weflow-cli 1.16.0 → 1.17.0

package/scripts/create_reading_notes.py

@@ -480,21 +480,21 @@ def main():
     parser.add_argument('--date', help='日期 YYYY-MM-DD（--refresh-queries 时不需要）')
     parser.add_argument('--source', default=DEFAULT_SOURCE, help='文章目录')
     parser.add_argument('--vault', default=DEFAULT_VAULT, help='Vault 目录')
-    parser.add_argument('--clean-summaries', action='store_true',
-                        help='只把已有笔记摘要段里的微信界面残留洗掉（本地，不调模型）')
+    parser.add_argument('--clean-summaries', action='store_true',
+                        help='只把已有笔记摘要段里的微信界面残留洗掉（本地，不调模型）')
     parser.add_argument('--refresh-queries', action='store_true',
                         help='只做这件事：把已有笔记里的 dataview 查询重写成当前模板（本地，不调模型）')
     args = parser.parse_args()
 
-    if args.clean_summaries:
-        # 本地清洗：动的是本地就能算出来的东西，不必把两万多篇重问一遍
-        result = clean_summaries(args.vault)
-        print('清洗摘要：%d 篇；本来就干净、没动的 %d 篇；读不出来的 %d 篇'
-              % (len(result['cleaned']), len(result['untouched']), len(result['skipped'])))
-        for name in result['skipped'][:5]:
-            print('   跳过:', name[:70])
-        return
-
+    if args.clean_summaries:
+        # 本地清洗：动的是本地就能算出来的东西，不必把两万多篇重问一遍
+        result = clean_summaries(args.vault)
+        print('清洗摘要：%d 篇；本来就干净、没动的 %d 篇；读不出来的 %d 篇'
+              % (len(result['cleaned']), len(result['untouched']), len(result['skipped'])))
+        for name in result['skipped'][:5]:
+            print('   跳过:', name[:70])
+        return
+
     if args.refresh_queries:
         result = refresh_dataview_blocks(args.vault)
         print('重写 %d 篇；没有查询块、没动的 %d 篇；读不出来的 %d 篇'

package/scripts/daily_task.ps1

@@ -1,213 +1,213 @@
-# Runs a daily report pass, with everything written to logs/daily-<date>.log.
-#
-# Two modes, because a WeChat official-account day only fills up gradually:
-#
-#   daily_task.ps1 noon   -> today so far (run at 13:00; half a day of push messages)
-#   daily_task.ps1        -> yesterday, complete (run at 00:05; same as before)
-#
-# The second pass is incremental by design: `.run_state.json` makes biz_daily skip the
-# articles the noon pass already handled, so 00:05 only fetches/summarises what arrived
-# in the afternoon, while README/index.html are rebuilt from every md on disk.
-#
-# Why this wrapper exists instead of putting the command straight into the scheduled task:
-#
-#  1. The task must not depend on a build artifact. It calls the python layer
-#     (scripts/pipeline.py) directly, which is the same source the repo builds from.
-#  2. A task whose output goes nowhere answers "it failed" and nothing else. One log
-#     file per run, so "why was yesterday short?" has an answer.
-#  3. Redirecting stdout to a FILE changes python's stdout encoding (it stops being the
-#     console and becomes the locale codepage). A title containing a character outside
-#     that codepage would then raise UnicodeEncodeError *after* the day was already
-#     written, i.e. the run looks like a failure while the artifacts are fine. Hence
-#     PYTHONIOENCODING/PYTHONUTF8 below.
-#
-# Extra arguments are appended, so `daily_task.ps1 --help` is a safe smoke test (it
-# prints the pipeline's help into that day's log and exits without touching anything).
-$ErrorActionPreference = 'Stop'
-
-$root = Split-Path -Parent $PSScriptRoot
-$logDir = Join-Path $root 'logs'
-if (-not (Test-Path $logDir)) { New-Item -ItemType Directory -Path $logDir | Out-Null }
-
-# Mode is the first positional word; anything else is forwarded to pipeline.py.
-$mode = 'day'
-$rest = @($args)
-if ($args.Count -gt 0 -and ($args[0] -eq 'noon' -or $args[0] -eq 'day')) {
-    $mode = $args[0]
-    $rest = if ($args.Count -gt 1) { @($args[1..($args.Count - 1)]) } else { @() }
-}
-
-$today = (Get-Date).ToString('yyyy-MM-dd')
-$yesterday = (Get-Date).AddDays(-1).ToString('yyyy-MM-dd')
-$targetDay = if ($mode -eq 'noon') { $today } else { $yesterday }
-
-$stamp = Get-Date -Format 'yyyy-MM-dd'
-$suffix = if ($mode -eq 'noon') { '-noon' } else { '' }
-$out = Join-Path $logDir ('daily-{0}{1}.log' -f $stamp, $suffix)
-$err = Join-Path $logDir ('daily-{0}{1}.err.log' -f $stamp, $suffix)
-
-$env:PYTHONIOENCODING = 'utf-8'
-$env:PYTHONUTF8 = '1'
-
-$python = (Get-Command python.exe).Source
-$script = Join-Path $PSScriptRoot 'pipeline.py'
-$modeArgs = if ($mode -eq 'noon') { @('--date', $today) } else { @('--yesterday') }
-$allArgs = @($script) + $modeArgs + @('--prefetch-bodies') + $rest
-
-# Idempotent "make sure the target day is as complete as it can be right now", not
-# "run at 08:20".
-#
-# Why: this machine slept from 2026-10-17 02:09 to 2026-10-18 15:26 and BOTH 08:20
-# triggers were counted as missed while StartWhenAvailable=On did not start the task
-# on wake (NumberOfMissedRuns=2, no run). A schedule that only fires if the machine
-# happens to be awake at one instant is not a schedule. With the guard below the task
-# can be triggered cheaply and often (schedule + at logon): if the target is already
-# done this exits in milliseconds, otherwise it produces/extends the day.
-#
-# The day-mode guard deliberately does NOT trust index.html alone: the noon pass also
-# writes one, so "index.html exists" would make the 00:05 pass skip the afternoon and
-# leave the day half-done behind a complete-looking page. `.articles.json`'s
-# generated_at tells us when the last pass actually ran; anything during that day
-# (before 23:00) is a mid-day artifact and must be extended.
-#
-# Note the day pass runs at 00:05 **the next day**, so a finished day is one whose
-# generated_at is later than the day itself - not one stamped at 23:xx. Testing
-# `hour -ge 23` alone would have made every 00:05 run redo the whole day (observed
-# while verifying this guard: generated_at 00:20 was judged incomplete).
-function Test-DayComplete([string]$dir, [string]$targetDay) {
-    $idx = Join-Path $dir 'index.html'
-    if (-not (Test-Path $idx)) { return $false }
-    $art = Join-Path $dir '.articles.json'
-    if (-not (Test-Path $art)) { return $true }   # old artifact without json: trust it
-    try {
-        $j = Get-Content $art -Raw -Encoding UTF8 | ConvertFrom-Json
-        $gen = [datetime]::ParseExact([string]$j.generated_at, 'yyyy-MM-dd HH:mm:ss', $null)
-        $genDay = $gen.ToString('yyyy-MM-dd')
-        # finished = generated on a later day (the usual 00:05 pass), or late the same night
-        return (($genDay -gt $targetDay) -or (($genDay -eq $targetDay) -and ($gen.Hour -ge 23)))
-    } catch { return $true }
-}
-
-# Skipped when arguments are passed, so `daily_task.ps1 --help` still works as a
-# smoke test with no side effects.
-if ($rest.Count -eq 0) {
-    $dayDir = Join-Path $root ('output\biz-daily\' + $targetDay)
-    $done = if ($mode -eq 'noon') { Test-Path (Join-Path $dayDir '.noon_done') } else { Test-DayComplete $dayDir $targetDay }
-    if ($done) {
-        $note = '===== {0}  [{1}] {2} already complete - skip =====' -f `
-            (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $mode, $targetDay
-        Add-Content -Path (Join-Path $logDir 'daily-task.log') -Value $note -Encoding UTF8
-        exit 0
-    }
-}
-
-# Start-Process OVERWRITES its redirect targets, so a same-day rerun would erase the log
-# of the run that just failed - exactly the one worth keeping. Rotate any existing pair to
-# daily-<date>.run<N>[.err].log first, so every attempt stays on disk. N is the first free
-# index, which also works when several reruns happen in one day.
-if (Test-Path $out) {
-    $n = 1
-    while (Test-Path (Join-Path $logDir ('daily-{0}{1}.run{2}.log' -f $stamp, $suffix, $n))) { $n++ }
-    Move-Item -Path $out -Destination (Join-Path $logDir ('daily-{0}{1}.run{2}.log' -f $stamp, $suffix, $n))
-    if (Test-Path $err) {
-        Move-Item -Path $err -Destination (Join-Path $logDir ('daily-{0}{1}.run{2}.err.log' -f $stamp, $suffix, $n))
-    }
-}
-
-# Start-Process writes the raw bytes through: no PowerShell error-record wrapping, and
-# no shell quoting to get wrong.
-$proc = Start-Process -FilePath $python -ArgumentList $allArgs -NoNewWindow -Wait -PassThru `
-    -RedirectStandardOutput $out -RedirectStandardError $err
-
-# Fallback for the HTML stage.
-#
-# `pipeline.py` fetches, summarises, writes the day, then renders `index.html`. That last step
-# has hung twice now (2026-10-18: 11 hours with no output; 2026-10-23: the run died after the
-# README and never produced the page). Losing the page also loses the mail, because mailing
-# happens only on success - so a single slow step silently costs the whole morning report.
-#
-# The fetch and summaries are already on disk at that point (`.articles.json`), so rendering is
-# retried on its own. `$proc` is replaced by the retry's exit code, which is what lets the mail
-# and index steps below run on a day where only the renderer failed.
-if ($proc.ExitCode -ne 0) {
-    $dayDir = Join-Path $root ('output\biz-daily\' + $targetDay)
-    $art = Join-Path $dayDir '.articles.json'
-    $idx = Join-Path $dayDir 'index.html'
-    $htmlScript = Join-Path $PSScriptRoot 'generate_html.py'
-    # Only retry when the data is there and the page is missing or older than the data:
-    # a page newer than `.articles.json` means rendering already happened this run.
-    $needsRender = (Test-Path $art) -and (Test-Path $htmlScript)
-    if ($needsRender -and (Test-Path $idx)) {
-        $needsRender = (Get-Item $art).LastWriteTime -gt (Get-Item $idx).LastWriteTime
-    }
-    if ($needsRender) {
-        Add-Content -Path (Join-Path $logDir 'daily-task.log') -Value `
-            ('===== {0}  [{1}] {2} pipeline exit {3}, retrying HTML only =====' -f `
-                (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $mode, $targetDay, $proc.ExitCode) -Encoding UTF8
-        $retryProc = Start-Process -FilePath $python `
-            -ArgumentList @($htmlScript, '--date', $targetDay) `
-            -NoNewWindow -Wait -PassThru `
-            -RedirectStandardOutput (Join-Path $logDir ('html-retry-{0}{1}.log' -f $stamp, $suffix)) `
-            -RedirectStandardError (Join-Path $logDir ('html-retry-{0}{1}.err.log' -f $stamp, $suffix))
-        if ($retryProc.ExitCode -eq 0) {
-            $proc = $retryProc
-        }
-    }
-}
-
-if ($proc.ExitCode -eq 0 -and $rest.Count -eq 0) {
-    # Marker for the noon pass only; the day pass is judged by generated_at above.
-    if ($mode -eq 'noon') {
-        $dayDir = Join-Path $root ('output\biz-daily\' + $targetDay)
-        if (Test-Path $dayDir) {
-            Set-Content -Path (Join-Path $dayDir '.noon_done') -Value (Get-Date -Format 'yyyy-MM-dd HH:mm:ss') -Encoding UTF8
-        }
-    }
-
-    # 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 (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 `
-                ('===== {0}  [{1}] {2} mail failed (exit {3}), see {4} =====' -f `
-                    (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $mode, $targetDay, $mailProc.ExitCode, $mailErr) -Encoding UTF8
-        }
-    }
-}
-
-exit $proc.ExitCode
+# Runs a daily report pass, with everything written to logs/daily-<date>.log.
+#
+# Two modes, because a WeChat official-account day only fills up gradually:
+#
+#   daily_task.ps1 noon   -> today so far (run at 13:00; half a day of push messages)
+#   daily_task.ps1        -> yesterday, complete (run at 00:05; same as before)
+#
+# The second pass is incremental by design: `.run_state.json` makes biz_daily skip the
+# articles the noon pass already handled, so 00:05 only fetches/summarises what arrived
+# in the afternoon, while README/index.html are rebuilt from every md on disk.
+#
+# Why this wrapper exists instead of putting the command straight into the scheduled task:
+#
+#  1. The task must not depend on a build artifact. It calls the python layer
+#     (scripts/pipeline.py) directly, which is the same source the repo builds from.
+#  2. A task whose output goes nowhere answers "it failed" and nothing else. One log
+#     file per run, so "why was yesterday short?" has an answer.
+#  3. Redirecting stdout to a FILE changes python's stdout encoding (it stops being the
+#     console and becomes the locale codepage). A title containing a character outside
+#     that codepage would then raise UnicodeEncodeError *after* the day was already
+#     written, i.e. the run looks like a failure while the artifacts are fine. Hence
+#     PYTHONIOENCODING/PYTHONUTF8 below.
+#
+# Extra arguments are appended, so `daily_task.ps1 --help` is a safe smoke test (it
+# prints the pipeline's help into that day's log and exits without touching anything).
+$ErrorActionPreference = 'Stop'
+
+$root = Split-Path -Parent $PSScriptRoot
+$logDir = Join-Path $root 'logs'
+if (-not (Test-Path $logDir)) { New-Item -ItemType Directory -Path $logDir | Out-Null }
+
+# Mode is the first positional word; anything else is forwarded to pipeline.py.
+$mode = 'day'
+$rest = @($args)
+if ($args.Count -gt 0 -and ($args[0] -eq 'noon' -or $args[0] -eq 'day')) {
+    $mode = $args[0]
+    $rest = if ($args.Count -gt 1) { @($args[1..($args.Count - 1)]) } else { @() }
+}
+
+$today = (Get-Date).ToString('yyyy-MM-dd')
+$yesterday = (Get-Date).AddDays(-1).ToString('yyyy-MM-dd')
+$targetDay = if ($mode -eq 'noon') { $today } else { $yesterday }
+
+$stamp = Get-Date -Format 'yyyy-MM-dd'
+$suffix = if ($mode -eq 'noon') { '-noon' } else { '' }
+$out = Join-Path $logDir ('daily-{0}{1}.log' -f $stamp, $suffix)
+$err = Join-Path $logDir ('daily-{0}{1}.err.log' -f $stamp, $suffix)
+
+$env:PYTHONIOENCODING = 'utf-8'
+$env:PYTHONUTF8 = '1'
+
+$python = (Get-Command python.exe).Source
+$script = Join-Path $PSScriptRoot 'pipeline.py'
+$modeArgs = if ($mode -eq 'noon') { @('--date', $today) } else { @('--yesterday') }
+$allArgs = @($script) + $modeArgs + @('--prefetch-bodies') + $rest
+
+# Idempotent "make sure the target day is as complete as it can be right now", not
+# "run at 08:20".
+#
+# Why: this machine slept from 2026-10-17 02:09 to 2026-10-18 15:26 and BOTH 08:20
+# triggers were counted as missed while StartWhenAvailable=On did not start the task
+# on wake (NumberOfMissedRuns=2, no run). A schedule that only fires if the machine
+# happens to be awake at one instant is not a schedule. With the guard below the task
+# can be triggered cheaply and often (schedule + at logon): if the target is already
+# done this exits in milliseconds, otherwise it produces/extends the day.
+#
+# The day-mode guard deliberately does NOT trust index.html alone: the noon pass also
+# writes one, so "index.html exists" would make the 00:05 pass skip the afternoon and
+# leave the day half-done behind a complete-looking page. `.articles.json`'s
+# generated_at tells us when the last pass actually ran; anything during that day
+# (before 23:00) is a mid-day artifact and must be extended.
+#
+# Note the day pass runs at 00:05 **the next day**, so a finished day is one whose
+# generated_at is later than the day itself - not one stamped at 23:xx. Testing
+# `hour -ge 23` alone would have made every 00:05 run redo the whole day (observed
+# while verifying this guard: generated_at 00:20 was judged incomplete).
+function Test-DayComplete([string]$dir, [string]$targetDay) {
+    $idx = Join-Path $dir 'index.html'
+    if (-not (Test-Path $idx)) { return $false }
+    $art = Join-Path $dir '.articles.json'
+    if (-not (Test-Path $art)) { return $true }   # old artifact without json: trust it
+    try {
+        $j = Get-Content $art -Raw -Encoding UTF8 | ConvertFrom-Json
+        $gen = [datetime]::ParseExact([string]$j.generated_at, 'yyyy-MM-dd HH:mm:ss', $null)
+        $genDay = $gen.ToString('yyyy-MM-dd')
+        # finished = generated on a later day (the usual 00:05 pass), or late the same night
+        return (($genDay -gt $targetDay) -or (($genDay -eq $targetDay) -and ($gen.Hour -ge 23)))
+    } catch { return $true }
+}
+
+# Skipped when arguments are passed, so `daily_task.ps1 --help` still works as a
+# smoke test with no side effects.
+if ($rest.Count -eq 0) {
+    $dayDir = Join-Path $root ('output\biz-daily\' + $targetDay)
+    $done = if ($mode -eq 'noon') { Test-Path (Join-Path $dayDir '.noon_done') } else { Test-DayComplete $dayDir $targetDay }
+    if ($done) {
+        $note = '===== {0}  [{1}] {2} already complete - skip =====' -f `
+            (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $mode, $targetDay
+        Add-Content -Path (Join-Path $logDir 'daily-task.log') -Value $note -Encoding UTF8
+        exit 0
+    }
+}
+
+# Start-Process OVERWRITES its redirect targets, so a same-day rerun would erase the log
+# of the run that just failed - exactly the one worth keeping. Rotate any existing pair to
+# daily-<date>.run<N>[.err].log first, so every attempt stays on disk. N is the first free
+# index, which also works when several reruns happen in one day.
+if (Test-Path $out) {
+    $n = 1
+    while (Test-Path (Join-Path $logDir ('daily-{0}{1}.run{2}.log' -f $stamp, $suffix, $n))) { $n++ }
+    Move-Item -Path $out -Destination (Join-Path $logDir ('daily-{0}{1}.run{2}.log' -f $stamp, $suffix, $n))
+    if (Test-Path $err) {
+        Move-Item -Path $err -Destination (Join-Path $logDir ('daily-{0}{1}.run{2}.err.log' -f $stamp, $suffix, $n))
+    }
+}
+
+# Start-Process writes the raw bytes through: no PowerShell error-record wrapping, and
+# no shell quoting to get wrong.
+$proc = Start-Process -FilePath $python -ArgumentList $allArgs -NoNewWindow -Wait -PassThru `
+    -RedirectStandardOutput $out -RedirectStandardError $err
+
+# Fallback for the HTML stage.
+#
+# `pipeline.py` fetches, summarises, writes the day, then renders `index.html`. That last step
+# has hung twice now (2026-10-18: 11 hours with no output; 2026-10-23: the run died after the
+# README and never produced the page). Losing the page also loses the mail, because mailing
+# happens only on success - so a single slow step silently costs the whole morning report.
+#
+# The fetch and summaries are already on disk at that point (`.articles.json`), so rendering is
+# retried on its own. `$proc` is replaced by the retry's exit code, which is what lets the mail
+# and index steps below run on a day where only the renderer failed.
+if ($proc.ExitCode -ne 0) {
+    $dayDir = Join-Path $root ('output\biz-daily\' + $targetDay)
+    $art = Join-Path $dayDir '.articles.json'
+    $idx = Join-Path $dayDir 'index.html'
+    $htmlScript = Join-Path $PSScriptRoot 'generate_html.py'
+    # Only retry when the data is there and the page is missing or older than the data:
+    # a page newer than `.articles.json` means rendering already happened this run.
+    $needsRender = (Test-Path $art) -and (Test-Path $htmlScript)
+    if ($needsRender -and (Test-Path $idx)) {
+        $needsRender = (Get-Item $art).LastWriteTime -gt (Get-Item $idx).LastWriteTime
+    }
+    if ($needsRender) {
+        Add-Content -Path (Join-Path $logDir 'daily-task.log') -Value `
+            ('===== {0}  [{1}] {2} pipeline exit {3}, retrying HTML only =====' -f `
+                (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $mode, $targetDay, $proc.ExitCode) -Encoding UTF8
+        $retryProc = Start-Process -FilePath $python `
+            -ArgumentList @($htmlScript, '--date', $targetDay) `
+            -NoNewWindow -Wait -PassThru `
+            -RedirectStandardOutput (Join-Path $logDir ('html-retry-{0}{1}.log' -f $stamp, $suffix)) `
+            -RedirectStandardError (Join-Path $logDir ('html-retry-{0}{1}.err.log' -f $stamp, $suffix))
+        if ($retryProc.ExitCode -eq 0) {
+            $proc = $retryProc
+        }
+    }
+}
+
+if ($proc.ExitCode -eq 0 -and $rest.Count -eq 0) {
+    # Marker for the noon pass only; the day pass is judged by generated_at above.
+    if ($mode -eq 'noon') {
+        $dayDir = Join-Path $root ('output\biz-daily\' + $targetDay)
+        if (Test-Path $dayDir) {
+            Set-Content -Path (Join-Path $dayDir '.noon_done') -Value (Get-Date -Format 'yyyy-MM-dd HH:mm:ss') -Encoding UTF8
+        }
+    }
+
+    # 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 (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 `
+                ('===== {0}  [{1}] {2} mail failed (exit {3}), see {4} =====' -f `
+                    (Get-Date -Format 'yyyy-MM-dd HH:mm:ss'), $mode, $targetDay, $mailProc.ExitCode, $mailErr) -Encoding UTF8
+        }
+    }
+}
+
+exit $proc.ExitCode