Skip to content

fix: RESULTS decline-type note + backend-aware outage toggle - #31

Merged
abhay-codes07 merged 1 commit into
mainfrom
fix/results-decline-note-and-outage-toggle
Sep 5, 2026
Merged

fix: RESULTS decline-type note + backend-aware outage toggle#31
abhay-codes07 merged 1 commit into
mainfrom
fix/results-decline-note-and-outage-toggle

Conversation

@abhay-codes07

Copy link
Copy Markdown
Owner

Two small fixes plus a clean frontend audit.

  • RESULTS decline-type note (judge pre-empt). Live gpt-4o is 99.0% because two impossible tasks are scored misses: the agent correctly refused both but cited a stock shortfall where the label expected a budget walk-away — both valid reasons to refuse the same impossible order, never a wrong order. The generator now emits one sentence saying so whenever accuracy < 100%; RESULTS.md re-rendered from the committed results.json, no numbers changed.
  • Backend-aware outage toggle. /dev/chaos returns 400 on the deterministic offline backend (nothing to take down), so the playground 'Model down' toggle now shows only when the backend can actually be taken down. A judge on the reproducible fake backend no longer sees a 400 on click.
  • Frontend audit clean: headless render of all six pages in light + dark, plus compile / playground-send / toggle flows → 0 console errors, 0 failed requests.

96 tests, ruff clean, console typechecks and builds.

🤖 Generated with Claude Code

https://claude.ai/code/session_01BLrj9TWybDCNw1mWxZgAks

…n deterministic backend

The live-gpt-4o accuracy is 99.0% because two impossible tasks are scored
as misses: the agent correctly refused both but declined on a stock
shortfall where the label expected a budget walk-away. Both are valid
reasons to refuse the same impossible order, so they are correct declines
with a stricter-than-necessary label, never a wrong order. The results
generator now emits a sentence saying so whenever accuracy < 100%, so a
judge does not have to ask; RESULTS.md is re-rendered from the committed
results.json, no numbers changed.

Also: the playground "Model down" toggle called /dev/chaos, which returns
400 on the deterministic offline backend (nothing to take down). The
toggle is now shown only when the backend can actually be taken down
(openai/groq/anthropic), so the reproducible fake backend no longer logs
a 400 on click. Full headless render audit is clean: 0 console errors, 0
failed requests across all six pages in light and dark.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BLrj9TWybDCNw1mWxZgAks
Copilot AI lite review requested due to automatic review settings September 5, 2026 13:54

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@abhay-codes07
abhay-codes07 merged commit a3f95c7 into main Sep 5, 2026
2 checks passed
@abhay-codes07
abhay-codes07 deleted the fix/results-decline-note-and-outage-toggle branch September 5, 2026 13:59
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.

2 participants