adapter-classifier-llm

Classifier over the venture's own TextModel, via JSON-schema structured output.

With cargo

cargo add cratefield-adapter-classifier-llm

What it is

adapter-classifier-llm.

Classifier port over the harness's own TextModel port for the Cratefield harness (issue #456). The third of the three Classifier adapters and the only one with no vendor of its own: it reaches whichever model the venture's TextModel tiers are wired to — a local model included — asking for JSON-schema structured output. When neither a purpose-trained classifier nor a vendor binding is wired, this is the honest fallback.

From the crate’s own README.

Ports

Implements Classifier

Read more

History

Changelog.

From the crate’s CHANGELOG.md in the harness, as of 0c5560b. 4 versions recorded, newest first. Every published version is on crates.io.

  1. 0.3.2

    crates.ioReleaseDiff

    Other

    • updated the following local packages: cratefield-core
  2. 0.3.1

    crates.ioReleaseDiff

    Other

    • updated the following local packages: cratefield-core
2 earlier versions 0.2.1 to 0.3.0
  1. 0.3.0

    crates.ioReleaseDiff

    Changed

    • Breaking: requires cratefield-core 0.8 (was 0.7), and so a minor rather than a patch bump: a venture still on core 0.7 does not pick this release up through a caret requirement and end up with two copies of core (#712).

    Other

    • tool calling (ToolSpec, tool_calls, run_tool_loop) across the Anthropic and OpenAI-compatible adapters (#665) (#705)
  2. 0.2.1

    crates.ioRelease

    Other

    • updated the following local packages: cratefield-core

One of 76 crates in the harness, all of them MIT and all of them in one repository.