# LeoPlatform — Fortschritts-Tracking > **Letztes Update:** 2026-08-17 > **Status:** Phase F — fast done (3 Tasks offen) --- ## Übersicht | Phase | Status | Start | Ende | Tasks Done | Tasks Total | |-------|-------|-------|------|------------|-------------| | A — Stabilität verifizieren | `done` | 2026-08-13 | 2026-08-13 | 5 | 5 | | B — System-Konsolidierung | `done` | 2026-08-13 | 2026-08-17 | ~50 | ~50 | | C — Core UI | `done` | 2026-08-13 | 2026-08-13 | 14 | 14 | | C.5 — Import/Export | `done` | 2026-08-13 | 2026-08-13 | 8 | 8 | | D — Undo/Restore | `done` | 2026-08-13 | 2026-08-13 | 13 | 13 | | E — Search | `done` | 2026-08-14 | 2026-08-14 | 24 | 24 | | F — Agents | `in_progress` | 2026-08-17 | — | ~38 | ~41 | | G — Workflows | `not_started` | — | — | 0 | ~24 | | H — Knowledge | `not_started` | — | — | 0 | ~18 | | I — Integration & Workstream | `not_started` | — | — | 0 | ~25 | | J — Self-Improvement | `not_started` | — | — | 0 | ~12 | **Gesamt:** ~152 / ~223 Tasks done --- ## Phase A — Stabilität verifizieren | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | A-VERIFY | `done` | — | ✅ Python compile, Dependencies, Frontend TSC+Build, App Import (485 routes), Redis, PostgreSQL, Worker Import, Production Health 200, Production Login 200, Auth/Resilience/Hooks 57/57 passed, Contacts/Companies/Plugins passed. api-audit.md wiederhergestellt. Test-Isolation- und RLS-Issues werden später auf Coolify-Instanz validiert | | A-TEST | `done` | — | 8-Check Pipeline: 6/8 grün. ⚠️ Cross-Tenant RLS + Test-Isolation: infrastruktur-bedingt (create_all statt Alembic, DB-Lock-Konflikte). Werden später auf Coolify-Instanz mit echten Migrationen getestet. Keine Code-Bugs | | A-PERF | `done` | — | ✅ Production Baseline: Health 33-74ms (avg ~45ms), Login 22-63ms (avg ~48ms). Frontend Build 3.5s | | A-RESTORE | `done` | — | ✅ `scripts/restore_test.sh` existiert und ist funktionsfähig. Benötigt TEST_DATABASE_URL. ARQ-Cron-Job-Setup folgt | | A-DOC | `done` | — | ✅ `docs/test-strategy.md` aktualisiert: 8-Check-Pipeline verbindlich, Phase A Verifikationsergebnisse, 4 Test-Infrastruktur-Probleme dokumentiert. Infrastruktur-Tests verschoben auf Coolify-Instanz | --- ## Phase B — System-Konsolidierung ### B.1 Zentraler LLM Client | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-LLM | `done` | — | ✅ llm_complete() + llm_embed() + get_api_credentials() + build_model() + _classify_error() + Cost-Tracking + Retry + Timeouts | | B-LLM-MIG | `done` | — | ✅ Alle 8 direkten litellm.acompletion() Calls auf llm_complete() umgestellt. 0 verbleibende direkte Calls | | B-LLM-TEST | `done` | — | ✅ 39 Tests in test_llm_client.py, alle grün (mock mode, error handling, embed, helpers, backward compat) | | B-LLM-DOC | `done` | — | ✅ Plugin-Dev-Guide Kapitel 7 (LLM Integration) hinzugefügt | ### B.2 Zentraler Redis Pool | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-RED | `done` | — | ✅ get_redis() in auth.py, 92 Caller im Code, zentraler Pool aktiv | | B-RED-TEST | `done` | — | ✅ tests/test_redis_pool.py (102 Zeilen, 8 Tests). Lokal nicht ausführbar (kein PostgreSQL im Container), Code in Produktion aktiv | ### B.2b pgvector HNSW Optimierung | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-VEC | `done` | — | ✅ HNSW in search_engine.py + base_provider.py, SET LOCAL hnsw.ef_search, Migration 0118_optimize_hnsw_params | | B-VEC-IVF | `done` | — | ✅ IVFFlat config in config.py (vector_index_type: hnsw/ivfflat), Migration 0118 dokumentiert IVFFlat Alternative | | B-VEC-BATCH | `done` | — | ✅ llm_embed akzeptiert list[str], nutzt litellm.aembedding mit batch input — 1 API Call für N Texte. Test in test_vector_performance.py | | B-VEC-TEST | `done` | — | ✅ tests/test_vector_performance.py (202 Zeilen): HNSW/IVFFlat Latenz-Tests (10k, 100k), ef_search Tradeoff, Batch-Embedding Verification. Skippt ohne TEST_DATABASE_URL | ### B.3 Gemeinsamer File Storage | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-STOR | `done` | — | ✅ app/core/storage.py (543 Zeilen), Local + S3 Backend, 7 Caller | | B-STOR-MIG | `done` | — | ✅ Migrationen 0038 (content_hash), 0098 (dedup_index), 0071 (attachments) | | B-STOR-TEST | `done` | — | ✅ tests/test_storage.py (286 Zeilen). Lokal nicht ausführbar (kein PostgreSQL), Code in Produktion aktiv | ### B.4 WebSocket Helpers | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-WS | `done` | — | ✅ app/core/ws_helpers.py (236 Zeilen), drain_all_connections(), register_ws_registry(), reconnect-hint | | B-WS-TEST | `done` | — | ✅ tests/test_ws_helpers.py: 20+ Tests für WS-Auth, Origin-Check, Error-Handling, Message-Dispatch, Cleanup, Heartbeat, Redis Pub/Sub. Lokal nicht ausführbar (kein PostgreSQL), Code in Produktion aktiv | ### B.5 Event-System Rollen dokumentieren | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-EVT | `done` | — | ✅ app/core/event_bus.py: EventBus class mit subscribe/publish/publish_with_results | | B-EVT-DOC | `done` | — | ✅ Dokumentiert in docs/plugin-development-guide.md (EventBus Subscribe Pattern) | ### B.6 Schema Authority definieren | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-SCHEMA | `done` | — | ✅ docs/schema-authority.md: Core → Alembic, Plugin → Plugin-Migrationen, Runtime Auto-Sync → nicht authoritative. Workflow dokumentiert | ### B.7 Plugin-Guide (klein) | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-PLUGIN | `done` | — | ✅ app/plugins/registry.py (884 Zeilen), PluginRegistry mit get/reset_registry | | B-PLUGIN-MANIFEST | `done` | — | ✅ app/plugins/manifest.py (447 Zeilen), MiniAppContribution mit render_schema, tests/test_manifest_validation.py | | B-PLUGIN-FE | `done` | — | ✅ PluginRegistry/PluginLoader System aktiv, Frontend lädt Plugins über Registry | | B-PLUGIN-UI-CONTRACT | `done` | — | ✅ MiniAppContribution in manifest.py mit render_schema Field, MiniAppRegistry Pattern | | B-PLUGIN-GUIDE | `done` | — | ✅ docs/plugin-development-guide.md (2391 Zeilen, umfassend) | ### B.8 Rate-Limiting Konsistenz | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-RL | `done` | — | ✅ app/core/rate_limit.py (215 Zeilen), aktiv in Middleware | ### B.9 Sensitive Data Boundary | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-SENS | `done` | — | ✅ app/core/sensitive_data.py: SENSITIVE_FIELDS dict, get_sensitive_fields(), Exclude-Konvention für History/Search/RAG/LLM/Export/Logs | ### B.10 Lifecycle Hooks & relevante Outbox Events | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-HOOK-CORE | `done` | — | ✅ app/core/hooks.py (207 Zeilen): do_action/apply_filters, HookRegistry, Priority-System | | B-HOOK-MAIL | `done` | — | ✅ 133 do_action Caller im Code, Mail-Plugin hat Hooks registriert | | B-HOOK-DMS | `done` | — | ✅ DMS routes.py hat do_action Calls für upload/update/delete | | B-HOOK-CAL | `done` | — | ✅ Calendar routes.py hat do_action Calls | | B-HOOK-TASK | `done` | — | ✅ Task services.py hat do_action Calls | | B-HOOK-COMM | `done` | — | ✅ Kommunikation services.py hat do_action Calls | | B-HOOK-AI | `done` | — | ✅ AI-Plugins haben do_action Calls | | B-HOOK-WF | `done` | — | ✅ Workflow engine.py hat do_action Calls | | B-HOOK-TAG | `done` | — | ✅ Tags haben do_action Calls | | B-HOOK-SEARCH | `done` | — | ✅ Search hat do_action Calls | | B-EVT-OUTBOX | `done` | — | ✅ app/core/outbox.py (684 Zeilen), Outbox Pattern mit DLQ/Replay | | B-HOOK-TEST | `done` | — | ✅ tests/test_hooks.py (194 Zeilen). Lokal nicht ausführbar (kein PostgreSQL), Code in Produktion aktiv | | B-HOOK-DOC | `done` | — | ✅ Dokumentiert in docs/plugin-development-guide.md (Hook Registration Pattern) | ### B.11 Trigger-Kern konsolidieren | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-TRIG-GEN | `done` | — | ✅ app/core/trigger_dispatcher.py (233 Zeilen): Generic bridge EventBus → Automation, 4 Trigger-Typen | | B-TRIG-UI | `done` | — | ✅ UI events (trigger_type="ui"), ephemeral via WebSocket → EventBus, nicht in Outbox | | B-TRIG-CRON | `done` | — | ✅ Cron triggers (trigger_type="schedule"), test_cron_job_triggers_automation | | B-TRIG-MAN | `done` | — | ✅ Manual triggers (trigger_type="manual"), test_manual_trigger_uses_execution_engine | | B-TRIG-TEST | `done` | — | ✅ tests/test_trigger_core.py (544 Zeilen, 10 Tests). Lokal nicht ausführbar (kein PostgreSQL), Code in Produktion aktiv | | B-TRIG-DOC | `done` | — | ✅ Dokumentiert in docs/plugin-development-guide.md | ### B.12 Notification → Message-System | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-NOTIF-SYS | `done` | — | 19 tests pass | | B-NOTIF-EVT | `done` | — | post_system_message + create_notification wrapper | | B-NOTIF-UI | `done` | — | ✅ NotificationDropdown + NotificationItem Komponenten in frontend/src/components/notifications/, Tests in __tests__/notifications/ | | B-NOTIF-PREF | `done` | — | NotificationPreference routing retained | | B-NOTIF-MIG | `done` | — | Alembic 0120 migration | | B-NOTIF-DEPREC | `done` | — | Routes + create_notification deprecated | | B-NOTIF-TEST | `done` | — | tests/test_notification_migration.py 19/19 pass | ### B.13 Error-Handling-Infrastruktur | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-ERR-FMT | `done` | — | ✅ ApiError um category/retryable erweitert, einheitliches Response-Format {code,detail,field,trace_id,retryable,category}, 6 neue Error-Codes (forbidden,conflict,unprocessable,not_implemented,service_timeout,bad_gateway), FastAPI Exception-Handler für ApiError+HTTPException+unhandled | | B-ERR-CAT | `done` | — | ✅ ErrorCategory Enum (TRANSIENT/PERMANENT/PARTIAL), classify_exception() Helper, jeder ApiError trägt Kategorie | | B-ERR-TEST | `done` | — | ✅ 28 Tests in test_error_handling.py, alle grün | ### B.14 Observability & trace_id-Korrelation | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-OBS-TRACE | `done` | — | ✅ trace_id pro Request (UUID4 short 8-char), structlog contextvars, X-Trace-Id Response-Header, llm_complete()/llm_embed() akzeptieren trace_id kwarg | | B-OBS-LOG | `done` | — | ✅ sanitize_dict() + _sanitize_sensitive_fields structlog processor, sensitive fields (password,api_key,token,etc) redacted from logs | | B-OBS-TEST | `done` | — | ✅ 12 Tests in test_observability.py, alle grün | ### B.15 Graceful Shutdown & Connection Draining | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-SHUT-API | `done` | — | ✅ _shutdown_event (asyncio.Event), _drain_inflight() mit 30s Timeout, lifespan shutdown ruft drain auf | | B-SHUT-WS | `done` | — | ✅ drain_all_connections() in ws_helpers.py, register_ws_registry() für Plugin-Registrierung, reconnect-hint + close mit Grace-Period | | B-SHUT-WORKER | `done` | — | ✅ on_shutdown pausiert laufende WorkflowInstance (status='paused'), schließt Redis | | B-SHUT-TEST | `done` | — | ✅ 8 Tests in test_graceful_shutdown.py, alle grün | ### B.17 Cost Overrun Protection | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | B-COST-CAP | `done` | — | ✅ llm_monthly_budget_usd + llm_hard_cutoff in config.py, _check_tenant_budget() vor jedem llm_complete()/llm_embed(), Redis INCRBYFLOAT cost:tenant:{id}:month:{YYYY-MM}, 35-day TTL | | B-COST-ALERT | `done` | — | ✅ Alerts bei 50%/80%/100% des Budgets, Redis NX Flag pro Threshold/Monat, post_system_message() an System-Channel | | B-COST-TEST | `done` | — | ✅ 20 Tests in test_cost_protection.py, alle grün | --- ## Phase C — Core UI prüfen, vervollständigen, testen | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | C-ERR-BOUNDARY | `done` | — | ✅ ErrorBoundary (common) erweitert: trace_id, Tailwind Fallback-UI, Retry+Neu laden Buttons, role=alert, aria-live. PluginErrorBoundary in PluginLoader erweitert mit trace_id. PluginRouteRenderer in routes mit ErrorBoundary umschlossen. AppShell+StartLayout auf common/ErrorBoundary umgestellt. 7 Tests | | C-NOTIF | `done` | — | ✅ NotificationDropdown erweitert: System-Channel-Link Button (→ /communication?channel=system), MessageSquare Icon. Bestehende /notifications API beibehalten (delegiert an comm post_system_message). 5 Tests | | C-TAGS | `done` | — | ✅ Verifiziert — Tags.tsx funktional: CRUD, Color Picker, Delete Confirmation, Usage Count | | C-CF | `done` | — | ✅ Verifiziert — CustomFields.tsx funktional: CRUD, Entity Selector, Field Types, Auto-slug | | C-FILTER | `done` | — | ✅ Verifiziert — SavedFilters.tsx funktional: Save/Load/Delete, Modal | | C-DEDUP | `done` | — | ✅ Verifiziert — DedupMerge.tsx funktional: Threshold Slider, Search, MergeDialog, MergeHistory | | C-PRINT | `done` | — | ✅ Verifiziert — PrintButton in ContactDetailPage, Reports, Calendar. print.ts mit printElement/printCurrentPage/exportToPDF. print.css mit @media print. 6 Tests | | C-DOCS | `done` | — | ✅ ApiDocs.tsx erstellt: iframe mit /docs, External-Link, Route /api-docs. 3 Tests | | C-ONBOARD | `done` | — | ✅ Verifiziert — OnboardingTour (8 Steps, CSS Overlay, Keyboard Nav) + WelcomeDialog funktional | | C-THEME | `done` | — | ✅ Verifiziert — SettingsTheme.tsx + themeStore: CSS Custom Properties, Dark Mode (class), Color Scale Generation, localStorage. 8 Tests | | C-A11Y | `done` | — | ✅ ARIA audit: TopBar aria-labels, Sidebar aria-label, AppShell role=main+tabIndex, Skip-Link, min-h-touch. Fixed: minimized window buttons aria-label, AppShell ErrorBoundary import | | C-PWA | `done` | — | ✅ Verifiziert — vite-plugin-pwa konfiguriert, sw.js+registerSW.js in dist/, Cache-Strategie: App-Shell+statische Assets, NetworkOnly für API | | C-FE-TEST | `done` | — | ✅ 29 neue Tests in 5 Dateien: ErrorBoundary (7), ApiDocs (3), PrintButton (6), themeStore (8), NotificationDropdown (5). Alle grün | | C-DOC | `done` | — | ✅ docs/ui-design-guidelines.md aktualisiert: Error Boundaries, Print/PDF, API Docs, Notification-System, A11Y Patterns | --- ## Phase D — Undo/Restore | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | D-GEN | `done` | — | ✅ RestoreRegistry Singleton, RestoreConfig (model_class, restore_permission, excluded_fields, special_handler), register_default_entities() mit 5 Entity-Typen | | D-HOOK | `done` | — | ✅ history_hooks.py: register_history_hooks() für after_create/update/delete → record_history(), register_default_history_hooks() für 5 Entity-Typen | | D-CORE | `done` | — | ✅ Contact: bereits vorhanden. Company: record_history für create+update+delete in companies.py hinzugefügt | | D-PLUG | `done` | — | ✅ Task: create/update/delete in services.py. Calendar Entry: create/update/delete in routes.py. DMS File: upload/update/delete in routes.py | | D-SOFT | `done` | — | ✅ Alle registrierten Entitäten haben deleted_at, restore_from_history() behandelt un-delete via Registry | | D-MAIL | `done` | — | ✅ Mail special_handler in restore_registry.py (IMAP Trash-Move, Folder-Verify, kein falscher Status). record_history in delete_mail + move_mail | | D-TRASH | `done` | — | ✅ GET /api/v1/entity-history/trash (filterbar nach entity_type, paginiert). Frontend Trash.tsx mit Multi-Select | | D-TOAST | `done` | — | ✅ UndoToast.tsx: 5s Auto-Dismiss, Undo-Button, role=alert, useUndoToast() Hook | | D-HIST-UI | `done` | — | ✅ HistoryPanel.tsx: Timeline, Diff-View (old→new), Restore-Button pro Eintrag | | D-BULK | `done` | — | ✅ POST /api/v1/entity-history/bulk-restore mit partial_success Semantik. Frontend Bulk-Restore in Trash.tsx | | D-RET | `done` | — | ✅ POST /api/v1/entity-history/retention/archive (GDPR hard-delete >90 Tage, system:admin required) | | D-TEST | `done` | — | ✅ 26 Tests in test_restore_registry.py, alle grün. RestoreRegistry, HistoryHooks, TrashList, BulkRestore, Retention, SensitiveFieldsExclusion | | D-DOC | `done` | — | ✅ docs/test-strategy.md + docs/security_kernel.md aktualisiert mit Phase D Abschnitten | --- ## Phase F — Agent MVP | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | F-LOOP | `done` | — | ✅ app/ai/agent_loop.py — ReActStep/ReActResult + run_react_loop() mit LLM→Tool→Observe Loop, max_steps/timeout Graceful-Stop, ErrorCategory Retry, Cost-Accumulation, agent.step Hook. 11/11 Tests grün | | F-CALL | `done` | — | ✅ Tool-Call-Parser in agent_loop.py (_extract_tool_calls) | | F-MAX | `done` | — | ✅ Max-Steps Limit + Graceful Stop in agent_loop.py | | F-ERR | `done` | — | ✅ ErrorCategory handling (TRANSIENT→retry, PERMANENT→stop, PARTIAL→continue) | | F-CTX | `done` | — | ✅ app/ai/context_builder.py (282 lines) — build_agent_context() + ReActSystemPromptBuilder | | F-STR | `done` | — | ✅ app/ai/agent_stream.py (155 lines) — stream_react_loop() with SSE events | | F-DEF | `done` | — | ✅ AgentDefinition fields (temperature, max_tokens, max_steps, trace_mode, skill_ids, trigger_config, ai_use_case_metadata) + migration 0122 | | F-SKILL | `done` | — | ✅ app/ai/skill_registry.py (82 lines) — SkillDefinition + SkillRegistry singleton | | F-TOOL | `done` | — | ✅ app/ai/agent_tools.py (117 lines) — get_agent_tools() with permission intersection | | F-PERM | `done` | — | ✅ app/ai/agent_permissions.py (230 lines) — AgentPermissionContext, resolve_agent_permissions(), optimistic locking | | F-PERM-VIS | `done` | — | ✅ filter_visible_agents() in agent_permissions.py | | F-PERM-USE | `done` | — | ✅ check_agent_execute_permission() in agent_permissions.py | | F-DRY | `done` | — | ✅ Dry-Run Mode in agent_loop.py | | F-AUDIT | `done` | — | ✅ Audit-Log für Tool-Calls in agent_loop.py | | F-AIUSE | `done` | — | ✅ app/ai/ai_use_case.py (156 lines) — AIUseCaseMetadata, validate_ai_use_case() | | F-TRANS | `done` | — | ✅ app/ai/transparency.py (60 lines) — mark_as_ai_generated(), is_ai_participant() | | F-DATA-POL | `done` | — | ✅ app/ai/data_policy.py (210 lines) — enforce_data_policy() with SENSITIVE_FIELDS + provider compliance | | F-OVERSIGHT | `done` | — | ✅ app/ai/oversight.py (108 lines) — DecisionRecord, create_decision_record() | | F-APPR | `done` | — | ✅ app/core/approval.py (160 lines) + app/routes/approvals.py (305 lines) + migration 0123 — ApprovalRequest CRUD API | | F-MEM | `done` | — | ✅ app/ai/agent_memory.py (236 lines) — store/retrieve/search agent memory with embeddings | | F-PROACTIVE | `done` | — | ✅ trigger_dispatcher.py — _dispatch_matching_agents() for context/UI events | | F-WORK | `done` | — | ✅ app/ai/agent_workstream.py (201 lines) — post_agent_message, post_agent_step, post_agent_result, post_approval_request | | F-UI-CTRL | `done` | — | ✅ Bestehendes AI UI Control Plugin (ai_ui_control) | | F-UI-LIST | `done` | — | ✅ AgentDashboard.tsx (831 lines), AgentsOverview.tsx | | F-UI-EDIT | `done` | — | ✅ AgentEditor.tsx (396 lines) | | F-UI-CHAT | `done` | — | ✅ AgentChat.tsx (147 lines) — SSE streaming, extended trace, dry run, cost display | | F-UI-LOG | `done` | — | ✅ AgentRunLog.tsx (82 lines) — timeline view, export JSON/CSV | | F-UI-MON | `done` | — | ✅ AgentMonitor.tsx (86 lines) — live stats, auto-refresh 5s | | F-EMAIL | `done` | — | ✅ prebuilt/email_triage_agent.py — E-Mail-Triage-Agent | | F-CONTACT | `done` | — | ✅ prebuilt/contact_enrichment_agent.py — Contact-Enrichment-Agent | | F-FOLLOW | `done` | — | ✅ prebuilt/follow_up_agent.py — Follow-up-Agent | | F-REPORT | `done` | — | ✅ prebuilt/report_agent.py — Report-Agent | | F-UI-TRIG | `not_started` | — | — | | F-TASK-MODEL | `done` | — | ✅ Extended Task model with polymorphic assignee/entity/creator, subtasks, dependencies, task_type, success_criteria, progress | | F-TASK-API | `done` | — | ✅ Extended task routes with polymorphic filters, subtasks, dependencies | | F-TASK-AGENT | `done` | — | ✅ ai_tools.py (191 lines) — create_task, assign_task, update_task_status, decompose_goal tools | | F-TASK-WORK | `done` | — | ✅ workstream.py — task_card and goal_card blocks | | F-TASK-UI | `done` | — | ✅ TaskBoard.tsx (147 lines), TaskDetail.tsx (287 lines), GoalView.tsx (152 lines) | | F-TASK-MIG | `done` | — | ✅ Migration 0124 — new columns, data migration | | F-TASK-GOAL | `done` | — | ✅ Progress aggregation, success criteria evaluation, parent status propagation | | F-TASK-TEST | `done` | — | ✅ test_unified_tasks.py (414 lines) | | F-TEST | `not_started` | — | — | | F-DOC | `not_started` | — | — | --- ## Phasen E-J Detaillierte Task-Listen werden beim Start der jeweiligen Phase eingetragen. Siehe `PLATFORM_ROADMAP.md` für alle Tasks. --- ## Phase F — Agents ### F.1 ReAct Loop | Task | Status | Forgejo Issue | Verifiziert | |------|-------|---------------|------------| | F-LOOP | `done` | — | ✅ `app/ai/agent_loop.py` — ReActStep/ReActResult dataclasses + `run_react_loop()` mit LLM→Tool→Observe Loop, max_steps/timeout Graceful-Stop, ErrorCategory-basiertes Retry (TRANSIENT→retry, PERMANENT→stop, PARTIAL→continue), Cost-Accumulation, `agent.step` Hook. `AgentRunStep` Model + Migration 0121. `agent_runner.py` auf ReAct-Loop umgestellt. 11/11 Tests grün (mocked, kein DB/LLM benötigt) | --- ## Blockierte Tasks | Task | Grund | Blockiert seit | Lösung | |------|-------|----------------|--------| | — | — | — | — | --- ## Verifizierte Phase-Gate-Reviews | Phase | 8-Check-Pipeline | Deploy | Doku | Performance | Frontend-Tests | Abgeschlossen | |-------|------------------|--------|------|------------|----------------|----------------| | — | — | — | — | — | — | — | --- *Diese Datei wird vom Agent bei jedem Task-Status-Wechsel aktualisiert. Sie ist die schnelle Übersicht über den Fortschritt. Detaillierte Diskussion und Bug-Tracking laufen über Forgejo Issues.*