Skip to content
Flow Like logo Flow Like Docs

Stream Invoke Agent Node

AI/Agents

Stream Invoke Agent

Executes an Agent with streaming, emitting chunks in real-time

agent_stream_invokellmLong running
Inputs3
Outputs6
Security exposure6/10
Packagellm

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.
6/10Medium
PrivacyPotential sensitivity of processed data.
7/10Low
PerformanceRuntime or resource pressure.
4/10Medium
GovernancePolicy, audit, or compliance impact.
6/10Medium
ReliabilityOperational stability considerations.
5/10Medium
CostExternal or compute cost impact.
6/10Medium

Input Pins

3

Input

Execution
exec_in

Execution trigger

Agent

Struct
agent

Configured Agent object with tools

AgentAgent16 fields
modelBitrequired

The LLM model id backing this agent

idstring
default ""
typeBitTypes
enum "Llm", "Vlm", "Tts", "Stt"...default "Other"
metaMap<string, Metadata>
default {}
*Metadatamap value
namestringrequired
descriptionstringrequired
long_descriptionstring | null
release_notesstring | null
tagsArray<string>required
+11 more fields
authorsArray<string>
default []
itemsstringarray item
repositorystring | null
default null
+14 more fields
model_display_namestring | null

Model display name

max_iterationsinteger:uint64required

Maximum number of iterations/tool calls before stopping

format uint64min 0
system_promptstring | null

System prompt for the agent

toolsArray<Tool>

Registered tools (function calling schemas for non-function tools)

default []
itemsToolarray item
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
namestringrequired
descriptionstring | null
parametersHistoryFunctionParametersrequired
function_refsMap<string, string>

Function references (node_id -> node_name mapping) These are converted to tools at execution time to keep data slim

default {}
*stringmap value
mcp_serversArray<McpServerConfig>

MCP servers with optional tool filtering

default []
itemsMcpServerConfigarray item

MCP server registration with optional tool filtering

uristringrequired

URI of the MCP server

tool_filterarray | null

Optional tool filter - if None, all tools are used If Some, only tools in this set are used

itemsstringarray item
thinking_enabledboolean

Whether the thinking tool is enabled

default false
historyanyOf (2)

Optional conversation history to initialize with

variant 1Historyvariant
modelstringrequired
messagesArray<HistoryMessage>required
itemsHistoryMessagearray item
presetstring | null
streamboolean | null
stream_optionsanyOf (2)
variant 1StreamOptionsvariant
variant 2nullvariant
+14 more fields
variant 2nullvariant
datafusion_contextsArray<DataFusionContext>

DataFusion sessions for SQL-based data analysis Multiple sessions can be added to give the agent access to different data sources

default []
itemsDataFusionContextarray item

DataFusion session context for SQL-based data analysis

session_cache_keystringrequired

Cache key to look up the session in ExecutionContext.cache

descriptionstring | null

User-provided description of what this data represents e.g., "Sales data from 2020-2024 including customer demographics"

table_descriptionsMap<string, string>

Per-table descriptions for better LLM understanding Key is the table name, value is description

default {}
*stringmap value
example_queriesArray<string>

Example SQL queries that work well with this data

default []
itemsstringarray item
table_schemasMap<string, string>

Auto-discovered table schemas (populated at runtime) Key is table name, value is schema description

default {}
*stringmap value
infinite_contextboolean

Enable infinite context mode with automatic context window management. When enabled, applies the selected context management strategy.

default false
context_management_modeContextManagementMode

Strategy for managing context when it exceeds the token budget. - Truncate: Sliding window, removes oldest messages (fast, no extra cost) - Summarize: LLM compresses old messages (preserves info, adds latency/cost)

default "Truncate"
variant 1constvariant

Sliding window truncation - removes oldest messages to fit budget. Fast, deterministic, no extra API costs. May lose important early context.

const "Truncate"
variant 2constvariant

LLM summarization - compresses old messages into a summary. Preserves key information but adds latency and API cost.

const "Summarize"
max_context_tokensinteger | null

Maximum tokens to retain when truncating history in infinite context mode. Defaults to 32000 tokens if not specified. Only used when infinite_context is true.

format uint32default nullmin 0
lazy_function_refsArray<LazyFunctionRef>

Lazy function references backed by a vector DB index. At execution time the agent can search this index to dynamically discover and load only the tools it actually needs, keeping the context window lean.

default []
itemsLazyFunctionRefarray item

Reference to a lazy function tool index stored in a vector DB. Allows agents to do hybrid search over a large pool of tools at execution time instead of loading all tool schemas into the context upfront.

db_cache_keystringrequired

Cache key used to look up the LanceDB connection

lazy_embedding_modelanyOf (2)

Embedding model shared across all lazy function tool indexes. The model's cache key is encoded into the vector DB table name, so swapping the model automatically uses a fresh table (old embeddings are abandoned).

variant 1CachedEmbeddingModelvariant
cache_keystringrequired
model_typeBitTypesrequired
enum "Llm", "Vlm", "Tts", "Stt"...
variant 2nullvariant
memoryanyOf (2)

Persistent memory configuration. When set, the agent gains built-in `_memory_search`, `_memory_store`, and `_memory_compress` tools to autonomously store, recall, and compress observations across conversations.

variant 1MemoryConfigvariant
databaseNodeDBConnectionrequired
cache_keystringrequired
embedding_modelCachedEmbeddingModelrequired
cache_keystringrequired
model_typeBitTypesrequired
enum "Llm", "Vlm", "Tts", "Stt"...
max_context_tokensinteger:uint32required
format uint32min 0
recall_strategyRecallStrategyrequired
enum "RecentFirst", "Relevance", "Hybrid"
recall_top_kinteger:uint32required
format uint32min 0
+2 more fields
variant 2nullvariant
Schema enforced

History

Struct
history

Conversation history to provide context

HistoryHistory19 fields
modelstringrequired
messagesArray<HistoryMessage>required
itemsHistoryMessagearray item
roleRolerequired
enum "system", "user", "assistant", "function"...
contentMessageContentrequired
variant 1stringvariant
variant 2Array<Content>variant
namestring | null
tool_callsarray | null
itemsToolCallarray item
tool_call_idstring | null
+1 more fields
presetstring | null
streamboolean | null
stream_optionsanyOf (2)
variant 1StreamOptionsvariant
include_usagebooleanrequired
variant 2nullvariant
max_completion_tokensinteger | null
format uint32min 0
top_pnumber | null
format float
temperaturenumber | null
format float
thinkinganyOf (2)
variant 1HistoryThinkingvariant
enum "off", "low", "mid", "high"
variant 2nullvariant
seedinteger | null
format uint32min 0
presence_penaltynumber | null
format float
frequency_penaltynumber | null
format float
userstring | null
stoparray | null
itemsstringarray item
response_formatanyOf (2)
variant 1ResponseFormatvariant
variant 1stringvariant
variant 2nullvariant
ninteger | null
format uint32min 0
toolsarray | null
itemsToolarray item
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
namestringrequired
descriptionstring | null
parametersHistoryFunctionParametersrequired
tool_choiceanyOf (2)
variant 1ToolChoicevariant
variant 1nullvariant
variant 2nullvariant
variant 3nullvariant
variant 4objectvariant
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
variant 2nullvariant
+1 more fields
Schema enforced

Output Pins

6

On Stream

Execution
on_stream

Triggers whenever the agent streams a chunk

Chunk

Struct
chunk

Latest streamed chunk from agent response

ResponseChunkResponseChunk8 fields
idstringrequired
choicesArray<ResponseChunkChoice>required
itemsResponseChunkChoicearray item
indexinteger:int32required
format int32
deltaanyOf (2)
variant 1Deltavariant
variant 2nullvariant
finish_reasonstring | null
logprobsanyOf (2)
variant 1LogProbsvariant
variant 2nullvariant
createdinteger | null
format uint64min 0
modelstring | null
service_tierstring | null
system_fingerprintstring | null
usageanyOf (2)
variant 1Usagevariant
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
variant 1PromptTokenDetailsvariant
variant 2nullvariant
+2 more fields
variant 2nullvariant
x_prefill_progressnumber | null
format float
Schema enforced

Done

Execution
exec_done

Fires when agent completes execution

Response

Struct
response

Final complete agent response

ResponseResponse8 fields
idstring | null
choicesArray<Choice>required
itemsChoicearray item
indexinteger:int32required
format int32
finish_reasonstringrequired
messageResponseMessagerequired
rolestringrequired
contentstring | null
refusalstring | null
annotationsarray | null
audioanyOf (2)
+2 more fields
logprobsanyOf (2)
variant 1LogProbsvariant
variant 2nullvariant
createdinteger | null
format uint64min 0
modelstring | null
service_tierstring | null
system_fingerprintstring | null
objectstring | null
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
variant 1PromptTokenDetailsvariant
cached_tokensinteger | null
format uint32min 0
audio_tokensinteger | null
format uint32min 0
variant 2nullvariant
+2 more fields
Schema enforced

History Out

Struct
history_out

Updated conversation history with all agent turns

HistoryHistory19 fields
modelstringrequired
messagesArray<HistoryMessage>required
itemsHistoryMessagearray item
roleRolerequired
enum "system", "user", "assistant", "function"...
contentMessageContentrequired
variant 1stringvariant
variant 2Array<Content>variant
namestring | null
tool_callsarray | null
itemsToolCallarray item
tool_call_idstring | null
+1 more fields
presetstring | null
streamboolean | null
stream_optionsanyOf (2)
variant 1StreamOptionsvariant
include_usagebooleanrequired
variant 2nullvariant
max_completion_tokensinteger | null
format uint32min 0
top_pnumber | null
format float
temperaturenumber | null
format float
thinkinganyOf (2)
variant 1HistoryThinkingvariant
enum "off", "low", "mid", "high"
variant 2nullvariant
seedinteger | null
format uint32min 0
presence_penaltynumber | null
format float
frequency_penaltynumber | null
format float
userstring | null
stoparray | null
itemsstringarray item
response_formatanyOf (2)
variant 1ResponseFormatvariant
variant 1stringvariant
variant 2nullvariant
ninteger | null
format uint32min 0
toolsarray | null
itemsToolarray item
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
namestringrequired
descriptionstring | null
parametersHistoryFunctionParametersrequired
tool_choiceanyOf (2)
variant 1ToolChoicevariant
variant 1nullvariant
variant 2nullvariant
variant 3nullvariant
variant 4objectvariant
typeToolTyperequired
enum "function"
functionHistoryFunctionrequired
variant 2nullvariant
+1 more fields
Schema enforced

Stats

Struct
stats

Token usage, cost, and model statistics

LLMUsageStatsLLMUsageStats5 fields
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
variant 1PromptTokenDetailsvariant
cached_tokensinteger | null
format uint32min 0
audio_tokensinteger | null
format uint32min 0
variant 2nullvariant
+2 more fields
modelstring | null
duration_msinteger | null
format uint64min 0
iterationsinteger | null
format uint32min 0
callsArray<ModelCallEntry>
itemsModelCallEntryarray item
modelstringrequired
usageUsagerequired
completion_tokensinteger:uint32required
format uint32min 0
prompt_tokensinteger:uint32required
format uint32min 0
total_tokensinteger:uint32required
format uint32min 0
costnumber | null
format double
prompt_tokens_detailsanyOf (2)
+2 more fields
duration_msinteger | null
format uint64min 0
Schema enforced

Node Info

Internal name
agent_stream_invoke
Category
AI/Agents
Version
4