feat(escalation): primitive הסלמה-לאדם loop-safe בשער-הפלטפורמה (#218) #405
@@ -57,6 +57,7 @@ from web.paperclip_client import (
|
||||
# ── raw imports: wrapped with telemetry below (state-affecting ops, #219) ──
|
||||
cancel_interaction as _cancel_interaction,
|
||||
cancel_run as _cancel_run,
|
||||
escalate_issue as _escalate_issue,
|
||||
post_comment as _post_comment,
|
||||
reap_stale_interactions as _reap_stale_interactions,
|
||||
reset_agent_session as _reset_agent_session,
|
||||
@@ -107,6 +108,12 @@ pc_post_comment = instrument(
|
||||
pc_cancel_interaction = instrument(
|
||||
"interaction.cancelled", keys=("issue_id", "interaction_id"),
|
||||
)(_cancel_interaction)
|
||||
# First-class escalation-to-chair (#218): the loop-safe alternative to leaving an
|
||||
# issue agent-owned+blocked. Emits a severity-tagged event so escalations are
|
||||
# countable per case in the same stream as the wakeups they replace.
|
||||
pc_escalate_issue = instrument(
|
||||
"agent.escalated", keys=("issue_id", "severity", "company_id", "reason"),
|
||||
)(_escalate_issue)
|
||||
pc_reap_stale_interactions = instrument(
|
||||
"interaction.reaped", result_keys=("cancelled",),
|
||||
)(_reap_stale_interactions)
|
||||
@@ -168,6 +175,7 @@ __all__ = [
|
||||
"pc_respond_to_interaction",
|
||||
"pc_cancel_interaction",
|
||||
"pc_reap_stale_interactions",
|
||||
"pc_escalate_issue",
|
||||
# agent-run observability + control (live view + smart management)
|
||||
"pc_list_live_runs",
|
||||
"pc_get_run_log",
|
||||
|
||||
25
web/app.py
25
web/app.py
@@ -61,6 +61,7 @@ from web.agent_platform_port import (
|
||||
pc_cancel_run,
|
||||
pc_create_project,
|
||||
pc_create_workflow_issue,
|
||||
pc_escalate_issue,
|
||||
pc_get_agents,
|
||||
pc_get_agents_for_case,
|
||||
pc_get_case_issues,
|
||||
@@ -4651,6 +4652,30 @@ async def api_reset_case_agents(case_number: str):
|
||||
return result
|
||||
|
||||
|
||||
class EscalateRequest(BaseModel):
|
||||
issue_id: str
|
||||
severity: Literal["critical", "high", "medium"]
|
||||
reason: str
|
||||
|
||||
|
||||
@app.post("/api/cases/{case_number}/agents/escalate")
|
||||
async def api_escalate_issue(case_number: str, req: EscalateRequest):
|
||||
"""Escalate a single stuck issue to the chair (#218).
|
||||
|
||||
The loop-safe alternative to leaving an issue agent-owned+blocked: hands the
|
||||
issue to the human in one atomic transition (in_review + assignee_user_id)
|
||||
and records a severity note, without re-waking any agent. Emits an
|
||||
``agent.escalated`` telemetry event via the Port.
|
||||
"""
|
||||
issues = await pc_get_case_issues(case_number)
|
||||
if not any(i["id"] == req.issue_id for i in issues):
|
||||
raise HTTPException(404, f"Issue {req.issue_id} לא שייך לתיק {case_number}")
|
||||
result = await pc_escalate_issue(req.issue_id, req.severity, req.reason)
|
||||
if not result.get("ok"):
|
||||
raise HTTPException(400, result.get("error", "ההסלמה נכשלה"))
|
||||
return result
|
||||
|
||||
|
||||
# ── Settings: MCP Server Configuration ────────────────────────────
|
||||
#
|
||||
# Source of truth for legal-ai env vars is Coolify (see memory:
|
||||
|
||||
@@ -856,6 +856,78 @@ async def reset_case_agents(case_number: str) -> dict:
|
||||
}
|
||||
|
||||
|
||||
ESCALATION_SEVERITIES = ("critical", "high", "medium")
|
||||
|
||||
|
||||
async def escalate_issue(
|
||||
issue_id: str, severity: str, reason: str, company_id: str = "",
|
||||
) -> dict:
|
||||
"""First-class, severity-routed escalation of a stuck issue to the chair (#218).
|
||||
|
||||
Replaces the fragile manual "PATCH dance" (reassign + set in_review + open an
|
||||
interaction) that repeatedly tripped Paperclip's recovery loops
|
||||
(``source_scoped_recovery_action`` / ``stranded_assigned_issue`` /
|
||||
``issue_reopened_via_comment``; see memory reference_paperclip_recovery_loops).
|
||||
|
||||
Two effects in **one DB transaction**, mirroring the proven loop-safe path of
|
||||
:func:`reset_case_agents` (raw SQL, not REST):
|
||||
|
||||
1. **Atomic human-owned transition** — a single ``UPDATE`` to the stable end
|
||||
state ``{status:'in_review', assignee_agent_id:null,
|
||||
assignee_user_id:CHAIM_USER_ID}`` (recovery-loops rule #7). Direct-DB on
|
||||
purpose: it bypasses Paperclip's disposition resolver — the very machinery
|
||||
whose multi-PATCH/`issue.released` behaviour *causes* the loops — so the
|
||||
issue lands human-owned in one shot with no ``done→todo`` flip.
|
||||
2. **Durable severity note** — an ``author_type='system'`` comment recording
|
||||
severity + reason. System-authored on purpose: the ``route-pending-comments``
|
||||
sweep routes only ``author_type='user'`` (chair) comments to the CEO, so a
|
||||
system note is inert w.r.t. routing and will **not** re-wake an agent
|
||||
(project_comment_delivery_guarantee). No wakeup is issued — the whole point
|
||||
is to hand off to the human, not re-invoke an agent.
|
||||
|
||||
The ``agent.escalated`` telemetry event is emitted by the Port wrapper
|
||||
(docs/spec/X15) — this is the loop-safe counterpart the CEO/analysts reach
|
||||
for instead of leaving an issue agent-owned+blocked.
|
||||
"""
|
||||
if severity not in ESCALATION_SEVERITIES:
|
||||
return {
|
||||
"ok": False,
|
||||
"error": f"invalid severity {severity!r}; expected one of {ESCALATION_SEVERITIES}",
|
||||
}
|
||||
|
||||
body = f"🚨 הסלמה [{severity}] לחיים\n\n{reason}"
|
||||
conn = await asyncpg.connect(PAPERCLIP_DB_URL)
|
||||
try:
|
||||
async with conn.transaction():
|
||||
row = await conn.fetchrow(
|
||||
"""UPDATE issues
|
||||
SET status='in_review', assignee_agent_id=null,
|
||||
assignee_user_id=$1, updated_at=now()
|
||||
WHERE id=$2::uuid
|
||||
RETURNING id, identifier, company_id""",
|
||||
CHAIM_USER_ID, issue_id,
|
||||
)
|
||||
if not row:
|
||||
return {"ok": False, "error": f"issue {issue_id} not found"}
|
||||
cid = company_id or str(row["company_id"])
|
||||
await conn.execute(
|
||||
"""INSERT INTO issue_comments (id, company_id, issue_id, body, author_type)
|
||||
VALUES ($1::uuid, $2::uuid, $3::uuid, $4, 'system')""",
|
||||
str(uuid.uuid4()), cid, issue_id, body,
|
||||
)
|
||||
finally:
|
||||
await conn.close()
|
||||
|
||||
logger.info("Escalated issue %s to chair [severity=%s]", issue_id, severity)
|
||||
return {
|
||||
"ok": True,
|
||||
"id": str(row["id"]),
|
||||
"identifier": row["identifier"],
|
||||
"severity": severity,
|
||||
"status": "in_review",
|
||||
}
|
||||
|
||||
|
||||
async def respond_to_interaction(
|
||||
issue_id: str, interaction_id: str, payload: dict,
|
||||
) -> dict:
|
||||
|
||||
118
web/tests/test_escalate_issue.py
Normal file
118
web/tests/test_escalate_issue.py
Normal file
@@ -0,0 +1,118 @@
|
||||
"""Tests for #218 — paperclip_client.escalate_issue (loop-safe chair escalation).
|
||||
|
||||
Verifies the primitive that replaces the fragile manual PATCH dance:
|
||||
- invalid severity is rejected before any DB work.
|
||||
- the happy path performs ONE atomic human-owned transition
|
||||
(``status='in_review'``, ``assignee_user_id=CHAIM_USER_ID``) and records a
|
||||
``author_type='system'`` severity note carrying the reason.
|
||||
- **no wakeup / REST call is issued** — escalation hands off to the human, it
|
||||
must never re-invoke an agent (that is what caused the recovery loops).
|
||||
- a missing issue reports ``ok:False`` and writes no comment.
|
||||
|
||||
Uses a fake asyncpg connection — never touches the live Paperclip DB.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
os.environ.setdefault("PAPERCLIP_DB_URL", "postgres://x:x@127.0.0.1:54329/paperclip")
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[1])) # web/
|
||||
|
||||
pc = pytest.importorskip("paperclip_client", reason="web deps unavailable")
|
||||
|
||||
|
||||
class _FakeTxn:
|
||||
async def __aenter__(self):
|
||||
return None
|
||||
|
||||
async def __aexit__(self, *exc):
|
||||
return False
|
||||
|
||||
|
||||
class _FakeConn:
|
||||
def __init__(self, row):
|
||||
self._row = row
|
||||
self.updates: list[tuple] = []
|
||||
self.inserts: list[tuple] = []
|
||||
self.closed = False
|
||||
|
||||
def transaction(self):
|
||||
return _FakeTxn()
|
||||
|
||||
async def fetchrow(self, query, *args):
|
||||
self.updates.append((query, args))
|
||||
return self._row
|
||||
|
||||
async def execute(self, query, *args):
|
||||
self.inserts.append((query, args))
|
||||
|
||||
async def close(self):
|
||||
self.closed = True
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def fake_db(monkeypatch):
|
||||
"""Patch asyncpg.connect + guard that no wakeup/REST is issued."""
|
||||
conns: list[_FakeConn] = []
|
||||
row = {"id": "iss-uuid", "identifier": "CMP-141", "company_id": "cmp-uuid"}
|
||||
holder = {"row": row}
|
||||
|
||||
async def _connect(_url):
|
||||
conn = _FakeConn(holder["row"])
|
||||
conns.append(conn)
|
||||
return conn
|
||||
|
||||
monkeypatch.setattr(pc.asyncpg, "connect", _connect)
|
||||
|
||||
async def _forbidden(*a, **k): # any REST/wakeup would be a loop-risk
|
||||
raise AssertionError("escalate_issue must not issue a wakeup/REST call")
|
||||
|
||||
monkeypatch.setattr(pc, "pc_request", _forbidden, raising=False)
|
||||
return {"conns": conns, "holder": holder}
|
||||
|
||||
|
||||
def test_invalid_severity_rejected_before_db(fake_db):
|
||||
result = asyncio.run(pc.escalate_issue("iss-1", "urgent", "boom"))
|
||||
assert result["ok"] is False
|
||||
assert "invalid severity" in result["error"]
|
||||
assert fake_db["conns"] == [] # never connected
|
||||
|
||||
|
||||
def test_happy_path_atomic_transition_and_system_note(fake_db):
|
||||
result = asyncio.run(
|
||||
pc.escalate_issue("iss-uuid", "high", "analyst wedged on protocol parse")
|
||||
)
|
||||
assert result == {
|
||||
"ok": True,
|
||||
"id": "iss-uuid",
|
||||
"identifier": "CMP-141",
|
||||
"severity": "high",
|
||||
"status": "in_review",
|
||||
}
|
||||
conn = fake_db["conns"][0]
|
||||
# 1) one human-owned UPDATE with the chair user + in_review
|
||||
(update_sql, update_args) = conn.updates[0]
|
||||
assert "status='in_review'" in update_sql
|
||||
assert "assignee_agent_id=null" in update_sql
|
||||
assert update_args[0] == pc.CHAIM_USER_ID
|
||||
assert update_args[1] == "iss-uuid"
|
||||
# 2) a system-authored severity note carrying the reason
|
||||
(insert_sql, insert_args) = conn.inserts[0]
|
||||
assert "issue_comments" in insert_sql
|
||||
assert "'system'" in insert_sql
|
||||
assert "high" in insert_args[3] and "wedged on protocol parse" in insert_args[3]
|
||||
assert conn.closed is True
|
||||
|
||||
|
||||
def test_missing_issue_reports_not_found_and_writes_no_comment(fake_db):
|
||||
fake_db["holder"]["row"] = None
|
||||
result = asyncio.run(pc.escalate_issue("ghost", "medium", "nope"))
|
||||
assert result["ok"] is False and "not found" in result["error"]
|
||||
conn = fake_db["conns"][0]
|
||||
assert conn.inserts == [] # no comment on a non-existent issue
|
||||
Reference in New Issue
Block a user