Open
Conversation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implements CodexProvider (JSON-RPC 2.0 over stdio) and OpenClawProvider (stderr NDJSON), following the same pattern as ClaudeCodeProvider. Updates registry to register all three providers and Dockerfile to install Codex CLI. Adds 14 new unit tests covering event parsing for both providers and registry integration. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add real-time WebSocket execution stream with polling fallback - Fix dark mode: replace hardcoded colors with CSS variables across execution-event, execution-timeline, mission-column, mission-card, and mission-detail-panel - Fix undefined CSS vars (--bg-secondary, --bg-hover) with --surface-3 - Add proper loading, error, and empty states to execution timeline - Add mobile touch scrolling to mission board Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…y-badge and agent-status Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…t, get_agent_result)
…, reducer perf, task error handling Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add human-agent comment system for missions with auto-posting on execution completion/failure, and fix critical chain-closure bugs: execution completion now writes back mission status, clears current_execution_id, terminates containers on cancel, and broadcasts real-time events via WebSocket. Frontend notification provider invalidates queries on mission/comment updates; Kanban shows all 7 status columns. Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…tch 400
- Guard against non-dict JSON lines and string content blocks in Claude
Code stream-json parsing (claude_code.py)
- Add isinstance check on result event's result field before calling .get()
- Default event.payload to {} in execution-event.tsx to prevent undefined access
- Expand ExecutionEventType and switch cases to handle backend event aliases
(assistant_text, tool_use_start, tool_use_end, execution_started, etc.)
- Allow re-dispatch of IN_PROGRESS missions when current execution is terminal
- Mission board UI and filtering improvements
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…sLive prop - Share EVENT_CONFIG objects between alias pairs instead of duplicating - Use config.label for status fallback instead of string replace - Extract AgentPickerContent sub-component to eliminate duplicated Popover+Command blocks in mission-detail-panel - Add isLive prop to ExecutionTimeline; past executions skip WebSocket and polling (N+1 connection fix) - Limit past executions to 10 in detail panel - Hoist inline imports in mission_service.py to module level - Use Date.parse for isOverdue to avoid unnecessary Date allocations Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Containers are no longer destroyed after each execution — they stay alive in a pool keyed by agent_profile_id and are reused on subsequent dispatches. The pool also stores the Claude Code session_id so the next execution resumes the prior conversation context via --resume. - Add ContainerPool (container_pool.py) with get/put/release/evict/cleanup - Rewrite ExecutionRunner.run() to pull from pool and release back - Start a reaper background task (every 5 min) to evict idle containers - On app shutdown, containers are left running for reuse after restart Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
… error display - Extract shared credentials module (utils/credentials.py) with API key validation - Pass credentials to docker exec via provider.execute(env=credentials) - Detect Claude Code is_error flag to mark failed executions correctly - Move build_credentials() before create_execution() to prevent orphan rows - Add conditional refetchInterval — stop polling terminal executions/missions - Use shared ACTIVE/TERMINAL status constants across frontend - Fix cancel button visibility based on actual execution status - Skip WebSocket for terminal executions in ExecutionTimeline - Add toastError on dispatch/cancel failure in mission detail panel Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
- Add defaultOptions.mutations.onError to QueryClient with toastError so all mutation failures show a toast automatically — covers ~23 previously silent call sites across missions, graphs, workspaces, folders, runs, and openclaw components - Wrap mutateAsync in try/catch in mission-create-dialog to prevent unhandled promise rejection - Remove redundant per-call-site onError from mission-detail-panel dispatch/cancel buttons (global handler covers them) Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…error boundaries - Add ValueError/RuntimeError/PermissionError → AppException translation in general_exception_handler, converting ~15 service-layer raises from 500 to proper 4xx responses without modifying any service code - Remove duplicate Exception handler in main.py that overrode unified format - Add safe_create_task() utility replacing ~15 bare asyncio.create_task calls with automatic error logging via done callbacks - Fix skills.py DB session leak: fire-and-forget tasks now own their session via AsyncSessionLocal instead of using request-scoped db - Fix codex.py ensure_future → put_nowait with QueueFull handling - Add Next.js error boundaries (error.tsx + global-error.tsx) for page and root layout crash recovery - Add QueryCache onError for background refetch failure toasts - Add BaseService.safe_commit() with auto-rollback on failure Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
- Remove 5 dead `import asyncio` with misleading noqa comments in skills.py - Fix _delete_from_container capturing closed request-scoped db session - Migrate mission_service.py to safe_create_task, remove private duplicate - Remove redundant except ValueError/PermissionError in mission_comments.py (global handler covers them; PermissionError was incorrectly mapped to 400) - Move safe_create_task imports to module top-level across 6 files - Add missing error.message fallback in global-error.tsx Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
… workspace ACL - Fix SQL injection in memory_service.py: replace raw f-string topic query with text().bindparams() parameterized binding - Add execution ownership verification to inject_message and approve_action endpoints — prevents cross-user execution manipulation - Add DANGEROUS_PATTERNS command denylist to execute_local_command, shared with PydanticSandboxAdapter — blocks rm -rf /, mkfs, dd, fork bombs - Add workspace membership checks to 16 endpoints across missions (7), agent_profiles (4), executions (1), mission_comments (4) using existing require_workspace_role dependency (viewer for reads, member for writes) - Remove redundant except ValueError/PermissionError in missions.py Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
- Fix WorkspaceMemberRole imported from wrong module (app.models.enums → app.models.workspace) - Reorder cheap enum validation before DB access check in create_mission - Move session_registry import to top-level in executions.py - Check session_registry (O(1)) before DB ownership query in inject/approve - Unify HTTPException → NotFoundException for consistent error handling - Move DANGEROUS_RE import to top-level in pydantic_adapter.py - Move denylist check before try block in command_executor.py Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…r, simplify Backend: - Add auto_approve toggle: bypassPermissions + DONE vs default + IN_REVIEW - Add @agent mention dispatch in comments with dedup - Add background scheduler (mission dispatcher + execution reaper) - Add DELETE agent endpoint with orphan mission cleanup - Expose agent profile fields, token usage (result_summary) in API - Add control_request/control_response protocol for approval flow - Add AssigneeType enum, TERMINAL_EXECUTION_STATUSES constant - Extract _create_and_start_execution shared helper - Convert post_execution_comment from classmethod to instance method - Fix: token usage preserved in error paths (claude_code.py) - Fix: custom_env → has_custom_env (security, write-only secrets) - Fix: BACKLOG gating aligned between assignee and mention paths - Consolidate list_dispatchable with optional workspace_id Frontend: - Add @mention input with agent dropdown in comment thread - Render mentions as styled badges in comments - Add auto_approve toggle in create dialog + detail panel - Show token usage in execution timeline header - Add status transition validation (MANUAL_TRANSITIONS) - Add approval_resolved event type and display - Lazy-load agent profiles (enabled on @ keystroke) Migrations: - Remove BLOCKED mission status - Add auto_approve column to missions Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
… imports Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Switch dispatch/cancel/finalize callers in missions.py, executions.py, mission_comments.py, and scheduler.py from MissionService to ExecutionLifecycleService. The mission_comments.py 4-tuple unpacking is intentionally ahead of the service return type change (Task 2.3). Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…ng executions Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…snapshot) Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Aggregates execution events across all runs in a thread. Cursor-based pagination via ?after=<event_id>. Filters out copilot_* events server-side. Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
- ThreadEvent type replaces ThreadMessage - threadService.listThreadEvents and sendChat replace message methods - useThreadEvents, useChatSend, useChatStream hooks Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
ChatPanel, ChatHistory, ChatEventBubble, ChatInput, ChatFilePreview, AttachmentChip, ThreadSidebar — chat UI rendering execution events as conversation bubbles. Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
- ChatFilePreview: inline text content fetch with line preview, image fullscreen lightbox, PDF iframe viewer, auto-open small files - ChatInput: drag-and-drop visual overlay, file validation with rejection logging, auto-resize textarea, max files indicator - ChatHistory: streaming "Agent is working..." indicator - All components have real error handling and loading states Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
- AgentChatTab, conversation-view, thread-list, use-agent-chat deleted - ChatPanel now serves as chat tab in agent detail page - workspaceId resolved in page component via useWorkspaces Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
- use-chat-stream: seq instead of sequence_no (matches ExecutionEvent type) - ChatEventBubble: typeof check for payload.trace (unknown → string) - ChatInput: cast ALLOWED_MIME_TYPES to readonly string[] for includes() Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
…0 errors Published versions stay frozen after the publish flow, causing all subsequent PATCH saves from the canvas to fail with 400. The builder now detects frozen versions on load and auto-unfreezes them to draft. Co-Authored-By: Claude Opus 4 (1M context) <noreply@anthropic.com>
Introduce root-level WorkspaceProvider with Zustand-persisted workspace selection, replacing 3 scattered workspace resolution patterns across 17+ files. Add permission guards (canEdit/canAdmin) to 7+ pages covering agent settings, tools, sandboxes, tokens, agents list, memory, and tasks. Fix crash on unauthenticated routes in useWorkspacePermissions hook. Delete dead code (use-workspace-permission.ts). Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
The list-runs API requires workspace_id for permission validation, but the copilot reconnect effect was omitting it, causing a 422 on page refresh. Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Replace soft-delete (archive) with hard delete that cascades through all dependent records: versions, releases, runs, executions, events, artifacts, and threads. Add delete button with destructive confirmation dialog to the agent list page. Change grid from 3 to 4 columns. Fix AgentSummary schema to include description field for list API. Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
…afeter into agent-studio-workflow
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
No description provided.