Skip to content

feat: add captcha solving logic #778

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
buggyhunter merged 6 commits into from
Aug 18, 2026
Merged

feat: add captcha solving logic #778

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
aa32e3c
feat: add captcha solving logic
alitariksahin Aug 18, 2026
c714a8b
chore(llms): regenerate llms.txt and llms-full.txt
github-actions[bot] Aug 18, 2026
55c164a
chore: remove captcha
alitariksahin Aug 18, 2026
659bc6a
chore(llms): regenerate llms.txt and llms-full.txt
github-actions[bot] Aug 18, 2026
e7abddd
chore: remove unnecessary run note
alitariksahin Aug 18, 2026
5a25888
chore(llms): regenerate llms.txt and llms-full.txt
github-actions[bot] Aug 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 7 additions & 19 deletions box/overall/browser/cookbook.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,29 +7,21 @@ description: "Runnable browser examples grouped by use case. Each one is self-co
Every example is a single self-contained file in the [Box SDK
repo](https://github.com/upstash/box/tree/main/packages/sdk/examples/browser).
All of them need `UPSTASH_BOX_API_KEY`. Examples marked **AI** use metered
browser AI (`run`, `act`, `extract`) and need a model provider key on the box
browser AI (`act`, `extract`, `observe`) and need a model provider key on the box
or account. Everything else runs with the Box key alone.
</Info>

## Agents
## Agentic browsing

Goal-driven browsing with `tab.run()`.
Goal-driven browsing: hand a goal to the box's agent, or drive your own loop.

<CardGroup cols={2}>
<Card title="Search with fallback" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/01-search-with-fallback.ts">
Constrained search with a fallback category. The agent evaluates results, rejects with reasons, and switches on its own. **AI**
<Card title="In-box agent" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agentic/01-in-box-agent.ts">
Hand a goal to `box.agent.run`; the box's agent drives the browser through the chrome-devtools MCP and writes results to the box (needs an agent key; bills coding-agent tokens). **Agent**
</Card>

<Card title="Playwright vs act vs run" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/02-playwright-vs-act-vs-run.ts">
The same task via Playwright, `act` plus `extract`, and `run`. Pick your autonomy level by token cost. **AI**
</Card>

<Card title="Observe, record, audit" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/03-observe-record-audit.ts">
The search again with live view, session recording, a decision log, and token accounting. **AI**
</Card>

<Card title="Multisite feed" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/04-multisite-feed.ts">
One prompt and one schema across three differently structured sites. **AI**
<Card title="Build your own loop" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agentic/02-build-your-own-loop.ts">
A live `observe` then `act(action)` then `extract` loop you own, with `extract` as the stop check. **AI**
</Card>
</CardGroup>

Expand Down Expand Up @@ -90,10 +82,6 @@ The box as a test environment.
The box hosts the app under test and browses it on its own localhost.
</Card>

<Card title="AI smoke tests" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/testing/03-ai-smoke-tests.ts">
Agent-driven smoke flow, cross-checked by deterministic DOM assertions, recorded on video. **AI**
</Card>

<Card title="Visual regression" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/testing/04-visual-regression.ts">
Pixelmatch diffs against baselines stored on the box.
</Card>
Expand Down
26 changes: 7 additions & 19 deletions llms-full.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2959,29 +2959,21 @@ Source: https://upstash.com/docs/box/overall/browser/cookbook
Every example is a single self-contained file in the [Box SDK
repo](https://github.com/upstash/box/tree/main/packages/sdk/examples/browser).
All of them need `UPSTASH_BOX_API_KEY`. Examples marked **AI** use metered
browser AI (`run`, `act`, `extract`) and need a model provider key on the box
browser AI (`act`, `extract`, `observe`) and need a model provider key on the box
or account. Everything else runs with the Box key alone.
</Info>

## Agents
## Agentic browsing

Goal-driven browsing with `tab.run()`.
Goal-driven browsing: hand a goal to the box's agent, or drive your own loop.

<CardGroup cols={2}>
<Card title="Search with fallback" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/01-search-with-fallback.ts">
Constrained search with a fallback category. The agent evaluates results, rejects with reasons, and switches on its own. **AI**
</Card>

<Card title="Playwright vs act vs run" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/02-playwright-vs-act-vs-run.ts">
The same task via Playwright, `act` plus `extract`, and `run`. Pick your autonomy level by token cost. **AI**
<Card title="In-box agent" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agentic/01-in-box-agent.ts">
Hand a goal to `box.agent.run`; the box's agent drives the browser through the chrome-devtools MCP and writes results to the box (needs an agent key; bills coding-agent tokens). **Agent**
</Card>

<Card title="Observe, record, audit" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/03-observe-record-audit.ts">
The search again with live view, session recording, a decision log, and token accounting. **AI**
</Card>

<Card title="Multisite feed" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agents/04-multisite-feed.ts">
One prompt and one schema across three differently structured sites. **AI**
<Card title="Build your own loop" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/agentic/02-build-your-own-loop.ts">
A live `observe` then `act(action)` then `extract` loop you own, with `extract` as the stop check. **AI**
</Card>
</CardGroup>

Expand Down Expand Up @@ -3042,10 +3034,6 @@ The box as a test environment.
The box hosts the app under test and browses it on its own localhost.
</Card>

<Card title="AI smoke tests" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/testing/03-ai-smoke-tests.ts">
Agent-driven smoke flow, cross-checked by deterministic DOM assertions, recorded on video. **AI**
</Card>

<Card title="Visual regression" href="https://github.com/upstash/box/blob/main/packages/sdk/examples/browser/testing/04-visual-regression.ts">
Pixelmatch diffs against baselines stored on the box.
</Card>
Expand Down