Skip to content

test(eval): collect reproducible trial inputs - #436

Merged
jackh726 merged 3 commits into
mainfrom
feat/agent-eval-evidence
Nov 16, 2026
Merged

jackh726 merged 3 commits into
mainfrom
feat/agent-eval-evidence

Conversation

@gmemuriuki

@gmemuriuki gmemuriuki commented Nov 9, 2026 •

Copy link
Copy Markdown
Contributor

What does this PR do?

The evaluator needs to record exactly what a trial ran before it can produce a useful result.

This reads Claude's reported model, version, usage, and final response, resolves expected skills back to their sources, and records stable digests for the task, plugins, and staged tools. The readers are kept independent from Symposium's production readers so that the evaluator
does not verify the product using the same implementation.

The tests cover recorded Claude transcripts, malformed and ambiguous skill sources, and the digest encoding.

Stack: #436 → #437 → #438 → #439 → #441 → #442 → #443

Disclosure questions

AI disclosure.

  • The AI tool authored large parts of the code

Questions for reviewers.

Are these the right inputs to record for a reproducible trial?

@fnzko fnzko left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for this. I've gone through it mainly by testing, not read the code in full detail (deferred that to Claude's). I left inline comments on #438, #439, #441 and #443

Besides those, a few things the RFD already asks for that seem worth doing in this stack, because this runner looks like the base for plugin authors' own evals (Benches like SWE-benches) we discussed a few days ago:

  • I love the approach, but the whole thing is done with a simulated client. To leave this in a better position for follow-up, I'd add a real agent run (if the real one has a different transcript, isn't reloading skills/hooks, or behaves differently, nothing ends up making sense).
  • Numbering trials by round shall be here, since in the RFD one round is trial-1-without-symposium + trial-1-with-symposium, but a capability batch now gives trial-1-... and trial-2-.... Easy to change now, after --trials it means a schema_version bump.

@gmemuriuki
gmemuriuki force-pushed the feat/agent-eval-evidence branch from df6cd19 to 4f20634 Compare November 9, 2026 16:57
@gmemuriuki

Copy link
Copy Markdown
Contributor Author
  • I love the approach, but the whole thing is done with a simulated client. To leave this in a better position for follow-up, I'd add a real agent run (if the real one has a different transcript, isn't reloading skills/hooks, or behaves differently, nothing ends up making sense).

I don't follow. WDYM?

@gmemuriuki

Copy link
Copy Markdown
Contributor Author
  • I love the approach, but the whole thing is done with a simulated client. To leave this in a better position for follow-up, I'd add a real agent run (if the real one has a different transcript, isn't reloading skills/hooks, or behaves differently, nothing ends up making sense).

I don't follow. WDYM?

Would you run it for me, so we can inspect the retained artifacts to confirm the above. If it exposes a real-client difference then, I'll address the concrete failure.

@gmemuriuki gmemuriuki self-assigned this Nov 10, 2026
gmemuriuki and others added 3 commits November 16, 2026 13:46
Read the model, token usage and final message from the transcript,
for result.json and response.txt. Usage is unsupported, reported or
unknown, so an empty field never hides a reader failure.

Sum modelUsage over models, since it covers subagents. Count an error
subtype as an error even when is_error is false.
Find the SKILL.md behind each expected skill as Symposium finds a
registry plugin's: a skill it would load, named by its frontmatter,
one origin per name. Reject a needed skill no plugin provides, any
skill two origins provide, and links a trial cannot copy.

Read each plugin manifest once for hooks and skills, and conclude
nothing when a plugin directory is missing.

Co-authored-by: Codex <codex@openai.com>
Copy the task, its fixtures, and its plugins into the batch once, and
create every trial from that snapshot, which create_trial now requires
and checks is its own batch's. The content hash is the snapshot's
digest, and the staged cargo-agents copy is hashed too.

A tree's digest covers sorted relative paths, entry kinds, and file
bytes, each length-prefixed; timestamps, permissions, and absolute
paths are left out, and links refused.
@gmemuriuki
gmemuriuki force-pushed the feat/agent-eval-evidence branch from 4f20634 to 4dc5878 Compare November 16, 2026 11:31
@jackh726
jackh726 added this pull request to the merge queue Nov 16, 2026
Merged via the queue into main with commit 727e5f1 Nov 16, 2026
8 checks passed
@jackh726
jackh726 deleted the feat/agent-eval-evidence branch November 16, 2026 14:35
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.

3 participants