fix(mcp): project reads list milestones without their plans, and cap done ones (#4045)

enter_project returned every milestone's full plan body. On a project with 39
milestones the handshake came to ~222k characters, 168k of them bodies (110k
from done milestones). That is past what an MCP client accepts as a tool
result, so the call meant to orient a session arrived as a file to page
through. It grows with a project's history, so any long-lived project on any
install gets there.

- brief_milestone_summary (services/milestones.py) trims summary rows to the
  listing fields: id, title, description, status, order_index and progress.
  The plan is get_milestone's job. user_id, project_id and timestamps repeat
  what the caller knows.
- enter_project and get_project share one block: every open milestone plus
  the 5 most recently updated done ones, in order. milestone_summary_omitted
  is attached only when older done ones were left out, and names
  list_milestones and get_milestone.
- list_milestones lists every milestone, done included, without bodies. It is
  the call the omitted line points to, and it had the same size problem.
- The REST project summary is unchanged; the web UI reads it.

Tests: trimming, the done cap and its order, the omitted key present and
absent, get_project and list_milestones, and a size ceiling on enter_project's
milestone block for a 200-milestone history.

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

src/scribe/services/milestones.py

@@ -238,3 +238,38 @@ async def get_project_milestone_summary(user_id: int, project_id: int) -> list[d
     """Ordered milestones with progress — the one-project view of
     get_project_milestone_summaries (two queries, not N+1)."""
     return (await get_project_milestone_summaries(user_id, [project_id])).get(project_id, [])
+
+
+# What a milestone LISTING needs: enough to say what each plan is and how far
+# along it is. The plan itself (`body`) is get_milestone's job. Summaries once
+# carried it, and on a project with 39 milestones enter_project came to ~222k
+# characters, 168k of them plan bodies. That is past what an MCP client will
+# accept as a tool result, so the session handshake arrived as a file to page
+# through (#4045). user_id / project_id / timestamps repeat what the caller
+# already knows.
+_BRIEF_FIELDS = (
+    "id", "title", "description", "status", "order_index",
+    "total", "completed", "pct", "status_counts",
+)
+
+
+def brief_milestone_summary(
+    rows: list[dict], *, done_kept: int | None = None,
+) -> tuple[list[dict], int]:
+    """Trim summary rows to the listing fields, optionally capping done ones.
+
+    `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.
+    """
+    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]
+    brief = [{k: r[k] for k in _BRIEF_FIELDS if k in r} for r in kept]
+    return brief, len(rows) - len(kept)