@warlock.js/ai-anthropic 5.34.2 → 5.35.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +6 -0
- package/llms-full.txt +4 -17
- package/llms.txt +1 -2
- package/package.json +3 -3
- package/skills/{setup-anthropic/SKILL.md → SKILL.md} +3 -3
- package/skills/index.md +0 -9
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,12 @@ All notable changes to `@warlock.js/ai-anthropic` are documented in this file.
|
|
|
4
4
|
|
|
5
5
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). `@warlock.js/*` packages are released in lockstep — every package shares the same version number, so a version below may list only the changes that affected this package.
|
|
6
6
|
|
|
7
|
+
## 5.34.3 - 2026-10-20
|
|
8
|
+
|
|
9
|
+
### Changed
|
|
10
|
+
|
|
11
|
+
- The agent skill now exports as `warlock-js-ai-anthropic`; package discovery descriptions stay within 450 characters.
|
|
12
|
+
|
|
7
13
|
## 5.34.2 - 2026-10-19
|
|
8
14
|
|
|
9
15
|
### Fixed
|
package/llms-full.txt
CHANGED
|
@@ -4,24 +4,11 @@
|
|
|
4
4
|
|
|
5
5
|
> Generated artifact. Concatenates every SKILL.md and reference file under `@warlock.js/ai-anthropic/skills/`. Re-run `node scripts/generate-llms.mjs` after any change.
|
|
6
6
|
|
|
7
|
-
##
|
|
7
|
+
## ai-anthropic `@warlock.js/ai-anthropic/skills/SKILL.md`
|
|
8
8
|
|
|
9
9
|
---
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
# @warlock.js/ai-anthropic
|
|
14
|
-
|
|
15
|
-
This adapter supplies provider-backed models for `@warlock.js/ai`. Read `setup-anthropic.md` to construct `AnthropicSDK`, configure extended thinking, prompt caching, token counting and usage costs, and understand provider-specific behavior.
|
|
16
|
-
|
|
17
|
-
For agent composition, read the `run-ai-agent` topic of the `@warlock.js/ai` package. Keep provider configuration here and application orchestration in that package.
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
## setup-anthropic `@warlock.js/ai-anthropic/setup-anthropic/SKILL.md`
|
|
21
|
-
|
|
22
|
-
---
|
|
23
|
-
name: setup-anthropic
|
|
24
|
-
description: 'Wire @warlock.js/ai-anthropic — new AnthropicSDK({apiKey, baseURL?, provider?}) for Claude, .model({name, vision?, structuredOutput?, reasoning?, thinkingMode?, promptCaching?, maxTokens?, maxOutputTokens?}). System-prompt hoisting, max_tokens required (default: model max output when streaming, 16384 non-streaming; maxOutputTokens for gateway ids), extended thinking via options.reasoning → adaptive thinking + output_config.effort (current/unknown models) or budget_tokens (Haiku 4.5, 4.6 and older; override with thinkingMode), prompt caching via promptCaching + options.cacheControl (per-call ttl), provider blocks (thinking/compaction) replayed verbatim via ModelResponse.blocks / Message.blocks, providerOptions.anthropic (betas, body fields such as context_management / fallbacks, thinkingDisplay), model.countTokens(), distinct finish reasons (pause_turn, refusal, context_exceeded), built-in Claude list prices (ANTHROPIC_MODEL_PRICING, anthropicPricingFor, withAnthropicCacheWriteRates), cost-truth usage (inputIncludesCache: false, cachedTokens/cacheWriteTokens/cacheWrite1hTokens, usage.cost on complete()), ProviderOverloadedError for 529, no first-party embeddings. Triggers: `AnthropicSDK`, `anthropic.model`, `anthropic.count`, `maxTokens`, `maxOutputTokens`, `max_tokens`, `reasoning`, `thinking`, `budget_tokens`, `thinkingMode`, `adaptive`, `cacheControl`, `providerOptions`, `blocks`, `countTokens`, `pause_turn`, `refusal`, `context_management`, `contextManagement`, `serverCompaction`, `clear_tool_uses`, `clear_thinking`, `thinkingBlockBinding`, `block_binding`, `preservedThinking`, `ai.providerTool`, `web_search_20250305`, `bash_20250124`, `text_editor_20250728`, `streamChunks`, `thinking_delta`, `compaction`, `promptCaching`, `cachedTokens`, `cacheWriteTokens`, `cacheWrite1hTokens`, `inputIncludesCache`, `ANTHROPIC_MODEL_PRICING`, `ProviderOverloadedError`, `claude-sonnet-4-6`, `claude-haiku-4-5`, `claude-opus-4-7`; "wire claude into warlock agent", "configure anthropic provider", "use claude sonnet", "anthropic gateway baseURL", "claude extended thinking", "anthropic prompt caching cost"; typical import `import { AnthropicSDK } from "@warlock.js/ai-anthropic"`. Skip: embeddings — the `setup-openai` topic of the `warlock-js-ai-openai` skill; sibling adapters `@warlock.js/ai-openai`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `@anthropic-ai/sdk`; Vercel `@ai-sdk/anthropic`.'
|
|
10
|
+
name: warlock-js-ai-anthropic
|
|
11
|
+
description: 'Anthropic Claude adapter for Warlock AI: `AnthropicSDK`, `AnthropicModel`, `AnthropicCallOptions` and `ANTHROPIC_MODEL_PRICING`. Use for "connect Claude", streaming, tools, thinking, caching, native search or context management through `sdk.model()`. Not this package → @warlock.js/ai for agents and custom tools; @warlock.js/ai-bedrock for Claude on AWS; @warlock.js/ai-cli for terminal agents.'
|
|
25
12
|
---
|
|
26
13
|
|
|
27
14
|
# `@warlock.js/ai-anthropic`
|
|
@@ -481,7 +468,7 @@ errors propagate. See the cost/budget guide for reserve mode.
|
|
|
481
468
|
|
|
482
469
|
## No embeddings
|
|
483
470
|
|
|
484
|
-
Anthropic ships no first-party embeddings API, so `AnthropicSDK` intentionally does **not** implement `embedder()` (the `SDKAdapterContract.embedder` slot is optional). Use `@warlock.js/ai-openai` (or another embeddings-capable adapter; see the `
|
|
471
|
+
Anthropic ships no first-party embeddings API, so `AnthropicSDK` intentionally does **not** implement `embedder()` (the `SDKAdapterContract.embedder` slot is optional). Use `@warlock.js/ai-openai` (or another embeddings-capable adapter; see the `warlock-js-ai-openai` skill) for vectors.
|
|
485
472
|
|
|
486
473
|
## When NOT to use this skill
|
|
487
474
|
|
package/llms.txt
CHANGED
|
@@ -6,5 +6,4 @@
|
|
|
6
6
|
|
|
7
7
|
## Skills
|
|
8
8
|
|
|
9
|
-
- [
|
|
10
|
-
- [setup-anthropic](@warlock.js/ai-anthropic/setup-anthropic/SKILL.md): Wire @warlock.js/ai-anthropic — new AnthropicSDK({apiKey, baseURL?, provider?}) for Claude, .model({name, vision?, structuredOutput?, reasoning?, thinkingMode?, promptCaching?, maxTokens?, maxOutputTokens?}). System-prompt hoisting, max_tokens required (default: model max output when streaming, 16384 non-streaming; maxOutputTokens for gateway ids), extended thinking via options.reasoning → adaptive thinking + output_config.effort (current/unknown models) or budget_tokens (Haiku 4.5, 4.6 and older; override with thinkingMode), prompt caching via promptCaching + options.cacheControl (per-call ttl), provider blocks (thinking/compaction) replayed verbatim via ModelResponse.blocks / Message.blocks, providerOptions.anthropic (betas, body fields such as context_management / fallbacks, thinkingDisplay), model.countTokens(), distinct finish reasons (pause_turn, refusal, context_exceeded), built-in Claude list prices (ANTHROPIC_MODEL_PRICING, anthropicPricingFor, withAnthropicCacheWriteRates), cost-truth usage (inputIncludesCache: false, cachedTokens/cacheWriteTokens/cacheWrite1hTokens, usage.cost on complete()), ProviderOverloadedError for 529, no first-party embeddings. Triggers: `AnthropicSDK`, `anthropic.model`, `anthropic.count`, `maxTokens`, `maxOutputTokens`, `max_tokens`, `reasoning`, `thinking`, `budget_tokens`, `thinkingMode`, `adaptive`, `cacheControl`, `providerOptions`, `blocks`, `countTokens`, `pause_turn`, `refusal`, `context_management`, `contextManagement`, `serverCompaction`, `clear_tool_uses`, `clear_thinking`, `thinkingBlockBinding`, `block_binding`, `preservedThinking`, `ai.providerTool`, `web_search_20250305`, `bash_20250124`, `text_editor_20250728`, `streamChunks`, `thinking_delta`, `compaction`, `promptCaching`, `cachedTokens`, `cacheWriteTokens`, `cacheWrite1hTokens`, `inputIncludesCache`, `ANTHROPIC_MODEL_PRICING`, `ProviderOverloadedError`, `claude-sonnet-4-6`, `claude-haiku-4-5`, `claude-opus-4-7`; "wire claude into warlock agent", "configure anthropic provider", "use claude sonnet", "anthropic gateway baseURL", "claude extended thinking", "anthropic prompt caching cost"; typical import `import { AnthropicSDK } from "@warlock.js/ai-anthropic"`. Skip: embeddings — the `setup-openai` topic of the `warlock-js-ai-openai` skill; sibling adapters `@warlock.js/ai-openai`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `@anthropic-ai/sdk`; Vercel `@ai-sdk/anthropic`.
|
|
9
|
+
- [ai-anthropic](@warlock.js/ai-anthropic/skills/SKILL.md): Anthropic Claude adapter for Warlock AI: `AnthropicSDK`, `AnthropicModel`, `AnthropicCallOptions` and `ANTHROPIC_MODEL_PRICING`. Use for "connect Claude", streaming, tools, thinking, caching, native search or context management through `sdk.model()`. Not this package → @warlock.js/ai for agents and custom tools; @warlock.js/ai-bedrock for Claude on AWS; @warlock.js/ai-cli for terminal agents.
|
package/package.json
CHANGED
|
@@ -15,13 +15,13 @@
|
|
|
15
15
|
"directory": "packages/ai-anthropic"
|
|
16
16
|
},
|
|
17
17
|
"peerDependencies": {
|
|
18
|
-
"@warlock.js/ai": "5.
|
|
18
|
+
"@warlock.js/ai": "5.35.0"
|
|
19
19
|
},
|
|
20
20
|
"dependencies": {
|
|
21
21
|
"@anthropic-ai/sdk": "^0.129.0",
|
|
22
|
-
"@warlock.js/logger": "5.
|
|
22
|
+
"@warlock.js/logger": "5.35.0"
|
|
23
23
|
},
|
|
24
|
-
"version": "5.
|
|
24
|
+
"version": "5.35.0",
|
|
25
25
|
"main": "./cjs/index.cjs",
|
|
26
26
|
"module": "./esm/index.mjs",
|
|
27
27
|
"types": "./esm/index.d.mts",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
3
|
-
description: '
|
|
2
|
+
name: warlock-js-ai-anthropic
|
|
3
|
+
description: 'Anthropic Claude adapter for Warlock AI: `AnthropicSDK`, `AnthropicModel`, `AnthropicCallOptions` and `ANTHROPIC_MODEL_PRICING`. Use for "connect Claude", streaming, tools, thinking, caching, native search or context management through `sdk.model()`. Not this package → @warlock.js/ai for agents and custom tools; @warlock.js/ai-bedrock for Claude on AWS; @warlock.js/ai-cli for terminal agents.'
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# `@warlock.js/ai-anthropic`
|
|
@@ -460,7 +460,7 @@ errors propagate. See the cost/budget guide for reserve mode.
|
|
|
460
460
|
|
|
461
461
|
## No embeddings
|
|
462
462
|
|
|
463
|
-
Anthropic ships no first-party embeddings API, so `AnthropicSDK` intentionally does **not** implement `embedder()` (the `SDKAdapterContract.embedder` slot is optional). Use `@warlock.js/ai-openai` (or another embeddings-capable adapter; see the `
|
|
463
|
+
Anthropic ships no first-party embeddings API, so `AnthropicSDK` intentionally does **not** implement `embedder()` (the `SDKAdapterContract.embedder` slot is optional). Use `@warlock.js/ai-openai` (or another embeddings-capable adapter; see the `warlock-js-ai-openai` skill) for vectors.
|
|
464
464
|
|
|
465
465
|
## When NOT to use this skill
|
|
466
466
|
|
package/skills/index.md
DELETED
|
@@ -1,9 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
description: "Provider adapter for Anthropic Messages API for Claude in Warlock AI applications. Exports `AnthropicSDK` with model and provider configuration for the shared AI contracts. Use when connecting this provider, configuring extended thinking, prompt caching, token counting and usage costs, or diagnosing provider requests and usage. Read `setup-anthropic` for construction and examples using ANTHROPIC_API_KEY. Not this package: agent loops, tools and workflows → @warlock.js/ai; HTTP and MCP tools → @warlock.js/ai-tools."
|
|
3
|
-
---
|
|
4
|
-
|
|
5
|
-
# @warlock.js/ai-anthropic
|
|
6
|
-
|
|
7
|
-
This adapter supplies provider-backed models for `@warlock.js/ai`. Read `setup-anthropic.md` to construct `AnthropicSDK`, configure extended thinking, prompt caching, token counting and usage costs, and understand provider-specific behavior.
|
|
8
|
-
|
|
9
|
-
For agent composition, read the `run-ai-agent` topic of the `@warlock.js/ai` package. Keep provider configuration here and application orchestration in that package.
|