@benzotti/jedi 0.1.2 → 0.1.4

package/framework/agents/jdi-backend.md

@@ -9,7 +9,7 @@ requires_components: []
 
 # JDI Backend Engineer
 
-**Learnings**: Read `.jdi/framework/learnings/backend.md` before starting work — follow them.
+**Learnings**: Read `.jdi/persistence/learnings.md` for consolidated team learnings, then `.jdi/framework/learnings/backend.md` for backend-specific conventions — follow them.
 
 You are the Backend Engineer. **Lead mode**: architect APIs, design schemas, review quality. **Senior mode**: implement features using Action/DTO/FormRequest pattern, write Pest tests.
 

package/framework/agents/jdi-devops.md

@@ -9,7 +9,7 @@ requires_components: []
 
 # JDI DevOps Engineer
 
-**Learnings**: Read `.jdi/framework/learnings/devops.md` before starting work — follow them.
+**Learnings**: Read `.jdi/persistence/learnings.md` for consolidated team learnings, then `.jdi/framework/learnings/devops.md` for devops-specific conventions — follow them.
 
 You are the DevOps Engineer. **Lead mode**: design infrastructure, deployment strategies, monitoring. **Senior mode**: manage dev environments, build processes, developer tooling.
 

package/framework/agents/jdi-executor.md

@@ -9,7 +9,7 @@ requires_components: [Verify, Commit, StateUpdate]
 
 # JDI Executor Agent
 
-**Learnings**: Read `.jdi/framework/learnings/general.md` before starting work — follow them.
+**Learnings**: Read `.jdi/persistence/learnings.md` for consolidated team learnings, then `.jdi/framework/learnings/general.md` for general conventions — follow them.
 
 You execute plan tasks with atomic commits, handle deviations, and maintain progress tracking.
 

package/framework/agents/jdi-feedback-learner.md

@@ -1,6 +1,6 @@
 ---
 name: jdi-feedback-learner
-description: Analyses PR review comments to extract learning opportunities and update project rules
+description: Analyses PR review comments to extract learning opportunities and update learnings files
 category: quality
 team: Quality Assurance
 model: sonnet
@@ -9,7 +9,7 @@ requires_components: []
 
 # JDI Feedback Learner Agent
 
-You analyse PR review comments for learning phrases and update project rule files accordingly.
+You analyse PR review comments for learning phrases and update learnings files accordingly.
 
 ## Learning Phrase Detection
 
@@ -26,13 +26,13 @@ You analyse PR review comments for learning phrases and update project rule file
 
 ## Categorisation
 
-| File Extension | Category | Target File |
-|----------------|----------|-------------|
-| .php | backend | .claude/rules/BACKEND_PATTERNS.md |
-| .ts, .tsx | frontend | .claude/rules/FRONTEND_PATTERNS.md |
-| routes/ | api | .claude/rules/API_ENDPOINTS.md |
-| .yaml, .json | config | .claude/rules/LEARNED_PATTERNS.md |
-| Other | general | .claude/rules/LEARNED_PATTERNS.md |
+| Content Scope | Category | Target File |
+|---------------|----------|-------------|
+| API, database, backend logic | backend | `.jdi/framework/learnings/backend.md` |
+| Components, hooks, UI, styling | frontend | `.jdi/framework/learnings/frontend.md` |
+| Tests, assertions, coverage | testing | `.jdi/framework/learnings/testing.md` |
+| CI/CD, Docker, infrastructure | devops | `.jdi/framework/learnings/devops.md` |
+| Cross-cutting, process, general | general | `.jdi/framework/learnings/general.md` |
 
 ---
 
@@ -41,11 +41,12 @@ You analyse PR review comments for learning phrases and update project rule file
 1. Receive PR comments from feedback command
 2. Scan for learning phrases (case-insensitive)
 3. Extract actionable rules from context
-4. Categorise by file type and content
+4. Categorise by content scope (see table above)
 5. Format as rule entries
-6. Check for duplicates
-7. Update appropriate rule files
-8. Report learnings extracted
+6. Check for duplicates in the target file
+7. Append to the appropriate `.jdi/framework/learnings/{category}.md` file
+8. Consolidate all category files into `.jdi/persistence/learnings.md` for cross-PR persistence
+9. Report learnings extracted
 
 ---
 
@@ -54,8 +55,7 @@ You analyse PR review comments for learning phrases and update project rule file
 ```markdown
 ### {Rule Title}
 
-**Source:** PR review feedback
-**Date:** {YYYY-MM-DD}
+**Source:** PR #{number} review ({reviewer_name})
 **Type:** {preferred_pattern | anti_pattern | convention | standard}
 
 {Clear description of the rule}
@@ -85,8 +85,9 @@ learnings_found: {count}
 rules_added: {count}
 duplicates_skipped: {count}
 files_updated:
-  - path: ".claude/rules/BACKEND_PATTERNS.md"
+  - path: ".jdi/framework/learnings/backend.md"
     rules_added: 1
+persistence_updated: true
 ```
 
-**Scope**: Detect learning phrases, extract rules, categorise, update rule files. Will NOT invent rules not in comments or override conflicting rules.
+**Scope**: Detect learning phrases, extract rules, categorise, update learnings files, persist consolidated learnings. Will NOT invent rules not in comments or override conflicting rules.

package/framework/agents/jdi-frontend.md

@@ -9,7 +9,7 @@ requires_components: []
 
 # JDI Frontend Engineer
 
-**Learnings**: Read `.jdi/framework/learnings/frontend.md` before starting work — follow them.
+**Learnings**: Read `.jdi/persistence/learnings.md` for consolidated team learnings, then `.jdi/framework/learnings/frontend.md` for frontend-specific conventions — follow them.
 
 You are the Frontend Engineer. **Lead mode**: architect component hierarchies, design state patterns, review quality. **Senior mode**: implement components, hooks, forms, data-fetching.
 

package/framework/agents/jdi-pr-feedback.md

@@ -76,6 +76,8 @@ For each learning found:
 | `devops.md` | CI/CD, Docker, infrastructure, build config | jdi-devops |
 | `general.md` | Cross-cutting concerns, conventions, process | jdi-executor |
 
+After updating category files, also write the consolidated learnings to `.jdi/persistence/learnings.md` so they persist across PRs via the GitHub Actions cache.
+
 If zero learnings found, output brief explanation why in feedback report under `## Learnings`.
 
 ### Step 6: Process All Comments

package/framework/agents/jdi-quality.md

@@ -9,7 +9,7 @@ requires_components: [Verify]
 
 # JDI Quality Agent
 
-**Learnings**: Read `.jdi/framework/learnings/testing.md` before starting work — follow them.
+**Learnings**: Read `.jdi/persistence/learnings.md` for consolidated team learnings, then `.jdi/framework/learnings/testing.md` for testing-specific conventions — follow them.
 
 You ensure software quality through testing strategies, edge case detection, and quality standards enforcement.
 

package/package.json

@@ -1,11 +1,15 @@
 {
   "name": "@benzotti/jedi",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "description": "JDI - Context-efficient AI development framework for Claude Code",
   "type": "module",
   "bin": {
     "jdi": "./dist/index.js"
   },
+  "exports": {
+    ".": "./dist/index.js",
+    "./storage": "./src/storage/index.ts"
+  },
   "scripts": {
     "build": "bun build src/index.ts --outdir dist --target bun",
     "dev": "bun run src/index.ts",
@@ -22,7 +26,8 @@
   },
   "files": [
     "dist",
-    "framework"
+    "framework",
+    "action"
   ],
   "repository": {
     "type": "git",