AWS's bedrockagentruntime service · portable interface driver.BedrockAgentRuntime · AWS index
| Operation | Description |
|---|---|
InvokeAgent |
|
Retrieve |
|
RetrieveAndGenerate |
Discovered by type assertion; only some providers implement these.
AgentMemory reads and deletes an agent's session-summary memory.
| Operation | Description |
|---|---|
DeleteAgentMemory |
|
GetAgentMemory |
AgenticRetriever plans and runs retrievals over knowledge bases.
| Operation | Description |
|---|---|
AgenticRetrieveStream |
DocumentReader locates the content of ingested knowledge-base documents.
| Operation | Description |
|---|---|
GetDocumentContent |
FlowExecutions invokes flows and manages their asynchronous executions.
| Operation | Description |
|---|---|
GetExecutionFlowSnapshot |
|
GetFlowExecution |
|
InvokeFlow |
|
ListFlowExecutionEvents |
|
ListFlowExecutions |
|
StartFlowExecution |
|
StopFlowExecution |
InlineAgents runs agents defined inline in the request.
| Operation | Description |
|---|---|
InvokeInlineAgent |
Invocations records invocations and their steps in a session.
| Operation | Description |
|---|---|
CreateInvocation |
|
GetInvocationStep |
|
ListInvocationSteps |
|
ListInvocations |
|
PutInvocationStep |
PromptOptimizer rewrites a prompt for a target model.
| Operation | Description |
|---|---|
OptimizePrompt |
QueryGenerator turns natural language into SQL (TEXT_TO_SQL).
| Operation | Description |
|---|---|
GenerateQuery |
Reranker orders documents by relevance to a query.
| Operation | Description |
|---|---|
Rerank |
Sessions manages session-management sessions.
| Operation | Description |
|---|---|
CreateSession |
|
DeleteSession |
|
EndSession |
|
GetSession |
|
ListSessions |
|
UpdateSession |
StreamingRetrieveAndGenerate answers RetrieveAndGenerateStream.
| Operation | Description |
|---|---|
RetrieveAndGenerateStream |
Tagger tags runtime resources (sessions) by ARN.
| Operation | Description |
|---|---|
ListTagsForResource |
|
TagResource |
|
UntagResource |
- There is no model inference. Agent answers, RetrieveAndGenerate answers and flow Prompt nodes use the Bedrock mock's deterministic completion; session summaries in agent memory, GenerateQuery SQL (a fixed
SELECTwith the question as a comment), OptimizePrompt rewrites and Rerank scores are deterministic approximations. Retrieval ranks a knowledge base's text documents (inline text, or text objects read from cloudemu S3 by direct ingestion or an ingestion job) by the share of the query's words they contain; there are no embeddings or chunking, and binary documents (PDF, Word, Excel) are not searched. Metadata filters (every RetrievalFilter operator) apply to a document's inline or.metadata.jsonattributes;overrideSearchType, implicit filters and reranking inside Retrieve are ignored. An empty knowledge base returns no results. - The agent does not plan. It calls an action-group function or API only when the input names it (a function name, with
_read as a space, or an API path), and takes parameters written asname=valueorname: value: a function's parameters, an API operation's path, query and header parameters, and its request-body properties. API schemas are read fromapiSchema.payload(JSON or YAML) orapiSchema.s3(cloudemu S3);$refreferences are not resolved. A RETURN_CONTROL action group hands the call back with areturnControlevent (apiInvocationInputcarriesrequestBody); a Lambda action group runs the Lambda mock with the documented agent event, includingrequestBody.content.<type>.propertiesfor API calls. From the Lambda's reply it reads the response body,responseState(FAILURE is a DependencyFailedException naming the function; REPROMPT is read as the observation, as there is no model to reprompt),sessionAttributesandpromptSessionAttributes(they replace the session's) andknowledgeBasesConfiguration(applied to the rest of the turn). Built-inAMAZON.*/ANTHROPIC.*action groups, code interpretation, collaborators, user confirmation andfiles(in the request'ssessionStateor as response events) are not modelled. A new input abandons a pending returnControl. - Traces cover orchestration (model input and output, rationale, action-group invocation, observations including the knowledge-base chunks found) plus a guardrail trace when a guardrail intervenes; pre- and post-processing traces appear only when the agent's
promptOverrideConfigurationenables those steps. Routing classifiers and custom orchestration are not produced. streamingConfigurations.streamFinalResponsesplits the answer into chunks of about 64 bytes at word boundaries;applyGuardrailIntervalis not used.- Guardrails come from the Bedrock mock, which evaluates only a guardrail's custom denied words.
- Flows run their definition from the Input node: Output nodes receive the input document, Condition nodes follow their
defaultconnection, and every other node passes its input through unchanged (no model, Lambda, Lex or knowledge-base calls, no loops or multi-turn input). The working draft (TSTALIASID) must be prepared.--async-settlekeeps a StartFlowExecutionRunningfor two seconds, the only window in which StopFlowExecution succeeds; restored executions read as finished. - Session-management sessions expire after one hour idle (EXPIRED) and are never deleted automatically (AWS removes them after 30 days).
encryptionKeyArnis stored, not used. A RetrieveAndGeneratesessionIdis echoed but carries no conversation. - GetDocumentContent serves text documents (inline, or read from S3), through a URL on the emulator that expires after 15 minutes and survives
--persistrestarts. CheckIngestedDocumentAcl and GetIngestedDocumentAcl are newer than the SDK version cloudemu builds against and are not served. - Agent invocations publish
AWS/Bedrock/Agentsmetrics (InvocationCount, TotalTime, the error and throttle counts, ModelInvocationCount, ModelLatency as 0, InputTokenCount, OutputTokenCount); TTFT is not published. Per-invocation CloudWatch Logs delivery needs the CloudWatch Logs vended-delivery API, which cloudemu does not have yet (#1560). - A runtime used on its own, without the bedrock-agent control plane, keeps its earlier behavior: it accepts any agent, alias and knowledge-base id and answers with simulated text.
- Invoking an agent's working draft (TSTALIASID) needs a prepared draft: after CreateAgent or any change to the draft, call PrepareAgent first. AWS does not document the exception for an unprepared draft; the emulator returns a ValidationException.
- Where AWS does not document the exact message (an alias rejecting invocations, an unprepared agent or flow, a stale returnControl invocationId, a non-SQL knowledge base for GenerateQuery, an S3 external source that can't be read), the emulator returns the documented exception with its own wording.
- Under
--enforce-auth, Bedrock Agent requests are authorized at service level (bedrock:*), and RetrieveAndGenerate reads S3 external sources without checking the caller'ss3:GetObjectpermission; per-operation authorization is #1562. sessionState.conversationHistoryseeds the earlier turns of a new session (each user message with the assistant message after it); it is ignored for a session that already has turns. Knowledge-base chunks that share no word with the question are not passed to the model as context. A session that times out is summarized into agent memory when the agent's memory is next read, or when its sessionId is invoked again.