* Fix Gemma 4 GGUF OpenAI API streams * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Avoid duplicate Responses stream disconnect watcher * Keep reasoning-only Responses output hidden * Address Gemma stream review comments * Avoid Responses stream task-group cleanup * Harden OpenAI chat completion streams * Address OpenAI stream review issues * Clean up Studio OpenAI stream helpers * Fix Studio passthrough cold stream timeout * Fix tool parser compatibility exports lint * Preserve audio stream disconnect cancellation * Avoid synthetic finish after passthrough errors * Address stream cleanup and Gemma parser reviews * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Gemma 4: parse bare-string tool args and keep safetensors tools for native <|tool_call> - Quote bare unquoted string values in Gemma native tool-call args (e.g. {location:Tokyo,unit:celsius}) so they parse; JSON scalars stay typed. - Stop _detect_safetensors_features from suppressing supports_tools for templates that emit Gemma native <|tool_call>, which the shared parser now reads. - Add tests for both. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Harden Gemma tool-call parsing and stream-error detection Address three issues in the Gemma-native tool-call path: - _quote_gemma_object_keys stopped a bare (unquoted) string value at the first comma, so an argument like `location:New York, NY` was split mid-value and the synthesized JSON failed to parse, dropping the whole tool call. A bare value now ends only at `}` or a comma that begins the next `key:` pair. - parse_tool_calls_from_text scanned the entire response for Gemma markers even inside a tool call already parsed from a `<tool_call>{...}` JSON block, so a marker-like string inside an argument (data) was promoted to a second, unintended tool call. Matches inside an already-consumed call span are now skipped. - _openai_passthrough_stream relied on _monitor_openai_sse_line to flag a stream error, which returns early when monitor_id is None (skip_api_monitor), so an upstream error chunk left saw_stream_error unset and the synthetic-finish guard emitted a successful finish_reason after a failed stream. Error chunks are now detected independently of API monitoring. Adds tests/test_gemma_tool_parse_edge_cases.py covering the comma and marker-injection cases. * Emit the terminal finish_reason chunk in GGUF streams The OpenAI chat-completions GGUF tool stream and plain stream both built a final ChatCompletionChunk carrying finish_reason but never yielded it, so clients received the optional usage chunk and [DONE] with no chunk carrying finish_reason. OpenAI-compatible consumers rely on that terminal choice to distinguish stop/length/tool_calls. Yield it before the usage chunk and [DONE], matching the other streaming paths. * Parse tool calls in document order and skip nested markers both ways Unify the JSON- and Gemma-format tool-call passes into a single position-ordered scan: - Calls are now emitted in byte order across both formats, so a mixed output like `<|tool_call>call:create{...}<tool_call|> ... <tool_call> {"name":"read",...}</tool_call>` executes create before read, matching the order they appear in (tools run in returned order). - A candidate that starts inside an already-accepted call's span is skipped, in both directions: a JSON marker inside a Gemma argument and a Gemma marker inside a JSON argument are treated as data, not promoted to a second executable tool call. Extends tests/test_gemma_tool_parse_edge_cases.py with the ordering and JSON-in-Gemma nesting cases. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Quote bare Gemma array elements; order finish before trailing usage - _quote_gemma_object_keys skipped array values, so a Gemma call with a bare-string array argument like labels:[bug,ui] produced invalid JSON and the whole tool call was dropped. Array values are now scanned and bare string elements quoted, while numbers, quoted strings, and JSON literals are preserved. - In the OpenAI passthrough stream, a trailing usage-only chunk (stream_options.include_usage) that arrived before any finish chunk was relayed before the synthetic finish, producing usage -> finish -> [DONE]. Emit the synthetic finish before that usage chunk so the order matches the other streams (finish -> usage -> [DONE]). Extends tests/test_gemma_tool_parse_edge_cases.py with the bare-array cases. * Harden Gemma array parsing, XML-parameter guard, and stream teardown Address five review findings on the Gemma tool-call and OpenAI passthrough streaming paths: - parse_tool_calls_from_text collected JSON and Gemma markers without the _inside_open_parameter guard, so a marker embedded in an existing <function=...><parameter=...> value was promoted to a separate tool call. Candidates that start inside an open XML parameter are now skipped, matching the guard the XML-style parser already applies. - _quote_gemma_array_elements preserved array elements starting with { or [ verbatim, so an array of objects (items:[{path:a}]) or a nested array failed json.loads and the whole call was dropped. Object and nested-array elements are now normalised recursively. - _openai_passthrough_stream synthesized a finish chunk before a trailing usage-only chunk and set saw_finish_reason, which made the EOF guard skip the [DONE] sentinel. The EOF path now emits [DONE] whenever the upstream omitted it, even after a finish chunk was already synthesized. - /generate/stream drove generation through asyncio.to_thread with no disconnect watcher, so a client disconnect during a long generation went unnoticed until the next send. It now runs _await_disconnect_then_cancel against the request, matching the other local streaming endpoints. - _SameTaskStreamingResponse closed the body iterator with aclose() on a send-side disconnect, raising GeneratorExit so the generators' cancellation handlers (which finish the api_monitor entry) never ran. It now throws CancelledError, falling back to aclose() when athrow is unavailable. Extends tests/test_gemma_tool_parse_edge_cases.py with array-of-objects, nested-array, and marker-inside-XML-parameter cases. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Watch disconnects on Anthropic streams; keep timestamps in Gemma values Two follow-ups on the streaming and tool-parse paths: - _anthropic_tool_stream and _anthropic_plain_stream drove generation through asyncio.to_thread(next, gen, ...) and only polled is_disconnected() between events, so a client disconnect during prefill or a long generation/tool step held the decode slot until the next event or a failed send. Both now run the _await_disconnect_then_cancel watcher used by the other local streams, stop it in finally, and break promptly when cancel_event is set. - _GEMMA_NEXT_KEY_RE treated any comma followed by word-chars-then-colon as the next key, so a bare value such as "meet at 10:00, 11:00 tomorrow" was split into bogus keys. The next-key token must now be identifier-shaped (start with a letter or underscore), so a comma before a timestamp, ratio, or other numeric-then-colon text stays part of the value. Adds a timestamp-in-bare-value regression test. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Guard nested markers, reset on disconnect, clean unstarted streams Three follow-ups on the tool-parse and streaming paths: - parse_tool_calls_from_text only skipped markers that fell inside a span it had already parsed successfully, so when an unquoted Gemma argument contained a literal marker (code:<|tool_call>call:terminal{...}<tool_call|>) the outer object failed to normalize, its span was never recorded, and the inner marker was promoted to a standalone terminal call. Candidates nested inside any other candidate's brace span are now skipped regardless of whether the enclosing candidate parsed, so a marker in malformed outer data is never executed. - /generate/stream skipped backend.reset_generation_state() when the disconnect watcher set cancel_event between chunks: the loop broke and the finally's reset is guarded on cancel_event being unset. A subprocess backend kept decoding after the client left. The cancel-break path now resets the backend. - _SameTaskStreamingResponse threw CancelledError / called aclose() on the body iterator on a send-side disconnect, but neither runs the try/finally of a generator that never started (early disconnect on http.response.start), so the passthrough's eagerly-opened upstream httpx stream and cancel-registry entry leaked. It now tracks whether the body started and, when it did not, runs an optional unstarted_cleanup hook; the OpenAI passthrough wires it to close the upstream resp/client and exit the cancel tracker. Adds a nested-unquoted-marker regression test. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com>
162 lines
6.9 KiB
Python
162 lines
6.9 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
|
|
|
|
"""Strict-mode (Auto-Heal disabled) tool-call parsing.
|
|
|
|
With ``allow_incomplete=False`` the parser must accept a well-formed
|
|
``<function=...>...</function>`` call even when the model appends prose
|
|
after the closing tag -- matching the JSON-style ``<tool_call>...`` path,
|
|
which already tolerates trailing text -- while still rejecting genuinely
|
|
truncated calls that never close.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
_BACKEND_DIR = str(Path(__file__).resolve().parent.parent)
|
|
if _BACKEND_DIR not in sys.path:
|
|
sys.path.insert(0, _BACKEND_DIR)
|
|
|
|
from core.inference.tool_call_parser import parse_tool_calls_from_text
|
|
|
|
|
|
def _only(text: str) -> dict:
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = False)
|
|
assert len(calls) == 1, f"expected exactly one call, got {len(calls)}: {calls!r}"
|
|
fn = calls[0]["function"]
|
|
return {"name": fn["name"], "arguments": json.loads(fn["arguments"])}
|
|
|
|
|
|
class TestFunctionStyleTrailingText:
|
|
def test_closed_function_with_trailing_prose_is_accepted(self):
|
|
text = (
|
|
"<function=web_search><parameter=query>weather london</parameter></function>"
|
|
" Let me check that for you."
|
|
)
|
|
call = _only(text)
|
|
assert call == {"name": "web_search", "arguments": {"query": "weather london"}}
|
|
|
|
def test_closed_function_with_trailing_whitespace_is_accepted(self):
|
|
text = "<function=web_search><parameter=query>cats</parameter></function> \n\n"
|
|
call = _only(text)
|
|
assert call == {"name": "web_search", "arguments": {"query": "cats"}}
|
|
|
|
def test_closed_function_without_trailing_text_still_parses(self):
|
|
text = "<function=web_search><parameter=query>cats</parameter></function>"
|
|
call = _only(text)
|
|
assert call == {"name": "web_search", "arguments": {"query": "cats"}}
|
|
|
|
def test_multi_param_with_trailing_prose(self):
|
|
text = (
|
|
"<function=terminal><parameter=command>ls -la</parameter>"
|
|
"<parameter=workdir>home</parameter></function> running it now"
|
|
)
|
|
call = _only(text)
|
|
assert call == {
|
|
"name": "terminal",
|
|
"arguments": {"command": "ls -la", "workdir": "home"},
|
|
}
|
|
|
|
def test_code_value_containing_literal_close_tag_is_preserved(self):
|
|
# The real closing </function> is the last one; the literal inside
|
|
# the code argument must survive (rfind, not the first match).
|
|
text = (
|
|
"<function=python><parameter=code>"
|
|
'print("</function>")'
|
|
"</parameter></function> all done"
|
|
)
|
|
call = _only(text)
|
|
assert call == {"name": "python", "arguments": {"code": 'print("</function>")'}}
|
|
|
|
def test_incomplete_function_without_close_is_still_rejected(self):
|
|
text = "<function=web_search><parameter=query>weather london"
|
|
assert parse_tool_calls_from_text(text, allow_incomplete = False) == []
|
|
|
|
def test_param_without_close_tag_is_rejected_in_strict_mode(self):
|
|
# Closing </function> present, but the single parameter never closes.
|
|
text = "<function=web_search><parameter=query>weather london</function>"
|
|
assert parse_tool_calls_from_text(text, allow_incomplete = False) == []
|
|
|
|
|
|
class TestParityWithJsonStyle:
|
|
def test_json_tool_call_with_trailing_prose_is_accepted(self):
|
|
text = (
|
|
'<tool_call>{"name":"web_search","arguments":{"query":"weather london"}}</tool_call>'
|
|
" Let me check that for you."
|
|
)
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = False)
|
|
assert len(calls) == 1
|
|
assert calls[0]["function"]["name"] == "web_search"
|
|
|
|
def test_function_and_json_styles_agree_on_trailing_text(self):
|
|
q = "weather london"
|
|
func = parse_tool_calls_from_text(
|
|
f"<function=web_search><parameter=query>{q}</parameter></function> trailing",
|
|
allow_incomplete = False,
|
|
)
|
|
js = parse_tool_calls_from_text(
|
|
f'<tool_call>{{"name":"web_search","arguments":{{"query":"{q}"}}}}</tool_call> trailing',
|
|
allow_incomplete = False,
|
|
)
|
|
assert len(func) == len(js) == 1
|
|
assert json.loads(func[0]["function"]["arguments"]) == {"query": q}
|
|
assert json.loads(js[0]["function"]["arguments"]) == {"query": q}
|
|
|
|
|
|
class TestGemmaNativeStyle:
|
|
def test_closed_native_call_with_trailing_prose_is_accepted(self):
|
|
text = (
|
|
'<|tool_call>call:terminal{command:"ls -la",workdir:"."}<tool_call|>' " running it now"
|
|
)
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = False)
|
|
assert len(calls) == 1
|
|
assert calls[0]["function"]["name"] == "terminal"
|
|
assert json.loads(calls[0]["function"]["arguments"]) == {
|
|
"command": "ls -la",
|
|
"workdir": ".",
|
|
}
|
|
|
|
def test_unclosed_native_call_requires_healing(self):
|
|
text = '<|tool_call>call:terminal{command:"ls"}'
|
|
assert parse_tool_calls_from_text(text, allow_incomplete = False) == []
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = True)
|
|
assert len(calls) == 1
|
|
assert calls[0]["function"]["name"] == "terminal"
|
|
|
|
def test_hyphenated_native_argument_name_is_accepted(self):
|
|
text = '<|tool_call>call:mcp__srv__create-issue{issue-title:"Bug report"}<tool_call|>'
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = False)
|
|
assert len(calls) == 1
|
|
assert calls[0]["function"]["name"] == "mcp__srv__create-issue"
|
|
assert json.loads(calls[0]["function"]["arguments"]) == {"issue-title": "Bug report"}
|
|
|
|
def test_native_template_quotes_preserve_windows_path(self):
|
|
text = r'<|tool_call>call:ls{path:<|"|>C:\Users\wasim\repo<|"|>}<tool_call|>'
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = False)
|
|
assert len(calls) == 1
|
|
assert json.loads(calls[0]["function"]["arguments"]) == {"path": r"C:\Users\wasim\repo"}
|
|
|
|
def test_bare_unquoted_string_values_are_accepted(self):
|
|
# Gemma can emit enum/string args unquoted; bare JSON scalars stay typed.
|
|
text = (
|
|
"<|tool_call>call:get_weather{location:Tokyo,unit:celsius,days:3,live:true}<tool_call|>"
|
|
)
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = False)
|
|
assert len(calls) == 1
|
|
assert json.loads(calls[0]["function"]["arguments"]) == {
|
|
"location": "Tokyo",
|
|
"unit": "celsius",
|
|
"days": 3,
|
|
"live": True,
|
|
}
|
|
|
|
|
|
class TestHealingPathUnaffected:
|
|
def test_auto_heal_still_repairs_unclosed_function(self):
|
|
text = "<function=web_search><parameter=query>cats"
|
|
calls = parse_tool_calls_from_text(text, allow_incomplete = True)
|
|
assert len(calls) == 1
|
|
assert calls[0]["function"]["name"] == "web_search"
|