feat(500): one end-of-turn request - the completion-section check folds into the reply check

The Stop hook sent the finished reply twice: scribe_report_check.sh checked a
task-closing reply for the completion sections in shell and reported to
/report-check, and scribe_reply_check.sh sent the same reply to /reply-rules
for the rule hold. Now the reply goes once. When the turn closed a task the
hook adds the close count and ids, and the server runs the section check
(services/report_check, the same three patterns) beside the reply hold,
folding both into one reason.

The report_check adherence log is still written for every checked reply
(milestone 409's number). A section hold marks the session, so its rewrite is
sent back once with rewrite:true to record how it came out, and is never held.
The block reason carries the completion shape's one line and points at
list_reply_shapes rather than at the skill. #5496 (step 4 of milestone 500).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

plugin/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "scribe",
   "description": "Scribe for Claude Code: connects the scribe MCP server, adds the hooks that deliver live project state and relevant records at the right moment, ships the shared client-neutral Scribe skills (using-scribe, writing-plans, reporting-back, systematic-debugging, verification, brainstorming, reusing-code, shape-accounting, family-canon), and syncs your saved Scribe Processes as skills (/scribe:sync).",
-  "version": "2026.10.09.1850",
+  "version": "2026.10.09.1938",
   "author": {
     "name": "Bryan Van Deusen"
   },

plugin/PACKAGING.md

@@ -15,7 +15,7 @@ another one means adding files, not moving or rewriting any.
 |---|---|---|
 | **The skills** | `plugin/skills/*/SKILL.md` | Agent Skills (the open SKILL.md format). They state every Scribe reflex in full and name no client. `tests/test_guidance_ownership.py` fails if a skill names a particular client, or references anything outside its own folder. Every client package ships this folder verbatim. |
 | **The MCP server** | `<base URL>/mcp` | HTTP, `Authorization: Bearer <fmcp_ key>`. Its `_INSTRUCTIONS` is a client-neutral orientation — the workflow across tools (≤1,600 chars, #4389); each tool's description carries its contract; in-band responses (`placement`, `report_back`, `systems_hint`, the duplicate gate, the guessed-id refusal) fire in every client. |
-| **The adapter API** | `<base URL>/api/plugin/*` | Plain `GET` endpoints any client's hooks can call with the same key (read scope is enough): `context` (live session state), `retrieve` (rules, preferences and notes for a message), `prior-art` (records and shape-ledger hints for code being written), `tool-rules` (rules for a command about to run), `report-check` (records a completion-report check and returns the reason for a block), `processes` (stored Processes to expose as skills). |
+| **The adapter API** | `<base URL>/api/plugin/*` | Plain `GET` endpoints any client's hooks can call with the same key (read scope is enough): `context` (live session state), `retrieve` (rules, preferences and notes for a message), `prior-art` (records and shape-ledger hints for code being written), `tool-rules` (rules for a command about to run), `reply-rules` (a `POST`: the finished reply, held for an unopened rule or — when the turn closed a task — for missing completion sections), `processes` (stored Processes to expose as skills). |
 | **The API key** | Scribe → Settings → API Keys | One `fmcp_` key per install. Read scope for hooks; write scope for the MCP tools. |
 
 ## Added by each client
@@ -40,8 +40,7 @@ another one means adding files, not moving or rewriting any.
 | `hooks/scribe_after_write.sh` | PostToolUse on shell commands: the same check for code written through the shell. |
 | `hooks/scribe_tool_rules.sh` | PreToolUse on shell commands: `GET /api/plugin/tool-rules`. |
 | `hooks/scribe_moment.sh` | PreToolUse on every tool: the rules mounted on the moments the call reaches, `POST /api/plugin/moment`; skips tools `GET /api/plugin/moment-tools` says reach nothing mounted, and Scribe's own (their responses carry `moment_rules`). |
-| `hooks/scribe_report_check.sh` | Stop: when the turn closed a task, checks the reply for the completion sections and reports to `GET /api/plugin/report-check`; blocks once, with the reason the server returns. |
-| `hooks/scribe_reply_check.sh` | Stop: sends the finished reply to `POST /api/plugin/reply-rules` — the rules mounted on the reply moments, and the reply against every rule's trigger; holds once per rule, with the reason the server returns, and never holds the rewrite. |
+| `hooks/scribe_reply_check.sh` | Stop: sends the finished reply to `POST /api/plugin/reply-rules` — the rules mounted on the reply moments, and the reply against every rule's trigger, and — when the turn closed a task — the completion-section check; holds once per rule, with the reason the server returns, and never holds the rewrite. |
 | `hooks/scribe_shape_check.sh` | Stop: sends the definitions the turn wrote (the write hooks' `<sid>.written.ids` ledger) to `GET /api/plugin/shape-check`; blocks once, with the reason the server returns, so the agent judges what it built. |
 | `hooks/scribe_sync_processes.sh` + `commands/sync.md` | `GET /api/plugin/processes` → `~/.claude/skills/scribe-proc-*` stubs; `/scribe:sync` on demand. |
 | `hooks/scribe_defs.sh` | Shared shell helpers: config, dedup ledgers, outage line. |

plugin/README.md

@@ -82,15 +82,16 @@ On install you'll be asked for:
   answer" line (8 s budget here — it runs after the tool, so it gates
   nothing). The extractor, the prose/data skip list, the local by-name
   duplicate arm and the outage line are shared in `hooks/scribe_defs.sh`.
-- `hooks/hooks.json` → Stop hook (`hooks/scribe_report_check.sh`): when the
-  turn closed a Scribe task (`update_task`/`create_task` with status done),
-  checks the reply that ends it for the completion sections — where the work
-  sits, what needs you, what comes next — and reports the outcome to
-  `GET /api/plugin/report-check`. If sections are missing it blocks once with
-  the reason the server returns, and records how the rewrite came out; it
-  never blocks twice, and never blocks when the instance did not record the
-  check (unconfigured or unreachable). Outcomes land in the admin logs under
-  category `plugin`, action `report_check`.
+- `hooks/hooks.json` → Stop hook (`hooks/scribe_reply_check.sh`): sends the
+  reply that ends the turn to `POST /api/plugin/reply-rules`, which holds it
+  once for an unopened rule mounted on the reply moments or matching the reply.
+  When the turn closed a Scribe task (`update_task`/`create_task` with status
+  done), the same request has the server check the reply for the completion
+  sections — where the work sits, what needs you, what comes next. If they are
+  missing it blocks once with the reason the server returns, and records how
+  the rewrite came out; it never blocks twice, and never blocks when the
+  instance did not record the check (unconfigured or unreachable). Outcomes
+  land in the admin logs under category `plugin`, action `report_check`.
 - `hooks/hooks.json` → a second Stop hook (`hooks/scribe_shape_check.sh`): the
   write hooks note every definition a write names (and every new file) in a
   session ledger; at the end of the turn this sends them to

plugin/hooks/hooks.json

@@ -104,10 +104,6 @@
     "Stop": [
       {
         "hooks": [
-          {
-            "type": "command",
-            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/scribe_report_check.sh\""
-          },
           {
             "type": "command",
             "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/scribe_reply_check.sh\""

plugin/hooks/scribe_defs.sh

@@ -135,8 +135,8 @@ scribe_json_flat_lines() {
 # Cheap by construction, because it runs on every prompt: the last 512 KB only,
 # and grep narrows to assistant records carrying a text block BEFORE anything is
 # parsed — a transcript is mostly tool results, and parsing those in awk is the
-# multi-second cost scribe_report_check.sh already measured. Fixed strings with
-# UNESCAPED quotes can only match at a record's own top level (see that hook).
+# multi-second cost the completion-report check measured (#4107). Fixed strings
+# with UNESCAPED quotes can only match at a record's own top level.
 # A sidechain is a subagent talking, not this session, so it is skipped.
 scribe_recent_context() {
   [ -n "${1:-}" ] && [ -f "$1" ] || return 0

plugin/hooks/scribe_json.awk

@@ -39,7 +39,7 @@
 #
 #   mode=lines  the input is JSONL — one JSON value per line — and a line that
 #               does not parse is DROPPED, the rest still read. This is the
-#               transcript in scribe_report_check.sh, where the window starts
+#               transcript the Stop hooks read, where the window starts
 #               mid-record by construction: `tail -n 3000` cuts wherever it
 #               cuts, and the first line is routinely half a record. It is
 #               exactly the `map(try fromjson catch empty)` the jq program it

plugin/hooks/scribe_reply_check.sh

@@ -9,7 +9,15 @@
 # text against every rule's trigger, as the backstop for whatever the earlier
 # arms missed. An unopened rule from either half holds the reply for one read.
 #
-# THE SAME CONTRACT AS scribe_report_check.sh, and for its reasons:
+# ONE END-OF-TURN REQUEST (milestone 500 step 4). When the turn closed a task,
+# the same request carries the task ids and the server also checks the reply
+# for the completion sections — once a Stop hook of its own
+# (scribe_report_check.sh), now the same call. The section check's outcome is
+# recorded (`report_check`, milestone 409's adherence number), and when it
+# held the reply, the rewrite is sent back once with `rewrite: true` so the
+# server can record how it came out. A rewrite is never held.
+#
+# THE CONTRACT, and the reasons for it:
 #   - the server decides and supplies the words; this hook blocks only on a
 #     reason it was given, so an unconfigured or unreachable instance never
 #     stops a session;
@@ -34,15 +42,43 @@ session_id=$(scribe_json_pick "$event_flat" '.session_id')
 active=$(scribe_json_pick "$event_flat" '.stop_hook_active')
 event_cwd=$(scribe_json_pick "$event_flat" '.cwd')
 
-# The rewrite after a hold goes out as written.
-[ "$active" = "true" ] && exit 0
 [ -n "$transcript" ] && [ -f "$transcript" ] && [ -n "$session_id" ] || exit 0
+
+state_dir="${TMPDIR:-/tmp}/scribe-priorart"
+mkdir -p "$state_dir" 2>/dev/null || true
+safe_sid=$(printf '%s' "$session_id" | tr -c 'A-Za-z0-9._-' '_')
+rulefile="$state_dir/${safe_sid}.rules.ids"
+stopfile="$state_dir/${safe_sid}.checkpoint.ids"
+# Set when the section check held the reply: the next stop is its rewrite.
+reportfile="$state_dir/${safe_sid}.reportcheck"
+
+# The rewrite after a hold goes out as written. Only a rewrite of a SECTION
+# hold is sent at all — to record how it came out; one after a rule hold, or
+# another plugin's block, has nothing to report.
+if [ "$active" = "true" ]; then
+  [ -f "$reportfile" ] || exit 0
+  rm -f "$reportfile" 2>/dev/null || true
+  rewrite=true
+else
+  rm -f "$reportfile" 2>/dev/null || true
+  rewrite=false
+fi
 scribe_config || exit 0
 
 facts=$(scribe_turn_facts "$transcript")
 [ "$(scribe_turn_fact "$facts" bounded)" = "1" ] || exit 0
 reply=$(scribe_turn_fact "$facts" reply | scribe_json_unescape)
+# The reply may not be in the transcript yet when the hook fires: an empty
+# reply is "cannot tell", never "missing everything".
 [ -n "$(printf '%s' "$reply" | tr -d '[:space:]')" ] || exit 0
+# How many tasks this turn closed, and which — successful closes only, this
+# session only (scribe_turn.awk). A task created already done closes with no
+# id, so the count is what says a check is due. Digits and commas only, so
+# both drop straight into the JSON.
+closed=$(scribe_turn_fact "$facts" closed | tr -cd '0-9')
+closed=${closed:-0}
+task_ids=$(scribe_turn_fact "$facts" task_ids | tr -cd '0-9,' | sed 's/,,*/,/g; s/^,//; s/,$//')
+[ "$rewrite" = "true" ] && [ "$closed" = "0" ] && exit 0
 
 # Bounded before encoding. The server reads the head and the tail — the part
 # of a report that asks something of the reader is at its end — so a very
@@ -51,12 +87,10 @@ if [ "${#reply}" -gt 12000 ]; then
   reply="${reply:0:4000} … ${reply: -8000}"
 fi
 reply_esc=$(printf '%s' "$reply" | scribe_json_escape) || exit 0
-
-state_dir="${TMPDIR:-/tmp}/scribe-priorart"
-mkdir -p "$state_dir" 2>/dev/null || true
-safe_sid=$(printf '%s' "$session_id" | tr -c 'A-Za-z0-9._-' '_')
-rulefile="$state_dir/${safe_sid}.rules.ids"
-stopfile="$state_dir/${safe_sid}.checkpoint.ids"
+closing=""
+if [ "$closed" != "0" ]; then
+  closing=$(printf ',"closed":%d,"closed_task_ids":[%s],"rewrite":%s' "$closed" "$task_ids" "$rewrite")
+fi
 
 query=""
 scope=$(scribe_scope_query "${event_cwd:-${CLAUDE_PROJECT_DIR:-$PWD}}")
@@ -70,15 +104,17 @@ if [ -f "$stopfile" ]; then
 fi
 query=${query#&}
 
-answer=$(printf '{"reply":"%s"}' "$reply_esc" | curl -fsS --max-time 6 \
+answer=$(printf '{"reply":"%s"%s}' "$reply_esc" "$closing" | curl -fsS --max-time 6 \
   -H "Authorization: Bearer ${token}" \
   -H "Content-Type: application/json" \
   --data-binary @- \
   "${url%/}/api/plugin/reply-rules${query:+?$query}" 2>/dev/null) || exit 0
 
+[ "$rewrite" = "true" ] && exit 0
 answer_flat=$(printf '%s' "$answer" | scribe_json_flat)
 reason=$(scribe_json_pick "$answer_flat" '.reason')
 [ -n "$reason" ] || exit 0
+[ "$(scribe_json_pick "$answer_flat" '.report_check')" = "blocked" ] && : > "$reportfile" 2>/dev/null
 
 # Recorded BEFORE the block is emitted, for the act checkpoint's reason: a
 # hold that is shown and not recorded is one that can be shown again.

plugin/hooks/scribe_report_check.sh

@@ -1,155 +0,0 @@
-#!/usr/bin/env bash
-# Scribe plugin — Stop hook: a reply that closes a task carries the completion
-# sections (milestone 409 step 5).
-#
-# Everything else the plugin does happens BEFORE the agent writes: context,
-# retrieval, the reporting-back skill. This is the one moment the finished
-# reply exists, so it is both the last chance to fix a report the operator
-# cannot read and the only place adherence to the shape can be measured.
-#
-# DETERMINISTIC, NO MODEL CALL. Three questions, cheapest first:
-#
-#   1. Did this turn close a Scribe task? An `update_task` / `create_task` tool
-#      call with status "done" since the turn's prompt, whose result was not an
-#      error. Most turns stop here, silently.
-#   2. Does the reply that ends the turn have the completion sections? Loosely:
-#      where the work sits (a record named by id and title, or step N of M),
-#      what needs the operator, and what comes next. Matched on the words that
-#      carry the meaning rather than exact headings, so the skill's wording can
-#      change without breaking this.
-#   3. If sections are missing, block once with a reason naming them. The agent
-#      rewrites; the rewrite is checked and recorded, and never blocked again.
-#
-# MEASURED FROM THE FIRST CALL. Each checked reply is reported to the instance
-# (`/api/plugin/report-check`): passed, blocked, and after a rewrite either
-# passed_after_rewrite or missing_after_rewrite. Turns that closed no task are
-# not reported — they would cost a request on every turn and add nothing to
-# the rate step 6 reads (blocked among checked replies).
-#
-# IT BLOCKS ONLY WHEN THE BLOCK IS RECORDED, AND ONLY IN THE SERVER'S WORDS.
-# The report goes out first; the instance answers a recorded `blocked` with
-# the reason to send the agent back with, and the hook blocks only on that
-# reason. An unconfigured or unreachable instance therefore never stops a
-# session, every intervention is one the numbers can see, and the guidance
-# text lives on the server (plugin/PACKAGING.md: hooks carry timing and
-# transport).
-#
-# THE TRANSCRIPT FORMAT IS OBSERVED, NOT DOCUMENTED. Claude Code documents
-# `transcript_path` and `stop_hook_active` for Stop, not the JSONL inside. As
-# read from real transcripts (2026-09-14): one content block per line;
-# `type: "assistant"` lines carry `message.content[]` blocks of `text` /
-# `tool_use` ({id, name, input}); tool results arrive as `type: "user"` lines
-# whose content is a `tool_result` array ({tool_use_id, is_error}); a turn's
-# prompt — typed, or a background-task notification — is a `user` line whose
-# content is a plain string and which is not `isMeta`. Anything that does not
-# parse that way makes the hook stay out of the way rather than guess.
-#
-# Config (same as the other hooks):
-#   CLAUDE_PLUGIN_OPTION_API_ENDPOINT  base URL, no trailing slash
-#   CLAUDE_PLUGIN_OPTION_API_TOKEN     fmcp_ API key (sensitive)
-#   SCRIBE_URL / SCRIBE_TOKEN override for the settings.json dogfooding path.
-set -uo pipefail
-
-command -v curl >/dev/null 2>&1 || exit 0
-
-# shellcheck source=plugin/hooks/scribe_defs.sh
-. "$(dirname "${BASH_SOURCE[0]}")/scribe_defs.sh"
-
-# Stop delivers { session_id, transcript_path, cwd, hook_event_name, stop_hook_active }.
-event=$(cat 2>/dev/null || true)
-event_flat=$(printf '%s' "$event" | scribe_json_flat)
-transcript=$(scribe_json_pick "$event_flat" '.transcript_path')
-[ -n "$transcript" ] && [ -f "$transcript" ] || exit 0
-session_id=$(scribe_json_pick "$event_flat" '.session_id')
-active=$(scribe_json_pick "$event_flat" '.stop_hook_active')
-event_cwd=$(scribe_json_pick "$event_flat" '.cwd')
-
-safe_sid=$(printf '%s' "${session_id:-nosession}" | tr -c 'A-Za-z0-9._-' '_')
-state_dir="${TMPDIR:-/tmp}/scribe-reportcheck"
-mkdir -p "$state_dir" 2>/dev/null || true
-marker="$state_dir/${safe_sid}.blocked"
-
-# Cheap prefilter: no task tool anywhere in the recent transcript → nothing to
-# check. Keeps the ordinary turn at one grep. Process substitution, NOT a pipe:
-# under `pipefail`, `grep -q` exiting on the first match kills `tail` with
-# SIGPIPE, and the pipeline then reports failure precisely when it matched.
-grep -q -E '"name":[[:space:]]*"([^"]*__)?(update|create)_task"' < <(tail -c 2000000 "$transcript" 2>/dev/null) || {
-  rm -f "$marker" 2>/dev/null || true
-  exit 0
-}
-
-# The turn, parsed once — scribe_turn_facts, shared with the reply check.
-facts=$(scribe_turn_facts "$transcript")
-fact() { scribe_turn_fact "$facts" "$1"; }
-
-[ "$(fact bounded)" = "1" ] || exit 0
-closed=$(fact closed)
-if [ "${closed:-0}" = "0" ]; then
-  rm -f "$marker" 2>/dev/null || true
-  exit 0
-fi
-# Escaped on one line coming out of awk, so the format survives a multi-line
-# reply; decoded here, once, where it is about to be read as text.
-reply=$(fact reply | scribe_json_unescape)
-task_ids=$(fact task_ids)
-
-# The reply may not be written to the transcript yet when the hook fires. An
-# empty reply is "cannot tell", not "missing everything" — stay out of the way.
-[ -n "$(printf '%s' "$reply" | tr -d '[:space:]')" ] || exit 0
-
-missing=()
-# Where the work sits: a record named by id AND title (#12 "…", milestone 3 "…"),
-# or a step position. A bare id is exactly the homework this shape removes.
-# shellcheck disable=SC2016 # backticks here are literal markdown, not an expansion
-grep -q -i -E '(#[0-9]+|milestone [0-9]+|task [0-9]+)[*_`]*[[:space:]]*[*_`]*["“]|step [0-9]+ of [0-9]+' <<< "$reply" \
-  || missing+=("where it sits")
-# What needs the operator — "needs you: nothing" counts; it is an answer.
-grep -q -i -E 'needs? (from )?you|nothing (is )?needed from you|your (call|decision)' <<< "$reply" \
-  || missing+=("needs you")
-# What comes next.
-grep -q -i -E '\bnext\b' <<< "$reply" \
-  || missing+=("next")
-
-# Reports the outcome; prints the instance's reply and returns 0 only if the
-# instance recorded it.
-report() {
-  scribe_config || return 1
-  local q repo enc m
-  q="outcome=$1&task_ids=${task_ids}"
-  m=$(IFS=,; printf '%s' "${missing[*]:-}")
-  if [ -n "$m" ]; then
-    enc=$(printf '%s' "$m" | scribe_urlenc) || enc=""
-    q="${q}&missing=${enc}"
-  fi
-  scope=$(scribe_scope_query "${event_cwd:-${CLAUDE_PROJECT_DIR:-$PWD}}")
-  [ -n "$scope" ] && q="${q}&${scope}"
-  curl -fsS --max-time 4 \
-    -H "Authorization: Bearer ${token}" \
-    "${url%/}/api/plugin/report-check?${q}" 2>/dev/null
-}
-
-if [ "$active" = "true" ]; then
-  # A Stop hook already blocked this stop. If it was this one, the reply is
-  # the rewrite: record how it came out, and let the session stop whatever
-  # the answer. If it was another plugin's block, this hook has nothing to add.
-  [ -f "$marker" ] || exit 0
-  rm -f "$marker" 2>/dev/null || true
-  if [ ${#missing[@]} -eq 0 ]; then report passed_after_rewrite >/dev/null; else report missing_after_rewrite >/dev/null; fi
-  exit 0
-fi
-rm -f "$marker" 2>/dev/null || true
-
-if [ ${#missing[@]} -eq 0 ]; then
-  report passed >/dev/null
-  exit 0
-fi
-
-# The words the agent is sent back with are the server's (plugin/PACKAGING.md:
-# a hook carries timing and transport). No reason back → nothing recorded →
-# no block.
-answer=$(report blocked) || exit 0
-reason=$(scribe_json_pick "$(printf '%s' "$answer" | scribe_json_flat)" '.reason')
-[ -n "$reason" ] || exit 0
-: > "$marker" 2>/dev/null || true
-printf '{"decision":"block","reason":"%s"}\n' "$(printf '%s' "$reason" | scribe_json_escape)"
-exit 0

plugin/hooks/scribe_shape_check.sh

@@ -10,7 +10,7 @@
 # words: the agent that built the code is the one participant who knows what
 # it is, and the end of the turn is the last moment that is still true.
 #
-# THE SAME DISCIPLINE AS scribe_report_check.sh, deliberately:
+# THE SAME DISCIPLINE AS the completion-section check in scribe_reply_check.sh:
 #   - it blocks only on a `reason` the instance returned, which it returns
 #     only for a block it RECORDED — an unconfigured or unreachable instance
 #     never stops a session, and every intervention is one the numbers see;

plugin/hooks/scribe_turn.awk

@@ -2,7 +2,7 @@
 #
 # Reads the flat `IDX<TAB>PATH<TAB>VALUE` stream that scribe_json.awk produces
 # in `mode=lines` from a Claude Code transcript, and answers the four questions
-# scribe_report_check.sh asks. It replaces a thirty-line jq program; the shape
+# the Stop hooks ask (scribe_reply_check.sh). It replaces a thirty-line jq program; the shape
 # of the answer is unchanged, so the hook around it reads the same.
 #
 #   bounded   1 if a user prompt was found in the window, else empty. A window

src/scribe/routes/plugin.py

@@ -367,28 +367,58 @@ async def reply_rules():
     the reply asks something), and the reply text against every rule's
     trigger — the backstop for whatever the earlier arms missed.
 
-    Body: `{"reply": "<text>"}`. Query: `repo` / `project_id` for the scope;
+    ONE END-OF-TURN REQUEST (milestone 500 step 4): a reply that closed tasks
+    is also checked here for the completion sections (services/report_check),
+    which used to be a Stop hook and an endpoint of its own. Both holds fold
+    into one `reason`; `report_check` says what the section check recorded, so
+    the hook knows the rewrite is one to report.
+
+    Body: `{"reply": "<text>", "closed": 1, "closed_task_ids": [41],
+    "rewrite": false}` — the last three only when the turn closed a task.
+    `closed` is the count and decides whether the check runs (a task created
+    already done has no id to list); `rewrite` marks the reply written after a
+    section hold, which is recorded and never held.
+    Query: `repo` / `project_id` for the scope;
     `held_rule_ids` (opened this session — exempt, as at the act checkpoint);
     `exclude_rule_ids` (named this session — not re-counted as surfaced);
     `stopped_rule_ids` (already held a reply or an act this session — a rule
     holds once, and the per-session cap counts these).
 
     Returns `reason` — the words the hook blocks with, empty when nothing
-    holds — plus `rule_ids` for the hook's ledger and `moments` reached.
+    holds — plus `rule_ids` for the hook's ledger, `moments` reached and
+    `report_check` (the recorded outcome, or "" when nothing was checked).
     """
     data = await request.get_json(silent=True) or {}
+    if not isinstance(data, dict):
+        data = {}
     reply = str(data.get("reply") or "")
+    # `type(...) is int`, not isinstance: JSON `true` would otherwise read as 1.
+    closed = data.get("closed") if type(data.get("closed")) is int else 0
+    ids = data.get("closed_task_ids")
+    task_ids = [i for i in ids if type(i) is int and i > 0][:20] if isinstance(ids, list) else []
+    rewrite = data.get("rewrite") is True
     project_id, _repo, _unbound = await _project_scope()
-    held = await moment_delivery_svc.reply_hold(
-        g.user.id, reply, project_id=project_id,
-        exclude=frozenset(_int_list(request.args.get("exclude_rule_ids"))),
-        held=frozenset(_int_list(request.args.get("held_rule_ids"))),
-        stopped=frozenset(_int_list(request.args.get("stopped_rule_ids"))),
-    )
+
+    checked: dict = {}
+    if closed > 0:
+        checked = await report_check_svc.check_reply(
+            g.user.id, reply, task_ids=task_ids, rewrite=rewrite, project_id=project_id or None,
+        )
+    # The rewrite after a hold goes out as written: recorded above, held by nothing.
+    held: dict = {}
+    if not rewrite:
+        held = await moment_delivery_svc.reply_hold(
+            g.user.id, reply, project_id=project_id,
+            exclude=frozenset(_int_list(request.args.get("exclude_rule_ids"))),
+            held=frozenset(_int_list(request.args.get("held_rule_ids"))),
+            stopped=frozenset(_int_list(request.args.get("stopped_rule_ids"))),
+        )
+    reasons = [r for r in (checked.get("reason", ""), held.get("reason", "")) if r]
     return jsonify({
-        "reason": held.get("reason", ""),
+        "reason": "\n\n".join(reasons),
         "rule_ids": held.get("rule_ids", []),
         "moments": held.get("moments", []),
+        "report_check": checked.get("outcome", ""),
     })
 
 
@@ -504,45 +534,6 @@ def _parse_shapes(raw: str) -> list[tuple[str, str]]:
     return out
 
 
-@plugin_bp.get("/report-check")
-@login_required
-async def report_check():
-    """Record what a Stop hook found in a reply that closed a task (milestone 409 step 5).
-
-    The hook decides which completion sections the reply lacks — a local check
-    of text it can read — and reports the outcome here. For `blocked` the
-    response carries the `reason` to send the agent back with: the words are
-    the server's, so every client's hook says the same thing (plugin/PACKAGING.md).
-    A hook blocks only on a `reason` it received, which means only on a block
-    that was recorded.
-
-    A GET for the reason every plugin endpoint is one: a read-scoped key must
-    be enough to run the plugin, and this records telemetry the way /retrieve
-    records a retrieval log.
-
-    Query:
-        outcome (str)   — passed | blocked | passed_after_rewrite |
-                          missing_after_rewrite. Anything else is a 400.
-        missing (opt)   — comma-separated sections the reply lacked:
-                          "where it sits", "needs you", "next".
-        task_ids (opt)  — comma-separated ids of the tasks the turn closed.
-        repo (opt)      — working repo remote, resolved like the other arms.
-    """
-    outcome = (request.args.get("outcome") or "").strip()
-    if outcome not in report_check_svc.OUTCOMES:
-        return jsonify({"error": f"outcome must be one of {list(report_check_svc.OUTCOMES)}"}), 400
-    missing = [m for m in (request.args.get("missing") or "").split(",") if m.strip()]
-    task_ids = _int_list(request.args.get("task_ids"))[:20]
-    project_id, _repo, _unbound = await _project_scope()
-    await report_check_svc.record_report_check(
-        g.user.id, outcome, missing=missing, task_ids=task_ids, project_id=project_id or None,
-    )
-    body: dict = {"status": "ok"}
-    if outcome == "blocked":
-        body["reason"] = report_check_svc.block_reason(missing)
-    return jsonify(body)
-
-
 @plugin_bp.get("/shape-check")
 @login_required
 async def shape_check():
@@ -557,7 +548,7 @@ async def shape_check():
     recorded, and never on the stop that follows one (`phase=after`).
 
     A GET like every plugin endpoint: a read-scoped key runs the plugin, and
-    this records telemetry the way /report-check does. It changes no ledger
+    this records telemetry the way /reply-rules records its section check. It changes no ledger
     row — the agent's own classify_shapes call does that.
 
     Query:

src/scribe/services/report_check.py

@@ -1,38 +1,60 @@
-"""The report-shape check: what the plugin's Stop hook found, and what it says.
+"""The report-shape check: does a reply that closed a task carry the completion
+sections, and what is it sent back with when it does not.
 
 WHY THIS EXISTS (milestone 409 step 5)
 
 Everything that helps an agent write a readable completion report arrives
-BEFORE the reply is written. A client's Stop hook is the one moment the
-finished reply exists, so it checks that a reply closing a task carries the
-completion sections (where the work sits, what needs the operator, what comes
-next), and reports what it found here. Two jobs live on this side:
+BEFORE the reply is written. The Stop hook is the one moment the finished reply
+exists, so a reply that closed a task is checked for the completion sections
+(where the work sits, what needs the operator, what comes next). Two jobs:
 
   - RECORDING the outcome, so the rate of `blocked` among checked replies is a
-    number milestone 409's last step can read rather than an impression.
-  - OWNING THE WORDS the agent is sent back with. A hook carries timing and
-    transport only (plugin/PACKAGING.md); guidance text comes from the server,
-    so a second client's hook gets the same instruction by calling the same
-    endpoint, and the wording changes in one place.
+    number rather than an impression (`category=plugin, action=report_check`).
+  - OWNING THE WORDS the agent is sent back with, so every client's hook says
+    the same thing (plugin/PACKAGING.md: hooks carry timing and transport).
+
+ONE END-OF-TURN REQUEST (milestone 500 step 4). This used to be a Stop hook of
+its own that checked the sections in shell and reported here; the reply-moment
+check sent the same reply to `/reply-rules` a moment later. The hook now sends
+the reply once, with the ids of the tasks the turn closed, and the section
+check runs here beside the reply hold. The patterns are the ones the shell
+used, matched on the words that carry the meaning rather than exact headings,
+so a shape's wording can change without breaking this.
 
 app_logs rather than a table of its own: one small event with a JSON detail is
 what that table holds, it already has retention and an admin viewer, and
-nothing here needs a join. If the numbers earn a readout, that is the moment to
-decide whether they earn a table.
+nothing here needs a join.
 """
 from __future__ import annotations
 
 import json
+import logging
+import re
 
 from scribe.models import async_session
 from scribe.models.app_log import AppLog
+from scribe.services import reply_shapes
+
+logger = logging.getLogger(__name__)
 
 OUTCOMES = ("passed", "blocked", "passed_after_rewrite", "missing_after_rewrite")
 
-# The sections a hook may name as missing, in the order the reason lists them.
-# Anything else a client sends is dropped rather than echoed into an
-# instruction the agent will follow.
-SECTIONS = ("where it sits", "needs you", "next")
+# The sections, in the order the reason lists them, each with what counts as
+# having it. A bare id ("closed #41") does not place the work: naming a record
+# by id AND title, or a step position, is the shape — the title is what spares
+# the reader a lookup. "Needs you: nothing" counts; it is an answer.
+SECTION_PATTERNS: dict[str, re.Pattern] = {
+    "where it sits": re.compile(
+        r'(#[0-9]+|milestone [0-9]+|task [0-9]+)[*_`]*\s*[*_`]*["“]|step [0-9]+ of [0-9]+', re.I),
+    "needs you": re.compile(
+        r"needs? (from )?you|nothing (is )?needed from you|your (call|decision)", re.I),
+    "next": re.compile(r"\bnext\b", re.I),
+}
+SECTIONS = tuple(SECTION_PATTERNS)
+
+
+def missing_sections(reply: str) -> list[str]:
+    return [name for name, pat in SECTION_PATTERNS.items() if not pat.search(reply or "")]
 
 
 def known_sections(missing: list[str]) -> list[str]:
@@ -43,16 +65,17 @@ def known_sections(missing: list[str]) -> list[str]:
 def block_reason(missing: list[str]) -> str:
     """What the agent is told when its completion report is sent back.
 
-    Names what is missing and points at the reporting-back skill for the shape
-    rather than restating it — the skill owns the shape (decision #4027).
+    Names what is missing and carries the completion shape's one line rather
+    than the whole shape: the shape itself was delivered when the task closed,
+    and `list_reply_shapes` has it in full.
     """
     listed = ", ".join(known_sections(missing)) or "the completion sections"
+    shape = reply_shapes.SHAPES["completion"]
     return (
         f"This turn closed a Scribe task, and the reply that ends it is missing: {listed}. "
-        "The operator reads this reply to find out where the work stands. Rewrite it as a "
-        "completion report (the reporting-back skill has the shape): where it sits — the task "
-        "or milestone by id and title, from `placement` — what now works, what needs them "
-        "(or \"nothing\"), and what comes next."
+        "The person the work is for reads this reply to find out where it stands. Rewrite it "
+        f"as a completion report — {shape.reminder} Take where it sits from `placement`, the "
+        "task or plan by id and title (`list_reply_shapes` has the shape in full)."
     )
 
 
@@ -78,3 +101,32 @@ async def record_report_check(
             details=json.dumps(details),
         ))
         await session.commit()
+
+
+async def check_reply(
+    user_id: int, reply: str, *, task_ids: list[int], rewrite: bool,
+    project_id: int | None = None,
+) -> dict:
+    """Check a reply that closed tasks, record the outcome, and say whether it is held.
+
+    `rewrite` is the reply written after an earlier hold: it is recorded and
+    never held again, so a hold costs one turn at most.
+
+    Returns {"outcome", "reason"} — `reason` empty unless the reply is held.
+    A hold happens only when its record was written: an outcome the numbers
+    cannot see is not one this check may act on, so a recording failure
+    degrades to no hold rather than to an unmeasured one.
+    """
+    missing = missing_sections(reply)
+    if rewrite:
+        outcome = "missing_after_rewrite" if missing else "passed_after_rewrite"
+    else:
+        outcome = "blocked" if missing else "passed"
+    try:
+        await record_report_check(user_id, outcome, missing=missing, task_ids=task_ids,
+                                  project_id=project_id)
+    except Exception:  # noqa: BLE001 - an unrecorded check never holds a reply
+        logger.warning("report check not recorded", exc_info=True)
+        return {"outcome": "", "reason": ""}
+    return {"outcome": outcome,
+            "reason": block_reason(missing) if outcome == "blocked" else ""}

tests/test_reply_moment.py

@@ -197,7 +197,8 @@ async def test_the_route_passes_the_reply_and_all_three_ledgers():
         with patch.object(routes.moment_delivery_svc, "reply_hold", hold):
             resp = await routes.reply_rules.__wrapped__()
         body = await resp.get_json()
-    assert body == {"reason": "Held.", "rule_ids": [11], "moments": ["reply.report"]}
+    assert body == {"reason": "Held.", "rule_ids": [11], "moments": ["reply.report"],
+                    "report_check": ""}
     assert hold.await_args.args == (7, "done")
     assert hold.await_args.kwargs == {
         "project_id": 3, "exclude": frozenset({5}), "held": frozenset({4}),
@@ -205,6 +206,55 @@ async def test_the_route_passes_the_reply_and_all_three_ledgers():
     }
 
 
+async def _reply_route(body, *, hold_reason="", checked=None):
+    from scribe.routes import plugin as routes
+
+    hold = AsyncMock(return_value={"reason": hold_reason, "rule_ids": [11] if hold_reason else [],
+                                   "moments": ["reply.report"]})
+    check = AsyncMock(return_value=checked or {"outcome": "passed", "reason": ""})
+    app = Quart(__name__)
+    async with app.test_request_context("/api/plugin/reply-rules", method="POST", json=body,
+                                        query_string={"project_id": "3"}):
+        g.user = type("U", (), {"id": 7})()
+        with patch.object(routes.moment_delivery_svc, "reply_hold", hold), \
+             patch.object(routes.report_check_svc, "check_reply", check):
+            resp = await routes.reply_rules.__wrapped__()
+        return await resp.get_json(), hold, check
+
+
+async def test_a_turn_that_closed_nothing_is_not_section_checked():
+    _body, _hold, check = await _reply_route({"reply": "done"})
+    check.assert_not_awaited()
+
+
+async def test_a_closing_turn_is_section_checked_and_both_holds_fold_into_one_reason():
+    """One end-of-turn request (milestone 500 step 4): the section check and
+    the rule hold answer together, in one `reason`."""
+    body, _hold, check = await _reply_route(
+        {"reply": "done", "closed": 1, "closed_task_ids": [41, True, "x"], "rewrite": False},
+        hold_reason="RULE HOLD", checked={"outcome": "blocked", "reason": "SECTIONS"},
+    )
+    assert body["reason"] == "SECTIONS\n\nRULE HOLD"
+    assert body["report_check"] == "blocked"
+    # JSON `true` is not task 1, and a string is not an id.
+    assert check.await_args.kwargs == {"task_ids": [41], "rewrite": False, "project_id": 3}
+
+
+async def test_a_task_created_already_done_is_checked_without_an_id():
+    _body, _hold, check = await _reply_route({"reply": "done", "closed": 1, "closed_task_ids": []})
+    assert check.await_args.kwargs["task_ids"] == []
+
+
+async def test_the_rewrite_is_recorded_and_held_by_nothing():
+    body, hold, check = await _reply_route(
+        {"reply": "done", "closed": 1, "closed_task_ids": [41], "rewrite": True},
+        checked={"outcome": "passed_after_rewrite", "reason": ""},
+    )
+    assert check.await_args.kwargs["rewrite"] is True
+    hold.assert_not_awaited()
+    assert body["reason"] == "" and body["report_check"] == "passed_after_rewrite"
+
+
 # ── the hook ────────────────────────────────────────────────────────────
 
 
@@ -251,6 +301,58 @@ def test_the_hook_blocks_in_the_servers_words_and_records_the_hold(tmp_path):
     assert seen[1]["exclude_rule_ids"] == ["11"]
 
 
+def _closing_transcript(tmp_path, *replies):
+    lines = [
+        {"type": "user", "message": {"role": "user", "content": "please finish it"}},
+        {"type": "assistant", "message": {"content": [
+            {"type": "tool_use", "id": "toolu_1", "name": "mcp__plugin_scribe_scribe__update_task",
+             "input": {"task_id": 41, "status": "done"}}]}},
+        {"type": "user", "message": {"content": [
+            {"type": "tool_result", "tool_use_id": "toolu_1", "is_error": False, "content": "{}"}]}},
+    ] + [{"type": "assistant", "message": {"content": [{"type": "text", "text": r}]}} for r in replies]
+    path = tmp_path / "t.jsonl"
+    path.write_text("\n".join(json.dumps(x, separators=(",", ":")) for x in lines) + "\n")
+    return path
+
+
+SECTION_HOLD = json.dumps({"reason": "Rewrite as a completion report.", "rule_ids": [],
+                           "moments": ["reply.report"], "report_check": "blocked"}).encode()
+
+
+def test_a_turn_that_closed_nothing_sends_no_close(tmp_path):
+    t = _transcript(tmp_path, "Done.")
+    with http_sink(by_path={"/api/plugin/reply-rules": QUIET}) as (port, seen):
+        _run(tmp_path, port, t)
+    assert "closed" not in json.loads(seen[0]["_body"])
+
+
+def test_a_section_hold_blocks_once_then_the_rewrite_is_reported_and_never_held(tmp_path):
+    """The completion-section check, folded into the one Stop request: the
+    first stop is held in the server's words, the rewrite goes back once with
+    `rewrite: true` so its outcome is recorded, and nothing after that is sent."""
+    t = _closing_transcript(tmp_path, "All done, pushed it.")
+    with http_sink(by_path={"/api/plugin/reply-rules": SECTION_HOLD}) as (port, seen):
+        out = json.loads(_run(tmp_path, port, t))
+        assert out == {"decision": "block", "reason": "Rewrite as a completion report."}
+        first = json.loads(seen[0]["_body"])
+        assert (first["closed"], first["closed_task_ids"], first["rewrite"]) == (1, [41], False)
+
+        rewritten = _closing_transcript(tmp_path, "All done, pushed it.", "Where this sits: …")
+        assert _run(tmp_path, port, rewritten, active=True) == ""
+        assert json.loads(seen[1]["_body"])["rewrite"] is True
+        # The marker is spent: a further stop in the loop sends nothing.
+        assert _run(tmp_path, port, rewritten, active=True) == ""
+        assert len(seen) == 2
+
+
+def test_a_rule_hold_on_a_closing_turn_does_not_mark_a_rewrite(tmp_path):
+    t = _closing_transcript(tmp_path, "Done.")
+    with http_sink(by_path={"/api/plugin/reply-rules": HELD}) as (port, seen):
+        _run(tmp_path, port, t)
+        assert _run(tmp_path, port, t, active=True) == ""
+    assert len(seen) == 1
+
+
 def test_the_hook_says_nothing_when_nothing_holds(tmp_path):
     t = _transcript(tmp_path, "Done.")
     with http_sink(by_path={"/api/plugin/reply-rules": QUIET}) as (port, _seen):

tests/test_report_check_hook.py

@@ -1,169 +0,0 @@
-"""The Stop hook that checks a task-closing reply for the completion sections
-(milestone 409 step 5).
-
-Runs the real shell against synthetic transcripts in the shape Claude Code
-writes (one content block per JSONL line) and the shared HTTP sink. What it
-pins: silence on every turn that closed nothing; a block only when the
-instance recorded it, in the words the instance returned; one rewrite at most,
-recorded; and no block from another plugin's loop or a failed task write.
-"""
-from __future__ import annotations
-
-import json
-import os
-import shutil
-import subprocess
-from pathlib import Path
-
-import pytest
-
-from tests.helpers import http_sink
-
-HOOK = Path(__file__).resolve().parents[1] / "plugin" / "hooks" / "scribe_report_check.sh"
-TOOL = "mcp__plugin_scribe_scribe__update_task"
-GOOD = ('**Where this sits:** milestone 12 "Move the backups offsite", step 3 of 5.\n'
-        "**What now works:** the sync runs nightly.\n**Needs you:** nothing.\n**Next:** alerts.")
-BAD = "All done, pushed it."
-REASON = "SERVER REASON: rewrite as a completion report"
-
-
-def _env(tmp_path, url="http://127.0.0.1:9"):
-    for tool in ("curl", "bash"):
-        if shutil.which(tool) is None:
-            pytest.skip(f"hook runtime tool {tool!r} not installed")
-    return {"PATH": os.environ["PATH"], "SCRIBE_URL": url, "SCRIBE_TOKEN": "t",
-            "TMPDIR": str(tmp_path), "HOME": str(tmp_path)}
-
-
-def _prompt(text="please finish it"):
-    return {"type": "user", "message": {"role": "user", "content": text}}
-
-
-def _tool_use(tid="toolu_1", status="done", name=TOOL, task_id=41):
-    return {"type": "assistant", "message": {"content": [
-        {"type": "tool_use", "id": tid, "name": name, "input": {"task_id": task_id, "status": status}}]}}
-
-
-def _result(tid="toolu_1", is_error=False):
-    return {"type": "user", "message": {"content": [
-        {"type": "tool_result", "tool_use_id": tid, "is_error": is_error, "content": "{}"}]}}
-
-
-def _text(text):
-    return {"type": "assistant", "message": {"content": [{"type": "text", "text": text}]}}
-
-
-def _transcript(tmp_path, lines):
-    path = tmp_path / "t.jsonl"
-    # Compact, like the file Claude Code writes ({"name":"…"}, no spaces).
-    path.write_text("\n".join(json.dumps(line, separators=(",", ":")) for line in lines) + "\n")
-    return path
-
-
-def _run(env, transcript, active=False, session="s1"):
-    out = subprocess.run(
-        ["bash", str(HOOK)],
-        input=json.dumps({"session_id": session, "transcript_path": str(transcript),
-                          "cwd": str(transcript.parent), "hook_event_name": "Stop",
-                          "stop_hook_active": active}),
-        capture_output=True, text=True, env=env, timeout=30,
-    )
-    assert out.returncode == 0, out.stderr
-    return out.stdout.strip()
-
-
-def _closing_turn(reply):
-    return [_prompt(), _text("On it."), _tool_use(), _result(), _text(reply)]
-
-
-def test_a_turn_that_closed_nothing_is_silent_and_reports_nothing(tmp_path):
-    with http_sink(b'{"status":"ok","reason":"x"}') as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        t = _transcript(tmp_path, [_prompt(), _tool_use(status="in_progress"), _result(), _text(BAD)])
-        assert _run(env, t) == ""
-        assert seen == []
-
-
-def test_a_complete_report_passes_silently_and_is_recorded(tmp_path):
-    with http_sink(b'{"status":"ok"}') as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        assert _run(env, _transcript(tmp_path, _closing_turn(GOOD))) == ""
-        assert [q["outcome"] for q in seen] == [["passed"]]
-        assert seen[0]["task_ids"] == ["41"]
-
-
-def test_a_missing_section_blocks_once_in_the_servers_words_then_records_the_rewrite(tmp_path):
-    reply = json.dumps({"status": "ok", "reason": REASON}).encode()
-    with http_sink(reply) as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        out = json.loads(_run(env, _transcript(tmp_path, _closing_turn(BAD))))
-        assert out == {"decision": "block", "reason": REASON}
-        assert seen[0]["outcome"] == ["blocked"]
-        assert seen[0]["missing"] == ["where it sits,needs you,next"]
-
-        # The rewrite: Claude Code sets stop_hook_active; the hook records and never blocks again.
-        rewritten = _transcript(tmp_path, _closing_turn(BAD) + [_text(GOOD)])
-        assert _run(env, rewritten, active=True) == ""
-        assert seen[1]["outcome"] == ["passed_after_rewrite"]
-        assert _run(env, rewritten, active=True) == ""
-        assert len(seen) == 2
-
-
-def test_a_rewrite_that_still_misses_is_recorded_and_not_blocked(tmp_path):
-    reply = json.dumps({"status": "ok", "reason": REASON}).encode()
-    with http_sink(reply) as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        t = _transcript(tmp_path, _closing_turn(BAD))
-        _run(env, t)
-        assert _run(env, t, active=True) == ""
-        assert [q["outcome"][0] for q in seen] == ["blocked", "missing_after_rewrite"]
-
-
-def test_another_hooks_block_loop_is_left_alone(tmp_path):
-    with http_sink(b'{"status":"ok","reason":"x"}') as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        assert _run(env, _transcript(tmp_path, _closing_turn(BAD)), active=True) == ""
-        assert seen == []
-
-
-def test_a_task_write_that_failed_closed_nothing(tmp_path):
-    with http_sink(b'{"status":"ok","reason":"x"}') as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        t = _transcript(tmp_path, [_prompt(), _tool_use(), _result(is_error=True), _text(BAD)])
-        assert _run(env, t) == ""
-        assert seen == []
-
-
-def test_a_task_closed_in_an_earlier_turn_does_not_count(tmp_path):
-    with http_sink(b'{"status":"ok","reason":"x"}') as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        t = _transcript(tmp_path, _closing_turn(GOOD) + [_prompt("thanks, what else?"), _text(BAD)])
-        assert _run(env, t) == ""
-        assert seen == []
-
-
-def test_a_reply_not_yet_written_is_not_judged(tmp_path):
-    with http_sink(b'{"status":"ok","reason":"x"}') as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        t = _transcript(tmp_path, [_prompt(), _tool_use(), _result()])
-        assert _run(env, t) == ""
-        assert seen == []
-
-
-def test_no_block_without_a_recorded_check(tmp_path):
-    t = _transcript(tmp_path, _closing_turn(BAD))
-    # Unreachable instance.
-    assert _run(_env(tmp_path), t) == ""
-    # An instance that answered but returned no reason.
-    with http_sink(b'{"status":"ok"}') as (port, seen):
-        assert _run(_env(tmp_path, f"http://127.0.0.1:{port}"), t, session="s2") == ""
-        assert seen[0]["outcome"] == ["blocked"]
-
-
-def test_a_bare_id_does_not_count_as_placing_the_work(tmp_path):
-    reply = json.dumps({"status": "ok", "reason": REASON}).encode()
-    with http_sink(reply) as (port, seen):
-        env = _env(tmp_path, f"http://127.0.0.1:{port}")
-        bare = "Closed #41.\n**Needs you:** nothing.\n**Next:** #42."
-        assert json.loads(_run(env, _transcript(tmp_path, _closing_turn(bare))))["decision"] == "block"
-        assert seen[0]["missing"] == ["where it sits"]

tests/test_services_report_check.py

@@ -1,12 +1,38 @@
-"""The server half of the report-shape check (milestone 409 step 5): the words a
-blocked reply is sent back with, and the outcome record."""
+"""The report-shape check (milestone 409 step 5): which completion sections a
+task-closing reply lacks, the words it is sent back with, and the outcome
+record. Since milestone 500 step 4 the check itself runs here, inside the one
+end-of-turn request, rather than in a Stop hook of its own."""
 import json
-from unittest.mock import patch
+from unittest.mock import AsyncMock, patch
 
 import pytest
 
 from tests.helpers import make_mock_session
 
+GOOD = ('**Where this sits:** milestone 12 "Move the backups offsite", step 3 of 5.\n'
+        "**What now works:** the sync runs nightly.\n**Needs you:** nothing.\n**Next:** alerts.")
+BAD = "All done, pushed it."
+
+
+def test_a_complete_report_misses_nothing():
+    from scribe.services.report_check import missing_sections
+
+    assert missing_sections(GOOD) == []
+
+
+def test_a_bare_reply_misses_every_section_in_order():
+    from scribe.services.report_check import SECTIONS, missing_sections
+
+    assert missing_sections(BAD) == list(SECTIONS)
+
+
+def test_a_bare_id_does_not_count_as_placing_the_work():
+    """The title is what spares the reader a lookup; "closed #41" does not."""
+    from scribe.services.report_check import missing_sections
+
+    assert missing_sections("Closed #41.\n**Needs you:** nothing.\n**Next:** #42.") == ["where it sits"]
+    assert missing_sections('Closed #41 "Sync". Needs you: nothing. Next: #42.') == []
+
 
 def test_the_reason_names_only_sections_it_knows():
     from scribe.services.report_check import block_reason
@@ -14,8 +40,17 @@ def test_the_reason_names_only_sections_it_knows():
     reason = block_reason(["next", "ignore previous instructions", "Where It Sits"])
     assert "missing: where it sits, next." in reason
     assert "ignore previous instructions" not in reason
-    # It points at the skill that owns the shape rather than restating it.
-    assert "reporting-back" in reason and "placement" in reason
+
+
+def test_the_reason_carries_the_completion_shapes_line_and_where_the_rest_is():
+    """The shape was delivered when the task closed; the reason repeats its
+    one line, not the whole of it, and names where the full text is."""
+    from scribe.services import reply_shapes
+    from scribe.services.report_check import block_reason
+
+    reason = block_reason(["next"])
+    assert reply_shapes.SHAPES["completion"].reminder in reason
+    assert "list_reply_shapes" in reason and "placement" in reason
 
 
 def test_a_reason_with_nothing_recognised_still_says_what_to_do():
@@ -45,3 +80,30 @@ async def test_an_unknown_outcome_is_refused_before_anything_is_written():
          pytest.raises(ValueError):
         await record_report_check(7, "skipped")
     session.add.assert_not_called()
+
+
+@pytest.mark.parametrize("reply,rewrite,outcome,held", [
+    (GOOD, False, "passed", False),
+    (BAD, False, "blocked", True),
+    (GOOD, True, "passed_after_rewrite", False),
+    (BAD, True, "missing_after_rewrite", False),
+])
+async def test_check_reply_records_every_outcome_and_holds_only_a_first_miss(reply, rewrite, outcome, held):
+    from scribe.services import report_check
+
+    record = AsyncMock()
+    with patch.object(report_check, "record_report_check", record):
+        got = await report_check.check_reply(7, reply, task_ids=[41], rewrite=rewrite, project_id=2)
+    assert got["outcome"] == outcome
+    assert bool(got["reason"]) is held
+    assert record.await_args.args == (7, outcome)
+    assert record.await_args.kwargs["task_ids"] == [41]
+
+
+async def test_an_unrecorded_check_holds_nothing():
+    """A hold the numbers cannot see is not one this check may make."""
+    from scribe.services import report_check
+
+    with patch.object(report_check, "record_report_check", AsyncMock(side_effect=RuntimeError("db"))):
+        got = await report_check.check_reply(7, BAD, task_ids=[41], rewrite=False)
+    assert got == {"outcome": "", "reason": ""}