- Raised the `go` directive from 1.24.1 to 1.26.5 to satisfy pgx/v5 and ollama's minimum Go version requirements and to pick up 15 patched standard library CVEs.
- Updated `pgx/v5`, `otel`/`otel/sdk`/`otlptracehttp`, `x/net`, and the AWS `eventstream` protocol package to their latest requested versions.
- Remediated govulncheck-flagged CVEs in `grpc`, `x/text`, `x/crypto`, `antchfx/xpath`, AWS SDK `bedrock*`/`s3` services, `etcd/server`, and `mongo-driver` v1/v2.
- Fixed ollama's `MainGPU` API type change (`int` -> `*int`) in `llms/ollama/options.go` without breaking the public `WithRunnerMainGPU` signature.
Add a single WithStructuredOutput(StructuredOutputConfig) call option
carrying a raw JSON Schema (Draft 2020-12), so one contract yields the
same guarantee — a normal-final response is a single JSON value matching
the schema — on OpenAI, Anthropic, Bedrock (Converse and legacy), Google
AI, Vertex, and Ollama. Each provider maps it to its native mechanism;
the result is validated locally against the original schema in the new
llms/structuredoutput package. Also fixes a latent Converse gap where the
response stop reason was never surfaced on ContentChoice.StopReason.
- Upgraded `github.com/ollama/ollama` from v0.14.3 to v0.16.3 across multiple modules to ensure compatibility with the latest features and fixes.
- Updated `github.com/klauspost/compress` from v1.18.0 to v1.18.3 in various modules to incorporate performance improvements and bug fixes.
- Adjusted go.mod and go.sum files in relevant examples to reflect these changes, ensuring all examples are using the latest dependency versions.
* examples: update examples, clean up module declarations
- Fix and relax lint rules (for now)
- Clean up and fix module declarations
- Add .gitattributes to mark go.sum as binary
* ci: separate and enhance CI workflows
- Split example builds into dedicated workflow
- Add comprehensive test coverage reporting
- Improve CI structure with matrix testing
- Add race condition testing
- Add automated PR coverage comments
* test: improve test reliability and agent message handling
- Simplify MRKL agent test to use basic math calculation
- Update OpenAI functions agent to use ToolChatMessage
- Add proper environment checks for Zep integration tests
* agents: fix issue in tool call handling for openai function agent
This is the first use of the refactoring made in #374 -- removing the
embeddings/openai directory entirely, since it can be now implemented
with NewEmbedder without duplicating code. The test was moved one
dir down and works with the new setup.
This is a model that can be used to similarly refactor the other
embeddings/* subdirs.
This is a large PR because it also updates example go.mods
For #379
Dmitry Ng