New projects from conversation (M2.5, PR B)

- propose_project(name, purpose, decisions) in a conversation goes up for
  a go-ahead (checked: a slug, not an existing project, no trailing
  question).
- On go, the provisioning checklist (D1): a repository with a README,
  protection on its default branch, the agent as a collaborator, a build
  VM, a deploy key, and the project entry as YAML with <...> to fill in.
- On "done", the agent reads its configuration again and adds the new
  project live (build_loop_agent(load=...); only additions), then checks
  what was provided (D4, verified, not assumed): permissions and
  protection as it sees them, then on a throwaway branch with an empty
  commit, a branch push must succeed and a push to the default branch and
  merging its own PR must be refused. The check's PR is closed and its
  branch deleted. Failures are said per item; nothing starts.
- Checked: the tracking issue (the distilled decisions, carrying the new
  item's ID), and the project's item, agreed and labelled `design`, whose
  first milestone is ARCHITECTURE.md and the build plan. A conversation
  waiting on provisioning doesn't close as idle.
- The walk replays exactly from its seed (item IDs too), and event IDs
  stay unique across simulated restarts, as a server's are.
- The test config holds output to 8192 tokens, under the test key's
  per-request cost cap.

Tests: new-project unit tests (checklist and its YAML parse as config, done
before the entry, what isn't set up, a checked project's record and first
PR, an existing name), protection enforced by a hook on the fake forge,
the walk proposing projects and saying done, and an e2e new project in a
repository the test operator provisions from the agent's checklist.

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_milestones.py

@@ -14,7 +14,7 @@ from nisse_dev.cancel import Cancel
 from nisse_dev.canonical import ToolCall
 from nisse_dev.execution import SSHHost
 from nisse_dev.git import GitRepo
-from nisse_dev.gitea import Comment, Issue, PullRequest, ReviewNote
+from nisse_dev.gitea import Comment, GiteaError, Issue, PullRequest, ReviewNote
 from nisse_dev.loop.agent import LoopAgent
 from nisse_dev.loop.driver import Driver
 from nisse_dev.loop.items import ANSWER, MERGE, WAITING, loop_of
@@ -124,6 +124,32 @@ class Forge:
     def close_pull_request(self, repo: str, index: int) -> None:
         self.prs[index]["state"] = "closed"
 
+    # what a new project's checks read (D4)
+    protected = False
+
+    def protect(self) -> None:
+        """Protection as the server enforces it: pushes to main refused by a
+        hook; merging needs an approval nobody here gives."""
+        hook = self.bare / "hooks" / "pre-receive"
+        hook.write_text(
+            "#!/bin/sh\nwhile read old new ref; do\n"
+            '  [ "$ref" = refs/heads/main ] && echo "main is protected" && exit 1\n'
+            "done\nexit 0\n"
+        )
+        hook.chmod(0o755)
+        self.protected = True
+
+    def repository(self, repo: str) -> dict[str, Any]:
+        return {"permissions": {"push": True}}
+
+    def branch(self, repo: str, name: str) -> dict[str, Any]:
+        return {"protected": self.protected, "user_can_push": not self.protected}
+
+    def merge_pull_request(self, repo: str, index: int) -> None:
+        if self.protected:
+            raise GiteaError("gitea POST merge returned 405: approvals needed")
+        self.merge(index)
+
     # what the operator does in Gitea
     def merge(self, n: int) -> None:
         head = f"refs/heads/{self.prs[n]['head']}"

nisse-dev/tests/test_loop_new_projects.py

@@ -0,0 +1,193 @@
+"""New projects on the new loop (M2.5, PR B): a conversation proposes one,
+the agent lists what it needs, and on "done" reads its configuration again
+and checks what was provided (D1, D4, D8) before opening the tracking issue
+and starting on the architecture. Real git on the throwaway build host,
+with protection enforced by a hook on the fake forge's bare repository."""
+
+import io
+import re
+from pathlib import Path
+from typing import Any
+
+import pytest
+import yaml
+from test_loop_milestones import DON, Forge, ScriptedModel, call, make_world
+from test_loop_projects import Router
+
+from nisse_dev.cancel import Cancel
+from nisse_dev.config import _parse_projects
+from nisse_dev.execution import SSHHost
+from nisse_dev.loop.agent import LoopAgent, Project
+from nisse_dev.loop.driver import Driver
+from nisse_dev.loop.items import CHAT, GO_AHEAD, MERGE, PROVISION, loop_of
+from nisse_dev.oplog import OpLog
+from nisse_dev.tools import Workspace
+from nisse_dev.transport import InMemoryTransport
+from nisse_dev.worker import InlineWorker
+
+PROPOSAL = call(
+    "propose_project",
+    name="tally",
+    purpose="A small command-line tally counter.",
+    decisions="Python 3.12 with pytest; no services, secrets or extra egress.",
+)
+
+
+@pytest.fixture
+def worlds(ssh_host: SSHHost, tmp_path: Path) -> dict[str, Any]:
+    sandbox = make_world(ssh_host, tmp_path / "sandbox")
+    tally = make_world(
+        ssh_host, tmp_path / "tally", store=sandbox["store"], repo_name="don/tally"
+    )
+    sandbox["forge"].issues.clear()  # only the conversation here
+    tally["forge"].issues.clear()
+    return {"sandbox": sandbox, "tally": tally}
+
+
+def agent_for(
+    worlds: dict[str, Any], model: ScriptedModel, *, entry_added: list[bool]
+) -> tuple[LoopAgent, InMemoryTransport]:
+    """An agent that knows only the sandbox; tally's entry appears in its
+    configuration once ``entry_added[0]`` is set."""
+    transport = InMemoryTransport()
+    cancel = Cancel()
+    router = Router({w["repo_name"]: w["forge"] for w in worlds.values()})
+    for w in worlds.values():
+        w["milestones"]._gitea = router
+
+    def runtime(name: str) -> Project:
+        w = worlds[name]
+        return Project(
+            name=name,
+            repo=w["repo_name"],
+            workspace=Workspace(w["host"], w["repo"].root, timeout_s=30),
+            milestones=w["milestones"],
+        )
+
+    def reload(known: set[str]) -> list[Project]:
+        names = ["sandbox", "tally"] if entry_added[0] else ["sandbox"]
+        return [runtime(n) for n in names if n not in known]
+
+    agent = LoopAgent(
+        worlds["sandbox"]["store"],
+        transport,
+        router,  # type: ignore[arg-type]
+        projects=[runtime("sandbox")],
+        account="nisse-dev",
+        operators={DON},
+        gitea_operators={"don"},
+        driver=Driver(model, "m", cancel=cancel),  # type: ignore[arg-type]
+        worker=InlineWorker(),
+        cancel=cancel,
+        oplog=OpLog("nisse-dev", io.StringIO()),
+        reload=reload,
+    )
+    transport.on_message(agent.on_message)
+    return agent, transport
+
+
+def conversation(worlds: dict[str, Any]) -> Any:
+    [chat] = [
+        i for i in worlds["sandbox"]["store"].work_items() if i.scope == "general"
+    ]
+    return chat
+
+
+def proposed(
+    worlds: Any, model: ScriptedModel, added: list[bool]
+) -> tuple[Any, Any, str]:
+    agent, transport = agent_for(worlds, model, entry_added=added)
+    root = transport.receive(DON, "I want a little tally counter, as its own project.")
+    assert transport.outbound[-1].text.startswith("rev-1: a new project, `tally`.")
+    assert loop_of(conversation(worlds)).wait == GO_AHEAD
+    transport.receive(DON, "go", thread=root)
+    return agent, transport, root
+
+
+def test_an_agreed_project_gets_a_checklist_with_its_entry(worlds: Any) -> None:
+    _, transport, _ = proposed(worlds, ScriptedModel([PROPOSAL]), [False])
+    loop = loop_of(conversation(worlds))
+    assert (loop.wait, loop.new_project) == (PROVISION, "tally")
+    checklist = transport.outbound[-1].text
+    for need in ("repository", "Protection", "collaborator", "build VM", "deploy key"):
+        assert need in checklist
+    # The entry is valid configuration once its placeholders are filled in.
+    entry = re.search(r"```yaml\n(.*?)\n```", checklist, re.DOTALL)
+    assert entry is not None
+    filled = (
+        entry.group(1)
+        .replace("<owner>/tally", "don/tally")
+        .replace("<the build VM>", "build.test")
+        .replace("<my SSH key for it>", "/k")
+        .replace("<the deploy key's private half>", "/p")
+    )
+    errors: list[str] = []
+    [project] = _parse_projects(yaml.safe_load(filled)["projects"], {}, errors)
+    assert errors == [] and project.name == "tally" and project.repo == "don/tally"
+
+
+def test_done_before_the_entry_is_added_says_so(worlds: Any) -> None:
+    _, transport, root = proposed(worlds, ScriptedModel([PROPOSAL]), [False])
+    transport.receive(DON, "done", thread=root)
+    assert "I don't see `tally` in my configuration yet" in transport.outbound[-1].text
+    assert loop_of(conversation(worlds)).new_project == "tally"
+
+
+def test_what_isnt_set_up_is_named_and_nothing_starts(worlds: Any) -> None:
+    added = [False]
+    _, transport, root = proposed(worlds, ScriptedModel([PROPOSAL]), added)
+    added[0] = True  # the entry is there, but tally's main isn't protected
+    transport.receive(DON, "done", thread=root)
+    said = transport.outbound[-1].text
+    assert said.startswith("Not ready yet:")
+    assert "main isn't protected" in said and "could merge my own PR" in said
+    assert loop_of(conversation(worlds)).new_project == "tally"
+    assert worlds["tally"]["forge"].issues == []
+    # The check's PR was closed and its branch deleted.
+    assert all(p["state"] == "closed" for p in worlds["tally"]["forge"].prs.values())
+
+
+def test_a_checked_project_gets_its_record_and_starts_on_its_design(
+    worlds: Any,
+) -> None:
+    added = [False]
+    model = ScriptedModel(
+        [PROPOSAL],
+        [  # tally's first item: the architecture and the build plan
+            call("start_milestone", name="architecture"),
+            call("write_file", path="ARCHITECTURE.md", content="# tally\n"),
+            call("write_file", path="docs/plans/tally.md", content="# plan\n"),
+            call("finish_milestone", summary="architecture and plan", final="no"),
+        ],
+    )
+    agent, transport, root = proposed(worlds, model, added)
+    forge: Forge = worlds["tally"]["forge"]
+    forge.protect()
+    added[0] = True
+    transport.receive(DON, "done", thread=root)
+
+    assert "tally" in agent._projects
+    [record] = forge.issues
+    marker = re.search(r"<!-- nisse-item: ([\w-]+) -->", record.body)
+    assert marker and "tally counter" in record.body
+    work = worlds["sandbox"]["store"].work_item(marker.group(1))
+    assert work.scope == "tally" and loop_of(work).started
+    assert "design" in loop_of(work).labels
+    assert loop_of(work).wait == MERGE
+    pr = max(n for n, p in forge.prs.items() if p["state"] == "open")
+    assert sorted(forge.files(pr)) == ["ARCHITECTURE.md", "docs/plans/tally.md"]
+    assert f"Part of #{record.number}" in forge.prs[pr]["body"]
+    chat = loop_of(conversation(worlds))
+    assert chat.became == (f"don/tally#{record.number}",)
+    assert (chat.wait, chat.new_project) == (CHAT, "")
+
+
+def test_a_project_name_that_exists_is_sent_back(worlds: Any) -> None:
+    model = ScriptedModel(
+        [call("propose_project", name="sandbox", purpose="again", decisions="x.")],
+        [call("reply", text="sandbox exists; shall I propose work on it?")],
+    )
+    agent, transport = agent_for(worlds, model, entry_added=[False])
+    transport.receive(DON, "a new sandbox?")
+    assert loop_of(conversation(worlds)).wait == CHAT
+    assert agent

nisse-dev/tests/test_loop_properties.py

@@ -11,6 +11,7 @@ the seed and the steps, so it replays exactly.
 import random
 import re
 import subprocess
+import uuid
 from pathlib import Path
 from typing import Any
 
@@ -32,6 +33,7 @@ from nisse_dev.loop.items import (
     CHAT,
     GO_AHEAD,
     MERGE,
+    PROVISION,
     RUNNING,
     WAITING,
     loop_of,
@@ -67,6 +69,15 @@ class PolicyModel:
         if roll < 0.12:
             return [ToolCall(call_id=f"p{self.n}", tool="nonsense", arguments={})]
         if "reply" in offered:  # a conversation: talk, or propose work
+            if self.rng.random() < 0.1:
+                return [
+                    call(
+                        "propose_project",
+                        name=f"proj{self.n}",
+                        purpose=f"a project {self.n}.",
+                        decisions="Python.",
+                    )
+                ]
             if self.rng.random() < 0.4:
                 return [
                     call(
@@ -125,6 +136,10 @@ class Walk:
 
     def _agent(self) -> tuple[LoopAgent, InMemoryTransport]:
         transport = InMemoryTransport()
+        # Event IDs are unique across restarts, as a server's are: a new
+        # transport goes on numbering where the old one stopped.
+        old = getattr(self, "transport", None)
+        transport._next_id = old._next_id if old is not None else 0
         cancel = Cancel()
         router = Router({w["repo_name"]: w["forge"] for w in self.worlds.values()})
         for w in self.worlds.values():
@@ -193,6 +208,8 @@ class Walk:
         if item and loop:
             weights.update({"go": 3, "answer": 2, "abandon": 1, "go-stale": 1})
             weights.update({"plain-yes": 2, "wait": 2})
+            if loop.new_project:
+                weights.update({"done": 2})
             if item.scope != "general":  # conversations aren't named by number
                 weights.update({"first": 1, "named-go": 1})
             if loop.pr:
@@ -203,6 +220,9 @@ class Walk:
         self.steps.append(f"{action}{self.name(item)}" if item else action)
         if action == "intake":
             self.agent.intake()
+        elif action == "done" and loop:
+            # The operator says a new project is ready; no entry was added.
+            self.transport.receive(DON, "done", thread=loop.thread)
         elif action == "chat":
             # A top-level message: a conversation of its own (L1, L5).
             self.transport.receive(DON, f"thinking aloud {len(self.steps)}")
@@ -295,6 +315,7 @@ class Walk:
             if item.status == "open" and item.position == WAITING:
                 explained = (
                     (loop.wait == CHAT and item.scope == "general")
+                    or (loop.wait == PROVISION and bool(loop.new_project))
                     or (loop.wait == GO_AHEAD and loop.rev > 0)
                     or (loop.wait == ANSWER and bool(loop.note))
                     or (loop.wait == MERGE and loop.pr > 0)
@@ -546,8 +567,18 @@ def _is_ancestor(bare: Path, commit: str, ref: str) -> bool:
     )
 
 
+def _seeded_ids(monkeypatch: pytest.MonkeyPatch, seed: int) -> None:
+    """Item IDs and branch names come from uuid4: seeded too, so a walk
+    replays exactly from its seed."""
+    ids = random.Random(seed)
+    monkeypatch.setattr(uuid, "uuid4", lambda: uuid.UUID(int=ids.getrandbits(128)))
+
+
 @pytest.mark.parametrize("seed", SEEDS)
-def test_the_loop_keeps_its_properties(world: dict[str, Any], seed: int) -> None:
+def test_the_loop_keeps_its_properties(
+    world: dict[str, Any], seed: int, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    _seeded_ids(monkeypatch, seed)
     walk = Walk({"sandbox": world}, seed)
     for _ in range(STEPS):
         walk.step()
@@ -556,9 +587,10 @@ def test_the_loop_keeps_its_properties(world: dict[str, Any], seed: int) -> None
 
 @pytest.mark.parametrize("seed", TWO_PROJECT_SEEDS)
 def test_two_projects_keep_the_properties(
-    ssh_host: SSHHost, tmp_path: Path, seed: int
+    ssh_host: SSHHost, tmp_path: Path, seed: int, monkeypatch: pytest.MonkeyPatch
 ) -> None:
     """D8: the same walk over two projects, whose issue numbers collide."""
+    _seeded_ids(monkeypatch, seed)
     sandbox = make_world(ssh_host, tmp_path / "sandbox")
     other = make_world(
         ssh_host, tmp_path / "other", store=sandbox["store"], repo_name="don/other"