4ec2ac9eb5
docs(roadmap): add I-APPR-LOOP task — Agent Loop Human-in-the-Loop Approval Integration (ARCH-F-1 finding)
2026-08-18 00:19:35 +02:00
c90c58945a
docs(arch-f): ARCH-F Architecture Review — 10 criteria checked, ✅ PASSED, 2 findings (Agent Loop approval gap, contact_id FK redundant), Phase G clearance granted
2026-08-18 00:16:46 +02:00
a323c706bd
fix(F): Phase F test fixes — UUID handling, MissingGreenlet, contact_id FK, decompose_goal milestone, success_criteria parent propagation, conftest PermissionsPlugin imports
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 23:23:40 +02:00
df57cd389d
docs(audit): update audit-consolidated-errors.md with verified status (2026-08-17) — P0 all fixed, P1 ~32 fixed, P2 ~35 fixed + 15 intentional
2026-08-17 22:27:00 +02:00
45ebbee26f
fix(audit): P2 frontend any→concrete types (181→61), heroicons→lucide-react, missing type exports, toast API, Select options, TaskStatus types; P2-9 hooks.py type annotations
2026-08-17 22:24:24 +02:00
40fd633917
fix(deploy): .gitignore — anchor all dir patterns to root (/logs/, /data/, /build/, /dist/, /venv/, /env/, /htmlcov/) to prevent recursive ignore of frontend source dirs
2026-08-17 20:42:56 +02:00
f888785b39
fix(deploy): .gitignore logs/ excluded frontend/src/pages/logs/ — Docker build failed
2026-08-17 20:33:01 +02:00
680557087e
feat(F): F-TEST + F-DOC + F-UI-TRIG — Phase F complete!
...
- F-TEST: tests/test_phase_f_agents.py (1425 lines, 45 tests, all pass) — ReAct Loop, Permissions, Approvals, Skills, Context Builder, Data Policy, Transparency, Workstream, Budget
- F-DOC: docs/api-documentation.md (Phase F endpoints), docs/plugin-development-guide.md (Agent chapter 32), docs/test-strategy.md (Phase F test conventions)
- F-UI-TRIG: trigger_dispatcher dispatches agents on ui.*/context.* events (already implemented in F-PROACTIVE)
- Bug fix: approval.py metadata reserved attribute renamed to request_metadata
- PROGRESS.md: Phase F marked done, ~155/223 tasks done (70%)
2026-08-17 19:36:42 +02:00
ff08ea8012
docs(progress): update Phase F status — 38/41 tasks done
2026-08-17 18:52:34 +02:00
a53dcc38d5
feat(F.14): Unified Task System — F-TASK-MODEL/API/AGENT/WORK/UI/MIG/GOAL/TEST
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- F-TASK-MODEL: Extended Task model with polymorphic assignee/entity/creator, subtasks, dependencies, task_type, success_criteria, progress
- F-TASK-API: Extended task routes with polymorphic filters, subtasks, dependencies, new lifecycle
- F-TASK-AGENT: ai_tools.py (191 lines) — create_task, assign_task, update_task_status, decompose_goal tools
- F-TASK-WORK: workstream.py — task_card and goal_card blocks in communication system
- F-TASK-UI: TaskBoard.tsx, TaskDetail.tsx, GoalView.tsx frontend components
- F-TASK-MIG: Migration 0124 — new columns, data migration for contact_id/assigned_to
- F-TASK-GOAL: Progress aggregation, success criteria evaluation, parent status propagation
- F-TASK-TEST: test_unified_tasks.py (414 lines)
- i18n updates for task system
2026-08-17 18:51:22 +02:00
06b281ba74
feat(F): F-PROACTIVE consolidate proactive AI — trigger_dispatcher dispatches agents on context/UI events
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 18:40:41 +02:00
131d761936
feat(F): F-UI-CHAT AgentChat, F-UI-LOG AgentRunLog, F-UI-MON AgentMonitor
...
- F-UI-CHAT: AgentChat.tsx (147 lines) — SSE streaming, extended trace toggle, dry run, cost display, stop button
- F-UI-LOG: AgentRunLog.tsx (82 lines) — timeline view, export JSON/CSV
- F-UI-MON: AgentMonitor.tsx (86 lines) — live stats, active runs, auto-refresh 5s
2026-08-17 18:34:29 +02:00
8ed6d27885
feat(F): F-WORK agent_workstream + F-EMAIL/CONTACT/FOLLOW/REPORT prebuilt agents
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- F-WORK: app/ai/agent_workstream.py (201 lines) — post_agent_message, post_agent_step, post_agent_result, post_approval_request
- F-EMAIL: prebuilt/email_triage_agent.py — E-Mail-Triage-Agent with 3 tools, max 10 steps, $0.50 budget
- F-CONTACT: prebuilt/contact_enrichment_agent.py — Contact-Enrichment-Agent with 3 tools, max 8 steps, $0.30 budget
- F-FOLLOW: prebuilt/follow_up_agent.py — Follow-up-Agent with 3 tools, max 8 steps, $0.30 budget
- F-REPORT: prebuilt/report_agent.py — Report-Agent with 2 tools, max 12 steps, $0.50 budget
- All compile checks pass
2026-08-17 18:33:45 +02:00
7ed79d3c1f
feat(F): F-UI-EDIT AgentEditor component + automation API client
2026-08-17 17:30:47 +02:00
158feec374
feat(F): F-MEM agent_memory + frontend agent overview components
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- F-MEM: app/ai/agent_memory.py (236 lines) — store/retrieve/search agent memory with embeddings
- Frontend: AgentDashboard.tsx (831 lines), AgentsOverview.tsx (35 lines) — agent list and dashboard
- agent_memory plugin models updated
2026-08-17 17:14:51 +02:00
638e3f3e1e
feat(F): F-PERM permissions, F-APPR approval, F-AIUSE metadata, F-TRANS transparency, F-DATA-POL data policy, F-OVERSIGHT decision record, F-DRY dry-run, F-AUDIT audit log
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- F-PERM: app/ai/agent_permissions.py (230 lines) — AgentPermissionContext, resolve_agent_permissions(), filter_visible_agents(), check_agent_execute_permission(), optimistic locking
- F-APPR: app/core/approval.py (160 lines) + app/routes/approvals.py (305 lines) + migration 0123 — ApprovalRequest model, CRUD API, approve/reject/expire
- F-AIUSE: app/ai/ai_use_case.py (156 lines) — AIUseCaseMetadata Pydantic model, validate_ai_use_case()
- F-TRANS: app/ai/transparency.py (60 lines) — mark_as_ai_generated(), is_ai_participant()
- F-DATA-POL: app/ai/data_policy.py (210 lines) — enforce_data_policy() with SENSITIVE_FIELDS + provider compliance
- F-OVERSIGHT: app/ai/oversight.py (108 lines) — DecisionRecord, create_decision_record()
- F-DRY: agent_loop.py updated with dry_run parameter
- F-AUDIT: agent_loop.py updated with audit log for tool calls
- agent_routes.py: AI use case metadata endpoints added
- main.py: approval routes registered
- All Python compile checks pass
2026-08-17 16:57:50 +02:00
dbeadd8ab1
feat(F): F-CTX context_builder, F-STR agent_stream, F-DEF agent definition fields, F-SKILL skill_registry, F-TOOL agent_tools
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- F-CTX: app/ai/context_builder.py (282 lines) — build_agent_context() + ReActSystemPromptBuilder
- F-STR: app/ai/agent_stream.py (155 lines) — stream_react_loop() with SSE events (step, status, done, error)
- F-DEF: AgentDefinition fields added (temperature, max_tokens, max_steps, trace_mode, skill_ids, trigger_config, ai_use_case_metadata) + migration 0122
- F-SKILL: app/ai/skill_registry.py (82 lines) — SkillDefinition + SkillRegistry singleton
- F-TOOL: app/ai/agent_tools.py (117 lines) — get_agent_tools() with permission intersection
- Skill CRUD routes: app/plugins/builtins/automation/skill_routes.py
- Tests: test_skill_registry.py (97 lines), test_agent_tools.py (219 lines)
- All Python compile checks pass, tests require PostgreSQL (infra issue, not code bug)
2026-08-17 16:40:55 +02:00
c760b5961c
feat(F-LOOP): true ReAct loop with structured Thought/Action/Observation step tracking
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- app/ai/agent_loop.py: ReActStep + ReActResult dataclasses, run_react_loop()
with LLM→Tool→Observe loop, max_steps/timeout graceful stop, ErrorCategory
retry (TRANSIENT→retry, PERMANENT→stop, PARTIAL→continue), cost accumulation,
agent.step hook, on_step callback
- app/plugins/builtins/automation/models.py: AgentRunStep model
- alembic/versions/0121_agent_run_steps.py: migration for agent run steps table
- app/plugins/builtins/automation/agent_runner.py: refactored to use run_react_loop(),
saves steps to DB, updates AgentRun with cost/status/duration
- tests/test_agent_loop.py: 11 tests (all passing, mocked, no DB/LLM needed)
- PROGRESS.md: Phase F started, F-LOOP marked done
2026-08-17 16:11:26 +02:00
da9be1e2f2
feat(B): complete remaining B-Tasks — B-SCHEMA, B-VEC-BATCH, B-VEC-TEST, B-WS-TEST
...
- B-SCHEMA: docs/schema-authority.md (Core→Alembic, Plugin→Plugin-Migration, Runtime→non-authoritative)
- B-VEC-BATCH: llm_embed already supports batch via litellm.aembedding (verified by test)
- B-VEC-TEST: tests/test_vector_performance.py (HNSW/IVFFlat latency, ef_search tradeoff, batch verification)
- B-WS-TEST: tests/test_ws_helpers.py already has 20+ tests (auth, origin, error, dispatch, cleanup, heartbeat, pub/sub)
- PROGRESS.md: Phase B marked done, ~114/223 tasks done
2026-08-17 16:02:17 +02:00
976a0ab55d
docs(progress): correct outdated B-Phase task statuses — 25 tasks were marked not_started but already implemented
2026-08-17 15:56:08 +02:00
3622022482
fix(dms): add missing FileMetadataResponse import
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 14:12:40 +02:00
765d6d3ab4
feat(dms): fix upload response_model, add content_hash migration, storage settings tab, roadmap external storage
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 14:09:00 +02:00
c6a727fbab
fix(dms): [object Object] error - safely stringify error objects
2026-08-17 13:15:17 +02:00
30c2e2d7c8
feat(ui): logs page, mein konto, remove settings/api-docs from topbar, accent hamburger, api docs in help
2026-08-17 13:07:30 +02:00
c3cc19da10
feat(ui): move back arrow from topbar to sidebar header on all pages
2026-08-17 12:24:04 +02:00
aa20aba2e7
feat(automation): own automation page with tree sidebar, separate from agents
2026-08-17 12:11:14 +02:00
93a53a43f6
feat(ui): remove KI/Automation from agents sidebar, add automation to start page, remove from topbar
2026-08-17 12:03:41 +02:00
7c6f33983d
feat(agents): own agents page with tree sidebar in StartLayout, like settings/help
2026-08-17 11:46:08 +02:00
cbb17c4ddd
feat(ui): clean settings duplicates, move agents to start page, remove from topbar dropdown
2026-08-17 11:39:25 +02:00
81be3478ff
feat(help): help page with tree navigation, 6 help articles, routes in StartLayout
2026-08-17 11:03:16 +02:00
d294f22e81
fix(settings): move padding to inner div to prevent button clipping
2026-08-17 10:51:14 +02:00
76a1da372f
fix(settings): sidebar collapses completely to 0px when hamburger toggled
2026-08-17 10:46:57 +02:00
3bbe8ce029
feat(ui): toggleable settings sidebar + back-to-start arrow in TopBar
2026-08-17 10:41:38 +02:00
47e4ebcbfb
feat(settings): move /settings from AppShell to StartLayout — no workspace sidebar
2026-08-17 10:21:39 +02:00
e0a5a41a6b
feat(start): hamburger toggles start page sidebar, settings accessible from start
2026-08-17 10:14:45 +02:00
371f2a55fe
fix(mail): correct indentation for mail.after_create do_action
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 09:01:28 +02:00
8de35a24a7
fix(hooks): 9 hook wiring fixes — DMS/Calendar name mismatch, Mail/Contact missing triggers
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 07:21:39 +02:00
0a1ba30ed7
fix(imports): agent_runner MailService→Mail model, fix trace_hooks syntax, fix trace_api_contracts warnings
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 07:17:27 +02:00
5b0b1e093a
fix(imports): 3 broken imports — ENTITY_MODELS path, Room→CommConversation, get_cached_mail_summary→MailService
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-17 07:14:29 +02:00
d50615e870
fix(search): GraphRagContract attribute name — graph_rag_search_provider → GraphRAGSearchProvider
Check Cross-Plugin Imports / check (push) Has been cancelled
2026-08-16 23:50:26 +02:00
c3595a1bac
fix(auth): useLogin maps login response to User, ProtectedRoute calls useAuth()
2026-08-16 23:32:07 +02:00
f265eef5ae
fix(auth): useAuth() hook in AppShell/StartLayout + is_system_admin in login response
2026-08-16 23:26:59 +02:00
daa7fe805a
fix(seed): set is_system_admin=True and seed default workspace on startup
...
- Admin user was created without is_system_admin=True, causing sidebar
to be empty (all permission checks failed)
- seed_default_workspace() was never called, so no workspaces existed
- Now seed_admin.py ensures is_system_admin=True for existing admins
and creates a default workspace if none exists
Fixes: sidebar empty, settings inaccessible
2026-08-16 14:39:45 +02:00
e25a1b4fec
fix(ui): CommandPalette outside Router context — white page fix; remove PWA; fix CSP for Google Fonts
2026-08-16 13:50:39 +02:00
db97a39133
feat(audit): P1 cross-tenant/RBAC tests, P3 test fixes, P2/P3 frontend fixes
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- P1-Tests: 12 test files with new cross-tenant isolation + RBAC tests
- P3-Tests: 8 fixes (duplicate fixtures, sys.path.insert, unused imports, KeyError)
- P3-Frontend: LucideIcons → ICON_MAP (2 files), inline styles → Tailwind (2 files)
- P3-Frontend: DOMPurify for iframe XSS, redundant regex removed, console.log → console.debug
- P2-Frontend: 2 notification API TODOs retained (requires larger refactor)
- conftest.py: create_no_perm_user helper added
- pyproject.toml: pythonpath for scripts/ added
- All checks green: ruff 0, F821 0, tsc 0, app 495 routes, cross-plugin 0
2026-08-16 01:30:02 +02:00
abbe7a18fc
fix(audit): P0-P3 audit fixes — 838 ruff errors → 0, 30 F821 bugs fixed, 118 files changed
...
- P0: hooks.py 3-tuple fix, trigger_dispatcher Contract, contacts/plugin unregister_actions_by_owner
- P0: 5 test files — check_permission mocks removed, hardcoded DB credential → env var
- P1: attachment_service DmsFile via Contract helper, restore_registry/history_hooks dedup
- P1: mail/plugin restore unregister, mcp_client datetime.now(UTC), saved_views/filters patterns
- P1: ProtectedRoute fail-closed, 13 test assertion fixes (bcrypt, DB-URLs, SECRET_KEYs)
- P2: deprecated notifications → post_system_message (3 files), forgejo Base, report_generator lazy import
- P2: webhooks permissions, deps.py/roles.py plugin perms removed, import_export default
- P2: address/tags/entity_links patterns removed, worker.py Contract-Umgehungen fixed
- P2: 28 frontend TODOs (hardcoded constants, deprecated notification API)
- P3: dead code, duplicates, deprecated imports, private attr, __import__ inline
- P3: 8 frontend TODOs (LucideIcons, inline styles, XSS, i18n)
- ruff: 838 → 0 (612 auto-fix + 246 manual + 27 F821 regression fix)
- F821: 30 → 0 (AutomationDefinition, DmsFile, user_id, Path, Any, String)
- Contract-Umgehungen: 2 neue gefunden (worker.py:169, worker.py:280) und gefixt
2026-08-16 01:17:18 +02:00
3d9b76cea4
feat(E): Unified Search — 24 Tasks complete
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- SPIKE-E: FTS+Vector+Permission benchmark on 10k records (all <30ms)
- E-PROV: supports_fts/vector/rag/graph capability flags on all providers
- E-FTS/VEC: All 11 providers refactored to BaseSearchProvider with permission filtering
- E-PERM: Over-fetch strategy for vector+permission (15x faster than ANY() filter)
- E-FUSE: rrf_fusion_multi() for N-way RRF over FTS+Vector+RAG+Graph
- E-LLM: Query understanding cleaned up to use central llm_complete()
- E-CHUNK: Document chunking module + document_chunks table with HNSW index
- E-EMB: Chunk embedding ARQ jobs (index_file_chunks, reindex_chunks)
- E-RAG: RAG retrieval via FileSearchProvider.search_rag()
- E-GRAPH: GraphRAG BFS traversal via GraphRAGSearchProvider.search_graph()
- E-IX-EVT: Auto-indexing via outbox events + delete/cleanup handlers
- E-IX-RE: Batch reindex with progress tracking + reindex_all job
- E-DATA-LIFE: Lifecycle module (remove/rebuild/restore/correct) + API endpoints
- E-K-MEM: AgentMemorySearchProvider
- E-P-AI: AIChatSearchProvider
- E-P-WF: WorkflowSearchProvider
- E-P-COMM: ConversationSearchProvider verified (already on BaseSearchProvider)
- E-API: Filter params (date_from/to, tags, sort) + /facets endpoint
- E-TOOL: unified_search AI tool registered in ToolRegistry
- E-MCP: Search tool in MCP server with normal RBAC/tenant checks
- E-UI-CMD: CommandPalette (Cmd+K) with debounced search + recent searches
- E-UI-FAC: SearchFacets, SearchResultCard, SavedSearches components
- E-TEST: 40 new tests in test_unified_search_phase_e.py (105 total green)
- E-DOC: api-documentation.md, plugin-development-guide.md, test-strategy.md updated
105 tests passing, TypeScript clean.
2026-08-14 01:34:58 +02:00
60f30d021b
fix(deploy): MAIL_ENCRYPTION_KEY zu docker-compose.yaml, .env.docker.example und deploy-guide.md hinzugefügt
...
Phase B Security-Fix (5d1b239
2026-08-13 23:50:04 +02:00
a4d0f0c35d
feat(D): Phase D — Undo/Restore komplett implementiert
...
Check Cross-Plugin Imports / check (push) Has been cancelled
- D-GEN: RestoreRegistry mit RestoreConfig (model_class, restore_permission, excluded_fields, special_handler)
- D-HOOK: history_hooks.py mit register_history_hooks() für after_create/update/delete
- D-CORE: Company create+update record_history in companies.py
- D-PLUG: Task/Calendar/DMS record_history in services/routes
- D-SOFT: Alle registrierten Entitäten haben deleted_at + un-delete via Registry
- D-MAIL: Mail special_handler (IMAP Trash-Move, Folder-Verify) + record_history in delete/move
- D-TRASH: GET /entity-history/trash (filterbar, paginiert) + Frontend Trash.tsx
- D-TOAST: UndoToast.tsx (5s Auto-Dismiss, useUndoToast Hook)
- D-HIST-UI: HistoryPanel.tsx (Timeline, Diff-View, Restore-Button)
- D-BULK: POST /entity-history/bulk-restore mit partial_success Semantik
- D-RET: POST /entity-history/retention/archive (GDPR hard-delete >90 Tage)
- D-TEST: 26 Tests in test_restore_registry.py, alle grün
- D-DOC: test-strategy.md + security_kernel.md aktualisiert
Backend: 10 Dateien, Frontend: 7 Dateien, Tests: 1 Datei, Docs: 3 Dateien
26/26 Tests passed, TSC 0 errors, App import 492 routes
2026-08-13 23:08:29 +02:00
29410f19d3
docs(C.5): Phase C.5 done — 8 Tasks, 45 Tests
2026-08-13 22:43:52 +02:00
Agent Zero