[bot] Instrument AWS Bedrock Agent Runtime (2,630,075 weekly downloads)
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 4/5
- Tempo stimato
- 3-5 giorni
- Idoneità per principianti
- 52/100
- Tipo di issue
- Funzionalità
- Chiarezza
- Abbastanza chiara
- Stato di attività
- Attiva
- Stack tecnologico
- aws, typescript
- Ambito
- backend, observability
Direzione di ricerca
Start by reading js/src/auto-instrumentations/configs/all.ts and js/src/span-origin.ts, then compare the existing Bedrock Runtime instrumentation with the AWS SDK commands named in the issue. The issue also identifies e2e/scenarios/ as the location for an instrumentation scenario. Done means direct use of Bedrock Agent Runtime commands is traced and the new instrumentation is registered.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Summary
@aws-sdk/client-bedrock-agent-runtime is AWS's official SDK for invoking pre-built Amazon Bedrock Agents and Bedrock Flows — a distinct agent-execution surface from the already-instrumented Bedrock Runtime client (@aws-sdk/client-bedrock-runtime, which only covers direct model Converse/InvokeModel calls). InvokeAgentCommand, InvokeFlowCommand, and InvokeInlineAgentCommand run an agent's multi-step reasoning/tool-use loop server-side and stream back the trace, but none of this is captured as spans today.
What's missing
BedrockAgentRuntimeClient+InvokeAgentCommand— runs a configured Bedrock Agent against a prompt/session, optionally streaming the agent's reasoning trace (enableTrace) and tool invocations.InvokeFlowCommand— executes a Bedrock Flow (a graph of prompt/tool/code nodes) and streams per-node outputs.InvokeInlineAgentCommand— runs an ad hoc (not pre-registered) agent definition.
This is a different package/API surface than the AWS Bedrock Agent Runtime client that Strands Agents SDK optionally depends on (@aws-sdk/client-bedrock-agent-runtime appears only as an optional peer dependency of @strands-agents/sdk for Strands's own Bedrock backend — see e2e/scenarios/strands-agent-sdk-instrumentation/pnpm-lock.yaml). A caller using this AWS SDK client directly (not through Strands) gets zero tracing.
Weekly downloads
Weekly downloads: 2,630,075 (as of 2026-10-12; window 2026-10-04–2026-10-10; source https://api.npmjs.org/downloads/point/last-week/@aws-sdk/client-bedrock-agent-runtime)
Braintrust docs status
not_found — Checked https://www.braintrust.dev/docs/integrations/ai-providers/bedrock, which documents only the Bedrock Runtime client (ConverseCommand, ConverseStreamCommand, InvokeModelCommand, InvokeModelWithResponseStreamCommand via wrapBedrockRuntime/the auto-instrumentation hook) and the @anthropic-ai/bedrock-sdk path. Also checked https://www.braintrust.dev/docs/guides/traces/integrations (full tracing/agent-framework integration list) — no mention of Bedrock Agents, InvokeAgent, or Bedrock Flows anywhere in Braintrust's docs.
Upstream sources
- https://www.npmjs.com/package/@aws-sdk/client-bedrock-agent-runtime
- https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_InvokeAgent.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-agent-runtime_example_bedrock-agent-runtime_InvokeAgent_section.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-agent-runtime_example_bedrock-agent-runtime_InvokeFlow_section.html
Local repo files inspected
js/src/auto-instrumentations/configs/all.ts(full instrumentation registry — onlybedrockRuntimeConfigsfor AWS Bedrock, no Bedrock Agent Runtime entry)js/src/span-origin.ts(INSTRUMENTATION_NAMES— onlyBEDROCK_RUNTIME, no Bedrock Agent entry)- Repo-wide case-insensitive search for
bedrock-agent-runtime/BedrockAgentRuntime/InvokeAgent/InvokeFlow(only matches: binary provider-response cassette blobs with coincidental byte sequences, and@aws-sdk/client-bedrock-agent-runtimelisted as an optional peer dependency ine2e/scenarios/strands-agent-sdk-instrumentation/pnpm-lock.yaml— i.e. Strands's own optional Bedrock backend, not direct instrumentation of this client) e2e/scenarios/directory listing (no Bedrock-Agent-named scenario)
- Lingua principale
- TypeScript
- Stelle
- 29
- Fork
- 16
- Merge medio
- 1g 19h
- PR unite (30g)
- 69
Preparare l'ambiente
- Include un Dockerfile o un file Docker Compose
- Nessun modello di pull request
- Nessuna guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di braintrustdata/braintrust-sdk-javascript
-
Difficoltà 3/5 1-2 giorni Idoneità per principianti 45/100
braintrustdata/braintrust-sdk-javascript#2619 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 4/5 3-5 giorni Idoneità per principianti 45/100
braintrustdata/braintrust-sdk-javascript#2618 ·
I maintainer di solito rispondono entro 1 giorno
-
typescript
Difficoltà 4/5 3-5 giorni Idoneità per principianti 48/100
braintrustdata/braintrust-sdk-javascript#2605 ·
I maintainer di solito rispondono entro 1 giorno
-
typescript
Difficoltà 4/5 3-5 giorni Idoneità per principianti 55/100
braintrustdata/braintrust-sdk-javascript#2578 ·
I maintainer di solito rispondono entro 1 giorno
-
[bot] Instrument Letta Agent SDK (143,425 weekly downloads)Forse già presa @karthiksenv l’ha presa 1 giorno fa. Apertatypescript
Difficoltà 4/5 3-5 giorni Idoneità per principianti 55/100
braintrustdata/braintrust-sdk-javascript#2577 ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di braintrustdata/braintrust-sdk-javascript
Issue simili
-
ai-driven-qa bug claude Minor
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
linagora/twake-contacts-frontend#241 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
I maintainer di solito rispondono entro 1 giorno
-
ui(ListToolbar): search takes the full row on a phone instead of sharing it with the result countAperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 64/100
I maintainer di solito rispondono entro 1 giorno
-
priority:high
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 70/100
ahmedkhaleel2004/gitdiagram#228 ·