Refine the Advanced modal, prompt path display, review identity summary, reset-to-default workflow, and compact policy controls. Improve mobile footer and profile-card wrapping, make Advanced tool and skill rows directly selectable, and extend WebUI regression coverage for the updated behavior.
Add scoped restore for inherited profiles through the existing sparse removal path, and streamline Manage agents with separator rows and no redundant footer.
Remove redundant customization signals, use theme-primary colors for compact identity actions, simplify delegation guidance, and extend focused WebUI regressions.
Rebase new-agent drafts when scope changes, recompute Review paths, preserve authored creation metadata, and align client validation with backend prompt requirements.
Guard pending removals and stale manager transitions from discarding edits, let only the newest profile-catalog request own selector state, and hide stale rows during refresh.
Finish the themed, responsive Easy and Advanced presentation and exercise the real Alpine stores with controlled state and request-order regressions.
Resolve effective policy through inherited layers without letting empty upper configs shadow restrictions, and carry canonical tool identities through local and MCP execution.
Enforce required policy hooks and parent delegation checks at runtime, keep installed connector capabilities configurable while disconnected, and remove complete blocked-tool examples from rendered prompts.
Use the canonical tool prompts for concise catalog descriptions and add regressions for plugin activation, dotted local names, MCP calls, layered policies, and parallel subordinate paths.
Validate destructive requests and project-derived scopes at the Agent Editor API boundary, and reuse the running-profile guard for deletion.
Recheck creation and availability invariants inside the existing mutation boundary, preserve project availability atomically through its dedicated owner, and keep Project Edit and Settings catalogs from replaying stale or unavailable profile state.
Add focused regressions for confirmation, collisions, malformed project metadata, avatar failures, running profiles, and sparse project updates.
Add per-scope availability, duplication, active-profile status, and inline project selection while keeping the profile switcher synchronized with runtime state.
Reconcile unavailable profiles at explicit disable, deletion, project-transition, and context-creation boundaries; polish validation, prompt layout, deletion, and completion states; and extend focused backend and WebUI coverage.
Reuse the existing project/profile layers so Manage agents can switch between Global and project scope while sparse reads, writes, resets, and policy configs stay bound to the selected layer.
Make deletion scope-owned, preserve inherited profiles, and open Save & test chats in the exact selected scope.
Refine the Easy and Advanced surfaces with direct prompt editing, visible tool controls, compact transfer lists, per-row profile actions, and clearer review and removal states.
Reuse the shared compact model preset selector, improve responsive layouts and copy, and extend focused WebUI contracts for the polished behavior.
Add the Easy and Advanced editor modal, its single Alpine store, profile-switcher entry points and avatars, and the fresh-chat handoff after a successful save.
Restore focus across the shared modal stack and lock down the current interaction contracts as a stable baseline for the dedicated visual-polish phase.
Add dedicated Agent Editor APIs that read layered profile state and execute explicit change plans for metadata, prompts, model presets, tool policy, skill policy, and avatars.
Keep writes sparse and user-scoped, preserve unknown files and keys, avoid the destructive legacy save path and all model calls, and cover profile lifecycle, validation, provenance, and reset behavior.
Extend _skills with sparse allow/block rules and an explicit default for future skills, using the existing layered plugin configuration and skill-entry normalization.
Enforce the policy across discovery, loading, and chat activation while preserving loaded history, legacy hidden-skill behavior, and canonical name/path identity.
Add one project/profile-aware resolver for canonical local, plugin, and MCP tool identities.
Apply it to text prompts, Responses schemas, connector stubs, local execution, MCP invocation, and delegated agents while preserving the response and vision invariants owned by the runtime.
Merge layered profile metadata by authored field presence so missing keys inherit while explicit empty values clear inherited values.
Move the default specifics prompt to the canonical prompts directory and cover sparse metadata and prompt-only overrides.
Prefer cached process render metadata over mutable DOM-tail state when re-rendering warnings. Add focused regression coverage and document the replay contract.
Move files and folders into directories or the parent path from the shared Files surface, with guarded multi-item backend moves and clear drop feedback.
Keep drag gestures independent from row selection, preserve unrelated selections after moves, and add focused regression coverage.
Keep postfix slash commands resolvable when messages are sent, but stop opening the composer menu for trailing slash tokens such as filesystem paths.\n\nAdd regression coverage and document the picker behavior.
Default Responses turns with Agent Zero function tools to a required, single native call while preserving explicit caller overrides.
Keep parallel work inside Agent Zero's parallel tool so complete tool roots reach the parser deterministically.
Expose grouped memory tools and conditional vision support while applying prompt render variables before deriving native metadata.
Stop guessing complex schemas from prose and keep native descriptions to compact discovery text, reducing the duplicated Responses tool payload.
Stop scanning every global model preset for missing credentials when building Welcome banners. Keep readiness scoped to the effective model configuration so first-send setup remains in the deferred chat gate.
Add regression coverage for unused OpenRouter presets and document the boundary.
Introduce the x-icon custom element and migrate first-party WebUI and bundled plugin markup while retaining legacy Material icon compatibility. Defer icon-font readiness until the splash-installed document is parsed so Firefox does not leave icons transparent. Centralize chat message collapse handling, avoid false Show More controls on short user messages, and align grouped-message pagination styling. Update DOX and add regression coverage for the icon and collapse behavior.
Introduce a WebUI extension manifest and rewrite the asset bundler/server to support caller-supplied entry sets, extension-injected entries, and negotiated gzip. Key changes: add get_webui_extension_manifest() to helpers/extension, refactor Stop logic into stop_context() and reuse it from the connector `/stop` command, and add a new `/rename` slash command for chat naming. ui_bundler now accepts entry_urls, includes enabled extension entry files, raises the embedded text file size limit to 512 KiB, computes per-entry-set cache keys, and returns a bundle version based on the bundle signature. ui_server applies Starlette GZip middleware, adds routes (/, /index.html, /ui/index, /safe), serves splash/safe documents, injects the serialized webui_extension_manifest into the rendered index, and streamlines the /ui/asset-bundle endpoint with ETag and gzip handling. Also add multiple WebUI assets and fonts, new/updated plugin command YAML and Python command handlers, and corresponding tests covering bundling, commands, chat naming, and WebUI behaviors. Documentation (.dox.md) updated to reflect the new runtime contracts and guidance.
Refactor of messages.js to support lazy rendering.
Move chat rename functionality out of core and into a new _chat_naming plugin, and add a built-in _pin_to_top plugin for sidebar pinning. The chat-naming plugin includes API handlers, prompts, helper logic for selecting user messages and budgeted Utility Model calls, a python monologue_start extension, web UI (modal, store, config, sidebar action), and comprehensive tests. Removed the old core renaming extension and deprecated prompts/tests. Also added pin-to-top plugin files (API, helpers, webui store, tests/docs) and updated various AGENTS.md docs to reflect the new plugins and lifecycle clarifications. Minor UI/js tweak: reorder speak/copy buttons in browser tool handler and add a new webui message-window.js along with related webui/store/component updates and test adjustments.
Keep setup conversations brief and progressive so agents ask only for the next required detail.
Require the user’s exact Agent Zero URL instead of suggesting a common or default port.
Expose reasoning effort, reasoning summary, and answer verbosity in the Codex OAuth provider card, defaulting effort to high.\n\nNormalize provider settings and apply them to Responses requests without overriding explicit request values.
Keep Agent Zero wrapper examples out of native function descriptions and expose the response text schema.\n\nRoute concatenated tool envelopes through repair before the plain response hook can render them as final text.
Introduce a UI asset bundler and delivery flow: adds helpers/ui_bundler.py to discover same-origin HTML/CSS/JS (<=40KiB), build a versioned JSON bundle, and serialize it for an authenticated /ui/asset-bundle endpoint (handlers added in helpers/ui_server.py with gzip and ETag support). Add webui/sw.js service-worker to accept a preload bundle, populate a per-version cache, serve bundled text entries immediately, and perform runtime caching/cleanup for eligible assets. Update webui/index.html to fetch the bundle asynchronously, send it to the worker, register the worker by bundle version, inline a non-blocking startup splash, and convert stylesheets to non-blocking preload loads. Expose extension readiness from webui/js/extensions.js (webui-extensions-loaded) so startup waits for Alpine and HTML extension loading. Add tests covering bundler behavior, service-worker expectations, and startup ordering.
Introduce a /stop API handler (api/stop.py) and its DOX to cancel an AgentContext run without deleting the context; it clears pause state, progress and logs an info step. Add tests for stopping behavior, chat working animation, and sidebar timestamp/spacing (tests/*). Update helpers/git._format_git_timestamp to emit UTC timestamps without a timezone suffix and add a test for it. Implement stop-related UI/UX: input-store.js gains a stop state, activateSendButton(), and stopAgent() to call /stop; chat-bar-input.html updates the send button markup, aria-label and stop styles. Update sidebar/chat list CSS to add the working-bubble animation, adjust chat row layout and action-button visibility, and left-sidebar/bottom styling (nowrap timestamp). Modify messages.js to hide kvps.finished from display and complete the active process group when finished. Minor welcome-composer and documentation updates to reflect these behaviors.
Place the internal Browser proxy fields in a native disclosure and keep its styling borderless. Refresh the guide screenshot and cover the config markup.
Add project-scoped HTTP and SOCKS proxy settings for the internal Docker browser, including bypass and optional authentication. Pass them through Playwright's native proxy option, restart active Browser runtimes when they change, and update regression coverage and user documentation.
Normalize the legacy reasoning_effort field at the Codex Responses proxy boundary so it cannot reach the upstream endpoint in an unsupported shape.
Preserve an explicit native reasoning object and cover alias conversion and precedence with regression tests.
Keep response tool calls at the top level so they can end the parent message loop instead of forcing an unnecessary follow-up turn.\n\nDocument the parallel constraint and cover both runtime rejection and prompt guidance.
Require verified window focus before target-bound typing and report remote computer-use receipts from observed evidence.\n\nGuide agents through scoped snapshots and focus verification while refusing window presses and identical failed-action retries.
Configure Cerebras as a native LiteLLM provider using Chat Completions and its live model catalog.
Expose Cerebras in onboarding with API-key guidance, a production default model, and a bundled logo, with focused provider and UI coverage.
Keep fenced examples readable in prompt Markdown while removing only JSON fence markers from the final assembled system prompt. Cover all bundled profiles and preserve non-JSON fences.
Explain that fenced examples are documentation-only and make the canonical response example match the required wire format. Add focused guardrails for the rendered instruction and unfenced example.
Guard partially parsed tool arguments while streaming and render both text and legacy message response fields. Keep live response logs synchronized without allowing incomplete code arguments to raise.
Route native Responses output text through the normalized response-tool executor instead of ending the monologue directly. Preserve active goal overrides and Responses state cleanup, wait for complete native streams, and reject empty response payloads.
Add responsive shell styling for a 250px desktop sidebar slot that yields to the mounted left panel and collapses on mobile.
Reserve the welcome composer's final height while nested input components hydrate, and document that component-local layout contract.
Require complete standalone text requests for execution while accepting supported text-tool formats. Route fenced and structurally broken tool intent through the existing misformat repair path so streamed chats do not remain in a thinking state.
Raise RepairableException when response lacks a top-level text or message string. The existing recovery path now warns the model to correct the call instead of exposing a KeyError, while preserving legacy message arguments.
Serve a bounded tail snapshot and cursor-based older pages for interactive clients. Preserve complete replay for clients that do not request history hints.
Return WebUI navigation after the initial document commit and align the socket timeout with browser command deadlines.
Remove forced viewport nudges and reject cropped or mismatched screencast frames so tab changes and pointer movement do not stretch the viewport.
