[pull] main from agent0ai:main - #4
Open
pull[bot] wants to merge 1648 commits into
Open
Conversation
Rename the Gemini OAuth provider surface to Google Cloud Gemini so the OAuth provider list points users toward the required Google Cloud project setup. Align model-provider metadata, usage-plan copy, README wording, and static assertions while keeping the Gemini API OAuth mechanics unchanged.
Reintroduce the shared .text-button primitive in WebUI button CSS so model-config preset controls no longer depend on the chat composer being mounted first. Document the shared compact text-action contract and add a focused regression covering Model Presets and Model Configuration text-button usage.
Split the monolithic a0-development skill into a lean entry point plus focused reference files for runtime, DOX, tools, extensions, API/WebUI, profiles, prompts, skills, projects, and plugin workflow. Update the skill DOX ownership for the new references directory and clarify the root framework-vs-agent Python runtimes plus port-discovery guidance. Verified with git diff --check, targeted skill/tool tests under PYTHONPATH, and live localhost:32769 skill loading/read_file checks before committing.
Restore restorable surface modals through the initFw_end extension hook and keep right-canvas state in session storage for normal reloads. Fix Desktop host visibility after modal cleanup so preserved iframes reattach to real modal or canvas hosts, and remove the duplicate file-browser path icon overlay.
Route the Configure credentials banner link through the welcome banner action dispatcher so it opens Settings directly at External Services > Authentication.\n\nAdd coverage for the unsecured connection banner and document the structured banner action contract for future banner links.
Reset inherited mobile white-space inside the chat compaction modal so template indentation does not render as large vertical gaps. Constrain the custom dialog body and raise the overlay above the mobile canvas rail.
Move the ctx_length control for main and utility model slots above the Advanced disclosure while keeping embeddings excluded. Add a static regression guard so primary context controls stay visible outside Advanced.
Suppress the chat progress ghost placeholder until a chat is selected so the welcome new-chat prompt remains the only visible composer hint. Add a focused static regression for the welcome composer idle-progress overlap case.
Use the same minimal trixie Xpra fallback package set for any architecture when the preferred Xpra repository is unsatisfiable. This lets amd64 recover from current xpra beta sid libopenjph dependency drift like arm64 already does.
Add a Launcher guide with runtime setup, Installs, Instances, and screenshot capture notes. Link the guide from README, quickstart, and docs index, and clarify the v1.20-to-v2.0 image upgrade path with backup/restore screenshots.
Raise the runtime container soft nofile limit before supervisord starts so WebUI and managed services inherit a larger descriptor allowance. Add an explicit compose nofile example, document the startup contract, and cover the limit raise and hard-limit cap with focused regression tests.
[codex] Add Tiny Local tool-use profile
Guard stream reconfiguration so pytest capture objects without reconfigure support can import the code execution TTY helper while preserving UTF-8 error handling for normal streams.
Disable pagers in non-interactive code execution shells
Move installation guidance out of the feature overview and split it into Launcher, A0 Install, and direct Docker paths. Add the A0 Launcher v0.9 download matrix, document headless A0 Install usage, and keep the visible architecture labels aligned with the requested x86/ARM wording.
Update the docs index, quickstart, and installation guide to present A0 Launcher, A0 Install, and direct Docker as distinct setup paths. Add the A0 Launcher v0.9 download matrix, document headless installer usage, and align visible architecture labels with the x86/ARM wording.
Add the missing 256x256 thumbnail asset for the built-in What's New plugin. The image is compressed under 20 KB and stored in the plugin web UI asset location used by bundled plugin cards.
Treat pre-output Responses API 400 validation failures as unsupported so OpenAI-compatible providers that reject /v1/responses payloads can retry through Chat Completions. Also prefer a valid tool-call JSON object after leading prose or incidental JSON to reduce false misformat warnings.
Save MCP image and image-resource payloads as scoped artifacts, return their paths in tool text and attachment metadata, and keep them model-visible through raw image history content. This gives downstream media delivery a real file path instead of only an inline data URL.
Default empty skills_tool calls to list, accept legacy method as a deprecated action alias, and warn when malformed SKILL.md frontmatter causes a skill to be skipped. Update the helper/tool DOX notes and focused regressions.
Keep the streaming early-stop caller untouched by making extract_json_root_string prefer the first complete JSON root that normalizes as a tool request while preserving its first-root fallback for non-tool JSON. Add regression coverage for incidental JSON before a streamed tool-call envelope.
Keep the malformed SKILL.md warning behavior, but reduce the diagnostic machinery to a once-per-path warning with line numbers only for parser-owned structural errors. Update the regression to assert the stable warning message without depending on the previous path/line/error dedupe key.
Keep the valid-tool-root preference added for streamed snapshots, but avoid collecting and re-walking parsed candidates. Remember the first parsed object/root while scanning and use a small predicate for tool-request recognition.
Keep fallback for endpoint-specific and Venice-style Responses payload rejections, but stop treating generic Bad Request validation text as proof that Responses is unsupported. Add a regression that generic pre-output Responses 400s raise without trying Chat Completions.
Restore parallel normalization tolerance for provider/model outputs that stringify the tool_calls array inside tool_args. The wrapper still expects normal tool-call objects after decoding, so nested parallel and document_query guards continue to run through the same validation path.
Let project- or agent-scoped plugins open the shared settings surface even without a custom form. Tool Access can now reach existing scoped configurations while inert Save and Reset actions remain hidden.
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.
Give Tool Access, Pin to Top, Chat Naming, and Agent Editor distinct 256px artwork aligned with the existing dark plugin gallery. Optimize every JPEG below 20 KB for fast plugin-list rendering.
Use Agent Zero's blue accent for the active On, Default, or Off segment so the selected permission state is immediately visible in Easy and Advanced modes.
Bundle the five-harness migration workflow under the _migrate_agents namespace, including preview/import safeguards, tests, documentation, WebUI assets, and the corrected upload modal behavior.
Bring the useful community enhancements into the built-in plugin with a current American voice catalog, speed controls, and in-memory weighted blending while preserving existing voice and speed configuration. Reuse the singleton Kokoro pipeline, validate blend inputs, show resolved ratios in status views, and cover the native flow with focused regression tests. Co-authored-by: twilso24 <122656888+twilso24@users.noreply.github.com>
Keep profile catalog reads lightweight by detecting sparse editor overrides without building removal plans for every agent. Use the chat snapshot refresh as the single switch trigger and share concurrent same-context catalog requests while preserving newest-context-wins behavior.
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.
Publish goal revisions through the shared state monitor and refresh the Goal UI only when the selected chat or goal state changes. Keep the local elapsed-time clock, remove recurring API requests, and cover the state-push contract with focused regressions.
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.
Add hour-aware output to the shared duration formatter while preserving existing seconds and minutes formatting. Reuse it for the goal elapsed counter and cover both formats with a focused regression test.
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.
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.
Document the optional ui, agent, and api caller context for plugin configuration hooks. Clarify the api default, backwards compatibility, explicit backend opt-in, and that caller context is not an authorization boundary.
Route remote document downloads through the existing public-only HTTP fetcher so direct and redirected non-public destinations are rejected while public redirects, request headers, proxy isolation, retries, timeouts, and size limits remain intact. Add focused CVE-2026-4308 regression coverage for private targets and genuine public-fetch compatibility.
Resolve individual and bulk download paths from the filesystem root so authenticated operators can download every path exposed by the File Browser and editor.\n\nKeep the existing authentication, CSRF, path normalization, and archive behavior, and cover downloads outside the Agent Zero runtime directory with a regression test.
…-out, stale-lock repair) Time Travel keeps a hidden git repository per workspace under /a0/usr/.time_travel/workspaces/<id>/repo.git and snapshots on every file change, but ships no retention: nothing deletes a shadow repository when its chat or project is removed (chat_remove never touches .time_travel), there is no delete/prune endpoint in the API or web UI, and a workspace whose 'git add' ever exceeds GIT_TIMEOUT_SECONDS strands repo.git/index.lock, failing every later snapshot with 'index.lock: File exists'. Observed on a live instance: 518 shadow repositories / 12 GB, most belonging to long-deleted chats, plus a permanently wedged workspace. This adds a throttled retention sweep driven from job_loop: - Orphans: live workspace paths (project folders, the configured workdir, per-chat workdirs) are forward-enumerated and hashed with the existing workspace_id_for derivation; a shadow directory matching none of them is unreachable from the UI forever and is removed after a grace window. - Optional age-out: retention_max_age_days (default 0 = keep forever) removes a live workspace's history when it has had no snapshot in N days. Time Travel lazily re-initializes an empty history on the next snapshot, so this is always safe for the feature. - Stale locks: repo.git/index.lock older than retention_stale_lock_minutes is removed (git subprocesses are killed at GIT_TIMEOUT_SECONDS, so no legitimate lock lives that long), un-wedging future snapshots. - Corrupt-repo set-asides (repo.git.invalid*) past the grace window. Deletion is refused for any path outside the shadow root. Settings render in the existing plugin-config pattern (default_config.yaml + webui/config.html, settings_sections: agent): enable toggle, sweep interval, age-out days, orphan grace, stale-lock age. Durable evidence lives next to the workspaces dir: retention.json (running totals + last sweep stamp) and retention.log (one JSON line per sweep naming everything removed, tail-capped at 1000). Sweeps run in a worker thread off the event loop, at most one in flight, default every 6 hours. Tests: tests/test_time_travel_retention.py (config defaults/clamps, the full sweep matrix, keep-forever default, disabled no-op, deletion guard, marker accrual, per-sweep history + cap, throttle, and workspace_id_for parity).
Treat opaque 400 type-discrimination errors from OpenAI-compatible Responses endpoints as shape-specific request rejections and retry through Chat Completions. Add focused regression coverage.
Upstream gates newer models on a version header. Attach resolve_codex_version() when non-empty so completions match /models. Fixes #1765
The live desktop renders in an iframe (.office-desktop-frame). Canvas resize is driven by a global pointermove from the left-edge handle; shrinking sweeps the cursor across the iframe, which captures the event and freezes the drag. Disable hit-testing on the frame while right-canvas-resizing is set on <body>.
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.
Replace the legacy guided-profile instructions with screenshot-led Easy and Advanced editor workflows, project availability, and A0 CLI creation. Document sparse YAML, Markdown, and JSON overrides for identity, prompts, Tool and MCP policy, Skills visibility, and model presets. Refresh adjacent guides and remove obsolete screenshots.
Use the shared toast action row and primary button classes for the Test in new chat action. Remove the plugin-specific link styling and cover the shared markup in the focused WebUI regression test.
Keep the migration UI available from the Plugins screen and update its documentation and ownership notes.
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.
9 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 : )