Commit Graph

282 Commits

Author SHA1 Message Date
Rich Haines 8fea011ea6 Merge pull request #147 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@1.0.0
2026-06-01 19:12:13 +02:00
github-actions[bot] 1ee6ee852e Version Packages 2026-06-01 17:11:11 +00:00
Rich Haines 17f5987722 Merge pull request #146 from vercel-labs/feat/native-default-model-policy
Use native model defaults when model is omitted
2026-06-01 19:10:24 +02:00
molebox cedf84b4bc Use native default when model is omitted 2026-06-01 18:48:13 +02:00
molebox aa66c4d35b Add native default model policy 2026-06-01 17:01:36 +02:00
Allen Zhou e4587b5434 Merge pull request #145 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@0.14.5
2026-05-29 17:35:24 -07:00
github-actions[bot] 3db1716a00 Version Packages 2026-05-30 00:34:54 +00:00
Allen Zhou fb4005237c Merge pull request #144 from vercel-labs/revert-141-enable-web-sources
Revert "Enable source-capable web tools for agent runs" (#141)
2026-05-29 17:34:02 -07:00
Allen Zhou 450bed3b94 Add changeset for revert of #141 2026-05-29 17:30:46 -07:00
Allen Zhou 2b7eddf90f Revert "Merge pull request #141 from vercel-labs/feat/enable-agent-web-sources"
This reverts commit daaeccb42c, reversing
changes made to cb2280db61.
2026-05-29 17:30:14 -07:00
Rich Haines ff51aaf83d Merge pull request #143 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@0.14.4
2026-05-29 17:06:41 +02:00
github-actions[bot] e0db9a3813 Version Packages 2026-05-29 15:03:07 +00:00
Rich Haines daaeccb42c Merge pull request #141 from vercel-labs/feat/enable-agent-web-sources
Enable source-capable web tools for agent runs
2026-05-29 17:02:23 +02:00
molebox 74be0aa25b Merge main into feat/enable-agent-web-sources 2026-05-29 16:51:52 +02:00
Allen Zhou cb2280db61 Merge pull request #142 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@0.14.3
2026-05-28 14:04:44 -07:00
github-actions[bot] a53721752b Version Packages 2026-05-28 18:45:17 +00:00
Allen Zhou 43bec69aba Merge pull request #140 from vercel-labs/fix/codex-reasoning-effort-default
Fix Codex profile reasoning_effort and verbosity defaults
2026-05-28 11:44:28 -07:00
molebox 2d27942cc3 Enable source-capable web tools for agent runs 2026-05-28 11:15:10 +02:00
Allen Zhou af62bc3fe9 Remove vercel-agent-eval-*.tgz from .gitignore
Per review feedback. Local `npm pack` artifacts can be cleaned up by
hand; no need for a project-level ignore rule.
2026-05-27 21:34:43 -07:00
Allen Zhou a9efa3ad1f Fix Codex profile reasoning_effort and verbosity defaults
The Codex CLI defaults both `model_reasoning_effort` and `model_verbosity`
to "low", but `gpt-5.2-codex` (the default Codex model) only accepts
"medium" for both. Out-of-the-box `codex exec` against the AI Gateway
fails with:

  Unsupported value: 'low' is not supported with the 'gpt-5.2-codex'
  model. Supported values are: 'medium'.

The error covers both the `reasoning.effort` and `text.verbosity`
request parameters, depending on which the model rejects first.

Set both fields to "medium" in two places:
- the generated profile config in ~/.codex/default.config.toml
- explicit -c flags on `codex exec`, since CLI flags have the highest
  precedence and we observed the profile-only setting being silently
  overridden by the CLI's "low" default in some Codex versions.

`generateCodexConfig` now accepts an optional `reasoningEffort`
parameter so callers can override per-run via
`model: "gpt-5.2-codex?reasoningEffort=high"`.

Verified end-to-end against the Vercel AI Gateway: a previously-failing
`codex exec` smoke run now completes in ~31s and returns a real
response instead of erroring at `turn.failed`.

Also added `vercel-agent-eval-*.tgz` to .gitignore so local `npm pack`
artifacts don't leak into commits.
2026-05-27 20:19:58 -07:00
Allen Zhou 096192204e Merge pull request #139 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@0.14.2
2026-05-27 19:55:33 -07:00
github-actions[bot] 8bb80230c4 Version Packages 2026-05-28 02:55:06 +00:00
Allen Zhou 79d0d3b4a0 Merge pull request #138 from vercel-labs/fix/codex-profile-config
Fix Codex profile config
2026-05-27 19:54:11 -07:00
molebox 5950d74405 Fix Codex profile config 2026-05-27 21:36:53 +02:00
Allen Zhou 330b743167 Merge pull request #130 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@0.14.1
2026-05-20 08:26:39 -07:00
github-actions[bot] 10cfa27c51 Version Packages 2026-05-13 08:02:51 +00:00
Rich Haines e66e522f13 Merge pull request #126 from vercel-labs/neutralize-sandbox-workspace
Neutralize sandbox workspace path
2026-05-13 10:01:50 +02:00
Allen Zhou ea8d7abba6 Neutralize sandbox workspace path 2026-05-06 16:52:56 -07:00
Allen Zhou 475b4bc879 Merge pull request #124 from vercel-labs/changeset-release/main
Version Packages
@vercel/agent-eval@0.14.0
2026-05-05 16:03:42 -07:00
github-actions[bot] 5294461898 Version Packages 2026-05-05 23:02:49 +00:00
Allen Zhou 9bc474f783 Merge pull request #123 from vercel-labs/a0-local-harness-support
Add response-only harness support
2026-05-05 16:01:59 -07:00
Allen Zhou c52126f198 Keep agent config validation strict 2026-05-05 15:58:10 -07:00
Allen Zhou 07614ec3b7 Add response-only harness support 2026-05-05 15:37:24 -07:00
github-actions[bot] f5cba1ea67 Version Packages (#122)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vercel/agent-eval@0.13.1
2026-04-26 08:51:13 -04:00
Jude Gao 384133b982 [CLI] Surface AI Gateway errors during failure classification (#121) 2026-04-26 02:22:46 -04:00
github-actions[bot] f7e79f7a1f Version Packages (#120)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vercel/agent-eval@0.13.0
2026-04-24 23:33:25 -04:00
Jude Gao 748fcc08d3 [Release] Use github-api commit mode for signed commits (#119)
* [CLI] Remove auto-retry of non-model failures

* [Release] Use github-api commit mode for signed commits
2026-04-24 23:31:51 -04:00
Jude Gao 660ea3ea20 [CLI] Remove auto-retry of non-model failures (#118) 2026-04-24 21:52:45 -04:00
github-actions[bot] 4b81d0f676 Version Packages (#116)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vercel/agent-eval@0.12.1
2026-04-17 03:09:12 +08:00
Jude Gao a3c2136f03 [Sandbox] Reconnect on terminated streams to avoid spurious failures on long commands (#115) 2026-04-16 15:06:15 -04:00
github-actions[bot] 69db6fca7b Version Packages (#114)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vercel/agent-eval@0.12.0
2026-04-16 11:39:53 -04:00
Jude Gao a209ae099f [Claude Code] Forward cliPackage and effort agentOptions to the CLI (#113) 2026-04-16 11:38:02 -04:00
github-actions[bot] 4385c53c84 Version Packages (#111)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vercel/agent-eval@0.11.0
2026-04-15 10:53:20 -04:00
Jude Gao f838bd7363 [OpenCode] Pass timeout to provider config (#112) 2026-04-15 10:41:25 -04:00
Jude Gao 481637dd6e Auto-retry non-model failures with configurable retry rounds (#110) 2026-04-14 23:26:27 -04:00
github-actions[bot] 01c6e88322 Version Packages (#109)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vercel/agent-eval@0.10.1
2026-04-14 22:01:08 -04:00
Jude Gao 5185640dde [OpenCode] Deep-merge vercel provider config and use user-space binary path (#108) 2026-04-14 21:57:07 -04:00
Jude Gao cb441f58be fix(ci): remove stale pnpm-lock.yaml to fix changeset publish
Changesets was detecting pnpm-lock.yaml and trying to publish with
pnpm, which isn't installed in CI. The project uses npm.
@vercel/agent-eval@0.10.0
2026-04-14 15:42:58 -04:00
github-actions[bot] 38faa84631 Version Packages (#107)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-14 15:31:11 -04:00
Rune Botten df0dfb6657 fix(codex): append to config.toml instead of overwriting (#104) 2026-04-14 15:28:28 -04:00