Skip to content

Commit a9ce24a

Browse files
github-actions[bot]claude
authored andcommitted
docs: Claude Code v2.1.101 + Agent SDK + Agents API
Captures significant version bump from 2.1.97 → 2.1.101 featuring: **v2.1.101 Highlights:** - `/team-onboarding` command for teammate ramp-up guides - Enterprise TLS proxy support (CA cert store integration) - Security fixes: command injection vulnerability + Bash permission bypass - Auto-creates default cloud environments for `/ultraplan` - Improved brief/focus modes, error messages, rate limit handling **v2.1.98 Highlights:** - Interactive Google Vertex AI setup wizard - Subprocess sandboxing with PID namespace isolation - Monitor tool for streaming background events - Perforce mode integration (`CLAUDE_CODE_PERFORCE_MODE`) **API Updates:** - Extensive Agent SDK and Agents API documentation updates - Updated tool reference and programmatic tool calling docs - Enhanced code execution tool documentation 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
1 parent 6c565dd commit a9ce24a

899 files changed

Lines changed: 162782 additions & 13401 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

content/.metadata.json

Lines changed: 1804 additions & 1783 deletions
Large diffs are not rendered by default.

content/CHANGELOG.md

Lines changed: 109 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,114 @@
11
# Changelog
22

3+
## 2.1.101
4+
5+
- Added `/team-onboarding` command to generate a teammate ramp-up guide from your local Claude Code usage
6+
- Added OS CA certificate store trust by default, so enterprise TLS proxies work without extra setup (set `CLAUDE_CODE_CERT_STORE=bundled` to use only bundled CAs)
7+
- `/ultraplan` and other remote-session features now auto-create a default cloud environment instead of requiring web setup first
8+
- Improved brief mode to retry once when Claude responds with plain text instead of a structured message
9+
- Improved focus mode: Claude now writes more self-contained summaries since it knows you only see its final message
10+
- Improved tool-not-available errors to explain why and how to proceed when the model calls a tool that exists but isn't available in the current context
11+
- Improved rate-limit retry messages to show which limit was hit and when it resets instead of an opaque seconds countdown
12+
- Improved refusal error messages to include the API-provided explanation when available
13+
- Improved `claude -p --resume <name>` to accept session titles set via `/rename` or `--name`
14+
- Improved settings resilience: an unrecognized hook event name in `settings.json` no longer causes the entire file to be ignored
15+
- Improved plugin hooks from plugins force-enabled by managed settings to run when `allowManagedHooksOnly` is set
16+
- Improved `/plugin` and `claude plugin update` to show a warning when the marketplace could not be refreshed, instead of silently reporting a stale version
17+
- Improved plan mode to hide the "Refine with Ultraplan" option when the user's org or auth setup can't reach Claude Code on the web
18+
- Improved beta tracing to honor `OTEL_LOG_USER_PROMPTS`, `OTEL_LOG_TOOL_DETAILS`, and `OTEL_LOG_TOOL_CONTENT`; sensitive span attributes are no longer emitted unless opted in
19+
- Improved SDK `query()` to clean up subprocess and temp files when consumers `break` from `for await` or use `await using`
20+
- Fixed a command injection vulnerability in the POSIX `which` fallback used by LSP binary detection
21+
- Fixed a memory leak where long sessions retained dozens of historical copies of the message list in the virtual scroller
22+
- Fixed `--resume`/`--continue` losing conversation context on large sessions when the loader anchored on a dead-end branch instead of the live conversation
23+
- Fixed `--resume` chain recovery bridging into an unrelated subagent conversation when a subagent message landed near a main-chain write gap
24+
- Fixed a crash on `--resume` when a persisted Edit/Write tool result was missing its `file_path`
25+
- Fixed a hardcoded 5-minute request timeout that aborted slow backends (local LLMs, extended thinking, slow gateways) regardless of `API_TIMEOUT_MS`
26+
- Fixed `permissions.deny` rules not overriding a PreToolUse hook's `permissionDecision: "ask"` — previously the hook could downgrade a deny into a prompt
27+
- Fixed `--setting-sources` without `user` causing background cleanup to ignore `cleanupPeriodDays` and delete conversation history older than 30 days
28+
- Fixed Bedrock SigV4 authentication failing with 403 when `ANTHROPIC_AUTH_TOKEN`, `apiKeyHelper`, or `ANTHROPIC_CUSTOM_HEADERS` set an Authorization header
29+
- Fixed `claude -w <name>` failing with "already exists" after a previous session's worktree cleanup left a stale directory
30+
- Fixed subagents not inheriting MCP tools from dynamically-injected servers
31+
- Fixed sub-agents running in isolated worktrees being denied Read/Edit access to files inside their own worktree
32+
- Fixed sandboxed Bash commands failing with `mktemp: No such file or directory` after a fresh boot
33+
- Fixed `claude mcp serve` tool calls failing with "Tool execution failed" in MCP clients that validate `outputSchema`
34+
- Fixed `RemoteTrigger` tool's `run` action sending an empty body and being rejected by the server
35+
- Fixed several `/resume` picker issues: narrow default view hiding sessions from other projects, unreachable preview on Windows Terminal, incorrect cwd in worktrees, session-not-found errors not surfacing in stderr, terminal title not being set, and resume hint overlapping the prompt input
36+
- Fixed Grep tool ENOENT when the embedded ripgrep binary path becomes stale (VS Code extension auto-update, macOS App Translocation); now falls back to system `rg` and self-heals mid-session
37+
- Fixed `/btw` writing a copy of the entire conversation to disk on every use
38+
- Fixed `/context` Free space and Messages breakdown disagreeing with the header percentage
39+
- Fixed several plugin issues: slash commands resolving to the wrong plugin with duplicate `name:` frontmatter, `/plugin update` failing with `ENAMETOOLONG`, Discover showing already-installed plugins, directory-source plugins loading from a stale version cache, and skills not honoring `context: fork` and `agent` frontmatter fields
40+
- Fixed the `/mcp` menu offering OAuth-specific actions for MCP servers configured with `headersHelper`; Reconnect is now offered instead to re-invoke the helper script
41+
- Fixed `ctrl+]`, `ctrl+\`, and `ctrl+^` keybindings not firing in terminals that send raw C0 control bytes (Terminal.app, default iTerm2, xterm)
42+
- Fixed `/login` OAuth URL rendering with padding that prevented clean mouse selection
43+
- Fixed rendering issues: flicker in non-fullscreen mode when content above the visible area changed, terminal scrollback being wiped during long sessions in non-fullscreen mode, and mouse-scroll escape sequences occasionally leaking into the prompt as text
44+
- Fixed crash when `settings.json` env values are numbers instead of strings
45+
- Fixed in-app settings writes (e.g. `/add-dir --remember`, `/config`) not refreshing the in-memory snapshot, preventing removed directories from being revoked mid-session
46+
- Fixed custom keybindings (`~/.claude/keybindings.json`) not loading on Bedrock, Vertex, and other third-party providers
47+
- Fixed `claude --continue -p` not correctly continuing sessions created by `-p` or the SDK
48+
- Fixed several Remote Control issues: worktrees removed on session crash, connection failures not persisting in the transcript, spurious "Disconnected" indicator in brief mode for local sessions, and `/remote-control` failing over SSH when only `CLAUDE_CODE_ORGANIZATION_UUID` is set
49+
- Fixed `/insights` sometimes omitting the report file link from its response
50+
- [VSCode] Fixed the file attachment below the chat input not clearing when the last editor tab is closed
51+
52+
## 2.1.98
53+
54+
- Added interactive Google Vertex AI setup wizard accessible from the login screen when selecting "3rd-party platform", guiding you through GCP authentication, project and region configuration, credential verification, and model pinning
55+
- Added `CLAUDE_CODE_PERFORCE_MODE` env var: when set, Edit/Write/NotebookEdit fail on read-only files with a `p4 edit` hint instead of silently overwriting them
56+
- Added Monitor tool for streaming events from background scripts
57+
- Added subprocess sandboxing with PID namespace isolation on Linux when `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` is set, and `CLAUDE_CODE_SCRIPT_CAPS` env var to limit per-session script invocations
58+
- Added `--exclude-dynamic-system-prompt-sections` flag to print mode for improved cross-user prompt caching
59+
- Added `workspace.git_worktree` to the status line JSON input, set whenever the current directory is inside a linked git worktree
60+
- Added W3C `TRACEPARENT` env var to Bash tool subprocesses when OTEL tracing is enabled, so child-process spans correctly parent to Claude Code's trace tree
61+
- LSP: Claude Code now identifies itself to language servers via `clientInfo` in the initialize request
62+
- Fixed a Bash tool permission bypass where a backslash-escaped flag could be auto-allowed as read-only and lead to arbitrary code execution
63+
- Fixed compound Bash commands bypassing forced permission prompts for safety checks and explicit ask rules in auto and bypass-permissions modes
64+
- Fixed read-only commands with env-var prefixes not prompting unless the var is known-safe (`LANG`, `TZ`, `NO_COLOR`, etc.)
65+
- Fixed redirects to `/dev/tcp/...` or `/dev/udp/...` not prompting instead of auto-allowing
66+
- Fixed stalled streaming responses timing out instead of falling back to non-streaming mode
67+
- Fixed 429 retries burning all attempts in ~13s when the server returns a small `Retry-After` — exponential backoff now applies as a minimum
68+
- Fixed MCP OAuth `oauth.authServerMetadataUrl` config override not being honored on token refresh after restart, affecting ADFS and similar IdPs
69+
- Fixed capital letters being dropped to lowercase on xterm and VS Code integrated terminal when the kitty keyboard protocol is active
70+
- Fixed macOS text replacements deleting the trigger word instead of inserting the substitution
71+
- Fixed `--dangerously-skip-permissions` being silently downgraded to accept-edits mode after approving a write to a protected path via Bash
72+
- Fixed managed-settings allow rules remaining active after an admin removed them, until process restart
73+
- Fixed `permissions.additionalDirectories` changes not applying mid-session — removed directories lose access immediately and added ones work without restart
74+
- Fixed removing a directory from `additionalDirectories` revoking access to the same directory passed via `--add-dir`
75+
- Fixed `Bash(cmd:*)` and `Bash(git commit *)` wildcard permission rules failing to match commands with extra spaces or tabs
76+
- Fixed `Bash(...)` deny rules being downgraded to a prompt for piped commands that mix `cd` with other segments
77+
- Fixed false Bash permission prompts for `cut -d /`, `paste -d /`, `column -s /`, `awk '{print $1}' file`, and filenames containing `%`
78+
- Fixed permission rules with names matching JavaScript prototype properties (e.g. `toString`) causing `settings.json` to be silently ignored
79+
- Fixed agent team members not inheriting the leader's permission mode when using `--dangerously-skip-permissions`
80+
- Fixed a crash in fullscreen mode when hovering over MCP tool results
81+
- Fixed copying wrapped URLs in fullscreen mode inserting spaces at line breaks
82+
- Fixed file-edit diffs disappearing from the UI on `--resume` when the edited file was larger than 10KB
83+
- Fixed several `/resume` picker issues: `--resume <name>` opening uneditable, filter reload wiping search state, empty list swallowing arrow keys, cross-project staleness, and transient task-status text replacing conversation summaries
84+
- Fixed `/export` not honoring absolute paths and `~`, and silently rewriting user-supplied extensions to `.txt`
85+
- Fixed `/effort max` being denied for unknown or future model IDs
86+
- Fixed slash command picker breaking when a plugin's frontmatter `name` is a YAML boolean keyword
87+
- Fixed rate-limit upsell text being hidden after message remounts
88+
- Fixed MCP tools with `_meta["anthropic/maxResultSizeChars"]` not bypassing the token-based persist layer
89+
- Fixed voice mode leaking dozens of space characters into the input when re-holding the push-to-talk key while the previous transcript is still processing
90+
- Fixed `DISABLE_AUTOUPDATER` not fully suppressing the npm registry version check and symlink modification on npm-based installs
91+
- Fixed a memory leak where Remote Control permission handler entries were retained for the lifetime of the session
92+
- Fixed background subagents that fail with an error not reporting partial progress to the parent agent
93+
- Fixed prompt-type Stop/SubagentStop hooks failing on long sessions, and hook evaluator API errors showing "JSON validation failed" instead of the real message
94+
- Fixed feedback survey rendering when dismissed
95+
- Fixed Bash `grep -f FILE` / `rg -f FILE` not prompting when reading a pattern file outside the working directory
96+
- Fixed stale subagent worktree cleanup removing worktrees that contain untracked files
97+
- Fixed `sandbox.network.allowMachLookup` not taking effect on macOS
98+
- Improved `/resume` filter hint labels and added project/worktree/branch names in the filter indicator
99+
- Improved footer indicators (Focus, notifications) to stay on the mode-indicator row instead of wrapping at narrow terminal widths
100+
- Improved `/agents` with a tabbed layout: a Running tab shows live subagents, and the Library tab adds Run agent and View running instance actions
101+
- Improved `/reload-plugins` to pick up plugin-provided skills without requiring a restart
102+
- Improved Accept Edits mode to auto-approve filesystem commands prefixed with safe env vars or process wrappers
103+
- Improved Vim mode: `j`/`k` in NORMAL mode now navigate history and select the footer pill at the input boundary
104+
- Improved hook errors in the transcript to include the first line of stderr for self-diagnosis without `--debug`
105+
- Improved OTEL tracing: interaction spans now correctly wrap full turns under concurrent SDK calls, and headless turns end spans per-turn
106+
- Improved transcript entries to carry final token usage instead of streaming placeholders
107+
- Updated the `/claude-api` skill to cover Managed Agents alongside Claude API
108+
- [VSCode] Fixed false-positive "requires git-bash" error on Windows when `CLAUDE_CODE_GIT_BASH_PATH` is set or Git is installed at a default location
109+
- Fixed `CLAUDE_CODE_MAX_CONTEXT_TOKENS` to honor `DISABLE_COMPACT` when it is set.
110+
- Dropped `/compact` hints when `DISABLE_COMPACT` is set.
111+
3112
## 2.1.97
4113

5114
- Added focus view toggle (`Ctrl+O`) in `NO_FLICKER` mode showing prompt, one-line tool summary with edit diffstats, and final response

content/blog/engineering/claude-code-best-practices.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -55,13 +55,13 @@ Best Practices for Claude Code
5555

5656
* [Overview](https://www.anthropic.com/docs/en/platforms)
5757
* [Remote Control](https://www.anthropic.com/docs/en/remote-control)
58-
* Claude Code on the web
59-
* Claude Code on desktop
58+
* Claude Code on the web
59+
* Claude Code on desktop
6060
* [Chrome extension (beta)](https://www.anthropic.com/docs/en/chrome)
6161
* [Computer use (preview)](https://www.anthropic.com/docs/en/computer-use)
6262
* [Visual Studio Code](https://www.anthropic.com/docs/en/vs-code)
6363
* [JetBrains IDEs](https://www.anthropic.com/docs/en/jetbrains)
64-
* Code review & CI/CD
64+
* Code review & CI/CD
6565
* [Claude Code in Slack](https://www.anthropic.com/docs/en/slack)
6666

6767
On this page
@@ -125,7 +125,7 @@ Claude performs dramatically better when it can verify its own work, like run te
125125

126126
| Strategy | Before | After |
127127
| --- | --- | --- |
128-
| **Provide verification criteria** | _”implement a function that validates email addresses"_ | _"write a validateEmail function. example test cases: [[email protected]](https://www.anthropic.com/cdn-cgi/l/email-protection#85f0f6e0f7c5e0fde4e8f5e9e0abe6eae8) is true, invalid is false, [[email protected]](https://www.anthropic.com/cdn-cgi/l/email-protection#5227213720127c313d3f) is false. run the tests after implementing”_ |
128+
| **Provide verification criteria** | _”implement a function that validates email addresses"_ | _"write a validateEmail function. example test cases: [[email protected]](https://www.anthropic.com/cdn-cgi/l/email-protection#c5b0b6a0b785a0bda4a8b5a9a0eba6aaa8) is true, invalid is false, [[email protected]](https://www.anthropic.com/cdn-cgi/l/email-protection#790c0a1c0b39571a1614) is false. run the tests after implementing”_ |
129129
| **Verify UI changes visually** | _”make the dashboard look better"_ | _"[paste screenshot] implement this design. take a screenshot of the result and compare it to the original. list differences and fix them”_ |
130130
| **Address root causes, not symptoms** | _”the build is failing"_ | _"the build fails with this error: [paste error]. fix it and verify the build succeeds. address the root cause, don’t suppress the error”_ |
131131

content/blog/engineering/claude-code-sandboxing.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -68,7 +68,7 @@ Our new sandboxed bash tool and Claude Code on the web offer substantial improve
6868
To get started with these tools:
6969

7070
1. Run `/sandbox` in Claude and check out [our docs](https://docs.claude.com/en/docs/claude-code/sandboxing) on how to configure this sandbox.
71-
2. Go to [claude.com/code](http://claude.ai/redirect/website.v1.93c40709-533b-444e-aacf-c48d96624ea1/code) to try out Claude Code on the web.
71+
2. Go to [claude.com/code](http://claude.ai/redirect/website.v1.ae8e2433-ce9e-48a0-b609-5dc2ec208fe5/code) to try out Claude Code on the web.
7272

7373
Or, if you're building your own agents, check out our [open-sourced sandboxing code](https://github.com/anthropic-experimental/sandbox-runtime), and consider integrating it into your work. We look forward to seeing what you build.
7474

content/claude-code-manifest.json

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,12 @@
11
{
22
"name": "@anthropic-ai/claude-code",
3-
"version": "2.1.97",
3+
"version": "2.1.101",
44
"author": {
55
"name": "Anthropic",
66
"email": "support@anthropic.com"
77
},
88
"license": "SEE LICENSE IN README.md",
9-
"_id": "@anthropic-ai/claude-code@2.1.97",
9+
"_id": "@anthropic-ai/claude-code@2.1.101",
1010
"maintainers": [
1111
{
1212
"name": "zak-anthropic",
@@ -73,20 +73,20 @@
7373
"claude": "cli.js"
7474
},
7575
"dist": {
76-
"shasum": "b790d417b4f47b897068ffff9b57812ccc81e707",
77-
"tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.97.tgz",
76+
"shasum": "7bfeb26d4a30d1d595238fcc0c77a03578765e4e",
77+
"tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.101.tgz",
7878
"fileCount": 20,
79-
"integrity": "sha512-8lKM/rFctBl+82bQ+0g0Lkbt9tJU/zYKAjWisNUq436/386n/VZQbnyjnibGkyqqB6mrX/3ub/cpFlpCu4FXLg==",
79+
"integrity": "sha512-abVVCKMDKl9jHzgoUhhBVAQY2fKVdLt13ag5EEDlybRUCRL+rEAZfBxOdQnKZbzH1AUW5VwqiELeMHFauO51DQ==",
8080
"signatures": [
8181
{
82-
"sig": "MEUCICG6rML8JBFMxvrHFFDhofBztC5mvsOLqHbO7G4bdU4MAiEA/TuR+/HzSBvE2e/5XokcLHWOLaw604eahZ4Hy+IFTew=",
82+
"sig": "MEUCIHQpLCVRpNHYtDtd9exDJA9bNc/HYuiYbvJkW5XuSO14AiEAlN7OuPCD6ozycFxIkQ0tLdBtNRoK31bSQ9C7C5E6hTQ=",
8383
"keyid": "SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"
8484
}
8585
],
86-
"unpackedSize": 48991994
86+
"unpackedSize": 49182697
8787
},
8888
"type": "module",
89-
"_from": "file:/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.97.tgz",
89+
"_from": "file:/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.101.tgz",
9090
"engines": {
9191
"node": ">=18.0.0"
9292
},
@@ -97,8 +97,8 @@
9797
"name": "wolffiex",
9898
"email": "wolffiex@anthropic.com"
9999
},
100-
"_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.97.tgz",
101-
"_integrity": "sha512-8lKM/rFctBl+82bQ+0g0Lkbt9tJU/zYKAjWisNUq436/386n/VZQbnyjnibGkyqqB6mrX/3ub/cpFlpCu4FXLg==",
100+
"_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.101.tgz",
101+
"_integrity": "sha512-abVVCKMDKl9jHzgoUhhBVAQY2fKVdLt13ag5EEDlybRUCRL+rEAZfBxOdQnKZbzH1AUW5VwqiELeMHFauO51DQ==",
102102
"_npmVersion": "10.8.2",
103103
"description": "Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.",
104104
"directories": {},
@@ -118,7 +118,7 @@
118118
"@img/sharp-linuxmusl-arm64": "^0.34.2"
119119
},
120120
"_npmOperationalInternal": {
121-
"tmp": "tmp/claude-code_2.1.97_1775683674825_0.4147276975853762",
121+
"tmp": "tmp/claude-code_2.1.101_1775846514890_0.06549110097992505",
122122
"host": "s3://npm-registry-packages-npm-production"
123123
}
124124
}

content/en/about-claude/pricing.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@ MTok = Million tokens. The "Base Input Tokens" column shows standard input prici
3333

3434
## Third-party platform pricing
3535

36-
Claude models are available on [AWS Bedrock](/docs/en/build-with-claude/claude-in-amazon-bedrock), [Google Vertex AI](/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](/docs/en/build-with-claude/claude-in-microsoft-foundry). For official pricing, visit:
36+
Claude models are available on [AWS Bedrock](/docs/en/build-with-claude/claude-on-amazon-bedrock), [Google Vertex AI](/docs/en/build-with-claude/claude-on-vertex-ai), and [Microsoft Foundry](/docs/en/build-with-claude/claude-in-microsoft-foundry). For official pricing, visit:
3737
- [AWS Bedrock pricing](https://aws.amazon.com/bedrock/pricing/)
3838
- [Google Vertex AI pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing)
3939
- [Microsoft Foundry pricing](https://azure.microsoft.com/en-us/pricing/details/ai-foundry/#pricing)

0 commit comments

Comments
 (0)