feat(supervise): host TUI drives approvals over HTTP, not the DB (Step 2b/2c)
The `bot-bottle supervise` operator TUI read and wrote the queue DB directly and tried a backend-specific live "apply" (which was unwired — it raised). It now talks only to the orchestrator control plane: - OrchestratorClient gains supervise_pending() + supervise_respond(). - discover_orchestrator_url() finds the one running per-host control plane by health-probing the backends' well-known :8099 addresses (docker publishes on loopback; the firecracker infra VM serves it on the orchestrator TAP) — no backend branching in the TUI. - discover_pending/approve/reject call the client; the server does the apply + response + audit atomically. The dead direct-DB apply/audit helpers and the docker/macos applicator imports are gone. - A missing control plane is now a clean one-line error up front, not a mid-curses crash. CLI tests move to mocking the client (the DB-write behaviour they used to assert is now server-side, covered by test_orchestrator_service). Docker's orchestrator-container DB wiring lands next so its /supervise endpoints hit the same shared DB. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
This commit is contained in:
+46
-80
@@ -20,32 +20,19 @@ from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from ..paths import bot_bottle_root
|
||||
from ..bottle_state import read_metadata
|
||||
from ..backend.docker.egress_apply import (
|
||||
EgressApplyError,
|
||||
applicator as _docker_applicator,
|
||||
)
|
||||
from ..backend.macos_container.egress_apply import (
|
||||
applicator as _macos_applicator,
|
||||
)
|
||||
from ..log import Die, error, info
|
||||
from ..orchestrator.client import (
|
||||
OrchestratorClient,
|
||||
OrchestratorClientError,
|
||||
discover_orchestrator_url,
|
||||
)
|
||||
|
||||
from ..supervise import (
|
||||
COMPONENT_FOR_TOOL,
|
||||
AuditEntry,
|
||||
Proposal,
|
||||
Response,
|
||||
STATUS_APPROVED,
|
||||
STATUS_MODIFIED,
|
||||
STATUS_REJECTED,
|
||||
TOOL_EGRESS_ALLOW,
|
||||
TOOL_EGRESS_BLOCK,
|
||||
TOOL_GITLEAKS_ALLOW,
|
||||
TOOL_EGRESS_TOKEN_ALLOW,
|
||||
list_all_pending_proposals,
|
||||
render_diff,
|
||||
write_audit_entry,
|
||||
write_response,
|
||||
)
|
||||
from ._common import PROG
|
||||
|
||||
@@ -65,25 +52,31 @@ class QueuedProposal:
|
||||
proposal: Proposal
|
||||
|
||||
|
||||
# Errors any remediation engine may raise. Caught by the TUI key
|
||||
# handlers and surfaced in the status line so a failed apply keeps
|
||||
# the proposal pending rather than crashing curses.
|
||||
ApplyError = (EgressApplyError,)
|
||||
# A failed operator action (orchestrator unreachable, bottle torn down,
|
||||
# 409) is caught by the TUI key handlers and surfaced in the status line so
|
||||
# the proposal stays pending rather than crashing curses.
|
||||
ApplyError = (OrchestratorClientError,)
|
||||
|
||||
|
||||
def apply_routes_change(slug: str, content: str) -> tuple[str, str]:
|
||||
meta = read_metadata(slug)
|
||||
backend = meta.backend if meta is not None else ""
|
||||
if backend == "macos-container":
|
||||
return _macos_applicator.apply_routes_change(slug, content)
|
||||
return _docker_applicator.apply_routes_change(slug, content)
|
||||
# The one per-host orchestrator, discovered lazily on first use. Every
|
||||
# operator action — list, approve, reject — goes through its HTTP control
|
||||
# plane (the orchestrator owns the single DB + live policy); there is no
|
||||
# direct-DB path and no backend branching here.
|
||||
_client_instance: OrchestratorClient | None = None
|
||||
|
||||
|
||||
def _client() -> OrchestratorClient:
|
||||
global _client_instance # noqa: PLW0603 — CLI-session singleton
|
||||
if _client_instance is None:
|
||||
_client_instance = OrchestratorClient(discover_orchestrator_url())
|
||||
return _client_instance
|
||||
|
||||
|
||||
def discover_pending() -> list[QueuedProposal]:
|
||||
"""Collect pending proposals across bottles."""
|
||||
"""Collect pending proposals across bottles from the orchestrator."""
|
||||
out = [
|
||||
QueuedProposal(proposal=proposal)
|
||||
for proposal in list_all_pending_proposals()
|
||||
QueuedProposal(proposal=Proposal.from_dict(d))
|
||||
for d in _client().supervise_pending()
|
||||
]
|
||||
out.sort(key=lambda q: q.proposal.arrival_timestamp)
|
||||
return out
|
||||
@@ -136,39 +129,27 @@ def approve(
|
||||
notes: str = "",
|
||||
final_file: str | None = None,
|
||||
) -> None:
|
||||
"""Apply the proposal, write the waiting response, and audit it."""
|
||||
status = STATUS_MODIFIED if final_file is not None else STATUS_APPROVED
|
||||
file_to_apply = final_file if final_file is not None else qp.proposal.proposed_file
|
||||
|
||||
diff_before, diff_after = "", ""
|
||||
if qp.proposal.tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
|
||||
diff_before, diff_after = apply_routes_change(
|
||||
qp.proposal.bottle_slug,
|
||||
file_to_apply,
|
||||
)
|
||||
|
||||
response = Response(
|
||||
proposal_id=qp.proposal.id,
|
||||
status=status,
|
||||
"""Approve (or, with `final_file`, modify-then-approve) via the
|
||||
orchestrator: it applies the route change to the bottle's live policy,
|
||||
writes the response that unblocks the agent, and audits it — one atomic
|
||||
server-side op. Raises `OrchestratorClientError` on failure."""
|
||||
_client().supervise_respond(
|
||||
qp.proposal.id,
|
||||
bottle_slug=qp.proposal.bottle_slug,
|
||||
decision="modify" if final_file is not None else "approve",
|
||||
notes=notes,
|
||||
final_file=final_file,
|
||||
)
|
||||
write_response(qp.proposal.bottle_slug, response)
|
||||
_write_audit(
|
||||
qp, action=status, notes=notes,
|
||||
diff_before=diff_before, diff_after=diff_after,
|
||||
)
|
||||
|
||||
|
||||
def reject(qp: QueuedProposal, *, reason: str) -> None:
|
||||
"""Write a rejection response and an audit entry."""
|
||||
response = Response(
|
||||
proposal_id=qp.proposal.id,
|
||||
status=STATUS_REJECTED,
|
||||
"""Reject via the orchestrator (writes the response + audit)."""
|
||||
_client().supervise_respond(
|
||||
qp.proposal.id,
|
||||
bottle_slug=qp.proposal.bottle_slug,
|
||||
decision="reject",
|
||||
notes=reason,
|
||||
final_file=None,
|
||||
)
|
||||
write_response(qp.proposal.bottle_slug, response)
|
||||
_write_audit(qp, action=STATUS_REJECTED, notes=reason, diff_before="", diff_after="")
|
||||
|
||||
|
||||
def _approve_from_tui(
|
||||
@@ -188,29 +169,6 @@ def _approve_from_tui(
|
||||
return _approval_status(qp, verb)
|
||||
|
||||
|
||||
def _write_audit(
|
||||
qp: QueuedProposal,
|
||||
*,
|
||||
action: str,
|
||||
notes: str,
|
||||
diff_before: str,
|
||||
diff_after: str,
|
||||
) -> None:
|
||||
"""Audit log for egress tool."""
|
||||
component = COMPONENT_FOR_TOOL.get(qp.proposal.tool)
|
||||
if component is None:
|
||||
return
|
||||
write_audit_entry(AuditEntry(
|
||||
timestamp=datetime.now(timezone.utc).isoformat(),
|
||||
bottle_slug=qp.proposal.bottle_slug,
|
||||
component=component,
|
||||
operator_action=action,
|
||||
operator_notes=notes,
|
||||
justification=qp.proposal.justification,
|
||||
diff=render_diff(diff_before, diff_after, label=component),
|
||||
))
|
||||
|
||||
|
||||
# --- $EDITOR integration --------------------------------------------------
|
||||
|
||||
|
||||
@@ -245,6 +203,14 @@ def cmd_supervise(argv: list[str]) -> int:
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
# Establish the orchestrator connection up front so a missing control
|
||||
# plane is a clean one-line error, not a curses crash mid-loop.
|
||||
try:
|
||||
_client()
|
||||
except OrchestratorClientError as e:
|
||||
error(str(e))
|
||||
return 1
|
||||
|
||||
if args.once:
|
||||
return _list_once()
|
||||
try:
|
||||
|
||||
@@ -135,10 +135,71 @@ class OrchestratorClient:
|
||||
bottles = payload.get("bottles")
|
||||
return bottles if isinstance(bottles, list) else []
|
||||
|
||||
# --- supervise queue (operator TUI) ------------------------------------
|
||||
|
||||
def supervise_pending(self) -> list[dict[str, object]]:
|
||||
"""Pending supervise proposals across all bottles
|
||||
(`GET /supervise/proposals`)."""
|
||||
payload = self._ok("GET", "/supervise/proposals")
|
||||
proposals = payload.get("proposals")
|
||||
return proposals if isinstance(proposals, list) else []
|
||||
|
||||
def supervise_respond(
|
||||
self,
|
||||
proposal_id: str,
|
||||
*,
|
||||
bottle_slug: str,
|
||||
decision: str,
|
||||
notes: str = "",
|
||||
final_file: str | None = None,
|
||||
) -> None:
|
||||
"""Record an operator decision (`POST /supervise/respond`). `decision`
|
||||
is approve/modify/reject. Raises `OrchestratorClientError` if the
|
||||
proposal is gone or the bottle can no longer be applied to (409)."""
|
||||
body: dict[str, object] = {
|
||||
"proposal_id": proposal_id,
|
||||
"bottle_slug": bottle_slug,
|
||||
"decision": decision,
|
||||
"notes": notes,
|
||||
}
|
||||
if final_file is not None:
|
||||
body["final_file"] = final_file
|
||||
self._ok("POST", "/supervise/respond", body)
|
||||
|
||||
|
||||
def discover_orchestrator_url(*, timeout: float = 2.0) -> str:
|
||||
"""The URL of the one running per-host orchestrator control plane, probing
|
||||
the backends' well-known control-plane addresses (both on port 8099):
|
||||
docker publishes it on loopback; the firecracker infra VM serves it on the
|
||||
orchestrator TAP. Returns the first that answers `/health`; raises if none
|
||||
do (no orchestrator up — launch a bottle first)."""
|
||||
candidates: list[str] = []
|
||||
try: # docker: loopback-published control plane
|
||||
from .lifecycle import DEFAULT_PORT as _DOCKER_PORT
|
||||
candidates.append(f"http://127.0.0.1:{_DOCKER_PORT}")
|
||||
except Exception: # noqa: BLE001 — backend optional
|
||||
candidates.append("http://127.0.0.1:8099")
|
||||
try: # firecracker: infra VM control plane on the orchestrator TAP
|
||||
from ..backend.firecracker import netpool
|
||||
from ..backend.firecracker.infra_vm import CONTROL_PLANE_PORT
|
||||
candidates.append(
|
||||
f"http://{netpool.orch_slot().guest_ip}:{CONTROL_PLANE_PORT}")
|
||||
except Exception: # noqa: BLE001 — backend optional / not firecracker
|
||||
pass
|
||||
for url in candidates:
|
||||
if OrchestratorClient(url, timeout=timeout).health():
|
||||
return url
|
||||
raise OrchestratorClientError(
|
||||
"no running orchestrator control plane found (tried "
|
||||
+ ", ".join(candidates)
|
||||
+ "); launch a bottle first"
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorClient",
|
||||
"OrchestratorClientError",
|
||||
"RegisteredBottle",
|
||||
"DEFAULT_TIMEOUT_SECONDS",
|
||||
"discover_orchestrator_url",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user