mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
4829f93a68
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.
87 lines
2.4 KiB
Python
87 lines
2.4 KiB
Python
"""bash-guard-hook.sh denies curl/wget against orchestrator/localhost.
|
|
|
|
The PreToolUse hook reads Claude Code's event JSON from stdin in the form
|
|
``{"tool_name": "Bash", "tool_input": {"command": "..."}}`` and exits with
|
|
code 2 to deny, 0 to allow. Tests wrap each command in that envelope.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
# tests/unit/scripts/test_bash_guard.py
|
|
# parents[0] = scripts
|
|
# parents[1] = unit
|
|
# parents[2] = tests
|
|
# parents[3] = <repo root>
|
|
GUARD = Path(__file__).parents[3] / "docker" / "scripts" / "bash-guard-hook.sh"
|
|
|
|
_DENIED = 2
|
|
_ALLOWED = 0
|
|
|
|
|
|
def _run(cmd: str) -> int:
|
|
payload = json.dumps({"tool_name": "Bash", "tool_input": {"command": cmd}})
|
|
result = subprocess.run(
|
|
[str(GUARD)],
|
|
input=payload,
|
|
capture_output=True,
|
|
text=True,
|
|
check=False,
|
|
)
|
|
return result.returncode
|
|
|
|
|
|
def test_blocks_internal_curl_to_orchestrator() -> None:
|
|
assert (
|
|
_run("curl http://roboco-orchestrator:8000/api/v2/flow/main_pm/delegate")
|
|
== _DENIED
|
|
)
|
|
|
|
|
|
def test_blocks_internal_curl_to_localhost() -> None:
|
|
assert _run("curl http://localhost:8000/api/v2/flow/developer/i_am_done") == _DENIED
|
|
|
|
|
|
def test_blocks_internal_curl_to_127() -> None:
|
|
assert _run("curl http://127.0.0.1:8000/api/health") == _DENIED
|
|
|
|
|
|
def test_blocks_scheme_less_curl_to_orchestrator() -> None:
|
|
assert _run("curl roboco-orchestrator:8000/api") != _ALLOWED
|
|
|
|
|
|
def test_blocks_scheme_less_curl_to_localhost() -> None:
|
|
assert _run("curl localhost:8000/api") != _ALLOWED
|
|
|
|
|
|
def test_blocks_scheme_less_curl_to_127() -> None:
|
|
assert _run("curl 127.0.0.1:8000/api") != _ALLOWED
|
|
|
|
|
|
def test_allows_external_curl_to_documentation() -> None:
|
|
assert _run("curl https://docs.python.org/3/") == _ALLOWED
|
|
|
|
|
|
def test_github_url_still_uses_github_specific_deny() -> None:
|
|
"""Existing GitHub deny rule must fire BEFORE the new gateway deny."""
|
|
payload = json.dumps(
|
|
{
|
|
"tool_name": "Bash",
|
|
"tool_input": {"command": "curl https://api.github.com/user"},
|
|
}
|
|
)
|
|
result = subprocess.run(
|
|
[str(GUARD)],
|
|
input=payload,
|
|
capture_output=True,
|
|
text=True,
|
|
check=False,
|
|
)
|
|
assert result.returncode != _ALLOWED
|
|
# The GitHub-specific message should appear, not the gateway message.
|
|
combined = (result.stdout + result.stderr).lower()
|
|
assert "github" in combined or "pat" in combined
|