feat(mcp): enter_project becomes a small primer: goal, recent work, open work, vocabulary (#4045)

The handshake carried the whole project record, every milestone's plan, full
rule text, the notes most recently edited and ~9k of design guidance. For
project 2 that was ~222k characters, past what an MCP client accepts as a tool
result. Each category was walked through with the operator and sized to what a
session needs on arrival; each names the call that has the rest.

- project: id, title, status and the full goal (session start's "full goal"
  pointer still lands here). get_project keeps the whole record.
- milestone_summary: the 5 most recently touched milestones, any status, most
  recent first, without plans. Summaries gain last_touched_at: the later of
  the milestone's own edit and its newest step update, from the query that
  already counts steps. milestone_summary_omitted counts the rest and points
  to list_milestones. get_project and list_milestones list every milestone,
  also without plans.
- open_tasks: the 10 most recently touched open tasks, with or without a
  milestone, each naming its milestone. list_notes gains sort="touched"
  (the later of updated_at and the newest work-log), because a log doesn't
  bump updated_at.
- recent_notes: dropped. Retrieval surfaces notes by relevance, and
  get_recent covers recency.
- systems: id and name.
- design_system: summary plus guidance_call. get_design_system gains
  resolved_guidance, the chain-merged prose; its own guidance field is only
  the departures, so session start's old pointer to it led to a fragment.
  The session start pointer and using-scribe's "Building UI" section now
  name resolved_guidance.
- rules: rules_payload(brief=True) gives project_rules as id and title plus
  subscribed_rulebooks, and records only what it shows. Retrieval delivers
  rules in full and ignores subscriptions (#4052). Other callers unchanged.
- pattern_coverage, inception and systems_bootstrap: unchanged.

Clients: the plugin's using-scribe skill, the compaction notice and session
start are updated here; the REST project summary only gains last_touched_at.
Plugin version minted.

Tests: a size ceiling on the handshake for a large project; milestone and
task selection and naming; brief rules; resolved_guidance; the session
start pointer; and a real-Postgres test that a work-log touches its task and
a step update touches its milestone.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy

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), and syncs your saved Scribe Processes as skills (/scribe:sync).",
-  "version": "2026.09.14.2254",
+  "version": "2026.09.15.0204",
   "author": {
     "name": "Bryan Van Deusen"
   },

plugin/hooks/scribe_session_context.sh

@@ -180,7 +180,7 @@ fi
 
 # Compaction re-grounding: lead with a reload banner when this fire is a compact.
 if [ "$source" = "compact" ]; then
-  prepend "> ⟳ This session was just COMPACTED — earlier turns are now a summary, so in-flight detail may be lost. Any rules that had been retrieved went into that summary with everything else, so treat yourself as holding none: before the next consequential act, ask again with \`search(content_type=\"rule\")\` rather than trusting a half-remembered one. Re-run \`enter_project()\` for the active project, check its open tasks and recent notes, and reconcile what you are mid-way through against what Scribe records. Scribe is the record."
+  prepend "> ⟳ This session was just COMPACTED — earlier turns are now a summary, so in-flight detail may be lost. Any rules that had been retrieved went into that summary with everything else, so treat yourself as holding none: before the next consequential act, ask again with \`search(content_type=\"rule\")\` rather than trusting a half-remembered one. Re-run \`enter_project()\` for the active project, check its recent milestones and open tasks, and reconcile what you are mid-way through against what Scribe records. Scribe is the record."
 fi
 
 # Nothing at all to inject → stay silent.

plugin/skills/using-scribe/SKILL.md

@@ -15,8 +15,8 @@ asked for.
 
 If the working repo maps to a Scribe project (you're in a known repo, or
 `list_repo_bindings` shows a binding), call `enter_project(id)` — it returns the
-project plus the rules bound to the areas it works in, open tasks, and recent
-notes in one shot.
+project's goal, the milestones and open tasks worked on most recently, its
+Systems and the titles of its own rules in one shot.
 
 Then **ask before you act**: before anything hard to reverse or outward-facing,
 search the rules for what you are about to do. Reflex 2 below is why asking,
@@ -294,9 +294,10 @@ really is a standing instruction about how to work.
 
 ## Building UI: the project's design system binds
 
-`enter_project` returns a `design_system` when the project has one, with the
-guidance **chain-merged** — the house style it inherits plus its own departures
-from it. Treat it the way you treat a rule.
+`enter_project` names the project's `design_system` when it has one. Before
+writing UI, read its guidance: `get_design_system(id)` returns it as
+`resolved_guidance`, **chain-merged** — the house style it inherits plus its own
+departures from it. Treat it the way you treat a rule.
 
 Before writing a colour, size, radius, weight or duration by hand, reach for a
 token: `resolve_design_system(id)` for the values, or

src/scribe/mcp/tools/design_systems.py

@@ -108,14 +108,22 @@ async def get_design_system(design_system_id: int) -> dict:
     For what it actually resolves to once inheritance is applied, use
     `resolve_design_system`. The two answer different questions and a system
     that overrides nothing has an empty token list but a full resolved set.
+
+    `resolved_guidance` is the prose to build UI from: the guidance of every
+    system in the inheritance chain, outermost ancestor first, so the house
+    style comes before this system's departures from it. `design_system`'s
+    own `guidance` field is only the departures. Read `resolved_guidance`
+    before writing UI; enter_project carries just the summary (#4045).
     """
     uid = current_user_id()
     system = await ds_svc.get_design_system(uid, design_system_id)
     if system is None:
         raise ValueError(f"design system {design_system_id} not found")
     tokens = await ds_svc.list_tokens(uid, design_system_id)
+    context = await ds_svc.design_context(uid, design_system_id)
     return {
         "design_system": system.to_dict(),
+        "resolved_guidance": context["guidance"] if context else [],
         "tokens": [t.to_dict() for t in tokens],
     }
 

src/scribe/mcp/tools/projects.py

@@ -42,41 +42,22 @@ async def list_projects() -> dict:
     return {"projects": [p.to_dict() for p in rows]}
 
 
-# Done milestones a project read still lists: the recent ones say what just
-# finished, and older ones are a list_milestones call away (#4045).
-_DONE_MILESTONES_KEPT = 5
-
-
-async def _milestone_block(uid: int, project_id: int) -> dict:
-    """`milestone_summary` for a project read, brief and bounded (#4045).
-
-    Every open milestone plus the most recent done ones, without plan bodies.
-    `milestone_summary_omitted` is attached only when older done milestones
-    were left out, and names the calls that reach them (#2483).
-    """
-    rows = await milestones_svc.get_project_milestone_summary(uid, project_id)
-    brief, omitted = milestones_svc.brief_milestone_summary(
-        rows, done_kept=_DONE_MILESTONES_KEPT,
-    )
-    out: dict = {"milestone_summary": brief}
-    if omitted:
-        out["milestone_summary_omitted"] = (
-            f"{omitted} older done milestone(s) not listed. "
-            f"list_milestones({project_id}) lists every milestone; "
-            "get_milestone(id) has one milestone's plan and steps."
-        )
-    return out
+# How many of each kind the handshake lists. Enough to say what was worked on
+# lately and what's open; the rest is a list_milestones / list_tasks call away.
+# The handshake once carried every milestone's plan and came to ~222k
+# characters, past what a client accepts as a tool result (#4045).
+_HANDSHAKE_MILESTONES = 5
+_HANDSHAKE_OPEN_TASKS = 10
 
 
 async def enter_project(project_id: int) -> dict:
-    """Session-start handshake: load full context for working on a project.
+    """Session-start handshake: a primer on the project before you work in it.
 
     Call this FIRST whenever you're about to do project-scoped work
     (start_planning, create_task, update_*, anything that takes a project_id).
-    One round-trip returns the project, its applicable rules (both rulebook-
-    subscribed and project-scoped), milestone progress, open tasks, and
-    recently-updated notes — everything you need to know the lay of the land
-    before mutating.
+    One round-trip returns what the project is for, what was worked on
+    lately, what's open, and the vocabulary to record against. It is kept
+    small on purpose: each part names the call that has the rest.
 
     No persistent server state: this is a read snapshot. Re-call if the
     session goes idle long enough that the data feels stale.
@@ -84,15 +65,29 @@ async def enter_project(project_id: int) -> dict:
     Args:
         project_id: The project to enter.
 
-    Returns a dict with keys: project, milestone_summary, applicable_rules,
-    project_rules, subscribed_rulebooks, applicable_rules_truncated,
-    open_tasks, recent_notes, design_system, systems, pattern_coverage —
-    plus systems_bootstrap, present only when it applies (see below).
+    Returns a dict with keys: project, milestone_summary, open_tasks, systems,
+    design_system, project_rules, subscribed_rulebooks, pattern_coverage —
+    plus milestone_summary_omitted, inception and systems_bootstrap, each
+    present only when it applies (see below).
 
-    `milestone_summary` lists every open milestone and the most recently
-    finished done ones, each with its description and progress but NOT its
-    plan: get_milestone(id) reads a plan. `milestone_summary_omitted` appears
-    only when older done milestones were left out, and says how many.
+    `project` is id, title, status and the full goal. get_project has the
+    whole record.
+
+    `milestone_summary` is the 5 most recently touched milestones, any status,
+    most recent first. Touched counts a step changing, not only the milestone
+    itself. Each carries its description and progress but NOT its plan:
+    get_milestone(id) reads a plan and its steps. `milestone_summary_omitted`
+    says how many others exist; list_milestones lists them all.
+
+    `open_tasks` is the 10 most recently touched todo / in-progress tasks,
+    with or without a milestone. A work-log counts as touching its task. Each
+    names its milestone. list_tasks has the rest.
+
+    `project_rules` lists the project's own rules by id and title, and
+    `subscribed_rulebooks` the rulebooks it draws on. A rule reaches you in
+    full when your work matches it; get_rule(id) reads one, and
+    search(content_type="rule") asks whether one covers what you are about
+    to do.
 
     `pattern_coverage` (usually null) is the shape-accounting line — how many
     of the bound repo's extracted shapes carry a classification against canon
@@ -110,7 +105,7 @@ async def enter_project(project_id: int) -> dict:
     updating a record, ask which of these areas it is about and pass their ids
     as `system_ids`. If the area a record describes is missing from this list,
     create it with create_system rather than leaving the area unmodelled. Read
-    a subsystem's accumulated records with list_system_records.
+    a subsystem's accumulated records with list_system_records. Each is id and name; get_system has the charter.
 
     `inception` (milestone 297) appears ONLY when the project is yours and
     nobody has decided what it inherits: it carries the current defaults
@@ -125,10 +120,12 @@ async def enter_project(project_id: int) -> dict:
     lists. It stops appearing the moment the first System exists.
 
     `design_system` is null unless the project points at one. When present it
-    carries the chain-merged guidance (the house style AND this project's
-    departures from it) plus a summary of the token set — treat it as binding
-    for any UI you write, and pull the values with resolve_design_system or
-    get_design_system_stylesheet before reaching for a literal.
+    is a summary (title, what it inherits, token count and groups) and
+    `guidance_call`. The guidance binds any UI you write the way a rule does:
+    before writing UI, read `resolved_guidance` from get_design_system (the
+    house style AND this project's departures from it), and pull values with
+    resolve_design_system or get_design_system_stylesheet before reaching for
+    a literal.
 
     Entering a project also SCOPES the session: reference and offer work on
     this project only, and pass its id to search / list_* so results stay
@@ -151,19 +148,22 @@ async def enter_project(project_id: int) -> dict:
     applicable = await rulebooks_svc.get_applicable_rules(
         project_id=project_id, user_id=uid,
     )
-    milestones = await _milestone_block(uid, project_id)
+    milestone_rows = await milestones_svc.get_project_milestone_summary(
+        uid, project_id,
+    )
+    milestone_summary, omitted = milestones_svc.brief_milestone_summary(
+        milestone_rows, limit=_HANDSHAKE_MILESTONES,
+    )
+    milestone_titles = {m["id"]: m.get("title") for m in milestone_rows}
     open_tasks, _ = await notes_svc.list_notes(
         uid, is_task=True, project_id=project_id,
-        status=["todo", "in_progress"], sort="updated_at", limit=10,
-    )
-    recent_notes, _ = await notes_svc.list_notes(
-        uid, is_task=False, project_id=project_id,
-        sort="updated_at", limit=5,
+        status=["todo", "in_progress"], sort="touched", limit=_HANDSHAKE_OPEN_TASKS,
     )
     # The tagging vocabulary. Surfaced HERE because an instruction to "tag
     # records to Systems" is only executable if the list is in front of the
     # agent when it writes — which it never was, and tagging stopped within
-    # three days of the feature landing (#2546's audit).
+    # three days of the feature landing (#2546's audit). Untagged writes now
+    # also ask with the vocabulary listed; this copy lets the first write tag.
     systems = await systems_svc.list_systems(uid, project_id)
 
     # The arrival-moment half of the bootstrap ask (#2683): session start is
@@ -185,24 +185,30 @@ async def enter_project(project_id: int) -> dict:
     if project.user_id == uid and not inception_svc.is_decided(project):
         inception_ask = await inception_svc.inception_ask(uid, project_id)
 
-    # Probably the largest surfacing by volume, and it emitted nothing — so
-    # the pulls it caused floated unattributed and the surfaced:pulled ratio
-    # ran against a denominator missing its biggest contributor (#2477). An
-    # AMBIENT source: these are top-N-by-recency, not a ranked choice, and the
-    # readout counts them apart so dead-weight detection isn't poisoned by
+    # An AMBIENT source (#2477): top-N-by-recency, not a ranked choice, and
+    # the readout counts it apart so dead-weight detection isn't poisoned by
     # "recently updated in a project you opened".
     record_surfaced(
         user_id=uid,
-        note_ids=[int(t.id) for t in open_tasks] + [int(n.id) for n in recent_notes],
+        note_ids=[int(t.id) for t in open_tasks],
         source="enter_project",
     )
     # A project need not have one, and most installs won't — null is ordinary
-    # here, not a missing prerequisite.
+    # here, not a missing prerequisite. Summary only: the guidance is ~9k of
+    # prose most sessions never use, so it's one call away (#4045).
     design_system = None
     if project.design_system_id:
-        design_system = await design_systems_svc.design_context(
+        design = await design_systems_svc.design_context(
             uid, project.design_system_id,
         )
+        if design:
+            design_system = {
+                k: design[k]
+                for k in ("id", "title", "inherits_from", "token_count", "token_groups")
+            }
+            design_system["guidance_call"] = (
+                f"get_design_system({design['id']}) → resolved_guidance"
+            )
 
     # Cache read ONLY — computing coverage moves a repo tarball and never
     # belongs in this request path. Null is the ordinary state (no forge, or
@@ -223,38 +229,33 @@ async def enter_project(project_id: int) -> dict:
     )
 
     out = {
-        "project": project.to_dict(),
+        "project": {
+            "id": project.id, "title": project.title,
+            "status": project.status, "goal": project.goal,
+        },
         "pattern_coverage": coverage_svc.coverage_line(coverage) if coverage else None,
-        # Trimmed to what tagging needs. The full charter is get_system's job —
-        # this list rides along on every session start, so it stays lean.
-        "systems": [
-            {
-                "id": s.id, "name": s.name,
-                "description": (s.description or "").split("\n")[0][:200],
-            }
-            for s in systems
-        ],
+        "systems": [{"id": s.id, "name": s.name} for s in systems],
         "design_system": design_system,
-        **milestones,
-        **rulebooks_svc.rules_payload(applicable, user_id=uid, source="enter_project"),
+        "milestone_summary": milestone_summary,
+        **rulebooks_svc.rules_payload(
+            applicable, user_id=uid, source="enter_project", brief=True,
+        ),
         "open_tasks": [
             {
                 "id": t.id, "title": t.title, "status": t.status,
-                "priority": t.priority, "task_kind": t.task_kind,
                 "milestone_id": t.milestone_id,
+                "milestone_title": milestone_titles.get(t.milestone_id),
             }
             for t in open_tasks
         ],
-        "recent_notes": [
-            {
-                "id": n.id, "title": n.title,
-                "updated_at": n.updated_at.isoformat() if n.updated_at else None,
-            }
-            for n in recent_notes
-        ],
     }
     # Attached only when it applies — a key that usually says null trains
     # readers to skip it (#2483), and this one exists to be acted on.
+    if omitted:
+        out["milestone_summary_omitted"] = (
+            f"{omitted} other milestone(s) not listed. "
+            f"list_milestones({project_id}) lists every milestone."
+        )
     if systems_bootstrap:
         out["systems_bootstrap"] = systems_bootstrap
     if inception_ask:
@@ -265,18 +266,18 @@ async def enter_project(project_id: int) -> dict:
 async def get_project(project_id: int) -> dict:
     """Fetch a Scribe project by ID.
 
-    Returns full project fields, a milestone_summary list (shaped as in
-    enter_project: open milestones and the recent done ones, no plan bodies,
-    with milestone_summary_omitted when older done ones were left out), and
-    the rulebook-applicable_rules / subscribed_rulebooks pair the assistant
-    should consult when working on this project.
+    Returns full project fields, a milestone_summary list (every milestone,
+    with description and progress but no plan body; get_milestone reads a
+    plan), and the rulebook-applicable_rules / subscribed_rulebooks pair the
+    assistant should consult when working on this project.
     """
     uid = current_user_id()
     project = await projects_svc.get_project(uid, project_id)
     if project is None:
         raise ValueError(f"project {project_id} not found")
     data = project.to_dict()
-    data.update(await _milestone_block(uid, project_id))
+    rows = await milestones_svc.get_project_milestone_summary(uid, project_id)
+    data["milestone_summary"], _ = milestones_svc.brief_milestone_summary(rows)
     applicable = await rulebooks_svc.get_applicable_rules(
         project_id=project_id, user_id=uid,
     )

src/scribe/services/milestones.py

@@ -213,9 +213,13 @@ async def get_project_milestone_summaries(
         )).scalars().all())
 
         counts: dict[int, dict[str, int]] = {}
+        step_touched: dict[int, datetime] = {}
         if milestones:
             rows = await session.execute(
-                select(Note.milestone_id, Note.status, func.count(Note.id))
+                select(
+                    Note.milestone_id, Note.status, func.count(Note.id),
+                    func.max(Note.updated_at),
+                )
                 .where(
                     Note.milestone_id.in_([m.id for m in milestones]),
                     Note.status.isnot(None),
@@ -223,13 +227,21 @@ async def get_project_milestone_summaries(
                 )
                 .group_by(Note.milestone_id, Note.status)
             )
-            for milestone_id, status, count in rows.fetchall():
+            for milestone_id, status, count, latest in rows.fetchall():
                 counts.setdefault(milestone_id, {})[status] = count
+                if latest and (milestone_id not in step_touched
+                               or latest > step_touched[milestone_id]):
+                    step_touched[milestone_id] = latest
 
     out: dict[int, list[dict]] = {pid: [] for pid in project_ids}
     for m in milestones:
         entry = m.to_dict()
         entry.update(_progress_from_counts(counts.get(m.id, {})))
+        # A milestone's own updated_at doesn't move when its steps do, so a
+        # plan whose steps closed today would read as untouched since it was
+        # written (#4045). Touched is the later of the two.
+        touched = [t for t in (m.updated_at, step_touched.get(m.id)) if t]
+        entry["last_touched_at"] = max(touched).isoformat() if touched else None
         out.setdefault(m.project_id, []).append(entry)
     return out
 
@@ -254,22 +266,20 @@ _BRIEF_FIELDS = (
 
 
 def brief_milestone_summary(
-    rows: list[dict], *, done_kept: int | None = None,
+    rows: list[dict], *, limit: int | None = None,
 ) -> tuple[list[dict], int]:
-    """Trim summary rows to the listing fields, optionally capping done ones.
+    """Trim summary rows to the listing fields, optionally keeping only the
+    most recently touched.
 
-    `done_kept` keeps only the N most recently updated done milestones (every
-    open one stays), in the original order_index order. A done plan is
-    history, and a handshake that grows with a project's whole history grows
-    past what a client accepts. None keeps every row. Returns (rows, omitted),
-    where `omitted` counts the done milestones left out.
+    With `limit`, keeps the N rows with the latest `last_touched_at`, whatever
+    their status, most recent first: a handshake says what was worked on
+    lately, and "active" alone doesn't (a plan can sit active for months).
+    Without it, every row stays in its original order. Returns (rows, omitted).
     """
-    if done_kept is None:
-        kept = rows
-    else:
-        done = [r for r in rows if r.get("status") == "done"]
-        recent = sorted(done, key=lambda r: r.get("updated_at") or "", reverse=True)
-        keep_ids = {r.get("id") for r in recent[:done_kept]}
-        kept = [r for r in rows if r.get("status") != "done" or r.get("id") in keep_ids]
+    kept = rows
+    if limit is not None:
+        kept = sorted(
+            rows, key=lambda r: r.get("last_touched_at") or "", reverse=True,
+        )[:limit]
     brief = [{k: r[k] for k in _BRIEF_FIELDS if k in r} for r in kept]
     return brief, len(rows) - len(kept)

src/scribe/services/notes.py

@@ -318,6 +318,9 @@ async def list_notes(
     degraded but never empty. Superseded records are not demoted here: the
     penalty reorders a top-k, and reordering a paginated, counted list would
     make page boundaries lie. The search surfaces carry the demotion.
+
+    `sort` is a Note column name, or "touched": the later of updated_at and
+    the record's newest work-log.
     """
     from scribe.services.access import notes_visibility_clause
 
@@ -442,6 +445,19 @@ async def list_notes(
         if semantic_order is not None:
             # A query is a relevance claim — see the docstring.
             query = query.order_by(semantic_order)
+        elif sort == "touched":
+            # Last touched: the later of the task's own edit and its newest
+            # work-log. Logging doesn't bump updated_at, so a task worked
+            # through its logs would otherwise sort as untouched (#4045).
+            # GREATEST skips a NULL, so a task with no logs sorts by its edit.
+            from scribe.models.task_log import TaskLog
+            last_log = (
+                select(func.max(TaskLog.created_at))
+                .where(TaskLog.task_id == Note.id)
+                .scalar_subquery()
+            )
+            touched = func.greatest(Note.updated_at, last_log)
+            query = query.order_by(touched.asc() if order == "asc" else touched.desc())
         else:
             sort_col = getattr(Note, sort, Note.updated_at)
             if order == "asc":

src/scribe/services/plugin_context.py

@@ -2236,8 +2236,9 @@ async def build_session_context(
                         f"Values: `resolve_design_system({design['id']})` · "
                         f"stylesheet: `get_design_system_stylesheet({design['id']})` "
                         f"· the prose (aesthetic, voice, where the accent may "
-                        f"appear): `enter_project` returns it, or "
-                        f"`get_design_system({design['id']})`.",
+                        f"appear), inherited house style included: "
+                        f"`get_design_system({design['id']})` → "
+                        f"`resolved_guidance`.",
                     ]
     elif unbound_repo:
         lines += [

src/scribe/services/rulebooks.py

@@ -1306,7 +1306,9 @@ async def get_applicable_rules(
     }
 
 
-def rules_payload(applicable: dict, *, user_id: int | None, source: str) -> dict:
+def rules_payload(
+    applicable: dict, *, user_id: int | None, source: str, brief: bool = False,
+) -> dict:
     """The caller-facing shape of a get_applicable_rules() result.
 
     Every surface that hands rules to an agent (enter_project, get_project,
@@ -1333,7 +1335,25 @@ def rules_payload(applicable: dict, *, user_id: int | None, source: str) -> dict
     (`plugin_context`) — computed a marker and showed nobody
     anything, and counting those would put rules in the denominator that no
     agent ever saw.
+
+    `brief` is the session handshake's form (#4045): the project's own rules
+    as id and title, and the subscribed rulebooks, nothing else. Rules reach a
+    session in full by retrieval, which ignores subscriptions, so the handshake
+    lists which constraints exist rather than restating them; get_rule reads
+    one. Only what is shown is recorded as surfaced.
     """
+    if brief:
+        project_rules = [
+            {"id": r["id"], "title": r["title"]}
+            for r in applicable.get("project_rules", [])
+        ]
+        record_rule_surfaced(
+            user_id=user_id, rule_ids=[r["id"] for r in project_rules], source=source,
+        )
+        return {
+            "project_rules": project_rules,
+            "subscribed_rulebooks": applicable["subscribed_rulebooks"],
+        }
     record_rule_surfaced(
         user_id=user_id,
         rule_ids=(

tests/test_guidance_ownership.py

@@ -112,7 +112,7 @@ TOPICS: tuple[Topic, ...] = (
     Topic("scribe is the system of record; keep one copy", U, ("one copy",),
           "let any existing local memory shrink", index=("one copy",)),
     Topic("orient: enter the project, check repo bindings", U, ("enter_project", "list_repo_bindings"),
-          "returns the project plus the rules bound to the areas it works in",
+          "the milestones and open tasks worked on most recently",
           index=("enter_project",)),
     Topic("rules are retrieved; ask before a consequential act", U, ('content_type="rule"', "nothing matched"),
           "an empty session is not evidence of an empty rulebook",

tests/test_integration_handshake_touched.py

@@ -0,0 +1,81 @@
+"""Real-Postgres tests for "recently touched" in the enter_project handshake (#4045).
+
+What a mock cannot show: that a work-log moves its task up the list even
+though logging never bumps the task's updated_at, and that a milestone whose
+steps changed today reads as touched today even though its own row is old.
+"""
+from datetime import datetime, timedelta, timezone
+
+import pytest
+import pytest_asyncio
+
+from scribe.models import async_session
+from scribe.models.milestone import Milestone
+from scribe.models.note import Note
+from scribe.models.project import Project
+from scribe.models.task_log import TaskLog
+from scribe.services import milestones as milestones_svc
+from scribe.services import notes as notes_svc
+from tests.helpers import ensure_user
+
+pytestmark = [pytest.mark.integration, pytest.mark.usefixtures("_dispose_engine", "_no_embedding")]
+
+NOW = datetime.now(timezone.utc)
+
+
+@pytest_asyncio.fixture
+async def world():
+    """Two open tasks and two milestones with deliberately staged timestamps."""
+    async with async_session() as s:
+        owner = await ensure_user(s, "handshake_owner")
+        project = Project(user_id=owner.id, title="Handshake target")
+        s.add(project)
+        await s.flush()
+
+        # Milestone "old plan": its own row is 30 days old, one step changed now.
+        old_plan = Milestone(user_id=owner.id, project_id=project.id, title="old plan",
+                             updated_at=NOW - timedelta(days=30))
+        # Milestone "recent edit": its own row changed 2 days ago, no steps.
+        recent_edit = Milestone(user_id=owner.id, project_id=project.id, title="recent edit",
+                                updated_at=NOW - timedelta(days=2))
+        s.add_all([old_plan, recent_edit])
+        await s.flush()
+
+        # "logged": last edited 10 days ago, but worked through a log just now.
+        logged = Note(user_id=owner.id, project_id=project.id, title="logged",
+                      status="todo", task_kind="work",
+                      updated_at=NOW - timedelta(days=10))
+        # "edited": last edited 1 day ago, no logs.
+        edited = Note(user_id=owner.id, project_id=project.id, title="edited",
+                      status="todo", task_kind="work",
+                      updated_at=NOW - timedelta(days=1))
+        step = Note(user_id=owner.id, project_id=project.id, milestone_id=old_plan.id,
+                    title="step", status="done", task_kind="work", updated_at=NOW)
+        s.add_all([logged, edited, step])
+        await s.flush()
+        s.add(TaskLog(task_id=logged.id, user_id=owner.id, content="worked on it",
+                      created_at=NOW))
+        ids = {"owner": owner.id, "pid": project.id, "logged": logged.id,
+               "edited": edited.id, "old_plan": old_plan.id, "recent_edit": recent_edit.id}
+        await s.commit()
+    return ids
+
+
+async def test_a_work_log_counts_as_touching_its_task(world):
+    by_edit, _ = await notes_svc.list_notes(
+        world["owner"], is_task=True, project_id=world["pid"],
+        status=["todo", "in_progress"], sort="updated_at",
+    )
+    by_touch, _ = await notes_svc.list_notes(
+        world["owner"], is_task=True, project_id=world["pid"],
+        status=["todo", "in_progress"], sort="touched",
+    )
+    assert [t.id for t in by_edit] == [world["edited"], world["logged"]]
+    assert [t.id for t in by_touch] == [world["logged"], world["edited"]]
+
+
+async def test_a_step_changing_counts_as_touching_its_milestone(world):
+    rows = await milestones_svc.get_project_milestone_summary(world["owner"], world["pid"])
+    brief, omitted = milestones_svc.brief_milestone_summary(rows, limit=1)
+    assert omitted == 1
+    assert [m["id"] for m in brief] == [world["old_plan"]]

tests/test_mcp_tool_design_systems.py

@@ -197,3 +197,25 @@ async def test_update_token_leaves_supersedes_alone_when_omitted():
         from scribe.mcp.tools.design_systems import update_design_token
         await update_design_token(token_id=9, purpose="text on action surfaces")
     assert "supersedes" not in svc.update_token.await_args.kwargs
+
+
+# --- get: the guidance a UI session builds from -----------------------------
+
+@pytest.mark.asyncio
+async def test_get_design_system_carries_the_chain_merged_guidance():
+    """enter_project carries only a summary and points here (#4045). The
+    system's own `guidance` field is only its departures; a session building
+    UI needs the house style too, so the merged form rides alongside."""
+    from scribe.mcp.tools.design_systems import get_design_system
+
+    merged = [{"design_system_id": 1, "title": "House", "guidance": "house style"},
+              {"design_system_id": 2, "title": "App", "guidance": "departures"}]
+    with patch("scribe.mcp.tools.design_systems.ds_svc.get_design_system",
+               AsyncMock(return_value=_fake_design_system())), \
+         patch("scribe.mcp.tools.design_systems.ds_svc.list_tokens",
+               AsyncMock(return_value=[])), \
+         patch("scribe.mcp.tools.design_systems.ds_svc.design_context",
+               AsyncMock(return_value={"guidance": merged})):
+        out = await get_design_system(2)
+
+    assert out["resolved_guidance"] == merged

tests/test_mcp_tool_projects.py

@@ -165,8 +165,8 @@ async def test_update_project_raises_when_not_found():
 
 @pytest.mark.asyncio
 async def test_enter_project_composes_full_context():
-    """enter_project pulls project + rules + milestone summary + open tasks +
-    recent notes in one composed call."""
+    """enter_project pulls project + rule titles + milestone summary + open
+    tasks in one composed call, each in its brief handshake form (#4045)."""
     p = fake_project(id=5, title="P")
     applicable_payload = {
         "rules": [{"id": 1, "title": "r1", "statement": "s",
@@ -199,14 +199,19 @@ async def test_enter_project_composes_full_context():
     ):
         out = await enter_project(project_id=5)
 
-    assert out["project"]["id"] == 5
+    assert out["project"] == {"id": 5, "title": "P", "status": "active", "goal": ""}
     assert out["milestone_summary"] == milestone_summary
-    assert out["applicable_rules"][0]["title"] == "r1"
-    assert out["project_rules"][0]["id"] == 99
+    # Rules arrive in full by retrieval; the handshake lists the project's own
+    # by id and title and drops the subscription bookkeeping (#4045).
+    assert out["project_rules"] == [{"id": 99, "title": "pr1"}]
     assert out["subscribed_rulebooks"] == [{"id": 2, "title": "rb"}]
-    assert out["open_tasks"][0]["id"] == 100
-    assert out["open_tasks"][0]["status"] == "in_progress"
-    assert out["recent_notes"][0]["id"] == 200
+    for gone in ("applicable_rules", "applicable_rules_truncated",
+                 "suppressed_rules", "suppressed_topics", "recent_notes"):
+        assert gone not in out, gone
+    assert out["open_tasks"] == [{
+        "id": 100, "title": "T1", "status": "in_progress",
+        "milestone_id": 10, "milestone_title": "MS",
+    }]
     # No design system on this project -> the key is present and null, not
     # absent. A caller that has to distinguish "no key" from "no system" will
     # eventually get it wrong.
@@ -252,10 +257,7 @@ async def test_enter_project_surfaces_the_systems_vocabulary():
     ):
         out = await enter_project(project_id=5)
 
-    assert out["systems"] == [
-        {"id": 3, "name": "retrieval",
-         "description": "Embeddings, ranking, auto-inject."}
-    ]
+    assert out["systems"] == [{"id": 3, "name": "retrieval"}]
 
 
 def _enter_project_stubs(p):
@@ -371,6 +373,9 @@ async def test_enter_project_hands_back_the_design_system_when_the_project_has_o
 
     assert out["design_system"]["token_count"] == 95
     assert out["design_system"]["inherits_from"] == ["House"]
+    # Summary only: the guidance is one call away (#4045).
+    assert "guidance" not in out["design_system"]
+    assert out["design_system"]["guidance_call"] == "get_design_system(9) → resolved_guidance"
     assert ctx.await_args.args == (7, 9)   # caller's id, the project's system
 
 

tests/test_milestone_summary_brief.py

@@ -1,12 +1,13 @@
-"""Milestone listings stay brief and bounded (#4045).
+"""The enter_project handshake stays a small primer (#4045).
 
-enter_project once carried every milestone's full plan body. On a project with
-39 milestones that came to ~222k characters, past what an MCP client accepts
-as a tool result, so the session handshake arrived as a file to page through.
+enter_project once carried every milestone's full plan body, the whole project
+record, full rule text and ~9k of design guidance. On a project with 39
+milestones that came to ~222k characters, past what an MCP client accepts as
+a tool result, so the session handshake arrived as a file to page through.
 """
 import contextlib
 import json
-from unittest.mock import AsyncMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
@@ -19,28 +20,32 @@ from tests.helpers import fake_project
 pytestmark = pytest.mark.usefixtures("_bind_user")
 
 PLAN = "A plan paragraph long enough to matter. " * 125  # ~5k chars
+GOAL = "What the project is for. " * 50                  # ~1.2k chars
 
 
-def _row(mid: int, status: str, updated: str) -> dict:
+def _milestone(mid: int, status: str, touched_day: int) -> dict:
     """A summary row as get_project_milestone_summary returns it."""
+    touched = f"2026-08-{touched_day:02d}T00:00:00+00:00"
     return {
         "id": mid, "user_id": 7, "project_id": 5, "title": f"M{mid}",
         "description": f"what M{mid} is for", "body": PLAN, "status": status,
         "order_index": mid, "created_at": "2026-01-01T00:00:00+00:00",
-        "updated_at": updated, "total": 4, "completed": 2, "pct": 50.0,
+        "updated_at": "2026-01-01T00:00:00+00:00", "last_touched_at": touched,
+        "total": 4, "completed": 2, "pct": 50.0,
         "status_counts": {"todo": 2, "in_progress": 0, "done": 2, "cancelled": 0},
     }
 
 
-def _history(done: int, active: int) -> list[dict]:
-    """`done` done milestones (higher id = more recently updated), then `active` open ones."""
-    rows = [_row(i, "done", f"2026-08-{i + 1:02d}T00:00:00+00:00") for i in range(done)]
-    rows += [_row(done + i, "active", "2026-01-01T00:00:00+00:00") for i in range(active)]
-    return rows
+def _history(count: int) -> list[dict]:
+    """`count` milestones, alternating done/active; higher id = touched later."""
+    return [
+        _milestone(i, "done" if i % 2 else "active", 1 + i % 28)
+        for i in range(count)
+    ]
 
 
 def test_brief_rows_leave_out_the_plan_and_what_the_caller_already_knows():
-    brief, omitted = brief_milestone_summary([_row(1, "active", "2026-09-01")])
+    brief, omitted = brief_milestone_summary([_milestone(1, "active", 3)])
     assert omitted == 0
     assert brief == [{
         "id": 1, "title": "M1", "description": "what M1 is for", "status": "active",
@@ -49,93 +54,145 @@ def test_brief_rows_leave_out_the_plan_and_what_the_caller_already_knows():
     }]
 
 
-def test_cap_keeps_every_open_milestone_and_the_most_recent_done_ones_in_order():
-    rows = _history(done=8, active=3)
-    brief, omitted = brief_milestone_summary(rows, done_kept=2)
-    assert omitted == 6
-    # The two most recently updated done ones (ids 6, 7) and all open ones,
-    # still in order_index order.
-    assert [r["id"] for r in brief] == [6, 7, 8, 9, 10]
+def test_limit_keeps_the_most_recently_touched_whatever_their_status():
+    """A plan can sit "active" for months; recency is what says it's current."""
+    rows = [_milestone(1, "active", 1), _milestone(2, "done", 9),
+            _milestone(3, "active", 5), _milestone(4, "done", 7)]
+    brief, omitted = brief_milestone_summary(rows, limit=2)
+    assert omitted == 2
+    assert [r["id"] for r in brief] == [2, 4]   # most recent first
 
 
-def test_no_cap_keeps_every_row():
-    brief, omitted = brief_milestone_summary(_history(done=8, active=3))
+def test_no_limit_keeps_every_row_in_order():
+    brief, omitted = brief_milestone_summary(_history(8))
     assert omitted == 0
-    assert len(brief) == 11
+    assert [r["id"] for r in brief] == list(range(8))
 
 
-def _enter_stubs(rows: list[dict]):
+def _task(tid: int, milestone_id: int | None) -> MagicMock:
+    t = MagicMock()
+    t.id = tid
+    t.title = f"T{tid}"
+    t.status = "todo"
+    t.milestone_id = milestone_id
+    return t
+
+
+def _enter_stubs(project, milestones: list[dict], tasks: list, *, rules=None, systems=None,
+                 design=None):
+    applicable = rules or {"rules": [], "project_rules": [], "truncated": False,
+                           "subscribed_rulebooks": []}
     return [
         patch("scribe.mcp.tools.projects.projects_svc.get_project",
-              AsyncMock(return_value=fake_project(id=5))),
+              AsyncMock(return_value=project)),
         patch("scribe.mcp.tools.projects.rulebooks_svc.get_applicable_rules",
-              AsyncMock(return_value={"rules": [], "truncated": False,
-                                      "subscribed_rulebooks": []})),
+              AsyncMock(return_value=applicable)),
         patch("scribe.mcp.tools.projects.milestones_svc.get_project_milestone_summary",
-              AsyncMock(return_value=rows)),
+              AsyncMock(return_value=milestones)),
         patch("scribe.mcp.tools.projects.notes_svc.list_notes",
-              AsyncMock(side_effect=[([], 0), ([], 0)])),
+              AsyncMock(return_value=(tasks, len(tasks)))),
         patch("scribe.mcp.tools.projects.systems_svc.list_systems",
-              AsyncMock(return_value=[])),
+              AsyncMock(return_value=systems or [])),
         patch("scribe.mcp.tools.projects.systems_tools.bootstrap_systems_ask",
               AsyncMock(return_value=None)),
+        patch("scribe.mcp.tools.projects.design_systems_svc.design_context",
+              AsyncMock(return_value=design)),
         patch("scribe.mcp.tools.projects.coverage_svc.cached_coverage",
               AsyncMock(return_value=None)),
         patch("scribe.mcp.tools.projects.spawn"),
     ]
 
 
-@pytest.mark.asyncio
-async def test_enter_project_stays_small_however_long_the_history():
-    """The ceiling is the point: a long-lived project's handshake must not
-    grow with its history. 200 milestones with 5k-character plans would be
-    ~1M characters if bodies rode along."""
+async def _enter(*stubs):
     with contextlib.ExitStack() as stack:
-        for cm in _enter_stubs(_history(done=190, active=10)):
-            stack.enter_context(cm)
+        mocks = [stack.enter_context(cm) for cm in stubs]
         out = await enter_project(project_id=5)
+    return out, mocks
 
-    summary = out["milestone_summary"]
-    assert all("body" not in m for m in summary)
-    assert sum(m["status"] == "done" for m in summary) == 5
-    assert sum(m["status"] == "active" for m in summary) == 10
-    assert out["milestone_summary_omitted"].startswith("185 older done milestone(s)")
-    assert "list_milestones(5)" in out["milestone_summary_omitted"]
-    assert len(json.dumps(out["milestone_summary"], indent=2)) < 10_000
+
+@pytest.mark.asyncio
+async def test_enter_project_stays_small_however_large_the_project():
+    """The ceiling is the point: a long-lived project's handshake must not
+    grow with its history. 200 milestones with 5k-character plans, 60 project
+    rules and 40 Systems would be well over 1M characters in the old shape."""
+    project = fake_project(id=5, design_system_id=9, goal=GOAL,
+                           description="Background. " * 300)
+    rules = {
+        "rules": [{"id": i, "title": f"r{i}", "statement": PLAN} for i in range(50)],
+        "project_rules": [{"id": 100 + i, "title": f"pr{i}", "statement": PLAN,
+                           "when_to_apply": PLAN} for i in range(60)],
+        "truncated": True, "subscribed_rulebooks": [{"id": 1, "title": "Family"}],
+        "suppressed_rules": [], "suppressed_topics": [],
+    }
+    systems = []
+    for i in range(40):
+        s = MagicMock()
+        s.id, s.name, s.description = i, f"Area {i}", PLAN
+        systems.append(s)
+    design = {"id": 9, "title": "Kit", "description": "", "inherits_from": ["House"],
+              "guidance": [{"design_system_id": 9, "title": "Kit", "guidance": PLAN * 2}],
+              "token_count": 111, "token_groups": ["accent", "surface"]}
+    tasks = [_task(1000 + i, i % 200) for i in range(10)]
+
+    out, _ = await _enter(*_enter_stubs(project, _history(200), tasks, rules=rules,
+                                        systems=systems, design=design))
+
+    assert len(out["milestone_summary"]) == 5
+    assert out["milestone_summary_omitted"].startswith("195 other milestone(s)")
+    assert len(out["open_tasks"]) == 10
+    assert "applicable_rules" not in out and "recent_notes" not in out
+    assert "guidance" not in out["design_system"]
+    # The fixed parts are bounded by their caps; what's left to grow is the
+    # goal, the rule and System titles, and the ask keys when they apply.
+    size = len(json.dumps(out, indent=2))
+    assert size < 16_000, size
+
+
+@pytest.mark.asyncio
+async def test_open_tasks_name_their_milestone_even_when_it_is_not_listed():
+    """The milestone list is capped at 5; a task's milestone can fall outside
+    it, and its id must not arrive without a name."""
+    milestones = _history(20)
+    tasks = [_task(1, 0), _task(2, None)]   # milestone 0 is the least recent
+    out, mocks = await _enter(*_enter_stubs(fake_project(id=5), milestones, tasks))
+
+    assert 0 not in [m["id"] for m in out["milestone_summary"]]
+    assert out["open_tasks"] == [
+        {"id": 1, "title": "T1", "status": "todo", "milestone_id": 0, "milestone_title": "M0"},
+        {"id": 2, "title": "T2", "status": "todo", "milestone_id": None, "milestone_title": None},
+    ]
+    list_notes = mocks[3]
+    assert list_notes.await_args.kwargs["sort"] == "touched"
+    assert list_notes.await_args.kwargs["limit"] == 10
 
 
 @pytest.mark.asyncio
 async def test_omitted_key_is_absent_when_nothing_was_left_out():
     """Attached only when it applies (#2483)."""
-    with contextlib.ExitStack() as stack:
-        for cm in _enter_stubs(_history(done=3, active=2)):
-            stack.enter_context(cm)
-        out = await enter_project(project_id=5)
-    assert len(out["milestone_summary"]) == 5
+    out, _ = await _enter(*_enter_stubs(fake_project(id=5), _history(3), []))
+    assert len(out["milestone_summary"]) == 3
     assert "milestone_summary_omitted" not in out
 
 
 @pytest.mark.asyncio
-async def test_get_project_uses_the_same_brief_block():
+async def test_get_project_lists_every_milestone_without_plans():
     with patch("scribe.mcp.tools.projects.projects_svc.get_project",
                AsyncMock(return_value=fake_project(id=5))), \
          patch("scribe.mcp.tools.projects.milestones_svc.get_project_milestone_summary",
-               AsyncMock(return_value=_history(done=9, active=1))), \
+               AsyncMock(return_value=_history(10))), \
          patch("scribe.mcp.tools.projects.rulebooks_svc.get_applicable_rules",
                AsyncMock(return_value={"rules": [], "truncated": False,
                                        "subscribed_rulebooks": []})):
         out = await get_project(project_id=5)
-    assert len(out["milestone_summary"]) == 6
+    assert len(out["milestone_summary"]) == 10
     assert all("body" not in m for m in out["milestone_summary"])
-    assert out["milestone_summary_omitted"].startswith("4 older done milestone(s)")
 
 
 @pytest.mark.asyncio
 async def test_list_milestones_lists_every_milestone_without_plans():
-    """The call milestone_summary_omitted points to: every milestone, done
-    ones included, and no bodies (get_milestone has the plan)."""
+    """The call milestone_summary_omitted points to."""
     with patch("scribe.mcp.tools.milestones.milestones_svc.get_project_milestone_summary",
-               AsyncMock(return_value=_history(done=30, active=2))):
+               AsyncMock(return_value=_history(30))):
         out = await list_milestones(project_id=5)
-    assert len(out["milestones"]) == 32
+    assert len(out["milestones"]) == 30
     assert all("body" not in m for m in out["milestones"])

tests/test_rule_usage_wiring.py

@@ -341,6 +341,33 @@ def test_rules_payload_records_both_the_family_and_project_halves():
     assert kw["source"] == "enter_project"
 
 
+def test_brief_rules_payload_lists_titles_and_records_only_what_it_shows():
+    """The handshake's form (#4045): project rules by id and title, the
+    subscribed rulebooks, nothing else. A subscription-derived rule it doesn't
+    show must not count as surfaced."""
+    from scribe.services import rulebooks as svc
+
+    rec = MagicMock()
+    with patch.object(svc, "record_rule_surfaced", rec):
+        out = svc.rules_payload(
+            {
+                "rules": [{"id": 10, "title": "family", "statement": "s"}],
+                "project_rules": [{"id": 12, "title": "own", "statement": "s"}],
+                "truncated": False,
+                "subscribed_rulebooks": [{"id": 1, "title": "Family"}],
+            },
+            user_id=1,
+            source="enter_project",
+            brief=True,
+        )
+
+    assert out == {
+        "project_rules": [{"id": 12, "title": "own"}],
+        "subscribed_rulebooks": [{"id": 1, "title": "Family"}],
+    }
+    assert rec.call_args.kwargs["rule_ids"] == [12]
+
+
 def test_every_rules_payload_caller_names_itself():
     """`source` is the CALLER's name, so the readout can still separate the
     session handshake from a mid-session milestone read. A shared constant here

tests/test_services_plugin_context.py

@@ -176,6 +176,9 @@ async def test_build_session_context_pushes_the_projects_design_system():
     # returns those rather than the resolved tokens.
     assert "resolve_design_system(9)" in ctx
     assert "get_design_system_stylesheet(9)" in ctx
+    # The prose pointer names the call that has the MERGED guidance, not
+    # enter_project, which carries only the summary now (#4045).
+    assert "`get_design_system(9)` → `resolved_guidance`" in ctx
 
 
 @pytest.mark.asyncio

tests/test_services_project_summaries.py

@@ -14,6 +14,7 @@ So these tests assert the number of sessions opened, not only the values
 returned. A version that produced identical output while opening a session per
 project would pass a correctness test and reproduce the outage.
 """
+from datetime import datetime, timezone
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
@@ -99,17 +100,27 @@ async def test_milestone_summaries_for_many_projects_open_ONE_session():
     a session per MILESTONE, which is what turned 25 into ~250."""
     from scribe.services import milestones as svc
 
-    m1 = MagicMock(id=10, project_id=1)
+    written = datetime(2026, 9, 1, tzinfo=timezone.utc)
+    m1 = MagicMock(id=10, project_id=1, updated_at=written)
     m1.to_dict = MagicMock(return_value={"id": 10, "title": "A"})
-    m2 = MagicMock(id=11, project_id=2)
+    m2 = MagicMock(id=11, project_id=2, updated_at=written)
     m2.to_dict = MagicMock(return_value={"id": 11, "title": "B"})
 
+    step_closed = datetime(2026, 9, 14, tzinfo=timezone.utc)
     opened = [0]
-    rows = [[m1, m2], [(10, "done", 2), (10, "todo", 1), (11, "cancelled", 1)]]
+    rows = [[m1, m2], [
+        (10, "done", 2, step_closed),
+        (10, "todo", 1, datetime(2026, 9, 2, tzinfo=timezone.utc)),
+        (11, "cancelled", 1, datetime(2026, 8, 1, tzinfo=timezone.utc)),
+    ]]
     with patch.object(svc, "async_session", _session_factory(opened, rows)):
         out = await svc.get_project_milestone_summaries(1, [1, 2])
 
     assert opened[0] == 1
+    # Touched is the later of the milestone's own edit and its newest step
+    # update (#4045): steps closing today count, an old step doesn't pull it back.
+    assert out[1][0]["last_touched_at"] == step_closed.isoformat()
+    assert out[2][0]["last_touched_at"] == written.isoformat()
     assert out[1][0]["completed"] == 2 and out[1][0]["total"] == 3
     # Cancelled is excluded from the denominator, so a milestone whose only
     # task was cancelled reads as complete rather than stalled at 0%.