Summarize the provider evidence sweeps into a scored Agent Zero tool-efficiency chart.\n\nDocument the scoring rubric, ranked provider/model results, recurring failure clusters, applied prompt/skill improvements, and follow-up candidates while keeping the raw EVIDENCE files untracked.
Update the computer-use skill so agents tell users to run /computer-use rearm when the desktop-control backend reports COMPUTER_USE_REARM_REQUIRED, instead of asking them to manually switch modes.
Allow the Linux Desktop state collector to report a healthy canvas when XFCE has no active application window, as long as the display, visible windows, and screenshots are available.
Document the readiness rule in the linux-desktop skill and add regression coverage for the bare-desktop active_window=null case.
Track computer-use CLI status, last error, and restore-token presence in connector metadata so stale Free Run settings are no longer treated as ready.
Materialize CLI-provided screenshot artifacts through Agent Zero's file helpers, stop dispatching computer_use_remote actions when metadata already reports rearm required, and teach the skill to give backend-agnostic rearm guidance without screenshot or vision fallbacks.
Standardize multi-action tools around tool_args.action while keeping parser compatibility for older tool/args, tool_name:action, and method-shaped requests. This keeps new prompts clean without breaking agents that learned the previous dialect.
Move A0 connector remote execution/file tools into stable standard prompts, make remote targeting independent of the active chat context, and skill-gate beta computer-use remote so it no longer weighs down the always-on tool list.
Align text editor, scheduler, skills, office artifact, memory, notify, and browser prompts/tools around the canonical action contract. Add scheduler update/timezone handling, skills_tool read_file, text editor patch coverage, and fixes for memory_forget, behaviour_adjustment, and code execution progress warnings.
Reduce default prompt pressure by compacting browser and scheduler prompts into skill-backed manifests, shortening skill catalog descriptions, and pruning noisy framework knowledge. Remove obsolete connector prompt stubs and root tool-call knowledge examples.
Tests: conda run -n a0 pytest tests/test_a0_connector_prompt_gating.py tests/test_tool_action_contracts.py tests/test_task_scheduler_timezone.py tests/test_text_editor_context_patch.py tests/test_tool_request_normalization.py tests/test_office_document_store.py::test_odf_is_advertised_and_docx_remains_explicit_compatibility tests/test_office_document_store.py::test_document_artifact_accepts_method_alias_for_ods_create tests/test_skills_runtime.py tests/test_default_prompt_budget.py::test_a0_small_profile_removed_and_prompt_text_generic -q
Tighten the final onboarding discovery cards so the setup suggestions take less vertical space.
Add a compact CLI Connector card with macOS/Linux and Windows install commands plus a small A0 terminal preview asset.
Default Bring Your Own Browser mode to the existing browser profile while exposing a clean Agent profile option in Browser settings with a clear warning for existing-profile access.
Forward the selected profile mode through the connector browser runtime, tolerate legacy config modules and old saved configs, and update regression coverage for the new payload shape.
Stop and remove the old a0_office_collabora supervisor program during Docker self-update preparation, before stale Collabora runtime paths are deleted. Add a narrow repo-side retirement hook so older bootstrap managers can clean the checked-out runtime without reinstalling desktop packages during health checks.
Harden XFCE desktop startup with explicit XDG config/data directories so upgraded Desktop sessions avoid the failsafe-session path after the Collabora-to-LibreOffice transition.
Add a screenshot-led guide for the guided onboarding wizard using Agent Zero API as the example setup. Link the guide from the docs hub, quickstart, and installation setup flow, and include optimized screenshots for choosing Cloud, selecting a provider, choosing models, and reaching the ready state.
Introduce a guided Cloud versus Local first-run modal with provider selection, account connection, model picking, and a ready state.\n\nAdd the reusable discovery auto-modal trigger, chat-created startup checks, onboarding-owned provider presentation metadata and assets, OAuth affordances, local provider guidance, and model-search hardening.\n\nKeep runtime provider data centralized while preserving onboarding-specific copy, logos, and docs links in the onboarding plugin.
Update onboarding.html
Update onboarding.html
Configure Ollama Cloud as an OpenAI-compatible chat provider with the hosted API base and model listing endpoint.\n\nAdd a focused provider config test so the integration stays key-required and keeps the expected /models endpoint.
Refresh README, quickstart, and the docs index around Browser, Desktop, A0 CLI, projects, memory, skills, profiles, and model presets.
Add optimized scoped screenshots for Web UI, Browser, Desktop, and CLI workflows.
Trim architecture-heavy developer pages toward DeepWiki handoffs so local docs stay focused on practical user guidance.
Save a static JPEG for each Browser tool call in the chat history folder and render that immutable image in transcript screenshot previews. Keep live Browser surface attachment available through stored browser/context metadata, and ignore generated Playwright CLI artifacts.
Attach the Browser canvas to active Docker sessions by returning an initial snapshot on subscribe and preserving valid frames through state-only updates. Route Markdown document opens through the right-canvas Desktop editor instead of the legacy office modal. Skip automatic office document response affordances for subordinate agents so delegated reviews keep their actual content.
Replace the combined A0 CLI remote workflow skill with separate text-editor and code-execution remote skills, update tool stubs to load the matching per-tool guide, and keep computer-use remote scoped to desktop control. Add prompt-gating coverage for the per-affordance skill split.
Add a protected connector endpoint for reading and updating the Browser plugin runtime backend so the A0 CLI can switch between Docker browser and Bring Your Own Browser mode. Keep legacy host_when_available values normalized to host_required, move the host/container setting to the top of Browser settings, and cover the config normalization path.
Remove the ambiguous Use host when ready option from the Browser plugin settings and present the host-required path as Bring Your Own Browser. Add concise Chrome/Chromium remote-debugging guidance, normalize legacy host_when_available values to the BYOB setting, and make missing host-browser connector setup a repairable error with regression coverage.
Move URL normalization into Agent Zero-owned Browser helper code and expose the content helper's required API contract from the shared asset. Normalize host-browser open/navigate payloads before they cross into the connector, including nested multi actions, and add regression coverage for helper payload delivery and URL edge cases.
Make the Browser plugin the source of truth for browser-page-content.js by attaching its source and sha256 to host-browser operations when the CLI has no matching helper hash. Store the helper hash in connector metadata and cover the routing/ensure path in tests.
Store and surface host-browser preparation and CDP endpoint metadata from A0 CLI.
Let Browser runtime prepare candidate CLIs before the first action, and keep host-required errors more actionable.
Simplify Host Browser settings language and document the Chrome remote-debugging consent flow.
Integrate host-browser routing into the existing Browser tool. Store connector host-browser metadata, add pending browser op resolution, select connector runtimes from Browser settings, enforce host-content privacy policy, support automatic host preparation, and document the A0 CLI host-browser flow.
Run a best-effort uv cache clean when the durable self-update manager consumes an update request. Cover uv-present, uv-missing, and cleanup-failure paths with focused tests, and document the new self-update step.
Delete the Browser plugin's injected bottom-action button so it no longer appears under the chat input while preserving the rest of the Browser surface entry points.
Update the browser regression coverage to assert the chat action stays absent.
Remove stale runtime directories and expand retired package coverage for startup/self-update cleanup.
Discover installed collaboraoffice* split packages dynamically so future package-name changes are still purged, and extend Office cleanup tests for the legacy /opt paths, known leftover packages, idempotency, and marker rerun behavior.
- Replace the two-step settings nav with a sticky accordion that tracks active sections
- Restyle the settings rail with opacity-based active state and hash-aware opening
- Reinitialize and clean up API example Ace editors across modal reopen cycles
- Preserve modal html classes and center settings loading/error states across the full modal body
Use /a0/tmp/playwright as the Browser plugin Chromium cache and Docker install target while preserving full Chromium installs.
Add startup migration cleanup for retired usr Playwright caches, update Browser status/runtime references and docs, and cover migration behavior with focused regressions.
Allow display_time=0 to create persistent grouped toasts that remain until dismissed or replaced.
Show immediate grouped Preparing download and Downloading feedback for backup ZIPs and file-browser directory/bulk ZIP downloads, with error replacement and focused static coverage.
Store remote tool metadata through a dedicated hello path, bind a declared context id to the websocket SID, and return acknowledged remote tool state so clients can verify gated tools such as code_execution_remote are visible to the active chat.
Use the Settings modal action order across plugin settings and related edit/create modals so primary actions appear before Cancel while preserving existing handlers and state logic.
Keep the project creation modal focused on basic project details and Git cloning, without loading model config data. Move project model selection into a collapsed Advanced Settings accordion on the edit screen, and reduce the project LLM UI to a global preset selector plus the existing tune-icon preset editor shortcut.
Track active Desktop runtime preparation in the _desktop hook, expose installing status through Desktop session status, and have the Desktop frontend poll with a neutral install message instead of showing missing dependencies while packages are still being installed after an update.
Run Office and Desktop apt operations through a shared in-process retry guard so startup/self-update hooks wait out transient apt locks instead of failing early. Include LibreOffice runtime packages in Desktop preparation because Desktop status and Writer/Calc/Impress launch paths require soffice, and cover both behaviors with regression tests.
Rename Office skills to product-neutral Writer, Calc, Impress, and document-artifact names while removing the visible legacy directories. Tighten connector list/delete behavior to the enabled catalog and prevent deletion of built-in plugin skills; also surface invalid skill YAML instead of silently accepting it.
Keep _office focused on document artifacts, Markdown sessions, LibreOffice-compatible file actions, and document persistence. Route binary document editing through explicit Desktop requests instead of cold-opening the live Desktop surface from artifact results.
Add the built-in _desktop plugin as the owner of Xpra/Xfce lifecycle, /desktop route installation, Desktop state, session APIs, surface registration, and the linux-desktop skill. Leave _office with explicit compatibility facades and self-update delegates so users coming from 1.10 through 1.13 keep their runtime cleanup path.
Introduce the shared surfaces frontend service and stylesheet so Browser and Desktop can register docked or floating live UI without special cases in modals.js. Update Browser and right-canvas integration to preserve active viewers across canvas/modal switches and avoid creating blank tabs unless explicitly requested.
Freeze pyreqwest-impersonate at 0.5.3 so duckduckgo-search installs the nearest older wheel-backed release. The newly published 0.5.5 release is source-only and fails Docker builds without cmake while compiling boring-sys-imp.
Reload LibreOffice-backed Writer, Spreadsheet, and Presentation documents after artifact edits by closing and reopening the visible document window instead of relying on a canvas repaint.
Cold-start Office canvas sessions from tool results, guard null document headers during initial render, and avoid terminating rehydrated desktop processes from temporary manager instances.
Unify Markdown and LibreOffice document handling around an active-file header in both canvas and modal views. Move creation into a shared + New menu, place Save beside file actions, and expose Rename/Close File from the document dropdown. Update the README with the refreshed Office and Browser screenshots plus the new Office UI behavior.
Remove Time Travel's floating modal behavior so it uses the standard centered modal shell and shared backdrop like Settings. Keep the modal-only sizing classes on the component document and stop exempting Time Travel from backdrop rendering.
Refine the Linux Desktop skill so agents distinguish shell prompts from target CLI prompts before sending natural-language input.
Use a generic nested CLI-agent launch pattern with TARGET_CLI and optional FALLBACK_CMD instead of Codex-specific instructions, and add canvas setup assertions to keep the guidance generic.
Import the chat input history navigation from neurocis PR #1573 while keeping the change scoped to the chat input files.
Adjust Down navigation so it only triggers when the caret is collapsed at end-of-text, preserving normal textarea movement from the start of multiline input.
Adds the explicit browser:screenshot action that writes JPEG/PNG files for vision_load, extends agent-callable Browser input actions, and documents the explicit vision workflow.
Adds the browser-forms on-demand skill and regression coverage for dispatch, runtime screenshot files, ref point resolution, upload path normalization, prompt discoverability, and label-wrapped form controls surfaced by the chat-driven E2E.
Keep Browser modal activation passive when switching from Desktop by reusing existing Browser sessions instead of creating a blank tab on viewer subscribe.
Add a Focus mode control to the Browser modal header matching Desktop's fullscreen/restore behavior.
Cover the passive subscribe path and Browser modal focus button in regression tests.
