Expose request compression in the new SDK and coordinate Bedrock support
Mantenedores costumam responder em até 3 dias
Avaliação
- Dificuldade
- 4/5
- Tempo estimado
- 3-5 dias
- Facilidade para iniciantes
- 35/100
- Tipo de issue
- Funcionalidade
- Clareza
- Razoavelmente clara
- Status de atividade
- Ativa
- Stack de tecnologia
- aws, python
- Domínio
- backend, cloud, documentation
Direção de pesquisa
Read the companion implementation in PR #111 and the Smithy Python issue #854 and PR #855 to understand the shared compression contract and generation workflow. Then inspect the generated Bedrock Runtime client, its client-level tests, and integration guidance mentioned in the issue. Done means adopting the released Smithy behavior through the normal dependency and generation workflow, testing the client configuration, and documenting the service capability requirement; Bedrock and Mantle support also needs coordination.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
Describe the feature
I'd like the new async Python SDK to expose request-body compression through its generated client configuration, and to establish how Bedrock and Mantle can support it.
We use AWS-hosted models for conversation-heavy agents. As conversations and tool results grow, uploading the next request becomes part of the wait before the first token. Giving applications an explicit compression choice would be a useful product capability for AWS-hosted inference.
Use Case
Anthropic announced gzip in Claude Code, and its changelog documents compression for large requests to api.anthropic.com. OpenAI documents zstd request bodies for the Responses API.
AWS offers models from these providers through Bedrock and its Mantle endpoint. I'd like AWS applications to be able to use supported compression capabilities too, without maintaining custom HTTP transports. Compression can reduce upload time; the benefit depends on payload size and the network. It doesn't reduce model tokens.
In checks on October 18, 2026 in us-east-1, matched requests using Anthropic Haiku succeeded uncompressed through Bedrock Converse/ConverseStream and Mantle Messages, including streaming responses. Gzip and zstd requests returned HTTP 400; Bedrock reported Unable to parse request body. This needs service coordination alongside the SDK implementation.
Proposed Solution
The companion PR adopts Smithy Python's shared compression implementation through the usual generated client configuration. An explicit request_compression_encoding="gzip" choice applies to supported requests without a size threshold, alongside an automatic mode. Unsupported explicit choices and conflicting disable settings fail before sending. The companion implementation supports gzip under the current Smithy contract; zstd needs a coordinated follow-up covering the contract and service support.
The explicit choice makes compression a requirement. A zero automatic threshold would still allow operations without compression metadata to send uncompressed requests; explicit gzip should fail before sending in that case.
The shared runtime and generator changes belong in Smithy Python. This repository should adopt that behavior through its normal generation and dependency workflow, with client-level tests and guidance explaining the service capability requirement. Adoption depends on a Smithy release containing the implementation. We should not manually advertise compression on Bedrock operations that don't accept it.
This generated client covers modeled Bedrock Runtime operations. Mantle's provider-compatible APIs need a separate API/client integration.
The diff includes client tests and guidance for this integration. I'd appreciate feedback on the generation and release process, and help connecting with the Bedrock/Mantle service owners. The checks above cover only the named Haiku routes; they include no OpenAI-route test or latency measurement.
Other Information
Companion implementation: PR.
- Smithy Python: shared runtime and code generation — issue, PR.
- Botocore: explicit compression choice for the existing SDK — issue, PR.
Acknowledgements
- I may be able to implement this feature request
- This feature might incur a breaking change
Affected area
service client (generated client under clients/), code generation, documentation
Relevant package(s)
aws-sdk-bedrock-runtime; shared compression implementation in smithy-python.
Source reviewed at 8f209d245501792c7b18ce197c194170ca4d6564.
Python version used
Python 3.12.13 for the companion implementation's local tests. See the companion PR for validation details.
- Linguagem predominante
- Python
- Estrelas
- 176
- Forks
- 25
- Merge médio
- 3d 3h
- PRs com merge (30d)
- 8
Preparar o ambiente
- Sem Dockerfile nem arquivo Docker Compose
- Sem modelo de pull request
- Ler o guia de contribuição
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de aws/aws-sdk-python
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 72/100
aws/aws-sdk-python#13 ·
Mantenedores costumam responder em até 3 dias
-
Dificuldade 5/5 Mais de uma semana Facilidade para iniciantes 25/100
aws/aws-sdk-python#99 ·
Mantenedores costumam responder em até 3 dias
-
Support Python 3.11Abertafeature-request p3 queued
Dificuldade 5/5 Mais de uma semana Facilidade para iniciantes 35/100
aws/aws-sdk-python#92 ·
Mantenedores costumam responder em até 3 dias
-
announcement
Dificuldade 5/5 Mais de uma semana Facilidade para iniciantes 25/100
aws/aws-sdk-python#90 ·
Mantenedores costumam responder em até 3 dias
-
announcement
Dificuldade 3/5 1-2 dias Facilidade para iniciantes 35/100
aws/aws-sdk-python#84 ·
Mantenedores costumam responder em até 3 dias
Todas as issues de aws/aws-sdk-python
Issues semelhantes
-
get_page_thumbnail modifies cached page images, affecting later thumbnails and picture exportsAberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 68/100
docling-project/docling-mcp#147 ·
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 80/100
Mantenedores costumam responder em até 1 dia
-
enhancement
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 76/100
autowarefoundation/autoware_carla_scenario#405 ·
Mantenedores costumam responder em até 1 dia
-
bug
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 79/100
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
mohitmishra786/readprism#322 ·
Mantenedores costumam responder em até 1 dia