The AI Toolchain — issue -231, December 29, 2025

The open source coding agent.

OpenCode v1.0.208 adds Bedrock region/bearer-token config, .claude/skills support, local plugin deps, and desktop image previews.

$ git clone --branch v1.0.208 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.208

• ›Adds support for region and bearer token configuration in Amazon Bedrock provider.
• ›Adds support for .claude/skills directory for organizing reusable skill definitions.
• ›Installs local plugin dependencies from package.json automatically.
• ›Adds auto-accept edits toggle in the desktop application.
• ›Adds image preview and deduplication for file uploads in the desktop application.

$ git clone --branch v1.0.207 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.207

Qwen Code SDK v0.1.1 adds Anthropic/Gemini providers, VSCode extension, /resume command, chat recording, Skills, and terminal bell settings.

$ git clone --branch sdk-typescript-v0.1.1 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout sdk-typescript-v0.1.1

$ /resume

• ›Adds /resume slash command to switch between sessions from the CLI UI.
• ›Adds --resume and --continue CLI options with -r and -C short aliases for session management.
• ›Adds gitCoAuthor setting to settings.json to control git co-author tagging in commits.
• ›Adds chat recording toggle via CLI flag and settings, enabling or disabling session recording.
• ›Adds terminal bell setting to enable or disable audio notifications.

$ git clone --branch v0.6.0-nightly.20251229.2bc80795 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.6.0-nightly.20251229.2bc80795

llama.cpp b7574 adds -to flag for configurable HTTP read timeouts on the inference server.

$ git clone --branch b7574 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7574

$ llama-server -m model.gguf -to 3600

• ›Adds -to command-line argument to server to set a configurable HTTP read timeout (previously fixed at 600 seconds), with internal TTFT crash protection raised to 90 days.
• ›Enables per-child-model HTTP timeout configuration when running server with child models.

$ git clone --branch b7567 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7567

Milvus Go SDK v2.6.2 adds QueryIterator for large result pagination and Struct Array field type support.

$ git clone --branch client/v2.6.2 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:
$ git checkout client/v2.6.2

opt := milvusclient.NewQueryIteratorOption("collection_name").
    WithBatchSize(500).
    WithFilter("age > 18").
    WithOutputFields("id", "name", "vector")

iter, err := client.QueryIterator(ctx, opt)
for {
    rs, err := iter.Next(ctx)
    if errors.Is(err, io.EOF) {
        break
    }
    // process rs...
}

• ›Adds client.QueryIterator(ctx, opt) method for PK-based pagination over large query result sets, supporting both Int64 and VarChar primary key types.
• ›Adds milvusclient.NewQueryIteratorOption with WithBatchSize(int) (default: 1000), WithIteratorLimit(int64), WithFilter(string), WithOutputFields(...string), WithPartitions(...string), and WithConsistencyLevel(ConsistencyLevel) options to configure iteration behavior.
• ›Adds iter.Next(ctx) on the returned iterator, returning io.EOF when exhausted, enabling a standard Go iteration loop over result pages.
• ›Adds columnStructArray column type implementing the Column interface, with support for parsing StructArrayField from protobuf responses and schema construction via entity.FieldTypeArray.