fix(bin): render fleet snapshots past the argv size ceiling

bin/fm-fleet-snapshot.sh

@@ -193,6 +193,39 @@ bool_json() {
   if [ "$1" = 1 ]; then printf 'true'; else printf 'false'; fi
 }
 
+# Feed large JSON values to jq on stdin instead of on argv.
+#
+# jq's --argjson hands its value to execve as ONE argv string, and Linux caps a
+# single argv string at MAX_ARG_STRLEN (131072 bytes) independently of the much
+# larger total ARG_MAX. Once a home's backlog, task inventory, or aggregated
+# secondmate state rendered past that ceiling, every composition that bound it
+# with --argjson died with "Argument list too long", and the failure was total:
+# the snapshot, the secondmate home summary, and the bearings projection over
+# them all produced no output at all.
+#
+# Every value that can grow with the size of a home is piped through here and
+# bound in the filter with `input`, which has no such ceiling. The value goes
+# from shell variable straight into the pipeline, so nothing large reaches argv
+# and there are no temp files to create, guard, or clean up on failure paths.
+# jq's own stdin is this pipe, so it also stays safe inside a `while read` loop.
+#
+# `input` binds in stream order, so each caller's leading `input as $name` lines
+# must match its argument order. Small, explicitly bounded values (counts, flags,
+# paths, single status lines) stay on --arg/--argjson where they read better.
+# When jq fails before draining stdin the writer hits EPIPE, and whether that is
+# visible depends on the inherited SIGPIPE disposition: at the default the writer
+# is killed silently, but where SIGPIPE is ignored - systemd services default to
+# IgnoreSIGPIPE=yes and the watcher units drive this script - Bash's builtin
+# printf outlives the closed pipe and reports the write error itself, wedging
+# writer noise into an otherwise clean failure report. The consumer owns the
+# pipeline failure, so the redirect below suppresses that writer diagnostic
+# unconditionally; exit status remains jq's and callers keep their existing
+# hard-failure checks. tests/fm-fleet-snapshot-argv-limit.test.sh pins both
+# dispositions.
+json_stdin() {  # <json>...
+  printf '%s\n' "$@" 2>/dev/null
+}
+
 path_present_json() {  # <path>
   local present=0
   [ -e "$1" ] && present=1
@@ -503,7 +536,7 @@ task_json_lines() {
     if [ -n "$worktree" ]; then worktree_json=$(path_present_json "$worktree"); else worktree_json=$(jq -n '{path:null,present:false}'); fi
     if [ -n "$home" ]; then home_json=$(path_present_json "$home"); else home_json=$(jq -n '{path:null,present:false}'); fi
 
-    jq -n \
+    json_stdin "$open_decisions_json" | jq -n \
       --arg id "$id" \
       --arg kind "$kind" \
       --arg harness "$harness" \
@@ -527,11 +560,11 @@ task_json_lines() {
       --argjson worktree_path "$worktree_json" \
       --argjson home_path "$home_json" \
       --argjson endpoint_exists "$endpoint_exists" \
-      --argjson open_decisions "$open_decisions_json" \
       --argjson pending_decision "$(bool_json "$pending_decision")" \
       --argjson blocked_event "$(bool_json "$blocked_event")" \
       --argjson report_present "$(bool_json "$report_present")" \
-      '{
+      'input as $open_decisions
+      | {
         id:$id,
         kind:$kind,
         harness:($harness // ""),
@@ -580,10 +613,9 @@ task_json_lines() {
 # Meta inventory remains the sole source of live workers; this object only
 # discloses backlog↔task inconsistency for renderers (Bearings omitted/gates).
 main_inventory_json() {  # <backlog-json> <tasks-json>
-  jq -n \
-    --argjson backlog "$1" \
-    --argjson tasks "$2" '
-    ([ $backlog.records[]?
+  json_stdin "$1" "$2" | jq -n '
+    input as $backlog | input as $tasks
+    | ([ $backlog.records[]?
        | select((.state == "in_flight" or .state == "queued") and (.structured | not)) ]) as $unstructured_current
     | ([ $backlog.records[]?
          | select(.state == "in_flight" and .structured and .requires_child_metadata) ]) as $owned_in_flight
@@ -608,16 +640,15 @@ main_inventory_json() {  # <backlog-json> <tasks-json>
 # This mode never reads parent events or terminal text and never aggregates
 # nested secondmates.
 secondmate_home_summary_json() {  # <backlog-json> <tasks-json>
-  jq -n \
+  json_stdin "$1" "$2" | jq -n \
     --arg generated "$SNAPSHOT_NOW" \
     --arg home "$FM_HOME" \
     --argjson child_n "$FM_SNAPSHOT_SECONDMATE_CHILDREN" \
     --argjson queued_n "$FM_SNAPSHOT_SECONDMATE_QUEUED" \
     --argjson decisions_n "$FM_SNAPSHOT_SECONDMATE_DECISIONS" \
-    --argjson landed_n "$FM_SNAPSHOT_SECONDMATE_LANDED_PER_HOME" \
-    --argjson backlog "$1" \
-    --argjson tasks "$2" '
-    def trunc($n):
+    --argjson landed_n "$FM_SNAPSHOT_SECONDMATE_LANDED_PER_HOME" '
+    input as $backlog | input as $tasks
+    | def trunc($n):
       tostring | gsub("\\s+"; " ")
       | if length > $n then .[:$n] + "…" else . end;
     ([ $backlog.records[]?
@@ -1027,8 +1058,9 @@ terminal_evidence_json() {  # <parent-task-json> <event-note> <evidence-contradi
 }
 
 parent_evidence_reconciliation_json() {  # <summary-json> <activities-json> <decisions-json>
-  jq -n --argjson summary "$1" --argjson activities "$2" --argjson decisions "$3" '
-    def keyed: . != null and . != "" and . != "default";
+  json_stdin "$1" "$2" "$3" | jq -n '
+    input as $summary | input as $activities | input as $decisions
+    | def keyed: . != null and . != "" and . != "default";
     def result($e; $matches; $complete; $surface):
       $e + {
         verdict:(if ($e.key | keyed | not) then "inconclusive"
@@ -1092,8 +1124,9 @@ secondmate_current_json() {  # <parent-tasks-json>
   local activity_scan activities decisions reconciliation provenance freshness reason summary summary_rc summary_bytes summary_valid summary_reason summary_invalidity state current_reason terminal terminal_contradiction contradiction
   local records='[]' seen_homes=''
   registry=$(registry_secondmates_json) || return 1
-  union=$(jq -n --argjson registry "$registry" --argjson tasks "$tasks" '
-    ($registry.records // []) as $registered
+  union=$(json_stdin "$registry" "$tasks" | jq -n '
+    input as $registry | input as $tasks
+    | ($registry.records // []) as $registered
     | (($registered | map(.id)) // []) as $registered_ids
     | ([ $registered[] as $r
          | $r + {parent_task:([$tasks[] | select(.id == $r.id)][0] // null)} ]
@@ -1216,13 +1249,14 @@ secondmate_current_json() {  # <parent-tasks-json>
           '{provenance:"parent-direct-report-terminal",trust:"untrusted-supplement",captured:false,observed_at:$observed,freshness:"not-collected",reason:"no useful contradiction check",lines:0,bytes:0,event_note_seen:false,contradiction:false}')
       fi
       if printf '%s' "$terminal" | jq -e '.contradiction == true' >/dev/null; then contradiction=true; fi
-      record=$(jq -n \
+      record=$(json_stdin "$summary" "$decisions" "$activities" "$activity_scan" "$reconciliation" | jq -n \
         --arg id "$id" --arg home "$home" --arg state "$state" --arg current_reason "$current_reason" --arg observed "$SNAPSHOT_NOW" \
-        --argjson registered "$registered" --argjson summary "$summary" --argjson summary_valid "$summary_valid" --argjson decisions "$decisions" \
-        --argjson activities "$activities" --argjson activity_scan "$activity_scan" \
-        --argjson reconciliation "$reconciliation" --argjson terminal "$terminal" --argjson contradiction "$contradiction" \
+        --argjson registered "$registered" --argjson summary_valid "$summary_valid" \
+        --argjson terminal "$terminal" --argjson contradiction "$contradiction" \
         --arg event_raw "$event_raw" --arg event_note "$event_note" --argjson event_age "$event_age" '
-        {id:$id,home:$home,registered:$registered,
+        input as $summary | input as $decisions | input as $activities
+        | input as $activity_scan | input as $reconciliation
+        | {id:$id,home:$home,registered:$registered,
          current:{state:$state,reason:($current_reason | if . == "" then null else . end)},invalidity:$summary.invalidity,
          provenance:{selected:"structured-home",structured_home:$home,summary_valid:$summary_valid,
            trust:(if $summary_valid then "complete" else "partial-structured" end),parent_event_role:"historical-only"},
@@ -1246,36 +1280,37 @@ secondmate_current_json() {  # <parent-tasks-json>
         terminal=$(jq -n --arg observed "$SNAPSHOT_NOW" \
           '{provenance:"parent-direct-report-terminal",trust:"untrusted-supplement",captured:false,observed_at:$observed,freshness:"not-collected",reason:"no parent event to compare",lines:0,bytes:0,event_note_seen:false,contradiction:false}')
       fi
-      record=$(jq -n \
+      record=$(json_stdin "$activities" "$activity_scan" "$decisions" | jq -n \
         --arg id "$id" --arg home "$home" --arg reason "$reason" --arg observed "$SNAPSHOT_NOW" \
         --arg provenance "$provenance" --arg freshness "$freshness" --arg event_raw "$event_raw" --arg event_note "$event_note" \
-        --argjson registered "$registered" --argjson event_age "$event_age" --argjson activities "$activities" --argjson activity_scan "$activity_scan" \
-        --argjson decisions "$decisions" --argjson terminal "$terminal" '
-        {id:$id,home:($home | if . == "" then null else . end),registered:$registered,
+        --argjson registered "$registered" --argjson event_age "$event_age" \
+        --argjson terminal "$terminal" '
+        input as $activities | input as $activity_scan | input as $decisions
+        | {id:$id,home:($home | if . == "" then null else . end),registered:$registered,
          current:{state:"unknown",reason:$reason},invalidity:null,
          provenance:{selected:$provenance,structured_home:($home | if . == "" then null else . end),parent_event_role:"fallback-only-not-current"},
          freshness:{status:$freshness,observed_at:$observed,age_seconds:$event_age},
          active_children:[],decisions_open:[],holds:[],queued:[],landed:[],endpoints:[],counts:{active_children:0,decisions_open:0,holds:0,queued:0,landed:0,endpoints:0},omitted:[],
          parent_event:{raw:$event_raw,note:$event_note,age_seconds:$event_age,open_activities:$activities,open_decisions:$decisions,activity_scan:$activity_scan},
          terminal_evidence:$terminal,contradiction:false}')
     fi
-    records=$(jq -n --argjson records "$records" --argjson record "$record" '$records + [$record]')
+    records=$(json_stdin "$records" "$record" | jq -n 'input as $records | input as $record | $records + [$record]')
   done <<EOF
 $rows
 EOF
-  jq -n \
-    --argjson registry "$(printf '%s' "$union" | jq '.registry')" \
-    --argjson records "$records" \
+  json_stdin "$(printf '%s' "$union" | jq '.registry')" "$records" | jq -n \
     --argjson total_registered "$total_registered" \
     --argjson total "$total" \
     --argjson shown "$shown" \
     --argjson truncated "$truncated" \
-    '{registry:$registry,records:$records,total_registered:$total_registered,total:$total,shown:$shown,truncated:$truncated}'
+    'input as $registry | input as $records
+     | {registry:$registry,records:$records,total_registered:$total_registered,total:$total,shown:$shown,truncated:$truncated}'
 }
 
 secondmate_landed_from_current_json() {  # <secondmate-current-json>
-  jq -n --argjson current "$1" '
-    {records:[ $current.records[]
+  json_stdin "$1" | jq -n '
+    input as $current
+    | {records:[ $current.records[]
       | select(.provenance.selected == "structured-home") as $mate
       | $mate.landed[]
       | . + {home:$mate.home,home_id:$mate.id}],
@@ -1329,21 +1364,24 @@ SECONDMATE_CURRENT_JSON=$(secondmate_current_json "$TASKS_JSON") \
 SECONDMATE_LANDED_JSON=$(secondmate_landed_from_current_json "$SECONDMATE_CURRENT_JSON") \
   || { echo "fm-fleet-snapshot: secondmate landed projection failed" >&2; exit 1; }
 
-jq -n \
+json_stdin \
+  "$BACKLOG_JSON" \
+  "$TASKS_JSON" \
+  "$MAIN_INVENTORY_JSON" \
+  "$SCOUT_REPORTS_JSON" \
+  "$SECONDMATE_CURRENT_JSON" \
+  "$SECONDMATE_LANDED_JSON" \
+  | jq -n \
   --arg generated "$SNAPSHOT_NOW" \
   --arg fm_home "$FM_HOME" \
   --arg fm_root "$FM_ROOT" \
   --arg state "$STATE" \
   --arg data "$DATA" \
   --arg config "$CONFIG" \
   --arg projects "$PROJECTS" \
-  --argjson backlog "$BACKLOG_JSON" \
-  --argjson tasks "$TASKS_JSON" \
-  --argjson main_inventory "$MAIN_INVENTORY_JSON" \
-  --argjson scout_reports "$SCOUT_REPORTS_JSON" \
-  --argjson secondmate_current "$SECONDMATE_CURRENT_JSON" \
-  --argjson secondmate_landed "$SECONDMATE_LANDED_JSON" \
-  'def backlog_by_id($id): ($backlog.records[]? | select(.structured == true and .id == $id) | .) // null;
+  'input as $backlog | input as $tasks | input as $main_inventory
+   | input as $scout_reports | input as $secondmate_current | input as $secondmate_landed
+   | def backlog_by_id($id): ($backlog.records[]? | select(.structured == true and .id == $id) | .) // null;
    def task_by_id($id): ($tasks[]? | select(.id == $id) | .) // null;
    def report_kind($id): (task_by_id($id).kind // backlog_by_id($id).kind // "scout");
    {

bin/fm-test-run.sh

@@ -172,7 +172,8 @@ family_for_basename() {
     fm-afk-inject-e2e.test.sh|fm-afk-return.test.sh)
       printf '%s\n' afk
       ;;
-    fm-bearings-snapshot.test.sh|fm-fleet-snapshot-view.test.sh)
+    fm-bearings-snapshot.test.sh|fm-fleet-snapshot-argv-limit.test.sh|\
+    fm-fleet-snapshot-view.test.sh)
       printf '%s\n' snapshot-bearings
       ;;
     fm-backend-cmux.test.sh|fm-backend-cmux-smoke.test.sh)