Skip to content

Feature:Add End Flag in run_sse API Response to Indicate LLM Model Completion #2919

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

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Feature:Add End Flag in run_sse API Response to Indicate LLM Model Completion #2919

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
a6e5454
feat: add customizable memory_service extension for get_fast_api_app
stonyme Sep 10, 2025
e34aec6
fix: improve type hint for memory_service parameter
stonyme Sep 10, 2025
2337eb0
feature:add session end marker, when llm final response
stonyme Sep 11, 2025
add5f8c
define SSE 'done' message as a constant
stonyme Sep 11, 2025
04204f6
Merge branch 'main' into feature/add-session-end-marker
stonyme Sep 12, 2025
261ddd6
Merge branch 'main' into feature/add-session-end-marker
stonyme Sep 12, 2025
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
2 changes: 2 additions & 0 deletions src/google/adk/cli/adk_web_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1076,6 +1076,8 @@ async def event_generator():
"Generated event in agent run streaming: %s", sse_event
)
yield f"data: {sse_event}\n\n"
# Add done flag when all data has been sent
yield "data: {\"done\": true}\n\n"
except Exception as e:
logger.exception("Error in event_generator: %s", e)
# You might want to yield an error event here
Expand Down
6 changes: 5 additions & 1 deletion src/google/adk/cli/fast_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
from ..auth.credential_service.in_memory_credential_service import InMemoryCredentialService
from ..evaluation.local_eval_set_results_manager import LocalEvalSetResultsManager
from ..evaluation.local_eval_sets_manager import LocalEvalSetsManager
from ..memory.base_memory_service import BaseMemoryService
from ..memory.in_memory_memory_service import InMemoryMemoryService
from ..memory.vertex_ai_memory_bank_service import VertexAiMemoryBankService
from ..runners import Runner
Expand All @@ -60,6 +61,7 @@ def get_fast_api_app(
session_db_kwargs: Optional[Mapping[str, Any]] = None,
artifact_service_uri: Optional[str] = None,
memory_service_uri: Optional[str] = None,
memory_service: Optional[BaseMemoryService] = None,
eval_storage_uri: Optional[str] = None,
allow_origins: Optional[list[str]] = None,
web: bool,
Expand Down Expand Up @@ -107,7 +109,9 @@ def _parse_agent_engine_resource_name(agent_engine_id_or_resource_name):
return project, location, agent_engine_id

# Build the Memory service
if memory_service_uri:
if memory_service:
pass
elif memory_service_uri:
if memory_service_uri.startswith("rag://"):
from ..memory.vertex_ai_rag_memory_service import VertexAiRagMemoryService

Expand Down