-
Notifications
You must be signed in to change notification settings - Fork 3.8k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#6606 In google/adk-python;
- Status: Open.#6603 In google/adk-python;
- Status: Open.
skip_summarization=True makes agent yield control after any tool calls in a workflow
request clarification[Status] The maintainer need clarification or more information from the author[Status] The maintainer need clarification or more information from the authortools[Component] This issue is related to tools[Component] This issue is related to toolsStatus: Open.OCIGenAILlm silently drops all but the first tool result when multiple tools are called in parallel
tools[Component] This issue is related to tools[Component] This issue is related to toolsStatus: Open.#6589 In google/adk-python;RemoteA2aAgent ends the invocation silently when the A2A stream stops before a terminal task state
a2a[Component] This issue is related a2a support inside ADK.[Component] This issue is related a2a support inside ADK.request clarification[Status] The maintainer need clarification or more information from the author[Status] The maintainer need clarification or more information from the authorStatus: Open.RemoteA2aAgent: a terminal A2A task carrying tool activity fails is_final_response(), so the turn cannot be detected as finished (non-streaming peer)
a2a[Component] This issue is related a2a support inside ADK.[Component] This issue is related a2a support inside ADK.request clarification[Status] The maintainer need clarification or more information from the author[Status] The maintainer need clarification or more information from the authorStatus: Open.chat wrapper (run_llm_agent_as_node) extracts task-delegation FCs from partial=True progressive-SSE chunks and breaks — the FC event is never persisted, orphaning the synthesized task FR and permanently poisoning the session
agent engine[Component] This issue is related to Vertex AI Agent Engine[Component] This issue is related to Vertex AI Agent EngineStatus: Open.contents request-processor (_rearrange_events_for_latest_function_response) raises ValueError on an orphaned function response, permanently poisoning the session — raise happens before before_model_callback, so no user hook can intercept it
agent engine[Component] This issue is related to Vertex AI Agent Engine[Component] This issue is related to Vertex AI Agent EngineStatus: Open.chat-mode wrapper (_llm_agent_wrapper.py) silently drops regular-tool FR when model emits regular FC + task FC in same turn → session poisoning
agent engine[Component] This issue is related to Vertex AI Agent Engine[Component] This issue is related to Vertex AI Agent Enginerequest clarification[Status] The maintainer need clarification or more information from the author[Status] The maintainer need clarification or more information from the authorStatus: Open.StreamingResponseAggregator causes infinite tool-call loop with transfer_to_agent + streaming
live[Component] This issue is related to live, voice and video chat[Component] This issue is related to live, voice and video chatStatus: Open.#6566 In google/adk-python;"Failed to detach context" (Token created in a different Context) logged as ERROR when caller stops runner.run_async() early
tracing[Component] This issue is related to OpenTelemetry tracing[Component] This issue is related to OpenTelemetry tracingStatus: Open.