@benzotti/jedi 0.1.0

package/framework/components/quality/PRReviewLocal.md

@@ -0,0 +1,99 @@
+---
+name: PRReviewLocal
+category: quality
+description: Local-only review output (no GitHub comments)
+---
+
+# PRReviewLocal
+
+When `post="false"` or invoked as `<JDI:PRReview post="false" />`:
+
+Skip Steps 9-10 (posting to GitHub).
+
+Instead, write the full structured review to a file:
+
+## File Output
+
+1. **Create the directory** if it does not exist:
+   ```bash
+   mkdir -p .jdi/reviews
+   ```
+
+2. **Write the review file** to `.jdi/reviews/PR-{pr_number}-review.md` with the following structure:
+
+```markdown
+---
+pr: {pr_number}
+title: "{pr_title}"
+author: "{author}"
+branch: "{head_branch} -> {base_branch}"
+url: "{pr_url}"
+reviewed_at: "{ISO timestamp}"
+verdict: "{APPROVE | REQUEST_CHANGES}"
+findings:
+  blockers: {N}
+  major: {N}
+  minor: {N}
+  suggestions: {N}
+  questions: {N}
+  praise: {N}
+---
+
+# PR Review: #{pr_number}
+
+**Title:** {pr_title}
+**Author:** {author}
+**Branch:** {head_branch} -> {base_branch}
+**URL:** {pr_url}
+**Files changed:** {count}
+**Lines:** +{additions} / -{deletions}
+
+---
+
+## Summary
+
+{1-2 sentence overall assessment}
+
+**Verdict:** {APPROVE | REQUEST_CHANGES}
+
+---
+
+## Findings
+
+### {severity emoji} {Severity}: {title}
+**File:** `{path/to/file.ts}:{line}`
+
+{Description}
+
+**Suggested fix:**
+\`\`\`{language}
+{code}
+\`\`\`
+
+---
+
+## Checklist
+
+- [{x or space}] Logic is correct
+- [{x or space}] Edge cases handled
+- [{x or space}] Error handling appropriate
+- [{x or space}] Types are correct
+- [{x or space}] No security issues
+- [{x or space}] Tests cover changes
+- [{x or space}] Follows project patterns
+- [{x or space}] No performance concerns
+```
+
+**IMPORTANT:** Include ALL findings organised by severity (highest to lowest). Only include severity sections that have findings.
+
+3. **Confirm the file was written:**
+
+**Output:**
+```
+Review file written
+  - Path: .jdi/reviews/PR-{pr_number}-review.md
+  - Findings: {total_count} ({blockers} blockers, {major} major, {minor} minor, {suggestions} suggestions)
+  - Verdict: {APPROVE | REQUEST_CHANGES}
+```
+
+Then proceed to Step 11 (return to master).

package/framework/config/jdi-config.yaml

@@ -0,0 +1,159 @@
+# JDI Global Configuration
+# Edit these settings to customise JDI behaviour
+
+version: "1.0.0"
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Workflow Settings
+# ─────────────────────────────────────────────────────────────────────────────
+workflow:
+  # Mode: yolo (autonomous) | interactive (confirm gates) | strict (all confirmations)
+  mode: yolo
+
+  # Depth: shallow | standard | deep (affects task granularity)
+  depth: standard
+
+  # Enable parallel plan execution within waves
+  parallelisation: true
+
+  # Commit planning docs to git
+  commit_docs: true
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Agent Toggles
+# ─────────────────────────────────────────────────────────────────────────────
+agents:
+  # Run research phase before planning
+  research: true
+
+  # Validate plans before execution
+  plan_check: true
+
+  # Verify outcomes after execution
+  verifier: true
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Model Routing
+# ─────────────────────────────────────────────────────────────────────────────
+models:
+  # Active profile: quality | balanced | budget
+  profile: balanced
+
+  # Profile definitions (agent -> model mapping)
+  profiles:
+    # Maximum reasoning power, use for critical work (~100% token baseline)
+    quality:
+      planner: opus
+      architect: opus
+      executor: opus
+      verifier: sonnet
+      researcher: sonnet
+      phase_researcher: sonnet
+      plan_checker: sonnet
+      debugger: opus
+      quality: sonnet
+
+    # Smart allocation for typical development (~40% less than quality)
+    balanced:
+      planner: opus
+      architect: opus
+      executor: sonnet
+      verifier: sonnet
+      researcher: sonnet
+      phase_researcher: sonnet
+      plan_checker: sonnet
+      debugger: sonnet
+      quality: sonnet
+
+    # Minimal opus usage, conserve quota (~60% less than quality)
+    budget:
+      planner: sonnet
+      architect: sonnet
+      executor: sonnet
+      verifier: haiku
+      researcher: haiku
+      phase_researcher: haiku
+      plan_checker: haiku
+      debugger: sonnet
+      quality: haiku
+
+  # Override specific agents (null = use profile default)
+  overrides:
+    planner: null
+    executor: null
+    verifier: null
+    researcher: null
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Default Paths and Values
+# ─────────────────────────────────────────────────────────────────────────────
+defaults:
+  branch_prefix: "feature/"
+  commit_types:
+    - feat
+    - fix
+    - refactor
+    - docs
+    - test
+    - chore
+    - perf
+    - style
+  plan_location: .jdi/plans
+  state_location: .jdi
+  thoughts_location: .jdi/thoughts
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Git Settings
+# ─────────────────────────────────────────────────────────────────────────────
+git:
+  # Automatically stage changes before commit
+  auto_stage: false
+
+  # Require clean worktree before operations
+  require_clean_worktree: false
+
+  # Branches that cannot be directly modified
+  protected_branches:
+    - main
+    - master
+    - develop
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Quality Gates
+# ─────────────────────────────────────────────────────────────────────────────
+quality:
+  # Run linter before each commit
+  run_lint_before_commit: true
+
+  # Run tests before creating PR
+  run_tests_before_pr: true
+
+  # Require verification pass before marking complete
+  require_verification: true
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Context Management
+# ─────────────────────────────────────────────────────────────────────────────
+context:
+  # Maximum files to include per task context
+  max_files_per_task: 5
+
+  # Number of tasks before recommending split
+  split_threshold_tasks: 3
+
+  # Context budget thresholds (0.0 - 1.0)
+  context_budget_warning: 0.5   # Yellow zone
+  context_budget_critical: 0.7  # Red zone
+
+# ─────────────────────────────────────────────────────────────────────────────
+# UI Settings
+# ─────────────────────────────────────────────────────────────────────────────
+ui:
+  # Show progress banners during execution
+  show_progress_banners: true
+
+  # Enable verbose output
+  verbose_mode: false
+
+  # Use emoji in output (disabled for cleaner logs)
+  emoji_enabled: false

package/framework/config/state.yaml

@@ -0,0 +1,72 @@
+session:
+  id: null
+  started_at: null
+  last_activity: null
+
+project:
+  name: null
+  root: null
+  initialised: false
+  initialised_at: null
+
+position:
+  phase: null
+  phase_name: null
+  plan: null
+  plan_name: null
+  task: null
+  task_name: null
+  status: idle
+
+progress:
+  phases_total: 0
+  phases_completed: 0
+  plans_total: 0
+  plans_completed: 0
+  tasks_total: 0
+  tasks_completed: 0
+
+current_plan:
+  path: null
+  tasks: []
+  completed_tasks: []
+  current_task_index: null
+
+current_phase:
+  waves:
+    computed: false
+    total_waves: 0
+    current_wave: null
+    structure: []
+  plans_by_wave: {}
+
+worktree:
+  active: false
+  path: null
+  branch: null
+  created_at: null
+  type: null
+
+continuation:
+  file: null
+  paused_at: null
+  resume_action: null
+
+commits:
+  session_commits: []
+  last_commit_hash: null
+  last_commit_message: null
+
+checkpoints:
+  last_checkpoint: null
+  checkpoint_type: null
+  awaiting_response: false
+
+deviations: []
+
+blockers: []
+
+metadata:
+  context_usage_estimate: 0
+  agent_spawns: 0
+  errors_encountered: 0

package/framework/config/variables.yaml

@@ -0,0 +1,43 @@
+feature:
+  name: null
+  description: null
+  type: null
+  branch: null
+  pr_number: null
+  pr_url: null
+
+context:
+  clickup_task_id: null
+  clickup_task_url: null
+  figma_url: null
+  figma_node_id: null
+  requirements_source: null
+
+implementation:
+  approach: null
+  key_decisions: []
+  files_created: []
+  files_modified: []
+  dependencies_added: []
+
+review:
+  reviewer: null
+  review_status: null
+  comments_total: 0
+  comments_resolved: 0
+  changes_requested: []
+
+testing:
+  test_files: []
+  coverage_before: null
+  coverage_after: null
+  tests_added: 0
+  tests_passed: null
+
+references:
+  related_files: []
+  related_components: []
+  documentation_urls: []
+  api_endpoints: []
+
+custom: {}

package/framework/hooks/checkpoint.md

@@ -0,0 +1,196 @@
+---
+name: checkpoint
+description: Handles checkpoint interactions
+trigger: checkpoint_reached
+---
+
+# Checkpoint Hook
+
+Handles pausing execution and managing user interaction at checkpoints.
+
+---
+
+## Trigger
+
+Fires when:
+- Task type is `checkpoint:human-verify`
+- Task type is `checkpoint:decision`
+- Task type is `checkpoint:human-action`
+- Auth gate or credential requirement detected
+
+---
+
+## Checkpoint Types
+
+### human-verify
+
+User needs to test/verify something.
+
+**Flow:**
+1. Present what was built
+2. Provide verification steps
+3. Wait for "approved" or issues
+
+**Template:**
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ JDI ► CHECKPOINT: Verification Required
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Phase:** {phase} | **Plan:** {plan} | **Task:** {n}/{total}
+
+## What Was Built
+
+{Summary of completed work}
+
+## Please Verify
+
+1. {Step 1}
+2. {Step 2}
+3. {Step 3}
+
+## Expected Behaviour
+
+{What you should see}
+
+───────────────────────────────────────────────────────────────
+
+Reply "approved" to continue, or describe any issues found.
+```
+
+### decision
+
+User needs to make a choice.
+
+**Flow:**
+1. Present decision context
+2. Show options with trade-offs
+3. Record choice and rationale
+
+**Template:**
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ JDI ► CHECKPOINT: Decision Required
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Decision:** {What needs to be decided}
+
+## Context
+
+{Why this decision matters}
+
+## Options
+
+| Option | Pros | Cons |
+|--------|------|------|
+| A: {option} | {pros} | {cons} |
+| B: {option} | {pros} | {cons} |
+| C: {option} | {pros} | {cons} |
+
+## Recommendation
+
+{If applicable, what we recommend and why}
+
+───────────────────────────────────────────────────────────────
+
+Reply with your choice (A/B/C) and any additional context.
+```
+
+### human-action
+
+User needs to do something manually.
+
+**Flow:**
+1. Explain what's needed
+2. Provide steps
+3. Wait for "done" confirmation
+4. Verify action worked
+
+**Template:**
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ JDI ► CHECKPOINT: Manual Action Required
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Action:** {What you need to do}
+
+## Why This Can't Be Automated
+
+{Reason - credentials, external system, etc.}
+
+## Steps
+
+1. {Step 1}
+2. {Step 2}
+3. {Step 3}
+
+## How to Verify
+
+{How we'll confirm it worked}
+
+───────────────────────────────────────────────────────────────
+
+Reply "done" when complete.
+```
+
+---
+
+## State Management
+
+On checkpoint:
+
+```yaml
+checkpoints:
+  last_checkpoint: "{timestamp}"
+  checkpoint_type: "{type}"
+  checkpoint_task: "{task_id}"
+  awaiting_response: true
+```
+
+On response:
+
+```yaml
+checkpoints:
+  awaiting_response: false
+  last_response: "{user_response}"
+  response_at: "{timestamp}"
+```
+
+---
+
+## Response Handling
+
+### "approved" / "done"
+- Continue to next task
+- Clear awaiting_response
+
+### Issues described
+- Parse user feedback
+- Return to task with feedback context
+- Address issues
+- Re-present checkpoint
+
+### Decision made
+- Record decision
+- Record rationale if provided
+- Apply decision to remaining work
+- Continue execution
+
+---
+
+## Timeout Behaviour
+
+If checkpoint awaits response for extended time:
+- State preserved in state.yaml
+- Can resume with `/jdi-implement-plan --resume`
+- Progress is not lost
+
+---
+
+## Outputs
+
+| Output | Purpose |
+|--------|---------|
+| Checkpoint display | User interaction |
+| State update | Track checkpoint |
+| Decision record | Document choices |

package/framework/hooks/jdi-worktree-cleanup.md

@@ -0,0 +1,123 @@
+---
+name: jdi-worktree-cleanup
+description: Clean up git worktree and associated branch after execution
+---
+
+# Worktree Cleanup Hook
+
+Clean up the git worktree and associated branch after worktree-based execution completes.
+
+---
+
+## When to Execute
+
+This hook is invoked after worktree execution completes, either:
+- After a **merge** (branch was merged into current branch)
+- After a **discard** (changes were discarded)
+
+---
+
+## Cleanup Steps
+
+### 1. Remove the Git Worktree
+
+```bash
+git worktree remove .worktrees/jdi-{plan-id} --force
+```
+
+The `--force` flag is used to handle cases where the worktree has uncommitted changes (which shouldn't happen in normal flow but provides safety).
+
+### 2. Delete the Branch
+
+**If branch was merged:**
+```bash
+git branch -d jdi/{plan-id}
+```
+Uses `-d` (safe delete) since the branch was already merged.
+
+**If branch was NOT merged (discard):**
+```bash
+git branch -D jdi/{plan-id}
+```
+Uses `-D` (force delete) since the branch was never merged.
+
+### 3. Remove Empty Worktrees Directory
+
+```bash
+rmdir .worktrees 2>/dev/null
+```
+
+Only removes the directory if it's empty. Silently fails if other worktrees exist.
+
+---
+
+## Error Handling
+
+### Worktree Removal Fails
+
+If the worktree removal fails (e.g., uncommitted changes, locked files):
+
+```
+⚠️ Warning: Could not remove worktree automatically.
+
+Manual cleanup commands:
+  git worktree remove .worktrees/jdi-{plan-id} --force
+  rm -rf .worktrees/jdi-{plan-id}
+```
+
+### Branch Deletion Fails
+
+If the branch deletion fails:
+
+```
+⚠️ Warning: Could not delete branch automatically.
+
+Manual cleanup command:
+  git branch -D jdi/{plan-id}
+```
+
+---
+
+## State Update
+
+After cleanup, update `.jdi/config/state.yaml`:
+
+1. Read `.jdi/config/state.yaml`
+2. Clear any worktree-related state:
+   ```yaml
+   worktree:
+     active: false
+     path: null
+     branch: null
+   ```
+3. Write the updated YAML back
+
+---
+
+## Full Cleanup Sequence
+
+```bash
+# 1. Remove worktree
+git worktree remove .worktrees/jdi-{plan-id} --force
+
+# 2. Delete branch (use -d if merged, -D if not)
+git branch -d jdi/{plan-id}  # or -D for discarded
+
+# 3. Clean up empty directory
+rmdir .worktrees 2>/dev/null
+
+# 4. Update state (handled by Read/Write tools)
+```
+
+---
+
+## Usage Example
+
+Called from `jdi-implement-plan.md` Step 3: Post-Execution:
+
+```
+After user selects "merge" or "discard":
+1. If merge: git merge jdi/{plan-id}
+2. Invoke this cleanup hook
+3. Report cleanup complete
+```