npm - thumbgate - Versions diffs - 1.30.0 → 1.34.0 - Mend

thumbgate 1.30.0 → 1.34.0

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.

Files changed (92) hide show

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 +105 -10
package/adapters/opencode/opencode.json +1 -1
package/bench/observability-eval-suite.json +2 -2
package/bin/cli.js +168 -31
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/claim-verifiers.example.json +42 -0
package/config/gates/claim-verifiers.json +25 -0
package/config/gates/default.json +217 -50
package/config/mcp-allowlists.json +233 -206
package/config/model-tiers.json +7 -2
package/glama.json +6 -0
package/hooks/hooks.json +1 -1
package/package.json +69 -12
package/public/assets/diagrams/before-after.svg +17 -16
package/public/assets/diagrams/hero-thumbs.svg +68 -0
package/public/assets/diagrams/loop.svg +19 -13
package/public/assets/diagrams/self-improving-thumbs-loop.svg +105 -0
package/public/compare.html +1 -0
package/public/dashboard.html +126 -28
package/public/evaluations.html +1 -1
package/public/index.html +142 -13
package/public/numbers.html +3 -2
package/public/pricing.html +143 -30
package/scripts/a-plus-evidence-scorecard.js +303 -0
package/scripts/agent-readiness.js +110 -0
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/auto-wire-hooks.js +20 -8
package/scripts/cli-schema.js +14 -0
package/scripts/colbert-style-maxsim.js +236 -0
package/scripts/cross-encoder-reranker.js +356 -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-loop.js +115 -7
package/scripts/feedback-paths.js +32 -13
package/scripts/feedback-quality.js +53 -0
package/scripts/feedback-schema.js +3 -0
package/scripts/file-ledger-lock.js +130 -0
package/scripts/filesystem-search.js +17 -7
package/scripts/financial-control-plane.js +1514 -0
package/scripts/gates-engine.js +202 -7
package/scripts/gemini-embedding-policy.js +1 -0
package/scripts/harness-tool-names.js +70 -0
package/scripts/hook-runtime.js +15 -3
package/scripts/hook-stop-anti-claim.js +63 -3
package/scripts/human-escalation.js +353 -41
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-reranker.js +55 -9
package/scripts/lesson-retrieval.js +305 -29
package/scripts/lesson-search.js +22 -8
package/scripts/llm-client.js +304 -15
package/scripts/model-tier-router.js +593 -0
package/scripts/pragmatic-hybrid-search.js +379 -0
package/scripts/provider-action-normalizer.js +11 -4
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/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/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.sh +8 -1
package/scripts/telemetry-analytics.js +13 -1
package/scripts/thumbgate-search.js +98 -6
package/scripts/tier-budget-guard.js +186 -0
package/scripts/tool-registry.js +141 -5
package/scripts/universal-claim-evaluator.js +767 -0
package/scripts/vector-store.js +154 -17
package/scripts/verify-marketing-pages-deployed.js +85 -3
package/scripts/workflow-sentinel.js +77 -11
package/server.json +44 -0
package/smithery.yaml +17 -0
package/src/api/server.js +196 -13

package/config/mcp-allowlists.json CHANGED Viewed

@@ -2,272 +2,299 @@
   "version": 3,
   "profiles": {
     "default": [
-      "recall",
-      "unified_context",
-      "set_task_scope",
-      "get_scope_state",
-      "satisfy_gate",
-      "capture_feedback",
-      "open_feedback_session",
       "append_feedback_context",
-      "finalize_feedback_session",
-      "feedback_summary",
-      "search_lessons",
-      "retrieve_lessons",
-      "search_thumbgate",
-      "plan_multimodal_retrieval",
-      "plan_context_footprint",
-      "plan_agent_design_governance",
-      "plan_proactive_agent_eval_guardrails",
-      "plan_reward_hacking_guardrails",
-      "plan_oss_pr_opportunity_scout",
-      "plan_chatgpt_ads_readiness",
-      "reflect_on_feedback",
-      "feedback_stats",
-      "diagnose_failure",
-      "list_intents",
-      "plan_intent",
-      "start_handoff",
-      "complete_handoff",
+      "approve_protected_action",
       "bootstrap_internal_agent",
-      "prevention_rules",
-      "export_dpo_pairs",
-      "export_hf_dataset",
-      "export_databricks_bundle",
+      "capture_feedback",
+      "capture_memory_feedback",
+      "check_operational_integrity",
+      "commerce_recall",
+      "complete_handoff",
       "construct_context_pack",
-      "evaluate_context_pack",
       "context_provenance",
-      "commerce_recall",
-      "generate_skill",
-      "set_branch_governance",
-      "get_branch_governance",
-      "approve_protected_action",
-      "track_action",
+      "context_stuff_lessons",
+      "create_purchase_requisition",
+      "dashboard",
+      "describe_reliability_entity",
+      "describe_semantic_entity",
       "detect_noop",
-      "record_action_receipt",
+      "diagnose_failure",
+      "distribute_context_to_agents",
+      "estimate_uncertainty",
+      "evaluate_context_pack",
+      "export_databricks_bundle",
+      "export_dpo_pairs",
+      "export_hf_dataset",
+      "feedback_stats",
+      "feedback_summary",
+      "finalize_feedback_session",
+      "gate_check",
+      "gate_stats",
+      "generate_operator_artifact",
+      "generate_skill",
       "get_action_receipts",
-      "record_task_outcome",
-      "get_task_outcomes",
       "get_agent_outcome_metrics",
-      "request_human_escalation",
-      "list_human_escalations",
-      "verify_claim",
-      "check_operational_integrity",
-      "workflow_sentinel",
-      "register_claim_gate",
-      "gate_stats",
-      "dashboard",
-      "settings_status",
-      "native_messaging_audit",
-      "list_harnesses",
-      "run_harness",
-      "run_autoresearch",
-      "estimate_uncertainty",
+      "get_branch_governance",
       "get_business_metrics",
-      "describe_semantic_entity",
-      "capture_memory_feedback",
       "get_reliability_rules",
-      "describe_reliability_entity",
-      "report_product_issue",
-      "require_evidence_for_claim",
-      "distribute_context_to_agents",
-      "session_report",
-      "generate_operator_artifact",
-      "run_managed_lesson_agent",
+      "get_scope_state",
+      "get_task_outcomes",
+      "list_harnesses",
+      "list_human_escalations",
+      "list_intents",
+      "list_purchase_requisitions",
       "managed_agent_status",
-      "run_self_distill",
-      "self_distill_status",
-      "context_stuff_lessons",
+      "native_messaging_audit",
+      "open_feedback_session",
       "parallel_workflow",
-      "perplexity_search",
       "perplexity_ask",
-      "perplexity_research",
       "perplexity_reason",
-      "suggest_fix"
-    ],
-    "essential": [
-      "recall",
-      "unified_context",
-      "set_task_scope",
-      "get_scope_state",
-      "satisfy_gate",
-      "capture_feedback",
-      "open_feedback_session",
-      "append_feedback_context",
-      "finalize_feedback_session",
-      "search_lessons",
-      "retrieve_lessons",
-      "search_thumbgate",
-      "plan_multimodal_retrieval",
-      "plan_context_footprint",
+      "perplexity_research",
+      "perplexity_search",
       "plan_agent_design_governance",
+      "plan_chatgpt_ads_readiness",
+      "plan_context_footprint",
+      "plan_intent",
+      "plan_multimodal_retrieval",
+      "plan_oss_pr_opportunity_scout",
       "plan_proactive_agent_eval_guardrails",
       "plan_reward_hacking_guardrails",
-      "plan_oss_pr_opportunity_scout",
-      "plan_chatgpt_ads_readiness",
-      "reflect_on_feedback",
       "prevention_rules",
-      "set_branch_governance",
-      "get_branch_governance",
-      "approve_protected_action",
-      "track_action",
+      "recall",
+      "record_action_receipt",
       "record_task_outcome",
-      "get_task_outcomes",
-      "get_agent_outcome_metrics",
+      "reconcile_purchase_ledger",
+      "reflect_on_feedback",
+      "register_claim_gate",
+      "report_product_issue",
       "request_human_escalation",
-      "list_human_escalations",
+      "reserve_purchase_requisition",
+      "require_evidence_for_claim",
+      "retrieve_lessons",
+      "run_autoresearch",
+      "run_harness",
+      "run_managed_lesson_agent",
+      "run_self_distill",
+      "satisfy_gate",
+      "search_lessons",
+      "search_thumbgate",
+      "self_distill_status",
+      "session_report",
+      "settle_purchase_requisition",
+      "set_branch_governance",
+      "set_task_scope",
+      "settings_status",
+      "start_handoff",
+      "suggest_fix",
+      "track_action",
+      "unified_context",
       "verify_claim",
+      "workflow_sentinel"
+    ],
+    "essential": [
+      "append_feedback_context",
+      "approve_protected_action",
+      "capture_feedback",
       "check_operational_integrity",
-      "workflow_sentinel",
+      "create_purchase_requisition",
+      "estimate_uncertainty",
       "feedback_stats",
       "feedback_summary",
-      "estimate_uncertainty",
-      "report_product_issue",
-      "require_evidence_for_claim",
-      "session_report",
+      "finalize_feedback_session",
+      "gate_check",
       "generate_operator_artifact",
+      "get_agent_outcome_metrics",
+      "get_branch_governance",
+      "get_scope_state",
+      "get_task_outcomes",
+      "list_human_escalations",
+      "list_purchase_requisitions",
+      "open_feedback_session",
       "parallel_workflow",
-      "suggest_fix"
-    ],
-    "commerce": [
-      "capture_feedback",
+      "plan_agent_design_governance",
+      "plan_chatgpt_ads_readiness",
+      "plan_context_footprint",
+      "plan_multimodal_retrieval",
+      "plan_oss_pr_opportunity_scout",
+      "plan_proactive_agent_eval_guardrails",
+      "plan_reward_hacking_guardrails",
+      "prevention_rules",
       "recall",
+      "record_task_outcome",
+      "reconcile_purchase_ledger",
+      "reflect_on_feedback",
+      "report_product_issue",
+      "request_human_escalation",
+      "reserve_purchase_requisition",
+      "require_evidence_for_claim",
       "retrieve_lessons",
+      "satisfy_gate",
+      "search_lessons",
       "search_thumbgate",
-      "commerce_recall",
-      "set_task_scope",
-      "get_scope_state",
+      "session_report",
+      "settle_purchase_requisition",
       "set_branch_governance",
-      "get_branch_governance",
-      "approve_protected_action",
+      "set_task_scope",
+      "suggest_fix",
       "track_action",
-      "record_task_outcome",
-      "get_task_outcomes",
-      "get_agent_outcome_metrics",
-      "request_human_escalation",
-      "list_human_escalations",
+      "unified_context",
       "verify_claim",
+      "workflow_sentinel"
+    ],
+    "commerce": [
+      "approve_protected_action",
+      "capture_feedback",
       "check_operational_integrity",
-      "workflow_sentinel",
-      "prevention_rules",
+      "commerce_recall",
+      "create_purchase_requisition",
       "feedback_stats",
       "feedback_summary",
-      "suggest_fix"
-    ],
-    "readonly": [
-      "recall",
-      "unified_context",
-      "feedback_summary",
-      "search_lessons",
-      "retrieve_lessons",
-      "search_thumbgate",
-      "plan_multimodal_retrieval",
-      "plan_context_footprint",
-      "plan_agent_design_governance",
-      "plan_proactive_agent_eval_guardrails",
-      "plan_reward_hacking_guardrails",
-      "plan_oss_pr_opportunity_scout",
-      "plan_chatgpt_ads_readiness",
-      "feedback_stats",
-      "diagnose_failure",
-      "list_harnesses",
-      "list_intents",
-      "plan_intent",
-      "context_provenance",
-      "get_scope_state",
+      "gate_check",
+      "get_agent_outcome_metrics",
       "get_branch_governance",
+      "get_scope_state",
       "get_task_outcomes",
-      "get_agent_outcome_metrics",
       "list_human_escalations",
+      "list_purchase_requisitions",
+      "prevention_rules",
+      "recall",
+      "record_task_outcome",
+      "reconcile_purchase_ledger",
+      "request_human_escalation",
+      "reserve_purchase_requisition",
+      "retrieve_lessons",
+      "search_thumbgate",
+      "set_branch_governance",
+      "set_task_scope",
+      "settle_purchase_requisition",
+      "suggest_fix",
+      "track_action",
       "verify_claim",
+      "workflow_sentinel"
+    ],
+    "readonly": [
       "check_operational_integrity",
-      "workflow_sentinel",
-      "gate_stats",
+      "context_provenance",
       "dashboard",
-      "settings_status",
-      "native_messaging_audit",
-      "get_business_metrics",
-      "describe_semantic_entity",
-      "get_reliability_rules",
       "describe_reliability_entity",
-      "require_evidence_for_claim",
-      "session_report",
+      "describe_semantic_entity",
+      "diagnose_failure",
+      "feedback_stats",
+      "feedback_summary",
+      "gate_check",
+      "gate_stats",
       "generate_operator_artifact",
-      "perplexity_search",
+      "get_agent_outcome_metrics",
+      "get_branch_governance",
+      "get_business_metrics",
+      "get_reliability_rules",
+      "get_scope_state",
+      "get_task_outcomes",
+      "list_harnesses",
+      "list_human_escalations",
+      "list_intents",
+      "list_purchase_requisitions",
+      "native_messaging_audit",
       "perplexity_ask",
-      "suggest_fix"
-    ],
-    "dispatch": [
-      "recall",
-      "unified_context",
-      "feedback_summary",
-      "search_lessons",
-      "retrieve_lessons",
-      "search_thumbgate",
-      "plan_multimodal_retrieval",
-      "plan_context_footprint",
+      "perplexity_search",
       "plan_agent_design_governance",
-      "plan_proactive_agent_eval_guardrails",
-      "plan_reward_hacking_guardrails",
-      "plan_oss_pr_opportunity_scout",
       "plan_chatgpt_ads_readiness",
-      "feedback_stats",
-      "diagnose_failure",
-      "list_harnesses",
-      "list_intents",
+      "plan_context_footprint",
       "plan_intent",
-      "run_harness",
-      "context_provenance",
-      "get_scope_state",
-      "get_branch_governance",
-      "get_task_outcomes",
-      "get_agent_outcome_metrics",
-      "list_human_escalations",
+      "plan_multimodal_retrieval",
+      "plan_oss_pr_opportunity_scout",
+      "plan_proactive_agent_eval_guardrails",
+      "plan_reward_hacking_guardrails",
+      "recall",
+      "reconcile_purchase_ledger",
+      "require_evidence_for_claim",
+      "retrieve_lessons",
+      "search_lessons",
+      "search_thumbgate",
+      "session_report",
+      "settings_status",
+      "suggest_fix",
+      "unified_context",
       "verify_claim",
+      "workflow_sentinel"
+    ],
+    "dispatch": [
       "check_operational_integrity",
-      "workflow_sentinel",
-      "gate_stats",
+      "context_provenance",
       "dashboard",
-      "settings_status",
-      "native_messaging_audit",
-      "get_business_metrics",
-      "describe_semantic_entity",
-      "get_reliability_rules",
       "describe_reliability_entity",
-      "require_evidence_for_claim",
-      "session_report",
+      "describe_semantic_entity",
+      "diagnose_failure",
+      "feedback_stats",
+      "feedback_summary",
+      "gate_check",
+      "gate_stats",
       "generate_operator_artifact",
-      "perplexity_search",
+      "get_agent_outcome_metrics",
+      "get_branch_governance",
+      "get_business_metrics",
+      "get_reliability_rules",
+      "get_scope_state",
+      "get_task_outcomes",
+      "list_harnesses",
+      "list_human_escalations",
+      "list_intents",
+      "list_purchase_requisitions",
+      "native_messaging_audit",
       "perplexity_ask",
-      "suggest_fix"
-    ],
-    "locked": [
-      "feedback_summary",
-      "search_lessons",
-      "retrieve_lessons",
-      "search_thumbgate",
-      "plan_context_footprint",
+      "perplexity_search",
       "plan_agent_design_governance",
+      "plan_chatgpt_ads_readiness",
+      "plan_context_footprint",
+      "plan_intent",
+      "plan_multimodal_retrieval",
+      "plan_oss_pr_opportunity_scout",
       "plan_proactive_agent_eval_guardrails",
       "plan_reward_hacking_guardrails",
-      "plan_oss_pr_opportunity_scout",
-      "plan_chatgpt_ads_readiness",
+      "recall",
+      "reconcile_purchase_ledger",
+      "require_evidence_for_claim",
+      "retrieve_lessons",
+      "run_harness",
+      "search_lessons",
+      "search_thumbgate",
+      "session_report",
+      "settings_status",
+      "suggest_fix",
+      "unified_context",
+      "verify_claim",
+      "workflow_sentinel"
+    ],
+    "locked": [
+      "check_operational_integrity",
       "diagnose_failure",
-      "list_intents",
-      "plan_intent",
-      "list_harnesses",
-      "get_scope_state",
+      "feedback_summary",
+      "gate_check",
+      "generate_operator_artifact",
+      "get_agent_outcome_metrics",
       "get_branch_governance",
+      "get_scope_state",
       "get_task_outcomes",
-      "get_agent_outcome_metrics",
+      "list_harnesses",
       "list_human_escalations",
-      "verify_claim",
-      "check_operational_integrity",
-      "workflow_sentinel",
-      "settings_status",
+      "list_intents",
+      "list_purchase_requisitions",
       "native_messaging_audit",
-      "generate_operator_artifact",
-      "suggest_fix"
+      "plan_agent_design_governance",
+      "plan_chatgpt_ads_readiness",
+      "plan_context_footprint",
+      "plan_intent",
+      "plan_oss_pr_opportunity_scout",
+      "plan_proactive_agent_eval_guardrails",
+      "plan_reward_hacking_guardrails",
+      "retrieve_lessons",
+      "reconcile_purchase_ledger",
+      "search_lessons",
+      "search_thumbgate",
+      "settings_status",
+      "suggest_fix",
+      "verify_claim",
+      "workflow_sentinel"
     ]
   }
 }

package/config/model-tiers.json CHANGED Viewed

@@ -4,6 +4,7 @@
     "nano": {
       "label": "GPT-5.4 nano",
       "modelId": "gpt-5.4-nano",
+      "provider": "openai",
       "taskTypes": ["classification", "extraction", "ranking", "labeling", "summarization"],
       "maxContextTokens": 32000,
       "costMultiplier": 0.1
@@ -11,6 +12,7 @@
     "mini": {
       "label": "GPT-5.4 mini",
       "modelId": "gpt-5.4-mini",
+      "provider": "openai",
       "taskTypes": ["code-edit", "test-generation", "review", "tool-use", "debugging"],
       "maxContextTokens": 200000,
       "costMultiplier": 0.4
@@ -18,6 +20,7 @@
     "frontier": {
       "label": "GPT-5.5",
       "modelId": "gpt-5.5",
+      "provider": "openai",
       "taskTypes": ["architecture", "cross-file", "complex-debugging", "large-context"],
       "maxContextTokens": 1000000,
       "costMultiplier": 1.0,
@@ -27,7 +30,9 @@
       }
     },
     "localFrontier": {
-      "label": "GLM 5.1",
+      "label": "Configured local frontier",
+      "modelId": null,
+      "provider": "openai-compatible",
       "taskTypes": [],
       "maxContextTokens": 1000000,
       "costMultiplier": 0.0,
@@ -35,7 +40,7 @@
         "tokenCap": 2000000,
         "requireReason": false
       },
-      "notes": "Self-hosted open-source tier. Activate via THUMBGATE_LOCAL_MODEL_FAMILY=glm-*. Zero marginal cost; no token budget enforcement needed."
+      "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."
     }
   },
   "escalationRules": {

package/glama.json ADDED Viewed

@@ -0,0 +1,6 @@
+{
+  "$schema": "https://glama.ai/mcp/schemas/server.json",
+  "maintainers": [
+    "IgorGanapolsky"
+  ]
+}

package/hooks/hooks.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "hooks": {
     "PreToolUse": [
       {
-        "matcher": "Bash|Edit|Write",
+        "matcher": ".*",
         "hooks": [
           {
             "type": "command",