@ryuenn3123/agentic-senior-core 3.0.29 → 3.0.31

package/.agent-context/rules/efficiency-vs-hype.md

@@ -2,15 +2,17 @@
 
 ## Latest-Compatible-First Rule
 
-The LLM may choose modern libraries and tooling when they fit the project. This rule does not prefer "no library" or any fixed dependency set.
+The LLM may choose modern libraries and tooling when they fit the project. This rule does not prefer "no library", "always add a library", or any fixed dependency set.
+
+New dependencies are allowed when they create a better practical tradeoff than custom implementation. The decision should be based on whether the dependency meaningfully improves efficiency, shortens delivery time, improves correctness, reduces maintenance burden, or avoids unnecessary in-house code.
 
 Before adding or recommending a dependency:
 - check current official docs, release notes, and setup guidance when the ecosystem decision matters
 - choose the latest stable compatible dependency version unless a project constraint blocks it
 - use the official scaffolder or setup command when it creates the current supported project shape
 - Only step down to an older dependency version after documenting the exact compatibility, runtime, platform, or ecosystem reason.
-- explain why the dependency improves maintainability, UX, performance, security, or delivery speed
+- explain why the dependency is a better tradeoff than local implementation for the current task
 - avoid packages that are stale, thinly maintained, too heavy for the job, or added only because they are popular
 - keep dependency boundaries replaceable when the library would spread through many files
 
-Reject offline dependency decisions, outdated tutorial versions, and trend choices that are not grounded in the current repo and brief.
+Reject offline dependency decisions, outdated tutorial versions, trend choices, and dependency avoidance choices that are not grounded in the current repo, brief, and delivery tradeoffs.

package/.agent-context/state/memory-continuity-benchmark.json

@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-04-25T11:56:18.296Z",
+  "generatedAt": "2026-04-26T02:26:19.926Z",
   "reportName": "memory-continuity-benchmark",
   "schemaVersion": "1.0.0",
   "passed": true,

package/.cursorrules

@@ -1,6 +1,6 @@
 # AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
 
-Generated by Agentic-Senior-Core CLI v3.0.29
+Generated by Agentic-Senior-Core CLI v3.0.31
 Timestamp: 2026-04-24T06:02:48.303Z
 Selected policy file: .agent-context/policies/llm-judge-threshold.json
 

package/.gemini/instructions.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 5c955eab4c644e7139c0c5a5609ea9af7d47fdc8e69617f407af01ccc8c64e43
+Canonical Snapshot SHA256: c2aef70028abc43f5e3f110a2fa90086cd6697bac42ec97a8d4db3c4477880d4
 
 Canonical policy source: [.instructions.md](../.instructions.md).
 

package/.github/copilot-instructions.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 5c955eab4c644e7139c0c5a5609ea9af7d47fdc8e69617f407af01ccc8c64e43
+Canonical Snapshot SHA256: c2aef70028abc43f5e3f110a2fa90086cd6697bac42ec97a8d4db3c4477880d4
 
 The canonical policy source for this repository is [.instructions.md](../.instructions.md).
 

package/.instructions.md

@@ -29,7 +29,7 @@ Available engineering rule files:
 - `error-handling.md` - Never swallow errors, use typed error codes
 - `testing.md` - Test pyramid, behavior over implementation
 - `git-workflow.md` - Conventional commits and change hygiene
-- `efficiency-vs-hype.md` - Latest-compatible, stable deps over trendy ones
+- `efficiency-vs-hype.md` - Practical dependency and tooling decisions over trend or avoidance bias
 - `api-docs.md` - OpenAPI 3.1 and public surface documentation
 - `microservices.md` - Evidence-required service splits and distributed-system boundaries
 - `event-driven.md` - Idempotency and event boundaries
@@ -38,7 +38,7 @@ Available engineering rule files:
 - `frontend-architecture.md` - UI structure, anti-generic boundaries, responsive mutation
 - `docker-runtime.md` - Latest-docs-first Dockerfile and Compose generation
 
-**What to do**: Resolve only the rule files relevant to the current task. Do not read the entire rule directory by default. For UI-only work, start with `bootstrap-design.md` and `frontend-architecture.md` and keep backend or DevOps rules unloaded unless the task explicitly crosses those boundaries. For Docker or Compose work, load `docker-runtime.md` and verify the latest official Docker docs before authoring container assets. For framework or package setup work, use the latest stable compatible dependency set and official setup flow unless a documented compatibility constraint blocks it.
+**What to do**: Resolve only the rule files relevant to the current task. Do not read the entire rule directory by default. For UI-only work, start with `bootstrap-design.md` and `frontend-architecture.md` and keep backend or DevOps rules unloaded unless the task explicitly crosses those boundaries. For Docker or Compose work, load `docker-runtime.md` and verify the latest official Docker docs before authoring container assets. For framework or package setup work, use the latest stable compatible dependency set and official setup flow unless a documented compatibility constraint blocks it. New dependencies are allowed when they produce a better practical tradeoff than custom implementation, including meaningful efficiency, delivery-time, correctness, or maintainability gains.
 
 ### Global Backend/API Governance Routing
 

package/.windsurfrules

@@ -1,6 +1,6 @@
 # AGENTIC-SENIOR-CORE DYNAMIC GOVERNANCE RULESET
 
-Generated by Agentic-Senior-Core CLI v3.0.29
+Generated by Agentic-Senior-Core CLI v3.0.31
 Timestamp: 2026-04-24T06:02:48.303Z
 Selected policy file: .agent-context/policies/llm-judge-threshold.json
 

package/AGENTS.md

@@ -2,7 +2,7 @@
 
 Adapter Mode: thin
 Adapter Source: .instructions.md
-Canonical Snapshot SHA256: 5c955eab4c644e7139c0c5a5609ea9af7d47fdc8e69617f407af01ccc8c64e43
+Canonical Snapshot SHA256: c2aef70028abc43f5e3f110a2fa90086cd6697bac42ec97a8d4db3c4477880d4
 
 This file is an adapter entrypoint for agent discovery.
 The canonical policy source is [.instructions.md](.instructions.md).

package/README.md

@@ -10,13 +10,12 @@
 **Production-grade Rules Engine (Governance Engine) for AI coding agents.**
 Works with Cursor, Windsurf, GitHub Copilot, Claude Code, Gemini, and other LLM-powered IDE workflows.
 
-Latest release: 3.0.29 (2026-04-25).
+Latest release: 3.0.30 (2026-04-25).
 
-Highlights in 3.0.29:
-- UI design contracts now require deterministic `anchorReference` traceability through `derivedTokenLogic` before implementation.
-- Compiled UI context can surface a top-of-file anchor commitment header from `docs/design-intent.json` so the creative direction is not buried under governance.
-- Library decisions now must be verified against current official docs or marked `pending-verification` with native/project-local fallbacks.
-- Release gate now validates the design-intent seed for token derivation and library verification completeness.
+Highlights in 3.0.30:
+- Root `mcp.json` now reflects the current 9-layer governance model instead of the old 8-layer metadata.
+- MCP knowledge metadata now includes 15 rules, 4 prompts including `bootstrap-design`, and the project-context layer.
+- MCP workflow wording now reinforces scope-first relevant-layer injection instead of eager load-all context.
 
 </div>
 

package/mcp.json

@@ -1,14 +1,14 @@
 {
-  "version": "1.0",
+  "version": "1.1",
   "name": "agentic-senior-core",
-  "description": "MCP configuration for governance-aware diagnostics and self-healing workflows with dynamic knowledge injection.",
+  "description": "MCP configuration for governance-aware diagnostics, scoped rule loading, and self-healing workflows with dynamic knowledge injection.",
   "knowledgeLayers": {
     "enabled": true,
-    "description": "8-layer dynamic knowledge injection for AI agents",
+    "description": "9-layer dynamic knowledge injection for AI agents",
     "layers": {
       "rules": {
         "path": ".agent-context/rules",
-        "count": 14,
+        "count": 15,
         "autoLoad": true
       },
       "stack-strategies": {
@@ -29,9 +29,9 @@
       },
       "prompts": {
         "path": ".agent-context/prompts",
-        "count": 3,
+        "count": 4,
         "autoLoad": true,
-        "templates": ["init-project", "refactor", "review-code"]
+        "templates": ["init-project", "bootstrap-design", "refactor", "review-code"]
       },
       "governance-modes": {
         "path": "dynamic",
@@ -41,13 +41,19 @@
       },
       "state": {
         "path": ".agent-context/state",
-        "count": 6,
+        "count": 22,
         "autoLoad": true
       },
       "policies": {
         "path": ".agent-context/policies",
         "count": 1,
         "autoLoad": true
+      },
+      "project-context": {
+        "path": "docs",
+        "count": 0,
+        "autoLoad": false,
+        "sources": ["project-brief", "architecture-decision-record", "flow-overview", "api-contract", "database-schema", "DESIGN", "design-intent"]
       }
     }
   },
@@ -76,15 +82,16 @@
     "full-knowledge-injection": {
       "trigger": ["workspace.initialize", "agent.start"],
       "steps": [
-        "load_all_knowledge_layers",
-        "inject_rules",
-        "inject_stack_strategies",
-        "inject_architecture_playbooks",
+        "resolve_scope_first",
+        "inject_relevant_rules",
+        "inject_runtime_decision_signals",
+        "inject_structural_planning_signals",
         "inject_execution_contracts",
         "inject_prompts",
         "inject_governance_modes",
         "inject_state",
-        "inject_policies"
+        "inject_policies",
+        "inject_project_context_when_relevant"
       ]
     }
   }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ryuenn3123/agentic-senior-core",
-  "version": "3.0.29",
+  "version": "3.0.31",
   "type": "module",
   "description": "Force your AI Agent to code like a Staff Engineer, not a Junior.",
   "bin": {