@benzotti/jedi 0.1.19 → 0.1.21

package/dist/index.js

@@ -11403,7 +11403,13 @@ var actionCommand = defineCommand({
         ``,
         `- If the feedback is a **question** ("why did you...", "what about...", "can you explain..."), answer it conversationally first. If the answer implies a change is needed, explain that and then apply it.`,
         `- If the feedback is an **approval** ("approved", "lgtm", "looks good", "ship it"), finalise the current work \u2014 create commits and/or a PR as appropriate.`,
-        `- If the feedback is a **refinement** ("change task 2", "use a different approach", "add error handling"), explain what you're changing and why, then apply the changes. Present an updated summary when done.`,
+        `- If the feedback is a **refinement** ("change task 2", "use a different approach", "add error handling"), explain what you're changing and why, then apply the changes. Present an updated summary with the full updated plan in a collapsible block:`,
+        `   <details>`,
+        `   <summary>View full plan</summary>`,
+        `   `,
+        `   [full updated plan content here as markdown]`,
+        `   `,
+        `   </details>`,
         ``,
         `Read state.yaml and any existing plan files to understand what was previously done. Apply changes incrementally \u2014 do not restart from scratch.`
       ].join(`
@@ -11428,6 +11434,14 @@ The above is prior conversation on this issue for context.
             ticketContext ? `
 Use the ClickUp ticket above as the primary requirements source.` : ``,
             ``,
+            `## Scope Rules`,
+            `IMPORTANT: Only plan what was explicitly requested. Do NOT add extras like testing, linting, formatting, CI, or tooling unless the user asked for them.`,
+            `If something is ambiguous, ask \u2014 do not guess.`,
+            ``,
+            `## Learnings`,
+            `Before planning, read .jdi/persistence/learnings.md and .jdi/framework/learnings/ if they exist. Apply any team preferences found.`,
+            ``,
+            `## Presentation`,
             `Follow the planning workflow in your spec. When presenting the plan:`,
             `1. Start with a brief summary of the approach`,
             `2. Include the FULL plan in a collapsible details block using this format:`,
@@ -11437,7 +11451,8 @@ Use the ClickUp ticket above as the primary requirements source.` : ``,
             `   [full plan content here as markdown]`,
             `   `,
             `   </details>`,
-            `3. Ask for feedback. The user will respond via another GitHub comment.`
+            `3. After the plan, suggest 3-5 optional additions the user might want (e.g. "Would you also like testing? linting? state management?"). These are NOT part of the plan.`,
+            `4. Ask for feedback. The user will respond via another GitHub comment.`
           ].join(`
 `);
           break;
@@ -11641,7 +11656,7 @@ var setupActionCommand = defineCommand({
 // package.json
 var package_default = {
   name: "@benzotti/jedi",
-  version: "0.1.19",
+  version: "0.1.21",
   description: "JDI - Context-efficient AI development framework for Claude Code",
   type: "module",
   bin: {

package/framework/agents/jdi-planner.md

@@ -13,6 +13,25 @@ You create executable implementation plans with proper task sizing, dependency m
 
 ---
 
+## CRITICAL: Scope Discipline
+
+You MUST only plan what was explicitly requested. Never infer, assume, or add extras.
+
+**Rules:**
+1. **Only include what was asked for.** If the user says "react app with vite and typescript", plan exactly that — scaffold, config, and nothing else.
+2. **Do not add tooling, testing, linting, formatting, CI, or any other extras** unless the user explicitly requests them.
+3. **Do not make subjective decisions.** If something is ambiguous (e.g. folder structure, routing library, state management), list it as an open question and ask the user — do not guess.
+4. **Suggest optional additions separately.** After presenting the plan, list 3-5 common additions the user might want (e.g. "Would you also like: testing (Vitest)? linting (ESLint)? formatting (Prettier)?"). These are suggestions, NOT part of the plan.
+5. **Same request = same plan.** Two identical requests must produce structurally identical plans. Achieve this by following the templates exactly and not improvising.
+
+## CRITICAL: Read Learnings First
+
+Before planning, ALWAYS:
+1. Read `.jdi/persistence/learnings.md` if it exists
+2. Read `.jdi/framework/learnings/` files if they exist
+3. Apply any team preferences found (e.g. "always use path aliases", "prefer Zustand over Redux")
+4. Learnings override your defaults — if the team has a preference, follow it
+
 ## CRITICAL: File Writing is Mandatory
 
 You MUST write files using Write/Edit tools. Returning plan content as text is NOT acceptable.
@@ -39,12 +58,23 @@ Plan files use human-readable slugged names: `{phase}-{plan}-{slug}.{suffix}`
 
 ## Task Sizing
 
+Use t-shirt sizes instead of time estimates:
+
+| Size | Scope |
+|------|-------|
+| **S** | Single file change, simple logic |
+| **M** | 2-4 files, moderate logic or integration |
+| **L** | 5+ files, complex logic, multiple subsystems |
+| **XL** | Too large — must be split into multiple tasks |
+
 | Constraint | Value |
 |------------|-------|
-| Duration | 15-60 min per task |
 | Tasks per plan | 2-4 maximum |
 | Context target | ~50% of budget |
 | Each task | Independently verifiable |
+| Max task size | L (split XL into smaller tasks) |
+
+Never use time estimates. Use S/M/L sizing in task manifests and plan summaries.
 
 ---
 
@@ -118,7 +148,7 @@ Read `.jdi/config/variables.yaml` (create from template if missing). Update: `fe
 3. Write each task to `.jdi/plans/{phase}-{plan}-{slug}.T{n}.md` — follow template from `.jdi/framework/templates/PLAN-TASK.md`. One file per task.
 
 #### 7b: Update ROADMAP.yaml
-Add plan entry to appropriate phase section with wave and duration.
+Add plan entry to appropriate phase section with wave and sizing.
 
 #### 7c: Update REQUIREMENTS.yaml Traceability
 Map requirements to plan tasks.
@@ -134,7 +164,7 @@ task_files:
   - .jdi/plans/{phase}-{plan}-{slug}.T1.md
   - .jdi/plans/{phase}-{plan}-{slug}.T2.md
 task_count: {n}
-estimated_duration: {time}
+overall_size: S | M | L
 wave: {assigned_wave}
 provides: [what this plan delivers]
 ```

package/framework/templates/PLAN.md

@@ -62,11 +62,11 @@ tech_stack:
 
 ## Tasks
 
-| Task | Name | Type | Wave | File |
-|------|------|------|------|------|
-| T1 | {Task Name} | auto | 1 | `{X}-{YY}-{plan-slug}.T1.md` |
-| T2 | {Task Name} | auto | 1 | `{X}-{YY}-{plan-slug}.T2.md` |
-| T3 | {Task Name} | checkpoint:human-verify | 2 | `{X}-{YY}-{plan-slug}.T3.md` |
+| Task | Name | Size | Type | Wave | File |
+|------|------|------|------|------|------|
+| T1 | {Task Name} | S | auto | 1 | `{X}-{YY}-{plan-slug}.T1.md` |
+| T2 | {Task Name} | M | auto | 1 | `{X}-{YY}-{plan-slug}.T2.md` |
+| T3 | {Task Name} | S | checkpoint:human-verify | 2 | `{X}-{YY}-{plan-slug}.T3.md` |
 
 > Task details are in individual files. See `task_files` in frontmatter.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@benzotti/jedi",
-  "version": "0.1.19",
+  "version": "0.1.21",
   "description": "JDI - Context-efficient AI development framework for Claude Code",
   "type": "module",
   "bin": {