Omit orphaned leading assistant messages from model history so Claude-compatible providers receive a user-first conversation.
Add regression coverage for the initial UI greeting path.
Temporarily stash tracked plugin edits while updating. Restore the original checkout and edits if the update cannot reapply them, and surface the conflict beside the Update button. Add isolated Git regression coverage for merge, no-op, and conflict cases.
Reject empty and whitespace-only chat context identifiers before provider or filesystem cleanup begins. This prevents malformed deletion requests from resolving to the shared chat directory and adds focused regression coverage.
Project updates and deletion previously persisted every loaded chat, while matching chats were written twice through the existing activation helpers.
Keep the established project lifecycle flow and remove the unconditional writes so only affected chats are saved once. Add focused regression coverage and document the persistence contract.
Normalize legacy global settings that still select the internal default profile to Agent 0. This keeps fresh chats aligned with the visible profile catalog while preserving existing chat selections.
Return skills only from skills_tool and remove the command-definition loading bridge. Leave slash-command discovery, invocation, and authoring with the Commands plugin and its user-facing surfaces.
Humanize MCP catalog labels with their server names while preserving canonical IDs. Suppress skill discovery prompts when skills_tool is unavailable and move the behaviour_adjustment prompt under the Memory plugin so disabling its implementation also removes its instructions.
Give Tools, MCPs, and Skills explicit default switches with segmented per-item policy controls while preserving sparse overrides. Simplify Advanced prompt editing around the full-height ACE surface and align the editor contracts and regression coverage.
Centralize omission of the internal default profile in the shared presentation catalog and keep status reporting intact for existing chats. Align Settings, model-switcher, Connector, Telegram, and selector contracts with focused 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.
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.
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.
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.
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.
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.
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.
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.
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.
Clear DeferredTask callables and arguments after completion or cancellation while running each invocation from a safe private snapshot. Preserve result retrieval and active restart behavior, clean up child tasks, and add best-effort local and SSH session destructors with focused lifecycle regression coverage.
Filter usr/.env masking to API keys and login/password credentials so ordinary settings cannot corrupt chat text. Keep global and project secrets protected, and cover full-response, prompt, and streaming behavior with a regression test.
Include usr/.env in the agent-facing SecretsManager sources so runtime credentials are masked in tool results, history, logs, and streamed output. Keep the writable default secrets manager scoped to usr/secrets.env.
Add regression coverage for dotenv masking and document the source contract.
Delegate skill discovery, parsing, lookup, search, and validation to helpers.skills so CLI behavior cannot drift from the runtime contract.
Generate canonical triggers metadata and cover valid and incomplete skill validation.
Make model presets a single global collection and treat presets as reusable setups (main, utility, embedding). Persisted scope configs now store only a preset name (Default is always present and immutable); project-scoped preset definitions were removed and attempts to edit/reset project presets are rejected. Add embedding-model support throughout: include embedding slot in presets, surface embedding in the switcher and override APIs, and notify extensions when the effective embedding model changes. Implement rename/retire propagation to update plugin configs, saved chats, and live AgentContext objects when preset names change or presets are removed. Update CLI/integration commands to use an "inherit" action for returning to the scoped preset and to report the effective scoped-or-chat preset. Add startup migration/bootstrap to initialize presets from remote or bundled fallback and numerous docs/UI text updates to reflect the new preset model. Extra: refactor config resolution helpers and add safety checks (validation, atomic writes) when saving presets.
Stop PrintStyle from creating per-process HTML files under /a0/logs and remove the obsolete tracked folder scaffolding.
Delete existing legacy log directories during startup migration so self-updated and manually upgraded installations are cleaned automatically. Point plugin debugging guidance to Docker output and add regression coverage for repeatable cleanup.
Resolve provider-safe Responses tool names back to their canonical MCP names inside the MCP handler before dispatch. Preserve canonical lookups and reject stale or unrelated aliases so local tool resolution can continue.
Add regression coverage for Google Workspace-style names and document the lookup contract.
Persist only durable Responses continuation metadata instead of repeated prompts and raw model payloads.
Normalize legacy AI message metadata during load while preserving structured output, unrelated metadata, and tool-result inputs.
Persist the frontend-extension notification as read before reloading so it does not reappear after refresh. Align plugin and updater toast actions with the shared small spacing token.
Make plugin frontend-reload and Agent Zero update notifications persistent until the user dismisses or acts on them. Reuse the existing zero-duration toast contract without changing ordinary notification timeouts.\n\nDocument the behavior and extend the persistent-toast regression coverage.
Capture each notification payload together with its GUID and update cursor under the notification manager lock. This prevents concurrent notify_user events from advancing the WebUI cursor without delivering the corresponding toast.\n\nAdd regression coverage for notification cursor continuity and update the helper contracts.
Add an Interface settings section with independent mobile and desktop toggles for the project selector, clock, connection status, and right canvas rail.
Persist the visibility map in instance settings, apply it at the shared WebUI surfaces, preserve existing defaults, and cover the contract with focused regression tests and DOX updates.
Add a configurable circuit breaker for consecutive malformed or repeated model outputs. Expose the limit in Agent Settings and render the stop notice from a framework prompt.
Write serialized chats to a same-directory temporary file, fsync it, and atomically replace chat.json so interrupted saves preserve the previous chat data.
Add regression coverage for interrupted replacement and document the persistence guarantee.
Pass each parent-visible child log into direct parallel worker execution so tool before_execution reuses it instead of creating a second generic tool log.
This keeps native badge types such as wait/progress (HDL) intact through execution, updates the parallel helper DOX contract, and adds a regression test for log reuse.
Resolve tool-specific log objects for all parallel child jobs, removing the code_execution_tool-only special case and using native get_log_object() when available, with generic fallback.
Update parallel_tools docs to reflect the shared logging contract and add coverage for wait/ fallback behavior in parallel-tool tests.
Skip usr/.time_travel during self-update user-data backups and add the same Time Travel shadow-history exclusion to default BackupService metadata.\n\nAdd focused regressions proving regular user files stay in backup coverage while Time Travel shadow repositories are omitted.
Load active-project AGENTS.md path-chain guidance into the protocol area without duplicating the project root instructions.
Move the AGENTS.md protocol wording into a prompt template, reuse existing file/path helpers, and cover direct-path discovery plus prompt assembly with focused tests.
Search the raw user message when recalling relevant skills instead of the rendered history wrapper.
Replace the stopword catalog with structural matching: names use normal terms, tags/triggers use long terms or phrase matches, and descriptions require phrase matches.
Switch the Skills catalog UI/API from scope-wide prompt pins to current-chat history loading, and remove user-facing removal of loaded skills.
Disable legacy active-skill prompt injection so forgotten scope config no longer inflates new-chat prompts.
