Merge pull request 'Add executor tool loop (A12/A15) — step 5b' (#12) from executor-loop into main

nisse-dev/src/nisse_dev/control.py

@@ -59,6 +59,14 @@ class AskHuman:
     question: str
 
 
+class MilestoneExecutor(Protocol):
+    """What the orchestrator needs from an executor loop; the concrete one
+    lives in nisse_dev.executor (imported there, not here, to keep the
+    dependency pointing one way)."""
+
+    def run(self, milestone: int) -> Any: ...
+
+
 class PlanningAgent(Protocol):
     def plan(
         self,
@@ -91,7 +99,9 @@ def _fresh_data() -> dict[str, Any]:
     return {
         "revs": {},
         "gate": None,
-        "question": None,
+        # What an operator reply in AWAIT_INPUT should resume. Every path into
+        # AWAIT_INPUT must set this, or the reply has nowhere to go.
+        "pending": None,
         "milestone": 1,
         "task_id": None,
         "roles": None,  # A11 mapping, pinned at task start
@@ -106,11 +116,13 @@ class Orchestrator:
         agent: PlanningAgent,
         operators: Iterable[str],
         roles: RoleMap | None = None,
+        executor: "MilestoneExecutor | None" = None,
     ) -> None:
         self._store = store
         self._transport = transport
         self._agent = agent
         self._roles = roles
+        self._executor = executor
         self._operators = set(operators)
         self._data = _fresh_data()
         self._project: str | None = None
@@ -128,11 +140,14 @@ class Orchestrator:
         self._store.oplog.task_id = self._data.get("task_id")
         gate = self._data.get("gate")
         if report.action == "await_input":
-            self._transition(AWAIT_INPUT, cause="boot: unresolved intents")
+            self._await_input(
-            self._transport.ask_question(
+                cause="boot: unresolved intents",
+                prompt=(
                     "restart found unresolved work: "
                     + "; ".join(report.notes)
                     + " — how should I proceed?"
+                ),
+                pending={"kind": "boot"},
             )
         elif state.state == IDLE or (
             state.state in (AWAIT_ARCH_SIGNOFF, AWAIT_MILESTONE_SIGNOFF) and gate
@@ -147,9 +162,10 @@ class Orchestrator:
         else:
             # Interrupted mid-turn (planning, executing, unanswered question):
             # never blind-resume (A3.6).
-            self._transition(AWAIT_INPUT, cause=f"boot: restarted in {state.state}")
+            self._await_input(
-            self._transport.ask_question(
+                cause=f"boot: restarted in {state.state}",
-                f"restarted mid-{state.state}; continue or re-plan?"
+                prompt=f"restarted mid-{state.state}; continue or re-plan?",
+                pending={"kind": "boot"},
             )
 
     def _handle(self, msg: InboundMessage) -> None:
@@ -207,17 +223,18 @@ class Orchestrator:
                 gate_name, self._project, feedback=feedback, answer=answer
             )
         except PlanningError as exc:
-            self._transition(AWAIT_INPUT, cause=f"planning failed: {exc}")
+            self._await_input(
-            self._transport.ask_question(
+                cause=f"planning failed: {exc}",
-                f"planning for {gate_name} failed ({exc}); retry or re-plan?"
+                prompt=f"planning for {gate_name} failed ({exc}); how should I proceed?",
+                pending={"kind": "planning_failed", "gate": gate_name},
             )
             return
         if isinstance(action, AskHuman):
-            self._data["question"] = {"text": action.question, "gate": gate_name}
+            self._await_input(
-            self._transition(
+                cause=f"agent question during {gate_name} planning",
-                AWAIT_INPUT, cause=f"agent question during {gate_name} planning"
+                prompt=action.question,
+                pending={"kind": "question", "gate": gate_name},
             )
-            self._transport.ask_question(action.question)
             return
         rev = self._data["revs"].get(gate_name, 0) + 1
         self._data["revs"][gate_name] = rev
@@ -259,7 +276,7 @@ class Orchestrator:
                 self._transition(
                     EXECUTING, cause=f"operator command: start milestone {milestone}"
                 )
-                self._transport.send_message(f"[stub] executing milestone {milestone}")
+                self._execute_milestone(milestone)
             else:
                 self._transport.send_message(
                     f"plan approved; say 'start milestone {milestone}' to begin"
@@ -313,18 +330,59 @@ class Orchestrator:
                 f"milestone plan approved; say 'start milestone {milestone}' to begin"
             )
 
+    def _execute_milestone(self, milestone: int) -> None:
+        if self._executor is None:
+            self._transport.send_message(f"[stub] executing milestone {milestone}")
+            return
+        self._transport.send_message(f"executing milestone {milestone}")
+        outcome = self._executor.run(milestone)
+        if outcome.status == "completed":
+            # PR_OPEN and the review loop arrive with the Gitea layer (B2);
+            # until then a finished milestone simply reports and waits.
+            self._transport.send_message(f"milestone {milestone} done: {outcome.note}")
+            return
+        self._await_input(
+            cause=f"milestone {milestone} {outcome.status}",
+            prompt=f"milestone {milestone} stopped ({outcome.status}): {outcome.note}",
+            pending={"kind": "milestone_stopped", "milestone": milestone},
+        )
+
+    def _await_input(self, *, cause: str, prompt: str, pending: dict[str, Any]) -> None:
+        self._data["pending"] = pending
+        self._transition(AWAIT_INPUT, cause=cause)
+        self._transport.ask_question(prompt)
+
     def _handle_answer(self, text: str) -> None:
-        question = self._data.get("question")
+        pending = self._data.get("pending")
-        if question is None:
+        if pending is None:
+            # Reached only if state was forced externally; say what works
+            # rather than dead-ending the operator.
             self._transport.send_message(
-                "awaiting operator resolution; no pending question to answer"
+                "waiting for direction, but I have no pending item to resume; "
+                "try 'status', or 'use <project>' to start over"
             )
             return
-        self._data["question"] = None
+        self._data["pending"] = None
-        gate_name = question["gate"]
+        match pending.get("kind"):
+            case "question" | "planning_failed":
+                gate_name = pending["gate"]
                 back = PLANNING_ARCH if gate_name == "arch" else MILESTONE_PLANNING
-        self._transition(back, cause="operator answered question")
+                self._transition(back, cause="operator answered; resuming planning")
                 self._run_planning_turn(gate_name, answer=text)
+            case "milestone_stopped":
+                milestone = pending["milestone"]
+                self._transition(
+                    AWAIT_MILESTONE_SIGNOFF,
+                    cause="operator answered; plan still approved",
+                )
+                self._transport.send_message(
+                    f"noted. the milestone {milestone} plan is still approved — "
+                    f"say 'start milestone {milestone}' to run it again"
+                )
+            case _:
+                self._transport.send_message(
+                    "noted. say 'status' for where things stand"
+                )
 
     def _transition(self, new_state: str, *, cause: str) -> None:
         state = self._store.get_state()

nisse-dev/src/nisse_dev/executor.py

@@ -0,0 +1,107 @@
+"""Local executor loop (spec A12 escalation triggers, A15 accommodations).
+
+Runs the approved plan with the executor role — the cheap local model doing
+mechanical work. Every tool call and result is checkpointed to the canonical
+log as it happens (A13), so a crash mid-milestone leaves a resumable record.
+
+Escalation is decided from outside the model (A12): consecutive command
+failures and hard caps on turns, never the model's own claim that it is stuck
+or finished-enough. Until delegation exists (step 7), an escalation gates to
+the human with the failures attached rather than engaging a frontier model.
+"""
+
+from dataclasses import dataclass
+from typing import Literal
+
+from nisse_dev.canonical import ToolCall, ToolResult
+from nisse_dev.llm import LLMClient, LLMError, RoleMap
+from nisse_dev.state import StateStore
+from nisse_dev.tools import EXECUTOR_TOOLS, Workspace
+
+EXECUTOR_SYSTEM = """You are nisse-dev's executor, doing mechanical work.
+
+Follow the approved plan above exactly. It was written to be executed
+verbatim; do not redesign it, expand its scope, or skip steps.
+
+Work by calling tools. Verify your work by running the project's tests.
+When every step of the plan is done and the tests pass, reply with a short
+plain-text summary and no tool call — that ends the milestone."""
+
+DEFAULT_MAX_TURNS = 24
+DEFAULT_FAILURE_LIMIT = 2
+
+
+@dataclass(frozen=True)
+class ExecutorOutcome:
+    status: Literal["completed", "capped", "escalate"]
+    note: str
+
+
+class LLMExecutor:
+    def __init__(
+        self,
+        client: LLMClient,
+        store: StateStore,
+        roles: RoleMap,
+        workspace: Workspace,
+        *,
+        max_turns: int = DEFAULT_MAX_TURNS,
+        failure_limit: int = DEFAULT_FAILURE_LIMIT,
+    ) -> None:
+        self._client = client
+        self._store = store
+        self._roles = roles
+        self._workspace = workspace
+        self._max_turns = max_turns
+        self._failure_limit = failure_limit
+
+    def run(self, milestone: int) -> ExecutorOutcome:
+        model = self._roles.resolve("executor")
+        system = f"{EXECUTOR_SYSTEM}\n\nYou are executing milestone {milestone}."
+        consecutive_failures = 0
+
+        for _turn in range(self._max_turns):
+            try:
+                produced = self._client.complete(
+                    self._store.read_events(),
+                    tools=EXECUTOR_TOOLS,
+                    model=model,
+                    system=system,
+                )
+            except LLMError as exc:
+                return ExecutorOutcome("escalate", f"executor call failed: {exc}")
+
+            calls: list[ToolCall] = []
+            for event in produced:
+                self._store.append_event(event)
+                if isinstance(event, ToolCall):
+                    calls.append(event)
+
+            if not calls:
+                return ExecutorOutcome("completed", "executor reported the plan done")
+
+            for call in calls:
+                outcome = self._workspace.dispatch(call.tool, call.arguments)
+                self._store.append_event(
+                    ToolResult(
+                        call_id=call.call_id,
+                        result=outcome.result,
+                        success=outcome.success,
+                    )
+                )
+                # Only commands count toward escalation: a failed read is the
+                # model looking around, a failed command is work not working.
+                if call.tool == "run_command":
+                    consecutive_failures = (
+                        0 if outcome.success else consecutive_failures + 1
+                    )
+                    if consecutive_failures >= self._failure_limit:
+                        return ExecutorOutcome(
+                            "escalate",
+                            f"{consecutive_failures} consecutive command failures; "
+                            f"last: {outcome.result[:500]}",
+                        )
+
+        return ExecutorOutcome(
+            "capped", f"hit the {self._max_turns}-turn cap for milestone {milestone}"
+        )

nisse-dev/src/nisse_dev/planner.py

@@ -11,7 +11,7 @@ crash mid-planning leaves a truthful transcript.
 
 from typing import Any
 
-from nisse_dev.canonical import AssistantText, ToolCall
+from nisse_dev.canonical import AssistantText, ToolCall, ToolResult
 from nisse_dev.control import AskHuman, PlanningError, SubmitPlan
 from nisse_dev.llm import LLMClient, LLMError, RoleMap
 from nisse_dev.state import StateStore
@@ -142,6 +142,21 @@ class LLMPlanningAgent:
                 continue
             if isinstance(event, ToolCall):
                 action = self._interpret(event)
+                if action is not None:
+                    # The gate is this call's outcome. Recording it keeps the
+                    # transcript renderable: providers reject a tool call with
+                    # no result, and the next planning turn replays this log.
+                    self._store.append_event(
+                        ToolResult(
+                            call_id=event.call_id,
+                            result=(
+                                "plan posted for approval; turn ended"
+                                if isinstance(action, SubmitPlan)
+                                else "question posted; awaiting the operator"
+                            ),
+                            success=True,
+                        )
+                    )
         return action
 
     def _interpret(self, call: ToolCall) -> SubmitPlan | AskHuman | None:

nisse-dev/src/nisse_dev/render.py

@@ -57,8 +57,24 @@ class OpenAIChatRenderer:
         messages: list[dict[str, Any]] = []
         if system is not None:
             messages.append({"role": "system", "content": system})
-        for stored in effective_events(events):
+        kept = effective_events(events)
+        answered = {e.event.call_id for e in kept if isinstance(e.event, ToolResult)}
+        for stored in kept:
             messages.append(self._message_for(stored.event))
+            # Providers reject a tool call with no result following it. One
+            # can legitimately be missing: a crash between the call and its
+            # result (A3), or a turn-ending gate tool. Render a placeholder so
+            # the transcript stays replayable rather than poisoned.
+            if isinstance(stored.event, ToolCall) and (
+                stored.event.call_id not in answered
+            ):
+                messages.append(
+                    {
+                        "role": "tool",
+                        "tool_call_id": stored.event.call_id,
+                        "content": "[no result recorded]",
+                    }
+                )
         body: dict[str, Any] = {"model": model, "messages": messages}
         if tools:
             body["tools"] = tools

nisse-dev/src/nisse_dev/tools.py

@@ -0,0 +1,204 @@
+"""Executor tools (spec A15: reduced schema, flat arguments).
+
+Deliberately unsandboxed. The VM is the trust boundary (B3) and tool use is
+auto-approved inside an approved unit of work (A4), so per-command
+confinement would add failure modes without adding safety. The workspace is
+where work happens — the default for relative paths and the command cwd — not
+a wall. Protecting agent state from the agent is a mount-layout concern
+(A2/B3), not this module's job.
+
+What *is* enforced here is operational: commands cannot hang the loop, cannot
+consume the context window with megabytes of build log, and do not inherit
+the agent's own credentials.
+"""
+
+import os
+import shutil
+import signal
+import subprocess
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any
+
+DEFAULT_TIMEOUT_S = 120
+MAX_OUTPUT_CHARS = 4000
+
+EXECUTOR_TOOLS: list[dict[str, Any]] = [
+    {
+        "type": "function",
+        "function": {
+            "name": "read_file",
+            "description": "Read a UTF-8 text file.",
+            "parameters": {
+                "type": "object",
+                "properties": {"path": {"type": "string"}},
+                "required": ["path"],
+            },
+        },
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "write_file",
+            "description": "Write a UTF-8 text file, creating parent directories.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "path": {"type": "string"},
+                    "content": {"type": "string"},
+                },
+                "required": ["path", "content"],
+            },
+        },
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "list_dir",
+            "description": "List the entries of a directory.",
+            "parameters": {
+                "type": "object",
+                "properties": {"path": {"type": "string"}},
+                "required": ["path"],
+            },
+        },
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "run_command",
+            "description": (
+                "Run a shell command in the workspace. Returns its exit code "
+                "and output; a non-zero exit is a result, not an error."
+            ),
+            "parameters": {
+                "type": "object",
+                "properties": {"command": {"type": "string"}},
+                "required": ["command"],
+            },
+        },
+    },
+]
+
+
+def _truncate(text: str) -> str:
+    if len(text) <= MAX_OUTPUT_CHARS:
+        return text
+    dropped = len(text) - MAX_OUTPUT_CHARS
+    return f"{text[:MAX_OUTPUT_CHARS]}\n[... {dropped} characters truncated]"
+
+
+def _child_env() -> dict[str, str]:
+    """The project's build and test code is arbitrary; it has no business
+    reading the agent's LiteLLM, Matrix, or Gitea credentials."""
+    return {k: v for k, v in os.environ.items() if not k.startswith("NISSE_")}
+
+
+@dataclass(frozen=True)
+class ToolOutcome:
+    result: str
+    success: bool
+
+
+class Workspace:
+    def __init__(self, root: Path, *, timeout_s: int = DEFAULT_TIMEOUT_S) -> None:
+        self.root = Path(root)
+        self.root.mkdir(parents=True, exist_ok=True)
+        self._timeout_s = timeout_s
+
+    def _resolve(self, path: str) -> Path:
+        candidate = Path(path)
+        return candidate if candidate.is_absolute() else self.root / candidate
+
+    def dispatch(self, tool: str, arguments: dict[str, Any]) -> ToolOutcome:
+        try:
+            match tool:
+                case "read_file":
+                    return self.read_file(str(arguments["path"]))
+                case "write_file":
+                    return self.write_file(
+                        str(arguments["path"]), str(arguments["content"])
+                    )
+                case "list_dir":
+                    return self.list_dir(str(arguments.get("path", ".")))
+                case "run_command":
+                    return self.run_command(str(arguments["command"]))
+                case _:
+                    return ToolOutcome(f"no such tool: {tool}", success=False)
+        except KeyError as exc:
+            return ToolOutcome(f"missing argument {exc} for {tool}", success=False)
+
+    def read_file(self, path: str) -> ToolOutcome:
+        target = self._resolve(path)
+        try:
+            return ToolOutcome(_truncate(target.read_text()), success=True)
+        except (OSError, UnicodeDecodeError) as exc:
+            return ToolOutcome(f"could not read {path}: {exc}", success=False)
+
+    def write_file(self, path: str, content: str) -> ToolOutcome:
+        target = self._resolve(path)
+        try:
+            target.parent.mkdir(parents=True, exist_ok=True)
+            target.write_text(content)
+        except OSError as exc:
+            return ToolOutcome(f"could not write {path}: {exc}", success=False)
+        return ToolOutcome(f"wrote {len(content)} characters to {path}", success=True)
+
+    def list_dir(self, path: str) -> ToolOutcome:
+        target = self._resolve(path)
+        try:
+            entries = sorted(
+                f"{p.name}/" if p.is_dir() else p.name for p in target.iterdir()
+            )
+        except OSError as exc:
+            return ToolOutcome(f"could not list {path}: {exc}", success=False)
+        return ToolOutcome(_truncate("\n".join(entries) or "(empty)"), success=True)
+
+    def run_command(self, command: str) -> ToolOutcome:
+        try:
+            # Popen rather than run(): on timeout, run() kills only the direct
+            # child, and TimeoutExpired carries no pid, so a backgrounded
+            # grandchild (a dev server, say) would survive. Holding the pid
+            # lets us kill the whole session.
+            process = subprocess.Popen(
+                command,
+                shell=True,
+                cwd=self.root,
+                env=_child_env(),
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+                stdin=subprocess.DEVNULL,
+                text=True,
+                start_new_session=True,
+            )
+        except OSError as exc:
+            return ToolOutcome(f"could not run command: {exc}", success=False)
+        try:
+            stdout, stderr = process.communicate(timeout=self._timeout_s)
+        except subprocess.TimeoutExpired:
+            self._kill_group(process)
+            return ToolOutcome(
+                f"command timed out after {self._timeout_s}s: {command}",
+                success=False,
+            )
+        body = _truncate(
+            f"exit code: {process.returncode}\nstdout:\n{stdout}\nstderr:\n{stderr}"
+        )
+        return ToolOutcome(body, success=process.returncode == 0)
+
+    @staticmethod
+    def _kill_group(process: "subprocess.Popen[str]") -> None:
+        try:
+            os.killpg(os.getpgid(process.pid), signal.SIGKILL)
+        except (ProcessLookupError, PermissionError):
+            process.kill()
+        # Drain the pipes of the now-dead group so no zombie is left behind.
+        try:
+            process.communicate(timeout=5)
+        except subprocess.TimeoutExpired:
+            pass
+
+    def reset(self) -> None:
+        """Discard workspace contents; used by tests, not by the agent."""
+        shutil.rmtree(self.root, ignore_errors=True)
+        self.root.mkdir(parents=True, exist_ok=True)

nisse-dev/tests/test_executor.py

@@ -0,0 +1,173 @@
+import io
+from pathlib import Path
+from typing import Any
+
+import pytest
+
+from nisse_dev.canonical import AssistantText, CanonicalEvent, StoredEvent, ToolCall
+from nisse_dev.executor import LLMExecutor
+from nisse_dev.llm import LLMError, RoleMap
+from nisse_dev.oplog import OpLog
+from nisse_dev.state import StateStore
+from nisse_dev.tools import Workspace
+
+ROLES = RoleMap(
+    executor="llama3.2",
+    planner="claude-haiku-4-5",
+    delegate="claude-haiku-4-5",
+    consultant="claude-haiku-4-5",
+)
+
+
+class ScriptedClient:
+    def __init__(self, turns: list[list[CanonicalEvent]]) -> None:
+        self._turns = turns
+        self.calls: list[dict[str, Any]] = []
+
+    def complete(
+        self,
+        events: list[StoredEvent],
+        tools: list[dict[str, Any]] | None,
+        model: str,
+        system: str | None = None,
+    ) -> list[CanonicalEvent]:
+        self.calls.append({"tools": tools, "model": model, "system": system})
+        if not self._turns:
+            return [AssistantText(text="done", model=model)]
+        return self._turns.pop(0)
+
+
+class FailingClient:
+    def complete(self, *args: Any, **kwargs: Any) -> list[CanonicalEvent]:
+        raise LLMError("proxy exploded")
+
+
+def call(tool: str, call_id: str = "c1", **arguments: Any) -> ToolCall:
+    return ToolCall(call_id=call_id, tool=tool, arguments=arguments)
+
+
+@pytest.fixture
+def store(tmp_path: Path) -> StateStore:
+    return StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
+
+
+@pytest.fixture
+def ws(tmp_path: Path) -> Workspace:
+    return Workspace(tmp_path / "work", timeout_s=10)
+
+
+def build(client: Any, store: StateStore, ws: Workspace, **kw: Any) -> LLMExecutor:
+    return LLMExecutor(client, store, ROLES, ws, **kw)
+
+
+def test_tool_calls_are_executed_and_results_logged(
+    store: StateStore, ws: Workspace
+) -> None:
+    client = ScriptedClient(
+        [
+            [call("write_file", path="app.py", content="print(1)\n")],
+            [AssistantText(text="wrote the file", model="llama3.2")],
+        ]
+    )
+    outcome = build(client, store, ws).run(milestone=1)
+
+    assert outcome.status == "completed"
+    assert (ws.root / "app.py").read_text() == "print(1)\n"
+    kinds = [type(e.event).__name__ for e in store.read_events()]
+    assert kinds == ["ToolCall", "ToolResult", "AssistantText"]
+
+
+def test_uses_executor_role_and_reduced_manifest(
+    store: StateStore, ws: Workspace
+) -> None:
+    client = ScriptedClient([])
+    build(client, store, ws).run(milestone=2)
+    assert client.calls[0]["model"] == "llama3.2"  # never the planner
+    names = [t["function"]["name"] for t in client.calls[0]["tools"]]
+    assert names == ["read_file", "write_file", "list_dir", "run_command"]
+    assert "milestone 2" in client.calls[0]["system"]
+
+
+def test_no_tool_call_ends_the_milestone(store: StateStore, ws: Workspace) -> None:
+    client = ScriptedClient([[AssistantText(text="all steps done", model="m")]])
+    assert build(client, store, ws).run(milestone=1).status == "completed"
+
+
+def test_two_consecutive_command_failures_escalate(
+    store: StateStore, ws: Workspace
+) -> None:
+    client = ScriptedClient(
+        [
+            [call("run_command", command="exit 1")],
+            [call("run_command", command="exit 1")],
+            [call("run_command", command="exit 1")],
+        ]
+    )
+    outcome = build(client, store, ws, failure_limit=2).run(milestone=1)
+    assert outcome.status == "escalate"
+    assert "2 consecutive command failures" in outcome.note
+    assert len(client.calls) == 2  # stopped, did not keep trying
+
+
+def test_a_success_resets_the_failure_count(store: StateStore, ws: Workspace) -> None:
+    client = ScriptedClient(
+        [
+            [call("run_command", command="exit 1")],
+            [call("run_command", command="true")],
+            [call("run_command", command="exit 1")],
+            [AssistantText(text="done", model="m")],
+        ]
+    )
+    assert build(client, store, ws, failure_limit=2).run(milestone=1).status == (
+        "completed"
+    )
+
+
+def test_failed_reads_do_not_count_toward_escalation(
+    store: StateStore, ws: Workspace
+) -> None:
+    client = ScriptedClient(
+        [
+            [call("read_file", path="missing-a.txt")],
+            [call("read_file", path="missing-b.txt")],
+            [AssistantText(text="looked around, done", model="m")],
+        ]
+    )
+    assert build(client, store, ws, failure_limit=2).run(milestone=1).status == (
+        "completed"
+    )
+
+
+def test_turn_cap_is_enforced(store: StateStore, ws: Workspace) -> None:
+    forever = [[call("list_dir", path=".")] for _ in range(50)]
+    client = ScriptedClient(forever)
+    outcome = build(client, store, ws, max_turns=3).run(milestone=1)
+    assert outcome.status == "capped"
+    assert "3-turn cap" in outcome.note
+    assert len(client.calls) == 3
+
+
+def test_llm_error_escalates_rather_than_crashing(
+    store: StateStore, ws: Workspace
+) -> None:
+    outcome = build(FailingClient(), store, ws).run(milestone=1)
+    assert outcome.status == "escalate"
+    assert "proxy exploded" in outcome.note
+
+
+def test_multiple_calls_in_one_turn_all_run(store: StateStore, ws: Workspace) -> None:
+    client = ScriptedClient(
+        [
+            [
+                call("write_file", call_id="a", path="one.txt", content="1"),
+                call("write_file", call_id="b", path="two.txt", content="2"),
+            ],
+            [AssistantText(text="done", model="m")],
+        ]
+    )
+    build(client, store, ws).run(milestone=1)
+    assert (ws.root / "one.txt").exists() and (ws.root / "two.txt").exists()
+    results = [
+        e.event for e in store.read_events() if type(e.event).__name__ == "ToolResult"
+    ]
+    assert {r.call_id for r in results} == {"a", "b"}

nisse-dev/tests/test_planner.py

@@ -12,7 +12,14 @@ from nisse_dev.canonical import (
     ToolCall,
     UserMessage,
 )
-from nisse_dev.control import AskHuman, Orchestrator, PlanningError, SubmitPlan
+from nisse_dev.control import (
+    AWAIT_ARCH_SIGNOFF,
+    AWAIT_MILESTONE_SIGNOFF,
+    AskHuman,
+    Orchestrator,
+    PlanningError,
+    SubmitPlan,
+)
 from nisse_dev.llm import RoleMap
 from nisse_dev.oplog import OpLog
 from nisse_dev.planner import PLANNER_TOOLS, LLMPlanningAgent
@@ -108,7 +115,18 @@ def test_model_output_is_appended_to_the_log(store: StateStore) -> None:
     )
     LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
     kinds = [type(e.event).__name__ for e in store.read_events()]
-    assert kinds == ["AssistantText", "ToolCall"]
+    assert kinds == ["AssistantText", "ToolCall", "ToolResult"]
+
+
+def test_gate_tool_call_is_answered_in_the_log(store: StateStore) -> None:
+    # submit_plan ends the turn and has no natural result, but a tool call
+    # left dangling makes the next render invalid for the provider.
+    client = ScriptedClient([[plan_call("the plan")]])
+    LLMPlanningAgent(client, store, ROLES).plan("arch", "demo")
+    events = [e.event for e in store.read_events()]
+    assert [type(e).__name__ for e in events] == ["ToolCall", "ToolResult"]
+    assert events[1].call_id == events[0].call_id
+    assert "posted for approval" in events[1].result
 
 
 def test_prose_only_turn_retries_once_then_raises(store: StateStore) -> None:
@@ -170,7 +188,13 @@ def test_use_project_produces_llm_plan_and_transcript(tmp_path: Path) -> None:
 
     events = [e.event for e in store.read_events()]
     kinds = [type(e).__name__ for e in events]
-    assert kinds == ["UserMessage", "ToolCall", "PlanSubmitted", "GateOpened"]
+    assert kinds == [
+        "UserMessage",
+        "ToolCall",
+        "ToolResult",
+        "PlanSubmitted",
+        "GateOpened",
+    ]
     submitted = next(e for e in events if isinstance(e, PlanSubmitted))
     assert submitted.model == "anthropic/claude-opus-5"  # pinned planner
 
@@ -195,6 +219,53 @@ def test_planning_failure_gates_to_await_input(tmp_path: Path) -> None:
     assert transport.outbound[-1].kind == "question"
 
 
+def test_operator_can_recover_from_a_planning_failure(tmp_path: Path) -> None:
+    # Regression: AWAIT_INPUT reached by any path other than ask_human used to
+    # record no pending item, so every operator reply was refused with "no
+    # pending question" and the agent was stuck for good.
+    prose = [AssistantText(text="prose", model="m")]
+    client = ScriptedClient([prose, prose, [plan_call("recovered plan")]])
+    _, store, transport = build(tmp_path, client)
+    transport.receive("don", "use demo")
+    assert store.get_state().state == "AWAIT_INPUT"
+
+    transport.receive("don", "try again, keep it short")
+
+    assert store.get_state().state == AWAIT_ARCH_SIGNOFF
+    assert "recovered plan" in transport.outbound[-1].text
+
+
+def test_operator_can_recover_after_a_stopped_milestone(tmp_path: Path) -> None:
+    class StoppedExecutor:
+        def run(self, milestone: int) -> Any:
+            from nisse_dev.executor import ExecutorOutcome
+
+            return ExecutorOutcome("escalate", "tests failed twice")
+
+    store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
+    transport = InMemoryTransport()
+    client = ScriptedClient([[plan_call("p1")], [plan_call("p2")]])
+    orch = Orchestrator(
+        store,
+        transport,
+        LLMPlanningAgent(client, store, ROLES),
+        operators={"don"},
+        roles=ROLES,
+        executor=StoppedExecutor(),
+    )
+    orch.start()
+    transport.receive("don", "use demo")
+    transport.receive("don", "approve")
+    transport.receive("don", "approve")
+    transport.receive("don", "start milestone 1")
+    assert store.get_state().state == "AWAIT_INPUT"
+
+    transport.receive("don", "ok, I fixed the dependency")
+
+    assert store.get_state().state == AWAIT_MILESTONE_SIGNOFF
+    assert "start milestone 1" in transport.outbound[-1].text
+
+
 def test_rejection_feedback_reaches_the_planner_via_the_log(
     tmp_path: Path,
 ) -> None:

nisse-dev/tests/test_render.py

@@ -71,6 +71,33 @@ def test_compaction_replaces_its_range_only() -> None:
     assert contents == ["kept", "[summary of earlier conversation]\nthe old stuff"]
 
 
+def test_tool_call_without_a_result_gets_a_placeholder() -> None:
+    # Providers reject a dangling tool_use; this happens after a crash (A3)
+    # or with turn-ending gate tools like submit_plan.
+    events = stored(
+        [
+            UserMessage(text="go", source="m:1"),
+            ToolCall(call_id="call-x", tool="submit_plan", arguments={}),
+        ]
+    )
+    body = OpenAIChatRenderer().render(events, tools=None, model="q")
+    assert [m["role"] for m in body["messages"]] == ["user", "assistant", "tool"]
+    assert body["messages"][2]["tool_call_id"] == "call-x"
+    assert body["messages"][2]["content"] == "[no result recorded]"
+
+
+def test_answered_tool_call_gets_no_placeholder() -> None:
+    events = stored(
+        [
+            ToolCall(call_id="call-x", tool="run_command", arguments={}),
+            ToolResult(call_id="call-x", result="ok", success=True),
+        ]
+    )
+    body = OpenAIChatRenderer().render(events, tools=None, model="q")
+    assert [m["role"] for m in body["messages"]] == ["assistant", "tool"]
+    assert body["messages"][1]["content"] == "ok"
+
+
 def test_gate_event_renders_as_context() -> None:
     events = stored([GateOpened(gate="arch", reason="plan submitted (rev-1)")])
     body = OpenAIChatRenderer().render(events, tools=None, model="q")

nisse-dev/tests/test_tools.py

@@ -0,0 +1,129 @@
+import os
+from pathlib import Path
+
+import pytest
+
+from nisse_dev.tools import EXECUTOR_TOOLS, MAX_OUTPUT_CHARS, Workspace
+
+
+@pytest.fixture
+def ws(tmp_path: Path) -> Workspace:
+    return Workspace(tmp_path / "work", timeout_s=10)
+
+
+def test_manifest_is_small_and_flat() -> None:
+    # A15: fewer tools, flatter arguments for the local executor.
+    names = [t["function"]["name"] for t in EXECUTOR_TOOLS]
+    assert names == ["read_file", "write_file", "list_dir", "run_command"]
+    for tool in EXECUTOR_TOOLS:
+        props = tool["function"]["parameters"]["properties"]
+        assert all(p["type"] == "string" for p in props.values())
+
+
+def test_write_then_read_round_trip(ws: Workspace) -> None:
+    assert ws.write_file("src/app.py", "print('hi')\n").success
+    outcome = ws.read_file("src/app.py")
+    assert outcome.success
+    assert outcome.result == "print('hi')\n"
+
+
+def test_relative_paths_land_in_the_workspace(ws: Workspace) -> None:
+    ws.write_file("notes.txt", "x")
+    assert (ws.root / "notes.txt").exists()
+
+
+def test_read_missing_file_is_a_failed_result_not_an_exception(
+    ws: Workspace,
+) -> None:
+    outcome = ws.read_file("nope.txt")
+    assert not outcome.success
+    assert "could not read" in outcome.result
+
+
+def test_list_dir(ws: Workspace) -> None:
+    ws.write_file("a.txt", "a")
+    ws.write_file("sub/b.txt", "b")
+    outcome = ws.list_dir(".")
+    assert outcome.success
+    assert outcome.result.splitlines() == ["a.txt", "sub/"]
+
+
+def test_list_empty_dir(ws: Workspace) -> None:
+    assert ws.list_dir(".").result == "(empty)"
+
+
+def test_run_command_success_reports_exit_code_and_stdout(ws: Workspace) -> None:
+    outcome = ws.run_command("echo hello")
+    assert outcome.success
+    assert "exit code: 0" in outcome.result
+    assert "hello" in outcome.result
+
+
+def test_nonzero_exit_is_a_result_not_an_error(ws: Workspace) -> None:
+    outcome = ws.run_command("exit 3")
+    assert not outcome.success  # feeds the A12 failure count
+    assert "exit code: 3" in outcome.result
+
+
+def test_command_runs_in_the_workspace(ws: Workspace) -> None:
+    ws.write_file("marker.txt", "here")
+    assert "marker.txt" in ws.run_command("ls").result
+
+
+def test_command_timeout_is_reported(tmp_path: Path) -> None:
+    ws = Workspace(tmp_path / "work", timeout_s=1)
+    outcome = ws.run_command("sleep 30")
+    assert not outcome.success
+    assert "timed out" in outcome.result
+
+
+def _is_running(pid: int) -> bool:
+    """os.kill(pid, 0) is not enough: a killed orphan stays a zombie until
+    something reaps it, and no init does that inside a CI container. Read the
+    process state instead."""
+    try:
+        stat = Path(f"/proc/{pid}/stat").read_text()
+    except FileNotFoundError:
+        return False
+    # State is the first field after the parenthesised comm.
+    return stat.rsplit(")", 1)[1].split()[0] != "Z"
+
+
+def test_timeout_kills_the_whole_process_group(tmp_path: Path) -> None:
+    ws = Workspace(tmp_path / "work", timeout_s=1)
+    pidfile = ws.root / "child.pid"
+    # A backgrounded grandchild must not outlive the timeout.
+    ws.run_command(f"(sleep 30 & echo $! > {pidfile}); sleep 30")
+    assert pidfile.exists()
+    pid = int(pidfile.read_text().strip())
+    assert _is_running(os.getpid()), "liveness check is broken, not the kill"
+    assert not _is_running(pid)
+
+
+def test_agent_credentials_are_not_inherited(
+    ws: Workspace, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    monkeypatch.setenv("NISSE_LLM_TOKEN", "sk-secret")
+    monkeypatch.setenv("PATH", os.environ["PATH"])
+    outcome = ws.run_command("echo [${NISSE_LLM_TOKEN}]")
+    assert "sk-secret" not in outcome.result
+    assert "[]" in outcome.result
+
+
+def test_stdin_is_closed_so_prompts_fail_fast(ws: Workspace) -> None:
+    outcome = ws.run_command("read line && echo got")
+    assert not outcome.success
+    assert "got" not in outcome.result
+
+
+def test_long_output_is_truncated(ws: Workspace) -> None:
+    outcome = ws.run_command("printf 'x%.0s' $(seq 1 20000)")
+    assert len(outcome.result) < MAX_OUTPUT_CHARS + 200
+    assert "truncated" in outcome.result
+
+
+def test_dispatch_unknown_tool_and_missing_argument(ws: Workspace) -> None:
+    assert not ws.dispatch("fly", {}).success
+    missing = ws.dispatch("read_file", {})
+    assert not missing.success
+    assert "missing argument" in missing.result

tests/integration/test_milestone_live.py

@@ -0,0 +1,107 @@
+"""End-to-end milestone against real models: plan with the planner role,
+approve through the gate, then let the executor role actually create and test
+a file on disk.
+
+Gated on NISSE_LIVE_PLANNER_MODEL like the planning test — it needs a model
+that holds the tool-call contract on both ends.
+"""
+
+import io
+import os
+from pathlib import Path
+
+import pytest
+
+from nisse_dev.control import (
+    AWAIT_ARCH_SIGNOFF,
+    AWAIT_INPUT,
+    AWAIT_MILESTONE_SIGNOFF,
+    EXECUTING,
+    Orchestrator,
+)
+from nisse_dev.envfile import load_env_file
+from nisse_dev.executor import LLMExecutor
+from nisse_dev.llm import LiteLLMClient, RoleMap
+from nisse_dev.oplog import OpLog
+from nisse_dev.planner import LLMPlanningAgent
+from nisse_dev.state import StateStore
+from nisse_dev.tools import Workspace
+from nisse_dev.transport import InMemoryTransport
+
+load_env_file(Path(__file__).resolve().parents[2] / ".env")
+
+SENTINEL = "NISSE_LIVE_PLANNER_MODEL"
+
+pytestmark = [
+    pytest.mark.integration,
+    pytest.mark.skipif(
+        not os.environ.get(SENTINEL),
+        reason=f"no live planner route configured ({SENTINEL} unset)",
+    ),
+]
+
+
+def _drive_to_execution(
+    store: StateStore, transport: InMemoryTransport, max_steps: int = 10
+) -> None:
+    """Play the operator. A scripted approve/approve/start sequence is not
+    robust against a live model: ask_human is a legitimate move at any gate,
+    and a question shifts the state machine under a fixed script. So respond
+    to whatever the agent actually did."""
+    for _ in range(max_steps):
+        state = store.get_state()
+        assert state is not None
+        if state.state == EXECUTING:
+            return
+        gate = state.data.get("gate") or {}
+        if state.state == AWAIT_INPUT:
+            transport.receive("don", "Use your best judgement and proceed.")
+        elif state.state == AWAIT_MILESTONE_SIGNOFF and gate.get("approved"):
+            transport.receive("don", "start milestone 1")
+        elif state.state in (AWAIT_ARCH_SIGNOFF, AWAIT_MILESTONE_SIGNOFF):
+            transport.receive("don", "approve")
+        else:
+            raise AssertionError(f"unexpected state {state.state}")
+    raise AssertionError(
+        f"never reached execution; last message: {transport.outbound[-1]}"
+    )
+
+
+def test_plan_approve_execute_produces_a_real_file(tmp_path: Path) -> None:
+    assert os.environ.get("NISSE_LLM_TOKEN"), (
+        f"{SENTINEL} is set, so the live path is expected to work, "
+        "but NISSE_LLM_TOKEN is missing"
+    )
+    # Both roles use the capable model here: the point is the whole gated
+    # loop over a real proxy, not local-model competence (measured separately).
+    model = os.environ[SENTINEL]
+    roles = RoleMap(executor=model, planner=model, delegate=model, consultant=model)
+    client = LiteLLMClient.from_env()
+    store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
+    workspace = Workspace(tmp_path / "work", timeout_s=60)
+    transport = InMemoryTransport()
+    orchestrator = Orchestrator(
+        store,
+        transport,
+        LLMPlanningAgent(client, store, roles),
+        operators={"don"},
+        roles=roles,
+        executor=LLMExecutor(client, store, roles, workspace, max_turns=10),
+    )
+    orchestrator.start()
+
+    transport.receive(
+        "don",
+        "use greet. Milestone 1: create greet.py in the workspace root defining "
+        "greet(name) returning 'Hello, <name>!', and verify it by running python.",
+    )
+    _drive_to_execution(store, transport)
+
+    state = store.get_state()
+    assert state is not None
+    assert state.state in (EXECUTING, AWAIT_INPUT)
+
+    created = list(workspace.root.rglob("*.py"))
+    assert created, f"executor created no Python file; said: {transport.outbound[-1]}"
+    combined = "\n".join(p.read_text() for p in created)
+    assert "def greet" in combined