donsetch 5.0.0 → 5.1.1
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/README.md +2 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -103,7 +103,7 @@ donsetch update
|
|
|
103
103
|
| `web_fetch` | Any URL as clean markdown, or only the part that answers: `must_contain` probes, `focus` passages, `toc` → `section`. Walls answered in-process, never by a browser. PDFs with OCR and per-page confidence, site adapters, page memory, batches of up to 12. |
|
|
104
104
|
| `web_search` | Keyless multi-engine search: 10+ backends, consensus plus semantic reranking, query-aware official-source placement. Ranked URLs and snippets, never a scraped article dump. |
|
|
105
105
|
| `web_crawl` | Best-first same-domain crawl. Sitemap plus frontier, `focus` ranking, elastic pacing, resume tokens, honest stop reasons. |
|
|
106
|
-
| `web_screenshot` | Rendered PNG of any URL through DonSeTch's browser (used only for screenshots
|
|
106
|
+
| `web_screenshot` | Rendered PNG of any URL through DonSeTch's browser (used only for screenshots), with the usual URL safety guards. |
|
|
107
107
|
|
|
108
108
|
MCP results default to self-contained text: leading `[meta]` JSON followed by source evidence, including for unknown client bridges. PNGs remain image blocks.
|
|
109
109
|
|
|
@@ -115,7 +115,7 @@ Every failure is structured: a stable `code` (`wall.challenge`, `guard.ssrf`, `d
|
|
|
115
115
|
- **PDFs done properly.** A custom PDFium FFI, no Python subprocess. Tables and borders come from the rendered bitmap, text from the glyph stream, and the trust audit flags exactly the regions that need OCR.
|
|
116
116
|
- **Crawl with manners.** Per-host adaptive pacing that honors `Retry-After` and robots `Crawl-delay`, cross-process politeness so two crawls do not double a site's rate, near-duplicate detection, resume tokens that survive restarts, and honest stop reasons.
|
|
117
117
|
- **Fetch that answers honestly.** `content_ok`, `thin`, `changed` with section diffs, and `must_contain` says `unverified` instead of a false "not found" when part of a page was unread. No fake success.
|
|
118
|
-
- **Walls named, not guessed.** A bot wall names its vendor and what it asks for; a login wall is a declared `wall.auth` (fetch carries no session
|
|
118
|
+
- **Walls named, not guessed.** A bot wall names its vendor and what it asks for; a login wall is a declared `wall.auth` (the fetch carries no session; authenticated work belongs to a browser driver).
|
|
119
119
|
- **Works everywhere.** Linux, macOS, Windows. npm, Homebrew, the Pi agent as a native extension, and the DeepSeek Harness as a first-class plugin.
|
|
120
120
|
|
|
121
121
|
## Sponsors
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "donsetch",
|
|
3
|
-
"version": "5.
|
|
3
|
+
"version": "5.1.1",
|
|
4
4
|
"description": "MCP server that gives AI agents the web: fetch, search, crawl and screenshot from one local Rust binary. Zero API keys, zero accounts, Chrome-true TLS.",
|
|
5
5
|
"license": "AGPL-3.0-only",
|
|
6
6
|
"author": "Bishesh Bhandari",
|