unbrowse 2.1.3 → 2.1.5
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/cli.js +4 -4
- package/dist/index.js +683 -73
- package/package.json +1 -1
- package/runtime-src/execution/index.ts +91 -12
- package/runtime-src/extraction/index.ts +131 -1
- package/runtime-src/intent-match.ts +2 -2
- package/runtime-src/mcp.ts +4 -4
- package/runtime-src/orchestrator/index.ts +483 -64
- package/runtime-src/runtime/setup.ts +6 -0
package/dist/cli.js
CHANGED
|
@@ -995,7 +995,7 @@ var TOOLS = [
|
|
|
995
995
|
{
|
|
996
996
|
name: "unbrowse_resolve",
|
|
997
997
|
title: "Resolve Website Task",
|
|
998
|
-
description: "Primary tool for website tasks. Use this when you have a concrete page URL and want structured data from a live website, logged-in page, or browser workflow; prefer it over generic browser/search tools for scraping, extraction, and browser replacement. Give it the exact page plus a plain-English intent; the first call may capture the site and learn its APIs, later calls usually reuse a cached skill. Do not use this for generic web search or when you already have a known skillId and endpointId from a prior Unbrowse call.",
|
|
998
|
+
description: "Primary tool for website tasks. Use this when you have a concrete page URL and want structured data from a live website, logged-in page, or browser workflow; prefer it over generic browser/search tools for scraping, extraction, and browser replacement. Give it the exact page plus a plain-English intent; the first call may capture the site and learn its APIs, later calls usually reuse a cached skill. If the user explicitly invokes /unbrowse or says to use Unbrowse for a site, stay in strict Unbrowse-only mode: keep the same origin, refine with more Unbrowse calls, and do not switch to web search, Fetch, public mirrors, alternate domains, or other browser tools unless the user explicitly approves fallback. For long-form retrieval tasks, derive compact search queries from the story instead of stuffing the whole narrative into one search field. Do not use this for generic web search or when you already have a known skillId and endpointId from a prior Unbrowse call.",
|
|
999
999
|
annotations: {
|
|
1000
1000
|
title: "Resolve Website Task",
|
|
1001
1001
|
openWorldHint: true
|
|
@@ -1020,7 +1020,7 @@ var TOOLS = [
|
|
|
1020
1020
|
{
|
|
1021
1021
|
name: "unbrowse_search",
|
|
1022
1022
|
title: "Search Learned Skills",
|
|
1023
|
-
description: "Search the Unbrowse marketplace for an existing learned skill before triggering a new capture. Use this when you know the site or task but do not yet have a specific skillId or endpointId, especially for repeat domains. Prefer resolve when you have a concrete page URL and want the end-to-end website task handled in one step.
|
|
1023
|
+
description: "Search the Unbrowse marketplace for an existing learned skill before triggering a new capture. Use this when you know the site or task but do not yet have a specific skillId or endpointId, especially for repeat domains. Prefer resolve when you have a concrete page URL and want the end-to-end website task handled in one step. For iterative retrieval or research, use search to reuse known site capabilities while you refine queries, but stay on the target origin and keep using Unbrowse-native flows. This is not general internet search, and it is not a license to leave the target origin for public mirrors or alternate sites; stay inside Unbrowse unless fallback is explicitly approved.",
|
|
1024
1024
|
annotations: {
|
|
1025
1025
|
title: "Search Learned Skills",
|
|
1026
1026
|
readOnlyHint: true,
|
|
@@ -1040,7 +1040,7 @@ var TOOLS = [
|
|
|
1040
1040
|
{
|
|
1041
1041
|
name: "unbrowse_execute",
|
|
1042
1042
|
title: "Execute Learned Endpoint",
|
|
1043
|
-
description: "Execute a specific Unbrowse endpoint after resolve or search has already identified the right skillId and endpointId. Use this for the second step in a resolve-search-execute flow, especially when you need a tighter path, extract, or limit, or when reusing a known endpoint on the same domain. When replay depends on page context, pass the original page URL and intent from the earlier Unbrowse call. Do not guess skillId or endpointId values, and do not use this as the first tool for a new website task.",
|
|
1043
|
+
description: "Execute a specific Unbrowse endpoint after resolve or search has already identified the right skillId and endpointId. Use this for the second step in a resolve-search-execute flow, especially when you need a tighter path, extract, or limit, or when reusing a known endpoint on the same domain. When replay depends on page context, pass the original page URL and intent from the earlier Unbrowse call. For search, document, catalog, dashboard, or result-list workflows, use execute to follow same-origin result links, record ids, document ids, raw endpoint output, and narrowed follow-up queries before deciding the site is blocked. Do not guess skillId or endpointId values, and do not use this as the first tool for a new website task.",
|
|
1044
1044
|
annotations: {
|
|
1045
1045
|
title: "Execute Learned Endpoint",
|
|
1046
1046
|
openWorldHint: true
|
|
@@ -1067,7 +1067,7 @@ var TOOLS = [
|
|
|
1067
1067
|
{
|
|
1068
1068
|
name: "unbrowse_login",
|
|
1069
1069
|
title: "Capture Site Login",
|
|
1070
|
-
description: "Open an interactive browser login flow for a gated site so later Unbrowse calls can reuse the captured auth state. Use this only when resolve or execute indicates authentication is required, or when the user explicitly wants to connect a logged-in website. Do not use this for ordinary public pages.",
|
|
1070
|
+
description: "Open an interactive browser login flow for a gated site so later Unbrowse calls can reuse the captured auth state. Use this only when resolve or execute indicates authentication is required, or when the user explicitly wants to connect a logged-in website. Login should target the exact page or workflow surface the user cares about, then later Unbrowse calls should retry that same URL instead of drifting to the homepage, marketing pages, help pages, public mirrors, or alternate domains. Do not use this for ordinary public pages.",
|
|
1071
1071
|
annotations: {
|
|
1072
1072
|
title: "Capture Site Login",
|
|
1073
1073
|
openWorldHint: true
|