@crypto512/jicon-mcp 2.2.1 → 2.3.0

package/TOOL_LIST.md

@@ -5,8 +5,8 @@ This document provides a comprehensive reference of all available tools in the J
 
 ## Summary
 
-**Total Tools**: 79
-- **Jira Tools**: 26 (21 read + 5 write)
+**Total Tools**: 80
+- **Jira Tools**: 27 (22 read + 5 write)
 - **Confluence Tools**: 21 (13 read + 8 write)
 - **Tempo Tools**: 13 (10 read + 3 write)
 - **Buffer Tools**: 11
@@ -17,7 +17,7 @@ This document provides a comprehensive reference of all available tools in the J
 - **PlantUML Tools**: 3
 
 **Note**: All data-heavy tools (search, list, get) **always** return buffered responses with metadata for origin tracking:
-- **JSON arrays**: Use `buffer_get_items` for complete items, `buffer_pipeline` for reports
+- **JSON arrays**: Use `buffer_get_items` for complete items, `buffer_transform` for reports
 - **XHTML**: Use `buffer_get_element` for element-based access
 - **Search**: Use `buffer_grep` to search within any buffer
 
@@ -49,7 +49,7 @@ JSON responses include `suggestedNextTools` based on context:
   "bufferId": "buf_xxx",
   "structure": { "type": "array", "itemCount": 500 },
   "suggestedNextTools": [
-    { "tool": "buffer_pipeline", "description": "Transform to table/report (98% token reduction)", "condition": "for Confluence reports" },
+    { "tool": "buffer_transform", "description": "Transform to table/report (98% token reduction)", "condition": "for Confluence reports" },
     { "tool": "buffer_get_items", "description": "Get complete items for AI analysis", "condition": "for detailed analysis" },
     { "tool": "buffer_grep", "description": "Search within results" }
   ]
@@ -111,7 +111,7 @@ When XHTML validation fails, the response includes element ID and suggested acti
 #### Jira Search → Confluence Report
 ```
 1. jira_search_issues(jql) → bufferId, suggestedNextTools
-2. buffer_pipeline(bufferId, pipeline) → tableBufferId (98% token reduction)
+2. buffer_transform(inputs, code) → tableBufferId (98% token reduction)
 3. confluence_edit(pageId) → pageBufferId, structure
 4. buffer_edit(pageBufferId, after=ID, fromBufferId=tableBufferId)
 5. confluence_draft_create(pageId, pageBufferId, autoRetry=true) → draft URL
@@ -121,7 +121,7 @@ When XHTML validation fails, the response includes element ID and suggested acti
 ```
 1. tempo_get_user_info() → workerKey
 2. tempo_get_worklogs(dateFrom, dateTo, workerKey) → bufferId, suggestedNextTools
-3. buffer_pipeline(bufferId, groupBy=project, sum=hours) → summaryBufferId
+3. buffer_transform(bufferId, groupBy=project, sum=hours) → summaryBufferId
 4. Use in report or display directly
 ```
 
@@ -137,7 +137,7 @@ When XHTML validation fails, the response includes element ID and suggested acti
 
 ---
 
-## Jira Tools (25)
+## Jira Tools (27)
 
 ### Localization / Non-English Jira
 
@@ -194,7 +194,7 @@ The server automatically handles localized changelog field names for activity tr
 }
 ```
 
-**Returns**: `bufferId` with issues. Use `buffer_pipeline` for tables, `buffer_get_items` for AI analysis.
+**Returns**: `bufferId` with issues. Use `buffer_transform` for tables, `buffer_get_items` for AI analysis.
 
 ---
 
@@ -366,7 +366,28 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 14. jira_get_board
+### 14. jira_list_boards
+**Description**: List all Jira Agile boards (Scrum and Kanban). Entry point for board discovery.
+**Use Cases**: Discover available boards, filter by project or type, find board IDs
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| projectKeyOrId | string | ✗ | Filter by project key or ID |
+| type | string | ✗ | Filter by board type ("scrum" or "kanban") |
+| name | string | ✗ | Filter by board name (contains) |
+
+**Returns**: `bufferId` with boards array. Each board has `id`, `name`, `type`, `projectKey`.
+
+**Examples**:
+```
+jira_list_boards()                         # All boards
+jira_list_boards(projectKeyOrId="PROJ")    # Boards for project
+jira_list_boards(type="scrum")             # Only Scrum boards
+```
+
+---
+
+### 15. jira_get_board
 **Description**: Get Agile board information
 **Use Cases**: View board details, get board configuration
 
@@ -378,7 +399,7 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 15. jira_get_sprints
+### 16. jira_get_sprints
 **Description**: List all sprints for a board
 **Use Cases**: View active sprints, check sprint schedules
 
@@ -391,7 +412,7 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 16. jira_get_sprint_issues
+### 17. jira_get_sprint_issues
 **Description**: Get all issues in a specific sprint
 **Use Cases**: View sprint backlog, check sprint progress
 
@@ -403,7 +424,7 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 17. jira_get_issue_watchers
+### 18. jira_get_issue_watchers
 **Description**: Get list of watchers on an issue
 **Use Cases**: See who's following an issue
 
@@ -413,7 +434,7 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 18. jira_get_issue_worklogs
+### 19. jira_get_issue_worklogs
 **Description**: Retrieve all worklogs from a Jira issue
 **Use Cases**: Analyze time logged against an issue, see worklog history
 
@@ -425,7 +446,7 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 19. jira_get_total_worklogs
+### 20. jira_get_total_worklogs
 **Description**: Get total worklogs for an issue and all its children recursively
 **Use Cases**: Get total time spent on an Epic including all stories and sub-tasks
 
@@ -437,7 +458,7 @@ The server automatically handles localized changelog field names for activity tr
 
 ---
 
-### 20. jira_list_epic_children
+### 21. jira_list_epic_children
 **Description**: List all children of an Epic/Initiative without needing JQL
 **Use Cases**: Get Epic children, list Initiative epics, find issue hierarchy
 
@@ -460,7 +481,7 @@ Automatically detects Epic Link and Parent Link fields for language-independent
 
 ---
 
-### 21. jira_get_activity_digest
+### 22. jira_get_activity_digest
 **Description**: Get recent activity across issues for LLM analysis. Returns DIRECTLY (not buffered).
 **Use Cases**: Project activity summary, team updates, blocker detection, weekly reports
 
@@ -501,7 +522,7 @@ Fetches comments, status changes, priority changes, and assignee changes - forma
 
 ---
 
-### 22. jira_get_recent_comments
+### 23. jira_get_recent_comments
 **Description**: Get comments across multiple issues for discussion analysis. Returns DIRECTLY (not buffered).
 **Use Cases**: Discussion summaries, finding comments about specific topics, tracking team communication
 
@@ -521,7 +542,7 @@ Fetches comments, status changes, priority changes, and assignee changes - forma
 
 ---
 
-### 23. jira_get_changelog
+### 24. jira_get_changelog
 **Description**: Get field changes across issues for tracking what happened. Returns DIRECTLY (not buffered).
 **Use Cases**: Status change tracking, priority escalation analysis, assignment history
 
@@ -551,7 +572,7 @@ Fetches comments, status changes, priority changes, and assignee changes - forma
 
 ---
 
-### 24. jira_analyze_epic
+### 25. jira_analyze_epic
 **Description**: Comprehensive Epic/Feature analysis for LLM insights. Returns DIRECTLY (not buffered).
 **Use Cases**: Epic progress analysis, velocity tracking, time metrics, feature status
 
@@ -596,7 +617,7 @@ Currently **3 issues** are in progress.
 
 ---
 
-### 25. jira_epic_summary
+### 26. jira_epic_summary
 **Description**: Lightweight Epic/Initiative summary with hierarchy and status breakdown. Returns DIRECTLY (not buffered).
 **Use Cases**: Quick Epic overview, status breakdown, cross-project dependencies
 
@@ -643,7 +664,7 @@ Provides quick overview without the heavy metrics of `jira_analyze_epic` - no ti
 
 ---
 
-### 26. jira_analyze_sprint
+### 27. jira_analyze_sprint
 **Description**: Comprehensive Sprint analysis for LLM insights. Returns DIRECTLY (not buffered).
 **Use Cases**: Sprint progress, risk assessment, team workload, daily standups
 
@@ -1402,13 +1423,13 @@ Aggregates Tempo worklogs and returns ranked results in markdown format.
 
 ---
 
-## Buffer Tools (11)
+## Buffer Tools (12)
 
 Buffer tools are used for local content management. All buffer operations are in-memory - write enforcement is on Jira/Confluence/Tempo tools.
 
 **XHTML Editing**: `buffer_edit` uses element IDs for precise positioning in XHTML content. Each element gets a unique ID when loaded - use `buffer_get_structure` to see them. `buffer_validate_xhtml` validates Confluence storage format. XHTML validation is also automatically applied before any Confluence write operation.
 
-**Data Pipelines**: `buffer_pipeline` transforms JSON buffers (from Jira/Tempo searches) with server-side filtering, grouping, sorting, and output generation - minimizing token usage.
+**Data Transformation**: `buffer_transform` transforms JSON buffers (from Jira/Tempo searches) with JavaScript code for filtering, grouping, sorting, and output generation - minimizing token usage.
 
 ### 1. buffer_create
 **Description**: Create a new buffer with initial content. Returns bufferId and structure.
@@ -1417,7 +1438,7 @@ Buffer tools are used for local content management. All buffer operations are in
 
 **Content types**:
 - **xhtml**: Confluence storage format. Returns element IDs for `buffer_edit`.
-- **json**: JSON data (array or object). Use `buffer_get_items` to access, `buffer_pipeline` to transform.
+- **json**: JSON data (array or object). Use `buffer_get_items` to access, `buffer_transform` to transform.
 
 **Use Cases**: Draft new Confluence pages, prepare content before persisting, create JSON arrays for aggregation
 
@@ -1632,14 +1653,14 @@ buffer_set_items({
 ---
 
 ### 5. buffer_list
-**Description**: List all active buffers with their metadata
-**Use Cases**: View active buffers, check expiration times
+**Description**: List all active buffers with their metadata. Buffers are cleaned up when session ends. Max buffers per session configurable via JICON_MAX_BUFFERS (default: 10); oldest unmodified evicted first when full.
+**Use Cases**: View active buffers, recover lost buffer IDs
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
 | (none) | | | |
 
-**Response includes**: `count`, list of buffers with `bufferId`, `totalSize`, `createdAt`, `expiresAt`, `metadata`
+**Response includes**: `count`, list of buffers with `bufferId`, `totalSize`, `createdAt`, `metadata`
 
 ---
 
@@ -1677,253 +1698,228 @@ buffer_set_items({
 
 ---
 
-### 8. buffer_pipeline
-**Description**: Transform JSON buffer data with a declarative pipeline: select fields, filter, group/aggregate, sort, format, and output to various formats.
-**Use Cases**: Server-side data transformation to minimize token usage, generate XHTML tables for Confluence, export to CSV/Markdown, aggregate statistics
-
-**Token Efficiency**: A pipeline that filters, sorts, and outputs a table executes in **1 tool call** instead of iterating through items. For pure data transforms, this achieves **98% token reduction**.
-
-**Schema Quick Reference:**
-```json
-{
-  "sourceBufferId": "buf_xxx",
-  "pipeline": {
-    "select": { "fields": [...] },
-    "filter": [...],
-    "groupBy": { "field": "...", "aggregations": [...] },
-    "sort": [...],
-    "limit": 10,
-    "format": [...],
-    "output": { "type": "xhtml_table", "table": {...} }
-  }
-}
-```
-
-**Common Mistakes:**
+### 8. buffer_transform
+**Description**: Execute JavaScript code in a secure QuickJS sandbox to transform buffer data.
+**Use Cases**: Server-side data transformation with full JavaScript expressiveness, generate XHTML tables for Confluence, custom filtering/grouping/aggregation
 
-| Wrong | Correct | Why |
-|-------|---------|-----|
-| `sortBy: [...]` | `sort: [...]` | Key name is "sort" not "sortBy" |
-| `transform: "map"` | `transform: "date"` | Valid: uppercase, lowercase, date, number, boolean, string |
-| No `output` | `output: {...}` | Required field - pipeline must have output |
-| `pipeline: "{...}"` | `pipeline: {...}` | Must be object, not JSON string |
-| After select: `sort: [{field: "issueType"}]` | `sort: [{field: "Type"}]` | After `select` renames "issueType" to "Type", use NEW name |
+**Token Efficiency**: A transformation generates complete output in **1 tool call** instead of iterating through items. For pure data transforms, this achieves **98% token reduction**.
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
-| bufferId | string | ✓ | Source buffer ID containing JSON array |
-| pipeline | object | ✓ | Pipeline definition (see below) |
+| inputs | object | ✓ | Map of variable name to buffer ID. Example: `{ issues: "buf_abc123" }` |
+| code | string | ✓ | JavaScript code to execute (ES2020, synchronous). Access inputs as globals, return value becomes output buffer. |
+| limits | object | ✗ | Optional `{ timeout: 5000, memory: 50000000 }` (default: 5s, 50MB) |
 
-**Type Requirement**: Buffer must have `contentType: "json"`. Returns error if buffer is XHTML or plain text.
+**Type Requirement**: All input buffers must have `contentType: "json"`. Returns error if buffer is XHTML or plain text.
 
-**Pipeline Definition:**
+**Built-in Helper Functions (available as globals):**
 
-```typescript
-{
-  // Stage 1: Select specific fields (optional)
-  select?: {
-    fields: [
-      { from: "key" },                           // Keep field as-is
-      { from: "priority.name", as: "Priority" }, // Rename field
-      { from: "created", transform: "date" }     // Transform value
-    ]
-  },
+| Category | Function | Description |
+|----------|----------|-------------|
+| **Aggregation** | `groupBy(array, keyOrFn)` | Group array by field or function → `{ key: items[] }` |
+| | `sum(array, field?)` | Sum numeric values |
+| | `avg(array, field?)` | Average numeric values |
+| | `min(array, field?)` | Minimum value |
+| | `max(array, field?)` | Maximum value |
+| | `count(array)` | Count items |
+| | `unique(array, field?)` | Unique values |
+| **Object** | `get(obj, 'path.to.field')` | Deep get with dot notation |
+| | `pick(obj, ['a', 'b'])` | Pick specific keys |
+| | `omit(obj, ['a'])` | Omit specific keys |
+| **Date** | `parseDate(string)` | Parse date → timestamp (ms) |
+| | `formatDate(ts, fmt?)` | Format timestamp (fmt: 'date', 'time', 'datetime', 'iso') |
+| | `daysBetween(d1, d2)` | Days between two dates |
+| **Output** | `toTable(array, config)` | Generate Confluence XHTML table |
+| | `toList(array, config)` | Generate Confluence XHTML list |
+| | `toMarkdownTable(array, config)` | Generate Markdown table |
+| | `toMarkdownList(array, config)` | Generate Markdown list |
 
-  // Stage 2: Filter items (optional, AND logic between conditions)
-  filter?: [
-    { field: "status.name", operator: "ne", value: "Done" },
-    { field: "priority.name", operator: "in", value: ["High", "Critical"] }
-  ],
+**Context Variables (for link generation):**
+- `JIRA_URL` - Jira base URL (from server config)
+- `CONFLUENCE_URL` - Confluence base URL (from server config)
 
-  // Stage 3: Group and aggregate (optional)
-  groupBy?: {
-    field: "assignee.displayName",
-    aggregations: [
-      { function: "count", as: "totalIssues" },
-      { function: "sum", field: "timeSpent", as: "totalTime" },
-      { function: "list", field: "key", as: "issueKeys" }
-    ]
-  },
+**toTable() Configuration:**
 
-  // Stage 4: Sort results (optional)
-  sort?: [
-    { field: "priority.name", direction: "asc" },
-    { field: "key", direction: "desc" }
+```javascript
+toTable(array, {
+  title: 'Table Title',           // Optional h2 above table
+  showRowNumbers: true,           // Add # column
+  tableClass: 'confluenceTable',  // CSS class
+  columns: [
+    { field: 'key', header: 'Issue', link: { type: 'jira' } },
+    { field: 'summary', header: 'Summary', width: '40%' },
+    { field: 'priority.name', header: 'Priority', align: 'center' }
   ],
-
-  // Stage 5: Limit results (optional)
-  limit?: 50,
-
-  // Stage 6: Conditional formatting (optional)
-  format?: [
+  format: [  // Conditional styling
     {
-      condition: { field: "priority.name", operator: "eq", value: "High" },
-      style: { color: "#dc3545", bold: true }
-    },
-    {
-      condition: { field: "status.name", operator: "eq", value: "Done" },
-      style: { color: "#28a745", icon: "✓" }
+      condition: { field: 'priority.name', operator: 'eq', value: 'Blocker' },
+      style: { color: '#d04437', bold: true, icon: '🔴' },
+      fields: ['priority.name']  // Apply to specific fields (or omit for row)
     }
-  ],
+  ]
+})
+```
 
-  // Stage 7: Output configuration (REQUIRED)
-  output: {
-    type: "xhtml_table",  // or "xhtml_list", "json", "csv", "markdown"
-    table: {
-      title: "Open Issues",
-      columns: [
-        { field: "key", header: "Issue", link: { type: "jira" } },
-        { field: "summary", header: "Summary" },
-        { field: "priority.name", header: "Priority" }
-      ]
+**toList() Configuration:**
+
+```javascript
+toList(array, {
+  title: 'List Title',
+  style: 'bullet',  // 'bullet', 'numbered', 'none'
+  template: '{{key}}: {{summary}} ({{assignee.displayName}})'
+})
+```
+
+**toMarkdownTable() Configuration:**
+
+```javascript
+toMarkdownTable(array, {
+  title: 'Table Title',           // Optional ## heading
+  showRowNumbers: true,           // Add # column
+  columns: [
+    { field: 'key', header: 'Issue', link: { type: 'jira' } },
+    { field: 'summary', header: 'Summary' },
+    { field: 'priority.name', header: 'Priority', align: 'center' }
+  ],
+  format: [  // Conditional styling (bold/italic in Markdown)
+    {
+      condition: { field: 'priority.name', operator: 'eq', value: 'Blocker' },
+      style: { bold: true, icon: '🔴' },
+      fields: ['priority.name']
     }
-  }
-}
+  ]
+})
+// Returns: { __markdown: true, content: "| # | Issue | Summary |..." }
 ```
 
-**Filter Operators:**
-
-| Operator | Description | Example |
-|----------|-------------|---------|
-| `eq` | Equals | `{ field: "status.name", operator: "eq", value: "Open" }` |
-| `ne` | Not equals | `{ field: "status.name", operator: "ne", value: "Done" }` |
-| `gt`, `lt`, `gte`, `lte` | Numeric comparison | `{ field: "priority.id", operator: "gt", value: 2 }` |
-| `contains` | Substring match (case-insensitive) | `{ field: "summary", operator: "contains", value: "bug" }` |
-| `startsWith`, `endsWith` | String prefix/suffix | `{ field: "key", operator: "startsWith", value: "PROJ-" }` |
-| `in`, `notIn` | Value in array | `{ field: "priority.name", operator: "in", value: ["High", "Critical"] }` |
-| `exists`, `notExists` | Field presence | `{ field: "assignee", operator: "exists" }` |
-| `empty`, `notEmpty` | Empty string/array/null | `{ field: "labels", operator: "notEmpty" }` |
-| `regex` | Regular expression | `{ field: "summary", operator: "regex", value: "^\\[BUG\\]" }` |
-
-**Aggregation Functions:**
-
-| Function | Description | Requires `field` |
-|----------|-------------|------------------|
-| `count` | Count items in group | No |
-| `sum` | Sum numeric values | Yes |
-| `avg` | Average numeric values | Yes |
-| `min`, `max` | Min/max numeric values | Yes |
-| `first`, `last` | First/last value | Yes |
-| `list` | Collect all values | Yes |
-| `unique` | Unique values | Yes |
-
-**Output Types:**
-
-| Type | Description | Config |
-|------|-------------|--------|
-| `xhtml_table` | Confluence-compatible table | `table: { title?, columns: [...], showRowNumbers? }` |
-| `xhtml_list` | Confluence-compatible list | `list: { title?, template: "{{key}}: {{summary}}", style?: "bullet"|"numbered"|"none" }` |
-| `json` | Clean JSON array | `includeMetadata?: boolean` |
-| `csv` | CSV with headers | `table: { columns: [...] }` |
-| `markdown` | Markdown table | `table: { columns: [...] }` |
-
-**Column Configuration:**
+**toMarkdownList() Configuration:**
 
-```typescript
-{
-  field: "key",                    // Field path (dot notation)
-  header: "Issue",                 // Column header text
-  link?: { type: "jira" },         // Auto-link (jira, confluence, url)
-  width?: "100px",                 // Column width
-  align?: "left" | "center" | "right"
-}
+```javascript
+toMarkdownList(array, {
+  title: 'List Title',
+  style: 'bullet',    // 'bullet', 'numbered', 'task'
+  template: '{{key}}: {{summary}} ({{assignee.displayName}})'
+})
+// Returns: { __markdown: true, content: "- PROJ-1: Fix bug..." }
 ```
 
-**Response includes**: `bufferId` (new output buffer), `inputItems`, `outputItems`, `pipelineStages`, `outputType`, `preview`, `bufferSizeBytes`, `structure` (for XHTML), `hint`
+**Link Types:**
+- `jira` - Auto-links to Jira issue using `key` field
+- `confluence` - Links to Confluence page by ID
+- `custom` - Custom URL template with `{{field}}` placeholders
+
+**Format Condition Operators:** `eq`, `ne`, `gt`, `lt`, `gte`, `lte`, `contains`, `startsWith`, `endsWith`, `in`, `notIn`, `exists`, `notExists`, `regex`, `empty`, `notEmpty`
+
+**Response includes**: `bufferId` (new output buffer), `contentType` (json, xhtml, or markdown), `itemCount` (for arrays), `hint`
 
 **Example - Filter and output table:**
-```typescript
+```javascript
 // Search returns bufferId with 500 issues
 jira_search_issues({ jql: "project = PROJ" })
 // -> { bufferId: "buf_issues", structure: { itemCount: 500 } }
 
 // Transform in ONE call (instead of iterating 500 items)
-buffer_pipeline({
-  bufferId: "buf_issues",
-  pipeline: {
-    filter: [
-      { field: "issuetype.name", operator: "eq", value: "Bug" },
-      { field: "status.name", operator: "ne", value: "Done" }
-    ],
-    sort: [{ field: "priority.name", direction: "asc" }],
-    limit: 20,
-    format: [
-      { condition: { field: "priority.name", operator: "eq", value: "High" },
-        style: { color: "#dc3545", bold: true } }
-    ],
-    output: {
-      type: "xhtml_table",
-      table: {
-        title: "Top 20 Open Bugs",
-        columns: [
-          { field: "key", header: "Issue", link: { type: "jira" } },
-          { field: "summary", header: "Summary" },
-          { field: "priority.name", header: "Priority" },
-          { field: "assignee.displayName", header: "Assignee" }
-        ]
-      }
-    }
-  }
+buffer_transform({
+  inputs: { issues: "buf_issues" },
+  code: `
+    const bugs = issues.filter(i =>
+      i.issuetype?.name === 'Bug' &&
+      i.status?.name !== 'Done'
+    );
+    bugs.sort((a, b) => (a.priority?.id || 0) - (b.priority?.id || 0));
+    const top20 = bugs.slice(0, 20);
+
+    return toTable(top20, {
+      title: 'Top 20 Open Bugs',
+      columns: [
+        { field: 'key', header: 'Issue', link: { type: 'jira' } },
+        { field: 'summary', header: 'Summary' },
+        { field: 'priority.name', header: 'Priority' },
+        { field: 'assignee.displayName', header: 'Assignee' }
+      ],
+      format: [
+        { condition: { field: 'priority.name', operator: 'eq', value: 'High' },
+          style: { color: '#dc3545', bold: true } }
+      ]
+    });
+  `
 })
-// -> { bufferId: "buf_result", outputItems: 15, preview: "<table>...", structure: [...] }
+// -> { bufferId: "buf_result", contentType: "xhtml" }
 ```
 
-**Example - Group by assignee with aggregations:**
-```typescript
-buffer_pipeline({
-  bufferId: "buf_issues",
-  pipeline: {
-    filter: [{ field: "status.name", operator: "ne", value: "Done" }],
-    groupBy: {
-      field: "assignee.displayName",
-      aggregations: [
-        { function: "count", as: "issueCount" },
-        { function: "list", field: "key", as: "issues" }
+**Example - Group by assignee with statistics:**
+```javascript
+buffer_transform({
+  inputs: { issues: "buf_issues" },
+  code: `
+    const open = issues.filter(i => i.status?.name !== 'Done');
+    const byAssignee = groupBy(open, 'assignee.displayName');
+
+    const stats = Object.entries(byAssignee).map(([name, items]) => ({
+      assignee: name || 'Unassigned',
+      count: items.length,
+      issues: items.map(i => i.key).join(', ')
+    }));
+
+    stats.sort((a, b) => b.count - a.count);
+
+    return toTable(stats, {
+      title: 'Issues by Assignee',
+      columns: [
+        { field: 'assignee', header: 'Assignee' },
+        { field: 'count', header: 'Count', align: 'right' },
+        { field: 'issues', header: 'Issue Keys' }
       ]
-    },
-    sort: [{ field: "issueCount", direction: "desc" }],
-    output: {
-      type: "xhtml_table",
-      table: {
-        title: "Issues by Assignee",
-        columns: [
-          { field: "displayName", header: "Assignee" },
-          { field: "issueCount", header: "Count" },
-          { field: "issues", header: "Issues" }
-        ]
-      }
-    }
-  }
+    });
+  `
 })
 ```
 
-**Example - Export to CSV:**
-```typescript
-buffer_pipeline({
-  bufferId: "buf_issues",
-  pipeline: {
-    select: {
-      fields: [
-        { from: "key" },
-        { from: "summary" },
-        { from: "status.name", as: "Status" },
-        { from: "created", transform: "date" }
+**Example - Return JSON for further processing:**
+```javascript
+buffer_transform({
+  inputs: { issues: "buf_issues" },
+  code: `
+    const summary = issues.map(i => ({
+      key: i.key,
+      summary: i.summary,
+      status: i.status?.name,
+      priority: i.priority?.name
+    }));
+    return summary;  // Returns JSON buffer, not XHTML
+  `
+})
+// -> { bufferId: "buf_result", contentType: "json", itemCount: 500 }
+```
+
+**Example - Markdown table output:**
+```javascript
+buffer_transform({
+  inputs: { issues: "buf_issues" },
+  code: `
+    const open = issues.filter(i => i.status?.name !== 'Done');
+    return toMarkdownTable(open.slice(0, 20), {
+      title: 'Open Issues',
+      columns: [
+        { field: 'key', header: 'Issue', link: { type: 'jira' } },
+        { field: 'summary', header: 'Summary' },
+        { field: 'status.name', header: 'Status' },
+        { field: 'priority.name', header: 'Priority', align: 'center' }
+      ],
+      format: [
+        { condition: { field: 'priority.name', operator: 'eq', value: 'High' },
+          style: { bold: true, icon: '🔴' } }
       ]
-    },
-    output: {
-      type: "csv",
-      table: {
-        columns: [
-          { field: "key", header: "Issue" },
-          { field: "summary", header: "Summary" },
-          { field: "Status", header: "Status" },
-          { field: "created", header: "Created" }
-        ]
-      }
-    }
-  }
+    });
+  `
 })
-// -> { bufferId: "buf_csv", output: "Issue,Summary,Status,Created\nPROJ-1,..." }
+// -> { bufferId: "buf_result", contentType: "markdown" }
+// Output:
+// ## Open Issues
+//
+// | Issue | Summary | Status | Priority |
+// | --- | --- | --- | :--: |
+// | [PROJ-1](https://jira.example.com/browse/PROJ-1) | Fix login bug | Open | 🔴 **High** |
 ```
 
 **Common Jira Fields:**
@@ -1937,7 +1933,7 @@ buffer_pipeline({
 **Workflow - Jira to Confluence table:**
 ```
 1. jira_search_issues(jql) → bufferId with JSON
-2. buffer_pipeline(bufferId, pipeline) → bufferId with XHTML table
+2. buffer_transform(inputs, code) → bufferId with XHTML table
 3. confluence_edit(pageId) → page bufferId
 4. buffer_edit(pageBufferId, after=ID, fromBufferId=tableBufferId)
 5. confluence_draft_create(pageId, pageBufferId) → draft for review
@@ -2139,6 +2135,79 @@ buffer_get_structure({ bufferId: "buf_xxx" })
 
 ---
 
+### 12. buffer_get_schema
+**Description**: Get the schema for a JSON buffer. Returns field names, types, and sample values from the actual data.
+**Use Cases**: Understand buffer structure before writing `buffer_transform` code, discover available fields for data processing
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| bufferId | string | ✓ | Buffer ID to get schema for |
+
+**Type Requirement**: Buffer must have `contentType: "json"`. Returns error if buffer is XHTML.
+
+**Schema Types**: Buffers from API tools have a named schema type (e.g., `jira_issue`, `tempo_worklog`, `confluence_page`). The schema defines all available fields with consistent structure.
+
+**Available Schema Types**:
+| Schema Type | Tools That Return It |
+|-------------|---------------------|
+| `jira_issue` | `jira_search_issues`, `jira_get_issue`, `jira_list_epic_children`, `jira_get_sprint_issues` |
+| `jira_comment` | `jira_get_issue_comments` |
+| `jira_project` | `jira_list_projects`, `jira_get_project` |
+| `jira_board` | `jira_get_board` |
+| `jira_sprint` | `jira_get_sprints` |
+| `jira_worklog` | `jira_get_issue_worklogs` |
+| `jira_worklog_total` | `jira_get_total_worklogs` |
+| `tempo_worklog` | `tempo_get_worklogs`, `tempo_get_worklog`, `tempo_get_team_worklogs`, `tempo_get_epic_worklogs` |
+| `tempo_account` | `tempo_get_accounts`, `tempo_get_account` |
+| `tempo_team` | `tempo_get_teams`, `tempo_get_team` |
+| `confluence_page` | `confluence_search_content`, `confluence_get_page_children` |
+| `confluence_space` | `confluence_list_spaces`, `confluence_get_space` |
+| `confluence_comment` | `confluence_get_comments` |
+| `confluence_attachment` | `confluence_list_attachments` |
+| `confluence_draft` | `confluence_draft_list` |
+
+**Response includes**: `bufferId`, `schemaType`, `description`, `itemCount` (for arrays), `fields` (with type, required, description, sample)
+
+**Example - Get schema before writing transform code:**
+```typescript
+// 1. Search returns bufferId with schemaType in response
+jira_search_issues({ jql: "project=PROJ" })
+// Returns: { bufferId: "buf_xxx", schemaType: "jira_issue", fields: ["key", "summary", "status", ...] }
+
+// 2. Get detailed schema with samples
+buffer_get_schema({ bufferId: "buf_xxx" })
+// Returns: {
+//   bufferId: "buf_xxx",
+//   schemaType: "jira_issue",
+//   description: "Jira issue with core fields flattened for easy access",
+//   itemCount: 45,
+//   fields: {
+//     key: { type: "string", required: true, description: "Issue key (e.g., PROJ-123)", sample: "PROJ-123" },
+//     summary: { type: "string", required: true, description: "Issue title/summary", sample: "Fix login bug" },
+//     status: { type: "string", required: true, description: "Current status name", sample: "In Progress" },
+//     assignee: { type: "string", required: false, description: "Assignee display name", sample: "John Doe" },
+//     ...
+//   }
+// }
+
+// 3. Now write accurate transform code using flat field names
+buffer_transform({
+  inputs: [{ bufferId: "buf_xxx" }],
+  code: `return toMarkdownTable(issues, {
+    columns: [
+      { field: 'key', header: 'Key' },
+      { field: 'summary', header: 'Summary' },
+      { field: 'status', header: 'Status' },
+      { field: 'assignee', header: 'Assignee' }
+    ]
+  });`
+})
+```
+
+**Key Benefit**: All tools returning the same schemaType produce identical field structure. Once you learn `jira_issue` fields, the same structure works for `jira_search_issues`, `jira_get_issue`, `jira_list_epic_children`, and `jira_get_sprint_issues`.
+
+---
+
 ## Workload Tools (2)
 
 Utility tools for time calculations. Always available with any Jira, Confluence, or Tempo action.
@@ -2426,7 +2495,7 @@ All data-heavy tools (search, list, get) **always** return buffered responses wi
     "title": "JQL: project = PROJ"
   },
   "accessors": {
-    "pipeline": { "tool": "buffer_pipeline", "description": "Transform to table/CSV/list" },
+    "transform": { "tool": "buffer_transform", "description": "Transform with JavaScript code" },
     "get_items": { "tool": "buffer_get_items", "description": "Get complete items for analysis" },
     "search": { "tool": "buffer_grep", "description": "Search within buffer" }
   }
@@ -2439,7 +2508,7 @@ All data-heavy tools (search, list, get) **always** return buffered responses wi
 - `contentType`: Buffer type (`json`, `xhtml`, `plain`)
 
 **Working with JSON Buffers (Jira/Tempo):**
-- `buffer_pipeline(bufferId, pipeline)` - Transform to table/CSV/list (98% token reduction)
+- `buffer_transform(inputs, code)` - Transform with JavaScript code (98% token reduction)
 - `buffer_get_items(bufferId, start, count)` - Get complete items for AI analysis
 - `buffer_grep(bufferId, pattern)` - Search within buffered data
 
@@ -2506,25 +2575,25 @@ Tools enforce type-safe buffer access - each tool only accepts buffers of the ty
 
 | Buffer Type | Tools That REQUIRE This Type |
 |-------------|------------------------------|
-| **json** | `buffer_pipeline`, `buffer_get_items` |
+| **json** | `buffer_transform`, `buffer_get_items` |
 | **xhtml** | `buffer_get_structure`, `buffer_get_element`, `buffer_validate_xhtml`, `confluence_draft_create` (with bufferId), `confluence_draft_save` |
 | **any** | `buffer_grep`, `buffer_list`, `buffer_clear`, `buffer_edit` (string mode) |
 
 **Error Messages**: When you use a tool with the wrong buffer type, you get a helpful error:
 ```
-buffer_pipeline requires json buffer, but got: xhtml.
+buffer_transform requires json buffer, but got: xhtml.
 For XHTML content, use buffer_edit or buffer_get_structure instead.
 ```
 
-**Key Principle**: If you have a JSON buffer (from Jira/Tempo search), use JSON-aware tools (`buffer_pipeline`, `buffer_get_items`). If you have an XHTML buffer (from Confluence), use XHTML-aware tools (`buffer_get_structure`, `buffer_edit` with element IDs).
+**Key Principle**: If you have a JSON buffer (from Jira/Tempo search), use JSON-aware tools (`buffer_transform`, `buffer_get_items`). If you have an XHTML buffer (from Confluence), use XHTML-aware tools (`buffer_get_structure`, `buffer_edit` with element IDs).
 
 ### Large Dataset Patterns
 
 **Simple table (no AI analysis):**
-Use `buffer_pipeline` - generates complete table in ONE tool call:
+Use `buffer_transform` - generates complete table in ONE tool call:
 ```typescript
 jira_search_issues({ jql: "project=PROJ" })  // → bufferId (500+ items)
-buffer_pipeline({ bufferId, pipeline: { output: { type: "xhtml_table", ... } } })  // → complete table!
+buffer_transform({ inputs: { issues: bufferId }, code: "return toTable(issues, { columns: [...] })" })  // → complete table!
 ```
 
 **Table with AI-enhanced columns (complexity, impact):**
@@ -2661,14 +2730,14 @@ buffer_validate_xhtml({
 **Automatic Validation:**
 XHTML content is automatically validated before Confluence writes (`confluence_draft_create`, `confluence_draft_save`).
 
-### JSON Pipeline Workflows
+### JSON Transform Workflows
 
-Use `buffer_pipeline` for efficient server-side data transformation. This eliminates the need to iterate through items in the LLM context.
+Use `buffer_transform` for efficient server-side data transformation. This eliminates the need to iterate through items in the LLM context.
 
 **Workflow - Search to Table (98% token reduction):**
 ```
 1. jira_search_issues(jql) → bufferId with JSON array
-2. buffer_pipeline(bufferId, pipeline) → bufferId with XHTML/CSV/Markdown
+2. buffer_transform(inputs, code) → bufferId with XHTML table
 3. Use result directly or insert into Confluence page
 ```
 
@@ -2679,29 +2748,27 @@ jira_search_issues({ jql: "project = PROJ AND type = Bug" })
 // → { bufferId: "buf_issues", structure: { itemCount: 150 } }
 
 // 2. Transform to table with one call (NOT iterating 150 items!)
-buffer_pipeline({
-  bufferId: "buf_issues",
-  pipeline: {
-    filter: [{ field: "status.name", operator: "ne", value: "Done" }],
-    sort: [{ field: "priority.name", direction: "asc" }],
-    format: [
-      { condition: { field: "priority.name", operator: "eq", value: "High" },
-        style: { color: "#dc3545", bold: true } }
-    ],
-    output: {
-      type: "xhtml_table",
-      table: {
-        title: "Open Bugs",
-        columns: [
-          { field: "key", header: "Issue", link: { type: "jira" } },
-          { field: "summary", header: "Summary" },
-          { field: "priority.name", header: "Priority" }
-        ]
-      }
-    }
-  }
+buffer_transform({
+  inputs: { issues: "buf_issues" },
+  code: `
+    const open = issues.filter(i => i.status?.name !== 'Done');
+    open.sort((a, b) => (a.priority?.id || 0) - (b.priority?.id || 0));
+
+    return toTable(open, {
+      title: 'Open Bugs',
+      columns: [
+        { field: 'key', header: 'Issue', link: { type: 'jira' } },
+        { field: 'summary', header: 'Summary' },
+        { field: 'priority.name', header: 'Priority' }
+      ],
+      format: [
+        { condition: { field: 'priority.name', operator: 'eq', value: 'High' },
+          style: { color: '#dc3545', bold: true } }
+      ]
+    });
+  `
 })
-// → { bufferId: "buf_table", outputItems: 45, preview: "<table>..." }
+// → { bufferId: "buf_table", contentType: "xhtml" }
 
 // 3. Insert into Confluence page
 confluence_edit("DOCS/Bug Report")
@@ -2715,41 +2782,39 @@ confluence_draft_create({ pageId: "123", bufferId: "buf_page" })
 **Workflow - Statistics Dashboard:**
 ```typescript
 // Group issues by assignee with counts
-buffer_pipeline({
-  bufferId: "buf_issues",
-  pipeline: {
-    filter: [{ field: "status.name", operator: "ne", value: "Done" }],
-    groupBy: {
-      field: "assignee.displayName",
-      aggregations: [
-        { function: "count", as: "total" },
-        { function: "list", field: "key", as: "issues" }
+buffer_transform({
+  inputs: { issues: "buf_issues" },
+  code: `
+    const open = issues.filter(i => i.status?.name !== 'Done');
+    const byAssignee = groupBy(open, 'assignee.displayName');
+
+    const stats = Object.entries(byAssignee).map(([name, items]) => ({
+      assignee: name || 'Unassigned',
+      total: items.length,
+      issues: items.map(i => i.key).join(', ')
+    }));
+    stats.sort((a, b) => b.total - a.total);
+
+    return toTable(stats, {
+      title: 'Work Distribution',
+      columns: [
+        { field: 'assignee', header: 'Assignee' },
+        { field: 'total', header: 'Open Issues', align: 'right' },
+        { field: 'issues', header: 'Issue Keys' }
       ]
-    },
-    sort: [{ field: "total", direction: "desc" }],
-    output: {
-      type: "xhtml_table",
-      table: {
-        title: "Work Distribution",
-        columns: [
-          { field: "displayName", header: "Assignee" },
-          { field: "total", header: "Open Issues" },
-          { field: "issues", header: "Issue Keys" }
-        ]
-      }
-    }
-  }
+    });
+  `
 })
 ```
 
-**When to Use `buffer_pipeline`:**
+**When to Use `buffer_transform`:**
 - Generating tables/lists for Confluence from Jira/Tempo data
 - Creating CSV/Markdown exports
 - Aggregating statistics (count by status, sum time by project, etc.)
 - Filtering and sorting large result sets server-side
 - Any data transformation that doesn't require LLM reasoning
 
-**When NOT to Use `buffer_pipeline`:**
+**When NOT to Use `buffer_transform`:**
 - When you need to read and understand each item's content
 - When decisions require LLM judgment (e.g., categorizing by sentiment)
 - When output format depends on item content analysis