The architecture has been updated

This commit is contained in:
Skyber_2 2026-03-31 23:31:36 +03:00
parent 805f7a017e
commit a01257ead9
1119 changed files with 226 additions and 352 deletions

View file

@ -0,0 +1,120 @@
"""
Tool Call Parser Registry
Client-side parsers that extract structured tool_calls from raw model output text.
Used in Phase 2 (VLLM server type) where ManagedServer's /generate endpoint returns
raw text without tool call parsing.
Each parser is a standalone reimplementation of the corresponding VLLM parser's
non-streaming extract_tool_calls() logic. No VLLM dependency -- only standard library
(re, json, uuid) and openai types.
Usage:
from environments.tool_call_parsers import get_parser
parser = get_parser("hermes")
content, tool_calls = parser.parse(raw_model_output)
# content = text with tool call markup stripped
# tool_calls = list of ChatCompletionMessageToolCall objects, or None
"""
import logging
from abc import ABC, abstractmethod
from typing import Dict, List, Optional, Tuple, Type
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
)
logger = logging.getLogger(__name__)
# Type alias for parser return value
ParseResult = Tuple[Optional[str], Optional[List[ChatCompletionMessageToolCall]]]
class ToolCallParser(ABC):
"""
Base class for tool call parsers.
Each parser knows how to extract structured tool_calls from a specific
model family's raw output text format.
"""
@abstractmethod
def parse(self, text: str) -> ParseResult:
"""
Parse raw model output text for tool calls.
Args:
text: Raw decoded text from the model's completion
Returns:
Tuple of (content, tool_calls) where:
- content: text with tool call markup stripped (the message 'content' field),
or None if the entire output was tool calls
- tool_calls: list of ChatCompletionMessageToolCall objects,
or None if no tool calls were found
"""
raise NotImplementedError
# Global parser registry: name -> parser class
PARSER_REGISTRY: Dict[str, Type[ToolCallParser]] = {}
def register_parser(name: str):
"""
Decorator to register a parser class under a given name.
Usage:
@register_parser("hermes")
class HermesToolCallParser(ToolCallParser):
...
"""
def decorator(cls: Type[ToolCallParser]) -> Type[ToolCallParser]:
PARSER_REGISTRY[name] = cls
return cls
return decorator
def get_parser(name: str) -> ToolCallParser:
"""
Get a parser instance by name.
Args:
name: Parser name (e.g., "hermes", "mistral", "llama3_json")
Returns:
Instantiated parser
Raises:
KeyError: If parser name is not found in registry
"""
if name not in PARSER_REGISTRY:
available = sorted(PARSER_REGISTRY.keys())
raise KeyError(
f"Tool call parser '{name}' not found. Available parsers: {available}"
)
return PARSER_REGISTRY[name]()
def list_parsers() -> List[str]:
"""Return sorted list of registered parser names."""
return sorted(PARSER_REGISTRY.keys())
# Import all parser modules to trigger registration via @register_parser decorators
# Each module registers itself when imported
from environments.tool_call_parsers.hermes_parser import HermesToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.longcat_parser import LongcatToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.mistral_parser import MistralToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.llama_parser import LlamaToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.qwen_parser import QwenToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.deepseek_v3_parser import DeepSeekV3ToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.deepseek_v3_1_parser import DeepSeekV31ToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.kimi_k2_parser import KimiK2ToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.glm45_parser import Glm45ToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.glm47_parser import Glm47ToolCallParser # noqa: E402, F401
from environments.tool_call_parsers.qwen3_coder_parser import Qwen3CoderToolCallParser # noqa: E402, F401

View file

@ -0,0 +1,72 @@
"""
DeepSeek V3.1 tool call parser.
Similar to V3 but with a slightly different format:
<toolcallbegin>function_name<toolsep>arguments<toolcallend>
Note: V3 has type+name before the separator, V3.1 has name before and args after.
Based on VLLM's DeepSeekV31ToolParser.extract_tool_calls()
"""
import re
import uuid
from typing import List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
@register_parser("deepseek_v3_1")
@register_parser("deepseek_v31")
class DeepSeekV31ToolCallParser(ToolCallParser):
"""
Parser for DeepSeek V3.1 tool calls.
Slightly different regex than V3: function_name comes before the separator,
arguments come after (no type field, no json code block wrapper).
"""
START_TOKEN = "<tool▁calls▁begin>"
# Regex captures: function_name, function_arguments
PATTERN = re.compile(
r"<tool▁call▁begin>(?P<function_name>.*?)<tool▁sep>(?P<function_arguments>.*?)<tool▁call▁end>",
re.DOTALL,
)
def parse(self, text: str) -> ParseResult:
if self.START_TOKEN not in text:
return text, None
try:
matches = self.PATTERN.findall(text)
if not matches:
return text, None
tool_calls: List[ChatCompletionMessageToolCall] = []
for match in matches:
func_name, func_args = match
tool_calls.append(
ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:8]}",
type="function",
function=Function(
name=func_name.strip(),
arguments=func_args.strip(),
),
)
)
if not tool_calls:
return text, None
content = text[: text.find(self.START_TOKEN)].strip()
return content if content else None, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,89 @@
"""
DeepSeek V3 tool call parser.
Format uses special unicode tokens:
<toolcallsbegin>
<toolcallbegin>type<toolsep>function_name
```json
{"arg": "value"}
```
<toolcallend>
<toolcallsend>
Fixes Issue #989: Support for multiple simultaneous tool calls.
"""
import re
import uuid
import logging
from typing import List, Optional, Tuple
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
logger = logging.getLogger(__name__)
@register_parser("deepseek_v3")
class DeepSeekV3ToolCallParser(ToolCallParser):
"""
Parser for DeepSeek V3 tool calls.
Uses special unicode tokens with fullwidth angle brackets and block elements.
Extracts type, function name, and JSON arguments from the structured format.
Ensures all tool calls are captured when the model executes multiple actions.
"""
START_TOKEN = "<tool▁calls▁begin>"
# Updated PATTERN: Using \s* instead of literal \n for increased robustness
# against variations in model formatting (Issue #989).
PATTERN = re.compile(
r"<tool▁call▁begin>(?P<type>.*?)<tool▁sep>(?P<function_name>.*?)\s*```json\s*(?P<function_arguments>.*?)\s*```\s*<tool▁call▁end>",
re.DOTALL,
)
def parse(self, text: str) -> ParseResult:
"""
Parses the input text and extracts all available tool calls.
"""
if self.START_TOKEN not in text:
return text, None
try:
# Using finditer to capture ALL tool calls in the sequence
matches = list(self.PATTERN.finditer(text))
if not matches:
return text, None
tool_calls: List[ChatCompletionMessageToolCall] = []
for match in matches:
func_name = match.group("function_name").strip()
func_args = match.group("function_arguments").strip()
tool_calls.append(
ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:8]}",
type="function",
function=Function(
name=func_name,
arguments=func_args,
),
)
)
if tool_calls:
# Content is text before the first tool call block
content_index = text.find(self.START_TOKEN)
content = text[:content_index].strip()
return content if content else None, tool_calls
return text, None
except Exception as e:
logger.error(f"Error parsing DeepSeek V3 tool calls: {e}")
return text, None

View file

@ -0,0 +1,109 @@
"""
GLM 4.5 (GLM-4-MoE) tool call parser.
Format uses custom arg_key/arg_value tags rather than standard JSON:
<tool_call>function_name
<arg_key>param1</arg_key><arg_value>value1</arg_value>
<arg_key>param2</arg_key><arg_value>value2</arg_value>
</tool_call>
Values are deserialized using json.loads -> ast.literal_eval -> raw string fallback.
Based on VLLM's Glm4MoeModelToolParser.extract_tool_calls()
"""
import ast
import json
import re
import uuid
from typing import Any, Dict, List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
def _deserialize_value(value: str) -> Any:
"""
Try to deserialize a string value to its native Python type.
Attempts json.loads, then ast.literal_eval, then returns raw string.
"""
try:
return json.loads(value)
except (json.JSONDecodeError, TypeError):
pass
try:
return ast.literal_eval(value)
except (ValueError, SyntaxError, TypeError):
pass
return value
@register_parser("glm45")
class Glm45ToolCallParser(ToolCallParser):
"""
Parser for GLM 4.5 (GLM-4-MoE) tool calls.
Uses <tool_call>...</tool_call> tags with <arg_key>/<arg_value> pairs
instead of standard JSON arguments.
"""
FUNC_CALL_REGEX = re.compile(r"<tool_call>.*?</tool_call>", re.DOTALL)
FUNC_DETAIL_REGEX = re.compile(r"<tool_call>([^\n]*)\n(.*)</tool_call>", re.DOTALL)
FUNC_ARG_REGEX = re.compile(
r"<arg_key>(.*?)</arg_key>\s*<arg_value>(.*?)</arg_value>", re.DOTALL
)
START_TOKEN = "<tool_call>"
def parse(self, text: str) -> ParseResult:
if self.START_TOKEN not in text:
return text, None
try:
matched_calls = self.FUNC_CALL_REGEX.findall(text)
if not matched_calls:
return text, None
tool_calls: List[ChatCompletionMessageToolCall] = []
for match in matched_calls:
detail = self.FUNC_DETAIL_REGEX.search(match)
if not detail:
continue
func_name = detail.group(1).strip()
func_args_raw = detail.group(2)
# Parse arg_key/arg_value pairs
pairs = self.FUNC_ARG_REGEX.findall(func_args_raw) if func_args_raw else []
arg_dict: Dict[str, Any] = {}
for key, value in pairs:
arg_key = key.strip()
arg_val = _deserialize_value(value.strip())
arg_dict[arg_key] = arg_val
tool_calls.append(
ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:8]}",
type="function",
function=Function(
name=func_name,
arguments=json.dumps(arg_dict, ensure_ascii=False),
),
)
)
if not tool_calls:
return text, None
content = text[: text.find(self.START_TOKEN)].strip()
return content if content else None, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,35 @@
"""
GLM 4.7 tool call parser.
Same as GLM 4.5 but with slightly different regex patterns.
The tool_call tags may wrap differently and arg parsing handles
newlines between key/value pairs.
Based on VLLM's Glm47MoeModelToolParser (extends Glm4MoeModelToolParser).
"""
import re
from environments.tool_call_parsers import ParseResult, register_parser
from environments.tool_call_parsers.glm45_parser import Glm45ToolCallParser
@register_parser("glm47")
class Glm47ToolCallParser(Glm45ToolCallParser):
"""
Parser for GLM 4.7 tool calls.
Extends GLM 4.5 with updated regex patterns.
"""
def __init__(self):
super().__init__()
# GLM 4.7 uses a slightly different detail regex that includes
# the <tool_call> wrapper and optional arg_key content
self.FUNC_DETAIL_REGEX = re.compile(
r"<tool_call>(.*?)(<arg_key>.*?)?</tool_call>", re.DOTALL
)
# GLM 4.7 handles newlines between arg_key and arg_value tags
self.FUNC_ARG_REGEX = re.compile(
r"<arg_key>(.*?)</arg_key>(?:\\n|\s)*<arg_value>(.*?)</arg_value>",
re.DOTALL,
)

View file

@ -0,0 +1,73 @@
"""
Hermes tool call parser.
Format: <tool_call>{"name": "func", "arguments": {...}}</tool_call>
Based on VLLM's Hermes2ProToolParser.extract_tool_calls()
"""
import json
import re
import uuid
from typing import List, Optional, Tuple
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
@register_parser("hermes")
class HermesToolCallParser(ToolCallParser):
"""
Parser for Hermes-format tool calls.
Matches <tool_call>...</tool_call> tags containing JSON with "name" and "arguments".
Also handles unclosed <tool_call> at end-of-string (truncated generation).
"""
# Matches both closed and unclosed tool_call tags
PATTERN = re.compile(
r"<tool_call>\s*(.*?)\s*</tool_call>|<tool_call>\s*(.*)", re.DOTALL
)
def parse(self, text: str) -> ParseResult:
if "<tool_call>" not in text:
return text, None
try:
matches = self.PATTERN.findall(text)
if not matches:
return text, None
tool_calls: List[ChatCompletionMessageToolCall] = []
for match in matches:
# match is a tuple: (closed_content, unclosed_content)
raw_json = match[0] if match[0] else match[1]
if not raw_json.strip():
continue
tc_data = json.loads(raw_json)
tool_calls.append(
ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:8]}",
type="function",
function=Function(
name=tc_data["name"],
arguments=json.dumps(
tc_data.get("arguments", {}), ensure_ascii=False
),
),
)
)
if not tool_calls:
return text, None
# Content is everything before the first <tool_call> tag
content = text[: text.find("<tool_call>")].strip()
return content if content else None, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,93 @@
"""
Kimi K2 tool call parser.
Format:
<|tool_calls_section_begin|>
<|tool_call_begin|>function_id:0<|tool_call_argument_begin|>{"arg": "val"}<|tool_call_end|>
<|tool_calls_section_end|>
The function_id format is typically "functions.func_name:index" or "func_name:index".
Based on VLLM's KimiK2ToolParser.extract_tool_calls()
"""
import re
import uuid
from typing import List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
@register_parser("kimi_k2")
class KimiK2ToolCallParser(ToolCallParser):
"""
Parser for Kimi K2 tool calls.
Uses section begin/end tokens wrapping individual tool call begin/end tokens.
The tool_call_id contains the function name (after last dot, before colon).
"""
# Support both singular and plural variants
START_TOKENS = [
"<|tool_calls_section_begin|>",
"<|tool_call_section_begin|>",
]
# Regex captures: tool_call_id (e.g., "functions.get_weather:0"), function_arguments
PATTERN = re.compile(
r"<\|tool_call_begin\|>\s*(?P<tool_call_id>[^<]+:\d+)\s*"
r"<\|tool_call_argument_begin\|>\s*"
r"(?P<function_arguments>(?:(?!<\|tool_call_begin\|>).)*?)\s*"
r"<\|tool_call_end\|>",
re.DOTALL,
)
def parse(self, text: str) -> ParseResult:
# Check for any variant of the start token
has_start = any(token in text for token in self.START_TOKENS)
if not has_start:
return text, None
try:
matches = self.PATTERN.findall(text)
if not matches:
return text, None
tool_calls: List[ChatCompletionMessageToolCall] = []
for match in matches:
function_id, function_args = match
# Extract function name from ID format: "functions.get_weather:0" -> "get_weather"
function_name = function_id.split(":")[0].split(".")[-1]
tool_calls.append(
ChatCompletionMessageToolCall(
id=function_id, # Preserve the original ID format
type="function",
function=Function(
name=function_name,
arguments=function_args.strip(),
),
)
)
if not tool_calls:
return text, None
# Content is everything before the tool calls section
earliest_start = len(text)
for token in self.START_TOKENS:
idx = text.find(token)
if idx >= 0 and idx < earliest_start:
earliest_start = idx
content = text[:earliest_start].strip()
return content if content else None, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,96 @@
"""
Llama 3.x / 4 tool call parser.
Format: The model outputs JSON objects with "name" and "arguments" (or "parameters") keys.
May be preceded by <|python_tag|> token. Supports multiple JSON objects separated
by content or semicolons.
Based on VLLM's Llama3JsonToolParser.extract_tool_calls()
"""
import json
import re
import uuid
from typing import List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
@register_parser("llama3_json")
@register_parser("llama4_json")
class LlamaToolCallParser(ToolCallParser):
"""
Parser for Llama 3.x and 4 JSON-format tool calls.
Finds JSON objects containing "name" + ("arguments" or "parameters") keys.
Uses Python's json.JSONDecoder.raw_decode for robust extraction of
JSON objects from mixed text.
"""
BOT_TOKEN = "<|python_tag|>"
# Regex to find the start of potential JSON objects
JSON_START = re.compile(r"\{")
def parse(self, text: str) -> ParseResult:
# Quick check: need either the bot token or a JSON brace
if self.BOT_TOKEN not in text and "{" not in text:
return text, None
try:
decoder = json.JSONDecoder()
tool_calls: List[ChatCompletionMessageToolCall] = []
end_index = -1 # Track where the last parsed JSON ended
for match in self.JSON_START.finditer(text):
start = match.start()
# Skip if this brace is inside a previously parsed JSON object
if start <= end_index:
continue
try:
obj, json_end = decoder.raw_decode(text[start:])
end_index = start + json_end
# Must have "name" and either "arguments" or "parameters"
name = obj.get("name")
args = obj.get("arguments", obj.get("parameters"))
if not name or args is None:
continue
# Normalize arguments to JSON string
if isinstance(args, dict):
args = json.dumps(args, ensure_ascii=False)
elif not isinstance(args, str):
args = json.dumps(args, ensure_ascii=False)
tool_calls.append(
ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:8]}",
type="function",
function=Function(name=name, arguments=args),
)
)
except (json.JSONDecodeError, KeyError, ValueError):
continue
if not tool_calls:
return text, None
# Content is everything before the first tool call JSON
# Find where the first tool call starts in the text
first_tc_start = text.find("{")
if self.BOT_TOKEN in text:
first_tc_start = text.find(self.BOT_TOKEN)
content = text[:first_tc_start].strip() if first_tc_start > 0 else None
return content, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,69 @@
"""
Longcat Flash Chat tool call parser.
Same as Hermes but uses <longcat_tool_call> tags instead of <tool_call>.
Based on VLLM's LongcatFlashToolParser (extends Hermes2ProToolParser).
"""
import json
import re
import uuid
from typing import List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
@register_parser("longcat")
class LongcatToolCallParser(ToolCallParser):
"""
Parser for Longcat Flash Chat tool calls.
Identical logic to Hermes, just different tag names.
"""
PATTERN = re.compile(
r"<longcat_tool_call>\s*(.*?)\s*</longcat_tool_call>|<longcat_tool_call>\s*(.*)",
re.DOTALL,
)
def parse(self, text: str) -> ParseResult:
if "<longcat_tool_call>" not in text:
return text, None
try:
matches = self.PATTERN.findall(text)
if not matches:
return text, None
tool_calls: List[ChatCompletionMessageToolCall] = []
for match in matches:
raw_json = match[0] if match[0] else match[1]
if not raw_json.strip():
continue
tc_data = json.loads(raw_json)
tool_calls.append(
ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:8]}",
type="function",
function=Function(
name=tc_data["name"],
arguments=json.dumps(
tc_data.get("arguments", {}), ensure_ascii=False
),
),
)
)
if not tool_calls:
return text, None
content = text[: text.find("<longcat_tool_call>")].strip()
return content if content else None, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,135 @@
"""
Mistral tool call parser.
Supports two formats depending on tokenizer version:
- Pre-v11: content[TOOL_CALLS] [{"name": ..., "arguments": {...}}, ...]
- v11+: content[TOOL_CALLS]tool_name1{"arg": "val"}[TOOL_CALLS]tool_name2{"arg": "val"}
Based on VLLM's MistralToolParser.extract_tool_calls()
The [TOOL_CALLS] token is the bot_token used by Mistral models.
"""
import json
import uuid
from typing import List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
def _generate_mistral_id() -> str:
"""Mistral tool call IDs are 9-char alphanumeric strings."""
import random
import string
return "".join(random.choices(string.ascii_letters + string.digits, k=9))
@register_parser("mistral")
class MistralToolCallParser(ToolCallParser):
"""
Parser for Mistral-format tool calls.
Detects format by checking if the content after [TOOL_CALLS] starts with '['
(pre-v11 JSON array) or with a tool name (v11+ format).
"""
# The [TOOL_CALLS] token -- may appear as different strings depending on tokenizer
BOT_TOKEN = "[TOOL_CALLS]"
def parse(self, text: str) -> ParseResult:
if self.BOT_TOKEN not in text:
return text, None
try:
parts = text.split(self.BOT_TOKEN)
content = parts[0].strip()
raw_tool_calls = parts[1:]
# Detect format: if the first raw part starts with '[', it's pre-v11
first_raw = raw_tool_calls[0].strip() if raw_tool_calls else ""
is_pre_v11 = first_raw.startswith("[") or first_raw.startswith("{")
tool_calls: List[ChatCompletionMessageToolCall] = []
if not is_pre_v11:
# v11+ format: [TOOL_CALLS]tool_name{args}[TOOL_CALLS]tool_name2{args2}
for raw in raw_tool_calls:
raw = raw.strip()
if not raw or "{" not in raw:
continue
brace_idx = raw.find("{")
tool_name = raw[:brace_idx].strip()
args_str = raw[brace_idx:]
# Validate and clean the JSON arguments
try:
parsed_args = json.loads(args_str)
args_str = json.dumps(parsed_args, ensure_ascii=False)
except json.JSONDecodeError:
pass # Keep raw if parsing fails
tool_calls.append(
ChatCompletionMessageToolCall(
id=_generate_mistral_id(),
type="function",
function=Function(name=tool_name, arguments=args_str),
)
)
else:
# Pre-v11 format: [TOOL_CALLS] [{"name": ..., "arguments": {...}}]
try:
parsed = json.loads(first_raw)
if isinstance(parsed, dict):
parsed = [parsed]
for tc in parsed:
args = tc.get("arguments", {})
if isinstance(args, dict):
args = json.dumps(args, ensure_ascii=False)
tool_calls.append(
ChatCompletionMessageToolCall(
id=_generate_mistral_id(),
type="function",
function=Function(
name=tc["name"], arguments=args
),
)
)
except json.JSONDecodeError:
# Fallback: extract JSON objects using raw_decode
decoder = json.JSONDecoder()
idx = 0
while idx < len(first_raw):
try:
obj, end_idx = decoder.raw_decode(first_raw, idx)
if isinstance(obj, dict) and "name" in obj:
args = obj.get("arguments", {})
if isinstance(args, dict):
args = json.dumps(args, ensure_ascii=False)
tool_calls.append(
ChatCompletionMessageToolCall(
id=_generate_mistral_id(),
type="function",
function=Function(
name=obj["name"], arguments=args
),
)
)
idx = end_idx
except json.JSONDecodeError:
idx += 1
if not tool_calls:
return text, None
return content if content else None, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,163 @@
"""
Qwen3-Coder tool call parser.
Format uses XML-style nested tags:
<tool_call>
<function=function_name>
<parameter=param_name>value</parameter>
<parameter=param_name2>value2</parameter>
</function>
</tool_call>
Parameters are extracted from <parameter=name>value</parameter> tags and
type-converted using the schema if available, otherwise treated as strings.
Based on VLLM's Qwen3CoderToolParser.extract_tool_calls()
"""
import ast
import json
import re
import uuid
from typing import Any, Dict, List, Optional
from openai.types.chat.chat_completion_message_tool_call import (
ChatCompletionMessageToolCall,
Function,
)
from environments.tool_call_parsers import ParseResult, ToolCallParser, register_parser
def _try_convert_value(value: str) -> Any:
"""
Try to convert a parameter value string to a native Python type.
Handles null, numbers, booleans, JSON objects/arrays, and falls back to string.
"""
stripped = value.strip()
# Handle null
if stripped.lower() == "null":
return None
# Try JSON first (handles objects, arrays, strings, numbers, booleans)
try:
return json.loads(stripped)
except (json.JSONDecodeError, TypeError):
pass
# Try Python literal eval (handles tuples, etc.)
try:
return ast.literal_eval(stripped)
except (ValueError, SyntaxError, TypeError):
pass
# Return as string
return stripped
@register_parser("qwen3_coder")
class Qwen3CoderToolCallParser(ToolCallParser):
"""
Parser for Qwen3-Coder XML-format tool calls.
Uses nested XML tags: <tool_call><function=name><parameter=key>val</parameter></function></tool_call>
"""
START_TOKEN = "<tool_call>"
FUNCTION_PREFIX = "<function="
# Find complete tool_call blocks (or unclosed at end)
TOOL_CALL_REGEX = re.compile(
r"<tool_call>(.*?)</tool_call>|<tool_call>(.*?)$", re.DOTALL
)
# Find function blocks within a tool_call
FUNCTION_REGEX = re.compile(
r"<function=(.*?)</function>|<function=(.*)$", re.DOTALL
)
# Find parameter blocks within a function
PARAMETER_REGEX = re.compile(
r"<parameter=(.*?)(?:</parameter>|(?=<parameter=)|(?=</function>)|$)",
re.DOTALL,
)
def _parse_function_call(self, function_str: str) -> Optional[ChatCompletionMessageToolCall]:
"""Parse a single <function=name>...</function> block into a ToolCall."""
try:
# Extract function name: everything before the first '>'
gt_idx = function_str.index(">")
func_name = function_str[:gt_idx].strip()
params_str = function_str[gt_idx + 1:]
# Extract parameters
param_dict: Dict[str, Any] = {}
for match_text in self.PARAMETER_REGEX.findall(params_str):
if ">" not in match_text:
continue
eq_idx = match_text.index(">")
param_name = match_text[:eq_idx].strip()
param_value = match_text[eq_idx + 1:]
# Clean up whitespace
if param_value.startswith("\n"):
param_value = param_value[1:]
if param_value.endswith("\n"):
param_value = param_value[:-1]
param_dict[param_name] = _try_convert_value(param_value)
return ChatCompletionMessageToolCall(
id=f"call_{uuid.uuid4().hex[:24]}",
type="function",
function=Function(
name=func_name,
arguments=json.dumps(param_dict, ensure_ascii=False),
),
)
except (ValueError, IndexError):
return None
def parse(self, text: str) -> ParseResult:
if self.FUNCTION_PREFIX not in text:
return text, None
try:
# Find all tool_call blocks
tc_matches = self.TOOL_CALL_REGEX.findall(text)
raw_blocks = [m[0] if m[0] else m[1] for m in tc_matches]
# Fallback: if no tool_call tags, try the whole text
if not raw_blocks:
raw_blocks = [text]
# Find function blocks within each tool_call
function_strs: List[str] = []
for block in raw_blocks:
func_matches = self.FUNCTION_REGEX.findall(block)
function_strs.extend(m[0] if m[0] else m[1] for m in func_matches)
if not function_strs:
return text, None
# Parse each function call
tool_calls: List[ChatCompletionMessageToolCall] = []
for func_str in function_strs:
tc = self._parse_function_call(func_str)
if tc is not None:
tool_calls.append(tc)
if not tool_calls:
return text, None
# Content before tool calls
first_tc = text.find(self.START_TOKEN)
if first_tc < 0:
first_tc = text.find(self.FUNCTION_PREFIX)
content = text[:first_tc].strip() if first_tc > 0 else None
return content, tool_calls
except Exception:
return text, None

View file

@ -0,0 +1,19 @@
"""
Qwen 2.5 tool call parser.
Uses the same <tool_call> format as Hermes.
Registered as a separate parser name for clarity when using --tool-parser=qwen.
"""
from environments.tool_call_parsers import register_parser
from environments.tool_call_parsers.hermes_parser import HermesToolCallParser
@register_parser("qwen")
class QwenToolCallParser(HermesToolCallParser):
"""
Parser for Qwen 2.5 tool calls.
Same <tool_call>{"name": ..., "arguments": ...}</tool_call> format as Hermes.
"""
pass # Identical format -- inherits everything from Hermes