thumbgate 1.29.2 → 1.31.0
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/plugin.json +1 -1
- package/.well-known/mcp/server-card.json +1 -1
- package/README.md +54 -16
- package/adapters/claude/.mcp.json +2 -2
- package/adapters/forge/forge.yaml +3 -3
- package/adapters/mcp/server-stdio.js +143 -14
- package/adapters/opencode/opencode.json +1 -1
- package/bench/observability-eval-suite.json +2 -2
- package/bin/cli.js +154 -36
- package/config/evals/generation-quality-golden.json +95 -0
- package/config/evals/rag-answer-quality-golden.json +91 -0
- package/config/evals/retrieval-hybrid-ablation.json +66 -0
- package/config/evals/retrieval-ranking-golden.json +522 -0
- package/config/gates/default.json +217 -50
- package/config/mcp-allowlists.json +215 -185
- package/config/model-tiers.json +7 -2
- package/config/post-deploy-marketing-pages.json +26 -1
- package/glama.json +6 -0
- package/package.json +94 -11
- package/public/architecture.html +130 -0
- package/public/assets/diagrams/agent-integration.png +0 -0
- package/public/assets/diagrams/before-after.svg +22 -0
- package/public/assets/diagrams/decision.svg +36 -0
- package/public/assets/diagrams/feedback-pipeline.png +0 -0
- package/public/assets/diagrams/hero-thumbs.svg +68 -0
- package/public/assets/diagrams/loop.svg +40 -0
- package/public/assets/diagrams/plugin-topology.png +0 -0
- package/public/assets/diagrams/pre-action-gate-loop.svg +59 -0
- package/public/assets/diagrams/self-improving-thumbs-loop.svg +105 -0
- package/public/assets/diagrams/stack.svg +18 -0
- package/public/assets/diagrams/thumbgate-architecture.png +0 -0
- package/public/case-studies.html +151 -0
- package/public/compare.html +1 -0
- package/public/dashboard.html +126 -28
- package/public/eval-scorecard.html +195 -0
- package/public/eval-scorecard.json +18 -0
- package/public/evaluations.html +168 -0
- package/public/index.html +143 -13
- package/public/numbers.html +3 -2
- package/public/pricing.html +143 -30
- package/public/whitepaper.html +189 -0
- package/scripts/a-plus-evidence-scorecard.js +303 -0
- package/scripts/activation-quickstart.js +1 -0
- package/scripts/agent-outcome-monitor.js +71 -1
- package/scripts/async-eval-observability.js +36 -11
- package/scripts/audit-trail.js +37 -1
- package/scripts/auto-promote-gates.js +149 -34
- package/scripts/billing.js +3 -1
- package/scripts/claude-feedback-sync.js +3 -2
- package/scripts/cli-feedback.js +13 -7
- package/scripts/colbert-style-maxsim.js +236 -0
- package/scripts/cross-encoder-reranker.js +359 -126
- package/scripts/dashboard-chat.js +350 -17
- package/scripts/document-intake.js +283 -7
- package/scripts/eval-quality-suite.js +204 -0
- package/scripts/feedback-aggregate.js +5 -2
- package/scripts/feedback-loop.js +359 -189
- package/scripts/feedback-paths.js +32 -13
- package/scripts/feedback-quality.js +53 -0
- package/scripts/filesystem-search.js +17 -7
- package/scripts/gates-engine.js +98 -4
- package/scripts/generate-case-study-outreach.js +253 -0
- package/scripts/generate-eval-scorecard.js +276 -0
- package/scripts/growth-campaigns.js +183 -0
- package/scripts/harness-tool-names.js +70 -0
- package/scripts/hook-runtime.js +10 -3
- package/scripts/jsonl-watcher.js +1 -0
- package/scripts/lesson-db.js +16 -5
- package/scripts/lesson-embedding-index.js +67 -20
- package/scripts/lesson-embedding-maintenance.js +177 -0
- package/scripts/lesson-inference.js +23 -4
- package/scripts/lesson-reranker.js +55 -9
- package/scripts/lesson-retrieval.js +375 -32
- package/scripts/lesson-search.js +48 -11
- package/scripts/llm-client.js +304 -15
- package/scripts/mcp-config.js +26 -5
- package/scripts/mcp-oauth.js +37 -2
- package/scripts/model-eval.js +308 -0
- package/scripts/model-tier-router.js +593 -0
- package/scripts/parallel-workflow-orchestrator.js +86 -22
- package/scripts/pragmatic-hybrid-search.js +379 -0
- package/scripts/published-cli.js +11 -1
- package/scripts/rag-document-pipeline.js +461 -0
- package/scripts/rag-structured-output.js +441 -0
- package/scripts/ragas-style-metrics.js +351 -0
- package/scripts/refresh-proof-pack.js +261 -0
- package/scripts/request-envelope.js +178 -0
- package/scripts/rerank-pipeline.js +370 -0
- package/scripts/rerank-quality-eval.js +155 -0
- package/scripts/retrieval-hybrid-ablation.js +120 -0
- package/scripts/retrieval-quality-tier.js +118 -0
- package/scripts/risk-scorer.js +144 -15
- package/scripts/secret-scanner.js +395 -4
- package/scripts/self-distill-agent.js +7 -1
- package/scripts/self-healing-check.js +25 -0
- package/scripts/skill-packs.js +183 -0
- package/scripts/slow-loop.js +72 -0
- package/scripts/statusline-links.js +1 -1
- package/scripts/statusline-local-stats.js +1 -1
- package/scripts/statusline.sh +8 -1
- package/scripts/telemetry-analytics.js +13 -1
- package/scripts/thumbgate-bench.js +13 -0
- package/scripts/thumbgate-search.js +98 -6
- package/scripts/tier-budget-guard.js +186 -0
- package/scripts/tool-kpi-tracker.js +124 -0
- package/scripts/tool-registry.js +95 -1
- package/scripts/vector-store.js +108 -4
- package/scripts/verify-marketing-pages-deployed.js +85 -3
- package/server.json +44 -0
- package/smithery.yaml +17 -0
- package/src/api/server.js +424 -99
|
@@ -2,248 +2,278 @@
|
|
|
2
2
|
"version": 3,
|
|
3
3
|
"profiles": {
|
|
4
4
|
"default": [
|
|
5
|
-
"recall",
|
|
6
|
-
"unified_context",
|
|
7
|
-
"set_task_scope",
|
|
8
|
-
"get_scope_state",
|
|
9
|
-
"satisfy_gate",
|
|
10
|
-
"capture_feedback",
|
|
11
|
-
"open_feedback_session",
|
|
12
5
|
"append_feedback_context",
|
|
13
|
-
"
|
|
14
|
-
"feedback_summary",
|
|
15
|
-
"search_lessons",
|
|
16
|
-
"retrieve_lessons",
|
|
17
|
-
"search_thumbgate",
|
|
18
|
-
"plan_multimodal_retrieval",
|
|
19
|
-
"plan_context_footprint",
|
|
20
|
-
"plan_agent_design_governance",
|
|
21
|
-
"plan_proactive_agent_eval_guardrails",
|
|
22
|
-
"plan_reward_hacking_guardrails",
|
|
23
|
-
"plan_oss_pr_opportunity_scout",
|
|
24
|
-
"plan_chatgpt_ads_readiness",
|
|
25
|
-
"reflect_on_feedback",
|
|
26
|
-
"feedback_stats",
|
|
27
|
-
"diagnose_failure",
|
|
28
|
-
"list_intents",
|
|
29
|
-
"plan_intent",
|
|
30
|
-
"start_handoff",
|
|
31
|
-
"complete_handoff",
|
|
6
|
+
"approve_protected_action",
|
|
32
7
|
"bootstrap_internal_agent",
|
|
33
|
-
"
|
|
34
|
-
"
|
|
35
|
-
"
|
|
36
|
-
"
|
|
8
|
+
"capture_feedback",
|
|
9
|
+
"capture_memory_feedback",
|
|
10
|
+
"check_operational_integrity",
|
|
11
|
+
"commerce_recall",
|
|
12
|
+
"complete_handoff",
|
|
37
13
|
"construct_context_pack",
|
|
38
|
-
"evaluate_context_pack",
|
|
39
14
|
"context_provenance",
|
|
40
|
-
"
|
|
41
|
-
"generate_skill",
|
|
42
|
-
"set_branch_governance",
|
|
43
|
-
"get_branch_governance",
|
|
44
|
-
"approve_protected_action",
|
|
45
|
-
"track_action",
|
|
46
|
-
"detect_noop",
|
|
47
|
-
"record_action_receipt",
|
|
48
|
-
"get_action_receipts",
|
|
49
|
-
"verify_claim",
|
|
50
|
-
"check_operational_integrity",
|
|
51
|
-
"workflow_sentinel",
|
|
52
|
-
"register_claim_gate",
|
|
53
|
-
"gate_stats",
|
|
15
|
+
"context_stuff_lessons",
|
|
54
16
|
"dashboard",
|
|
55
|
-
"settings_status",
|
|
56
|
-
"native_messaging_audit",
|
|
57
|
-
"list_harnesses",
|
|
58
|
-
"run_harness",
|
|
59
|
-
"run_autoresearch",
|
|
60
|
-
"estimate_uncertainty",
|
|
61
|
-
"get_business_metrics",
|
|
62
|
-
"describe_semantic_entity",
|
|
63
|
-
"capture_memory_feedback",
|
|
64
|
-
"get_reliability_rules",
|
|
65
17
|
"describe_reliability_entity",
|
|
66
|
-
"
|
|
67
|
-
"
|
|
18
|
+
"describe_semantic_entity",
|
|
19
|
+
"detect_noop",
|
|
20
|
+
"diagnose_failure",
|
|
68
21
|
"distribute_context_to_agents",
|
|
69
|
-
"
|
|
22
|
+
"estimate_uncertainty",
|
|
23
|
+
"evaluate_context_pack",
|
|
24
|
+
"export_databricks_bundle",
|
|
25
|
+
"export_dpo_pairs",
|
|
26
|
+
"export_hf_dataset",
|
|
27
|
+
"feedback_stats",
|
|
28
|
+
"feedback_summary",
|
|
29
|
+
"finalize_feedback_session",
|
|
30
|
+
"gate_check",
|
|
31
|
+
"gate_stats",
|
|
70
32
|
"generate_operator_artifact",
|
|
71
|
-
"
|
|
33
|
+
"generate_skill",
|
|
34
|
+
"get_action_receipts",
|
|
35
|
+
"get_agent_outcome_metrics",
|
|
36
|
+
"get_branch_governance",
|
|
37
|
+
"get_business_metrics",
|
|
38
|
+
"get_reliability_rules",
|
|
39
|
+
"get_scope_state",
|
|
40
|
+
"get_task_outcomes",
|
|
41
|
+
"list_harnesses",
|
|
42
|
+
"list_human_escalations",
|
|
43
|
+
"list_intents",
|
|
72
44
|
"managed_agent_status",
|
|
73
|
-
"
|
|
74
|
-
"
|
|
75
|
-
"
|
|
76
|
-
"perplexity_search",
|
|
45
|
+
"native_messaging_audit",
|
|
46
|
+
"open_feedback_session",
|
|
47
|
+
"parallel_workflow",
|
|
77
48
|
"perplexity_ask",
|
|
78
|
-
"perplexity_research",
|
|
79
49
|
"perplexity_reason",
|
|
80
|
-
"
|
|
81
|
-
|
|
82
|
-
"essential": [
|
|
83
|
-
"recall",
|
|
84
|
-
"unified_context",
|
|
85
|
-
"set_task_scope",
|
|
86
|
-
"get_scope_state",
|
|
87
|
-
"satisfy_gate",
|
|
88
|
-
"capture_feedback",
|
|
89
|
-
"open_feedback_session",
|
|
90
|
-
"append_feedback_context",
|
|
91
|
-
"finalize_feedback_session",
|
|
92
|
-
"search_lessons",
|
|
93
|
-
"retrieve_lessons",
|
|
94
|
-
"search_thumbgate",
|
|
95
|
-
"plan_multimodal_retrieval",
|
|
96
|
-
"plan_context_footprint",
|
|
50
|
+
"perplexity_research",
|
|
51
|
+
"perplexity_search",
|
|
97
52
|
"plan_agent_design_governance",
|
|
53
|
+
"plan_chatgpt_ads_readiness",
|
|
54
|
+
"plan_context_footprint",
|
|
55
|
+
"plan_intent",
|
|
56
|
+
"plan_multimodal_retrieval",
|
|
57
|
+
"plan_oss_pr_opportunity_scout",
|
|
98
58
|
"plan_proactive_agent_eval_guardrails",
|
|
99
59
|
"plan_reward_hacking_guardrails",
|
|
100
|
-
"plan_oss_pr_opportunity_scout",
|
|
101
|
-
"plan_chatgpt_ads_readiness",
|
|
102
|
-
"reflect_on_feedback",
|
|
103
60
|
"prevention_rules",
|
|
61
|
+
"recall",
|
|
62
|
+
"record_action_receipt",
|
|
63
|
+
"record_task_outcome",
|
|
64
|
+
"reflect_on_feedback",
|
|
65
|
+
"register_claim_gate",
|
|
66
|
+
"report_product_issue",
|
|
67
|
+
"request_human_escalation",
|
|
68
|
+
"require_evidence_for_claim",
|
|
69
|
+
"retrieve_lessons",
|
|
70
|
+
"run_autoresearch",
|
|
71
|
+
"run_harness",
|
|
72
|
+
"run_managed_lesson_agent",
|
|
73
|
+
"run_self_distill",
|
|
74
|
+
"satisfy_gate",
|
|
75
|
+
"search_lessons",
|
|
76
|
+
"search_thumbgate",
|
|
77
|
+
"self_distill_status",
|
|
78
|
+
"session_report",
|
|
104
79
|
"set_branch_governance",
|
|
105
|
-
"
|
|
106
|
-
"
|
|
80
|
+
"set_task_scope",
|
|
81
|
+
"settings_status",
|
|
82
|
+
"start_handoff",
|
|
83
|
+
"suggest_fix",
|
|
107
84
|
"track_action",
|
|
85
|
+
"unified_context",
|
|
108
86
|
"verify_claim",
|
|
87
|
+
"workflow_sentinel"
|
|
88
|
+
],
|
|
89
|
+
"essential": [
|
|
90
|
+
"append_feedback_context",
|
|
91
|
+
"approve_protected_action",
|
|
92
|
+
"capture_feedback",
|
|
109
93
|
"check_operational_integrity",
|
|
110
|
-
"
|
|
94
|
+
"estimate_uncertainty",
|
|
111
95
|
"feedback_stats",
|
|
112
96
|
"feedback_summary",
|
|
113
|
-
"
|
|
114
|
-
"
|
|
115
|
-
"require_evidence_for_claim",
|
|
116
|
-
"session_report",
|
|
97
|
+
"finalize_feedback_session",
|
|
98
|
+
"gate_check",
|
|
117
99
|
"generate_operator_artifact",
|
|
118
|
-
"
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
"
|
|
100
|
+
"get_agent_outcome_metrics",
|
|
101
|
+
"get_branch_governance",
|
|
102
|
+
"get_scope_state",
|
|
103
|
+
"get_task_outcomes",
|
|
104
|
+
"list_human_escalations",
|
|
105
|
+
"open_feedback_session",
|
|
106
|
+
"parallel_workflow",
|
|
107
|
+
"plan_agent_design_governance",
|
|
108
|
+
"plan_chatgpt_ads_readiness",
|
|
109
|
+
"plan_context_footprint",
|
|
110
|
+
"plan_multimodal_retrieval",
|
|
111
|
+
"plan_oss_pr_opportunity_scout",
|
|
112
|
+
"plan_proactive_agent_eval_guardrails",
|
|
113
|
+
"plan_reward_hacking_guardrails",
|
|
114
|
+
"prevention_rules",
|
|
122
115
|
"recall",
|
|
116
|
+
"record_task_outcome",
|
|
117
|
+
"reflect_on_feedback",
|
|
118
|
+
"report_product_issue",
|
|
119
|
+
"request_human_escalation",
|
|
120
|
+
"require_evidence_for_claim",
|
|
123
121
|
"retrieve_lessons",
|
|
122
|
+
"satisfy_gate",
|
|
123
|
+
"search_lessons",
|
|
124
124
|
"search_thumbgate",
|
|
125
|
-
"
|
|
126
|
-
"set_task_scope",
|
|
127
|
-
"get_scope_state",
|
|
125
|
+
"session_report",
|
|
128
126
|
"set_branch_governance",
|
|
129
|
-
"
|
|
130
|
-
"
|
|
127
|
+
"set_task_scope",
|
|
128
|
+
"suggest_fix",
|
|
131
129
|
"track_action",
|
|
130
|
+
"unified_context",
|
|
132
131
|
"verify_claim",
|
|
132
|
+
"workflow_sentinel"
|
|
133
|
+
],
|
|
134
|
+
"commerce": [
|
|
135
|
+
"approve_protected_action",
|
|
136
|
+
"capture_feedback",
|
|
133
137
|
"check_operational_integrity",
|
|
134
|
-
"
|
|
135
|
-
"prevention_rules",
|
|
138
|
+
"commerce_recall",
|
|
136
139
|
"feedback_stats",
|
|
137
140
|
"feedback_summary",
|
|
138
|
-
"
|
|
139
|
-
|
|
140
|
-
|
|
141
|
+
"gate_check",
|
|
142
|
+
"get_agent_outcome_metrics",
|
|
143
|
+
"get_branch_governance",
|
|
144
|
+
"get_scope_state",
|
|
145
|
+
"get_task_outcomes",
|
|
146
|
+
"list_human_escalations",
|
|
147
|
+
"prevention_rules",
|
|
141
148
|
"recall",
|
|
142
|
-
"
|
|
143
|
-
"
|
|
144
|
-
"search_lessons",
|
|
149
|
+
"record_task_outcome",
|
|
150
|
+
"request_human_escalation",
|
|
145
151
|
"retrieve_lessons",
|
|
146
152
|
"search_thumbgate",
|
|
147
|
-
"
|
|
148
|
-
"
|
|
149
|
-
"
|
|
150
|
-
"
|
|
151
|
-
"plan_reward_hacking_guardrails",
|
|
152
|
-
"plan_oss_pr_opportunity_scout",
|
|
153
|
-
"plan_chatgpt_ads_readiness",
|
|
154
|
-
"feedback_stats",
|
|
155
|
-
"diagnose_failure",
|
|
156
|
-
"list_harnesses",
|
|
157
|
-
"list_intents",
|
|
158
|
-
"plan_intent",
|
|
159
|
-
"start_handoff",
|
|
160
|
-
"complete_handoff",
|
|
161
|
-
"context_provenance",
|
|
162
|
-
"get_scope_state",
|
|
163
|
-
"get_branch_governance",
|
|
153
|
+
"set_branch_governance",
|
|
154
|
+
"set_task_scope",
|
|
155
|
+
"suggest_fix",
|
|
156
|
+
"track_action",
|
|
164
157
|
"verify_claim",
|
|
158
|
+
"workflow_sentinel"
|
|
159
|
+
],
|
|
160
|
+
"readonly": [
|
|
165
161
|
"check_operational_integrity",
|
|
166
|
-
"
|
|
167
|
-
"gate_stats",
|
|
162
|
+
"context_provenance",
|
|
168
163
|
"dashboard",
|
|
169
|
-
"settings_status",
|
|
170
|
-
"native_messaging_audit",
|
|
171
|
-
"get_business_metrics",
|
|
172
|
-
"describe_semantic_entity",
|
|
173
|
-
"get_reliability_rules",
|
|
174
164
|
"describe_reliability_entity",
|
|
175
|
-
"
|
|
176
|
-
"
|
|
165
|
+
"describe_semantic_entity",
|
|
166
|
+
"diagnose_failure",
|
|
167
|
+
"feedback_stats",
|
|
168
|
+
"feedback_summary",
|
|
169
|
+
"gate_check",
|
|
170
|
+
"gate_stats",
|
|
177
171
|
"generate_operator_artifact",
|
|
178
|
-
"
|
|
172
|
+
"get_agent_outcome_metrics",
|
|
173
|
+
"get_branch_governance",
|
|
174
|
+
"get_business_metrics",
|
|
175
|
+
"get_reliability_rules",
|
|
176
|
+
"get_scope_state",
|
|
177
|
+
"get_task_outcomes",
|
|
178
|
+
"list_harnesses",
|
|
179
|
+
"list_human_escalations",
|
|
180
|
+
"list_intents",
|
|
181
|
+
"native_messaging_audit",
|
|
179
182
|
"perplexity_ask",
|
|
180
|
-
"
|
|
181
|
-
],
|
|
182
|
-
"dispatch": [
|
|
183
|
-
"recall",
|
|
184
|
-
"unified_context",
|
|
185
|
-
"feedback_summary",
|
|
186
|
-
"search_lessons",
|
|
187
|
-
"retrieve_lessons",
|
|
188
|
-
"search_thumbgate",
|
|
189
|
-
"plan_multimodal_retrieval",
|
|
190
|
-
"plan_context_footprint",
|
|
183
|
+
"perplexity_search",
|
|
191
184
|
"plan_agent_design_governance",
|
|
192
|
-
"plan_proactive_agent_eval_guardrails",
|
|
193
|
-
"plan_reward_hacking_guardrails",
|
|
194
|
-
"plan_oss_pr_opportunity_scout",
|
|
195
185
|
"plan_chatgpt_ads_readiness",
|
|
196
|
-
"
|
|
197
|
-
"diagnose_failure",
|
|
198
|
-
"list_harnesses",
|
|
199
|
-
"list_intents",
|
|
186
|
+
"plan_context_footprint",
|
|
200
187
|
"plan_intent",
|
|
201
|
-
"
|
|
202
|
-
"
|
|
203
|
-
"
|
|
204
|
-
"
|
|
188
|
+
"plan_multimodal_retrieval",
|
|
189
|
+
"plan_oss_pr_opportunity_scout",
|
|
190
|
+
"plan_proactive_agent_eval_guardrails",
|
|
191
|
+
"plan_reward_hacking_guardrails",
|
|
192
|
+
"recall",
|
|
193
|
+
"require_evidence_for_claim",
|
|
194
|
+
"retrieve_lessons",
|
|
195
|
+
"search_lessons",
|
|
196
|
+
"search_thumbgate",
|
|
197
|
+
"session_report",
|
|
198
|
+
"settings_status",
|
|
199
|
+
"suggest_fix",
|
|
200
|
+
"unified_context",
|
|
205
201
|
"verify_claim",
|
|
202
|
+
"workflow_sentinel"
|
|
203
|
+
],
|
|
204
|
+
"dispatch": [
|
|
206
205
|
"check_operational_integrity",
|
|
207
|
-
"
|
|
208
|
-
"gate_stats",
|
|
206
|
+
"context_provenance",
|
|
209
207
|
"dashboard",
|
|
210
|
-
"
|
|
211
|
-
"native_messaging_audit",
|
|
212
|
-
"get_business_metrics",
|
|
208
|
+
"describe_reliability_entity",
|
|
213
209
|
"describe_semantic_entity",
|
|
210
|
+
"diagnose_failure",
|
|
211
|
+
"feedback_stats",
|
|
212
|
+
"feedback_summary",
|
|
213
|
+
"gate_check",
|
|
214
|
+
"gate_stats",
|
|
215
|
+
"generate_operator_artifact",
|
|
216
|
+
"get_agent_outcome_metrics",
|
|
217
|
+
"get_branch_governance",
|
|
218
|
+
"get_business_metrics",
|
|
214
219
|
"get_reliability_rules",
|
|
215
|
-
"
|
|
220
|
+
"get_scope_state",
|
|
221
|
+
"get_task_outcomes",
|
|
222
|
+
"list_harnesses",
|
|
223
|
+
"list_human_escalations",
|
|
224
|
+
"list_intents",
|
|
225
|
+
"native_messaging_audit",
|
|
226
|
+
"perplexity_ask",
|
|
227
|
+
"perplexity_search",
|
|
228
|
+
"plan_agent_design_governance",
|
|
229
|
+
"plan_chatgpt_ads_readiness",
|
|
230
|
+
"plan_context_footprint",
|
|
231
|
+
"plan_intent",
|
|
232
|
+
"plan_multimodal_retrieval",
|
|
233
|
+
"plan_oss_pr_opportunity_scout",
|
|
234
|
+
"plan_proactive_agent_eval_guardrails",
|
|
235
|
+
"plan_reward_hacking_guardrails",
|
|
236
|
+
"recall",
|
|
216
237
|
"require_evidence_for_claim",
|
|
238
|
+
"retrieve_lessons",
|
|
239
|
+
"run_harness",
|
|
240
|
+
"search_lessons",
|
|
241
|
+
"search_thumbgate",
|
|
217
242
|
"session_report",
|
|
218
|
-
"
|
|
219
|
-
"
|
|
220
|
-
"
|
|
221
|
-
"
|
|
243
|
+
"settings_status",
|
|
244
|
+
"suggest_fix",
|
|
245
|
+
"unified_context",
|
|
246
|
+
"verify_claim",
|
|
247
|
+
"workflow_sentinel"
|
|
222
248
|
],
|
|
223
249
|
"locked": [
|
|
250
|
+
"check_operational_integrity",
|
|
251
|
+
"diagnose_failure",
|
|
224
252
|
"feedback_summary",
|
|
225
|
-
"
|
|
226
|
-
"
|
|
227
|
-
"
|
|
228
|
-
"
|
|
253
|
+
"gate_check",
|
|
254
|
+
"generate_operator_artifact",
|
|
255
|
+
"get_agent_outcome_metrics",
|
|
256
|
+
"get_branch_governance",
|
|
257
|
+
"get_scope_state",
|
|
258
|
+
"get_task_outcomes",
|
|
259
|
+
"list_harnesses",
|
|
260
|
+
"list_human_escalations",
|
|
261
|
+
"list_intents",
|
|
262
|
+
"native_messaging_audit",
|
|
229
263
|
"plan_agent_design_governance",
|
|
230
|
-
"plan_proactive_agent_eval_guardrails",
|
|
231
|
-
"plan_reward_hacking_guardrails",
|
|
232
|
-
"plan_oss_pr_opportunity_scout",
|
|
233
264
|
"plan_chatgpt_ads_readiness",
|
|
234
|
-
"
|
|
235
|
-
"list_intents",
|
|
265
|
+
"plan_context_footprint",
|
|
236
266
|
"plan_intent",
|
|
237
|
-
"
|
|
238
|
-
"
|
|
239
|
-
"
|
|
240
|
-
"
|
|
241
|
-
"
|
|
242
|
-
"
|
|
267
|
+
"plan_oss_pr_opportunity_scout",
|
|
268
|
+
"plan_proactive_agent_eval_guardrails",
|
|
269
|
+
"plan_reward_hacking_guardrails",
|
|
270
|
+
"retrieve_lessons",
|
|
271
|
+
"search_lessons",
|
|
272
|
+
"search_thumbgate",
|
|
243
273
|
"settings_status",
|
|
244
|
-
"
|
|
245
|
-
"
|
|
246
|
-
"
|
|
274
|
+
"suggest_fix",
|
|
275
|
+
"verify_claim",
|
|
276
|
+
"workflow_sentinel"
|
|
247
277
|
]
|
|
248
278
|
}
|
|
249
279
|
}
|
package/config/model-tiers.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
|
4
4
|
"nano": {
|
|
5
5
|
"label": "GPT-5.4 nano",
|
|
6
6
|
"modelId": "gpt-5.4-nano",
|
|
7
|
+
"provider": "openai",
|
|
7
8
|
"taskTypes": ["classification", "extraction", "ranking", "labeling", "summarization"],
|
|
8
9
|
"maxContextTokens": 32000,
|
|
9
10
|
"costMultiplier": 0.1
|
|
@@ -11,6 +12,7 @@
|
|
|
11
12
|
"mini": {
|
|
12
13
|
"label": "GPT-5.4 mini",
|
|
13
14
|
"modelId": "gpt-5.4-mini",
|
|
15
|
+
"provider": "openai",
|
|
14
16
|
"taskTypes": ["code-edit", "test-generation", "review", "tool-use", "debugging"],
|
|
15
17
|
"maxContextTokens": 200000,
|
|
16
18
|
"costMultiplier": 0.4
|
|
@@ -18,6 +20,7 @@
|
|
|
18
20
|
"frontier": {
|
|
19
21
|
"label": "GPT-5.5",
|
|
20
22
|
"modelId": "gpt-5.5",
|
|
23
|
+
"provider": "openai",
|
|
21
24
|
"taskTypes": ["architecture", "cross-file", "complex-debugging", "large-context"],
|
|
22
25
|
"maxContextTokens": 1000000,
|
|
23
26
|
"costMultiplier": 1.0,
|
|
@@ -27,7 +30,9 @@
|
|
|
27
30
|
}
|
|
28
31
|
},
|
|
29
32
|
"localFrontier": {
|
|
30
|
-
"label": "
|
|
33
|
+
"label": "Configured local frontier",
|
|
34
|
+
"modelId": null,
|
|
35
|
+
"provider": "openai-compatible",
|
|
31
36
|
"taskTypes": [],
|
|
32
37
|
"maxContextTokens": 1000000,
|
|
33
38
|
"costMultiplier": 0.0,
|
|
@@ -35,7 +40,7 @@
|
|
|
35
40
|
"tokenCap": 2000000,
|
|
36
41
|
"requireReason": false
|
|
37
42
|
},
|
|
38
|
-
"notes": "Self-hosted open-source tier.
|
|
43
|
+
"notes": "Self-hosted open-source tier. The runtime derives the served model from THUMBGATE_MODEL_ROLE_NORMAL, THUMBGATE_LOCAL_MODEL, THUMBGATE_MODEL_ID, or THUMBGATE_LOCAL_MODEL_FAMILY. Zero marginal API cost; no token budget enforcement needed."
|
|
39
44
|
}
|
|
40
45
|
},
|
|
41
46
|
"escalationRules": {
|
|
@@ -5,7 +5,7 @@
|
|
|
5
5
|
{
|
|
6
6
|
"route": "/",
|
|
7
7
|
"sentinel": "Stop AI agent mistakes before they cost you",
|
|
8
|
-
"description": "Home page hero (lifeblood
|
|
8
|
+
"description": "Home page hero (lifeblood \u2014 never regress)"
|
|
9
9
|
},
|
|
10
10
|
{
|
|
11
11
|
"route": "/pro",
|
|
@@ -75,6 +75,31 @@
|
|
|
75
75
|
"route": "/leash-beta",
|
|
76
76
|
"sentinel": "Stop Runaway AI Agents From Freezing Your Machine",
|
|
77
77
|
"description": "Hermes Mobile founding beta / Leash Pro pricing landing"
|
|
78
|
+
},
|
|
79
|
+
{
|
|
80
|
+
"route": "/whitepaper",
|
|
81
|
+
"sentinel": "How we know ThumbGate works",
|
|
82
|
+
"description": "Evaluation white paper"
|
|
83
|
+
},
|
|
84
|
+
{
|
|
85
|
+
"route": "/architecture",
|
|
86
|
+
"sentinel": "Architecture diagrams",
|
|
87
|
+
"description": "Public diagram gallery"
|
|
88
|
+
},
|
|
89
|
+
{
|
|
90
|
+
"route": "/eval-scorecard",
|
|
91
|
+
"sentinel": "Eval scorecard",
|
|
92
|
+
"description": "ThumbGate Bench scorecard"
|
|
93
|
+
},
|
|
94
|
+
{
|
|
95
|
+
"route": "/evaluations",
|
|
96
|
+
"sentinel": "How We Evaluate",
|
|
97
|
+
"description": "ML evaluation methodology page"
|
|
98
|
+
},
|
|
99
|
+
{
|
|
100
|
+
"route": "/case-studies",
|
|
101
|
+
"sentinel": "Case studies",
|
|
102
|
+
"description": "Dogfood case studies proof page"
|
|
78
103
|
}
|
|
79
104
|
]
|
|
80
105
|
}
|