@warlock.js/ai-groq 5.27.0 → 5.29.0

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.
Files changed (5) hide show
  1. package/CHANGELOG.md +12 -0
  2. package/llms-full.txt +6 -6
  3. package/llms.txt +1 -1
  4. package/package.json +4 -4
  5. package/skills/setup-groq/SKILL.md +6 -6
package/CHANGELOG.md CHANGED
@@ -4,6 +4,18 @@ All notable changes to `@warlock.js/ai-groq` 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
+ ## 5.29.0 - 2026-10-01
8
+
9
+ ### Changed
10
+
11
+ - Lockstep release; package APIs are unchanged. Skills refer to other topics by name instead of file paths, so cross-references keep working after `agent-kit` copies them into an app.
12
+
13
+ ## 5.28.0 - 2026-10-01
14
+
15
+ ### Changed
16
+
17
+ - Lockstep release; package APIs are unchanged. `llms.txt` now lists every skill topic with its description (frontmatter in CRLF files was skipped).
18
+
7
19
  ## 5.27.0 - 2026-10-01
8
20
 
9
21
  ### Changed
package/llms-full.txt CHANGED
@@ -8,7 +8,7 @@
8
8
 
9
9
  ---
10
10
  name: setup-groq
11
- description: 'Wire @warlock.js/ai-groq — new GroqSDK({apiKey, baseURL?, provider?, pricing?}) for Groq-hosted open models on LPU hardware (llama-3.3-70b-versatile, llama-3.1-8b-instant, openai/gpt-oss-120b/20b, deepseek-r1-distill-llama-70b). Thin wrapper over @warlock.js/ai-openai — uses the OpenAI-compatible endpoint https://api.groq.com/openai/v1, delegating transport/streaming/structured-output/errors to OpenAISDK while injecting Groqs OWN vision/reasoning inference + default pricing. .model({name, vision?, reasoning?, structuredOutput?}) for ModelContract. Triggers: `GroqSDK`, `groq.model`, `groq.count`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `gpt-oss`, `deepseek-r1-distill`, `groq vision`, `groq reasoning`, `reasoning_effort`, `https://api.groq.com/openai/v1`, OpenAI-compatible Groq, LPU, fast inference; "wire groq into a warlock agent", "use llama 3.3 on groq", "run gpt-oss / deepseek reasoning on groq", "point warlock at the groq endpoint"; import `import { GroqSDK } from "@warlock.js/ai-groq"`. Skip: agent wiring — `@warlock.js/ai/run-ai-agent/SKILL.md`; adapter comparison — `@warlock.js/ai/pick-ai-provider/SKILL.md`; the wrapped adapter `@warlock.js/ai-openai` (`setup-openai`); embeddings (Groq has none — use openai/google); siblings `@warlock.js/ai-anthropic`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `groq-sdk` / `openai` SDK.'
11
+ description: 'Wire @warlock.js/ai-groq — new GroqSDK({apiKey, baseURL?, provider?, pricing?}) for Groq-hosted open models on LPU hardware (llama-3.3-70b-versatile, llama-3.1-8b-instant, openai/gpt-oss-120b/20b, deepseek-r1-distill-llama-70b). Thin wrapper over @warlock.js/ai-openai — uses the OpenAI-compatible endpoint https://api.groq.com/openai/v1, delegating transport/streaming/structured-output/errors to OpenAISDK while injecting Groqs OWN vision/reasoning inference + default pricing. .model({name, vision?, reasoning?, structuredOutput?}) for ModelContract. Triggers: `GroqSDK`, `groq.model`, `groq.count`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `gpt-oss`, `deepseek-r1-distill`, `groq vision`, `groq reasoning`, `reasoning_effort`, `https://api.groq.com/openai/v1`, OpenAI-compatible Groq, LPU, fast inference; "wire groq into a warlock agent", "use llama 3.3 on groq", "run gpt-oss / deepseek reasoning on groq", "point warlock at the groq endpoint"; import `import { GroqSDK } from "@warlock.js/ai-groq"`. Skip: 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; the wrapped adapter `@warlock.js/ai-openai` (`setup-openai`); embeddings (Groq has none — use openai/google); siblings `@warlock.js/ai-anthropic`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `groq-sdk` / `openai` SDK.'
12
12
  ---
13
13
 
14
14
  # `@warlock.js/ai-groq`
@@ -72,7 +72,7 @@ await model.complete(messages, { reasoning: { effort: "high" } }); // → reas
72
72
 
73
73
  ## Structured output & streaming
74
74
 
75
- Inherited unchanged from `@warlock.js/ai-openai`: a `responseSchema` maps to `response_format: json_schema` (strict) when the schema is a proper root object, else loose `json_object`; `model.stream()` drains the streaming Chat Completions response and yields `delta` / `tool-call` / `done` chunks with `include_usage` on. See [`setup-openai`](@warlock.js/ai-openai/skills/setup-openai/SKILL.md) for the full wire behavior.
75
+ Inherited unchanged from `@warlock.js/ai-openai`: a `responseSchema` maps to `response_format: json_schema` (strict) when the schema is a proper root object, else loose `json_object`; `model.stream()` drains the streaming Chat Completions response and yields `delta` / `tool-call` / `done` chunks with `include_usage` on. See the `setup-openai` topic of the `warlock-js-ai-openai` skill for the full wire behavior.
76
76
 
77
77
  ## Embeddings — not available on Groq
78
78
 
@@ -105,7 +105,7 @@ Good for budgeting; not for billing.
105
105
 
106
106
  ## Errors
107
107
 
108
- Raw errors are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy by the inner OpenAI adapter's error wrapper (dispatch keys on `status + code`). See [`@warlock.js/ai/handle-ai-errors/SKILL.md`](@warlock.js/ai/handle-ai-errors/SKILL.md). Note Groq's documented OpenAI-compat gaps — `n` must be `1`, and `logprobs` / `logit_bias` / `top_logprobs` / `messages[].name` are unsupported.
108
+ Raw errors are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy by the inner OpenAI adapter's error wrapper (dispatch keys on `status + code`). See the `handle-ai-errors` topic of the `warlock-js-ai` skill. Note Groq's documented OpenAI-compat gaps — `n` must be `1`, and `logprobs` / `logit_bias` / `top_logprobs` / `messages[].name` are unsupported.
109
109
 
110
110
  ## When NOT to use this skill
111
111
 
@@ -115,8 +115,8 @@ Raw errors are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy by th
115
115
 
116
116
  ## See also
117
117
 
118
- - [`@warlock.js/ai-openai/skills/setup-openai/SKILL.md`](@warlock.js/ai-openai/skills/setup-openai/SKILL.md) — the wrapped adapter; full wire / streaming / structured-output detail
119
- - [`@warlock.js/ai/run-ai-agent/SKILL.md`](@warlock.js/ai/run-ai-agent/SKILL.md) — passing the model into `ai.agent({...})`
120
- - [`@warlock.js/ai/pick-ai-provider/SKILL.md`](@warlock.js/ai/pick-ai-provider/SKILL.md) — adapter comparison
118
+ - The `setup-openai` topic of the `warlock-js-ai-openai` skill — the wrapped adapter; full wire / streaming / structured-output detail
119
+ - The `run-ai-agent` topic of the `warlock-js-ai` skill — passing the model into `ai.agent({...})`
120
+ - The `pick-ai-provider` topic of the `warlock-js-ai` skill — adapter comparison
121
121
 
122
122
 
package/llms.txt CHANGED
@@ -6,4 +6,4 @@
6
6
 
7
7
  ## Skills
8
8
 
9
- - [setup-groq](@warlock.js/ai-groq/setup-groq/SKILL.md): (no description)
9
+ - [setup-groq](@warlock.js/ai-groq/setup-groq/SKILL.md): Wire @warlock.js/ai-groq — new GroqSDK({apiKey, baseURL?, provider?, pricing?}) for Groq-hosted open models on LPU hardware (llama-3.3-70b-versatile, llama-3.1-8b-instant, openai/gpt-oss-120b/20b, deepseek-r1-distill-llama-70b). Thin wrapper over @warlock.js/ai-openai — uses the OpenAI-compatible endpoint https://api.groq.com/openai/v1, delegating transport/streaming/structured-output/errors to OpenAISDK while injecting Groqs OWN vision/reasoning inference + default pricing. .model({name, vision?, reasoning?, structuredOutput?}) for ModelContract. Triggers: `GroqSDK`, `groq.model`, `groq.count`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `gpt-oss`, `deepseek-r1-distill`, `groq vision`, `groq reasoning`, `reasoning_effort`, `https://api.groq.com/openai/v1`, OpenAI-compatible Groq, LPU, fast inference; "wire groq into a warlock agent", "use llama 3.3 on groq", "run gpt-oss / deepseek reasoning on groq", "point warlock at the groq endpoint"; import `import { GroqSDK } from "@warlock.js/ai-groq"`. Skip: 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; the wrapped adapter `@warlock.js/ai-openai` (`setup-openai`); embeddings (Groq has none — use openai/google); siblings `@warlock.js/ai-anthropic`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `groq-sdk` / `openai` SDK.
package/package.json CHANGED
@@ -15,13 +15,13 @@
15
15
  "url": "https://github.com/warlockjs/ai-groq"
16
16
  },
17
17
  "peerDependencies": {
18
- "@warlock.js/ai": "5.27.0"
18
+ "@warlock.js/ai": "5.29.0"
19
19
  },
20
20
  "dependencies": {
21
- "@warlock.js/ai-openai": "5.27.0",
22
- "@warlock.js/logger": "5.27.0"
21
+ "@warlock.js/ai-openai": "5.29.0",
22
+ "@warlock.js/logger": "5.29.0"
23
23
  },
24
- "version": "5.27.0",
24
+ "version": "5.29.0",
25
25
  "main": "./cjs/index.cjs",
26
26
  "module": "./esm/index.mjs",
27
27
  "types": "./esm/index.d.mts",
package/skills/setup-groq/SKILL.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: setup-groq
3
- description: 'Wire @warlock.js/ai-groq — new GroqSDK({apiKey, baseURL?, provider?, pricing?}) for Groq-hosted open models on LPU hardware (llama-3.3-70b-versatile, llama-3.1-8b-instant, openai/gpt-oss-120b/20b, deepseek-r1-distill-llama-70b). Thin wrapper over @warlock.js/ai-openai — uses the OpenAI-compatible endpoint https://api.groq.com/openai/v1, delegating transport/streaming/structured-output/errors to OpenAISDK while injecting Groqs OWN vision/reasoning inference + default pricing. .model({name, vision?, reasoning?, structuredOutput?}) for ModelContract. Triggers: `GroqSDK`, `groq.model`, `groq.count`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `gpt-oss`, `deepseek-r1-distill`, `groq vision`, `groq reasoning`, `reasoning_effort`, `https://api.groq.com/openai/v1`, OpenAI-compatible Groq, LPU, fast inference; "wire groq into a warlock agent", "use llama 3.3 on groq", "run gpt-oss / deepseek reasoning on groq", "point warlock at the groq endpoint"; import `import { GroqSDK } from "@warlock.js/ai-groq"`. Skip: agent wiring — `@warlock.js/ai/run-ai-agent/SKILL.md`; adapter comparison — `@warlock.js/ai/pick-ai-provider/SKILL.md`; the wrapped adapter `@warlock.js/ai-openai` (`setup-openai`); embeddings (Groq has none — use openai/google); siblings `@warlock.js/ai-anthropic`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `groq-sdk` / `openai` SDK.'
3
+ description: 'Wire @warlock.js/ai-groq — new GroqSDK({apiKey, baseURL?, provider?, pricing?}) for Groq-hosted open models on LPU hardware (llama-3.3-70b-versatile, llama-3.1-8b-instant, openai/gpt-oss-120b/20b, deepseek-r1-distill-llama-70b). Thin wrapper over @warlock.js/ai-openai — uses the OpenAI-compatible endpoint https://api.groq.com/openai/v1, delegating transport/streaming/structured-output/errors to OpenAISDK while injecting Groqs OWN vision/reasoning inference + default pricing. .model({name, vision?, reasoning?, structuredOutput?}) for ModelContract. Triggers: `GroqSDK`, `groq.model`, `groq.count`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `gpt-oss`, `deepseek-r1-distill`, `groq vision`, `groq reasoning`, `reasoning_effort`, `https://api.groq.com/openai/v1`, OpenAI-compatible Groq, LPU, fast inference; "wire groq into a warlock agent", "use llama 3.3 on groq", "run gpt-oss / deepseek reasoning on groq", "point warlock at the groq endpoint"; import `import { GroqSDK } from "@warlock.js/ai-groq"`. Skip: 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; the wrapped adapter `@warlock.js/ai-openai` (`setup-openai`); embeddings (Groq has none — use openai/google); siblings `@warlock.js/ai-anthropic`, `@warlock.js/ai-bedrock`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`; raw `groq-sdk` / `openai` SDK.'
4
4
  ---
5
5
 
6
6
  # `@warlock.js/ai-groq`
@@ -64,7 +64,7 @@ await model.complete(messages, { reasoning: { effort: "high" } }); // → reas
64
64
 
65
65
  ## Structured output & streaming
66
66
 
67
- Inherited unchanged from `@warlock.js/ai-openai`: a `responseSchema` maps to `response_format: json_schema` (strict) when the schema is a proper root object, else loose `json_object`; `model.stream()` drains the streaming Chat Completions response and yields `delta` / `tool-call` / `done` chunks with `include_usage` on. See [`setup-openai`](@warlock.js/ai-openai/skills/setup-openai/SKILL.md) for the full wire behavior.
67
+ Inherited unchanged from `@warlock.js/ai-openai`: a `responseSchema` maps to `response_format: json_schema` (strict) when the schema is a proper root object, else loose `json_object`; `model.stream()` drains the streaming Chat Completions response and yields `delta` / `tool-call` / `done` chunks with `include_usage` on. See the `setup-openai` topic of the `warlock-js-ai-openai` skill for the full wire behavior.
68
68
 
69
69
  ## Embeddings — not available on Groq
70
70
 
@@ -97,7 +97,7 @@ Good for budgeting; not for billing.
97
97
 
98
98
  ## Errors
99
99
 
100
- Raw errors are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy by the inner OpenAI adapter's error wrapper (dispatch keys on `status + code`). See [`@warlock.js/ai/handle-ai-errors/SKILL.md`](@warlock.js/ai/handle-ai-errors/SKILL.md). Note Groq's documented OpenAI-compat gaps — `n` must be `1`, and `logprobs` / `logit_bias` / `top_logprobs` / `messages[].name` are unsupported.
100
+ Raw errors are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy by the inner OpenAI adapter's error wrapper (dispatch keys on `status + code`). See the `handle-ai-errors` topic of the `warlock-js-ai` skill. Note Groq's documented OpenAI-compat gaps — `n` must be `1`, and `logprobs` / `logit_bias` / `top_logprobs` / `messages[].name` are unsupported.
101
101
 
102
102
  ## When NOT to use this skill
103
103
 
@@ -107,6 +107,6 @@ Raw errors are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy by th
107
107
 
108
108
  ## See also
109
109
 
110
- - [`@warlock.js/ai-openai/skills/setup-openai/SKILL.md`](@warlock.js/ai-openai/skills/setup-openai/SKILL.md) — the wrapped adapter; full wire / streaming / structured-output detail
111
- - [`@warlock.js/ai/run-ai-agent/SKILL.md`](@warlock.js/ai/run-ai-agent/SKILL.md) — passing the model into `ai.agent({...})`
112
- - [`@warlock.js/ai/pick-ai-provider/SKILL.md`](@warlock.js/ai/pick-ai-provider/SKILL.md) — adapter comparison
110
+ - The `setup-openai` topic of the `warlock-js-ai-openai` skill — the wrapped adapter; full wire / streaming / structured-output detail
111
+ - The `run-ai-agent` topic of the `warlock-js-ai` skill — passing the model into `ai.agent({...})`
112
+ - The `pick-ai-provider` topic of the `warlock-js-ai` skill — adapter comparison