sscoble/pi-mono
1
0
Fork 0
mirror of https://github.com/badlogic/pi-mono.git synced 2026-11-05 23:37:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

feat(ai): add requiresNonNullAssistantContent compat flag (#8118)

Browse source 
Closes #8063
This commit is contained in:
gaoyk19 2026-11-04 18:29:54 +08:00 • committed by GitHub
parent 25490ea49b
commit 14b804d809
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 134 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
packages/coding-agent/docs/models-configuration.md
View file

@ -118,6 +118,7 @@ See [Describe model input and caching](models.md#describe-model-input-and-cachin
| `maxTokensField` | `"max_completion_tokens" \| "max_tokens"` | | Which field to use for max tokens. Default: auto-detected from URL. |
| `requiresToolResultName` | boolean | | Whether tool results require the name field. Default: auto-detected from URL. |
| `requiresAssistantAfterToolResult` | boolean | | Whether a user message after tool results requires an assistant message in between. Default: auto-detected from URL. |
| `requiresNonNullAssistantContent` | boolean | | Whether replayed assistant messages with no text (e.g. tool-call-only messages) must send "" instead of null content. Default: false. |
| `requiresThinkingAsText` | boolean | | Whether thinking blocks must be converted to text blocks with <thinking> delimiters. Default: auto-detected from URL. |
| `requiresReasoningContentOnAssistantMessages` | boolean | | Whether all replayed assistant messages must include an empty reasoning_content field when reasoning is enabled. Default: auto-detected from URL. |
| `thinkingFormat` | `"openai" \| "openrouter" \| "deepseek" \| "together" \| "baseten" \| "zai" \| "qwen" \| "chat-template" \| "qwen-chat-template" \| "string-thinking" \| "ant-ling"` | | Format for reasoning or thinking parameters. When omitted, Pi auto-detects the format from the provider URL. "openai" uses reasoning_effort, "openrouter" uses reasoning.effort, "deepseek" uses thinking.type plus reasoning_effort when supported, "together" uses reasoning.enabled plus reasoning_effort when supported, "baseten" uses configurable chat_template_args plus reasoning_effort when supported, "zai" uses thinking.type, "qwen" uses top-level enable_thinking, "qwen-chat-template" uses chat_template_kwargs.enable_thinking and preserve_thinking, "chat-template" uses configurable chat_template_kwargs, "string-thinking" uses top-level thinking, and "ant-ling" uses reasoning.effort only when the mapped effort is non-null. |

4
packages/coding-agent/schemas/models.schema.json
View file

@ -552,6 +552,10 @@
"type": "boolean",
"description": "Whether a user message after tool results requires an assistant message in between. Default: auto-detected from URL."
},
"requiresNonNullAssistantContent": {
"type": "boolean",
"description": "Whether replayed assistant messages with no text (e.g. tool-call-only messages) must send \"\" instead of null content. Default: false."
},
"requiresThinkingAsText": {
"type": "boolean",
"description": "Whether thinking blocks must be converted to text blocks with <thinking> delimiters. Default: auto-detected from URL."