@softspark/ai-toolkit 2.1.0 → 2.1.2

package/AGENTS.md

@@ -386,3 +386,50 @@ Testing expert. Use for writing tests (unit, integration, e2e), TDD workflow, te
 
 ---
 
+<!-- TOOLKIT:jira-rules START -->
+<!-- Auto-injected by ai-toolkit. Re-run to update. -->
+
+# Jira MCP Server
+
+Tools: `sync_tasks`, `read_cached_tasks`, `update_task_status`, `add_task_comment`, `reassign_task`, `get_task_statuses`, `get_task_details`, `log_task_time`, `get_task_time_tracking`
+
+## Key Rules
+
+- **Always `sync_tasks` first** before reading — cache may be stale.
+- **Time format:** `"2h 30m"` — hours and minutes only, never days.
+- **Status changes:** call `get_task_statuses` first to check valid transitions.
+- **Multi-instance:** project key determines which Jira instance is used (mapped in config.json).
+
+## Workflow
+
+1. `sync_tasks(jql="assignee=currentUser() AND status!=Done")` — fetch fresh
+2. `read_cached_tasks()` — work offline
+3. `get_task_details(task_key="PROJ-123")` — deep dive
+4. `update_task_status(...)` / `add_task_comment(...)` / `log_task_time(...)` — mutate
+
+<!-- TOOLKIT:jira-rules END -->
+<!-- TOOLKIT:rag-mcp-rules START -->
+<!-- Auto-injected by ai-toolkit. Re-run to update. -->
+
+## INSTANT ACTION RULE (GOLDEN RULE)
+
+**ANY technical question? -> INSTANTLY call `smart_query()` OR `hybrid_search_kb()` BEFORE outputting text!**
+
+1. **Search First:** `smart_query()` or `hybrid_search_kb()` (NEVER skip, even if you "know").
+2. **Cite Sources:** always include `[PATH: kb/...]`.
+3. **Strict Order:** Semantic Search -> Files -> External Docs -> General Knowledge.
+
+Default tool: `smart_query()`. Use `hybrid_search_kb()` for speed, `crag_search()` for vague queries, `multi_hop_search()` for complex reasoning.
+
+## kb_id vs file_path
+
+- `get_document(path=...)` takes `kb_id` from search results (e.g., `local/softspark/project/reference/api.md`)
+- `Read`/`Edit` take filesystem `file_path` (e.g., `./reference/api.md`)
+- **DO NOT CONFUSE** these fields.
+
+## SOPs
+
+ALWAYS check `kb/procedures/` first: `smart_query("SOP for <task>")`.
+
+<!-- TOOLKIT:rag-mcp-rules END -->
+

package/CHANGELOG.md

@@ -7,6 +7,32 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v2.1.2 — Idempotent Update Fix (2026-04-13)
+
+### Fixed
+- **`ai-toolkit update` no longer dirties git** — generators now skip custom rule emission when called by `inject_with_rules()` (which handles injection separately). Previously, `update` caused AGENTS.md and other generated files to gain extra blank lines on every run.
+
+---
+
+## v2.1.1 — Custom Rules in Generators & README Restructure (2026-04-13)
+
+### Fixed
+- **Custom rules in generators** — `generate:all` now includes registered custom rules (from `ai-toolkit add-rule`) in all single-file generators (Cursor, Windsurf, Copilot, Gemini, AGENTS.md) and directory-based generators (Cline, Roo, Codex, Augment, Antigravity, Cursor MDC). Previously custom rules were lost on regeneration.
+- **AGENTS.md double generation** — `generate-all` CLI no longer generates AGENTS.md twice; uses `codex-md` (superset) only
+- **CLI help completeness** — added missing `--persona` option and `codex` to `--editors` list in `ai-toolkit help`
+
+### Changed
+- **README restructured** — reduced from 951 to 292 lines with Table of Contents, "What's New" section, and links to KB docs. Detailed content moved to dedicated KB documents.
+- **npm `generate:agents`** — now uses `generate_codex.py` (consistent with CLI `generate-all`)
+- **Test assertions** — generator file count tests use `>= 6` to accommodate registered custom rules
+
+### New Files
+- `kb/reference/cli-reference.md` — complete CLI command reference (moved from README)
+- `kb/reference/unique-features.md` — detailed differentiators documentation (moved from README)
+- `kb/reference/comparison.md` — ecosystem comparison table (moved from README)
+
+---
+
 ## v2.1.0 — Codex CLI Support & Native Editor MCP Install (2026-04-13)
 
 ### Added