test: harden AI analysis path

.trellis/spec/backend/ai-sdk-integration.md

@@ -394,6 +394,7 @@ ANTHROPIC_API_KEY=sk-ant-...
   - `errorCategory` / `errorReason`: sanitized only for failed rows
 - Failed rows must not store prompts, full resident context snapshots, API keys, or raw provider errors.
 - Knowledge retrieval may return enabled platform knowledge and enabled active-organization knowledge only.
+- Completed elder analysis `resultJson.citations` must be derived from citation IDs actually referenced by `keyFindings[].citationIds` and `recommendations[].citationIds`; do not append unused available citations.
 
 ### 4. Validation & Error Matrix
 
@@ -407,6 +408,7 @@ ANTHROPIC_API_KEY=sk-ant-...
 - Missing `AI_API_KEY` -> save failed analysis with `missing_config`, return structured failure.
 - Provider failure -> save failed analysis with `provider_error` or `timeout`.
 - Invalid model output -> save failed analysis with `schema_validation_failed`.
+- Unknown citation IDs in findings or recommendations -> save failed analysis with `schema_validation_failed`, return structured failure.
 
 ### 5. Good/Base/Bad Cases
 
@@ -420,6 +422,7 @@ ANTHROPIC_API_KEY=sk-ant-...
 - Permission seeding assertions for `ai:*` and `knowledge:*` default role grants.
 - Knowledge retrieval tests for platform shared, own organization, other organization, and disabled entry filtering.
 - Analysis tests for missing config, schema validation failure, failed-history sanitization, and data-scope redaction.
+- Analysis tests for unknown citation rejection and referenced-only citation persistence.
 - Route tests for auth/permission failures and standard response shape.
 
 ### 7. Wrong vs Correct
@@ -435,10 +438,20 @@ await model.invoke(JSON.stringify(residentRows));
 #### Correct
 
 ```typescript
-// Keep model calls in modules/ai/server and build permission-aware context first.
+// Keep model calls in modules/ai/server and persist only citations that findings/recommendations reference.
 const result = await generateElderAiAnalysis(auth.context, elderId);
 if (!result.success) {
   return jsonFailure(result.reason, result.status);
 }
 return jsonSuccess("AI 分析已生成", { analysis: result.data.analysis }, 201);
 ```
+
+```typescript
+// Good evidence chain: every cited source ID is from the allowed resident/knowledge citations.
+const finding = {
+  category: "跌倒风险",
+  severity: "warning",
+  evidence: "夜间徘徊后需要加强通道清理和巡视。",
+  citationIds: ["resident-1", "kb-1"],
+};
+```