Release v0.3.19#298
Merged
Merged
Conversation
The `What is smoke-core?` callout previously sat in step 10 right after `agentops eval init`, but the evaluator name is only actually needed in step 11 where `Find the evaluator name` already explains the same content in proper context. Removing the duplicate keeps step 10 focused on running the smoke gate. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Step 11 previously told readers to `find the entry with a local_uri` without saying what that evaluator (`smoke-core` in the seeded eval.yaml) actually is or where it came from. Add a short paragraph right before `Find the evaluator name` that explains the difference between the built-in evaluators and the auto-generated local rubric evaluator, and why `rubrics:` in agentops.yaml reference its name. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
) azd ai agent eval emits one aggregate pass-rate metric per evaluator (coherence, fluency, smoke-core), not one metric per rubric dimension. Step 11.3 previously instructed readers to set thresholds on the dimension ids (correct_itinerary, adherence_to_constraints, clear_practical_notes), which always fails with `threshold metric(s) not found in azd results`. Switch the example thresholds to the evaluator names azd actually emits (0..1 pass-rate scale) and add a callout explaining why dimension-level thresholds are not supported today. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The tutorial previously stopped at the terminal's aggregate pass/fail output, which makes the eval steps feel like a black box. Add a reusable `See the run in the Foundry portal` section at the end of step 10 (deep-link via results report_url + manual nav + what each pane shows) and link back to it from the step 11 multi-turn re-run and the step 11.4 rubric re-run. Step 11.4 also gets an explicit walkthrough of the `View rubric details` modal so users see the per-dimension judge scores even though the CLI threshold lives on the aggregate. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…k, terser logs (#297) Four user-visible issues with `execution: azd` runs: 1. `report.md` shipped an empty `Dataset:` line because the eval.yaml parser only recognized `dataset_reference:` and `azd ai agent eval init` actually emits `dataset_file:`. EvalRecipe now accepts `dataset_file:` and `_recipe_dataset_path` prefers it. 2. `report.md` shipped a header-only `## Rows` table on every azd run (azd does not expose per-row metrics through `agentops eval run`). The reporter now omits the row sections when `result.rows` is empty and instead emits a `## Per-row breakdown` callout linking to the Foundry run. 3. The CLI did not surface the Foundry run URL. `azd_runner.normalize_to_results` now captures `report_url` from the azd payload and the CLI prints a `Foundry run:` line next to the results paths. 4. `Running azd backend: azd --no-prompt ai agent eval run --config <long absolute path> --output json` was unreadable; replaced with `Running azd backend: azd ai agent eval run` (full command stays in the failure debug logs added in 0.3.18). The `delegating to azd ai agent eval` startup line also uses a workspace-relative recipe path. 921 unit tests pass. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Release v0.3.19
Automated release branch created from
develop.What happened
release/v0.3.19created fromdevelopCHANGELOG.mdupdated: versioned section[0.3.19]added0.3.19(package.json, plugin.json, marketplace.json)Next steps
maingit tag v0.3.19 && git push origin v0.3.19git checkout develop && git merge main && git push origin developChecklist
v0.3.19pushed