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._transport.ask_question(
-                "restart found unresolved work: "
-                + "; ".join(report.notes)
-                + " — how should I proceed?"
+            self._await_input(
+                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._transport.ask_question(
-                f"restarted mid-{state.state}; continue or re-plan?"
+            self._await_input(
+                cause=f"boot: restarted in {state.state}",
+                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._transport.ask_question(
-                f"planning for {gate_name} failed ({exc}); retry or re-plan?"
+            self._await_input(
+                cause=f"planning failed: {exc}",
+                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._transition(
-                AWAIT_INPUT, cause=f"agent question during {gate_name} planning"
+            self._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")
-        if question is None:
+        pending = self._data.get("pending")
+        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
-        gate_name = question["gate"]
-        back = PLANNING_ARCH if gate_name == "arch" else MILESTONE_PLANNING
-        self._transition(back, cause="operator answered question")
-        self._run_planning_turn(gate_name, answer=text)
+        self._data["pending"] = None
+        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; 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)