refactor: centralize CoT parsing in backend for streaming mode

common/arg.cpp

@@ -3425,7 +3425,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         {"--reasoning-format"}, "FORMAT",
         "controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:\n"
         "- none: leaves thoughts unparsed in `message.content`\n"
-        "- deepseek: puts thoughts in `message.reasoning_content` (except in streaming mode, which behaves as `none`)\n"
+        "- deepseek: puts thoughts in `message.reasoning_content`\n"
+        "- deepseek-legacy: keeps `<think>` tags in `message.content` while also populating `message.reasoning_content`\n"
         "(default: auto)",
         [](common_params & params, const std::string & value) {
             params.reasoning_format = common_reasoning_format_from_name(value);

common/chat-parser.cpp

@@ -3,9 +3,12 @@
 #include "log.h"
 #include "regex-partial.h"
 
+#include <algorithm>
+#include <cctype>
 #include <optional>
 #include <stdexcept>
 #include <string>
+#include <string_view>
 #include <vector>
 
 using json = nlohmann::ordered_json;
@@ -166,6 +169,27 @@ void common_chat_msg_parser::consume_literal(const std::string & literal) {
 }
 
 bool common_chat_msg_parser::try_parse_reasoning(const std::string & start_think, const std::string & end_think) {
+    std::string pending_reasoning_prefix;
+
+    if (syntax_.reasoning_format == COMMON_REASONING_FORMAT_NONE) {
+        return false;
+    }
+
+    auto set_reasoning_prefix = [&](size_t prefix_pos) {
+        if (!syntax_.thinking_forced_open || syntax_.reasoning_in_content) {
+            return;
+        }
+        if (prefix_pos + start_think.size() > input_.size()) {
+            pending_reasoning_prefix.clear();
+            return;
+        }
+        // Capture the exact literal that opened the reasoning section so we can
+        // surface it back to callers. This ensures formats that force the
+        // reasoning tag open (e.g. DeepSeek R1) retain their original prefix
+        // instead of dropping it during parsing.
+        pending_reasoning_prefix = input_.substr(prefix_pos, start_think.size());
+    };
+
     auto handle_reasoning = [&](const std::string & reasoning, bool closed) {
         auto stripped_reasoning = string_strip(reasoning);
         if (stripped_reasoning.empty()) {
@@ -178,28 +202,116 @@ bool common_chat_msg_parser::try_parse_reasoning(const std::string & start_think
                 add_content(syntax_.reasoning_format == COMMON_REASONING_FORMAT_DEEPSEEK ? "</think>" : end_think);
             }
         } else {
+            if (!pending_reasoning_prefix.empty()) {
+                add_reasoning_content(pending_reasoning_prefix);
+                pending_reasoning_prefix.clear();
+            }
             add_reasoning_content(stripped_reasoning);
         }
     };
-    if (syntax_.reasoning_format != COMMON_REASONING_FORMAT_NONE) {
-        if (syntax_.thinking_forced_open || try_consume_literal(start_think)) {
-            if (auto res = try_find_literal(end_think)) {
-                handle_reasoning(res->prelude, /* closed */ true);
-                consume_spaces();
-                return true;
-            }
-            auto rest = consume_rest();
+
+    const size_t saved_pos = pos_;
+    const size_t saved_content_size = result_.content.size();
+    const size_t saved_reasoning_size = result_.reasoning_content.size();
+
+    auto restore_state = [&]() {
+        move_to(saved_pos);
+        result_.content.resize(saved_content_size);
+        result_.reasoning_content.resize(saved_reasoning_size);
+    };
+
+    // Allow leading whitespace to be preserved as content when reasoning is present at the start
+    size_t cursor = pos_;
+    size_t whitespace_end = cursor;
+    while (whitespace_end < input_.size() && std::isspace(static_cast<unsigned char>(input_[whitespace_end]))) {
+        ++whitespace_end;
+    }
+
+    if (whitespace_end >= input_.size()) {
+        restore_state();
+        if (syntax_.thinking_forced_open) {
+            auto rest = input_.substr(saved_pos);
             if (!rest.empty()) {
                 handle_reasoning(rest, /* closed */ !is_partial());
             }
-            // Allow unclosed thinking tags, for now (https://github.com/ggml-org/llama.cpp/issues/13812, https://github.com/ggml-org/llama.cpp/issues/13877)
-            // if (!syntax_.thinking_forced_open) {
-            //     throw common_chat_msg_partial_exception(end_think);
-            // }
+            move_to(input_.size());
             return true;
         }
+        return false;
+    }
+
+    cursor = whitespace_end;
+    const size_t remaining = input_.size() - cursor;
+    const size_t start_prefix = std::min(start_think.size(), remaining);
+    const bool has_start_tag = input_.compare(cursor, start_prefix, start_think, 0, start_prefix) == 0;
+
+    if (has_start_tag && start_prefix < start_think.size()) {
+        move_to(input_.size());
+        return true;
+    }
+
+    if (has_start_tag) {
+        if (whitespace_end > pos_) {
+            add_content(input_.substr(pos_, whitespace_end - pos_));
+        }
+        set_reasoning_prefix(cursor);
+        cursor += start_think.size();
+    } else if (syntax_.thinking_forced_open) {
+        cursor = whitespace_end;
+    } else {
+        restore_state();
+        return false;
+    }
+    while (true) {
+        if (cursor >= input_.size()) {
+            move_to(input_.size());
+            return true;
+        }
+
+        size_t end_pos = input_.find(end_think, cursor);
+        if (end_pos == std::string::npos) {
+            std::string_view remaining_view(input_.data() + cursor, input_.size() - cursor);
+            size_t partial_off = string_find_partial_stop(remaining_view, end_think);
+            size_t reasoning_end = partial_off == std::string::npos ? input_.size() : cursor + partial_off;
+            if (reasoning_end > cursor) {
+                handle_reasoning(input_.substr(cursor, reasoning_end - cursor), /* closed */ partial_off == std::string::npos && !is_partial());
+            }
+            move_to(input_.size());
+            return true;
+        }
+
+        if (end_pos > cursor) {
+            handle_reasoning(input_.substr(cursor, end_pos - cursor), /* closed */ true);
+        } else {
+            handle_reasoning("", /* closed */ true);
+        }
+
+        cursor = end_pos + end_think.size();
+
+        while (cursor < input_.size() && std::isspace(static_cast<unsigned char>(input_[cursor]))) {
+            ++cursor;
+        }
+
+        const size_t next_remaining = input_.size() - cursor;
+        if (next_remaining == 0) {
+            move_to(cursor);
+            return true;
+        }
+
+        const size_t next_prefix = std::min(start_think.size(), next_remaining);
+        if (input_.compare(cursor, next_prefix, start_think, 0, next_prefix) == 0) {
+            if (next_prefix < start_think.size()) {
+                move_to(input_.size());
+                return true;
+            }
+            set_reasoning_prefix(cursor);
+            cursor += start_think.size();
+            continue;
+        }
+
+        move_to(cursor);
+        return true;
     }
-    return false;
 }
 
 std::string common_chat_msg_parser::consume_rest() {

common/chat.cpp

@@ -1408,6 +1408,8 @@ static common_chat_params common_chat_params_init_apertus(const common_chat_temp
     return data;
 }
 static void common_chat_parse_llama_3_1(common_chat_msg_parser & builder, bool with_builtin_tools = false) {
+    builder.try_parse_reasoning("<think>", "</think>");
+
     if (!builder.syntax().parse_tool_calls) {
         builder.add_content(builder.consume_rest());
         return;
@@ -2862,6 +2864,7 @@ common_chat_params common_chat_templates_apply(
 }
 
 static void common_chat_parse_content_only(common_chat_msg_parser & builder) {
+    builder.try_parse_reasoning("<think>", "</think>");
     builder.add_content(builder.consume_rest());
 }
 

common/common.h

@@ -432,7 +432,7 @@ struct common_params {
     std::string chat_template = "";                                                                         // NOLINT
     bool use_jinja = false;                                                                                 // NOLINT
     bool enable_chat_template = true;
-    common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_AUTO;
+    common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK;
     int reasoning_budget = -1;
     bool prefill_assistant = true;                                                                          // if true, any trailing assistant message will be prefilled into the response
 

tests/test-chat-parser.cpp

@@ -106,6 +106,34 @@ static void test_reasoning() {
     assert_equals("<think>Cogito</think>", builder.result().content);
     assert_equals("Ergo sum", builder.consume_rest());
   }
+  {
+    const std::string variant("content_only_inline_think");
+    common_chat_syntax syntax = {
+        /* .format = */ COMMON_CHAT_FORMAT_CONTENT_ONLY,
+        /* .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK,
+        /* .reasoning_in_content = */ false,
+        /* .thinking_forced_open = */ false,
+        /* .parse_tool_calls = */ false,
+    };
+    const std::string input = "<think>Pense</think>Bonjour";
+    auto msg = common_chat_parse(input, false, syntax);
+    assert_equals(variant, std::string("Pense"), msg.reasoning_content);
+    assert_equals(variant, std::string("Bonjour"), msg.content);
+  }
+  {
+    const std::string variant("llama_3_inline_think");
+    common_chat_syntax syntax = {
+        /* .format = */ COMMON_CHAT_FORMAT_LLAMA_3_X,
+        /* .reasoning_format = */ COMMON_REASONING_FORMAT_DEEPSEEK,
+        /* .reasoning_in_content = */ false,
+        /* .thinking_forced_open = */ false,
+        /* .parse_tool_calls = */ false,
+    };
+    const std::string input = "<think>Plan</think>Réponse";
+    auto msg = common_chat_parse(input, false, syntax);
+    assert_equals(variant, std::string("Plan"), msg.reasoning_content);
+    assert_equals(variant, std::string("Réponse"), msg.content);
+  }
   // Test DeepSeek V3.1 parsing - reasoning content followed by "</think>" and then regular content
   {
     common_chat_syntax syntax = {

tools/server/README.md

@@ -190,7 +190,7 @@ The project is under active development, and we are [looking for feedback and co
 | `--no-slots` | disables slots monitoring endpoint<br/>(env: LLAMA_ARG_NO_ENDPOINT_SLOTS) |
 | `--slot-save-path PATH` | path to save slot kv cache (default: disabled) |
 | `--jinja` | use jinja template for chat (default: disabled)<br/>(env: LLAMA_ARG_JINJA) |
-| `--reasoning-format FORMAT` | controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:<br/>- none: leaves thoughts unparsed in `message.content`<br/>- deepseek: puts thoughts in `message.reasoning_content` (except in streaming mode, which behaves as `none`)<br/>(default: auto)<br/>(env: LLAMA_ARG_THINK) |
+| `--reasoning-format FORMAT` | controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:<br/>- none: leaves thoughts unparsed in `message.content`<br/>- deepseek: puts thoughts in `message.reasoning_content`<br/>- deepseek-legacy: keeps `<think>` tags in `message.content` while also populating `message.reasoning_content`<br/>(default: deepseek)<br/>(env: LLAMA_ARG_THINK) |
 | `--reasoning-budget N` | controls the amount of thinking allowed; currently only one of: -1 for unrestricted thinking budget, or 0 to disable thinking (default: -1)<br/>(env: LLAMA_ARG_THINK_BUDGET) |
 | `--chat-template JINJA_TEMPLATE` | set custom jinja chat template (default: template taken from model's metadata)<br/>if suffix/prefix are specified, template will be disabled<br/>only commonly used templates are accepted (unless --jinja is set before this flag):<br/>list of built-in templates:<br/>bailing, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek2, deepseek3, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, phi3, phi4, rwkv-world, seed_oss, smolvlm, vicuna, vicuna-orca, yandex, zephyr<br/>(env: LLAMA_ARG_CHAT_TEMPLATE) |
 | `--chat-template-file JINJA_TEMPLATE_FILE` | set custom jinja chat template file (default: template taken from model's metadata)<br/>if suffix/prefix are specified, template will be disabled<br/>only commonly used templates are accepted (unless --jinja is set before this flag):<br/>list of built-in templates:<br/>bailing, chatglm3, chatglm4, chatml, command-r, deepseek, deepseek2, deepseek3, exaone3, exaone4, falcon3, gemma, gigachat, glmedge, gpt-oss, granite, hunyuan-dense, hunyuan-moe, kimi-k2, llama2, llama2-sys, llama2-sys-bos, llama2-sys-strip, llama3, llama4, megrez, minicpm, mistral-v1, mistral-v3, mistral-v3-tekken, mistral-v7, mistral-v7-tekken, monarch, openchat, orion, phi3, phi4, rwkv-world, seed_oss, smolvlm, vicuna, vicuna-orca, yandex, zephyr<br/>(env: LLAMA_ARG_CHAT_TEMPLATE_FILE) |

tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessage.svelte

@@ -1,7 +1,6 @@
 <script lang="ts">
 	import { getDeletionInfo } from '$lib/stores/chat.svelte';
 	import { copyToClipboard } from '$lib/utils/copy';
-	import { parseThinkingContent } from '$lib/utils/thinking';
 	import ChatMessageAssistant from './ChatMessageAssistant.svelte';
 	import ChatMessageUser from './ChatMessageUser.svelte';
 
@@ -47,26 +46,13 @@
 
 	let thinkingContent = $derived.by(() => {
 		if (message.role === 'assistant') {
-			if (message.thinking) {
-				return message.thinking;
-			}
-
-			const parsed = parseThinkingContent(message.content);
+			const trimmedThinking = message.thinking?.trim();
 
-			return parsed.thinking;
+			return trimmedThinking ? trimmedThinking : null;
 		}
 		return null;
 	});
 
-	let messageContent = $derived.by(() => {
-		if (message.role === 'assistant') {
-			const parsed = parseThinkingContent(message.content);
-			return parsed.cleanContent?.replace('<|channel|>analysis', '');
-		}
-
-		return message.content?.replace('<|channel|>analysis', '');
-	});
-
 	function handleCancelEdit() {
 		isEditing = false;
 		editedContent = message.content;
@@ -165,7 +151,7 @@
 		{editedContent}
 		{isEditing}
 		{message}
-		{messageContent}
+		messageContent={message.content}
 		onCancelEdit={handleCancelEdit}
 		onConfirmDelete={handleConfirmDelete}
 		onCopy={handleCopy}

tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte

@@ -131,7 +131,11 @@
 			</div>
 		</div>
 	{:else if message.role === 'assistant'}
-		<MarkdownContent content={messageContent || ''} />
+		{#if config().disableReasoningFormat}
+			<pre class="raw-output">{messageContent || ''}</pre>
+		{:else}
+			<MarkdownContent content={messageContent || ''} />
+		{/if}
 	{:else}
 		<div class="text-sm whitespace-pre-wrap">
 			{messageContent}
@@ -203,4 +207,21 @@
 			background-position: -200% 0;
 		}
 	}
+
+	.raw-output {
+		width: 100%;
+		max-width: 48rem;
+		margin-top: 1.5rem;
+		padding: 1rem 1.25rem;
+		border-radius: 1rem;
+		background: hsl(var(--muted) / 0.3);
+		color: var(--foreground);
+		font-family:
+			ui-monospace, SFMono-Regular, 'SF Mono', Monaco, 'Cascadia Code', 'Roboto Mono', Consolas,
+			'Liberation Mono', Menlo, monospace;
+		font-size: 0.875rem;
+		line-height: 1.6;
+		white-space: pre-wrap;
+		word-break: break-word;
+	}
 </style>

tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettingsDialog.svelte

@@ -148,6 +148,12 @@
 					key: 'showThoughtInProgress',
 					label: 'Show thought in progress',
 					type: 'checkbox'
+				},
+				{
+					key: 'disableReasoningFormat',
+					label:
+						'Show raw LLM output without backend parsing and frontend Markdown rendering to inspect streaming across different models.',
+					type: 'checkbox'
 				}
 			]
 		},

tools/server/webui/src/lib/constants/settings-config.ts

@@ -6,6 +6,7 @@ export const SETTING_CONFIG_DEFAULT: Record<string, string | number | boolean> =
 	theme: 'system',
 	showTokensPerSecond: false,
 	showThoughtInProgress: false,
+	disableReasoningFormat: false,
 	keepStatsVisible: false,
 	askForTitleConfirmation: false,
 	pasteLongTextToFileLen: 2500,
@@ -76,6 +77,8 @@ export const SETTING_CONFIG_INFO: Record<string, string> = {
 	custom: 'Custom JSON parameters to send to the API. Must be valid JSON format.',
 	showTokensPerSecond: 'Display generation speed in tokens per second during streaming.',
 	showThoughtInProgress: 'Expand thought process by default when generating messages.',
+	disableReasoningFormat:
+		'Show raw LLM output without backend parsing and frontend Markdown rendering to inspect streaming across different models.',
 	keepStatsVisible: 'Keep processing statistics visible after generation finishes.',
 	askForTitleConfirmation:
 		'Ask for confirmation before automatically changing conversation title when editing the first message.',