@softspark/jira-mcp 1.2.0 → 1.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -7,6 +7,36 @@ Versioning follows [Semantic Versioning](https://semver.org/).
7
7
 
8
8
  ---
9
9
 
10
+ ## v1.4.0 -- Delete Tools & Error Hardening (2026-04-15)
11
+
12
+ ### Added
13
+ - **`delete_task` tool** -- delete a Jira issue with ownership enforcement (creator only) and explicit user approval guard.
14
+ - **`delete_comment` tool** -- delete a comment with ownership enforcement (author only) and explicit user approval guard.
15
+ - **Markdown table support in ADF** -- `markdownToAdf()` now converts markdown tables to ADF table nodes.
16
+
17
+ ### Changed
18
+ - **Narrowed cache cleanup catch blocks** -- `deleteTask()` and `logTime()` now catch only `TaskNotFoundError` and `CacheNotFoundError` instead of swallowing all exceptions. Unexpected I/O or corruption errors propagate.
19
+
20
+ ### Fixed
21
+ - **Silent cache errors** -- cache I/O failures during post-delete and post-worklog cleanup were silently ignored, leaving stale entries without any signal.
22
+
23
+ ## v1.3.0 -- File-Backed Templates & Approval Hooks (2026-04-15)
24
+
25
+ ### Added
26
+ - **File-backed template catalog** -- ship built-in comment and single-task templates as physical markdown files under `templates-system/`.
27
+ - **Template management CLI** -- add `jira-mcp template add/list/show/remove` for global user overrides in `~/.softspark/jira-mcp/templates/`.
28
+ - **Task templates for `create_task`** -- add `list_task_templates` and template-based issue creation with variable rendering.
29
+ - **Comment approval hook manifest** -- ship `hooks/jira-mcp-hooks.json` for ai-toolkit `inject-hook` flows that preview and gate Jira comment writes.
30
+
31
+ ### Changed
32
+ - **Template loading model** -- resolve active templates from system files plus global user overrides, with user files winning on `id` collisions.
33
+ - **Configuration init** -- create dedicated template directories for comments, single-task templates, and bulk task configs.
34
+ - **README validation** -- exclude internal tool helpers from MCP tool counts and refresh counts to match the current source tree.
35
+
36
+ ### Fixed
37
+ - **Comment write safety** -- require explicit `user_approved=true` before `add_task_comment` and `add_templated_comment` can mutate Jira.
38
+ - **Comment preview flow** -- render templated comment previews before execution so approval can target the exact outgoing markdown.
39
+
10
40
  ## v1.2.0 -- Per-Instance Credentials & Jira API Migration (2026-04-14)
11
41
 
12
42
  ### Added
package/README.md CHANGED
@@ -4,17 +4,17 @@
4
4
 
5
5
  [![CI](https://github.com/softspark/jira-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/softspark/jira-mcp/actions/workflows/ci.yml)
6
6
  [![npm](https://img.shields.io/npm/v/@softspark/jira-mcp)](https://www.npmjs.com/package/@softspark/jira-mcp)
7
- [![version](https://img.shields.io/badge/version-1.1.0-blue)](CHANGELOG.md)
7
+ [![version](https://img.shields.io/badge/version-1.3.0-blue)](CHANGELOG.md)
8
8
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
9
9
 
10
10
  ---
11
11
 
12
- ## What's New in v1.2.0
12
+ ## What's New in v1.4.0
13
13
 
14
- - **Per-instance credentials** -- `set-credentials --url` allows different API tokens per Jira instance. Auto-migrates legacy format.
15
- - **Jira Cloud API migration** -- search endpoint updated to `/rest/api/3/search/jql` (old endpoint returns 410).
16
- - **Live Jira smoke tests** -- post-release SOP tests all 15 MCP tools against a sandbox project.
17
- - **518 tests** across 52 test files.
14
+ - **`delete_task` and `delete_comment` tools** -- guarded destructive operations with ownership enforcement and explicit approval.
15
+ - **Markdown table support** -- `markdownToAdf()` converts tables to native ADF table nodes.
16
+ - **Hardened error handling** -- cache cleanup no longer swallows unexpected I/O errors.
17
+ - **561 tests** across 58 test files.
18
18
 
19
19
  See [CHANGELOG.md](CHANGELOG.md) for full details.
20
20
 
@@ -74,6 +74,10 @@ All configuration lives in `~/.softspark/jira-mcp/` (created by `jira-mcp config
74
74
  | `jira-mcp serve` | Start MCP server (explicit) |
75
75
  | `jira-mcp create <path>` | Create tasks from config file (dry-run by default) |
76
76
  | `jira-mcp create-monthly` | Create monthly admin tasks from built-in templates |
77
+ | `jira-mcp template add <type> <path>` | Install a template override from a local markdown file |
78
+ | `jira-mcp template list [type]` | List active comment/task templates |
79
+ | `jira-mcp template show <type> <id>` | Show the active template file content |
80
+ | `jira-mcp template remove <type> <id>` | Remove a user-installed template override |
77
81
  | `jira-mcp config init` | Initialize global config at `~/.softspark/jira-mcp/` |
78
82
  | `jira-mcp config add-project <key> <url>` | Add a Jira project to config |
79
83
  | `jira-mcp config remove-project <key>` | Remove a project from config |
@@ -95,7 +99,9 @@ All configuration lives in `~/.softspark/jira-mcp/` (created by `jira-mcp config
95
99
  | `read_cached_tasks` | Read tasks from cache without hitting Jira | `task_key?` |
96
100
  | `update_task_status` | Change task status via workflow transition | `task_key`, `status` |
97
101
  | `update_task` | Update existing issue fields (markdown → ADF) | `task_key`, `summary?`, `description?`, `priority?`, `labels?` |
98
- | `add_task_comment` | Add a markdown comment (auto-converted to ADF) | `task_key`, `comment` |
102
+ | `add_task_comment` | Add a markdown comment (auto-converted to ADF) | `task_key`, `comment`, `user_approved` |
103
+ | `delete_task` | Delete a task, only when the authenticated user is the task creator | `task_key`, `user_approved` |
104
+ | `delete_comment` | Delete a comment, only when the authenticated user is the comment author | `task_key`, `comment_id`, `user_approved` |
99
105
  | `reassign_task` | Reassign or unassign a task | `task_key`, `assignee_email?` |
100
106
  | `get_task_statuses` | Get valid workflow transitions for a task | `task_key` |
101
107
  | `get_task_details` | Get full details with description, comments, and language | `task_key` |
@@ -103,8 +109,9 @@ All configuration lives in `~/.softspark/jira-mcp/` (created by `jira-mcp config
103
109
  | `log_task_time` | Log work time (`"2h 30m"` format, no days) | `task_key`, `time_spent`, `comment?` |
104
110
  | `get_task_time_tracking` | Get time tracking info (estimate, spent, remaining) | `task_key` |
105
111
  | `list_comment_templates` | List available comment templates | `category?` |
106
- | `add_templated_comment` | Add comment using a template or raw markdown | `task_key`, `template_id?`, `variables?`, `markdown?` |
107
- | `create_task` | Create a new Jira issue with ADF description | `project_key`, `summary`, `description?`, `assignee_email?`, `labels?`, `epic_key?` |
112
+ | `list_task_templates` | List available task templates for `create_task` | |
113
+ | `add_templated_comment` | Add comment using a template or raw markdown | `task_key`, `template_id?`, `variables?`, `markdown?`, `user_approved` |
114
+ | `create_task` | Create a new Jira issue with explicit fields or a task template | `project_key`, `summary?`, `template_id?`, `variables?`, `description?`, `assignee_email?`, `labels?`, `epic_key?` |
108
115
  | `search_tasks` | Search Jira issues with JQL (no caching) | `jql`, `max_results?`, `project_key?` |
109
116
 
110
117
  ## Comment Templates
@@ -130,6 +137,23 @@ Example with Claude Code:
130
137
 
131
138
  The AI will use `add_templated_comment` with `template_id: "status-update"` automatically.
132
139
 
140
+ ### File-Backed Overrides
141
+
142
+ System templates are shipped as markdown files. User overrides are loaded from:
143
+
144
+ ```text
145
+ ~/.softspark/jira-mcp/templates/comments/
146
+ ~/.softspark/jira-mcp/templates/task-templates/
147
+ ```
148
+
149
+ If a user file has the same `id` as a system template, the user file wins globally for all projects.
150
+
151
+ ```bash
152
+ jira-mcp template add comment ./my-status-update.md
153
+ jira-mcp template add task ./my-bug-task.md
154
+ jira-mcp template list
155
+ ```
156
+
133
157
  ## Usage with Claude Code
134
158
 
135
159
  Add to your Claude Code MCP configuration (`~/.claude/claude_desktop_config.json` or project-level):
@@ -160,7 +184,19 @@ Or copy `rules/jira-mcp.md` to your ai-toolkit rules directory manually. The rul
160
184
  - **Sync before read** -- cache may be stale
161
185
  - **Status transitions** -- check valid transitions before changing status
162
186
  - **Time format** -- `"2h 30m"`, never days
163
- - **All 15 MCP tools** and **16 CLI commands** reference
187
+ - **All 18 MCP tools** and **20 CLI commands** reference
188
+
189
+ ### AI Toolkit Hooks
190
+
191
+ To require explicit user approval before Jira comment writes, inject the repo-owned hook manifest:
192
+
193
+ ```bash
194
+ ai-toolkit inject-hook https://raw.githubusercontent.com/softspark/jira-mcp/main/hooks/jira-mcp-hooks.json
195
+ ```
196
+
197
+ This installs a `PreToolUse` guard for `add_task_comment` and `add_templated_comment`. The hook blocks the tool call, shows the exact comment preview, and tells the agent to retry only after the user approves it with `user_approved=true`.
198
+
199
+ The MCP server still enforces `user_approved=true` at runtime, so the hook is UX guidance plus an extra safety layer rather than the only check.
164
200
 
165
201
  ## Usage with Other MCP Clients
166
202
 
@@ -187,14 +223,15 @@ src/
187
223
  commands/
188
224
  cache/ Cache management subcommands
189
225
  config/ Config management subcommands
226
+ template/ File-backed template management subcommands
190
227
  create.ts Bulk task creation command
191
228
  create-monthly.ts Monthly admin task automation
192
229
  config/ Configuration loading and Zod validation
193
230
  connector/ Jira API client (built-in fetch, instance pool)
194
231
  errors/ Typed error hierarchy
195
232
  operations/ Business logic (status, comments, time tracking)
196
- templates/ Comment template system (registry + built-in templates)
197
- tools/ MCP tool handlers (15 tools, one file per tool)
233
+ templates/ File-backed comment/task template loading and registries
234
+ tools/ MCP tool handlers (18 tools, one file per tool)
198
235
  types/ Shared TypeScript types
199
236
  server.ts MCP server setup and tool registration
200
237
  cli.ts CLI entry point
@@ -208,7 +245,7 @@ src/
208
245
 
209
246
  **Local caching** -- tasks synced to `~/.softspark/jira-mcp/cache/` with atomic writes (tmp + rename). Work offline with `read_cached_tasks`, sync on demand. Workflow and user caches for status validation and assignee resolution.
210
247
 
211
- **Comment templates** -- 8 built-in templates with `{{variable}}` interpolation and `{{#var}}...{{/var}}` conditional blocks. Status updates, blockers, handoffs, reviews. See [Templates Reference](kb/reference/templates.md).
248
+ **File-backed templates** -- 8 built-in comment templates and built-in task templates are stored as markdown files, with global user overrides loaded from `~/.softspark/jira-mcp/templates/`. Both support `{{variable}}` interpolation and `{{#var}}...{{/var}}` conditional blocks. See [Templates Reference](kb/reference/templates.md).
212
249
 
213
250
  **Language configuration** -- global `default_language` with per-project override. Supports: pl, en, de, es, fr, pt, it, nl. `get_project_language` tool and `language` field in `get_task_details` let AI assistants write content in the correct language. See [Configuration](kb/reference/configuration.md).
214
251
 
@@ -218,16 +255,16 @@ src/
218
255
 
219
256
  **Supply chain protection** -- `ignore-scripts=true`, no axios, no dynamic requires. Self-contained 520KB bundle, 1 runtime dep (commander).
220
257
 
221
- **Typed error hierarchy** -- 15 error classes with machine-readable codes. Every tool returns structured `{ success, error, code }` responses. No stack traces leak to MCP clients.
258
+ **Typed error hierarchy** -- 20 error classes with machine-readable codes. Every tool returns structured `{ success, error, code }` responses. No stack traces leak to MCP clients.
222
259
 
223
- **Strict TypeScript** -- `strict: true`, no `any`, `readonly` interfaces, Zod validation at all boundaries, 518 tests across 52 test files. Self-contained 520KB package.
260
+ **Strict TypeScript** -- `strict: true`, no `any`, `readonly` interfaces, Zod validation at all boundaries, 558 tests across 58 test files. Self-contained 520KB package.
224
261
 
225
262
  ## Documentation
226
263
 
227
264
  | Document | Description |
228
265
  |----------|-------------|
229
266
  | [Architecture](kb/reference/architecture.md) | System design and module overview |
230
- | [API Reference](kb/reference/api.md) | All 15 MCP tools with schemas |
267
+ | [API Reference](kb/reference/api.md) | All 18 MCP tools with schemas |
231
268
  | [Configuration](kb/reference/configuration.md) | Config files, env vars, multi-instance |
232
269
  | [ADF Format](kb/reference/adf.md) | Atlassian Document Format conversion |
233
270
  | [Caching](kb/reference/caching.md) | Task, workflow, and user caching |