Anant Goel
d12b980ee0
Adds native support for AWS Bedrock's Mantle endpoint (`bedrock-mantle`), which serves models with no `Converse`/`Invoke` support on `bedrock-runtime`, such as GPT-5.5, GPT-5.4, and Grok 4.3 but more importantly **open-weight** models Closes #60471 ## What's changed - Renamed the existing `Model` enum in the `bedrock` crate to `ConverseModel`, and added a new `MantleModel` enum for Mantle-only models. Mantle models reuse the existing OpenAI-compatible Chat Completions/Responses request and response plumbing (`into_open_ai`/`into_open_ai_response`, `OpenAiEventMapper`/`OpenAiResponseEventMapper`) already used by the native OpenAI and OpenAI-compatible providers, rather than introducing new marshalling code. - Added a `BedrockMantleModel` language model that routes requests to the `bedrock-mantle` endpoint, dispatching to Chat Completions or the Responses API depending on the model. Mantle models appear in the model picker alongside Converse models under the same Bedrock provider. - Added region gating: `bedrock-mantle` is only available in a subset of AWS Regions, so using a Mantle model outside of them surfaces a clear error naming the current Region and the supported ones, instead of an opaque HTTP failure. - Implemented Bedrock bearer token authentication for Mantle requests: a configured Bedrock API key is used as-is, and every other auth method (IAM credentials, named profile, SSO, automatic) derives a short-term token by locally SigV4-presigning a `CallWithBearerToken` request. This requires no extra network round trip and no token caching, since re-signing locally is cheap. - Added a specific error for the 403 you get when your credentials have `bedrock:CallWithBearerToken` but not the separate `bedrock-mantle:CallWithBearerToken` permission Mantle models require, since this is the most common misconfiguration. - Added a `mantle_available_models` setting so custom models served through `bedrock-mantle` can be configured, the same way other providers support custom models via `available_models`. - Documented Mantle models and the new setting in the Amazon Bedrock section of [Use a Gateway](https://zed.dev/docs/ai/use-a-gateway#amazon-bedrock). ## Testing - Added unit tests covering: the local SigV4 bearer-token signing (including a byte-for-byte cross-check against a reference implementation), Mantle endpoint URL construction, the Mantle-supported-regions list, thinking-effort normalization, and the settings-to-model protocol mapping. - `cargo test -p bedrock -p language_models -p settings_content -p settings` passes. - `./script/clippy` passes with no new warnings. Release Notes: - Added native support for AWS Bedrock's Mantle endpoint, enabling GPT-5.5, GPT-5.4, and Grok 4.3 through the Amazon Bedrock provider.
85 lines
2.8 KiB
TOML
85 lines
2.8 KiB
TOML
[package]
|
|
name = "language_models"
|
|
version = "0.1.0"
|
|
edition.workspace = true
|
|
publish.workspace = true
|
|
license = "GPL-3.0-or-later"
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[lib]
|
|
path = "src/language_models.rs"
|
|
|
|
[dependencies]
|
|
ai_onboarding.workspace = true
|
|
async-lock.workspace = true
|
|
anthropic = { workspace = true, features = ["schemars"] }
|
|
anyhow.workspace = true
|
|
aws-config = { workspace = true, features = ["behavior-version-latest"] }
|
|
aws-credential-types = { workspace = true, features = ["hardcoded-credentials"] }
|
|
aws-sigv4.workspace = true
|
|
aws_http_client.workspace = true
|
|
base64.workspace = true
|
|
bedrock = { workspace = true, features = ["schemars"] }
|
|
client.workspace = true
|
|
cloud_api_client.workspace = true
|
|
cloud_api_types.workspace = true
|
|
collections.workspace = true
|
|
component.workspace = true
|
|
convert_case.workspace = true
|
|
copilot.workspace = true
|
|
copilot_chat.workspace = true
|
|
copilot_ui.workspace = true
|
|
credentials_provider.workspace = true
|
|
deepseek = { workspace = true, features = ["schemars"] }
|
|
extension.workspace = true
|
|
extension_host.workspace = true
|
|
fs.workspace = true
|
|
futures.workspace = true
|
|
google_ai = { workspace = true, features = ["schemars"] }
|
|
gpui.workspace = true
|
|
gpui_tokio.workspace = true
|
|
http_client.workspace = true
|
|
language.workspace = true
|
|
language_model.workspace = true
|
|
language_models_cloud.workspace = true
|
|
llama_cpp = { workspace = true, features = ["schemars"] }
|
|
lmstudio = { workspace = true, features = ["schemars"] }
|
|
log.workspace = true
|
|
menu.workspace = true
|
|
mistral = { workspace = true, features = ["schemars"] }
|
|
oauth_callback_server.workspace = true
|
|
ollama = { workspace = true, features = ["schemars"] }
|
|
open_ai = { workspace = true, features = ["schemars"] }
|
|
opencode = { workspace = true, features = ["schemars"] }
|
|
open_router = { workspace = true, features = ["schemars"] }
|
|
rand.workspace = true
|
|
release_channel.workspace = true
|
|
schemars.workspace = true
|
|
sha2.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
settings.workspace = true
|
|
smol.workspace = true
|
|
strum.workspace = true
|
|
tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
|
|
ui.workspace = true
|
|
ui_input.workspace = true
|
|
url.workspace = true
|
|
util.workspace = true
|
|
x_ai = { workspace = true, features = ["schemars"] }
|
|
|
|
[dev-dependencies]
|
|
client = { workspace = true, features = ["test-support"] }
|
|
clock = { workspace = true, features = ["test-support"] }
|
|
cloud_llm_client.workspace = true
|
|
db = { workspace = true, features = ["test-support"] }
|
|
feature_flags.workspace = true
|
|
gpui = { workspace = true, features = ["test-support"] }
|
|
http_client = { workspace = true, features = ["test-support"] }
|
|
language_model = { workspace = true, features = ["test-support"] }
|
|
parking_lot.workspace = true
|
|
pretty_assertions.workspace = true
|
|
settings = { workspace = true, features = ["test-support"] }
|