@benzotti/jedi 0.1.20 → 0.1.22

package/dist/index.js

@@ -9299,8 +9299,8 @@ You are Jedi, an AI development framework that uses specialised agents to plan,
 ## Identity
 
 You are **Jedi**, not Claude. Always refer to yourself as "Jedi" in your responses.
-Use "Jedi" in summaries, status updates, and sign-offs (e.g. "Jedi has completed..." not "Claude has completed...").
-End each response with a brief signature line: \`\u2014 Jedi\`
+Use "Jedi" in summaries and status updates (e.g. "Jedi has completed..." not "Claude has completed...").
+Do not add a signature line \u2014 the response is already branded by the Jedi CLI.
 
 ## Framework
 
@@ -9324,6 +9324,12 @@ Check \`.jdi/persistence/codebase-index.md\` for an indexed representation of th
 If it exists, use it for faster navigation. If it doesn't, consider generating one
 and saving it to \`.jdi/persistence/codebase-index.md\` for future runs.
 
+## Scope Discipline
+
+Only do what was explicitly requested. Do not add extras, tooling, or features the user did not ask for.
+If something is ambiguous, ask \u2014 do not guess.
+Use S/M/L t-shirt sizing, never time estimates.
+
 ## Workflow Routing
 
 Based on the user's request, follow the appropriate workflow:
@@ -11403,7 +11409,13 @@ 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(`
@@ -11621,7 +11633,7 @@ var setupActionCommand = defineCommand({
     consola.box([
       "Jedi GitHub Action Setup",
       "",
-      "Uses: anthropics/claude-code-action@v1",
+      "Uses: Jedi CLI via Claude Code",
       "Trigger: 'Hey Jedi' in issue/PR comments",
       "",
       "Required secrets (set via GitHub UI or CLI):",
@@ -11650,7 +11662,7 @@ var setupActionCommand = defineCommand({
 // package.json
 var package_default = {
   name: "@benzotti/jedi",
-  version: "0.1.20",
+  version: "0.1.22",
   description: "JDI - Context-efficient AI development framework for Claude Code",
   type: "module",
   bin: {

package/framework/agents/jdi-planner.md

@@ -58,12 +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.
 
 ---
 
@@ -137,7 +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.
@@ -153,7 +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": "0.1.20",
+  "version": "0.1.22",
   "description": "JDI - Context-efficient AI development framework for Claude Code",
   "type": "module",
   "bin": {