Release v0.3.18#292
Merged
Merged
Conversation
) Step 10 (Check the selected eval runner) was a 387-line wall covering azd recipe init, smoke gate, multi-turn upgrade, optional Foundry full conversations, rubric creation, ASSERT runner, Red Team runner, and the evidence pack pull-in. Readers were dropping off mid-step. Split into three focused steps without changing any technical content or removing the optional multi-turn / Foundry portal path: - Step 10: Initialize the azd eval recipe and run the smoke gate. - Step 11: Harden the gate with the conversation-aware dataset and the Travel Agent rubric. Keeps the 'Optional: Full conversations in the Foundry portal' subsection. - Step 12: Add ASSERT and Red Team to the release gate (absorbs the former 10a/10b/10c subsections, including the evidence pack pull-in). Renumber sections 11..18 to 13..20 and update 9 internal cross-references ('in step 13' to 'in step 15', 'in step 16' to 'in step 18', 'workflows in step 11' to 'workflows in step 13', 'in step 12' to 'in step 14', 'baseline run in step 13' to 'baseline run in step 15'). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…tart (#290) Replace 'open-source framework and CLI' with 'open-source AgentOps jumpstart' in the README badge subtitle and Overview. Framework implied something users had to inherit from or build inside, which AgentOps is not — it orchestrates external tools (Foundry Evaluations, ASSERT, PyRIT, Azure Monitor, azd) and ships normalized evidence. Also add 'observability' to the activity list so the descriptor reflects that AgentOps surfaces App Insights production telemetry through the Cockpit and Doctor, not just release-gate evaluation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When `execution: azd` fails, `agentops eval run` previously bubbled up only the active azd spinner line (e.g. `Resolving eval context...`), giving users no actionable diagnostic. The runner now includes the full command, exit code, and both stderr and stdout in the error, and persists raw streams to `.agentops/results/<ts>/azd_eval_run_{stdout,stderr}.log` (plus matching `azd_eval_show_*` files when the show step fails).
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 v0.3.18
Automated release branch created from
develop.What happened
release/v0.3.18created fromdevelopCHANGELOG.mdupdated: versioned section[0.3.18]added0.3.18(package.json, plugin.json, marketplace.json)Next steps
maingit tag v0.3.18 && git push origin v0.3.18git checkout develop && git merge main && git push origin developChecklist
v0.3.18pushed