docs(spec): align provider list with implementation #5325

Closed
HAL9000 wants to merge 1 commits from spec/additional-llm-providers-gemini-groq-cohere-together-ollama-mistral into master
+10 -5
View File
@@ -20441,7 +20441,7 @@ The complete set of fields available in an actor definition. For the formal JSON
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `config.provider` | string | Yes (LLM) | LLM provider identifier: `openai`, `anthropic`, `google`, `azure`, `openrouter`, etc. |
| `config.provider` | string | Yes (LLM) | LLM provider identifier: `openai`, `anthropic`, `google`, `gemini`, `azure`, `openrouter`, `groq`, `cohere`, `together`, etc. |
| `config.model` | string | Yes (LLM) | Model identifier within the provider. |
| `config.actor` | string | No | Combined `provider/model` format (alternative to separate `provider` + `model`). |
| `config.system_prompt` | string | No | System prompt text with Jinja2 template support. |
@@ -30816,6 +30816,11 @@ Provider credential keys follow the pattern `provider.<name>.<field>`. Each prov
| `provider.google.gemini-api-key` | string | *(not set)* | `GEMINI_API_KEY` | API key for Google Gemini models. Required when using Gemini-based actors. The standard `GEMINI_API_KEY` environment variable is checked for compatibility with Google's tooling. |
| `provider.huggingface.token` | string | *(not set)* | `HF_TOKEN` | Access token for Hugging Face Inference API. Required when using Hugging Face-hosted models. The standard `HF_TOKEN` environment variable is checked for compatibility with Hugging Face tooling. |
| `provider.openrouter.api-key` | string | *(not set)* | `OPENROUTER_API_KEY` | API key for OpenRouter. Required when using OpenRouter as a provider. |
| `provider.groq.api-key` | string | *(not set)* | `GROQ_API_KEY` | API key for Groq Cloud inference. Required when using Groq-hosted models (e.g., `llama-3.1-70b-versatile`). Groq provides high-throughput, low-latency inference for open-source models. |
| `provider.cohere.api-key` | string | *(not set)* | `COHERE_API_KEY` | API key for Cohere models. Required when using Cohere-based actors (e.g., `command-r-plus`). |
| `provider.together.api-key` | string | *(not set)* | `TOGETHER_API_KEY` | API key for Together AI. Required when using Together-hosted open-source models (e.g., `meta-llama/Llama-3.1-70B-Instruct-Turbo`). |
> **Note:** Support for additional providers such as Mistral AI and Ollama is tracked in [issue #5257](https://git.cleverthis.com/cleveragents/cleveragents-core/issues/5257). Those providers will be documented here once their implementations land.
#### Configuration Scoping
@@ -31183,7 +31188,7 @@ The following is the formal [JSON Schema](https://json-schema.org/) definition f
<span style="color: cyan; font-weight: 600;">&quot;properties&quot;</span>: {
<span style="color: cyan; font-weight: 600;">&quot;provider&quot;</span>: {
<span style="color: cyan; font-weight: 600;">&quot;type&quot;</span>: <span style="color: #66cc66;">&quot;string&quot;</span>,
<span style="color: cyan; font-weight: 600;">&quot;description&quot;</span>: <span style="color: #66cc66;">&quot;LLM provider identifier: openai, anthropic, google, azure, openrouter, etc.&quot;</span>
<span style="color: cyan; font-weight: 600;">&quot;description&quot;</span>: <span style="color: #66cc66;">&quot;LLM provider identifier: openai, anthropic, google, gemini, azure, openrouter, groq, cohere, together, etc.&quot;</span>
},
<span style="color: cyan; font-weight: 600;">&quot;model&quot;</span>: {
<span style="color: cyan; font-weight: 600;">&quot;type&quot;</span>: <span style="color: #66cc66;">&quot;string&quot;</span>,
@@ -31512,7 +31517,7 @@ The following annotated YAML provides an easier-to-read overview of the same sch
<span style="color: cyan; font-weight: 600;">type</span>: <span style="color: magenta;">llm | tool</span><span style="opacity: 0.7;"> # Actor type (required)</span>
<span style="color: cyan; font-weight: 600;">config</span>:
<span style="opacity: 0.7;"> # ── For type: llm ──────────────────────────────────────────</span>
<span style="color: cyan; font-weight: 600;">provider</span>: <span style="color: #66cc66;">&lt;string&gt;</span><span style="opacity: 0.7;"> # Provider identifier: openai, anthropic, google, azure, openrouter, etc. (required for LLM)</span>
<span style="color: cyan; font-weight: 600;">provider</span>: <span style="color: #66cc66;">&lt;string&gt;</span><span style="opacity: 0.7;"> # Provider identifier: openai, anthropic, google, gemini, azure, openrouter, groq, cohere, together, etc. (required for LLM)</span>
<span style="color: cyan; font-weight: 600;">model</span>: <span style="color: #66cc66;">&lt;string&gt;</span><span style="opacity: 0.7;"> # Model identifier: gpt-4, claude-3.5-sonnet, etc. (required for LLM)</span>
<span style="opacity: 0.7;"> # OR use the combined format:</span>
<span style="color: cyan; font-weight: 600;">actor</span>: <span style="color: #66cc66;">&quot;&lt;provider&gt;/&lt;model&gt;&quot;</span><span style="opacity: 0.7;"> # Combined provider/model (alternative to provider + model)</span>
@@ -31685,8 +31690,8 @@ The following annotated YAML provides an easier-to-read overview of the same sch
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `type` | string | Yes | Actor type. `llm` for language model actors, `tool` for tool-based actors. |
| `config.provider` | string | Yes (LLM) | LLM provider identifier: `openai`, `anthropic`, `google`, `azure`, `openrouter`, etc. |
| `config.model` | string | Yes (LLM) | Model identifier within the provider: `gpt-4`, `claude-3.5-sonnet`, `gemini-pro`, etc. |
| `config.provider` | string | Yes (LLM) | LLM provider identifier: `openai`, `anthropic`, `google`, `gemini`, `azure`, `openrouter`, `groq`, `cohere`, `together`, etc. |
| `config.model` | string | Yes (LLM) | Model identifier within the provider: `gpt-4`, `claude-3.5-sonnet`, `gemini-pro`, `command-r-plus`, `llama-3.1-70b-versatile`, etc. |
| `config.actor` | string | No | Combined `provider/model` format. Alternative to specifying `provider` and `model` separately. |
| `config.system_prompt` | string | No | System prompt text. Supports Jinja2 template syntax for dynamic content. |
| `config.temperature` | float | Provider default | Sampling temperature (0.0 to 2.0). Lower values are more deterministic. |