smashimo/oh-my-pi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai): implemented fallback handling and option for qwen reasoning effort

Browse Source 
- Added `qwenTemplateReasoningEffort` model compatibility option to disable Qwen chat template kwargs for strict local servers.
- Implemented fallback handling to strip rejected `chat_template_kwargs.reasoning_effort` and hoist values to top-level fields.
- Added comprehensive test coverage for Qwen reasoning effort fallback and keyword rejections.
This commit is contained in:
can1357
2026-08-19 17:40:39 +02:00
parent 7099457f84
commit 74bc1f442e
7 changed files with 267 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/models.md
+1
View File
@@ -517,6 +517,7 @@ Reasoning / thinking:
- `supportsReasoningParams` — whether request shaping may send reasoning params at all. Default: auto (off for GitHub Copilot chat-completions).
- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh|max`) to provider-specific strings (e.g. Fireworks GLM maps `minimal -> "none"`).
- `thinkingFormat` — request shape for thinking: `"openai"` (`reasoning_effort`), `"openrouter"` (`reasoning: { effort }`), `"zai"` (`thinking: { type: "enabled" }`), `"qwen"` (top-level `enable_thinking`), or `"qwen-chat-template"` (`chat_template_kwargs.enable_thinking`). Default: `"openai"`.
- `qwenTemplateReasoningEffort` — route the selected effort onto the Qwen 3.8+ chat template's `reasoning_effort` kwarg (`chat_template_kwargs.reasoning_effort`, plus the top-level field on the `qwen` dialect). Default: auto (on for Qwen 3.8+ ids on local non-Ollama backends). Set `false` for strict servers that reject unknown `chat_template_kwargs`; effort selections are then not sent for the Qwen dialects and the template runs at its own default.
- `reasoningContentField` — assistant field carrying chain-of-thought: `"reasoning_content"`, `"reasoning"`, or `"reasoning_text"`. Default: auto.
- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.
- `allowsSyntheticReasoningContentForToolCalls` — allow a placeholder reasoning field when a prior assistant tool-call turn lacks provider reasoning content. Default: `true`; set `false` for providers that validate the exact reasoning value.