Repository navigation
Permalink
Comparing changes
Choose two branches to see what’s changed or to start a new pull request.
If you need to, you can also or
learn more about diff comparisons.
Open a pull request
Create a new pull request by comparing changes across two branches. If you need to, you can also .
Learn more about diff comparisons here.
...
- 4 commits
- 195 files changed
- 3 contributors
Commits on Oct 13, 2026
-
feat: v1alpha1 protobuf contract + native gRPC (#251)
* chore: cleanup * feat(api): add the v1alpha1 protobuf contract with generated Go, Python and TypeScript code * feat(api): build session and turn views with token presence and coded gaps * feat(api): serve the v1alpha1 gRPC API with session watch, runs and evaluation, plus redaction and storage fixes * feat(ui): render the live view and annotation queue from server session views * chore(ui): make eslint clean and run it in CI * feat(chart): ship the gRPC API port in the image and chart, tag the Go module on release, and document the API * test(api): cover the v1alpha1 gRPC services, converters, views, redaction, self tracing, watchers and Postgres repos * fix(ui): commit the generated OTLP logs module hidden by the logs gitignore rule, and fail proto-check on ignored generated files
-
Give rubric_based_* metrics a public rubric path (#132) (#229)
* Give rubric_based_* metrics a public rubric path (#132) The rubric-based metrics have been reachable only through the internal build_eval_metric(..., rubrics=...) call: the metric builder accepted rubrics, the eval-set format documented them on cases and invocations, and nothing on the config, CLI or API path passed any of them through, so the metrics were listed as not working. Rubrics can now be declared on a builtin evaluator in the eval config, as {id, text} mappings or plain strings with positional ids, with duplicate ids refused. At run time the runner matches the eval case, not only its conversation, and the matched case's rubrics and each expected invocation's rubrics are attached to the actual invocations the way ADK's own eval service attaches them, with the metric's rubric type given to rubrics that have none, since ADK applies invocation rubrics by type. A rubric metric with no rubric from the config, the case or an invocation reports an error before any judge call rather than an empty evaluation. Its result carries per-rubric scores per invocation and overall in details. The API lists the rubric metrics as working. * docs: a case-level rubric is judged once per invocation * fix(rubrics): retain ADK parity on the public evaluation path * fix(rubrics): keep conversation metric unavailable until integrated * test(rubrics): cover clarification and completion through the public path * refactor(rubrics): one rubric metric constant, rubrics on the v1alpha1 contract --------- Co-authored-by: krisztianfekete <[email protected]>
-
Loading
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff v0.10.0...v0.11.0