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/src/nisse_dev/git.py

@@ -255,6 +255,13 @@ class GitRepo:
         self._git("commit", "-q", "-m", message)
         return self.head_sha()
 
+    def changed_paths(self, since: str) -> list[str]:
+        """Every path the work changes relative to ``since``, committed or
+        not, new files included; build artifacts aren't work (#80)."""
+        tracked = self._git("diff", "--name-only", since).splitlines()
+        new = self._git("ls-files", "--others", "--exclude-standard").splitlines()
+        return sorted({p for p in [*tracked, *new] if p})
+
     def left_out(self) -> list[str]:
         """Changes not in the last commit: build artifacts the harness left
         out, to be reported rather than silently dropped (D4)."""

nisse-dev/src/nisse_dev/loop/agent.py

@@ -150,9 +150,11 @@ LABELS = {
     "discuss": "This issue is labelled discuss: talk it through with the "
     "operator (ask_human) before restating, and restate only once you agree "
     "on what is wanted.",
-    "design": "This issue is labelled design: agree the design with the "
+    "design": "This issue is labelled design: the design comes before any "
-    "operator before any code. Your restatement puts the design to them; "
+    "code. Your first milestone is documents only: ARCHITECTURE.md and a "
-    "code waits for their go-ahead on it.",
+    "build plan under docs/plans/, in a PR of their own (if you restate, put "
+    "the design to the operator). Code starts in a later milestone, after that "
+    "PR has merged; the harness refuses a design milestone with anything else.",
 }
 
 
@@ -519,6 +521,9 @@ class LoopAgent:
             if pr.merged:
                 self._fact(item, f"PR #{loop.pr} merged")
                 loop, position = replace(loop, pr=0, pr_url="", branch=""), READY
+                if "design" in loop.labels and not loop.design_merged:
+                    self._fact(item, "the design has merged: code may follow")
+                    loop = replace(loop, design_merged=True)
             elif pr.state != "open":
                 self._fact(item, f"PR #{loop.pr} was closed without merging")
                 loop, position = replace(loop, pr=0, pr_url="", branch=""), READY
@@ -1047,7 +1052,8 @@ class LoopAgent:
                 project.repo,
                 title,
                 f"{brief}\n\nFrom a conversation with the operator, agreed there "
-                f"as rev-{loop.rev}. First: ARCHITECTURE.md and the build plan."
+                f"as rev-{loop.rev}. First: ARCHITECTURE.md and the build plan, "
+                "in a PR of documents only; code after it has merged."
                 f"\n\n<!-- nisse-item: {new_id} -->",
             )
             self._gitea.assign_issue(project.repo, number, self._account)
@@ -1211,6 +1217,32 @@ class LoopAgent:
                 )
         self._last_project = here
 
+    def _design_problem(self, item_id: str) -> str | None:
+        """D1, D2: a `design` item agrees its design before any code. Until
+        a PR of it has merged, a milestone holds documents only."""
+        item = self._store.work_item(item_id)
+        if item is None:
+            return None
+        loop = loop_of(item)
+        milestones = self._at(item).milestones
+        if "design" not in loop.labels or loop.design_merged or milestones is None:
+            return None
+        try:
+            changed = milestones.changed()
+        except GitError:
+            return None  # publishing reports what's wrong with the workspace
+        code = [
+            p for p in changed if p != "ARCHITECTURE.md" and not p.startswith("docs/")
+        ]
+        if not code:
+            return None
+        return (
+            "not published: this milestone is the design, so it holds documents "
+            "only (ARCHITECTURE.md, docs/); code starts in a later milestone, "
+            "after this one's PR has merged. Take these out of it (they can "
+            "wait in the plan): " + ", ".join(code)
+        )
+
     def _converse_run(self, item: WorkItem) -> None:
         """A conversation's turn (L1, L5): it talks, and may propose work on
         a project. No workspace, nothing to run."""
@@ -1329,7 +1361,10 @@ class LoopAgent:
                 tools=tools,
                 workspace=workspace,
                 handlers={"start_milestone": lambda args: self._start(item.id, args)},
-                checks={"restate": _restatement_problem},
+                checks={
+                    "restate": _restatement_problem,
+                    "finish_milestone": lambda args: self._design_problem(item.id),
+                },
             )
         finally:
             self._running = False

nisse-dev/src/nisse_dev/loop/items.py

@@ -55,6 +55,7 @@ class Loop:
     proposal_title: str = ""
     proposal_kind: str = ""  # "work" on a project, or a new "project"
     new_project: str = ""  # a new project being provisioned (D1)
+    design_merged: bool = False  # a `design` item's design PR has merged (D1, D2)
     # Where the operator last spoke (D5: answer where asked): "" for the
     # Matrix thread, or the PR it came from, with the inline location and a
     # little of what they said, for quoting.

nisse-dev/src/nisse_dev/loop/milestones.py

@@ -161,6 +161,10 @@ class Milestones:
         if git.remote_sha(self._remote, parked, credential=self._credential):
             git.delete_remote_branch(self._remote, parked, credential=self._credential)
 
+    def changed(self) -> list[str]:
+        """What the current milestone changes, from the default branch."""
+        return self._git.changed_paths(f"origin/{self._base}")
+
     # -- a new project's checks (D1, D4) -----------------------------------------
 
     def verify_access(self, account: str) -> list[str]:

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}",