Compare commits

..

8 Commits

Author SHA1 Message Date
GitHub Actions
125d63feae chore: Update CHANGELOG.md and feed.xml 2026-07-02 23:35:12 +00:00
GitHub Actions
5dc12eb281 chore: Update CHANGELOG.md and feed.xml 2026-07-02 22:54:58 +00:00
GitHub Actions
75709eacf1 chore: Update CHANGELOG.md and feed.xml 2026-07-01 20:45:29 +00:00
GitHub Actions
a56ff02e85 chore: Update CHANGELOG.md and feed.xml 2026-06-30 17:56:30 +00:00
GitHub Actions
c80896ca84 chore: Update CHANGELOG.md and feed.xml 2026-06-29 23:27:25 +00:00
Roy Arsan
3c3558207e Merge pull request #72363 from anthropics/royarsan/gateway-gcp-agent-platform
Gateway GCP example: Agent Platform rebrand and README cleanup
2026-06-29 18:26:37 -05:00
Roy Arsan
f605f0b68d Gateway GCP example: Agent Platform rebrand and README cleanup
- Update Vertex AI prose references to Agent Platform across the example
  (READMEs, script/terraform comments, config template). Functional
  identifiers are unchanged: the 'provider: vertex' config key,
  roles/aiplatform.user, aiplatform.googleapis.com, and the terraform
  resource label (renaming it would recreate the IAM binding in existing
  states). First mentions keep '(formerly Vertex AI)' for searchability.
- Drop the README's self-referential public-mirror link.
2026-06-29 23:13:09 +00:00
Roy Arsan
27e561ba3d Merge pull request #72361 from anthropics/royarsan/gateway-gcp-example
Add Claude Gateway on GCP example deployment assets
2026-06-29 17:45:07 -05:00
7 changed files with 222 additions and 75 deletions

View File

@@ -1,5 +1,102 @@
# Changelog
## 2.1.199
- Stacked slash-skill invocations like `/skill-a /skill-b do XYZ` now load all leading skills (up to 5), not just the first
- Fixed SSL certificate errors (TLS-inspecting proxies, missing `NODE_EXTRA_CA_CERTS`, expired certs) burning retries before showing actionable guidance — they now fail immediately with the fix hint
- Fixed streaming responses being discarded when the API emits a mid-stream overloaded/server error after partial output — the partial is now kept with an incomplete-response notice
- Fixed subagents cut off by a rate limit or server error silently failing instead of returning their partial work to the parent
- Fixed subagents reporting API errors (e.g. usage limit reached) as successful results — the error is now reported to the parent agent
- Fixed the background-agent daemon on Linux killing itself and every running agent every ~50 seconds after an unclean shutdown left a corrupted worker record
- Fixed background agents failing to cold-start over SSH on macOS with "Could not switch to audit session" (regression in 2.1.196)
- Fixed `claude stop` being silently undone when it raced a background-agent respawn — the respawn now honors the stop
- Fixed background job progress indicators stalling for minutes while the job ran long commands
- Fixed background sessions on memory-starved machines showing a generic error — they now indicate low memory and suggest freeing resources
- Fixed remote sessions briefly flapping between Working and Idle in the agent view when a background agent completes
- Fixed idle subagents vanishing from the agent panel while other subagents were still working; surplus idle agents now collapse into an expandable summary row
- Fixed typing `/model` or `/fast` while viewing a subagent silently opening the lead's model picker — a notice now explains the command applies to the lead
- Fixed `SessionStart`, `Setup`, and `SubagentStart` hooks silently hiding stderr when exiting with code 2 — the error is now shown in the transcript
- Fixed `claude --dangerously-skip-permissions daemon <subcommand>` being treated as a chat prompt instead of running the subcommand
- Fixed `SendMessage` silently misrouting when a re-spawned agent reuses a previous agent's name — the tool now detects the mismatch and asks the caller to retarget
- Fixed opening or resuming a session with no new messages needlessly growing the transcript file
- Fixed backgrounding a session with `←` or `/background` dropping its `/color` from the agent view row
- Fixed resetting a corrupted config file from the startup recovery dialog destroying it unrecoverably — it now backs up the file first
- Fixed Claude in Chrome repeatedly opening the reconnect page when sessions run from different builds or config directories
- Fixed plan mode not prompting for state-changing browser tool calls; read-only `browser_batch` calls are now correctly auto-allowed
- Transient server rate-limit errors (429s unrelated to your usage limit) are now retried automatically with backoff for subscribers instead of failing the turn
- `CLAUDE_CODE_RETRY_WATCHDOG` now raises the default retry count for non-capacity transient errors to 300 and lifts the cap of 15 on `CLAUDE_CODE_MAX_RETRIES`
- `claude agents` session rows now show pull-request links as bare `#N` without the redundant "PR" label
## 2.1.198
- Subagents now run in the background by default, so Claude keeps working while they run and is notified when they finish (previously a gradual rollout)
- Claude in Chrome is now generally available
- Added background agent notifications in `claude agents` — sessions that need input or finish now fire the `Notification` hook (`agent_needs_input` / `agent_completed`)
- Added `/dataviz` skill for chart and dashboard design guidance with a runnable color-palette validator
- Gateway: added Claude Platform on AWS (anthropicAws) as an upstream provider; model-not-found responses now advance the failover chain
- Background agents launched from `claude agents` now commit, push, and open a draft PR when they finish code work in a worktree, instead of stopping to ask
- The built-in Explore agent now inherits the main session's model (capped at opus) instead of running on haiku
- Subagents and context compaction now inherit the session's extended thinking configuration, improving output quality on delegated tasks
- Fixed brief network drops mid-response aborting the turn — transient errors like ECONNRESET now retry with backoff instead of failing
- Fixed excessive background classifier requests when sandboxed processes repeatedly accessed the same network host
- Fixed background tasks in web, desktop, and VS Code task panels getting stuck on "Running" after they finish or after resuming a session
- Fixed agent teams: a teammate that dies on an API error now reports "failed" to the lead, and messaging a stuck teammate wakes it to retry immediately
- Fixed the `/diff` panel not refreshing when you switch branches or commit outside the session
- Fixed markdown tables overflowing and wrapping their right border when rendered in fullscreen mode
- Fixed Claude Platform on AWS and Mantle sessions dead-ending with "Please run /login" when the STS token expires — `awsAuthRefresh` now runs automatically
- Fixed "no route to host" for local-network hosts in macOS background agent sessions by declaring Local Network entitlements
- Fixed `/desktop` failing with "Cannot determine working directory" after entering and exiting a worktree
- Fixed background agents repeatedly showing "Reconnecting…" every ~52 seconds on macOS while the agents view was open
- Fixed pressing `←` inside `claude attach <id>` exiting to the shell instead of opening the agent view
- Fixed `claude --bg` silently creating an unattachable session when combined with `--print`/`-p`; the conflicting flags are now rejected up front
- Fixed the workflow progress view dropping the earliest agents from the list while the phase counter stayed correct in SDK and desktop-app sessions
- Fixed `.claude/rules/` conditional rules not loading when the target file is reached via a symlinked path
- Fixed Cmd+click not opening URLs in fullscreen mode in Warp on macOS
- Fixed double-click word selection in fullscreen mode to select the entire URL including the scheme
- Fixed plan mode not auto-allowing read-only tool calls when a session starts in plan mode
- Fixed `/branch` deriving its default fork name from the compaction summary instead of the first real prompt
- Improved focus mode: subagents launched in a turn now appear in its activity summary, and completed background notifications fold into a single count
- Improved syntax highlighting accuracy in code blocks, diffs, and file previews by upgrading to highlight.js 11
- Keyboard shortcut hints now show opt/cmd instead of alt/super when connected from a Mac over SSH
- Improved API retry UX: the error reason is now shown after the second attempt, and a status page link replaces the spinner tip when the API is overloaded
- `/login` now opens the sign-in dialog from the `claude agents` view instead of saying it isn't available
- Subagents now treat messages from the agent that launched them as normal task direction; an agent's message is still never treated as the user's approval
- Removed the `/agents` wizard; ask Claude to create or manage subagents, or edit `.claude/agents/` directly
## 2.1.197
- Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5
## 2.1.196
- Added support for organization default models — admins set it in the org console; it shows as "Org default" (or "Role default") in `/model` when you haven't picked one yourself
- Added readable default names for sessions at start, making them easier to identify and message
- Added clickable file attachments in chat — Cmd/Ctrl-click reveals the file in Finder/Explorer
- Security: `claude mcp list`/`get` no longer spawn `.mcp.json` servers that a repo self-approved via a committed `.claude/settings.json`; untrusted workspaces show `⏸ Pending approval`
- Fixed waking a background job permanently deleting its conversation and re-running the original prompt when the transcript probe misread a real transcript; the file is now set aside, never deleted
- Fixed the rate-limit warning flickering off and rate-limit telemetry being over-counted when multiple parallel requests were in flight at the moment a usage limit was hit
- Fixed duplicate recap lines after a background session's turn: a schema-rejected StructuredOutput attempt no longer renders alongside its retry
- Fixed PowerShell `git diff`/`git grep`, `egrep`/`fgrep`, and quoted search patterns containing `|` being reported as failures when they exit 1, matching Bash behavior
- Fixed multiple `claude agents` side panel issues: keyboard focus getting stuck when opening an agent, background jobs losing their subagent types on every open, and sessions showing incorrect status while actively running
- Fixed `claude agents --dangerously-skip-permissions` silently falling back to auto mode instead of showing the bypass disclaimer and applying bypass mode to spawned agents
- Fixed mid-turn crash recovery for Remote sessions — sessions interrupted by a server restart now auto-resume on the next worker
- Fixed sessions moved with `/cd` reappearing in the old directory's resume list after a non-graceful exit when the old path contained special characters
- Fixed `claude plugin validate` skipping local plugins whose source is "." and stopping after the first error class
- Fixed Esc Esc at an idle prompt not opening the rewind menu (regression); use Ctrl+C or Ctrl+X Ctrl+K to stop background agents
- Fixed MCP OAuth requesting the authorization server's full `scopes_supported` catalog when no scope is specified, causing `invalid_scope` failures on GitLab self-hosted and other enterprise IdPs
- Fixed `/context` showing 0 tokens for all tool groups on Bedrock
- Fixed `/deep-research` misreporting verifier failures as "all claims refuted" instead of `unverified`
- Fixed plugin dependency version pins not being honored when the marketplace was added as a local folder path backed by a git repo
- Fixed `claude agents` session status: completed rows no longer flip between "Done" and "Needs your input", stalled agents are now labeled "Needs attention", and results that mention a PR show a clickable link
- Fixed voice dictation swallowing spaces and spuriously starting a recording during very fast typing when voice mode is enabled
- Improved background session reliability: long-running commands and workflows now survive the session's process being stopped, restarted, or updated — including on Windows, where background shells are handed off instead of being killed
- Improved background agents: workers killed by a daemon restart are now automatically resumed from where they left off the next time the agents view opens
- Improved `/code-review` workflow: merged five cleanup finders into one, cutting token usage by roughly 25%
- Reduced per-frame rendering work in the terminal UI by skipping no-op subtree walks during streaming
- The streaming idle watchdog is now on by default for all providers — it aborts and retries when a response stream produces no events for 5 minutes. Set `CLAUDE_ENABLE_STREAM_WATCHDOG=0` to disable.
- Remote Control is now disabled when `ANTHROPIC_BASE_URL` points at a non-Anthropic host, matching the existing behavior under `CLAUDE_CODE_USE_BEDROCK`/`_VERTEX`/`_FOUNDRY`
- Changed opening the agents view from a foreground session to require a single `←` press instead of two, matching the behavior in background sessions
## 2.1.195
- Added `CLAUDE_CODE_DISABLE_MOUSE_CLICKS` to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll

View File

@@ -1,18 +1,17 @@
# Claude Gateway on Google Cloud
Reference deployment artifacts for running Claude Gateway on GCP with Vertex AI
as the upstream: Cloud Run or GKE, Cloud SQL for PostgreSQL, Secret Manager, and
service-account auth to Vertex AI.
Reference deployment artifacts for running Claude Gateway on GCP with Agent
Platform (formerly Vertex AI) as the upstream: Cloud Run or GKE, Cloud SQL for
PostgreSQL, Secret Manager, and service-account auth to Agent Platform.
These files are provided as a working example rather than a supported production
deployment. Adapt them to your own environment.
- **Walkthrough**: https://code.claude.com/docs/en/claude-apps-gateway-on-gcp
- **Public mirror**: https://github.com/anthropics/claude-code/tree/main/examples/gateway/gcp
| File | Purpose |
|---|---|
| `setup.sh` | Scripts the walkthrough end to end via `gcloud` |
| `Dockerfile` | Runtime image for the `claude gateway` binary |
| `gateway.yaml.example` | Gateway config template, GCP-shaped (Vertex upstream, Google Workspace IdP) |
| `gateway.yaml.example` | Gateway config template, GCP-shaped (Agent Platform upstream, Google Workspace IdP) |
| `terraform/` | Provisions the full architecture (two-pass apply — see `terraform/README.md`) |

View File

@@ -1,7 +1,8 @@
# gateway.yaml.example — Claude Gateway config template, GCP-shaped (walkthrough §6).
#
# Google Workspace IdP + Vertex upstream, following the walkthrough at
# https://code.claude.com/docs/en/claude-apps-gateway-on-gcp. The active sections
# Google Workspace IdP + Agent Platform (formerly Vertex AI) upstream, following
# the walkthrough at https://code.claude.com/docs/en/claude-apps-gateway-on-gcp.
# The active sections
# below are a strict subset of the full configuration reference at
# https://code.claude.com/docs/en/claude-apps-gateway; optional keys are included
# commented-out.
@@ -88,11 +89,11 @@ session:
store:
postgres_url: ${GATEWAY_POSTGRES_URL} # private-IP Cloud SQL; built with ?sslmode=require by setup.sh
# ── Upstreams — Vertex AI ────────────────────────────────────────────────────
# ── Upstreams — Agent Platform ───────────────────────────────────────────────
upstreams:
- provider: vertex
region: us-east5 # a region where the Claude models you need are published in Model Garden
project_id: REPLACE_ME # your GCP project ID for Vertex access
project_id: REPLACE_ME # your GCP project ID for Agent Platform access
auth: {} # ADC via Cloud Run SA / GKE Workload Identity (preferred — no static keys)
# base_url: https://us-east5-aiplatform.p.googleapis.com # Private Service Connect endpoint
# Add more upstreams for failover (tried top→bottom on 5xx/timeout/501): a

View File

@@ -29,7 +29,7 @@ set -euo pipefail
# ---- configuration (env-overridable) ----------------------------------------
PROJECT_ID="${PROJECT_ID:-$(gcloud config get-value project 2>/dev/null)}"
REGION="${REGION:-${CLOUDSDK_COMPUTE_REGION:-us-east5}}" # guide §1 uses us-east5 (Vertex model region)
REGION="${REGION:-${CLOUDSDK_COMPUTE_REGION:-us-east5}}" # guide §1 uses us-east5 (Agent Platform model region)
SA_NAME="${SA_NAME:-claude-gateway}" # §2 service account
SA_EMAIL="${SA_NAME}@${PROJECT_ID}.iam.gserviceaccount.com"
@@ -157,7 +157,7 @@ fi
# and GKE.
gcloud projects add-iam-policy-binding "${PROJECT_ID}" \
--member="serviceAccount:${SA_EMAIL}" \
--role="roles/aiplatform.user" --condition=None >/dev/null # Vertex inference (§2)
--role="roles/aiplatform.user" --condition=None >/dev/null # Agent Platform inference (§2)
# ---- 3 Build & push image to Artifact Registry ----------------------------
log "Ensuring Artifact Registry repo and image (§3)"
@@ -390,7 +390,7 @@ fi
# Direct VPC egress (--network/--subnet/--vpc-egress) puts the service on the
# VPC so it reaches the Cloud SQL PRIVATE IP directly — matching the private-IP
# connection string in the postgres-url secret. private-ranges-only keeps public
# egress (Vertex, accounts.google.com) off the VPC, so no Cloud NAT is needed.
# egress (Agent Platform, accounts.google.com) off the VPC, so no Cloud NAT is needed.
# We deliberately do NOT use --add-cloudsql-instances (that's the Auth Proxy /
# socket path, which would need a different connection string).
#

View File

@@ -50,7 +50,7 @@ resource "google_service_account" "gateway" {
# Run and GKE.
resource "google_project_iam_member" "vertex" {
project = var.project_id
role = "roles/aiplatform.user" # Vertex inference
role = "roles/aiplatform.user" # Agent Platform inference
member = "serviceAccount:${google_service_account.gateway.email}"
}
@@ -310,7 +310,7 @@ resource "google_cloud_run_v2_service" "gateway" {
network = google_compute_network.vpc.id
subnetwork = google_compute_subnetwork.subnet.id
}
egress = "PRIVATE_RANGES_ONLY" # public egress (Vertex, accounts.google.com) bypasses the VPC -> no Cloud NAT needed
egress = "PRIVATE_RANGES_ONLY" # public egress (Agent Platform, accounts.google.com) bypasses the VPC -> no Cloud NAT needed
}
containers {

View File

@@ -6,7 +6,7 @@ variable "project_id" {
}
variable "region" {
description = "Infra region for Artifact Registry, Cloud SQL, subnet, and Cloud Run. (Vertex region is set separately inside gateway.yaml.)"
description = "Infra region for Artifact Registry, Cloud SQL, subnet, and Cloud Run. (Agent Platform region is set separately inside gateway.yaml.)"
type = string
default = "us-east5"
}

170
feed.xml
View File

@@ -6,7 +6,116 @@
<author><name>Anthropic</name></author>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/>
<link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/>
<updated>2026-06-26T21:29:36Z</updated>
<updated>2026-07-02T23:35:12Z</updated>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.199</id>
<title>Claude Code v2.1.199</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.199"/>
<updated>2026-07-02T23:35:12Z</updated>
<content type="html">&lt;p&gt;• Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first&lt;/p&gt;
&lt;p&gt;• Fixed SSL certificate errors (TLS-inspecting proxies, missing NODE_EXTRA_CA_CERTS, expired certs) burning retries before showing actionable guidance — they now fail immediately with the fix hint&lt;/p&gt;
&lt;p&gt;• Fixed streaming responses being discarded when the API emits a mid-stream overloaded/server error after partial output — the partial is now kept with an incomplete-response notice&lt;/p&gt;
&lt;p&gt;• Fixed subagents cut off by a rate limit or server error silently failing instead of returning their partial work to the parent&lt;/p&gt;
&lt;p&gt;• Fixed subagents reporting API errors (e.g. usage limit reached) as successful results — the error is now reported to the parent agent&lt;/p&gt;
&lt;p&gt;• Fixed the background-agent daemon on Linux killing itself and every running agent every ~50 seconds after an unclean shutdown left a corrupted worker record&lt;/p&gt;
&lt;p&gt;• Fixed background agents failing to cold-start over SSH on macOS with "Could not switch to audit session" (regression in 2.1.196)&lt;/p&gt;
&lt;p&gt;• Fixed claude stop being silently undone when it raced a background-agent respawn — the respawn now honors the stop&lt;/p&gt;
&lt;p&gt;• Fixed background job progress indicators stalling for minutes while the job ran long commands&lt;/p&gt;
&lt;p&gt;• Fixed background sessions on memory-starved machines showing a generic error — they now indicate low memory and suggest freeing resources&lt;/p&gt;
&lt;p&gt;• Fixed remote sessions briefly flapping between Working and Idle in the agent view when a background agent completes&lt;/p&gt;
&lt;p&gt;• Fixed idle subagents vanishing from the agent panel while other subagents were still working; surplus idle agents now collapse into an expandable summary row&lt;/p&gt;
&lt;p&gt;• Fixed typing /model or /fast while viewing a subagent silently opening the lead's model picker — a notice now explains the command applies to the lead&lt;/p&gt;
&lt;p&gt;• Fixed SessionStart, Setup, and SubagentStart hooks silently hiding stderr when exiting with code 2 — the error is now shown in the transcript&lt;/p&gt;
&lt;p&gt;• Fixed claude --dangerously-skip-permissions daemon &amp;lt;subcommand&amp;gt; being treated as a chat prompt instead of running the subcommand&lt;/p&gt;
&lt;p&gt;• Fixed SendMessage silently misrouting when a re-spawned agent reuses a previous agent's name — the tool now detects the mismatch and asks the caller to retarget&lt;/p&gt;
&lt;p&gt;• Fixed opening or resuming a session with no new messages needlessly growing the transcript file&lt;/p&gt;
&lt;p&gt;• Fixed backgrounding a session with ← or /background dropping its /color from the agent view row&lt;/p&gt;
&lt;p&gt;• Fixed resetting a corrupted config file from the startup recovery dialog destroying it unrecoverably — it now backs up the file first&lt;/p&gt;
&lt;p&gt;• Fixed Claude in Chrome repeatedly opening the reconnect page when sessions run from different builds or config directories&lt;/p&gt;
&lt;p&gt;• Fixed plan mode not prompting for state-changing browser tool calls; read-only browser_batch calls are now correctly auto-allowed&lt;/p&gt;
&lt;p&gt;• Transient server rate-limit errors (429s unrelated to your usage limit) are now retried automatically with backoff for subscribers instead of failing the turn&lt;/p&gt;
&lt;p&gt;• CLAUDE_CODE_RETRY_WATCHDOG now raises the default retry count for non-capacity transient errors to 300 and lifts the cap of 15 on CLAUDE_CODE_MAX_RETRIES&lt;/p&gt;
&lt;p&gt;• claude agents session rows now show pull-request links as bare #N without the redundant "PR" label&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.198</id>
<title>Claude Code v2.1.198</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.198"/>
<updated>2026-07-01T20:45:29Z</updated>
<content type="html">&lt;p&gt;• Subagents now run in the background by default, so Claude keeps working while they run and is notified when they finish (previously a gradual rollout)&lt;/p&gt;
&lt;p&gt;• Claude in Chrome is now generally available&lt;/p&gt;
&lt;p&gt;• Added background agent notifications in claude agents — sessions that need input or finish now fire the Notification hook (agent_needs_input / agent_completed)&lt;/p&gt;
&lt;p&gt;• Added /dataviz skill for chart and dashboard design guidance with a runnable color-palette validator&lt;/p&gt;
&lt;p&gt;• Gateway: added Claude Platform on AWS (anthropicAws) as an upstream provider; model-not-found responses now advance the failover chain&lt;/p&gt;
&lt;p&gt;• Background agents launched from claude agents now commit, push, and open a draft PR when they finish code work in a worktree, instead of stopping to ask&lt;/p&gt;
&lt;p&gt;• The built-in Explore agent now inherits the main session's model (capped at opus) instead of running on haiku&lt;/p&gt;
&lt;p&gt;• Subagents and context compaction now inherit the session's extended thinking configuration, improving output quality on delegated tasks&lt;/p&gt;
&lt;p&gt;• Fixed brief network drops mid-response aborting the turn — transient errors like ECONNRESET now retry with backoff instead of failing&lt;/p&gt;
&lt;p&gt;• Fixed excessive background classifier requests when sandboxed processes repeatedly accessed the same network host&lt;/p&gt;
&lt;p&gt;• Fixed background tasks in web, desktop, and VS Code task panels getting stuck on "Running" after they finish or after resuming a session&lt;/p&gt;
&lt;p&gt;• Fixed agent teams: a teammate that dies on an API error now reports "failed" to the lead, and messaging a stuck teammate wakes it to retry immediately&lt;/p&gt;
&lt;p&gt;• Fixed the /diff panel not refreshing when you switch branches or commit outside the session&lt;/p&gt;
&lt;p&gt;• Fixed markdown tables overflowing and wrapping their right border when rendered in fullscreen mode&lt;/p&gt;
&lt;p&gt;• Fixed Claude Platform on AWS and Mantle sessions dead-ending with "Please run /login" when the STS token expires — awsAuthRefresh now runs automatically&lt;/p&gt;
&lt;p&gt;• Fixed "no route to host" for local-network hosts in macOS background agent sessions by declaring Local Network entitlements&lt;/p&gt;
&lt;p&gt;• Fixed /desktop failing with "Cannot determine working directory" after entering and exiting a worktree&lt;/p&gt;
&lt;p&gt;• Fixed background agents repeatedly showing "Reconnecting…" every ~52 seconds on macOS while the agents view was open&lt;/p&gt;
&lt;p&gt;• Fixed pressing ← inside claude attach &amp;lt;id&amp;gt; exiting to the shell instead of opening the agent view&lt;/p&gt;
&lt;p&gt;• Fixed claude --bg silently creating an unattachable session when combined with --print/-p; the conflicting flags are now rejected up front&lt;/p&gt;
&lt;p&gt;• Fixed the workflow progress view dropping the earliest agents from the list while the phase counter stayed correct in SDK and desktop-app sessions&lt;/p&gt;
&lt;p&gt;• Fixed .claude/rules/ conditional rules not loading when the target file is reached via a symlinked path&lt;/p&gt;
&lt;p&gt;• Fixed Cmd+click not opening URLs in fullscreen mode in Warp on macOS&lt;/p&gt;
&lt;p&gt;• Fixed double-click word selection in fullscreen mode to select the entire URL including the scheme&lt;/p&gt;
&lt;p&gt;• Fixed plan mode not auto-allowing read-only tool calls when a session starts in plan mode&lt;/p&gt;
&lt;p&gt;• Fixed /branch deriving its default fork name from the compaction summary instead of the first real prompt&lt;/p&gt;
&lt;p&gt;• Improved focus mode: subagents launched in a turn now appear in its activity summary, and completed background notifications fold into a single count&lt;/p&gt;
&lt;p&gt;• Improved syntax highlighting accuracy in code blocks, diffs, and file previews by upgrading to highlight.js 11&lt;/p&gt;
&lt;p&gt;• Keyboard shortcut hints now show opt/cmd instead of alt/super when connected from a Mac over SSH&lt;/p&gt;
&lt;p&gt;• Improved API retry UX: the error reason is now shown after the second attempt, and a status page link replaces the spinner tip when the API is overloaded&lt;/p&gt;
&lt;p&gt;• /login now opens the sign-in dialog from the claude agents view instead of saying it isn't available&lt;/p&gt;
&lt;p&gt;• Subagents now treat messages from the agent that launched them as normal task direction; an agent's message is still never treated as the user's approval&lt;/p&gt;
&lt;p&gt;• Removed the /agents wizard; ask Claude to create or manage subagents, or edit .claude/agents/ directly&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.197</id>
<title>Claude Code v2.1.197</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.197"/>
<updated>2026-06-30T17:56:29Z</updated>
<content type="html">&lt;p&gt;• Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.196</id>
<title>Claude Code v2.1.196</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.196"/>
<updated>2026-06-29T23:27:24Z</updated>
<content type="html">&lt;p&gt;• Added support for organization default models — admins set it in the org console; it shows as "Org default" (or "Role default") in /model when you haven't picked one yourself&lt;/p&gt;
&lt;p&gt;• Added readable default names for sessions at start, making them easier to identify and message&lt;/p&gt;
&lt;p&gt;• Added clickable file attachments in chat — Cmd/Ctrl-click reveals the file in Finder/Explorer&lt;/p&gt;
&lt;p&gt;• Security: claude mcp list/get no longer spawn .mcp.json servers that a repo self-approved via a committed .claude/settings.json; untrusted workspaces show ⏸ Pending approval&lt;/p&gt;
&lt;p&gt;• Fixed waking a background job permanently deleting its conversation and re-running the original prompt when the transcript probe misread a real transcript; the file is now set aside, never deleted&lt;/p&gt;
&lt;p&gt;• Fixed the rate-limit warning flickering off and rate-limit telemetry being over-counted when multiple parallel requests were in flight at the moment a usage limit was hit&lt;/p&gt;
&lt;p&gt;• Fixed duplicate recap lines after a background session's turn: a schema-rejected StructuredOutput attempt no longer renders alongside its retry&lt;/p&gt;
&lt;p&gt;• Fixed PowerShell git diff/git grep, egrep/fgrep, and quoted search patterns containing | being reported as failures when they exit 1, matching Bash behavior&lt;/p&gt;
&lt;p&gt;• Fixed multiple claude agents side panel issues: keyboard focus getting stuck when opening an agent, background jobs losing their subagent types on every open, and sessions showing incorrect status while actively running&lt;/p&gt;
&lt;p&gt;• Fixed claude agents --dangerously-skip-permissions silently falling back to auto mode instead of showing the bypass disclaimer and applying bypass mode to spawned agents&lt;/p&gt;
&lt;p&gt;• Fixed mid-turn crash recovery for Remote sessions — sessions interrupted by a server restart now auto-resume on the next worker&lt;/p&gt;
&lt;p&gt;• Fixed sessions moved with /cd reappearing in the old directory's resume list after a non-graceful exit when the old path contained special characters&lt;/p&gt;
&lt;p&gt;• Fixed claude plugin validate skipping local plugins whose source is "." and stopping after the first error class&lt;/p&gt;
&lt;p&gt;• Fixed Esc Esc at an idle prompt not opening the rewind menu (regression); use Ctrl+C or Ctrl+X Ctrl+K to stop background agents&lt;/p&gt;
&lt;p&gt;• Fixed MCP OAuth requesting the authorization server's full scopes_supported catalog when no scope is specified, causing invalid_scope failures on GitLab self-hosted and other enterprise IdPs&lt;/p&gt;
&lt;p&gt;• Fixed /context showing 0 tokens for all tool groups on Bedrock&lt;/p&gt;
&lt;p&gt;• Fixed /deep-research misreporting verifier failures as "all claims refuted" instead of unverified&lt;/p&gt;
&lt;p&gt;• Fixed plugin dependency version pins not being honored when the marketplace was added as a local folder path backed by a git repo&lt;/p&gt;
&lt;p&gt;• Fixed claude agents session status: completed rows no longer flip between "Done" and "Needs your input", stalled agents are now labeled "Needs attention", and results that mention a PR show a clickable link&lt;/p&gt;
&lt;p&gt;• Fixed voice dictation swallowing spaces and spuriously starting a recording during very fast typing when voice mode is enabled&lt;/p&gt;
&lt;p&gt;• Improved background session reliability: long-running commands and workflows now survive the session's process being stopped, restarted, or updated — including on Windows, where background shells are handed off instead of being killed&lt;/p&gt;
&lt;p&gt;• Improved background agents: workers killed by a daemon restart are now automatically resumed from where they left off the next time the agents view opens&lt;/p&gt;
&lt;p&gt;• Improved /code-review workflow: merged five cleanup finders into one, cutting token usage by roughly 25%&lt;/p&gt;
&lt;p&gt;• Reduced per-frame rendering work in the terminal UI by skipping no-op subtree walks during streaming&lt;/p&gt;
&lt;p&gt;• The streaming idle watchdog is now on by default for all providers — it aborts and retries when a response stream produces no events for 5 minutes. Set CLAUDE_ENABLE_STREAM_WATCHDOG=0 to disable.&lt;/p&gt;
&lt;p&gt;• Remote Control is now disabled when ANTHROPIC_BASE_URL points at a non-Anthropic host, matching the existing behavior under CLAUDE_CODE_USE_BEDROCK/_VERTEX/_FOUNDRY&lt;/p&gt;
&lt;p&gt;• Changed opening the agents view from a foreground session to require a single ← press instead of two, matching the behavior in background sessions&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.195</id>
<title>Claude Code v2.1.195</title>
@@ -363,63 +472,4 @@
&lt;p&gt;• Stopped promoting /loop in remote sessions, where pending loops don't keep the container alive&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed PowerShell tool calls rendering as raw JSON instead of a proper command display and permission dialog, and stripped ANSI escape codes from displayed shell output&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.170</id>
<title>Claude Code v2.1.170</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.170"/>
<updated>2026-06-09T17:23:03Z</updated>
<content type="html">&lt;p&gt;• Introducing Claude Fable 5: a Mythos-class model that weve made safe for general use. Fables capabilities exceed those of any model weve ever made generally available. Update to version 2.1.170 for access. https://www.anthropic.com/news/claude-fable-5-mythos-5&lt;/p&gt;
&lt;p&gt;• Fixed sessions not saving transcripts (and not appearing in --resume) when launched from the VS Code integrated terminal or any shell that inherited Claude Code environment variables.&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.169</id>
<title>Claude Code v2.1.169</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.169"/>
<updated>2026-06-08T21:57:10Z</updated>
<content type="html">&lt;p&gt;• Self-hosted runner: added a post-session lifecycle hook that runs after the session ends and before the workspace is deleted, so you can snapshot uncommitted work or export logs; also made the child-process SIGTERM→SIGKILL window configurable (default unchanged at 5s)&lt;/p&gt;
&lt;p&gt;• Added --safe-mode flag (and CLAUDE_CODE_SAFE_MODE) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting&lt;/p&gt;
&lt;p&gt;• Added /cd command to move a session to a new working directory without breaking the prompt cache mid-session&lt;/p&gt;
&lt;p&gt;• Added a disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS environment variable to hide bundled skills, workflows, and built-in slash commands from the model&lt;/p&gt;
&lt;p&gt;• Fixed Up/Down arrows jumping to command history past the wrapped rows of a long input line — they now move through each visual row first, and history recall enters at the near edge&lt;/p&gt;
&lt;p&gt;• Fixed enterprise managed MCP policies (allowedMcpServers/deniedMcpServers) not being enforced on reconnect, IDE-typed configs, --mcp-config servers during the first session after install, or before remote settings loaded; also fixed slow cold starts for orgs without remote settings&lt;/p&gt;
&lt;p&gt;• Fixed a ~30-50ms UI stall at the start of each turn for macOS users logged in with claude.ai credentials&lt;/p&gt;
&lt;p&gt;• Fixed claude -p being slow or appearing to hang on Windows while waiting for the slash-command/skill scan (regression in 2.1.161)&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control getting stuck on "reconnecting" after resuming a session when an OAuth token refresh happened at the same time&lt;/p&gt;
&lt;p&gt;• Fixed Git Credential Manager's "Connect to GitHub" popup appearing on Windows at startup when background git commands ran without cached credentials&lt;/p&gt;
&lt;p&gt;• Fixed footer hints (e.g. "esc to interrupt") not showing for users with a custom statusline&lt;/p&gt;
&lt;p&gt;• Fixed stale permission and dialog prompts reappearing every time you reattached to a remote session whose worker had died while waiting on them&lt;/p&gt;
&lt;p&gt;• Fixed claude agents --json omitting blocked and just-dispatched background sessions; added --all to include completed sessions, plus new id and state fields&lt;/p&gt;
&lt;p&gt;• Fixed agents view leaving a stale/garbled frame after navigating back from an agent on WSL in Windows Terminal&lt;/p&gt;
&lt;p&gt;• Fixed background agents ignoring project-level settings env values (e.g. ANTHROPIC_MODEL) when dispatched onto a pre-warmed worker&lt;/p&gt;
&lt;p&gt;• Fixed MCPB plugin cache being spuriously invalidated on Windows, causing unnecessary re-extraction&lt;/p&gt;
&lt;p&gt;• Fixed plugin .in_use PID lock files accumulating without bound; stale markers from crashed sessions are now swept once per day&lt;/p&gt;
&lt;p&gt;• Fixed untrusted project settings being able to set OTEL client-certificate paths without trust confirmation&lt;/p&gt;
&lt;p&gt;• /workflows now opens immediately even while a turn is in progress&lt;/p&gt;
&lt;p&gt;• Improved TaskCreate reliability: malformed inputs are repaired automatically and validation errors for unloaded tools include the schema&lt;/p&gt;
&lt;p&gt;• Improved the error message shown when your organization has disabled API key authentication, with guidance based on where the active API key comes from&lt;/p&gt;
&lt;p&gt;• Reduced CPU usage while responses stream and during spinner animations&lt;/p&gt;
&lt;p&gt;• Restored a default 5-minute idle timeout on Vertex/Foundry so a stalled stream aborts instead of hanging indefinitely; set API_FORCE_IDLE_TIMEOUT=0 to opt out&lt;/p&gt;
&lt;p&gt;• Remote-managed settings with an invalid entry now apply their remaining valid policies and surface the validation error, instead of silently dropping the whole payload&lt;/p&gt;
&lt;p&gt;• Background sessions now preserve --ide, --chrome, --bare, --remote-control, and other flags across retire→wake, and respawn state validation was hardened&lt;/p&gt;
&lt;p&gt;• Background sessions are now told that shared-checkout edits are blocked until they enter a worktree, avoiding a wasted rejected edit before EnterWorktree&lt;/p&gt;
&lt;p&gt;• The "CLAUDE.md is too long" warning threshold now scales with the model's context window&lt;/p&gt;
&lt;p&gt;• Auto-updater on Windows now stops retrying within a session once claude.exe is held by another process&lt;/p&gt;
&lt;p&gt;• Improved color contrast for skill tags in the slash-command menu&lt;/p&gt;
&lt;p&gt;• Promo credit claims for Apple/Google-billed subscribers without a payment method now explain where to add one&lt;/p&gt;
&lt;p&gt;• Added a tip suggesting claude agents when running multiple concurrent sessions&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.168</id>
<title>Claude Code v2.1.168</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.168"/>
<updated>2026-06-06T23:41:47Z</updated>
<content type="html">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
</entry>
<entry>
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.167</id>
<title>Claude Code v2.1.167</title>
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.167"/>
<updated>2026-06-06T01:33:29Z</updated>
<content type="html">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
</entry>
</feed>