The server release CI workflow fails on ubuntu-latest because
patch-windows-exe.ts requires Wine to run rcedit. Thread the existing
--ci flag through compileServerBinaries so Windows PE metadata patching
is skipped in CI mode with a warning log.
* feat: add server release workflow
* fix: address PR review comments for 0331-add_server_release_workflow
* refactor: rework 0331-add_server_release_workflow based on feedback
* refactor: rework 0331-add_server_release_workflow based on feedback
* feat(cli): skip self-update prompts for package manager installs
Checks BROWSEROS_INSTALL_METHOD env var (npm, brew) and skips automatic
update checks. Users should use their package manager's update mechanism.
FormatNotice now shows the appropriate upgrade command based on install method.
* feat(cli): add npm bin wrapper for browseros-cli
* feat(cli): add npm postinstall script to download platform binary
Downloads the correct platform binary from GitHub releases during npm
install, verifies SHA256 checksums, and extracts to .binary directory.
* feat(cli): add npm package metadata and README
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: move npm package files to correct monorepo path
The bin wrapper and postinstall were created at apps/cli/npm/ instead of
packages/browseros-agent/apps/cli/npm/. Moves them to the correct location.
* style: use node: protocol for builtin module imports
* feat(cli): add Makefile npm targets and release workflow npm publish step
Adds npm-version and npm-publish Makefile targets for version sync.
Adds Node.js setup and npm publish step to the release workflow.
Adds npm/npx install instructions to release notes template.
* fix(cli): fail on missing checksum entry and limit redirect depth
- Abort if checksums.txt downloaded but archive entry is missing
- Warn if checksums.txt itself failed to download
- Cap redirect depth at 5 to prevent stack overflow on circular redirects
* fix(cli): match install.sh checksum behavior — warn instead of abort
The existing shell installer (install.sh) warns and continues when the
checksum entry is missing from checksums.txt. Match that behavior in the
npm postinstall to avoid unnecessary install failures. Both files come
from the same GitHub release, so the checksum is a corruption check,
not a strong security boundary.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The model picker in NewProviderDialog rendered inline, causing dialog
resizing and lacked keyboard navigation. Replace it with a Popover +
Command (shadcn Combobox) pattern and add fuse.js for fuzzy search.
- Replace custom ModelPickerList with Popover + Command dropdown
- Add fuse.js for fuzzy model search (replaces string.includes)
- Add MODEL_SELECTED_EVENT and AI_PROVIDER_UPDATED_EVENT analytics
- Enrich PROVIDER_SELECTED_EVENT with model_id in chat sessions
* feat: add browseros-cli self-updater
* fix: address review comments for 0327-cli_self_updater
* fix: address PR review comments for 0327-cli_self_updater
* fix: replace goreleaser with Makefile-based release build
Remove .goreleaser.yml (required Pro license for monorepo field) and
consolidate cross-compilation into `make release`. CI now uses the same
Makefile target, fixing a bug where POSTHOG_API_KEY was missing from
release ldflags.
* fix: address critical self-updater bugs from code review
- Fix SHA256 checksum mismatch: verify archive checksum before extraction
instead of verifying extracted binary against archive hash (was always
failing). Add VerifyChecksum() and integration test.
- Fix JSON field name mismatch: TypeScript was emitting camelCase
(publishedAt, archiveFormat) but Go expected snake_case
(published_at, archive_format). Manifest parsing was silently broken.
- Add decompression size limit (256 MB) to prevent zip/gzip bombs.
- Don't update LastCheckedAt on transient errors so retry happens on
next CLI invocation instead of waiting 24h.
* feat: add PostHog usage analytics to CLI
Add anonymous command-level analytics to browseros-cli using the PostHog
Go SDK. Tracks which commands are executed, their success/failure status,
and duration — no PII or person profiles.
- New analytics package with Init/Track/Close singleton
- Distinct ID resolves from server's browseros_id (server.json), falls
back to CLI-generated UUID (~/.config/browseros-cli/install_id)
- API key injected at build time via ldflags (dev builds = silent no-op)
- Server now writes browseros_id into server.json for cross-surface
identity correlation
* fix: address PR review feedback for #603
- Return "unknown" for unrecognized args in commandName to avoid
sending arbitrary user input to PostHog
- Revert goreleaser to {{ .Env.POSTHOG_API_KEY }} (intentional hard
fail — release builds must have the key set)
- go mod tidy to fix posthog-go direct/indirect marker
- Add POSTHOG_API_KEY to .env.production.example
* feat: upload CLI binaries to CDN during release and gate workflow to core team
- Extend scripts/build/cli/upload.ts with uploadCliRelease() that pushes
archives + checksums to R2 under versioned (cli/v{VERSION}/) and latest
(cli/latest/) paths, plus a version.txt for lightweight latest resolution
- Update scripts/build/cli.ts entry point with --release/--version/--binaries-dir
flags (existing no-args behavior preserved for upload:cli-installers)
- Rewrite install.sh and install.ps1 to fetch from cdn.browseros.com instead of
GitHub releases API — eliminates rate limits and API dependency
- Add environment: release-core to release-cli.yml for core-team gating via
GitHub environment protection rules
- Add Bun setup + CDN upload step to the workflow between build and GitHub release
* fix: address review feedback for PR #602
- Make loadProdEnv return empty map when .env.production is absent so
pickEnv falls through to process.env in CI (Greptile P1)
- Add semver format validation for version string in install.sh and
install.ps1 to guard against malformed CDN responses
- Pass inputs.version via env var instead of inline ${{ }} interpolation
to prevent command injection in workflow shell
* 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.
* fix(cli): fix hdiutil mount detection, update README with install/launch/init flow
* 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.
* fix(cli): remove -quiet from hdiutil so mount point is detected
* fix: add refresh indicator to chat history when fetching latest conversations
Show a non-blocking "Fetching latest conversations" indicator at the top
of the history list while the cached data is being refreshed. Users can
still interact with the cached conversation list during the refresh.
* perf: reduce chat history query payload — fetch last 2 messages instead of 5
The conversation list only displays the last user message as a preview.
Fetching 5 messages per conversation was wasteful — each message contains
the full UIMessage object (tool calls, reasoning, etc.) multiplied by
50 conversations per page. Reduced to last 2 which is sufficient to
find the last user message in a user→assistant exchange.
* perf: use first+DESC instead of last+ASC to push LIMIT down to SQL
PostGraphile's `last: N` doesn't map to SQL LIMIT — it uses a padded
LIMIT 10 and slices in application code. Changing to `first: 2` with
ORDER_INDEX_DESC generates a true SQL LIMIT 2, reducing rows scanned
from 500 to 100 per page (50 conversations × 2 vs 10 messages each).
No UX impact — extractLastUserMessage() filters by role regardless
of message order.
* chore: update react query packages
* feat: replace localforage with idb-keyval
* fix: remove filesystem tools when no workspace is selected
- Make workingDir optional on ResolvedAgentConfig
- Remove resolveSessionDir() fallback that always created a session dir,
masking the no-workspace state and keeping filesystem tools available
- Gate buildFilesystemToolSet() on workingDir being defined
- Add workspace change detection mid-conversation — rebuilds the agent
session when workspace is added, removed, or switched (same pattern
as existing MCP server change detection)
- download_file falls back to tmpdir() when no workspace is set
- Memory/soul tools are unaffected — they use ~/BrowserOS/ paths
* fix: sanitize message history when session rebuilds with different tools
When a session is rebuilt due to workspace or MCP changes, the carried-over
message history may contain tool parts for tools that no longer exist in
the new session. The AI SDK validates messages against the current toolset
and rejects parts with no matching schema.
- Add toolNames getter to AiSdkAgent exposing registered tool names
- Add sanitizeMessagesForToolset() to strip tool parts referencing
removed tools from carried-over messages
- Apply sanitization in both MCP and workspace session rebuilds
* fix: prepend tool-change context to user message on session rebuild
When workspace or MCP integrations change mid-conversation, prepend a
[Context: ...] block to the user's message explaining what changed.
This prevents the LLM from hallucinating tool usage based on patterns
in the carried-over conversation history.
Context messages vary by change type:
- Workspace removed: lists unavailable filesystem tools, suggests
selecting a working directory
- Workspace added: confirms filesystem tools are available with path
- Workspace switched: notes the new working directory
- MCP changed: notes that some integration tools may have changed
Only fires on the first message after a rebuild. Invisible in the UI.
* fix: make MCP change context specific about which apps were added/removed
Diff the old and new MCP server keys to produce specific context like:
- "The following app integrations were disconnected: Gmail, Slack."
- "The following app integrations were connected: Linear."
instead of a generic "some tools may no longer be available" message.
* refactor: extract shared rebuildSession helper in ChatService
Eliminates the duplicated 20-line dispose→create→sanitize→store flow
that existed separately in both the MCP and workspace change-detection
blocks.
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
* test: add sanitizeMessagesForToolset test suite
Tests for the message sanitization that runs when a session rebuilds
with a different toolset (workspace or MCP change mid-conversation):
- Preserves messages with no tool parts
- Preserves tool parts when tool is in the toolset
- Strips tool parts when tool is NOT in the toolset
- Strips multiple removed tool parts from same message
- Keeps browser tools while removing filesystem tools
- Removes messages that become empty after stripping
- Preserves non-tool parts (reasoning, step-start, file)
- Returns same references when no filtering needed
- Handles empty message array and empty toolset
* style: fix biome formatting in chat-service.ts
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
* feat: isolate new-tab agent navigation from origin tab
Add origin-aware navigation isolation so the agent never navigates
away from the new-tab chat UI. This is a two-layer defense:
1. Prompt adaptation: When origin is 'newtab', the system prompt's
execution and tool-selection sections are rewritten to prohibit
navigating the active tab and default all lookups to new_page.
2. Tool-level guards: navigate_page and close_page reject attempts
to act on the origin tab when in newtab mode, returning an error
that teaches the agent to self-correct.
The client now sends an `origin` field ('sidepanel' | 'newtab')
instead of injecting a soft NEWTAB_SYSTEM_PROMPT that LLMs could
ignore. Backwards compatible — defaults to 'sidepanel'.
Closes TKT-592, addresses TKT-564
* test: add newtab origin navigation guard tests
- 14 new prompt tests verifying the system prompt adapts correctly
for newtab vs sidepanel origin (execution rules, tool selection table,
absence of conflicting single-tab guidance)
- 6 new integration tests for navigate_page and close_page guards:
rejects origin tab in newtab mode, allows non-origin tabs, allows
all tabs in sidepanel mode, backwards compatible with no session
- Simplify CLI section: remove confusing MCP jargon, clarify it works
from terminal and AI coding agents
- Replace "point the CLI at your MCP server" with plain language
- Add Vertical Tabs to the features list
* 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
* 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.
* 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
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).
* 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>
* 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
* 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
- 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
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.
* 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.
* 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)
* 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
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
- 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>
* 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
* docs: add setup guides for ChatGPT Pro, GitHub Copilot, and Qwen Code
Add individual OAuth setup guide pages with step-by-step screenshots
for each provider. Add "Use Your Existing Subscription" section to the
Bring Your Own LLM page with card links to each guide. Register pages
in docs navigation.
* docs: add ChatGPT Pro setup screenshots
* docs: use custom provider icons for OAuth setup cards
* docs: inline SVG icons in provider cards for dark mode support
* docs: place provider icons above card titles
* feat: improve rate limit UX, usage page, and provider selector
- Show "Add your own provider for unlimited usage" CTA when BrowserOS
credits are exhausted or daily limit is reached
- Fix credit exhaustion detection to match actual error message
- Improve Usage page: remove disabled Add Credits button, add "Coming
soon" badge, add "Want unlimited usage?" section linking to providers
- Add "+ Add Provider" button at bottom of chat provider selector dropdown
* fix: use asChild pattern for Button+anchor in usage page
Replace nested <a><Button> (invalid HTML) with Button asChild
pattern per shadcn/ui convention.
* feat: UI improvements for OAuth dialog, provider badges, and events docs
- Replace OAuth device code toast with a proper Dialog showing the code
prominently with a copy button (GitHub Copilot, Qwen Code, ChatGPT Pro)
- Add "New" badge on provider template cards for ChatGPT Plus/Pro,
GitHub Copilot, and Qwen Code with orange border highlight
- Add events.md documenting all analytics events across the platform
* fix: add verificationUri to DeviceCodeDialog for popup-blocked fallback
Add verificationUri to PendingDeviceCode interface and pass it from
both handleClientAuth and handleServerAuth. Render a fallback "Open
verification page" link in DeviceCodeDialog so users can navigate
to the auth page if the popup was blocked.
- Add MCP promo banner on AI providers page with "New" badge and
"66+ tools" highlight, linking to /settings/mcp
- Add Quick Setup section on MCP settings page with copy-paste
commands for Claude Code, Gemini CLI, Codex, Claude Desktop, OpenClaw
- Consolidate MCP settings: move restart button inline with server URL,
remove separate MCP Server Settings card
- Add analytics event for promo banner clicks
* feat(eval): show mean score instead of pass/fail in report and viewer
* feat(eval): integrate NopeCHA CAPTCHA solver into eval pipeline
Add CAPTCHA detection and waiting so screenshots capture post-solve state.
Run headed with xvfb on CI since headless breaks extension content scripts.
- Add CaptchaWaiter module (detect reCAPTCHA/hCaptcha/Turnstile, poll until solved)
- Add optional `captcha` config block to EvalConfigSchema
- Wait for CAPTCHA solve before screenshot in single-agent and orchestrator-executor
- Patch NopeCHA manifest with API key before launching workers
- Fix CAPTCHA_EXT_DIR path (was pointing one level too high)
- Remove --incognito (extensions don't run in incognito; fresh user-data-dir isolates)
- CI: install xvfb, run headed via xvfb-run, pass NOPECHA_API_KEY secret
* fix: remove daily rate-limit middleware
The daily conversation rate limit is no longer needed. Remove the
middleware, RateLimiter class, fetch-config, error type, shared
constants, DB schema table, and integration tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove unused getDb() method
No longer needed after rate-limiter removal.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The eval's single-agent was passing raw task.query as the prompt,
without browser context (active tab URL, title). The agent didn't
know which page it was on, causing it to ask "which website?" instead
of browsing.
Use formatUserMessage() (same as chat-service.ts) to include browser
context in the prompt. Re-export formatUserMessage from agent/tool-loop.
* fix: prevent deleted scheduled tasks from reappearing after sync
When a scheduled task was deleted, the sync function would see the
remote job missing locally and re-add it, undoing the delete. Fix by
tracking pending deletions in storage so the sync function deletes
them from the backend instead of re-adding them locally.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: use read-modify-write for pending deletions to prevent concurrent clobber
Re-read pendingDeletionStorage before write-back and only remove
resolved IDs, preserving any new entries added by concurrent
removeJob calls during the sync's network I/O.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The test workflow captured exit codes but never failed the job, so PR
checks always showed green even when tests failed. Exit with the
captured code in the summarize step so each suite properly reports
pass/fail. Not a required check, so failures remain non-blocking.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(eval): switch to ubuntu-latest runner, add OE-Clado config
- Switch workflow from self-hosted Mac Studio to ubuntu-latest
- Install BrowserOS Linux .deb in CI (no self-hosted runner needed)
- Add browseros-oe-clado-weekly.json config for orchestrator-executor
- Fix report chart to show date+time (not just date)
- Make BROWSEROS_BINARY configurable via env var
* feat(eval): add NopeCHA captcha solver extension to eval runs
- Auto-load NopeCHA extension in eval Chrome instances
- Works in incognito + headless mode
- CI workflow downloads NopeCHA before eval
- extensions/ directory gitignored (downloaded at runtime)
* feat(eval): per-config concurrency — different configs run in parallel
* feat(eval): remove concurrency limit — all runs execute in parallel
* ci: run browseros tests on pull requests
* refactor: rework 0320-github_action_for_tests based on feedback
* refactor: rework 0320-github_action_for_tests based on feedback
* chore: add CI artifacts to .gitignore
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove mikepenz/action-junit-report to fix check suite misattribution
The JUnit report action creates check runs that GitHub associates with the
CLA check suite instead of the Tests check suite, causing test reports to
appear under "CLA Assistant" in the PR checks UI.
Remove the action and rely on job status + step summary + artifact upload
for test result visibility.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(eval): weekly eval pipeline with R2 uploads and trend dashboard
Add infrastructure for running weekly evaluations and tracking score
trends over time:
- Auto-generated output dirs: results/{config-name}/{timestamp}/
Each eval run gets its own timestamped folder, nothing is overwritten.
- upload-run.ts: uploads eval results to Cloudflare R2. Supports
uploading a specific run or all un-uploaded runs for a config.
- weekly-report.ts: generates an interactive HTML dashboard from R2
data. Config dropdown, trend chart with hover tooltips, searchable
runs table. Groups runs by config name.
- viewer.html: client-facing 3-column run viewer (task list,
screenshots with autoplay, agent stream with messages.jsonl).
Shows performance grader axis breakdown with per-axis scores.
- browseros-agent-weekly.json: weekly benchmark config (kimi-k2p5,
webbench-2of4-50, 10 workers, performance grader, headless).
- eval-weekly.yml: GitHub Actions workflow with cron (Saturday 6am)
and manual trigger. Runs on self-hosted Mac Studio runner.
Concurrency group ensures only one eval runs at a time.
- Dashboard updates: load previous runs, messages.jsonl viewer,
grade badges show percentages, async stream loading.
- Grader updates: timeout 30min, max turns 100, DOM content
verification guidance for performance grader.
* fix(eval): address Greptile review — injection, nested dirs, escaping
- Fix script injection in eval-weekly.yml: pass github.event.inputs
through env var instead of interpolating into shell
- Fix /api/runs to enumerate nested results/{config}/{timestamp}/ dirs
- Fix /api/load-run to allow single-slash run names (config/timestamp)
- Add HTML escaping for R2-sourced values in weekly-report.ts
- Escape axis names in viewer.html renderAxesBreakdown
* fix(eval): fix biome lint — non-null assertion, template literals
* fix(eval): fix biome errors — replace var with let, fix inner function declaration
* fix(eval): address Greptile P2 issues
- isRunDir: check all subdirs for metadata.json, not just first 3
- eval-runner: guard configPath for dashboard-driven runs (fallback to 'eval')
- load-run: default unknown termination_reason to 'failed' not 'completed'
* feat(eval): make BROWSEROS_BINARY configurable via env var
The OAuth callback server on port 1455 was bound eagerly at startup,
crashing the server if another BrowserOS instance was already running.
Rewrite as a lazy class (OAuthCallbackServer) that:
- Only binds port 1455 when the user initiates a ChatGPT Pro login
- Sends GET /cancel to any existing server on the port first, then
retries up to 5 times (follows Codex CLI's cancel+retry pattern)
- Exposes /cancel endpoint so other instances/tools can cancel us
- Releases the port after the OAuth callback arrives
- Device-code providers (GitHub Copilot, Qwen) never touch port 1455
This allows running eval, dev instances, and multiple BrowserOS
instances without port conflicts. OAuth login works on whichever
instance initiates it — the others continue without OAuth.
* feat: auto-discover server port via ~/.browseros/server.json
Server writes its port to ~/.browseros/server.json on startup so the CLI
can auto-discover the server URL without requiring `browseros-cli init`.
Discovery chain: BROWSEROS_URL env > config.yaml > server.json > error
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address review feedback for PR #504
- Use synchronous unlinkSync in stop() since process.exit() fires
immediately after, abandoning any pending async operations
- Wrap writeServerConfig in try/catch so a write failure doesn't crash
a healthy server for a convenience feature
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: type server discovery config and add version metadata
Add ServerDiscoveryConfig interface to @browseros/shared and enrich
server.json with server_version, browseros_version, and chromium_version.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: normalize URL from server.json for consistency
All other URL sources (env var, config.yaml) pass through
normalizeServerURL; apply the same to the server.json path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add voice recording UI with waveform overlay to new tab search bar
Add a microphone button to the NewTab search bar that opens a fullscreen
recording overlay powered by react-voice-visualizer. The overlay shows a
real-time waveform visualization during recording, recording time, and a
stop button. On completion, the audio is transcribed via the existing
gateway endpoint and the transcript auto-navigates to inline chat.
Changes:
- Extract transcribeAudio() to shared lib/voice/transcribe-audio.ts
- Add VoiceRecordingOverlay component with react-voice-visualizer
- Add Mic button to NewTab search bar
- Track analytics via existing NEWTAB_VOICE_* events
- Handle cancel (backdrop click) vs submit (stop button) correctly
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address PR review comments for voice recording overlay
- Reset processingRef on transcription error to prevent stuck state
- Use stable callback refs to prevent useEffect re-runs from inline
arrow function props (fixes timer reset and unnecessary re-processing)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: replace voice overlay with inline sidepanel-style voice UI
Remove react-voice-visualizer dependency and VoiceRecordingOverlay.
Instead use the same inline voice pattern as the sidepanel ChatInput:
- Waveform bars replace the search input during recording
- Mic/stop/loading button states in the search bar
- Transcript populates the search input on completion
- Voice error shown inline below the search bar
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* test: add build smoke test to catch compile failures
Compiles the server binary (darwin-arm64) and verifies --version outputs
the correct version from package.json. Uses an empty resource manifest
and stub env vars so the test runs without R2 access or real secrets.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address review feedback for PR #511
- Derive build target from process.platform/arch for CI portability
- Include binary stderr in --version assertion for better diagnostics
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
sharp is a native C module (libvips) whose .node binaries can't be
embedded in Bun compiled executables. It was imported at the top level
in copilot-fetch.ts, crashing the entire server at startup.
Replace with jimp (pure JavaScript, zero native deps) which bundles
cleanly into compiled binaries. Same resize algorithm preserved.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Qwen Code as OAuth LLM provider with refactored OAuth hooks
Add Alibaba Qwen Code as a third OAuth provider using Device Code flow
with PKCE. Free tier: 2,000 requests/day, up to 1M token context.
Refactoring:
- Extract useOAuthProviderFlow hook (eliminates ~180 lines of duplicated
OAuth logic from AISettingsPage for ChatGPT Pro + Copilot + Qwen)
- Extract resolveOAuthConfig in config.ts (shared resolver for all OAuth
providers, parameterized by provider name, default model, refresh flag)
- Generalize token-manager device code flow to support PKCE
(code_challenge/code_verifier) and form-urlencoded content type
New code:
- Qwen Code provider config with PKCE + form encoding flags
- Provider factories (both provider.ts and provider-factory.ts)
- Extension UI (template card, models, analytics, dialog)
* fix: use portal.qwen.ai as API base URL for OAuth tokens
DashScope (dashscope.aliyuncs.com) expects Alibaba Cloud API keys,
not OAuth tokens from chat.qwen.ai. The correct endpoint for OAuth
Bearer tokens is portal.qwen.ai/v1.
* fix: correct Qwen Code model IDs and context windows
- coder-model (1M context): virtual alias that routes to best model
- qwen3-coder-plus (1M): was incorrectly 131K
- qwen3-coder-flash (1M): new, speed-optimized variant
- qwen3.5-plus (1M): was incorrectly 1048576 (power-of-two vs decimal)
- Removed qwen3-coder-next (local/self-hosted, not available via OAuth)
- Default model changed to coder-model (auto-routes server-side)
* fix: move Qwen device code request to extension (bypasses WAF)
Alibaba WAF blocks server-side requests to chat.qwen.ai. Move the
initial device code request to the extension (browser context with
cookies), then hand off the deviceCode + codeVerifier to the server
for background polling via new POST /oauth/:provider/poll endpoint.
* fix: persist OAuth flow-started flag in sessionStorage
The flowStartedRef was lost when the component remounted (e.g. user
navigated to onboarding then back to settings). Use sessionStorage
to persist the flag so auto-create works after navigation.
* revert: remove sessionStorage for OAuth flow flag
Revert to simple useRef pattern matching the original ChatGPT Pro
implementation. The auto-create works when the user stays on the
AI settings page during auth.
* revert: move Qwen back to server-side device code flow
WAF block was temporary (rate-limiting), not permanent. Server-side
fetch to chat.qwen.ai now works. Reverted client-side device code
approach — Qwen now uses the same clean server-side flow as Copilot.
Removed: clientSideDeviceCode config, startClientSideDeviceCode(),
POST /oauth/:provider/poll endpoint, startDeviceCodePolling().
* feat: add WAF detection, rate-limit protection, and token storage endpoint
- Detect WAF captcha responses (HTML instead of JSON) in device code
request and token polling, with user-friendly error messages
- Add 30s cooldown on "USE" button to prevent rapid clicks triggering WAF
- WAF-blocked poll requests silently retry instead of aborting
- Add POST /oauth/:provider/token endpoint for storing externally-provided
tokens (useful for future fallback flows)
- Add storeTokens() method to OAuthTokenManager
- Pass server error messages through to extension toast notifications
* refactor: remove 30s cooldown, simplify OAuth hook
The hook is now identical for all providers — server handles retries
via activeDeviceFlows.delete(). Removed flowStartedAtRef cooldown
that was blocking legitimate retries.
* feat: client-side OAuth for Copilot and Qwen Code
Move device code OAuth flow to the extension for GitHub Copilot and
Qwen Code. The extension makes requests using Chrome's network stack,
which bypasses Alibaba WAF TLS fingerprint detection that blocks
server-side Bun/Node.js fetch.
New files:
- client-oauth.ts: Client-side device code + PKCE + token polling
Changes:
- useOAuthProviderFlow: handleClientAuth() for providers with clientAuth
config, handleServerAuth() for others (ChatGPT Pro)
- AISettingsPage: clientAuth config for Copilot and Qwen Code
- WAF detection: opens provider site for captcha solving on block
Server-side device code flow preserved as fallback (token-manager.ts,
providers.ts). Token storage via POST /oauth/:provider/token endpoint.
* fix: export OAuthProviderFlowConfig type, fix typecheck errors
- Export OAuthProviderFlowConfig interface so AISettingsPage can use it
instead of duplicating the type inline
- Fix string | null → string | undefined for agentServerUrl parameter
Add CHATGPT_PRO_SUPPORT and GITHUB_COPILOT_SUPPORT feature flags gated
on minServerVersion 0.0.77. Hide template cards and provider type
dropdown options when the server doesn't support the OAuth endpoints.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add model selector to newtab search bar
Add AI provider/model selector button to the newtab homepage footer bar,
matching the existing button aesthetics (Workspace, Tabs, Apps). Reuses
ChatProviderSelector popover from sidepanel. Users can now see and change
their AI provider before starting a conversation from the newtab page.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: clean up newtab footer with icon-only buttons
Reduce visual clutter in the search bar footer by converting Provider,
Workspace, and Tabs buttons to compact icon-only buttons (8x8). Text
labels and chevron indicators are removed — native title tooltips
provide discoverability on hover. Apps button on the right keeps its
text label per user preference.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: add hover-expand labels to newtab footer icon buttons
Replace static title tooltips with smooth hover-expand animation —
buttons show icon-only by default, text label slides out on hover
via max-w transition. Gives a clean compact look while keeping
labels discoverable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: revert workspace/tabs to full text, keep provider hover-expand only
Restore full text labels for Workspace and Tabs buttons. Only the
provider selector uses the compact icon + hover-expand pattern.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: simplify provider selector to plain icon button
Remove hover-expand animation, use a simple icon-only button with
native title tooltip for the provider selector.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add GitHub Copilot as OAuth-based LLM provider
Add GitHub Copilot as a second OAuth provider using the Device Code flow
(RFC 8628). Users authenticate via github.com/login/device, and the server
polls for token completion. Supports 25+ models through a single Copilot
subscription.
Key changes:
- Device Code OAuth flow in token manager (poll with safety margin)
- Custom fetch wrapper injecting Copilot headers + vision detection
- Provider factory using createOpenAICompatible for Chat Completions API
- Extension UI with template card, auto-create on auth, and disconnect
* fix: address PR review comments for GitHub Copilot OAuth
- Validate device code response for error fields (GitHub can return 200
with error payload)
- Store empty refreshToken instead of access token for GitHub tokens
- Add closeButton to Toaster for dismissing device code toast
* fix: add github-copilot to agent provider factory
The chat route uses a separate provider-factory.ts (agent layer) from the
test-provider route (llm/provider.ts). Added createGitHubCopilotFactory
to the agent factory so chat works with GitHub Copilot.
* fix: add github-copilot to provider icons, models, and dialog
- Add Github icon from lucide-react to providerIcons map
- Add 8 Copilot models (GPT-4o, Claude, Gemini, Grok) to models.ts
- Add github-copilot to NewProviderDialog zod enum, validation skip,
canTest check, and OAuth credential message
* fix: reorder copilot models with free-tier models first
Put models available on Copilot Free at the top (gpt-4o, gpt-4.1,
gpt-5-mini, claude-haiku-4.5, grok-code-fast-1), followed by
premium models that require paid Copilot subscription.
* fix: set correct 64K context window for Copilot models
Copilot API enforces a 64K input token limit regardless of the
underlying model's native context window. Updated all model entries
and the default template to 64000 so compaction triggers correctly.
* fix: use actual per-model prompt limits from Copilot /models API
Queried api.githubcopilot.com/models for real max_prompt_tokens values.
GPT-4o/4.1 have 64K, Claude/gpt-5-mini have 128K, GPT-5.x have 272K.
Also updated model list to match what's actually available on the API
(e.g. claude-sonnet-4.6 instead of 4.5, added gpt-5.4/5.2-codex).
* feat: resize images for Copilot using VS Code's algorithm
Large screenshots cause 413 errors on Copilot's API. Resize images
following VS Code's approach: max 2048px longest side, 768px shortest
side, re-encode as JPEG at 75% quality. Uses sharp for server-side
image processing.
* fix: address all Greptile P1 review comments
- Add .catch() on fire-and-forget pollDeviceCode to prevent unhandled
rejection crashes (Node 15+)
- Add deduplication guard (activeDeviceFlows Set) to prevent concurrent
device code flows for the same provider
- Add runtime validation of server response in frontend before calling
window.open() and showing toast
- Remove dead GITHUB_DEVICE_VERIFICATION constant from urls.ts
* fix: upgrade biome to 2.4.8, fix all lint errors, and address review bugs
- Upgrade biome from 2.4.5 to 2.4.8 (matches CI) and migrate configs
- Fix image resize: only re-encode when dimensions actually change
- Fix device code polling: retry on transient network errors instead of aborting
- Allow restarting device code flow (clear old flow instead of throwing 500)
- Fix pre-existing noNonNullAssertion and noExplicitAny lint errors globally
* fix: address Greptile P2 review — image resize and config guard
- Fix early-return guard: check max/min sides against their respective
limits (MAX_LONG_SIDE/MAX_SHORT_SIDE) instead of both against SHORT
- Preserve PNG alpha: detect hasAlpha and keep PNG format instead of
unconditionally converting to lossy JPEG
- Keep browserosId guard in resolveGitHubCopilotConfig consistent with
ChatGPT Pro pattern (safety check that caller context is valid)
* feat: update Copilot models to full list from pricing page, default to gpt-5-mini
Added all 23 models from GitHub Copilot pricing page. Ordered with
free-tier models first (gpt-5-mini, claude-haiku-4.5), then premium.
Changed default from gpt-4o to gpt-5-mini since it's unlimited on
Pro plan and has 128K context (vs gpt-4o's 64K limit).
* fix(skills): read-only view mode for built-in skills
- SkillCard shows Eye icon + "View" for built-in, Pencil + "Edit" for user
- SkillDialog in read-only mode: disabled fields, no toolbar on markdown
editor, "View Skill" title, "Close" button, no "Update Skill"
- Hide tip section in read-only mode
* fix(skills): use react-markdown for read-only skill view
Replace MDXEditor with react-markdown for viewing built-in skills.
MDXEditor chokes on code fences, angle brackets, and image syntax
causing content truncation. react-markdown handles standard markdown
correctly with no rendering issues.
* Revert "feat: convert settings to popup dialog (#477)"
This reverts commit 42aa0ff1ef.
* fix: address review feedback for PR #498
- Remove erroneous SETTINGS_PAGE_VIEWED_EVENT tracking from SidebarLayout
(was firing on every non-settings page navigation)
- Fix mobile settings sidebar not closing on route change by merging
setMobileOpen(false) into the pathname-dependent analytics useEffect
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: select text and pass to sidepanel
* fix: lint issues
* fix: persist selection across tabs
* fix: review comments
* fix: change when the selection is cleared
* feat: sanitize url
* fix(skills): UI section separation and fix find-alternatives rendering
- Split skills page into "My Skills" (user) and "BrowserOS Skills" (built-in) sections
- Fix find-alternatives SKILL.md — replace angle bracket placeholders with curly
braces to prevent MDXEditor from parsing them as JSX and rendering empty content
* fix(skills): bump find-alternatives to v1.1 for CDN sync
* feat: updated chat ui from homepage
* fix: vertical scroll
* fix: horizontal scroll issue
* fix: lint issues
* fix: header width
* fix: message input from home to chat
* feat: created sidebar header support in new tab chat
* fix: remove history from new tab chat
* fix: remove the shared element transition
* fix: lint issues
* fix: review comments
* fix: defer the sendMessage callback
* fix: all code concerns
* fix: preserve state of chat on homepage
* fix: review comments
* fix(skills): separate built-in and user skills into distinct directories
- Move built-in skills to ~/.browseros/skills/builtin/, user skills stay in root
- Unify seed + sync into single syncBuiltinSkills() function, delete seed.ts
- Preserve user's enabled/disabled state during remote sync version updates
- Add catalog reconciliation — remove built-in skills dropped from remote catalog
- Fallback to bundled defaults per-skill when remote sync fails
- One-time migration moves existing default skills from root to builtin/
- Add builtIn field to SkillMeta, determined by directory (not metadata)
- UI shows "Built-in" badge, hides delete button for built-in skills
- Reject deletion of built-in skills in service layer
- Check both dirs for ID collision on skill creation
* fix(skills): address review — dedup by id, guard applyEnabled regex
- loader.ts: deduplication now keys on skill.id (directory slug) not
skill.name (display name), preventing silent drops on name collision
- remote-sync.ts: applyEnabled checks if regex matched before writing,
logs warning if remote content lacks an enabled field
* fix(skills): reconciliation preserves bundled defaults, delete returns 403
- reconcileRemovedSkills now keeps DEFAULT_SKILLS IDs in the safe set,
preventing delete-then-reinstall cycle that lost enabled:false state
- DELETE /skills/:id returns 403 for built-in skills instead of 500
* refactor(skills): simplify syncBuiltinSkills to single clean pass
Build content map (bundled + remote), iterate once, preserve enabled,
reconcile deletions. Removes 7 helper functions, 70 lines of code.
* refactor(skills): extract syncOneSkill, patch content before writing
- syncBuiltinSkills is now 15 lines: build map, iterate, clean up
- syncOneSkill: flat, patches enabled state before writing (single write)
- setEnabled: pure function for content patching
- removeObsoleteSkills: extracted from inline block
* feat: convert settings page to popup dialog, move workflows to main nav
Replace the dedicated settings page layout (SettingsSidebarLayout) with a
modal dialog (SettingsDialog) that opens on top of the current page. Settings
are now accessible via a dialog triggered from the main sidebar, eliminating
the confusing dual-sidebar navigation pattern.
- Create SettingsDialog with tabbed left panel and content area
- Move Workflows into main sidebar navigation (feature-gated)
- Remove /settings/* routes (except /settings/survey)
- Delete SettingsSidebarLayout and SettingsSidebar components
- Update backward compatibility redirects
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: setup new urls for the dialog box
* fix: dialog close button
* fix: settings analytics
* fix: address review comments
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
* feat: add ChatGPT Pro OAuth as LLM provider
Adds OAuth 2.0 (Authorization Code + PKCE) flow so users can authenticate
with their ChatGPT Pro subscription to power BrowserOS's agent, matching
the pattern used by Codex CLI, OpenCode, and Pi.
Server:
- OAuth token lifecycle (PKCE, exchange, refresh, SQLite storage)
- Dedicated callback server on port 1455 (Codex client ID registration)
- Codex fetch wrapper routing API calls to chatgpt.com/backend-api
- Config resolution + provider factories for all code paths (chat, test, refine)
Extension:
- ChatGPT Pro template card with OAuth flow trigger
- Status polling hook + auto-create provider on auth success
- Model list with Codex-supported models (gpt-5.x-codex family)
* fix: address Greptile PR review comments
- Wire OAuth callback server stop handle into onShutdown (P1: port 1455 leak)
- Guard against missing refresh token + clear stale tokens on failed refresh (P1)
- Add logger.warn to silent catch in codex-fetch body mutation
- Document JWT trust assumption in parseAccessTokenClaims
- Source model ID from provider template instead of hard-coding
* simplify: remove unnecessary OAuth shutdown wiring and useCallback
- Revert OAuthHandle interface — callback server port releases on process exit
- Remove stopCallbackServer from shutdown flow (dead code)
- Remove all useCallback from useOAuthStatus per CLAUDE.md guidance
* style: add readonly modifiers and braces per TS style guide
* docs: add E2E test screenshots for ChatGPT Pro OAuth
* fix: strip item IDs from Codex requests to fix multi-turn conversations
* fix: preserve function_call_output IDs in Codex requests
* fix: resolve Codex store=false + tool-use incompatibility
- Pass providerOptions { openai: { store: false } } to ToolLoopAgent
so the AI SDK inlines content instead of using item_reference
- Strip item IDs and previous_response_id in codex-fetch (safety net)
- Use .responses() model (Codex only speaks Responses API format)
* fix: remove non-Codex model gpt-5.2 from chatgpt-pro model list
* fix: strip unsupported Codex params and update model list
- Strip temperature, max_tokens, top_p from Codex requests (unsupported)
- Add all available Codex models including gpt-5.4, gpt-5.2, gpt-5.1
* chore: remove screenshots containing email
* feat: enable reasoning events for ChatGPT Pro Codex models
* chore: set reasoning effort to high for ChatGPT Pro
* feat: add configurable reasoning effort and summary for ChatGPT Pro
- Add reasoningEffort (none/low/medium/high) and reasoningSummary
(auto/concise/detailed) dropdowns in the Edit Provider dialog
- Pass through extension → chat request → agent config → providerOptions
- Defaults: effort=high, summary=auto
* fix: strip max_output_tokens from Codex requests (fixes compaction)
* fix: address Greptile P1 issues
- Fix default model fallback: gpt-4o → gpt-5.3-codex (Codex endpoint)
- Clear stale tokens on refresh failure (prevents infinite retry loop)
- Only auto-create provider after explicit OAuth flow, not on page load
- Add catch block to auto-create effect with error toast
* feat: add remote skill download and auto-sync
Download default skills from remote catalog on first setup with
bundled fallback when offline. Background sync every 45 minutes
checks for new/updated skills without overwriting user-customized
ones. Tracks installed defaults via content hashes in a local
manifest file.
* feat: make skills catalog URL configurable and add generation script
Add SKILLS_CATALOG_URL env var (following CODEGEN_SERVICE_URL pattern)
with fallback to the default constant. Add script to generate
catalog.json from bundled defaults for static hosting.
* feat: add R2 upload script and use cdn.browseros.com for catalog URL
Add upload-skills-catalog.ts that generates and uploads catalog.json
to Cloudflare R2 (same infra as existing build artifacts). Update
default catalog URL to cdn.browseros.com/skills/v1/catalog.json.
* test: add E2E tests for remote skill sync against live CDN
* fix: address code review findings — security, validation, DRY
- Add path traversal protection via safeSkillDir in writeSkillFile
and readSkillContent (reuses existing validation from service.ts)
- Add runtime type guards for catalog JSON and manifest JSON parsing
- Fix seedFromRemote to return false on partial failure so bundled
fallback kicks in
- Add per-skill error handling in syncRemoteSkills so one bad skill
doesn't crash the entire sync
- Wire stopSkillSync into Application.stop() shutdown path
- Extract version from frontmatter in seedFromBundled instead of
hardcoding '1.0'
- Consolidate duplicated logic: reuse installSkill/writeSkillFile/
contentHash/saveManifest from remote-sync.ts in seed.ts
- Extract shared catalog generation into scripts/catalog-utils.ts
* test: add flow tests for all four sync scenarios against live CDN
* refactor: remove redundant scripts and inline catalog generation
Drop generate-skills-catalog.ts, catalog-utils.ts, and
e2e-remote-sync.test.ts (covered by flows.test.ts). Inline
catalog generation into upload-skills-catalog.ts.
* test: add full E2E server flow test against live CDN
Tests all 7 steps of the real server lifecycle: fresh seed from CDN,
no-op sync, user edit preservation, skill reinstall, custom skill
protection, background timer firing, and second startup skip.
* chore: remove e2e-server-flow test
* fix: address Greptile review — entry validation, size limit, DRY, no-op saves
- Validate individual skill entries in catalog (id, version, content
must all be strings) not just the top-level shape
- Add 1MB response size limit on catalog fetch to prevent resource
exhaustion from compromised/misconfigured CDN
- Skip manifest save when sync cycle had no changes (avoids
unnecessary disk I/O every 45 minutes)
- Share extractVersion via remote-sync.ts export, remove duplicate
from seed.ts
* fix: prevent bundled fallback from overwriting partial remote seeds
When seedFromRemote partially fails, the bundled fallback now skips
skills already in the manifest (installed by the partial remote
seed). Also adds Content-Length early check before downloading the
full catalog response body.
* fix: run sync immediately on startup, not just on interval
Previously the first sync fired 45 minutes after boot. Now
startSkillSync runs one sync immediately so returning users
get skill updates right away.
* refactor: simplify sync — remote always wins, remove manifest
Remote catalog is the source of truth. If a skill exists in the
catalog, its version is compared against local frontmatter and
overwritten when newer. No manifest file, no content hashes.
User-created skills (IDs not in catalog) are never touched.
* fix: skip bundled skills already installed by partial remote seed
* chore: remove unreliable Content-Length check
* chore: remove size limit checks, fetch timeout is sufficient
* feat: add "Rewrite with AI" prompt refinement for scheduled tasks
Add a lightweight /refine-prompt endpoint that uses generateText to
rewrite rough scheduled task prompts into clear, actionable instructions.
The UI adds a sparkle-icon button next to the Prompt label in the
NewScheduledTaskDialog with loading state, undo support, and disabled
state when the textarea is empty.
* fix: clear stale undo ref on dialog re-open and pass providerId to refinePrompt
- Reset originalPromptRef when dialog opens and on form submit to
prevent stale "Undo rewrite" button on re-open
- Accept optional providerId in refinePrompt() so the form's selected
provider is used for refinement instead of always the system default
* fix: hide undo rewrite link while refinement is in flight
* fix: reset isRefining state on dialog re-open
* fix: ignore stale refine-prompt responses after dialog re-open
Use a request generation counter so that if the dialog is closed and
re-opened while a rewrite is in flight, the stale response is silently
discarded instead of overwriting the fresh form state.
* fix: invalidate stale refine requests on dialog reopen and rename to kebab-case
- Increment refineRequestIdRef on dialog open so in-flight requests
from a previous session are discarded when they complete
- Rename refinePrompt.ts to refine-prompt.ts per CLAUDE.md file naming
* feat: add voice input to agent chat sidebar
Allow users to record voice and transcribe to text in the chat input.
Mic button shows when input is empty, waveform visualizer during recording,
transcription via OpenAI (llm.browseros.com/api/transcribe).
- Extract shared useVoiceInput hook to lib/voice/
- Time-domain waveform bars that bounce per-frequency-band
- Bar height capped to fit input container
- Analytics events for recording lifecycle
* fix: address review — add fetch timeout, await stopRecording, deduplicate VoiceInputState
- Add AbortSignal.timeout(30s) to transcription fetch
- Await stopRecording() and track analytics after completion
- Export VoiceInputState from useVoiceInput, import in consumers
* fix: await startRecording before tracking, narrow SurveyChat effect deps
- Await startRecording() so analytics only fires after mic permission granted
- Narrow SurveyChat useEffect dependency from [voice] to [voice.transcript, voice.isTranscribing]
* fix: analytics only tracks on success, clean up stream on failure, type API response
- startRecording returns boolean; track(RECORDING_STARTED) only fires on success
- Catch block cleans up MediaStream tracks and AudioContext on partial failure
- Type transcription API response with TranscribeResponse interface
* fix: keep mic button always visible alongside send button
Mic and send are now separate buttons, both always visible.
Mic is disabled while AI is streaming. Send is disabled during
recording/transcribing. Buttons are no longer absolutely positioned
inside the textarea — they sit beside it in the flex row.
* fix: keep mic button always visible inside input alongside send
Both mic and send buttons are always visible inside the input field,
positioned on the right side (ChatGPT-style). Mic is disabled while
AI is streaming. Send is disabled during recording/transcribing.
* fix: remove unreachable CSS branch in recording waveform div
* feat: add CDP UI inspector script for dev self-testing
* fix: address code review feedback for inspect-ui script
- Use Delete key (not Backspace) to match server's keyboard.ts clearField
- Add windowId resolution to open-sidepanel (chrome.sidePanel.open requires it)
- Make target matching case-insensitive
- Replace process.exit(1) in eval with thrown error for proper cleanup
- Add comment referencing DEV_PORTS source of truth
* docs: add self-testing workflow for UI changes via CDP inspector
* fix: runtime fixes for inspect-ui discovered during live testing
- Remove Input.enable (domain has no enable method)
- Add DOM.getDocument before DOM operations (required by protocol)
- Use BrowserOS-specific sidePanel.browserosToggle API instead of
standard chrome.sidePanel.open (side panel starts disabled)
- Enable side panel with setOptions before toggling
* feat: add test-ui skill for visual testing of agent extension UI
Adds a Claude Code skill that lets the agent visually test both
surfaces of the BrowserOS extension:
- New tab page (app.html) — left sidebar with Home, Scheduled Tasks,
Settings, Skills, Memory, Soul, Connect Apps
- Right side panel (sidepanel.html) — chat interface
Includes all gotchas discovered through real testing: randomized ports,
fresh profile onboarding redirect, stale element IDs after navigation,
BrowserOS-specific sidePanel APIs, DOM.getDocument requirement.
* feat: add press_key, scroll, hover, select_option, wait_for to inspect-ui
Brings inspect-ui.ts to parity with server's MCP input tools:
- press_key: key combos like Enter, Control+A, Meta+Shift+P
(ported from keyboard.ts pressCombo)
- scroll: up/down/left/right with configurable amount
- hover: hover over element by ID for tooltip/hover state testing
- select_option: select dropdown option by value or visible text
(ported from browser.ts selectOption)
- wait_for: poll for text or CSS selector with 10s timeout
Updated skill documentation with new commands and examples.
* docs: prefer snapshot over screenshot, add holistic debugging guidance
- Add snapshot vs screenshot guidance table — prefer snapshot for
structural checks, screenshot only for visual/layout verification
- Add server log checking instructions ([agent], [server], [build] tags)
- Add JS error checking via eval
- Add API connectivity verification
- Add common issues troubleshooting table
- Update all examples to use snapshot as default verification
* fix: address Greptile review feedback
- Replace process.exit(1) with process.exitCode + return in cmdWaitFor
to allow async CDP cleanup in finally blocks
- Fix cmdScroll enabling Runtime instead of Page domain
- Add BROWSEROS_EXTENSION_ID env var override for extension ID
- Align CLAUDE.md dev server command with SKILL.md canonical command
take_snapshot only used the AX tree, which misses custom components
(cursor:pointer divs, onclick handlers, etc.) that lack ARIA roles.
These elements appeared as role="generic" and were invisible to the agent.
Changes:
- Merge findCursorInteractiveElements into snapshot() so take_snapshot
catches cursor:pointer, onclick, and tabindex elements
- Add DisclosureTriangle to INTERACTIVE_ROLES for <summary> elements
- Use aria-label as text fallback in cursor detection for icon-only buttons
- Fix dedup bug in enhancedSnapshot that was silently dropping all
cursor-detected elements by checking against all AX node IDs instead
of only already-included output IDs
- Add hover_at, type_at, drag_at coordinate tools to server
- Add hoverAt, typeAt, dragAt methods to Browser class
- Export server internals (browser, tool-loop, registry) for eval imports
- Copy eval app from enterprise repo with agents, graders, runner, dashboard
- Nest eval-targets inside apps/eval
- Adapt sessionExecutionDir → workingDir for current server API
- Add biome ignore for dashboard HTML to prevent lint breaking onclick handlers
* feat: add get_console_logs tool to surface browser console output
Captures Runtime.consoleAPICalled, Runtime.exceptionThrown, and
Log.entryAdded CDP events per page with a FIFO ring buffer (500 entries).
- ConsoleCollector: per-page buffers with O(1) session routing via Map lookup
- Session-aware CDP event dispatching (onSessionEvent) in CdpBackend
- Log.enable() added alongside Runtime.enable() in attachToPage
- Single tool with level hierarchy, text search, limit, and clear params
- Buffer clears on main-frame navigation, cleaned up on page close
* fix: address review — handle session re-attach, remove dead code
- ConsoleCollector.attach() now updates session mapping on re-attach
instead of early-returning, preventing silent event drops after
target detach/re-attach (e.g. tab crash, cross-process navigation)
- Remove unused clearConsoleLogs() and ConsoleCollector.clear()
* feat: add per-task LLM provider selection for scheduled tasks
Allow users to choose which AI provider a scheduled task runs with,
using the same ChatProviderSelector component from the new-tab page.
Falls back to the global default provider when none is selected or
if the selected provider has been deleted.
* fix: lint issues
* chore: updated to latest schema.graphql file
---------
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
The AI SDK can produce assistant messages with empty parts (parts:[]) when
a stream is aborted, and providers reject assistant messages with empty text
content. This adds a validation utility that filters both cases before
sending messages to createAgentUIStreamResponse and when persisting them.
Mintlify deploys docs by cloning the repo but does not run `git lfs
pull`. The `.gitattributes` rule `docs/images/** filter=lfs` caused
all doc images to be stored as ~130-byte LFS pointer files, which
Mintlify served as-is — breaking every image on the site.
Removing the LFS rule and re-adding the files as regular git blobs
fixes all images without changing any paths or MDX files.
Also fixes broken Slack link placeholder in troubleshooting page.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Images in docs/images/ are served as broken 130-byte placeholders by
Mintlify CDN. Co-locating images with the MDX file (matching the
working pattern in features/workflow/ and features/cowork/) bypasses
this issue. Also fixes the Slack link placeholder.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: fallback to default BrowserOS provider when provider is null
When the extension first loads, provider config is loaded async from
storage. If a chat request fires before loading completes (race
condition), provider is null and the server receives provider: undefined,
causing a Zod validation error. This adds a fallback to
createDefaultBrowserOSProvider() in both chat paths (sidepanel and
scheduled tasks) so provider.type is always defined.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: fallback to first provider when default provider ID is stale
When defaultProviderId in storage doesn't match any loaded provider
(e.g. after Kimi/Moonshot rollout), selectedProvider was null causing
provider: undefined in chat requests. Now falls back to providers[0].
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: repair stale defaultProviderId in storage on load
When the stored default provider ID doesn't match any loaded provider,
write back the corrected ID (providers[0].id) to storage so it doesn't
silently persist across sessions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Comment out non-working Canva and Exa integrations from the OAuth MCP
servers list and remove their imports/icon mappings from the UI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: replace rate limit CTAs with Kimi/Moonshot partnership links
Comment out old "Learn more" and "take a quick survey" links on the
daily limit error banner. Replace with Kimi API key docs link and
direct Moonshot AI platform link for conversion tracking.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove partnership tagline from rate limit banner
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The Docs link in the settings sidebar was using the Info icon (circle
with "i"). Changed it to BookOpen which is the standard icon for
documentation links.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Track docs/images/** and docs/videos/** with Git LFS
- Add packages/browseros/build/tools/ to .gitignore
- Remove appimagetool-x86_64.AppImage from version control (downloaded on demand by build script)
* fix: scheduled task agent not using hidden window for new pages
The agent prompt only told the agent to pass windowId with `new_page`
but not `new_hidden_page`, which the agent prefers for background work.
The agent also had no instruction against closing or replacing its
dedicated hidden window, causing pages to scatter across uncontrolled
windows.
Expanded the scheduled task prompt rules to:
- Cover both `new_page` and `new_hidden_page` windowId requirement
- Forbid closing the dedicated hidden window
- Forbid creating new windows
- Added `new_hidden_page` to tool reference for MCP consumers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove duplicate hidden window creation from scheduled task frontend
The server's ChatService already creates a hidden window for scheduled
tasks (chat-service.ts:99-126), but the frontend (scheduledJobRuns.ts)
was also creating a minimized Chrome window that the server immediately
overwrote. This caused two windows to be created per scheduled task run,
with only one being used.
Removed from scheduledJobRuns.ts:
- chrome.windows.create() call
- 1-second race condition delay hack (FIXME)
- chrome.windows.remove() cleanup
- windowId/activeTab params to getChatServerResponse()
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* chore: bump server version
* fix: remove dead getCdpToolReference and unused prompt exports
The getCdpToolReference function was always excluded by the AI SDK agent
(tool schemas are injected by the SDK itself) and never used by the MCP
server (which has its own MCP_INSTRUCTIONS). Also removes unused exports
getSystemPrompt and PROMPT_SECTION_KEYS.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* chore: bump server version
* fix: move session dirs to ~/.browseros/sessions and update skill paths
Session directories now live under ~/.browseros/sessions/{conversationId}/
instead of executionDir/sessions/. Adds 30-day cleanup for stale sessions
at server startup. Updates 6 default skills to reference the working
directory instead of hardcoding ~/Downloads/.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: rename sessionExecutionDir to workingDir across server
Consistent naming for the per-conversation working directory:
- ResolvedAgentConfig.sessionExecutionDir → workingDir
- ToolDirectories.executionDir → workingDir
- resolveExecutionPath() → resolveWorkingPath()
- buildBrowserToolSet param: executionDir → workingDir
Server-level executionDir (DB, logs) unchanged.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address PR review — restore emoji folder name, refresh session mtime
- Revert "Read Later" back to "📚 Read Later" to avoid creating
duplicate bookmark folders for existing users
- Touch session dir mtime on each message via utimes() so cleanup
correctly reflects last activity, not just directory creation time
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address PR review round 2 — remove dead executionDir, fix emoji
- Remove executionDir from ChatServiceDeps and ChatRouteDeps since
resolveSessionDir now uses getSessionsDir() directly
- Fix missed emoji in notification format template
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
safeSkillDir() used a hardcoded `/` in the startsWith path traversal
check. On Windows, path.resolve() returns backslash paths, so the check
always failed — blocking getSkill, createSkill, updateSkill, deleteSkill.
Replace `${skillsDir}/` with `${skillsDir}${sep}` using path.sep from
node:path, which returns `\` on Windows and `/` on POSIX.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: persist default kimi hub provider to BrowserOS prefs on first load
When VITE_PUBLIC_KIMI_LAUNCH is enabled, loadProviders() returned default
Kimi provider in-memory but never saved it to the BrowserOS pref. The
browser's C++ code reads the pref directly and found it empty, so Kimi
didn't appear in the toolbar until the user manually edited and saved.
Now loadProviders() persists defaults and ensureKimiFirst() additions to
the pref, keeping the browser in sync with what the extension UI shows.
Fixes#428
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use reference equality for ensureKimiFirst change detection
Address PR review: reference check (normalized !== providers) is more
semantically precise than length comparison since ensureKimiFirst returns
the same reference when unchanged.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Return a friendly JSON response when users curl GET /mcp instead of
an opaque 503. Narrows the catch-all .all() to .post() since the MCP
Streamable HTTP transport only needs POST for stateless servers.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Skills page navigation is now hidden when the server version is below
0.0.73, matching the gating pattern used for Memory, Soul, and Workflows.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: move skills into main page navigation
Mirror the soul move pattern (166f6e1b) — promote Skills from
settings sidebar to primary navigation at /home/skills. Adds
backward-compat redirect from /settings/skills.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove missing dismiss-popups skill reference
The SKILL.md file doesn't exist on disk, causing a module
resolution error at server startup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: bootstrap 12 default agent skills for new users
Seed common browser automation skills (summarize, research, extract data,
fill forms, dismiss popups, screenshots, organize tabs, compare prices,
save page, monitor changes, read later, manage bookmarks) into
~/.browseros/skills/ on first startup when no user skills exist.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: populate skill edit dialog with existing content
The edit dialog form fields were empty because Radix Dialog's
onOpenChange doesn't fire when the open prop changes programmatically.
Replace the handleOpenChange wrapper with a useEffect that syncs form
state whenever editingSkill changes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: correct tool names in default skill instructions
- memory_save → memory_write (actual tool name in memory toolset)
- delete_bookmark → remove_bookmark (actual tool name in registry)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move skill content from TS template literals to separate SKILL.md files
Replace the monolithic defaults.ts (738-line file with escaped template
literals) with individual SKILL.md files per skill. Uses Bun's text
import (`with { type: 'text' }`) to inline content at bundle time.
Adds md.d.ts for TypeScript module resolution.
Much easier to read and edit skill content as plain markdown.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add build:server:test and start:server:test scripts for local binary testing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: refresh agent skills settings UI
* fix: address PR review comments for 0311-skills_ui_refresh
* feat: enhance default skills with file persistence, HTML reports, and add find-alternatives
Rewrite deep-research, extract-data, compare-prices, manage-bookmarks, and
read-later skills to follow a structured phase-based workflow. Key changes:
- All research skills now save data incrementally to disk instead of
accumulating in memory
- Add HTML report generation (light theme) with source links for
deep-research, extract-data, and compare-prices
- Use hidden windows and parallel tabs (max 10) for multi-source extraction
- Simplify read-later to just bookmark + PDF save
- Simplify manage-bookmarks to max 3-5 top-level folders with confirmation
- Add new find-alternatives skill for product alternative research with
1-5 star ranking
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: simplify skills page rendering
* fix: clean-up skill
* fix: address review feedback for PR #478
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add core memory viewer and editor to newtab
Adds a new Memory page (/home/memory) that lets users view and
inline-edit their agent's core memories (CORE.md). Includes server
API endpoints (GET/PUT /memory) with Zod validation, React Query
hook with optimistic updates, and example prompts to teach the
agent through conversation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: improve memory examples with browser-aware prompts
Replace tech-specific examples with universal ones that leverage
the agent's browser tools — learning from bookmarks, summarizing
browsing history, reading open tabs, and setting communication
preferences.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: hide focus grid on memory page, same as soul page
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: reword history example to understand user, not just summarize
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: reset stale save error on edit/cancel, surface server errors
Address Greptile review:
- Reset mutation state in handleEdit/handleCancel/handleCreate to
prevent stale error from reappearing on re-entry to edit mode
- Parse server response body on save failure to show actual error
message (e.g. Zod validation) instead of generic "Failed to save"
* fix: cap memory viewer height with internal scroll
Long CORE.md content now scrolls within the card (max 480px) instead
of expanding the entire page. Applies to both read and edit modes.
* fix: polish memory viewer scroll UX
- Use viewport-relative max height (60vh) instead of fixed 480px
- Add styled-scrollbar for thin, themed scrollbar in both modes
- Add bottom fade gradient to hint at more content below
- Fixes width misalignment caused by system scrollbar stealing space
* feat: customize agent personality
* fix: reset soul with right types
* chore: use rpc client for setting personality
* fix: validation for new endpoint
* fix: compaction config for small context windows (≤32K)
Raise COMPACTION_SMALL_CONTEXT_WINDOW from 16K to 32K so models like
Haiku 4.5 (30K context) use proportional 50% reserve instead of the
fixed 20K reserve. Also scale fixedOverhead for small contexts (capped
at 40% of context window) to prevent the doom loop where overhead alone
triggers compaction on every step.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add compaction tuning guidance to limits constants
Explain the relationship between SMALL_CONTEXT_WINDOW and
FIXED_OVERHEAD so devs know the 24K minimum constraint when
tweaking these values.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add window focus listener in ChatFooter that focuses the textarea when
the side panel receives focus. Handles both initial open (via
document.hasFocus check on mount) and re-focus scenarios (via window
focus event). Guards against stealing focus from other interactive
elements.
Companion Chromium fix: side_panel_coordinator.cc now always calls
RequestFocus() in PopulateSidePanel(), not just when there's no
previous entry — ensuring the side panel WebContents receives focus
on every open/toggle.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add 2-stage pruning to compaction pipeline before LLM summarization
Add two new lightweight stages to the compaction prepareStep pipeline that
recover context tokens cheaply before falling back to expensive LLM
summarization:
- Stage 2: Use AI SDK's pruneMessages to remove old tool call/result
pairs beyond the last 6 messages entirely
- Stage 3: Replace remaining tool output values with short placeholders
("[Cleared — N chars]") while preserving tool call structure and IDs
Both stages re-estimate tokens from message content (not stale step
usage) after modifying messages. The existing LLM summarization and
sliding window fallback remain as Stage 4.
Also adds estimateTokensForThreshold() helper, clearToolOutputs()
function, and COMPACTION_PRUNE_KEEP_RECENT_MESSAGES /
COMPACTION_CLEAR_OUTPUT_MIN_CHARS constants.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: reorder compaction pipeline — truncate before clear, protect recent tools
- Stage 0: Check threshold, return untouched when under (no data loss)
- Stage 1: Prune old tool call/result pairs beyond last 6 messages
- Stage 2: Truncate large tool outputs to 15K chars (keeps partial content)
- Stage 3: Clear old tool outputs with placeholders, protect last 2
- Stage 4: LLM-based compaction with sliding window fallback
clearToolOutputs now accepts keepRecentCount parameter (default 2) to
skip the N most recent tool messages from clearing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: limits fixes
* fix: address review — preserve toKeep context, derive test values from constants
- When Stage 3 (clearToolOutputs) doesn't resolve overflow, pass
truncated (not cleared) messages to Stage 4 so toKeep retains
meaningful tool outputs for the agent's immediate context
- Add comment explaining intentional conservatism in post-prune
token estimation (step usage is stale, must re-estimate safely)
- Refactor computeConfig tests to derive expected values from
AGENT_LIMITS constants instead of hardcoding magic numbers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The system prompt referenced `browser_open_tab` which was renamed to
`new_page`. This caused models to infer a `browser_*` naming convention
and call non-existent tools like `browser_navigate`, resulting in
MCP error -32602.
Fixes TKT-540
* feat: new tools for breadcrumbs
* feat: setup scheduled task card
* feat: added dismiss cooldown
* chore: update prompt
* fix: support api key tool
* fix: prompt text to limit nudges
* fix: scheduled tasks card
* fix: update nudges prompt
* feat: skip nudges when user dismisses nudge
* fix: ensure nudges only show if they are not dismissed
* Revert "fix: ensure nudges only show if they are not dismissed"
This reverts commit d825254698829b8e9941aae7873bd440027d0c74.
* Revert "feat: skip nudges when user dismisses nudge"
This reverts commit 12b552b454d10ec4209b88668fc48681423ff6fc.
* Revert "fix: update nudges prompt"
This reverts commit 80b7520b953b4d3cbed2ed477b9e508e39938dca.
* feat: update agent with mcp when new mcp connection is added
* feat: created connect apps option as a blocking card system
* feat: schedule tasks passive without dismiss
* fix: nudges and prompt texts
* fix: biome lint errors
* fix: review comments
* fix: resolve comments
* fix: review comments
* fix: review comments
* fix: auto resolve state
* fix: eliminate the race where the async delete could resolve after the
new session
* feat: track ignored apps list
* fix: empty response text object on message reply
* feat: sync previously connected mcps
* feat: sync integrations with klavis
* feat: account for unauthenticated connections
* fix: analytics events
* fix: typescript issues
* fix: klavis client issue
* fix: invalid mcps causing entire responses from failing
* fix: prompt with card for integrations when the integration fails
* fix: prompt structure to support declined apps
* fix: refresh session on mcp changes
* feat: add agent skills system with catalog, loader, and UI
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: return 500 for server errors in PUT/DELETE skill routes
Previously both handlers returned 404 for all errors, masking filesystem
failures (disk full, permission denied) as "not found". Now only
"not found" errors return 404; everything else returns 500.
* fix: align SKILL.md format with agentskills.io spec
- Move `enabled` and `version` into `metadata` field (spec only allows
name, description, license, compatibility, metadata, allowed-tools)
- Frontmatter `name` now matches directory name (lowercase kebab-case)
- Human-readable name stored in `metadata.display-name`
- Add index signature to SkillMetadata for arbitrary string keys
- Validate frontmatter with type guard in getSkill (remove unsafe cast)
- updateSkill now preserves existing frontmatter fields (license, etc.)
- Tighten buildSkillMd param from Record<string, unknown> to SkillFrontmatter
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- truncateToolOutputs: handle all output.type variants (text, json,
content) by checking output.value directly instead of branching on
type. The old code missed type 'content' (array of content parts),
causing 1M+ char tool results to pass through untouched.
- estimateTokens: change chars/4 to chars/3 — HTML/Markdown content
tokenizes at ~3.14 chars/token empirically, not 4.
- COMPACTION_FIXED_OVERHEAD: 5K → 12K to account for system prompt
(~2.5K tokens) + tool definitions as JSON Schema (~8-9K tokens).
- Apply truncateToolOutputs in prepareStep (Stage 0) before token
estimation, not just during summarization.
* fix: robust compaction with Pi-style token counting + overflow middleware
Root cause: getCurrentTokenCount() returned stale inputTokens from the
previous step, ignoring new tool results added to messages since that
step. A large tool output (DOM snapshot, page content) caused a token
jump that bypassed the compaction threshold check, leading to
context_length_exceeded errors (322K tokens sent, model max 262K).
Layer 1 — Accurate token counting (proactive):
- Adopt Pi coding agent's additive approach: base(inputTokens) +
outputTokens + estimate(trailing tool results)
- Trailing tool results are estimated by walking backwards from end of
messages array until a non-tool message is found
- Falls back to full estimation with safety multiplier when no real
usage data is available (first step of a turn)
Layer 2 — Context overflow middleware (reactive):
- LanguageModelV3Middleware that wraps doGenerate/doStream
- Catches context_length_exceeded errors at the model call level
- Truncates prompt (keeps system messages + most recent non-system
messages targeting 60% of context window)
- Retries the model call once
Verified end-to-end with real model (Gemini Flash Lite via OpenRouter)
on 16K context window: 4 compactions triggered correctly across 8
steps, no context_length_exceeded errors.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: adopt Pi-style overflow detection patterns + fix truncation edge case
- Replace 6 generic substring matches with 17 provider-specific regex
patterns from Pi coding agent (Anthropic, OpenAI, Google, xAI, Groq,
OpenRouter, Bedrock, Copilot, llama.cpp, LM Studio, MiniMax, Kimi,
Mistral, z.ai)
- Fix truncatePrompt edge case: when the last message alone exceeds the
target, keepFrom was never updated → empty non-system messages. Now
always keeps at least the most recent non-system message.
- Add runtime guard for LanguageModelV3 cast in ai-sdk-agent.ts
- Add tests for false-positive rejection and truncation edge case
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The Kimi K2.5 model supports a 256,000 token context window, not
128,000. Updated the provider template and model config to reflect
the correct value.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: return element coordinates in tool responses and DPR in screenshots
- click, hover, fill, drag now return resolved coordinates in response text
- take_screenshot returns devicePixelRatio for mapping coordinates to pixels
- Coordinates are in CSS pixels; multiply by DPR to get screenshot pixels
* fix: use Promise.allSettled in screenshot to prevent DPR eval from aborting capture
Runtime.evaluate for devicePixelRatio can fail on PDF pages or
chrome-extension pages. Using Promise.allSettled ensures the screenshot
still succeeds, falling back to DPR=1.
* feat: gate Moonshot AI provider behind VITE_PUBLIC_KIMI_LAUNCH flag
Hide all Moonshot/Kimi provider UI when the launch flag is off:
- Filter moonshot from provider templates and type dropdown
- Gate Kimi flare badges in HubProviderRow
- Gate Kimi auto-insertion in LLM hub storage
- Add analytics events for Kimi API key configuration and guide clicks
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: allow editing existing moonshot providers when launch flag is off
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add search provider settings page with 5 engine options
Allow users to select their preferred search engine (Google, DuckDuckGo,
Bing, Brave Search, Yahoo) from a new settings page. The selected provider
drives search suggestions, search URL navigation, placeholder text, and
analytics tracking. Replaces all hardcoded Google references with the
stored preference. Adds Brave Search support, replacing Yandex.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add error handling for search provider storage writes
Write to storage before updating React state so UI never diverges from
persisted value on failure. Add try/catch in the settings page to show
an error toast if the write fails.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: migrate stale 400k context window for browseros provider
Existing installations cached the old 400k default in extension storage.
Always normalize the browseros provider's contextWindow to 200k on load,
matching the current default and preventing compaction from failing.
* fix: add browseros-auto model with 200k context length
* fix: setup migrations using the migrations api for context window size
---------
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
* fix: anchor agent to active tab page ID from browser context
Generalize the scheduled-task page anchoring instruction to all tasks.
The agent now always uses the page ID from Browser Context instead of
calling get_active_page or list_pages, preventing it from operating
on the wrong tab.
* fix: add chatMode guard and scope windowLine to scheduled tasks
- Skip page-context section in chat mode where list_pages is allowed
- Only show windowId instruction for scheduled tasks (hidden window)
* feat: integrate models.dev registry for auto-populated model defaults
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: fall back to upstream provider for model registry lookup
When the browseros meta-provider is used, the registry lookup now
also tries the upstream provider (e.g., openrouter, anthropic) so
that BrowserOS-hosted models get correct context window and image
support defaults.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add Object.hasOwn guards to prevent prototype chain lookup
Addresses Greptile review: bracket notation on the registry object
could return prototype-chain properties for keys like __proto__ or
constructor, bypassing the 404 guard in the route handler.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add browseros-cli Go CLI for browser automation
Implements a full-featured CLI that communicates with the BrowserOS MCP
server over JSON-RPC 2.0 / StreamableHTTP. Covers all 54 MCP tools across
10 categories with a hybrid command structure (flat verbs for hot-path
commands, grouped noun-verb for resource management).
- MCP client with initialize + tools/call pattern, thread-safe request IDs
- Dual output: human-readable default, --json for structured/piped usage
- Implicit active page resolution with --page override
- 21 command files: open, nav, snap, click, fill, scroll, eval, ss, pdf,
dom, wait, dialog, pages, window, bookmark, history, group, health, info
- Cobra CLI framework with fatih/color for terminal formatting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add end-to-end integration tests for browseros-cli
Go integration tests gated by `//go:build integration` that exercise the
CLI binary against a running BrowserOS server. Tests build the binary,
run commands via exec.Command, and verify JSON output.
Covers: health, version, page lifecycle (open → text → snap → eval →
screenshot → nav → reload → close), active page, info, error handling,
and invalid page ID rejection. Skips gracefully when no server is running.
Run with: go test -tags integration -v ./...
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add init command and fix MCP client bugs
- Add `browseros-cli init` command that prompts for the server URL,
verifies connectivity, and saves to ~/.config/browseros-cli/config.json
- Config priority: --server flag > BROWSEROS_URL env > config file > default
- Fix Accept header: include text/event-stream (required by StreamableHTTPTransport)
- Fix nil args: send empty object {} instead of null for tools with no params
- Update error messages to suggest `browseros-cli init` on connection failure
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add README for browseros-cli with setup, usage, and testing guide
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: always send arguments object in MCP tools/call
Go's json omitempty omits empty maps, causing the arguments field to be
missing from tools/call requests. The MCP SDK requires arguments to be
an object (even empty {}), not undefined. Remove omitempty from the tag.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: update help menu to be have groups
* refactor: replace hand-rolled MCP client with official Go SDK
Switch from custom JSON-RPC implementation to the official
github.com/modelcontextprotocol/go-sdk. This removes all hand-rolled
protocol types (jsonrpcRequest, jsonrpcResponse, RPCError, etc.) and
uses the SDK's StreamableClientTransport with DisableStandaloneSSE
for clean CLI process lifecycle.
Also adds URL normalization/validation, config command, and
updates init/README to reference YAML config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add server-level instructions that get injected into the LLM system
prompt when external MCP clients (Claude Desktop, Cursor, Gemini CLI)
connect. Covers browser automation workflow, Klavis integration
discovery, and auth flow guidance.
* feat: add inline chat experience to new tab page
Bring the full sidepanel chat experience to the new tab page. When
users select an AI suggestion from the search bar, the page transitions
inline to a full chat view instead of opening the sidepanel.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove unnecessary comments from NewTab.tsx
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address PR review comments
- Move NEWTAB_CHAT_STARTED_EVENT tracking to startInlineChat where it
actually fires (was dead code in NewTabChat handleSubmit)
- Add NEWTAB_CHAT_RESET_EVENT tracking to handleNewConversation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: gate newtab chat behind NEWTAB_CHAT_SUPPORT feature flag
When the flag is off (BrowserOS < 0.40.0), falls back to opening the
sidepanel via openSidePanelWithSearch (previous behavior). In dev mode
all features are enabled, so inline chat works during development.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add newtab origin context to chat system prompt
When chatting from the new tab page, the AI is instructed to open
content in new tabs rather than navigating the current tab, keeping
the user's new tab page accessible.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The AI SDK agent (v2) was allowing all 54 browser tools in chat mode,
while the Gemini agent correctly restricted to 6 read-only tools.
Extract CHAT_MODE_ALLOWED_TOOLS to a shared constant and filter
browser tools in AiSdkAgent.create() when chatMode is true.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: expose Klavis MCP tools to external MCP clients
Connect to Klavis Strata at server startup and register discovered tools
on each per-request McpServer instance. This lets external MCP clients
(Claude Code, Gemini CLI) access Klavis-proxied integrations (Gmail,
Slack, GitHub, etc.) alongside browser tools.
- Add register-klavis-mcp.ts with connectKlavisProxy() and registerKlavisTools()
- Wire KlavisProxyHandle through server.ts -> mcp routes -> mcp-server
- Use structured logging and proper type imports
* fix: forward Klavis tool schemas and add shutdown cleanup
- Use zod-from-json-schema to convert Strata's JSON Schema to Zod,
so MCP clients see proper parameter names, types, and required fields
- Close Klavis proxy transport on server shutdown
- Move per-request Klavis tool registration logging to debug level
- Use proper type imports instead of inline import() types
- Fix connectKlavisProxy return type (never returns null)
* fix: add timeout to Klavis MCP connect/listTools and log shutdown errors
* fix: clear timeout timer and pre-compute Klavis tool schemas at startup
* fix: use client.close() instead of transport.close() for proper cleanup
Add SOUL_SUPPORT feature flag to capabilities system requiring
minServerVersion 0.0.67. Hides "Agent Soul" nav item in settings
sidebar for older servers that lack the /soul endpoint.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Summary
- Add `VITE_PUBLIC_KIMI_LAUNCH` feature flag controlling Kimi partnership branding
- BrowserOS provider card shows "Powered by Kimi K2.5 from Moonshot AI" badge and "Extended usage limits for the next 2 weeks!" when flag is on
- Moonshot/Kimi highlighted as "Recommended" in provider templates
- LLM Hub defaults to Kimi, ChatGPT, Claude, Gemini (with legacy defaults migration)
- Kimi hub row shows "Powered by Moonshot AI" flare
- Model selector locked to kimi-k2.5
- "How to get a Kimi API key" link in provider dialog
- Moonshot provider fully integrated across frontend and backend
* fix: refactor SDK BrowserService to use Browser class directly
The tools system was completely rewritten with new tool names and response
formats. BrowserService was calling non-existent MCP tools (browser_get_active_tab,
browser_navigate, etc.) that returned structuredContent which no longer exists.
Replaced MCP HTTP client calls with direct Browser class method calls:
- getActiveTab → browser.getActivePage() / browser.listPages()
- getPageContent → browser.contentAsMarkdown()
- getScreenshot → browser.screenshot()
- navigate → browser.goto() with tabId/windowId resolution
- getPageLoadStatus → browser.listPages() with isLoading check
- getInteractiveElements → browser.snapshot() / browser.enhancedSnapshot()
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address PR review — consistent tabId guard and remove dead PageContent type
- Change `if (tabId)` to `if (tabId !== undefined)` in navigate() to match
the guard style used for windowId and elsewhere in the file
- Remove orphaned PageContent interface no longer imported after refactor
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
SIGQUIT (Ctrl+\) was not in the signal notify list, causing Go's default
handler to dump goroutines. On macOS ARM64 this triggers a known runtime
bug where semasleep panics on the signal stack.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add "don't show again" checkbox to JTBD survey popup
Mirrors the ImportDataHint pattern — adds a checkbox that permanently
suppresses the survey popup when checked and dismissed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: persist dontShowAgain when user clicks Take Survey
Addresses Greptile review — if the checkbox is checked and the user
clicks "Take Survey", persist the flag before opening the survey so
the popup won't reappear if the survey tab is closed without starting.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: show "don't show again" only after 2nd popup, increase interval to 10 msgs
- Track shownCount in storage, only show checkbox on 3rd+ appearance
- Increase MESSAGE_THRESHOLD from 5 to 10 messages between popups
- Add DONT_SHOW_AGAIN_AFTER constant (2) for configurability
- Pass showDontShowAgain through the component chain
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: thread dontShowAgain through onTakeSurvey to avoid duplicate analytics
Addresses Greptile review — previously clicking "Take Survey" with the
checkbox checked would fire both dismissed and clicked events. Now the
dontShowAgain flag is threaded through onTakeSurvey, which persists it
without firing a dismiss event.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The --new flag creates a fresh temp profile directory but WXT's
chromiumProfile was hardcoded to /tmp/browseros-dev, ignoring it.
Pass BROWSEROS_USER_DATA_DIR env var from the Go dev tool and read
it in web-ext.config.ts.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: filter out messages with empty parts to prevent follow-up crash
When an assistant response is interrupted or errors before producing content,
a UIMessage with empty parts remains in the chat state. On the next send, the
AI SDK validates all messages and rejects the empty-parts message with
"Message must contain at least one part". This filters them out when not
streaming and adds a safety guard in formatConversationHistory.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: filter empty-parts messages before persisting to storage
Addresses race condition where the save effect could persist messages
with empty parts before the cleanup effect's state update applies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: limit claude code review to PR creation and @claude comments
Reduces unnecessary action runs and token usage by only triggering the
review on initial PR open, and re-running when @claude is mentioned.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: restrict @claude trigger to trusted contributors
Only repo owners, org members, and collaborators can invoke the review
via @claude comments, preventing external users from consuming token quota.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: consolidate claude workflows and auto-run on PR creation
Remove separate claude-code-review.yml and add pull_request trigger
to claude.yml so it runs automatically on PR open without needing
@claude in the body.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: restore author_association guard on issue_comment trigger
The consolidation commit dropped the author_association check from the
issue_comment condition. Without it, any external commenter could invoke
Claude and consume token quota. Restores the guard to limit triggers to
OWNER, MEMBER, and COLLABORATOR.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: apply author_association guard to review comment triggers
Extends the OWNER/MEMBER/COLLABORATOR check to pull_request_review_comment
and pull_request_review events, preventing external users from triggering
Claude via review comments.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: gate previousConversation array format behind BrowserOS 0.41.0.0
Older servers reject the array format for previousConversation with a
ZodError ("Expected string, received array"). Gate the feature behind
BrowserOS >= 0.41.0.0 which bundles server >= 0.0.64 that accepts both
array and string formats.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use minServerVersion 0.0.64 for previousConversation gate
Server version is the direct indicator of schema support, more accurate
than using BrowserOS version as a proxy.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: fall back to string format for previousConversation on old servers
Instead of omitting previousConversation entirely on servers < 0.0.64,
serialize the conversation history as a "role: content" string which
old servers accept via their z.string() schema.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add get_dom and search_dom tools for HTML DOM inspection
Add two new observation tools:
- get_dom: Returns raw HTML of a page or scoped element via CSS selector
- search_dom: Fuzzy searches DOM elements by text, attributes, IDs, and
class names using Fuse.js with extended search syntax support
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: use CDP DOM protocol instead of injected scripts for DOM tools
Replace Runtime.evaluate-based approach with native CDP DOM methods:
- get_dom uses DOM.getDocument + DOM.querySelector + DOM.getOuterHTML
- search_dom uses DOM.performSearch + DOM.getSearchResults + DOM.describeNode
- Remove fuse.js dependency (CDP performSearch handles text/CSS/XPath natively)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add comprehensive tests for get_dom and search_dom tools
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve text nodes to parent elements in searchDom
CDP performSearch returns text nodes (nodeType 3) for plain text queries.
describeNode does not populate parentId, so use resolveNode + callFunctionOn
to get parentElement, then requestNode to obtain the parent's nodeId.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add limit bounds validation and searchId leak prevention
- Add .int().min(1).max(200) to search_dom limit parameter
- Wrap searchDom result processing in try/finally to ensure
discardSearchResults is always called
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Tests were passing raw Chrome tabIds to group_tabs and ungroup_tabs tools,
but the Zod schemas expect pageIds (MCP-layer page IDs). The tabIds field
was silently stripped during validation, causing both tests to fail.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add new CDP tools for links, hidden pages/windows, show/move
- get_page_links: extract deduplicated links from a page via evaluate
- new_hidden_page: open a hidden tab for background automation
- create_hidden_window: create a hidden window for background automation
- show_page: restore a hidden page back into a visible window
- move_page: move a tab to a different window or position
- Default includeLinks to false in get_page_content
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: use AX tree for get_page_links, add tests, fix test scripts
- Refactor get_page_links to use accessibility tree instead of raw JS
evaluate — more reliable for role="link" elements and shadow DOM
- Add extractLinkNodes() to snapshot.ts and getPageLinks() to browser.ts
- Add tests for get_page_links (constructed HTML with dedup/filtering),
new_hidden_page, show_page, move_page, create_hidden_window
- Fix root package.json test scripts to match server's actual scripts
- Update CLAUDE.md test docs to reflect current structure
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: move ChatV2Service to api/services layer and add resolvePageIds
Move ChatV2Service from agent/tool-loop/ to api/services/ where it
belongs as a service-layer concern. Add resolvePageIds() to convert
Chrome tab IDs to internal page IDs before they reach the agent,
fixing undefined pageId issues in browser automation tools.
Clean up server.ts by removing the USE_TOOL_AGENT flag, SessionManager,
and old chat route import — both /chat and /chat-v2 now directly use
createChatV2Routes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address review comments for chat-v2-service
- Fix TOCTOU race: derive isNewSession inside the creation block
instead of separate has()/get() calls
- Log warning when resolvePageIds can't map a tab ID
- Deduplicate tab IDs with Set before resolving
- Remove redundant null check on session in onFinish
- Add license header
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: update bun.lock
* fix: skip resolvePageIds for scheduled tasks to prevent pageId corruption
Scheduled tasks build browserContext with internal page IDs from
browser.newPage(), not Chrome tab IDs. The unconditional second
resolvePageIds() call was passing these internal IDs to resolveTabIds()
which expects Chrome tab IDs, causing the lookup to fail and overwrite
correct pageIds with undefined.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add biome-ignore comments for noExcessiveCognitiveComplexity on compaction.ts
and grep.ts, and noExplicitAny on filesystem test helpers.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: generalized compaction prompts with split turn handling
Replace browser-specific XML prompts with domain-agnostic markdown format.
Add split turn detection and parallel summarization for large single-turn
conversations. Switch compaction from generateText to streamText for
Fireworks API compatibility. Add comprehensive unit and E2E tests (84 total).
* fix: address code review issues for compaction (PR #391)
Enforce COMPACTION_MAX_SUMMARIZATION_INPUT cap, extract shared
callSummarizer helper, add runtime type guard for experimental_context,
move magic constants to AGENT_LIMITS, and remove dead constants.
* fix: cap truncatedTurnPrefix input to maxSummarizationInput
Apply the same sliding window cap to turn prefix messages that was
already applied to toSummarize, preventing unbounded LLM input for
long single-turn conversations with many tool calls.
* fix: reduce browseros-auto default context window to 200K
The 400K setting caused compaction to trigger at ~383K, but the actual
model limit is 262K. Conversations hit the hard limit before compaction
could kick in.
* feat: replace flaky TypeScript dev:watch with Go CLI (devwatch)
The Bun-based scripts/dev/start.ts orchestrator had fundamental issues with
WXT when launched via `bun run --filter` with cwd manipulation. This replaces
it with a Go CLI at tools/devwatch/ that provides:
- Process supervision with auto-restart on crash
- Colored log streaming with [tag] prefixes
- Automatic port discovery (--new flag)
- Fresh user-data directory creation
- Process group management for clean shutdown (SIGTERM → SIGKILL escalation)
- CDP readiness polling before starting the server
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: run agent codegen before wxt and add force-kill on double Ctrl+C
- Run graphql-codegen if generated/graphql/ doesn't exist, matching the
agent's own `dev` script behavior
- Second Ctrl+C sends SIGKILL to all process groups and exits immediately,
so you're never stuck in a restart loop
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add run.sh wrapper that checks for Go and prompts to install
If Go isn't installed, shows a clear message with install instructions
(brew install go / go.dev/dl). Also skips rebuilding if the binary
already exists and main.go hasn't changed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: show double Ctrl+C hint at startup
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: swap ANSI escape codes for fatih/color
Adds proper TTY detection, NO_COLOR env var support, and cleaner
color API. Also improves help output with bold/dim styling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: restructure devwatch into browseros-dev CLI with cobra subcommands
Expands the single-file devwatch into a modular CLI with three subcommands:
- `watch` — dev environment with process supervision (port of devwatch)
- `test` — start test env, run bun test, clean up (replaces TS test helpers)
- `cleanup` — kill ports + remove orphaned temp dirs (replaces cleanup.sh)
Shared Go packages for browser lifecycle (CDP polling, arg building),
server health checks (health + extension status), and process management
(managed proc, port killing, streaming, monorepo root finding).
Fixes PR #389 feedback:
- Add timeout after SIGKILL in Stop() to prevent indefinite hang
- Fix run.sh freshness check to detect changes in all .go files
- Add double Ctrl+C force-kill to test command
- Guard test cleanup with sync.Once to prevent race condition
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: replace run.sh freshness logic with Makefile
Make handles timestamp-based dependency tracking natively. The Makefile
rebuilds only when any .go file, go.mod, or go.sum is newer than the
binary. run.sh just checks for Go, calls make, and execs the binary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use fresh browser context for selected tabs on each message
Previously, session.browserContext (set on the first message) always
took precedence via the nullish coalescing operator. On subsequent
messages with different tab selections, the new selectedTabs from the
request were silently ignored.
Now normal messages always use request.browserContext so freshly
selected tabs are included. Scheduled tasks still use the stored
session context to preserve the hidden window's pageId/windowId.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use singleton transport for MCP route
MCP SDK 1.26.0 added a strict guard in Protocol.connect() that throws
"Already connected to a transport" if called when already connected.
The previous code created a new transport per request and called
connect() each time, causing every request after the first to fail
with -32603 Internal server error.
Move transport creation outside the request handler and add
isConnected() check per @hono/mcp docs pattern.
* fix: per-request MCP server+transport for SDK 1.26.0 compat
MCP SDK 1.26.0 patched a security vulnerability (GHSA-345p-7cg4-v4c7)
where sharing a singleton McpServer across requests could leak
cross-client response data via message ID collisions.
Create fresh McpServer + StreamableHTTPTransport per request:
no shared state, no race conditions, no ID collisions.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The agent had no knowledge of its working directory, so it couldn't
reference created files by absolute path or help users locate them.
Pass sessionExecutionDir into buildSystemPrompt for both AiSdkAgent
and GeminiAgent so the prompt includes a <workspace> section with
the resolved directory path.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Previously, session.browserContext (set on the first message) always
took precedence via the nullish coalescing operator. On subsequent
messages with different tab selections, the new selectedTabs from the
request were silently ignored.
Now normal messages always use request.browserContext so freshly
selected tabs are included. Scheduled tasks still use the stored
session context to preserve the hidden window's pageId/windowId.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: new onboarding flow
* feat: co-ordinate the sign in and import hints
* fix: ux on step one
* fix: make custom option friendlier
* feat: added required fields
* feat: setup step two redirection
* fix: remove copy url button
* feat: store profile info from onboarding
* feat: sync onboarding profile to api
* feat: show confetti when the onboarding completes
* fix: change the options in onboarding demo
* feat: setup missing analytics events
* fix: lint issues
* ci: fix typescript error
* fix: sign in hint
* fix: restore glow overlay for CDP-based tools
After migrating to CDP tools, glow broke because the hook looked for
input.tabId (controller tools) while CDP tools use input.page (pageId).
- Server: add getTabIdForPage() to Browser, include tabId in tool output
- Client: extract tabId from output, fall back to active Chrome tab
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: use ToolResultMetadata for tabId resolution
Move tabId resolution from tool-adapter into the framework layer:
- response.ts: add ToolResultMetadata interface with tabId field
- framework.ts: auto-resolve pageId→tabId after tool execution
- tool-adapter.ts: just forward metadata (no domain logic)
This makes metadata available to all ToolResult consumers, not just
the AI SDK adapter, and the metadata bag is extensible for future fields.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add todo
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: replace pi-mono filesystem tools with native Bun/Node.js implementation
Remove @mariozechner/pi-coding-agent and @mariozechner/pi-agent-core
dependencies that caused bun compile issues (tree traversal, package.json
resolution). Reimplement all 7 filesystem tools (read, write, edit, bash,
grep, find, ls) using only Bun and Node.js built-in libraries.
- No external binary dependencies (no ripgrep, fd, etc.)
- Cross-platform: Linux, macOS, Windows
- 107 tests covering all tools and utilities
- Pure JS grep/find using Bun.Glob and async directory walking
* fix: add explicit ENOENT handling in grep tool stat() call
* feat: ensure scheduled tasks open in hidden tab
* fix: update scheduled task result in the UI
* fix: remove unnecessary useEffect
* fix: race condition with deleteSession
Instead of a hardcoded experimentId=daily_limit, randomly assign users
to one of four survey direction buckets (competitor, switching, workflow,
activation) matching the round 2 survey pattern.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Copy dev workflow skills (dev, dev1-start through dev7-pr, dev-debug,
ts-style-review) to project .claude/skills/ so they're available to all
contributors. Excludes twitter agent and browseros browser skills.
Update .gitignore to track .claude/skills/ and .claude/commands/.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: update to support more klavis MCP servers
* fix: minor icon fix
* fix: normalize klavis mcp auth flow compatibility
* feat: add API key auth flow for Klavis MCP servers
Servers that use API key authentication (Stripe, Cloudflare, Brave
Search, Exa, Mem0, Resend, Mixpanel, PostHog, Postman, Zendesk,
Intercom) were failing with "Failed to add app" because the frontend
only handled OAuth flows. This adds the complete API key auth path:
- Backend: apiKeyUrls in StrataCreateResponse, submitApiKey() method,
/servers/submit-api-key route
- Frontend: ApiKeyDialog component, useSubmitApiKey hook, ConnectMCP
updated to show dialog for API-key servers instead of opening OAuth
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove broken success check in Klavis submitApiKey
The Klavis /mcp-server/instance/set-auth endpoint returns
{ message: "Authentication updated successfully." } without a
success field. Our code checked `data.success` which was always
undefined, causing API key auth to fail even when Klavis accepted
the key. The request() method already throws on non-2xx responses,
so the explicit check was redundant and incorrect.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Round 2 direction parameter to JTBD survey frontend
Thread direction parameter from popup trigger through URL params to the
survey chat API. Randomly assign one of 4 investigation directions
(competitor, switching, workflow, activation) when the in-app popup
triggers, encoding it as experimentId=r2_{direction} for analytics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: remove direction param, encode in experimentId instead
Direction is now encoded entirely in experimentId (e.g., "r2_competitor").
Remove the separate direction URL param and prop threading — the backend
derives direction from experimentId. Simplifies the frontend to only
set experimentId with a random direction on popup trigger.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: setup
* fix: compact workflow tidbits within streamed assistant parts
feat: collapse workflow tidbit status messages in graph chat
* Revert "fix: compact workflow tidbits within streamed assistant parts"
This reverts commit f5fa6d6b7a480dfc001ede6de7949f45c7777f37.
* fix: collapse workflow tidbit status messages in graph chat
Tidbit messages (jokes/status ending with ...) during workflow execution
now replace each other in place instead of stacking as separate chat
bubbles. Handles both consecutive tidbit messages and multiple tidbit
text parts within a single streamed message.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: compact multi-line tidbits within a single text part
Tidbits arrive as text-deltas accumulated into a single text part
(e.g. "Generating workflow…\nReticulating splines…\n..."). The previous
fix only handled separate parts and separate messages but not multiple
tidbit lines within one part. Added compactTidbitLinesInPart to trim
multi-line tidbit text to just the last line.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Added max-h-[85vh] and overflow-y-auto to DialogContent component
to enable scrolling when dialog content exceeds viewport height.
This fixes the scheduled task dialog not showing scroll when
content is too long.
https://claude.ai/code/session_01CP8aUnunJpW9mYwTbt3gpt
Co-authored-by: Claude <noreply@anthropic.com>
* chore: baseline setup
* fix: resolve stale closure bug in LLM Hub provider management
saveProvider and deleteProvider were wrapped in useCallback with
[providers] dependency, building updated arrays from the closure-captured
providers state. When adding a provider then deleting another, the delete
callback could have a stale providers array that didn't include the newly
added one — causing the new provider to be lost when written to storage.
Fix: read current state from persistent storage via loadProviders()
before every mutation, matching the pattern used in useLlmProviders.ts.
Remove useCallback wrappers since they no longer depend on providers state.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: inject stop button to pages controlled by agent (#334)
* chore: baseline setup
* feat(agent): When the agent is running, right now we inject an orange glow. See the `apps/age
Task ID: TOiaMuDz
* fix: clean up agent storage
* fix: improve the stop button style
* fix: type issues with stopAgentStorage
---------
Co-authored-by: BrowserOS Coding Agent <coding-agent@browseros.com>
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
* fix: resolve stale closure bug in LLM Hub provider management
saveProvider and deleteProvider were wrapped in useCallback with
[providers] dependency, building updated arrays from the closure-captured
providers state. When adding a provider then deleting another, the delete
callback could have a stale providers array that didn't include the newly
added one — causing the new provider to be lost when written to storage.
Fix: read current state from persistent storage via loadProviders()
before every mutation, matching the pattern used in useLlmProviders.ts.
Remove useCallback wrappers since they no longer depend on providers state.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: BrowserOS Coding Agent <coding-agent@browseros.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
* chore: baseline setup
* feat(agent): When the agent is running, right now we inject an orange glow. See the `apps/age
Task ID: TOiaMuDz
* fix: clean up agent storage
* fix: improve the stop button style
* fix: type issues with stopAgentStorage
---------
Co-authored-by: BrowserOS Coding Agent <coding-agent@browseros.com>
Co-authored-by: Dani Akash <DaniAkash@users.noreply.github.com>
saveProvider and deleteProvider used useCallback with [providers]
dependency, causing a stale closure bug. When adding a new provider
then deleting another, the delete callback still referenced the old
providers array (before the add), losing the newly added provider.
Now reads current state from storage before each mutation, matching
the pattern used in useLlmProviders. Also removes unnecessary
useCallback wrappers per project conventions.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Check session existence in ChatService before passing previousConversation
to the agent. Only pass it for new sessions — existing sessions already
have real conversation history in the GeminiClient.
Automatically detect whether custom MCP servers use Streamable HTTP or
SSE transport by probing with a POST request before creating the config.
- Add detectMcpTransport() utility that probes the server endpoint
- If POST returns 200 with JSON/event-stream, use Streamable HTTP
- If POST returns 404/405 or fails, fall back to SSE transport
- Cache detection results per URL with 1-hour TTL
- Skip caching for transient errors (5xx, network failures)
Known servers (browseros-mcp, klavis-strata) skip detection and use
Streamable HTTP directly.
* fix: incorrect tool call for getting page snapshot
* feat: let llm know the page is loaded after enrichment is complete
* feat: improve prompt to prevent calling getActiveTab
* feat: added enrichment to the get_load_status tool
* fix: tips
* fix: show tips only 1/5 times
* fix: guard against empty tips array in getRandomTip
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: biome exhaustive deps in SurveyChat voice effect
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: remove wrapped controller tools and enrich context with windowid
* refactor: remove windowid from all the tools
* feat: pass window id to mcp server via request headers
* feat: enrich possible toolcalls to reduce roundtrip
* feat: show scheduled tasks tab if job runs are empty
* chore: switch tabs after creating new tasks
* feat: provide option to cancel and retry scheduled tasks
* feat: provide option to retry and cancel jobs on the popups
* chore: fix minor race condition between window cleanup and job status
update
* fix: keep previous data in chat history
* feat: use react query for restoring conversation messages
* fix: loading issue with chat history
* fix: use state instead of ref for the restoredConversationId
* fix: handle not found scenario on both local and remote restoration
* Revert "fix: handle not found scenario on both local and remote restoration"
This reverts commit d4725134087af047fe18bc6519f5ad5244104544.
* fix: handle conversation not found scenario
* chore: added a loading indicator for the chat history page
* chore: reset restored conversation id state
* feat: do not create tab groups for scheduled tasks
* chore: simplify system prompt to make excluding steps easier
* chore: consistent prompt composer
* feat: created auth client
* feat: created login page for testing auth
* feat: setup logout page
* feat: setup graphql codegen
* feat: setup graphql + react query utils
* feat: setup queryprovider with localforage
* feat: created auth provider
* feat: update claude.md
* feat: documents for bulk conversation upload
* chore: install missing package
* fix: setup codegen to scan for .ts files
* chore: setup check conversation query
* feat: upload conversation by profileId
* chore: upload messages in batches
* feat: account for edge cases in conversation upload
* feat: delete uploaded conversations from localstorage
* feat: load conversation history from api
* feat: implement delete conversation using graphql
* feat: delete confirmation for conversation history
* fix: issue with clearing conversations after upload
* feat: implement pagination for graphql chat history
* chore: update CLAUDE.md
* chore: update claude.md
* feat: save conversations to server
* fix: handle streaming check on remote conversation save
* feat: restore conversation from graphql
* fix: timestamp issue on the chat history page
* feat: sync llm providers from background script
* feat: update llm providers on change via background script
* chore: added a try catch block
* feat: display incomplete providers in separate UI
* feat: delete provider on server when initiated by user
* feat: setup scheduled tasks storage to sync to graphql
* feat: auto run sync in background script
* fix: sync all keys of scheduled tasks based on updatedAt timestamp
* feat: added login dropdown on the sidebar
* feat: simplify sidenav header
* feat: update header design after login
* feat: setup profile page
* feat: added back button to profile page
* fix: scrollbar flash in profile page
* feat: finish login handshake
* feat: clear storage on logout
* fix: logout page style
* feat: added tooltip to encourage user to sign in
* feat: added back button to login page
* fix: upload logic for profile picture
* feat: account for profile name in sidebar branding
* chore: set file upload url from backend request
* chore: remove default placeholder from profile component
* chore: sync with main
* Revert "chore: sync with main"
This reverts commit 77e06b894ce30235d1bfa31c8e2699b34df423a5.
* Reapply "chore: sync with main"
This reverts commit dd921d97cc9794d1872e13689c881f68e4dfee47.
* chore: updated lock file
* fix: run codegen before build:ext
* fix: run codegen before build:gent
* fix: remove hardcoded localhost header in magic link
---------
Co-authored-by: Nikhil Sonti <nikhilsv92@gmail.com>
* fix: use source files for agent-sdk during development
Export src/index.ts directly in workspace mode so the server can import
without requiring a build step. publishConfig overrides exports to use
dist/ when publishing to npm.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: onboarding try it
* fix: summarize current page
* fix: ask browser os opens in agent mode
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: agent mode on or off
* fix: cleaner whitelist for chat mode
* fix: cleaner whitelist for chat mode
* feat: agent mode with tooltip
* feat: agent mode chat mode final UI
* feat: previous conversation history
* fix: re-enable the DELETE endpoint
* fix: make bun run start:server show lgos
* fix: minor text change
* fix: keep 16k context window size
* fix: use message ref to get access to full restored messages (when create prev conversation history)
* fix: don't run watchdog in dev-mode
* Revert "fix: re-enable the DELETE endpoint"
This reverts commit 9cbbbab6768c7c412c8f65bd88643e2856fa5169.
---------
Co-authored-by: Nikhil Sonti <nikhilsv92@gmail.com>
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: add timeout and window based mutex to improve speed
* fix: move suspense boundary closer to corresponding pages
* fix: pre-resolve the client via singleton to speed up the clientPromise
* feat: apply theme background faster with plain script
* chore: update biome version
* feat: make rpc client persist promise with useMemo and remove loading
text
* fix: replace dvh with vh
* fix: replace dvh with vh in create graph
* fix: import clean-up + unit test for transformCode
* feat: improve formatter
* feat: grep interactive tool
* fix: simple, detailed, full formatter options
* fix: viewport legend
* fix: add vscode launch.json for debugging
* fix: grep show before and after, also click before type/clear
* feat: move to bun plugin to intercept WASM
* feat: new build/server.ts with refactored
* fix: clean-up source map dirs before build
* fix: remove elide for build
* fix: clean-up source map ordering
* feat: v1 ui for the file selector
* feat: integrate with browseros.choosePath API
* feat: gate workspace folder for 0.36.0.4 as requires new browserOS.choosePath API
* fix: add default folder option
* fix: clean-up old code
* feat: create conversations storage hook
* feat: save conversation hook
* feat: created chat layout
* feat: created chat history button
* feat: setup chat history view links
* chore: updated placeholder
* fix: width of the chat history screen
* feat: provide navigation from history page back to conversation page
* fix: issue with restoring conversation id
* chore: do not update history when content doesn't change
* feat: mark active conversation id
* fix: syncing the conversation id ref
* feat: improve the logic for node width
* feat: use dagre to display loops
* chore: use animated dots for loops
* feat: create graph using cytoscape
* feat: use cytoscape html label
* feat: setup dynamic label height and width
* feat: set reasonable zoom levels
* feat: use theme colors for nodes
* feat: use mutation observer to change color schemes
* feat: implement dark mode with pure css
* chore: remove unused libraries
* fix: sanitize label with dompurify
* feat: add support for jtbd agent to accept max turns and experiment id as query params
* fix: add jtbd agent integration with workflow
* fix: change message threshold to 5
* fix: tempDir is executionDir and create per session execution dir
* fix: move create() in gemini-agent to top
* fix: log(debug) directories
* fix: chat routes bug
* feat: support userSessionDir in /chat request schema
* fix: clean-up un-used types
* fix: lint errors
- moved chatprovider selector to a shared component
- reimplement chat header as it was simple and we can have graph mode specific options there instead of reusing chat header from sidepanel
* feat: custom node component
* feat: create resizable panels for graph ui
* feat: setup hono rpc on agent
* feat: created getClient util
* feat: created rpc client provider
* chore: reafctor agent sdk
* chore: created usechat hook
* chore: graph create update endpoint return ai sdk stream
* chore: graph create update endpoint return ai sdk stream
* chore: graph create update endpoint return ai sdk stream
* chore: graph create update endpoint return ai sdk stream
* feat: graph chat component
* feat: integrate input field
* feat: make getActionForMessage optional
* feat: integrate chat messages ui
* feat: update graph canvas with latest message
* feat: support editing graph with new message
* feat: create chat test function
* fix: created chat test api integration
* chore: remove background window state
* chore: improve agent ui stream
* chore: print error
* feat: create workflow storage
* feat: created workflows screen on options page
* feat: added error handling to workflows chat
* chore: ignore graph code generation folder
* fix: provide a better header title name
* fix: buttons accessibility on graph canvas
* feat: improve test and save workflow button state
* chore: provide autofocus to the workflow header
* feat: setup save and edit options on the workflow
* feat: open the workflow in edit mode
* fix: use sentry to capture server exception
* feat: integrate run workflow using dialog box
* feat: display errors in the run dialog box
* fix: use rpc client to delete workflows
* feat: fix panel sizes on graph creation
* fix: provide suspense fallback boundary for the options page
* feat: auto fitview on graph updates
* fix: node colors in the graph
* chore: make minimap movable
* feat: provide styling to react flow controls
* fix: missing imports
* fix: pass personalization to workflow runs
* feat: provide back button in workflow page
* feat: added confirmation when leaving workflow page without saving
* feat: provide animation to nodes
* feat: autofit canvas to resizepanel size
* feat: added workflows to newtab page
* fix: typescript lint errors
* feat: enforce bun version
* fix: typecheck command
---------
Co-authored-by: shivammittal274 <mittal.shivam103@gmail.com>
* feat: v0.1 jtbd popup for users
* feat: v0.2 jtbd popup based on messages sent
* fix: clean up previous chat status and added comment
* chore: change threshold to 15
* fix: show popup only when every N messages
* fix: set survey taken only after clicking start on welcome page
* feat: v0.1 of voice transcription for JTBD survey
Add voice input capability to the JTBD Product Survey chat:
- useVoiceInput hook for audio recording and transcription
- VoiceInputButton component for mic/stop/loading states
- Waveform visualization during recording
- Integration with BrowserOS gateway transcription endpoint
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* style: make voice button orange like send button
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: refactor jtbd agent
* chore: udpate text
* fix: clean up stop recording if stopped midway
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: replace bun install with bun ci in workflow files
* chore: update react router
* chore: update posthog
* fix: vulnerable package versions
* Revert "fix: replace bun install with bun ci in workflow files"
This reverts commit 2924fe496fc340555506d305e57b81cb87d45dae.
* fix: add debug logging for start:dev
* feat: use eventsource-parser for schedule tasks
* fix: remove reasoning traces, minor UI updates for schedule task
* fix: bug with textdelta
* fix: controller-ext is built separately
* fix: remove un-used scripts in agent/
* fix: rename to assistant
* fix: add build scripts
* feat: new start:dev to start both
* fix: update gitignore
* feat: --new-ports support for dev:start
* feat: update start-all to support port and new data dir
* fix: add help insturctions for start:dev
* chore: refactoring
* fix: return all response parts from tool execution
Previously, handleToolExecution only returned responseParts[0], causing
data loss when tools returned multiple parts. This fix:
- Changes ToolExecutionResult.part to ToolExecutionResult.parts (array)
- Returns all responseParts instead of just the first one
- Spreads all parts into toolResponseParts in processToolRequests
This workflow runs a daily security audit on the codebase, checking for vulnerabilities and sending the results to Slack. It includes steps for checking out the code, setting up Bun, installing dependencies, running the audit, parsing results, and notifying via Slack.
* feat: support browserOS server version in capabilities
* feat: add personalisation support flag
* fix: gate personalisation based on server support
* fix: gitignore minor
* fix: clean-up passing logger, bad pattern it's singleton
* feat: refactor main.ts (#148)
* fix: logger in main
* feat: refactor chat route and split into service (#149)
* fix: logger in chatserver
* feat: scheduled tasks base ui
* chore: fix biome version
* fix: type issues
* chore: remove use callback
* chore: refactor scheduleStorage types
* feat: create storage hooks for job & job runs
* feat: integrate listing with store
* feat: schedule tasks dialog integration
* feat: integrate view and runs
* feat: sync alarm state
* fix: check for enabled jobs in alarm state
* feat: createAlarmFromJob utility
* feat: updated edit hooks to update alarms
* feat: getChatServerResponse util
* feat: run jobs in schedule
* feat: update job run stat with storage
* feat: discard old runs over 15
* feat: provide graph mode entry
* feat: footer link with scheduler option
* feat: use a nicer loader for task runs
* feat: schedule results component
* feat: scheduler results in new tab page
* feat: nicer date formatting with dayjs
* feat: use run-result-dialog for displaying run results in new tab
* chore: delete mocked storage methods
* chore: remove unused code
* chore: remove all job runs when a job is deleted
* feat: use shadcn elements for schedule results component
* feat: render results in markdown view
* chore: added important update on logic sharing
* chore: remove loading state in scheduledtaskslist
* feat: run the background job in a unfocused window
* feat: provide mcp options to the background scheduled tasks
* chore: clean up stale jobs on chrome restart or update
* fix: background window not cleaned up on error
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* chore: fix type issues
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* feat: agent-sdk outline
* feat: unit tests for agent-sdk
* feat: implement /sdk routes
* feat: integration test for agent-sdk with server
* feat: ENV to disble headless mode for testing
* feat: act() integration test working
* chore: refactor package/shared to have constants/ and /types separately
* feat: verify() and extract() sdk APIs
* feat: extract() use remote endpoint for extraction
* feat: verify() implemented - lazy parsing to avoid strong schema checks
* fix: remove generateStructuredOutput as not models support it
* fix: clean-up LLM types and use zod schema
* fix: typecheck vitetest error
* fix: remove directly calling GeminiAgent in sdk act()
* fix: lefthook for refactor warning
* fix: refactor routes/sdk to move business logic out
* chore: fix monorepo setup
1) use single .env.development file at the root
2) update package.json to contain commands to start server and agent
3) rename "Assistant" package name to "agent"
4) rename HTTP_MCP_PORT to SERVER_PORT
* chore: update README
* chore: update .env.example
* ci: update dependabot to focus on security
Added open-pull-requests-limit, enabled beta ecosystems (for bun support) and only allow only security updates
* chore: fix whitespaces
* ci: update dependency groups to only apply to security-updates
* feat: use pino logger, use logger interface across ext and server
* fix: no need prefixes in logger as we parse stack trace
* chore: update claude.md
* fix: clean-up old docs
* feat: refactored test utils
* fix: clean-up dev scripts and move to scripts/dev
* fix: clean-up script
* fix: refactor tests into properly controller tests and cdp tests
* feat: import all the missing tests before refactor
* fix: biome errors for tests
* fix: few type errors and add exceptiosn
* fix: few more type errors
* fix: remove agent port from tests
* fix: exclude tests from tsconfig, bun run tests natively
* fix: mcpServer test now waits for extension connected
- Delete apps/server/src/mcp/server.ts and index.ts (replaced by http/routes/mcp.ts)
- Delete apps/server/src/agent/http/HttpServer.ts, types.ts, index.ts (replaced by http/)
- Move ChatRequestSchema and related types to http/types.ts
- Update imports in GeminiAgent.ts, agent/types.ts, agent/index.ts
- Remove deprecated exports from agent/index.ts
- Remove commented out startMcpServer and startAgentServer functions from main.ts
- Add routes/chat.ts with POST /chat and DELETE /chat/:conversationId
- SSE streaming with abort detection via honoStream.onAbort()
- Rate limiting for BrowserOS provider
- Session management via SessionManager
- Reuses existing GeminiAgent execution logic
- Add routes/mcp.ts using StreamableHTTPTransport from @hono/mcp
- Per-request transport to prevent JSON-RPC request ID collisions
- Reuse tool registration logic from existing MCP server
- Security check with isLocalhostRequest() using Bun server.requestIP()
- Supports enableJsonResponse for JSON responses (not SSE)
- Add routes/provider.ts with Zod validation for provider testing
- Add routes/klavis.ts with all Klavis OAuth endpoints
- Update server.ts to compose new routes
* feat: refactor packages into single project
* feat: created apps directory
* chore: removed duplicate packages
* fix: delete package-lock.json
since project uses bun
* feat: mcp support
* feat: mcp support added
* feat: third party mcp support
* feat: third party mcp support
* feat: mcp support extended to all oauth urls and user integrations
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: fetch daily rate limit from the gateway
* chore: survey link for usage limit
* fix: remove initial query from rate limiter table to keep it simple (as it is not required)
Fixes "unexpected tool_use_id found in tool_result blocks" API errors that
occur after conversation compression removes one half of a tool_use/tool_result pair.
Root cause: The existing filter logic checked if tool_use IDs had matching
tool_results (and vice versa), but when filtering orphans, the IDs were not
removed from the tracking sets. This caused corresponding counterparts in
later Contents to pass through the filter, creating mismatched pairs.
Changes:
- Add cascading deletion: when filtering an orphan tool_result, also delete
its ID from allToolResultIds so later tool_uses with that ID are filtered
- Add cascading deletion: when filtering an orphan tool_use, also delete
its ID from allToolCallIds so later tool_results with that ID are filtered
- Add mergeConsecutiveToolMessages() to combine split tool messages into a
single message, satisfying the API requirement that all tool_results must
immediately follow their tool_use in one message
- Add comprehensive test coverage for orphan filtering scenarios
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: support reading config from TOML file
* fix: wip toml config
* refactor: one config, merged from args, config and config.toml example
* fix: update package.json to have bun start:with_toml
* docs: add quick toml explaination
* refactor: clean-up /init endpoint, we'll use TOML to pass config
* fix: make reconnect interval every 5s
* fix: make host as 127.0.0.1 as some localhost can resolve to ipv6
* feat: make controller-ext check the port each time it reconnects
Switch from x64-modern (requires AVX2) to x64-baseline (SSE4.2 only)
for Linux and Windows builds. This fixes the "Illegal instruction"
crash on pre-Haswell Intel CPUs (Ivy Bridge, Sandy Bridge) and
pre-Excavator AMD CPUs that lack AVX2 support.
Fixes: MCP server crashes with SIGILL on Ivy Bridge CPUs
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
- Request only accepts contextWindowSize
- GeminiAgent computes compressionThreshold internally using fixed 0.75 ratio
- Follows YAGNI principle - no need to expose compressionRatio to UI
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* vercel ai adpater for gemini cli
* tests fixed based upon v5
* remove logic for normalisation for openai (not needed)
* tests fixed based upon v5
* agent core logic
* fix: logger to truncate only in console, write full log to file
* fix: logs dir and proper env parsing
* feat: add focus event to switch the primary controller
* adding resources-dir arg and using that for finding codex binary
* write logs to resource-dir
* handle default executable path for codex
* fix: code-sdk-ts build to have bun
* update to use browseros config
* adding skipGitRepocheck and other configs
* new codex binary integration
* refactor agentConfig
* default eventGaptimeout is 120s
* minor updates
* update env
* fix: gateway gets the config and passes to AgentConfig
Changed mcp.servers to mcp_servers to match Codex CLI config format.
The Codex CLI expects MCP server configuration to use mcp_servers
(underscore) not mcp.servers (dot) in config.toml. This fixes
programmatic MCP configuration via -c CLI flags.
Changes:
- Use mcp_servers instead of mcp.servers
- Clear global config first with -c mcp_servers={}
- Set individual properties with dotted notation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* rename PORT to AGENT_PORT
* rename WebsocketManger to ControllerBridge
* update the log info
* fix: rename wsManager to controllerBridge
* update Logger to use common/Logger
* fix: logger, unify and standarize the naming
* remove standalone agent
* rename to controller-based, cdp-based, cleaner imports in main and claude-sdk
* refactor: main.ts
* refactor: .env
* update controller-ext manifest
* add extension-controller build commands in main package.json
* remove controller-ext environments and move to constants
* update package.json build commands
* fix: controller-ext webpack to combine files for production
* webpack: enable console logs for controller-ext for now in prod
* update README
* adding agent-port arg and updating test
* fix: commander --help issue
* fix: mcp server package mis-match
* add browseros starting for test
* integrate test added
* fix tests to use BrowserOS
* monorepo: core
* monorepo: tools and server
* mono: repo refactor
* moved tests, removed old files
* update server tests
* agent server location and TBD
* fix formatting
* add new workflows
* rename core to common, mcp-server, to mcp, agent-server to agent
* remove nodejs tests
* test: add simple GitHub Actions workflow for running tests on PR
* test workflow
* feat: add test coverage reporting to GitHub Actions workflow
- Run tests with --coverage flag to generate coverage reports
- Display coverage summary in PR comments
- Upload coverage artifacts for analysis
- Show coverage in GitHub Actions summary
* simple test workflow
github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA'))
steps:
- name:'CLA Assistant'
if:(github.event.comment.body == 'recheck' || github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA') || github.event_name == 'pull_request_target'
**CLA Assistant Lite bot** Thank you for your submission! We require contributors to sign our [Contributor License Agreement](https://github.com/browseros-ai/BrowserOS/blob/main/CLA.md) before we can accept your contribution.
Thank you for your contribution! Before we can merge this PR, we need you to sign our [Contributor License Agreement](https://github.com/${{ github.repository }}/blob/main/CLA.md).
By signing the CLA, you confirm that:
- You have read and agree to the AGPL-3.0 license terms
- Your contribution is your original work
- You grant us the rights to use your contribution under the AGPL-3.0 license
**To sign the CLA**, please add a comment to this PR with the following text:
**To sign the CLA, please comment on this PR with:**
`I have read the CLA Document and I hereby sign the CLA`
```
I have read the CLA Document and I hereby sign the CLA
```
You only need to sign once. After signing, this check will pass automatically.
---
<details>
<summary>Troubleshooting</summary>
- **Already signed but still failing?** Comment `recheck` to trigger a re-verification.
- **Signed with a different email?** Make sure your commit email matches your GitHub account email, or add your commit email to your GitHub account.
</details>
custom-pr-sign-comment:'I have read the CLA Document and I hereby sign the CLA'
custom-allsigned-prcomment:|
**CLA Assistant Lite bot** ✅ All contributors have signed the CLA. Thank you for helping make BrowserOS better!
# Lock PR after merge to prevent signature tampering
<imgsrc="https://img.shields.io/badge/Download-macOS-black?style=flat&logo=apple&logoColor=white"alt="Download for macOS (beta)"/>
@@ -22,146 +23,183 @@
<br/>
</div>
##
🌐 BrowserOS is an open-source Chromium fork that runs AI agents natively. **The privacy-first alternative to ChatGPT Atlas, Perplexity Comet, and Dia.**
BrowserOS is an open-source Chromium fork that runs AI agents natively. **The privacy-first alternative to ChatGPT Atlas, Perplexity Comet, and Dia.**
🔒 Use your own API keys or run local models with Ollama. Your data never leaves your machine.
Use your own API keys or run local models with Ollama. Your data never leaves your machine.
💡 Join our [Discord](https://discord.gg/YKwjt5vuKr) or [Slack](https://dub.sh/browserOS-slack) and help us build! Have feature requests? [Suggest here](https://github.com/browseros-ai/BrowserOS/issues/99).
2.**Import your Chrome data** (optional) — bookmarks, passwords, extensions all carry over
3.**Connect your AI provider** — Claude, OpenAI, Gemini, ChatGPT Pro via OAuth, or local models via Ollama/LM Studio
2. Import your Chrome data (optional)
## Features
3. Connect your AI provider — use Claude, OpenAI, Gemini, or local models via Ollama and LMStudio.
4. Start automating!
## 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
-🔒 Privacy first — bring your own keys or run local models with Ollama. Your browsing history stays on your machine
- 🤝 [BrowserOS as MCP server](https://docs.browseros.com/features/use-with-claude-code) — control the browser from `claude-code`, `gemini-cli`, or any MCP client (31 tools)
- 🔄 [Workflows](https://docs.browseros.com/features/workflows) — build repeatable browser automations with a visual graph builder
- 📂 [Cowork](https://docs.browseros.com/features/cowork) — combine browser automation with local file operations. Research the web, save reports to your folder
- ⏰ [Scheduled Tasks](https://docs.browseros.com/features/scheduled-tasks) — run the agent on autopilot, daily or every few minutes
- 💬 [LLM Hub](https://docs.browseros.com/features/llm-chat-hub) — compare Claude, ChatGPT, and Gemini side-by-side on any page
- 🛡️ Built-in ad blocker — [10x more protection than Chrome](https://docs.browseros.com/features/ad-blocking) with uBlock Origin + Manifest V2 support
- 🚀 100% open source under AGPL-3.0
| Feature | Description | Docs |
|---------|-------------|------|
| **AI Agent** | 53+ browser automation tools — navigate, click, type, extract data, all with natural language | [Guide](https://docs.browseros.com/getting-started) |
| **MCP Server** | Control the browser from Claude Code, Gemini CLI, or any MCP client | [Setup](https://docs.browseros.com/features/use-with-claude-code) |
| **Workflows** | Build repeatable browser automations with a visual graph builder | [Docs](https://docs.browseros.com/features/workflows) |
| **Cowork** | Combine browser automation with local file operations — research the web, save reports to your folder | [Docs](https://docs.browseros.com/features/cowork) |
| **Scheduled Tasks** | Run agents on autopilot — daily, hourly, or every few minutes | [Docs](https://docs.browseros.com/features/scheduled-tasks) |
| **Memory**| Persistent memory across conversations — your assistant remembers context over time | [Docs](https://docs.browseros.com/features/memory) |
| **SOUL.md** | Define your AI's personality and instructions in a single markdown file | [Docs](https://docs.browseros.com/features/soul-md) |
| **LLM Hub** | Compare Claude, ChatGPT, and Gemini responses side-by-side on any page | [Docs](https://docs.browseros.com/features/llm-chat-hub) |
| **40+ App Integrations** | Gmail, Slack, GitHub, Linear, Notion, Figma, Salesforce, and more via MCP | [Docs](https://docs.browseros.com/features/connect-apps) |
| **Vertical Tabs** | Side-panel tab management — stay organized even with 100+ tabs open | [Docs](https://docs.browseros.com/features/vertical-tabs) |
| **Ad Blocking** | uBlock Origin + Manifest V2 support — [10x more protection](https://docs.browseros.com/features/ad-blocking) than Chrome | [Docs](https://docs.browseros.com/features/ad-blocking) |
| **Cloud Sync** | Sync browser config and agent history across devices | [Docs](https://docs.browseros.com/features/sync) |
| **Skills** | Custom instruction sets that shape how your AI assistant behaves | [Docs](https://docs.browseros.com/features/skills) |
| **Smart Nudges** | Contextual suggestions to connect apps and use features at the right moment | [Docs](https://docs.browseros.com/features/smart-nudges) |
## Demos
### 🤖 BrowserOS agent in action
### BrowserOS agent in action
[](https://www.youtube.com/watch?v=SoSFev5R5dI)
<br/><br/>
### 🎇 Install [BrowserOS as MCP](https://docs.browseros.com/features/use-with-claude-code) and control it from `claude-code`
### Install [BrowserOS as MCP](https://docs.browseros.com/features/use-with-claude-code) and control it from `claude-code`
For the first time since Netscape pioneered the web in 1994, AI gives us the chance to completely reimagine the browser. We've seen tools like Cursor deliver 10x productivity gains for developers—yet everyday browsing remains frustratingly archaic.
Use `browseros-cli` to launch and control BrowserOS from the terminal or from AI coding agents like Claude Code.
You're likely juggling 70+ tabs, battling your browser instead of having it assist you. Routine tasks, like ordering something from amazon or filling a form should be handled seamlessly by AI agents.
**macOS / Linux:**
At BrowserOS, we're convinced that AI should empower you by automating tasks locally and securely—keeping your data private. We are building the best browser for this future!
**Agent development** (TypeScript/Go) — see the [agent monorepo README](packages/browseros-agent/README.md) for setup instructions.
**Browser development** (C++/Python) — requires ~100GB disk space. See [`packages/browseros`](packages/browseros/) for build instructions.
## Credits
- [ungoogled-chromium](https://github.com/ungoogled-software/ungoogled-chromium) — BrowserOS uses some patches for enhanced privacy. Thanks to everyone behind this project!
- [The Chromium Project](https://www.chromium.org/) — at the core of BrowserOS, making it possible to exist in the first place.
## License
BrowserOS is open source under the [AGPL-3.0 license](LICENSE).
## Credits
- [ungoogled-chromium](https://github.com/ungoogled-software/ungoogled-chromium) - BrowserOS uses some patches for enhanced privacy. Thanks to everyone behind this project!
- [The Chromium Project](https://www.chromium.org/) - At the core of BrowserOS, making it possible to exist in the first place.
## Citation
If you use BrowserOS in your research or project, please cite:
```bibtex
@software{browseros2025,
author={Sonti, Nithin and Sonti, Nikhil and {BrowserOS-team}},
title={BrowserOS: The open-source Agentic browser},
[](https://www.star-history.com/#browseros-ai/BrowserOS&Date)
Already paying for ChatGPT Pro, GitHub Copilot, or Qwen Code? Connect your existing account to BrowserOS with a single sign-in — no API keys, no extra cost.
description: "Use your ChatGPT subscription to power BrowserOS"
---
Connect your ChatGPT Pro or Plus subscription to BrowserOS and access GPT-5 Codex, GPT-5.4, and the full lineup of OpenAI's most advanced models — with up to 400K context. No API keys needed.
## Setup
**1.** Open BrowserOS and go to **Settings** (`chrome://browseros/settings`). You'll see the AI Providers section.
**4.** Once authorized, ChatGPT will appear as a provider in your settings. Select a model and start using it.
## Available Models
| Model | Context Window |
|-------|---------------|
| `gpt-5.4` | 400K |
| `gpt-5.3-codex` | 400K |
| `gpt-5.2-codex` | 400K |
| `gpt-5.2` | 200K |
| `gpt-5.1-codex` | 400K |
| `gpt-5.1-codex-max` | 400K |
| `gpt-5.1-codex-mini` | 400K |
| `gpt-5.1` | 200K |
<Info>
ChatGPT Pro subscribers have access to the full model lineup. ChatGPT Plus subscribers can access a subset of models depending on their plan. The available models will be shown automatically after you connect.
</Info>
<Tip>
The Codex models (e.g., `gpt-5.3-codex`) are optimized for code and reasoning tasks — ideal for complex browser automation workflows that involve form filling, data extraction, and multi-step navigation.
</Tip>
## Reasoning Settings
ChatGPT Pro includes additional settings for models that support reasoning:
- **Reasoning Effort** — Control how much the model "thinks" before responding. Options: none, low, medium, high.
- **Reasoning Summary** — Choose how reasoning is displayed. Options: auto, concise, detailed.
These settings are available in the provider configuration after connecting.
## Disconnecting
To disconnect your OpenAI account, go to **Settings**, find the ChatGPT Plus/Pro provider, and click **Disconnect**. Your OAuth tokens will be immediately deleted from your machine.
description: "Use your GitHub Copilot subscription to power BrowserOS"
---
Connect your GitHub Copilot subscription to BrowserOS and access 19+ models — including Claude, GPT-5, and Gemini — through a single GitHub sign-in. No API keys needed.
<Info>
**Free tier** includes GPT-5 Mini, Claude Haiku 4.5, GPT-4o, and GPT-4.1. **Copilot Pro** ($10/month) unlocks Claude Sonnet 4.6, Claude Opus 4.6, Gemini 3 Pro, GPT-5.4, and more.
</Info>
## Setup
**1.** Open BrowserOS and go to **Settings** (`chrome://browseros/settings`). You'll see the AI Providers section.
**2.** Click **USE** on the **GitHub Copilot** card. A device code will appear — copy it, then click the link to open GitHub's device authorization page.
**5.** Once authorized, GitHub Copilot will appear as a provider in your settings. Select a model and start using it.
## Available Models
### Free Tier
| Model | Context Window |
|-------|---------------|
| `gpt-5-mini` | 128K |
| `claude-haiku-4.5` | 128K |
| `gpt-4o` | 64K |
| `gpt-4.1` | 64K |
### Copilot Pro / Pro+
| Model | Context Window |
|-------|---------------|
| `claude-sonnet-4.6` | 200K |
| `claude-opus-4.6` | 200K |
| `gemini-2.5-pro` | 1M |
| `gemini-3-pro-preview` | 1M |
| `gpt-5.4` | 400K |
| `gpt-5.3-codex` | 400K |
| `gpt-5.2-codex` | 400K |
| `grok-code-fast-1` | 128K |
<Tip>
GitHub Copilot is the most versatile provider — one subscription gives you access to models from OpenAI, Anthropic, Google, and xAI. Great if you want to switch between models for different tasks.
</Tip>
## Disconnecting
To disconnect your GitHub account, go to **Settings**, find the GitHub Copilot provider, and click **Disconnect**. Your OAuth tokens will be immediately deleted from your machine.
description: "Use your Qwen Code account to power BrowserOS"
---
Connect your Qwen Code account to BrowserOS and access Alibaba's coding models with up to a **1 million token context window** — the largest of any provider we support. No API keys needed.
## Setup
**1.** Open BrowserOS and go to **Settings** (`chrome://browseros/settings`). You'll see the AI Providers section.
**4.** Once authorized, Qwen Code will appear as a provider in your settings. Select a model and start using it.
## Available Models
| Model | Context Window |
|-------|---------------|
| `coder-model` | 1M |
| `qwen3-coder-plus` | 1M |
| `qwen3-coder-flash` | 1M |
| `qwen3.5-plus` | 1M |
<Tip>
Qwen Code's 1 million token context window is ideal for tasks that involve long documents, entire documentation sites, or working across many browser tabs simultaneously — the agent can hold everything in context at once.
</Tip>
## Disconnecting
To disconnect your Qwen account, go to **Settings**, find the Qwen Code provider, and click **Disconnect**. Your OAuth tokens will be immediately deleted from your machine.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.