Implement the harness contract and prove it against rein-aharness (GLAS-WP-0001-T02/T03/T04)
- src/glas_harness/contract.py: Rein ABC (start_session/dispatch_tool/
end_session), SandboxHandle/ToolCall/ToolResult, per docs/harness-contract.md.
- reins/rein_aharness.py: adapter around the rein-aharness CLI. Collapses
a whole `agent-harness run` into one dispatch_tool call for now (no
per-tool hooks yet — tracked in rein-aharness HARNESS-WP-0002-T03);
verifies success via new-commit detection, mirroring rein-aharness's
own success signal.
- gateway.py + cli.py: resolves a sand-boxer sandbox, runs one task
through a rein, tears the sandbox down.
- registry/reins/*.yaml (rein-aharness implemented, rein-openweights
planned) and profiles/harness.agent-dev{,-local}.yaml, pairing with
sand-boxer's profile.agent-dev and the new profile.bwrap-local.
Tested against a real local git repo + mocked SandboxManager/CLI
subprocess (10 tests, all passing). A real live run against the actual
Claude Code CLI is deliberately left for a human-triggered follow-up —
not executed autonomously since it spends real API credits/credentials.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
parent
97a50fc780
commit
5681fce787
16 changed files with 556 additions and 4 deletions
0
src/glas_harness/__init__.py
Normal file
0
src/glas_harness/__init__.py
Normal file
42
src/glas_harness/cli.py
Normal file
42
src/glas_harness/cli.py
Normal file
|
|
@ -0,0 +1,42 @@
|
|||
"""glas-harness CLI — minimal gateway invocation (GLAS-WP-0001-T04)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import sys
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser(prog="glas-harness")
|
||||
sub = parser.add_subparsers(dest="command", required=True)
|
||||
|
||||
run = sub.add_parser("run", help="Run one task through a rein inside a sand-boxer sandbox")
|
||||
run.add_argument("--sandbox-profile", required=True, help="e.g. profile.bwrap-local")
|
||||
run.add_argument("--repo", required=True, help="Local repo path to mirror into the sandbox")
|
||||
run.add_argument("--title", required=True)
|
||||
run.add_argument("--description", required=True)
|
||||
run.add_argument("--actor", default="agt")
|
||||
run.add_argument("--project", default="glas-harness")
|
||||
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
if args.command == "run":
|
||||
from glas_harness.gateway import run_task_through_rein
|
||||
|
||||
result = run_task_through_rein(
|
||||
sandbox_profile=args.sandbox_profile,
|
||||
repo=args.repo,
|
||||
title=args.title,
|
||||
description=args.description,
|
||||
actor=args.actor,
|
||||
project=args.project,
|
||||
)
|
||||
print(json.dumps(result, indent=2))
|
||||
return 0 if result["tool_ok"] else 1
|
||||
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
54
src/glas_harness/contract.py
Normal file
54
src/glas_harness/contract.py
Normal file
|
|
@ -0,0 +1,54 @@
|
|||
"""The harness contract a concrete rein implements.
|
||||
|
||||
See docs/harness-contract.md for the full session-lifecycle diagram and
|
||||
GLAS-WP-0001-T01. glas-harness owns the outer loop (profile resolution,
|
||||
sandbox request/teardown via sand-boxer, State Hub reporting, actor
|
||||
attribution); a rein owns the inner agentic loop.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any
|
||||
|
||||
|
||||
@dataclass
|
||||
class SandboxHandle:
|
||||
"""What glas-harness got back from sand-boxer's create()."""
|
||||
|
||||
sandbox_id: str
|
||||
host: str
|
||||
reachability: dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ToolCall:
|
||||
name: str
|
||||
args: dict[str, Any] = field(default_factory=dict)
|
||||
actor: str = "agt"
|
||||
|
||||
|
||||
@dataclass
|
||||
class ToolResult:
|
||||
ok: bool
|
||||
output: str = ""
|
||||
error: str | None = None
|
||||
|
||||
|
||||
class Rein(ABC):
|
||||
"""Base class for concrete harness backends (reins)."""
|
||||
|
||||
@abstractmethod
|
||||
def start_session(
|
||||
self, profile: dict[str, Any], inputs: dict[str, str], sandbox: SandboxHandle
|
||||
) -> dict[str, str]:
|
||||
"""Begin an agent session bound to a sandbox. Returns a session handle."""
|
||||
|
||||
@abstractmethod
|
||||
def dispatch_tool(self, session: dict[str, str], tool_call: ToolCall) -> ToolResult:
|
||||
"""Run one tool call under the session's policy."""
|
||||
|
||||
@abstractmethod
|
||||
def end_session(self, session: dict[str, str]) -> dict[str, str]:
|
||||
"""Close the session. Returns a summary (commit sha, outcome, ...)."""
|
||||
72
src/glas_harness/gateway.py
Normal file
72
src/glas_harness/gateway.py
Normal file
|
|
@ -0,0 +1,72 @@
|
|||
"""Minimal gateway proving the harness contract against rein-aharness.
|
||||
|
||||
GLAS-WP-0001-T04: resolve a sand-boxer profile, request a sandbox,
|
||||
dispatch one rein-aharness task through the Rein contract, verify a
|
||||
commit landed, tear the sandbox down. This is the parity proof gating
|
||||
any later "retire rein-aharness as a standalone concern" conversation —
|
||||
it is not itself that conversation.
|
||||
|
||||
Requires the `sandbox` extra (sand-boxer installed as a sibling
|
||||
editable dependency).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from sandboxer.core.manager import SandboxManager
|
||||
from sandboxer.models import Consumer, SandboxCreateRequest
|
||||
|
||||
from glas_harness.contract import Rein, SandboxHandle, ToolCall
|
||||
from glas_harness.reins.rein_aharness import ReinAharness
|
||||
|
||||
|
||||
def run_task_through_rein(
|
||||
*,
|
||||
sandbox_profile: str,
|
||||
repo: str,
|
||||
title: str,
|
||||
description: str,
|
||||
rein: Rein | None = None,
|
||||
actor: str = "agt",
|
||||
project: str = "glas-harness",
|
||||
manager: SandboxManager | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Resolve `sandbox_profile`, run one task inside it via `rein`, verify, tear down.
|
||||
|
||||
Defaults to `ReinAharness` when no rein is supplied — the only
|
||||
implemented rein as of GLAS-WP-0001-T04. `rein-openweights` plugs in
|
||||
the same way once REIN-OW-WP-0001 lands.
|
||||
"""
|
||||
manager = manager or SandboxManager()
|
||||
rein = rein or ReinAharness()
|
||||
|
||||
request = SandboxCreateRequest(
|
||||
profile=sandbox_profile,
|
||||
inputs={"repo": repo},
|
||||
consumer=Consumer(actor=actor, project=project),
|
||||
)
|
||||
status = manager.create(request)
|
||||
try:
|
||||
reachability = status.reachability.model_dump(mode="json") if status.reachability else {}
|
||||
sandbox = SandboxHandle(
|
||||
sandbox_id=status.sandbox_id, host=status.host or "", reachability=reachability
|
||||
)
|
||||
|
||||
session = rein.start_session(
|
||||
profile={"id": sandbox_profile},
|
||||
inputs={"title": title, "description": description},
|
||||
sandbox=sandbox,
|
||||
)
|
||||
tool_result = rein.dispatch_tool(session, ToolCall(name="run_task", actor=actor))
|
||||
summary = rein.end_session(session)
|
||||
|
||||
return {
|
||||
"sandbox_id": status.sandbox_id,
|
||||
"tool_ok": tool_result.ok,
|
||||
"tool_output": tool_result.output,
|
||||
"tool_error": tool_result.error,
|
||||
"summary": summary,
|
||||
}
|
||||
finally:
|
||||
manager.destroy(status.sandbox_id)
|
||||
0
src/glas_harness/reins/__init__.py
Normal file
0
src/glas_harness/reins/__init__.py
Normal file
102
src/glas_harness/reins/rein_aharness.py
Normal file
102
src/glas_harness/reins/rein_aharness.py
Normal file
|
|
@ -0,0 +1,102 @@
|
|||
"""ReinAharness — glas-harness adapter around the rein-aharness CLI.
|
||||
|
||||
rein-aharness's `run` command performs an entire bounded agentic session
|
||||
(persona load, Claude Code CLI subprocess, commit verification) as one
|
||||
opaque unit — it does not yet expose per-tool-call hooks from outside
|
||||
(that refactor is tracked in
|
||||
rein-aharness/workplans/HARNESS-WP-0002-T03). Until then, dispatch_tool
|
||||
collapses the whole run into a single call rather than true per-tool
|
||||
granularity; this adapter proves the contract's *shape* (start/dispatch/
|
||||
end + sandbox handoff), not fine-grained tool interception yet.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from glas_harness.contract import Rein, SandboxHandle, ToolCall, ToolResult
|
||||
|
||||
|
||||
class ReinAharnessNotInstalled(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
class ReinAharness(Rein):
|
||||
def __init__(self, cli_bin: str = "agent-harness") -> None:
|
||||
self.cli_bin = cli_bin
|
||||
|
||||
def _bin(self) -> str:
|
||||
resolved = shutil.which(self.cli_bin)
|
||||
if not resolved:
|
||||
raise ReinAharnessNotInstalled(
|
||||
f"'{self.cli_bin}' not found on PATH — install rein-aharness first"
|
||||
)
|
||||
return resolved
|
||||
|
||||
def start_session(
|
||||
self, profile: dict[str, Any], inputs: dict[str, str], sandbox: SandboxHandle
|
||||
) -> dict[str, str]:
|
||||
target_repo = (
|
||||
inputs.get("target_repo")
|
||||
or sandbox.reachability.get("workspace_dir")
|
||||
or sandbox.reachability.get("remote_dir")
|
||||
)
|
||||
if not target_repo:
|
||||
raise ValueError("no target_repo resolvable from inputs or sandbox reachability")
|
||||
|
||||
task_file = inputs.get("task_file")
|
||||
if not task_file:
|
||||
task_spec = {
|
||||
"title": inputs["title"],
|
||||
"description": inputs["description"],
|
||||
"target_repo": target_repo,
|
||||
"agent": inputs.get("agent", "coach"),
|
||||
}
|
||||
fd = tempfile.NamedTemporaryFile(
|
||||
mode="w", suffix=".json", prefix="glas-harness-task-", delete=False
|
||||
)
|
||||
json.dump(task_spec, fd)
|
||||
fd.close()
|
||||
task_file = fd.name
|
||||
|
||||
return {
|
||||
"sandbox_id": sandbox.sandbox_id,
|
||||
"task_file": task_file,
|
||||
"target_repo": target_repo,
|
||||
"head_before": self._git_head(target_repo),
|
||||
}
|
||||
|
||||
def dispatch_tool(self, session: dict[str, str], tool_call: ToolCall) -> ToolResult:
|
||||
argv = [
|
||||
self._bin(),
|
||||
"run",
|
||||
"--task-file",
|
||||
session["task_file"],
|
||||
"--no-hub",
|
||||
"--no-metrics",
|
||||
]
|
||||
proc = subprocess.run(argv, capture_output=True, text=True)
|
||||
ok = proc.returncode == 0
|
||||
return ToolResult(ok=ok, output=proc.stdout, error=None if ok else proc.stderr)
|
||||
|
||||
def end_session(self, session: dict[str, str]) -> dict[str, str]:
|
||||
head_after = self._git_head(session["target_repo"])
|
||||
committed = bool(head_after) and head_after != session.get("head_before")
|
||||
return {
|
||||
"commit_sha": head_after or "",
|
||||
"committed": str(committed),
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _git_head(repo: str) -> str:
|
||||
proc = subprocess.run(
|
||||
["git", "-C", str(Path(repo).expanduser()), "rev-parse", "HEAD"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
return proc.stdout.strip() if proc.returncode == 0 else ""
|
||||
Loading…
Add table
Add a link
Reference in a new issue