displayName
Gemini CLI Core (current)
agentVersionId
packageRef
loopIteratorPolicy
tool-use-loop
loopIteratorNotes
Tool-use loop over Gemini's `generateContent` (streaming) API. Each turn, the model emits `functionCall` parts; the CLI executes them and feeds back `functionResponse` parts. The loop advances until a chunk arrives with `finishReason: STOP` (or `MAX_TOKENS` / `SAFETY`).
contextManagementStrategy
platform-managed
compactionTriggerNotes
Gemini CLI relies on the model's 1M-token context window directly; no in-CLI compaction is performed for the @current pin.
subagentInvokerPolicy
tool-call-handoff
subagentInvokerNotes
Gemini CLI follows the ADK `sub_agents` pattern: subagent invocation is a structured tool-call whose target name resolves to another agent definition; the CLI dispatches a child `generateContent` loop for the sub-task.
resultSynthesisPolicy
model-direct
resultSynthesisNotes
Final text parts are streamed as they arrive; the CLI emits a post_response hook after the last chunk with `finishReason: STOP` is observed.
stopDetectionStrategy
structured-end-event
transportClientLibrary
@google/genai
supportedTransportProtocols
parallelToolCallHandling
native
streamingFidelity
full
thinkingChannelHandling
passthrough