Repository navigation
docs: full per-scenario TEST_REPORT (run5) + believability pass/fail detail - #10
Merged
Merged
Conversation
…ss/fail detail
Per request: detailed pass/fail in the TEST_REPORT.html style.
- eval/test_report.py: parameterised (--results <dir>, --out) so the full per-scenario
report can pair the current narrations (eval/hourly_runs batches) with any judged run;
judge-model note updated to all-Sonnet/run5.
- eval/hourly_runs/TEST_REPORT.{md,html}: REGENERATED from run5 (Phase A + M3 + renderer
fix + coherent corpus) — 2686/2800 = 95.9%; aggregate tables + every scenario as an
expandable PASS/FLAG with its stimulus (input events) and the exact narration the judge
saw, all-Sonnet.
- eval/BELIEVABILITY_REPORT.{md,html}: added §7 detailed pass/fail (114 run5 FLAGs by
persona/sub-corpus + filterable full list; unit-test inventory 307 collected / 303
passed / 4 skipped) and pointers to the full TEST_REPORT.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
RobertMalczyk
pushed a commit
that referenced
this pull request
Jun 24, 2026
Integrate the advanced main (believability/eval work, PRs #9/#10) before merging M-MEM back. Conflict-free. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016rWVvvhWijSuLMEhzjiUhu
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the detailed pass/fail in TEST_REPORT.html style, regenerated from the final run5 (95.9%).
eval/hourly_runs/TEST_REPORT.{md,html}regenerated from run5: aggregate tables + every scenario as an expandable PASS/FLAG with its stimulus (input events) and the exact narration the judge saw (all-Sonnet, 2686/2800).eval/test_report.pyparameterised (--results/--out) so the report can pair current narrations with any judged run.eval/BELIEVABILITY_REPORT.{md,html}gain a detailed pass/fail section (114 run5 FLAGs by persona/sub-corpus + filterable list; unit-test inventory 307 collected / 303 passed / 4 skipped) + pointers to the full report.Docs only — no engine/test changes.
🤖 Generated with Claude Code