shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(coding-agent): harden clipboard copy

Browse Source 
closes #3639
This commit is contained in:
Mario Zechner
2026-04-24 12:52:32 +02:00
parent 9fdb12f985
commit 1e33492525
24 changed files with 561 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
packages/coding-agent/docs/custom-provider.md
View File

@@ -627,11 +627,12 @@ interface ProviderModelConfig {
requiresToolResultName?: boolean;
requiresAssistantAfterToolResult?: boolean;
requiresThinkingAsText?: boolean;
thinkingFormat?: "openai" | "zai" | "qwen" | "qwen-chat-template";
requiresReasoningContentOnAssistantMessages?: boolean;
thinkingFormat?: "openai" | "deepseek" | "zai" | "qwen" | "qwen-chat-template";
cacheControlFormat?: "anthropic";
};
}
```
`qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
`deepseek` sends `thinking: { type: "enabled" | "disabled" }` and `reasoning_effort` when enabled. `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
`cacheControlFormat: "anthropic"` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and last user/assistant text content.

3
packages/coding-agent/docs/models.md
View File

@@ -338,7 +338,8 @@ For providers with partial OpenAI compatibility, use the `compat` field.
| `requiresToolResultName` | Include `name` on tool result messages |
| `requiresAssistantAfterToolResult` | Insert an assistant message before a user message after tool results |
| `requiresThinkingAsText` | Convert thinking blocks to plain text |
| `thinkingFormat` | Use `reasoning_effort`, `zai`, `qwen`, or `qwen-chat-template` thinking parameters |
| `requiresReasoningContentOnAssistantMessages` | Include empty `reasoning_content` on all replayed assistant messages when reasoning is enabled |
| `thinkingFormat` | Use `reasoning_effort`, `deepseek`, `zai`, `qwen`, or `qwen-chat-template` thinking parameters |
| `cacheControlFormat` | Use Anthropic-style `cache_control` markers on the system prompt, last tool definition, and last user/assistant text content. Currently only `anthropic` is supported. |
| `supportsStrictMode` | Include the `strict` field in tool definitions |
| `supportsLongCacheRetention` | Whether the provider accepts long cache retention when cache retention is `long`: `prompt_cache_retention: "24h"` for OpenAI prompt caching, or `cache_control.ttl: "1h"` when `cacheControlFormat` is `anthropic`. Default: `true`. |

2
packages/coding-agent/docs/providers.md
View File

@@ -56,6 +56,7 @@ pi
| Anthropic | `ANTHROPIC_API_KEY` | `anthropic` |
| Azure OpenAI Responses | `AZURE_OPENAI_API_KEY` | `azure-openai-responses` |
| OpenAI | `OPENAI_API_KEY` | `openai` |
| DeepSeek | `DEEPSEEK_API_KEY` | `deepseek` |
| Google Gemini | `GEMINI_API_KEY` | `google` |
| Mistral | `MISTRAL_API_KEY` | `mistral` |
| Groq | `GROQ_API_KEY` | `groq` |
@@ -82,6 +83,7 @@ Store credentials in `~/.pi/agent/auth.json`:
{
"anthropic": { "type": "api_key", "key": "sk-ant-..." },
"openai": { "type": "api_key", "key": "sk-..." },
"deepseek": { "type": "api_key", "key": "sk-..." },
"google": { "type": "api_key", "key": "..." },
"opencode": { "type": "api_key", "key": "..." },
"opencode-go": { "type": "api_key", "key": "..." }