Skip to content

Latest results with LLM streaming and pre-tool speech #219

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
fanny-riols wants to merge 2 commits into
base: main
Choose a base branch
from
+8 −8
Draft

Latest results with LLM streaming and pre-tool speech #219

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ff1e0a6
Enable LLM streaming and pretool speech by default
fanny-riols Aug 10, 2026
7f4ae31
Merge branch 'main' into pr/streaming-pretoolspeech
fanny-riols Aug 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/eva/models/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,7 +196,7 @@ class ModelConfig(BaseModel):

# CASCADE-only latency controls.
pre_tool_speech: str = Field(
"off",
"auto",
description="Prompt a model-generated lead-in before tool calls: 'off' or 'auto'.",
)

Expand All @@ -206,7 +206,7 @@ def _normalize_pre_tool_speech(cls, value: str) -> str:
return value.lower() if isinstance(value, str) else value

llm_streaming: bool = Field(
False,
True,
description="Stream Chat Completions output to TTS sentence-by-sentence.",
)
parallel_tool_calls: bool | None = Field(
Expand Down
12 changes: 6 additions & 6 deletions tests/unit/models/test_config_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -848,16 +848,16 @@ def test_runconfig_roundtrip(self):


class TestLatencyOptimizationFlags:
def test_defaults_off(self):
def test_defaults_on(self):
c = _config(env_vars=_BASE_ENV)
assert c.model.pre_tool_speech == "off"
assert c.model.llm_streaming is False

def test_set_via_env(self):
c = _config(env_vars=_BASE_ENV | {"EVA_MODEL__PRE_TOOL_SPEECH": "auto", "EVA_MODEL__LLM_STREAMING": "true"})
assert c.model.pre_tool_speech == "auto"
assert c.model.llm_streaming is True

def test_set_via_env(self):
c = _config(env_vars=_BASE_ENV | {"EVA_MODEL__PRE_TOOL_SPEECH": "off", "EVA_MODEL__LLM_STREAMING": "false"})
assert c.model.pre_tool_speech == "off"
assert c.model.llm_streaming is False

@pytest.mark.parametrize("value", ["bogus", "force"])
def test_invalid_pre_tool_speech_rejected(self, value):
with pytest.raises(ValueError):
Expand Down
Loading