@raishin/vanguard-frontier-agentic 3.17.0 → 3.18.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +2 -2
- package/.claude-plugin/plugin.json +2 -1
- package/.cursor-plugin/plugin.json +2 -1
- package/.github/plugin/marketplace.json +1 -1
- package/README.md +11 -11
- package/agents/AGENTS.md +1 -1
- package/agents/README.md +2 -2
- package/agents/gcp/README.md +1 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/AGENT.md +129 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/claude-code.agent.md +119 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/codex.toml +126 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/copilot.agent.md +124 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/cursor.agent.md +119 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/gemini.agent.md +125 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/kiro-cli.agent.json +5 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/harnesses/kiro-ide.agent.md +118 -0
- package/agents/gcp/gcp-agent-runtime-review-agent/metadata.json +51 -0
- package/catalog/agents.json +41 -0
- package/catalog/asset-integrity.json +155 -50
- package/catalog/install-roles.json +2 -0
- package/catalog/model-assignments.json +33 -0
- package/catalog/skill-manifest.json +62 -15
- package/catalog/skills.json +37 -0
- package/package.json +1 -1
- package/plugins/vanguard-frontier-agentic/.codex-plugin/plugin.json +1 -1
- package/powers/vanguard-gcp/POWER.md +1 -1
- package/skills/cross-functional/agentic-board-protocol/SKILL.md +1 -1
- package/skills/cross-functional/agentic-board-protocol/references/handoff-envelope.md +1 -0
- package/skills/cross-functional/agentic-board-protocol/references/stop-conditions.md +1 -1
- package/skills/cross-functional/agentic-security-review/SKILL.md +3 -2
- package/skills/cross-functional/agentic-system-architecture-review/SKILL.md +3 -2
- package/skills/gcp/README.md +2 -1
- package/skills/gcp/gcp-agent-runtime-review/SKILL.md +98 -0
- package/skills/gcp/gcp-agent-runtime-review/metadata.json +37 -0
- package/skills/gcp/gcp-agent-runtime-review/references/adk-runtime-controls.md +77 -0
- package/skills/gcp/gcp-agent-runtime-review/references/deployment-and-lifecycle.md +63 -0
- package/skills/gcp/gcp-agent-runtime-review/references/identity-and-network-boundaries.md +52 -0
- package/skills/gcp/gcp-agent-runtime-review/references/official-sources.md +40 -0
- package/skills/gcp/gcp-agent-runtime-review/references/verification-and-evaluations.md +43 -0
- package/skills/gcp/gcp-agent-runtime-review/references/workflow-and-output.md +48 -0
- package/skills/gcp/gcp-maestro/SKILL.md +2 -1
- package/tests/agentic-board-suite/_build_fixtures.py +56 -1
- package/tests/agentic-board-suite/agentic_board_rules.py +25 -0
- package/tests/agentic-board-suite/fixtures/invalid/DR-CHALLENGE-COMPLETE--hard-gate-left-behind-by-proposer-swap.json +22 -22
- package/tests/agentic-board-suite/fixtures/invalid/DR-ONE-REQUEST--superseding-request-from-another-proposer.json +25 -25
- package/tests/agentic-board-suite/fixtures/invalid/DR-RISK-CARRIED--concurrent-higher-tier-envelope.json +16 -16
- package/tests/agentic-board-suite/fixtures/invalid/DRC-HARD-GATE-ACCEPTANCE--withdrawal-on-another-proposers-revision.json +25 -25
- package/tests/agentic-board-suite/fixtures/invalid/HO-ATTEN-FANOUT-BUDGET--siblings-overdraw-pool.json +246 -0
- package/tests/agentic-board-suite/fixtures/valid/v01x-fanout-fills-pool-exactly.json +243 -0
- package/tests/agentic-board-suite/fixtures/valid/v11x-designated-challenge-first-answer-over-cap.json +25 -25
- package/tests/agentic-board-suite/test_agentic_board.py +11 -0
- package/tests/fixtures/README.md +1 -1
- package/tests/fixtures/gcp-maestro-routing/expected/045-happy-agent-runtime-review.json +6 -0
- package/tests/fixtures/gcp-maestro-routing/expected/046-happy-agent-runtime-review-legacy-name.json +6 -0
- package/tests/fixtures/gcp-maestro-routing/expected/047-happy-agent-runtime-review-sdk-migration.json +6 -0
- package/tests/fixtures/gcp-maestro-routing/expected/adv-liveguard-07-agent-runtime-deletion.json +6 -0
- package/tests/fixtures/gcp-maestro-routing/expected/adv-scope-agent-runtime-vs-training.json +6 -0
- package/tests/fixtures/gcp-maestro-routing/inputs/045-happy-agent-runtime-review.json +7 -0
- package/tests/fixtures/gcp-maestro-routing/inputs/046-happy-agent-runtime-review-legacy-name.json +8 -0
- package/tests/fixtures/gcp-maestro-routing/inputs/047-happy-agent-runtime-review-sdk-migration.json +8 -0
- package/tests/fixtures/gcp-maestro-routing/inputs/adv-liveguard-07-agent-runtime-deletion.json +7 -0
- package/tests/fixtures/gcp-maestro-routing/inputs/adv-scope-agent-runtime-vs-training.json +7 -0
- package/tests/fixtures/gcp-maestro-routing/taxonomy.json +15 -0
|
@@ -0,0 +1,243 @@
|
|
|
1
|
+
{
|
|
2
|
+
"description": "Valid variant of v01: fanout fills pool exactly.",
|
|
3
|
+
"messages": [
|
|
4
|
+
{
|
|
5
|
+
"schema_version": "1.0.0",
|
|
6
|
+
"message_type": "delegate",
|
|
7
|
+
"task_id": "v01-m1",
|
|
8
|
+
"correlation_id": "v01-corr",
|
|
9
|
+
"parent_task_id": null,
|
|
10
|
+
"hop_count": 0,
|
|
11
|
+
"max_hops": 8,
|
|
12
|
+
"sent_at": "2026-10-01T09:01:00Z",
|
|
13
|
+
"source": {
|
|
14
|
+
"kind": "principal",
|
|
15
|
+
"subject": "subject:corp-idp:7c1e9a40b2d35f68",
|
|
16
|
+
"role": "platform-owner"
|
|
17
|
+
},
|
|
18
|
+
"destination": {
|
|
19
|
+
"kind": "agent",
|
|
20
|
+
"id": "agentic-system-architecture-review-agent"
|
|
21
|
+
},
|
|
22
|
+
"objective": "Assess whether a single tool-using agent or a deterministic workflow fits a read-only knowledge-base Q&A assistant.",
|
|
23
|
+
"input_schema_version": "1.0.0",
|
|
24
|
+
"subject_risk_tier": "R0",
|
|
25
|
+
"data_classification": "internal",
|
|
26
|
+
"materiality_flags": [],
|
|
27
|
+
"authorized_actions": [
|
|
28
|
+
"read",
|
|
29
|
+
"analyze",
|
|
30
|
+
"recommend",
|
|
31
|
+
"challenge",
|
|
32
|
+
"escalate"
|
|
33
|
+
],
|
|
34
|
+
"do_not_do_list": [
|
|
35
|
+
"Do not execute, deploy, or mutate any system",
|
|
36
|
+
"Do not request, store, or echo credentials, tokens, or secrets",
|
|
37
|
+
"Do not record an approval on behalf of a human"
|
|
38
|
+
],
|
|
39
|
+
"evidence_refs": [
|
|
40
|
+
{
|
|
41
|
+
"ref": "repo:docs/design/v01.md#section-1",
|
|
42
|
+
"label": "repo-evidence"
|
|
43
|
+
}
|
|
44
|
+
],
|
|
45
|
+
"missing_evidence": [],
|
|
46
|
+
"budget": {
|
|
47
|
+
"currency": "USD",
|
|
48
|
+
"limit_tool_calls": 40,
|
|
49
|
+
"spent_tool_calls": 0,
|
|
50
|
+
"limit_tokens": 400000,
|
|
51
|
+
"spent_tokens": 0,
|
|
52
|
+
"limit_cost_minor": 2000,
|
|
53
|
+
"spent_cost_minor": 0
|
|
54
|
+
},
|
|
55
|
+
"deadline": "2026-10-08T17:00:00Z",
|
|
56
|
+
"approval_state": "not-required",
|
|
57
|
+
"expected_output_schema": "agentic-review-verdict/1.0.0",
|
|
58
|
+
"status": "dispatched",
|
|
59
|
+
"stop_reasons": [],
|
|
60
|
+
"synthetic": true
|
|
61
|
+
},
|
|
62
|
+
{
|
|
63
|
+
"schema_version": "1.0.0",
|
|
64
|
+
"message_type": "return",
|
|
65
|
+
"task_id": "v01-m2",
|
|
66
|
+
"correlation_id": "v01-corr",
|
|
67
|
+
"parent_task_id": "v01-m1",
|
|
68
|
+
"hop_count": 1,
|
|
69
|
+
"max_hops": 8,
|
|
70
|
+
"sent_at": "2026-10-01T09:02:00Z",
|
|
71
|
+
"source": {
|
|
72
|
+
"kind": "agent",
|
|
73
|
+
"id": "agentic-system-architecture-review-agent"
|
|
74
|
+
},
|
|
75
|
+
"destination": {
|
|
76
|
+
"kind": "principal",
|
|
77
|
+
"subject": "subject:corp-idp:7c1e9a40b2d35f68",
|
|
78
|
+
"role": "platform-owner"
|
|
79
|
+
},
|
|
80
|
+
"objective": "Return the pattern-selection verdict for the knowledge-base assistant review.",
|
|
81
|
+
"input_schema_version": "1.0.0",
|
|
82
|
+
"subject_risk_tier": "R0",
|
|
83
|
+
"data_classification": "internal",
|
|
84
|
+
"materiality_flags": [],
|
|
85
|
+
"authorized_actions": [
|
|
86
|
+
"read",
|
|
87
|
+
"analyze",
|
|
88
|
+
"recommend",
|
|
89
|
+
"challenge",
|
|
90
|
+
"escalate"
|
|
91
|
+
],
|
|
92
|
+
"do_not_do_list": [
|
|
93
|
+
"Do not execute, deploy, or mutate any system",
|
|
94
|
+
"Do not request, store, or echo credentials, tokens, or secrets",
|
|
95
|
+
"Do not record an approval on behalf of a human"
|
|
96
|
+
],
|
|
97
|
+
"evidence_refs": [
|
|
98
|
+
{
|
|
99
|
+
"ref": "repo:docs/design/v01.md#section-1",
|
|
100
|
+
"label": "repo-evidence"
|
|
101
|
+
}
|
|
102
|
+
],
|
|
103
|
+
"missing_evidence": [],
|
|
104
|
+
"budget": {
|
|
105
|
+
"currency": "USD",
|
|
106
|
+
"limit_tool_calls": 40,
|
|
107
|
+
"spent_tool_calls": 6,
|
|
108
|
+
"limit_tokens": 400000,
|
|
109
|
+
"spent_tokens": 30000,
|
|
110
|
+
"limit_cost_minor": 2000,
|
|
111
|
+
"spent_cost_minor": 120
|
|
112
|
+
},
|
|
113
|
+
"deadline": "2026-10-08T17:00:00Z",
|
|
114
|
+
"approval_state": "not-required",
|
|
115
|
+
"expected_output_schema": "agentic-review-verdict/1.0.0",
|
|
116
|
+
"status": "completed",
|
|
117
|
+
"stop_reasons": [],
|
|
118
|
+
"synthetic": true,
|
|
119
|
+
"verdict": {
|
|
120
|
+
"outcome": "simpler-pattern-sufficient",
|
|
121
|
+
"summary": "A single retrieval agent with a fixed tool list meets the requirement; multi-agent adds handoff cost without separation-of-duties benefit.",
|
|
122
|
+
"conditions": [
|
|
123
|
+
"Bound tool calls per request",
|
|
124
|
+
"Log retrieval sources per answer"
|
|
125
|
+
]
|
|
126
|
+
}
|
|
127
|
+
},
|
|
128
|
+
{
|
|
129
|
+
"schema_version": "1.0.0",
|
|
130
|
+
"message_type": "delegate",
|
|
131
|
+
"task_id": "v01-m3",
|
|
132
|
+
"correlation_id": "v01-corr",
|
|
133
|
+
"parent_task_id": "v01-m1",
|
|
134
|
+
"hop_count": 1,
|
|
135
|
+
"max_hops": 8,
|
|
136
|
+
"sent_at": "2026-10-01T09:01:30Z",
|
|
137
|
+
"source": {
|
|
138
|
+
"kind": "agent",
|
|
139
|
+
"id": "agentic-system-architecture-review-agent"
|
|
140
|
+
},
|
|
141
|
+
"destination": {
|
|
142
|
+
"kind": "agent",
|
|
143
|
+
"id": "agentic-security-review-agent"
|
|
144
|
+
},
|
|
145
|
+
"objective": "Assess whether the retrieval index exposes documents across access groups.",
|
|
146
|
+
"input_schema_version": "1.0.0",
|
|
147
|
+
"subject_risk_tier": "R0",
|
|
148
|
+
"data_classification": "internal",
|
|
149
|
+
"materiality_flags": [],
|
|
150
|
+
"authorized_actions": [
|
|
151
|
+
"read",
|
|
152
|
+
"analyze",
|
|
153
|
+
"recommend",
|
|
154
|
+
"challenge",
|
|
155
|
+
"escalate"
|
|
156
|
+
],
|
|
157
|
+
"do_not_do_list": [
|
|
158
|
+
"Do not execute, deploy, or mutate any system",
|
|
159
|
+
"Do not request, store, or echo credentials, tokens, or secrets",
|
|
160
|
+
"Do not record an approval on behalf of a human"
|
|
161
|
+
],
|
|
162
|
+
"evidence_refs": [
|
|
163
|
+
{
|
|
164
|
+
"ref": "repo:docs/design/v01.md#section-1",
|
|
165
|
+
"label": "repo-evidence"
|
|
166
|
+
}
|
|
167
|
+
],
|
|
168
|
+
"missing_evidence": [],
|
|
169
|
+
"budget": {
|
|
170
|
+
"currency": "USD",
|
|
171
|
+
"limit_tool_calls": 20,
|
|
172
|
+
"spent_tool_calls": 2,
|
|
173
|
+
"limit_tokens": 200000,
|
|
174
|
+
"spent_tokens": 10000,
|
|
175
|
+
"limit_cost_minor": 1000,
|
|
176
|
+
"spent_cost_minor": 40
|
|
177
|
+
},
|
|
178
|
+
"deadline": "2026-10-08T17:00:00Z",
|
|
179
|
+
"approval_state": "not-required",
|
|
180
|
+
"expected_output_schema": "agentic-review-verdict/1.0.0",
|
|
181
|
+
"status": "dispatched",
|
|
182
|
+
"stop_reasons": [],
|
|
183
|
+
"synthetic": true
|
|
184
|
+
},
|
|
185
|
+
{
|
|
186
|
+
"schema_version": "1.0.0",
|
|
187
|
+
"message_type": "delegate",
|
|
188
|
+
"task_id": "v01-m4",
|
|
189
|
+
"correlation_id": "v01-corr",
|
|
190
|
+
"parent_task_id": "v01-m1",
|
|
191
|
+
"hop_count": 1,
|
|
192
|
+
"max_hops": 8,
|
|
193
|
+
"sent_at": "2026-10-01T09:01:40Z",
|
|
194
|
+
"source": {
|
|
195
|
+
"kind": "agent",
|
|
196
|
+
"id": "agentic-system-architecture-review-agent"
|
|
197
|
+
},
|
|
198
|
+
"destination": {
|
|
199
|
+
"kind": "agent",
|
|
200
|
+
"id": "agentic-security-review-agent"
|
|
201
|
+
},
|
|
202
|
+
"objective": "Assess whether answer logging stores personal data beyond retention.",
|
|
203
|
+
"input_schema_version": "1.0.0",
|
|
204
|
+
"subject_risk_tier": "R0",
|
|
205
|
+
"data_classification": "internal",
|
|
206
|
+
"materiality_flags": [],
|
|
207
|
+
"authorized_actions": [
|
|
208
|
+
"read",
|
|
209
|
+
"analyze",
|
|
210
|
+
"recommend",
|
|
211
|
+
"challenge",
|
|
212
|
+
"escalate"
|
|
213
|
+
],
|
|
214
|
+
"do_not_do_list": [
|
|
215
|
+
"Do not execute, deploy, or mutate any system",
|
|
216
|
+
"Do not request, store, or echo credentials, tokens, or secrets",
|
|
217
|
+
"Do not record an approval on behalf of a human"
|
|
218
|
+
],
|
|
219
|
+
"evidence_refs": [
|
|
220
|
+
{
|
|
221
|
+
"ref": "repo:docs/design/v01.md#section-1",
|
|
222
|
+
"label": "repo-evidence"
|
|
223
|
+
}
|
|
224
|
+
],
|
|
225
|
+
"missing_evidence": [],
|
|
226
|
+
"budget": {
|
|
227
|
+
"currency": "USD",
|
|
228
|
+
"limit_tool_calls": 22,
|
|
229
|
+
"spent_tool_calls": 4,
|
|
230
|
+
"limit_tokens": 210000,
|
|
231
|
+
"spent_tokens": 20000,
|
|
232
|
+
"limit_cost_minor": 1040,
|
|
233
|
+
"spent_cost_minor": 80
|
|
234
|
+
},
|
|
235
|
+
"deadline": "2026-10-08T17:00:00Z",
|
|
236
|
+
"approval_state": "not-required",
|
|
237
|
+
"expected_output_schema": "agentic-review-verdict/1.0.0",
|
|
238
|
+
"status": "dispatched",
|
|
239
|
+
"stop_reasons": [],
|
|
240
|
+
"synthetic": true
|
|
241
|
+
}
|
|
242
|
+
]
|
|
243
|
+
}
|
|
@@ -110,11 +110,11 @@
|
|
|
110
110
|
"missing_evidence": [],
|
|
111
111
|
"budget": {
|
|
112
112
|
"currency": "USD",
|
|
113
|
-
"limit_tool_calls":
|
|
113
|
+
"limit_tool_calls": 32,
|
|
114
114
|
"spent_tool_calls": 8,
|
|
115
|
-
"limit_tokens":
|
|
115
|
+
"limit_tokens": 360000,
|
|
116
116
|
"spent_tokens": 40000,
|
|
117
|
-
"limit_cost_minor":
|
|
117
|
+
"limit_cost_minor": 1840,
|
|
118
118
|
"spent_cost_minor": 160
|
|
119
119
|
},
|
|
120
120
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -169,11 +169,11 @@
|
|
|
169
169
|
"missing_evidence": [],
|
|
170
170
|
"budget": {
|
|
171
171
|
"currency": "USD",
|
|
172
|
-
"limit_tool_calls":
|
|
172
|
+
"limit_tool_calls": 12,
|
|
173
173
|
"spent_tool_calls": 8,
|
|
174
|
-
"limit_tokens":
|
|
174
|
+
"limit_tokens": 60000,
|
|
175
175
|
"spent_tokens": 40000,
|
|
176
|
-
"limit_cost_minor":
|
|
176
|
+
"limit_cost_minor": 240,
|
|
177
177
|
"spent_cost_minor": 160
|
|
178
178
|
},
|
|
179
179
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -228,11 +228,11 @@
|
|
|
228
228
|
"missing_evidence": [],
|
|
229
229
|
"budget": {
|
|
230
230
|
"currency": "USD",
|
|
231
|
-
"limit_tool_calls":
|
|
231
|
+
"limit_tool_calls": 12,
|
|
232
232
|
"spent_tool_calls": 8,
|
|
233
|
-
"limit_tokens":
|
|
233
|
+
"limit_tokens": 60000,
|
|
234
234
|
"spent_tokens": 40000,
|
|
235
|
-
"limit_cost_minor":
|
|
235
|
+
"limit_cost_minor": 240,
|
|
236
236
|
"spent_cost_minor": 160
|
|
237
237
|
},
|
|
238
238
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -287,11 +287,11 @@
|
|
|
287
287
|
"missing_evidence": [],
|
|
288
288
|
"budget": {
|
|
289
289
|
"currency": "USD",
|
|
290
|
-
"limit_tool_calls":
|
|
290
|
+
"limit_tool_calls": 32,
|
|
291
291
|
"spent_tool_calls": 20,
|
|
292
|
-
"limit_tokens":
|
|
292
|
+
"limit_tokens": 360000,
|
|
293
293
|
"spent_tokens": 100000,
|
|
294
|
-
"limit_cost_minor":
|
|
294
|
+
"limit_cost_minor": 1840,
|
|
295
295
|
"spent_cost_minor": 400
|
|
296
296
|
},
|
|
297
297
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -356,11 +356,11 @@
|
|
|
356
356
|
"missing_evidence": [],
|
|
357
357
|
"budget": {
|
|
358
358
|
"currency": "USD",
|
|
359
|
-
"limit_tool_calls":
|
|
359
|
+
"limit_tool_calls": 32,
|
|
360
360
|
"spent_tool_calls": 20,
|
|
361
|
-
"limit_tokens":
|
|
361
|
+
"limit_tokens": 360000,
|
|
362
362
|
"spent_tokens": 100000,
|
|
363
|
-
"limit_cost_minor":
|
|
363
|
+
"limit_cost_minor": 1840,
|
|
364
364
|
"spent_cost_minor": 400
|
|
365
365
|
},
|
|
366
366
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -422,11 +422,11 @@
|
|
|
422
422
|
"missing_evidence": [],
|
|
423
423
|
"budget": {
|
|
424
424
|
"currency": "USD",
|
|
425
|
-
"limit_tool_calls":
|
|
425
|
+
"limit_tool_calls": 32,
|
|
426
426
|
"spent_tool_calls": 20,
|
|
427
|
-
"limit_tokens":
|
|
427
|
+
"limit_tokens": 360000,
|
|
428
428
|
"spent_tokens": 100000,
|
|
429
|
-
"limit_cost_minor":
|
|
429
|
+
"limit_cost_minor": 1840,
|
|
430
430
|
"spent_cost_minor": 400
|
|
431
431
|
},
|
|
432
432
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -482,11 +482,11 @@
|
|
|
482
482
|
"missing_evidence": [],
|
|
483
483
|
"budget": {
|
|
484
484
|
"currency": "USD",
|
|
485
|
-
"limit_tool_calls":
|
|
485
|
+
"limit_tool_calls": 32,
|
|
486
486
|
"spent_tool_calls": 22,
|
|
487
|
-
"limit_tokens":
|
|
487
|
+
"limit_tokens": 360000,
|
|
488
488
|
"spent_tokens": 110000,
|
|
489
|
-
"limit_cost_minor":
|
|
489
|
+
"limit_cost_minor": 1840,
|
|
490
490
|
"spent_cost_minor": 440
|
|
491
491
|
},
|
|
492
492
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -564,11 +564,11 @@
|
|
|
564
564
|
"missing_evidence": [],
|
|
565
565
|
"budget": {
|
|
566
566
|
"currency": "USD",
|
|
567
|
-
"limit_tool_calls":
|
|
567
|
+
"limit_tool_calls": 32,
|
|
568
568
|
"spent_tool_calls": 22,
|
|
569
|
-
"limit_tokens":
|
|
569
|
+
"limit_tokens": 360000,
|
|
570
570
|
"spent_tokens": 110000,
|
|
571
|
-
"limit_cost_minor":
|
|
571
|
+
"limit_cost_minor": 1840,
|
|
572
572
|
"spent_cost_minor": 440
|
|
573
573
|
},
|
|
574
574
|
"deadline": "2026-10-08T17:00:00Z",
|
|
@@ -579,7 +579,7 @@
|
|
|
579
579
|
"synthetic": true,
|
|
580
580
|
"decision_record": {
|
|
581
581
|
"request_task_id": "v11-m10",
|
|
582
|
-
"request_digest": "sha256:
|
|
582
|
+
"request_digest": "sha256:1646ef9bc193a9017fca9e7616b16754ec869b06ec241498ccc036b61b3e7204",
|
|
583
583
|
"outcome": "reject",
|
|
584
584
|
"decided_by": {
|
|
585
585
|
"kind": "principal",
|
|
@@ -302,6 +302,14 @@ class BoardInvariantTests(unittest.TestCase):
|
|
|
302
302
|
with self.subTest(skill=skill_id):
|
|
303
303
|
text = (ROOT / f"skills/cross-functional/{skill_id}/SKILL.md").read_text(encoding="utf-8")
|
|
304
304
|
self.assertRegex(text, r"(?m)^allowed-tools: Read Grep Glob$")
|
|
305
|
+
# allowed-tools only pre-approves; disallowed-tools removes tools while the skill is active
|
|
306
|
+
# (https://code.claude.com/docs/en/skills). The protocol skill stays unrestricted because
|
|
307
|
+
# principals author record sets and run the offline gate under it.
|
|
308
|
+
restrict = r"(?m)^disallowed-tools: Write Edit NotebookEdit Bash$"
|
|
309
|
+
if skill_id == "agentic-board-protocol":
|
|
310
|
+
self.assertNotRegex(text, r"(?m)^disallowed-tools:")
|
|
311
|
+
else:
|
|
312
|
+
self.assertRegex(text, restrict)
|
|
305
313
|
refs = sorted((ROOT / f"skills/cross-functional/{skill_id}/references").glob("*.md"))
|
|
306
314
|
self.assertTrue(1 <= len(refs) <= 5, "progressive disclosure: 1-5 topic references")
|
|
307
315
|
for ref in refs:
|
|
@@ -410,6 +418,9 @@ class TargetedMutantTests(unittest.TestCase):
|
|
|
410
418
|
("spent monotonic", 'cb[f"spent_{d}"] < pb[f"spent_{d}"]', 'cb[f"spent_{d}"] <= pb[f"spent_{d}"]'),
|
|
411
419
|
("record after request", 'if env["sent_at"] < request["sent_at"] or', 'if env["sent_at"] <= request["sent_at"] or'),
|
|
412
420
|
("destination tier", "not in DISPATCHABLE_TIERS", "in DISPATCHABLE_TIERS"),
|
|
421
|
+
("fan-out comparison", 'if headroom > pb[f"limit_{d}"]', 'if headroom >= pb[f"limit_{d}"]'),
|
|
422
|
+
("fan-out pool", '- max(b[f"spent_{d}"] for b in budgets)', '- min(b[f"spent_{d}"] for b in budgets)'),
|
|
423
|
+
("fan-out threshold", "if len(budgets) < 2:", "if len(budgets) < 3:"),
|
|
413
424
|
("one request", 'if len([r for r in requests if "supersedes_task_id" not in r["decision_request"]]) > 1:',
|
|
414
425
|
'if len([r for r in requests if "supersedes_task_id" not in r["decision_request"]]) > 2:'),
|
|
415
426
|
("counted round", 'rounds[c["task_id"]] = max(1, sum(1 for e in received if order.precedes(e, c)))',
|
package/tests/fixtures/README.md
CHANGED
|
@@ -65,5 +65,5 @@ The grader provides three structural guarantees:
|
|
|
65
65
|
## Numbers (current)
|
|
66
66
|
|
|
67
67
|
- <!-- count:global:maestros -->35<!-- /count --> maestros covered, one routing fixture directory each
|
|
68
|
-
- <!-- count:global:scenarios -->
|
|
68
|
+
- <!-- count:global:scenarios -->845<!-- /count --> scenarios validated
|
|
69
69
|
- enforced by `validate:maestro-routing`, one of the <!-- count:global:gates -->31<!-- /count --> `npm run validate` gates
|
|
@@ -1,6 +1,21 @@
|
|
|
1
1
|
{
|
|
2
2
|
"provider": "gcp",
|
|
3
3
|
"domains": {
|
|
4
|
+
"agent-runtime-review": {
|
|
5
|
+
"keywords": [
|
|
6
|
+
"agent runtime",
|
|
7
|
+
"agent engine",
|
|
8
|
+
"reasoning engine",
|
|
9
|
+
"reasoningengine",
|
|
10
|
+
"adk",
|
|
11
|
+
"agent development kit",
|
|
12
|
+
"adk deploy",
|
|
13
|
+
"agentplatform",
|
|
14
|
+
"memory bank",
|
|
15
|
+
"agent identity"
|
|
16
|
+
],
|
|
17
|
+
"agent": "gcp-agent-runtime-review-agent"
|
|
18
|
+
},
|
|
4
19
|
"alloydb-ai-developer": {
|
|
5
20
|
"keywords": [
|
|
6
21
|
"alloydb",
|