@warlock.js/ai-deepseek 5.34.1 → 5.34.3

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 CHANGED
@@ -4,6 +4,12 @@ All notable changes to `@warlock.js/ai-deepseek` 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-deepseek`; package discovery descriptions stay within 450 characters.
12
+
7
13
  ## 5.32.0 - 2026-10-18
8
14
 
9
15
  ### Changed
package/llms-full.txt CHANGED
@@ -4,16 +4,16 @@
4
4
 
5
5
  > Generated artifact. Concatenates every SKILL.md and reference file under `@warlock.js/ai-deepseek/skills/`. Re-run `node scripts/generate-llms.mjs` after any change.
6
6
 
7
- ## setup-deepseek `@warlock.js/ai-deepseek/setup-deepseek/SKILL.md`
7
+ ## ai-deepseek `@warlock.js/ai-deepseek/skills/SKILL.md`
8
8
 
9
9
  ---
10
- name: setup-deepseek
11
- description: 'Wire @warlock.js/ai-deepseek — new DeepSeekSDK({apiKey, baseURL?, provider?, pricing?}) for DeepSeek''s OpenAI-compatible API, .model({name, reasoning?, vision?, structuredOutput?, responseFormat?}) for ModelContract. Thin wrapper over @warlock.js/ai-openai''s OpenAISDK pinned to https://api.deepseek.com with provider "deepseek"; injects DeepSeek-specific reasoning/vision inference + built-in pricing. Models: deepseek-flash / deepseek-v4-flash, deepseek-v4-pro, legacy deepseek-chat / deepseek-reasoner. Built-in peak-rate pricing (DEEPSEEK_DEFAULT_PRICING) and an opt-in off-peak table (DEEPSEEK_OFF_PEAK_PRICING). Triggers: `DeepSeekSDK`, `DEEPSEEK_DEFAULT_PRICING`, `DEEPSEEK_OFF_PEAK_PRICING`, `deepseek-chat`, `deepseek-reasoner`, `deepseek-v4`, `api.deepseek.com`, `DEEPSEEK_API_KEY`, reasoning effort on deepseek; "wire deepseek into a warlock agent", "use deepseek-reasoner", "configure deepseek-chat", "route a warlock agent through deepseek". Skip: OpenAI/Azure/OpenRouter — `@warlock.js/ai-openai`; agent wiring — the `run-ai-agent` topic of the `warlock-js-ai` skill; adapter comparison — the `pick-ai-provider` topic of the `warlock-js-ai` skill; raw deepseek HTTP / the `openai` SDK directly. Typical import `import { DeepSeekSDK } from "@warlock.js/ai-deepseek"`.'
10
+ name: warlock-js-ai-deepseek
11
+ description: 'DeepSeek adapter for Warlock AI: `DeepSeekSDK`, `DEEPSEEK_CHAT_MODELS`, `DEEPSEEK_DEFAULT_PRICING` and `DEEPSEEK_OFF_PEAK_PRICING`. Use for "connect DeepSeek", reasoning, streaming, tools, capability inference or per-model pricing through `sdk.model()`. Not this package → @warlock.js/ai for agents, tools and workflows; @warlock.js/ai-openai for generic OpenAI-compatible endpoints.'
12
12
  ---
13
13
 
14
14
  # `@warlock.js/ai-deepseek`
15
15
 
16
- Provider adapter for DeepSeek. DeepSeek's API is **OpenAI-compatible**, so this package is a **thin wrapper** over `@warlock.js/ai-openai`'s `OpenAISDK` (the `setup-openai` topic of the `warlock-js-ai-openai` skill): it constructs an internal `OpenAISDK` pinned to `https://api.deepseek.com` with `provider: "deepseek"` and delegates `model()` / `embedder()` / `image()` / `count()` to it — while injecting DeepSeek's own capability inference and pricing so the right flags are set even though the model names aren't OpenAI names. Pair with `@warlock.js/ai` for the agent / tool / system-prompt surface.
16
+ Provider adapter for DeepSeek. DeepSeek's API is **OpenAI-compatible**, so this package is a **thin wrapper** over `@warlock.js/ai-openai`'s `OpenAISDK` (the `warlock-js-ai-openai` skill): it constructs an internal `OpenAISDK` pinned to `https://api.deepseek.com` with `provider: "deepseek"` and delegates `model()` / `embedder()` / `image()` / `count()` to it — while injecting DeepSeek's own capability inference and pricing so the right flags are set even though the model names aren't OpenAI names. Pair with `@warlock.js/ai` for the agent / tool / system-prompt surface.
17
17
 
18
18
  ## Construction
19
19
 
@@ -70,7 +70,7 @@ deepseek.model({ name: "deepseek-reasoner", reasoning: false }); // suppress it
70
70
 
71
71
  ## Uses the OpenAI-compatible endpoint
72
72
 
73
- Everything on the wire — Chat Completions request/response shape, streaming loop, tool-call accumulation, structured-output `response_format`, multipart message mapping, and error wrapping — is inherited **unchanged** from `OpenAIModel`. See the `setup-openai` topic of the `warlock-js-ai-openai` skill for the wire-level detail; it all applies here against `https://api.deepseek.com`.
73
+ Everything on the wire — Chat Completions request/response shape, streaming loop, tool-call accumulation, structured-output `response_format`, multipart message mapping, and error wrapping — is inherited **unchanged** from `OpenAIModel`. See the `warlock-js-ai-openai` skill for the wire-level detail; it all applies here against `https://api.deepseek.com`.
74
74
 
75
75
  Structured output, reasoning effort, and streaming therefore behave exactly as documented for the OpenAI adapter:
76
76
 
@@ -129,7 +129,7 @@ Raw errors surface through the wrapped OpenAI adapter's wrapper into the typed `
129
129
 
130
130
  ## See also
131
131
 
132
- - The `setup-openai` topic of the `warlock-js-ai-openai` skill — the wrapped adapter; all wire-level behavior.
132
+ - The `warlock-js-ai-openai` skill — the wrapped adapter; all wire-level behavior.
133
133
  - The `run-ai-agent` topic of the `warlock-js-ai` skill — passing the model into `ai.agent({...})`.
134
134
  - The `pick-ai-provider` topic of the `warlock-js-ai` skill — adapter comparison.
135
135
 
package/llms.txt CHANGED
@@ -6,4 +6,4 @@
6
6
 
7
7
  ## Skills
8
8
 
9
- - [setup-deepseek](@warlock.js/ai-deepseek/setup-deepseek/SKILL.md): Wire @warlock.js/ai-deepseek — new DeepSeekSDK({apiKey, baseURL?, provider?, pricing?}) for DeepSeek's OpenAI-compatible API, .model({name, reasoning?, vision?, structuredOutput?, responseFormat?}) for ModelContract. Thin wrapper over @warlock.js/ai-openai's OpenAISDK pinned to https://api.deepseek.com with provider "deepseek"; injects DeepSeek-specific reasoning/vision inference + built-in pricing. Models: deepseek-flash / deepseek-v4-flash, deepseek-v4-pro, legacy deepseek-chat / deepseek-reasoner. Built-in peak-rate pricing (DEEPSEEK_DEFAULT_PRICING) and an opt-in off-peak table (DEEPSEEK_OFF_PEAK_PRICING). Triggers: `DeepSeekSDK`, `DEEPSEEK_DEFAULT_PRICING`, `DEEPSEEK_OFF_PEAK_PRICING`, `deepseek-chat`, `deepseek-reasoner`, `deepseek-v4`, `api.deepseek.com`, `DEEPSEEK_API_KEY`, reasoning effort on deepseek; "wire deepseek into a warlock agent", "use deepseek-reasoner", "configure deepseek-chat", "route a warlock agent through deepseek". Skip: OpenAI/Azure/OpenRouter — `@warlock.js/ai-openai`; agent wiring — the `run-ai-agent` topic of the `warlock-js-ai` skill; adapter comparison — the `pick-ai-provider` topic of the `warlock-js-ai` skill; raw deepseek HTTP / the `openai` SDK directly. Typical import `import { DeepSeekSDK } from "@warlock.js/ai-deepseek"`.
9
+ - [ai-deepseek](@warlock.js/ai-deepseek/skills/SKILL.md): DeepSeek adapter for Warlock AI: `DeepSeekSDK`, `DEEPSEEK_CHAT_MODELS`, `DEEPSEEK_DEFAULT_PRICING` and `DEEPSEEK_OFF_PEAK_PRICING`. Use for "connect DeepSeek", reasoning, streaming, tools, capability inference or per-model pricing through `sdk.model()`. Not this package → @warlock.js/ai for agents, tools and workflows; @warlock.js/ai-openai for generic OpenAI-compatible endpoints.
package/package.json CHANGED
@@ -14,13 +14,13 @@
14
14
  "directory": "packages/ai-deepseek"
15
15
  },
16
16
  "dependencies": {
17
- "@warlock.js/ai-openai": "5.34.1",
18
- "@warlock.js/logger": "5.34.1"
17
+ "@warlock.js/ai-openai": "5.34.3",
18
+ "@warlock.js/logger": "5.34.3"
19
19
  },
20
20
  "peerDependencies": {
21
- "@warlock.js/ai": "5.34.1"
21
+ "@warlock.js/ai": "5.34.3"
22
22
  },
23
- "version": "5.34.1",
23
+ "version": "5.34.3",
24
24
  "main": "./cjs/index.cjs",
25
25
  "module": "./esm/index.mjs",
26
26
  "types": "./esm/index.d.mts",
@@ -1,11 +1,11 @@
1
1
  ---
2
- name: setup-deepseek
3
- description: 'Wire @warlock.js/ai-deepseek — new DeepSeekSDK({apiKey, baseURL?, provider?, pricing?}) for DeepSeek''s OpenAI-compatible API, .model({name, reasoning?, vision?, structuredOutput?, responseFormat?}) for ModelContract. Thin wrapper over @warlock.js/ai-openai''s OpenAISDK pinned to https://api.deepseek.com with provider "deepseek"; injects DeepSeek-specific reasoning/vision inference + built-in pricing. Models: deepseek-flash / deepseek-v4-flash, deepseek-v4-pro, legacy deepseek-chat / deepseek-reasoner. Built-in peak-rate pricing (DEEPSEEK_DEFAULT_PRICING) and an opt-in off-peak table (DEEPSEEK_OFF_PEAK_PRICING). Triggers: `DeepSeekSDK`, `DEEPSEEK_DEFAULT_PRICING`, `DEEPSEEK_OFF_PEAK_PRICING`, `deepseek-chat`, `deepseek-reasoner`, `deepseek-v4`, `api.deepseek.com`, `DEEPSEEK_API_KEY`, reasoning effort on deepseek; "wire deepseek into a warlock agent", "use deepseek-reasoner", "configure deepseek-chat", "route a warlock agent through deepseek". Skip: OpenAI/Azure/OpenRouter — `@warlock.js/ai-openai`; agent wiring — the `run-ai-agent` topic of the `warlock-js-ai` skill; adapter comparison — the `pick-ai-provider` topic of the `warlock-js-ai` skill; raw deepseek HTTP / the `openai` SDK directly. Typical import `import { DeepSeekSDK } from "@warlock.js/ai-deepseek"`.'
2
+ name: warlock-js-ai-deepseek
3
+ description: 'DeepSeek adapter for Warlock AI: `DeepSeekSDK`, `DEEPSEEK_CHAT_MODELS`, `DEEPSEEK_DEFAULT_PRICING` and `DEEPSEEK_OFF_PEAK_PRICING`. Use for "connect DeepSeek", reasoning, streaming, tools, capability inference or per-model pricing through `sdk.model()`. Not this package → @warlock.js/ai for agents, tools and workflows; @warlock.js/ai-openai for generic OpenAI-compatible endpoints.'
4
4
  ---
5
5
 
6
6
  # `@warlock.js/ai-deepseek`
7
7
 
8
- Provider adapter for DeepSeek. DeepSeek's API is **OpenAI-compatible**, so this package is a **thin wrapper** over `@warlock.js/ai-openai`'s `OpenAISDK` (the `setup-openai` topic of the `warlock-js-ai-openai` skill): it constructs an internal `OpenAISDK` pinned to `https://api.deepseek.com` with `provider: "deepseek"` and delegates `model()` / `embedder()` / `image()` / `count()` to it — while injecting DeepSeek's own capability inference and pricing so the right flags are set even though the model names aren't OpenAI names. Pair with `@warlock.js/ai` for the agent / tool / system-prompt surface.
8
+ Provider adapter for DeepSeek. DeepSeek's API is **OpenAI-compatible**, so this package is a **thin wrapper** over `@warlock.js/ai-openai`'s `OpenAISDK` (the `warlock-js-ai-openai` skill): it constructs an internal `OpenAISDK` pinned to `https://api.deepseek.com` with `provider: "deepseek"` and delegates `model()` / `embedder()` / `image()` / `count()` to it — while injecting DeepSeek's own capability inference and pricing so the right flags are set even though the model names aren't OpenAI names. Pair with `@warlock.js/ai` for the agent / tool / system-prompt surface.
9
9
 
10
10
  ## Construction
11
11
 
@@ -62,7 +62,7 @@ deepseek.model({ name: "deepseek-reasoner", reasoning: false }); // suppress it
62
62
 
63
63
  ## Uses the OpenAI-compatible endpoint
64
64
 
65
- Everything on the wire — Chat Completions request/response shape, streaming loop, tool-call accumulation, structured-output `response_format`, multipart message mapping, and error wrapping — is inherited **unchanged** from `OpenAIModel`. See the `setup-openai` topic of the `warlock-js-ai-openai` skill for the wire-level detail; it all applies here against `https://api.deepseek.com`.
65
+ Everything on the wire — Chat Completions request/response shape, streaming loop, tool-call accumulation, structured-output `response_format`, multipart message mapping, and error wrapping — is inherited **unchanged** from `OpenAIModel`. See the `warlock-js-ai-openai` skill for the wire-level detail; it all applies here against `https://api.deepseek.com`.
66
66
 
67
67
  Structured output, reasoning effort, and streaming therefore behave exactly as documented for the OpenAI adapter:
68
68
 
@@ -121,7 +121,7 @@ Raw errors surface through the wrapped OpenAI adapter's wrapper into the typed `
121
121
 
122
122
  ## See also
123
123
 
124
- - The `setup-openai` topic of the `warlock-js-ai-openai` skill — the wrapped adapter; all wire-level behavior.
124
+ - The `warlock-js-ai-openai` skill — the wrapped adapter; all wire-level behavior.
125
125
  - The `run-ai-agent` topic of the `warlock-js-ai` skill — passing the model into `ai.agent({...})`.
126
126
  - The `pick-ai-provider` topic of the `warlock-js-ai` skill — adapter comparison.
127
127