Compare commits

...

27 Commits

Author SHA1 Message Date
Nikhil Sonti
bc90766714 fix: bun.lock update 2026-03-26 17:34:40 -07:00
Nikhil Sonti
de50c5b378 fix: move cli install docs to top-level readme 2026-03-26 17:30:46 -07:00
Nikhil Sonti
ffe48948ff feat: add CDN upload flow for cli installers 2026-03-26 17:29:07 -07:00
Nikhil
03b45013a6 feat(cli): add install scripts for macOS, Linux, and Windows (#587)
* feat(cli): add install scripts for macOS, Linux, and Windows

Bash script (install.sh) for macOS/Linux and PowerShell script
(install.ps1) for Windows. Both download the correct platform binary
from GitHub Releases with checksum verification, version resolution,
and PATH setup.

* fix(cli): address PR review comments for install scripts

- Add checksum verification to install.ps1 using Get-FileHash
- Add warnings on all checksum skip paths in install.sh
- Use grep -F (fixed-string) instead of regex for filename matching
- Add ?per_page=100 to GitHub API call in install.ps1
- Use random temp directory name in install.ps1 to avoid collisions

* fix(cli): address installer review feedback
2026-03-26 17:05:21 -07:00
shivammittal274
aa85907212 Feat/cli launch ready v2 (#582)
* fix(cli): use full path for dist artifacts in release step

* test: temporarily allow release workflow on any branch

* fix(cli): restore main-only guard, remove goreleaser dependency

Replaces GoReleaser (Pro-only monorepo feature) with plain go build.
Tested: RC release created successfully on branch with all 6 binaries.
2026-03-27 01:28:04 +05:30
Nikhil
085352a6f0 fix(ui): resolve MCP promo banner dismiss button overlapping with text (#581)
Move dismiss button from absolute positioning to inline flex child,
preventing it from overlapping with the "Set up" button.
2026-03-26 12:54:00 -07:00
shivammittal274
c0578d0e53 Feat/cli launch ready v2 (#580)
* fix(cli): update goreleaser tag_prefix to match browseros-cli-v* format

* fix(cli): replace goreleaser with plain go build for releases

GoReleaser free version cannot parse prefixed tags (browseros-cli-v*).
monorepo.tag_prefix is a Pro-only feature.

Replaced with direct go build + gh release create:
- Builds all 6 targets with go build (verified locally)
- Creates tar.gz/zip archives with checksums
- Uses gh release create to publish
- No external tool dependency
2026-03-27 01:12:25 +05:30
shivammittal274
663c18ee97 fix(cli): update goreleaser tag_prefix to match browseros-cli-v* format (#579) 2026-03-27 01:07:36 +05:30
Dani Akash
48727750b4 fix: change CLI tag format from cli/v* to browseros-cli-v* (#578)
GoReleaser free cannot parse slash-prefixed tags (cli/v0.0.1) as semver.
Switch to browseros-cli-v0.0.1 format which is valid semver after
stripping the prefix. Remove the monorepo config (GoReleaser Pro only).
2026-03-27 00:58:13 +05:30
Dani Akash
30a3a96a57 fix: add monorepo tag prefix for goreleaser to parse cli/ tags (#576) 2026-03-27 00:50:38 +05:30
shivammittal274
6773ce39da ci(cli): manual dispatch release workflow (#574)
* ci(cli): change release workflow to manual dispatch from main

- Trigger via Actions UI with a version input (e.g. "0.1.0")
- Only runs on main branch
- Creates git tag cli/v<version> automatically
- Then GoReleaser builds all 6 binaries and creates the GitHub Release

* feat: add scoped release notes, changelog PR, and idempotent tags to CLI workflow

- Add concurrency group to prevent parallel releases
- Add scoped release notes from commits touching the CLI directory
- Pass release notes to goreleaser via --release-notes flag
- Make tag creation idempotent for safe re-runs
- Tag the saved release SHA, not HEAD after branching
- Add CHANGELOG.md and auto-update via PR with auto-merge
- Add pull-requests: write permission

---------

Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
2026-03-27 00:41:08 +05:30
github-actions[bot]
342a3e4a07 docs: update agent extension changelog for v0.0.52 (#573)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-03-26 19:01:46 +00:00
Dani Akash
09406ea794 feat: add release workflow for agent extension (#572)
* feat: add release workflow for agent extension

Adds a workflow_dispatch workflow that builds the WXT extension,
creates a .zip for sideloading, generates scoped release notes with
contributors and PR links, creates a GitHub release with the zip
attached, and opens an auto-merge PR to update CHANGELOG.md.

* fix: correct API URL to api.browseros.com

* fix: remove duplicate PR numbers and contributors from extension release notes

Apply the same fixes from the agent-sdk workflow:
- Skip PR number if already in commit subject (squash merges)
- Remove custom Contributors section (GitHub auto-generates one)
- Clean up unused variables

* fix: use absolute path for extension zip in release upload

* fix: wxt zip already builds, use correct output path

- Remove separate build step since wxt zip runs the build internally
- Fix zip path from .output/*.zip to dist/*-chrome.zip

* fix: run codegen before wxt zip to generate graphql types
2026-03-27 00:29:47 +05:30
Dani Akash
1f00cbc9cc feat: add release workflow for agent extension (#566)
* feat: add release workflow for agent extension

Adds a workflow_dispatch workflow that builds the WXT extension,
creates a .zip for sideloading, generates scoped release notes with
contributors and PR links, creates a GitHub release with the zip
attached, and opens an auto-merge PR to update CHANGELOG.md.

* fix: correct API URL to api.browseros.com

* fix: remove duplicate PR numbers and contributors from extension release notes

Apply the same fixes from the agent-sdk workflow:
- Skip PR number if already in commit subject (squash merges)
- Remove custom Contributors section (GitHub auto-generates one)
- Clean up unused variables

* fix: use absolute path for extension zip in release upload

* fix: wxt zip already builds, use correct output path

- Remove separate build step since wxt zip runs the build internally
- Fix zip path from .output/*.zip to dist/*-chrome.zip
2026-03-27 00:23:04 +05:30
Dani Akash
422a829f5e fix: remove duplicate PR numbers and contributors from release notes (#571)
- Skip adding PR number if already present in the commit subject
  (squash merges include "(#123)" automatically)
- Remove custom Contributors section since GitHub auto-generates one
  with avatars at the bottom of every release
2026-03-27 00:07:13 +05:30
github-actions[bot]
ed109fcedf docs: update agent-sdk changelog for v0.0.7 (#570)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-03-26 18:31:39 +00:00
Dani Akash
19af96d08e chore: bump @browseros-ai/agent-sdk to 0.0.7 (#569) 2026-03-27 00:00:35 +05:30
Dani Akash
e0304b203c chore: bump @browseros-ai/agent-sdk to 0.0.6 (#568) 2026-03-26 23:53:35 +05:30
Nikhil
af65bdbcfb feat(build): add build:server:ci script with --compile-only flag (#567)
Add a compile-only mode to the server build pipeline for CI/CD
environments that don't have R2 credentials. The --compile-only flag
skips resource staging and upload, producing only compiled binaries.
2026-03-26 11:21:39 -07:00
Dani Akash
d79c2a4123 feat: create GitHub release with changelog on agent-sdk publish (#564)
* feat: create GitHub release with changelog on agent-sdk publish

After publishing to npm, the workflow now:
- Tags the commit as agent-sdk-v<version>
- Generates release notes from commits that modified the agent-sdk
  directory since the last agent-sdk release tag
- Creates a GitHub release with those notes

First release will show "Initial release" since no previous tag exists.

* feat: update CHANGELOG.md on agent-sdk release

Add a CHANGELOG.md for @browseros-ai/agent-sdk and update the release
workflow to prepend a versioned entry with the release notes before
creating the GitHub release. The changelog is committed to main
automatically.

* fix: address review issues in agent-sdk release workflow

- Add explicit permissions: contents: write
- Replace sed with head/tail for safe CHANGELOG insertion (fixes
  double-quote and backslash corruption in commit messages)
- Handle empty release notes with "No notable changes." fallback
- Make git tag idempotent for workflow reruns (2>/dev/null || true)

* fix: use PR with auto-merge for changelog updates

Direct push to main fails due to branch protection requiring PRs.
Instead, create a branch, open a PR, and auto-merge via squash.

* feat: add contributors and PR links to agent-sdk release notes

Release notes now include PR numbers (linked automatically by GitHub),
GitHub usernames for each commit author, and a contributors section
at the bottom. All scoped to commits that modified the agent-sdk path.

* fix: reorder release steps and fix tag/idempotency issues

- Capture release SHA before any branching so the tag always points
  to the main commit that was built and published to npm
- Reorder: generate notes → publish → tag/release → changelog PR
  (changelog is lowest-stakes, runs last)
- Make tag push and release create idempotent for safe re-runs
  (fall back to gh release edit if release already exists)
- Add || true to gh pr merge --auto in case auto-merge is not enabled
- Explicit git checkout main before creating changelog branch

* fix: explicit error handling for tag/release and contributor dedup

- Replace silent || true guards with explicit checks that log what's
  happening (tag exists, remote tag exists, release exists) so errors
  are visible instead of swallowed
- Fix contributor dedup: use grep -qw (word match) instead of grep -qF
  (substring match) so "dan" isn't excluded when "dansmith" exists

* fix: exclude current version tag when finding previous release

On re-runs, the current version's tag already exists on the remote, so
PREV_TAG resolves to it and git log produces empty output. Filter it
out so release notes are generated against the actual previous version.

* ci: prevent concurrent agent-sdk release runs

Add concurrency group so multiple dispatches queue instead of racing
on the same tag/release/PR.
2026-03-26 23:38:14 +05:30
shivammittal274
e3d57e5347 feat(cli): production-ready CLI with auto-launch, install, and cross-platform builds (#555)
* feat(cli): production-ready CLI with auto-launch, install, and cross-platform builds

- init: accept URL argument and --auto flag for non-interactive setup
- install: new command to download BrowserOS app for current platform
- launch: auto-detect and launch BrowserOS when server is not running
- discovery: prefer server.json (live) over config.yaml (may be stale)
- errors: actionable messages guiding users to init/install
- goreleaser: cross-platform builds for 6 targets (darwin/linux/windows × amd64/arm64)
- ci: GitHub Actions workflow to release CLI binaries on cli/v* tag push

* fix(cli): check health status code and add progress dots during launch

- Health check in newClient() now verifies HTTP 200, not just no error
- waitForServer prints dots during the 30s poll so users know it's working

* refactor(cli): make launch an explicit command, remove auto-launch from newClient

- launch: new explicit command to find and open BrowserOS app
- launch: probes server.json, config, and common ports before launching
- launch: if already running, reports URL instead of launching again
- init --auto: uses port probing to find running servers
- install --deb: errors on non-Linux instead of silently downloading DMG
- error messages: guide users to launch/install/init explicitly
- removed: auto-launch from newClient() — CLI never does something surprising

* fix(cli): platform-native detection, launch, and install for all OSes

Detection (isBrowserOSInstalled):
- macOS: uses `open -Ra` to query Launch Services (no hardcoded paths)
- Linux: checks /usr/bin/browseros (.deb), browseros.desktop, AppImage search
- Windows: checks %LOCALAPPDATA%\BrowserOS\Application\BrowserOS.exe
  and HKCU/HKLM uninstall registry keys

Launch (startBrowserOS):
- macOS: `open -b com.browseros.BrowserOS` (bundle ID, not path)
- Linux: `browseros` binary, AppImage, or `gtk-launch browseros`
  (fixed: was using xdg-open which opens by MIME type, not desktop files)
- Windows: runs BrowserOS.exe from known Chromium per-user install path
  (fixed: was using `cmd /c start BrowserOS` which doesn't resolve)

Install (runPostInstall):
- macOS: hdiutil attach → cp -R to /Applications → hdiutil detach
- Linux: chmod +x for AppImage, dpkg -i instruction for .deb
- Windows: launches installer exe
- --deb flag now errors on non-Linux platforms

Removed auto-launch from newClient() — CLI never does surprising things.

Sources verified from:
- packages/browseros/build/common/context.py (binary names per platform)
- packages/browseros/build/modules/package/linux.py (.deb structure, .desktop file)
- packages/browseros/chromium_patches/chrome/install_static/chromium_install_modes.h
  (Windows base_app_name="BrowserOS", registry GUID, install paths)
- /Applications/BrowserOS.app/Contents/Info.plist (bundle ID)
2026-03-26 23:12:55 +05:30
Dani Akash
392312f203 ci: only run PR title validation on open and edit (#565)
Remove synchronize and reopened triggers since this workflow only
validates the PR title, which doesn't change on new commits or reopen.
2026-03-26 23:06:11 +05:30
Dani Akash
0f193055c7 fix: broaden connection error detection for main page and sidepanel (#563)
* fix: broaden connection error detection for main page and sidepanel

The connection error check required both "Failed to fetch" AND
"127.0.0.1" in the error message. On the main page, the browser
only produces "Failed to fetch" without the IP, so users saw a
generic "Something went wrong" instead of the troubleshooting link.

Broaden detection to also match "localhost" and bare "Failed to fetch"
errors that don't contain an external URL. Also pass providerType in
NewTabChat so provider-specific errors render correctly.

Closes #526

* fix: simplify connection error detection

All chat requests go through the local BrowserOS agent server, so any
"Failed to fetch" error is always a local connection issue. Remove the
unnecessary 127.0.0.1/localhost/URL checks.

* fix: pass providerType to agentUrlError ChatError instances
2026-03-26 20:55:40 +05:30
Dani Akash
f45cb58889 fix: stop sending port-in-use errors to Sentry (#558)
Port conflicts are expected — Chromium retries with a different port.
These errors were flooding Sentry (14k+ events) without user impact.

- handleStartupError: move Sentry.captureException below the
  port-in-use check so it only fires for unexpected startup errors
- handleControllerStartupError: skip Sentry capture for port errors
- index.ts: exit early for port errors before Sentry capture
2026-03-26 09:32:18 +05:30
shivammittal274
37ead6d129 fix: add cursor-pointer to credit badge in sidepanel (#554) 2026-03-26 00:09:58 +05:30
Nikhil
5ea9463030 fix: widen scheduled task results dialog and add horizontal scroll for tables (#549)
- Change dialog width from sm:max-w-2xl (672px) to sm:w-[70vw] sm:max-w-4xl
  so it takes 70% of viewport width, capped at 896px
- Add overflow-x-auto on table wrappers so wide tables scroll horizontally
  instead of being clipped

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-24 16:27:46 -07:00
shivammittal274
dde35ccbd5 feat: integrate models.dev for dynamic LLM provider/model data (#547)
* feat: integrate models.dev for dynamic LLM provider/model data (#TKT-657)

Replace hardcoded model lists with data sourced from models.dev so new
providers and models appear automatically when the community adds them.

- Add build script (scripts/generate-models.ts) that fetches models.dev/api.json
  and outputs a compact JSON with 10 providers and 520 models
- Replace hardcoded MODELS_DATA (50 models) with dynamic models.dev lookups
- Add searchable model combobox (Popover + Command) replacing plain Select dropdown
- Enrich provider templates with models.dev metadata (context window, image support)
- Keep chatgpt-pro, qwen-code, browseros, openai-compatible as hardcoded providers

* fix: address review — remove ollama-cloud mapping, fix default models, remove dead code

- Remove ollama from PROVIDER_MAP (ollama-cloud has cloud models, not local)
- Add ollama to CUSTOM_PROVIDER_MODELS with empty list (users type custom IDs)
- Update defaultModelIds to ones that exist in models.dev data:
  openrouter → anthropic/claude-sonnet-4.5
  lmstudio → openai/gpt-oss-20b
  bedrock → anthropic.claude-sonnet-4-6
- Remove dead isCustomModel export
- Regenerate models-dev-data.json (9 providers, 486 models)

* fix: model suggestion list focus/dismiss behavior

- List only opens when input is focused or user types
- Clicking a model selects it and closes the list
- Clicking outside (blur) dismisses the list
- onMouseDown preventDefault on list items prevents blur race condition

* refactor: extract ModelPickerList component with proper open/close UX

- Collapsed state: Select-like trigger showing selected model + chevron
- Expanded state: search input + scrollable filtered list, inline
- Click outside or Escape to close, Enter to submit custom model
- Extracted as separate component (reduces dialog nesting, testable)
- No more setTimeout hacks for blur handling

* chore: remove plan doc from repo
2026-03-25 02:41:07 +05:30
47 changed files with 7434 additions and 321 deletions

View File

@@ -2,7 +2,7 @@ name: PR Conventional Commit Validation
on:
pull_request:
types: [opened, synchronize, reopened, edited]
types: [opened, edited]
permissions:
pull-requests: write

View File

@@ -0,0 +1,148 @@
name: Release Agent Extension
on:
workflow_dispatch:
concurrency:
group: release-agent-extension
cancel-in-progress: false
jobs:
release:
if: github.ref == 'refs/heads/main'
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
defaults:
run:
working-directory: packages/browseros-agent/apps/agent
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- uses: oven-sh/setup-bun@v2
- name: Install dependencies
run: bun ci
working-directory: packages/browseros-agent
- name: Build and zip extension
run: bun run codegen && bun run zip
env:
VITE_PUBLIC_BROWSEROS_API: https://api.browseros.com
- name: Get version and zip path
id: version
run: |
echo "version=$(node -p "require('./package.json').version")" >> "$GITHUB_OUTPUT"
echo "release_sha=$(git rev-parse HEAD)" >> "$GITHUB_OUTPUT"
ZIP_FILE=$(ls "$(pwd)/dist/"*-chrome.zip | head -n 1)
echo "zip_path=$ZIP_FILE" >> "$GITHUB_OUTPUT"
echo "zip_name=$(basename "$ZIP_FILE")" >> "$GITHUB_OUTPUT"
- name: Generate release notes
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
AGENT_PATH="packages/browseros-agent/apps/agent"
CURRENT_TAG="agent-extension-v${{ steps.version.outputs.version }}"
PREV_TAG=$(git tag -l "agent-extension-v*" --sort=-v:refname | grep -v "^${CURRENT_TAG}$" | head -n 1)
if [ -z "$PREV_TAG" ]; then
echo "Initial release" > /tmp/release-notes.md
else
COMMITS=$(git log "$PREV_TAG"..HEAD --pretty=format:"%H" -- "$AGENT_PATH")
if [ -z "$COMMITS" ]; then
echo "No notable changes." > /tmp/release-notes.md
else
echo "## What's Changed" > /tmp/release-notes.md
echo "" >> /tmp/release-notes.md
while IFS= read -r SHA; do
SUBJECT=$(git log -1 --pretty=format:"%s" "$SHA")
PR_NUM=$(gh api "/repos/${{ github.repository }}/commits/${SHA}/pulls" --jq '.[0].number // empty' 2>/dev/null)
# Skip PR number if already in the commit subject (squash merges include it)
if [ -n "$PR_NUM" ] && ! echo "$SUBJECT" | grep -qF "(#${PR_NUM})"; then
echo "- ${SUBJECT} (#${PR_NUM})" >> /tmp/release-notes.md
else
echo "- ${SUBJECT}" >> /tmp/release-notes.md
fi
done <<< "$COMMITS"
fi
fi
working-directory: ${{ github.workspace }}
- name: Create GitHub release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
TAG="agent-extension-v${{ steps.version.outputs.version }}"
RELEASE_SHA="${{ steps.version.outputs.release_sha }}"
TITLE="BrowserOS Agent Extension v${{ steps.version.outputs.version }}"
if git rev-parse "$TAG" >/dev/null 2>&1; then
echo "Tag $TAG already exists, skipping tag creation"
else
git tag "$TAG" "$RELEASE_SHA"
fi
if git ls-remote --tags origin "$TAG" | grep -q "$TAG"; then
echo "Tag $TAG already on remote, skipping push"
else
git push origin "$TAG"
fi
if gh release view "$TAG" >/dev/null 2>&1; then
echo "Release $TAG already exists, updating"
gh release edit "$TAG" --title "$TITLE" --notes-file /tmp/release-notes.md
gh release upload "$TAG" "${{ steps.version.outputs.zip_path }}" --clobber
else
gh release create "$TAG" \
--title "$TITLE" \
--notes-file /tmp/release-notes.md \
"${{ steps.version.outputs.zip_path }}"
fi
working-directory: ${{ github.workspace }}
- name: Update CHANGELOG.md via PR
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
VERSION="${{ steps.version.outputs.version }}"
DATE=$(date -u +"%Y-%m-%d")
BRANCH="docs/agent-extension-changelog-v${VERSION}"
CHANGELOG="packages/browseros-agent/apps/agent/CHANGELOG.md"
git checkout main
{
head -n 1 "$CHANGELOG"
echo ""
echo "## v${VERSION} (${DATE})"
echo ""
cat /tmp/release-notes.md
echo ""
tail -n +2 "$CHANGELOG"
} > /tmp/new-changelog.md
mv /tmp/new-changelog.md "$CHANGELOG"
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
git checkout -b "$BRANCH"
git add "$CHANGELOG"
git commit -m "docs: update agent extension changelog for v${VERSION}"
git push origin "$BRANCH"
gh pr create \
--title "docs: update agent extension changelog for v${VERSION}" \
--body "Auto-generated changelog update for BrowserOS Agent Extension v${VERSION}." \
--base main \
--head "$BRANCH"
gh pr merge "$BRANCH" --squash --auto || true
working-directory: ${{ github.workspace }}

View File

@@ -3,16 +3,25 @@ name: Release Agent SDK
on:
workflow_dispatch:
concurrency:
group: release-agent-sdk
cancel-in-progress: false
jobs:
publish:
if: github.ref == 'refs/heads/main'
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
defaults:
run:
working-directory: packages/browseros-agent/packages/agent-sdk
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- uses: oven-sh/setup-bun@v2
@@ -31,7 +40,129 @@ jobs:
- name: Test
run: bun test
- name: Get version
id: version
run: |
echo "version=$(node -p "require('./package.json').version")" >> "$GITHUB_OUTPUT"
echo "release_sha=$(git rev-parse HEAD)" >> "$GITHUB_OUTPUT"
- name: Generate release notes
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
SDK_PATH="packages/browseros-agent/packages/agent-sdk"
CURRENT_TAG="agent-sdk-v${{ steps.version.outputs.version }}"
# Find the previous tag, excluding the current version's tag
# (which may already exist from a prior failed run)
PREV_TAG=$(git tag -l "agent-sdk-v*" --sort=-v:refname | grep -v "^${CURRENT_TAG}$" | head -n 1)
if [ -z "$PREV_TAG" ]; then
echo "Initial release" > /tmp/release-notes.md
else
# Get commits scoped to the SDK directory
COMMITS=$(git log "$PREV_TAG"..HEAD --pretty=format:"%H" -- "$SDK_PATH")
if [ -z "$COMMITS" ]; then
echo "No notable changes." > /tmp/release-notes.md
else
echo "## What's Changed" > /tmp/release-notes.md
echo "" >> /tmp/release-notes.md
# For each commit, find the associated PR and format with author
CONTRIBUTORS=""
while IFS= read -r SHA; do
# Get commit subject and author
SUBJECT=$(git log -1 --pretty=format:"%s" "$SHA")
AUTHOR=$(git log -1 --pretty=format:"%an" "$SHA")
GITHUB_USER=$(gh api "/repos/${{ github.repository }}/commits/${SHA}" --jq '.author.login // empty' 2>/dev/null)
# Find associated PR number
PR_NUM=$(gh api "/repos/${{ github.repository }}/commits/${SHA}/pulls" --jq '.[0].number // empty' 2>/dev/null)
# Format line: skip PR number if already in the commit subject
# (squash merges include "(#123)" in the subject automatically)
if [ -n "$PR_NUM" ] && ! echo "$SUBJECT" | grep -qF "(#${PR_NUM})"; then
echo "- ${SUBJECT} (#${PR_NUM})" >> /tmp/release-notes.md
else
echo "- ${SUBJECT}" >> /tmp/release-notes.md
fi
done <<< "$COMMITS"
fi
fi
working-directory: ${{ github.workspace }}
- name: Publish
run: npm publish --access public
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
- name: Create GitHub release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
TAG="agent-sdk-v${{ steps.version.outputs.version }}"
RELEASE_SHA="${{ steps.version.outputs.release_sha }}"
TITLE="@browseros-ai/agent-sdk v${{ steps.version.outputs.version }}"
# Create or reuse tag (idempotent for re-runs)
if git rev-parse "$TAG" >/dev/null 2>&1; then
echo "Tag $TAG already exists, skipping tag creation"
else
git tag "$TAG" "$RELEASE_SHA"
fi
# Push tag (skip if already on remote)
if git ls-remote --tags origin "$TAG" | grep -q "$TAG"; then
echo "Tag $TAG already on remote, skipping push"
else
git push origin "$TAG"
fi
# Create or update release
if gh release view "$TAG" >/dev/null 2>&1; then
echo "Release $TAG already exists, updating"
gh release edit "$TAG" --title "$TITLE" --notes-file /tmp/release-notes.md
else
gh release create "$TAG" --title "$TITLE" --notes-file /tmp/release-notes.md
fi
working-directory: ${{ github.workspace }}
- name: Update CHANGELOG.md via PR
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
VERSION="${{ steps.version.outputs.version }}"
DATE=$(date -u +"%Y-%m-%d")
BRANCH="docs/agent-sdk-changelog-v${VERSION}"
CHANGELOG="packages/browseros-agent/packages/agent-sdk/CHANGELOG.md"
# Return to main before branching
git checkout main
# Use head/tail to safely insert without sed quoting issues
{
head -n 1 "$CHANGELOG"
echo ""
echo "## v${VERSION} (${DATE})"
echo ""
cat /tmp/release-notes.md
echo ""
tail -n +2 "$CHANGELOG"
} > /tmp/new-changelog.md
mv /tmp/new-changelog.md "$CHANGELOG"
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
git checkout -b "$BRANCH"
git add "$CHANGELOG"
git commit -m "docs: update agent-sdk changelog for v${VERSION}"
git push origin "$BRANCH"
gh pr create \
--title "docs: update agent-sdk changelog for v${VERSION}" \
--body "Auto-generated changelog update for @browseros-ai/agent-sdk v${VERSION}." \
--base main \
--head "$BRANCH"
gh pr merge "$BRANCH" --squash --auto || true
working-directory: ${{ github.workspace }}

122
.github/workflows/release-cli.yml vendored Normal file
View File

@@ -0,0 +1,122 @@
name: Release CLI
on:
workflow_dispatch:
inputs:
version:
description: "Release version (e.g. 0.1.0)"
required: true
type: string
concurrency:
group: release-cli
cancel-in-progress: false
jobs:
release:
if: github.ref == 'refs/heads/main'
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
defaults:
run:
working-directory: packages/browseros-agent/apps/cli
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- uses: actions/setup-go@v5
with:
go-version-file: packages/browseros-agent/apps/cli/go.mod
- name: Run tests
run: go test ./... -v
- name: Run vet
run: go vet ./...
- name: Build all platforms
run: |
VERSION="${{ inputs.version }}"
LDFLAGS="-s -w -X main.version=${VERSION}"
DIST="dist"
mkdir -p "$DIST"
for pair in darwin/amd64 darwin/arm64 linux/amd64 linux/arm64 windows/amd64 windows/arm64; do
OS="${pair%/*}"
ARCH="${pair#*/}"
BIN="browseros-cli"
EXT=""
if [ "$OS" = "windows" ]; then EXT=".exe"; fi
echo "Building ${OS}/${ARCH}..."
GOOS=$OS GOARCH=$ARCH CGO_ENABLED=0 go build -trimpath -ldflags "$LDFLAGS" -o "${DIST}/${BIN}${EXT}" .
ARCHIVE="browseros-cli_${VERSION}_${OS}_${ARCH}"
if [ "$OS" = "windows" ]; then
(cd "$DIST" && zip "${ARCHIVE}.zip" "${BIN}${EXT}")
else
(cd "$DIST" && tar czf "${ARCHIVE}.tar.gz" "${BIN}")
fi
rm "${DIST}/${BIN}${EXT}"
done
(cd "$DIST" && sha256sum *.tar.gz *.zip > checksums.txt)
echo "=== Built artifacts ==="
ls -lh "$DIST"
- name: Generate release notes
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
CLI_PATH="packages/browseros-agent/apps/cli"
TAG="browseros-cli-v${{ inputs.version }}"
PREV_TAG=$(git tag -l "browseros-cli-v*" --sort=-v:refname | grep -v "^${TAG}$" | head -n 1)
if [ -z "$PREV_TAG" ]; then
echo "Initial release of browseros-cli." > /tmp/release-notes.md
else
COMMITS=$(git log "$PREV_TAG"..HEAD --pretty=format:"%H" -- "$CLI_PATH")
if [ -z "$COMMITS" ]; then
echo "No notable changes." > /tmp/release-notes.md
else
echo "## What's Changed" > /tmp/release-notes.md
echo "" >> /tmp/release-notes.md
while IFS= read -r SHA; do
SUBJECT=$(git log -1 --pretty=format:"%s" "$SHA")
PR_NUM=$(gh api "/repos/${{ github.repository }}/commits/${SHA}/pulls" --jq '.[0].number // empty' 2>/dev/null)
if [ -n "$PR_NUM" ] && ! echo "$SUBJECT" | grep -qF "(#${PR_NUM})"; then
echo "- ${SUBJECT} (#${PR_NUM})" >> /tmp/release-notes.md
else
echo "- ${SUBJECT}" >> /tmp/release-notes.md
fi
done <<< "$COMMITS"
fi
fi
working-directory: ${{ github.workspace }}
- name: Create tag and release
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
TAG="browseros-cli-v${{ inputs.version }}"
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
if ! git rev-parse "$TAG" >/dev/null 2>&1; then
git tag -a "$TAG" -m "browseros-cli v${{ inputs.version }}"
git push origin "$TAG"
fi
CLI_DIST="packages/browseros-agent/apps/cli/dist"
gh release create "$TAG" \
--title "browseros-cli v${{ inputs.version }}" \
--notes-file /tmp/release-notes.md \
${CLI_DIST}/*
working-directory: ${{ github.workspace }}

View File

@@ -43,6 +43,24 @@
4. Start automating!
## Install `browseros-cli`
Use `browseros-cli` when you want to control BrowserOS from the terminal or scripts via the BrowserOS MCP server.
### macOS / Linux
```bash
curl -fsSL https://cdn.browseros.com/cli/install.sh | bash
```
### Windows
```powershell
irm https://cdn.browseros.com/cli/install.ps1 | iex
```
After install, run `browseros-cli init` to point the CLI at your BrowserOS MCP server.
## What makes BrowserOS special
- 🏠 Feels like home — same Chrome interface, all your extensions just work
- 🤖 AI agents that run on YOUR browser, not in the cloud
@@ -164,4 +182,3 @@ Thank you to all our supporters!
Built with ❤️ from San Francisco
</p>

View File

@@ -195,3 +195,4 @@ test-results/
.agent/
.llm/
.grove/
docs/plans/2026-03-24-models-dev-integration.md

View File

@@ -81,6 +81,9 @@ bun run dev:server # Build server for development
bun run dev:ext # Build extension for development
bun run dist:server # Build server for production (all targets)
bun run dist:ext # Build extension for production
# Refresh models.dev data
bun run generate:models # Fetches latest from models.dev/api.json
```
## Architecture

View File

@@ -0,0 +1,6 @@
# BrowserOS Agent Extension
## v0.0.52 (2026-03-26)
Initial release

View File

@@ -66,7 +66,7 @@ export const RunResultDialog: FC<RunResultDialogProps> = ({
return (
<Dialog open={!!run} onOpenChange={onOpenChange}>
<DialogContent className="sm:max-w-2xl">
<DialogContent className="sm:w-[70vw] sm:max-w-4xl">
<DialogHeader>
<DialogTitle className="flex items-center gap-2">
{run.status === 'completed' ? (
@@ -94,7 +94,7 @@ export const RunResultDialog: FC<RunResultDialogProps> = ({
<p className="text-destructive text-sm">{run.result}</p>
</div>
) : run.result ? (
<div className="prose prose-sm dark:prose-invert [&_[data-streamdown='code-block']]:!w-full [&_[data-streamdown='table-wrapper']]:!w-full max-w-none break-words rounded-lg border border-border bg-muted/50 p-4">
<div className="prose prose-sm dark:prose-invert [&_[data-streamdown='code-block']]:!w-full [&_[data-streamdown='table-wrapper']]:!w-full max-w-none break-words rounded-lg border border-border bg-muted/50 p-4 [&_[data-streamdown='table-wrapper']]:overflow-x-auto">
<MessageResponse>{run.result}</MessageResponse>
</div>
) : (

View File

@@ -14,7 +14,7 @@ export const CreditBadge: FC<CreditBadgeProps> = ({ credits, onClick }) => {
type="button"
onClick={onClick}
className={cn(
'inline-flex items-center gap-1 rounded-md px-1.5 py-0.5 font-medium text-xs transition-colors hover:bg-muted/50',
'inline-flex cursor-pointer items-center gap-1 rounded-md px-1.5 py-0.5 font-medium text-xs transition-colors hover:bg-muted/50',
getCreditTextColor(credits),
)}
title={`${credits} credits remaining`}

View File

@@ -17,7 +17,7 @@ export const McpPromoBanner: FC = () => {
}
return (
<div className="relative flex items-center gap-4 rounded-xl border border-border bg-card p-4 shadow-sm transition-all hover:shadow-md">
<div className="flex items-center gap-4 rounded-xl border border-border bg-card p-4 shadow-sm transition-all hover:shadow-md">
<div className="flex h-10 w-10 shrink-0 items-center justify-center rounded-lg bg-[var(--accent-orange)]/10">
<Server className="h-5 w-5 text-[var(--accent-orange)]" />
</div>
@@ -48,7 +48,7 @@ export const McpPromoBanner: FC = () => {
<button
type="button"
onClick={() => setDismissed(true)}
className="absolute top-2 right-2 rounded-sm p-1 text-muted-foreground opacity-50 transition-opacity hover:opacity-100"
className="shrink-0 rounded-sm p-1 text-muted-foreground opacity-50 transition-opacity hover:opacity-100"
>
<X className="h-3.5 w-3.5" />
</button>

View File

@@ -1,6 +1,13 @@
import { zodResolver } from '@hookform/resolvers/zod'
import { CheckCircle2, ExternalLink, Loader2, XCircle } from 'lucide-react'
import { type FC, useEffect, useState } from 'react'
import {
CheckCircle2,
ChevronDown,
ExternalLink,
Loader2,
SearchIcon,
XCircle,
} from 'lucide-react'
import { type FC, useEffect, useRef, useState } from 'react'
import { useForm } from 'react-hook-form'
import { z } from 'zod/v3'
import { Button } from '@/components/ui/button'
@@ -47,7 +54,12 @@ import {
import { type TestResult, testProvider } from '@/lib/llm-providers/testProvider'
import type { LlmProviderConfig, ProviderType } from '@/lib/llm-providers/types'
import { track } from '@/lib/metrics/track'
import { getModelContextLength, getModelOptions } from './models'
import { cn } from '@/lib/utils'
import {
getModelContextLength,
getModelsForProvider,
type ModelInfo,
} from './models'
const providerTypeEnum = z.enum([
'moonshot',
@@ -163,6 +175,107 @@ export const providerFormSchema = z
*/
export type ProviderFormValues = z.infer<typeof providerFormSchema>
function formatContextWindow(tokens: number): string {
if (tokens >= 1000000)
return `${(tokens / 1000000).toFixed(tokens % 1000000 === 0 ? 0 : 1)}M`
if (tokens >= 1000) return `${Math.round(tokens / 1000)}K`
return `${tokens}`
}
function ModelPickerList({
models,
selectedModelId,
onSelect,
onCustomSubmit,
onClose,
}: {
models: ModelInfo[]
selectedModelId: string
onSelect: (modelId: string) => void
onCustomSubmit: (modelId: string) => void
onClose: () => void
}) {
const [search, setSearch] = useState('')
const inputRef = useRef<HTMLInputElement>(null)
const containerRef = useRef<HTMLDivElement>(null)
useEffect(() => {
inputRef.current?.focus()
}, [])
useEffect(() => {
const handleClickOutside = (e: MouseEvent) => {
if (
containerRef.current &&
!containerRef.current.contains(e.target as Node)
) {
onClose()
}
}
document.addEventListener('mousedown', handleClickOutside)
return () => document.removeEventListener('mousedown', handleClickOutside)
}, [onClose])
const query = search.toLowerCase()
const filtered = query
? models.filter((m) => m.modelId.toLowerCase().includes(query))
: models
const handleKeyDown = (e: React.KeyboardEvent) => {
if (e.key === 'Enter' && search) {
e.preventDefault()
onCustomSubmit(search)
}
if (e.key === 'Escape') {
onClose()
}
}
return (
<div ref={containerRef} className="rounded-md border">
<div className="flex items-center gap-2 border-b px-3">
<SearchIcon className="h-4 w-4 shrink-0 text-muted-foreground opacity-50" />
<input
ref={inputRef}
type="text"
value={search}
onChange={(e) => setSearch(e.target.value)}
onKeyDown={handleKeyDown}
placeholder="Search or type a custom model ID..."
className="flex h-9 w-full bg-transparent py-2 text-sm outline-none placeholder:text-muted-foreground"
/>
</div>
<div className="max-h-[200px] overflow-y-auto">
{filtered.length > 0 ? (
filtered.map((model) => {
const isSelected = selectedModelId === model.modelId
return (
<button
key={model.modelId}
type="button"
onClick={() => onSelect(model.modelId)}
className={cn(
'flex w-full items-center justify-between px-3 py-2 text-left text-sm transition-colors hover:bg-accent',
isSelected && 'bg-accent font-medium',
)}
>
<span className="truncate">{model.modelId}</span>
<span className="ml-2 shrink-0 rounded-md bg-muted px-1.5 py-0.5 font-mono text-[10px] text-muted-foreground">
{formatContextWindow(model.contextLength)}
</span>
</button>
)
})
) : (
<div className="px-3 py-6 text-center text-muted-foreground text-sm">
No models match. Press Enter to use &quot;{search}&quot;
</div>
)}
</div>
</div>
)
}
/**
* Props for NewProviderDialog
* @public
@@ -188,9 +301,9 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
initialValues,
onSave,
}) => {
const [isCustomModel, setIsCustomModel] = useState(false)
const [isTesting, setIsTesting] = useState(false)
const [testResult, setTestResult] = useState<TestResult | null>(null)
const [modelListOpen, setModelListOpen] = useState(false)
const { supports } = useCapabilities()
const { baseUrl: agentServerUrl } = useAgentServerUrl()
const kimiLaunch = useKimiLaunch()
@@ -261,8 +374,7 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
watchedSessionToken,
])
// Get model options for current provider type
const modelOptions = getModelOptions(watchedType as ProviderType)
const modelInfoList = getModelsForProvider(watchedType as ProviderType)
// Handle provider type change (user-initiated via Select)
const handleTypeChange = (newType: ProviderType) => {
@@ -272,14 +384,13 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
form.setValue('baseUrl', defaultUrl)
}
form.setValue('modelId', '')
setIsCustomModel(false)
}
// Auto-fill context window when model changes (only for new providers)
useEffect(() => {
if (initialValues?.id) return
if (watchedModelId && watchedModelId !== 'custom') {
if (watchedModelId) {
const contextLength = getModelContextLength(
watchedType as ProviderType,
watchedModelId,
@@ -290,17 +401,6 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
}
}, [watchedModelId, watchedType, form, initialValues?.id])
// Handle model selection (including custom option)
const handleModelChange = (value: string) => {
if (value === 'custom') {
setIsCustomModel(true)
form.setValue('modelId', '')
} else {
setIsCustomModel(false)
form.setValue('modelId', value)
}
}
// Reset form when initialValues change
useEffect(() => {
if (initialValues) {
@@ -325,7 +425,6 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
reasoningEffort: initialValues.reasoningEffort || 'high',
reasoningSummary: initialValues.reasoningSummary || 'auto',
})
setIsCustomModel(false)
}
}, [initialValues, form])
@@ -352,7 +451,6 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
reasoningEffort: 'high',
reasoningSummary: 'auto',
})
setIsCustomModel(false)
}
// Clear test result when dialog opens/closes
setTestResult(null)
@@ -811,52 +909,51 @@ export const NewProviderDialog: FC<NewProviderDialogProps> = ({
control={form.control}
name="modelId"
render={({ field }) => (
<FormItem>
<FormItem className="flex flex-col">
<FormLabel>Model *</FormLabel>
{isCustomModel || modelOptions.length === 1 ? (
<>
<FormControl>
<Input
placeholder={
watchedType === 'azure'
? 'Enter your deployment name'
: watchedType === 'bedrock'
? 'e.g., anthropic.claude-3-5-sonnet-20241022-v2:0'
: 'Enter custom model ID'
}
{...field}
/>
</FormControl>
{modelOptions.length > 1 && (
<Button
type="button"
variant="link"
size="sm"
className="h-auto p-0 text-xs"
onClick={() => setIsCustomModel(false)}
>
Back to model list
</Button>
)}
</>
{modelInfoList.length === 0 ? (
<FormControl>
<Input
placeholder={
watchedType === 'azure'
? 'Enter your deployment name'
: watchedType === 'bedrock'
? 'e.g., anthropic.claude-3-5-sonnet-20241022-v2:0'
: 'Enter model ID'
}
{...field}
/>
</FormControl>
) : modelListOpen ? (
<ModelPickerList
models={modelInfoList}
selectedModelId={field.value}
onSelect={(modelId) => {
form.setValue('modelId', modelId)
setModelListOpen(false)
}}
onCustomSubmit={(modelId) => {
form.setValue('modelId', modelId)
setModelListOpen(false)
}}
onClose={() => setModelListOpen(false)}
/>
) : (
<Select
onValueChange={handleModelChange}
value={field.value}
<button
type="button"
onClick={() => setModelListOpen(true)}
className={cn(
'flex h-9 w-full items-center justify-between rounded-md border border-input bg-transparent px-3 py-1 text-sm shadow-xs',
field.value
? 'text-foreground'
: 'text-muted-foreground',
)}
>
<FormControl>
<SelectTrigger className="w-full">
<SelectValue placeholder="Select a model" />
</SelectTrigger>
</FormControl>
<SelectContent>
{modelOptions.map((modelId) => (
<SelectItem key={modelId} value={modelId}>
{modelId === 'custom' ? '+ Custom model' : modelId}
</SelectItem>
))}
</SelectContent>
</Select>
<span className="truncate">
{field.value || 'Select a model...'}
</span>
<ChevronDown className="ml-2 h-4 w-4 shrink-0 opacity-50" />
</button>
)}
<FormMessage />
</FormItem>

View File

@@ -1,98 +1,21 @@
import {
getModelsDevModels,
type ModelsDevModel,
} from '@/lib/llm-providers/models-dev'
import type { ProviderType } from '@/lib/llm-providers/types'
/**
* Model information with context length
*/
export interface ModelInfo {
modelId: string
contextLength: number
supportsImages?: boolean
supportsReasoning?: boolean
supportsToolCall?: boolean
}
/**
* Models data organized by provider type (matches backend AIProvider enum)
*/
export interface ModelsData {
anthropic: ModelInfo[]
openai: ModelInfo[]
'openai-compatible': ModelInfo[]
google: ModelInfo[]
openrouter: ModelInfo[]
azure: ModelInfo[]
ollama: ModelInfo[]
lmstudio: ModelInfo[]
bedrock: ModelInfo[]
browseros: ModelInfo[]
moonshot: ModelInfo[]
'chatgpt-pro': ModelInfo[]
'github-copilot': ModelInfo[]
'qwen-code': ModelInfo[]
}
/**
* Available models per provider with context lengths
* Based on: https://github.com/browseros-ai/BrowserOS-agent/blob/main/src/options/data/models.ts
*/
export const MODELS_DATA: ModelsData = {
moonshot: [{ modelId: 'kimi-k2.5', contextLength: 200000 }],
anthropic: [
{ modelId: 'claude-opus-4-5-20251101', contextLength: 200000 },
{ modelId: 'claude-haiku-4-5-20251001', contextLength: 200000 },
{ modelId: 'claude-sonnet-4-5-20250929', contextLength: 200000 },
{ modelId: 'claude-sonnet-4-20250514', contextLength: 200000 },
{ modelId: 'claude-opus-4-20250514', contextLength: 200000 },
{ modelId: 'claude-3-7-sonnet-20250219', contextLength: 200000 },
{ modelId: 'claude-3-5-haiku-20241022', contextLength: 200000 },
],
openai: [
{ modelId: 'gpt-5.2', contextLength: 200000 },
{ modelId: 'gpt-5.2-pro', contextLength: 200000 },
{ modelId: 'gpt-5', contextLength: 200000 },
{ modelId: 'gpt-5-mini', contextLength: 200000 },
{ modelId: 'gpt-5-nano', contextLength: 200000 },
{ modelId: 'gpt-4.1', contextLength: 200000 },
{ modelId: 'gpt-4.1-mini', contextLength: 200000 },
{ modelId: 'o4-mini', contextLength: 200000 },
{ modelId: 'o3-mini', contextLength: 200000 },
{ modelId: 'gpt-4o', contextLength: 128000 },
{ modelId: 'gpt-4o-mini', contextLength: 128000 },
],
'openai-compatible': [],
google: [
{ modelId: 'gemini-3-pro-preview', contextLength: 1048576 },
{ modelId: 'gemini-3-flash-preview', contextLength: 1048576 },
{ modelId: 'gemini-2.5-flash', contextLength: 1048576 },
{ modelId: 'gemini-2.5-pro', contextLength: 1048576 },
],
openrouter: [
{ modelId: 'google/gemini-3-pro-preview', contextLength: 1048576 },
{ modelId: 'google/gemini-3-flash-preview', contextLength: 1048576 },
{ modelId: 'google/gemini-2.5-flash', contextLength: 1048576 },
{ modelId: 'anthropic/claude-opus-4.5', contextLength: 200000 },
{ modelId: 'anthropic/claude-haiku-4.5', contextLength: 200000 },
{ modelId: 'anthropic/claude-sonnet-4.5', contextLength: 200000 },
{ modelId: 'anthropic/claude-sonnet-4', contextLength: 200000 },
{ modelId: 'anthropic/claude-3.7-sonnet', contextLength: 200000 },
{ modelId: 'openai/gpt-4o', contextLength: 128000 },
{ modelId: 'openai/gpt-oss-120b', contextLength: 128000 },
{ modelId: 'openai/gpt-oss-20b', contextLength: 128000 },
{ modelId: 'qwen/qwen3-14b', contextLength: 131072 },
{ modelId: 'qwen/qwen3-8b', contextLength: 131072 },
],
azure: [],
ollama: [
{ modelId: 'qwen3:4b', contextLength: 262144 },
{ modelId: 'qwen3:8b', contextLength: 40960 },
{ modelId: 'qwen3:14b', contextLength: 40960 },
{ modelId: 'gpt-oss:20b', contextLength: 128000 },
{ modelId: 'gpt-oss:120b', contextLength: 128000 },
],
lmstudio: [
{ modelId: 'openai/gpt-oss-20b', contextLength: 128000 },
{ modelId: 'openai/gpt-oss-120b', contextLength: 128000 },
{ modelId: 'qwen/qwen3-vl-8b', contextLength: 131072 },
],
bedrock: [],
const CUSTOM_PROVIDER_MODELS: Partial<Record<ProviderType, ModelInfo[]>> = {
browseros: [{ modelId: 'browseros-auto', contextLength: 200000 }],
'openai-compatible': [],
ollama: [],
'chatgpt-pro': [
{ modelId: 'gpt-5.4', contextLength: 400000 },
{ modelId: 'gpt-5.3-codex', contextLength: 400000 },
@@ -103,32 +26,6 @@ export const MODELS_DATA: ModelsData = {
{ modelId: 'gpt-5.1-codex-mini', contextLength: 400000 },
{ modelId: 'gpt-5.1', contextLength: 200000 },
],
'github-copilot': [
// Free tier (unlimited with Pro)
{ modelId: 'gpt-5-mini', contextLength: 128000 },
{ modelId: 'claude-haiku-4.5', contextLength: 128000 },
{ modelId: 'gpt-4o', contextLength: 64000 },
{ modelId: 'gpt-4.1', contextLength: 64000 },
// Premium models (Pro: 300/mo, Pro+: 1500/mo)
{ modelId: 'claude-sonnet-4.6', contextLength: 128000 },
{ modelId: 'claude-sonnet-4.5', contextLength: 128000 },
{ modelId: 'claude-sonnet-4', contextLength: 128000 },
{ modelId: 'claude-opus-4.6', contextLength: 128000 },
{ modelId: 'claude-opus-4.5', contextLength: 128000 },
{ modelId: 'gemini-2.5-pro', contextLength: 128000 },
{ modelId: 'gemini-3-pro-preview', contextLength: 128000 },
{ modelId: 'gemini-3-flash-preview', contextLength: 128000 },
{ modelId: 'gemini-3.1-pro-preview', contextLength: 128000 },
{ modelId: 'gpt-5.4', contextLength: 272000 },
{ modelId: 'gpt-5.4-mini', contextLength: 128000 },
{ modelId: 'gpt-5.3-codex', contextLength: 272000 },
{ modelId: 'gpt-5.2-codex', contextLength: 272000 },
{ modelId: 'gpt-5.2', contextLength: 128000 },
{ modelId: 'gpt-5.1-codex', contextLength: 128000 },
{ modelId: 'gpt-5.1-codex-max', contextLength: 128000 },
{ modelId: 'gpt-5.1', contextLength: 128000 },
{ modelId: 'grok-code-fast-1', contextLength: 128000 },
],
'qwen-code': [
{ modelId: 'coder-model', contextLength: 1000000 },
{ modelId: 'qwen3-coder-plus', contextLength: 1000000 },
@@ -137,25 +34,23 @@ export const MODELS_DATA: ModelsData = {
],
}
/**
* Get models for a specific provider type
*/
function fromModelsDevModel(m: ModelsDevModel): ModelInfo {
return {
modelId: m.id,
contextLength: m.contextWindow,
supportsImages: m.supportsImages,
supportsReasoning: m.supportsReasoning,
supportsToolCall: m.supportsToolCall,
}
}
export function getModelsForProvider(providerType: ProviderType): ModelInfo[] {
return MODELS_DATA[providerType] || []
const custom = CUSTOM_PROVIDER_MODELS[providerType]
if (custom !== undefined) return custom
return getModelsDevModels(providerType).map(fromModelsDevModel)
}
/**
* Get model options for select dropdown (model IDs + custom option)
*/
export function getModelOptions(providerType: ProviderType): string[] {
const models = getModelsForProvider(providerType)
const modelIds = models.map((m) => m.modelId)
return modelIds.length > 0 ? [...modelIds, 'custom'] : ['custom']
}
/**
* Get context length for a specific model
*/
export function getModelContextLength(
providerType: ProviderType,
modelId: string,
@@ -164,14 +59,3 @@ export function getModelContextLength(
const model = models.find((m) => m.modelId === modelId)
return model?.contextLength
}
/**
* Check if model ID is a custom (user-entered) value
*/
export function isCustomModel(
providerType: ProviderType,
modelId: string,
): boolean {
const models = getModelsForProvider(providerType)
return !models.some((m) => m.modelId === modelId)
}

View File

@@ -169,8 +169,15 @@ export const NewTabChat: FC = () => {
onDismissJtbdPopup={() => {}}
/>
)}
{agentUrlError && <ChatError error={agentUrlError} />}
{chatError && <ChatError error={chatError} />}
{agentUrlError && (
<ChatError
error={agentUrlError}
providerType={selectedProvider?.type}
/>
)}
{chatError && (
<ChatError error={chatError} providerType={selectedProvider?.type} />
)}
</main>
<div className="mx-auto w-full max-w-3xl flex-shrink-0 px-4 pb-2">

View File

@@ -224,7 +224,12 @@ export const Chat = () => {
onDismissJtbdPopup={onDismissJtbdPopup}
/>
)}
{agentUrlError && <ChatError error={agentUrlError} />}
{agentUrlError && (
<ChatError
error={agentUrlError}
providerType={selectedProvider?.type}
/>
)}
{chatError && (
<ChatError error={chatError} providerType={selectedProvider?.type} />
)}

View File

@@ -34,11 +34,9 @@ function parseErrorMessage(
} {
const isBrowserosProvider = providerType === 'browseros'
// Detect MCP server connection failures (universal — affects all providers)
if (
(message.includes('Failed to fetch') || message.includes('fetch failed')) &&
message.includes('127.0.0.1')
) {
// All chat requests go through the local BrowserOS agent server, so any
// fetch failure is always a local connection issue.
if (message.includes('Failed to fetch') || message.includes('fetch failed')) {
return {
text: 'Unable to connect to BrowserOS agent. Follow below instructions.',
url: 'https://docs.browseros.com/troubleshooting/connection-issues',

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,35 @@
import data from './models-dev-data.json'
export interface ModelsDevModel {
id: string
name: string
contextWindow: number
maxOutput: number
supportsImages: boolean
supportsReasoning: boolean
supportsToolCall: boolean
inputCost?: number
outputCost?: number
}
export interface ModelsDevProvider {
name: string
api?: string
doc: string
models: ModelsDevModel[]
}
const modelsDevData: Record<string, ModelsDevProvider> = data as Record<
string,
ModelsDevProvider
>
export function getModelsDevProvider(
providerId: string,
): ModelsDevProvider | undefined {
return modelsDevData[providerId]
}
export function getModelsDevModels(providerId: string): ModelsDevModel[] {
return modelsDevData[providerId]?.models ?? []
}

View File

@@ -1,3 +1,4 @@
import { getModelsDevProvider } from './models-dev'
import type { ProviderType } from './types'
/**
@@ -15,6 +16,30 @@ export interface ProviderTemplate {
apiKeyUrl?: string
}
function enrichTemplate(
providerId: ProviderType,
overrides: {
defaultModelId: string
defaultBaseUrl?: string
apiKeyUrl?: string
setupGuideUrl?: string
},
): ProviderTemplate {
const provider = getModelsDevProvider(providerId)
const model = provider?.models.find((m) => m.id === overrides.defaultModelId)
return {
id: providerId,
name: provider?.name ?? providerId,
defaultBaseUrl: overrides.defaultBaseUrl ?? provider?.api ?? '',
defaultModelId: overrides.defaultModelId,
supportsImages: model?.supportsImages ?? true,
contextWindow: model?.contextWindow ?? 128000,
...(overrides.apiKeyUrl && { apiKeyUrl: overrides.apiKeyUrl }),
...(overrides.setupGuideUrl && { setupGuideUrl: overrides.setupGuideUrl }),
}
}
/**
* Available provider templates for quick setup
* @public
@@ -57,17 +82,12 @@ export const providerTemplates: ProviderTemplate[] = [
apiKeyUrl: 'https://platform.moonshot.ai/console/api-keys',
setupGuideUrl: 'https://platform.moonshot.ai/console/api-keys',
},
{
id: 'openai',
name: 'OpenAI',
defaultBaseUrl: 'https://api.openai.com/v1',
defaultModelId: 'gpt-4',
supportsImages: true,
contextWindow: 128000,
enrichTemplate('openai', {
defaultModelId: 'gpt-5',
apiKeyUrl: 'https://platform.openai.com/api-keys',
setupGuideUrl:
'https://docs.browseros.com/features/bring-your-own-llm#openai',
},
}),
{
id: 'openai-compatible',
name: 'OpenAI Compatible',
@@ -76,28 +96,18 @@ export const providerTemplates: ProviderTemplate[] = [
supportsImages: true,
contextWindow: 128000,
},
{
id: 'anthropic',
name: 'Anthropic',
defaultBaseUrl: 'https://api.anthropic.com/v1',
defaultModelId: 'claude-3-5-sonnet-20241022',
supportsImages: true,
contextWindow: 200000,
enrichTemplate('anthropic', {
defaultModelId: 'claude-sonnet-4-6',
apiKeyUrl: 'https://console.anthropic.com/settings/keys',
setupGuideUrl:
'https://docs.browseros.com/features/bring-your-own-llm#claude',
},
{
id: 'google',
name: 'Gemini',
defaultBaseUrl: 'https://generativelanguage.googleapis.com/v1beta',
defaultModelId: 'gemini-1.5-pro',
supportsImages: true,
contextWindow: 1000000,
}),
enrichTemplate('google', {
defaultModelId: 'gemini-2.5-flash',
apiKeyUrl: 'https://aistudio.google.com/app/apikey',
setupGuideUrl:
'https://docs.browseros.com/features/bring-your-own-llm#gemini',
},
}),
{
id: 'ollama',
name: 'Ollama',
@@ -108,47 +118,28 @@ export const providerTemplates: ProviderTemplate[] = [
setupGuideUrl:
'https://docs.browseros.com/features/bring-your-own-llm#ollama',
},
{
id: 'openrouter',
name: 'OpenRouter',
defaultBaseUrl: 'https://openrouter.ai/api/v1',
defaultModelId: 'openai/gpt-4-turbo',
supportsImages: true,
contextWindow: 128000,
enrichTemplate('openrouter', {
defaultModelId: 'anthropic/claude-sonnet-4.5',
apiKeyUrl: 'https://openrouter.ai/keys',
setupGuideUrl:
'https://docs.browseros.com/features/bring-your-own-llm#openrouter',
},
{
id: 'lmstudio',
name: 'LM Studio',
}),
enrichTemplate('lmstudio', {
defaultModelId: 'openai/gpt-oss-20b',
defaultBaseUrl: 'http://localhost:1234/v1',
defaultModelId: 'local-model',
supportsImages: false,
contextWindow: 32000,
setupGuideUrl:
'https://docs.browseros.com/features/bring-your-own-llm#lmstudio',
},
{
id: 'azure',
name: 'Azure',
defaultBaseUrl: '',
}),
enrichTemplate('azure', {
defaultModelId: '',
supportsImages: true,
contextWindow: 128000,
apiKeyUrl:
'https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/OpenAI',
},
{
id: 'bedrock',
name: 'AWS Bedrock',
defaultBaseUrl: '',
defaultModelId: '',
supportsImages: true,
contextWindow: 200000,
}),
enrichTemplate('bedrock', {
defaultModelId: 'anthropic.claude-sonnet-4-6',
setupGuideUrl:
'https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html',
},
}),
]
/**

View File

@@ -0,0 +1,7 @@
# Production upload env for CLI installer scripts
R2_ACCOUNT_ID=
R2_ACCESS_KEY_ID=
R2_SECRET_ACCESS_KEY=
R2_BUCKET=browseros
R2_UPLOAD_PREFIX=cli

View File

@@ -1 +1,2 @@
browseros-cli
dist

View File

@@ -0,0 +1,50 @@
version: 2
project_name: browseros-cli
monorepo:
tag_prefix: browseros-cli-
builds:
- main: .
binary: browseros-cli
env:
- CGO_ENABLED=0
flags:
- -trimpath
ldflags:
- -s -w -X main.version={{ .Version }}
targets:
- darwin_amd64
- darwin_arm64
- linux_amd64
- linux_arm64
- windows_amd64
- windows_arm64
archives:
- format: tar.gz
format_overrides:
- goos: windows
format: zip
name_template: "{{ .ProjectName }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
files:
- "none*"
checksum:
name_template: checksums.txt
changelog:
sort: asc
filters:
exclude:
- "^docs:"
- "^test:"
- "^ci:"
release:
github:
owner: browseros-ai
name: BrowserOS
prerelease: auto
name_template: "browseros-cli v{{ .Version }}"

View File

@@ -0,0 +1 @@
# BrowserOS CLI

View File

@@ -18,3 +18,9 @@ vet:
test:
go test -tags integration -v -timeout 120s ./...
release-dry:
goreleaser release --snapshot --clean
release:
goreleaser release --clean

View File

@@ -17,8 +17,10 @@ import (
)
func init() {
var autoDiscover bool
cmd := &cobra.Command{
Use: "init",
Use: "init [url]",
Short: "Configure the BrowserOS server connection",
Long: `Set up the CLI by providing the MCP server URL from BrowserOS.
@@ -26,33 +28,59 @@ Open BrowserOS → Settings → BrowserOS MCP to find your Server URL.
The URL looks like: http://127.0.0.1:9004/mcp
The port varies per installation, so this step is required on first use.
Run again if your port changes.`,
Run again if your port changes.
Three modes:
browseros-cli init <url> Non-interactive, use the provided URL
browseros-cli init --auto Auto-discover from ~/.browseros/server.json
browseros-cli init Interactive prompt`,
Annotations: map[string]string{"group": "Setup:"},
Args: cobra.NoArgs,
Args: cobra.MaximumNArgs(1),
Run: func(cmd *cobra.Command, args []string) {
bold := color.New(color.Bold)
green := color.New(color.FgGreen)
dim := color.New(color.Faint)
fmt.Println()
bold.Println("BrowserOS CLI Setup")
fmt.Println()
fmt.Println("Open BrowserOS → Settings → BrowserOS MCP")
fmt.Println("Copy the Server URL shown there.")
fmt.Println()
dim.Println("It looks like: http://127.0.0.1:9004/mcp")
fmt.Println()
var input string
reader := bufio.NewReader(os.Stdin)
fmt.Print("Server URL: ")
input, err := reader.ReadString('\n')
if err != nil {
output.Error("failed to read input", 1)
}
input = strings.TrimSpace(input)
switch {
case len(args) == 1:
// Non-interactive: URL provided as argument
input = args[0]
if input == "" {
output.Error("no URL provided", 1)
case autoDiscover:
// Auto-discover: server.json → config → probe common ports
discovered := probeRunningServer()
if discovered == "" {
output.Error("auto-discovery failed: no running BrowserOS found.\n\n"+
" If not running: browseros-cli launch\n"+
" If not installed: browseros-cli install", 1)
}
input = discovered
fmt.Printf("Auto-discovered server at %s\n", input)
default:
// Interactive prompt (original behavior)
fmt.Println()
bold.Println("BrowserOS CLI Setup")
fmt.Println()
fmt.Println("Open BrowserOS → Settings → BrowserOS MCP")
fmt.Println("Copy the Server URL shown there.")
fmt.Println()
dim.Println("It looks like: http://127.0.0.1:9004/mcp")
fmt.Println()
reader := bufio.NewReader(os.Stdin)
fmt.Print("Server URL: ")
line, err := reader.ReadString('\n')
if err != nil {
output.Error("failed to read input", 1)
}
input = strings.TrimSpace(line)
if input == "" {
output.Error("no URL provided", 1)
}
}
baseURL := normalizeServerURL(input)
@@ -88,5 +116,6 @@ Run again if your port changes.`,
},
}
cmd.Flags().BoolVar(&autoDiscover, "auto", false, "Auto-discover server URL from ~/.browseros/server.json")
rootCmd.AddCommand(cmd)
}

View File

@@ -0,0 +1,247 @@
package cmd
import (
"fmt"
"io"
"net/http"
"os"
"os/exec"
"path/filepath"
"runtime"
"time"
"browseros-cli/output"
"github.com/fatih/color"
"github.com/spf13/cobra"
)
func init() {
cmd := &cobra.Command{
Use: "install",
Short: "Download and install BrowserOS for the current platform",
Long: `Download BrowserOS for your platform and start the installation.
macOS: Downloads .dmg, mounts it, and copies BrowserOS to /Applications
Windows: Downloads installer .exe and launches it
Linux: Downloads AppImage (or .deb with --deb flag)
After installation:
browseros-cli launch # start BrowserOS
browseros-cli init --auto # configure the CLI`,
Annotations: map[string]string{"group": "Setup:"},
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, args []string) {
dir, _ := cmd.Flags().GetString("dir")
deb, _ := cmd.Flags().GetBool("deb")
if deb && runtime.GOOS != "linux" {
output.Error("--deb is only available on Linux", 1)
}
downloadURL, filename := resolveDownload(deb)
destPath := filepath.Join(dir, filename)
bold := color.New(color.Bold)
green := color.New(color.FgGreen)
dim := color.New(color.Faint)
bold.Printf("Downloading BrowserOS for %s...\n", platformDisplayName())
dim.Printf(" %s\n", downloadURL)
fmt.Println()
client := &http.Client{Timeout: 10 * time.Minute}
resp, err := client.Get(downloadURL)
if err != nil {
output.Errorf(1, "download failed: %v", err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
output.Errorf(1, "download failed: HTTP %d", resp.StatusCode)
}
file, err := os.Create(destPath)
if err != nil {
output.Errorf(1, "create file: %v", err)
}
written, err := io.Copy(file, resp.Body)
file.Close()
if err != nil {
os.Remove(destPath)
output.Errorf(1, "download interrupted: %v", err)
}
green.Printf("Downloaded %s (%.1f MB)\n", filename, float64(written)/(1024*1024))
fmt.Println()
runPostInstall(destPath, deb, dim)
fmt.Println()
bold.Println("Next steps:")
dim.Println(" browseros-cli launch # start BrowserOS")
dim.Println(" browseros-cli init --auto # configure the CLI")
},
}
cmd.Flags().String("dir", ".", "Directory to download the installer to")
cmd.Flags().Bool("deb", false, "Download .deb package instead of AppImage (Linux only)")
rootCmd.AddCommand(cmd)
}
func resolveDownload(deb bool) (url, filename string) {
switch runtime.GOOS {
case "darwin":
return "https://files.browseros.com/download/BrowserOS.dmg", "BrowserOS.dmg"
case "windows":
return "https://files.browseros.com/download/BrowserOS_installer.exe", "BrowserOS_installer.exe"
case "linux":
if deb {
return "https://cdn.browseros.com/download/BrowserOS.deb", "BrowserOS.deb"
}
return "https://files.browseros.com/download/BrowserOS.AppImage", "BrowserOS.AppImage"
default:
output.Errorf(1, "unsupported platform: %s/%s\n Download manually from https://browseros.com", runtime.GOOS, runtime.GOARCH)
return "", ""
}
}
func platformDisplayName() string {
switch runtime.GOOS {
case "darwin":
return "macOS"
case "windows":
return "Windows"
case "linux":
return "Linux"
default:
return runtime.GOOS
}
}
func runPostInstall(path string, deb bool, dim *color.Color) {
switch runtime.GOOS {
case "darwin":
installMacOS(path, dim)
case "linux":
if deb {
dim.Println("Install the .deb package:")
fmt.Printf(" sudo dpkg -i %s\n", path)
} else {
os.Chmod(path, 0755)
dim.Printf("AppImage is ready to run: ./%s\n", filepath.Base(path))
}
case "windows":
fmt.Println("Launching installer...")
if err := exec.Command("cmd", "/c", "start", "", path).Run(); err != nil {
dim.Printf("Could not launch installer automatically. Run: %s\n", path)
} else {
dim.Println("Follow the installer prompts to complete setup.")
}
}
}
// installMacOS mounts the DMG and copies BrowserOS.app to /Applications.
func installMacOS(dmgPath string, dim *color.Color) {
fmt.Println("Mounting disk image...")
mountOut, err := exec.Command("hdiutil", "attach", dmgPath, "-nobrowse", "-quiet").Output()
if err != nil {
dim.Println("Could not mount DMG automatically.")
dim.Printf(" Open it manually: open %s\n", dmgPath)
return
}
// Find the mount point (last field of last line of hdiutil output)
mountPoint := ""
for _, line := range splitLines(string(mountOut)) {
fields := splitTabs(line)
if len(fields) > 0 {
mountPoint = fields[len(fields)-1]
}
}
if mountPoint == "" {
dim.Println("DMG mounted but could not determine mount point.")
dim.Printf(" Open it manually: open %s\n", dmgPath)
return
}
// Look for BrowserOS.app in the mounted volume
appSrc := filepath.Join(mountPoint, "BrowserOS.app")
if _, err := os.Stat(appSrc); err != nil {
dim.Printf("DMG mounted at %s but BrowserOS.app not found inside.\n", mountPoint)
dim.Printf(" Check the volume manually: open %s\n", mountPoint)
exec.Command("hdiutil", "detach", mountPoint, "-quiet").Run()
return
}
appDest := "/Applications/BrowserOS.app"
fmt.Printf("Installing to %s...\n", appDest)
// Remove existing installation if present
os.RemoveAll(appDest)
// Copy using cp -R (preserves code signatures, symlinks, etc.)
if err := exec.Command("cp", "-R", appSrc, appDest).Run(); err != nil {
dim.Printf("Could not copy to /Applications (may need sudo).\n")
dim.Printf(" Try: sudo cp -R \"%s\" /Applications/\n", appSrc)
exec.Command("hdiutil", "detach", mountPoint, "-quiet").Run()
return
}
// Unmount
exec.Command("hdiutil", "detach", mountPoint, "-quiet").Run()
// Clean up DMG
os.Remove(dmgPath)
fmt.Println("BrowserOS installed to /Applications/BrowserOS.app")
}
func splitLines(s string) []string {
var lines []string
for _, line := range filepath.SplitList(s) {
lines = append(lines, line)
}
// filepath.SplitList uses : on unix, not newlines — use manual split
result := []string{}
start := 0
for i := 0; i < len(s); i++ {
if s[i] == '\n' {
line := s[start:i]
if len(line) > 0 {
result = append(result, line)
}
start = i + 1
}
}
if start < len(s) {
result = append(result, s[start:])
}
return result
}
func splitTabs(s string) []string {
result := []string{}
start := 0
for i := 0; i < len(s); i++ {
if s[i] == '\t' {
field := s[start:i]
if len(field) > 0 {
result = append(result, field)
}
start = i + 1
}
}
if start < len(s) {
field := s[start:]
if len(field) > 0 {
result = append(result, field)
}
}
return result
}

View File

@@ -0,0 +1,287 @@
package cmd
import (
"fmt"
"net/http"
"os"
"os/exec"
"path/filepath"
"runtime"
"strings"
"time"
"browseros-cli/output"
"github.com/fatih/color"
"github.com/spf13/cobra"
)
// macOS bundle identifier — verified from BrowserOS.app/Contents/Info.plist
const browserOSBundleID = "com.browseros.BrowserOS"
func init() {
cmd := &cobra.Command{
Use: "launch",
Short: "Launch the BrowserOS application",
Long: `Find and launch the BrowserOS application.
Uses platform-native detection to find BrowserOS, launches it,
and waits for the server to become ready.
If BrowserOS is already running, reports the server URL.`,
Annotations: map[string]string{"group": "Setup:"},
Args: cobra.NoArgs,
Run: func(cmd *cobra.Command, args []string) {
green := color.New(color.FgGreen)
dim := color.New(color.Faint)
waitSecs, _ := cmd.Flags().GetInt("wait")
if url := probeRunningServer(); url != "" {
green.Printf("BrowserOS is already running at %s\n", url)
return
}
if !isBrowserOSInstalled() {
output.Error("BrowserOS is not installed.\n\n"+
" To install: browseros-cli install", 1)
}
fmt.Println("Launching BrowserOS...")
if err := startBrowserOS(); err != nil {
output.Errorf(1, "failed to launch: %v", err)
}
fmt.Print("Waiting for server")
url, ok := waitForServer(time.Duration(waitSecs) * time.Second)
fmt.Println()
if !ok {
output.Error("BrowserOS launched but server didn't respond within "+
fmt.Sprintf("%d seconds.\n", waitSecs)+
" Check if BrowserOS is fully loaded, then retry.", 1)
}
green.Printf("BrowserOS is ready at %s\n", url)
fmt.Println()
dim.Println("Next: browseros-cli init --auto")
},
}
cmd.Flags().Int("wait", 30, "Seconds to wait for server to start")
rootCmd.AddCommand(cmd)
}
// ---------------------------------------------------------------------------
// Server probing
// ---------------------------------------------------------------------------
// probeRunningServer checks server.json, config, and common ports for a running server.
func probeRunningServer() string {
check := func(baseURL string) bool {
client := &http.Client{Timeout: 2 * time.Second}
resp, err := client.Get(baseURL + "/health")
if err != nil {
return false
}
resp.Body.Close()
return resp.StatusCode == 200
}
// 1. server.json — written by BrowserOS on startup with the actual port
if url := loadBrowserosServerURL(); url != "" && check(url) {
return url
}
// 2. Saved config / env var
if url := defaultServerURL(); url != "" && check(url) {
return url
}
// 3. Probe common BrowserOS ports as last resort
for _, port := range []int{9100, 9200, 9300} {
url := fmt.Sprintf("http://127.0.0.1:%d", port)
if check(url) {
return url
}
}
return ""
}
// ---------------------------------------------------------------------------
// Platform-native installation detection
// ---------------------------------------------------------------------------
// isBrowserOSInstalled checks if BrowserOS is installed using platform-native methods.
//
// macOS: `open -Ra "BrowserOS"` — queries Launch Services (finds apps anywhere)
// Linux: checks /usr/bin/browseros (.deb), browseros.desktop, or AppImage files
// Windows: checks executable at %LOCALAPPDATA%\BrowserOS\Application\BrowserOS.exe
// and registry uninstall key (per-user Chromium install pattern)
func isBrowserOSInstalled() bool {
switch runtime.GOOS {
case "darwin":
// open -Ra checks if Launch Services knows about the app without launching it.
// Works regardless of where the app is installed.
return exec.Command("open", "-Ra", "BrowserOS").Run() == nil
case "linux":
// .deb install puts `browseros` in /usr/bin/
if _, err := exec.LookPath("browseros"); err == nil {
return true
}
// .deb also creates browseros.desktop
for _, dir := range []string{
"/usr/share/applications",
filepath.Join(userHomeDir(), ".local/share/applications"),
} {
if _, err := os.Stat(filepath.Join(dir, "browseros.desktop")); err == nil {
return true
}
}
// AppImage — user may have it in ~/Downloads, ~/Applications, etc.
return findLinuxAppImage() != ""
case "windows":
// Chromium per-user install: %LOCALAPPDATA%\BrowserOS\Application\BrowserOS.exe
if exePath := windowsBrowserOSExe(); exePath != "" {
if _, err := os.Stat(exePath); err == nil {
return true
}
}
// Fallback: check uninstall registry (per-user install uses HKCU)
for _, root := range []string{"HKCU", "HKLM"} {
key := root + `\Software\Microsoft\Windows\CurrentVersion\Uninstall\BrowserOS`
if exec.Command("reg", "query", key, "/v", "DisplayName").Run() == nil {
return true
}
}
return false
}
return false
}
// ---------------------------------------------------------------------------
// Platform-native launch
// ---------------------------------------------------------------------------
// startBrowserOS launches BrowserOS using platform-native methods.
//
// macOS: `open -b com.browseros.BrowserOS` — launches by bundle ID
// Linux: runs `browseros` binary or AppImage directly
// Windows: runs BrowserOS.exe from the known install path
func startBrowserOS() error {
switch runtime.GOOS {
case "darwin":
// Launch by bundle ID via Launch Services — no hardcoded paths needed.
return exec.Command("open", "-b", browserOSBundleID).Run()
case "linux":
// .deb install: browseros is in PATH
if p, err := exec.LookPath("browseros"); err == nil {
return startDetached(p)
}
// AppImage: run it directly
if appImage := findLinuxAppImage(); appImage != "" {
return startDetached(appImage)
}
// .desktop file: use gtk-launch (not xdg-open, which opens by MIME type)
if _, err := exec.LookPath("gtk-launch"); err == nil {
return exec.Command("gtk-launch", "browseros").Run()
}
return fmt.Errorf("BrowserOS found but could not determine how to launch it")
case "windows":
if exePath := windowsBrowserOSExe(); exePath != "" {
if _, err := os.Stat(exePath); err == nil {
return startDetached(exePath)
}
}
return fmt.Errorf("BrowserOS.exe not found at expected location")
default:
return fmt.Errorf("unsupported platform: %s", runtime.GOOS)
}
}
// ---------------------------------------------------------------------------
// Helpers
// ---------------------------------------------------------------------------
// startDetached starts a process in the background without inheriting stdio.
func startDetached(path string, args ...string) error {
cmd := exec.Command(path, args...)
cmd.Stdout = nil
cmd.Stderr = nil
cmd.Stdin = nil
return cmd.Start()
}
// windowsBrowserOSExe returns the expected BrowserOS.exe path on Windows.
// Chromium per-user installs go to %LOCALAPPDATA%\<base_app_name>\Application\<binary>.
// base_app_name = "BrowserOS" (from chromium_install_modes.h)
func windowsBrowserOSExe() string {
localAppData := os.Getenv("LOCALAPPDATA")
if localAppData == "" {
return ""
}
return filepath.Join(localAppData, "BrowserOS", "Application", "BrowserOS.exe")
}
// findLinuxAppImage searches common locations for a BrowserOS AppImage.
func findLinuxAppImage() string {
home := userHomeDir()
if home == "" {
return ""
}
for _, dir := range []string{
home,
filepath.Join(home, "Applications"),
filepath.Join(home, "Downloads"),
"/opt",
} {
entries, err := os.ReadDir(dir)
if err != nil {
continue
}
for _, e := range entries {
name := e.Name()
if strings.HasPrefix(name, "BrowserOS") && strings.HasSuffix(name, ".AppImage") {
return filepath.Join(dir, name)
}
}
}
return ""
}
// userHomeDir returns the home directory or empty string.
func userHomeDir() string {
home, err := os.UserHomeDir()
if err != nil {
return ""
}
return home
}
// waitForServer polls until a BrowserOS server responds or timeout.
func waitForServer(maxWait time.Duration) (string, bool) {
client := &http.Client{Timeout: 2 * time.Second}
deadline := time.Now().Add(maxWait)
for time.Now().Before(deadline) {
// server.json is written by BrowserOS on startup with the actual port
if url := loadBrowserosServerURL(); url != "" {
resp, err := client.Get(url + "/health")
if err == nil {
resp.Body.Close()
if resp.StatusCode == 200 {
return url, true
}
}
}
fmt.Print(".")
time.Sleep(1 * time.Second)
}
return "", false
}

View File

@@ -167,10 +167,17 @@ func envBool(key string) bool {
}
func defaultServerURL() string {
// 1. Explicit env var always wins
if env := normalizeServerURL(os.Getenv("BROWSEROS_URL")); env != "" {
return env
}
// 2. Live discovery file from running BrowserOS (most current)
if url := loadBrowserosServerURL(); url != "" {
return url
}
// 3. Saved config (may be stale if port changed)
cfg, err := config.Load()
if err == nil {
if url := normalizeServerURL(cfg.ServerURL); url != "" {
@@ -178,10 +185,6 @@ func defaultServerURL() string {
}
}
if url := loadBrowserosServerURL(); url != "" {
return url
}
return ""
}
@@ -225,6 +228,9 @@ func validateServerURL(raw string) (string, error) {
}
return "", fmt.Errorf(
"BrowserOS server URL is not configured.\n Open BrowserOS -> Settings -> BrowserOS MCP and copy the Server URL.\n Then run: browseros-cli init",
"BrowserOS server URL is not configured.\n\n" +
" If BrowserOS is running: browseros-cli init --auto\n" +
" If BrowserOS is closed: browseros-cli launch\n" +
" If not installed: browseros-cli install",
)
}

View File

@@ -44,7 +44,10 @@ func (c *Client) connect(ctx context.Context) (*sdkmcp.ClientSession, error) {
session, err := sdkClient.Connect(ctx, transport, nil)
if err != nil {
return nil, fmt.Errorf("cannot connect to BrowserOS at %s: %w\n Is the server running? Try: browseros-cli init", c.BaseURL, err)
return nil, fmt.Errorf("cannot connect to BrowserOS at %s: %w\n\n"+
" If BrowserOS is running on a different port: browseros-cli init --auto\n"+
" If BrowserOS is not running: browseros-cli launch\n"+
" If not installed: browseros-cli install", c.BaseURL, err)
}
return session, nil
}
@@ -184,7 +187,10 @@ func (c *Client) Status() (map[string]any, error) {
func (c *Client) restGET(path string) (map[string]any, error) {
resp, err := c.HTTPClient.Get(c.BaseURL + path)
if err != nil {
return nil, fmt.Errorf("cannot connect to BrowserOS at %s: %w\n Try: browseros-cli init", c.BaseURL, err)
return nil, fmt.Errorf("cannot connect to BrowserOS at %s: %w\n\n"+
" If BrowserOS is running on a different port: browseros-cli init --auto\n"+
" If BrowserOS is not running: browseros-cli launch\n"+
" If not installed: browseros-cli install", c.BaseURL, err)
}
defer resp.Body.Close()

View File

@@ -0,0 +1,147 @@
#
# Install browseros-cli for Windows — downloads the latest release binary.
#
# Usage (PowerShell — save and run):
# Invoke-WebRequest -Uri "https://cdn.browseros.com/cli/install.ps1" -OutFile install.ps1
# .\install.ps1
# .\install.ps1 -Version "0.1.0" -Dir "C:\tools\browseros"
#
# Usage (one-liner, uses env vars for options):
# & { $env:BROWSEROS_VERSION="0.1.0"; irm https://cdn.browseros.com/cli/install.ps1 | iex }
#
param(
[string]$Version = "",
[string]$Dir = ""
)
$ErrorActionPreference = "Stop"
# TLS 1.2 — required for GitHub, older PS 5.1 defaults to TLS 1.0
[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12
$Repo = "browseros-ai/BrowserOS"
$Binary = "browseros-cli"
# When piped via irm | iex, param() is ignored — fall back to env vars
if (-not $Version) { $Version = $env:BROWSEROS_VERSION }
if (-not $Dir) { $Dir = if ($env:BROWSEROS_DIR) { $env:BROWSEROS_DIR } else { "$env:LOCALAPPDATA\browseros-cli\bin" } }
# ── Resolve latest version ───────────────────────────────────────────────────
if (-not $Version) {
Write-Host "Fetching latest version..."
$releases = Invoke-RestMethod "https://api.github.com/repos/$Repo/releases?per_page=100"
$tag = ($releases `
| Where-Object { $_.tag_name -match "^browseros-cli-v" -and $_.tag_name -notmatch "-rc" } `
| Select-Object -First 1).tag_name
if (-not $tag) {
Write-Error "Could not determine latest version. Try: -Version 0.1.0"
exit 1
}
$Version = $tag -replace "^browseros-cli-v", ""
}
Write-Host "Installing browseros-cli v$Version..."
# ── Detect architecture ──────────────────────────────────────────────────────
# $env:PROCESSOR_ARCHITECTURE lies under x64 emulation on ARM64 Windows.
# Use .NET RuntimeInformation when available, fall back to PROCESSOR_ARCHITEW6432.
$Arch = "amd64"
try {
$osArch = [System.Runtime.InteropServices.RuntimeInformation]::OSArchitecture
if ($osArch -eq [System.Runtime.InteropServices.Architecture]::Arm64) { $Arch = "arm64" }
} catch {
if ($env:PROCESSOR_ARCHITEW6432 -eq "ARM64" -or $env:PROCESSOR_ARCHITECTURE -eq "ARM64") {
$Arch = "arm64"
}
}
if (-not [Environment]::Is64BitOperatingSystem) {
Write-Error "32-bit Windows is not supported."
exit 1
}
# ── Download and extract ─────────────────────────────────────────────────────
$Tag = "browseros-cli-v$Version"
$Filename = "${Binary}_${Version}_windows_${Arch}.zip"
$Url = "https://github.com/$Repo/releases/download/$Tag/$Filename"
$ChecksumUrl = "https://github.com/$Repo/releases/download/$Tag/checksums.txt"
$TmpDir = Join-Path ([System.IO.Path]::GetTempPath()) ("browseros-cli-install-" + [System.IO.Path]::GetRandomFileName())
try {
New-Item -ItemType Directory -Path $TmpDir | Out-Null
$ZipPath = Join-Path $TmpDir $Filename
Write-Host "Downloading $Url..."
Invoke-WebRequest -Uri $Url -OutFile $ZipPath -UseBasicParsing
$ChecksumPath = Join-Path $TmpDir "checksums.txt"
$ChecksumAvailable = $true
try {
Invoke-WebRequest -Uri $ChecksumUrl -OutFile $ChecksumPath -UseBasicParsing
} catch {
$ChecksumAvailable = $false
Write-Warning "Could not fetch checksums.txt; skipping checksum verification. $($_.Exception.Message)"
}
if ($ChecksumAvailable) {
$ExpectedChecksum = $null
foreach ($line in Get-Content $ChecksumPath) {
$parts = $line -split '\s+', 2
if ($parts.Length -eq 2 -and $parts[1] -eq $Filename) {
$ExpectedChecksum = $parts[0].ToLowerInvariant()
break
}
}
if ($ExpectedChecksum) {
$ActualChecksum = (Get-FileHash -Path $ZipPath -Algorithm SHA256).Hash.ToLowerInvariant()
if ($ActualChecksum -ne $ExpectedChecksum) {
Write-Error "Checksum mismatch (expected $ExpectedChecksum, got $ActualChecksum)"
exit 1
}
Write-Host "Checksum verified."
} else {
Write-Warning "Checksum not found in checksums.txt; skipping checksum verification."
}
}
Expand-Archive -Path $ZipPath -DestinationPath $TmpDir -Force
$Exe = Get-ChildItem -Path $TmpDir -Filter "$Binary.exe" -File -Recurse | Select-Object -First 1
if (-not $Exe) {
Write-Error "Binary not found in archive."
exit 1
}
# ── Install ──────────────────────────────────────────────────────────────
if (-not (Test-Path $Dir)) {
New-Item -ItemType Directory -Path $Dir -Force | Out-Null
}
Move-Item -Force $Exe.FullName (Join-Path $Dir "$Binary.exe")
Write-Host "Installed $Binary.exe to $Dir"
} finally {
if (Test-Path $TmpDir) { Remove-Item -Recurse -Force $TmpDir -ErrorAction SilentlyContinue }
}
# ── PATH ─────────────────────────────────────────────────────────────────────
$UserPath = [Environment]::GetEnvironmentVariable("Path", "User")
$PathEntries = $UserPath -split ";" | Where-Object { $_ -ne "" }
if ($Dir -notin $PathEntries) {
Write-Host ""
Write-Host "Adding $Dir to your user PATH..."
[Environment]::SetEnvironmentVariable("Path", "$Dir;$UserPath", "User")
$env:Path = "$Dir;$env:Path"
Write-Host "Done. Restart your terminal for PATH changes to take effect."
}
Write-Host ""
Write-Host "Run 'browseros-cli --help' to get started."

View File

@@ -0,0 +1,153 @@
#!/usr/bin/env bash
#
# Install browseros-cli — downloads the latest release binary for your platform.
#
# Usage:
# curl -fsSL https://cdn.browseros.com/cli/install.sh | bash
#
# # Or with options:
# curl -fsSL https://cdn.browseros.com/cli/install.sh | bash -s -- --version 0.1.0 --dir /usr/local/bin
set -euo pipefail
REPO="browseros-ai/BrowserOS"
BINARY="browseros-cli"
INSTALL_DIR="${HOME}/.browseros/bin"
# ── Parse arguments ──────────────────────────────────────────────────────────
VERSION=""
CUSTOM_DIR=""
while [[ $# -gt 0 ]]; do
case "$1" in
--version)
[[ $# -lt 2 ]] && { echo "Error: --version requires a value" >&2; exit 1; }
VERSION="$2"; shift 2 ;;
--dir)
[[ $# -lt 2 ]] && { echo "Error: --dir requires a value" >&2; exit 1; }
CUSTOM_DIR="$2"; shift 2 ;;
--help)
echo "Usage: install.sh [--version VERSION] [--dir INSTALL_DIR]"
echo ""
echo " --version Install a specific version (default: latest)"
echo " --dir Install directory (default: ~/.browseros/bin)"
exit 0
;;
*) echo "Unknown option: $1" >&2; exit 1 ;;
esac
done
[[ -n "$CUSTOM_DIR" ]] && INSTALL_DIR="$CUSTOM_DIR"
# ── Resolve latest version ───────────────────────────────────────────────────
if [[ -z "$VERSION" ]]; then
# Use per_page=1 with a tag name filter via the releases endpoint.
# The tags all start with "browseros-cli-v" so we grab page 1 of those.
VERSION=$(curl -fsSL "https://api.github.com/repos/${REPO}/releases?per_page=100" \
| grep -o '"tag_name": *"browseros-cli-v[^"]*"' \
| grep -v -- "-rc" \
| head -1 \
| sed 's/.*browseros-cli-v//; s/"//')
if [[ -z "$VERSION" ]]; then
echo "Error: could not determine latest version." >&2
echo " Try: install.sh --version 0.1.0" >&2
exit 1
fi
fi
echo "Installing browseros-cli v${VERSION}..."
# ── Detect platform ──────────────────────────────────────────────────────────
OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m)
case "$OS" in
darwin) OS="darwin" ;;
linux) OS="linux" ;;
*) echo "Error: unsupported OS: $OS" >&2; exit 1 ;;
esac
case "$ARCH" in
x86_64|amd64) ARCH="amd64" ;;
arm64|aarch64) ARCH="arm64" ;;
*) echo "Error: unsupported architecture: $ARCH" >&2; exit 1 ;;
esac
# ── Download and extract ─────────────────────────────────────────────────────
FILENAME="${BINARY}_${VERSION}_${OS}_${ARCH}.tar.gz"
TAG="browseros-cli-v${VERSION}"
URL="https://github.com/${REPO}/releases/download/${TAG}/${FILENAME}"
CHECKSUM_URL="https://github.com/${REPO}/releases/download/${TAG}/checksums.txt"
TMPDIR_DL=$(mktemp -d)
trap 'rm -rf "$TMPDIR_DL"' EXIT
echo "Downloading ${URL}..."
curl -fSL --progress-bar -o "${TMPDIR_DL}/${FILENAME}" "$URL"
# Verify checksum if sha256sum/shasum is available
if curl -fsSL -o "${TMPDIR_DL}/checksums.txt" "$CHECKSUM_URL" 2>/dev/null; then
expected=$(awk -v filename="$FILENAME" '$2 == filename { print $1; exit }' "${TMPDIR_DL}/checksums.txt")
if [[ -n "$expected" ]]; then
if command -v sha256sum >/dev/null 2>&1; then
actual=$(sha256sum "${TMPDIR_DL}/${FILENAME}" | awk '{print $1}')
elif command -v shasum >/dev/null 2>&1; then
actual=$(shasum -a 256 "${TMPDIR_DL}/${FILENAME}" | awk '{print $1}')
else
actual=""
echo "Warning: no sha256sum/shasum found; skipping checksum verification." >&2
fi
if [[ -n "$actual" && "$actual" != "$expected" ]]; then
echo "Error: checksum mismatch (expected ${expected}, got ${actual})" >&2
exit 1
fi
[[ -n "$actual" ]] && echo "Checksum verified."
else
echo "Warning: checksum not found in checksums.txt; skipping verification." >&2
fi
else
echo "Warning: could not fetch checksums.txt; skipping checksum verification." >&2
fi
tar -xzf "${TMPDIR_DL}/${FILENAME}" -C "$TMPDIR_DL"
BINARY_PATH="${TMPDIR_DL}/${BINARY}"
if [[ ! -f "$BINARY_PATH" ]]; then
BINARY_PATH=$(find "$TMPDIR_DL" -type f -name "$BINARY" -print -quit)
fi
if [[ -z "$BINARY_PATH" || ! -f "$BINARY_PATH" ]]; then
echo "Error: binary not found in archive." >&2
exit 1
fi
# ── Install ──────────────────────────────────────────────────────────────────
mkdir -p "$INSTALL_DIR"
mv "$BINARY_PATH" "${INSTALL_DIR}/${BINARY}"
chmod +x "${INSTALL_DIR}/${BINARY}"
echo "Installed ${BINARY} to ${INSTALL_DIR}/${BINARY}"
# ── PATH hint ────────────────────────────────────────────────────────────────
if ! echo "$PATH" | tr ':' '\n' | grep -qx "$INSTALL_DIR"; then
echo ""
echo "Add browseros-cli to your PATH:"
echo ""
SHELL_NAME=$(basename "${SHELL:-/bin/bash}")
case "$SHELL_NAME" in
zsh) echo " echo 'export PATH=\"${INSTALL_DIR}:\$PATH\"' >> ~/.zshrc && source ~/.zshrc" ;;
fish) echo " fish_add_path ${INSTALL_DIR}" ;;
*) echo " echo 'export PATH=\"${INSTALL_DIR}:\$PATH\"' >> ~/.bashrc && source ~/.bashrc" ;;
esac
fi
echo ""
echo "Run 'browseros-cli --help' to get started."

View File

@@ -1225,7 +1225,7 @@
const score = graders[firstKey].score;
if (typeof score === 'number') {
const pct = Math.round(score * 100);
return { label: pct + '%', cls: pct >= 75 ? 'pass' : 'fail' };
return { label: `${pct}%`, cls: pct >= 75 ? 'pass' : 'fail' };
}
const anyPass = keys.some((k) => graders[k].pass);
return { label: anyPass ? 'PASS' : 'FAIL', cls: anyPass ? 'pass' : 'fail' };

View File

@@ -20,6 +20,7 @@ import './lib/polyfill'
import { EXIT_CODES } from '@browseros/shared/constants/exit-codes'
import { CommanderError } from 'commander'
import { loadServerConfig } from './config'
import { isPortInUseError } from './lib/port-binding'
import { Sentry } from './lib/sentry'
import { Application } from './main'
@@ -39,6 +40,9 @@ try {
if (error instanceof CommanderError) {
process.exit(error.exitCode)
}
if (isPortInUseError(error)) {
process.exit(EXIT_CODES.PORT_CONFLICT)
}
Sentry.captureException(error)
console.error('Failed to start server:', error)
process.exit(EXIT_CODES.GENERAL_ERROR)

View File

@@ -231,7 +231,6 @@ export class Application {
console.error(
`[FATAL] Failed to start ${serverName} on port ${port}: ${errorMsg}`,
)
Sentry.captureException(error)
if (isPortInUseError(error)) {
console.error(
@@ -240,6 +239,7 @@ export class Application {
process.exit(EXIT_CODES.PORT_CONFLICT)
}
Sentry.captureException(error)
process.exit(EXIT_CODES.GENERAL_ERROR)
}
@@ -255,7 +255,9 @@ export class Application {
{ port },
)
}
Sentry.captureException(error)
if (!isPortInUseError(error)) {
Sentry.captureException(error)
}
}
private logStartupSummary(controllerServerStarted: boolean): void {

View File

@@ -231,7 +231,7 @@
},
"packages/agent-sdk": {
"name": "@browseros-ai/agent-sdk",
"version": "0.0.5",
"version": "0.0.7",
"dependencies": {
"eventsource-parser": "^3.0.6",
"zod-to-json-schema": "^3.24.1",

View File

@@ -19,7 +19,9 @@
"start:agent": "bun ./scripts/build/controller-ext.ts && bun run --filter @browseros/agent dev",
"build": "bun run build:server && bun run build:agent && bun run build:ext",
"build:server": "FORCE_COLOR=1 bun scripts/build/server.ts --target=all",
"build:server:ci": "FORCE_COLOR=1 bun scripts/build/server.ts --target=all --compile-only",
"build:server:test": "FORCE_COLOR=1 bun scripts/build/server.ts --target=darwin-arm64 --no-upload",
"upload:cli-installers": "bun scripts/build/cli.ts",
"start:server:test": "bun run build:server:test && set -a && . apps/server/.env.development && set +a && dist/prod/server/.tmp/binaries/browseros-server-darwin-arm64",
"build:agent:dev": "FORCE_COLOR=1 bun run --filter @browseros/agent --elide-lines=0 build:dev",
"build:agent": "bun run codegen:agent && bun run --filter @browseros/agent build",
@@ -34,6 +36,7 @@
"lint": "bunx biome check",
"lint:fix": "bunx biome check --write --unsafe",
"gen:cdp": "bun scripts/codegen/cdp-protocol.ts",
"generate:models": "bun scripts/generate-models.ts",
"clean": "rimraf dist"
},
"repository": "browseros-ai/BrowserOS-server",

View File

@@ -0,0 +1,12 @@
# @browseros-ai/agent-sdk
## v0.0.7 (2026-03-26)
## What's Changed
- chore: bump @browseros-ai/agent-sdk to 0.0.7 (#569) (#569) @DaniAkash
## Contributors
- @DaniAkash

View File

@@ -1,6 +1,6 @@
{
"name": "@browseros-ai/agent-sdk",
"version": "0.0.5",
"version": "0.0.7",
"description": "Browser automation SDK for BrowserOS - navigate, interact, extract data with natural language",
"type": "module",
"license": "AGPL-3.0-or-later",

View File

@@ -0,0 +1,9 @@
#!/usr/bin/env bun
import { runCliInstallerUpload } from './cli/upload'
runCliInstallerUpload().catch((error) => {
const message = error instanceof Error ? error.message : String(error)
console.error(`\n✗ ${message}\n`)
process.exit(1)
})

View File

@@ -0,0 +1,52 @@
import { existsSync, readFileSync } from 'node:fs'
import { join } from 'node:path'
import { parse } from 'dotenv'
import type { R2Config } from '../server/types'
const PROD_ENV_PATH = join('apps', 'cli', '.env.production')
const PROD_ENV_TEMPLATE_PATH = join('apps', 'cli', '.env.production.example')
function pickEnv(name: string, fileEnv: Record<string, string>): string {
const value = process.env[name] ?? fileEnv[name]
if (!value || value.trim().length === 0) {
throw new Error(`Missing required environment variable: ${name}`)
}
return value
}
function loadProdEnv(rootDir: string): Record<string, string> {
const prodEnvPath = join(rootDir, PROD_ENV_PATH)
if (!existsSync(prodEnvPath)) {
const templatePath = join(rootDir, PROD_ENV_TEMPLATE_PATH)
if (existsSync(templatePath)) {
throw new Error(
`Missing ${PROD_ENV_PATH}. Create it from ${PROD_ENV_TEMPLATE_PATH} before running upload:cli-installers.`,
)
}
throw new Error(
`Missing ${PROD_ENV_PATH}. The template file ${PROD_ENV_TEMPLATE_PATH} was not found.`,
)
}
return parse(readFileSync(prodEnvPath, 'utf-8'))
}
export interface CliUploadConfig {
r2: R2Config
}
export function loadCliUploadConfig(rootDir: string): CliUploadConfig {
const fileEnv = loadProdEnv(rootDir)
return {
r2: {
accountId: pickEnv('R2_ACCOUNT_ID', fileEnv),
accessKeyId: pickEnv('R2_ACCESS_KEY_ID', fileEnv),
secretAccessKey: pickEnv('R2_SECRET_ACCESS_KEY', fileEnv),
bucket: pickEnv('R2_BUCKET', fileEnv),
downloadPrefix: '',
uploadPrefix:
process.env.R2_UPLOAD_PREFIX ?? fileEnv.R2_UPLOAD_PREFIX ?? 'cli',
},
}
}

View File

@@ -0,0 +1,56 @@
import { existsSync } from 'node:fs'
import { dirname, join, resolve } from 'node:path'
import { fileURLToPath } from 'node:url'
import { log } from '../log'
import { createR2Client, joinObjectKey, uploadFileToObject } from '../server/r2'
import { loadCliUploadConfig } from './config'
const CDN_BASE_URL = 'https://cdn.browseros.com'
const INSTALLERS = [
{
filePath: join('apps', 'cli', 'scripts', 'install.sh'),
objectName: 'install.sh',
contentType: 'text/x-shellscript; charset=utf-8',
},
{
filePath: join('apps', 'cli', 'scripts', 'install.ps1'),
objectName: 'install.ps1',
contentType: 'text/plain; charset=utf-8',
},
] as const
export async function runCliInstallerUpload(): Promise<void> {
const rootDir = resolve(dirname(fileURLToPath(import.meta.url)), '../../..')
process.chdir(rootDir)
await uploadCliInstallers(rootDir)
}
export async function uploadCliInstallers(rootDir: string): Promise<void> {
const { r2 } = loadCliUploadConfig(rootDir)
const client = createR2Client(r2)
log.header('Uploading BrowserOS CLI installer scripts')
try {
for (const installer of INSTALLERS) {
const absolutePath = join(rootDir, installer.filePath)
if (!existsSync(absolutePath)) {
throw new Error(`Installer script not found: ${installer.filePath}`)
}
const objectKey = joinObjectKey(r2.uploadPrefix, installer.objectName)
log.step(`Uploading ${installer.filePath}`)
await uploadFileToObject(client, r2, objectKey, absolutePath, {
contentType: installer.contentType,
})
log.success(`Uploaded ${objectKey}`)
log.info(`${CDN_BASE_URL}/${objectKey}`)
}
log.done('CLI installer upload completed')
} finally {
client.destroy()
}
}

View File

@@ -21,16 +21,24 @@ export function parseBuildArgs(argv: string[]): BuildArgs {
)
.option('--upload', 'Upload artifact zips to R2')
.option('--no-upload', 'Skip zip upload to R2')
.option(
'--compile-only',
'Compile binaries only (skip R2 staging and upload)',
)
program.parse(argv, { from: 'user' })
const options = program.opts<{
target: string
manifest: string
upload: boolean
compileOnly: boolean
}>()
const compileOnly = options.compileOnly ?? false
return {
targets: resolveTargets(options.target),
manifestPath: options.manifest,
upload: options.upload ?? true,
upload: compileOnly ? false : (options.upload ?? true),
compileOnly,
}
}

View File

@@ -74,7 +74,14 @@ function validateProductionEnv(envVars: Record<string, string>): void {
}
}
export function loadBuildConfig(rootDir: string): BuildConfig {
export interface LoadBuildConfigOptions {
compileOnly?: boolean
}
export function loadBuildConfig(
rootDir: string,
options: LoadBuildConfigOptions = {},
): BuildConfig {
const fileEnv = loadProdEnv(rootDir)
const envVars = buildInlineEnv(fileEnv)
validateProductionEnv(envVars)
@@ -85,6 +92,10 @@ export function loadBuildConfig(rootDir: string): BuildConfig {
...process.env,
}
if (options.compileOnly) {
return { version: readServerVersion(rootDir), envVars, processEnv }
}
return {
version: readServerVersion(rootDir),
envVars,

View File

@@ -15,19 +15,14 @@ export async function runProdResourceBuild(argv: string[]): Promise<void> {
process.chdir(rootDir)
const args = parseBuildArgs(argv)
const manifestPath = resolve(rootDir, args.manifestPath)
if (!existsSync(manifestPath)) {
throw new Error(`Manifest not found: ${manifestPath}`)
}
const buildConfig = loadBuildConfig(rootDir)
const manifest = loadManifest(manifestPath)
const distRoot = getDistProdRoot()
const buildConfig = loadBuildConfig(rootDir, {
compileOnly: args.compileOnly,
})
log.header(`Building BrowserOS server artifacts v${buildConfig.version}`)
log.info(`Targets: ${args.targets.map((target) => target.id).join(', ')}`)
log.info(`Manifest: ${manifestPath}`)
log.info(`Upload: ${args.upload ? 'enabled' : 'disabled'}`)
log.info(`Mode: ${args.compileOnly ? 'compile-only' : 'full'}`)
const compiled = await compileServerBinaries(
args.targets,
@@ -36,7 +31,26 @@ export async function runProdResourceBuild(argv: string[]): Promise<void> {
buildConfig.version,
)
const client = createR2Client(buildConfig.r2)
if (args.compileOnly) {
log.done('Compile-only build completed')
for (const binary of compiled) {
log.info(`${binary.target.id}: ${binary.binaryPath}`)
}
return
}
const manifestPath = resolve(rootDir, args.manifestPath)
if (!existsSync(manifestPath)) {
throw new Error(`Manifest not found: ${manifestPath}`)
}
const manifest = loadManifest(manifestPath)
const distRoot = getDistProdRoot()
const r2 = buildConfig.r2
if (!r2) {
throw new Error('R2 configuration is required for full builds')
}
const client = createR2Client(r2)
const stagedArtifacts = []
try {
@@ -51,7 +65,7 @@ export async function runProdResourceBuild(argv: string[]): Promise<void> {
binary.target,
rules,
client,
buildConfig.r2,
r2,
buildConfig.version,
)
stagedArtifacts.push(staged)
@@ -62,7 +76,7 @@ export async function runProdResourceBuild(argv: string[]): Promise<void> {
stagedArtifacts,
buildConfig.version,
client,
buildConfig.r2,
r2,
args.upload,
)

View File

@@ -10,6 +10,10 @@ import {
import type { R2Config } from './types'
export interface UploadFileOptions {
contentType?: string
}
function createClientConfig(r2: R2Config): S3ClientConfig {
return {
region: 'auto',
@@ -81,6 +85,7 @@ export async function uploadFileToObject(
r2: R2Config,
key: string,
filePath: string,
options: UploadFileOptions = {},
): Promise<void> {
const data = await readFile(filePath)
await client.send(
@@ -88,7 +93,7 @@ export async function uploadFileToObject(
Bucket: r2.bucket,
Key: key,
Body: data,
ContentType: 'application/zip',
ContentType: options.contentType ?? 'application/zip',
}),
)
}

View File

@@ -21,6 +21,7 @@ export interface BuildArgs {
targets: BuildTarget[]
manifestPath: string
upload: boolean
compileOnly: boolean
}
export interface R2Config {
@@ -36,7 +37,7 @@ export interface BuildConfig {
version: string
envVars: Record<string, string>
processEnv: NodeJS.ProcessEnv
r2: R2Config
r2?: R2Config
}
export interface ResourceSource {

View File

@@ -0,0 +1,145 @@
/**
* Fetches models.dev/api.json and generates a compact models data file
* for BrowserOS. Run: bun scripts/generate-models.ts
*/
const API_URL = 'https://models.dev/api.json'
const OUTPUT_PATH = new URL(
'../apps/agent/lib/llm-providers/models-dev-data.json',
import.meta.url,
).pathname
interface ModelsDevModel {
id: string
name: string
family?: string
attachment: boolean
reasoning: boolean
tool_call: boolean
structured_output?: boolean
modalities: { input: string[]; output: string[] }
cost?: {
input: number
output: number
cache_read?: number
cache_write?: number
}
limit: { context: number; output: number; input?: number }
status?: string
release_date: string
last_updated: string
}
interface ModelsDevProvider {
id: string
name: string
npm: string
api?: string
doc: string
env: string[]
models: Record<string, ModelsDevModel>
}
interface OutputModel {
id: string
name: string
contextWindow: number
maxOutput: number
supportsImages: boolean
supportsReasoning: boolean
supportsToolCall: boolean
inputCost?: number
outputCost?: number
}
interface OutputProvider {
name: string
api?: string
doc: string
models: OutputModel[]
}
// models.dev ID → BrowserOS provider ID
const PROVIDER_MAP: Record<string, string> = {
anthropic: 'anthropic',
openai: 'openai',
google: 'google',
openrouter: 'openrouter',
azure: 'azure',
'amazon-bedrock': 'bedrock',
lmstudio: 'lmstudio',
moonshotai: 'moonshot',
'github-copilot': 'github-copilot',
}
function transformModel(model: ModelsDevModel): OutputModel | null {
if (model.status === 'deprecated') return null
const supportsImages =
model.attachment || model.modalities.input.includes('image')
return {
id: model.id,
name: model.name,
contextWindow: model.limit.context,
maxOutput: model.limit.output,
supportsImages,
supportsReasoning: model.reasoning,
supportsToolCall: model.tool_call,
...(model.cost && {
inputCost: model.cost.input,
outputCost: model.cost.output,
}),
}
}
async function main() {
console.log(`Fetching ${API_URL}...`)
const response = await fetch(API_URL)
if (!response.ok) throw new Error(`Failed to fetch: ${response.status}`)
const data: Record<string, ModelsDevProvider> = await response.json()
console.log(`Fetched ${Object.keys(data).length} providers`)
const output: Record<string, OutputProvider> = {}
for (const [modelsDevId, browserosId] of Object.entries(PROVIDER_MAP)) {
const provider = data[modelsDevId]
if (!provider) {
console.warn(`Provider not found in models.dev: ${modelsDevId}`)
continue
}
const models = Object.values(provider.models)
.map(transformModel)
.filter((m): m is OutputModel => m !== null)
.sort((a, b) => {
const dateA = provider.models[a.id]?.last_updated ?? ''
const dateB = provider.models[b.id]?.last_updated ?? ''
return dateB.localeCompare(dateA)
})
output[browserosId] = {
name: provider.name,
...(provider.api && { api: provider.api }),
doc: provider.doc,
models,
}
}
const totalModels = Object.values(output).reduce(
(sum, p) => sum + p.models.length,
0,
)
console.log(
`Generated ${Object.keys(output).length} providers with ${totalModels} models`,
)
await Bun.write(OUTPUT_PATH, JSON.stringify(output, null, 2))
console.log(`Written to ${OUTPUT_PATH}`)
}
main().catch((err) => {
console.error(err)
process.exit(1)
})