mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-15 09:12:18 +00:00
fix(gemini): preserve thoughtSignature emitted on a separate thought part
Gemini 3+ may place the thought signature on a thought part that precedes
the functionCall part, rather than on the functionCall part itself.
`_transform_parts` only read `thoughtSignature` from parts containing
`functionCall`, so in that shape the signature was dropped: never stored,
never echoed back on the next turn.
Downstream this surfaces as a hard 400 from the Gemini API on the second
tool-calling turn:
Function call is missing a thought_signature in functionCall parts.
This is required for tools to work correctly
Carry a pending signature forward from the thought part and consume it on
the first function call that follows — in parallel calls only the first one
carries a signature. A signature present on the functionCall part keeps
precedence, so the existing behaviour is unchanged.
Closes #25322
This commit is contained in:
parent
328a5f5d60
commit
d4e0ee35b0
2 changed files with 85 additions and 1 deletions
|
|
@ -1556,14 +1556,25 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
|
|||
]:
|
||||
function: ChatCompletionToolCallFunctionChunk | None = None
|
||||
_tools: Final[list[ChatCompletionToolCallChunk]] = []
|
||||
# Gemini 3+ may emit the thought signature on a preceding thought part
|
||||
# instead of on the functionCall part itself. Carry it forward so it is
|
||||
# not dropped; consume it on the first function call that follows, since
|
||||
# in parallel calls only the first one carries a signature.
|
||||
pending_thought_signature: str | None = None
|
||||
for part in parts:
|
||||
if part.get("thought") and part.get("thoughtSignature"):
|
||||
pending_thought_signature = part.get("thoughtSignature")
|
||||
continue
|
||||
if "functionCall" in part:
|
||||
_function_chunk: ChatCompletionToolCallFunctionChunk = {
|
||||
"name": part["functionCall"]["name"],
|
||||
"arguments": json.dumps(part["functionCall"]["args"], ensure_ascii=False),
|
||||
}
|
||||
# Extract thought signature if present
|
||||
thought_signature = part.get("thoughtSignature")
|
||||
# Extract thought signature if present. Fall back to the one
|
||||
# carried by a preceding thought part (Gemini 3+ places it there).
|
||||
thought_signature = part.get("thoughtSignature") or pending_thought_signature
|
||||
pending_thought_signature = None
|
||||
# Gemini 3.5+ returns a stable `id` per function call to enable
|
||||
# strict response matching. Preserve it as the OpenAI
|
||||
# tool_call_id so it can be echoed back unchanged.
|
||||
|
|
|
|||
|
|
@ -285,3 +285,76 @@ def test_parallel_tool_calls_with_signatures(enable_preview_features):
|
|||
assert THOUGHT_SIGNATURE_SEPARATOR not in tools[1]["id"]
|
||||
sig2 = _get_thought_signature_from_tool({"id": tools[1]["id"], "type": "function"})
|
||||
assert sig2 is None
|
||||
|
||||
|
||||
def test_thought_signature_on_separate_thought_part_is_preserved():
|
||||
"""Gemini 3+ places the signature on a thought part, not on the functionCall part.
|
||||
|
||||
Regression for the case where `_transform_parts` only looked at the
|
||||
functionCall part and silently dropped the signature, so it was never
|
||||
echoed back on the next turn.
|
||||
"""
|
||||
test_signature = "CvsBAdHtim9thoughtPartSignature"
|
||||
parts = [
|
||||
HttpxPartType(thought=True, thoughtSignature=test_signature),
|
||||
HttpxPartType(functionCall={"name": "get_weather", "args": {"city": "Recife"}}),
|
||||
]
|
||||
|
||||
_, tools, _ = VertexGeminiConfig._transform_parts(
|
||||
parts=parts,
|
||||
cumulative_tool_call_idx=0,
|
||||
is_function_call=False,
|
||||
)
|
||||
|
||||
assert tools is not None and len(tools) == 1
|
||||
assert (
|
||||
tools[0].get("provider_specific_fields", {}).get("thought_signature")
|
||||
== test_signature
|
||||
)
|
||||
|
||||
|
||||
def test_thought_signature_on_function_call_part_still_wins():
|
||||
"""A signature on the functionCall part keeps precedence over a pending one."""
|
||||
own_signature = "CvsBAdHtim9onTheCallPart"
|
||||
parts = [
|
||||
HttpxPartType(thought=True, thoughtSignature="CvsBAdHtim9onTheThoughtPart"),
|
||||
HttpxPartType(
|
||||
functionCall={"name": "get_weather", "args": {"city": "Recife"}},
|
||||
thoughtSignature=own_signature,
|
||||
),
|
||||
]
|
||||
|
||||
_, tools, _ = VertexGeminiConfig._transform_parts(
|
||||
parts=parts,
|
||||
cumulative_tool_call_idx=0,
|
||||
is_function_call=False,
|
||||
)
|
||||
|
||||
assert tools is not None and len(tools) == 1
|
||||
assert (
|
||||
tools[0].get("provider_specific_fields", {}).get("thought_signature")
|
||||
== own_signature
|
||||
)
|
||||
|
||||
|
||||
def test_pending_thought_signature_is_consumed_once():
|
||||
"""In parallel calls only the first function call carries a signature."""
|
||||
test_signature = "CvsBAdHtim9onlyForTheFirstCall"
|
||||
parts = [
|
||||
HttpxPartType(thought=True, thoughtSignature=test_signature),
|
||||
HttpxPartType(functionCall={"name": "get_weather", "args": {"city": "Recife"}}),
|
||||
HttpxPartType(functionCall={"name": "get_time", "args": {"city": "Recife"}}),
|
||||
]
|
||||
|
||||
_, tools, _ = VertexGeminiConfig._transform_parts(
|
||||
parts=parts,
|
||||
cumulative_tool_call_idx=0,
|
||||
is_function_call=False,
|
||||
)
|
||||
|
||||
assert tools is not None and len(tools) == 2
|
||||
assert (
|
||||
tools[0].get("provider_specific_fields", {}).get("thought_signature")
|
||||
== test_signature
|
||||
)
|
||||
assert tools[1].get("provider_specific_fields") is None
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue