[pull] main from agent0ai:main#4
Open
pull[bot] wants to merge 1323 commits into
Open
Conversation
Remove the Collabora/WOPI runtime and route stack, including the old status APIs, proxy helpers, bootstrap extensions, and WOPI store tests. Add the Markdown-first document store, LibreOffice status/conversion helpers, LibreOfficeKit session bridge, and reusable Xpra virtual desktop gateway used by the new document runtime. Update image and self-update bootstrap paths so existing containers can acquire the LibreOffice, XFCE, Xpra, and desktop-control dependencies through the normal install hooks instead of an ad hoc manual install.
Rework the Office canvas into the Desktop surface, with Markdown editing for text documents and official LibreOffice/Xpra sessions for DOCX, XLSX, and PPTX. The panel now presents Desktop-oriented actions, named header buttons, persistent session tabs, adaptive modal/canvas sizing, and fast client-side Xpra frame fitting during resize. Stop auto-opening the canvas from document tool results, hide the canvas on mobile-width layouts, and emit resize lifecycle events so embedded desktop surfaces can pause expensive work while the user drags.
Add a linux-desktop skill that teaches Agent Zero how to operate the persistent XFCE/Xpra desktop through desktopctl.sh, including app launch, focus, click, typing, and stable folder entry points for Workdir, Projects, Skills, Agents, and Downloads. Add a Calc cell-edit helper that opens a workbook through the visible LibreOffice Calc desktop session, updates a requested sheet cell, saves, and verifies the XLSX on disk. Expand the Office canvas setup tests to cover Desktop branding, Xpra package requirements, resize behavior, mobile canvas gating, and the new skill helpers.
Teach the browser page-content helper to traverse open shadow roots and assigned slot nodes when collecting text, rendering list/inline children, and resolving selectors. This lets Agent Zero inspect modern component-heavy pages more accurately without depending only on light-DOM textContent. Bump the injected helper version so existing browser contexts can refresh to the new DOM traversal behavior.
Make Desktop canvas and modal handoffs resize the live Xpra viewport deterministically by syncing the visible frame, making backend resize requests authoritative, unloading hidden iframe clients, and guarding Xpra HTML menu callbacks when the menu is disabled. Also forwards wheel events from the embedded Xpra canvas so mouse and trackpad scrolling reach the Linux desktop session.
Make Markdown the first-class document workflow in the office skills and state the Desktop/LibreOffice path as opt-in for GUI or binary Office work. Remove passive Browser canvas auto-opening from tool results; Browser result handling now only syncs an already-open Browser canvas, while explicit user buttons can still open the canvas or modal. Add regression coverage for the no-auto-open policy and Markdown-first skill guidance.
Add an explicit close button to the right canvas toolbar, next to the undock control, and cover its label, handler, and ordering in the canvas regression test. Treat document_artifact tool_args.method as an action alias so calls like method=create with format=xlsx create workbooks instead of falling back to LibreOffice status. Add regression coverage for the exact XLSX creation shape.
This reverts commit 7c59ac9.
Keep Office document artifacts from auto-opening the canvas while adding plugin-owned Download and Open in canvas message actions. Add format-specific skills for Markdown, Word, Excel, and presentation workflows, and clarify the startup-warmed Desktop runtime remains visually opt-in.\n\nCover the Excel method=create path, Markdown-first/no-auto-open policies, response affordance copy, document action buttons, and Desktop bootstrap with focused regressions.
Sync document_artifact results into an already-open Office canvas without auto-opening a closed canvas. Generate PPTX artifacts through the Office plugin writer so PowerPoint decks open in Impress with visible multi-slide content. Add focused regression coverage for canvas sync behavior and PPTX slide creation.
feat(browser): multi-tab awareness + modifier-key click
Render Browser tool Screenshot KVPs as clickable live thumbnails that open the Browser canvas while preserving the existing lower-row Browser action.\n\nAdd a lightweight websocket snapshot endpoint for existing browser runtimes and keep preview frame memory bounded with revocable object URLs.
Fix annotation panel stacking so draft popovers render above the annotations recap.\n\nAllow the annotations recap tray to float within the browser stage by dragging its header, with bounded positioning and cleanup when annotations are cleared or the browser surface unmounts.
Expose extension deletion from the Browser internal settings page and keep the compact Browser dropdown focused on quick enable/install actions.\n\nAdd a guarded uninstall API that only deletes Browser-managed extension folders, updates enabled extension paths, refreshes the settings UI, and covers managed versus external paths with regression tests.
Add a Time Travel entry directly under Files in the sidebar dropdown and route it through the existing modal. Stop Time Travel from registering or mounting a right-canvas surface, and keep modal refresh tied to the modal state.
Bridge copy, cut, paste, and common edit shortcuts from the Browser modal and canvas screenshot surface into the Playwright runtime while preserving native clipboard behavior for Agent Zero UI fields. Add websocket and runtime clipboard handling with regression coverage for frontend shortcut routing, paste fallback, and viewer input dispatch.
Move Remote Link and Space Agent into the sidebar dropdown while removing their right-canvas rail actions. Rename Scheduler-facing UI to Tasks and collapse Chat Actions behind a persisted dropdown accordion.
Make the Desktop iframe explicitly focusable and re-arm Xpra keyboard capture on load and click so typed input reaches the remote session reliably.\n\nAdd regression assertions for the Xpra keyboard bridge contract.
Make the embedded Xpra Desktop use the browser cursor as the only visible cursor by suppressing the shadow pointer overlay and pointer-position renderer without blocking pointer input. Prefer the active Office host iframe when choosing the Desktop frame, then force resize recovery during modal-to-canvas docking so the Xpra desktop, window, and canvas refill the canvas after handoff.
Route binary Office documents through the persistent Desktop surface while keeping Markdown in the custom tabbed editor. Harden Xpra clipboard bridging and explicit clipboard flags so host paste can reach the desktop session. Align XFCE and LibreOffice profile paths with Agent Zero locations: downloads for wallpapers, configured workdir for default saves and the Workdir shortcut, and trusted metadata for generated launchers.
Route DOCX, spreadsheets, and presentations exclusively through the Xpra desktop LibreOffice session. Keep the custom canvas path focused on Markdown source editing, remove the old dashboard/preview/native LibreOfficeKit code, and update tests and runtime package declarations to match the new Office surface.
Expose a directory-only Download ZIP action in the file browser menu and make folder downloads use a stable .zip filename from the existing download endpoint.
Add a pencil action beside Save that reuses the existing file browser rename modal for open Office documents. Preserve document metadata after filesystem renames, retarget active LibreOffice desktop sessions to the new path, and cover the rename flow in Office regression tests.
Adds a branded file-browser toolbar with current-folder search, visible selection, and selection status. Introduces bulk copy paths, ZIP download, and delete actions backed by dedicated API handlers so selected files are processed as one browser operation.
Install a curated README into generated Agent Zero Desktop sessions so the Xfce workspace explains the habitat concept, credits the open-source foundations and Jan Tomášek, and gives users Terminal commands for popular agent CLIs. Keep the README as an _office plugin asset and copy it into the Desktop profile during launcher preparation.
Detect openable Chrome extension UI pages from manifests and expose resolved chrome-extension URLs to the Browser UI. Render an Open button in the compact Browser extension dropdown and cover manifest UI metadata with regression tests.
Show hidden files by default in Thunar-backed Desktop sessions while preserving existing file manager profile settings. Hide the default Xfce Mail Reader and Web Browser helper entries from the Applications menu through local XDG overrides, and cover the generated Desktop profile artifacts with targeted tests.
Allow users to disconnect their OpenAI account by clearing stored ChatGPT OAuth tokens while preserving unrelated auth data. Fetch and normalize Codex usage windows, then show remaining percentage and reset timing in the OAuth settings UI. Add focused tests for usage parsing and disconnect cleanup.
Keep model config markup focused on setup and let the store own settings-object lifecycle hooks. This initializes UI-only kwargs fields after scope loads while preserving dirty tracking for reset/default changes.
This reverts commit 46112c9.
Generalize benchmark lessons into prompt guidance for reading specs and tests first, making narrow edits, verifying exact artifacts, cleaning temporary work, recovering from tool failures, and avoiding success claims after partial output or timeouts. Update the developer profile to skip unnecessary interviews for clear bounded tasks while keeping structured clarification for broad mandates. Add code-execution prompt guardrails for long-running and exact-output work without encoding benchmark-specific answers.
Raise bundled defaults and fallback timeout tuples for normal and output runtimes so builds, installs, servers, tests, and training jobs have room to stream or poll without premature timeout. Document the long-running work behavior while keeping normal command execution bounded and directing extended work toward output polling.
Filter passive fragment memories before consolidation so action history, temporary artifacts, local runtime coordinates, and personal absolute paths do not get saved automatically. Tighten memory utility prompts toward durable preferences, stable project facts, recurring constraints, and reusable solutions while keeping explicit memory_save behavior unchanged. Add focused tests for fragment quality gating.
From testing and benchmarks, telling the agent what memory_forget is for more explicitly helps with memory consolidation, which lacks part of the awareness about stale (duplicates are usually well-covered).
Move the concrete verification and final-report guidance into the default solving prompt so generic Agent Zero carries the coding-harness habit. Shrink the developer profile copy to a profile-scale reminder that extends the core discipline without duplicating a long checklist.
Add prompt-only guidance that treats memory timestamps as soft recency signals instead of hard TTLs. Encourage newer/current facts to win for mutable conflicts while preserving old durable preferences or project facts unless current evidence shows they are stale, false, superseded, duplicated, or unwanted.
Send the normal _code_execution timeout group to connected A0 CLI sessions for terminal, Python, Node.js, input, and output remote execution. Size the plugin-side wait budget from the selected timeout group with a small transport grace period and update the tool prompt to steer long-running work toward output polling.
Expose the Core Agent Zero version from both connector capabilities and connector_hello so A0 CLI clients can warn when they are older than the connected server.
Add support for including a top-level AGENTS.md in a project's system instructions while keeping backwards-compatible defaults. Introduces include_agents_md project metadata (defaults to true), normalization and save logic, and helper functions to discover and format AGENTS.md and other instruction files into the system prompt. Updates build_system_prompt_vars to assemble instruction parts, adds UI checkbox in project edit form, normalizes defaults in the projects store, and adds tests for the new behavior. Also documents the compatibility rule in AGENTS.md and adds a small prompt rule reminder.
Add a shared provider-registry-backed OAuth status summary for the status API and discovery cards. Redesign the OAuth settings modal around provider rows, inline usage, provider details, and account-backed model slots while keeping legacy Codex compatibility fields intact.
Load OAuth account providers from the status API on the path, cloud, and setup steps instead of relying on a Codex-only strip. Support provider-specific setup fields, device-code and browser callback flows, model loading by provider, the local DeepSeek icon, and the polished account heading copy.
Disable LiteParse OCR automatically for PDFs at or above the configured page threshold, independent of sampled text density. Add adaptive index chunk sizing for large extracted documents so first-run document_query calls avoid spending the full batch timeout embedding thousands of small chunks. Update the settings UI, README, dependency hook, and regression tests for the new behavior.
Stop forcing the bundled Office, Desktop, and Editor plugins on by setting their manifests to always_enabled: false. This restores normal plugin activation controls while preserving explicit manifest intent.
Reuse the DocumentQueryStore per chat context so repeated document_query calls can see an existing vector DB instead of re-parsing and re-embedding the same document every time. Add a regression test that proves a second store lookup in the same context reuses the indexed document while a separate context stays isolated.
Flatten dropped or selected folders into ordinary file attachments while preserving basename display and existing multi-file upload behavior. Make the composer attachment menu actions open their hidden file inputs directly, and label them as Attach files and Attach folder.
Update the Browser tool prompt and plugin DOX so agents list and activate existing tabs by URL or title before opening new host-browser tabs.
Return users to their original requested page after login, with robust same-origin validation to prevent open redirects. Co-Author Agent Hero <agent-hero@neurocis.ai>
…irects Co-authored-by: Agent Hero <agent.hero@neurocis.ai>
Bound _a0_connector context snapshots and live stream reads so long chats are replayed in small WebSocket frames instead of one oversized payload. Replay remaining historical entries as connector_context_snapshot pages before switching to live connector_context_event streaming, and preserve LogOutput.end cursor semantics throughout.
Add connected-account provider dropdowns for Main and Utility model slots in OAuth settings. Keep model search and selection scoped to each slot's chosen provider so multiple connected OAuth accounts can be used independently.
[feat] Adds login redirect after authentication
Remove the static OAuth API-key placeholder from provider defaults and gate the runtime dummy key on provider connection status. This keeps unconnected OAuth providers blank in API-key surfaces while preserving the local proxy shim for connected account-backed providers. Update OAuth docs and regressions for the new contract.
Move device-code, manual callback, and setup controls into the provider row that started the OAuth flow so pending state stays anchored to its provider. Add static coverage and plugin DOX guidance for inline provider detail rendering.
Update the OAuth settings poller to wait for the provider interval, carry slow_down interval updates forward, and respect provider expiration times so GitHub Copilot device-code auth can complete after browser authorization. Dispatch the legacy device-login endpoint by provider_id and add regressions plus DOX guidance for provider-aware device polling.
Normalize active Remote Control URLs to same-origin values before adding them to CSRF allowlists, so Tailscale Funnel URLs with paths or trailing slashes can bootstrap tokens correctly. Allow WebSocket origin validation to trust only the currently active Remote Control origin, including Docker split-process tunnel service URLs, while preserving rejection for unrelated external origins. Add focused regression coverage for active Tailscale-style origins, tunnel-service origin lookup, and negative cross-origin cases; keep run_ui decorator re-exports compatible with existing CSRF tests.
Open the Editor file browser from the active project context before falling back to the configured workdir. Keep manual Editor launches on the empty start page instead of auto-creating blank Markdown files, while preserving explicit Markdown creation from the empty state. Add static regression coverage for both behaviors.
Move the Editor preview/source toggle into the left-side toolbar cluster so mode switching sits with editing controls. Add a dedicated right-side Save button and remove Save from the overflow menu, leaving the menu for rename and close actions. Cover the toolbar placement with a static regression test.
Add direct directory navigation to the file browser path bar and preserve the current listing when typed paths fail. Add a default-enabled setting to remember the last successful file browser directory, while keeping explicit open paths deterministic.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )