fux-engine 3.0.0-alpha.2 → 3.0.0-alpha.4

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/fux.mjs +0 -0
  2. package/mcp-tools.json +1 -1
  3. package/package.json +1 -1
package/fux.mjs CHANGED
Binary file
package/mcp-tools.json CHANGED
@@ -3,7 +3,7 @@
3
3
  "tools": [
4
4
  {
5
5
  "name": "fux_search",
6
- "description": "Search the committed index for documents relevant to a natural-language question. Returns ranked documents with content hashes and the headings that match your query -- section-level, not line-level; call fux_passage for the lines. This is the call to make first for any 'where is X' or 'why did we decide Y' question about this repository. READ THE `confidence` BLOCK BEFORE USING THE RESULTS. If `confidence.answerable` is false, do not answer from these results at all -- say what was searched and stop. If `confidence.band` is 'partial', answer but name every term in `confidence.missing`: those are words from the question that appear in no document here. If it is 'weak', the ranking could not separate the top hits -- `answerable` is false there too, so abstain: say that the documents do not say, name what was searched, and report the candidates rather than a conclusion. The payload also carries `related`: documents that NO query word matched, returned because the ranked results above LINK to them, each with the `route` it was reached by. They are not matches and must never be cited as one -- read a related document with fux_passage before you use it, and say that you followed a link to it rather than found it.",
6
+ "description": "Search the committed index for documents relevant to a natural-language question. Returns ranked documents with content hashes and the headings that match your query -- section-level, not line-level; call fux_passage for the lines. This is the call to make first for any 'where is X' or 'why did we decide Y' question about this repository. READ THE `confidence` BLOCK BEFORE USING THE RESULTS. If `confidence.answerable` is false, do not answer from these results at all -- say what was searched and stop. If `confidence.band` is 'partial', answer but name every term in `confidence.missing`: those are words from the question that appear in no document here. If it is 'weak', the ranking could not separate the top hits -- that is a SIGNAL and not a refusal (`answerable` stays true): read the near-tied candidates and judge, and if neither answers, say the documents do not say and report what was searched rather than a conclusion. The payload also carries `related`: documents that NO query word matched, returned because the ranked results above LINK to them, each with the `route` it was reached by. They are not matches and must never be cited as one -- read a related document with fux_passage before you use it, and say that you followed a link to it rather than found it.",
7
7
  "inputSchema": {
8
8
  "type": "object",
9
9
  "properties": {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "fux-engine",
3
- "version": "3.0.0-alpha.2",
3
+ "version": "3.0.0-alpha.4",
4
4
  "description": "Read a fux index from Node. Ranked, cited answers from a small index committed to git — no server, no model, no Python.",
5
5
  "type": "module",
6
6
  "engines": { "node": ">=20" },