claudecode-omc 5.2.0 → 5.4.0

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

@@ -0,0 +1,206 @@
+# HTTP Error Codes Reference
+
+This file documents HTTP error codes returned by the Claude API, their common causes, and how to handle them. For language-specific error handling examples, see the `python/` or `typescript/` folders.
+
+## Error Code Summary
+
+| Code | Error Type              | Retryable | Common Cause                         |
+| ---- | ----------------------- | --------- | ------------------------------------ |
+| 400  | `invalid_request_error` | No        | Invalid request format or parameters |
+| 401  | `authentication_error`  | No        | Invalid or missing API key           |
+| 403  | `permission_error`      | No        | API key lacks permission             |
+| 404  | `not_found_error`       | No        | Invalid endpoint or model ID         |
+| 413  | `request_too_large`     | No        | Request exceeds size limits          |
+| 429  | `rate_limit_error`      | Yes       | Too many requests                    |
+| 500  | `api_error`             | Yes       | Anthropic service issue              |
+| 529  | `overloaded_error`      | Yes       | API is temporarily overloaded        |
+
+## Detailed Error Information
+
+### 400 Bad Request
+
+**Causes:**
+
+- Malformed JSON in request body
+- Missing required parameters (`model`, `max_tokens`, `messages`)
+- Invalid parameter types (e.g., string where integer expected)
+- Empty messages array
+- Messages not alternating user/assistant
+
+**Example error:**
+
+```json
+{
+  "type": "error",
+  "error": {
+    "type": "invalid_request_error",
+    "message": "messages: roles must alternate between \"user\" and \"assistant\""
+  },
+  "request_id": "req_011CSHoEeqs5C35K2UUqR7Fy"
+}
+```
+
+**Fix:** Validate request structure before sending. Check that:
+
+- `model` is a valid model ID
+- `max_tokens` is a positive integer
+- `messages` array is non-empty and alternates correctly
+
+---
+
+### 401 Unauthorized
+
+**Causes:**
+
+- Missing `x-api-key` header or `Authorization` header
+- Invalid API key format
+- Revoked or deleted API key
+
+**Fix:** Ensure `ANTHROPIC_API_KEY` environment variable is set correctly.
+
+---
+
+### 403 Forbidden
+
+**Causes:**
+
+- API key doesn't have access to the requested model
+- Organization-level restrictions
+- Attempting to access beta features without beta access
+
+**Fix:** Check your API key permissions in the Console. You may need a different API key or to request access to specific features.
+
+---
+
+### 404 Not Found
+
+**Causes:**
+
+- Typo in model ID (e.g., `claude-sonnet-4.6` instead of `claude-sonnet-4-6`)
+- Using deprecated model ID
+- Invalid API endpoint
+
+**Fix:** Use exact model IDs from the models documentation. You can use aliases (e.g., `claude-opus-4-6`).
+
+---
+
+### 413 Request Too Large
+
+**Causes:**
+
+- Request body exceeds maximum size
+- Too many tokens in input
+- Image data too large
+
+**Fix:** Reduce input size — truncate conversation history, compress/resize images, or split large documents into chunks.
+
+---
+
+### 400 Validation Errors
+
+Some 400 errors are specifically related to parameter validation:
+
+- `max_tokens` exceeds model's limit
+- Invalid `temperature` value (must be 0.0-1.0)
+- `budget_tokens` >= `max_tokens` in extended thinking
+- Invalid tool definition schema
+
+**Common mistake with extended thinking:**
+
+```
+# Wrong: budget_tokens must be < max_tokens
+thinking: budget_tokens=10000, max_tokens=1000  → Error!
+
+# Correct
+thinking: budget_tokens=10000, max_tokens=16000
+```
+
+---
+
+### 429 Rate Limited
+
+**Causes:**
+
+- Exceeded requests per minute (RPM)
+- Exceeded tokens per minute (TPM)
+- Exceeded tokens per day (TPD)
+
+**Headers to check:**
+
+- `retry-after`: Seconds to wait before retrying
+- `x-ratelimit-limit-*`: Your limits
+- `x-ratelimit-remaining-*`: Remaining quota
+
+**Fix:** The Anthropic SDKs automatically retry 429 and 5xx errors with exponential backoff (default: `max_retries=2`). For custom retry behavior, see the language-specific error handling examples.
+
+---
+
+### 500 Internal Server Error
+
+**Causes:**
+
+- Temporary Anthropic service issue
+- Bug in API processing
+
+**Fix:** Retry with exponential backoff. If persistent, check [status.anthropic.com](https://status.anthropic.com).
+
+---
+
+### 529 Overloaded
+
+**Causes:**
+
+- High API demand
+- Service capacity reached
+
+**Fix:** Retry with exponential backoff. Consider using a different model (Haiku is often less loaded), spreading requests over time, or implementing request queuing.
+
+---
+
+## Common Mistakes and Fixes
+
+| Mistake                         | Error            | Fix                                                     |
+| ------------------------------- | ---------------- | ------------------------------------------------------- |
+| `budget_tokens` >= `max_tokens` | 400              | Ensure `budget_tokens` < `max_tokens`                   |
+| Typo in model ID                | 404              | Use valid model ID like `claude-opus-4-6`               |
+| First message is `assistant`    | 400              | First message must be `user`                            |
+| Consecutive same-role messages  | 400              | Alternate `user` and `assistant`                        |
+| API key in code                 | 401 (leaked key) | Use environment variable                                |
+| Custom retry needs              | 429/5xx          | SDK retries automatically; customize with `max_retries` |
+
+## Typed Exceptions in SDKs
+
+**Always use the SDK's typed exception classes** instead of checking error messages with string matching. Each HTTP error code maps to a specific exception class:
+
+| HTTP Code | TypeScript Class                  | Python Class                      |
+| --------- | --------------------------------- | --------------------------------- |
+| 400       | `Anthropic.BadRequestError`       | `anthropic.BadRequestError`       |
+| 401       | `Anthropic.AuthenticationError`   | `anthropic.AuthenticationError`   |
+| 403       | `Anthropic.PermissionDeniedError` | `anthropic.PermissionDeniedError` |
+| 404       | `Anthropic.NotFoundError`         | `anthropic.NotFoundError`         |
+| 429       | `Anthropic.RateLimitError`        | `anthropic.RateLimitError`        |
+| 500+      | `Anthropic.InternalServerError`   | `anthropic.InternalServerError`   |
+| Any       | `Anthropic.APIError`              | `anthropic.APIError`              |
+
+```typescript
+// ✅ Correct: use typed exceptions
+try {
+  const response = await client.messages.create({...});
+} catch (error) {
+  if (error instanceof Anthropic.RateLimitError) {
+    // Handle rate limiting
+  } else if (error instanceof Anthropic.APIError) {
+    console.error(`API error ${error.status}:`, error.message);
+  }
+}
+
+// ❌ Wrong: don't check error messages with string matching
+try {
+  const response = await client.messages.create({...});
+} catch (error) {
+  const msg = error instanceof Error ? error.message : String(error);
+  if (msg.includes("429") || msg.includes("rate_limit")) { ... }
+}
+```
+
+All exception classes extend `Anthropic.APIError`, which has a `status` property. Use `instanceof` checks from most specific to least specific (e.g., check `RateLimitError` before `APIError`).

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

@@ -0,0 +1,121 @@
+# Live Documentation Sources
+
+This file contains WebFetch URLs for fetching current information from platform.claude.com and Agent SDK repositories. Use these when users need the latest data that may have changed since the cached content was last updated.
+
+## When to Use WebFetch
+
+- User explicitly asks for "latest" or "current" information
+- Cached data seems incorrect
+- User asks about features not covered in cached content
+- User needs specific API details or examples
+
+## Claude API Documentation URLs
+
+### Models & Pricing
+
+| Topic           | URL                                                                   | Extraction Prompt                                                               |
+| --------------- | --------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
+| Models Overview | `https://platform.claude.com/docs/en/about-claude/models/overview.md` | "Extract current model IDs, context windows, and pricing for all Claude models" |
+| Pricing         | `https://platform.claude.com/docs/en/pricing.md`                      | "Extract current pricing per million tokens for input and output"               |
+
+### Core Features
+
+| Topic             | URL                                                                          | Extraction Prompt                                                                      |
+| ----------------- | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
+| Extended Thinking | `https://platform.claude.com/docs/en/build-with-claude/extended-thinking.md` | "Extract extended thinking parameters, budget_tokens requirements, and usage examples" |
+| Adaptive Thinking | `https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking.md` | "Extract adaptive thinking setup, effort levels, and Claude Opus 4.6 usage examples"         |
+| Effort Parameter  | `https://platform.claude.com/docs/en/build-with-claude/effort.md`            | "Extract effort levels, cost-quality tradeoffs, and interaction with thinking"        |
+| Tool Use          | `https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview.md`  | "Extract tool definition schema, tool_choice options, and handling tool results"       |
+| Streaming         | `https://platform.claude.com/docs/en/build-with-claude/streaming.md`         | "Extract streaming event types, SDK examples, and best practices"                      |
+| Prompt Caching    | `https://platform.claude.com/docs/en/build-with-claude/prompt-caching.md`    | "Extract cache_control usage, pricing benefits, and implementation examples"           |
+
+### Media & Files
+
+| Topic       | URL                                                                    | Extraction Prompt                                                 |
+| ----------- | ---------------------------------------------------------------------- | ----------------------------------------------------------------- |
+| Vision      | `https://platform.claude.com/docs/en/build-with-claude/vision.md`      | "Extract supported image formats, size limits, and code examples" |
+| PDF Support | `https://platform.claude.com/docs/en/build-with-claude/pdf-support.md` | "Extract PDF handling capabilities, limits, and examples"         |
+
+### API Operations
+
+| Topic            | URL                                                                         | Extraction Prompt                                                                                       |
+| ---------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
+| Batch Processing | `https://platform.claude.com/docs/en/build-with-claude/batch-processing.md` | "Extract batch API endpoints, request format, and polling for results"                                  |
+| Files API        | `https://platform.claude.com/docs/en/build-with-claude/files.md`            | "Extract file upload, download, and referencing in messages, including supported types and beta header" |
+| Token Counting   | `https://platform.claude.com/docs/en/build-with-claude/token-counting.md`   | "Extract token counting API usage and examples"                                                         |
+| Rate Limits      | `https://platform.claude.com/docs/en/api/rate-limits.md`                    | "Extract current rate limits by tier and model"                                                         |
+| Errors           | `https://platform.claude.com/docs/en/api/errors.md`                         | "Extract HTTP error codes, meanings, and retry guidance"                                                |
+
+### Tools
+
+| Topic          | URL                                                                                    | Extraction Prompt                                                                        |
+| -------------- | -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
+| Code Execution | `https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool.md` | "Extract code execution tool setup, file upload, container reuse, and response handling" |
+| Computer Use   | `https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use.md`        | "Extract computer use tool setup, capabilities, and implementation examples"             |
+
+### Advanced Features
+
+| Topic              | URL                                                                           | Extraction Prompt                                   |
+| ------------------ | ----------------------------------------------------------------------------- | --------------------------------------------------- |
+| Structured Outputs | `https://platform.claude.com/docs/en/build-with-claude/structured-outputs.md` | "Extract output_config.format usage and schema enforcement"                           |
+| Compaction         | `https://platform.claude.com/docs/en/build-with-claude/compaction.md`         | "Extract compaction setup, trigger config, and streaming with compaction"             |
+| Citations          | `https://platform.claude.com/docs/en/build-with-claude/citations.md`          | "Extract citation format and implementation"        |
+| Context Windows    | `https://platform.claude.com/docs/en/build-with-claude/context-windows.md`    | "Extract context window sizes and token management" |
+
+---
+
+## Claude API SDK Repositories
+
+| SDK        | URL                                                       | Description                    |
+| ---------- | --------------------------------------------------------- | ------------------------------ |
+| Python     | `https://github.com/anthropics/anthropic-sdk-python`     | `anthropic` pip package source |
+| TypeScript | `https://github.com/anthropics/anthropic-sdk-typescript` | `@anthropic-ai/sdk` npm source |
+| Java       | `https://github.com/anthropics/anthropic-sdk-java`       | `anthropic-java` Maven source  |
+| Go         | `https://github.com/anthropics/anthropic-sdk-go`         | Go module source               |
+| Ruby       | `https://github.com/anthropics/anthropic-sdk-ruby`       | `anthropic` gem source         |
+| C#         | `https://github.com/anthropics/anthropic-sdk-csharp`     | NuGet package source           |
+| PHP        | `https://github.com/anthropics/anthropic-sdk-php`        | Composer package source        |
+
+---
+
+## Agent SDK Documentation URLs
+
+### Core Documentation
+
+| Topic                | URL                                                         | Extraction Prompt                                               |
+| -------------------- | ----------------------------------------------------------- | --------------------------------------------------------------- |
+| Agent SDK Overview   | `https://platform.claude.com/docs/en/agent-sdk.md`          | "Extract the Agent SDK overview, key features, and use cases"   |
+| Agent SDK Python     | `https://github.com/anthropics/claude-agent-sdk-python`     | "Extract Python SDK installation, imports, and basic usage"     |
+| Agent SDK TypeScript | `https://github.com/anthropics/claude-agent-sdk-typescript` | "Extract TypeScript SDK installation, imports, and basic usage" |
+
+### SDK Reference (GitHub READMEs)
+
+| Topic          | URL                                                                                       | Extraction Prompt                                            |
+| -------------- | ----------------------------------------------------------------------------------------- | ------------------------------------------------------------ |
+| Python SDK     | `https://raw.githubusercontent.com/anthropics/claude-agent-sdk-python/main/README.md`     | "Extract Python SDK API reference, classes, and methods"     |
+| TypeScript SDK | `https://raw.githubusercontent.com/anthropics/claude-agent-sdk-typescript/main/README.md` | "Extract TypeScript SDK API reference, types, and functions" |
+
+### npm/PyPI Packages
+
+| Package                             | URL                                                            | Description               |
+| ----------------------------------- | -------------------------------------------------------------- | ------------------------- |
+| claude-agent-sdk (Python)           | `https://pypi.org/project/claude-agent-sdk/`                   | Python package on PyPI    |
+| @anthropic-ai/claude-agent-sdk (TS) | `https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk` | TypeScript package on npm |
+
+### GitHub Repositories
+
+| Resource       | URL                                                         | Description                         |
+| -------------- | ----------------------------------------------------------- | ----------------------------------- |
+| Python SDK     | `https://github.com/anthropics/claude-agent-sdk-python`     | Python package source               |
+| TypeScript SDK | `https://github.com/anthropics/claude-agent-sdk-typescript` | TypeScript/Node.js package source   |
+| MCP Servers    | `https://github.com/modelcontextprotocol`                   | Official MCP server implementations |
+
+---
+
+## Fallback Strategy
+
+If WebFetch fails (network issues, URL changed):
+
+1. Use cached content from the language-specific files (note the cache date)
+2. Inform user the data may be outdated
+3. Suggest they check platform.claude.com or the GitHub repos directly

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

@@ -0,0 +1,119 @@
+# Claude Model Catalog
+
+**Only use exact model IDs listed in this file.** Never guess or construct model IDs — incorrect IDs will cause API errors. Use aliases wherever available. For the latest information, WebFetch the Models Overview URL in `shared/live-sources.md`, or query the Models API directly (see Programmatic Model Discovery below).
+
+## Programmatic Model Discovery
+
+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.max_input_tokens   # context window (int)
+m.max_tokens         # max output tokens (int)
+
+# capabilities is an untyped nested dict — bracket access, check ["supported"] at the leaf
+caps = m.capabilities
+caps["image_input"]["supported"]                       # vision
+caps["thinking"]["types"]["adaptive"]["supported"]     # adaptive thinking
+caps["effort"]["max"]["supported"]                     # effort: max (also low/medium/high)
+caps["structured_outputs"]["supported"]
+caps["context_management"]["compact_20260112"]["supported"]
+
+# filter across all models — iterate the page object directly (auto-paginates); do NOT use .data
+[m for m in client.models.list()
+ if m.capabilities["thinking"]["types"]["adaptive"]["supported"]
+ and m.max_input_tokens >= 200_000]
+```
+
+Top-level fields (`id`, `display_name`, `max_input_tokens`, `max_tokens`) are typed attributes. `capabilities` is a dict — use bracket access, not attribute access. The API returns the full capability tree for every model with `supported: true/false` at each leaf, so bracket chains are safe without `.get()` guards. TypeScript SDK: same method names, also auto-paginates on iteration.
+
+### Raw HTTP
+
+```bash
+curl https://api.anthropic.com/v1/models/claude-opus-4-6 \
+  -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,
+  "max_tokens": 128000,
+  "capabilities": {
+    "image_input": {"supported": true},
+    "structured_outputs": {"supported": true},
+    "thinking": {"supported": true, "types": {"enabled": {"supported": true}, "adaptive": {"supported": true}}},
+    "effort": {"supported": true, "low": {"supported": true}, …, "max": {"supported": true}},
+    …
+  }
+}
+```
+
+## Current Models (recommended)
+
+| 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 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 Haiku 4.5** — Fastest and most cost-effective model for simple tasks.
+
+## Legacy Models (still active)
+
+| Friendly Name     | Alias (use this)    | Full ID                       | Status |
+|-------------------|---------------------|-------------------------------|--------|
+| Claude Opus 4.5   | `claude-opus-4-5`   | `claude-opus-4-5-20251101`    | Active |
+| Claude Opus 4.1   | `claude-opus-4-1`   | `claude-opus-4-1-20250805`    | Active |
+| Claude Sonnet 4.5 | `claude-sonnet-4-5` | `claude-sonnet-4-5-20250929`  | Active |
+| Claude Sonnet 4   | `claude-sonnet-4-0` | `claude-sonnet-4-20250514`    | Active |
+| Claude Opus 4     | `claude-opus-4-0`   | `claude-opus-4-20250514`      | Active |
+
+## Deprecated Models (retiring soon)
+
+| Friendly Name     | Alias (use this)    | Full ID                       | Status     | Retires      |
+|-------------------|---------------------|-------------------------------|------------|--------------|
+| Claude Haiku 3    | —                   | `claude-3-haiku-20240307`     | Deprecated | Apr 19, 2026 |
+
+## Retired Models (no longer available)
+
+| Friendly Name     | Full ID                       | Retired     |
+|-------------------|-------------------------------|-------------|
+| Claude Sonnet 3.7 | `claude-3-7-sonnet-20250219`  | Feb 19, 2026 |
+| Claude Haiku 3.5  | `claude-3-5-haiku-20241022`   | Feb 19, 2026 |
+| Claude Opus 3     | `claude-3-opus-20240229`      | Jan 5, 2026 |
+| Claude Sonnet 3.5 | `claude-3-5-sonnet-20241022`  | Oct 28, 2025 |
+| Claude Sonnet 3.5 | `claude-3-5-sonnet-20240620`  | Oct 28, 2025 |
+| Claude Sonnet 3   | `claude-3-sonnet-20240229`    | Jul 21, 2025 |
+| Claude 2.1        | `claude-2.1`                  | Jul 21, 2025 |
+| Claude 2.0        | `claude-2.0`                  | Jul 21, 2025 |
+
+## Resolving User Requests
+
+When a user asks for a model by name, use this table to find the correct model ID:
+
+| User says...                              | Use this model ID              |
+|-------------------------------------------|--------------------------------|
+| "opus", "most powerful"                   | `claude-opus-4-6`              |
+| "opus 4.6"                                | `claude-opus-4-6`              |
+| "opus 4.5"                                | `claude-opus-4-5`              |
+| "opus 4.1"                                | `claude-opus-4-1`              |
+| "opus 4", "opus 4.0"                      | `claude-opus-4-0`              |
+| "sonnet", "balanced"                      | `claude-sonnet-4-6`            |
+| "sonnet 4.6"                              | `claude-sonnet-4-6`            |
+| "sonnet 4.5"                              | `claude-sonnet-4-5`            |
+| "sonnet 4", "sonnet 4.0"                  | `claude-sonnet-4-0`            |
+| "sonnet 3.7"                              | Retired — suggest `claude-sonnet-4-5` |
+| "sonnet 3.5"                              | Retired — suggest `claude-sonnet-4-5` |
+| "haiku", "fast", "cheap"                  | `claude-haiku-4-5`             |
+| "haiku 4.5"                               | `claude-haiku-4-5`             |
+| "haiku 3.5"                               | Retired — suggest `claude-haiku-4-5` |
+| "haiku 3"                                 | Deprecated — suggest `claude-haiku-4-5` |

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

@@ -0,0 +1,128 @@
+# Prompt Caching — Design & Optimization
+
+This file covers how to design prompt-building code for effective caching. For language-specific syntax, see the `## Prompt Caching` section in each language's README or single-file doc.
+
+## The one invariant everything follows from
+
+**Prompt caching is a prefix match. Any change anywhere in the prefix invalidates everything after it.**
+
+The cache key is derived from the exact bytes of the rendered prompt up to each `cache_control` breakpoint. A single byte difference at position N — a timestamp, a reordered JSON key, a different tool in the list — invalidates the cache for all breakpoints at positions ≥ N.
+
+Render order is: `tools` → `system` → `messages`. A breakpoint on the last system block caches both tools and system together.
+
+Design the prompt-building path around this constraint. Get the ordering right and most caching works for free. Get it wrong and no amount of `cache_control` markers will help.
+
+---
+
+## Workflow for optimizing existing code
+
+When asked to add or optimize caching:
+
+1. **Trace the prompt assembly path.** Find where `system`, `tools`, and `messages` are constructed. Identify every input that flows into them.
+2. **Classify each input by stability:**
+   - Never changes → belongs early in the prompt, before any breakpoint
+   - Changes per-session → belongs after the global prefix, cache per-session
+   - Changes per-turn → belongs at the end, after the last breakpoint
+   - Changes per-request (timestamps, UUIDs, random IDs) → **eliminate or move to the very end**
+3. **Check rendered order matches stability order.** Stable content must physically precede volatile content. If a timestamp is interpolated into the system prompt header, everything after it is uncacheable regardless of markers.
+4. **Place breakpoints at stability boundaries.** See placement patterns below.
+5. **Audit for silent invalidators.** See anti-patterns table.
+
+---
+
+## Placement patterns
+
+### Large system prompt shared across many requests
+
+Put a breakpoint on the last system text block. If there are tools, they render before system — the marker on the last system block caches tools + system together.
+
+```json
+"system": [
+  {"type": "text", "text": "<large shared prompt>", "cache_control": {"type": "ephemeral"}}
+]
+```
+
+### Multi-turn conversations
+
+Put a breakpoint on the last content block of the most-recently-appended turn. Each subsequent request reuses the entire prior conversation prefix. Earlier breakpoints remain valid read points, so hits accrue incrementally as the conversation grows.
+
+```json
+// Last content block of the last user turn
+messages[-1].content[-1].cache_control = {"type": "ephemeral"}
+```
+
+### Shared prefix, varying suffix
+
+Many requests share a large fixed preamble (few-shot examples, retrieved docs, instructions) but differ in the final question. Put the breakpoint at the end of the **shared** portion, not at the end of the whole prompt — otherwise every request writes a distinct cache entry and nothing is ever read.
+
+```json
+"messages": [{"role": "user", "content": [
+  {"type": "text", "text": "<shared context>", "cache_control": {"type": "ephemeral"}},
+  {"type": "text", "text": "<varying question>"}  // no marker — differs every time
+]}]
+```
+
+### Prompts that change from the beginning every time
+
+Don't cache. If the first 1K tokens differ per request, there is no reusable prefix. Adding `cache_control` only pays the cache-write premium with zero reads. Leave it off.
+
+---
+
+## Architectural guidance
+
+These are the decisions that matter more than marker placement. Fix these first.
+
+**Keep the system prompt frozen.** Don't interpolate "current date: X", "mode: Y", "user name: Z" into the system prompt — those sit at the front of the prefix and invalidate everything downstream. Inject dynamic context as a user or assistant message later in `messages`. A message at turn 5 invalidates nothing before turn 5.
+
+**Don't change tools or model mid-conversation.** Tools render at position 0; adding, removing, or reordering a tool invalidates the entire cache. Same for switching models (caches are model-scoped). If you need "modes", don't swap the tool set — give Claude a tool that records the mode transition, or pass the mode as message content. Serialize tools deterministically (sort by name).
+
+**Fork operations must reuse the parent's exact prefix.** Side computations (summarization, compaction, sub-agents) often spin up a separate API call. If the fork rebuilds `system` / `tools` / `model` with any difference, it misses the parent's cache entirely. Copy the parent's `system`, `tools`, and `model` verbatim, then append fork-specific content at the end.
+
+---
+
+## Silent invalidators
+
+When reviewing code, grep for these inside anything that feeds the prompt prefix:
+
+| Pattern | Why it breaks caching |
+|---|---|
+| `datetime.now()` / `Date.now()` / `time.time()` in system prompt | Prefix changes every request |
+| `uuid4()` / `crypto.randomUUID()` / request IDs early in content | Same — every request is unique |
+| `json.dumps(d)` without `sort_keys=True` / iterating a `set` | Non-deterministic serialization → prefix bytes differ |
+| f-string interpolating session/user ID into system prompt | Per-user prefix; no cross-user sharing |
+| Conditional system sections (`if flag: system += ...`) | Every flag combination is a distinct prefix |
+| `tools=build_tools(user)` where set varies per user | Tools render at position 0; nothing caches across users |
+
+Fix by moving the dynamic piece after the last breakpoint, making it deterministic, or deleting it if it's not load-bearing.
+
+---
+
+## API reference
+
+```json
+"cache_control": {"type": "ephemeral"}              // 5-minute TTL (default)
+"cache_control": {"type": "ephemeral", "ttl": "1h"} // 1-hour TTL
+```
+
+- 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.
+
+**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.
+
+---
+
+## Verifying cache hits
+
+The response `usage` object reports cache activity:
+
+| Field | Meaning |
+|---|---|
+| `cache_creation_input_tokens` | Tokens written to cache this request (you paid the ~1.25× write premium) |
+| `cache_read_input_tokens` | Tokens served from cache this request (you paid ~0.1×) |
+| `input_tokens` | Tokens processed at full price (not cached) |
+
+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.
+
+Language-specific access: `response.usage.cache_read_input_tokens` (Python/TS/Ruby), `$message->usage->cacheReadInputTokens` (PHP), `resp.Usage.CacheReadInputTokens` (Go/C#), `.usage().cacheReadInputTokens()` (Java).