weflow-cli 1.14.0 → 1.14.1

package/CHANGELOG.md

@@ -17,6 +17,22 @@ purpose** - a hand-written "latest is X" is exactly the claim that goes stale he
 
 All notable user-facing changes are recorded here. This project follows [Semantic Versioning](https://semver.org/).
 
+## 1.14.1
+
+- **The daily run now keeps the retrieval indexes fresh.** On 2026-10-22 the semantic index was
+  still at 10-15 and the phrase index at 10-17, so `search` could not find anything newer than a
+  week ago - nothing had ever refreshed them. After the day's report is written, the wrapper runs
+  `semantic_search.py update` (embeds only what is missing: 4,061 new records on that first run)
+  and `semantic_search.py phrase-build` (local FTS, no API cost). Each has its own log and neither
+  can fail the day.
+- **The noon pass mails too, and says it is half a day.** It used to generate silently, which read
+  as "it never ran" - the only evidence was a log file. The noon email is titled
+  「…（截至中午）」 and states that the complete version arrives the next morning, so the two daily
+  emails cannot be mistaken for duplicates.
+- **`phrase-build` no longer fails when `VACUUM` cannot run.** `VACUUM` needs a temp file, and in a
+  restricted environment it reports `unable to open database file` *after* the index has been
+  written successfully - that turned a good rebuild into exit code 1.
+
 ## 1.14.0
 
 - **A daily report you can receive by mail, cut down to the topics you actually read.**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "weflow-cli",
-  "version": "1.14.0",
+  "version": "1.14.1",
   "description": "让 AI 读懂你的微信 — 公众号日报·聊天导出·知识库搜索·MCP Server",
   "type": "module",
   "bin": {

package/scripts/daily_mail.py

@@ -423,6 +423,7 @@ def main():
     ap.add_argument('--date', required=True, help='YYYY-MM-DD')
     ap.add_argument('--to', default='', help='收件人；缺省用配置 dailyMailTo，再缺省发给自己')
     ap.add_argument('--topics', default=','.join(DEFAULT_TOPICS), help='逗号分隔的主题')
+    ap.add_argument('--label', default='', help='标题后缀，如「截至中午」——区分半日速览与次日完整版')
     ap.add_argument('--no-digest', action='store_true', help='不生成每主题的 AI 综述（省钱、更快）')
     ap.add_argument('--dry-run', action='store_true', help='只渲染，不发送')
     args = ap.parse_args()
@@ -449,7 +450,11 @@ def main():
     print(f'正文含 GitHub 链接: {with_repo} 篇')
 
     text_body, html_body, total = render(args.date, groups, digests, bodies, clusters)
-    subject = f'公众号日报 {args.date}：{" / ".join(t for t in topics if groups.get(t))} {total} 篇'
+    label = (args.label or '').strip()
+    suffix = f'（{label}）' if label else ''
+    subject = f'公众号日报 {args.date}{suffix}：{" / ".join(t for t in topics if groups.get(t))} {total} 篇'
+    if label:
+        text_body = f'【{label}】以下是到此刻为止收到的 {total} 篇。完整版会在次日凌晨按整天重发。\n\n' + text_body
 
     user, auth = smtp_settings()
     to = args.to or str(cfg.get('dailyMailTo') or '') or user

package/scripts/daily_task.ps1

@@ -128,18 +128,43 @@ if ($proc.ExitCode -eq 0 -and $rest.Count -eq 0) {
         }
     }
 
-    # Mail is a separate step on purpose: the day's product is already on disk, so a mail
-    # failure must not turn a successful run into a failed one (and must not stop the
-    # noon marker from being written). It has its own log pair.
-    #
-    # **Only the day pass mails.** The noon pass is a half day, so mailing it too means two
-    # emails a day where the second one repeats the first - the user asked for one email,
-    # and the complete day is the one worth reading (2026-10-20).
+    # Retrieval indexes lag behind unless something refreshes them: on 2026-10-22 the
+    # semantic index was still at 10-15 (7 days stale) and the phrase index at 10-17, so
+    # `search` simply could not find anything newer. Both run here, after the day is on
+    # disk, in their own logs -- a failure is recorded and never fails the day.
+    $searchScript = Join-Path $PSScriptRoot 'semantic_search.py'
+    if ($mode -eq 'day' -and (Test-Path $searchScript)) {
+        $idxOut = Join-Path $logDir ('index-{0}.log' -f $stamp)
+        $idxErr = Join-Path $logDir ('index-{0}.err.log' -f $stamp)
+        # `update` only embeds what is not in the index yet (4,061 new records on the first
+        # run after a week). `phrase-build` is local FTS, no API, so it rebuilds in full.
+        $idxProc = Start-Process -FilePath $python `
+            -ArgumentList @($searchScript, 'update', '--article-days', '30') `
+            -NoNewWindow -Wait -PassThru -RedirectStandardOutput $idxOut -RedirectStandardError $idxErr
+        $phraseProc = Start-Process -FilePath $python `
+            -ArgumentList @($searchScript, 'phrase-build') `
+            -NoNewWindow -Wait -PassThru `
+            -RedirectStandardOutput (Join-Path $logDir ('phrase-{0}.log' -f $stamp)) `
+            -RedirectStandardError (Join-Path $logDir ('phrase-{0}.err.log' -f $stamp))
+        if ($idxProc.ExitCode -ne 0 -or $phraseProc.ExitCode -ne 0) {
+            Add-Content -Path (Join-Path $logDir 'daily-task.log') -Value `
+                ('===== {0}  index update failed (update={1}, phrase={2}), see {3} =====' -f `
+                    (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $idxProc.ExitCode, $phraseProc.ExitCode, $idxErr) -Encoding UTF8
+        }
+    }
+
+    # **Both passes mail now.** The noon pass used to be silent, which read as "it never
+    # ran" - the only way to tell it had done anything was to open the log. The two emails
+    # are clearly different: the noon one is labelled 截至中午 and says the complete version
+    # follows next morning. Mail is still its own step with its own log pair, so a mail
+    # failure never fails the day nor blocks the noon marker.
     $mailScript = Join-Path $PSScriptRoot 'daily_mail.py'
     $mailOut = Join-Path $logDir ('daily-mail-{0}{1}.log' -f $stamp, $suffix)
     $mailErr = Join-Path $logDir ('daily-mail-{0}{1}.err.log' -f $stamp, $suffix)
-    if ($mode -eq 'day' -and (Test-Path $mailScript)) {
-        $mailProc = Start-Process -FilePath $python -ArgumentList @($mailScript, '--date', $targetDay) `
+    if (Test-Path $mailScript) {
+        $mailArgs = @($mailScript, '--date', $targetDay)
+        if ($mode -eq 'noon') { $mailArgs += @('--label', '截至中午') }
+        $mailProc = Start-Process -FilePath $python -ArgumentList $mailArgs `
             -NoNewWindow -Wait -PassThru -RedirectStandardOutput $mailOut -RedirectStandardError $mailErr
         if ($mailProc.ExitCode -ne 0) {
             Add-Content -Path (Join-Path $logDir 'daily-task.log') -Value `

package/scripts/semantic_search.py

@@ -1235,7 +1235,15 @@ def build_phrase_index(line: str = 'all', db_path=None, meta_path=None):
         conn.executemany('INSERT INTO hits(body, rid, line, label, date, title)'
                          ' VALUES (?, ?, ?, ?, ?, ?)', rows)
         conn.commit()
-        conn.execute('VACUUM')
+        # `VACUUM` 要写临时文件；在受限环境（沙箱 / %TEMP% 不可写）它会报
+        # `unable to open database file`，而**数据其实已经写进去了** —— 那一步只是把库压实。
+        # 所以它失败不能被当成"索引没建好"：2026-10-22 实测 155MB 的库内容完整，
+        # 却因为这一行让整个 phrase-build 的退出码变成非 0。
+        try:
+            conn.execute('VACUUM')
+        except Exception as exc:
+            print(f'[WARN] 短语索引已写入，但 VACUUM 失败（{type(exc).__name__}: {exc}）'
+                  '——只是没压实，查询不受影响', file=sys.stderr)
     finally:
         conn.close()
     return {'records': len(rows), 'byLine': by_line, 'textMissing': text_missing,