This Month in Claude
A plain-English digest of what's changed recently across Claude โ so you can skim "what's new and what it means for me" without reading every changelog. Newest first.
:::info How this page stays current Entries are added by the community and by an automated watcher that flags upstream changes for a human to write up. Each entry links its official source. See something missing? Add it. :::
How to read an entryโ
Each update is tagged by surface โ ๐ฃ๏ธ Apps (chat/voice/mobile), ๐ ๏ธ Claude Code, ๐ API, ๐ง Models โ and answers "what it means for you."
Recent updatesโ
- ๐ ๏ธ Claude Code โ Self-hosted environments shipped August 7, 2026 in beta (Claude Code v2.1.224) on Team and Enterprise plans โ a first-party way to execute Claude Code cloud sessions (web, mobile, desktop,
claude --cloud, scheduled routines) on your own hosts while orchestration and inference stay onapi.anthropic.com. Three moving parts, same shape as GitHub Actions: an environment (a named destination created on the Cloud environments admin page, IDccpool_...), one or more runners (long-livedclaude self-hosted-runnerprocesses on your Linux or macOS hosts), and sessions (spawned childclaudeprocesses that clone the repo and stream events back). Every connection is outbound HTTPS โ Anthropic never opens a port into your network. The operational surprise: a runner locks to the first user that lands on it and only serves that user until it drains, so minimum fleet size = concurrent active users, not concurrent sessions. Not available under ZDR; inference can't be routed off Anthropic (no Bedrock, Vertex, Foundry, or LLM gateway); GitHub-only checkouts today; Claude Tag, Claude Security, and Code Review sessions don't route yet. What it means: the full practitioner guide โ the four-command quickstart, the--drain-grace-sec/--retire-atlifecycle, the network shape, the production checklist, and the six gotchas (including the show-once environment secret and the 5-minute clock-skew auth failure) โ is at Self-Hosted Environments: run cloud sessions on your own boxes. - ๐ API โ Inference Hooks shipped August 5, 2026 in beta for Claude Enterprise โ a first-party, HTTPS webhook (not a WebSocket, despite some coverage) that lets your DLP or in-house AI security server allow-or-deny every governed prompt on claude.ai, Claude Code, and Cowork before the model sees it. One config covers all three surfaces. Every request is signed per Standard Webhooks (HMAC-SHA256 over
{webhook-id}.{webhook-timestamp}.{raw body}with yourwhsec_secret), the verdict is a small JSON object ({"action": "allow"}or{"action": "deny", "deny_reason": "..."}โ deliberately noredacttoday), and the transcript your server sees is what the user sees (text, tool calls, extracted attachment text) โ never system prompts, hidden reasoning, or raw file bytes. What it means: the biggest ops levers are the verdict timeout (1โ10 000 ms, 5 s default), failure handling (block vs allow uninspected), and the circuit breaker that stops enforcement on sustained failures โ get the deep-dive with the two signing bugs that catch every first integration and the shadow โ percentage โ role-exclusion โ enforce rollout playbook at Inference Hooks: inline DLP for Claude Enterprise. - ๐ API (cross-AI) โ MCP Apps, the first official Model Context Protocol extension, is now covered in depth on AILmanac. Finalized January 26, 2026 and folded into the 2026-07-28 stateless core spec, MCP Apps lets a server ship an HTML UI that any MCP client renders in a sandboxed iframe, with the iframe speaking JSON-RPC 2.0 over
postMessageback to the host. Extension identifierio.modelcontextprotocol/ui, MIMEtext/html;profile=mcp-app, resources atui://<server>/<name>, tools link via_meta.ui.resourceUri. Default CSP isconnect-src 'none'โ a UI cannot fetch anywhere until the resource declaresconnectDomains. What it means: every UI-initiated write is still a normal tool call the host mediates โ Apps can render and propose, they cannot silently execute. The full deep-dive on when it beats a plain result, the wire shapes, and the security model: MCP Apps: Interactive UIs Inside a Tool Call. - ๐ฃ๏ธ Apps โ Claude Cowork now runs on web + mobile with scheduled tasks โ launched July 7, 2026 (Max first, other paid plans rolling in over the following weeks). The architectural shift: Cowork sessions now execute on Anthropic's servers, not your machine, so scheduled tasks run on their cadence with the laptop closed and no device online. Frequency options are hourly / daily / weekdays / weekly / manual (no cron), each run spawns a fresh session with your connectors + skills + plugins, and approval prompts get pushed to your phone mid-run. Local file / browser / computer use stay desktop-only โ audit any scheduled prompt for local-machine actions or it'll silently skip them. What it means: the practical playbook (capability-by-surface matrix, the Dispatch-vs-Scheduled-vs-Interactive distinction, and the four gotchas that break silent runs โ including OAuth drift and the "if I'm asleep" timeout hole) is at Cowork Scheduled Tasks: Agents That Run With No Device On.
- ๐ง Models (cross-AI) โ OpenAI previewed its "next major model" Astra on August 1, 2026 โ not with a keynote, but by pushing ten Lean-4 formalized proofs of previously unsolved problems (sphere packing, Connes rigidity, non-sofic groups, quantum parallel repetition, Ramsey lower bounds, etc.) to
openai/ten-proofs. OpenAI described Astra as a multi-agent, long-horizon system that "coordinates multiple agents working together on long-running tasks over hours or days." What it means: there is no API, no pricing, no ChatGPT surface, and no release date โ Astra is internal-only and heading into the new U.S. federal review process. The widely-quoted "$2,000" figure is the token cost at Sol's API rates, not Astra's price. Your Claude vs GPT-5.6 vs Gemini decision this month does not change; keep shipping. Full "confirmed vs unknown" breakdown, the ten problems, and a should-I-wait rule of thumb: OpenAI Astra: The Preview Field Note. - ๐ API โ Enterprise user-management endpoints entered beta on July 13, 2026 โ the Admin API's members and invites endpoints are now callable on Claude Enterprise organizations (in addition to Console), and a new set of RBAC group and custom-role endpoints ships alongside them. Groups and custom-role routes require
anthropic-beta: ce-user-management-2026-07-13and DROP theanthropic-versionheader; members and invites take neither. Scopes are granular (read:members,write:members,read:rbac_groups,write:rbac_groups,read:org_audit). What it means: you can now automate offboarding, quarterly group audits, and JIT hire onboarding entirely from CI โ see the full playbook and the three gotchas at The Admin API: automate your Claude org. - ๐ API โ Managed Agents Memory Stores entered public beta on July 22, 2026 โ a first-party, server-side persistent-memory primitive for Managed Agents. Stores mount into the session sandbox at
/mnt/memory/<slug>/and the agent reads/writes them with its standard file tools. Every write creates an immutable memory version (30-day retention minimum), you can redact history for compliance, andcontent_sha256preconditions give you optimistic concurrency. Limits: 8 stores per session, 2,000 memories per store, 100 kB per memory. What it means: the biggest header gotcha โ memory-store endpoints useagent-memory-2026-07-22; session endpoints (including attaching a store) still usemanaged-agents-2026-04-01, and sending both on the same request returns 400. Full walkthrough: Managed Agents Memory Stores. - ๐ง Models โ Claude Opus 5 (
claude-opus-5) shipped July 24, 2026 โ Anthropic's fourth model in two months. Same $5 in / $25 out per MTok pricing as Opus 4.8, same 1M context and 128k output, but materially better numbers: 44.4% on Frontier-Bench v0.1 (vs Opus 4.8's 18.7%), 96.0% on SWE-bench Verified, 30.16% on ARC-AGI-3. Now the default on Claude Max and strongest available on Claude Pro. Two contract changes will break naive migrations: adaptive thinking is on by default and shares yourmax_tokensbudget, andthinking: {"type": "disabled"}now returns 400 at the newxhighormaxeffort tiers. What it means: if you pinclaude-opus-4-8, read Claude Opus 5: The Field Guide before flipping the ID, and plan the Opus 4.1 โ Opus 5 migration before the 5 August 2026 retirement. - ๐ ๏ธ Claude Code โ Screen reader mode shipped July 14, 2026. Turn it on with
claude --ax-screen-reader,CLAUDE_AX_SCREEN_READER=1, or"axScreenReader": truein settings: it plain-texts the transcript, hides decorative glyphs, flattens nested tables intoHeader: value.lines, and announces permission-mode changes aloud when you cycle with Shift+Tab. The same release addedvimInsertModeRemaps(mapjjโ Escape) and mouse-click support in fullscreen menus. What it means: the CLI is now usable with assistive tech and lower-strain input โ see Claude Code Accessibility. - ๐ ๏ธ Claude Code โ In-app browser on Desktop (Week 28, July 6โ10, 2026): Claude Code on desktop gets a built-in browser, so Claude can pull up docs, designs, or any site and interact with pages the way it already does with local dev-server previews. Also that week:
/doctor(alias/checkup) is a full setup checkup that diagnoses and can fix issues, and auto mode now blocks transcript tampering and asks beforerm -rfon unresolved variables. What it means: Claude can verify against real web pages without leaving the session, and setup problems get a one-command diagnosis. - ๐ง Models โ Claude Sonnet 5 shipped June 30, 2026 and is now the default model in Claude Code, with a native 1M-token context window and introductory pricing through August 31, 2026. It's the new balanced "start here" Sonnet tier, superseding Claude Sonnet 4.6 (now a legacy model). What it means: if you pin a model, migrate to
claude-sonnet-5โ but read Claude Sonnet 5: The Field Guide first, because non-defaulttemperature/top_p/top_know returns 400, manual extended thinking returns 400, adaptive thinking is on by default, and the new tokenizer produces ~30% more tokens for the same text. Also check the Current Models & Pricing table for exact IDs and live pricing before relying on a number from a blog post. - ๐ ๏ธ Claude Code โ Dynamic workflows are in research preview: ask for one (or set
/effort ultracode) and Claude writes a JavaScript script that orchestrates tens to hundreds of subagents in the background โ for codebase-wide audits, large migrations, and cross-checked research. Run/deep-researchto see the bundled one, or/workflowsto watch runs. What it means: you can now take on fleet-scale tasks one conversation could never coordinate, with the orchestration saved as a rerunnable command. See Dynamic Workflows & ultracode. - ๐ง Models โ A new top-tier model, Claude Fable 5 (
claude-fable-5) and its Glasswing-only sibling Mythos 5 (claude-mythos-5) shipped June 9, 2026 on Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud and Microsoft Foundry โ Anthropic's first "Mythos-class" models, sitting above Opus. They share a 1M-token context, up to 128K output, and $10 / $50 per MTok pricing. What it means: Fable 5 is NOT a drop-in for Opus 4.8 โ it refuses in-band as HTTP 200 withstop_reason: "refusal", adaptive thinking is the only mode, raw chain-of-thought is never returned, and Anthropic added a newfallbacksparameter + SDK middleware + fallback-credit billing specifically for retries on Opus 4.8. It also carries mandatory 30-day retention (no ZDR). See the full field guide โ Claude Fable 5 & Mythos 5: The Flagship Field Guide. - ๐ ๏ธ Claude Code โ Subagents can now spawn their own subagents (up to 5 levels deep), and
/code-review --fixapplies review findings to your working tree. What it means: delegation composes deeper, and review can close the loop instead of just reporting. Cross-check the official changelog for exact behavior. - ๐ API โ Capabilities like structured output, extended thinking, and prompt caching evolve. What it means: re-check the API section before relying on exact parameters.
Want the firehose?โ
This is a digest, not a complete log. For everything: