Make Telegram tool lifecycle hooks no-op for contexts that do not expose a raw data dict or do not carry the Telegram bot marker.

This keeps global tool extension dispatch safe for non-Telegram contexts, including Responses API tool-call regression tests, without changing behavior for real Telegram sessions.

Wrap FastA2A agent card generation so Agent Zero advertises streaming support on A2A endpoints by default.

Add focused regression coverage for the agent-card capability rewrite and proxy wiring, and update the helper DOX profile for the new wrapper.

Limit LiteLLM module mutation to documented global switches such as drop_params, while preserving configured LiteLLM kwargs as per-call options. Avoid freezing global kwargs into provider defaults so runtime settings remain current, and extend focused tests for drop_params, additional_drop_params, and provider default behavior.

- add a parallel wrapper and runtime for concurrent background tool calls
- run parallel call_subordinate jobs as child chats with visible subagent steps that match normal subordinate args
- render parallel child tool steps with normal tool-call args while keeping job handles in wrapper results and prompt extras
- group parallel child chats in the sidebar with persistent accordion and caret behavior
- add prompt, extension, DOX, and regression coverage

- document that parallel accepts full reply-shaped tool call objects and ignores planning-only fields
- steer prompt guidance toward one mixed batch for ready independent calls instead of splitting by tool type
- add normalization and prompt regression coverage plus matching DOX notes

Hide A0 connector remote tool prompts unless a connected CLI advertises the matching capability. Remote file access enables text_editor_remote, F4-enabled remote execution enables code_execution_remote, and supported enabled Computer Use that is not in rearm-required state enables computer_use_remote.

Apply the same gate to Responses API function-tool generation, move the prompt hook to the active tool-prompt extension path, and update connector prompt wording, DOX, and regression coverage.

Verified with:
- conda run -n a0 pytest tests/test_a0_connector_prompt_gating.py tests/test_default_prompt_budget.py tests/test_responses_architecture.py -q

The code execution tool runs commands inside TTY-backed shells (local PTY and
remote SSH). Commands like `git diff`/`git log` detect the TTY and pipe output
through a pager (more/less). These shells never receive interactive input, so
the pager blocks forever and spins at 100% CPU per process — on a 16-core host
5 pager processes pegged 5 cores for 8+ hours (#1697).

Disable pagers in both session types:
- LocalInteractiveSession: inject PAGER=cat / GIT_PAGER=cat into the TTY env
- SSHInteractiveSession: export the same in the initial shell command

`cat` streams the output through instead of blocking, and also covers other
pager-using tools (man, systemctl, journalctl). Adds regression tests.

Fixes #1697

Keep running parallel jobs alive when an await call reaches its timeout so agents can await the same job ids again instead of cancelling child work. Distinguish direct background tool workers from call_subordinate child chats so nested subordinate chats can use parallel normally while true worker recursion remains blocked. Update the parallel prompt, DOX notes, and regressions for non-destructive timeout and non-blocking collect semantics.

Keep the browser tool prompt as a compact callable contract and move detailed workflows into browser-automation, with fragile form guidance chained through browser-form-workflows. Add regression coverage for the skills_tool loading path, host browser setup hint, and prompt token ceiling.

Add shipped local-provider defaults for LM Studio and Ollama so Dockerized Agent Zero can reach host-running services without manual api_base edits. Map host.docker.internal in the sample Compose file for Linux Docker, document the behavior, and cover the provider defaults and compose mapping with focused regression tests.

Add oMLX as a first-class local chat and embedding provider using the Docker-friendly host.docker.internal:8000/v1 default and LiteLLM hosted_vllm wiring. Mark it as a no-key local provider, include it in onboarding with a bundled logo, document Apple Silicon setup including paged SSD cache, and cover the provider defaults, model search behavior, and onboarding metadata with focused tests.

Add llama.cpp / llama-server support:
- Register llama.cpp chat and embedding providers through hosted_vllm defaults on host.docker.internal:8080.
- Add onboarding metadata, a bundled icon, no-key provider metadata, model discovery coverage, setup docs, and tests.

Add vLLM support:
- Register vLLM chat and embedding providers through hosted_vllm defaults on host.docker.internal:8000.
- Add onboarding metadata, a bundled icon, no-key provider metadata, model discovery coverage, setup docs, and tests.
- Strip empty tools arrays from the Responses-to-chat fallback path so strict OpenAI-compatible servers accept local vLLM calls.

Prefer explicit tool_name examples and first prompt headings when deriving native Responses function tool names, falling back to the prompt filename only when no callable name is declared.

Add regression coverage for code_execution_tool, memory_load, call_subordinate, behaviour_adjustment, and filename-only fallback, and document the contract in responses_tools DOX.

Add trigger frontmatter for browser automation and browser form workflow skills so relevant-skill recall surfaces them for rendered browsing, screenshots, host-browser, and form-heavy tasks. Update build-skill guidance to document trigger metadata and add regression coverage for parsing and ranking the browser skills.

Reject document_query during parallel tool-call normalization before worker jobs are started. Add prompt guidance so the model avoids batching document_query, and update DOX plus regressions for the new sequential-only contract.

Buffer JSON/base64 connector_file_op_result chunks per pending file operation and resolve only after the complete result is assembled.

Validate malformed chunk metadata with a pending-operation error, while preserving the existing single-payload behavior for small file operations.

Move explicit skill loads out of per-turn prompt extras and into normal tool-result history, with revision metadata for duplicate detection. Duplicate load calls now omit the full body only when the same revision remains model-visible after history output assembly.

When compression hides an explicitly loaded skill body, reattach the current missing revision as a normal skills_tool history result under one fixed budget. Preserve skill name and revision metadata in automatic and manual compaction summaries without copying full skill bodies.

Raises the Socket.IO heartbeat interval and timeout defaults so long context and prompt work do not trip python-engineio's empty packet queue timeout.

Adds positive-integer environment overrides and updates the runtime configuration regression test.

Create the .a0proj/skills directory during project metadata setup so Project Settings can open the skills folder for new projects. Repair the folder when loading existing project settings, and cover both creation and repair with regression tests.

Patch stale sentence-transformer embedding provider/model aliases at the _model_config read/build boundary so memory embeddings use the intended local HuggingFace provider without adding provider-specific logic to models.py.

Cover stale alias forms, the bare default alias, normal OpenAI embedding pass-through, and missing API-key detection with focused regression tests.

Validate call_subordinate profile arguments against available agent profiles so missing profiles fail as repairable errors. Persist each agent's profile in saved chats and avoid flattening existing subordinate profiles during profile switches, settings refresh, or restart reload.

Default the WebUI Browser surface back to live CDP screencast while keeping snapshot/state transport as a fallback. Carry viewer transport through the WebSocket API and Browser store, use screencast metadata to avoid extra frame dimension decode, and include frame-chain action metadata in Browser content results. Update Browser prompts, skill guidance, DOX, and focused regressions so agent actions prefer DOM/CDP refs while the visible Browser remains responsive.

Add a Settings > Skills scanner section and modal backed by Snyk Agent Scan-oriented checks and prompts. Wire uploaded skill zips from Import Skills into the scanner before import, and add a preparation API that extracts archives into temporary scan roots without installing or executing them.

Harden shared skill zip extraction against traversal, backslash paths, and symlink entries, and cover the new flow with focused scanner tests.

Remove agent profile scoping from the List Skills and Import Skills settings sections so skills are scoped only by project.

Move Scan Skills after Import Skills in both navigation metadata and rendered section order, and add an MCP-style search affordance to List Skills with filtered results and an empty search state.

Release MCP config locks before awaited initialization or tool calls, isolate MCP session operations in disposable DeferredTask workers, and bound session cleanup so wedged transports cannot freeze later agent work.

Add deterministic MCP regression coverage for lock scope, config update initialization, cleanup timeouts, and isolated operation timeouts. Update the helper DOX contract for the new concurrency and cleanup behavior.

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.

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.

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.

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.

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.

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.

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.

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.

Place the internal Browser proxy fields in a native disclosure and keep its styling borderless. Refresh the guide screenshot and cover the config markup.

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.

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.

remove text and enlarge logo

Delegate scoped command discovery to the Commands plugin and let skills_tool list or read effective slash-command definitions without invoking them.

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.

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 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.

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.

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.

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.

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.

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.

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.

Route Nebius, Z.AI, Z.AI Coding, and Gemini API OAuth directly through Chat Completions.

Avoid unsupported /responses probes and keep provider defaults aligned with documented upstream capabilities.

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.

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.

Prefer cached process render metadata over mutable DOM-tail state when re-rendering warnings. Add focused regression coverage and document the replay contract.

Point the root README's A0 Launcher downloads and release note link at the published v1.5 assets without moving the Agent Zero release tag.

Set the default consecutive unusable response threshold to five and align the Agent Settings copy, helper DOX, and regression assertion.