Repository navigation
Conversation
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Draft. The harness for the fresh-run measurement in #1434. No results yet: the runs wait for the shared fixture slot. Stacked on #1446.
benchmark/verification_coverage/openemr_run.py: fresh Claude Sonnet 5.5 agent runs on OpenEMR, with faults injected in the fixture database only. It reuses scoreboard: timed OpenEMR arms 3-6, arm 5 API step, agent/screen/API comparison #1365's triggers and poller, and adds three classes:collateral_edit_bot,concurrent_edit_otherandmisread_source. Each item is judged by threeverify-runengines from their own checkouts, each with its own baseline: the scoreboard: timed OpenEMR arms 3-6, arm 5 API step, agent/screen/API comparison #1365 engine, main with verify-run: a changed non-target record is collateral, not only a vanished one (#1373) #1375, and this stack. The last uses OpenEMR's audit log for attribution and the referral document for the round trip.openimis_run.py: the same on openIMIS, withrecord_fieldattribution fromAuditUserID/ValidityFrom, declaredserver_set.openemr_gate.py: the fault gate on the OpenEMR test copy (no model calls) for the full patient list and an email-scoped read.exec_mariadb.py: a SELECT-only DB-API shim throughdocker exec, for the audit-log read.summarize.py: per-class catch rates and false alarms intoRESULTS.md.scoreboard/tasks/openimis.py:OPENIMIS_HTTP_PORTfor a second copy; the default is unchanged.The results commit will add the rows,
RESULTS.md, the public-artifacts inventory and aCAPABILITIES.mdline.🤖 Generated with Claude Code