Add deterministic evaluation handoff bundle#100
Merged
Conversation
coreytshaffer
marked this pull request as ready for review
July 17, 2026 08:04
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
tc eval build-handoff --fixture <jsonl> --actuals-dir <dir> --out-dir <new-dir>evaluation_handoff_manifest.v0with sorted entries and SHA-256 digests--forceWhy
CR-123 established the file-based evaluation handoff contract but deliberately did not materialize a bundle. CR-127 implements that bounded packaging step so operators can hand deterministic, inspectable static evidence to the external evaluator without adding scoring or evaluator execution inside TriageCore.
Impact
The builder requires explicit paths, copies source evidence byte-for-byte, rejects malformed, unsafe, unknown, sensitive, overlapping, or ambiguous inputs with closed reason codes, and leaves no final bundle after failure. Missing actuals remain allowed because the external evaluator—not TriageCore—owns pass/fail judgment.
Boundaries
No scoring, matching, verdicts, certification, evaluator execution/import, model/backend/network calls, routing, ledger, worker, approval behavior, automatic discovery, default paths, overwrite, compression, signing, upload, or publication is added.
Validation
python -m pytest -q— 971 passed, 2 skippedpython -m triage_core.tc_cli audit --privacy-invariants— 698 records passedgit diff --check— clean