@comfanion/workflow 4.37.2 → 4.38.1-dev.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@comfanion/workflow",
-  "version": "4.37.2",
+  "version": "4.38.1-dev.1",
   "description": "Initialize OpenCode Workflow system for AI-assisted development with semantic code search",
   "type": "module",
   "bin": {

package/src/build-info.json

@@ -1,6 +1,6 @@
 {
-  "version": "4.37.2",
-  "buildDate": "2026-01-26T20:36:35.766Z",
+  "version": "4.38.1-dev.1",
+  "buildDate": "2026-01-27T01:03:19.105Z",
   "files": [
     "config.yaml",
     "FLOW.yaml",

package/src/opencode/FLOW.yaml

@@ -254,6 +254,83 @@ pipeline:
     # IMPLEMENTATION PHASE
     # =========================================================================
     
+    - id: dev-sprint
+      name: Sprint Implementation (Full Workflow)
+      description: Implement entire sprint - all epics with auto-compaction
+      phase: implementation
+      command: /dev-sprint [sprint-number]
+      agent: dev
+      skills:
+        - dev-story
+        - test-design
+        - code-review
+      artifacts:
+        input:
+          - docs/sprint-artifacts/sprint-status.yaml
+          - docs/sprint-artifacts/backlog/epic-*.md
+          - CLAUDE.md
+        output:
+          - All epic implementations
+          - Updated sprint-status.yaml
+          - Sprint summary report
+      workflow:
+        description: |
+          Execute all epics in sprint sequentially:
+          1. Read sprint-status.yaml, find epics
+          2. For each epic: /dev-epic → compact
+          3. Continue until all epics done
+          4. Run sprint integration tests
+      config:
+        auto_compact: "config.yaml → epic_workflow.auto_compact"
+        auto_fix: "config.yaml → epic_workflow.auto_fix"
+      next: dev-epic  # Can also run individual epics
+    
+    - id: dev-epic
+      name: Epic Implementation (Full Workflow)
+      description: Implement entire epic - all stories with auto-compaction
+      phase: implementation
+      command: /dev-epic [epic-path]
+      agent: dev
+      skills:
+        - dev-story
+        - test-design
+        - code-review
+      artifacts:
+        input:
+          - docs/sprint-artifacts/backlog/epic-*.md
+          - docs/sprint-artifacts/sprint-*/.sprint-state/epic-*-state.yaml
+          - CLAUDE.md
+        output:
+          - All story implementations
+          - Epic state file (updated)
+          - Epic summary report
+      workflow:
+        description: |
+          Execute all stories in epic sequentially:
+          1. Read epic file, find stories
+          2. For each story: /dev-story → @reviewer → compact
+          3. Auto-fix review issues (max 3 attempts)
+          4. Continue until all stories done
+          5. Run epic integration tests
+        state_management:
+          location: "docs/sprint-artifacts/sprint-N/.sprint-state/epic-XX-state.yaml"
+          preserves:
+            - Current story index
+            - Completed stories
+            - Pending stories
+            - Review status
+        compaction:
+          trigger: "After each story completion"
+          restores:
+            - Epic state file (progress)
+            - Next story file (what to do)
+            - CLAUDE.md, PRD, Architecture (context)
+      config:
+        auto_compact: "config.yaml → epic_workflow.auto_compact"
+        auto_fix: "config.yaml → epic_workflow.auto_fix"
+        max_fix_attempts: "config.yaml → epic_workflow.max_fix_attempts"
+      next: dev-story  # Can also run individual stories
+    
     - id: dev-story
       name: Story Implementation
       description: Implement story using red-green-refactor cycle

package/src/opencode/commands/dev-epic.md

@@ -0,0 +1,19 @@
+---
+description: Execute full epic - implement all stories sequentially with auto-compaction between stories
+agent: dev
+---
+
+# /dev-epic Command
+
+Implement an entire epic by following the `dev-epic` skill.
+
+## Process
+
+1.  **Load Skill**: Read and follow the instructions in `.opencode/skills/dev-epic/SKILL.md`.
+2.  **Initialize**: Create the epic-level TODO list and the epic state file as described in the skill.
+3.  **Execute**: Enter the story -> review -> compact -> loop until all stories in the TODO list are complete.
+4.  **Finalize**: Run final tests and report completion.
+
+## IMPORTANT SKILLS TO LOAD
+
+- `dev-epic` - The primary algorithm for this command.

package/src/opencode/commands/dev-sprint.md

@@ -0,0 +1,19 @@
+---
+description: Execute full sprint - implement all epics sequentially with auto-compaction between epics
+agent: dev
+---
+
+# /dev-sprint Command
+
+Implement an entire sprint by following the `dev-sprint` skill.
+
+## Process
+
+1.  **Load Skill**: Read and follow the instructions in `.opencode/skills/dev-sprint/SKILL.md`.
+2.  **Initialize**: Create the sprint-level TODO list and update `sprint-status.yaml` as described in the skill.
+3.  **Execute**: Enter the epic -> review -> compact -> loop until all epics in the TODO list are complete.
+4.  **Finalize**: Run final sprint tests and report completion.
+
+## IMPORTANT SKILLS TO LOAD
+
+- `dev-sprint` - The primary algorithm for this command.

package/src/opencode/commands/dev-story.md

@@ -13,8 +13,17 @@ Implement a story using red-green-refactor cycle with TODO tracking.
 1. Find or load story file
 2. Load project context (CLAUDE.md, docs/prd.md, docs/architecture.md)
 3. Use skill dev-story, test-design
-3. **Create TODO list from story tasks** (for progress tracking)
-4. Mark story as `in-progress`
+4. **Create TODO list for full scope of work** (tasks + tests + review):
+   - Parse story file, extract all tasks
+   - Add each task to TODO
+   - **If `config.yaml → development.auto_review: true`**: Add review task to TODO
+   ```
+   [ ] Task 1: Create User entity
+   [ ] Task 2: Add repository
+   [ ] Task 3: Write integration tests
+   [ ] Code review by @reviewer    ← if auto_review: true
+   ```
+5. Mark story as `in-progress`
 
 ### Phase 2: Implementation (for each task)
 5. **Mark task as `in_progress` in TODO**

package/src/opencode/commands/quick.md

@@ -19,26 +19,23 @@ Automatically used when:
 - Single file or < 5 files affected
 - No new requirements needed
 - No architecture changes
-- Estimated time < 2 hours
+- T-shirt size: S or M
 
 ## Quick Workflow
 
 ```
 ┌────────────────────┐
-│ 1. Quick Doc       │  Create minimal change doc
-│    (2-5 min)       │
+│ 1. Quick Doc  [XS] │  Create minimal change doc
 └────────┬───────────┘
          │
          ▼
 ┌────────────────────┐
-│ 2. Implement       │  Make the change
-│    (varies)        │
+│ 2. Implement [S-M] │  Make the change
 └────────┬───────────┘
          │
          ▼
 ┌────────────────────┐
-│ 3. Test & Verify   │  Verify it works
-│    (5-10 min)      │
+│ 3. Test       [XS] │  Verify it works
 └────────┬───────────┘
          │
          ▼
@@ -119,7 +116,7 @@ For valid quick changes:
 ## Quick Change: [Title]
 
 **Scale:** L0 (Hotfix) / L1 (Small)
-**Estimated Time:** [X] minutes/hours
+**Size:** S / M
 
 ### Files to Modify
 

package/src/opencode/config.yaml

@@ -164,7 +164,6 @@ development:
   
   # Task structure
   task:
-    max_hours: 2           # Maximum hours per atomic task
     include_tests: true    # Each task includes test as validation
     require_interface: true # Interface defined before implementation
 
@@ -197,6 +196,53 @@ development:
         - NUMBERS     # Add metrics/numbers
         - LINK        # Add links/references
 
+# =============================================================================
+# EPIC WORKFLOW (/dev-epic command)
+# =============================================================================
+epic_workflow:
+  # Auto-compact between stories (saves context, continues next story)
+  # When true: story done → compact → restore context → next story
+  # When false: story done → ask user to continue
+  auto_compact: true
+  
+  # Auto-fix code review issues
+  # When true: review failed → @coder fixes → re-review → continue
+  # When false: review failed → HALT, ask user
+  auto_fix: true
+  
+  # Max fix attempts before HALT (prevents infinite loops)
+  max_fix_attempts: 3
+  
+  # Pause between stories for manual review
+  # When true: story done → show summary → ask to continue
+  # When false: story done → immediately start next story
+  pause_between_stories: false
+  
+  # Run integration tests after each story
+  # When true: story done → run integration tests → continue
+  # When false: skip per-story integration tests
+  test_after_each_story: false
+  
+  # Run integration tests after epic complete
+  # When true: all stories done → run epic integration tests
+  # When false: skip epic integration tests
+  test_after_epic: true
+  
+  # Compaction strategy
+  compaction:
+    # Save epic state to sprint-status.yaml
+    save_epic_state: true
+    
+    # Files to preserve in context after compaction
+    preserve_files:
+      - "CLAUDE.md"
+      - "AGENTS.md"
+      - "docs/prd.md"
+      - "docs/architecture.md"
+      - "docs/coding-standards/README.md"
+      - "docs/coding-standards/patterns.md"
+      # Epic file and next story added dynamically
+
 # =============================================================================
 # CHANGELOG
 # =============================================================================

package/src/opencode/opencode.json

@@ -4,9 +4,7 @@
   "instructions": [
     "AGENTS.md",
     ".opencode/FLOW.yaml",
-    ".opencode/config.yaml",
-    "docs/prd.md",
-    "docs/architecture.md"
+    ".opencode/config.yaml"
   ],
   
   "agent": {

package/src/opencode/plugins/README.md

@@ -52,10 +52,11 @@ Checks for updates and shows a toast notification if a newer version is availabl
 
 ### custom-compaction.ts
 
-Intelligent session compaction that preserves flow context.
+Intelligent session compaction that preserves flow context with epic workflow support.
 
 **Features:**
 - Tracks todo list and story task status
+- **Epic workflow state preservation** (new!)
 - Identifies critical documentation files for context
 - Generates smart continuation prompts
 - Differentiates between completed and interrupted tasks
@@ -68,8 +69,31 @@ Intelligent session compaction that preserves flow context.
 |----------|-------------------|
 | **Task Completed** | Summary of completed work, next steps, validation reminders |
 | **Task Interrupted** | Current task, what was done, resume instructions, file list |
+| **Epic in Progress** | Epic state file, current story, next action, minimal context |
+
+**Epic Workflow Support:**
+
+When `/dev-epic` is running, the plugin:
+1. Finds active epic state file in `sprint-N/.sprint-state/epic-XX-state.yaml`
+2. Reads current story from epic state
+3. Generates minimal read commands:
+   - Epic state file (progress tracking)
+   - Next story file (what to do)
+   - CLAUDE.md, PRD, Architecture (context)
+4. Agent resumes automatically without re-reading completed stories
+
+**Epic State File Location:**
+```
+docs/sprint-artifacts/
+  sprint-1/
+    .sprint-state/
+      epic-01-state.yaml    # Tracks epic-01 progress
+      epic-02-state.yaml    # Tracks epic-02 progress
+```
 
 **Critical Files Passed to Context:**
+
+**For regular /dev-story:**
 - `CLAUDE.md` - Project coding standards
 - `AGENTS.md` - Agent definitions
 - `project-context.md` - Project overview
@@ -79,6 +103,13 @@ Intelligent session compaction that preserves flow context.
 - `docs/coding-standards/*.md` - Coding patterns
 - Active story file (if in progress)
 
+**For /dev-epic workflow:**
+- Epic state file (e.g., `sprint-1/.sprint-state/epic-01-state.yaml`)
+- Next story file (from epic state)
+- `CLAUDE.md`, `AGENTS.md`, `docs/prd.md`, `docs/architecture.md`
+- ❌ **NOT** completed story files (saves context!)
+- ❌ **NOT** epic file (info in state file)
+
 ## Installation
 
 Plugins in `.opencode/plugins/` are automatically loaded by OpenCode.