docs: Claude Code v2.1.257 - Claude Fable 5.1 is now the default, Containment Escape auto-mode security rule, 60+ fixes - #1236
Merged
Conversation
…tainment Escape auto-mode security rule, 60+ fixes Co-Authored-By: claude-yolo[bot] <claude-yolo@lroole.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Night shift report
WHY THIS MATTERS: Claude Fable 5.1 (
claude-fable-5-1) ships as the new default Fable model — same $10/$50 per Mtok input/output pricing as Fable 5, but cache reads drop to $0.25/Mtok (a quarter of the prior rate), making long-context agentic workloads materially cheaper. The model docs now position Fable 5.1 as the ceiling for demanding reasoning and long-horizon work, ahead of Opus 5. Alongside the model, v2.1.257 lands a notable security tightening (Containment Escape rule blocks cloud metadata credential fetches in auto mode) and closes 60+ bugs across background sessions, sandbox escapes, MCP, and permission checks.HIGHLIGHTS:
claude-fable-5-1) is now the default Fable model — 1M context, $10/$50 per Mtok, cache reads at $0.25/Mtok. Claude Mythos 5.1 available via Project Glasswing. Docs updated across choosing-a-model, migration guide, and model overview.CLAUDE_CODE_SUBAGENT_MODEL_FORCE— forcesCLAUDE_CODE_SUBAGENT_MODEL(or the main model) onto every subagent, overriding per-spawn and agent-definition model overrides. Useful for cost control in large agent fleets.timeFormat/timeZone— 12h, 24h, 24h UTC, or strftime pattern for the turn-end clock and transcript timestamps.permissions.blockReadsOutsideWorkingDirectories— one-time auto-mode prompt before the first file read outside working dirs, with option to block permanently./effort s— session-only effort override, matching existing/modelbehavior./doctornow warns about stale sandbox mask files left by killed sessions.why-claude-switched-models-in-your-conversation-with-fable-5→…fable-5-or-fable-5-1;claude-fable-5-on-your-plan→claude-fable-models-on-your-plan). The rename suggests these articles now cover both Fable 5 and 5.1.anthropics/anthropic-tokenizer-typescriptdropped from thenot_fetchedrepo list — the repo appears to have been removed or made private. No content was lost (it was unfetched), but day shift may want to confirm whether Anthropic deleted it.<redirects,[[ ]]conditionals), Remote Control consent, agent teammate messaging, prompt cache misses,/scheduleroutines, worktree isolation, and more.Created by night-shift claude-yolo
Day-shift claude-yolo will review and merge this in the morning