feat(scrape): cron uses documents scrape with --log-file

Monthly cron now runs the unified documents workflow with teed logs
and paired JSON summaries instead of host scrape shell redirect.

.docs/Recurring-Scrape-Setup.md

@@ -297,6 +297,9 @@ Check logs from your last run:
 # Primary log file (default from setup-cron.sh)
 tail -f logs/discord-scrape.log
 
+# Machine-readable totals beside the cron log
+./scripts/print-scrape-summary.sh logs/discord-scrape.summary.json
+
 # Recent cron execution (system log)
 sudo grep discord-scrape /var/log/syslog  # Debian/Ubuntu
 sudo grep discord-scrape /var/log/cron    # CentOS/RHEL

docs/plans/2026-06-04-079-feat-cron-documents-scrape-log-file-plan.md

@@ -0,0 +1,57 @@
+---
+title: "feat: Cron uses documents scrape with --log-file"
+type: feat
+status: complete
+date: 2026-06-04
+origin: /lfg — plan 078 deferred wire --log-file into setup-cron crontab line
+---
+
+# feat: Cron uses documents scrape with --log-file
+
+## Summary
+
+Change `setup-cron.sh` to install `run-documents-scrape.sh --log-file PATH` instead of `run-discord-scrape-host.sh scrape >> log`. Cron jobs get archive verify, disk preflight, lock gate, teed logs, and paired JSON summaries.
+
+## Problem Frame
+
+Plan 078 added `--log-file` tee to documents scrape, but monthly cron still invokes the bare host wrapper with shell `>>` redirect — bypassing the unified workflow and JSON summary pairing.
+
+## Requirements
+
+| ID | Requirement |
+|----|-------------|
+| R1 | Cron job line runs `run-documents-scrape.sh --config HOST_CONFIG --log-file LOG_FILE` |
+| R2 | `--target`, `--channel`, `--guild` forwarded to documents scrape |
+| R3 | Cron sets `DCE_ENV_FILE`, `DCE_COMPOSE_FILE`, `DCE_COMPOSE_TTY=0` (no shell `>>` redirect) |
+| R4 | `run-documents-scrape.sh` accepts `--guild` passthrough like `--channel` |
+| R5 | `setup-cron-smoke.sh` asserts documents scrape + `--log-file` in crontab |
+| R6 | Docs note cron log + `<basename>.summary.json` |
+| R7 | `DCE_MIN_FREE_MB=0 ./scripts/run-all-smokes.sh` → 23/23 |
+
+## Implementation Units
+
+### U1. setup-cron.sh
+
+**Files:** `scripts/setup-cron.sh`, `scripts/tests/setup-cron-smoke.sh`
+
+### U2. run-documents-scrape.sh
+
+**Files:** `scripts/run-documents-scrape.sh` (--guild passthrough)
+
+### U3. Docs
+
+**Files:** `docs/recurring-scrape-merge-readiness.md`, `.docs/Recurring-Scrape-Setup.md`
+
+## Verification
+
+```bash
+DCE_MIN_FREE_MB=0 ./scripts/run-all-smokes.sh
+```
+
+## Scope Boundaries
+
+### Deferred
+
+- Live KotOR catch-up on host
+- Refresh PR #1538 body with plans 070–079 stamps
+- `--salvage-before-scrape` on cron (operator opt-in only)

docs/recurring-scrape-merge-readiness.md

@@ -186,6 +186,8 @@ DCE_MIN_FREE_MB=0 ./scripts/run-operator-validation.sh \
 
 **Plan 078 (2026-06-04):** `run-documents-scrape.sh` `--log-file` with auto tee on live scrapes; summary pairs with log basename.
 
+**Plan 079 (2026-06-04):** `setup-cron.sh` installs `run-documents-scrape.sh --log-file` (unified workflow + JSON summary) instead of bare host scrape redirect.
+
 **Disk:** ~65 GiB free on `/home` (2026-05-30); large channel merges still need headroom.
 
 ## CI note (fork PRs)

scripts/run-documents-scrape.sh

@@ -35,6 +35,7 @@ Options:
   --salvage-before-scrape  Run salvage-only pass before preflight and incremental scrape
   --target NAME Limit preflight/scrape to one configured target
   --channel ID  With exactly one --target, limit scrape to channel ID (repeatable)
+  --guild ID    With exactly one --target, limit scrape to guild ID (repeatable)
   --config PATH Scrape target config (default: config/scrape-targets.json)
   --log-file PATH Append full workflow output to this file (default on live scrape: logs/documents-scrape-UTC.log)
   --summary-file PATH  Machine-readable scrape summary JSON (default: <log-basename>.summary.json on live scrape)
@@ -172,6 +173,11 @@ main() {
         passthrough+=(--channel "$2")
         shift 2
         ;;
+      --guild)
+        [[ $# -ge 2 ]] || die "Missing value for --guild."
+        passthrough+=(--guild "$2")
+        shift 2
+        ;;
       --config)
         [[ $# -ge 2 ]] || die "Missing value for --config."
         CONFIG_PATH=$2

scripts/setup-cron.sh

@@ -7,6 +7,7 @@ REPO_ROOT="${DCE_REPO_ROOT:-$(cd "$SCRIPT_DIR/.." && pwd -P)}"
 COMPOSE_FILE="${DCE_COMPOSE_FILE:-$REPO_ROOT/docker-compose.yml}"
 ENV_FILE="${DCE_ENV_FILE:-$REPO_ROOT/scrape.env}"
 HOST_RUNNER="${DCE_HOST_RUNNER:-$REPO_ROOT/scripts/run-discord-scrape-host.sh}"
+DOCUMENTS_SCRAPE="${DCE_DOCUMENTS_SCRAPE:-$REPO_ROOT/scripts/run-documents-scrape.sh}"
 CONFIG_FILE="${DCE_CONFIG_FILE:-$REPO_ROOT/config/scrape-targets.json}"
 LOG_FILE="${DCE_LOG_FILE:-$REPO_ROOT/logs/discord-scrape.log}"
 JOB_NAME="discord-scrape"
@@ -292,6 +293,7 @@ main() {
 
   [[ -f "$COMPOSE_FILE" ]] || die "Missing compose file: $COMPOSE_FILE"
   [[ -x "$HOST_RUNNER" ]] || die "Missing or non-executable host runner: $HOST_RUNNER"
+  [[ -x "$DOCUMENTS_SCRAPE" ]] || die "Missing or non-executable documents scrape: $DOCUMENTS_SCRAPE"
   [[ -f "$CONFIG_FILE" ]] || die "Missing config file: $CONFIG_FILE"
   "$JQ_BIN" empty "$CONFIG_FILE" >/dev/null 2>&1 || die "Invalid JSON config: $CONFIG_FILE"
 
@@ -334,11 +336,9 @@ main() {
   fi
 
   scrape_args=(
-    "$HOST_RUNNER"
-    --env-file "$ENV_FILE"
-    --compose-file "$COMPOSE_FILE"
-    scrape
-    --config "$(container_config_path "$CONFIG_FILE")"
+    "$DOCUMENTS_SCRAPE"
+    --config "$CONFIG_FILE"
+    --log-file "$LOG_FILE"
   )
   append_target_args scrape_args
   scrape_command=$(printf '%q ' "${scrape_args[@]}")
@@ -348,7 +348,7 @@ main() {
     lock_prefix=""
   fi
 
-  job_line="$cron_line cd $(printf '%q' "$REPO_ROOT") && DCE_COMPOSE_TTY=0 ${lock_prefix}${scrape_command}>> $(printf '%q' "$LOG_FILE") 2>&1"
+  job_line="$cron_line cd $(printf '%q' "$REPO_ROOT") && DCE_COMPOSE_TTY=0 DCE_ENV_FILE=$(printf '%q' "$ENV_FILE") DCE_COMPOSE_FILE=$(printf '%q' "$COMPOSE_FILE") ${lock_prefix}${scrape_command}"
 
   local cron_block
   cron_block=$(printf '%s\n%s\n%s\n' "$begin_marker" "$job_line" "$end_marker")

scripts/tests/setup-cron-smoke.sh

@@ -85,8 +85,11 @@ run_setup
 grep -q '^MAILTO=test@example.com$' "$CRONTAB_FILE" || { echo "expected unrelated crontab line to remain" >&2; exit 1; }
 [[ "$(grep -c '^# BEGIN discord-scrape$' "$CRONTAB_FILE")" == "1" ]] || { echo "expected exactly one managed cron block after install" >&2; exit 1; }
 grep -q 'compose --env-file' "$DOCKER_LOG" || { echo "expected docker preflight to run during install" >&2; exit 1; }
-grep -q 'scripts/run-discord-scrape-host.sh' "$CRONTAB_FILE" || { echo "expected cron job to run host wrapper" >&2; exit 1; }
-grep -q 'DCE_COMPOSE_TTY=0' "$CRONTAB_FILE" || { echo "expected cron job to disable compose TTY for log append" >&2; exit 1; }
+grep -q 'scripts/run-documents-scrape.sh' "$CRONTAB_FILE" || { echo "expected cron job to run documents scrape" >&2; exit 1; }
+grep -q -- '--log-file' "$CRONTAB_FILE" || { echo "expected cron job to pass --log-file" >&2; exit 1; }
+grep -q 'DCE_ENV_FILE=' "$CRONTAB_FILE" || { echo "expected cron job to set DCE_ENV_FILE" >&2; exit 1; }
+grep -q 'DCE_COMPOSE_TTY=0' "$CRONTAB_FILE" || { echo "expected cron job to disable compose TTY" >&2; exit 1; }
+grep -q '>>' "$CRONTAB_FILE" && { echo "expected cron job to rely on documents scrape tee, not shell redirect" >&2; exit 1; }
 
 run_setup
 [[ "$(grep -c '^# BEGIN discord-scrape$' "$CRONTAB_FILE")" == "1" ]] || { echo "expected exactly one managed cron block after reinstall" >&2; exit 1; }