create-universal-ai-context 2.4.0 → 2.6.0-final

package/templates/base/commands/rpi-research.md

@@ -1,88 +1,145 @@
----
-name: rpi-research
-version: "1.0.0"
-description: "RPI Research Phase: Systematic codebase exploration for feature/fix analysis"
-category: "rpi-orchestration"
-rpi_phase: "research"
-context_budget_estimate: "50K tokens"
-typical_context_usage: "25%"
-prerequisites: []
-outputs:
-  - "Research document in .ai-context/research/active/[name]_research.md"
-  - "File inventory with line references"
-  - "Call chain diagrams"
-  - "Dependency map"
-next_commands: ["/rpi-plan"]
-related_agents: ["context-engineer", "core-architect"]
-examples:
-  - command: "/rpi-research user-authentication"
-    description: "Research authentication flow for new feature"
-  - command: "/rpi-research payment-bug-fix"
-    description: "Investigate payment processing issue"
-exit_criteria:
-  - "Research document created in .ai-context/research/active/"
-  - "All relevant files identified (3-20 files)"
-  - "Call chains traced with line numbers"
-  - "Dependencies mapped"
-  - "150-word summary generated"
----
-
-# RPI Research Phase
-
-**Purpose:** Systematic, zero-code-modification exploration
-
-**Syntax:** `/rpi-research [feature-name]`
-
-**Example:**
-```bash
-/rpi-research user-authentication
-/rpi-research payment-bug-fix
-```
-
----
-
-## Execution Steps
-
-### Step 1: Initialize Research Document
-Create `.ai-context/research/active/[feature]_research.md` from RESEARCH_TEMPLATE.md
-
-### Step 2: Entry Point Discovery (3 parallel agents)
-- Agent 1: API/Route entry points
-- Agent 2: Business logic locations
-- Agent 3: Database/external integrations
-
-### Step 3: Call Chain Tracing
-- Read entry point files
-- Trace 3 levels deep
-- Record with file:line references
-
-### Step 4: Dependency Mapping
-- Internal service dependencies
-- External API dependencies
-
-### Step 5: Test Coverage Analysis
-- Find existing tests
-- Identify gaps
-
-### Step 6: Generate Summary
-- 150-word summary for Plan phase
-
----
-
-## Output
-
-Research document in `.ai-context/research/active/[feature]_research.md`
-
----
-
-## Context Budget
-
-- Target: 25% of 200k (50k tokens)
-- Compaction: After each major step
-- Final: ~20k tokens (research doc only)
-
----
-
-## Next Step
-
-After completion: `/rpi-plan [feature-name]`
+---
+name: rpi-research
+version: "2.0.0"
+description: "RPI Research Phase: Systematic codebase exploration with parallel agents and chunked output for rpi-plan consumption"
+category: "rpi-orchestration"
+rpi_phase: "research"
+context_budget_estimate: "50K tokens"
+typical_context_usage: "25%"
+parallel_agents: "3-5"
+chunk_output: true
+inter_phase_aware: true
+prerequisites: []
+outputs:
+  - "Research document in .ai-context/research/active/[name]_research.md"
+  - "Chunk manifest with 3-7 research chunks"
+  - "File inventory with line references per chunk"
+  - "Call chain diagrams per chunk"
+  - "Dependency map per chunk"
+  - "Inter-phase contract for rpi-plan"
+next_commands: ["/rpi-plan"]
+related_agents: ["context-engineer", "core-architect"]
+examples:
+  - command: "/rpi-research user-authentication"
+    description: "Research authentication flow with parallel agents creating chunked output"
+  - command: "/rpi-research payment-bug-fix"
+    description: "Investigate payment processing issue across multiple chunks"
+exit_criteria:
+  - "Research document created in .ai-context/research/active/"
+  - "Chunk manifest created with 3-7 chunks"
+  - "All chunks marked as COMPLETE"
+  - "All relevant files identified per chunk (3-20 files total)"
+  - "Call chains traced with line numbers per chunk"
+  - "Dependencies mapped per chunk"
+  - "150-word summary generated"
+  - "Inter-phase contract documented for rpi-plan"
+---
+
+# RPI Research Phase (Enhanced with Parallel Agents & Chunks)
+
+**Purpose:** Systematic, zero-code-modification exploration using parallel agents that produce chunk-structured output for rpi-plan consumption
+
+**Syntax:** `/rpi-research [feature-name]`
+
+**Example:**
+```bash
+/rpi-research user-authentication
+/rpi-research payment-bug-fix
+```
+
+---
+
+## Key Innovation: Inter-Phase Awareness
+
+RPI-Research **KNOWS** how RPI-Plan will consume its output:
+- Output is structured into research chunks (CHUNK-R1, CHUNK-R2, etc.)
+- Each chunk is self-contained with files, dependencies, and status
+- RPI-Plan will create a CHUNK-Pn todolist per CHUNK-Rn
+- Chunk manifest enables sequential processing by RPI-Plan
+
+---
+
+## Parallel Agent Strategy
+
+Spawn 3-5 parallel Explore agents, each focused on a specific domain:
+
+```
+┌─────────────────────────────────────────────────────────┐
+│ PARALLEL AGENT DISPATCH                                 │
+├─────────────────────────────────────────────────────────┤
+│ Agent 1: API/Route Entry Points        → CHUNK-R1      │
+│ Agent 2: Business Logic & Models       → CHUNK-R2      │
+│ Agent 3: Database/Storage Layer        → CHUNK-R3      │
+│ Agent 4: External Integrations         → CHUNK-R4      │
+│ Agent 5: Test Coverage Analysis        → CHUNK-R5      │
+└─────────────────────────────────────────────────────────┘
+```
+
+---
+
+## Execution Steps
+
+### Step 1: Initialize Research Document
+Create `.ai-context/research/active/[feature]_research.md` from RESEARCH_TEMPLATE.md
+
+### Step 2: Spawn Parallel Agents (3-5 agents)
+
+Each agent receives:
+- Feature name and objective
+- Assigned domain (API, Logic, DB, External, Tests)
+- Required output format (chunk structure)
+- Line number requirement for all file references
+
+### Step 3: Aggregate Chunk Results
+
+Collect outputs from all agents and structure into:
+- Chunk Manifest (table of all chunks with status)
+- Individual chunk sections with full details
+- Inter-phase contract specifying rpi-plan expectations
+
+### Step 4: Generate Summary
+
+Create 150-word summary that:
+- References key files from each chunk
+- Provides overview of feature implementation
+- Recommends approach for planning phase
+
+### Step 5: Finalize Inter-Phase Contract
+
+Document explicitly what RPI-Plan should expect:
+```
+EXPECTED_CONSUMER: rpi-plan
+CHUNK_PROCESSING_ORDER: sequential (R1 → R2 → R3 → R4 → R5)
+MARK_AS_PLANNED_WHEN: chunk todolist created
+REQUIRED_OUTPUT: CHUNK-Pn per CHUNK-Rn
+```
+
+---
+
+## Output Format
+
+### Chunk Manifest (Required)
+```markdown
+| Chunk ID | Domain | Status | Files | Ready for Planning |
+|----------|--------|--------|-------|-------------------|
+| CHUNK-R1 | API/Routes | COMPLETE | 3 | ✅ |
+| CHUNK-R2 | Business Logic | COMPLETE | 4 | ✅ |
+...
+```
+
+---
+
+## Context Budget
+
+- Target: 25% of 200k (50k tokens)
+- Per-agent budget: ~10k tokens each
+- Compaction: After each agent returns
+- Final: ~20k tokens (research doc only)
+
+---
+
+## Next Step
+
+After completion: `/rpi-plan [feature-name]`
+
+RPI-Plan will read chunk manifest and create CHUNK-Pn todolist per CHUNK-Rn

package/templates/base/commands/session-resume.md

@@ -1,144 +1,144 @@
----
-name: session-resume
-description: Resume a previous session with full context restoration
-version: 1.0.0
-category: session
-context_budget: 10000
-inputs:
-  - session/current/state.json
-  - session/history/**/*.json
-outputs:
-  - Restored session context
----
-
-# /session-resume
-
-Resume a previous session, restoring task context, loaded files reference, and pending updates.
-
-## Syntax
-
-```
-/session-resume [sessionId | --list | --last]
-```
-
-## Options
-
-| Option | Description |
-|--------|-------------|
-| `sessionId` | Resume specific session by ID |
-| `--list` | Show available sessions |
-| `--last` | Resume most recent session (default) |
-| `--checkpoint <id>` | Resume from specific checkpoint |
-
-## Examples
-
-### Resume Last Session
-```
-/session-resume
-```
-or
-```
-/session-resume --last
-```
-
-### List Available Sessions
-```
-/session-resume --list
-```
-Shows recent sessions with IDs, dates, and task names.
-
-### Resume Specific Session
-```
-/session-resume abc123-def456
-```
-
-### Resume from Checkpoint
-```
-/session-resume --checkpoint chk-789xyz
-```
-
-## What Gets Restored
-
-| Data | Action |
-|------|--------|
-| Phase | Set to previous RPI phase |
-| Task | Display task name and description |
-| Files | List files that were loaded (for re-loading) |
-| Pending Updates | Show queued doc updates |
-| Context | Suggest files to reload |
-
-## Resume Flow
-
-1. **Load Session State**
-   - Read from history or current state
-   - Validate session data
-
-2. **Display Summary**
-   ```
-   RESUMING SESSION
-
-   Session: abc123-def456
-   Started: 2025-01-24 10:30:00
-   Phase: implement (Step 3 of 5)
-   Task: Add user authentication
-
-   Files Previously Loaded:
-   - src/auth/login.py
-   - src/models/user.py
-   - tests/test_auth.py
-
-   Pending Documentation Updates: 3
-   - workflows/authentication.md (line numbers shifted)
-   - workflows/user-management.md (new function added)
-
-   Artifacts:
-   - research/active/user-auth_research.md
-   - plans/active/user-auth_plan.md
-   ```
-
-3. **Offer Actions**
-   - [Continue] - Proceed with task
-   - [Load Files] - Reload previously loaded files
-   - [Process Updates] - Run /auto-sync for pending updates
-   - [Start Fresh] - Archive and start new session
-
-## Session List Format
-
-```
-AVAILABLE SESSIONS
-
-ID                    Date        Phase      Task
-────────────────────────────────────────────────────────
-abc123-def456        2025-01-24  implement  Add user auth
-def789-ghi012        2025-01-23  research   Fix payment bug
-jkl345-mno678        2025-01-22  plan       Refactor API
-
-Use: /session-resume <ID>
-```
-
-## Integration with RPI
-
-When resuming during an RPI workflow:
-- **Research phase**: Shows research document path
-- **Plan phase**: Shows plan document path
-- **Implement phase**: Shows current step and remaining steps
-
-## Configuration
-
-In `.ai-context/settings.json`:
-```json
-{
-  "session": {
-    "max_history_days": 30,
-    "auto_archive_completed": true
-  }
-}
-```
-
-## Related Commands
-
-- `/session-save` - Save current session
-- `/collab handoff` - Create team handoff
-- `/rpi-research` - Start research phase
-- `/rpi-plan` - Start plan phase
-- `/rpi-implement` - Start implement phase
+---
+name: session-resume
+description: Resume a previous session with full context restoration
+version: 1.0.0
+category: session
+context_budget: 10000
+inputs:
+  - session/current/state.json
+  - session/history/**/*.json
+outputs:
+  - Restored session context
+---
+
+# /session-resume
+
+Resume a previous session, restoring task context, loaded files reference, and pending updates.
+
+## Syntax
+
+```
+/session-resume [sessionId | --list | --last]
+```
+
+## Options
+
+| Option | Description |
+|--------|-------------|
+| `sessionId` | Resume specific session by ID |
+| `--list` | Show available sessions |
+| `--last` | Resume most recent session (default) |
+| `--checkpoint <id>` | Resume from specific checkpoint |
+
+## Examples
+
+### Resume Last Session
+```
+/session-resume
+```
+or
+```
+/session-resume --last
+```
+
+### List Available Sessions
+```
+/session-resume --list
+```
+Shows recent sessions with IDs, dates, and task names.
+
+### Resume Specific Session
+```
+/session-resume abc123-def456
+```
+
+### Resume from Checkpoint
+```
+/session-resume --checkpoint chk-789xyz
+```
+
+## What Gets Restored
+
+| Data | Action |
+|------|--------|
+| Phase | Set to previous RPI phase |
+| Task | Display task name and description |
+| Files | List files that were loaded (for re-loading) |
+| Pending Updates | Show queued doc updates |
+| Context | Suggest files to reload |
+
+## Resume Flow
+
+1. **Load Session State**
+   - Read from history or current state
+   - Validate session data
+
+2. **Display Summary**
+   ```
+   RESUMING SESSION
+
+   Session: abc123-def456
+   Started: 2025-01-24 10:30:00
+   Phase: implement (Step 3 of 5)
+   Task: Add user authentication
+
+   Files Previously Loaded:
+   - src/auth/login.py
+   - src/models/user.py
+   - tests/test_auth.py
+
+   Pending Documentation Updates: 3
+   - workflows/authentication.md (line numbers shifted)
+   - workflows/user-management.md (new function added)
+
+   Artifacts:
+   - research/active/user-auth_research.md
+   - plans/active/user-auth_plan.md
+   ```
+
+3. **Offer Actions**
+   - [Continue] - Proceed with task
+   - [Load Files] - Reload previously loaded files
+   - [Process Updates] - Run /auto-sync for pending updates
+   - [Start Fresh] - Archive and start new session
+
+## Session List Format
+
+```
+AVAILABLE SESSIONS
+
+ID                    Date        Phase      Task
+────────────────────────────────────────────────────────
+abc123-def456        2025-01-24  implement  Add user auth
+def789-ghi012        2025-01-23  research   Fix payment bug
+jkl345-mno678        2025-01-22  plan       Refactor API
+
+Use: /session-resume <ID>
+```
+
+## Integration with RPI
+
+When resuming during an RPI workflow:
+- **Research phase**: Shows research document path
+- **Plan phase**: Shows plan document path
+- **Implement phase**: Shows current step and remaining steps
+
+## Configuration
+
+In `.ai-context/settings.json`:
+```json
+{
+  "session": {
+    "max_history_days": 30,
+    "auto_archive_completed": true
+  }
+}
+```
+
+## Related Commands
+
+- `/session-save` - Save current session
+- `/collab handoff` - Create team handoff
+- `/rpi-research` - Start research phase
+- `/rpi-plan` - Start plan phase
+- `/rpi-implement` - Start implement phase