Backfill sparse report sections, add enrichment section refresh, and bootstrap first-admin

Reports: the LLM reliably used company_enrichment for prose fields but inconsistently populated the parallel Finding-list/string-list fields from the same evidence, even with progressively more explicit prompting. Add a code-level backfill (products, recent developments, financial signals, strategic initiatives, regulatory signals, risks/opportunities mirrored from SWOT, unknowns, monitoring recommendations) that only ever fills in what the model left empty, never overwrites what it produced. Enrichment tab: reorder sections (Products/Recent updates before Customers/Competitors) and add a per-section "Refresh" button that re-fetches just one of NinjaPear's six independent per-company endpoints when it came back empty - confirmed live that a data-coverage gap (e.g. Amazon returning no products) is real provider behavior, not a bug. Auth: the first account registered on a deployment with zero existing admins is now auto-promoted to admin, closing the chicken-and-egg gap where the only path to admin access was direct DB access. Self-heals if the last admin ever deletes their account. Also bumps nginx's proxy_read_timeout for api.ciagent.org to cover the enrichment refresh's synchronous funding-endpoint call (up to 5 minutes per NinjaPear's docs). Co-Authored-By: Claude Sonnet 5 <[email protected]>
2026-08-06 17:41:02 -04:00
parent 1be3e53584
commit 18305b545c
18 changed files with 1087 additions and 53 deletions
@@ -20,6 +20,7 @@ from datetime import UTC, datetime
 from sqlalchemy.ext.asyncio import AsyncSession

 from app.core.config import Settings
+from app.core.errors import NotFoundError
 from app.core.logging import get_logger
 from app.enrichment.base import EnrichmentProvider
 from app.models.company import Company
@@ -174,3 +175,104 @@ async def enrich_company(
        failed_sections=list(errors.keys()),
    )
    return enrichment
+
+
+# Every entry here maps 1:1 onto one of NinjaPear's independent
+# per-company endpoints (see app/enrichment/ninjapear.py) - refreshing one
+# section never re-fetches or touches any of the others.
+REFRESHABLE_SECTIONS = ("details", "funding", "updates", "competitors", "products", "customers")
+
+
+async def refresh_section(
+    db: AsyncSession,
+    settings: Settings,
+    provider: EnrichmentProvider,
+    company: Company,
+    section: str,
+) -> CompanyEnrichment:
+    """Re-runs a single NinjaPear endpoint for a company that already has
+    an enrichment record but came back empty or failed for just this one
+    section (e.g. `products` returning `[]` while everything else
+    succeeded - a real, honest gap in NinjaPear's own coverage for that
+    company, not a bug in this app). Only ever replaces this section's own
+    slice of `data`/`errors` - every other section's stored data is left
+    exactly as it was."""
+    if section not in REFRESHABLE_SECTIONS:
+        raise ValueError(f"Unknown enrichment section: {section}")
+
+    repo = CompanyEnrichmentRepository(db)
+    existing = await repo.get_for_company(company.id)
+    if existing is None:
+        raise NotFoundError("Company has no enrichment record to refresh")
+
+    website = company.official_website
+    data = dict(existing.data)
+    errors = dict(existing.errors)
+    credits_spent = existing.credits_spent or 0
+
+    try:
+        if section == "details":
+            details = await provider.get_company_details(company.name, website)
+            data["employee_count"] = details.employee_count_range
+            data["description"] = details.description
+            data["industry"] = details.industry
+            data["founded_year"] = details.founded_year
+            data["specialties"] = details.specialties
+            new_leadership = [m.model_dump() for m in details.leadership_team]
+            # A details refresh re-fetches the leadership roster itself,
+            # but not the separate per-leader work_email/person_profile
+            # lookups - preserve those by matching on name so a refresh
+            # never regresses contact info that was already found.
+            old_by_name = {
+                m.get("name"): m for m in (data.get("leadership_team") or []) if m.get("name")
+            }
+            for member in new_leadership:
+                old = old_by_name.get(member.get("name"))
+                if old:
+                    member["work_email"] = member.get("work_email") or old.get("work_email")
+                    member["profile_url"] = member.get("profile_url") or old.get("profile_url")
+                    member["bio"] = member.get("bio") or old.get("bio")
+            data["leadership_team"] = new_leadership
+        elif section == "funding":
+            funding = await provider.get_funding(company.name, website)
+            data["funding"] = funding.model_dump()
+        elif section == "updates":
+            updates = await provider.get_updates(company.name, website)
+            data["recent_updates"] = [u.model_dump() for u in updates]
+        elif section == "competitors":
+            competitors = await provider.get_competitors(company.name, website)
+            data["competitors"] = [c.model_dump() for c in competitors]
+        elif section == "products":
+            products = await provider.get_products(company.name, website)
+            data["products"] = [p.model_dump() for p in products]
+        elif section == "customers":
+            customers = await provider.get_customers(company.name, website)
+            data["customers"] = [c.model_dump() for c in customers]
+        errors.pop(section, None)
+        credits_spent += _CREDIT_COSTS.get(section, 0)
+    except Exception as exc:  # noqa: BLE001 - surfaced via `errors`, same as the initial run
+        errors[section] = str(exc)
+        logger.warning(
+            "enrichment_section_refresh_failed",
+            section=section,
+            company_id=str(company.id),
+            error=str(exc),
+        )
+
+    new_status = EnrichmentStatus.PARTIAL if errors else EnrichmentStatus.COMPLETE
+    enrichment = await repo.upsert(
+        company.id,
+        status=new_status,
+        data=data,
+        errors=errors,
+        credits_spent=credits_spent,
+        fetched_at=datetime.now(UTC),
+    )
+    await db.commit()
+    logger.info(
+        "company_enrichment_section_refreshed",
+        company_id=str(company.id),
+        section=section,
+        succeeded=section not in errors,
+    )
+    return enrichment