Add Day 1 agent runtime foundations with task and event schemas, verifier support, capability metadata, graph event tracing, and regression coverage while preserving the direct execution path.
Align the L3 graph, agent service, and sync tool shims on one canonical continuity contract so clarification resumes and persisted snapshots behave consistently. Add targeted regressions and hardening notes covering system-message coalescing, async bridge usage, and continuity rehydration.
Persist streaming chat state during generator cleanup, close the SSE inner stream safely, and reject cross-user conversation access while locking the behavior with focused regressions.
Make the project start more reliably in the current Windows bash setup, add a safe root .env.example for onboarding, and lower the backend Python floor to 3.11 to match the validated local environment.
Expand the agents page into a three-tier org chart, refine zoom and active route feedback, and cover the hierarchy behavior with targeted tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add sub-commander orchestration updates, align frontend integrations, and refine knowledge view behavior without including local data artifacts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Strengthen the Ultron command center with clearer blueprint-style hierarchy, embedded route telemetry, and test coverage for active path visualization.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Use shell-based setup and startup flows that work more reliably across
Windows bash environments and Linux. This keeps environment bootstrap
and service startup aligned while avoiding fragile process handling.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Refresh the agent graph state and prompt wiring so the newer backend and
frontend orchestration features share the same execution model. This
keeps the remaining agent-side changes aligned with the rest of the
batch.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Capture the current local data snapshot and planning artifacts alongside
this development batch so the workspace state matches the code changes.
This preserves the reference materials and generated files that were
kept in the working tree.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Expand the frontend with brain, graph, and chat workspace updates so the
new backend orchestration and memory features have matching screens.
These changes also wire the new APIs into routing and add focused view
and routing tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce the backend pieces for brain memory ingestion, routing, and
system telemetry so the new knowledge workflows can project data into a
brain view. The supporting tests lock in the new behavior and keep the
expanded backend surface stable.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Keep folder selection stable across refreshes, surface upload failures
more clearly, and add focused composable tests for the knowledge page.
This keeps newly uploaded files visible and makes MinerU dependency
errors easier to understand from the frontend.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Normalize uploaded documents into structured markdown, add clearer parser
errors for missing dependencies, and cover the ingestion flow with
backend tests. This also replaces deprecated UTC timestamp helpers in
the touched backend paths so the knowledge pipeline stays warning-free.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move the runtime log screen into the new pages structure, add compact page navigation, and apply the minimal component fixes needed to keep the refactored frontend buildable.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Reorganize the frontend around app-level routing and page modules so the runtime and feature screens share a clearer navigation and composition layout for future work.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Make runtime log queries support request correlation and date-range diagnostics with shared filtering semantics so the log page can use one consistent contract.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implemented a complete log system for tracking:
- Agent logs:智能体调用
- System logs: 系统运行
- Chat logs: 问答对话
Backend:
- Log model with type, level, user_id, message, source, duration_ms
- LogService with methods for logging and querying
- API endpoints: GET /api/logs, GET /api/logs/stats, GET /api/logs/recent
Frontend:
- LogView.vue with filters, stats, pagination, auto-refresh
- log.ts API client with TypeScript interfaces
- Added "运行日志" nav item to sidebar
SQLAlchemy wasn't detecting changes when we modified the dict in place
and re-assigned the same object reference. Using deep copy ensures
the ORM sees the update.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When test passes, props.model.enabled is updated but editingModel wasn't
synced, causing save button to remain disabled.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove old card-based model list UI
- Add LLM config state management (expandedRow, editingSnapshot)
- Implement addModel/removeModel with embedding/rerank constraints
- Implement updateModel, testModel, saveModel, toggleRow, cancelEdit
- Add showRequiredWarning computed property
- Rewrite template with 4 LLM type sections using LLMTableRow
- Add styles for llm-type-section, warning-bar, etc.
- Update loadSettings to initialize with empty arrays
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
