Soften backend claim for Auto availability; rewrap comments
Secret Scan / scan (push) Canceled after 0s
Build App (Preview) / create-release (pull_request) Canceled after 0s
Build App (Preview) / test (pull_request) Canceled after 0s
Build App (Preview) / build-linux (pull_request) Canceled after 0s
Build App (Preview) / build-macos (pull_request) Canceled after 0s
Build App (Preview) / build-windows (pull_request) Canceled after 0s
Build App (Preview) / prune-previews (pull_request) Canceled after 0s
Build App (Preview) / compute-version (pull_request) Canceled after 1s
Build Container / build-container (pull_request) Canceled after 4s
Secret Scan / scan (pull_request) Canceled after 6s

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-09-25 09:55:00 -07:00
co-authored by Claude Opus 5.5
parent 99d8493008
commit e198edfb7c
2 changed files with 7 additions and 4 deletions
+5 -3
View File
@@ -484,8 +484,9 @@ the way they did: one that had Full Permissions on becomes **Bypass**, one that
**Auto** sits between Accept Edits and Bypass: Claude Code's own classifier reviews each action, **Auto** sits between Accept Edits and Bypass: Claude Code's own classifier reviews each action,
lets routine work through and blocks things that look risky (such as destructive or lets routine work through and blocks things that look risky (such as destructive or
exfiltrating commands) — no prompts either way. Whether it is available depends on your Claude exfiltrating commands) — no prompts either way. Whether it is available depends on your Claude
Code account, model and backend (local and OpenAI-compatible backends won't qualify). When it Code account, model and backend (local and OpenAI-compatible backends usually won't
isn't available, Claude Code quietly starts in its normal prompting mode instead. qualify). When it isn't available, Claude Code quietly starts in its normal prompting mode
instead.
### When a change takes effect ### When a change takes effect
@@ -1359,7 +1360,8 @@ with `--dangerously-skip-permissions`. Because the mode travels into the contain
environment variable, **stop and start the project** after changing it for the scheduler to see the environment variable, **stop and start the project** after changing it for the scheduler to see the
change. Remember that a headless run cannot answer a permission prompt, so in any mode other than change. Remember that a headless run cannot answer a permission prompt, so in any mode other than
**Auto** or **Bypass** a task may stop early when Claude Code asks for approval (in Auto, blocked **Auto** or **Bypass** a task may stop early when Claude Code asks for approval (in Auto, blocked
actions are denied instead, unless Auto is unavailable and Claude Code falls back to prompting); the run log records the mode actions are denied instead, unless Auto is unavailable and Claude Code falls back to
prompting); the run log records the mode
that was used. that was used.
### Creating Tasks ### Creating Tasks
+2 -1
View File
@@ -64,7 +64,8 @@ TASK_TYPE=$(jq -r '.type' "$TASK_FILE")
# mode other than "bypass" means the task may stop early when Claude Code asks # mode other than "bypass" means the task may stop early when Claude Code asks
# for permission. In "auto", classifier-blocked actions are denied instead of # for permission. In "auto", classifier-blocked actions are denied instead of
# prompted, but if auto mode is unavailable for the session's model/backend, # prompted, but if auto mode is unavailable for the session's model/backend,
# Claude Code falls back to prompting and the same stall applies. Unset or unrecognized values pass no flag (Claude's default). # Claude Code falls back to prompting and the same stall applies.
# Unset or unrecognized values pass no flag (Claude's default).
PERMISSION_ARGS=() PERMISSION_ARGS=()
case "${TRIPLE_C_PERMISSION_MODE:-}" in case "${TRIPLE_C_PERMISSION_MODE:-}" in
plan) PERMISSION_ARGS=(--permission-mode plan) ;; plan) PERMISSION_ARGS=(--permission-mode plan) ;;