Add auditable harness suite and probe receipts - #22
Open
zwright8 wants to merge 1 commit into
Open
Conversation
Eval and Evidence workers need one command surface that can prove runner readiness and execute more than one scenario without hand-edited setup. This extends the existing harness script with no-network probe receipts and mock suite receipts, then registers both artifacts for schema and semantic validation.
Constraint: Repository is public, so committed docs use repo-relative examples and no local autonomy state.
Constraint: Live Hermes/OpenClaw/Codex runners are not available in unit tests, so the new interface composes existing mock harness runs first.
Rejected: Add live endpoint probing in this packet | would require credentials/network state and would be brittle for downstream offline workers.
Confidence: high
Scope-risk: moderate
Directive: Keep future live runner support behind the same probe/suite receipt contracts so Eval and Evidence workers do not branch on provider-specific files.
Tested: python3 -m unittest tests.test_harness_suite_probe tests.test_harness_manifest_cli tests.test_harness_tool_policy tests.test_harness_replay_matrix tests.test_schema_registry
Tested: /opt/homebrew/bin/python3.11 -m unittest tests.test_harness_suite_probe tests.test_harness_manifest_cli tests.test_harness_tool_policy tests.test_harness_replay_matrix tests.test_schema_registry tests.test_deployment_hardening
Tested: git diff --cached -U0 --diff-filter=ACMR | rg '^\+' | rg -n -S '(/U[s]ers/|/h[o]me/[^[:space:]]+|C:/U[s]ers/|Documents/Git[H]ub|[.]codex[-]goal[-]worktrees|[.]codex/automations|[A-Za-z0-9._%+-]+[@][A-Za-z0-9.-]+[.][A-Za-z]{2,})' (no matches)
Not-tested: Live Hermes/OpenClaw/Codex endpoint execution; this packet only adds offline mock probe and suite receipts.
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.
Summary
Verification
Delivery Status