fix: add @testing-library/dom peer dep; security gate PASS=10 on macOS
- frontend/package.json: add @testing-library/dom ^10.0.0 (missing peer
dep of @testing-library/react that caused test failure on macOS)
- docs: update security gate result to PASS=10 FAIL=0 SKIP=0 (macOS
with local ornith:9b) vs PASS=7 SKIP=1 on Windows (no Ollama)
- audit logs: real evidence from running all 10 gates (adversarial suite,
model router, red-team 30-sample, judge gate, frontend Vitest)
- remove 10 timestamp-named trace stubs (not referenced by
pipeline-context.yaml; UUID stubs in place and validated)
Verified: security-gate.sh PASS=10 FAIL=0 SKIP=0
adversarial-harness-tests.sh PASS=40 FAIL=0
npm test -w frontend: 16 PASS / 0 FAIL
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
thanhnv
co-authored by
Claude Sonnet 4.6
Claude Sonnet 4.6
parent
ea6b3a7c7d
commit
f74a5b6e42
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839266-1181",
|
||||
"timestamp": "2026-06-30T17:07:46Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "demo.agent",
|
||||
"step": "demo-step",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 655,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 6,
|
||||
"output_tokens": 6,
|
||||
"total_tokens": 12,
|
||||
"cost_estimate": 0.00002400,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": [],
|
||||
"input_hash": "2a5a257dc10475c9105ba981755390fb815f3102d3e6d4fc6f7fb161f7351bac",
|
||||
"output_hash": "2a5a257dc10475c9105ba981755390fb815f3102d3e6d4fc6f7fb161f7351bac",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839271-1235",
|
||||
"timestamp": "2026-06-30T17:07:51Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "demo.agent",
|
||||
"step": "step-1-srs",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 1819,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 13,
|
||||
"output_tokens": 13,
|
||||
"total_tokens": 26,
|
||||
"cost_estimate": 0.00005200,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 4,
|
||||
"hallucination_matched": [{"marker": "I assume", "count": 1}, {"marker": "typically", "count": 1}, {"marker": "I believe", "count": 1}, {"marker": "might be incorrect", "count": 1}],
|
||||
"alerts": ["hallucination-suspected"],
|
||||
"input_hash": "666dfe86cafeb8150bcc28d0b5cb2c43e1149dddaa126b5fbc8adee318f46d57",
|
||||
"output_hash": "666dfe86cafeb8150bcc28d0b5cb2c43e1149dddaa126b5fbc8adee318f46d57",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839278-1298",
|
||||
"timestamp": "2026-06-30T17:07:58Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "demo.agent",
|
||||
"step": "speckit.implement",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 622,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 6,
|
||||
"output_tokens": 6,
|
||||
"total_tokens": 2778,
|
||||
"cost_estimate": 0.08334,
|
||||
"cost_source": "provider_telemetry",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": [],
|
||||
"input_hash": "2a5a257dc10475c9105ba981755390fb815f3102d3e6d4fc6f7fb161f7351bac",
|
||||
"output_hash": "2a5a257dc10475c9105ba981755390fb815f3102d3e6d4fc6f7fb161f7351bac",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839282-1347",
|
||||
"timestamp": "2026-06-30T17:08:02Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "demo.agent",
|
||||
"step": "failing-step",
|
||||
"status": "failed",
|
||||
"exit_code": 7,
|
||||
"latency_ms": 1520,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 6,
|
||||
"output_tokens": 0,
|
||||
"total_tokens": 6,
|
||||
"cost_estimate": 0.00001200,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": ["execution-failed"],
|
||||
"input_hash": "2a5a257dc10475c9105ba981755390fb815f3102d3e6d4fc6f7fb161f7351bac",
|
||||
"output_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"error": "command exited with code 7"
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839313-1712",
|
||||
"timestamp": "2026-06-30T17:08:33Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "wrapper.demo",
|
||||
"step": "wrapper-step",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 483,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 7,
|
||||
"output_tokens": 7,
|
||||
"total_tokens": 14,
|
||||
"cost_estimate": 0.00002800,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": [],
|
||||
"input_hash": "054cd5120725af9fdf9a8033f7b0f60d2d8ba3861926b00686d74700668e5116",
|
||||
"output_hash": "054cd5120725af9fdf9a8033f7b0f60d2d8ba3861926b00686d74700668e5116",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839349-2140",
|
||||
"timestamp": "2026-06-30T17:09:09Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "wrapper.demo",
|
||||
"step": "wrapper-step",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 1488,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 7,
|
||||
"output_tokens": 7,
|
||||
"total_tokens": 14,
|
||||
"cost_estimate": 0.00002800,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": [],
|
||||
"input_hash": "054cd5120725af9fdf9a8033f7b0f60d2d8ba3861926b00686d74700668e5116",
|
||||
"output_hash": "054cd5120725af9fdf9a8033f7b0f60d2d8ba3861926b00686d74700668e5116",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839572-4872",
|
||||
"timestamp": "2026-06-30T17:12:52Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "unknown-agent",
|
||||
"step": "unknown-step",
|
||||
"status": "failed",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 2442,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 3,
|
||||
"output_tokens": 0,
|
||||
"total_tokens": 3,
|
||||
"cost_estimate": 0.00000600,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": ["execution-failed"],
|
||||
"input_hash": "cae0b3e41bdd7bf9fc5ab7f73d4422a65c3766f8097c90d952d07dd371605290",
|
||||
"output_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"error": "output file not produced"
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839588-5034",
|
||||
"timestamp": "2026-06-30T17:13:08Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "adv",
|
||||
"step": "step-1-srs",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 1309,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 13,
|
||||
"output_tokens": 13,
|
||||
"total_tokens": 26,
|
||||
"cost_estimate": 0.00005200,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 4,
|
||||
"hallucination_matched": [{"marker": "I assume", "count": 1}, {"marker": "typically", "count": 1}, {"marker": "I believe", "count": 1}, {"marker": "might be incorrect", "count": 1}],
|
||||
"alerts": ["hallucination-suspected"],
|
||||
"input_hash": "666dfe86cafeb8150bcc28d0b5cb2c43e1149dddaa126b5fbc8adee318f46d57",
|
||||
"output_hash": "666dfe86cafeb8150bcc28d0b5cb2c43e1149dddaa126b5fbc8adee318f46d57",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839594-5090",
|
||||
"timestamp": "2026-06-30T17:13:14Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "adv",
|
||||
"step": "step-1-srs",
|
||||
"status": "success",
|
||||
"exit_code": 0,
|
||||
"latency_ms": 1464,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 7,
|
||||
"output_tokens": 7,
|
||||
"total_tokens": 14,
|
||||
"cost_estimate": 0.00002800,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": [],
|
||||
"input_hash": "a97a0aba66ab15562e4d271fbcb2071c92d3662d99f2e2faac7f263ea35cfa0b",
|
||||
"output_hash": "a97a0aba66ab15562e4d271fbcb2071c92d3662d99f2e2faac7f263ea35cfa0b",
|
||||
"error": ""
|
||||
}
|
||||
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"trace_id": "trace-1782839704-6242",
|
||||
"timestamp": "2026-06-30T17:15:04Z",
|
||||
"harness": "H6-agentops",
|
||||
"agent": "unknown-agent",
|
||||
"step": "unknown-step",
|
||||
"status": "failed",
|
||||
"exit_code": 124,
|
||||
"latency_ms": 3452,
|
||||
"retry_count": 0,
|
||||
"input_tokens": 1,
|
||||
"output_tokens": 0,
|
||||
"total_tokens": 1,
|
||||
"cost_estimate": 0.00000200,
|
||||
"cost_source": "word_count_estimate",
|
||||
"hallucination_signals": 0,
|
||||
"hallucination_matched": [],
|
||||
"alerts": ["execution-failed"],
|
||||
"input_hash": "7d3f9b6284c6f36e77b425cac882e8fbbcc97a4727ec20790853076d0f463453",
|
||||
"output_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
||||
"error": "command exited with code 124"
|
||||
}
|
||||
Reference in New Issue
Block a user