@hanna84/mcp-writing 3.29.0 → 3.29.2

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.
Files changed (3) hide show
  1. package/CHANGELOG.md +14 -0
  2. package/README.md +11 -1
  3. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -4,9 +4,23 @@ All notable changes to this project will be documented in this file. Dates are d
4
4
 
5
5
  Generated by [`auto-changelog`](https://github.com/CookPete/auto-changelog).
6
6
 
7
+ #### [v3.29.2](https://github.com/hannasdev/mcp-writing/compare/v3.29.1...v3.29.2)
8
+
9
+ - ci: skip PR template check for Dependabot [`#241`](https://github.com/hannasdev/mcp-writing/pull/241)
10
+
11
+ #### [v3.29.1](https://github.com/hannasdev/mcp-writing/compare/v3.29.0...v3.29.1)
12
+
13
+ > 7 June 2026
14
+
15
+ - docs: close Human Input Forgiveness initiative [`#240`](https://github.com/hannasdev/mcp-writing/pull/240)
16
+ - Release 3.29.1 [`8055d63`](https://github.com/hannasdev/mcp-writing/commit/8055d635819ae2ab76ab733166719763e1b756b2)
17
+
7
18
  #### [v3.29.0](https://github.com/hannasdev/mcp-writing/compare/v3.28.0...v3.29.0)
8
19
 
20
+ > 7 June 2026
21
+
9
22
  - feat: resolve scene vocabulary variants [`#239`](https://github.com/hannasdev/mcp-writing/pull/239)
23
+ - Release 3.29.0 [`bb81824`](https://github.com/hannasdev/mcp-writing/commit/bb81824fcb04640b3e62fae2cee6bd39bcd8af14)
10
24
 
11
25
  #### [v3.28.0](https://github.com/hannasdev/mcp-writing/compare/v3.27.0...v3.28.0)
12
26
 
package/README.md CHANGED
@@ -28,7 +28,7 @@ Instead of feeding an entire manuscript to an AI and hoping it fits in the conte
28
28
 
29
29
  **Current status:**
30
30
  - **Core platform complete:** Metadata-first analysis, SQLite-canonical structural and relationship metadata, compatibility sidecar maintenance, AI-assisted prose editing with confirmation + git history, review bundles, and Scrivener Direct extraction are all implemented.
31
- - **Recently completed:** Relationship Metadata Boundary closed the sidecar-first scene relationship mutation path, added SQLite-first paired and one-sided evidence workflows, and preserved legacy sidecar/frontmatter compatibility for sync and import.
31
+ - **Recently completed:** Human Input Forgiveness made selected request-boundary inputs more forgiving, clarified keyword metadata search boundaries, and recorded temp-fixture replay validation while preserving stable canonical IDs.
32
32
  - **Active development:** No initiative is currently selected.
33
33
  - **Deferred backlog:** OpenClaw integration, client-agnostic setup, divisions, and embeddings search.
34
34
  - **Ideas and open questions:** tracked separately so future exploration does not distort the active roadmap.
@@ -122,6 +122,16 @@ const items = parsed.results ?? [];
122
122
  const totalCount = parsed.total_count ?? items.length;
123
123
  ```
124
124
 
125
+ ## Canonical IDs and forgiving inputs
126
+
127
+ Stable IDs remain the canonical identity for projects, chapters, scenes, characters, places, and relationship writes. When you already know the ID, pass it exactly.
128
+
129
+ Some request-boundary fields now accept unambiguous human-shaped inputs, such as scene titles, character names, place names, or case variants. Successful tools still write and return canonical IDs, with `resolved_from` details when the input was resolved from a non-canonical value. Ambiguous matches, near matches, or suggested-only values fail or return advisory suggestions without mutating canonical state.
130
+
131
+ Tags and Save the Cat beats remain freeform editorial vocabulary. `find_scenes` can match existing tag and beat casing variants, and metadata updates can suggest nearby existing vocabulary, but supplied tag and beat text is preserved unless you intentionally change it.
132
+
133
+ `search_metadata` is keyword/FTS metadata search over indexed titles, loglines, tags, characters, places, and versions. It is not semantic search and does not search prose text; use `get_scene_prose` after metadata search or structured filters identify likely scenes. Semantic/prose search remains deferred to the Embedding-Based Search backlog.
134
+
125
135
  ## Usage scenarios
126
136
 
127
137
  ### 1) Continuity pass before sending chapters to beta readers
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@hanna84/mcp-writing",
3
- "version": "3.29.0",
3
+ "version": "3.29.2",
4
4
  "description": "MCP service for AI-assisted reasoning and editing on long-form fiction projects",
5
5
  "homepage": "https://hannasdev.github.io/mcp-writing/",
6
6
  "type": "module",