A design milestone holds documents only, enforced

Found by the first local e2e run: qwen3.8-27b put a new project's code in
the same PR as its ARCHITECTURE.md, with no build plan. D1 says a `design`
item agrees its design before any code, and that rested on wording only.

- Until a PR of a `design` item has merged, finish_milestone is sent back
  if the milestone changes anything but ARCHITECTURE.md and docs/, naming
  the paths to take out. The merge is recorded (design_merged) and code
  may follow.
- The label's instruction and the new project's brief say so plainly:
  documents first, in a PR of their own; code after it has merged.

Tests: a design milestone with code is sent back and only the documents
are published, then code after the merge; the walk's model follows the
rule.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

nisse-dev/tests/test_loop_multi.py

@@ -19,6 +19,7 @@ from test_loop_milestones import (
 from test_loop_milestones import world as world  # noqa: PLC0414 -- the fixture
 
 from nisse_dev.canonical import ToolCall, ToolResult
+from nisse_dev.gitea import Issue
 from nisse_dev.loop.items import MERGE, WAITING, loop_of
 
 
@@ -174,3 +175,44 @@ def test_an_unsaid_final_closes_the_issue(world: dict[str, Any]) -> None:
     say(transport, world, "go")
     [pr] = forge.prs
     assert "Closes #14" in forge.prs[pr]["body"]
+
+
+def test_a_design_milestone_holds_documents_only(world: dict[str, Any]) -> None:
+    """D1, D2: a `design` item agrees its design before any code; the
+    harness refuses a design milestone with code in it."""
+    forge: Forge = world["forge"]
+    forge.issues[0] = Issue(14, "Add count_words", "count words", "don", ("design",))
+    model = ScriptedModel(
+        RESTATE,
+        [
+            call("start_milestone", name="design"),
+            call("write_file", path="ARCHITECTURE.md", content="# arch\n"),
+            call("write_file", path="docs/plans/words.md", content="# plan\n"),
+            call("write_file", path="words.py", content="W = 1\n"),  # too soon
+            call("finish_milestone", summary="design", final="no"),
+        ],
+        [
+            call("run_command", command="rm words.py"),
+            call("finish_milestone", summary="design", final="no"),
+        ],
+        milestone("words.py", final="yes"),  # after the design merged
+    )
+    agent, transport = loop_agent(world, model)
+    agent.intake()
+    say(transport, world, "go")
+    [design] = forge.prs
+    assert sorted(forge.files(design)) == ["ARCHITECTURE.md", "docs/plans/words.md"]
+    refused = [
+        e.event.result
+        for e in world["store"].transcript(item(world).id, "driver").read()
+        if isinstance(e.event, ToolResult)
+        and "this milestone is the design" in e.event.result
+    ]
+    assert refused and "words.py" in refused[0]
+
+    forge.merge(design)
+    agent.watch()
+    agent._schedule()
+    code = max(forge.prs)
+    assert code != design and forge.files(code) == ["words.py"]
+    assert loop_of(item(world)).design_merged

nisse-dev/tests/test_loop_properties.py

@@ -63,6 +63,11 @@ class PolicyModel:
         self.n += 1
         offered = {t["function"]["name"] for t in tools}
         facts = [getattr(e.event, "text", "") for e in events]
+        # A `design` item writes documents until its design has merged.
+        design = "labelled design" in (system or "") and not any(
+            "the design has merged" in t for t in facts
+        )
+        path = f"docs/d{self.n}.md" if design else f"f{self.n}.py"
         roll = self.rng.random()
         if roll < 0.08:
             return [call("ask_human", question=f"question {self.n}?")]
@@ -98,7 +103,7 @@ class PolicyModel:
             # Half done, then a question: work a switch must park.
             return [
                 call("start_milestone", name=f"m{self.n}"),
-                call("write_file", path=f"f{self.n}.py", content=f"x = {self.n}\n"),
+                call("write_file", path=path, content=f"x = {self.n}\n"),
                 call("ask_human", question=f"halfway {self.n}?"),
             ]
         merged = any("merged" in t for t in facts[-6:])
@@ -106,7 +111,7 @@ class PolicyModel:
             return [call("close_item", summary=f"done {self.n}")]
         return [
             call("start_milestone", name=f"m{self.n}"),
-            call("write_file", path=f"f{self.n}.py", content=f"x = {self.n}\n"),
+            call("write_file", path=path, content=f"x = {self.n}\n"),
             call(
                 "finish_milestone",
                 summary=f"work {self.n}",