Files
roboco/tests/unit/mcp_servers/test_do_server.py
T
Renn F 4829f93a68 fix(gateway): unblock task claim; full Phase 0/1/2 remediation
Resolves the 100% claim-failure rate introduced by the gateway rewrite
  (commit 62bda0c plus 78 follow-ups). Live smoke runs hit
  `404 /api/v2/flow/developer/...` on every dev verb plus a manifest
  fallback that silently exposed off-role verbs to PMs — confirmed
  firing simultaneously in NAS agent logs (be-dev-1, be-pm, main-pm).

  Audit reports under docs/internal/audit_2026_05_04/ catalogue 49
  defects across gateway, services, prompts, MCP transport, substrate,
  and tests (8 detail reports + master synthesis). Six smoking guns;
  three proven in production logs.

  Phase 0 — unblock claim:
  - URL prefix /api/v2/flow/dev → /developer; slug-map board roles
    (product_owner, head_marketing) → /board (D-01)
  - _i_will_work_on AttributeError on None across pending /
    needs_revision / claimed re-entry branches (D-02)
  - Seed last_heartbeat_at in _qa_or_doc_claim (D-03)
  - Drop misleading i_have_committed verb; dev flow uses commit() (D-04)
  - Manifest mount via compose; flow_server + do_server fail loud
    instead of exposing all-verbs fallback (D-12)
  - MCP _post() surfaces envelope body on 4xx so agents see remediate
    hints (D-13)
    on git failure so retries aren't blocked by half-state (S-01)

  Phase 1 — lifecycle stability:
  - _resolve_skill falls back to AgentTable.capabilities (D-06)
  - main_pm_complete uses kwargs for escalate_to_ceo (D-07)
  - i_am_done auto-runs submit_verification when in_progress (D-08)
  - active_claimant_id wired in claim/unclaim paths — single-claimant
    invariant now functional (D-05)
  - qa_pass/qa_fail assert claimed_by parity with qa_agent_id (D-18)
  - Prompt-drift sweep: fail() shape, i_am_done(task_id, notes),
    subtask cap (12 hard / 8 soft), error-code symbology rewritten in
    base.md + per-role anti-patterns (D-10/11/29/30/31, D-37)

  Phase 2 — invariants + architecture:
  - Real-DB integration test exercising claim → in_progress → commit
    → submit_for_qa → i_am_done → awaiting_qa (P2-1)
  - choreographer.py → package; 3 of 6 role mixins extracted
    (board, doc, qa). _impl.py 2,526 → 2,080 lines (-18%). Continuation
    plan in docs/internal/audit_2026_05_04/p2_2_decompose_plan.md (P2-2)
  - Closure guards consolidated via _subtasks_not_terminal_envelope (P2-3)
  - TaskService.unclaim_for_reaper routed through canonical
    _validate_and_set_status; in_progress → pending added to
    VALID_TRANSITIONS (P2-4)
  - Dead code removed: i_am_done_with_catchup verb, _run_catch_up helper
    (P2-5)
  - 6 state-machine invariants asserted via property test (P2-6)
  - attempt_id (uuid4) stamped on every gateway.rejected audit row (P2-7)
  - _reconcile_orphan_claims_on_startup rolls back tasks left CLAIMED
    with branch_name=NULL from prior crashes (P2-8)
  - scripts/regenerate_verb_tables.py introspects Pydantic schemas +
    role_config; compose_prompt injects per-role tables as a layer.
    Eliminates the prompt-drift class structurally (P2-9)

  Other:
  - D-48: orchestrator mounts host's ~/.claude.json when present so
    agents don't boot from backup recovery on every spawn
  - D-49: dev dispatcher rejects role-mismatched spawns (e.g. doc task
    assigned to dev agent)

  Tests: 553 pass · ruff + mypy clean. Live NAS smoke verification
  pending — needs the stack brought back up.
2026-05-04 23:43:55 +02:00

141 lines
4.8 KiB
Python

"""Tests for roboco-do MCP server."""
from __future__ import annotations
import json
import tempfile
from pathlib import Path
from unittest.mock import MagicMock, patch
import pytest
# Same pattern as test_flow_server: do_server now refuses to start without
# a manifest (audit P0-5 / D-12). The test fixture writes a stub manifest
# with the full do-tool superset; production manifests are role-scoped.
_DO_TEST_MANIFEST = {
"agent_id": "00000000-0000-0000-0000-000000000001",
"role": "developer",
"team": "backend",
"workspace_path": "/tmp/test",
"flow_tools": [],
"do_tools": ["commit", "note", "say", "dm", "notify", "evidence"],
"read_tools": [],
"write_tools": [],
"bash_allowed": True,
"subagent_allowed": False,
"subagent_model": None,
"env": {},
}
@pytest.fixture
def do_module(monkeypatch): # type: ignore[no-untyped-def]
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000001")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "developer")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
manifest_path = Path(tempfile.mkdtemp()) / "tool-manifest.json"
manifest_path.write_text(json.dumps(_DO_TEST_MANIFEST))
monkeypatch.setenv("ROBOCO_TOOL_MANIFEST_PATH", str(manifest_path))
import importlib
import roboco.mcp.do_server as srv
importlib.reload(srv)
return srv
def test_commit_posts_message_and_files(do_module): # type: ignore[no-untyped-def]
fake_client = MagicMock()
fake_client.__enter__.return_value = fake_client
fake_response = MagicMock()
fake_response.json.return_value = {"status": "in_progress", "task_id": "x"}
fake_client.post.return_value = fake_response
with patch("httpx.Client", return_value=fake_client):
result = do_module.commit("feat(api): add /healthz", files=["foo.py"])
assert result["status"] == "in_progress"
args, kwargs = fake_client.post.call_args
assert "/api/v2/do/commit" in args[0]
assert kwargs["json"] == {"message": "feat(api): add /healthz", "files": ["foo.py"]}
def test_note_default_scope_note(do_module): # type: ignore[no-untyped-def]
fake_client = MagicMock()
fake_client.__enter__.return_value = fake_client
fake_response = MagicMock()
fake_response.json.return_value = {"status": "noted"}
fake_client.post.return_value = fake_response
with patch("httpx.Client", return_value=fake_client):
do_module.note("hello world")
_args, kwargs = fake_client.post.call_args
assert kwargs["json"]["scope"] == "note"
def test_note_with_scope_reflect(do_module): # type: ignore[no-untyped-def]
fake_client = MagicMock()
fake_client.__enter__.return_value = fake_client
fake_response = MagicMock()
fake_response.json.return_value = {"status": "noted"}
fake_client.post.return_value = fake_response
with patch("httpx.Client", return_value=fake_client):
do_module.note("did x", scope="reflect")
_args, kwargs = fake_client.post.call_args
assert kwargs["json"]["scope"] == "reflect"
def test_say_posts_channel_and_text(do_module): # type: ignore[no-untyped-def]
fake_client = MagicMock()
fake_client.__enter__.return_value = fake_client
fake_response = MagicMock()
fake_response.json.return_value = {"status": "posted"}
fake_client.post.return_value = fake_response
with patch("httpx.Client", return_value=fake_client):
do_module.say("backend-cell", "hello")
_args, kwargs = fake_client.post.call_args
assert kwargs["json"] == {
"channel": "backend-cell",
"text": "hello",
"task_id": None,
}
def test_dm_posts_all_fields(do_module): # type: ignore[no-untyped-def]
fake_client = MagicMock()
fake_client.__enter__.return_value = fake_client
fake_response = MagicMock()
fake_response.json.return_value = {"status": "sent"}
fake_client.post.return_value = fake_response
with patch("httpx.Client", return_value=fake_client):
do_module.dm("be-qa", "review please", task_id="t1", skill="code_review")
_args, kwargs = fake_client.post.call_args
assert kwargs["json"] == {
"recipient": "be-qa",
"text": "review please",
"task_id": "t1",
"skill": "code_review",
}
def test_evidence_posts_task_id(do_module): # type: ignore[no-untyped-def]
fake_client = MagicMock()
fake_client.__enter__.return_value = fake_client
fake_response = MagicMock()
fake_response.json.return_value = {"status": "ok", "evidence": {}}
fake_client.post.return_value = fake_response
with patch("httpx.Client", return_value=fake_client):
do_module.evidence("task-uuid")
args, kwargs = fake_client.post.call_args
assert "/api/v2/do/evidence" in args[0]
assert kwargs["json"] == {"task_id": "task-uuid"}