flex-md 4.4.2 → 4.4.6

package/README.md

@@ -629,7 +629,61 @@ Detailed guides can be found in the [docs](./docs) folder:
 - [Token Estimation Guide](./docs/token-estimation.md) - How estimation works
 - [Smart Toolbox Guide](./docs/smart-toolbox.md) - Using analysis features
 - [MDFlex Compliance Spec](./docs/mdflex-compliance.md) - Output enforcement
-- [OFS Syntax Guide](./SPEC.md) - Output Format Spec syntax
+
+## Output Format Spec (OFS) Syntax Reference
+
+Flex-MD uses a simple Markdown block to define the expected output contract. This block is both machine-readable (for validation) and human-readable (for the LLM).
+
+### 1. Basic Structure
+
+Start with `## Output format`. List sections using `- Name — Kind`.
+
+```markdown
+## Output format
+- Summary — text (required)
+- Reasoning — ordered list (required)
+- Key Tags — list (optional)
+```
+
+### 2. Available Kinds
+
+| Kind | Description | Validation Rule |
+| :--- | :--- | :--- |
+| `text` (or `prose`) | Any text content. | Always matches if section exists. |
+| `list` | Unordered bullets. | Body must contain `- items`. |
+| `ordered list` | Numbered list. | Body must contain `1. items`. |
+| `table` | Markdown table. | Must match column headers. |
+
+### 3. Tables
+
+Define tables by specifying columns in parentheses.
+
+```markdown
+Tables:
+- (Name, Age, Role — table)
+- (Rank, Team, Score — ordered table)
+```
+
+- **table**: Standard Markdown pipe table.
+- **ordered table**: Must have a first column `#` with row numbers `1..N`.
+
+### 4. Instructions & Constraints
+
+You can add instructions under any section item to guide the LLM.
+
+```markdown
+- Summary — text
+    Length: 2-3 sentences. No bullet points.
+```
+
+### 5. Empty Sections
+
+Define what to write if a section has no content:
+
+```markdown
+Empty sections:
+- If a section is empty, write `None`.
+```
 
 ## Migration from v3.0
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "flex-md",
-  "version": "4.4.2",
+  "version": "4.4.6",
   "description": "Parse and stringify FlexMD: semi-structured Markdown with three powerful layers - Frames, Output Format Spec (OFS), and Detection/Extraction.",
   "license": "MIT",
   "author": "",
@@ -54,7 +54,7 @@
   "dependencies": {
     "nd": "^1.2.0",
     "nx-helpers": "^1.5.0",
-    "nx-json-parser": "^1.1.0",
+    "nx-json-parser": "^1.2.1",
     "nx-md-parser": "^2.2.0"
   }
 }