Skip to content

Commit e1366b1

Browse files
github-actions[bot]claude-yolo[bot]
authored andcommitted
docs: Claude Code v2.1.214 - Security permission fixes, EndConversation tool, OTel enhancements
Co-Authored-By: claude-yolo[bot] <claude-yolo@lroole.com>
1 parent c456fcd commit e1366b1

154 files changed

Lines changed: 2288 additions & 1037 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: 308 additions & 280 deletions
Large diffs are not rendered by default.

content/CHANGELOG.md

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,55 @@
11
# Changelog
22

3+
## 2.1.214
4+
5+
- Fixed single-segment `dir/**` allow rules like `Edit(src/**)` auto-approving writes to nested `dir/` directories anywhere in the tree instead of only `<cwd>/dir`
6+
- Fixed a permission-check bypass affecting commands run in Windows PowerShell 5.1 sessions
7+
- Fixed Bash permission checks to fail closed on file-descriptor redirect forms that bash parses differently than the permission analyzer
8+
- Fixed Bash permission checks misjudging very long commands — commands over 10,000 characters now always prompt instead of running automatically
9+
- Fixed Bash permission checks treating zsh variable subscripts and modifiers in `[[ ]]` comparisons as inert text — these commands now prompt for approval
10+
- Fixed Bash permission checks to no longer auto-approve certain `help` and `man` commands that could run unsafe options, command substitutions, or backslash paths
11+
- Fixed permission prompts on remote sessions that could proceed before the local confirmation dialog
12+
- Added the EndConversation tool: Claude can end sessions with highly abusive users or jailbreak attempts, as on claude.ai since 2025 — see https://www.anthropic.com/research/end-subset-conversations
13+
- Added a periodic progress heartbeat for long-running tool calls that previously went silent
14+
- Added an ISO `modified` timestamp to memory file frontmatter
15+
- Added `message.uuid`, `client_request_id`, and `tool_source` attributes to OpenTelemetry log events for message-level correlation and tool provenance
16+
- Added `CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH` to configure the 60 KB truncation limit on OpenTelemetry content attributes
17+
- Added reasoning effort to the `subagentStatusLine` payload, so custom agent rows can render model and effort
18+
- Added permission prompts for `docker` commands (including the Podman `docker` shim) carrying daemon-redirect flags (`--url`, `--connection`, `--identity`, and Podman's remote mode) that previously ran without one
19+
- Fixed a crash when a GrowthBook feature evaluates to null, and a bug where a malformed flag payload could wipe the cached feature flags
20+
- Fixed Bash tool killing the Claude session when a `pkill -f` pattern accidentally matched the CLI's own process (Linux)
21+
- Fixed unbounded memory growth when `--settings` points at a device file or multi-GB file; oversized (>2 MiB) settings files now fail at startup with a clear error
22+
- Fixed streaming turns failing with "Socket is closed" behind corporate proxies on Windows
23+
- Fixed stream-json output truncation at exit for slow-reading SDK/pipeline consumers; the exit drain now scales with queued bytes instead of a flat 2s cap
24+
- Fixed scheduled tasks refusing their own configured prompt as untrusted input — the fired prompt is now delivered as the session's assigned task
25+
- Fixed PowerShell tool commands hanging until timeout when a child process waited on standard input (Windows)
26+
- Fixed Python scripts under the PowerShell tool crashing with UnicodeDecodeError when reading non-UTF-8 data from standard input (Windows)
27+
- Fixed Python scripts run via the PowerShell tool crashing with UnicodeEncodeError on non-ASCII output, and PowerShell 7 error messages containing raw ANSI escape sequences (Windows)
28+
- Fixed the PowerShell tool reporting `where.exe`, `fc.exe`, and `diff.exe` as errors when they return a valid negative answer (Windows)
29+
- Fixed `>` and `>>` under the PowerShell tool on Windows PowerShell 5.1 writing UTF-16LE files that other tools couldn't read as UTF-8
30+
- Fixed a displaced background daemon deleting its successor's control socket on shutdown, which made the next client kill the healthy replacement daemon
31+
- Fixed background sessions parked with `` or `/background` and left idle keeping the background daemon and a worker process alive indefinitely
32+
- Fixed completed background sessions being impossible to remove via `claude rm` or the agent view once the background service had gone idle
33+
- Fixed background sessions dispatched from a non-git folder being impossible to delete from the agents view
34+
- Fixed reopening a stopped background session failing to restore its saved conversation when an unreadable folder exists in the session store
35+
- Fixed the Remote Control "session ready" push notification firing for sessions where Remote Control was not explicitly enabled
36+
- Fixed `/install-github-app` and the `/mcp` settings menu being blocked in agent-view sessions — they're now refused only in background sessions with no terminal attached
37+
- Fixed plugins enabled via the `--settings` CLI flag not loading (regression since v2.1.181)
38+
- Fixed feature flags going stale in long-running sessions after the OAuth token rotates
39+
- Fixed `/ultrareview` refusing to run in repos with no merge base — it now offers to review all tracked files
40+
- Fixed `claude update` and `claude doctor` hanging silently, and the `/status` System diagnostics section going blank, when a shell-config path is a directory
41+
- Fixed memory frontmatter values being silently truncated at an inline `#` when memory files are saved
42+
- Fixed session cost and token telemetry double-counting on streams that emit multiple cumulative `message_delta` frames
43+
- Fixed a spurious "check your network" warning that appeared while the advisor was thinking
44+
- Fixed hooks with exit code 2 not blocking as documented when the hook's stdout JSON fails schema validation
45+
- Fixed OTel log events emitted outside the turn's async context missing the interaction span's trace context
46+
- Fixed MCP transient errors during prompts/resources refresh clearing the server's slash commands and resources
47+
- Improved the `claude rc` workspace-trust error in the home directory to say trust there is never saved and to suggest running from a project directory
48+
- Changed single-segment `dir/**` hook `if:` conditions to match only `<cwd>/dir`; write `**/dir/**` for any-depth matching. `deny`/`ask` permission rules keep their any-depth match.
49+
- Changed `file` commands using `-m`/`--magic-file` or `-f`/`--files-from` to require permission instead of being auto-allowed as read-only
50+
- Changed keep-alive connection pooling to disable after a stale-connection error, so retries open a fresh socket
51+
- Changed SessionStart hooks to report source `"fork"` when a session begins as a fork instead of `"resume"`
52+
353
## 2.1.212
454

555
- `/fork` now copies your conversation into a new background session (its own row in `claude agents`) while you keep working; the in-session subagent it used to launch is now `/subtask`

content/claude-code-manifest.json

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,12 @@
11
{
22
"name": "@anthropic-ai/claude-code",
3-
"version": "2.1.212",
3+
"version": "2.1.214",
44
"author": {
55
"name": "Anthropic",
66
"email": "support@anthropic.com"
77
},
88
"license": "SEE LICENSE IN README.md",
9-
"_id": "@anthropic-ai/claude-code@2.1.212",
9+
"_id": "@anthropic-ai/claude-code@2.1.214",
1010
"maintainers": [
1111
{
1212
"name": "zak-anthropic",
@@ -69,20 +69,20 @@
6969
"claude": "bin/claude.exe"
7070
},
7171
"dist": {
72-
"shasum": "7e8059b59c88e03a81e866662d3026e2a064a638",
73-
"tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.212.tgz",
72+
"shasum": "99ea5554ae1498cc5128e1b0b72f35250f5a7994",
73+
"tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.214.tgz",
7474
"fileCount": 7,
75-
"integrity": "sha512-MEasj1oaoARRKEWU7eHJ6DWC2TC8ogml9QUDihbmxYI2Ij5Ol1leW90DIj8/a0xX3lfHZOwT3gJr0JxVKa8Sxw==",
75+
"integrity": "sha512-Gf8XbPHBacVqBlxx8sMnKWPEU6AvRNUcjD0FS6zhD44fCgCHcpbpxwSoTbHlLTqKsr/0S7wdfhjjOIq8WlYbng==",
7676
"signatures": [
7777
{
78-
"sig": "MEQCIH+1m6cgl34lDUtw9OqJYSZE3sZmgoROr3U5sHFyZC/XAiBMiH7TyF6Ka3o+omNezfmBQ/xt6trP/nGAc7h8RfoZNw==",
78+
"sig": "MEYCIQDCJvyztDj3LDciHfikf9PC2wV/YZ30aFhKyv61bocnMAIhAL3p+i085yIADcjreFZ21gTwVIo0/drxZmnjUzAiLfzC",
7979
"keyid": "SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"
8080
}
8181
],
8282
"unpackedSize": 165282
8383
},
8484
"type": "module",
85-
"_from": "file:staged-npm/anthropic-ai-claude-code-2.1.212.tgz",
85+
"_from": "file:staged-npm/anthropic-ai-claude-code-2.1.214.tgz",
8686
"engines": {
8787
"node": ">=22.0.0"
8888
},
@@ -94,8 +94,8 @@
9494
"name": "wolffiex",
9595
"email": "wolffiex@anthropic.com"
9696
},
97-
"_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/staged-npm/anthropic-ai-claude-code-2.1.212.tgz",
98-
"_integrity": "sha512-MEasj1oaoARRKEWU7eHJ6DWC2TC8ogml9QUDihbmxYI2Ij5Ol1leW90DIj8/a0xX3lfHZOwT3gJr0JxVKa8Sxw==",
97+
"_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/staged-npm/anthropic-ai-claude-code-2.1.214.tgz",
98+
"_integrity": "sha512-Gf8XbPHBacVqBlxx8sMnKWPEU6AvRNUcjD0FS6zhD44fCgCHcpbpxwSoTbHlLTqKsr/0S7wdfhjjOIq8WlYbng==",
9999
"_npmVersion": "11.16.0",
100100
"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.",
101101
"directories": {},
@@ -104,17 +104,17 @@
104104
"_hasShrinkwrap": false,
105105
"readmeFilename": "README.md",
106106
"optionalDependencies": {
107-
"@anthropic-ai/claude-code-linux-x64": "2.1.212",
108-
"@anthropic-ai/claude-code-win32-x64": "2.1.212",
109-
"@anthropic-ai/claude-code-darwin-x64": "2.1.212",
110-
"@anthropic-ai/claude-code-linux-arm64": "2.1.212",
111-
"@anthropic-ai/claude-code-win32-arm64": "2.1.212",
112-
"@anthropic-ai/claude-code-darwin-arm64": "2.1.212",
113-
"@anthropic-ai/claude-code-linux-x64-musl": "2.1.212",
114-
"@anthropic-ai/claude-code-linux-arm64-musl": "2.1.212"
107+
"@anthropic-ai/claude-code-linux-x64": "2.1.214",
108+
"@anthropic-ai/claude-code-win32-x64": "2.1.214",
109+
"@anthropic-ai/claude-code-darwin-x64": "2.1.214",
110+
"@anthropic-ai/claude-code-linux-arm64": "2.1.214",
111+
"@anthropic-ai/claude-code-win32-arm64": "2.1.214",
112+
"@anthropic-ai/claude-code-darwin-arm64": "2.1.214",
113+
"@anthropic-ai/claude-code-linux-x64-musl": "2.1.214",
114+
"@anthropic-ai/claude-code-linux-arm64-musl": "2.1.214"
115115
},
116116
"_npmOperationalInternal": {
117-
"tmp": "tmp/claude-code_2.1.212_1784229624194_0.005650864120049448",
117+
"tmp": "tmp/claude-code_2.1.214_1784333621505_0.33682896826816733",
118118
"host": "s3://npm-registry-packages-npm-production"
119119
}
120120
}

content/en/build-with-claude/vision.md

Lines changed: 12 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1259,16 +1259,18 @@ Each model has a maximum native image resolution, expressed as a long-edge limit
12591259
12601260
High-resolution support is automatic on the listed models and requires no beta header or client-side opt-in.
12611261
1262-
The following table shows the visual-token cost for several image sizes on each tier:
1263-
1264-
| Image size | Standard-tier tokens | High-resolution-tier tokens |
1265-
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
1266-
| 200x200 px (0.04 megapixels) | 64 | 64 |
1267-
| 1000x1000 px (1 megapixel) | 1296 | 1296 |
1268-
| 1092x1092 px (1.19 megapixels) | 1521 | 1521 |
1269-
| 1920x1080 px (2.07 megapixels) | <Tooltip tooltipContent="Exceeds the standard tier's resolution limit; the image is downscaled before processing, which caps the token cost.">1560</Tooltip> | 2691 |
1270-
| 2000x1500 px (3 megapixels) | <Tooltip tooltipContent="Exceeds the standard tier's resolution limit; the image is downscaled before processing, which caps the token cost.">1564</Tooltip> | 3888 |
1271-
| 3840x2160 px (8.29 megapixels) | <Tooltip tooltipContent="Exceeds the standard tier's resolution limit; the image is downscaled before processing, which caps the token cost.">1560</Tooltip> | <Tooltip tooltipContent="Exceeds the high-resolution tier's limit; the image is downscaled before processing, which caps the token cost.">4784</Tooltip> |
1262+
The following table shows the downsized resolution and visual-token cost for several image sizes on each tier:
1263+
1264+
| Image size | Standard tier: downsized to | Standard tier: tokens | High-resolution tier: downsized to | High-resolution tier: tokens |
1265+
| ------------------------------ | --------------------------- | --------------------- | ---------------------------------- | ---------------------------- |
1266+
| 200x200 px (0.04 megapixels) | Not resized | 64 | Not resized | 64 |
1267+
| 1000x1000 px (1 megapixel) | Not resized | 1296 | Not resized | 1296 |
1268+
| 1092x1092 px (1.19 megapixels) | Not resized | 1521 | Not resized | 1521 |
1269+
| 1920x1080 px (2.07 megapixels) | 1456x819 px | 1560 | Not resized | 2691 |
1270+
| 2000x1500 px (3 megapixels) | 1269x952 px | 1564 | Not resized | 3888 |
1271+
| 3840x2160 px (8.29 megapixels) | 1456x819 px | 1560 | 2576x1449 px | 4784 |
1272+
1273+
When an image is downsized, Claude scales it to the largest size that fits the tier's limits while preserving its aspect ratio. This caps the token cost. For the precise rule and a reference implementation, see [How Claude resizes and pads images](/docs/en/build-with-claude/vision-coordinates#how-claude-resizes-and-pads-images).
12721274
12731275
To estimate cost, multiply the token count by the [per-token price of the model](https://claude.com/pricing) you're using. For example, at Claude Haiku 4.5's $1 per million input tokens (standard tier), the 1000×1000 image costs about $1.30 per thousand images. At Claude Opus 4.8's $5 per million (high-resolution tier), the same image costs about $6.48 per thousand and the 4K image about $23.92 per thousand.
12741276

0 commit comments

Comments
 (0)