gpt-oss: implement harmony parsing (#15181)

* model : add harmony parser for gpt-oss

* gpt-oss : fix grammar trigger from causing empty stack

* gpt-oss: tweak the grammar trigger again

* gpt-oss : add support for recipient in role header

* gpt-oss : fix ungrouped tool calls in grammar

* gpt-oss : loosen function name matching during parse

* gpt-oss : clean up workarounds

* gpt-oss : add template tests

* gpt-oss : simulate thinking and tool call tags

* gpt-oss : undo think tags when reasoning_format is none

* gpt-oss : set special tokens back to user defined

* gpt-oss : update openai-gpt-oss template

* server : filter out harmony thought messages

* gpt-oss : simplify parsing

tools/server/webui/src/components/ChatMessage.tsx

@@ -62,8 +62,7 @@ export default function ChatMessage({
       return { content: msg.content };
     }
     const REGEX_THINK_OPEN = /<think>|<\|channel\|>analysis<\|message\|>/;
-    const REGEX_THINK_CLOSE =
-      /<\/think>|<\|start\|>assistant<\|channel\|>final<\|message\|>/;
+    const REGEX_THINK_CLOSE = /<\/think>|<\|end\|>/;
     let actualContent = '';
     let thought = '';
     let isThinking = false;

tools/server/webui/src/utils/misc.ts

@@ -131,9 +131,7 @@ export function filterThoughtFromMsgs(messages: APIMessage[]) {
       content:
         msg.role === 'assistant'
           ? contentStr
-              .split(
-                /<\/think>|<\|start\|>assistant<\|channel\|>final<\|message\|>/
-              )
+              .split(/<\/think>|<\|end\|>/)
               .at(-1)!
               .trim()
           : contentStr,