getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-15 13:03:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(ai): Remove old API reference from README

Browse source
This commit is contained in:
Mario Zechner 2025-08-31 22:35:23 +02:00
parent 8f4e96f207
commit c960d36da1
2 changed files with 5 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

16
packages/ai/README.md
View file

@ -4,22 +4,6 @@ Unified LLM API with automatic model discovery, provider configuration, token an
**Note**: This library only includes models that support tool calling (function calling), as this is essential for agentic workflows.
## API Changes in v0.5.15+
The `AssistantMessage` response structure has been updated to support multiple content blocks of different types. Instead of separate fields for `text`, `thinking`, and `toolCalls`, responses now have a unified `content` array that can contain multiple blocks of each type in any order.
```typescript
// Old API (pre-0.5.15)
response.text // single text string
response.thinking // single thinking string
response.toolCalls // array of tool calls
// New API (0.5.15+)
response.content // array of TextContent | ThinkingContent | ToolCall blocks
```
This change allows models to return multiple thinking and text blocks, which is especially useful for complex reasoning tasks.
## Supported Providers
- **OpenAI**

10
packages/pods/src/models.json
View file

@ -114,7 +114,7 @@
}
}
],
"notes": "Requires vLLM 0.10.1+gptoss. Tools/functoin calls only via /v1/responses endpoint."
"notes": "Tools/function calls only via /v1/responses endpoint."
},
"openai/gpt-oss-120b": {
"name": "GPT-OSS-120B",
@ -123,25 +123,25 @@
"gpuCount": 1,
"gpuTypes": ["H100", "H200"],
"args": ["--async-scheduling", "--gpu-memory-utilization", "0.95", "--max-num-batched-tokens", "1024"],
"notes": "Single GPU deployment. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
"notes": "Single GPU deployment. Tools/function calls only via /v1/responses endpoint."
},
{
"gpuCount": 2,
"gpuTypes": ["H100", "H200"],
"args": ["--tensor-parallel-size", "2", "--async-scheduling", "--gpu-memory-utilization", "0.94"],
"notes": "Recommended for H100/H200. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
"notes": "Recommended for H100/H200. Tools/function calls only via /v1/responses endpoint."
},
{
"gpuCount": 4,
"gpuTypes": ["H100", "H200"],
"args": ["--tensor-parallel-size", "4", "--async-scheduling"],
"notes": "Higher throughput. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
"notes": "Higher throughput. Tools/function calls only via /v1/responses endpoint."
},
{
"gpuCount": 8,
"gpuTypes": ["H100", "H200"],
"args": ["--tensor-parallel-size", "8", "--async-scheduling"],
"notes": "Maximum throughput for evaluation workloads. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
"notes": "Maximum throughput for evaluation workloads. Tools/function calls only via /v1/responses endpoint."
}
]
},