@vheins/local-memory-mcp 0.8.48 → 0.9.0
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/dist/{chunk-QCCKQZ5G.js → chunk-XSGHXB35.js} +381 -40
- package/dist/dashboard/public/assets/{index-BaWIMG1g.css → index-Cbts6Uv0.css} +1 -1
- package/dist/dashboard/public/assets/index-ZEQxhvIi.js +86 -0
- package/dist/dashboard/public/index.html +2 -2
- package/dist/dashboard/server.js +179 -7
- package/dist/mcp/server.js +262 -105
- package/dist/prompts/csl-scrapper.md +5 -1
- package/package.json +1 -1
- package/dist/dashboard/public/assets/index-DEY6a44I.js +0 -86
|
@@ -16,11 +16,13 @@ Goal:
|
|
|
16
16
|
- Use the web_fetch tool (if available) to retrieve the content of the provided Source URL.
|
|
17
17
|
- Extract only source-backed coding standards from the documentation.
|
|
18
18
|
- Produce one atomic CSL entry per distinct rule, constraint, prohibition, or required workflow.
|
|
19
|
-
- Each entry must be ready for the standard-store tool shape: name, content, context, version, language, stack, tags, metadata, repo, is_global.
|
|
19
|
+
- Each entry must be ready for the standard-store tool shape: name, content, parent_id, context, version, language, stack, tags, metadata, repo, is_global.
|
|
20
20
|
- Identify documentation navigation menus (e.g., sidebars, index pages) containing links to related sub-pages. If present, create iterative scraping tasks for these sub-pages.
|
|
21
|
+
- Detect documentation hierarchy when a page contains an umbrella rule with narrower sub-rules. In that case, emit one parent entry plus child entries linked with `parent_id`.
|
|
21
22
|
|
|
22
23
|
Atomic entry rules:
|
|
23
24
|
- One entry = one rule. Split bundled guidance into separate entries.
|
|
25
|
+
- Use parent/child only for genuine hierarchy: parent = umbrella principle, child = narrower enforceable specialization.
|
|
24
26
|
- Keep content concise, imperative, and implementation-relevant.
|
|
25
27
|
- ALWAYS include relevant code examples or snippets from the source that illustrate or enforce the rule. Do NOT discard code blocks.
|
|
26
28
|
- Preserve the source meaning without inventing requirements.
|
|
@@ -32,12 +34,14 @@ Atomic entry rules:
|
|
|
32
34
|
Output contract:
|
|
33
35
|
- If tool calls are available:
|
|
34
36
|
- Emit one `standard-store` call per accepted entry.
|
|
37
|
+
- When parent/child hierarchy exists, emit the parent first, then emit children with `parent_id` referencing the created parent standard ID.
|
|
35
38
|
- Emit one `task-create` call for each discovered documentation sub-page URL. The task title should be "Scrape: [URL]" and the description should instruct to use the `csl-scrapper` prompt for that URL.
|
|
36
39
|
- If tool calls are unavailable, return a JSON object with:
|
|
37
40
|
- `standards`: Array of `standard-store`-compatible payloads.
|
|
38
41
|
- `next_urls`: Array of sub-page URLs to scrape.
|
|
39
42
|
- Use title-like names for the "name" field and store the atomic rule text along with its code examples in "content".
|
|
40
43
|
- Use "context" for the topic area (for example: naming, error-handling, routing, testing, hooks, security).
|
|
44
|
+
- Use `parent_id` only when the source explicitly shows the rule is nested under a broader parent concept on the same page.
|
|
41
45
|
- Default version to "1.0.0" only when the source gives no versioning signal.
|
|
42
46
|
- Prefer is_global=true unless the source is clearly repo-specific.
|
|
43
47
|
|