memory: distinguish a failed extraction from an empty one

Probing the extraction path with a real model call showed it returning a
zero-candidate outcome — indistinguishable from "the conversation had
nothing worth keeping". It was actually an auth failure delivered as a JSON
error body rather than a thrown error, which coerceText turned into an empty
string, which parseCandidates turned into an empty array.

extract() now reports `error` and a `rawText` preview instead of collapsing
every failure mode into `{candidates: []}`. An auth error arriving as a
return value rather than a throw is the common case, not the exotic one.

memory_inspect prints the error and the raw response, so this class of
failure now shows up instead of looking like a healthy extractor that
rarely fires.

Verified: thrown error, error object, empty string, and null each produce a
specific message; valid JSON and fenced JSON still parse.

plugins/memory/index.ts

@@ -529,6 +529,7 @@ export default Plugin.define({
             const when = new Date(Number(extraction.at)).toISOString().slice(0, 19).replace("T", " ")
             lines.push(`  抽取：${when} → ${String(extraction.outcome)}`)
             if (extraction.reason) lines.push(`    原因：${String(extraction.reason)}`)
+            if (extraction.reasonDetail) lines.push(`    细节：${String(extraction.reasonDetail)}`)
             if (extraction.model) lines.push(`    模型：${String(extraction.model)}`)
           } else {
             lines.push(
@@ -537,6 +538,10 @@ export default Plugin.define({
                 : "  抽取：已关闭（autoExtract: false）",
             )
           }
+          if (extraction && extraction.error) {
+            lines.push(`    ⚠ 模型调用异常：${String(extraction.error)}`)
+            if (extraction.rawText) lines.push(`    原始返回：${String(extraction.rawText).slice(0, 160)}`)
+          }
 
           return { content: lines.join("\n") }
         },
@@ -755,10 +760,14 @@ async function runExtraction(
     }
     await noteDiag(ctx, "lastExtraction", {
       at: Date.now(),
-      outcome: "no-candidates",
-      reason: outcome.rejected.length ? "候选全部被去重或密钥拦截" : "抽取器认为没有值得记的东西",
+      outcome: outcome.error ? "failed" : "no-candidates",
+      ...(outcome.error ? { reason: outcome.error } : {}),
+      reasonDetail: outcome.rejected.length
+        ? "候选全部被去重或密钥拦截"
+        : "抽取器认为没有值得记的东西",
       rejected: outcome.rejected.length,
       model: `${model.providerID}/${model.id}`,
+      ...(outcome.rawText ? { rawText: outcome.rawText } : {}),
     })
     return
   }