Skip to content

Latest commit

 

History

History
147 lines (104 loc) · 8.07 KB

bedrockagentruntime.md

File metadata and controls

147 lines (104 loc) · 8.07 KB

BedrockAgentRuntime

AWS's bedrockagentruntime service · portable interface driver.BedrockAgentRuntime · AWS index

Operations (3)

Operation Description
InvokeAgent
Retrieve
RetrieveAndGenerate

Optional capabilities

Discovered by type assertion; only some providers implement these.

AgentMemory

AgentMemory reads and deletes an agent's session-summary memory.

Operation Description
DeleteAgentMemory
GetAgentMemory

AgenticRetriever

AgenticRetriever plans and runs retrievals over knowledge bases.

Operation Description
AgenticRetrieveStream

DocumentReader

DocumentReader locates the content of ingested knowledge-base documents.

Operation Description
GetDocumentContent

FlowExecutions

FlowExecutions invokes flows and manages their asynchronous executions.

Operation Description
GetExecutionFlowSnapshot
GetFlowExecution
InvokeFlow
ListFlowExecutionEvents
ListFlowExecutions
StartFlowExecution
StopFlowExecution

InlineAgents

InlineAgents runs agents defined inline in the request.

Operation Description
InvokeInlineAgent

Invocations

Invocations records invocations and their steps in a session.

Operation Description
CreateInvocation
GetInvocationStep
ListInvocationSteps
ListInvocations
PutInvocationStep

PromptOptimizer

PromptOptimizer rewrites a prompt for a target model.

Operation Description
OptimizePrompt

QueryGenerator

QueryGenerator turns natural language into SQL (TEXT_TO_SQL).

Operation Description
GenerateQuery

Reranker

Reranker orders documents by relevance to a query.

Operation Description
Rerank

Sessions

Sessions manages session-management sessions.

Operation Description
CreateSession
DeleteSession
EndSession
GetSession
ListSessions
UpdateSession

StreamingRetrieveAndGenerate

StreamingRetrieveAndGenerate answers RetrieveAndGenerateStream.

Operation Description
RetrieveAndGenerateStream

Tagger

Tagger tags runtime resources (sessions) by ARN.

Operation Description
ListTagsForResource
TagResource
UntagResource

Not in scope

  • 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 SELECT with 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.json attributes; 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 as name=value or name: value: a function's parameters, an API operation's path, query and header parameters, and its request-body properties. API schemas are read from apiSchema.payload (JSON or YAML) or apiSchema.s3 (cloudemu S3); $ref references are not resolved. A RETURN_CONTROL action group hands the call back with a returnControl event (apiInvocationInput carries requestBody); a Lambda action group runs the Lambda mock with the documented agent event, including requestBody.content.<type>.properties for 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), sessionAttributes and promptSessionAttributes (they replace the session's) and knowledgeBasesConfiguration (applied to the rest of the turn). Built-in AMAZON.*/ANTHROPIC.* action groups, code interpretation, collaborators, user confirmation and files (in the request's sessionState or 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 promptOverrideConfiguration enables those steps. Routing classifiers and custom orchestration are not produced.
  • streamingConfigurations.streamFinalResponse splits the answer into chunks of about 64 bytes at word boundaries; applyGuardrailInterval is 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 default connection, 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-settle keeps a StartFlowExecution Running for 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). encryptionKeyArn is stored, not used. A RetrieveAndGenerate sessionId is 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 --persist restarts. CheckIngestedDocumentAcl and GetIngestedDocumentAcl are newer than the SDK version cloudemu builds against and are not served.
  • Agent invocations publish AWS/Bedrock/Agents metrics (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's s3:GetObject permission; per-operation authorization is #1562.
  • sessionState.conversationHistory seeds 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.