This PR keeps the Browser Agent runtime behavior as-is and only adds in the model-preset option for browser runs (highly requested by our users).
The Browser Agent can now use either:
- the effective Main Model from `_model_config`, or
- one saved `_model_config` preset dedicated to browser tasks
- this PR brings back LLM customization for Browser Agent plugin, but without over engineering. Model presets-only, not custom provider + LLM, like we have in Email Integration.
- created a separate `browser-agent-store.js` page store to remove JS from within x-data in the HTML markup of main.html
Introduce the builtin `_a0_connector` plugin that lets the host-side
A0 CLI connect to Agent Zero over authenticated HTTP and `/ws`.
This adds connector capability discovery, chat/context lifecycle
endpoints, log streaming, and the remote text editing, code execution,
and file tree bridge used by the CLI workflow.
Add shared transport-level control commands so Telegram, WhatsApp, and
email threads can manage the active chat directly.
- add a shared integration command helper for /project, /config, /send,
and /queue send
- wire native command handling into Telegram and WhatsApp sessions
- expose Telegram control commands through bot command routing and update
transport docs
- add email thread command handling for existing A0 email conversations
- add an optional per-handler email conversation preset backed by model
presets in the email settings UI and default config
- document the new transport control flow across Telegram, WhatsApp, and
email
Redesign the three messaging integration panels with a clearer, more guided
setup flow and polished user experience.
- simplify the email panel by surfacing the essentials first, moving
advanced scheduling behind Advanced, and making connection checks more
visible
- redesign Telegram and WhatsApp as step-based setup flows with clearer
status states, safer access warnings, richer test feedback, and more
responsive layouts
- add shared plugin-settings wizard footer support, extract WhatsApp state
into its own store, and align test-connection messages with the new UX
ux: ease Email connector setup and refresh copy
- Redesign the Email connector settings around a guided first-run flow with a clearer empty state, provider presets, and much friendlier copy
- Move server, routing, and scheduling power-user controls into an `Advanced` section while keeping the existing config model compatible
- Improve connection-test messaging, add Exchange inbound validation, and refresh the dashboard Email card copy while keeping the card visible
- Verify the updated setup flow in the browser on desktop and mobile
update and simplify x-data based on established frontend patterns
Update 10_discovery_cards.py
further polishing and first-draft no-click model for email and telegram
update whatsapp
Update telegram-config-store.js
Added a builtin plugin that you can open from the chat input plus button menu, which shows you a list of skills that you can directly activate in the current context/project.
Default configs allow users to start over with skills already active, instead of losing time and tokens asking Agent Zero to do it.
Update prompt for manual skill selector
add thumbnail for _skills builtin plugin
- Add FAISS index integrity checks using a SHA-256 sidecar (`index.faiss.sha256`) and write hash on save.
- Harden `memory_load` filter evaluation with input validation (allowlist + length cap) and `simple_eval(..., functions={})`.
- Add score-preserving similarity search and use real relevance scores in consolidation (including best-score dedupe by memory id).
- Prevent utility-model context overflows by truncating memorize input history for fragments and solutions.
Restore main.communication, main.solving, main.tips and tool.response, which made the model dumber. For some reasons the drawback was more visible with frontier LLMs.
restore builtin plugins and agent0 profile
Add the always-enabled `_discovery` plugin to turn the welcome screen into a discovery surface for the Plugin Hub and A0 integrations.
Includes a hero card plus Telegram, Email, and WhatsApp feature cards, with persistent dismiss/restore state, CTA routing to plugin config screens, and self-contained placeholder artwork. Implemented entirely through the existing WebUI extension mechanism with no core welcome-screen changes.
stores cleanup
layout polish and onboarding integration
Move feature card titles beside thumbnails for better space efficiency
and visibility. Restructure card markup and styles to support a fluid
grid layout and horizontal alignment.
Integrate discovery cards into the final onboarding step via a new
'onboarding-success-end' extension point, ensuring new users see
extension opportunities immediately after setup.
Hide discovery cards on the dashboard while the missing API key
onboarding banner is visible to reduce UI noise and user confusion during initial config.
update discovery card initialization and loading logic
Enhance the discovery store to fetch cards from the API, improving the dynamic loading of discovery cards based on user context. This change optimizes the user experience by ensuring relevant cards are displayed immediately after onboarding and when modals are closed.
And on top of that, there's a proper backend for these new cards.
Promote the a0_small prompt work into the shipped default stack.
Token count for default prompt, accounting for tools, plugins, secrets placeholders, inactive project, etc: 2996 tokens.
- migrate compact prompt fragments into core prompts, plugin-owned prompts, and the agent0 overlay
- remove the obsolete a0_small profile and rename the tool-call knowledge reference to a generic framework file
- keep a small set of high-value JSON examples while preserving key guardrails for tool names, tool args, and method-style calls
- bake balanced conciseness into default response behavior without changing the initial greeting
- drop the call_sub prompt-side loader and keep call_sub guidance self-contained
- restore essential secrets/security guidance, preserve inactive-project messaging, and rebalance the A2A prompt
- add a regression test that verifies the assembled default agent0 prompt stays under the token budget and retains critical guardrails
Ensure printed output and HTML logs are safe by importing and applying sanitize_string, opening log files with utf-8 and errors='replace', and sanitizing text before writing. Add tests to verify lone surrogate characters are replaced and that logging won't crash on invalid Unicode. In the plugin installer UI, introduce POPULAR_PLUGIN_MIN_STARS and centralize popularity checking in _isPopularPlugin, using it for filtering and counts.
Add a shared safe markdown pipeline for plugin READMEs and docs.
- vendor DOMPurify and introduce a shared safe-markdown helper
- centralize GitHub README link/image rebasing, including repo routes like `releases`
- sanitize rendered HTML before all plugin-related x-html sinks
- apply the shared renderer to Plugin Hub README, installed plugin README, and markdown modal docs
- preserve target/rel handling for external links
Remove the scan queue mechanism that serialized plugin scans. Each scan now runs in its own temporary chat context immediately upon request, allowing multiple scans to execute in parallel. Update UI to reflect that scans are no longer queued and remove the "queued" state tracking from store and API.
- Add model switcher component for chat input with progress display
- Enhance model config store with active preset/model retrieval
- Show agent progress as ghost text in chat input placeholder
- Add agent artifact patterns to .gitignore
Remove force parameter parsing and passing from _fetch_index method in PluginInstall API handler. The force refresh functionality is now handled client-side through cache-busting headers and timestamp parameters added in previous commit (c7a9836).
- Add force parameter to plugin index fetch with cache-busting headers and timestamp
- Add openIndexView and reloadIndex methods to pluginInstallStore for explicit refresh
- Add request sequence tracking to prevent race conditions in concurrent index loads
- Move models summary state from component to store with loading/caching support
- Add refreshModelsSummary, ensureModelsSummaryLoaded, and modal
- Update default backup path from /a0/tmp/self-update-backups to /root/update-backups in self_update_manager.py, helpers/self_update.py, and documentation
- Move aiogram from global requirements.txt to plugin-local requirements for _telegram_integration
- Add ensure_dependencies() helper that installs aiogram on-demand via uv pip install
- Add has_aiogram() check to avoid
Launch Chromium with --no-sandbox alongside --headless=new so the browser agent
runs in containers without sandbox failures (temp profile missing bug).
Factor LLM workarounds into helpers: sanitize structured JSON before browser-use/Pydantic parsing, and normalize OpenRouter requests that use strict json_schema (lighter json_object path plus schema hint in messages,
relax strict tool flags so providers like Anthropic don't error out).
- Rename presets: "Efficiency" → "Max Power", "Intelligence" → "Balance", add "Cost Efficient"
- Update preset models: use Claude Opus 4.6, Sonnet 4.6, Kimi K2.5, GPT-5.4-mini/nano, Gemini 3.1 Flash Lite
- Adjust context lengths and vision capabilities across presets
- Pin chardet<6 to avoid import warnings from requests when unstructured is installed
- Replace settings-updated listener with modal-closed event
Move the browser model instantiation logic out of `_model_config` and into `_browser_agent` to properly invert the dependency direction.
This prevents the always-enabled `_model_config` plugin from taking a hard dependency on the optional `_browser_agent` module, ensuring it won't break if the browser module is removed or replaced.
