docs: Claude Code v2.1.220 - mid-conversation tool changes beta, fallback API overhaul, plan mode + auto mode integration

content/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 2.1.220
+
+- Bug fixes and reliability improvements
+
 ## 2.1.219
 
 - Added Claude Opus 5 (`claude-opus-5`), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok
@@ -10,10 +14,7 @@
 - Added nested subagent forwarding in stream-json: subagents spawned at depth-2+ now appear when `--forward-subagent-text` is set, keyed by their spawning Agent `tool_use` id
 - Fixed `claude -p` text output dropping the answer already produced when a turn dies on a mid-stream API error
 - Added HTTP status and error text to `claude mcp list` and `/mcp` when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace
-- Fixed a permission you approved while a self-hosted runner was restarting being dropped when the session resumed, so the approved action now runs
 - Fixed the Fable model row showing "Requires usage credits" for plans that include it, when a stale cache had baked the label in
-- Fixed a SIGTERM arriving while a self-hosted runner was starting up leaving a stale active row until the lease expired; it now deregisters cleanly
-- Added structured failure categories to self-hosted runner spawn and session failures, so hook errors, runner crashes and config errors can be told apart
 - Fixed the `/model` picker showing the merged Opus row as plain "Opus" instead of "Opus (1M context)"
 - Fixed copy-on-select inside GNU screen printing base64 into the terminal instead of copying the selection
 - Fixed Remote Control clients keeping a stale fast-mode status after a model switch, reconnect, or failed org check
@@ -953,7 +954,6 @@
 
 ## 2.1.169
 
-- 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)
 - 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
 - Added `/cd` command to move a session to a new working directory without breaking the prompt cache mid-session
 - 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

content/claude-code-manifest.json

@@ -1,12 +1,12 @@
 {
   "name": "@anthropic-ai/claude-code",
-  "version": "2.1.219",
+  "version": "2.1.220",
   "author": {
     "name": "Anthropic",
     "email": "support@anthropic.com"
   },
   "license": "SEE LICENSE IN README.md",
-  "_id": "@anthropic-ai/claude-code@2.1.219",
+  "_id": "@anthropic-ai/claude-code@2.1.220",
   "maintainers": [
     {
       "name": "zak-anthropic",
@@ -69,24 +69,24 @@
     "claude": "bin/claude.exe"
   },
   "dist": {
-    "shasum": "7849f29b80da65065a14f16d520a7f8c433f895b",
-    "tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.219.tgz",
+    "shasum": "29e7249f01f9602b78c2d5f3c2f1c8a11b2ebcb4",
+    "tarball": "https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-2.1.220.tgz",
     "fileCount": 7,
-    "integrity": "sha512-6PVBrRsKHFi0gzv5bCabVL+XSqI3F8AR6ekFx4gpzdE5a9XotqewolID0PbcdD9IyWVYCIDET4GDCcUdA89i3Q==",
+    "integrity": "sha512-ogBrvwkqF9f8okmnXKxmRNHuvtFxFEffe5pWdqOV3iQDxlUOKirFqnyWC7NGXXnDA4WkkbPH8pvSbwyCR2Auyw==",
     "signatures": [
       {
-        "sig": "MEQCIG75mrsMxC3YQTnCcPmBeHwr1f9g7ePFmyx5w2CXKvG4AiAhugEXOCz+p4i9ah/rKGNQ7W6bD1P91J1ZN9KRzVJdSg==",
+        "sig": "MEUCIHW1JyfEcj1vhz8RXPKrYC4Hd8AacYkcd3YCWdvM4bSIAiEAwqLm9vy1jpLerInCnPvHPMQdXwVQ3ysAR1ulFc5YzyY=",
         "keyid": "SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"
       },
       {
-        "sig": "MEUCIQCWsFSESf0pIESXKkYOlZvGH6SGYGzsslI7QD7g/aeEYwIgHlgHLYRj4GcQ51PyprSajcWQk0yZ7B34NupQZ6b6eWQ=",
+        "sig": "MEUCIBgobvXrtU5I+/OOn7mGb2Z9Y+PmFwH6x5UCd6vK32jiAiEAsqm9BJnZ7USra8F85N99oIE5OrbO7zMcXZxuhWiDlPc=",
         "keyid": "SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"
       }
     ],
     "unpackedSize": 165478
   },
   "type": "module",
-  "_from": "file:staged-npm/anthropic-ai-claude-code-2.1.219.tgz",
+  "_from": "file:staged-npm/anthropic-ai-claude-code-2.1.220.tgz",
   "engines": {
     "node": ">=22.0.0"
   },
@@ -98,8 +98,8 @@
     "name": "wolffiex",
     "email": "wolffiex@anthropic.com"
   },
-  "_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/staged-npm/anthropic-ai-claude-code-2.1.219.tgz",
-  "_integrity": "sha512-6PVBrRsKHFi0gzv5bCabVL+XSqI3F8AR6ekFx4gpzdE5a9XotqewolID0PbcdD9IyWVYCIDET4GDCcUdA89i3Q==",
+  "_resolved": "/home/runner/work/claude-cli-internal/claude-cli-internal/staged-npm/anthropic-ai-claude-code-2.1.220.tgz",
+  "_integrity": "sha512-ogBrvwkqF9f8okmnXKxmRNHuvtFxFEffe5pWdqOV3iQDxlUOKirFqnyWC7NGXXnDA4WkkbPH8pvSbwyCR2Auyw==",
   "_npmVersion": "11.16.0",
   "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": {},
@@ -108,17 +108,17 @@
   "_hasShrinkwrap": false,
   "readmeFilename": "README.md",
   "optionalDependencies": {
-    "@anthropic-ai/claude-code-linux-x64": "2.1.219",
-    "@anthropic-ai/claude-code-win32-x64": "2.1.219",
-    "@anthropic-ai/claude-code-darwin-x64": "2.1.219",
-    "@anthropic-ai/claude-code-linux-arm64": "2.1.219",
-    "@anthropic-ai/claude-code-win32-arm64": "2.1.219",
-    "@anthropic-ai/claude-code-darwin-arm64": "2.1.219",
-    "@anthropic-ai/claude-code-linux-x64-musl": "2.1.219",
-    "@anthropic-ai/claude-code-linux-arm64-musl": "2.1.219"
+    "@anthropic-ai/claude-code-linux-x64": "2.1.220",
+    "@anthropic-ai/claude-code-win32-x64": "2.1.220",
+    "@anthropic-ai/claude-code-darwin-x64": "2.1.220",
+    "@anthropic-ai/claude-code-linux-arm64": "2.1.220",
+    "@anthropic-ai/claude-code-win32-arm64": "2.1.220",
+    "@anthropic-ai/claude-code-darwin-arm64": "2.1.220",
+    "@anthropic-ai/claude-code-linux-x64-musl": "2.1.220",
+    "@anthropic-ai/claude-code-linux-arm64-musl": "2.1.220"
   },
   "_npmOperationalInternal": {
-    "tmp": "tmp/claude-code_2.1.219_1784909509727_0.3364890058271168",
+    "tmp": "tmp/claude-code_2.1.220_1784934681711_0.3834738675106979",
     "host": "s3://npm-registry-packages-npm-production"
   }
 }

content/en/about-claude/models/choosing-a-model.md

@@ -9,9 +9,9 @@ Selecting the optimal Claude model for your application involves balancing three
 When choosing a Claude model, consider first evaluating these factors:
 
 * **Capabilities:** What specific features or capabilities will you need the model to have to meet your needs?
-* **Speed:** How quickly does the model need to respond in your application? Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7 support [fast mode](/docs/en/build-with-claude/fast-mode) (research preview), which delivers up to 2.5x higher output speed at premium pricing. Fast mode on Claude Opus 4.7 is deprecated, with removal on July 24, 2026.
+* **Speed:** How quickly does the model need to respond in your application? Claude Opus 5 and Claude Opus 4.8 support [fast mode](/docs/en/build-with-claude/fast-mode) (research preview), which delivers up to 2.5x higher output speed at premium pricing.
 * **Cost:** What's your budget for both development and production usage?
-* **Effort:** Recent Opus and Sonnet models support an [effort parameter](/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7, the `xhigh` effort level, between `high` and `max`, is the best setting for most coding and agentic use cases.
+* **Effort:** Recent Opus and Sonnet models support an [effort parameter](/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Claude Opus 5, start with the default (`high`) and adjust up or down based on your evals. On Claude Opus 4.8 and Claude Opus 4.7, the `xhigh` effort level, between `high` and `max`, is the best setting for most coding and agentic use cases.
 
 Knowing these answers in advance will make narrowing down and deciding which model to use much easier.
 
@@ -55,7 +55,7 @@ This approach is best for:
 * Advanced coding and high-autonomy agentic work
 
 <Note>
-  The [effort parameter](/docs/en/build-with-claude/effort) defaults to `high` on Claude Opus 5 and Claude Opus 4.8, including in Claude Code and the Messages API. Use `xhigh` for coding, high-autonomy work, and the most intelligence-demanding tasks.
+  The [effort parameter](/docs/en/build-with-claude/effort) defaults to `high` on Claude Opus 5 and Claude Opus 4.8, including in Claude Code and the Messages API. On Claude Opus 5, start at the default and step up to `xhigh` for the most demanding coding and agentic work. On Claude Opus 4.8, use `xhigh` for coding, high-autonomy work, and the most intelligence-demanding tasks.
 </Note>
 
 **Claude Opus 5** (`claude-opus-5`) is a step-change improvement over Claude Opus 4.8, strong on deep reasoning, agentic and long-horizon tasks, and test-time compute scaling. Claude Opus 5 supports a 1M token context window by default and up to 128k output tokens, and is priced at $5 per million input tokens and $25 per million output tokens.

content/en/about-claude/models/introducing-claude-fable-5-and-claude-mythos-5.md

@@ -38,7 +38,7 @@ When Claude Fable 5 declines a request, the Messages API returns `stop_reason: "
 
 A request that Claude Fable 5 refuses can usually be served by another Claude model. There are three ways to retry:
 
-* **Server-side:** Pass the `fallbacks` parameter to have the API retry for you (in beta on the Claude API). See [Server-side fallback](/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback).
+* **Server-side:** Pass the `fallbacks` parameter to have the API retry for you, using its `"default"` mode for Anthropic's recommended models or naming your own (in beta on the Claude API). See [Server-side fallback](/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback).
 * **Client-side:** Use the [SDK middleware](/docs/en/cli-sdks-libraries/middleware) to retry from the client on any platform. See [Client-side fallback](/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback).
 * **Manual:** Build the retry yourself, on any platform and in any language. See [Fallback credit](/docs/en/build-with-claude/fallback-credit).