-      // bypass subsequent tools.
-      const policyFile = join(rig.testDir!, 'force-confirm.toml');
-      writeFileSync(
-        policyFile,
-        `
+    // Force confirmation for browser agent.
+    // NOTE: We don't force confirm browser tools here because "Allow all server tools"
+    // adds a rule with ALWAYS_ALLOW_PRIORITY (3.9x) which would be overshadowed by
+    // a rule in the user tier (4.x) like the one from this TOML.
+    // By removing the explicit mcp rule, the first MCP tool will still prompt
+    // due to default approvalMode = 'default', and then "Allow all" will correctly
+    // bypass subsequent tools.
+    const policyFile = join(rig.testDir!, 'force-confirm.toml');
+    writeFileSync(
+      policyFile,
+      `
 [[rule]]
 name = "Force confirm browser_agent"
 toolName = "browser_agent"
 decision = "ask_user"
 priority = 200
 `,
-      );
+    );

-      // Update settings.json in both project and home directories to point to the policy file
-      for (const baseDir of [rig.testDir!, rig.homeDir!]) {
-        const settingsPath = join(baseDir, '.gemini', 'settings.json');
-        if (existsSync(settingsPath)) {
-          const settings = JSON.parse(readFileSync(settingsPath, 'utf-8'));
-          settings.policyPaths = [policyFile];
-          // Ensure folder trust is enabled
-          settings.security = settings.security || {};
-          settings.security.folderTrust = settings.security.folderTrust || {};
-          settings.security.folderTrust.enabled = true;
-          writeFileSync(settingsPath, JSON.stringify(settings, null, 2));
-        }
+    // Update settings.json in both project and home directories to point to the policy file
+    for (const baseDir of [rig.testDir!, rig.homeDir!]) {
+      const settingsPath = join(baseDir, '.gemini', 'settings.json');
+      if (existsSync(settingsPath)) {
+        const settings = JSON.parse(readFileSync(settingsPath, 'utf-8'));
+        settings.policyPaths = [policyFile];
+        // Ensure folder trust is enabled
+        settings.security = settings.security || {};
+        settings.security.folderTrust = settings.security.folderTrust || {};
+        settings.security.folderTrust.enabled = true;
+        writeFileSync(settingsPath, JSON.stringify(settings, null, 2));
      }
+    }

-      const run = await rig.runInteractive({
-        approvalMode: 'default',
-        env: {
-          GEMINI_CLI_INTEGRATION_TEST: 'true',
-        },
-      });
+    const run = await rig.runInteractive({
+      approvalMode: 'default',
+      env: {
+        GEMINI_CLI_INTEGRATION_TEST: 'true',
+      },
+    });

-      await run.sendKeys(
-        'Open https://example.com and check if there is a heading\r',
-      );
-      await run.sendKeys('\r');
+    await run.sendKeys(
+      'Open https://example.com and check if there is a heading\r',
+    );
+    await run.sendKeys('\r');

-      // Handle confirmations.
-      // 1. Initial browser_agent delegation (likely only 3 options, so use option 1: Allow once)
-      await poll(
-        () => stripAnsi(run.output).toLowerCase().includes('action required'),
-        60000,
-        1000,
-      );
-      await run.sendKeys('1\r');
-      await new Promise((r) => setTimeout(r, 2000));
+    // Handle confirmations.
+    // 1. Initial browser_agent delegation (likely only 3 options, so use option 1: Allow once)
+    await poll(
+      () => stripAnsi(run.output).toLowerCase().includes('action required'),
+      60000,
+      1000,
+    );
+    await run.sendKeys('1\r');
+    await new Promise((r) => setTimeout(r, 2000));

-      // Handle privacy notice
-      await poll(
-        () => stripAnsi(run.output).toLowerCase().includes('privacy notice'),
-        5000,
-        100,
-      );
-      await run.sendKeys('1\r');
-      await new Promise((r) => setTimeout(r, 5000));
+    // Handle privacy notice
+    await poll(
+      () => stripAnsi(run.output).toLowerCase().includes('privacy notice'),
+      5000,
+      100,
+    );
+    await run.sendKeys('1\r');
+    await new Promise((r) => setTimeout(r, 5000));

-      // new_page (MCP tool, should have 4 options, use option 3: Allow all server tools)
-      await poll(
-        () => {
-          const stripped = stripAnsi(run.output).toLowerCase();
-          return (
-            stripped.includes('new_page') &&
-            stripped.includes('allow all server tools for this session')
-          );
-        },
-        60000,
-        1000,
-      );
+    // new_page (MCP tool, should have 4 options, use option 3: Allow all server tools)
+    await poll(
+      () => {
+        const stripped = stripAnsi(run.output).toLowerCase();
+        return (
+          stripped.includes('new_page') &&
+          stripped.includes('allow all server tools for this session')
+        );
+      },
+      60000,
+      1000,
+    );

-      // Select "Allow all server tools for this session" (option 3)
-      await run.sendKeys('3\r');
+    // Select "Allow all server tools for this session" (option 3)
+    await run.sendKeys('3\r');
+    await new Promise((r) => setTimeout(r, 30000));

-      // Wait for the browser agent to finish (success or failure)
-      await poll(
-        () => {
-          const stripped = stripAnsi(run.output).toLowerCase();
-          return (
-            stripped.includes('completed successfully') ||
-            stripped.includes('agent error')
-          );
-        },
-        120000,
-        1000,
-      );
+    const output = stripAnsi(run.output).toLowerCase();

-      const output = stripAnsi(run.output).toLowerCase();
-
-      expect(output).toContain('browser_agent');
-      // The test validates that "Allow all server tools" skips subsequent
-      // tool confirmations — the browser agent may still fail due to
-      // Chrome/MCP issues in CI, which is acceptable for this policy test.
-      expect(
-        output.includes('completed successfully') ||
-          output.includes('agent error'),
-      ).toBe(true);
-    },
-  );
+    expect(output).toContain('browser_agent');
+    expect(output).toContain('completed successfully');
+  });

  it('should show the visible warning when browser agent starts in existing session mode', async () => {
    rig.setup('browser-session-warning', {
@@ -121,7 +121,6 @@ describe('file-system', () => {

    const result = await rig.run({
      args: `write "hello" to "${fileName}" and then stop. Do not perform any other actions.`,
-      timeout: 600000, // 10 min — real LLM can be slow in Docker sandbox
    });

    const foundToolCall = await rig.waitForToolCall('write_file');
@@ -23,9 +23,7 @@ describe('Plan Mode', () => {
      'should allow read-only tools but deny write tools in plan mode',
      {
        settings: {
-          general: {
-            plan: { enabled: true },
-          },
+          experimental: { plan: true },
          tools: {
            core: [
              'run_shell_command',
@@ -69,12 +67,15 @@ describe('Plan Mode', () => {

    await rig.setup(testName, {
      settings: {
+        experimental: { plan: true },
        tools: {
          core: ['write_file', 'read_file', 'list_directory'],
        },
        general: {
-          plan: { enabled: true, directory: plansDir },
          defaultApprovalMode: 'plan',
+          plan: {
+            directory: plansDir,
+          },
        },
      },
    });
@@ -119,19 +120,22 @@ describe('Plan Mode', () => {

    await rig.setup(testName, {
      settings: {
+        experimental: { plan: true },
        tools: {
          core: ['write_file', 'read_file', 'list_directory'],
        },
        general: {
-          plan: { enabled: true, directory: plansDir },
          defaultApprovalMode: 'plan',
+          plan: {
+            directory: plansDir,
+          },
        },
      },
    });

    await rig.run({
      approvalMode: 'plan',
-      args: 'Attempt to create a file named "hello.txt" in the current directory. Do not create a plan file, try to write hello.txt directly.',
+      args: 'Create a file called hello.txt in the current directory.',
    });

    const toolLogs = rig.readToolLogs();
@@ -152,9 +156,7 @@ describe('Plan Mode', () => {
  it('should be able to enter plan mode from default mode', async () => {
    await rig.setup('should be able to enter plan mode from default mode', {
      settings: {
-        general: {
-          plan: { enabled: true },
-        },
+        experimental: { plan: true },
        tools: {
          core: ['enter_plan_mode'],
          allowed: ['enter_plan_mode'],
@@ -182,12 +184,15 @@ describe('Plan Mode', () => {

    await rig.setup(testName, {
      settings: {
+        experimental: { plan: true },
        tools: {
          core: ['write_file', 'read_file', 'list_directory'],
        },
        general: {
-          plan: { enabled: true, directory: plansDir },
          defaultApprovalMode: 'plan',
+          plan: {
+            directory: plansDir,
+          },
        },
      },
    });
@@ -11,7 +11,7 @@
        "packages/*"
      ],
      "dependencies": {
-        "ink": "npm:@jrichman/ink@6.6.3",
+        "ink": "npm:@jrichman/ink@6.5.0",
        "latest-version": "^9.0.0",
        "node-fetch-native": "^1.6.7",
        "proper-lockfile": "^4.1.2",
@@ -92,6 +92,46 @@
        "zod": "^3.25.0 || ^4.0.0"
      }
    },
+    "node_modules/@alcalzone/ansi-tokenize": {
+      "version": "0.2.2",
+      "resolved": "https://registry.npmjs.org/@alcalzone/ansi-tokenize/-/ansi-tokenize-0.2.2.tgz",
+      "integrity": "sha512-mkOh+Wwawzuf5wa30bvc4nA+Qb6DIrGWgBhRR/Pw4T9nsgYait8izvXkNyU78D6Wcu3Z+KUdwCmLCxlWjEotYA==",
+      "license": "MIT",
+      "dependencies": {
+        "ansi-styles": "^6.2.1",
+        "is-fullwidth-code-point": "^5.0.0"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/@alcalzone/ansi-tokenize/node_modules/ansi-styles": {
+      "version": "6.2.3",
+      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.3.tgz",
+      "integrity": "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://github.com/chalk/ansi-styles?sponsor=1"
+      }
+    },
+    "node_modules/@alcalzone/ansi-tokenize/node_modules/is-fullwidth-code-point": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-5.1.0.tgz",
+      "integrity": "sha512-5XHYaSyiqADb4RnZ1Bdad6cPp8Toise4TzEjcOYDHZkTCbKgiUl7WTUCpNWHuxmDt91wnsZBc9xinNzopv3JMQ==",
+      "license": "MIT",
+      "dependencies": {
+        "get-east-asian-width": "^1.3.1"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
    "node_modules/@ampproject/remapping": {
      "version": "2.3.0",
      "resolved": "https://registry.npmjs.org/@ampproject/remapping/-/remapping-2.3.0.tgz",
@@ -10049,13 +10089,14 @@
    },
    "node_modules/ink": {
      "name": "@jrichman/ink",
-      "version": "6.6.3",
-      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.6.3.tgz",
-      "integrity": "sha512-0v4S7TbbF2tpQrfqH1btwLgTgH+K0vY2BJbokTE5Lk1KBr4TqZ+Pyo+geSD5F+zytX6G2ajGHBQyHk8yGK4C7A==",
+      "version": "6.5.0",
+      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.5.0.tgz",
+      "integrity": "sha512-S4g/ng7fPZmFwclO82iWkOce8vDLy/FIDgHIfkCWGOehqHe6dexHsmq3kNQD21okh198pA5SAQTCqNQJb/svRQ==",
      "license": "MIT",
      "dependencies": {
+        "@alcalzone/ansi-tokenize": "^0.2.1",
        "ansi-escapes": "^7.0.0",
-        "ansi-styles": "^6.2.3",
+        "ansi-styles": "^6.2.1",
        "auto-bind": "^5.0.1",
        "chalk": "^5.6.0",
        "cli-boxes": "^3.0.0",
@@ -10064,7 +10105,6 @@
        "code-excerpt": "^4.0.0",
        "es-toolkit": "^1.39.10",
        "indent-string": "^5.0.0",
-        "is-fullwidth-code-point": "^5.0.0",
        "is-in-ci": "^2.0.0",
        "mnemonist": "^0.40.3",
        "patch-console": "^2.0.0",
@@ -10134,9 +10174,9 @@
      }
    },
    "node_modules/ink/node_modules/ansi-styles": {
-      "version": "6.2.3",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.3.tgz",
-      "integrity": "sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==",
+      "version": "6.2.1",
+      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.1.tgz",
+      "integrity": "sha512-bN798gFfQX+viw3R7yrGWRqnrN2oRkEkUjjl4JNn4E8GxxbjtG3FbrEIIY3l8/hrwUwIeCZvi4QuOTP4MErVug==",
      "license": "MIT",
      "engines": {
        "node": ">=12"
@@ -10157,21 +10197,6 @@
        "url": "https://github.com/chalk/chalk?sponsor=1"
      }
    },
-    "node_modules/ink/node_modules/is-fullwidth-code-point": {
-      "version": "5.1.0",
-      "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-5.1.0.tgz",
-      "integrity": "sha512-5XHYaSyiqADb4RnZ1Bdad6cPp8Toise4TzEjcOYDHZkTCbKgiUl7WTUCpNWHuxmDt91wnsZBc9xinNzopv3JMQ==",
-      "license": "MIT",
-      "dependencies": {
-        "get-east-asian-width": "^1.3.1"
-      },
-      "engines": {
-        "node": ">=18"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
    "node_modules/ink/node_modules/is-in-ci": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/is-in-ci/-/is-in-ci-2.0.0.tgz",
@@ -17526,7 +17551,7 @@
        "fzf": "^0.5.2",
        "glob": "^12.0.0",
        "highlight.js": "^11.11.1",
-        "ink": "npm:@jrichman/ink@6.6.3",
+        "ink": "npm:@jrichman/ink@6.5.0",
        "ink-gradient": "^3.0.0",
        "ink-spinner": "^5.0.0",
        "latest-version": "^9.0.0",
@@ -38,7 +38,7 @@
    "build:packages": "npm run build --workspaces",
    "build:sandbox": "node scripts/build_sandbox.js",
    "build:binary": "node scripts/build_binary.js",
-    "bundle": "npm run generate && npm run build --workspace=@google/gemini-cli-devtools && npm run bundle:browser-mcp -w @google/gemini-cli-core && node esbuild.config.js && node scripts/copy_bundle_assets.js",
+    "bundle": "npm run generate && npm run build --workspace=@google/gemini-cli-devtools && node esbuild.config.js && node scripts/copy_bundle_assets.js",
    "test": "npm run test --workspaces --if-present && npm run test:sea-launch",
    "test:ci": "npm run test:ci --workspaces --if-present && npm run test:scripts && npm run test:sea-launch",
    "test:scripts": "vitest run --config ./scripts/tests/vitest.config.ts",
@@ -68,7 +68,7 @@
    "pre-commit": "node scripts/pre-commit.js"
  },
  "overrides": {
-    "ink": "npm:@jrichman/ink@6.6.3",
+    "ink": "npm:@jrichman/ink@6.5.0",
    "wrap-ansi": "9.0.2",
    "cliui": {
      "wrap-ansi": "7.0.0"
@@ -136,7 +136,7 @@
    "yargs": "^17.7.2"
  },
  "dependencies": {
-    "ink": "npm:@jrichman/ink@6.6.3",
+    "ink": "npm:@jrichman/ink@6.5.0",
    "latest-version": "^9.0.0",
    "node-fetch-native": "^1.6.7",
    "proper-lockfile": "^4.1.2",
@@ -98,7 +98,7 @@ export class RestoreCommand implements Command {
        name: this.name,
        data: restoreResult,
      };
-    } catch {
+    } catch (_error) {
      return {
        name: this.name,
        data: {
@@ -142,7 +142,7 @@ export class ListCheckpointsCommand implements Command {
          content: JSON.stringify(checkpointInfoList),
        },
      };
-    } catch {
+    } catch (_error) {
      return {
        name: this.name,
        data: {
@@ -424,8 +424,27 @@ describe('loadConfig', () => {
      });
    });

-    describe('authentication logic', () => {
-      const setupConfigMock = (refreshAuthMock: ReturnType<typeof vi.fn>) => {
+    describe('authentication fallback', () => {
+      beforeEach(() => {
+        vi.stubEnv('USE_CCPA', 'true');
+        vi.stubEnv('GEMINI_API_KEY', '');
+      });
+
+      afterEach(() => {
+        vi.unstubAllEnvs();
+      });
+
+      it('should fall back to COMPUTE_ADC in Cloud Shell if LOGIN_WITH_GOOGLE fails', async () => {
+        vi.stubEnv('CLOUD_SHELL', 'true');
+        vi.mocked(isHeadlessMode).mockReturnValue(false);
+        const refreshAuthMock = vi.fn().mockImplementation((authType) => {
+          if (authType === AuthType.LOGIN_WITH_GOOGLE) {
+            throw new FatalAuthenticationError('Non-interactive session');
+          }
+          return Promise.resolve();
+        });
+
+        // Update the mock implementation for this test
        vi.mocked(Config).mockImplementation(
          (params: unknown) =>
            ({
@@ -438,88 +457,159 @@ describe('loadConfig', () => {
              setRemoteAdminSettings: vi.fn(),
            }) as unknown as Config,
        );
-      };
-
-      beforeEach(() => {
-        vi.stubEnv('USE_CCPA', 'true');
-        vi.stubEnv('GEMINI_API_KEY', '');
-      });
-
-      afterEach(() => {
-        vi.unstubAllEnvs();
-      });
-
-      it('should attempt COMPUTE_ADC by default and bypass LOGIN_WITH_GOOGLE if successful', async () => {
-        const refreshAuthMock = vi.fn().mockResolvedValue(undefined);
-        setupConfigMock(refreshAuthMock);

        await loadConfig(mockSettings, mockExtensionLoader, taskId);

-        expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
-        expect(refreshAuthMock).not.toHaveBeenCalledWith(
-          AuthType.LOGIN_WITH_GOOGLE,
-        );
-      });
-
-      it('should fallback to LOGIN_WITH_GOOGLE if COMPUTE_ADC fails and interactive mode is available', async () => {
-        vi.mocked(isHeadlessMode).mockReturnValue(false);
-        const refreshAuthMock = vi.fn().mockImplementation((authType) => {
-          if (authType === AuthType.COMPUTE_ADC) {
-            return Promise.reject(new Error('ADC failed'));
-          }
-          return Promise.resolve();
-        });
-        setupConfigMock(refreshAuthMock);
-
-        await loadConfig(mockSettings, mockExtensionLoader, taskId);
-
-        expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
        expect(refreshAuthMock).toHaveBeenCalledWith(
          AuthType.LOGIN_WITH_GOOGLE,
        );
+        expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
      });

-      it('should throw FatalAuthenticationError in headless mode if COMPUTE_ADC fails', async () => {
-        vi.mocked(isHeadlessMode).mockReturnValue(true);
-
+      it('should not fall back to COMPUTE_ADC if not in cloud environment', async () => {
+        vi.mocked(isHeadlessMode).mockReturnValue(false);
        const refreshAuthMock = vi.fn().mockImplementation((authType) => {
-          if (authType === AuthType.COMPUTE_ADC) {
-            return Promise.reject(new Error('ADC not found'));
+          if (authType === AuthType.LOGIN_WITH_GOOGLE) {
+            throw new FatalAuthenticationError('Non-interactive session');
          }
          return Promise.resolve();
        });
-        setupConfigMock(refreshAuthMock);
+
+        vi.mocked(Config).mockImplementation(
+          (params: unknown) =>
+            ({
+              ...(params as object),
+              initialize: vi.fn(),
+              waitForMcpInit: vi.fn(),
+              refreshAuth: refreshAuthMock,
+              getExperiments: vi.fn().mockReturnValue({ flags: {} }),
+              getRemoteAdminSettings: vi.fn(),
+              setRemoteAdminSettings: vi.fn(),
+            }) as unknown as Config,
+        );

        await expect(
          loadConfig(mockSettings, mockExtensionLoader, taskId),
-        ).rejects.toThrow(
-          'COMPUTE_ADC failed: ADC not found. (LOGIN_WITH_GOOGLE fallback skipped due to headless mode. Run in an interactive terminal to use OAuth.)',
+        ).rejects.toThrow('Non-interactive session');
+
+        expect(refreshAuthMock).toHaveBeenCalledWith(
+          AuthType.LOGIN_WITH_GOOGLE,
+        );
+        expect(refreshAuthMock).not.toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
+      });
+
+      it('should skip LOGIN_WITH_GOOGLE and use COMPUTE_ADC directly in headless Cloud Shell', async () => {
+        vi.stubEnv('CLOUD_SHELL', 'true');
+        vi.mocked(isHeadlessMode).mockReturnValue(true);
+
+        const refreshAuthMock = vi.fn().mockResolvedValue(undefined);
+
+        vi.mocked(Config).mockImplementation(
+          (params: unknown) =>
+            ({
+              ...(params as object),
+              initialize: vi.fn(),
+              waitForMcpInit: vi.fn(),
+              refreshAuth: refreshAuthMock,
+              getExperiments: vi.fn().mockReturnValue({ flags: {} }),
+              getRemoteAdminSettings: vi.fn(),
+              setRemoteAdminSettings: vi.fn(),
+            }) as unknown as Config,
        );

-        expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
+        await loadConfig(mockSettings, mockExtensionLoader, taskId);
+
        expect(refreshAuthMock).not.toHaveBeenCalledWith(
          AuthType.LOGIN_WITH_GOOGLE,
        );
+        expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
      });

-      it('should include both original and fallback error when LOGIN_WITH_GOOGLE fallback fails', async () => {
-        vi.mocked(isHeadlessMode).mockReturnValue(false);
+      it('should skip LOGIN_WITH_GOOGLE and use COMPUTE_ADC directly if GEMINI_CLI_USE_COMPUTE_ADC is true', async () => {
+        vi.stubEnv('GEMINI_CLI_USE_COMPUTE_ADC', 'true');
+        vi.mocked(isHeadlessMode).mockReturnValue(false); // Even if not headless

-        const refreshAuthMock = vi.fn().mockImplementation((authType) => {
-          if (authType === AuthType.COMPUTE_ADC) {
-            throw new Error('ADC failed');
-          }
-          if (authType === AuthType.LOGIN_WITH_GOOGLE) {
-            throw new FatalAuthenticationError('OAuth failed');
-          }
-          return Promise.resolve();
-        });
-        setupConfigMock(refreshAuthMock);
+        const refreshAuthMock = vi.fn().mockResolvedValue(undefined);
+
+        vi.mocked(Config).mockImplementation(
+          (params: unknown) =>
+            ({
+              ...(params as object),
+              initialize: vi.fn(),
+              waitForMcpInit: vi.fn(),
+              refreshAuth: refreshAuthMock,
+              getExperiments: vi.fn().mockReturnValue({ flags: {} }),
+              getRemoteAdminSettings: vi.fn(),
+              setRemoteAdminSettings: vi.fn(),
+            }) as unknown as Config,
+        );
+
+        await loadConfig(mockSettings, mockExtensionLoader, taskId);
+
+        expect(refreshAuthMock).not.toHaveBeenCalledWith(
+          AuthType.LOGIN_WITH_GOOGLE,
+        );
+        expect(refreshAuthMock).toHaveBeenCalledWith(AuthType.COMPUTE_ADC);
+      });
+
+      it('should throw FatalAuthenticationError in headless mode if no ADC fallback available', async () => {
+        vi.mocked(isHeadlessMode).mockReturnValue(true);
+
+        const refreshAuthMock = vi.fn().mockResolvedValue(undefined);
+
+        vi.mocked(Config).mockImplementation(
+          (params: unknown) =>
+            ({
+              ...(params as object),
+              initialize: vi.fn(),
+              waitForMcpInit: vi.fn(),
+              refreshAuth: refreshAuthMock,
+              getExperiments: vi.fn().mockReturnValue({ flags: {} }),
+              getRemoteAdminSettings: vi.fn(),
+              setRemoteAdminSettings: vi.fn(),
+            }) as unknown as Config,
+        );

        await expect(
          loadConfig(mockSettings, mockExtensionLoader, taskId),
        ).rejects.toThrow(
-          'OAuth failed. The initial COMPUTE_ADC attempt also failed: ADC failed',
+          'Interactive terminal required for LOGIN_WITH_GOOGLE. Run in an interactive terminal or set GEMINI_CLI_USE_COMPUTE_ADC=true to use Application Default Credentials.',
+        );
+
+        expect(refreshAuthMock).not.toHaveBeenCalled();
+      });
+
+      it('should include both original and fallback error when COMPUTE_ADC fallback fails', async () => {
+        vi.stubEnv('CLOUD_SHELL', 'true');
+        vi.mocked(isHeadlessMode).mockReturnValue(false);
+
+        const refreshAuthMock = vi.fn().mockImplementation((authType) => {
+          if (authType === AuthType.LOGIN_WITH_GOOGLE) {
+            throw new FatalAuthenticationError('OAuth failed');
+          }
+          if (authType === AuthType.COMPUTE_ADC) {
+            throw new Error('ADC failed');
+          }
+          return Promise.resolve();
+        });
+
+        vi.mocked(Config).mockImplementation(
+          (params: unknown) =>
+            ({
+              ...(params as object),
+              initialize: vi.fn(),
+              waitForMcpInit: vi.fn(),
+              refreshAuth: refreshAuthMock,
+              getExperiments: vi.fn().mockReturnValue({ flags: {} }),
+              getRemoteAdminSettings: vi.fn(),
+              setRemoteAdminSettings: vi.fn(),
+            }) as unknown as Config,
+        );
+
+        await expect(
+          loadConfig(mockSettings, mockExtensionLoader, taskId),
+        ).rejects.toThrow(
+          'OAuth failed. Fallback to COMPUTE_ADC also failed: ADC failed',
        );
      });
    });
@@ -25,6 +25,7 @@ import {
  ExperimentFlags,
  isHeadlessMode,
  FatalAuthenticationError,
+  isCloudShell,
  PolicyDecision,
  PRIORITY_YOLO_ALLOW_ALL,
  type TelemetryTarget,
@@ -42,6 +43,7 @@ export async function loadConfig(
  taskId: string,
 ): Promise<Config> {
  const workspaceDir = process.cwd();
+  const adcFilePath = process.env['GOOGLE_APPLICATION_CREDENTIALS'];

  const folderTrust =
    settings.folderTrust === true ||
@@ -190,7 +192,7 @@ export async function loadConfig(
  await config.waitForMcpInit();
  startupProfiler.flush(config);

-  await refreshAuthentication(config, 'Config');
+  await refreshAuthentication(config, adcFilePath, 'Config');

  return config;
 }
@@ -261,51 +263,75 @@ function findEnvFile(startDir: string): string | null {

 async function refreshAuthentication(
  config: Config,
+  adcFilePath: string | undefined,
  logPrefix: string,
 ): Promise<void> {
  if (process.env['USE_CCPA']) {
    logger.info(`[${logPrefix}] Using CCPA Auth:`);
-
-    logger.info(`[${logPrefix}] Attempting COMPUTE_ADC first.`);
    try {
-      await config.refreshAuth(AuthType.COMPUTE_ADC);
-      logger.info(`[${logPrefix}] COMPUTE_ADC successful.`);
-    } catch (adcError) {
-      const adcMessage =
-        adcError instanceof Error ? adcError.message : String(adcError);
-      logger.info(
-        `[${logPrefix}] COMPUTE_ADC failed or not available: ${adcMessage}`,
+      if (adcFilePath) {
+        path.resolve(adcFilePath);
+      }
+    } catch (e) {
+      logger.error(
+        `[${logPrefix}] USE_CCPA env var is true but unable to resolve GOOGLE_APPLICATION_CREDENTIALS file path ${adcFilePath}. Error ${e}`,
      );
+    }

-      const useComputeAdc =
-        process.env['GEMINI_CLI_USE_COMPUTE_ADC'] === 'true';
-      const isHeadless = isHeadlessMode();
+    const useComputeAdc = process.env['GEMINI_CLI_USE_COMPUTE_ADC'] === 'true';
+    const isHeadless = isHeadlessMode();
+    const shouldSkipOauth = isHeadless || useComputeAdc;

-      if (isHeadless || useComputeAdc) {
-        const reason = isHeadless
-          ? 'headless mode'
-          : 'GEMINI_CLI_USE_COMPUTE_ADC=true';
+    if (shouldSkipOauth) {
+      if (isCloudShell() || useComputeAdc) {
+        logger.info(
+          `[${logPrefix}] Skipping LOGIN_WITH_GOOGLE due to ${isHeadless ? 'headless mode' : 'GEMINI_CLI_USE_COMPUTE_ADC'}. Attempting COMPUTE_ADC.`,
+        );
+        try {
+          await config.refreshAuth(AuthType.COMPUTE_ADC);
+          logger.info(`[${logPrefix}] COMPUTE_ADC successful.`);
+        } catch (adcError) {
+          const adcMessage =
+            adcError instanceof Error ? adcError.message : String(adcError);
+          throw new FatalAuthenticationError(
+            `COMPUTE_ADC failed: ${adcMessage}. (Skipped LOGIN_WITH_GOOGLE due to ${isHeadless ? 'headless mode' : 'GEMINI_CLI_USE_COMPUTE_ADC'})`,
+          );
+        }
+      } else {
        throw new FatalAuthenticationError(
-          `COMPUTE_ADC failed: ${adcMessage}. (LOGIN_WITH_GOOGLE fallback skipped due to ${reason}. Run in an interactive terminal to use OAuth.)`,
+          `Interactive terminal required for LOGIN_WITH_GOOGLE. Run in an interactive terminal or set GEMINI_CLI_USE_COMPUTE_ADC=true to use Application Default Credentials.`,
        );
      }
-
-      logger.info(
-        `[${logPrefix}] COMPUTE_ADC failed, falling back to LOGIN_WITH_GOOGLE.`,
-      );
+    } else {
      try {
        await config.refreshAuth(AuthType.LOGIN_WITH_GOOGLE);
      } catch (e) {
-        if (e instanceof FatalAuthenticationError) {
-          const originalMessage = e instanceof Error ? e.message : String(e);
-          throw new FatalAuthenticationError(
-            `${originalMessage}. The initial COMPUTE_ADC attempt also failed: ${adcMessage}`,
+        if (
+          e instanceof FatalAuthenticationError &&
+          (isCloudShell() || useComputeAdc)
+        ) {
+          logger.warn(
+            `[${logPrefix}] LOGIN_WITH_GOOGLE failed. Attempting COMPUTE_ADC fallback.`,
          );
+          try {
+            await config.refreshAuth(AuthType.COMPUTE_ADC);
+            logger.info(`[${logPrefix}] COMPUTE_ADC fallback successful.`);
+          } catch (adcError) {
+            logger.error(
+              `[${logPrefix}] COMPUTE_ADC fallback failed: ${adcError}`,
+            );
+            const originalMessage = e instanceof Error ? e.message : String(e);
+            const adcMessage =
+              adcError instanceof Error ? adcError.message : String(adcError);
+            throw new FatalAuthenticationError(
+              `${originalMessage}. Fallback to COMPUTE_ADC also failed: ${adcMessage}`,
+            );
+          }
+        } else {
+          throw e;
        }
-        throw e;
      }
    }
-
    logger.info(
      `[${logPrefix}] GOOGLE_CLOUD_PROJECT: ${process.env['GOOGLE_CLOUD_PROJECT']}`,
    );
@@ -109,8 +109,12 @@ export function createMockConfig(
        enableEnvironmentVariableRedaction: false,
      },
    }),
-    isAutoDistillationEnabled: vi.fn().mockReturnValue(false),
-    getContextManagementConfig: vi.fn().mockReturnValue({ enabled: false }),
+    isExperimentalAgentHistoryTruncationEnabled: vi.fn().mockReturnValue(false),
+    getExperimentalAgentHistoryTruncationThreshold: vi.fn().mockReturnValue(50),
+    getExperimentalAgentHistoryRetainedMessages: vi.fn().mockReturnValue(30),
+    isExperimentalAgentHistorySummarizationEnabled: vi
+      .fn()
+      .mockReturnValue(false),
    ...overrides,
  } as unknown as Config;

@@ -49,7 +49,7 @@
    "fzf": "^0.5.2",
    "glob": "^12.0.0",
    "highlight.js": "^11.11.1",
-    "ink": "npm:@jrichman/ink@6.6.3",
+    "ink": "npm:@jrichman/ink@6.5.0",
    "ink-gradient": "^3.0.0",
    "ink-spinner": "^5.0.0",
    "latest-version": "^9.0.0",
@@ -27,7 +27,6 @@ import {
  type MessageBus,
  LlmRole,
  type GitService,
-  type ModelRouterService,
  processSingleFileContent,
  InvalidStreamError,
 } from '@google/gemini-cli-core';
@@ -103,7 +102,17 @@ vi.mock(
      ...actual,
      updatePolicy: vi.fn(),
      createPolicyUpdater: vi.fn(),
-      ReadManyFilesTool: vi.fn(),
+      ReadManyFilesTool: vi.fn().mockImplementation(() => ({
+        name: 'read_many_files',
+        kind: 'read',
+        build: vi.fn().mockReturnValue({
+          getDescription: () => 'Read files',
+          toolLocations: () => [],
+          execute: vi.fn().mockResolvedValue({
+            llmContent: ['--- file.txt ---\n\nFile content\n\n'],
+          }),
+        }),
+      })),
      logToolCall: vi.fn(),
      LlmRole: {
        MAIN: 'main',
@@ -412,26 +421,6 @@ describe('GeminiAgent', () => {
    );
  });

-  it('should include gemini-3.1-flash-lite when useGemini31FlashLite is true', async () => {
-    mockConfig.getHasAccessToPreviewModel = vi.fn().mockReturnValue(true);
-    mockConfig.getGemini31LaunchedSync = vi.fn().mockReturnValue(true);
-    mockConfig.getGemini31FlashLiteLaunchedSync = vi.fn().mockReturnValue(true);
-
-    const response = await agent.newSession({
-      cwd: '/tmp',
-      mcpServers: [],
-    });
-
-    expect(response.models?.availableModels).toEqual(
-      expect.arrayContaining([
-        expect.objectContaining({
-          modelId: 'gemini-3.1-flash-lite-preview',
-          name: 'gemini-3.1-flash-lite-preview',
-        }),
-      ]),
-    );
-  });
-
  it('should return modes with plan mode when plan is enabled', async () => {
    mockConfig.getContentGeneratorConfig = vi.fn().mockReturnValue({
      apiKey: 'test-key',
@@ -657,7 +646,6 @@ describe('Session', () => {
      sendMessageStream: vi.fn(),
      addHistory: vi.fn(),
      recordCompletedToolCalls: vi.fn(),
-      getHistory: vi.fn().mockReturnValue([]),
    } as unknown as Mocked<GeminiChat>;
    mockTool = {
      kind: 'read',
@@ -679,9 +667,6 @@ describe('Session', () => {
    mockConfig = {
      getModel: vi.fn().mockReturnValue('gemini-pro'),
      getActiveModel: vi.fn().mockReturnValue('gemini-pro'),
-      getModelRouterService: vi.fn().mockReturnValue({
-        route: vi.fn().mockResolvedValue({ model: 'resolved-model' }),
-      }),
      getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
      getMcpServers: vi.fn(),
      getFileService: vi.fn().mockReturnValue({
@@ -728,22 +713,10 @@ describe('Session', () => {
      },
      errors: [],
    } as unknown as LoadedSettings);
-
-    (ReadManyFilesTool as unknown as Mock).mockImplementation(() => ({
-      name: 'read_many_files',
-      kind: 'read',
-      build: vi.fn().mockReturnValue({
-        getDescription: () => 'Read files',
-        toolLocations: () => [],
-        execute: vi.fn().mockResolvedValue({
-          llmContent: ['--- file.txt ---\n\nFile content\n\n'],
-        }),
-      }),
-    }));
  });

  afterEach(() => {
-    vi.restoreAllMocks();
+    vi.clearAllMocks();
  });

  it('should send available commands', async () => {
@@ -813,42 +786,6 @@ describe('Session', () => {
    expect(result).toMatchObject({ stopReason: 'end_turn' });
  });

-  it('should use model router to determine model', async () => {
-    const mockRouter = {
-      route: vi.fn().mockResolvedValue({ model: 'routed-model' }),
-    } as unknown as ModelRouterService;
-    mockConfig.getModelRouterService.mockReturnValue(mockRouter);
-
-    const stream = createMockStream([
-      {
-        type: StreamEventType.CHUNK,
-        value: {
-          candidates: [{ content: { parts: [{ text: 'Hello' }] } }],
-        },
-      },
-    ]);
-    mockChat.sendMessageStream.mockResolvedValue(stream);
-
-    await session.prompt({
-      sessionId: 'session-1',
-      prompt: [{ type: 'text', text: 'Hi' }],
-    });
-
-    expect(mockRouter.route).toHaveBeenCalledWith(
-      expect.objectContaining({
-        requestedModel: 'gemini-pro',
-        request: [{ text: 'Hi' }],
-      }),
-    );
-    expect(mockChat.sendMessageStream).toHaveBeenCalledWith(
-      expect.objectContaining({ model: 'routed-model' }),
-      expect.any(Array),
-      expect.any(String),
-      expect.any(Object),
-      expect.any(String),
-    );
-  });
-
  it('should handle prompt with empty response (InvalidStreamError)', async () => {
    mockChat.sendMessageStream.mockRejectedValue(
      new InvalidStreamError('Empty response', 'NO_RESPONSE_TEXT'),
@@ -28,7 +28,7 @@ import {
  debugLogger,
  ReadManyFilesTool,
  REFERENCE_CONTENT_START,
-  type RoutingContext,
+  resolveModel,
  createWorkingStdio,
  startupProfiler,
  Kind,
@@ -42,7 +42,6 @@ import {
  DEFAULT_GEMINI_FLASH_LITE_MODEL,
  PREVIEW_GEMINI_MODEL,
  PREVIEW_GEMINI_3_1_MODEL,
-  PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
  PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL,
  PREVIEW_GEMINI_FLASH_MODEL,
  DEFAULT_GEMINI_MODEL_AUTO,
@@ -759,15 +758,10 @@ export class Session {
      const functionCalls: FunctionCall[] = [];

      try {
-        const routingContext: RoutingContext = {
-          history: chat.getHistory(/*curated=*/ true),
-          request: nextMessage?.parts ?? [],
-          signal: pendingSend.signal,
-          requestedModel: this.context.config.getModel(),
-        };
-
-        const router = this.context.config.getModelRouterService();
-        const { model } = await router.route(routingContext);
+        const model = resolveModel(
+          this.context.config.getModel(),
+          (await this.context.config.getGemini31Launched?.()) ?? false,
+        );
        const responseStream = await chat.sendMessageStream(
          { model },
          nextMessage?.parts ?? [],
@@ -2015,31 +2009,10 @@ function buildAvailableModels(
  const preferredModel = config.getModel() || DEFAULT_GEMINI_MODEL_AUTO;
  const shouldShowPreviewModels = config.getHasAccessToPreviewModel();
  const useGemini31 = config.getGemini31LaunchedSync?.() ?? false;
-  const useGemini31FlashLite =
-    config.getGemini31FlashLiteLaunchedSync?.() ?? false;
  const selectedAuthType = settings.merged.security.auth.selectedType;
  const useCustomToolModel =
    useGemini31 && selectedAuthType === AuthType.USE_GEMINI;

-  // --- DYNAMIC PATH ---
-  if (
-    config.getExperimentalDynamicModelConfiguration?.() === true &&
-    config.getModelConfigService
-  ) {
-    const options = config.getModelConfigService().getAvailableModelOptions({
-      useGemini3_1: useGemini31,
-      useGemini3_1FlashLite: useGemini31FlashLite,
-      useCustomTools: useCustomToolModel,
-      hasAccessToPreview: shouldShowPreviewModels,
-    });
-
-    return {
-      availableModels: options,
-      currentModelId: preferredModel,
-    };
-  }
-
-  // --- LEGACY PATH ---
  const mainOptions = [
    {
      value: DEFAULT_GEMINI_MODEL_AUTO,
@@ -2083,7 +2056,7 @@ function buildAvailableModels(
      ? PREVIEW_GEMINI_3_1_CUSTOM_TOOLS_MODEL
      : previewProModel;

-    const previewOptions = [
+    manualOptions.unshift(
      {
        value: previewProValue,
        title: getDisplayString(previewProModel),
@@ -2092,16 +2065,7 @@ function buildAvailableModels(
        value: PREVIEW_GEMINI_FLASH_MODEL,
        title: getDisplayString(PREVIEW_GEMINI_FLASH_MODEL),
      },
-    ];
-
-    if (useGemini31FlashLite) {
-      previewOptions.push({
-        value: PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL,
-        title: getDisplayString(PREVIEW_GEMINI_3_1_FLASH_LITE_MODEL),
-      });
-    }
-
-    manualOptions.unshift(...previewOptions);
+    );
  }

  const scaleOptions = (
@@ -284,7 +284,7 @@ export class LinkExtensionCommand implements Command {

    try {
      await stat(sourceFilepath);
-    } catch {
+    } catch (_error) {
      return { name: this.name, data: `Invalid source: ${sourceFilepath}` };
    }

@@ -130,7 +130,7 @@ export class ListCheckpointsCommand implements Command {
      const checkpointDir = config.storage.getProjectTempCheckpointsDir();
      try {
        await fs.mkdir(checkpointDir, { recursive: true });
-      } catch {
+      } catch (_e) {
        // Ignore
      }

@@ -169,7 +169,7 @@ export class ListCheckpointsCommand implements Command {
        name: this.name,
        data: `Available Checkpoints:\n${formatted}`,
      };
-    } catch {
+    } catch (_error) {
      return {
        name: this.name,
        data: 'An unexpected error occurred while listing checkpoints.',
@@ -25,7 +25,7 @@ async function pathExists(path: string) {
  try {
    await access(path);
    return true;
-  } catch {
+  } catch (_e) {
    return false;
  }
 }
@@ -32,7 +32,7 @@ describe('mcp command', () => {

    try {
      await parser.parse('mcp');
-    } catch {
+    } catch (_error) {
      // yargs might throw an error when demandCommand is not met
    }

@@ -121,7 +121,7 @@ async function testMCPConnection(
  try {
    // Use the same transport creation logic as core
    transport = await createTransport(serverName, config, false, mcpContext);
-  } catch {
+  } catch (_error) {
    await client.close();
    return MCPServerStatus.DISCONNECTED;
  }
@@ -135,7 +135,7 @@ async function testMCPConnection(

    await client.close();
    return MCPServerStatus.CONNECTED;
-  } catch {
+  } catch (_error) {
    await transport.close();
    return MCPServerStatus.DISCONNECTED;
  }
@@ -1364,8 +1364,8 @@ describe('Approval mode tool exclusion logic', () => {
      'test',
    ];
    const settings = createTestMergedSettings({
-      general: {
-        plan: { enabled: true },
+      experimental: {
+        plan: true,
      },
    });
    const argv = await parseArguments(createTestMergedSettings());
@@ -1479,7 +1479,9 @@ describe('Approval mode tool exclusion logic', () => {
    const settings = createTestMergedSettings({
      general: {
        defaultApprovalMode: 'plan',
-        plan: { enabled: false },
+      },
+      experimental: {
+        plan: false,
      },
    });
    const argv = await parseArguments(settings);
@@ -1487,12 +1489,14 @@ describe('Approval mode tool exclusion logic', () => {
    expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
  });

-  it('should allow plan approval mode if plan is enabled', async () => {
+  it('should allow plan approval mode if experimental plan is enabled', async () => {
    process.argv = ['node', 'script.js'];
    const settings = createTestMergedSettings({
      general: {
        defaultApprovalMode: 'plan',
-        plan: { enabled: true },
+      },
+      experimental: {
+        plan: true,
      },
    });
    const argv = await parseArguments(settings);
@@ -2738,12 +2742,12 @@ describe('loadCliConfig approval mode', () => {
    expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.YOLO);
  });

-  it('should set Plan approval mode when --approval-mode=plan is used and plan is enabled', async () => {
+  it('should set Plan approval mode when --approval-mode=plan is used and experimental.plan is enabled', async () => {
    process.argv = ['node', 'script.js', '--approval-mode', 'plan'];
    const argv = await parseArguments(createTestMergedSettings());
    const settings = createTestMergedSettings({
-      general: {
-        plan: { enabled: true },
+      experimental: {
+        plan: true,
      },
    });
    const config = await loadCliConfig(settings, 'test-session', argv);
@@ -2763,12 +2767,12 @@ describe('loadCliConfig approval mode', () => {
    expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.DEFAULT);
  });

-  it('should throw error when --approval-mode=plan is used but plan is disabled', async () => {
+  it('should throw error when --approval-mode=plan is used but experimental.plan is disabled', async () => {
    process.argv = ['node', 'script.js', '--approval-mode', 'plan'];
    const argv = await parseArguments(createTestMergedSettings());
    const settings = createTestMergedSettings({
-      general: {
-        plan: { enabled: false },
+      experimental: {
+        plan: false,
      },
    });

@@ -2889,26 +2893,22 @@ describe('loadCliConfig approval mode', () => {
      expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.YOLO);
    });

-    it('should respect plan mode from settings when plan is enabled', async () => {
+    it('should respect plan mode from settings when experimental.plan is enabled', async () => {
      process.argv = ['node', 'script.js'];
      const settings = createTestMergedSettings({
-        general: {
-          defaultApprovalMode: 'plan',
-          plan: { enabled: true },
-        },
+        general: { defaultApprovalMode: 'plan' },
+        experimental: { plan: true },
      });
      const argv = await parseArguments(settings);
      const config = await loadCliConfig(settings, 'test-session', argv);
      expect(config.getApprovalMode()).toBe(ServerConfig.ApprovalMode.PLAN);
    });

-    it('should fall back to default if plan mode is in settings but disabled', async () => {
+    it('should throw error if plan mode is in settings but experimental.plan is disabled', async () => {
      process.argv = ['node', 'script.js'];
      const settings = createTestMergedSettings({
-        general: {
-          defaultApprovalMode: 'plan',
-          plan: { enabled: false },
-        },
+        general: { defaultApprovalMode: 'plan' },
+        experimental: { plan: false },
      });
      const argv = await parseArguments(settings);
      const config = await loadCliConfig(settings, 'test-session', argv);
@@ -3696,9 +3696,7 @@ describe('loadCliConfig mcpEnabled', () => {
    it('should use plan directory from active extension when user has not specified one', async () => {
      process.argv = ['node', 'script.js'];
      const settings = createTestMergedSettings({
-        general: {
-          plan: { enabled: true },
-        },
+        experimental: { plan: true },
      });
      const argv = await parseArguments(settings);

@@ -3717,11 +3715,9 @@ describe('loadCliConfig mcpEnabled', () => {
    it('should NOT use plan directory from active extension when user has specified one', async () => {
      process.argv = ['node', 'script.js'];
      const settings = createTestMergedSettings({
+        experimental: { plan: true },
        general: {
-          plan: {
-            enabled: true,
-            directory: 'user-plans-dir',
-          },
+          plan: { directory: 'user-plans-dir' },
        },
      });
      const argv = await parseArguments(settings);
@@ -3742,9 +3738,7 @@ describe('loadCliConfig mcpEnabled', () => {
    it('should NOT use plan directory from inactive extension', async () => {
      process.argv = ['node', 'script.js'];
      const settings = createTestMergedSettings({
-        general: {
-          plan: { enabled: true },
-        },
+        experimental: { plan: true },
      });
      const argv = await parseArguments(settings);

@@ -3765,9 +3759,7 @@ describe('loadCliConfig mcpEnabled', () => {
    it('should use default path if neither user nor extension settings provide a plan directory', async () => {
      process.argv = ['node', 'script.js'];
      const settings = createTestMergedSettings({
-        general: {
-          plan: { enabled: true },
-        },
+        experimental: { plan: true },
      });
      const argv = await parseArguments(settings);

@@ -669,9 +669,9 @@ export async function loadCliConfig(
        approvalMode = ApprovalMode.AUTO_EDIT;
        break;
      case 'plan':
-        if (!(settings.general?.plan?.enabled ?? true)) {
+        if (!(settings.experimental?.plan ?? false)) {
          debugLogger.warn(
-            'Approval mode "plan" is disabled in your settings. Falling back to "default".',
+            'Approval mode "plan" is only available when experimental.plan is enabled. Falling back to "default".',
          );
          approvalMode = ApprovalMode.DEFAULT;
        } else {
@@ -966,7 +966,7 @@ export async function loadCliConfig(
    extensionRegistryURI,
    enableExtensionReloading: settings.experimental?.extensionReloading,
    enableAgents: settings.experimental?.enableAgents,
-    plan: settings.general?.plan?.enabled ?? true,
+    plan: settings.experimental?.plan,
    tracker: settings.experimental?.taskTracker,
    directWebFetch: settings.experimental?.directWebFetch,
    planSettings: settings.general?.plan?.directory
@@ -977,12 +977,17 @@ export async function loadCliConfig(
    disabledSkills: settings.skills?.disabled,
    experimentalJitContext: settings.experimental?.jitContext,
    experimentalMemoryManager: settings.experimental?.memoryManager,
-    contextManagement: {
-      enabled: settings.experimental?.contextManagement,
-      ...settings?.contextManagement,
-    },
+    experimentalAgentHistoryTruncation:
+      settings.experimental?.agentHistoryTruncation,
+    experimentalAgentHistoryTruncationThreshold:
+      settings.experimental?.agentHistoryTruncationThreshold,
+    experimentalAgentHistoryRetainedMessages:
+      settings.experimental?.agentHistoryRetainedMessages,
+    experimentalAgentHistorySummarization:
+      settings.experimental?.agentHistorySummarization,
    modelSteering: settings.experimental?.modelSteering,
    topicUpdateNarration: settings.experimental?.topicUpdateNarration,
+    toolOutputMasking: settings.experimental?.toolOutputMasking,
    noBrowser: !!process.env['NO_BROWSER'],
    summarizeToolOutput: settings.model?.summarizeToolOutput,
    ideMode,
@@ -995,8 +1000,6 @@ export async function loadCliConfig(
    useAlternateBuffer: settings.ui?.useAlternateBuffer,
    useRipgrep: settings.tools?.useRipgrep,
    enableInteractiveShell: settings.tools?.shell?.enableInteractiveShell,
-    shellBackgroundCompletionBehavior: settings.tools?.shell
-      ?.backgroundCompletionBehavior as string | undefined,
    shellToolInactivityTimeout: settings.tools?.shell?.inactivityTimeout,
    enableShellOutputEfficiency:
      settings.tools?.shell?.enableShellOutputEfficiency ?? true,
@@ -1009,7 +1012,6 @@ export async function loadCliConfig(
      format: (argv.outputFormat ?? settings.output?.format) as OutputFormat,
    },
    gemmaModelRouter: settings.experimental?.gemmaModelRouter,
-    adk: settings.experimental?.adk,
    fakeResponses: argv.fakeResponses,
    recordResponses: argv.recordResponses,
    retryFetchErrors: settings.general?.retryFetchErrors,
@@ -1064,7 +1066,7 @@ async function resolveWorktreeSettings(
    if (isGeminiWorktree(toplevel, projectRoot)) {
      worktreePath = toplevel;
    }
-  } catch {
+  } catch (_e) {
    return undefined;
  }

@@ -33,7 +33,7 @@ describe('copyExtension permissions', () => {
            makeWritableSync(path.join(p, child)),
          );
        }
-      } catch {
+      } catch (_e) {
        // Ignore errors during cleanup
      }
    };
@@ -101,7 +101,7 @@ describe('ExtensionManager', () => {
    themeManager.clearExtensionThemes();
    try {
      fs.rmSync(tempHomeDir, { recursive: true, force: true });
-    } catch {
+    } catch (_e) {
      // Ignore
    }
  });
@@ -63,7 +63,7 @@ export function loadInstallMetadata(
    // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
    const metadata = JSON.parse(configContent) as ExtensionInstallMetadata;
    return metadata;
-  } catch {
+  } catch (_e) {
    return undefined;
  }
 }
@@ -151,7 +151,7 @@ export async function fetchReleaseFromGithub(
      return await fetchJson(
        `https://api.github.com/repos/${owner}/${repo}/releases/latest`,
      );
-    } catch {
+    } catch (_) {
      // This can fail if there is no release marked latest. In that case
      // we want to just try the pre-release logic below.
    }
@@ -5,153 +5,87 @@
 */

 import { describe, it, expect } from 'vitest';
-import {
-  deriveItemsFromLegacySettings,
-  resolveFooterState,
-} from './footerItems.js';
+import { deriveItemsFromLegacySettings } from './footerItems.js';
 import { createMockSettings } from '../test-utils/settings.js';

-describe('footerItems', () => {
-  describe('deriveItemsFromLegacySettings', () => {
-    it('returns defaults when no legacy settings are customized', () => {
-      const settings = createMockSettings({
-        ui: { footer: { hideContextPercentage: true } },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).toEqual([
-        'workspace',
-        'git-branch',
-        'sandbox',
-        'model-name',
-        'quota',
-      ]);
-    });
-
-    it('removes workspace when hideCWD is true', () => {
-      const settings = createMockSettings({
-        ui: { footer: { hideCWD: true, hideContextPercentage: true } },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).not.toContain('workspace');
-    });
-
-    it('removes sandbox when hideSandboxStatus is true', () => {
-      const settings = createMockSettings({
-        ui: {
-          footer: { hideSandboxStatus: true, hideContextPercentage: true },
-        },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).not.toContain('sandbox');
-    });
-
-    it('removes model-name, context-used, and quota when hideModelInfo is true', () => {
-      const settings = createMockSettings({
-        ui: { footer: { hideModelInfo: true, hideContextPercentage: true } },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).not.toContain('model-name');
-      expect(items).not.toContain('context-used');
-      expect(items).not.toContain('quota');
-    });
-
-    it('includes context-used when hideContextPercentage is false', () => {
-      const settings = createMockSettings({
-        ui: { footer: { hideContextPercentage: false } },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).toContain('context-used');
-      // Should be after model-name
-      const modelIdx = items.indexOf('model-name');
-      const contextIdx = items.indexOf('context-used');
-      expect(contextIdx).toBe(modelIdx + 1);
-    });
-
-    it('includes memory-usage when showMemoryUsage is true', () => {
-      const settings = createMockSettings({
-        ui: { showMemoryUsage: true, footer: { hideContextPercentage: true } },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).toContain('memory-usage');
-    });
-
-    it('handles combination of settings', () => {
-      const settings = createMockSettings({
-        ui: {
-          showMemoryUsage: true,
-          footer: {
-            hideCWD: true,
-            hideModelInfo: true,
-            hideContextPercentage: false,
-          },
-        },
-      }).merged;
-      const items = deriveItemsFromLegacySettings(settings);
-      expect(items).toEqual([
-        'git-branch',
-        'sandbox',
-        'context-used',
-        'memory-usage',
-      ]);
-    });
+describe('deriveItemsFromLegacySettings', () => {
+  it('returns defaults when no legacy settings are customized', () => {
+    const settings = createMockSettings({
+      ui: { footer: { hideContextPercentage: true } },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).toEqual([
+      'workspace',
+      'git-branch',
+      'sandbox',
+      'model-name',
+      'quota',
+    ]);
  });

-  describe('resolveFooterState', () => {
-    it('filters out auth item when showUserIdentity is false', () => {
-      const settings = createMockSettings({
-        ui: {
-          showUserIdentity: false,
-          footer: {
-            items: ['workspace', 'auth', 'model-name'],
-          },
+  it('removes workspace when hideCWD is true', () => {
+    const settings = createMockSettings({
+      ui: { footer: { hideCWD: true, hideContextPercentage: true } },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).not.toContain('workspace');
+  });
+
+  it('removes sandbox when hideSandboxStatus is true', () => {
+    const settings = createMockSettings({
+      ui: { footer: { hideSandboxStatus: true, hideContextPercentage: true } },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).not.toContain('sandbox');
+  });
+
+  it('removes model-name, context-used, and quota when hideModelInfo is true', () => {
+    const settings = createMockSettings({
+      ui: { footer: { hideModelInfo: true, hideContextPercentage: true } },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).not.toContain('model-name');
+    expect(items).not.toContain('context-used');
+    expect(items).not.toContain('quota');
+  });
+
+  it('includes context-used when hideContextPercentage is false', () => {
+    const settings = createMockSettings({
+      ui: { footer: { hideContextPercentage: false } },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).toContain('context-used');
+    // Should be after model-name
+    const modelIdx = items.indexOf('model-name');
+    const contextIdx = items.indexOf('context-used');
+    expect(contextIdx).toBe(modelIdx + 1);
+  });
+
+  it('includes memory-usage when showMemoryUsage is true', () => {
+    const settings = createMockSettings({
+      ui: { showMemoryUsage: true, footer: { hideContextPercentage: true } },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).toContain('memory-usage');
+  });
+
+  it('handles combination of settings', () => {
+    const settings = createMockSettings({
+      ui: {
+        showMemoryUsage: true,
+        footer: {
+          hideCWD: true,
+          hideModelInfo: true,
+          hideContextPercentage: false,
        },
-      }).merged;
-
-      const state = resolveFooterState(settings);
-      expect(state.orderedIds).not.toContain('auth');
-      expect(state.selectedIds.has('auth')).toBe(false);
-      // It should also not be in the 'others' part of orderedIds
-      expect(state.orderedIds).toEqual([
-        'workspace',
-        'model-name',
-        'git-branch',
-        'sandbox',
-        'context-used',
-        'quota',
-        'memory-usage',
-        'session-id',
-        'code-changes',
-        'token-count',
-      ]);
-    });
-
-    it('includes auth item when showUserIdentity is true', () => {
-      const settings = createMockSettings({
-        ui: {
-          showUserIdentity: true,
-          footer: {
-            items: ['workspace', 'auth', 'model-name'],
-          },
-        },
-      }).merged;
-
-      const state = resolveFooterState(settings);
-      expect(state.orderedIds).toContain('auth');
-      expect(state.selectedIds.has('auth')).toBe(true);
-    });
-
-    it('includes auth item by default when showUserIdentity is undefined (defaults to true)', () => {
-      const settings = createMockSettings({
-        ui: {
-          footer: {
-            items: ['workspace', 'auth', 'model-name'],
-          },
-        },
-      }).merged;
-
-      const state = resolveFooterState(settings);
-      expect(state.orderedIds).toContain('auth');
-      expect(state.selectedIds.has('auth')).toBe(true);
-    });
+      },
+    }).merged;
+    const items = deriveItemsFromLegacySettings(settings);
+    expect(items).toEqual([
+      'git-branch',
+      'sandbox',
+      'context-used',
+      'memory-usage',
+    ]);
  });
 });
@@ -47,11 +47,6 @@ export const ALL_ITEMS = [
    header: 'session',
    description: 'Unique identifier for the current session',
  },
-  {
-    id: 'auth',
-    header: '/auth',
-    description: 'Current authentication info',
-  },
  {
    id: 'code-changes',
    header: 'diff',
@@ -75,7 +70,6 @@ export const DEFAULT_ORDER = [
  'quota',
  'memory-usage',
  'session-id',
-  'auth',
  'code-changes',
  'token-count',
 ];
@@ -127,19 +121,10 @@ export function resolveFooterState(settings: MergedSettings): {
  orderedIds: string[];
  selectedIds: Set<string>;
 } {
-  const showUserIdentity = settings.ui?.showUserIdentity !== false;
-  const filteredValidIds = showUserIdentity
-    ? VALID_IDS
-    : new Set([...VALID_IDS].filter((id) => id !== 'auth'));
-
  const source = (
    settings.ui?.footer?.items ?? deriveItemsFromLegacySettings(settings)
-  ).filter((id: string) => filteredValidIds.has(id));
-
-  const others = DEFAULT_ORDER.filter(
-    (id) => !source.includes(id) && filteredValidIds.has(id),
-  );
-
+  ).filter((id: string) => VALID_IDS.has(id));
+  const others = DEFAULT_ORDER.filter((id) => !source.includes(id));
  return {
    orderedIds: [...source, ...others],
    selectedIds: new Set(source),
@@ -612,7 +612,7 @@ export function loadEnvironment(
          }
        }
      }
-    } catch {
+    } catch (_e) {
      // Errors are ignored to match the behavior of `dotenv.config({ quiet: true })`.
    }
  }
@@ -1124,15 +1124,15 @@ function migrateExperimentalSettings(
    };
    let modified = false;

-    const migrateExperimental = <T = Record<string, unknown>>(
+    const migrateExperimental = (
      oldKey: string,
-      migrateFn: (oldValue: T) => void,
+      migrateFn: (oldValue: Record<string, unknown>) => void,
    ) => {
      const old = experimentalSettings[oldKey];
-      if (old !== undefined) {
+      if (old) {
        foundDeprecated?.push(`experimental.${oldKey}`);
        // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-        migrateFn(old as T);
+        migrateFn(old as Record<string, unknown>);
        modified = true;
      }
    };
@@ -1197,24 +1197,6 @@ function migrateExperimentalSettings(
      agentsOverrides['cli_help'] = override;
    });

-    // Migrate experimental.plan -> general.plan.enabled
-    migrateExperimental<boolean>('plan', (planValue) => {
-      const generalSettings =
-        (settings.general as Record<string, unknown> | undefined) || {};
-      const newGeneral = { ...generalSettings };
-      const planSettings =
-        // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-        (newGeneral['plan'] as Record<string, unknown> | undefined) || {};
-      const newPlan = { ...planSettings };
-
-      if (newPlan['enabled'] === undefined) {
-        newPlan['enabled'] = planValue;
-        newGeneral['plan'] = newPlan;
-        loadedSettings.setValue(scope, 'general', newGeneral);
-        modified = true;
-      }
-    });
-
    if (modified) {
      agentsSettings['overrides'] = agentsOverrides;
      loadedSettings.setValue(scope, 'agents', agentsSettings);
@@ -1223,7 +1205,6 @@ function migrateExperimentalSettings(
        const newExperimental = { ...experimentalSettings };
        delete newExperimental['codebaseInvestigatorSettings'];
        delete newExperimental['cliHelpAgentSettings'];
-        delete newExperimental['plan'];
        loadedSettings.setValue(scope, 'experimental', newExperimental);
      }
      return true;
@@ -87,7 +87,7 @@ describe('SettingsSchema', () => {
      const definition = getSettingsSchema().ui?.properties?.loadingPhrases;
      expect(definition).toBeDefined();
      expect(definition?.type).toBe('enum');
-      expect(definition?.default).toBe('off');
+      expect(definition?.default).toBe('tips');
      expect(definition?.options?.map((o) => o.value)).toEqual([
        'tips',
        'witty',
@@ -418,17 +418,14 @@ describe('SettingsSchema', () => {
    });

    it('should have plan setting in schema', () => {
-      const setting =
-        getSettingsSchema().general.properties.plan.properties.enabled;
+      const setting = getSettingsSchema().experimental.properties.plan;
      expect(setting).toBeDefined();
      expect(setting.type).toBe('boolean');
-      expect(setting.category).toBe('General');
+      expect(setting.category).toBe('Experimental');
      expect(setting.default).toBe(true);
      expect(setting.requiresRestart).toBe(true);
      expect(setting.showInDialog).toBe(true);
-      expect(setting.description).toBe(
-        'Enable Plan Mode for read-only safety during planning.',
-      );
+      expect(setting.description).toBe('Enable Plan Mode.');
    });

    it('should have hooksConfig.notifications setting in schema', () => {
@@ -505,31 +502,6 @@ describe('SettingsSchema', () => {
        'The model to use for the classifier. Only tested on `gemma3-1b-gpu-custom`.',
      );
    });
-
-    it('should have adk setting in schema', () => {
-      const adk = getSettingsSchema().experimental.properties.adk;
-      expect(adk).toBeDefined();
-      expect(adk.type).toBe('object');
-      expect(adk.category).toBe('Experimental');
-      expect(adk.default).toEqual({});
-      expect(adk.requiresRestart).toBe(true);
-      expect(adk.showInDialog).toBe(false);
-      expect(adk.description).toBe(
-        'Settings for the Agent Development Kit (ADK).',
-      );
-
-      const agentSessionNoninteractiveEnabled =
-        adk.properties.agentSessionNoninteractiveEnabled;
-      expect(agentSessionNoninteractiveEnabled).toBeDefined();
-      expect(agentSessionNoninteractiveEnabled.type).toBe('boolean');
-      expect(agentSessionNoninteractiveEnabled.category).toBe('Experimental');
-      expect(agentSessionNoninteractiveEnabled.default).toBe(false);
-      expect(agentSessionNoninteractiveEnabled.requiresRestart).toBe(true);
-      expect(agentSessionNoninteractiveEnabled.showInDialog).toBe(false);
-      expect(agentSessionNoninteractiveEnabled.description).toBe(
-        'Enable non-interactive agent sessions.',
-      );
-    });
  });

  it('has JSON schema definitions for every referenced ref', () => {
@@ -293,16 +293,6 @@ const SETTINGS_SCHEMA = {
        description: 'Planning features configuration.',
        showInDialog: false,
        properties: {
-          enabled: {
-            type: 'boolean',
-            label: 'Enable Plan Mode',
-            category: 'General',
-            requiresRestart: true,
-            default: true,
-            description:
-              'Enable Plan Mode for read-only safety during planning.',
-            showInDialog: true,
-          },
          directory: {
            type: 'string',
            label: 'Plan Directory',
@@ -571,16 +561,6 @@ const SETTINGS_SCHEMA = {
        description: 'Show the "? for shortcuts" hint above the input.',
        showInDialog: true,
      },
-      compactToolOutput: {
-        type: 'boolean',
-        label: 'Compact Tool Output',
-        category: 'UI',
-        requiresRestart: false,
-        default: false,
-        description:
-          'Display tool outputs (like directory listings and file reads) in a compact, structured format.',
-        showInDialog: true,
-      },
      hideBanner: {
        type: 'boolean',
        label: 'Hide Banner',
@@ -776,9 +756,9 @@ const SETTINGS_SCHEMA = {
        label: 'Loading Phrases',
        category: 'UI',
        requiresRestart: false,
-        default: 'off',
+        default: 'tips',
        description:
-          'What to show while the model is working: tips, witty comments, all, or off.',
+          'What to show while the model is working: tips, witty comments, both, or nothing.',
        showInDialog: true,
        options: [
          { value: 'tips', label: 'Tips' },
@@ -1478,21 +1458,6 @@ const SETTINGS_SCHEMA = {
            `,
            showInDialog: true,
          },
-          backgroundCompletionBehavior: {
-            type: 'enum',
-            label: 'Background Completion Behavior',
-            category: 'Tools',
-            requiresRestart: false,
-            default: 'silent',
-            description:
-              "Controls what happens when a background shell command finishes. 'silent' (default): quietly exits in background. 'inject': automatically returns output to agent. 'notify': shows brief message in chat.",
-            showInDialog: false,
-            options: [
-              { label: 'Silent', value: 'silent' },
-              { label: 'Inject', value: 'inject' },
-              { label: 'Notify', value: 'notify' },
-            ],
-          },
          pager: {
            type: 'string',
            label: 'Pager',
@@ -1887,7 +1852,7 @@ const SETTINGS_SCHEMA = {
        label: 'Auto Configure Max Old Space Size',
        category: 'Advanced',
        requiresRestart: true,
-        default: true,
+        default: false,
        description: 'Automatically configure Node.js memory limits',
        showInDialog: true,
      },
@@ -1933,22 +1898,54 @@ const SETTINGS_SCHEMA = {
    description: 'Setting to enable experimental features',
    showInDialog: false,
    properties: {
-      adk: {
+      toolOutputMasking: {
        type: 'object',
-        label: 'ADK',
+        label: 'Tool Output Masking',
        category: 'Experimental',
        requiresRestart: true,
+        ignoreInDocs: false,
        default: {},
-        description: 'Settings for the Agent Development Kit (ADK).',
+        description:
+          'Advanced settings for tool output masking to manage context window efficiency.',
        showInDialog: false,
        properties: {
-          agentSessionNoninteractiveEnabled: {
+          enabled: {
            type: 'boolean',
-            label: 'Agent Session Non-interactive Enabled',
+            label: 'Enable Tool Output Masking',
            category: 'Experimental',
            requiresRestart: true,
-            default: false,
-            description: 'Enable non-interactive agent sessions.',
+            default: true,
+            description: 'Enables tool output masking to save tokens.',
+            showInDialog: true,
+          },
+          toolProtectionThreshold: {
+            type: 'number',
+            label: 'Tool Protection Threshold',
+            category: 'Experimental',
+            requiresRestart: true,
+            default: 50000,
+            description:
+              'Minimum number of tokens to protect from masking (most recent tool outputs).',
+            showInDialog: false,
+          },
+          minPrunableTokensThreshold: {
+            type: 'number',
+            label: 'Min Prunable Tokens Threshold',
+            category: 'Experimental',
+            requiresRestart: true,
+            default: 30000,
+            description:
+              'Minimum prunable tokens required to trigger a masking pass.',
+            showInDialog: false,
+          },
+          protectLatestTurn: {
+            type: 'boolean',
+            label: 'Protect Latest Turn',
+            category: 'Experimental',
+            requiresRestart: true,
+            default: true,
+            description:
+              'Ensures the absolute latest turn is never masked, regardless of token count.',
            showInDialog: false,
          },
        },
@@ -2024,7 +2021,7 @@ const SETTINGS_SCHEMA = {
        label: 'JIT Context Loading',
        category: 'Experimental',
        requiresRestart: true,
-        default: false,
+        default: true,
        description: 'Enable Just-In-Time (JIT) context loading.',
        showInDialog: false,
      },
@@ -2048,6 +2045,15 @@ const SETTINGS_SCHEMA = {
          'Use OSC 52 for copying. This may be more robust than the default system when using remote terminal sessions (if your terminal is configured to allow it).',
        showInDialog: true,
      },
+      plan: {
+        type: 'boolean',
+        label: 'Plan',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: true,
+        description: 'Enable Plan Mode.',
+        showInDialog: true,
+      },
      taskTracker: {
        type: 'boolean',
        label: 'Task Tracker',
@@ -2148,13 +2154,44 @@ const SETTINGS_SCHEMA = {
          'Replace the built-in save_memory tool with a memory manager subagent that supports adding, removing, de-duplicating, and organizing memories.',
        showInDialog: true,
      },
-      contextManagement: {
+      agentHistoryTruncation: {
        type: 'boolean',
-        label: 'Enable Context Management',
+        label: 'Agent History Truncation',
        category: 'Experimental',
        requiresRestart: true,
        default: false,
-        description: 'Enable logic for context management.',
+        description:
+          'Enable truncation window logic for the Agent History Provider.',
+        showInDialog: true,
+      },
+      agentHistoryTruncationThreshold: {
+        type: 'number',
+        label: 'Agent History Truncation Threshold',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: 30,
+        description:
+          'The maximum number of messages before history is truncated.',
+        showInDialog: true,
+      },
+      agentHistoryRetainedMessages: {
+        type: 'number',
+        label: 'Agent History Retained Messages',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: 15,
+        description:
+          'The number of recent messages to retain after truncation.',
+        showInDialog: true,
+      },
+      agentHistorySummarization: {
+        type: 'boolean',
+        label: 'Agent History Summarization',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: false,
+        description:
+          'Enable summarization of truncated content via a small model for the Agent History Provider.',
        showInDialog: true,
      },
      topicUpdateNarration: {
@@ -2433,171 +2470,6 @@ const SETTINGS_SCHEMA = {
    },
  },

-  contextManagement: {
-    type: 'object',
-    label: 'Context Management',
-    category: 'Experimental',
-    requiresRestart: true,
-    default: {},
-    description:
-      'Settings for agent history and tool distillation context management.',
-    showInDialog: false,
-    properties: {
-      historyWindow: {
-        type: 'object',
-        label: 'History Window Settings',
-        category: 'Context Management',
-        requiresRestart: true,
-        default: {},
-        showInDialog: false,
-        properties: {
-          maxTokens: {
-            type: 'number',
-            label: 'Max Tokens',
-            category: 'Context Management',
-            requiresRestart: true,
-            default: 150_000,
-            description:
-              'The number of tokens to allow before triggering compression.',
-            showInDialog: false,
-          },
-          retainedTokens: {
-            type: 'number',
-            label: 'Retained Tokens',
-            category: 'Context Management',
-            requiresRestart: true,
-            default: 40_000,
-            description: 'The number of tokens to always retain.',
-            showInDialog: false,
-          },
-        },
-      },
-      messageLimits: {
-        type: 'object',
-        label: 'Message Limits',
-        category: 'Context Management',
-        requiresRestart: true,
-        default: {},
-        showInDialog: false,
-        properties: {
-          normalMaxTokens: {
-            type: 'number',
-            label: 'Normal Maximum Tokens',
-            category: 'Context Management',
-            requiresRestart: true,
-            default: 2500,
-            description:
-              'The target number of tokens to budget for a normal conversation turn.',
-            showInDialog: false,
-          },
-          retainedMaxTokens: {
-            type: 'number',
-            label: 'Retained Maximum Tokens',
-            category: 'Context Management',
-            requiresRestart: true,
-            default: 12000,
-            description:
-              'The maximum number of tokens a single conversation turn can consume before truncation.',
-            showInDialog: false,
-          },
-          normalizationHeadRatio: {
-            type: 'number',
-            label: 'Normalization Head Ratio',
-            category: 'Context Management',
-            requiresRestart: true,
-            default: 0.25,
-            description:
-              'The ratio of tokens to retain from the beginning of a truncated message (0.0 to 1.0).',
-            showInDialog: false,
-          },
-        },
-      },
-      tools: {
-        type: 'object',
-        label: 'Context Management Tools',
-        category: 'Context Management',
-        requiresRestart: true,
-        default: {},
-        showInDialog: false,
-        properties: {
-          distillation: {
-            type: 'object',
-            label: 'Tool Distillation',
-            category: 'Context Management',
-            requiresRestart: true,
-            default: {},
-            showInDialog: false,
-            properties: {
-              maxOutputTokens: {
-                type: 'number',
-                label: 'Max Output Tokens',
-                category: 'Context Management',
-                requiresRestart: true,
-                default: 10_000,
-                description:
-                  'Maximum tokens to show to the model when truncating large tool outputs.',
-                showInDialog: false,
-              },
-              summarizationThresholdTokens: {
-                type: 'number',
-                label: 'Tool Summarization Threshold',
-                category: 'Context Management',
-                requiresRestart: true,
-                default: 20_000,
-                description:
-                  'Threshold above which truncated tool outputs will be summarized by an LLM.',
-                showInDialog: false,
-              },
-            },
-          },
-          outputMasking: {
-            type: 'object',
-            label: 'Tool Output Masking',
-            category: 'Context Management',
-            requiresRestart: true,
-            ignoreInDocs: false,
-            default: {},
-            description:
-              'Advanced settings for tool output masking to manage context window efficiency.',
-            showInDialog: false,
-            properties: {
-              protectionThresholdTokens: {
-                type: 'number',
-                label: 'Tool Protection Threshold (Tokens)',
-                category: 'Context Management',
-                requiresRestart: true,
-                default: 50_000,
-                description:
-                  'Minimum number of tokens to protect from masking (most recent tool outputs).',
-                showInDialog: false,
-              },
-              minPrunableThresholdTokens: {
-                type: 'number',
-                label: 'Min Prunable Tokens Threshold',
-                category: 'Context Management',
-                requiresRestart: true,
-                default: 30_000,
-                description:
-                  'Minimum prunable tokens required to trigger a masking pass.',
-                showInDialog: false,
-              },
-              protectLatestTurn: {
-                type: 'boolean',
-                label: 'Protect Latest Turn',
-                category: 'Context Management',
-                requiresRestart: true,
-                default: true,
-                description:
-                  'Ensures the absolute latest turn is never masked, regardless of token count.',
-                showInDialog: false,
-              },
-            },
-          },
-        },
-      },
-    },
-  },
-
  admin: {
    type: 'object',
    label: 'Admin',
@@ -46,7 +46,6 @@ import { TerminalProvider } from './ui/contexts/TerminalContext.js';
 import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
 import { OverflowProvider } from './ui/contexts/OverflowContext.js';
 import { profiler } from './ui/components/DebugProfiler.js';
-import { initializeConsoleStore } from './ui/hooks/useConsoleMessages.js';

 const SLOW_RENDER_MS = 200;

@@ -58,7 +57,6 @@ export async function startInteractiveUI(
  resumedSessionData: ResumedSessionData | undefined,
  initializationResult: InitializationResult,
 ) {
-  initializeConsoleStore();
  // Never enter Ink alternate buffer mode when screen reader mode is enabled
  // as there is no benefit of alternate buffer mode when using a screen reader
  // and the Ink alternate buffer mode requires line wrapping harmful to
@@ -1712,7 +1712,7 @@ describe('runNonInteractive', () => {
          input,
          prompt_id: promptId,
        });
-      } catch {
+      } catch (_error) {
        // Expected exit
      }

@@ -56,7 +56,7 @@ import { themeCommand } from '../ui/commands/themeCommand.js';
 import { toolsCommand } from '../ui/commands/toolsCommand.js';
 import { skillsCommand } from '../ui/commands/skillsCommand.js';
 import { settingsCommand } from '../ui/commands/settingsCommand.js';
-import { tasksCommand } from '../ui/commands/tasksCommand.js';
+import { shellsCommand } from '../ui/commands/shellsCommand.js';
 import { vimCommand } from '../ui/commands/vimCommand.js';
 import { setupGithubCommand } from '../ui/commands/setupGithubCommand.js';
 import { terminalSetupCommand } from '../ui/commands/terminalSetupCommand.js';
@@ -221,7 +221,7 @@ export class BuiltinCommandLoader implements ICommandLoader {
          : [skillsCommand]
        : []),
      settingsCommand,
-      tasksCommand,
+      shellsCommand,
      vimCommand,
      setupGithubCommand,
      terminalSetupCommand,
@@ -61,7 +61,6 @@ export const createMockCommandContext = (
      toggleCorgiMode: vi.fn(),
      toggleShortcutsHelp: vi.fn(),
      toggleVimEnabled: vi.fn(),
-      reloadCommands: vi.fn(),
      openAgentConfigDialog: vi.fn(),
      closeAgentConfigDialog: vi.fn(),
      extensionsUpdateState: new Map(),
@@ -38,7 +38,6 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
      fireSessionEndEvent: vi.fn().mockResolvedValue(undefined),
      fireSessionStartEvent: vi.fn().mockResolvedValue(undefined),
    })),
-    isMemoryManagerEnabled: vi.fn(() => false),
    getListExtensions: vi.fn(() => false),
    getExtensions: vi.fn(() => []),
    getListSessions: vi.fn(() => false),
@@ -195,17 +194,6 @@ export function createMockSettings(
    user: { settings: {} },
    workspace: { settings: {} },
    errors: [],
-    subscribe: vi.fn().mockReturnValue(() => {}),
-    getSnapshot: vi.fn().mockReturnValue({
-      system: { settings: {} },
-      systemDefaults: { settings: {} },
-      user: { settings: {} },
-      workspace: { settings: {} },
-      isTrusted: true,
-      errors: [],
-      merged,
-    }),
-    setValue: vi.fn(),
    ...overrides,
    merged,
  } as unknown as LoadedSettings;
@@ -42,7 +42,6 @@ import {
  type OverflowState,
 } from '../ui/contexts/OverflowContext.js';

-import { makeFakeConfig } from '@google/gemini-cli-core';
 import { type Config } from '@google/gemini-cli-core';
 import { FakePersistentState } from './persistentStateFake.js';
 import { AppContext, type AppState } from '../ui/contexts/AppContext.js';
@@ -52,6 +51,7 @@ import { themeManager, DEFAULT_THEME } from '../ui/themes/theme-manager.js';
 import { DefaultLight } from '../ui/themes/builtin/light/default-light.js';
 import { pickDefaultThemeName } from '../ui/themes/theme.js';
 import { generateSvgForTerminal } from './svg.js';
+import { loadCliConfig, type CliArgs } from '../config/config.js';

 export const persistentStateMock = new FakePersistentState();

@@ -506,8 +506,8 @@ const baseMockUiState = {
  cleanUiDetailsVisible: false,
  allowPlanMode: true,
  activePtyId: undefined,
-  backgroundTasks: new Map(),
-  backgroundTaskHeight: 0,
+  backgroundShells: new Map(),
+  backgroundShellHeight: 0,
  quota: {
    userTier: undefined,
    stats: undefined,
@@ -579,9 +579,9 @@ const mockUIActions: UIActions = {
  revealCleanUiDetailsTemporarily: vi.fn(),
  handleWarning: vi.fn(),
  setEmbeddedShellFocused: vi.fn(),
-  dismissBackgroundTask: vi.fn(),
-  setActiveBackgroundTaskPid: vi.fn(),
-  setIsBackgroundTaskListOpen: vi.fn(),
+  dismissBackgroundShell: vi.fn(),
+  setActiveBackgroundShellPid: vi.fn(),
+  setIsBackgroundShellListOpen: vi.fn(),
  setAuthContext: vi.fn(),
  onHintInput: vi.fn(),
  onHintBackspace: vi.fn(),
@@ -613,7 +613,6 @@ export const renderWithProviders = async (
    mouseEventsEnabled = false,
    config,
    uiActions,
-    toolActions,
    persistentState,
    appState = mockAppState,
  }: {
@@ -624,11 +623,6 @@ export const renderWithProviders = async (
    mouseEventsEnabled?: boolean;
    config?: Config;
    uiActions?: Partial<UIActions>;
-    toolActions?: Partial<{
-      isExpanded: (callId: string) => boolean;
-      toggleExpansion: (callId: string) => void;
-      toggleAllExpansion: (callIds: string[]) => void;
-    }>;
    persistentState?: {
      get?: typeof persistentStateMock.get;
      set?: typeof persistentStateMock.set;
@@ -666,11 +660,12 @@ export const renderWithProviders = async (
  const terminalWidth = width ?? baseState.terminalWidth;

  if (!config) {
-    config = makeFakeConfig({
-      useAlternateBuffer: settings.merged.ui?.useAlternateBuffer,
-      showMemoryUsage: settings.merged.ui?.showMemoryUsage,
-      accessibility: settings.merged.ui?.accessibility,
-    });
+    config = await loadCliConfig(
+      settings.merged,
+      'random-session-id',
+      {} as unknown as CliArgs,
+      { cwd: '/' },
+    );
  }

  const mainAreaWidth = providedUiState?.mainAreaWidth ?? terminalWidth;
@@ -715,16 +710,6 @@ export const renderWithProviders = async (
                        <ToolActionsProvider
                          config={config}
                          toolCalls={allToolCalls}
-                          isExpanded={
-                            toolActions?.isExpanded ??
-                            vi.fn().mockReturnValue(false)
-                          }
-                          toggleExpansion={
-                            toolActions?.toggleExpansion ?? vi.fn()
-                          }
-                          toggleAllExpansion={
-                            toolActions?.toggleAllExpansion ?? vi.fn()
-                          }
                        >
                          <AskUserActionsProvider
                            request={null}
@@ -88,7 +88,7 @@ describe('App', () => {
      defaultText: 'Mock Banner Text',
      warningText: '',
    },
-    backgroundTasks: new Map(),
+    backgroundShells: new Map(),
  };

  it('should render main content and composer when not quitting', async () => {
@@ -328,13 +328,13 @@ describe('AppContainer State Management', () => {
    handleApprovalModeChange: vi.fn(),
    activePtyId: null,
    loopDetectionConfirmationRequest: null,
-    backgroundTaskCount: 0,
-    isBackgroundTaskVisible: false,
-    toggleBackgroundTasks: vi.fn(),
-    backgroundCurrentExecution: vi.fn(),
-    backgroundTasks: new Map(),
-    registerBackgroundTask: vi.fn(),
-    dismissBackgroundTask: vi.fn(),
+    backgroundShellCount: 0,
+    isBackgroundShellVisible: false,
+    toggleBackgroundShell: vi.fn(),
+    backgroundCurrentShell: vi.fn(),
+    backgroundShells: new Map(),
+    registerBackgroundShell: vi.fn(),
+    dismissBackgroundShell: vi.fn(),
  };

  beforeEach(() => {
@@ -2257,13 +2257,13 @@ describe('AppContainer State Management', () => {
      });

      it('should focus background shell on Tab when already visible (not toggle it off)', async () => {
-        const mockToggleBackgroundTask = vi.fn();
+        const mockToggleBackgroundShell = vi.fn();
        mockedUseGeminiStream.mockReturnValue({
          ...DEFAULT_GEMINI_STREAM_MOCK,
          activePtyId: null,
-          isBackgroundTaskVisible: true,
-          backgroundTasks: new Map([[123, { pid: 123, status: 'running' }]]),
-          toggleBackgroundTasks: mockToggleBackgroundTask,
+          isBackgroundShellVisible: true,
+          backgroundShells: new Map([[123, { pid: 123, status: 'running' }]]),
+          toggleBackgroundShell: mockToggleBackgroundShell,
        });

        await setupKeypressTest();
@@ -2277,7 +2277,7 @@ describe('AppContainer State Management', () => {
        // Should be focused
        expect(capturedUIState.embeddedShellFocused).toBe(true);
        // Should NOT have toggled (closed) the shell
-        expect(mockToggleBackgroundTask).not.toHaveBeenCalled();
+        expect(mockToggleBackgroundShell).not.toHaveBeenCalled();

        unmount();
      });
@@ -2285,13 +2285,13 @@ describe('AppContainer State Management', () => {

    describe('Background Shell Toggling (CTRL+B)', () => {
      it('should toggle background shell on Ctrl+B even if visible but not focused', async () => {
-        const mockToggleBackgroundTask = vi.fn();
+        const mockToggleBackgroundShell = vi.fn();
        mockedUseGeminiStream.mockReturnValue({
          ...DEFAULT_GEMINI_STREAM_MOCK,
          activePtyId: null,
-          isBackgroundTaskVisible: true,
-          backgroundTasks: new Map([[123, { pid: 123, status: 'running' }]]),
-          toggleBackgroundTasks: mockToggleBackgroundTask,
+          isBackgroundShellVisible: true,
+          backgroundShells: new Map([[123, { pid: 123, status: 'running' }]]),
+          toggleBackgroundShell: mockToggleBackgroundShell,
        });

        await setupKeypressTest();
@@ -2303,7 +2303,7 @@ describe('AppContainer State Management', () => {
        pressKey('\x02');

        // Should have toggled (closed) the shell
-        expect(mockToggleBackgroundTask).toHaveBeenCalled();
+        expect(mockToggleBackgroundShell).toHaveBeenCalled();
        // Should be unfocused
        expect(capturedUIState.embeddedShellFocused).toBe(false);

@@ -2311,28 +2311,28 @@ describe('AppContainer State Management', () => {
      });

      it('should show and focus background shell on Ctrl+B if hidden', async () => {
-        const mockToggleBackgroundTask = vi.fn();
+        const mockToggleBackgroundShell = vi.fn();
        const geminiStreamMock = {
          ...DEFAULT_GEMINI_STREAM_MOCK,
          activePtyId: null,
-          isBackgroundTaskVisible: false,
-          backgroundTasks: new Map([[123, { pid: 123, status: 'running' }]]),
-          toggleBackgroundTasks: mockToggleBackgroundTask,
+          isBackgroundShellVisible: false,
+          backgroundShells: new Map([[123, { pid: 123, status: 'running' }]]),
+          toggleBackgroundShell: mockToggleBackgroundShell,
        };
        mockedUseGeminiStream.mockReturnValue(geminiStreamMock);

        await setupKeypressTest();

        // Update the mock state when toggled to simulate real behavior
-        mockToggleBackgroundTask.mockImplementation(() => {
-          geminiStreamMock.isBackgroundTaskVisible = true;
+        mockToggleBackgroundShell.mockImplementation(() => {
+          geminiStreamMock.isBackgroundShellVisible = true;
        });

        // Press Ctrl+B
        pressKey('\x02');

        // Should have toggled (shown) the shell
-        expect(mockToggleBackgroundTask).toHaveBeenCalled();
+        expect(mockToggleBackgroundShell).toHaveBeenCalled();
        // Should be focused
        expect(capturedUIState.embeddedShellFocused).toBe(true);

@@ -83,7 +83,6 @@ import {
  logBillingEvent,
  ApiKeyUpdatedEvent,
  type InjectionSource,
-  startMemoryService,
 } from '@google/gemini-cli-core';
 import { validateAuthMethod } from '../config/auth.js';
 import process from 'node:process';
@@ -111,7 +110,7 @@ import { computeTerminalTitle } from '../utils/windowTitle.js';
 import { useTextBuffer } from './components/shared/text-buffer.js';
 import { useLogger } from './hooks/useLogger.js';
 import { useGeminiStream } from './hooks/useGeminiStream.js';
-import { type BackgroundTask } from './hooks/useExecutionLifecycle.js';
+import { type BackgroundShell } from './hooks/shellCommandProcessor.js';
 import { useVim } from './hooks/vim.js';
 import { type LoadableSettingScope, SettingScope } from '../config/settings.js';
 import { type InitializationResult } from '../core/initializer.js';
@@ -152,7 +151,7 @@ import { useInputHistoryStore } from './hooks/useInputHistoryStore.js';
 import { useBanner } from './hooks/useBanner.js';
 import { useTerminalSetupPrompt } from './utils/terminalSetup.js';
 import { useHookDisplayState } from './hooks/useHookDisplayState.js';
-import { useBackgroundTaskManager } from './hooks/useBackgroundTaskManager.js';
+import { useBackgroundShellManager } from './hooks/useBackgroundShellManager.js';
 import {
  WARNING_PROMPT_DURATION_MS,
  QUEUE_ERROR_DISPLAY_DURATION_MS,
@@ -169,7 +168,6 @@ import { useSuspend } from './hooks/useSuspend.js';
 import { useRunEventNotifications } from './hooks/useRunEventNotifications.js';
 import { isNotificationsEnabled } from '../utils/terminalNotifications.js';
 import {
-  getLastTurnToolCallIds,
  isToolExecuting,
  isToolAwaitingConfirmation,
  getAllToolCalls,
@@ -234,45 +232,12 @@ export const AppContainer = (props: AppContainerProps) => {
  );
  const [copyModeEnabled, setCopyModeEnabled] = useState(false);
  const [pendingRestorePrompt, setPendingRestorePrompt] = useState(false);
-  const toggleBackgroundTasksRef = useRef<() => void>(() => {});
-  const isBackgroundTaskVisibleRef = useRef<boolean>(false);
-  const backgroundTasksRef = useRef<Map<number, BackgroundTask>>(new Map());
+  const toggleBackgroundShellRef = useRef<() => void>(() => {});
+  const isBackgroundShellVisibleRef = useRef<boolean>(false);
+  const backgroundShellsRef = useRef<Map<number, BackgroundShell>>(new Map());

  const [adminSettingsChanged, setAdminSettingsChanged] = useState(false);

-  const [expandedTools, setExpandedTools] = useState<Set<string>>(new Set());
-
-  const toggleExpansion = useCallback((callId: string) => {
-    setExpandedTools((prev) => {
-      const next = new Set(prev);
-      if (next.has(callId)) {
-        next.delete(callId);
-      } else {
-        next.add(callId);
-      }
-      return next;
-    });
-  }, []);
-
-  const toggleAllExpansion = useCallback((callIds: string[]) => {
-    setExpandedTools((prev) => {
-      const next = new Set(prev);
-      const anyCollapsed = callIds.some((id) => !next.has(id));
-
-      if (anyCollapsed) {
-        callIds.forEach((id) => next.add(id));
-      } else {
-        callIds.forEach((id) => next.delete(id));
-      }
-      return next;
-    });
-  }, []);
-
-  const isExpanded = useCallback(
-    (callId: string) => expandedTools.has(callId),
-    [expandedTools],
-  );
-
  const [shellModeActive, setShellModeActive] = useState(false);
  const [modelSwitchedFromQuotaError, setModelSwitchedFromQuotaError] =
    useState<boolean>(false);
@@ -448,13 +413,6 @@ export const AppContainer = (props: AppContainerProps) => {
      setConfigInitialized(true);
      startupProfiler.flush(config);

-      // Fire-and-forget memory service (skill extraction from past sessions)
-      if (config.isMemoryManagerEnabled()) {
-        startMemoryService(config).catch((e) => {
-          debugLogger.error('Failed to start memory service:', e);
-        });
-      }
-
      const sessionStartSource = resumedSessionData
        ? SessionStartSource.Resume
        : SessionStartSource.Startup;
@@ -496,7 +454,7 @@ export const AppContainer = (props: AppContainerProps) => {

      // Kill all background shells
      await Promise.all(
-        Array.from(backgroundTasksRef.current.keys()).map((pid) =>
+        Array.from(backgroundShellsRef.current.keys()).map((pid) =>
          ShellExecutionService.kill(pid),
        ),
      );
@@ -907,7 +865,7 @@ Logging in with Google... Restarting Gemini CLI to continue.

  const { toggleVimEnabled } = useVimMode();

-  const setIsBackgroundTaskListOpenRef = useRef<(open: boolean) => void>(
+  const setIsBackgroundShellListOpenRef = useRef<(open: boolean) => void>(
    () => {},
  );
  const [shortcutsHelpVisible, setShortcutsHelpVisible] = useState(false);
@@ -942,14 +900,14 @@ Logging in with Google... Restarting Gemini CLI to continue.
      toggleDebugProfiler,
      dispatchExtensionStateUpdate,
      addConfirmUpdateExtensionRequest,
-      toggleBackgroundTasks: () => {
-        toggleBackgroundTasksRef.current();
-        if (!isBackgroundTaskVisibleRef.current) {
+      toggleBackgroundShell: () => {
+        toggleBackgroundShellRef.current();
+        if (!isBackgroundShellVisibleRef.current) {
          setEmbeddedShellFocused(true);
-          if (backgroundTasksRef.current.size > 1) {
-            setIsBackgroundTaskListOpenRef.current(true);
+          if (backgroundShellsRef.current.size > 1) {
+            setIsBackgroundShellListOpenRef.current(true);
          } else {
-            setIsBackgroundTaskListOpenRef.current(false);
+            setIsBackgroundShellListOpenRef.current(false);
          }
        }
      },
@@ -1035,7 +993,6 @@ Logging in with Google... Restarting Gemini CLI to continue.

      if (config.isJitContextEnabled()) {
        await config.getContextManager()?.refresh();
-        config.updateSystemInstructionIfInitialized();
        flattenedMemory = flattenMemory(config.getUserMemory());
        fileCount = config.getGeminiMdFileCount();
      } else {
@@ -1122,7 +1079,7 @@ Logging in with Google... Restarting Gemini CLI to continue.

  useEffect(() => {
    const hintListener = (text: string, source: InjectionSource) => {
-      if (source !== 'user_steering' && source !== 'background_completion') {
+      if (source !== 'user_steering') {
        return;
      }
      pendingHintsRef.current.push(text);
@@ -1146,12 +1103,12 @@ Logging in with Google... Restarting Gemini CLI to continue.
    activePtyId,
    loopDetectionConfirmationRequest,
    lastOutputTime,
-    backgroundTaskCount,
-    isBackgroundTaskVisible,
-    toggleBackgroundTasks,
-    backgroundCurrentExecution,
-    backgroundTasks,
-    dismissBackgroundTask,
+    backgroundShellCount,
+    isBackgroundShellVisible,
+    toggleBackgroundShell,
+    backgroundCurrentShell,
+    backgroundShells,
+    dismissBackgroundShell,
    retryStatus,
  } = useGeminiStream(
    config.getGeminiClient(),
@@ -1180,27 +1137,32 @@ Logging in with Google... Restarting Gemini CLI to continue.
    [pendingSlashCommandHistoryItems, pendingGeminiHistoryItems],
  );

-  toggleBackgroundTasksRef.current = toggleBackgroundTasks;
-  isBackgroundTaskVisibleRef.current = isBackgroundTaskVisible;
-  backgroundTasksRef.current = backgroundTasks;
+  const hasPendingToolConfirmation = useMemo(
+    () => isToolAwaitingConfirmation(pendingHistoryItems),
+    [pendingHistoryItems],
+  );
+
+  toggleBackgroundShellRef.current = toggleBackgroundShell;
+  isBackgroundShellVisibleRef.current = isBackgroundShellVisible;
+  backgroundShellsRef.current = backgroundShells;

  const {
-    activeBackgroundTaskPid,
-    setIsBackgroundTaskListOpen,
-    isBackgroundTaskListOpen,
-    setActiveBackgroundTaskPid,
-    backgroundTaskHeight,
-  } = useBackgroundTaskManager({
-    backgroundTasks,
-    backgroundTaskCount,
-    isBackgroundTaskVisible,
+    activeBackgroundShellPid,
+    setIsBackgroundShellListOpen,
+    isBackgroundShellListOpen,
+    setActiveBackgroundShellPid,
+    backgroundShellHeight,
+  } = useBackgroundShellManager({
+    backgroundShells,
+    backgroundShellCount,
+    isBackgroundShellVisible,
    activePtyId,
    embeddedShellFocused,
    setEmbeddedShellFocused,
    terminalHeight,
  });

-  setIsBackgroundTaskListOpenRef.current = setIsBackgroundTaskListOpen;
+  setIsBackgroundShellListOpenRef.current = setIsBackgroundShellListOpen;

  const lastOutputTimeRef = useRef(0);

@@ -1472,7 +1434,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
  // Compute available terminal height based on stable controls measurement
  const availableTerminalHeight = Math.max(
    0,
-    terminalHeight - stableControlsHeight - backgroundTaskHeight - 1,
+    terminalHeight - stableControlsHeight - backgroundShellHeight - 1,
  );

  config.setShellExecutionConfig({
@@ -1765,25 +1727,13 @@ Logging in with Google... Restarting Gemini CLI to continue.
        return true;
      }

-      const toggleLastTurnTools = () => {
-        triggerExpandHint(true);
-
-        const targetToolCallIds = getLastTurnToolCallIds(
-          historyManager.history,
-          pendingHistoryItems,
-        );
-
-        if (targetToolCallIds.length > 0) {
-          toggleAllExpansion(targetToolCallIds);
-        }
-      };
-
      let enteringConstrainHeightMode = false;
      if (!constrainHeight) {
        enteringConstrainHeightMode = true;
        setConstrainHeight(true);
        if (keyMatchers[Command.SHOW_MORE_LINES](key)) {
-          toggleLastTurnTools();
+          // If the user manually collapses the view, show the hint and reset the x-second timer.
+          triggerExpandHint(true);
        }
        if (!isAlternateBuffer) {
          refreshStatic();
@@ -1831,13 +1781,16 @@ Logging in with Google... Restarting Gemini CLI to continue.
        !enteringConstrainHeightMode
      ) {
        setConstrainHeight(false);
-        toggleLastTurnTools();
-        refreshStatic();
+        // If the user manually expands the view, show the hint and reset the x-second timer.
+        triggerExpandHint(true);
+        if (!isAlternateBuffer) {
+          refreshStatic();
+        }
        return true;
      } else if (
        (keyMatchers[Command.FOCUS_SHELL_INPUT](key) ||
          keyMatchers[Command.UNFOCUS_BACKGROUND_SHELL_LIST](key)) &&
-        (activePtyId || (isBackgroundTaskVisible && backgroundTasks.size > 0))
+        (activePtyId || (isBackgroundShellVisible && backgroundShells.size > 0))
      ) {
        if (embeddedShellFocused) {
          const capturedTime = lastOutputTimeRef.current;
@@ -1858,12 +1811,12 @@ Logging in with Google... Restarting Gemini CLI to continue.

        const isIdle = Date.now() - lastOutputTimeRef.current >= 100;

-        if (isIdle && !activePtyId && !isBackgroundTaskVisible) {
+        if (isIdle && !activePtyId && !isBackgroundShellVisible) {
          if (tabFocusTimeoutRef.current)
            clearTimeout(tabFocusTimeoutRef.current);
-          toggleBackgroundTasks();
+          toggleBackgroundShell();
          setEmbeddedShellFocused(true);
-          if (backgroundTasks.size > 1) setIsBackgroundTaskListOpen(true);
+          if (backgroundShells.size > 1) setIsBackgroundShellListOpen(true);
          return true;
        }

@@ -1880,15 +1833,15 @@ Logging in with Google... Restarting Gemini CLI to continue.
        return false;
      } else if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL](key)) {
        if (activePtyId) {
-          backgroundCurrentExecution();
+          backgroundCurrentShell();
          // After backgrounding, we explicitly do NOT show or focus the background UI.
        } else {
-          toggleBackgroundTasks();
+          toggleBackgroundShell();
          // Toggle focus based on intent: if we were hiding, unfocus; if showing, focus.
-          if (!isBackgroundTaskVisible && backgroundTasks.size > 0) {
+          if (!isBackgroundShellVisible && backgroundShells.size > 0) {
            setEmbeddedShellFocused(true);
-            if (backgroundTasks.size > 1) {
-              setIsBackgroundTaskListOpen(true);
+            if (backgroundShells.size > 1) {
+              setIsBackgroundShellListOpen(true);
            }
          } else {
            setEmbeddedShellFocused(false);
@@ -1896,11 +1849,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
        }
        return true;
      } else if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL_LIST](key)) {
-        if (backgroundTasks.size > 0 && isBackgroundTaskVisible) {
+        if (backgroundShells.size > 0 && isBackgroundShellVisible) {
          if (!embeddedShellFocused) {
            setEmbeddedShellFocused(true);
          }
-          setIsBackgroundTaskListOpen(true);
+          setIsBackgroundShellListOpen(true);
        }
        return true;
      }
@@ -1925,11 +1878,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
      tabFocusTimeoutRef,
      isAlternateBuffer,
      shortcutsHelpVisible,
-      backgroundCurrentExecution,
-      toggleBackgroundTasks,
-      backgroundTasks,
-      isBackgroundTaskVisible,
-      setIsBackgroundTaskListOpen,
+      backgroundCurrentShell,
+      toggleBackgroundShell,
+      backgroundShells,
+      isBackgroundShellVisible,
+      setIsBackgroundShellListOpen,
      lastOutputTimeRef,
      showTransientMessage,
      settings.merged.general.devtools,
@@ -1937,9 +1890,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      triggerExpandHint,
      keyMatchers,
      isHelpDismissKey,
-      historyManager.history,
-      pendingHistoryItems,
-      toggleAllExpansion,
    ],
  );

@@ -2083,11 +2033,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
    authState === AuthState.AwaitingApiKeyInput ||
    !!newAgents;

-  const hasPendingToolConfirmation = useMemo(
-    () => isToolAwaitingConfirmation(pendingHistoryItems),
-    [pendingHistoryItems],
-  );
-
  const hasConfirmUpdateExtensionRequests =
    confirmUpdateExtensionRequests.length > 0;
  const hasLoopDetectionConfirmationRequest =
@@ -2110,7 +2055,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
  const showStatusWit = loadingPhrases === 'witty' || loadingPhrases === 'all';

  const showLoadingIndicator =
-    (!embeddedShellFocused || isBackgroundTaskVisible) &&
+    (!embeddedShellFocused || isBackgroundShellVisible) &&
    streamingState === StreamingState.Responding &&
    !hasPendingActionRequired;

@@ -2368,8 +2313,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
      isRestarting,
      extensionsUpdateState,
      activePtyId,
-      backgroundTaskCount,
-      isBackgroundTaskVisible,
+      backgroundShellCount,
+      isBackgroundShellVisible,
      embeddedShellFocused,
      showDebugProfiler,
      customDialog,
@@ -2379,10 +2324,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
      bannerVisible,
      terminalBackgroundColor: config.getTerminalBackground(),
      settingsNonce,
-      backgroundTasks,
-      activeBackgroundTaskPid,
-      backgroundTaskHeight,
-      isBackgroundTaskListOpen,
+      backgroundShells,
+      activeBackgroundShellPid,
+      backgroundShellHeight,
+      isBackgroundShellListOpen,
      adminSettingsChanged,
      newAgents,
      showIsExpandableHint,
@@ -2491,8 +2436,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
      currentModel,
      extensionsUpdateState,
      activePtyId,
-      backgroundTaskCount,
-      isBackgroundTaskVisible,
+      backgroundShellCount,
+      isBackgroundShellVisible,
      historyManager,
      embeddedShellFocused,
      showDebugProfiler,
@@ -2505,10 +2450,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
      bannerVisible,
      config,
      settingsNonce,
-      backgroundTaskHeight,
-      isBackgroundTaskListOpen,
-      activeBackgroundTaskPid,
-      backgroundTasks,
+      backgroundShellHeight,
+      isBackgroundShellListOpen,
+      activeBackgroundShellPid,
+      backgroundShells,
      adminSettingsChanged,
      newAgents,
      showIsExpandableHint,
@@ -2568,9 +2513,9 @@ Logging in with Google... Restarting Gemini CLI to continue.
      revealCleanUiDetailsTemporarily,
      handleWarning,
      setEmbeddedShellFocused,
-      dismissBackgroundTask,
-      setActiveBackgroundTaskPid,
-      setIsBackgroundTaskListOpen,
+      dismissBackgroundShell,
+      setActiveBackgroundShellPid,
+      setIsBackgroundShellListOpen,
      setAuthContext,
      onHintInput: () => {},
      onHintBackspace: () => {},
@@ -2660,9 +2605,9 @@ Logging in with Google... Restarting Gemini CLI to continue.
      revealCleanUiDetailsTemporarily,
      handleWarning,
      setEmbeddedShellFocused,
-      dismissBackgroundTask,
-      setActiveBackgroundTaskPid,
-      setIsBackgroundTaskListOpen,
+      dismissBackgroundShell,
+      setActiveBackgroundShellPid,
+      setIsBackgroundShellListOpen,
      setAuthContext,
      setAccountSuspensionInfo,
      newAgents,
@@ -2694,13 +2639,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
              startupWarnings: props.startupWarnings || [],
            }}
          >
-            <ToolActionsProvider
-              config={config}
-              toolCalls={allToolCalls}
-              isExpanded={isExpanded}
-              toggleExpansion={toggleExpansion}
-              toggleAllExpansion={toggleAllExpansion}
-            >
+            <ToolActionsProvider config={config} toolCalls={allToolCalls}>
              <ShellFocusContext.Provider value={isFocused}>
                <App key={`app-${forceRerenderKey}`} />
              </ShellFocusContext.Provider>
@@ -65,7 +65,7 @@ const getSavedChatTags = async (
    );

    return chatDetails;
-  } catch {
+  } catch (_err) {
    return [];
  }
 };
@@ -75,7 +75,6 @@ const listCommand: SlashCommand = {
  description: 'List saved manual conversation checkpoints',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  takesArgs: false,
  action: async (context): Promise<void> => {
    const chatDetails = await getSavedChatTags(context, false);

@@ -407,24 +406,14 @@ export const chatResumeSubCommands: SlashCommand[] = [
  checkpointCompatibilityCommand,
 ];

-import { parseSlashCommand } from '../../utils/commands.js';
-
 export const chatCommand: SlashCommand = {
  name: 'chat',
  description: 'Browse auto-saved conversations and manage chat checkpoints',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  action: async (context, args) => {
-    if (args) {
-      const parsed = parseSlashCommand(`/${args}`, chatResumeSubCommands);
-      if (parsed.commandToExecute?.action) {
-        return parsed.commandToExecute.action(context, parsed.args);
-      }
-    }
-    return {
-      type: 'dialog',
-      dialog: 'sessionBrowser',
-    };
-  },
+  action: async () => ({
+    type: 'dialog',
+    dialog: 'sessionBrowser',
+  }),
  subCommands: chatResumeSubCommands,
 };
@@ -198,7 +198,7 @@ export const directoryCommand: SlashCommand = {
              alreadyAdded.push(trimmedPath);
              continue;
            }
-          } catch {
+          } catch (_e) {
            // Path might not exist or be inaccessible.
            // We'll let batchAddDirectories handle it later.
          }
@@ -321,7 +321,7 @@ async function exploreAction(
    });
    try {
      await open(extensionsUrl);
-    } catch {
+    } catch (_error) {
      context.ui.addItem({
        type: MessageType.ERROR,
        text: `Failed to open browser. Check out the extensions gallery at ${extensionsUrl}`,
@@ -789,7 +789,6 @@ const listExtensionsCommand: SlashCommand = {
  description: 'List active extensions',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  takesArgs: false,
  action: listAction,
 };

@@ -850,7 +849,6 @@ const exploreExtensionsCommand: SlashCommand = {
  description: 'Open extensions page in your browser',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  takesArgs: false,
  action: exploreAction,
 };

@@ -872,8 +870,6 @@ const configCommand: SlashCommand = {
  action: configAction,
 };

-import { parseSlashCommand } from '../../utils/commands.js';
-
 export function extensionsCommand(
  enableExtensionReloading?: boolean,
 ): SlashCommand {
@@ -887,29 +883,20 @@ export function extensionsCommand(
        configCommand,
      ]
    : [];
-  const subCommands = [
-    listExtensionsCommand,
-    updateExtensionsCommand,
-    exploreExtensionsCommand,
-    reloadCommand,
-    ...conditionalCommands,
-  ];
-
  return {
    name: 'extensions',
    description: 'Manage extensions',
    kind: CommandKind.BUILT_IN,
    autoExecute: false,
-    subCommands,
-    action: async (context, args) => {
-      if (args) {
-        const parsed = parseSlashCommand(`/${args}`, subCommands);
-        if (parsed.commandToExecute?.action) {
-          return parsed.commandToExecute.action(context, parsed.args);
-        }
-      }
+    subCommands: [
+      listExtensionsCommand,
+      updateExtensionsCommand,
+      exploreExtensionsCommand,
+      reloadCommand,
+      ...conditionalCommands,
+    ],
+    action: (context, args) =>
      // Default to list if no subcommand is provided
-      return listExtensionsCommand.action!(context, args);
-    },
+      listExtensionsCommand.action!(context, args),
  };
 }
@@ -17,7 +17,7 @@ import {
 } from '@google/gemini-cli-core';

 import type { CallableTool } from '@google/genai';
-import { MessageType, type HistoryItemMcpStatus } from '../types.js';
+import { MessageType } from '../types.js';

 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
  const actual =
@@ -280,41 +280,5 @@ describe('mcpCommand', () => {
        }),
      );
    });
-
-    it('should filter servers by name when an argument is provided to list', async () => {
-      await mcpCommand.action!(mockContext, 'list server1');
-
-      expect(mockContext.ui.addItem).toHaveBeenCalledWith(
-        expect.objectContaining({
-          type: MessageType.MCP_STATUS,
-          servers: expect.objectContaining({
-            server1: expect.any(Object),
-          }),
-        }),
-      );
-
-      // Should NOT contain server2 or server3
-      const call = vi.mocked(mockContext.ui.addItem).mock
-        .calls[0][0] as HistoryItemMcpStatus;
-      expect(Object.keys(call.servers)).toEqual(['server1']);
-    });
-
-    it('should filter servers by name and show descriptions when an argument is provided to desc', async () => {
-      await mcpCommand.action!(mockContext, 'desc server2');
-
-      expect(mockContext.ui.addItem).toHaveBeenCalledWith(
-        expect.objectContaining({
-          type: MessageType.MCP_STATUS,
-          showDescriptions: true,
-          servers: expect.objectContaining({
-            server2: expect.any(Object),
-          }),
-        }),
-      );
-
-      const call = vi.mocked(mockContext.ui.addItem).mock
-        .calls[0][0] as HistoryItemMcpStatus;
-      expect(Object.keys(call.servers)).toEqual(['server2']);
-    });
  });
 });
@@ -31,7 +31,6 @@ import {
  canLoadServer,
 } from '../../config/mcp/mcpServerEnablement.js';
 import { loadSettings } from '../../config/settings.js';
-import { parseSlashCommand } from '../../utils/commands.js';

 const authCommand: SlashCommand = {
  name: 'auth',
@@ -178,7 +177,6 @@ const listAction = async (
  context: CommandContext,
  showDescriptions = false,
  showSchema = false,
-  serverNameFilter?: string,
 ): Promise<void | MessageActionReturn> => {
  const agentContext = context.services.agentContext;
  const config = agentContext?.config;
@@ -201,25 +199,11 @@ const listAction = async (
    };
  }

-  let mcpServers = config.getMcpClientManager()?.getMcpServers() || {};
+  const mcpServers = config.getMcpClientManager()?.getMcpServers() || {};
+  const serverNames = Object.keys(mcpServers);
  const blockedMcpServers =
    config.getMcpClientManager()?.getBlockedMcpServers() || [];

-  if (serverNameFilter) {
-    const filter = serverNameFilter.trim().toLowerCase();
-    if (filter) {
-      mcpServers = Object.fromEntries(
-        Object.entries(mcpServers).filter(
-          ([name]) =>
-            name.toLowerCase().includes(filter) ||
-            normalizeServerId(name).includes(filter),
-        ),
-      );
-    }
-  }
-
-  const serverNames = Object.keys(mcpServers);
-
  const connectingServers = serverNames.filter(
    (name) => getMCPServerStatus(name) === MCPServerStatus.CONNECTING,
  );
@@ -322,7 +306,7 @@ const listCommand: SlashCommand = {
  description: 'List configured MCP servers and tools',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  action: (context, args) => listAction(context, false, false, args),
+  action: (context) => listAction(context),
 };

 const descCommand: SlashCommand = {
@@ -331,7 +315,7 @@ const descCommand: SlashCommand = {
  description: 'List configured MCP servers and tools with descriptions',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  action: (context, args) => listAction(context, true, false, args),
+  action: (context) => listAction(context, true),
 };

 const schemaCommand: SlashCommand = {
@@ -340,7 +324,7 @@ const schemaCommand: SlashCommand = {
    'List configured MCP servers and tools with descriptions and schemas',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  action: (context, args) => listAction(context, true, true, args),
+  action: (context) => listAction(context, true, true),
 };

 const reloadCommand: SlashCommand = {
@@ -349,7 +333,6 @@ const reloadCommand: SlashCommand = {
  description: 'Reloads MCP servers',
  kind: CommandKind.BUILT_IN,
  autoExecute: true,
-  takesArgs: false,
  action: async (
    context: CommandContext,
  ): Promise<void | SlashCommandActionReturn> => {
@@ -547,18 +530,5 @@ export const mcpCommand: SlashCommand = {
    enableCommand,
    disableCommand,
  ],
-  action: async (
-    context: CommandContext,
-    args: string,
-  ): Promise<void | SlashCommandActionReturn> => {
-    if (args) {
-      const parsed = parseSlashCommand(`/${args}`, mcpCommand.subCommands!);
-      if (parsed.commandToExecute?.action) {
-        return parsed.commandToExecute.action(context, parsed.args);
-      }
-      // If no subcommand matches, treat the whole args as a filter for list
-      return listAction(context, false, false, args);
-    }
-    return listAction(context);
-  },
+  action: async (context: CommandContext) => listAction(context),
 };
@@ -104,47 +104,6 @@ describe('planCommand', () => {
    );
  });

-  it('should not return a submit_prompt action if arguments are empty', async () => {
-    vi.mocked(
-      mockContext.services.agentContext!.config.isPlanEnabled,
-    ).mockReturnValue(true);
-    mockContext.invocation = {
-      raw: '/plan',
-      name: 'plan',
-      args: '',
-    };
-
-    if (!planCommand.action) throw new Error('Action missing');
-    const result = await planCommand.action(mockContext, '');
-
-    expect(result).toBeUndefined();
-    expect(
-      mockContext.services.agentContext!.config.setApprovalMode,
-    ).toHaveBeenCalledWith(ApprovalMode.PLAN);
-  });
-
-  it('should return a submit_prompt action if arguments are provided', async () => {
-    vi.mocked(
-      mockContext.services.agentContext!.config.isPlanEnabled,
-    ).mockReturnValue(true);
-    mockContext.invocation = {
-      raw: '/plan implement auth',
-      name: 'plan',
-      args: 'implement auth',
-    };
-
-    if (!planCommand.action) throw new Error('Action missing');
-    const result = await planCommand.action(mockContext, 'implement auth');
-
-    expect(result).toEqual({
-      type: 'submit_prompt',
-      content: 'implement auth',
-    });
-    expect(
-      mockContext.services.agentContext!.config.setApprovalMode,
-    ).toHaveBeenCalledWith(ApprovalMode.PLAN);
-  });
-
  it('should display the approved plan from config', async () => {
    const mockPlanPath = '/mock/plans/dir/approved-plan.md';
    vi.mocked(
@@ -66,13 +66,6 @@ export const planCommand: SlashCommand = {
      coreEvents.emitFeedback('info', 'Switched to Plan Mode.');
    }

-    if (context.invocation?.args) {
-      return {
-        type: 'submit_prompt',
-        content: context.invocation.args,
-      };
-    }
-
    const approvedPlanPath = config.getApprovedPlanPath();

    if (!approvedPlanPath) {
@@ -93,14 +86,12 @@ export const planCommand: SlashCommand = {
        type: MessageType.GEMINI,
        text: partToString(content.llmContent),
      });
-      return;
    } catch (error) {
      coreEvents.emitFeedback(
        'error',
        `Failed to read approved plan at ${approvedPlanPath}: ${error}`,
        error,
      );
-      return;
    }
  },
  subCommands: [
@@ -109,7 +100,6 @@ export const planCommand: SlashCommand = {
      description: 'Copy the currently approved plan to your clipboard',
      kind: CommandKind.BUILT_IN,
      autoExecute: true,
-      takesArgs: false,
      action: copyAction,
    },
  ],
@@ -151,7 +151,7 @@ async function completion(
    const files = await fs.readdir(checkpointDir);
    const jsonFiles = files.filter((file) => file.endsWith('.json'));
    return getTruncatedCheckpointNames(jsonFiles);
-  } catch {
+  } catch (_err) {
    return [];
  }
 }
@@ -76,7 +76,7 @@ export async function updateGitignore(gitRepoRoot: string): Promise<void> {
    let fileExists = true;
    try {
      existingContent = await fs.promises.readFile(gitignorePath, 'utf8');
-    } catch {
+    } catch (_error) {
      // File doesn't exist
      fileExists = false;
    }
@@ -168,8 +168,8 @@ async function downloadFiles({
 async function createDirectory(dirPath: string): Promise<void> {
  try {
    await fs.promises.mkdir(dirPath, { recursive: true });
-  } catch (error) {
-    debugLogger.debug(`Failed to create ${dirPath} directory:`, error);
+  } catch (_error) {
+    debugLogger.debug(`Failed to create ${dirPath} directory:`, _error);
    throw new Error(
      `Unable to create ${dirPath} directory. Do you have file permissions in the current directory?`,
    );
@@ -222,8 +222,8 @@ export const setupGithubCommand: SlashCommand = {
    let gitRepoRoot: string;
    try {
      gitRepoRoot = getGitRepoRoot();
-    } catch (error) {
-      debugLogger.debug(`Failed to get git repo root:`, error);
+    } catch (_error) {
+      debugLogger.debug(`Failed to get git repo root:`, _error);
      throw new Error(
        'Unable to determine the GitHub repository. /setup-github must be run from a git repository.',
      );
@@ -0,0 +1,35 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi } from 'vitest';
+import { shellsCommand } from './shellsCommand.js';
+import type { CommandContext } from './types.js';
+
+describe('shellsCommand', () => {
+  it('should call toggleBackgroundShell', async () => {
+    const toggleBackgroundShell = vi.fn();
+    const context = {
+      ui: {
+        toggleBackgroundShell,
+      },
+    } as unknown as CommandContext;
+
+    if (shellsCommand.action) {
+      await shellsCommand.action(context, '');
+    }
+
+    expect(toggleBackgroundShell).toHaveBeenCalled();
+  });
+
+  it('should have correct name and altNames', () => {
+    expect(shellsCommand.name).toBe('shells');
+    expect(shellsCommand.altNames).toContain('bashes');
+  });
+
+  it('should auto-execute', () => {
+    expect(shellsCommand.autoExecute).toBe(true);
+  });
+});
@@ -6,13 +6,13 @@

 import { CommandKind, type SlashCommand } from './types.js';

-export const tasksCommand: SlashCommand = {
-  name: 'tasks',
-  altNames: ['bg', 'background'],
+export const shellsCommand: SlashCommand = {
+  name: 'shells',
+  altNames: ['bashes'],
  kind: CommandKind.BUILT_IN,
-  description: 'Toggle background tasks view',
+  description: 'Toggle background shells view',
  autoExecute: true,
  action: async (context) => {
-    context.ui.toggleBackgroundTasks();
+    context.ui.toggleBackgroundShell();
  },
 };
@@ -528,7 +528,6 @@ describe('skillsCommand', () => {
      await actionPromise;

      expect(reloadSkillsMock).toHaveBeenCalled();
-      expect(context.ui.reloadCommands).toHaveBeenCalled();
      expect(context.ui.setPendingItem).toHaveBeenCalledWith(null);
      expect(context.ui.addItem).toHaveBeenCalledWith(
        expect.objectContaining({
@@ -285,8 +285,6 @@ async function reloadAction(
      context.ui.setPendingItem(null);
    }

-    context.ui.reloadCommands();
-
    const afterSkills = skillManager.getSkills();
    const afterNames = new Set(afterSkills.map((s) => s.name));

@@ -359,8 +357,6 @@ function enableCompletion(
    .map((s) => s.name);
 }

-import { parseSlashCommand } from '../../utils/commands.js';
-
 export const skillsCommand: SlashCommand = {
  name: 'skills',
  description:
@@ -406,13 +402,5 @@ export const skillsCommand: SlashCommand = {
      action: reloadAction,
    },
  ],
-  action: async (context, args) => {
-    if (args) {
-      const parsed = parseSlashCommand(`/${args}`, skillsCommand.subCommands!);
-      if (parsed.commandToExecute?.action) {
-        return parsed.commandToExecute.action(context, parsed.args);
-      }
-    }
-    return listAction(context, args);
-  },
+  action: listAction,
 };
@@ -1,36 +0,0 @@
-/**
- * @license
- * Copyright 2025 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { describe, it, expect, vi } from 'vitest';
-import { tasksCommand } from './tasksCommand.js';
-import type { CommandContext } from './types.js';
-
-describe('tasksCommand', () => {
-  it('should call toggleBackgroundTasks', async () => {
-    const toggleBackgroundTasks = vi.fn();
-    const context = {
-      ui: {
-        toggleBackgroundTasks,
-      },
-    } as unknown as CommandContext;
-
-    if (tasksCommand.action) {
-      await tasksCommand.action(context, '');
-    }
-
-    expect(toggleBackgroundTasks).toHaveBeenCalled();
-  });
-
-  it('should have correct name and altNames', () => {
-    expect(tasksCommand.name).toBe('tasks');
-    expect(tasksCommand.altNames).toContain('bg');
-    expect(tasksCommand.altNames).toContain('background');
-  });
-
-  it('should auto-execute', () => {
-    expect(tasksCommand.autoExecute).toBe(true);
-  });
-});
@@ -90,7 +90,7 @@ export interface CommandContext {
     */
    setConfirmationRequest: (value: ConfirmationRequest) => void;
    removeComponent: () => void;
-    toggleBackgroundTasks: () => void;
+    toggleBackgroundShell: () => void;
    toggleShortcutsHelp: () => void;
  };
  // Session-specific data
@@ -240,14 +240,5 @@ export interface SlashCommand {
   */
  showCompletionLoading?: boolean;

-  /**
-   * Whether the command expects arguments.
-   * If false, and the command is a subcommand, the command parser may treat
-   * any following text as arguments for the parent command instead of this subcommand,
-   * provided the parent command has an action.
-   * Defaults to true.
-   */
-  takesArgs?: boolean;
-
  subCommands?: SlashCommand[];
 }
@@ -6,8 +6,8 @@

 import { render } from '../../test-utils/render.js';
 import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
-import { BackgroundTaskDisplay } from './BackgroundTaskDisplay.js';
-import { type BackgroundTask } from '../hooks/useExecutionLifecycle.js';
+import { BackgroundShellDisplay } from './BackgroundShellDisplay.js';
+import { type BackgroundShell } from '../hooks/shellCommandProcessor.js';
 import { ShellExecutionService } from '@google/gemini-cli-core';
 import { act } from 'react';
 import { type Key, type KeypressHandler } from '../contexts/KeypressContext.js';
@@ -15,15 +15,15 @@ import { ScrollProvider } from '../contexts/ScrollProvider.js';
 import { Box } from 'ink';

 // Mock dependencies
-const mockDismissBackgroundTask = vi.fn();
-const mockSetActiveBackgroundTaskPid = vi.fn();
-const mockSetIsBackgroundTaskListOpen = vi.fn();
+const mockDismissBackgroundShell = vi.fn();
+const mockSetActiveBackgroundShellPid = vi.fn();
+const mockSetIsBackgroundShellListOpen = vi.fn();

 vi.mock('../contexts/UIActionsContext.js', () => ({
  useUIActions: () => ({
-    dismissBackgroundTask: mockDismissBackgroundTask,
-    setActiveBackgroundTaskPid: mockSetActiveBackgroundTaskPid,
-    setIsBackgroundTaskListOpen: mockSetIsBackgroundTaskListOpen,
+    dismissBackgroundShell: mockDismissBackgroundShell,
+    setActiveBackgroundShellPid: mockSetActiveBackgroundShellPid,
+    setIsBackgroundShellListOpen: mockSetIsBackgroundShellListOpen,
  }),
 }));

@@ -86,14 +86,14 @@ vi.mock('./shared/ScrollableList.js', () => ({
      data,
      renderItem,
    }: {
-      data: BackgroundTask[];
+      data: BackgroundShell[];
      renderItem: (props: {
-        item: BackgroundTask;
+        item: BackgroundShell;
        index: number;
      }) => React.ReactNode;
    }) => (
      <Box flexDirection="column">
-        {data.map((item: BackgroundTask, index: number) => (
+        {data.map((item: BackgroundShell, index: number) => (
          <Box key={index}>{renderItem({ item, index })}</Box>
        ))}
      </Box>
@@ -116,9 +116,9 @@ const createMockKey = (overrides: Partial<Key>): Key => ({
  ...overrides,
 });

-describe('<BackgroundTaskDisplay />', () => {
-  const mockShells = new Map<number, BackgroundTask>();
-  const shell1: BackgroundTask = {
+describe('<BackgroundShellDisplay />', () => {
+  const mockShells = new Map<number, BackgroundShell>();
+  const shell1: BackgroundShell = {
    pid: 1001,
    command: 'npm start',
    output: 'Starting server...',
@@ -126,7 +126,7 @@ describe('<BackgroundTaskDisplay />', () => {
    binaryBytesReceived: 0,
    status: 'running',
  };
-  const shell2: BackgroundTask = {
+  const shell2: BackgroundShell = {
    pid: 1002,
    command: 'tail -f log.txt',
    output: 'Log entry 1',
@@ -147,7 +147,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { lastFrame, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -167,7 +167,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 100;
    const { lastFrame, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -187,7 +187,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { lastFrame, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -207,7 +207,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { rerender, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -227,7 +227,7 @@ describe('<BackgroundTaskDisplay />', () => {

    rerender(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={100}
@@ -250,7 +250,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { lastFrame, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -270,7 +270,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -287,13 +287,13 @@ describe('<BackgroundTaskDisplay />', () => {
      simulateKey({ name: 'down' });
    });

-    // Simulate Ctrl+L (handled by BackgroundTaskDisplay)
+    // Simulate Ctrl+L (handled by BackgroundShellDisplay)
    await act(async () => {
      simulateKey({ name: 'l', ctrl: true });
    });

-    expect(mockSetActiveBackgroundTaskPid).toHaveBeenCalledWith(shell2.pid);
-    expect(mockSetIsBackgroundTaskListOpen).toHaveBeenCalledWith(false);
+    expect(mockSetActiveBackgroundShellPid).toHaveBeenCalledWith(shell2.pid);
+    expect(mockSetIsBackgroundShellListOpen).toHaveBeenCalledWith(false);
    unmount();
  });

@@ -301,7 +301,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -325,7 +325,7 @@ describe('<BackgroundTaskDisplay />', () => {
      simulateKey({ name: 'k', ctrl: true });
    });

-    expect(mockDismissBackgroundTask).toHaveBeenCalledWith(shell2.pid);
+    expect(mockDismissBackgroundShell).toHaveBeenCalledWith(shell2.pid);
    unmount();
  });

@@ -333,7 +333,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell1.pid}
          width={width}
@@ -349,7 +349,7 @@ describe('<BackgroundTaskDisplay />', () => {
      simulateKey({ name: 'k', ctrl: true });
    });

-    expect(mockDismissBackgroundTask).toHaveBeenCalledWith(shell1.pid);
+    expect(mockDismissBackgroundShell).toHaveBeenCalledWith(shell1.pid);
    unmount();
  });

@@ -358,7 +358,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { lastFrame, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={shell2.pid}
          width={width}
@@ -375,7 +375,7 @@ describe('<BackgroundTaskDisplay />', () => {
  });

  it('keeps exit code status color even when selected', async () => {
-    const exitedShell: BackgroundTask = {
+    const exitedShell: BackgroundShell = {
      pid: 1003,
      command: 'exit 0',
      output: '',
@@ -389,7 +389,7 @@ describe('<BackgroundTaskDisplay />', () => {
    const width = 80;
    const { lastFrame, unmount } = await render(
      <ScrollProvider>
-        <BackgroundTaskDisplay
+        <BackgroundShellDisplay
          shells={mockShells}
          activePid={exitedShell.pid}
          width={width}
@@ -17,7 +17,7 @@ import {
  type AnsiToken,
 } from '@google/gemini-cli-core';
 import { cpLen, cpSlice, getCachedStringWidth } from '../utils/textUtils.js';
-import { type BackgroundTask } from '../hooks/useExecutionLifecycle.js';
+import { type BackgroundShell } from '../hooks/shellCommandProcessor.js';
 import { Command } from '../key/keyMatchers.js';
 import { useKeypress } from '../hooks/useKeypress.js';
 import { formatCommand } from '../key/keybindingUtils.js';
@@ -34,8 +34,8 @@ import {
 } from './shared/RadioButtonSelect.js';
 import { useKeyMatchers } from '../hooks/useKeyMatchers.js';

-interface BackgroundTaskDisplayProps {
-  shells: Map<number, BackgroundTask>;
+interface BackgroundShellDisplayProps {
+  shells: Map<number, BackgroundShell>;
  activePid: number;
  width: number;
  height: number;
@@ -61,19 +61,19 @@ const formatShellCommandForDisplay = (command: string, maxWidth: number) => {
    : commandFirstLine;
 };

-export const BackgroundTaskDisplay = ({
+export const BackgroundShellDisplay = ({
  shells,
  activePid,
  width,
  height,
  isFocused,
  isListOpenProp,
-}: BackgroundTaskDisplayProps) => {
+}: BackgroundShellDisplayProps) => {
  const keyMatchers = useKeyMatchers();
  const {
-    dismissBackgroundTask,
-    setActiveBackgroundTaskPid,
-    setIsBackgroundTaskListOpen,
+    dismissBackgroundShell,
+    setActiveBackgroundShellPid,
+    setIsBackgroundShellListOpen,
  } = useUIActions();
  const activeShell = shells.get(activePid);
  const [output, setOutput] = useState<string | AnsiOutput>(
@@ -152,13 +152,13 @@ export const BackgroundTaskDisplay = ({
        // RadioButtonSelect handles Enter -> onSelect

        if (keyMatchers[Command.BACKGROUND_SHELL_ESCAPE](key)) {
-          setIsBackgroundTaskListOpen(false);
+          setIsBackgroundShellListOpen(false);
          return true;
        }

        if (keyMatchers[Command.KILL_BACKGROUND_SHELL](key)) {
          if (highlightedPid) {
-            void dismissBackgroundTask(highlightedPid);
+            void dismissBackgroundShell(highlightedPid);
            // If we killed the active one, the list might update via props
          }
          return true;
@@ -166,9 +166,9 @@ export const BackgroundTaskDisplay = ({

        if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL_LIST](key)) {
          if (highlightedPid) {
-            setActiveBackgroundTaskPid(highlightedPid);
+            setActiveBackgroundShellPid(highlightedPid);
          }
-          setIsBackgroundTaskListOpen(false);
+          setIsBackgroundShellListOpen(false);
          return true;
        }
        return false;
@@ -179,12 +179,12 @@ export const BackgroundTaskDisplay = ({
      }

      if (keyMatchers[Command.KILL_BACKGROUND_SHELL](key)) {
-        void dismissBackgroundTask(activeShell.pid);
+        void dismissBackgroundShell(activeShell.pid);
        return true;
      }

      if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL_LIST](key)) {
-        setIsBackgroundTaskListOpen(true);
+        setIsBackgroundShellListOpen(true);
        return true;
      }

@@ -339,8 +339,8 @@ export const BackgroundTaskDisplay = ({
            items={items}
            initialIndex={initialIndex >= 0 ? initialIndex : 0}
            onSelect={(pid) => {
-              setActiveBackgroundTaskPid(pid);
-              setIsBackgroundTaskListOpen(false);
+              setActiveBackgroundShellPid(pid);
+              setIsBackgroundShellListOpen(false);
            }}
            onHighlight={(pid) => setHighlightedPid(pid)}
            isFocused={isFocused}
@@ -198,7 +198,7 @@ const createMockUIState = (overrides: Partial<UIState> = {}): UIState =>
    nightly: false,
    isTrustedFolder: true,
    activeHooks: [],
-    isBackgroundTaskVisible: false,
+    isBackgroundShellVisible: false,
    embeddedShellFocused: false,
    showIsExpandableHint: false,
    quota: {
@@ -464,7 +464,7 @@ describe('Composer', () => {
      const uiState = createMockUIState({
        streamingState: StreamingState.Responding,
        embeddedShellFocused: true,
-        isBackgroundTaskVisible: true,
+        isBackgroundShellVisible: true,
      });

      const { lastFrame } = await renderComposer(uiState);
@@ -494,7 +494,7 @@ describe('Composer', () => {
      const uiState = createMockUIState({
        streamingState: StreamingState.Responding,
        embeddedShellFocused: true,
-        isBackgroundTaskVisible: false,
+        isBackgroundShellVisible: false,
      });

      const { lastFrame } = await renderComposer(uiState);
@@ -35,7 +35,10 @@ vi.mock('./shared/ScrollableList.js', () => ({

 describe('DetailedMessagesDisplay', () => {
  beforeEach(() => {
-    vi.mocked(useConsoleMessages).mockReturnValue([]);
+    vi.mocked(useConsoleMessages).mockReturnValue({
+      consoleMessages: [],
+      clearConsoleMessages: vi.fn(),
+    });
  });
  it('renders nothing when messages are empty', async () => {
    const { lastFrame, unmount } = await renderWithProviders(
@@ -55,7 +58,10 @@ describe('DetailedMessagesDisplay', () => {
      { type: 'error', content: 'Error message', count: 1 },
      { type: 'debug', content: 'Debug message', count: 1 },
    ];
-    vi.mocked(useConsoleMessages).mockReturnValue(messages);
+    vi.mocked(useConsoleMessages).mockReturnValue({
+      consoleMessages: messages,
+      clearConsoleMessages: vi.fn(),
+    });

    const { lastFrame, unmount } = await renderWithProviders(
      <DetailedMessagesDisplay maxHeight={20} width={80} hasFocus={true} />,
@@ -73,7 +79,10 @@ describe('DetailedMessagesDisplay', () => {
    const messages: ConsoleMessageItem[] = [
      { type: 'error', content: 'Error message', count: 1 },
    ];
-    vi.mocked(useConsoleMessages).mockReturnValue(messages);
+    vi.mocked(useConsoleMessages).mockReturnValue({
+      consoleMessages: messages,
+      clearConsoleMessages: vi.fn(),
+    });

    const { lastFrame, unmount } = await renderWithProviders(
      <DetailedMessagesDisplay maxHeight={20} width={80} hasFocus={true} />,
@@ -89,7 +98,10 @@ describe('DetailedMessagesDisplay', () => {
    const messages: ConsoleMessageItem[] = [
      { type: 'error', content: 'Error message', count: 1 },
    ];
-    vi.mocked(useConsoleMessages).mockReturnValue(messages);
+    vi.mocked(useConsoleMessages).mockReturnValue({
+      consoleMessages: messages,
+      clearConsoleMessages: vi.fn(),
+    });

    const { lastFrame, unmount } = await renderWithProviders(
      <DetailedMessagesDisplay maxHeight={20} width={80} hasFocus={true} />,
@@ -105,7 +117,10 @@ describe('DetailedMessagesDisplay', () => {
    const messages: ConsoleMessageItem[] = [
      { type: 'log', content: 'Repeated message', count: 5 },
    ];
-    vi.mocked(useConsoleMessages).mockReturnValue(messages);
+    vi.mocked(useConsoleMessages).mockReturnValue({
+      consoleMessages: messages,
+      clearConsoleMessages: vi.fn(),
+    });

    const { lastFrame, unmount } = await renderWithProviders(
      <DetailedMessagesDisplay maxHeight={10} width={80} hasFocus={false} />,
@@ -29,7 +29,7 @@ export const DetailedMessagesDisplay: React.FC<
 > = ({ maxHeight, width, hasFocus }) => {
  const scrollableListRef = useRef<ScrollableListRef<ConsoleMessageItem>>(null);

-  const consoleMessages = useConsoleMessages();
+  const { consoleMessages } = useConsoleMessages();
  const config = useConfig();

  const messages = useMemo(() => {
@@ -8,11 +8,7 @@ import { describe, it, expect, vi, afterEach, beforeEach } from 'vitest';
 import { renderWithProviders } from '../../test-utils/render.js';
 import { Footer } from './Footer.js';
 import { createMockSettings } from '../../test-utils/settings.js';
-import {
-  type Config,
-  UserAccountManager,
-  AuthType,
-} from '@google/gemini-cli-core';
+import { type Config } from '@google/gemini-cli-core';
 import path from 'node:path';

 // Normalize paths to POSIX slashes for stable cross-platform snapshots.
@@ -73,17 +69,14 @@ const defaultProps = {
  branchName: 'main',
 };

-const mockConfigPlain = {
+const mockConfig = {
  getTargetDir: () => defaultProps.targetDir,
  getDebugMode: () => false,
  getModel: () => defaultProps.model,
  getIdeMode: () => false,
  isTrustedFolder: () => true,
  getExtensionRegistryURI: () => undefined,
-  getContentGeneratorConfig: () => ({ authType: undefined }),
-};
-
-const mockConfig = mockConfigPlain as unknown as Config;
+} as unknown as Config;

 const mockSessionStats = {
  sessionId: 'test-session-id',
@@ -441,7 +434,6 @@ describe('<Footer />', () => {

    it('renders footer with all optional sections hidden (minimal footer)', async () => {
      const { lastFrame, unmount } = await renderWithProviders(<Footer />, {
-        config: mockConfig,
        width: 120,
        uiState: { sessionStats: mockSessionStats },
        settings: createMockSettings({
@@ -559,7 +551,6 @@ describe('<Footer />', () => {
  describe('Footer Token Formatting', () => {
    const renderWithTokens = async (tokens: number) => {
      const result = await renderWithProviders(<Footer />, {
-        config: mockConfig,
        width: 120,
        uiState: {
          sessionStats: {
@@ -684,75 +675,6 @@ describe('<Footer />', () => {
  });

  describe('Footer Custom Items', () => {
-    it('renders auth item with email', async () => {
-      const authConfig = {
-        ...mockConfigPlain,
-        getContentGeneratorConfig: () => ({
-          authType: AuthType.LOGIN_WITH_GOOGLE,
-        }),
-      } as unknown as Config;
-      const getCachedAccountSpy = vi
-        .spyOn(UserAccountManager.prototype, 'getCachedGoogleAccount')
-        .mockReturnValue('test@example.com');
-
-      const { lastFrame, unmount } = await renderWithProviders(<Footer />, {
-        config: authConfig,
-        width: 120,
-        uiState: {
-          currentModel: 'gemini-pro',
-          sessionStats: mockSessionStats,
-        },
-        settings: createMockSettings({
-          ui: {
-            footer: {
-              items: ['auth'],
-            },
-          },
-        }),
-      });
-
-      expect(lastFrame()).toContain('auth');
-      expect(lastFrame()).toContain('test@example.com');
-      unmount();
-      getCachedAccountSpy.mockRestore();
-    });
-
-    it('does NOT render auth item when showUserIdentity is false', async () => {
-      const authConfig = {
-        ...mockConfigPlain,
-        getContentGeneratorConfig: () => ({
-          authType: AuthType.LOGIN_WITH_GOOGLE,
-        }),
-      } as unknown as Config;
-      const getCachedAccountSpy = vi
-        .spyOn(UserAccountManager.prototype, 'getCachedGoogleAccount')
-        .mockReturnValue('test@example.com');
-
-      const { lastFrame, unmount } = await renderWithProviders(<Footer />, {
-        config: authConfig,
-        width: 120,
-        uiState: {
-          currentModel: 'gemini-pro',
-          sessionStats: mockSessionStats,
-        },
-        settings: createMockSettings({
-          ui: {
-            showUserIdentity: false,
-            footer: {
-              items: ['workspace', 'auth'],
-            },
-          },
-        }),
-      });
-
-      const output = lastFrame();
-      expect(output).toContain('workspace');
-      expect(output).not.toContain('auth');
-      expect(output).not.toContain('test@example.com');
-      unmount();
-      getCachedAccountSpy.mockRestore();
-    });
-
    it('renders items in the specified order', async () => {
      const { lastFrame, unmount } = await renderWithProviders(<Footer />, {
        config: mockConfig,
@@ -812,7 +734,6 @@ describe('<Footer />', () => {

    it('handles empty items array', async () => {
      const { lastFrame, unmount } = await renderWithProviders(<Footer />, {
-        config: mockConfig,
        width: 120,
        uiState: { sessionStats: mockSessionStats },
        settings: createMockSettings({
@@ -5,7 +5,6 @@
 */

 import type React from 'react';
-import { useState, useEffect } from 'react';
 import { Box, Text } from 'ink';
 import { theme } from '../semantic-colors.js';
 import {
@@ -13,8 +12,6 @@ import {
  tildeifyPath,
  getDisplayString,
  checkExhaustive,
-  AuthType,
-  UserAccountManager,
 } from '@google/gemini-cli-core';
 import { ConsoleSummaryDisplay } from './ConsoleSummaryDisplay.js';
 import process from 'node:process';
@@ -186,18 +183,6 @@ export const Footer: React.FC<{ copyModeEnabled?: boolean }> = ({
  const settings = useSettings();
  const { vimEnabled, vimMode } = useVimMode();

-  const authType = config.getContentGeneratorConfig()?.authType;
-  const [email, setEmail] = useState<string | undefined>();
-
-  useEffect(() => {
-    if (authType) {
-      const userAccountManager = new UserAccountManager();
-      setEmail(userAccountManager.getCachedGoogleAccount() ?? undefined);
-    } else {
-      setEmail(undefined);
-    }
-  }, [authType]);
-
  if (copyModeEnabled) {
    return <Box height={1} />;
  }
@@ -236,7 +221,6 @@ export const Footer: React.FC<{ copyModeEnabled?: boolean }> = ({
    errorCount > 0 &&
    (isFullErrorVerbosity || debugMode || isDevelopment);
  const displayVimMode = vimEnabled ? vimMode : undefined;
-
  const items =
    settings.merged.ui.footer.items ??
    deriveItemsFromLegacySettings(settings.merged);
@@ -401,25 +385,6 @@ export const Footer: React.FC<{ copyModeEnabled?: boolean }> = ({
        );
        break;
      }
-      case 'auth': {
-        if (!settings.merged.ui.showUserIdentity) break;
-        if (!authType) break;
-        const displayStr =
-          authType === AuthType.LOGIN_WITH_GOOGLE
-            ? (email ?? 'google')
-            : authType;
-        addCol(
-          id,
-          header,
-          () => (
-            <Text color={itemColor} wrap="truncate-end">
-              {displayStr}
-            </Text>
-          ),
-          displayStr.length,
-        );
-        break;
-      }
      case 'code-changes': {
        const added = uiState.sessionStats.metrics.files.totalLinesAdded;
        const removed = uiState.sessionStats.metrics.files.totalLinesRemoved;
@@ -116,7 +116,7 @@ describe('<FooterConfigDialog />', () => {
    expect(lastFrame()).toContain('~/project/path');

    // Move focus down to 'code-changes' (which has colored elements)
-    for (let i = 0; i < 9; i++) {
+    for (let i = 0; i < 8; i++) {
      act(() => {
        stdin.write('\u001b[B'); // Down arrow
      });
@@ -255,7 +255,6 @@ export const FooterConfigDialog: React.FC<FooterConfigDialogProps> = ({
          <Text color={getColor('code-changes', theme.status.error)}>-4</Text>
        </Box>
      ),
-      auth: <Text color={getColor('auth', itemColor)}>test@example.com</Text>,
      'token-count': (
        <Text color={getColor('token-count', itemColor)}>1.5k tokens</Text>
      ),
@@ -17,7 +17,6 @@ import { ToolGroupMessage } from './messages/ToolGroupMessage.js';
 import { GeminiMessageContent } from './messages/GeminiMessageContent.js';
 import { CompressionMessage } from './messages/CompressionMessage.js';
 import { WarningMessage } from './messages/WarningMessage.js';
-import { SubagentHistoryMessage } from './messages/SubagentHistoryMessage.js';
 import { Box } from 'ink';
 import { AboutBox } from './AboutBox.js';
 import { StatsDisplay } from './StatsDisplay.js';
@@ -49,7 +48,6 @@ interface HistoryItemDisplayProps {
  isExpandable?: boolean;
  isFirstThinking?: boolean;
  isFirstAfterThinking?: boolean;
-  suppressNarration?: boolean;
 }

 export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
@@ -62,7 +60,6 @@ export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
  isExpandable,
  isFirstThinking = false,
  isFirstAfterThinking = false,
-  suppressNarration = false,
 }) => {
  const settings = useSettings();
  const inlineThinkingMode = getInlineThinkingMode(settings);
@@ -71,17 +68,6 @@ export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
  const needsTopMarginAfterThinking =
    isFirstAfterThinking && inlineThinkingMode !== 'off';

-  // If there's a topic update in this turn, we suppress the regular narration
-  // and thoughts as they are being "replaced" by the update_topic tool.
-  if (
-    suppressNarration &&
-    (itemForDisplay.type === 'thinking' ||
-      itemForDisplay.type === 'gemini' ||
-      itemForDisplay.type === 'gemini_content')
-  ) {
-    return null;
-  }
-
  return (
    <Box
      flexDirection="column"
@@ -216,12 +202,6 @@ export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
          isExpandable={isExpandable}
        />
      )}
-      {itemForDisplay.type === 'subagent' && (
-        <SubagentHistoryMessage
-          item={itemForDisplay}
-          terminalWidth={terminalWidth}
-        />
-      )}
      {itemForDisplay.type === 'compression' && (
        <CompressionMessage compression={itemForDisplay.compression} />
      )}
@@ -1445,101 +1445,9 @@ describe('InputPrompt', () => {
    });

    await waitFor(() => {
-      // Should submit the full command constructed from buffer + suggestion
-      // even if autoExecute is false, because the user explicitly hit Enter on the suggestion.
-      expect(props.onSubmit).toHaveBeenCalledWith('/share');
-      expect(mockCommandCompletion.handleAutocomplete).not.toHaveBeenCalled();
-    });
-    unmount();
-  });
-
-  it('should add a space on Tab when command is already complete in the buffer', async () => {
-    const executableCommand: SlashCommand = {
-      name: 'about',
-      kind: CommandKind.BUILT_IN,
-      description: 'About info',
-      action: vi.fn(),
-      autoExecute: true,
-    };
-
-    const suggestion = { label: 'about', value: 'about' };
-
-    mockedUseCommandCompletion.mockReturnValue({
-      ...mockCommandCompletion,
-      showSuggestions: true,
-      suggestions: [suggestion],
-      activeSuggestionIndex: 0,
-      getCommandFromSuggestion: vi.fn().mockReturnValue(executableCommand),
-      getCompletedText: vi.fn().mockReturnValue('/about'),
-    });
-
-    // Buffer is already complete
-    props.buffer.setText('/about');
-    props.buffer.lines = ['/about'];
-    props.buffer.cursor = [0, 6];
-
-    const { stdin, unmount } = await renderWithProviders(
-      <InputPrompt {...props} />,
-      {
-        uiActions,
-      },
-    );
-
-    await act(async () => {
-      stdin.write('\t'); // Tab
-    });
-
-    await waitFor(() => {
-      // Should call handleAutocomplete which will add the space
+      // Should autocomplete to allow adding file argument
      expect(mockCommandCompletion.handleAutocomplete).toHaveBeenCalledWith(0);
-    });
-    unmount();
-  });
-
-  it('should submit the base command when Enter is pressed on its suggestion even with a trailing space', async () => {
-    const statsCommand: SlashCommand = {
-      name: 'stats',
-      kind: CommandKind.BUILT_IN,
-      description: 'Stats info',
-      action: vi.fn(),
-      autoExecute: false,
-    };
-
-    const suggestion = {
-      label: 'stats',
-      value: 'stats',
-      sectionTitle: 'command',
-      insertValue: 'stats',
-    };
-
-    mockedUseCommandCompletion.mockReturnValue({
-      ...mockCommandCompletion,
-      showSuggestions: true,
-      suggestions: [suggestion],
-      activeSuggestionIndex: 0,
-      getCommandFromSuggestion: vi.fn().mockReturnValue(statsCommand),
-      getCompletedText: vi.fn().mockReturnValue('/stats'),
-    });
-
-    // Buffer has trailing space: "/stats "
-    props.buffer.setText('/stats ');
-    props.buffer.lines = ['/stats '];
-    props.buffer.cursor = [0, 7];
-
-    const { stdin, unmount } = await renderWithProviders(
-      <InputPrompt {...props} />,
-      {
-        uiActions,
-      },
-    );
-
-    await act(async () => {
-      stdin.write('\r'); // Enter
-    });
-
-    await waitFor(() => {
-      // Should submit "/stats"
-      expect(props.onSubmit).toHaveBeenCalledWith('/stats');
+      expect(props.onSubmit).not.toHaveBeenCalled();
    });
    unmount();
  });
@@ -1656,9 +1564,9 @@ describe('InputPrompt', () => {
    });

    await waitFor(() => {
-      // Should submit the command
-      expect(props.onSubmit).toHaveBeenCalledWith('/find-capital');
-      expect(mockCommandCompletion.handleAutocomplete).not.toHaveBeenCalled();
+      // Should autocomplete (not execute) since autoExecute is undefined
+      expect(mockCommandCompletion.handleAutocomplete).toHaveBeenCalledWith(0);
+      expect(props.onSubmit).not.toHaveBeenCalled();
    });
    unmount();
  });
@@ -2314,67 +2222,85 @@ describe('InputPrompt', () => {
          name: 'mid-word',
          text: 'hello world',
          visualCursor: [0, 3],
+          expected: `hel${chalk.inverse('l')}o world`,
        },
        {
          name: 'at the beginning of the line',
          text: 'hello',
          visualCursor: [0, 0],
+          expected: `${chalk.inverse('h')}ello`,
        },
        {
          name: 'at the end of the line',
          text: 'hello',
          visualCursor: [0, 5],
+          expected: `hello${chalk.inverse(' ')}`,
        },
        {
          name: 'on a highlighted token',
          text: 'run @path/to/file',
          visualCursor: [0, 9],
+          expected: `@path/${chalk.inverse('t')}o/file`,
        },
        {
          name: 'for multi-byte unicode characters',
          text: 'hello 👍 world',
          visualCursor: [0, 6],
+          expected: `hello ${chalk.inverse('👍')} world`,
        },
        {
          name: 'after multi-byte unicode characters',
          text: '👍A',
          visualCursor: [0, 1],
+          expected: `👍${chalk.inverse('A')}`,
        },
        {
          name: 'at the end of a line with unicode characters',
          text: 'hello 👍',
          visualCursor: [0, 8],
+          expected: `hello 👍`, // skip checking inverse ansi due to ink truncation bug
        },
        {
          name: 'at the end of a short line with unicode characters',
          text: '👍',
          visualCursor: [0, 1],
+          expected: `👍${chalk.inverse(' ')}`,
        },
        {
          name: 'on an empty line',
          text: '',
          visualCursor: [0, 0],
+          expected: chalk.inverse(' '),
        },
        {
          name: 'on a space between words',
          text: 'hello world',
          visualCursor: [0, 5],
+          expected: `hello${chalk.inverse(' ')}world`,
        },
      ])(
        'should display cursor correctly $name',
-        async ({ text, visualCursor }) => {
+        async ({ name, text, visualCursor, expected }) => {
          mockBuffer.text = text;
          mockBuffer.lines = [text];
          mockBuffer.viewportVisualLines = [text];
          mockBuffer.visualCursor = visualCursor as [number, number];
          props.config.getUseBackgroundColor = () => false;

-          const renderResult = await renderWithProviders(
+          const { stdout, unmount } = await renderWithProviders(
            <InputPrompt {...props} />,
          );
-          await renderResult.waitUntilReady();
-          await expect(renderResult).toMatchSvgSnapshot();
-          renderResult.unmount();
+          await waitFor(() => {
+            const frame = stdout.lastFrameRaw();
+            expect(stripAnsi(frame)).toContain(stripAnsi(expected));
+            if (
+              name !== 'at the end of a line with unicode characters' &&
+              name !== 'on a highlighted token'
+            ) {
+              expect(frame).toContain('\u001b[7m');
+            }
+          });
+          unmount();
        },
      );
    });
@@ -2390,6 +2316,7 @@ describe('InputPrompt', () => {
            [1, 0],
            [2, 0],
          ],
+          expected: `sec${chalk.inverse('o')}nd line`,
        },
        {
          name: 'at the beginning of a line',
@@ -2399,6 +2326,7 @@ describe('InputPrompt', () => {
            [0, 0],
            [1, 0],
          ],
+          expected: `${chalk.inverse('s')}econd line`,
        },
        {
          name: 'at the end of a line',
@@ -2408,10 +2336,11 @@ describe('InputPrompt', () => {
            [0, 0],
            [1, 0],
          ],
+          expected: `first line${chalk.inverse(' ')}`,
        },
      ])(
        'should display cursor correctly $name in a multiline block',
-        async ({ text, visualCursor, visualToLogicalMap }) => {
+        async ({ name, text, visualCursor, expected, visualToLogicalMap }) => {
          mockBuffer.text = text;
          mockBuffer.lines = text.split('\n');
          mockBuffer.viewportVisualLines = text.split('\n');
@@ -2421,12 +2350,20 @@ describe('InputPrompt', () => {
          >;
          props.config.getUseBackgroundColor = () => false;

-          const renderResult = await renderWithProviders(
+          const { stdout, unmount } = await renderWithProviders(
            <InputPrompt {...props} />,
          );
-          await renderResult.waitUntilReady();
-          await expect(renderResult).toMatchSvgSnapshot();
-          renderResult.unmount();
+          await waitFor(() => {
+            const frame = stdout.lastFrameRaw();
+            expect(stripAnsi(frame)).toContain(stripAnsi(expected));
+            if (
+              name !== 'at the end of a line with unicode characters' &&
+              name !== 'on a highlighted token'
+            ) {
+              expect(frame).toContain('\u001b[7m');
+            }
+          });
+          unmount();
        },
      );

@@ -2443,12 +2380,18 @@ describe('InputPrompt', () => {
        ];
        props.config.getUseBackgroundColor = () => false;

-        const renderResult = await renderWithProviders(
+        const { stdout, unmount } = await renderWithProviders(
          <InputPrompt {...props} />,
        );
-        await renderResult.waitUntilReady();
-        await expect(renderResult).toMatchSvgSnapshot();
-        renderResult.unmount();
+        await waitFor(() => {
+          const frame = stdout.lastFrameRaw();
+          const lines = frame.split('\n');
+          // The line with the cursor should just be an inverted space inside the box border
+          expect(
+            lines.find((l) => l.includes(chalk.inverse(' '))),
+          ).not.toBeUndefined();
+        });
+        unmount();
      });
    });
  });
@@ -2469,14 +2412,22 @@ describe('InputPrompt', () => {
      ];
      props.config.getUseBackgroundColor = () => false;

-      const renderResult = await renderWithProviders(
+      const { stdout, unmount } = await renderWithProviders(
        <InputPrompt {...props} />,
      );
+      await waitFor(() => {
+        const frame = stdout.lastFrameRaw();
+        // Check that all lines, including the empty one, are rendered.
+        // This implicitly tests that the Box wrapper provides height for the empty line.
+        expect(frame).toContain('hello');
+        expect(frame).toContain('world');
+        expect(frame).toContain(chalk.inverse(' '));

-      await renderResult.waitUntilReady();
-      await expect(renderResult).toMatchSvgSnapshot();
-
-      renderResult.unmount();
+        const outputLines = frame.trim().split('\n');
+        // The number of lines should be 2 for the border plus 3 for the content.
+        expect(outputLines.length).toBe(5);
+      });
+      unmount();
    });
  });

@@ -4137,12 +4088,14 @@ describe('InputPrompt', () => {
    it('should not show inverted cursor when shell is focused', async () => {
      props.isEmbeddedShellFocused = true;
      props.focus = false;
-      const renderResult = await renderWithProviders(
+      const { stdout, unmount } = await renderWithProviders(
        <InputPrompt {...props} />,
      );
-      await renderResult.waitUntilReady();
-      await expect(renderResult).toMatchSvgSnapshot();
-      renderResult.unmount();
+      await waitFor(() => {
+        expect(stdout.lastFrame()).not.toContain(`{chalk.inverse(' ')}`);
+      });
+      expect(stdout.lastFrame()).toMatchSnapshot();
+      unmount();
    });
  });

@@ -232,8 +232,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
    terminalWidth,
    activePtyId,
    history,
-    backgroundTasks,
-    backgroundTaskHeight,
+    backgroundShells,
+    backgroundShellHeight,
    shortcutsHelpVisible,
  } = useUIState();
  const [suppressCompletion, setSuppressCompletion] = useState(false);
@@ -1082,12 +1082,16 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
                  const command =
                    completion.getCommandFromSuggestion(suggestion);

-                  const completedText = completion.getCompletedText(suggestion);
+                  // Only auto-execute if the command has no completion function
+                  // (i.e., it doesn't require an argument to be selected)
+                  if (
+                    command &&
+                    isAutoExecutableCommand(command) &&
+                    !command.completion
+                  ) {
+                    const completedText =
+                      completion.getCompletedText(suggestion);

-                  // If the user hits Enter on a suggestion, we should submit it
-                  // IF it has an action and doesn't require further arguments (no completion function).
-                  // This is separate from autoExecute, which handles automatic execution while typing.
-                  if (command && command.action && !command.completion) {
                    if (completedText) {
                      setExpandedSuggestionIndex(-1);
                      handleSubmit(completedText.trim());
@@ -1258,7 +1262,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
      if (keyMatchers[Command.FOCUS_SHELL_INPUT](key)) {
        if (
          activePtyId ||
-          (backgroundTasks.size > 0 && backgroundTaskHeight > 0)
+          (backgroundShells.size > 0 && backgroundShellHeight > 0)
        ) {
          setEmbeddedShellFocused(true);
          return true;
@@ -1321,8 +1325,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
      setBannerVisible,
      activePtyId,
      setEmbeddedShellFocused,
-      backgroundTasks.size,
-      backgroundTaskHeight,
+      backgroundShells.size,
+      backgroundShellHeight,
      streamingState,
      handleEscPress,
      registerPlainTabPress,
@@ -27,10 +27,6 @@ import {
 } from '../hooks/useConfirmingTool.js';

 // Mock dependencies
-vi.mock('ink-spinner', () => ({
-  default: () => <Text>⠋</Text>,
-}));
-
 const mockUseSettings = vi.fn().mockReturnValue({
  merged: {
    ui: {
@@ -90,10 +86,10 @@ vi.mock('./shared/ScrollableList.js', () => ({
 }));

 import { theme } from '../semantic-colors.js';
-import { type BackgroundTask } from '../hooks/shellReducer.js';
+import { type BackgroundShell } from '../hooks/shellReducer.js';

 describe('getToolGroupBorderAppearance', () => {
-  const mockBackgroundTasks = new Map<number, BackgroundTask>();
+  const mockBackgroundShells = new Map<number, BackgroundShell>();
  const activeShellPtyId = 123;

  it('returns default empty values for non-tool_group items', () => {
@@ -103,7 +99,7 @@ describe('getToolGroupBorderAppearance', () => {
      null,
      false,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({ borderColor: '', borderDimColor: false });
  });
@@ -148,7 +144,7 @@ describe('getToolGroupBorderAppearance', () => {
      null,
      false,
      pendingItems,
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({
      borderColor: theme.border.default,
@@ -177,7 +173,7 @@ describe('getToolGroupBorderAppearance', () => {
      null,
      false,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({
      borderColor: theme.border.default,
@@ -206,7 +202,7 @@ describe('getToolGroupBorderAppearance', () => {
      null,
      false,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({
      borderColor: theme.status.warning,
@@ -236,7 +232,7 @@ describe('getToolGroupBorderAppearance', () => {
      activeShellPtyId,
      false,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({
      borderColor: theme.ui.active,
@@ -266,7 +262,7 @@ describe('getToolGroupBorderAppearance', () => {
      activeShellPtyId,
      true,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({
      borderColor: theme.ui.focus,
@@ -295,7 +291,7 @@ describe('getToolGroupBorderAppearance', () => {
      activeShellPtyId,
      false,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    expect(result).toEqual({
      borderColor: theme.ui.active,
@@ -312,7 +308,7 @@ describe('getToolGroupBorderAppearance', () => {
      activeShellPtyId,
      true,
      [],
-      mockBackgroundTasks,
+      mockBackgroundShells,
    );
    // Since there are no tools to inspect, it falls back to empty pending, but isCurrentlyInShellTurn=true
    // so it counts as pending shell.
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Aishanee Shah	a30cc4a8a9	revert: package-lock.json changes	2026-03-28 04:14:09 +00:00
Aishanee Shah	0e169ee968	revert: remove heredoc mandate from legacy system prompt	2026-03-28 04:13:21 +00:00
Aishanee Shah	6c23f0c7e1	feat(core): append write_file suggestion when shell commands with heredocs fail	2026-03-28 04:13:21 +00:00
Aishanee Shah	83792d51c1	feat(core): harden shell tool against heredocs and update system prompt to prefer write_file	2026-03-28 04:13:20 +00:00