maestro-flow 0.3.11 → 0.3.13

package/workflows/memory.md

@@ -8,7 +8,7 @@ Two memory stores with different purposes:
 
 | Store | Path | Format | Index |
 |-------|------|--------|-------|
-| `workflow` | `.workflow/memory/` | `MEM-*.md`, `TIP-*.md` | `memory-index.json` |
+| `workflow` | `.workflow/memory/` | `MEM-*.md`, `TIP-*.md` | `.workflow/wiki-index.json` (unified, auto-managed by WikiIndexer) |
 | `system` | `~/.claude/projects/{project}/memory/` | `MEMORY.md` + topic `.md` files | None (flat files) |
 
 **System memory path detection:**
@@ -30,7 +30,7 @@ Detect both memory store paths:
 ```bash
 # Workflow memory
 WF_MEMORY_DIR=".workflow/memory"
-WF_INDEX_FILE="$WF_MEMORY_DIR/memory-index.json"
+WF_INDEX_FILE=".workflow/wiki-index.json"  # unified index (auto-managed by WikiIndexer)
 
 # System memory — derive from project git root or cwd
 PROJECT_ROOT=$(pwd)
@@ -40,7 +40,7 @@ SYS_MEMORY_DIR="$HOME/.claude/projects/$(echo "$PROJECT_ROOT" | sed 's|[/\\:]|-|
 ```
 
 Verify which stores exist:
-- Workflow: check `$WF_INDEX_FILE` exists
+- Workflow: check `.workflow/memory/` directory exists (index is auto-managed)
 - System: check `$SYS_MEMORY_DIR/MEMORY.md` exists
 
 If neither exists, report E001.
@@ -69,7 +69,7 @@ Parse arguments and detect subcommand:
 List entries from targeted stores.
 
 **Workflow store** (if exists):
-1. Read `memory-index.json`
+1. Use `maestro wiki list --type memory --json` (reads unified `.workflow/wiki-index.json`)
 2. Apply filters (--tag, --type, --before, --after)
 3. Sort by timestamp descending
 
@@ -108,7 +108,7 @@ Hints:
 Full-text search across both stores.
 
 **Workflow store:**
-1. Search `memory-index.json` fields: `summary`, `tags`, `id`
+1. Use `maestro wiki search "<query>" --json` or filter `.workflow/wiki-index.json` fields: `summary`, `tags`, `id`
 2. For deeper matches, read individual `.md` files and search content
 
 **System store:**
@@ -138,7 +138,7 @@ View: /manage-memory view <ID|filename>
 Display full content of a memory entry.
 
 **Workflow entry** (ID matches `MEM-*` or `TIP-*`):
-1. Validate ID exists in `memory-index.json`
+1. Validate ID exists via `maestro wiki get <id>` or in `.workflow/wiki-index.json`
 2. Read the corresponding `.md` file
 3. Display with metadata header
 
@@ -188,9 +188,9 @@ Changes: {summary of edits}
 Remove a memory entry or file.
 
 **Workflow entry:**
-1. Validate ID in `memory-index.json`
+1. Validate ID via `maestro wiki get <id>` or in `.workflow/wiki-index.json`
 2. Show summary, confirm with AskUserQuestion (unless --confirm)
-3. Remove `.md` file + index entry
+3. Remove `.md` file (WikiIndexer auto-updates index on next access)
 
 **System file:**
 1. Validate file exists (NEVER allow deleting MEMORY.md — only topic files)
@@ -213,7 +213,7 @@ Bulk cleanup — workflow store only.
 
 At least one filter required: --tag, --type, --before, --after.
 
-1. Read `memory-index.json`, apply filters
+1. Read `.workflow/wiki-index.json`, apply filters
 2. Display candidates table
 3. If `--dry-run`, stop after display
 4. Confirm with AskUserQuestion
@@ -232,9 +232,9 @@ Post-operation integrity check.
 
 **Workflow store:**
 1. Scan `.workflow/memory/` for `.md` files
-2. Compare with `memory-index.json` entries
+2. Compare with `.workflow/wiki-index.json` entries (type=memory)
 3. Report orphaned files or dangling references
-4. Offer to fix inconsistencies
+4. Offer to fix inconsistencies (WikiIndexer re-indexes on next write)
 
 **System store:**
 1. Check MEMORY.md links to topic files
@@ -260,13 +260,9 @@ Parse arguments and detect execution mode:
 
 ```bash
 MEMORY_DIR=".workflow/memory"
-INDEX_FILE="$MEMORY_DIR/memory-index.json"
 mkdir -p "$MEMORY_DIR"
-
-# Initialize index if not exists
-if [ ! -f "$INDEX_FILE" ]; then
-  echo '{"entries":[],"_metadata":{"created":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","version":"1.0"}}' > "$INDEX_FILE"
-fi
+# Note: wiki-index.json is auto-managed by WikiIndexer at .workflow/wiki-index.json
+# No manual index initialization needed
 ```
 
 When ambiguous, use AskUserQuestion:
@@ -355,36 +351,14 @@ Write entry file with sections:
 - Tags (from --tag flag)
 - Context (auto-detected from recent conversation files)
 
-### Step 4: Update Index
-
-Append entry metadata to memory-index.json.
-
-Read `memory-index.json`, append new entry to `entries[]`:
+### Step 4: Wiki Index (Auto-managed)
 
-```json
-{
-  "id": "MEM-20260315-143022",
-  "type": "compact",
-  "timestamp": "2026-03-15T14:30:22Z",
-  "file": "MEM-20260315-143022.md",
-  "summary": "Session objective in one line",
-  "tags": [],
-  "project_root": "/path/to/project",
-  "session_id": "WFS-001"
-}
-```
+Memory files are automatically indexed by WikiIndexer into the unified `.workflow/wiki-index.json`. No manual index update is needed — the persistent index is regenerated on next `maestro wiki` access or any write operation.
 
-For tips:
-```json
-{
-  "id": "TIP-20260315-143022",
-  "type": "tip",
-  "timestamp": "2026-03-15T14:30:22Z",
-  "file": "TIP-20260315-143022.md",
-  "summary": "First 80 chars of note content",
-  "tags": ["config", "redis"],
-  "project_root": "/path/to/project"
-}
+For immediate visibility after capture:
+```bash
+maestro wiki get memory-{slug}         # verify entry exists in wiki
+maestro wiki list --type memory        # list all memory entries
 ```
 
 ### Step 5: Report
@@ -400,7 +374,7 @@ Type:    compact
 Plan:    {plan_source} ({plan_line_count} lines preserved)
 
 To restore: Read .workflow/memory/{ENTRY_ID}.md
-To search:  Read .workflow/memory/memory-index.json
+To search:  maestro wiki list --type memory
 ```
 
 **Tip mode:**
@@ -410,33 +384,14 @@ Entry:   {ENTRY_ID}
 File:    .workflow/memory/{ENTRY_ID}.md
 Tags:    {tags}
 
-To search: Read .workflow/memory/memory-index.json
+To search: maestro wiki list --type memory --tag {tags}
 ```
 
 ---
 
-## Index Schema
-
-```json
-{
-  "entries": [
-    {
-      "id": "MEM-20260315-143022",
-      "type": "compact | tip",
-      "timestamp": "2026-03-15T14:30:22Z",
-      "file": "MEM-20260315-143022.md",
-      "summary": "One-line description",
-      "tags": [],
-      "project_root": "D:\\project",
-      "session_id": "WFS-001 | null"
-    }
-  ],
-  "_metadata": {
-    "created": "2026-03-15T00:00:00Z",
-    "version": "1.0"
-  }
-}
-```
+## Index
+
+Memory entries are indexed in the unified `.workflow/wiki-index.json` by WikiIndexer. Each memory file becomes a wiki entry of type `memory` with fields derived from frontmatter (id, title, tags, summary). Use `maestro wiki list --type memory --json` to query the index programmatically.
 
 ## Compact Entry Structure
 
@@ -492,5 +447,5 @@ Quick note for ideas, snippets, reminders.
 
 ## Retrieval
 
-Read `.workflow/memory/memory-index.json` to find entries by type, tags, or date.
-Read individual `.md` files for full content.
+Use `maestro wiki list --type memory` to find entries by type, tags, or date.
+Use `maestro wiki get <id>` or read individual `.md` files for full content.

package/workflows/merge.md

@@ -103,15 +103,18 @@ IF NOT target:
 completedPhases = []
 incompletePhases = []
 
-for (phaseNum of target.owned_phases):
-  NN = String(phaseNum).padStart(2, '0')
-  Glob: {target.path}/.workflow/phases/{NN}-*/index.json
-  Read → wtIndex
+// Read worktree state for artifact registry check
+Read {target.path}/.workflow/state.json → wtState (if exists)
+wtArtifacts = wtState?.artifacts ?? []
 
-  IF wtIndex.status === "completed":
-    completedPhases.push({ phase: phaseNum, index: wtIndex })
+// Check phase completeness via artifact registry
+for (phaseNum of target.owned_phases):
+  execArtifacts = wtArtifacts.filter(a => a.type === 'execute' && a.phase === phaseNum)
+  IF execArtifacts.some(a => a.status === 'completed'):
+    completedPhases.push({ phase: phaseNum })
   ELSE:
-    incompletePhases.push({ phase: phaseNum, status: wtIndex.status })
+    status = execArtifacts.length > 0 ? execArtifacts[0].status : 'no_execute_artifact'
+    incompletePhases.push({ phase: phaseNum, status })
 
 IF incompletePhases.length > 0 AND NOT force:
   WARN W002: "M{target.milestone_num} ({target.milestone}) has incomplete phases:"
@@ -181,51 +184,44 @@ Step_7:
 
 Display "Syncing workflow artifacts for M{target.milestone_num} ({target.milestone})..."
 
-// 7a: Copy all owned phase directories from worktree to main
-for (phaseNum of target.owned_phases):
-  NN = String(phaseNum).padStart(2, '0')
-  Glob: {target.path}/.workflow/phases/{NN}-*/
-  phaseDir = matched directory name
-
-  srcDir = target.path + "/.workflow/phases/" + phaseDir + "/"
-  dstDir = ".workflow/phases/" + phaseDir + "/"
-
-  Bash("cp -r {srcDir}* {dstDir}")
-
-// 7b: Atomic state reconciliation
 Read .workflow/state.json → mainState
 
-for (phaseNum of target.owned_phases):
-  NN = String(phaseNum).padStart(2, '0')
-  Glob: .workflow/phases/{NN}-*/index.json
-  Read → phaseIndex
-
-  IF phaseIndex.status === "completed":
-    mainState.phases_summary.completed += 1
-    mainState.phases_summary.pending -= 1
-    IF mainState.phases_summary.pending < 0:
-      mainState.phases_summary.pending = 0
-
-    mainState.transition_history = mainState.transition_history ?? []
-    mainState.transition_history.push({
-      milestone_num: target.milestone_num,
-      milestone: target.milestone,
-      phase: phaseNum,
-      action: "worktree_merge",
-      completed_at: phaseIndex.completed_at ?? getUtc8ISOString(),
-      branch: target.branch
-    })
-  ELSE IF phaseIndex.status !== "forked":
-    mainState.phases_summary.in_progress += 1
-    mainState.phases_summary.pending -= 1
-    IF mainState.phases_summary.pending < 0:
-      mainState.phases_summary.pending = 0
-
-  phaseIndex.updated_at = getUtc8ISOString()
-  Write .workflow/phases/{NN}-{slug}/index.json: phaseIndex
+// 7a: Copy scratch dirs from worktree to main
+Read {target.path}/.workflow/state.json → wtState
+wtArtifacts = wtState?.artifacts ?? []
+milestoneArtifacts = wtArtifacts.filter(a =>
+  a.path && (a.milestone === target.milestone || target.owned_phases.includes(a.phase))
+)
+for (art of milestoneArtifacts):
+  srcDir = target.path + "/.workflow/" + art.path
+  dstDir = ".workflow/" + art.path
+  IF directory_exists(srcDir):
+    Bash("mkdir -p {dstDir} && cp -r {srcDir}/* {dstDir}/")
+
+// 7b: Merge artifact registries
+mainArtifacts = mainState.artifacts ?? []
+existingIds = new Set(mainArtifacts.map(a => a.id))
+for (art of wtArtifacts):
+  IF existingIds.has(art.id):
+    // Update existing artifact status
+    idx = mainArtifacts.findIndex(a => a.id === art.id)
+    mainArtifacts[idx] = art
+  ELSE:
+    mainArtifacts.push(art)
+mainState.artifacts = mainArtifacts
+
+// Record merge in transition history
+mainState.transition_history = mainState.transition_history ?? []
+mainState.transition_history.push({
+  milestone_num: target.milestone_num,
+  milestone: target.milestone,
+  action: "worktree_merge",
+  completed_at: getUtc8ISOString(),
+  branch: target.branch,
+  phases: target.owned_phases
+})
 
 // Merge accumulated context from worktree
-Read target.path + "/.workflow/state.json" → wtState (if exists)
 IF wtState?.accumulated_context:
   for (decision of (wtState.accumulated_context.key_decisions ?? [])):
     IF NOT mainState.accumulated_context.key_decisions.includes(decision):
@@ -236,12 +232,12 @@ IF wtState?.accumulated_context:
 mainState.last_updated = getUtc8ISOString()
 Write .workflow/state.json: mainState
 
-// 7c: Update roadmap.md
+// 7c: Update roadmap.md (mark completed phases)
 Read .workflow/roadmap.md → roadmap
 for (phaseNum of target.owned_phases):
-  Read phase index → check if completed
-  IF completed:
-    Append " ✅ COMPLETED" to phase title line
+  isCompleted = completedPhases.some(p => p.phase === phaseNum)
+  IF isCompleted:
+    Append " ✅ COMPLETED" to phase title line in roadmap
 Write .workflow/roadmap.md: roadmap
 ```
 

package/workflows/milestone-complete.md

@@ -66,24 +66,41 @@ Check existing entries to avoid duplicates when appending in Step 3.
    - Extract patterns discovered
    - Extract pitfalls encountered
 
-2. Aggregate learnings and append to `.workflow/specs/learnings.md`:
+2. Aggregate learnings and append to `.workflow/specs/learnings.md` using `<spec-entry>` closed-tag format:
    ```
    For each strategy adjustment:
-     ### [YYYY-MM-DD HH:mm] decision: {summary}
+     <spec-entry category="learning" keywords="{auto-extracted}" date="{YYYY-MM-DD}" source="milestone-complete">
+
+     ### {summary}
+
      {content}
-     Milestone: {milestone} | Source: milestone-complete
+     Milestone: {milestone}
+
+     </spec-entry>
 
    For each pattern:
-     ### [YYYY-MM-DD HH:mm] pattern: {summary}
+     <spec-entry category="learning" keywords="{auto-extracted}" date="{YYYY-MM-DD}" source="milestone-complete">
+
+     ### {summary}
+
      {content}
-     Milestone: {milestone} | Source: milestone-complete
+     Milestone: {milestone}
+
+     </spec-entry>
 
    For each pitfall:
-     ### [YYYY-MM-DD HH:mm] bug: {summary}
+     <spec-entry category="learning" keywords="{auto-extracted}" date="{YYYY-MM-DD}" source="milestone-complete">
+
+     ### {summary}
+
      {content}
-     Milestone: {milestone} | Source: milestone-complete
+     Milestone: {milestone}
+
+     </spec-entry>
    ```
 
+   **Keyword extraction**: Extract 3-5 domain-specific terms from the content (same rules as `spec-add`).
+
 ---
 
 ## Step 4: Update State