Files
centdix 79ac6312e8 feat(ai): handle aws bedrock as provider (#7155)
* backend draft

* fix for tool and streaming

* do frontend side

* working

* working tools

* rm

* handle list endpoint

* handle for ai agents

* fix for models requiring inference id

* cleaning

* fix desc issue

* fix tool usage

* fix structured output

* cleaning

* fix for api

* rm

* fix input images

* cleaning

* chore: use aws sdk (#7156)

* feat(ai): Add AWS SDK dependencies for Bedrock integration

- Add aws-sdk-bedrockruntime v1.113.0
- Add aws-credential-types for bearer token authentication
- Update rustls to v0.23.35 for compatibility
- Dependencies added to windmill-common for AI features

* feat(ai): Add bearer token provider for Bedrock authentication

- Implement BearerTokenProvider using aws_credential_types
- Simple token-based auth using API keys from Windmill resources
- Add basic unit tests for provider creation
- Export bedrock_auth module in lib.rs

* feat(ai): Add Bedrock client wrapper with region extraction

- Implement BedrockClient wrapper around AWS SDK client
- Bearer token authentication integration
- Extract AWS region from Bedrock base URL automatically
- Comprehensive unit tests for region extraction
- Make aws-config non-optional dependency for AI features
- Update feature flags to reflect new dependency structure

* cargo

* feat(ai): Implement non-streaming Bedrock via AWS SDK

Use official AWS SDK instead of manual HTTP requests for better type safety and maintainability. Implements the Bedrock converse() API for non-streaming requests with proper bearer token authentication and message format conversion between OpenAI and Bedrock formats.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* refactor(ai): Eliminate Simple* conversion types for Bedrock SDK

- Move AI types to windmill-common/src/ai_types.rs for shared access
- Update bedrock_converters to work directly with OpenAI types
- Remove ~200 lines of conversion boilerplate from ai_executor.rs and bedrock.rs
- Remove unused imports to clean compilation warnings
- Benefits: 50% fewer conversion steps, no information loss, easier maintenance

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat(ai): Add streaming support for AWS Bedrock SDK

- Implement converse_stream() for Bedrock streaming responses
- Use EventReceiver.recv() to process stream events
- Extract text deltas using bedrock_stream_event_to_text()
- Send TokenDelta events to StreamEventProcessor for real-time updates
- Refactor request building to eliminate duplication between streaming and non-streaming
- Clean, minimal implementation following AWS SDK patterns

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* revert flake change

* fix

* feat(ai): Add tool calls and image support for Bedrock streaming

**Phase 1: Streaming Tool Call Support**
- Add stream event processing functions in bedrock_converters.rs:
  - bedrock_stream_event_to_tool_start() - Extract tool use start from ContentBlockStart
  - bedrock_stream_event_to_tool_delta() - Extract tool input deltas from ContentBlockDelta
  - bedrock_stream_event_is_block_stop() - Detect ContentBlockStop events
  - streaming_tool_calls_to_openai() - Convert accumulated tool calls to OpenAI format
- Update ai_executor.rs streaming loop with tool call accumulator (HashMap)
- Track current tool use ID during streaming
- Send ToolCallArguments events to StreamEventProcessor
- Return accumulated tool calls instead of empty vector

**Phase 2: Image Input Support**
- Add parse_image_data_url() to extract format and base64 data from data URLs
- Add content_part_to_block() to convert ContentPart to Bedrock ContentBlock
- Refactor convert_message() to handle multi-part content with images
- Support ImageUrl conversion to Bedrock ImageBlock with proper format (png/jpeg/gif/webp)
- Import AWS SDK image types: ImageBlock, ImageSource, ImageFormat
- Keep content_to_text() helper for system message text extraction

**Benefits**:
-  Tool calling now works in both streaming and non-streaming modes
-  Images are properly converted instead of being silently dropped
-  Structured output works in streaming (uses tool calling)
-  Full feature parity with manual HTTP implementation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* cleaning

* fix(ai): Add S3 image support and structured output for Bedrock

**Fixes:**
1. **S3 Image Support**: Call prepare_messages_for_api() before Bedrock SDK path to convert S3Objects to ImageUrls
   - Downloads images from S3 and encodes as base64 data URLs
   - Ensures images are properly handled in both streaming and non-streaming modes

2. **Structured Output**: Add ToolChoice::Any when structured output tool is present
   - Forces Bedrock to call the structured_output tool
   - Ensures JSON schema compliance for structured output
   - Works in both streaming and non-streaming modes

**Changes:**
- ai_executor.rs: Call prepare_messages_for_api() for Bedrock SDK path
- ai_executor.rs: Set tool_choice to Any when structured_output_tool_name is present
- aws_bedrock.rs: Remove unused ToolChoice imports (used via full path in worker)

**Testing:**
-  S3 images are now downloaded and converted before API call
-  Structured output now forces tool usage with ToolChoice::Any
-  Both work in streaming and non-streaming modes

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* cleaning

* cleaning

* cleaning

* better error

* cleaning

* cleaning

* rm

* rename

* apply region

---------

Co-authored-by: Claude <noreply@anthropic.com>

* fix default

* no panic

* no print

* use utils file

* cleaning

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-11-17 18:57:59 +00:00

158 lines
5.9 KiB
TOML

[package]
name = "windmill-worker"
version.workspace = true
authors.workspace = true
edition.workspace = true
[lib]
name = "windmill_worker"
path = "src/lib.rs"
[features]
default = []
private = []
prometheus = ["dep:prometheus", "windmill-common/prometheus"]
enterprise = ["windmill-queue/enterprise", "windmill-git-sync/enterprise", "windmill-common/enterprise", "dep:pem", "dep:tokio-util"]
mssql = ["dep:tiberius"]
bigquery = ["dep:gcp_auth"]
benchmark = ["windmill-queue/benchmark", "windmill-common/benchmark"]
parquet = ["windmill-common/parquet", "dep:object_store"]
flow_testing = []
cloud = []
sqlx = []
deno_core = ["dep:deno_fetch", "dep:deno_webidl", "dep:deno_web", "dep:deno_net", "dep:deno_console", "dep:deno_url", "dep:deno_core",
"dep:deno_ast", "dep:deno_tls", "dep:deno_permissions", "dep:deno_io", "dep:deno_runtime", "dep:deno_telemetry", "dep:deno_error", "dep:winapi"]
libffi_mac = ["dep:libffi-sys"]
otel = ["windmill-common/otel", "dep:opentelemetry"]
dind = ["dep:bollard"]
php = ["dep:windmill-parser-php"]
mysql = ["dep:mysql_async"]
oracledb = ["dep:oracle"]
python = ["dep:windmill-parser-py", "dep:windmill-parser-py-imports"]
csharp = ["dep:windmill-parser-csharp"]
rust = ["dep:windmill-parser-rust"]
nu = ["dep:windmill-parser-nu"]
java = ["dep:windmill-parser-java"]
ruby = ["dep:windmill-parser-ruby"]
duckdb = ["dep:libloading"]
[dependencies]
windmill-queue.workspace = true
windmill-audit.workspace = true # there isn't really a reason for audit-worth actions to happen in the worker.
windmill-common = { workspace = true, default-features = false }
windmill-macros.workspace = true
windmill-parser.workspace = true
windmill-parser-ts.workspace = true
windmill-parser-go.workspace = true
windmill-parser-rust = { workspace = true, optional = true }
windmill-parser-csharp = { workspace = true, optional = true }
windmill-parser-nu = { workspace = true, optional = true }
windmill-parser-java = { workspace = true, optional = true }
windmill-parser-ruby = { workspace = true, optional = true }
windmill-parser-py = { workspace = true, optional = true }
windmill-parser-yaml.workspace = true
windmill-parser-py-imports = { workspace = true, optional = true }
windmill-parser-bash.workspace = true
windmill-parser-sql.workspace = true
windmill-parser-graphql.workspace = true
windmill-parser-php = { workspace = true, optional = true }
windmill-git-sync.workspace = true
rmcp = { version = "0.8.1", features = ["client", "transport-streamable-http-client", "transport-streamable-http-client-reqwest"] }
aws-sdk-bedrockruntime.workspace = true
aws-config.workspace = true
aws-credential-types.workspace = true
aws-smithy-types.workspace = true
flume.workspace = true
sqlx.workspace = true
uuid.workspace = true
ulid.workspace = true
tracing.workspace = true
tokio.workspace = true
tokio-stream.workspace = true
serde.workspace = true
serde_json.workspace = true
futures.workspace = true
async-recursion.workspace = true
async-trait.workspace = true
anyhow.workspace = true
itertools.workspace = true
regex.workspace = true
prometheus = { workspace = true, optional = true }
lazy_static.workspace = true
chrono.workspace = true
dotenv.workspace = true
rand.workspace = true # TODO: Remove. only used by token creation hack.
const_format.workspace = true
mappable-rc.workspace = true
git-version.workspace = true
dyn-iter.workspace = true
once_cell.workspace = true
tokio-postgres.workspace = true
bit-vec.workspace = true
url.workspace = true
deno_telemetry = { workspace = true, optional = true }
deno_fetch = { workspace = true, optional = true }
deno_webidl = { workspace = true, optional = true }
deno_web = { workspace = true, optional = true }
deno_net = { workspace = true, optional = true }
deno_console = { workspace = true, optional = true }
deno_url = { workspace = true, optional = true }
deno_core = { workspace = true, optional = true }
deno_ast = { workspace = true, optional = true }
deno_tls = { workspace = true, optional = true }
deno_permissions = { workspace = true, optional = true }
deno_io = { workspace = true, optional = true }
deno_error = { workspace = true, optional = true }
async-stream.workspace = true
postgres-native-tls.workspace = true
native-tls.workspace = true
mysql_async = { workspace = true, optional = true }
base64.workspace = true
gcp_auth = { workspace = true, optional = true }
rust_decimal.workspace = true
jsonwebtoken.workspace = true
sha2.workspace = true
pem = { workspace = true, optional = true }
urlencoding.workspace = true
nix.workspace = true
bytes.workspace = true
reqwest.workspace = true
reqwest-middleware.workspace = true
eventsource-stream.workspace = true
mime_guess.workspace = true
hex.workspace = true
tiberius = { workspace = true, optional = true }
tokio-util = { workspace = true, optional = true }
tar.workspace = true
object_store = { workspace = true, optional = true}
convert_case.workspace = true
yaml-rust.workspace = true
backon.workspace = true
winapi = { workspace = true, optional = true }
pep440_rs.workspace = true
process-wrap.workspace = true
async-once-cell.workspace = true
libloading = { workspace = true, optional = true }
opentelemetry = { workspace = true, optional = true }
bollard = { workspace = true, optional = true }
oracle = { workspace = true, optional = true }
[build-dependencies]
deno_fetch = { workspace = true, optional = true }
deno_webidl = { workspace = true, optional = true }
deno_web = { workspace = true, optional = true }
deno_net = { workspace = true, optional = true }
deno_console = { workspace = true, optional = true }
deno_url = { workspace = true, optional = true }
deno_core = { workspace = true, optional = true }
deno_ast = { workspace = true, optional = true }
deno_tls = { workspace = true, optional = true }
deno_permissions = { workspace = true, optional = true }
deno_io = { workspace = true, optional = true }
deno_runtime = { workspace = true, optional = true }
deno_telemetry = { workspace = true, optional = true }
winapi = { workspace = true, optional = true }
libffi-sys = { workspace = true, optional = true }