codex rust-v0.154.0-alpha.4
Release 0.154.0-alpha.4
Updated 2026-09-05 12:15 UTC
What the AI labs actually published today, pulled straight from their own blogs, changelogs and status pages. No commentary, no rewritten headlines, nothing from a rumour account.
77 items over the last seven days · every day we've collected
Items a day over the last 14 days, busiest 21.
It's early. The labs mostly publish during the American working day, so a quiet morning here is normal rather than a sign we've stopped looking.
1 item from 1 lab. 1 release.
Release 0.154.0-alpha.4
10 items from 3 labs. 1 post, 5 releases, 1 changelog entry, 1 incident and 2 deprecations. OpenAI was busiest with 5.
Bug Fixes Fixed Astra’s visibility in the bundled model picker and made it the bundled default when no model is explicitly configured. ( #42874 ) Updated Astra’s guidance to use asynchronous questions only when the tool is available in the session. ( #42878 ) Changelog Full Changelog: rust-v0.153.3...rust-v0.153.4 #42874 [0.153 hotfix] Show Astra in bundled model picker @rhan-oai #42878 [0.153 hotfix] Qualify Astra async-question guidance by tool availability @rhan-oai
1.4.0 (2026-09-04) Full Changelog: v1.3.0...v1.4.0 Features api: add Claude Tag category and user breakdowns to usage reports ( 9fce1e4 ) api: add named types for organization compliance settings state ( 1de1957 ) api: add support for sending a workspace ID on more endpoints ( d1d2c01 ) Bug Fixes client: raise a clear error when an httpx object is passed instead of an httpx2 one ( 9447099 ) repair custom-code merge in messages resources ( #580 ) ( 85454ca ) Chores examples: refresh platform model IDs ( #499 ) ( 182abb5 ) internal: bundle the mock server spec and update dev tooling ( f9b0cf2…
Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters Added --append-subagent-system-prompt-file to read the subagent system prompt from a file, for prompts too large to pass on the command line Added /skill-doctor to show which loaded skills go unused and what they cost in context, so you…
What's changed Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters Added --append-subagent-system-prompt-file to read the subagent system prompt from a file, for prompts too large to pass on the command line Added /skill-doctor to show which loaded skills go unused and what they cost in…
New Features Added GPT-6-Astra to the Amazon Bedrock model picker for Mantle and Runtime global/US routes. ( #42805 ) Bug Fixes Corrected GPT-6-Astra’s guidance for asynchronous clarification questions to use the supported tool and recognize that it accepts text only. ( #42809 ) Changelog Full Changelog: rust-v0.153.2...rust-v0.153.3 #42805 [0.153 hotfix] Add GPT-6-Astra to Amazon Bedrock catalogs @celia-oai #42809 [0.153 hotfix] Update Astra async-question guidance @rhan-oai
Now tracking this page; changes will appear here as they happen. Latest announcements: 2026-08-26: Transcription models; 2026-07-20: Legacy audio, realtime, and transcription models; 2026-06-11: GPT-5 and o3 model deprecations; 2026-06-03: Reusable prompts; 2026-06-03: Evals platform; 2026-06-03: Agent Builder
Now tracking this page; changes will appear here as they happen. Latest announcements: 2026-06-05: Claude Opus 4.1 model; 2026-04-14: Claude Sonnet 4 and Claude Opus 4 models; 2026-02-19: Claude Haiku 3 model; 2025-12-19: Claude Haiku 3.5 model; 2025-10-28: Claude Sonnet 3.7 model; 2025-08-13: Claude Sonnet 3.5 models
Status: Resolved All impacted services have now fully recovered. Affected components Voice mode (Operational) Conversations (Operational) Image Generation (Operational) Codex Web (Operational) File uploads (Operational)
Release 0.154.0-alpha.3
Bug Fixes Corrected the GPT-6-Astra Fast tier description to say “2x speed, increased usage” instead of “1.5x.” This changes only the displayed text, not how requests run. ( #42632 ) Changelog Full Changelog: rust-v0.153.1...rust-v0.153.2 #42632 Fix GPT-6-Astra Fast tier description for 0.153.2 @anp-oai
What's changed Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field Added /reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists Added a text form of /advisor ( /advisor , /advisor <model> , /advisor off ) for the desktop app, Remote Control, and other headless ( -p /Agent SDK) sessions Added…
Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field Added /reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists Added a text form of /advisor (/advisor, /advisor , /advisor off) for the desktop app, Remote Control, and other headless (-p/Agent SDK) sessions Added oidc.scope_on_refresh to the…
Release 0.154.0-alpha.2
Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json); entries that name a command to run are skipped Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding Added recognition of glab mr create/merge/close/reopen/note/update so GitLab merge requests show as MR !N in the collapsed tool summary and refresh the footer MR badge Added --json to claude plugin validate for a machine-readable…
What's changed Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json ); entries that name a command to run are skipped Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding Added recognition of glab mr create/merge/close/reopen/note/update so GitLab merge requests show as MR !N in the collapsed tool summary and refresh the footer MR badge Added --json to claude plugin validate for a…
Sep 2 , 21:44 UTC Resolved - The issue affecting Claude Sonnet 5 has been resolved. Impact occurred from 2:05pm PT / 21:05 UTC to 2:19pm PT / 21:19 UTC. Sep 2 , 21:17 UTC Investigating - We are investigating elevated errors on requests to Claude Sonnet 5. We will provide an update as soon as possible.
Status: Resolved The issue affecting new account creation has been resolved.
Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255 Fixed remote and scheduled sessions failing with "user messages must have non-empty content" after a re-sent permission approval could not be applied
What's changed Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255 Fixed remote and scheduled sessions failing with "user messages must have non-empty content" after a re-sent permission approval could not be applied
Release 0.153.0-alpha.4
Aug 31 , 20:36 UTC Resolved - The issue affecting Claude Code has been resolved. Impact occurred from 16∶55 to 19∶16 UTC. Aug 31 , 19:21 UTC Investigating - We are investigating reports of degraded performance affecting Claude in Slack, Claude Code on the web, and Code Review. We will provide an update as soon as possible.
Status: Resolved All impacted services have now fully recovered. Affected components ChatGPT Work (Operational)
Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit
What's changed Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit
3.6.0 (2026-08-27) Features api: add compute_units to Responses and Chat Completions usage ( #3749 ) ( 52421d1 ) Bug Fixes auth: harden X.509 workload identity integration ( #3740 ) ( fc3ad6c ) Chores deps-dev: bump @stdy/cli from 0.22.1 to 0.22.2 ( #3719 ) ( 4f5598c ) deps-dev: bump mypy from 1.17 to 2.3.1 ( #3747 ) ( 0b52c9e ) deps-dev: bump pandas-stubs from 2.2.2.240807 to 2.3.3.260113 ( #3659 ) ( 95f0b43 ) deps-dev: bump pyright from 1.1.399 to 1.1.413 ( #3744 ) ( 9917c6e ) deps-dev: bump rich from 14.2.0 to 15.0.0 ( #3717 ) ( 7a5484d ) deps: bump actions/checkout from 6.0.2 to 7.0.1 (…
Aug 28 , 20:21 UTC Resolved - The issue affecting Claude Cowork and Claude Code on the web has been resolved. Aug 28 , 18:21 UTC Monitoring - A mitigation has been applied for the issue affecting Claude Cowork and Claude Code on the web, and we are monitoring for recovery. Sessions that disconnected earlier can be retried Aug 28 , 17:22 UTC Identified - We have identified an issue with an upstream cloud provider affecting Claude Cowork and Claude Code on the web. Some sessions may fail to start or disconnect mid-task; affected sessions can be retried. We are in contact with the provider and…
Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the estimated re-cache cost Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only) Added a Spend limit bar to /usage and a rate_limits.spend_limit status line field for developers behind a Claude apps gateway with spend limits Added a per-session prompt-cache line to /cost (hit ratio, misses, tokens re-cached, warm/cold) and a matching…
What's changed Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the estimated re-cache cost Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only) Added a Spend limit bar to /usage and a rate_limits.spend_limit status line field for developers behind a Claude apps gateway with spend limits Added a per-session prompt-cache line to /cost (hit ratio, misses, tokens re-cached, warm/cold)…
Status: Resolved All impacted services have now fully recovered. Affected components Agent (Operational) ChatGPT Work (Operational)
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 <label> (or SELF_HOSTED_RUNNER_CLIENT_LABEL ) to override the label the runner registers with (default: hostname) Added…
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-managed settings…
1.2.0 (2026-08-27) Full Changelog: v1.1.0...v1.2.0 Features api: beta files/skills namespaces use GA shapes; drop dated beta header pins ( 9df4565 ) Bug Fixes aws,bedrock: sign raw request bytes so binary file uploads work ( #531 ) ( f50e910 ) ci: resolve assignment aliases in detect-breaking-changes ( f2c4925 ) sessions: make event accumulator forward-compatible with new event types ( #533 ) ( cbbaf6e ) tools: let read return a view_range of a file over the size cap ( #538 ) ( b68e876 ) tools: preserve exact file bytes in the agent toolset and memory tool (no newline translation) ( #540 ) (…
Everything a single lab has published, with its current models and prices underneath.
We fetch 23 sources every fifteen minutes: lab blogs, GitHub release notes, product changelogs, status pages and deprecation tables. Anything new goes on the page within the quarter hour.
Four of the labs publish a feed you can subscribe to yourself. The rest don't, and we wrote down which is which.
Once a day is over its page settles, so a link to 5 Sep 2026 still shows 5 Sep 2026 next year. A late post can still slot into a past day, if that's the date the lab put on it. If you want a model instead of a date, Model Watch collects everything said about one model in one place, and the price table has what each one costs.