claudecode-omc 5.6.5 → 5.6.7

package/bundled/upstream/anthropic-skills/skills/claude-api/shared/models.md

@@ -7,9 +7,9 @@
 For **live** capability data — context window, max output tokens, feature support (thinking, vision, effort, structured outputs, etc.) — query the Models API instead of relying on the cached tables below. Use this when the user asks "what's the context window for X", "does model X support vision/thinking/effort", "which models support feature Y", or wants to select a model by capability at runtime.
 
 ```python
-m = client.models.retrieve("claude-opus-4-6")
-m.id                 # "claude-opus-4-6"
-m.display_name       # "Claude Opus 4.6"
+m = client.models.retrieve("claude-opus-4-7")
+m.id                 # "claude-opus-4-7"
+m.display_name       # "Claude Opus 4.7"
 m.max_input_tokens   # context window (int)
 m.max_tokens         # max output tokens (int)
 
@@ -32,21 +32,21 @@ Top-level fields (`id`, `display_name`, `max_input_tokens`, `max_tokens`) are ty
 ### Raw HTTP
 
 ```bash
-curl https://api.anthropic.com/v1/models/claude-opus-4-6 \
+curl https://api.anthropic.com/v1/models/claude-opus-4-7 \
   -H "x-api-key: $ANTHROPIC_API_KEY" \
   -H "anthropic-version: 2023-06-01"
 ```
 
 ```json
 {
-  "id": "claude-opus-4-6",
-  "display_name": "Claude Opus 4.6",
-  "max_input_tokens": 1000000,
+  "id": "claude-opus-4-7",
+  "display_name": "Claude Opus 4.7",
+  "max_input_tokens": 200000,
   "max_tokens": 128000,
   "capabilities": {
     "image_input": {"supported": true},
     "structured_outputs": {"supported": true},
-    "thinking": {"supported": true, "types": {"enabled": {"supported": true}, "adaptive": {"supported": true}}},
+    "thinking": {"supported": true, "types": {"enabled": {"supported": false}, "adaptive": {"supported": true}}},
     "effort": {"supported": true, "low": {"supported": true}, …, "max": {"supported": true}},
     …
   }
@@ -57,14 +57,15 @@ curl https://api.anthropic.com/v1/models/claude-opus-4-6 \
 
 | Friendly Name     | Alias (use this)    | Full ID                       | Context        | Max Output | Status |
 |-------------------|---------------------|-------------------------------|----------------|------------|--------|
-| Claude Opus 4.6   | `claude-opus-4-6`   | —                             | 200K (1M beta) | 128K       | Active |
-| Claude Sonnet 4.6 | `claude-sonnet-4-6` | -                             | 200K (1M beta) | 64K        | Active |
+| Claude Opus 4.7   | `claude-opus-4-7`   | —                             | 1M             | 128K       | Active |
+| Claude Opus 4.6   | `claude-opus-4-6`   | —                             | 1M             | 128K       | Active |
+| Claude Sonnet 4.6 | `claude-sonnet-4-6` | -                             | 1M             | 64K        | Active |
 | Claude Haiku 4.5  | `claude-haiku-4-5`  | `claude-haiku-4-5-20251001`   | 200K           | 64K        | Active |
 
 ### Model Descriptions
-
-- **Claude Opus 4.6** — Our most intelligent model for building agents and coding. Supports adaptive thinking (recommended), 128K max output tokens (requires streaming for large outputs). 1M context window available in beta via `context-1m-2025-08-07` header.
-- **Claude Sonnet 4.6** — Our best combination of speed and intelligence. Supports adaptive thinking (recommended). 1M context window available in beta via `context-1m-2025-08-07` header. 64K max output tokens.
+- **Claude Opus 4.7** — The most capable Claude model to date — highly autonomous, strong on long-horizon agentic work, knowledge work, vision, and memory. Adaptive thinking only; sampling parameters and `budget_tokens` are removed. 1M context window at standard API pricing (no long-context premium) — see `shared/model-migration.md` → Migrating to Opus 4.7 for breaking changes.
+- **Claude Opus 4.6** — Previous-generation Opus. Supports adaptive thinking (recommended), 128K max output tokens (requires streaming for large outputs). 1M context window.
+- **Claude Sonnet 4.6** — Our best combination of speed and intelligence. Supports adaptive thinking (recommended). 1M context window. 64K max output tokens.
 - **Claude Haiku 4.5** — Fastest and most cost-effective model for simple tasks.
 
 ## Legacy Models (still active)
@@ -102,7 +103,8 @@ When a user asks for a model by name, use this table to find the correct model I
 
 | User says...                              | Use this model ID              |
 |-------------------------------------------|--------------------------------|
-| "opus", "most powerful"                   | `claude-opus-4-6`              |
+| "opus", "most powerful"                   | `claude-opus-4-7`              |
+| "opus 4.7"                                | `claude-opus-4-7`              |
 | "opus 4.6"                                | `claude-opus-4-6`              |
 | "opus 4.5"                                | `claude-opus-4-5`              |
 | "opus 4.1"                                | `claude-opus-4-1`              |

package/bundled/upstream/anthropic-skills/skills/claude-api/shared/prompt-caching.md

@@ -107,9 +107,17 @@ Fix by moving the dynamic piece after the last breakpoint, making it determinist
 - Max **4** `cache_control` breakpoints per request.
 - Goes on any content block: system text blocks, tool definitions, message content blocks (`text`, `image`, `tool_use`, `tool_result`, `document`).
 - Top-level `cache_control` on `messages.create()` auto-places on the last cacheable block — simplest option when you don't need fine-grained placement.
-- Minimum cacheable prefix is model-dependent (typically 1024–2048 tokens). Shorter prefixes silently won't cache even with a marker.
+- Minimum cacheable prefix is model-dependent. Shorter prefixes silently won't cache even with a marker — no error, just `cache_creation_input_tokens: 0`:
 
-**Economics:** Cache writes cost ~1.25× base input price; reads cost ~0.1×. A prefix must be used in at least two requests within TTL to break even (one writes the cache, subsequent ones read it). For bursty traffic, the 1-hour TTL keeps entries alive across gaps.
+| Model | Minimum |
+|---|---:|
+| Opus 4.7, Opus 4.6, Opus 4.5, Haiku 4.5 | 4096 tokens |
+| Sonnet 4.6, Haiku 3.5, Haiku 3 | 2048 tokens |
+| Sonnet 4.5, Sonnet 4.1, Sonnet 4, Sonnet 3.7 | 1024 tokens |
+
+A 3K-token prompt caches on Sonnet 4.5 but silently won't on Opus 4.7.
+
+**Economics:** Cache reads cost ~0.1× base input price. Cache writes cost **1.25× for 5-minute TTL, 2× for 1-hour TTL**. Break-even depends on TTL: with 5-minute TTL, two requests break even (1.25× + 0.1× = 1.35× vs 2× uncached); with 1-hour TTL, you need at least three requests (2× + 0.2× = 2.2× vs 3× uncached). The 1-hour TTL keeps entries alive across gaps in bursty traffic, but the doubled write cost means it needs more reads to pay off.
 
 ---
 
@@ -125,4 +133,39 @@ The response `usage` object reports cache activity:
 
 If `cache_read_input_tokens` is zero across repeated requests with identical prefixes, a silent invalidator is at work — diff the rendered prompt bytes between two requests to find it.
 
+**`input_tokens` is the uncached remainder only.** Total prompt size = `input_tokens + cache_creation_input_tokens + cache_read_input_tokens`. If your agent ran for hours but `input_tokens` shows 4K, the rest was served from cache — check the sum, not the single field.
+
 Language-specific access: `response.usage.cache_read_input_tokens` (Python/TS/Ruby), `$message->usage->cacheReadInputTokens` (PHP), `resp.Usage.CacheReadInputTokens` (Go/C#), `.usage().cacheReadInputTokens()` (Java).
+
+---
+
+## Invalidation hierarchy
+
+Not every parameter change invalidates everything. The API has three cache tiers, and changes only invalidate their own tier and below:
+
+| Change | Tools cache | System cache | Messages cache |
+|---|:---:|:---:|:---:|
+| Tool definitions (add/remove/reorder) | ❌ | ❌ | ❌ |
+| Model switch | ❌ | ❌ | ❌ |
+| `speed`, web-search, citations toggle | ✅ | ❌ | ❌ |
+| System prompt content | ✅ | ❌ | ❌ |
+| `tool_choice`, images, `thinking` enable/disable | ✅ | ✅ | ❌ |
+| Message content | ✅ | ✅ | ❌ |
+
+Implication: you can change `tool_choice` per-request or toggle `thinking` without losing the tools+system cache. Don't over-worry about these — only tool-definition and model changes force a full rebuild.
+
+---
+
+## 20-block lookback window
+
+Each breakpoint walks backward **at most 20 content blocks** to find a prior cache entry. If a single turn adds more than 20 blocks (common in agentic loops with many tool_use/tool_result pairs), the next request's breakpoint won't find the previous cache and silently misses.
+
+Fix: place an intermediate breakpoint every ~15 blocks in long turns, or put the marker on a block that's within 20 of the previous turn's last cached block.
+
+---
+
+## Concurrent-request timing
+
+A cache entry becomes readable only after the first response **begins streaming**. N parallel requests with identical prefixes all pay full price — none can read what the others are still writing.
+
+For fan-out patterns: send 1 request, await the first streamed token (not the full response), then fire the remaining N−1. They'll read the cache the first one just wrote.

package/bundled/upstream/anthropic-skills/skills/claude-api/shared/tool-use-concepts.md

@@ -1,6 +1,6 @@
 # Tool Use Concepts
 
-This file covers the conceptual foundations of tool use with the Claude API. For language-specific code examples, see the `python/`, `typescript/`, or other language folders.
+This file covers the conceptual foundations of tool use with the Claude API. For language-specific code examples, see the `python/`, `typescript/`, or other language folders. For decision heuristics on which tools to expose, how to manage context in long-running agents, and caching strategy, see `agent-design.md`.
 
 ## User-Defined Tools
 
@@ -74,7 +74,7 @@ if response.stop_reason == "pause_turn":
     ]
     # Make another API request — server resumes automatically
     response = client.messages.create(
-        model="claude-opus-4-6", messages=messages, tools=tools
+        model="claude-opus-4-7", messages=messages, tools=tools
     )
 ```
 
@@ -171,7 +171,7 @@ Web search and web fetch let Claude search the web and retrieve page content. Th
 ]
 ```
 
-### Dynamic Filtering (Opus 4.6 / Sonnet 4.6)
+### Dynamic Filtering (Opus 4.7 / Opus 4.6 / Sonnet 4.6)
 
 The `web_search_20260209` and `web_fetch_20260209` versions support **dynamic filtering** — Claude writes and executes code to filter search results before they reach the context window, improving accuracy and token efficiency. Dynamic filtering is built into these tool versions and activates automatically; you do not need to separately declare the `code_execution` tool or pass any beta header.
 
@@ -192,7 +192,9 @@ Without dynamic filtering, the previous `web_search_20250305` version is also av
 
 ## Server-Side Tools: Programmatic Tool Calling
 
-Programmatic tool calling lets Claude execute complex multi-tool workflows in code, keeping intermediate results out of the context window. Claude writes code that calls your tools directly, reducing token usage for multi-step operations.
+With standard tool use, each tool call is a round trip: Claude calls, the result enters Claude's context, Claude reasons, then calls the next tool. Chained calls accumulate latency and tokens — most of that intermediate data is never needed again.
+
+Programmatic tool calling lets Claude compose those calls into a script. The script runs in the code execution container; when it invokes a tool, the container pauses, the call executes, and the result returns to the running code (not to Claude's context). The script processes it with normal control flow. Only the final output returns to Claude. Use it when chaining many tool calls or when intermediate results are large and should be filtered before reaching the context window.
 
 For full documentation, use WebFetch:
 
@@ -202,7 +204,7 @@ For full documentation, use WebFetch:
 
 ## Server-Side Tools: Tool Search
 
-The tool search tool lets Claude dynamically discover tools from large libraries without loading all definitions into the context window. Useful when you have many tools but only a few are relevant to any given query.
+The tool search tool lets Claude dynamically discover tools from large libraries without loading all definitions into the context window. Use it when you have many tools but only a few are relevant to any given request. Discovered tool schemas are appended to the request, not swapped in — this preserves the prompt cache (see `agent-design.md` §Caching for Agents).
 
 For full documentation, use WebFetch:
 
@@ -210,6 +212,16 @@ For full documentation, use WebFetch:
 
 ---
 
+## Skills
+
+Skills package task-specific instructions that Claude loads only when relevant. Each skill is a folder containing a `SKILL.md` file. The skill's short description sits in context by default; Claude reads the full file when the current task calls for it. Use skills to keep specialized instructions out of the base system prompt without losing discoverability.
+
+For full documentation, use WebFetch:
+
+- URL: `https://platform.claude.com/docs/en/agents-and-tools/skills`
+
+---
+
 ## Tool Use Examples
 
 You can provide sample tool calls directly in your tool definitions to demonstrate usage patterns and reduce parameter errors. This helps Claude understand how to correctly format tool inputs, especially for tools with complex schemas.
@@ -230,6 +242,16 @@ For full documentation, use WebFetch:
 
 ---
 
+## Context Editing
+
+Context editing clears stale tool results and thinking blocks from the transcript as a long-running agent accumulates turns. Unlike compaction (which summarizes), context editing prunes — the cleared content is removed, not replaced. Use it when old tool outputs are no longer relevant and you want to keep the transcript lean without losing the conversation structure. Thresholds for what to clear are configurable.
+
+For full documentation, use WebFetch:
+
+- URL: `https://platform.claude.com/docs/en/build-with-claude/context-editing`
+
+---
+
 ## Client-Side Tools: Memory
 
 The memory tool enables Claude to store and retrieve information across conversations through a memory file directory. Claude can create, read, update, and delete files that persist between sessions.
@@ -258,7 +280,7 @@ Two features are available:
 - **JSON outputs** (`output_config.format`): Control Claude's response format
 - **Strict tool use** (`strict: true`): Guarantee valid tool parameter schemas
 
-**Supported models:** Claude Opus 4.6, Claude Sonnet 4.6, and Claude Haiku 4.5. Legacy models (Claude Opus 4.5, Claude Opus 4.1) also support structured outputs.
+**Supported models:** Claude Opus 4.7, Claude Sonnet 4.6, and Claude Haiku 4.5. Legacy models (Claude Opus 4.5, Claude Opus 4.1) also support structured outputs.
 
 > **Recommended:** Use `client.messages.parse()` which automatically validates responses against your schema. When using `messages.create()` directly, use `output_config: {format: {...}}`. The `output_format` convenience parameter is also accepted by some SDK methods (e.g., `.parse()`), but `output_config.format` is the canonical API-level parameter.
 

package/bundled/upstream/anthropic-skills/skills/claude-api/typescript/claude-api/README.md

@@ -24,7 +24,7 @@ const client = new Anthropic({ apiKey: "your-api-key" });
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [{ role: "user", content: "What is the capital of France?" }],
 });
@@ -43,7 +43,7 @@ for (const block of response.content) {
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   system:
     "You are a helpful coding assistant. Always provide examples in Python.",
@@ -59,7 +59,7 @@ const response = await client.messages.create({
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -84,7 +84,7 @@ import fs from "fs";
 const imageData = fs.readFileSync("image.png").toString("base64");
 
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -113,7 +113,7 @@ Use top-level `cache_control` to automatically cache the last cacheable block in
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   cache_control: { type: "ephemeral" }, // auto-caches the last cacheable block
   system: "You are an expert on this large document...",
@@ -127,7 +127,7 @@ For fine-grained control, add `cache_control` to specific content blocks:
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   system: [
     {
@@ -141,7 +141,7 @@ const response = await client.messages.create({
 
 // With explicit TTL (time-to-live)
 const response2 = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   system: [
     {
@@ -168,13 +168,13 @@ If `cache_read_input_tokens` is zero across repeated identical-prefix requests,
 
 ## Extended Thinking
 
-> **Opus 4.6 and Sonnet 4.6:** Use adaptive thinking. `budget_tokens` is deprecated on both Opus 4.6 and Sonnet 4.6.
+> **Opus 4.7, Opus 4.6, and Sonnet 4.6:** Use adaptive thinking. `budget_tokens` is removed on Opus 4.7 (400 if sent); deprecated on Opus 4.6 and Sonnet 4.6.
 > **Older models:** Use `thinking: {type: "enabled", budget_tokens: N}` (must be < `max_tokens`, min 1024).
 
 ```typescript
-// Opus 4.6: adaptive thinking (recommended)
+// Opus 4.7 / 4.6: adaptive thinking (recommended)
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   thinking: { type: "adaptive" },
   output_config: { effort: "high" }, // low | medium | high | max
@@ -232,7 +232,7 @@ const messages: Anthropic.MessageParam[] = [
 ];
 
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: messages,
 });
@@ -248,7 +248,7 @@ const response = await client.messages.create({
 
 ### Compaction (long conversations)
 
-> **Beta, Opus 4.6 and Sonnet 4.6.** When conversations approach the 200K context window, compaction automatically summarizes earlier context server-side. The API returns a `compaction` block; you must pass it back on subsequent requests — append `response.content`, not just the text.
+> **Beta, Opus 4.7, Opus 4.6, and Sonnet 4.6.** When conversations approach the 200K context window, compaction automatically summarizes earlier context server-side. The API returns a `compaction` block; you must pass it back on subsequent requests — append `response.content`, not just the text.
 
 ```typescript
 import Anthropic from "@anthropic-ai/sdk";
@@ -261,7 +261,7 @@ async function chat(userMessage: string): Promise<string> {
 
   const response = await client.beta.messages.create({
     betas: ["compact-2026-01-12"],
-    model: "claude-opus-4-6",
+    model: "claude-opus-4-7",
     max_tokens: 16000,
     messages,
     context_management: {
@@ -308,7 +308,7 @@ The `stop_reason` field in the response indicates why the model stopped generati
 ```typescript
 // Automatic caching (simplest — caches the last cacheable block)
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   cache_control: { type: "ephemeral" },
   system: largeDocumentText, // e.g., 50KB of context
@@ -323,7 +323,7 @@ const response = await client.messages.create({
 
 ```typescript
 const countResponse = await client.messages.countTokens({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   messages: messages,
   system: system,
 });

package/bundled/upstream/anthropic-skills/skills/claude-api/typescript/claude-api/batches.md

@@ -24,7 +24,7 @@ const messageBatch = await client.messages.batches.create({
     {
       custom_id: "request-1",
       params: {
-        model: "claude-opus-4-6",
+        model: "claude-opus-4-7",
         max_tokens: 16000,
         messages: [
           { role: "user", content: "Summarize climate change impacts" },
@@ -34,7 +34,7 @@ const messageBatch = await client.messages.batches.create({
     {
       custom_id: "request-2",
       params: {
-        model: "claude-opus-4-6",
+        model: "claude-opus-4-7",
         max_tokens: 16000,
         messages: [
           { role: "user", content: "Explain quantum computing basics" },

package/bundled/upstream/anthropic-skills/skills/claude-api/typescript/claude-api/files-api.md

@@ -41,7 +41,7 @@ console.log(`Size: ${uploaded.size_bytes} bytes`);
 
 ```typescript
 const response = await client.beta.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {

package/bundled/upstream/anthropic-skills/skills/claude-api/typescript/claude-api/streaming.md

@@ -4,7 +4,7 @@
 
 ```typescript
 const stream = client.messages.stream({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 64000,
   messages: [{ role: "user", content: "Write a story" }],
 });
@@ -23,11 +23,11 @@ for await (const event of stream) {
 
 ## Handling Different Content Types
 
-> **Opus 4.6:** Use `thinking: {type: "adaptive"}`. On older models, use `thinking: {type: "enabled", budget_tokens: N}` instead.
+> **Opus 4.7 / Opus 4.6:** Use `thinking: {type: "adaptive"}`. On older models, use `thinking: {type: "enabled", budget_tokens: N}` instead.
 
 ```typescript
 const stream = client.messages.stream({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 64000,
   thinking: { type: "adaptive" },
   messages: [{ role: "user", content: "Analyze this problem" }],
@@ -82,7 +82,7 @@ const getWeather = betaZodTool({
 });
 
 const runner = client.beta.messages.toolRunner({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 64000,
   tools: [getWeather],
   messages: [
@@ -117,7 +117,7 @@ for await (const messageStream of runner) {
 
 ```typescript
 const stream = client.messages.stream({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 64000,
   messages: [{ role: "user", content: "Hello" }],
 });

package/bundled/upstream/anthropic-skills/skills/claude-api/typescript/claude-api/tool-use.md

@@ -30,7 +30,7 @@ const getWeather = betaZodTool({
 
 // The tool runner handles the agentic loop and returns the final message
 const finalMessage = await client.beta.messages.toolRunner({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   tools: [getWeather],
   messages: [{ role: "user", content: "What's the weather in Paris?" }],
@@ -61,7 +61,7 @@ let messages: Anthropic.MessageParam[] = [{ role: "user", content: userInput }];
 
 while (true) {
   const response = await client.messages.create({
-    model: "claude-opus-4-6",
+    model: "claude-opus-4-7",
     max_tokens: 16000,
     tools: tools,
     messages: messages,
@@ -108,7 +108,7 @@ let messages: Anthropic.MessageParam[] = [{ role: "user", content: userInput }];
 
 while (true) {
   const stream = client.messages.stream({
-    model: "claude-opus-4-6",
+    model: "claude-opus-4-7",
     max_tokens: 64000,
     tools,
     messages,
@@ -163,7 +163,7 @@ while (true) {
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   tools: tools,
   messages: [{ role: "user", content: "What's the weather in Paris?" }],
@@ -174,7 +174,7 @@ for (const block of response.content) {
     const result = await executeTool(block.name, block.input);
 
     const followup = await client.messages.create({
-      model: "claude-opus-4-6",
+      model: "claude-opus-4-7",
       max_tokens: 16000,
       tools: tools,
       messages: [
@@ -198,7 +198,7 @@ for (const block of response.content) {
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   tools: tools,
   tool_choice: { type: "tool", name: "get_weather" },
@@ -217,7 +217,7 @@ Version-suffixed `type` literals; `name` is fixed per interface. Pass plain obje
 ```typescript
 // ✓ let inference work — no annotation
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   tools: [
     { type: "text_editor_20250728", name: "str_replace_based_edit_tool" },
@@ -257,7 +257,7 @@ import Anthropic from "@anthropic-ai/sdk";
 const client = new Anthropic();
 
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -305,7 +305,7 @@ const uploaded = await client.beta.files.upload({
 // Code execution is GA; Files API is still beta (pass via RequestOptions)
 const response = await client.messages.create(
   {
-    model: "claude-opus-4-6",
+    model: "claude-opus-4-7",
     max_tokens: 16000,
     messages: [
       {
@@ -365,7 +365,7 @@ for (const block of response.content) {
 ```typescript
 // First request: set up environment
 const response1 = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -382,7 +382,7 @@ const containerId = response1.container!.id;
 
 const response2 = await client.messages.create({
   container: containerId,
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -402,7 +402,7 @@ const response2 = await client.messages.create({
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -436,7 +436,7 @@ const handlers: MemoryToolHandlers = {
 const memory = betaMemoryTool(handlers);
 
 const runner = client.beta.messages.toolRunner({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   tools: [memory],
   messages: [{ role: "user", content: "Remember my preferences" }],
@@ -473,7 +473,7 @@ const ContactInfoSchema = z.object({
 const client = new Anthropic();
 
 const response = await client.messages.parse({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {
@@ -495,7 +495,7 @@ console.log(response.parsed_output!.name); // "Jane Doe"
 
 ```typescript
 const response = await client.messages.create({
-  model: "claude-opus-4-6",
+  model: "claude-opus-4-7",
   max_tokens: 16000,
   messages: [
     {