SMOODEV-2620: th crawl crawl/map, scrape extract/screenshot/render, search --scrape, knowledge add-url#214
Merged
Merged
Conversation
…r, search --scrape, knowledge add-url Give agents the full crawler surface from the CLI so a session can discover, crawl, and ingest a site without hand-rolling api-prime requests. Scrape gains LLM extract + screenshot + JS-render controls; new `crawl crawl` does whole-site markdown, `crawl map` does URL discovery, `search --scrape` crawl-enriches results with full page content, and `knowledge add-url` kicks off an async crawl→ingest job into the org's knowledge base. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
🦋 Changeset detectedLatest commit: 9b07ab1 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
Agents driving the CLI could only
th crawl scrapea single page andth search. There was no way to crawl a whole site, discover URLs, run structured LLM extraction, or ingest a site into the org knowledge base without hand-rolling api-prime requests.Solution
Wire the full crawler/search/knowledge surface into
th, against the known api-prime contracts:th crawl scrape—--extract <SPEC>(JSON verbatim, else{"prompt": …}),--screenshot(appends to formats),--render <MODE>. extract/render are authed-only.th crawl crawl <seed>— NEW authed whole-site crawl:--limit,--max-depth(→maxDiscoveryDepth),--extract,--json. Default output:completed/total+ one URL per line.th crawl map <url>— NEW authed URL discovery:--search,--limit,--include-subdomains,--json. Default: one link per line.th search --scrape— forcessearchDepth: "advanced"to crawl-enrich each result (authed tier; clamped on free tier).th api knowledge add-url <url>— NEW authed command →POST /organizations/{org}/knowledge/websites{urls:[url], name}(--namedefaults to URL), kicks off async crawl→ingest.Verification
cargo build -p smooai-smooth-cli --bin thcompiles clean (only pre-existing warnings in other modules).--helpoutputs render:th crawl --help(scrape/crawl/map), the three subcommands' flags,th search --help(--scrape),th api knowledge --help(add-url) andth api knowledge add-url --help.@smooai/smooth: minor).Backend crawl/search/knowledge routes are being added in parallel; this CLI is written against the known contract.
🤖 Generated with Claude Code