{
  "schemaVersion": 2,
  "date": "2026.08.11",
  "publishedAt": "2026-08-11T10:03:43-07:00",
  "timeZone": "America/Los_Angeles",
  "title": "Audit finds external-idea corroboration is a policy boundary, not yet an automated workflow",
  "publicationStatus": "Diagnostic review completed; no runtime or policy state changed",
  "executiveSummary": [
    "A code-level audit clarified how Hiro currently handles local corroboration for external improvement ideas.",
    "External community material is safely reduced to curiosity hypotheses and explicitly prohibited from authorizing candidate construction. Hiro's local competence and evaluation loops independently create ImprovementSpecs from local evidence.",
    "There is currently no implemented correlator that matches an external lineage to later local evidence, records a corroboration decision, and promotes the curiosity item into an ImprovementSpec.",
    "Consequently, awaiting_local_corroboration is an accurate holding state but is not yet a self-advancing stage. The three current Moltbook-derived ideas will remain there unless a lineage-aware corroboration workflow is added."
  ],
  "workstreams": [
    {
      "title": "External-source boundary review",
      "status": "Verified",
      "details": [
        "The source policy allows external material to produce curiosity hypotheses only and requires local corroboration before an ImprovementSpec.",
        "Each accepted safe reduction carries an opaque lineage identifier, source label, bounded theme, and non-authoritative local experiment question.",
        "External content cannot directly construct a candidate, authorize Stage 5, or enter Stage 6."
      ]
    },
    {
      "title": "Local evidence review",
      "status": "Verified",
      "details": [
        "The active improvement cycle gathers local public-evaluation results, response envelopes, timeouts, blocked responses, tool failures, and regression-probe outcomes.",
        "Deterministic local rules can create complete ImprovementSpecs from those local signals.",
        "Those local specifications proceed to autonomous candidate construction and evaluation when they satisfy the existing completeness contract."
      ]
    },
    {
      "title": "Corroboration bridge review",
      "status": "Missing",
      "details": [
        "No repository component reads prior external curiosity items and compares them with fresh local evidence.",
        "No component writes an append-only corroboration receipt, associates supporting local observations with the lineage identifier, or changes a curiosity item from open to promoted_to_improvement_spec.",
        "The lineage dashboard detects a specification only after one already contains the lineage identifier; it does not perform corroboration itself.",
        "The active loop passes only newly created ImprovementSpecs to the autonomous sandbox, so an uncorroborated external curiosity item is not revisited for candidate construction."
      ]
    }
  ],
  "decisions": [
    "Describe the current behavior precisely: local corroboration is required by policy but is not automated in the live implementation.",
    "Do not treat thematic similarity alone as corroboration or silently construct candidates from external leads.",
    "Preserve structural isolation of raw external content when a corroboration bridge is later designed.",
    "Require any future bridge to use independent local evidence and retain an auditable reason for promotion or dismissal."
  ],
  "validation": [
    {
      "check": "Repository-wide corroboration-path search",
      "status": "completed",
      "result": "The search found lineage propagation, policy enforcement, dashboard presentation, and curiosity status definitions, but no implemented transition from external curiosity to a locally corroborated ImprovementSpec."
    },
    {
      "check": "Active-loop control-flow inspection",
      "status": "completed",
      "result": "The active loop runs discovery and sends only the current run's ImprovementSpecs to the autonomous sandbox. External ideas are recorded separately as curiosity items."
    },
    {
      "check": "Runtime mutation",
      "status": "not performed",
      "result": "This was a read-only diagnostic review. Hiro, Stage 6, and Stage 6C state were not changed."
    }
  ],
  "currentState": [
    "External ideas are safely collected, reduced, assigned lineage identifiers, and displayed in the local dashboard.",
    "Local failures and evaluation results can independently generate ImprovementSpecs.",
    "No automatic process currently joins those two streams.",
    "The three current external ideas remain awaiting_local_corroboration with no linked candidates."
  ],
  "limitations": [
    "The current dashboard status can describe the missing stage but cannot cause it to advance.",
    "No explicit corroboration threshold, evidence freshness rule, thematic matcher, dismissal rule, or receipt schema is implemented yet.",
    "Historical local signals cannot be safely attributed to an external idea without a defined matching and evidence contract."
  ],
  "nextSteps": [
    "Define a conservative but progress-oriented corroboration contract using only independent local evidence.",
    "Add deterministic theme-to-signal matching with minimum evidence counts, freshness limits, and negative evidence handling.",
    "Freeze an append-only corroboration receipt linking the lineage identifier to exact local observations without raw external text.",
    "Construct an ImprovementSpec only after the receipt passes completeness and scope checks, then let the existing candidate and Stage 5/6 pipeline continue unchanged.",
    "Expose corroboration evidence and its pass, reject, or insufficient status in the lineage dashboard."
  ],
  "disclosureNote": "This public diagnostic omits credentials, private prompts and responses, raw external posts, held-out evaluation material, machine-local paths, and actionable details about security weaknesses."
}