Skip to content

fix(aether-evals): capture agent diff from start commit - #306

Merged
jcarver989 merged 2 commits into
mainfrom
fix/evals-agent-diff-start-commit
Jul 29, 2026
Merged

fix(aether-evals): capture agent diff from start commit#306
jcarver989 merged 2 commits into
mainfrom
fix/evals-agent-diff-start-commit

Conversation

@jcarver989

Copy link
Copy Markdown
Contributor

Summary

  • compare agent changes with the immutable eval start commit in TypeScript and Rust
  • preserve committed, staged, and unstaged tracked changes for grading
  • cover committed, staged, unstaged, added, deleted, and unchanged workspace states
  • bump @aether-agent/evals to 0.3.1

Test plan

  • pnpm --filter @aether-agent/evals typecheck
  • pnpm --filter @aether-agent/evals build
  • pnpm --filter @aether-agent/evals test
  • just test -p aether-evals
  • cargo clippy -p aether-evals --all-targets --all-features --no-deps -- -D warnings
  • cargo fmt --check --all

just lint -p aether-evals is currently blocked by the pre-existing unused ResponsesRequestPolicy::mantle warning in aether-llm; targeted Clippy for aether-evals passes.

Compare the final tracked workspace state with the immutable eval start revision so committed agent changes remain available for grading.
@jcarver989
jcarver989 enabled auto-merge (squash) July 29, 2026 12:33
@jcarver989
jcarver989 merged commit 137c2f1 into main Jul 29, 2026
18 of 19 checks passed
@jcarver989
jcarver989 deleted the fix/evals-agent-diff-start-commit branch July 29, 2026 12:51
jcarver989 pushed a commit that referenced this pull request Jul 29, 2026
## 🤖 New release

* `aether-lspd`: 0.1.28 -> 0.1.29
* `aether-evals`: 0.2.20 -> 0.2.21
* `aether-mcp-servers`: 0.4.34 -> 0.4.35
* `aether-agent-cli`: 0.7.31 -> 0.7.32
* `aether-schemas`: 0.1.15 -> 0.1.16

<details><summary><i><b>Changelog</b></i></summary><p>

## `aether-lspd`

<blockquote>

##
[0.1.29](aether-lspd-v0.1.28...aether-lspd-v0.1.29)
- 2026-07-29

### Fixed

- *(aether-lspd)* Race condition with lsp events
([#308](#308))
</blockquote>

## `aether-evals`

<blockquote>

##
[0.2.21](aether-evals-v0.2.20...aether-evals-v0.2.21)
- 2026-07-29

### Fixed

- *(aether-evals)* capture agent diff from start commit
([#306](#306))
</blockquote>

## `aether-mcp-servers`

<blockquote>

##
[0.4.35](aether-mcp-servers-v0.4.34...aether-mcp-servers-v0.4.35)
- 2026-07-29

### Other

- updated the following local packages: aether-lspd, aether-lspd
</blockquote>

## `aether-agent-cli`

<blockquote>

##
[0.7.32](aether-agent-cli-v0.7.31...aether-agent-cli-v0.7.32)
- 2026-07-29

### Other

- updated the following local packages: aether-lspd, aether-mcp-servers
</blockquote>

## `aether-schemas`

<blockquote>

##
[0.1.16](aether-schemas-v0.1.15...aether-schemas-v0.1.16)
- 2026-07-29

### Other

- updated the following local packages: aether-evals, aether-agent-cli
</blockquote>


</p></details>

---
This PR was generated with
[release-plz](https://github.com/release-plz/release-plz/).

Co-authored-by: contextbridge-pr-automation[bot] <259134118+contextbridge-pr-automation[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant