› Protime Labs / Signals
A filtered read of AI-agent, Microsoft 365 Copilot, and Anthropic enterprise news — pulled daily, scored for relevance, and pruned to what an enterprise architect actually needs to know. Source links open externally.
Breaking Claude Code Opus 5 Auto Mode Anthropic are putting a great deal of faith in Claude Code's auto mode for protecting their coding agent users against prompt injection attacks. They recently made that the default and have made bold claims about its effectiveness. Johann Rehberger is one of the most credible prompt injection researchers active today. He found an attack against auto mode which he claims works 80% of the time, by tricking Claude Code into downloading and uncompressing a zip archive, then executing code that imports base64 without noticing that this will import and execute a
What's changed Added --restricted (or CLAUDE_CODE_RESTRICTED=1 ): removes the built-in tools that run commands or code and WebFetch (unless named in --tools ), keeps file tools inside the working directory, refuses bypassPermissions , and ignores user, project and local settings files Added experimental.cacheTtl ( "5m" or "1h" ) to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured Added claude self-hosted-runner --client-label (or SELF_HOSTED_RUNNER_CLIENT_LABEL ) to override the label the runner registers with (default: hostname) Added server-mana
What's changed Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting) Added {id, text, cooldownSessions, priority} entries, tipsFile , and label to spinnerTipsOverride , so organizations can rotate their own tips alongside the built-in ones Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost
0.121.0 (2026-08-26) Full Changelog: sdk-v0.120.0...sdk-v0.121.0 Features api: add updates thinking display mode (beta) ( 22274ea ) api: add missing anthropic-beta values ( 0779f02 ) api: add support for Organization API endpoints ( 8b61e7a ) helpers: support Standard Schema for structured outputs and tools ( 7880078 ) Bug Fixes tools: keep the tool runner going on pause_turn ( #288 ) ( f040dc9 ) types: don't reference NodeJS.ProcessEnv from published types ( #367 ) ( fd38dfd ) Chores docs: clarify skill version latest support and memory version retention ( 7405a69 ) examples: remove redundant
1.1.0 (2026-08-26) Full Changelog: v1.0.0...v1.1.0 Features api: add updates thinking display mode (beta) ( eb4a73f ) api: add missing anthropic-beta values ( dbebd15 ) api: add support for Organization API endpoints ( 5a5b8fc ) Bug Fixes docs: correct link for long requests error ( #1884 ) ( 4474f31 ), closes #1883 tools: keep the tool runner going on pause_turn ( #343 ) ( ab1ec60 ) Chores docs: clarify skill version latest support and memory version retention ( a754f3b ) internal: cancel superseded CI runs ( c061ab1 ) internal: minor workflow reformat ( 1569002 ) internal: remove the legacy
What's changed Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main) ), since they also match options inserted before the subcommand Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base
Release: llm-anthropic 0.27 This release of the Anthropic plugin for LLM mainly provides compatibility with the recently released anthropic v1.0.0 Python library, which switches from httpx to httpx2 . OpenAI made the same change in their v3.0.0 release two weeks ago. Anthropic provide this migration guide for upgrading to 1.0, so I prompted Fable 5 in Claude Code with: Upgrade to anthropic>=1 - read https://raw.githubusercontent.com/anthropics/anthropic-sdk-python/refs/heads/main/MIGRATION.md and get the tests passing Here's the resulting PR . Tags: python , httpx , llm , anthropic , claude
Anthropic’s best AI model struggles to attract users as cheaper tools thrive A few interesting numbers in this FT story gathered from "people with knowledge of the matter": Anthropic's "annualized revenue" for July is up to $65bn - it was $47bn in May, and I collected more historic numbers here . Anthropic expect Q3 to be profitable according to the same model they used to declare Q2 profitable. "It also told investors that it had 6,000 customers that spend $100,000 annually or more." As for OpenAI, "annualised revenue has jumped 35 per cent in the quarter to date and is now over $40bn, with t
Prior to Fable, it felt silly to waste too much time improving your coding harness or context strategies. A new model would arrive at the same price (or cheaper!) and paper over most of your problems. But then Fable landed. It was (and still is!) incredible . But the cost was so high and Opus was good enough (as was 5.6, K3, and even GLM) for most of the code we needed. So we started to think about what work went where. — Drew Breunig , Fable & The End of the Free Lunch Tags: drew-breunig , anthropic , claude , llm-pricing , ai , llms , generative-ai , claude-mythos-fable
Configure retention for Microsoft 365 Copilot memory to help preserve historical versions of memory items for security, compliance, and investigation scenarios. Copilot memory includes saved memories and details inferred from chat history that enable more personalized and context-aware Copilot experiences. Copilot memory items are stored in a hidden folder in the user’s Exchange mailbox. This capability will enable retention and versioning support for inactive memory items so that administrators can maintain visibility into memory changes while active memory continues to be managed by the Copi