docs: Claude Code v2.1.97 - Claude Code 2.1.97 + New Agents API

content/CHANGELOG.md

@@ -1,5 +1,54 @@
 # Changelog
 
+## 2.1.97
+
+- Added focus view toggle (`Ctrl+O`) in `NO_FLICKER` mode showing prompt, one-line tool summary with edit diffstats, and final response
+- Added `refreshInterval` status line setting to re-run the status line command every N seconds
+- Added `workspace.git_worktree` to the status line JSON input, set when the current directory is inside a linked git worktree
+- Added `● N running` indicator in `/agents` next to agent types with live subagent instances
+- Added syntax highlighting for Cedar policy files (`.cedar`, `.cedarpolicy`)
+- Fixed `--dangerously-skip-permissions` being silently downgraded to accept-edits mode after approving a write to a protected path
+- Fixed and hardened Bash tool permissions, tightening checks around env-var prefixes and network redirects, and reducing false prompts on common commands
+- Fixed permission rules with names matching JavaScript prototype properties (e.g. `toString`) causing `settings.json` to be silently ignored
+- Fixed managed-settings allow rules remaining active after an admin removed them until process restart
+- Fixed `permissions.additionalDirectories` changes in settings not applying mid-session
+- Fixed removing a directory from `settings.permissions.additionalDirectories` revoking access to the same directory passed via `--add-dir`
+- Fixed MCP HTTP/SSE connections accumulating ~50 MB/hr of unreleased buffers when servers reconnect
+- Fixed MCP OAuth `oauth.authServerMetadataUrl` not being honored on token refresh after restart, fixing ADFS and similar IdPs
+- Fixed 429 retries burning all attempts in ~13 seconds when the server returns a small `Retry-After` — exponential backoff now applies as a minimum
+- Fixed rate-limit upgrade options disappearing after context compaction
+- Fixed several `/resume` picker issues: `--resume <name>` opening uneditable, Ctrl+A reload wiping search, empty list swallowing navigation, task-status text replacing conversation summary, and cross-project staleness
+- Fixed file-edit diffs disappearing on `--resume` when the edited file was larger than 10KB
+- Fixed `--resume` cache misses and lost mid-turn input from attachment messages not being saved to the transcript
+- Fixed messages typed while Claude is working not being persisted to the transcript
+- Fixed prompt-type `Stop`/`SubagentStop` hooks failing on long sessions, and hook evaluator API errors displaying "JSON validation failed" instead of the actual message
+- Fixed subagents with worktree isolation or `cwd:` override leaking their working directory back to the parent session's Bash tool
+- Fixed compaction writing duplicate multi-MB subagent transcript files on prompt-too-long retries
+- Fixed `claude plugin update` reporting "already at the latest version" for git-based marketplace plugins when the remote had newer commits
+- Fixed slash command picker breaking when a plugin's frontmatter `name` is a YAML boolean keyword
+- Fixed copying wrapped URLs in `NO_FLICKER` mode inserting spaces at line breaks
+- Fixed scroll rendering artifacts in `NO_FLICKER` mode when running inside zellij
+- Fixed a crash in `NO_FLICKER` mode when hovering over MCP tool results
+- Fixed a `NO_FLICKER` mode memory leak where API retries left stale streaming state
+- Fixed slow mouse-wheel scrolling in `NO_FLICKER` mode on Windows Terminal
+- Fixed custom status line not displaying in `NO_FLICKER` mode on terminals shorter than 24 rows
+- Fixed Shift+Enter and Alt/Cmd+arrow shortcuts not working in Warp with `NO_FLICKER` mode
+- Fixed Korean/Japanese/Unicode text becoming garbled when copied in no-flicker mode on Windows
+- Fixed Bedrock SigV4 authentication failing when `AWS_BEARER_TOKEN_BEDROCK` or `ANTHROPIC_BEDROCK_BASE_URL` are set to empty strings (as GitHub Actions does for unset inputs)
+- Improved Accept Edits mode to auto-approve filesystem commands prefixed with safe env vars or process wrappers (e.g. `LANG=C rm foo`, `timeout 5 mkdir out`)
+- Improved auto mode and bypass-permissions mode to auto-approve sandbox network access prompts
+- Improved sandbox: `sandbox.network.allowMachLookup` now takes effect on macOS
+- Improved image handling: pasted and attached images are now compressed to the same token budget as images read via the Read tool
+- Improved slash command and `@`-mention completion to trigger after CJK sentence punctuation, so Japanese/Chinese input no longer requires a space before `/` or `@`
+- Improved Bridge sessions to show the local git repo, branch, and working directory on the claude.ai session card
+- Improved footer layout: indicators (Focus, notifications) now stay on the mode-indicator row instead of wrapping below
+- Improved context-low warning to show as a transient footer notification instead of a persistent row
+- Improved markdown blockquotes to show a continuous left bar across wrapped lines
+- Improved session transcript size by skipping empty hook entries and capping stored pre-edit file copies
+- Improved transcript accuracy: per-block entries now carry the final token usage instead of the streaming placeholder
+- Improved Bash tool OTEL tracing: subprocesses now inherit a W3C `TRACEPARENT` env var when tracing is enabled
+- Updated `/claude-api` skill to cover Managed Agents alongside the Claude API
+
 ## 2.1.96
 
 - Fixed Bedrock requests failing with `403 "Authorization header is missing"` when using `AWS_BEARER_TOKEN_BEDROCK` or `CLAUDE_CODE_SKIP_BEDROCK_AUTH` (regression in 2.1.94)

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

@@ -29,7 +29,7 @@ Use Claude Code
 
 Best Practices for Claude Code
 
-[Getting started](https://www.anthropic.com/docs/en/overview)[Build with Claude Code](https://www.anthropic.com/docs/en/sub-agents)[Deployment](https://www.anthropic.com/docs/en/third-party-integrations)[Administration](https://www.anthropic.com/docs/en/setup)[Configuration](https://www.anthropic.com/docs/en/settings)[Reference](https://www.anthropic.com/docs/en/cli-reference)[What's New](https://www.anthropic.com/docs/en/whats-new)[Resources](https://www.anthropic.com/docs/en/legal-and-compliance)
+[Getting started](https://www.anthropic.com/docs/en/overview)[Build with Claude Code](https://www.anthropic.com/docs/en/sub-agents)[Deployment](https://www.anthropic.com/docs/en/third-party-integrations)[Administration](https://www.anthropic.com/docs/en/setup)[Configuration](https://www.anthropic.com/docs/en/settings)[Reference](https://www.anthropic.com/docs/en/cli-reference)[Agent SDK](https://www.anthropic.com/docs/en/agent-sdk/overview)[What's New](https://www.anthropic.com/docs/en/whats-new)[Resources](https://www.anthropic.com/docs/en/legal-and-compliance)
 
 ##### Getting started
 
@@ -125,7 +125,7 @@ Claude performs dramatically better when it can verify its own work, like run te
 
 | Strategy | Before | After |
 | --- | --- | --- |
-| **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#7005031502301508111d001c155e131f1d) is true, invalid is false, [[email protected]](https://www.anthropic.com/cdn-cgi/l/email-protection#b8cdcbddcaf896dbd7d5) is false. run the tests after implementing”_ |
+| **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#423731273002273a232f322e276c212d2f) is true, invalid is false, [[email protected]](https://www.anthropic.com/cdn-cgi/l/email-protection#0d787e687f4d236e6260) is false. run the tests after implementing”_ |
 | **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”_ |
 | **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”_ |
 

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

@@ -68,7 +68,7 @@ Our new sandboxed bash tool and Claude Code on the web offer substantial improve
 To get started with these tools:
 
 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.
-2.   Go to [claude.com/code](http://claude.ai/redirect/website.v1.91b9b576-38af-40d7-8b65-118a3bfcad75/code) to try out Claude Code on the web.
+2.   Go to [claude.com/code](http://claude.ai/redirect/website.v1.2c75e6bb-6a63-4eff-b77e-916242daf86e/code) to try out Claude Code on the web.
 
 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.
 

content/claude-code-manifest.json

@@ -1,12 +1,12 @@
 {
   "name": "@anthropic-ai/claude-code",
-  "version": "2.1.96",
+  "version": "2.1.97",
   "author": {
     "name": "Anthropic",
     "email": "support@anthropic.com"
   },
   "license": "SEE LICENSE IN README.md",
-  "_id": "@anthropic-ai/claude-code@2.1.96",
+  "_id": "@anthropic-ai/claude-code@2.1.97",
   "maintainers": [
     {
       "name": "zak-anthropic",
@@ -73,20 +73,20 @@
     "claude": "cli.js"
   },
   "dist": {
-    "shasum": "d528e9638292c7b275c896b283e4a8e6959ef0ef",
-    "tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.96.tgz",
+    "shasum": "b790d417b4f47b897068ffff9b57812ccc81e707",
+    "tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.97.tgz",
     "fileCount": 20,
-    "integrity": "sha512-ETrc0+1qWHaqtKi+ixbsAecZyM+H52VIJj+zWIvw3jBU/JZ9v5vnE2kHShM1lcpr+Gji7GXk23l0CMGLA7hC0g==",
+    "integrity": "sha512-8lKM/rFctBl+82bQ+0g0Lkbt9tJU/zYKAjWisNUq436/386n/VZQbnyjnibGkyqqB6mrX/3ub/cpFlpCu4FXLg==",
     "signatures": [
       {
-        "sig": "MEUCIDfVFVFY0qtDRV8JGrx0/QKyh70/hWuV+lO0LSTt2zz6AiEA20JmCcoQACXgZOSLdrLxZ8I2356j3KvBbianSlhxu0A=",
+        "sig": "MEUCICG6rML8JBFMxvrHFFDhofBztC5mvsOLqHbO7G4bdU4MAiEA/TuR+/HzSBvE2e/5XokcLHWOLaw604eahZ4Hy+IFTew=",
         "keyid": "SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"
       }
     ],
-    "unpackedSize": 48924836
+    "unpackedSize": 48991994
   },
   "type": "module",
-  "_from": "file:/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.96.tgz",
+  "_from": "file:/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.97.tgz",
   "engines": {
     "node": ">=18.0.0"
   },
@@ -97,8 +97,8 @@
     "name": "wolffiex",
     "email": "wolffiex@anthropic.com"
   },
-  "_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.96.tgz",
-  "_integrity": "sha512-ETrc0+1qWHaqtKi+ixbsAecZyM+H52VIJj+zWIvw3jBU/JZ9v5vnE2kHShM1lcpr+Gji7GXk23l0CMGLA7hC0g==",
+  "_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/build-external/anthropic-ai-claude-code-2.1.97.tgz",
+  "_integrity": "sha512-8lKM/rFctBl+82bQ+0g0Lkbt9tJU/zYKAjWisNUq436/386n/VZQbnyjnibGkyqqB6mrX/3ub/cpFlpCu4FXLg==",
   "_npmVersion": "10.8.2",
   "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.",
   "directories": {},
@@ -118,7 +118,7 @@
     "@img/sharp-linuxmusl-arm64": "^0.34.2"
   },
   "_npmOperationalInternal": {
-    "tmp": "tmp/claude-code_2.1.96_1775622763975_0.7218051294969574",
+    "tmp": "tmp/claude-code_2.1.97_1775683674825_0.4147276975853762",
     "host": "s3://npm-registry-packages-npm-production"
   }
 }

content/en/about-claude/models/migration-guide.md

@@ -4,6 +4,10 @@ Guide for migrating to Claude 4.6 models from previous Claude versions
 
 ---
 
+<Note>
+This guide covers migrating [Messages API](/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](/docs/en/managed-agents/overview), see [Migrating between model versions](/docs/en/managed-agents/migration#migrating-between-model-versions). The Managed Agents runtime handles most of the request-shape changes described here.
+</Note>
+
 ## Migrating to Claude 4.6
 
 Claude Opus 4.6 is a near drop-in replacement for Claude 4.5, with a few breaking changes to be aware of. For a full list of new features, see [What's new in Claude 4.6](/docs/en/about-claude/models/whats-new-claude-4-6).
@@ -50,6 +54,20 @@ These are not required but will improve your experience:
    )
    ```
 
+   ```bash CLI
+   ant messages create <<'YAML'
+   model: claude-opus-4-6
+   max_tokens: 16000
+   thinking:
+     type: adaptive
+   output_config:
+     effort: high
+   messages:
+     - role: user
+       content: Your prompt here
+   YAML
+   ```
+
    ```typescript TypeScript hidelines={1..2}
    import Anthropic from "@anthropic-ai/sdk";
 
@@ -222,7 +240,7 @@ model = "claude-opus-4-6"  # After
    Use only `temperature` OR `top_p`, not both:
 
 
-   ```python nocheck
+   ```python Python nocheck
    # Before - This will error in Claude 4+ models
    response = client.messages.create(
        model="claude-3-7-sonnet-20250219",
@@ -263,7 +281,7 @@ model = "claude-opus-4-6"  # After
    Update your application to [handle `refusal` stop reasons](/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals):
 
 
-   ```python nocheck
+   ```python Python nocheck
    response = client.messages.create(...)
 
    if response.stop_reason == "refusal":
@@ -276,7 +294,7 @@ model = "claude-opus-4-6"  # After
    Claude 4.5+ models return a `model_context_window_exceeded` stop reason when generation stops due to hitting the context window limit, rather than the requested `max_tokens` limit. Update your application to handle this new stop reason:
 
 
-   ```python nocheck
+   ```python Python nocheck
    response = client.messages.create(...)
 
    if response.stop_reason == "model_context_window_exceeded":
@@ -436,6 +454,18 @@ curl https://api.anthropic.com/v1/messages \
 }'
 ```
 
+```bash CLI
+ant messages create <<'YAML'
+model: claude-sonnet-4-6
+max_tokens: 8192
+output_config:
+  effort: low
+messages:
+  - role: user
+    content: Your prompt here
+YAML
+```
+
 ```python Python
 response = client.messages.create(
     model="claude-sonnet-4-6",
@@ -615,6 +645,20 @@ curl https://api.anthropic.com/v1/messages \
 }'
 ```
 
+```bash CLI nocheck
+ant messages create <<'YAML'
+model: claude-sonnet-4-6
+max_tokens: 64000
+thinking:
+  type: adaptive
+output_config:
+  effort: medium
+messages:
+  - role: user
+    content: Your prompt here
+YAML
+```
+
 ```python Python nocheck
 response = client.messages.create(
     model="claude-sonnet-4-6",
@@ -803,6 +847,21 @@ curl https://api.anthropic.com/v1/messages \
 }'
 ```
 
+```bash CLI
+ant beta:messages create --beta interleaved-thinking-2025-05-14 <<'YAML'
+model: claude-sonnet-4-6
+max_tokens: 16384
+thinking:
+  type: enabled
+  budget_tokens: 16384
+output_config:
+  effort: medium
+messages:
+  - role: user
+    content: Your prompt here
+YAML
+```
+
 ```python Python
 response = client.beta.messages.create(
     model="claude-sonnet-4-6",
@@ -995,6 +1054,21 @@ curl https://api.anthropic.com/v1/messages \
 }'
 ```
 
+```bash CLI
+ant beta:messages create --beta interleaved-thinking-2025-05-14 <<'YAML'
+model: claude-sonnet-4-6
+max_tokens: 8192
+thinking:
+  type: enabled
+  budget_tokens: 16384
+output_config:
+  effort: low
+messages:
+  - role: user
+    content: Your prompt here
+YAML
+```
+
 ```python Python
 response = client.beta.messages.create(
     model="claude-sonnet-4-6",

content/en/about-claude/models/whats-new-claude-4-6.md

@@ -25,7 +25,7 @@ For complete pricing and specs, see the [models overview](/docs/en/about-claude/
 
 `thinking: {type: "enabled"}` and `budget_tokens` are **deprecated** on Opus 4.6 and Sonnet 4.6. They remain functional but will be removed in a future model release. Use adaptive thinking and the [effort parameter](/docs/en/build-with-claude/effort) to control thinking depth instead. Adaptive thinking also automatically enables interleaved thinking.
 
-```python
+```python Python
 response = client.messages.create(
     model="claude-opus-4-6",
     max_tokens=16000,
@@ -66,7 +66,7 @@ The following tools are now generally available:
 
 [Fast mode](/docs/en/build-with-claude/fast-mode) (`speed: "fast"`) delivers significantly faster output token generation for Opus models. Fast mode is up to 2.5x as fast at premium pricing ($30/$150 per MTok). This is the same model running with faster inference (no change to intelligence or capabilities).
 
-```python
+```python Python
 response = client.beta.messages.create(
     model="claude-opus-4-6",
     max_tokens=4096,
@@ -106,7 +106,7 @@ On **Sonnet 4.6**, the `interleaved-thinking-2025-05-14` beta header is still fu
 
 The `output_format` parameter for [structured outputs](/docs/en/build-with-claude/structured-outputs) has been moved to `output_config.format`. The old parameter remains functional but is deprecated and will be removed in a future model release.
 
-```python nocheck
+```python Python nocheck
 # Before
 response = client.messages.create(
     output_format={"type": "json_schema", "schema": {...}},