HKUDS/Vibe-Trading · error · ValueError

complete goals require verified evidence

Error message

complete goals require verified evidence

What it means

A completion audit row for a required criterion used result satisfied/satisfied_with_caveat but supplied no evidence_ids. Completed goals must cite evidence for every satisfied criterion.

Source

Thrown at agent/src/goal/store.py:915

        return self._claim_from_row(row)

    def _validate_completion_audit(
        self,
        goal: GoalRecord,
        audit: list[AuditRow],
    ) -> None:
        criteria = self.list_criteria(goal.goal_id)
        rows_by_criterion = {row.criterion_id: row for row in audit}
        for criterion in criteria:
            if not criterion.required:
                continue
            row = rows_by_criterion.get(criterion.criterion_id)
            if row is None:
                raise ValueError(f"missing audit row for criterion {criterion.criterion_id}")
            if row.result not in _COMPLETION_RESULTS:
                raise ValueError(f"criterion {criterion.criterion_id} is not satisfied")
            if row.result in {"satisfied", "satisfied_with_caveat"} and not row.evidence_ids:
                raise ValueError("complete goals require verified evidence")
            if row.result == "not_applicable_user_accepted" and not row.notes.strip():
                raise ValueError("not-applicable criteria require acceptance notes")
            has_verified_evidence = False
            for evidence_id in row.evidence_ids:
                evidence = self._get_evidence(evidence_id)
                if evidence is None or evidence.goal_id != goal.goal_id:
                    raise ValueError(f"unknown evidence_id: {evidence_id}")
                if evidence.criterion_id != criterion.criterion_id:
                    raise ValueError(
                        f"evidence {evidence_id} does not match criterion {criterion.criterion_id}"
                    )
                if evidence.verification_status == "verified":
                    has_verified_evidence = True
            if row.result in {"satisfied", "satisfied_with_caveat"} and not has_verified_evidence:
                raise ValueError("complete goals require verified evidence")

    def _get_evidence(self, evidence_id: str) -> EvidenceRecord | None:
        row = self._conn.execute(

View on GitHub (pinned to 80ffdda44c)

Solutions

  1. append_evidence for the criterion first and put the returned evidence_id(s) in the audit row
  2. If no artifact backs the criterion, it cannot be marked satisfied — either produce evidence or mark it not_applicable_user_accepted with notes
  3. Add a builder check that every satisfied row has non-empty evidence_ids

Example fix

// before
AuditRow(criterion_id="c1", result="satisfied", evidence_ids=[])
// after
ev = store.append_evidence(session_id, goal_id, criterion_id="c1", ...)
AuditRow(criterion_id="c1", result="satisfied", evidence_ids=[ev.evidence_id])
Defensive patterns

Strategy: validation

Validate before calling

for row in audit:
    if row.result in {"satisfied", "satisfied_with_caveat"}:
        assert row.evidence_ids, f"{row.criterion_id} satisfied without evidence"

Type guard

def satisfied_rows_have_evidence(audit: list) -> bool:
    return all(r.evidence_ids for r in audit if r.result in {"satisfied", "satisfied_with_caveat"})

Try / catch

except ValueError as e: if 'require verified evidence' in str(e): append evidence, rebuild audit, retry once

Prevention

When it happens

Trigger: update_status with an audit row where result is satisfied (or satisfied_with_caveat) and evidence_ids is empty or None.

Common situations: Agent declares success narratively without having appended evidence rows; evidence appended to a different goal or criterion; evidence_ids dropped during serialization.

Related errors

AI-assisted analysis of HKUDS/Vibe-Trading@80ffdda44c (2026-08-28). Data as JSON: /api/errors/ea074f55e83ecd57. Report an issue: GitHub.