Clear repository except README

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -1,117 +0,0 @@
-{% macro render_extra_keys(json_dict, handled_keys) %}
-    {%- if json_dict is mapping %}
-        {%- for json_key in json_dict if json_key not in handled_keys %}
-            {%- if json_dict[json_key] is string %}
-                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
-            {%- else %}
-                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
-            {%- endif %}
-        {%- endfor %}
-    {%- endif %}
-{%- endmacro %}
-
-{%- if messages[0]["role"] == "system" %}
-    {%- set system_message = messages[0]["content"] %}
-    {%- set loop_messages = messages[1:] %}
-{%- else %}
-    {%- set loop_messages = messages %}
-{%- endif %}
-
-{%- if not tools is defined %}
-    {%- set tools = [] %}
-{%- endif %}
-
-{%- if system_message is defined %}
-    {{- "<|im_start|>system\n" + system_message }}
-{%- else %}
-    {%- if tools is iterable and tools | length > 0 %}
-        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
-    {%- endif %}
-{%- endif %}
-{%- if tools is iterable and tools | length > 0 %}
-    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
-    {{- "<tools>" }}
-    {%- for tool in tools %}
-        {%- if tool.function is defined %}
-            {%- set tool = tool.function %}
-        {%- endif %}
-        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
-        {%- if tool.description is defined %}
-            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
-        {%- endif %}
-        {{- '\n<parameters>' }}
-        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
-            {%- for param_name, param_fields in tool.parameters.properties|items %}
-                {{- '\n<parameter>' }}
-                {{- '\n<name>' ~ param_name ~ '</name>' }}
-                {%- if param_fields.type is defined %}
-                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
-                {%- endif %}
-                {%- if param_fields.description is defined %}
-                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
-                {%- endif %}
-                {%- set handled_keys = ['name', 'type', 'description'] %}
-                {{- render_extra_keys(param_fields, handled_keys) }}
-                {{- '\n</parameter>' }}
-            {%- endfor %}
-        {%- endif %}
-        {%- set handled_keys = ['type', 'properties'] %}
-        {{- render_extra_keys(tool.parameters, handled_keys) }}
-        {{- '\n</parameters>' }}
-        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
-        {{- render_extra_keys(tool, handled_keys) }}
-        {{- '\n</function>' }}
-    {%- endfor %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-{%- endif %}
-{%- if system_message is defined %}
-    {{- '<|im_end|>\n' }}
-{%- else %}
-    {%- if tools is iterable and tools | length > 0 %}
-        {{- '<|im_end|>\n' }}
-    {%- endif %}
-{%- endif %}
-{%- for message in loop_messages %}
-    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
-        {{- '<|im_start|>' + message.role }}
-        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
-            {{- '\n' + message.content | trim + '\n' }}
-        {%- endif %}
-        {%- for tool_call in message.tool_calls %}
-            {%- if tool_call.function is defined %}
-                {%- set tool_call = tool_call.function %}
-            {%- endif %}
-            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-            {%- if tool_call.arguments is defined %}
-                {%- for args_name, args_value in tool_call.arguments|items %}
-                    {{- '<parameter=' + args_name + '>\n' }}
-                    {%- set args_value = args_value if args_value is string else args_value | tojson | safe %}
-                    {{- args_value }}
-                    {{- '\n</parameter>\n' }}
-                {%- endfor %}
-            {%- endif %}
-            {{- '</function>\n</tool_call>' }}
-        {%- endfor %}
-        {{- '<|im_end|>\n' }}
-    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
-    {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
-        {%- endif %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- else %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}

config.json

@@ -1,44 +0,0 @@
-{
-  "architectures": [
-    "Qwen3NextForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0,
-  "bos_token_id": 151643,
-  "decoder_sparse_step": 1,
-  "eos_token_id": 151645,
-  "full_attention_interval": 4,
-  "head_dim": 256,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 5120,
-  "linear_conv_kernel_dim": 4,
-  "linear_key_head_dim": 128,
-  "linear_num_key_heads": 16,
-  "linear_num_value_heads": 32,
-  "linear_value_head_dim": 128,
-  "max_position_embeddings": 262144,
-  "mlp_only_layers": [],
-  "model_type": "qwen3_next",
-  "moe_intermediate_size": 512,
-  "norm_topk_prob": true,
-  "num_attention_heads": 16,
-  "num_experts": 512,
-  "num_experts_per_tok": 10,
-  "num_hidden_layers": 48,
-  "num_key_value_heads": 2,
-  "output_router_logits": false,
-  "partial_rotary_factor": 0.25,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 5000000,
-  "router_aux_loss_coef": 0.001,
-  "shared_expert_intermediate_size": 512,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.57.0.dev0",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}

generation_config.json

@@ -1,13 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 1.0,
-  "top_k": 40,
-  "top_p": 0.95,
-  "transformers_version": "4.57.3"
-}

qwen3_coder_detector_sgl.py

@@ -1,474 +0,0 @@
-import ast
-import json
-import logging
-import re
-from typing import Any, List, Optional
-
-from sglang.srt.entrypoints.openai.protocol import Tool
-from sglang.srt.function_call.base_format_detector import BaseFormatDetector
-from sglang.srt.function_call.core_types import (
-    StreamingParseResult,
-    ToolCallItem,
-    _GetInfoFunc,
-)
-
-logger = logging.getLogger(__name__)
-
-
-class Qwen3CoderDetector(BaseFormatDetector):
-    def __init__(self):
-        super().__init__()
-
-        # Sentinel tokens
-        self.tool_call_start_token: str = "<tool_call>"
-        self.tool_call_end_token: str = "</tool_call>"
-        self.tool_call_prefix: str = "<function="
-        self.function_end_token: str = "</function>"
-        self.parameter_prefix: str = "<parameter="
-        self.parameter_end_token: str = "</parameter>"
-
-        # Regex for non-streaming fallback
-        self.tool_call_regex = re.compile(r"<tool_call>(.*?)</tool_call>", re.DOTALL)
-        self.tool_call_function_regex = re.compile(
-            r"<function=(.*?)</function>|<function=(.*)$", re.DOTALL
-        )
-        self.tool_call_parameter_regex = re.compile(
-            r"<parameter=(.*?)(?:</parameter>|(?=<parameter=)|(?=</function>)|$)",
-            re.DOTALL,
-        )
-
-        # Streaming State
-        # Base class already initializes _buffer, we just use it directly
-        # No need to check with hasattr - we control the lifecycle through inheritance
-
-        # Index pointing to the next character to be processed in buffer
-        self.parsed_pos: int = 0
-        # Parameter count inside the current tool being processed, used to determine whether to add comma
-        self.current_tool_param_count: int = 0
-        # Flag indicating whether current tool has already sent '{'
-        self.json_started: bool = False
-
-        # [FIX] New state flag: mark whether inside tool_call structure block
-        self.is_inside_tool_call: bool = False
-
-        # Initialize attributes that were missing in the original PR
-        self.current_func_name: Optional[str] = None
-
-    def has_tool_call(self, text: str) -> bool:
-        return self.tool_call_start_token in text
-
-    def _get_arguments_config(
-        self, func_name: str, tools: Optional[list[Tool]]
-    ) -> dict:
-        """Extract argument configuration for a function."""
-        if tools is None:
-            return {}
-        for config in tools:
-            try:
-                config_type = config.type
-                config_function = config.function
-                config_function_name = config_function.name
-            except AttributeError:
-                continue
-
-            if config_type == "function" and config_function_name == func_name:
-                try:
-                    params = config_function.parameters
-                except AttributeError:
-                    return {}
-
-                if isinstance(params, dict) and "properties" in params:
-                    return params["properties"]
-                elif isinstance(params, dict):
-                    return params
-                else:
-                    return {}
-        logger.warning(f"Tool '{func_name}' is not defined in the tools list.")
-        return {}
-
-    def _convert_param_value(
-        self, param_value: str, param_name: str, param_config: dict, func_name: str
-    ) -> Any:
-        """Convert parameter value based on its type in the schema."""
-        # Handle null value for any type
-        if param_value.lower() == "null":
-            return None
-
-        if param_name not in param_config:
-            if param_config != {}:
-                logger.warning(
-                    f"Parsed parameter '{param_name}' is not defined in the tool "
-                    f"parameters for tool '{func_name}', directly returning the string value."
-                )
-            return param_value
-
-        if (
-            isinstance(param_config[param_name], dict)
-            and "type" in param_config[param_name]
-        ):
-            param_type = str(param_config[param_name]["type"]).strip().lower()
-        else:
-            param_type = "string"
-        if param_type in ["string", "str", "text", "varchar", "char", "enum"]:
-            return param_value
-        elif (
-            param_type.startswith("int")
-            or param_type.startswith("uint")
-            or param_type.startswith("long")
-            or param_type.startswith("short")
-            or param_type.startswith("unsigned")
-        ):
-            try:
-                param_value = int(param_value)
-            except Exception:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' is not an integer in tool "
-                    f"'{func_name}', degenerating to string."
-                )
-            return param_value
-        elif param_type.startswith("num") or param_type.startswith("float"):
-            try:
-                maybe_convert = (
-                    False if "." in param_value or "e" in param_value.lower() else True
-                )
-                param_value: float = float(param_value)
-                if maybe_convert and param_value.is_integer():
-                    param_value = int(param_value)
-            except Exception:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a float in tool "
-                    f"'{func_name}', degenerating to string."
-                )
-            return param_value
-        elif param_type in ["boolean", "bool", "binary"]:
-            param_value = param_value.lower()
-            if param_value not in ["true", "false"]:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a boolean (`true` of `false`) in tool '{func_name}', degenerating to false."
-                )
-            return param_value == "true"
-        else:
-            if (
-                param_type in ["object", "array", "arr"]
-                or param_type.startswith("dict")
-                or param_type.startswith("list")
-            ):
-                try:
-                    param_value = json.loads(param_value)
-                    return param_value
-                except Exception:
-                    logger.warning(
-                        f"Parsed value '{param_value}' of parameter '{param_name}' cannot be parsed with json.loads in tool "
-                        f"'{func_name}', will try other methods to parse it."
-                    )
-            try:
-                param_value = ast.literal_eval(param_value)  # safer
-            except Exception:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' cannot be converted via Python `ast.literal_eval()` in tool '{func_name}', degenerating to string."
-                )
-            return param_value
-
-    def detect_and_parse(self, text: str, tools: List[Tool]) -> StreamingParseResult:
-        """One-shot parsing for non-streaming scenarios."""
-        if self.tool_call_start_token not in text:
-            return StreamingParseResult(normal_text=text)
-
-        calls = []
-        try:
-            # Simple cleanup of the text to find tool calls
-            # Note: This is a simplified regex approach consistent with vLLM
-            raw_tool_calls = self.tool_call_regex.findall(text)
-            if not raw_tool_calls:
-                # Fallback: maybe the whole text is inside the tag or tags are stripped
-                if self.tool_call_prefix in text:
-                    raw_tool_calls = [text]
-
-            tool_idx = 0
-            for tool_content in raw_tool_calls:
-                # Find function calls
-                funcs = self.tool_call_function_regex.findall(tool_content)
-                for func_match in funcs:
-                    func_body = func_match[0] or func_match[1]
-                    if ">" not in func_body:
-                        continue
-
-                    name_end = func_body.index(">")
-                    func_name = func_body[:name_end]
-                    params_str = func_body[name_end + 1 :]
-
-                    param_config = self._get_arguments_config(func_name, tools)
-                    parsed_params = {}
-
-                    for p_match in self.tool_call_parameter_regex.findall(params_str):
-                        if ">" not in p_match:
-                            continue
-                        p_idx = p_match.index(">")
-                        p_name = p_match[:p_idx]
-                        p_val = p_match[p_idx + 1 :]
-                        # Remove prefixing and trailing \n
-                        if p_val.startswith("\n"):
-                            p_val = p_val[1:]
-                        if p_val.endswith("\n"):
-                            p_val = p_val[:-1]
-
-                        parsed_params[p_name] = self._convert_param_value(
-                            p_val, p_name, param_config, func_name
-                        )
-
-                    calls.append(
-                        ToolCallItem(
-                            tool_index=tool_idx,
-                            name=func_name,
-                            parameters=json.dumps(parsed_params, ensure_ascii=False),
-                        )
-                    )
-                    tool_idx += 1
-
-            # Determine normal text (text before the first tool call)
-            start_idx = text.find(self.tool_call_start_token)
-            if start_idx == -1:
-                start_idx = text.find(self.tool_call_prefix)
-            normal_text = text[:start_idx] if start_idx > 0 else ""
-
-            return StreamingParseResult(normal_text=normal_text, calls=calls)
-
-        except Exception as e:
-            logger.error(f"Error in detect_and_parse: {e}")
-            return StreamingParseResult(normal_text=text)
-
-    def parse_streaming_increment(
-        self, new_text: str, tools: List[Tool]
-    ) -> StreamingParseResult:
-        """
-        Robust cursor-based streaming parser.
-        """
-        self._buffer += new_text
-
-        # Guard against empty buffer
-        if not self._buffer:
-            return StreamingParseResult()
-
-        calls = []
-        normal_text_chunks = []
-
-        while True:
-            # Working text slice
-            current_slice = self._buffer[self.parsed_pos :]
-
-            # Optimization: If almost empty, wait for more
-            if not current_slice:
-                break
-
-            # -------------------------------------------------------
-            # 1. Priority detection: check if it's the start of Tool Call
-            # -------------------------------------------------------
-            if current_slice.startswith(self.tool_call_start_token):
-                self.parsed_pos += len(self.tool_call_start_token)
-                self.is_inside_tool_call = True
-                continue
-
-            # -------------------------------------------------------
-            # 2. Function Name: <function=name>
-            # -------------------------------------------------------
-            if current_slice.startswith(self.tool_call_prefix):
-                end_angle = current_slice.find(">")
-                if end_angle != -1:
-                    func_name = current_slice[len(self.tool_call_prefix) : end_angle]
-
-                    self.current_tool_id += 1
-                    self.current_tool_name_sent = True
-                    self.current_tool_param_count = 0
-                    self.json_started = False
-                    self.current_func_name = func_name
-
-                    calls.append(
-                        ToolCallItem(
-                            tool_index=self.current_tool_id,
-                            name=func_name,
-                            parameters="",
-                        )
-                    )
-
-                    self.parsed_pos += end_angle + 1
-                    continue
-                else:
-                    # Incomplete tag
-                    break
-
-            # -------------------------------------------------------
-            # 3. Parameter: <parameter=name>value...
-            # -------------------------------------------------------
-            if current_slice.startswith(self.parameter_prefix):
-                name_end = current_slice.find(">")
-                if name_end != -1:
-                    value_start_idx = name_end + 1
-                    rest_of_slice = current_slice[value_start_idx:]
-
-                    # A parameter can end in multiple ways:
-                    # 1. [Normal] Encounter </parameter>
-                    # 2. [Abnormal] Encounter next <parameter=
-                    # 3. [Abnormal] Encounter </function>
-                    # So we need to find the smallest one as the parameter end position.
-                    cand_end_param = rest_of_slice.find(self.parameter_end_token)
-                    cand_next_param = rest_of_slice.find(self.parameter_prefix)
-                    cand_end_func = rest_of_slice.find(self.function_end_token)
-
-                    candidates = []
-                    if cand_end_param != -1:
-                        candidates.append(
-                            (cand_end_param, len(self.parameter_end_token))
-                        )
-                    if cand_next_param != -1:
-                        candidates.append((cand_next_param, 0))
-                    if cand_end_func != -1:
-                        candidates.append((cand_end_func, 0))
-
-                    if candidates:
-                        best_cand = min(candidates, key=lambda x: x[0])
-                        end_pos = best_cand[0]
-                        end_token_len = best_cand[1]
-
-                        param_name = current_slice[
-                            len(self.parameter_prefix) : name_end
-                        ]
-                        raw_value = rest_of_slice[:end_pos]
-
-                        # Cleanup value
-                        if raw_value.startswith("\n"):
-                            raw_value = raw_value[1:]
-                        if raw_value.endswith("\n"):
-                            raw_value = raw_value[:-1]
-
-                        # JSON Construction
-                        if not self.json_started:
-                            calls.append(
-                                ToolCallItem(
-                                    tool_index=self.current_tool_id, parameters="{"
-                                )
-                            )
-                            self.json_started = True
-
-                        param_config = self._get_arguments_config(
-                            self.current_func_name, tools
-                        )
-                        converted_val = self._convert_param_value(
-                            raw_value, param_name, param_config, self.current_func_name
-                        )
-
-                        # Construct JSON fragment: "key": value
-                        # Note: We must be careful with json.dumps to ensure valid JSON streaming
-                        json_key_val = f"{json.dumps(param_name)}: {json.dumps(converted_val, ensure_ascii=False)}"
-
-                        if self.current_tool_param_count > 0:
-                            fragment = f", {json_key_val}"
-                        else:
-                            fragment = json_key_val
-
-                        calls.append(
-                            ToolCallItem(
-                                tool_index=self.current_tool_id, parameters=fragment
-                            )
-                        )
-                        self.current_tool_param_count += 1
-
-                        # Advance cursor
-                        total_len = (name_end + 1) + end_pos + end_token_len
-                        self.parsed_pos += total_len
-                        continue
-
-                # Incomplete parameter tag or value
-                break
-
-            # -------------------------------------------------------
-            # 4. Function End: </function>
-            # -------------------------------------------------------
-            if current_slice.startswith(self.function_end_token):
-                if not self.json_started:
-                    calls.append(
-                        ToolCallItem(tool_index=self.current_tool_id, parameters="{")
-                    )
-                    self.json_started = True
-
-                calls.append(
-                    ToolCallItem(tool_index=self.current_tool_id, parameters="}")
-                )
-                self.parsed_pos += len(self.function_end_token)
-                self.current_func_name = None
-                continue
-
-            # -------------------------------------------------------
-            # 5. Tool Call End: </tool_call>
-            # -------------------------------------------------------
-            if current_slice.startswith(self.tool_call_end_token):
-                self.parsed_pos += len(self.tool_call_end_token)
-                self.is_inside_tool_call = False  # [FIX] Exit tool call region
-                continue
-
-            # -------------------------------------------------------
-            # 6. Handling content / whitespace / normal text
-            # -------------------------------------------------------
-            # If current position is not the start of a tag (i.e., doesn't start with <), it might be plain text,
-            # or a newline between two tags.
-            # But we need to be careful not to output truncated tags like "<fun" as text.
-
-            next_open_angle = current_slice.find("<")
-
-            if next_open_angle == -1:
-                # This entire segment is plain text
-                if not self.is_inside_tool_call:
-                    normal_text_chunks.append(current_slice)
-                # [FIX] If inside tool call, discard this text (usually \n), don't append
-                self.parsed_pos += len(current_slice)
-                continue
-
-            elif next_open_angle == 0:
-                # Looks like a Tag, but doesn't match any known Tag above
-
-                possible_tags = [
-                    self.tool_call_start_token,
-                    self.tool_call_end_token,
-                    self.tool_call_prefix,
-                    self.function_end_token,
-                    self.parameter_prefix,
-                    self.parameter_end_token,
-                ]
-
-                is_potential_tag = False
-                for tag in possible_tags:
-                    if tag.startswith(current_slice):
-                        is_potential_tag = True
-                        break
-
-                if is_potential_tag:
-                    break  # Wait for more
-                else:
-                    # Just a plain '<' symbol
-                    if not self.is_inside_tool_call:
-                        normal_text_chunks.append("<")
-                    self.parsed_pos += 1
-                    continue
-
-            else:
-                # '<' is in the middle
-                text_segment = current_slice[:next_open_angle]
-                if not self.is_inside_tool_call:
-                    normal_text_chunks.append(text_segment)
-                # [FIX] If inside tool call, discard whitespace/text before Tag
-                self.parsed_pos += next_open_angle
-                continue
-
-        # Memory Cleanup: Slice the buffer
-        # Keep unparsed part, discard parsed part
-        if self.parsed_pos > 0:
-            self._buffer = self._buffer[self.parsed_pos :]
-            self.parsed_pos = 0
-
-        normal_text = "".join(normal_text_chunks) if normal_text_chunks else ""
-        return StreamingParseResult(calls=calls, normal_text=normal_text)
-
-    def supports_structural_tag(self) -> bool:
-        return False
-
-    def structure_info(self) -> _GetInfoFunc:
-        raise NotImplementedError

qwen3coder_tool_parser_vllm.py

@@ -1,690 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-import ast
-import json
-import uuid
-from collections.abc import Sequence
-from typing import Any, List, Optional, Union
-
-import regex as re
-
-from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
-                                              ChatCompletionToolsParam,
-                                              DeltaFunctionCall, DeltaMessage,
-                                              DeltaToolCall,
-                                              ExtractedToolCallInformation,
-                                              FunctionCall, ToolCall)
-from vllm.entrypoints.openai.tool_parsers.abstract_tool_parser import (
-    ToolParser, ToolParserManager)
-from vllm.logger import init_logger
-from vllm.transformers_utils.tokenizer import AnyTokenizer
-
-logger = init_logger(__name__)
-
-
-@ToolParserManager.register_module("qwen3_coder")
-class Qwen3CoderToolParser(ToolParser):
-
-    def __init__(self, tokenizer: AnyTokenizer):
-        super().__init__(tokenizer)
-
-        self.current_tool_name_sent: bool = False
-        self.prev_tool_call_arr: list[dict] = []
-        self.current_tool_id: int = -1
-        self.streamed_args_for_tool: list[str] = []
-
-        # Sentinel tokens for streaming mode
-        self.tool_call_start_token: str = "<tool_call>"
-        self.tool_call_end_token: str = "</tool_call>"
-        self.tool_call_prefix: str = "<function="
-        self.function_end_token: str = "</function>"
-        self.parameter_prefix: str = "<parameter="
-        self.parameter_end_token: str = "</parameter>"
-        self.is_tool_call_started: bool = False
-        self.failed_count: int = 0
-
-        # Enhanced streaming state - reset for each new message
-        self._reset_streaming_state()
-
-        # Regex patterns
-        self.tool_call_complete_regex = re.compile(
-            r"<tool_call>(.*?)</tool_call>", re.DOTALL)
-        self.tool_call_regex = re.compile(
-            r"<tool_call>(.*?)</tool_call>|<tool_call>(.*?)$", re.DOTALL)
-        self.tool_call_function_regex = re.compile(
-            r"<function=(.*?)</function>|<function=(.*)$", re.DOTALL)
-        self.tool_call_parameter_regex = re.compile(
-            r"<parameter=(.*?)(?:</parameter>|(?=<parameter=)|(?=</function>)|$)",
-            re.DOTALL)
-
-        if not self.model_tokenizer:
-            raise ValueError(
-                "The model tokenizer must be passed to the ToolParser "
-                "constructor during construction.")
-
-        self.tool_call_start_token_id = self.vocab.get(
-            self.tool_call_start_token)
-        self.tool_call_end_token_id = self.vocab.get(self.tool_call_end_token)
-
-        if self.tool_call_start_token_id is None or self.tool_call_end_token_id is None:
-            raise RuntimeError(
-                "Qwen3 XML Tool parser could not locate tool call start/end "
-                "tokens in the tokenizer!")
-
-        logger.info(
-            f"vLLM Successfully import tool parser {self.__class__.__name__} !"
-        )
-
-    def _generate_tool_call_id(self) -> str:
-        """Generate a unique tool call ID."""
-        return f"call_{uuid.uuid4().hex[:24]}"
-
-    def _reset_streaming_state(self):
-        """Reset all streaming state."""
-        self.current_tool_index = 0
-        self.is_tool_call_started = False
-        self.header_sent = False
-        self.current_tool_id = None
-        self.current_function_name = None
-        self.current_param_name = None
-        self.current_param_value = ""
-        self.param_count = 0
-        self.in_param = False
-        self.in_function = False
-        self.accumulated_text = ""
-        self.json_started = False
-        self.json_closed = False
-        # Store accumulated parameters for type conversion
-        self.accumulated_params = {}
-        self.streaming_request = None
-
-    def _get_arguments_config(
-            self, func_name: str,
-            tools: Optional[list[ChatCompletionToolsParam]]) -> dict:
-        """Extract argument configuration for a function."""
-        if tools is None:
-            return {}
-        for config in tools:
-            if not hasattr(config, "type") or not (hasattr(
-                    config, "function") and hasattr(config.function, "name")):
-                continue
-            if config.type == "function" and config.function.name == func_name:
-                if not hasattr(config.function, "parameters"):
-                    return {}
-                params = config.function.parameters
-                if isinstance(params, dict) and "properties" in params:
-                    return params["properties"]
-                elif isinstance(params, dict):
-                    return params
-                else:
-                    return {}
-        logger.warning(f"Tool '{func_name}' is not defined in the tools list.")
-        return {}
-
-    def _convert_param_value(self, param_value: str, param_name: str,
-                             param_config: dict, func_name: str) -> Any:
-        """Convert parameter value based on its type in the schema."""
-        # Handle null value for any type
-        if param_value.lower() == "null":
-            return None
-
-        if param_name not in param_config:
-            if param_config != {}:
-                logger.warning(
-                    f"Parsed parameter '{param_name}' is not defined in the tool "
-                    f"parameters for tool '{func_name}', directly returning the string value."
-                )
-            return param_value
-
-        if isinstance(param_config[param_name],
-                      dict) and "type" in param_config[param_name]:
-            param_type = str(param_config[param_name]["type"]).strip().lower()
-        else:
-            param_type = "string"
-        if param_type in ["string", "str", "text", "varchar", "char", "enum"]:
-            return param_value
-        elif param_type.startswith("int") or param_type.startswith(
-                "uint") or param_type.startswith(
-                    "long") or param_type.startswith(
-                        "short") or param_type.startswith("unsigned"):
-            try:
-                param_value = int(param_value)
-            except:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' is not an integer in tool "
-                    f"'{func_name}', degenerating to string.")
-            return param_value
-        elif param_type.startswith("num") or param_type.startswith("float"):
-            try:
-                maybe_convert = False if "." in param_value or "e" in param_value.lower() else True
-                param_value: float = float(param_value)
-                if maybe_convert and param_value.is_integer():
-                    param_value = int(param_value)
-            except:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a float in tool "
-                    f"'{func_name}', degenerating to string.")
-            return param_value
-        elif param_type in ["boolean", "bool", "binary"]:
-            param_value = param_value.lower()
-            if param_value not in ["true", "false"]:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' is not a boolean (`true` of `false`) in tool '{func_name}', degenerating to false."
-                )
-            return param_value == "true"
-        else:
-            if param_type in ["object", "array", "arr"
-                              ] or param_type.startswith(
-                                  "dict") or param_type.startswith("list"):
-                try:
-                    param_value = json.loads(param_value)
-                    return param_value
-                except:
-                    logger.warning(
-                        f"Parsed value '{param_value}' of parameter '{param_name}' cannot be parsed with json.loads in tool "
-                        f"'{func_name}', will try other methods to parse it.")
-            try:
-                param_value = ast.literal_eval(param_value)  # safer
-            except:
-                logger.warning(
-                    f"Parsed value '{param_value}' of parameter '{param_name}' cannot be converted via Python `ast.literal_eval()` in tool '{func_name}', degenerating to string."
-                )
-            return param_value
-
-    def _parse_xml_function_call(
-            self, function_call_str: str,
-            tools: Optional[list[ChatCompletionToolsParam]]
-    ) -> Optional[ToolCall]:
-
-        # Extract function name
-        end_index = function_call_str.index(">")
-        function_name = function_call_str[:end_index]
-        param_config = self._get_arguments_config(function_name, tools)
-        parameters = function_call_str[end_index + 1:]
-        param_dict = {}
-        for match_text in self.tool_call_parameter_regex.findall(parameters):
-            idx = match_text.index(">")
-            param_name = match_text[:idx]
-            param_value = str(match_text[idx + 1:])
-            # Remove prefix and trailing \n
-            if param_value.startswith("\n"):
-                param_value = param_value[1:]
-            if param_value.endswith("\n"):
-                param_value = param_value[:-1]
-
-            param_dict[param_name] = self._convert_param_value(
-                param_value, param_name, param_config, function_name)
-        return ToolCall(
-            type="function",
-            function=FunctionCall(name=function_name,
-                                  arguments=json.dumps(param_dict,
-                                                       ensure_ascii=False)),
-        )
-
-    def _get_function_calls(self, model_output: str) -> List[str]:
-        # Find all tool calls
-        matched_ranges = self.tool_call_regex.findall(model_output)
-        raw_tool_calls = [
-            match[0] if match[0] else match[1] for match in matched_ranges
-        ]
-
-        # Back-off strategy if no tool_call tags found
-        if len(raw_tool_calls) == 0:
-            raw_tool_calls = [model_output]
-
-        raw_function_calls = []
-        for tool_call in raw_tool_calls:
-            raw_function_calls.extend(
-                self.tool_call_function_regex.findall(tool_call))
-
-        function_calls = [
-            match[0] if match[0] else match[1] for match in raw_function_calls
-        ]
-        return function_calls
-
-    def extract_tool_calls(
-        self,
-        model_output: str,
-        request: ChatCompletionRequest,
-    ) -> ExtractedToolCallInformation:
-        # Quick check to avoid unnecessary processing
-        if self.tool_call_prefix not in model_output:
-            return ExtractedToolCallInformation(tools_called=False,
-                                                tool_calls=[],
-                                                content=model_output)
-
-        try:
-            function_calls = self._get_function_calls(model_output)
-            if len(function_calls) == 0:
-                return ExtractedToolCallInformation(tools_called=False,
-                                                    tool_calls=[],
-                                                    content=model_output)
-
-            tool_calls = [
-                self._parse_xml_function_call(function_call_str, request.tools)
-                for function_call_str in function_calls
-            ]
-
-            # Populate prev_tool_call_arr for serving layer to set finish_reason
-            self.prev_tool_call_arr.clear()  # Clear previous calls
-            for tool_call in tool_calls:
-                if tool_call:
-                    self.prev_tool_call_arr.append({
-                        "name":
-                        tool_call.function.name,
-                        "arguments":
-                        tool_call.function.arguments,
-                    })
-
-            # Extract content before tool calls
-            content_index = model_output.find(self.tool_call_start_token)
-            content_index = content_index if content_index >= 0 else model_output.find(
-                self.tool_call_prefix)
-            content = model_output[:content_index]  # .rstrip()
-
-            return ExtractedToolCallInformation(
-                tools_called=(len(tool_calls) > 0),
-                tool_calls=tool_calls,
-                content=content if content else None,
-            )
-
-        except Exception:
-            logger.exception("Error in extracting tool call from response.")
-            return ExtractedToolCallInformation(tools_called=False,
-                                                tool_calls=[],
-                                                content=model_output)
-
-    def extract_tool_calls_streaming(
-        self,
-        previous_text: str,
-        current_text: str,
-        delta_text: str,
-        previous_token_ids: Sequence[int],
-        current_token_ids: Sequence[int],
-        delta_token_ids: Sequence[int],
-        request: ChatCompletionRequest,
-    ) -> Union[DeltaMessage, None]:
-        # Store request for type conversion
-        if not previous_text:
-            self._reset_streaming_state()
-            self.streaming_request = request
-
-        # If no delta text, return None unless it's an EOS token after tool calls
-        if not delta_text:
-            # Check if this is an EOS token after all tool calls are complete
-            # We check for tool calls in the text even if is_tool_call_started is False
-            # because it might have been reset after processing all tools
-            if delta_token_ids and self.tool_call_end_token_id not in delta_token_ids:
-                # Count complete tool calls
-                complete_calls = len(
-                    self.tool_call_complete_regex.findall(current_text))
-
-                # If we have completed tool calls and populated prev_tool_call_arr
-                if complete_calls > 0 and len(self.prev_tool_call_arr) > 0:
-                    # Check if all tool calls are closed
-                    open_calls = current_text.count(
-                        self.tool_call_start_token) - current_text.count(
-                            self.tool_call_end_token)
-                    if open_calls == 0:
-                        # Return empty delta message to allow finish_reason processing
-                        return DeltaMessage(content="")
-                elif not self.is_tool_call_started and current_text:
-                    # This is a regular content response that's now complete
-                    return DeltaMessage(content="")
-            return None
-
-        # Update accumulated text
-        self.accumulated_text = current_text
-
-        # Check if we need to advance to next tool
-        if self.json_closed and not self.in_function:
-            # Check if this tool call has ended
-            tool_ends = current_text.count(self.tool_call_end_token)
-            if tool_ends > self.current_tool_index:
-                # This tool has ended, advance to next
-                self.current_tool_index += 1
-                self.header_sent = False
-                self.param_count = 0
-                self.json_started = False
-                self.json_closed = False
-                self.accumulated_params = {}
-
-                # Check if there are more tool calls
-                tool_starts = current_text.count(self.tool_call_start_token)
-                if self.current_tool_index >= tool_starts:
-                    # No more tool calls
-                    self.is_tool_call_started = False
-                # Continue processing next tool
-                return None
-
-        # Handle normal content before tool calls
-        if not self.is_tool_call_started:
-            # Check if tool call is starting
-            if self.tool_call_start_token_id in delta_token_ids or self.tool_call_start_token in delta_text:
-                self.is_tool_call_started = True
-                # Return any content before the tool call
-                if self.tool_call_start_token in delta_text:
-                    content_before = delta_text[:delta_text.index(
-                        self.tool_call_start_token)]
-                    if content_before:
-                        return DeltaMessage(content=content_before)
-                return None
-            else:
-                # Check if we're between tool calls - skip whitespace
-                if current_text.rstrip().endswith(self.tool_call_end_token):
-                    # We just ended a tool call, skip whitespace
-                    if delta_text.strip() == "":
-                        return None
-                # Normal content, no tool call
-                return DeltaMessage(content=delta_text)
-
-        # Check if we're between tool calls (waiting for next one)
-        # Count tool calls we've seen vs processed
-        tool_starts_count = current_text.count(self.tool_call_start_token)
-        if self.current_tool_index >= tool_starts_count:
-            # We're past all tool calls, shouldn't be here
-            return None
-
-        # We're in a tool call, find the current tool call portion
-        # Need to find the correct tool call based on current_tool_index
-        tool_starts = []
-        idx = 0
-        while True:
-            idx = current_text.find(self.tool_call_start_token, idx)
-            if idx == -1:
-                break
-            tool_starts.append(idx)
-            idx += len(self.tool_call_start_token)
-
-        if self.current_tool_index >= len(tool_starts):
-            # No more tool calls to process yet
-            return None
-
-        tool_start_idx = tool_starts[self.current_tool_index]
-        # Find where this tool call ends (or current position if not ended yet)
-        tool_end_idx = current_text.find(self.tool_call_end_token,
-                                         tool_start_idx)
-        if tool_end_idx == -1:
-            tool_text = current_text[tool_start_idx:]
-        else:
-            tool_text = current_text[tool_start_idx:tool_end_idx +
-                                     len(self.tool_call_end_token)]
-
-        # Looking for function header
-        if not self.header_sent:
-            if self.tool_call_prefix in tool_text:
-                func_start = tool_text.find(self.tool_call_prefix) + len(
-                    self.tool_call_prefix)
-                func_end = tool_text.find(">", func_start)
-
-                if func_end != -1:
-                    # Found complete function name
-                    self.current_function_name = tool_text[func_start:func_end]
-                    self.current_tool_id = self._generate_tool_call_id()
-                    self.header_sent = True
-                    self.in_function = True
-
-                    # IMPORTANT: Add to prev_tool_call_arr immediately when we detect a tool call
-                    # This ensures finish_reason="tool_calls" even if parsing isn't complete
-                    already_added = any(
-                        tool.get("name") == self.current_function_name
-                        for tool in self.prev_tool_call_arr)
-                    if not already_added:
-                        self.prev_tool_call_arr.append({
-                            "name": self.current_function_name,
-                            "arguments":
-                            "{}",  # Placeholder, will be updated later
-                        })
-
-                    # Send header with function info
-                    return DeltaMessage(tool_calls=[
-                        DeltaToolCall(
-                            index=self.current_tool_index,
-                            id=self.current_tool_id,
-                            function=DeltaFunctionCall(
-                                name=self.current_function_name, arguments=""),
-                            type="function",
-                        )
-                    ])
-            return None
-
-        # We've sent header, now handle function body
-        if self.in_function:
-            # Send opening brace if not sent yet
-            if not self.json_started and self.parameter_prefix not in delta_text:
-                self.json_started = True
-                return DeltaMessage(tool_calls=[
-                    DeltaToolCall(
-                        index=self.current_tool_index,
-                        function=DeltaFunctionCall(arguments="{"),
-                    )
-                ])
-
-            # Make sure json_started is set if we're processing parameters
-            if not self.json_started:
-                self.json_started = True
-
-            # Check for function end in accumulated text
-            if not self.json_closed and self.function_end_token in tool_text:
-                # Close JSON
-                self.json_closed = True
-
-                # Extract the complete tool call to update prev_tool_call_arr with final arguments
-                # Find the function content
-                func_start = tool_text.find(self.tool_call_prefix) + len(
-                    self.tool_call_prefix)
-                func_content_end = tool_text.find(self.function_end_token,
-                                                  func_start)
-                if func_content_end != -1:
-                    func_content = tool_text[func_start:func_content_end]
-                    # Parse to get the complete arguments
-                    try:
-                        parsed_tool = self._parse_xml_function_call(
-                            func_content, self.streaming_request.tools
-                            if self.streaming_request else None)
-                        if parsed_tool:
-                            # Update existing entry in prev_tool_call_arr with complete arguments
-                            for i, tool in enumerate(self.prev_tool_call_arr):
-                                if tool.get(
-                                        "name") == parsed_tool.function.name:
-                                    self.prev_tool_call_arr[i][
-                                        "arguments"] = parsed_tool.function.arguments
-                                    break
-                    except Exception:
-                        pass  # Ignore parsing errors during streaming
-
-                result = DeltaMessage(tool_calls=[
-                    DeltaToolCall(
-                        index=self.current_tool_index,
-                        function=DeltaFunctionCall(arguments="}"),
-                    )
-                ])
-
-                # Reset state for next tool
-                self.in_function = False
-                self.json_closed = True
-                self.accumulated_params = {}
-
-                return result
-
-            # Look for parameters
-            # Find all parameter starts
-            param_starts = []
-            idx = 0
-            while True:
-                idx = tool_text.find(self.parameter_prefix, idx)
-                if idx == -1:
-                    break
-                param_starts.append(idx)
-                idx += len(self.parameter_prefix)
-
-            # Check if we should start a new parameter
-            if not self.in_param and self.param_count < len(param_starts):
-
-                if len(param_starts) > self.param_count:
-                    # Process the next parameter
-                    param_idx = param_starts[self.param_count]
-                    param_start = param_idx + len(self.parameter_prefix)
-                    remaining = tool_text[param_start:]
-
-                    if ">" in remaining:
-                        # We have the complete parameter name
-                        name_end = remaining.find(">")
-                        self.current_param_name = remaining[:name_end]
-
-                        # Find the parameter value
-                        value_start = param_start + name_end + 1
-                        value_text = tool_text[value_start:]
-                        if value_text.startswith("\n"):
-                            value_text = value_text[1:]
-
-                        # Find where this parameter ends
-                        param_end_idx = value_text.find(
-                            self.parameter_end_token)
-                        if param_end_idx == -1:
-                            # No closing tag, look for next parameter or function end
-                            next_param_idx = value_text.find(
-                                self.parameter_prefix)
-                            func_end_idx = value_text.find(
-                                self.function_end_token)
-
-                            if next_param_idx != -1 and (func_end_idx == -1
-                                                         or next_param_idx
-                                                         < func_end_idx):
-                                param_end_idx = next_param_idx
-                            elif func_end_idx != -1:
-                                param_end_idx = func_end_idx
-                            else:
-                                # Neither found, check if tool call is complete
-                                if self.tool_call_end_token in tool_text:
-                                    # Tool call is complete, so parameter must be complete too
-                                    # Use all remaining text before function end as value
-                                    param_end_idx = len(value_text)
-                                else:
-                                    # Still streaming, wait for more content
-                                    return None
-
-                        if param_end_idx != -1:
-                            # Complete parameter found
-                            param_value = value_text[:param_end_idx]
-                            if param_value.endswith("\n"):
-                                param_value = param_value[:-1]
-
-                            # Store raw value for later processing
-                            self.accumulated_params[
-                                self.current_param_name] = param_value
-
-                            # Get parameter configuration for type conversion
-                            param_config = self._get_arguments_config(
-                                self.current_function_name,
-                                self.streaming_request.tools
-                                if self.streaming_request else None)
-
-                            # Convert the parameter value to the appropriate type
-                            converted_value = self._convert_param_value(
-                                param_value, self.current_param_name,
-                                param_config, self.current_function_name)
-
-                            # Build JSON fragment based on the converted type
-                            # Use json.dumps to properly serialize the value
-                            serialized_value = json.dumps(converted_value,
-                                                          ensure_ascii=False)
-
-                            if self.param_count == 0:
-                                json_fragment = f'"{self.current_param_name}": {serialized_value}'
-                            else:
-                                json_fragment = f', "{self.current_param_name}": {serialized_value}'
-
-                            self.param_count += 1
-
-                            return DeltaMessage(tool_calls=[
-                                DeltaToolCall(
-                                    index=self.current_tool_index,
-                                    function=DeltaFunctionCall(
-                                        arguments=json_fragment),
-                                )
-                            ])
-
-            # Continue parameter value - Not used in the current implementation
-            # since we process complete parameters above
-            if self.in_param:
-                if self.parameter_end_token in delta_text:
-                    # End of parameter
-                    end_idx = delta_text.find(self.parameter_end_token)
-                    value_chunk = delta_text[:end_idx]
-
-                    # Skip past > if at start
-                    if not self.current_param_value and ">" in value_chunk:
-                        gt_idx = value_chunk.find(">")
-                        value_chunk = value_chunk[gt_idx + 1:]
-
-                    if not self.current_param_value and value_chunk.startswith(
-                            "\n"):
-                        value_chunk = value_chunk[1:]
-
-                    # Store complete value
-                    full_value = self.current_param_value + value_chunk
-                    self.accumulated_params[
-                        self.current_param_name] = full_value
-
-                    # Get parameter configuration for type conversion
-                    param_config = self._get_arguments_config(
-                        self.current_function_name,
-                        self.streaming_request.tools
-                        if self.streaming_request else None)
-
-                    # Convert the parameter value to the appropriate type
-                    converted_value = self._convert_param_value(
-                        full_value, self.current_param_name, param_config,
-                        self.current_function_name)
-
-                    # Serialize the converted value
-                    serialized_value = json.dumps(converted_value,
-                                                  ensure_ascii=False)
-
-                    # Since we've been streaming the quoted version, we need to close it properly
-                    # This is complex - for now just complete the value
-                    self.in_param = False
-                    self.current_param_value = ""
-
-                    # Just close the current parameter string
-                    return DeltaMessage(tool_calls=[
-                        DeltaToolCall(
-                            index=self.current_tool_index,
-                            function=DeltaFunctionCall(
-                                arguments='"'),  # Close the string quote
-                        )
-                    ])
-                else:
-                    # Continue accumulating value
-                    value_chunk = delta_text
-
-                    # Handle first chunk after param name
-                    if not self.current_param_value and ">" in value_chunk:
-                        gt_idx = value_chunk.find(">")
-                        value_chunk = value_chunk[gt_idx + 1:]
-
-                    if not self.current_param_value and value_chunk.startswith(
-                            "\n"):
-                        value_chunk = value_chunk[1:]
-
-                    if value_chunk:
-                        # Stream the escaped delta
-                        prev_escaped = json.dumps(
-                            self.current_param_value, ensure_ascii=False
-                        )[1:-1] if self.current_param_value else ""
-                        self.current_param_value += value_chunk
-                        full_escaped = json.dumps(self.current_param_value,
-                                                  ensure_ascii=False)[1:-1]
-                        delta_escaped = full_escaped[len(prev_escaped):]
-
-                        if delta_escaped:
-                            return DeltaMessage(tool_calls=[
-                                DeltaToolCall(
-                                    index=self.current_tool_index,
-                                    function=DeltaFunctionCall(
-                                        arguments=delta_escaped),
-                                )
-                            ])
-
-        return None

tokenizer_config.json

@@ -1,239 +0,0 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151665": {
-      "content": "<tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151666": {
-      "content": "</tool_response>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151667": {
-      "content": "<think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151668": {
-      "content": "</think>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{% macro render_extra_keys(json_dict, handled_keys) %}\n    {%- if json_dict is mapping %}\n        {%- for json_key in json_dict if json_key not in handled_keys %}\n            {%- if json_dict[json_key] is string %}\n                {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}\n            {%- else %}\n                {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endmacro %}\n\n{%- if messages[0][\"role\"] == \"system\" %}\n    {%- set system_message = messages[0][\"content\"] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{%- if not tools is defined %}\n    {%- set tools = [] %}\n{%- endif %}\n\n{%- if system_message is defined %}\n    {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n    {%- if tools is iterable and tools | length > 0 %}\n        {{- \"<|im_start|>system\\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks.\" }}\n    {%- endif %}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n    {{- \"\\n\\n# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n    {{- \"<tools>\" }}\n    {%- for tool in tools %}\n        {%- if tool.function is defined %}\n            {%- set tool = tool.function %}\n        {%- endif %}\n        {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n        {%- if tool.description is defined %}\n            {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n        {%- endif %}\n        {{- '\\n<parameters>' }}\n        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}\n            {%- for param_name, param_fields in tool.parameters.properties|items %}\n                {{- '\\n<parameter>' }}\n                {{- '\\n<name>' ~ param_name ~ '</name>' }}\n                {%- if param_fields.type is defined %}\n                    {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n                {%- endif %}\n                {%- if param_fields.description is defined %}\n                    {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n                {%- endif %}\n                {%- set handled_keys = ['name', 'type', 'description'] %}\n                {{- render_extra_keys(param_fields, handled_keys) }}\n                {{- '\\n</parameter>' }}\n            {%- endfor %}\n        {%- endif %}\n        {%- set handled_keys = ['type', 'properties'] %}\n        {{- render_extra_keys(tool.parameters, handled_keys) }}\n        {{- '\\n</parameters>' }}\n        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}\n        {{- render_extra_keys(tool, handled_keys) }}\n        {{- '\\n</function>' }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n{%- endif %}\n{%- if system_message is defined %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if tools is iterable and tools | length > 0 %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in loop_messages %}\n    {%- if message.role == \"assistant\" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}\n            {{- '\\n' + message.content | trim + '\\n' }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n            {%- if tool_call.arguments is defined %}\n                {%- for args_name, args_value in tool_call.arguments|items %}\n                    {{- '<parameter=' + args_name + '>\\n' }}\n                    {%- set args_value = args_value if args_value is string else args_value | tojson | safe %}\n                    {{- args_value }}\n                    {{- '\\n</parameter>\\n' }}\n                {%- endfor %}\n            {%- endif %}\n            {{- '</function>\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"user\" or message.role == \"system\" or message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 1048576,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "add_bos_token": false
-}

veriloop-coder-00001-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c89934c258f0f5acd3ce2dbf311fa3d2ff41751dda53f89b3597d66074e3377f
-size 3999619256

veriloop-coder-00002-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dc31a76af8f4f6167c5ee5c00af334ce23194e21e1f60ca2ce7d5bd6b19542a1
-size 3999841784

veriloop-coder-00003-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b02ecb9cfcb7a9e0cda77f9fc8f0e235aea0097b4809099272b36cb56855a4a
-size 3999515584

veriloop-coder-00004-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b4b0da4cb9394fa08ac752f9bda9008b4e6f5b8de7e5291e8704482daff8ccb
-size 7999685256

veriloop-coder-00005-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:60350080c02054d48a6fd17b325abafd25fa0b86657d37014c75df484c23c7c8
-size 3999853216

veriloop-coder-00006-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa7cded8114dfd22e7bdc43d48b8a32503a66ef1c8d9a6c89f517a04fb4e43f9
-size 3999841912

veriloop-coder-00007-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:55cbd3e60fb0a1a055043ae996dbce063aac1591d68f149799aca582ef6ea811
-size 3999842000

veriloop-coder-00008-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c47f55654ad72a8ac749a6e0fd2c942a8e2d40c3e38d6e4a9d93dc396830f66
-size 7999362056

veriloop-coder-00009-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f8ef5fe9f9355d5ad6ed8e880a08baf6a7b06c7a3a05f44456b9c8b7f6f4d767
-size 4000181296

veriloop-coder-00010-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d973d1b1605fda5ccd5de4a0ac8d3afc192f43fe6f22ffc20b2eab31035bc41d
-size 3999843880

veriloop-coder-00011-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:167b69cb389dc18cfbf7eb3a106ad8e2d705552c0a71db7d92b44a8ebc1d2195
-size 3999517472

veriloop-coder-00012-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e47317518854d30f4d3162a12b19fee0c1b2b39a75d48e483e10eb6c596c65e
-size 8000026728

veriloop-coder-00013-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5e7c3bcdb221eb4a2bb7df03e0d8c56fa7a06a448217d75b63dc077f1627cfc
-size 3999517256

veriloop-coder-00014-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e69d4dde8ea6ea8deac8afb435c6de896750a5acc94aae2943991a00afb8644
-size 3999843880

veriloop-coder-00015-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:737892dff0624b51a7bd06255d7c0e3e97d29ab539af3d43f5a648b0dd4456ab
-size 3999843880

veriloop-coder-00016-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82d48d3ba46f7a991f71de8a8913754821568b96ee362c4fe849456425b852bb
-size 7999700184

veriloop-coder-00017-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c53b02373a5a194fd8f7a9165b4535105b1b6dbbafff582bdc3df5ea10c0f5c
-size 3999843792

veriloop-coder-00018-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1f187aa4808d54963bf45cfbe5010f72f3c3d81b6584bceb69fddef82e239e9
-size 3999843880

veriloop-coder-00019-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5286e5b13a884128b9708d2292071c3323dbba8cca78c4af353e8cac9f85d6ec
-size 3999517464

veriloop-coder-00020-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:172a1d0591c51ae14663fe7b25b8b637c17e3e55c136458a6bf25a4a260bb7bc
-size 8000026560

veriloop-coder-00021-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:709d90cf4589d741c3b8937042322d4c309d78eba1f303b7b284756b7f8fa71f
-size 3999517472

veriloop-coder-00022-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:01c374c13cef0c83ba569bbc0e1599da0ccc49e7e6d078c9bf24fff66ddef933
-size 3999843880

veriloop-coder-00023-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:314f820942b2bf4e2934fda07346ad5020132d147d4d182084718c7de3ed70a7
-size 3999843984

veriloop-coder-00024-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c3f249fa9c68669ed1f0a54b3e0bb7020612919b7a0ff13d0084e5cfbc1bbefb
-size 7999700048

veriloop-coder-00025-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:686af3d1671569a4b4412bbad8ef78ba915332f4ae13e6a58d68887c0c2ab3a1
-size 3999843880

veriloop-coder-00026-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb3852b6b899bacc68803b2ba2fa04d955bb34b94ddecb8f72a899bb5eb7d155
-size 3999843880

veriloop-coder-00027-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76e735fe4b0974e99754a0cc6b90e17a38066cfd2889415e523638c8dcc94394
-size 3999517688

veriloop-coder-00028-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b8d90f301aa8e63e6522efc7712107497730e99da12b4a5cd2714ea92ffb6709
-size 8000026336

veriloop-coder-00029-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5e09b49eab76341aa5577852cda15f9841ad28bd2f94f141e5ab41a5658aaee5
-size 3999517472

veriloop-coder-00030-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:19355aff4f4e0c6b3cd737360fced4c5c70ac3508d41baf1c08c821d21479851
-size 3999843872

veriloop-coder-00031-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e7deeba55a043cb909602eda1a2f90cb07f0a607b1f7ab237ff49f7874fb75be
-size 3999844264

veriloop-coder-00032-of-00032.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:883708543caeaf44fe9fd6445f77c6e115c1a9b15c3923d2c598997f2d629ec8
-size 7365428440