* Studio: coerce tool_call arguments to dict before chat templating Strict tool chat templates (e.g. mlx-community Qwen3.5 checkpoints) iterate arguments.items() and raise "TypeError: Can only get item pairs from a mapping" when a prior assistant tool call is re-rendered on the next turn. The agentic loop stores arguments in the OpenAI JSON-string form (as_assistant_tool_call), which is correct on the wire and for llama-server, but the transformers / MLX paths apply_chat_template directly and hit the strict Jinja templates. Normalize each assistant tool_call's function.arguments from a JSON string to a dict inside apply_chat_template_for_generation (shared by both the MLX and safetensors paths). A dict renders on strict and lenient templates alike; non-JSON / non-dict values are left untouched, and the OpenAI-format as_assistant_tool_call (used by the GGUF path + API responses) is unchanged. Verified against the real mlx-community/Qwen3.5-2B-8bit template: string args raised the tester's error, the fix renders cleanly, and the lenient unsloth/Qwen3.5-0.8B template still works. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: make tool-arg coercion a string-first fallback (non-regressive) Render the original OpenAI string-arg form first and only coerce arguments to a dict when the template raises the mapping TypeError, instead of always coercing. Any template that already renders is now byte-identical (a template that emits arguments verbatim keeps the JSON string, not a Python dict repr). Verified across Llama-3, Qwen2.5, Qwen3, Qwen3.5, Phi-3.5 (byte-identical) and mlx-community/Qwen3.5-2B-8bit (strict -> fixed). Gemma-3 / Mistral tool-template errors are unrelated (role alternation / tool-id length) and identical with or without the change. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Make core.inference package init lazy so dependency-light helpers import standalone Importing any core.inference submodule ran the package __init__, which eagerly imported orchestrator and llama_cpp; both pull loggers -> structlog (and httpx), so a dependency-light helper like chat_template_helpers dragged in the full heavy stack and its unit test failed to collect in a backend env without structlog. Defer those imports to attribute access via PEP 562 __getattr__, mirroring the lazy pattern already in core/__init__.py. The re-exports resolve unchanged on first access. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Retry dict-coercion for strict templates that raise non-TypeError apply_chat_template_for_generation only retried the OpenAI JSON-string arguments coercion when the first render raised TypeError (the arguments.items() form). The bundled gemma-4.jinja instead rejects string arguments with raise_exception, which surfaces as a Jinja error, so a second tool turn with string function.arguments propagated and failed rather than retrying with the parsed dict. Broaden the outer catch to Exception, still gated on there being a string arg to normalize (normalized is messages -> re-raise), so unrelated template errors and templates that already render are unaffected. * Tighten comments in tool-call argument coercion helper and tests * Tighten tool-call argument coercion comments --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
157 lines
5.2 KiB
Python
157 lines
5.2 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""apply_chat_template_for_generation must coerce assistant tool_call arguments
|
|
from the OpenAI JSON-string form to a dict before rendering. Strict tool
|
|
templates (e.g. mlx-community Qwen3.5 checkpoints) iterate arguments.items() and
|
|
raise "Can only get item pairs from a mapping." on the string form when a prior
|
|
tool call is re-rendered on the next turn (MLX + transformers paths).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
_BACKEND = Path(__file__).resolve().parent.parent
|
|
if str(_BACKEND) not in sys.path:
|
|
sys.path.insert(0, str(_BACKEND))
|
|
|
|
from core.inference.chat_template_helpers import ( # noqa: E402
|
|
_normalize_tool_call_arguments,
|
|
apply_chat_template_for_generation,
|
|
)
|
|
|
|
|
|
def _conv(arguments):
|
|
return [
|
|
{"role": "user", "content": "weather?"},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{
|
|
"type": "function",
|
|
"id": "c1",
|
|
"function": {"name": "web_search", "arguments": arguments},
|
|
}
|
|
],
|
|
},
|
|
{"role": "tool", "name": "web_search", "content": "21C sunny"},
|
|
]
|
|
|
|
|
|
class _StrictTemplateTokenizer:
|
|
"""Mimics a strict Qwen tool template: rejects string tool_call arguments."""
|
|
|
|
def apply_chat_template(
|
|
self,
|
|
messages,
|
|
*,
|
|
tokenize = False,
|
|
add_generation_prompt = True,
|
|
**kw,
|
|
):
|
|
for msg in messages:
|
|
for call in msg.get("tool_calls", []) or []:
|
|
args = call.get("function", {}).get("arguments")
|
|
if isinstance(args, str):
|
|
raise TypeError("Can only get item pairs from a mapping.")
|
|
return "RENDERED"
|
|
|
|
|
|
def test_string_arguments_are_parsed_to_dict():
|
|
out = _normalize_tool_call_arguments(_conv('{"query": "sweden"}'))
|
|
args = out[1]["tool_calls"][0]["function"]["arguments"]
|
|
assert args == {"query": "sweden"}
|
|
|
|
|
|
def test_dict_arguments_untouched_and_no_copy():
|
|
conv = _conv({"query": "sweden"})
|
|
assert _normalize_tool_call_arguments(conv) is conv
|
|
|
|
|
|
def test_non_json_string_left_as_is():
|
|
out = _normalize_tool_call_arguments(_conv("not json"))
|
|
assert out[1]["tool_calls"][0]["function"]["arguments"] == "not json"
|
|
|
|
|
|
def test_render_succeeds_on_strict_template_with_string_arguments():
|
|
# Regression: strict template + string args used to raise.
|
|
result = apply_chat_template_for_generation(_StrictTemplateTokenizer(), _conv('{"query": "x"}'))
|
|
assert result == "RENDERED"
|
|
|
|
|
|
class _RecordingTokenizer:
|
|
"""Lenient template: renders whatever arguments it is given (string or dict)."""
|
|
|
|
def __init__(self):
|
|
self.seen_arguments = None
|
|
|
|
def apply_chat_template(
|
|
self,
|
|
messages,
|
|
*,
|
|
tokenize = False,
|
|
add_generation_prompt = True,
|
|
**kw,
|
|
):
|
|
for msg in messages:
|
|
for call in msg.get("tool_calls", []) or []:
|
|
self.seen_arguments = call.get("function", {}).get("arguments")
|
|
return "RENDERED"
|
|
|
|
|
|
def test_lenient_template_receives_original_string_untouched():
|
|
# Lenient template must see the exact original string, not a coerced dict.
|
|
tok = _RecordingTokenizer()
|
|
apply_chat_template_for_generation(tok, _conv('{"query": "x"}'))
|
|
assert tok.seen_arguments == '{"query": "x"}'
|
|
|
|
|
|
def test_messages_without_tool_calls_pass_through_unchanged():
|
|
conv = [{"role": "user", "content": "hi"}]
|
|
assert _normalize_tool_call_arguments(conv) is conv
|
|
|
|
|
|
class _RaiseExceptionTemplateTokenizer:
|
|
"""Mimics the bundled gemma-4.jinja: rejects string tool_call arguments via
|
|
``raise_exception(...)``, which surfaces as a Jinja error, NOT a TypeError."""
|
|
|
|
def apply_chat_template(
|
|
self,
|
|
messages,
|
|
*,
|
|
tokenize = False,
|
|
add_generation_prompt = True,
|
|
**kw,
|
|
):
|
|
for msg in messages:
|
|
for call in msg.get("tool_calls", []) or []:
|
|
args = call.get("function", {}).get("arguments")
|
|
if isinstance(args, str):
|
|
raise ValueError(
|
|
"chat_template: tool_calls[].function.arguments must be a "
|
|
"JSON object (mapping), not a string."
|
|
)
|
|
return "RENDERED"
|
|
|
|
|
|
def test_render_succeeds_on_raise_exception_template_with_string_arguments():
|
|
# Regression: gemma-4.jinja rejects string args via a non-TypeError; retry must still coerce.
|
|
result = apply_chat_template_for_generation(
|
|
_RaiseExceptionTemplateTokenizer(), _conv('{"query": "x"}')
|
|
)
|
|
assert result == "RENDERED"
|
|
|
|
|
|
def test_unrelated_template_error_still_propagates_with_dict_args():
|
|
# Failure unrelated to string args (dict args, nothing to coerce) must propagate.
|
|
class _AlwaysRaises:
|
|
def apply_chat_template(self, messages, **kw):
|
|
raise ValueError("template is broken")
|
|
|
|
with pytest.raises(ValueError, match = "broken"):
|
|
apply_chat_template_for_generation(_AlwaysRaises(), _conv({"query": "x"}))
|