feat: migrate npm registry from Verdaccio to Gitea Packages

packages/concept-engine/src/steps/00b-research.ts

@@ -0,0 +1,121 @@
+// ============================================================================
+// Step 00b: Research — Industry Research via @mintel/journaling (No LLM hallus)
+// Uses Serper API for real web search results about the industry/company.
+// ============================================================================
+
+import type { ConceptState, StepResult } from "../types.js";
+
+interface ResearchResult {
+    companyContext: string[];
+    industryInsights: string[];
+    competitorInfo: string[];
+}
+
+/**
+ * Research the company and industry using real web search data.
+ * Uses @mintel/journaling's ResearchAgent — results are grounded in real sources.
+ *
+ * NOTE: The journaling package can cause unhandled rejections that crash the process.
+ * We wrap each call in an additional safety layer.
+ */
+export async function executeResearch(
+    state: ConceptState,
+): Promise<StepResult<ResearchResult>> {
+    const startTime = Date.now();
+
+    const companyName = state.siteProfile?.companyInfo?.name || "";
+    const websiteTopic = state.siteProfile?.services?.slice(0, 3).join(", ") || "";
+    const domain = state.siteProfile?.domain || "";
+
+    if (!companyName && !websiteTopic && !domain) {
+        return {
+            success: true,
+            data: { companyContext: [], industryInsights: [], competitorInfo: [] },
+            usage: { step: "00b-research", model: "none", promptTokens: 0, completionTokens: 0, cost: 0, durationMs: 0 },
+        };
+    }
+
+    // Safety wrapper: catch ANY unhandled rejections during this step
+    const safeCall = <T>(fn: () => Promise<T>, fallback: T): Promise<T> => {
+        return new Promise<T>((resolve) => {
+            const handler = (err: any) => {
+                console.warn(`  ⚠️ Unhandled rejection caught in research: ${err?.message || err}`);
+                process.removeListener("unhandledRejection", handler);
+                resolve(fallback);
+            };
+            process.on("unhandledRejection", handler);
+
+            fn()
+                .then((result) => {
+                    process.removeListener("unhandledRejection", handler);
+                    resolve(result);
+                })
+                .catch((err) => {
+                    process.removeListener("unhandledRejection", handler);
+                    console.warn(`  ⚠️ Research call failed: ${err?.message || err}`);
+                    resolve(fallback);
+                });
+        });
+    };
+
+    try {
+        const { ResearchAgent } = await import("@mintel/journaling");
+        const agent = new ResearchAgent(process.env.OPENROUTER_API_KEY || "");
+
+        const results: ResearchResult = {
+            companyContext: [],
+            industryInsights: [],
+            competitorInfo: [],
+        };
+
+        // 1. Research the company itself
+        if (companyName || domain) {
+            const searchQuery = companyName
+                ? `${companyName} ${websiteTopic} Unternehmen`
+                : `site:${domain}`;
+
+            console.log(`  🔍 Researching: "${searchQuery}"...`);
+            const facts = await safeCall(
+                () => agent.researchTopic(searchQuery),
+                [] as any[],
+            );
+            results.companyContext = (facts || [])
+                .filter((f: any) => f?.fact || f?.value || f?.text || f?.statement)
+                .map((f: any) => f.fact || f.value || f.text || f.statement)
+                .slice(0, 5);
+        }
+
+        // 2. Industry research
+        if (websiteTopic) {
+            console.log(`  🔍 Researching industry: "${websiteTopic}"...`);
+            const insights = await safeCall(
+                () => agent.researchCompetitors(websiteTopic),
+                [] as any[],
+            );
+            results.industryInsights = (insights || []).slice(0, 5);
+        }
+
+        const totalFacts = results.companyContext.length + results.industryInsights.length + results.competitorInfo.length;
+        console.log(`  📊 Research found ${totalFacts} data points.`);
+
+        return {
+            success: true,
+            data: results,
+            usage: {
+                step: "00b-research",
+                model: "serper/datacommons",
+                promptTokens: 0,
+                completionTokens: 0,
+                cost: 0,
+                durationMs: Date.now() - startTime,
+            },
+        };
+    } catch (err) {
+        console.warn(`  ⚠️ Research step skipped: ${(err as Error).message}`);
+        return {
+            success: true,
+            data: { companyContext: [], industryInsights: [], competitorInfo: [] },
+            usage: { step: "00b-research", model: "none", promptTokens: 0, completionTokens: 0, cost: 0, durationMs: Date.now() - startTime },
+        };
+    }
+}