Leopoldadmin/leocrm
1
0
Fork 0
Code Issues 363 Pull Requests Actions 7 Packages Projects Releases 1 Wiki Activity
1,160 Commits 2 Branches 4 Tags
063e41e995bf7eae9c5c105cf07db7b439d7470e
Commit Graph

31 Commits

Author SHA1 Message Date
Agent Zero a614ab337b fix: schema drifts, RLS policies, wiki plugin, agent_loop syntax, test imports, frontend error handling
Check Cross-Plugin Imports / check (push) Has been cancelled
Details 
- Migration 0135: Fix 3 VARCHAR length drifts + 2 missing tables (forgejo_reported_errors, pgp_keys)
- Migration 0136: Fix 8 RLS policies referencing app.tenant_id instead of app.current_tenant_id
- wiki/__init__.py: Import WikiPlugin for discover_builtins()
- wiki/plugin.py: Fix SyntaxError (unterminated triple-quoted string)
- agent_loop.py: Fix SyntaxError (stray n character in dict)
- test_p1_6_dms_streaming.py: Fix import (CHUNK_SIZE removed, use _sanitize_filename only)
- conftest.py: Use create_all only (alembic conflicts with create_all in tests)
- frontend errorTypes.ts: asError() now handles nested detail objects
- AGENTS.md: Sub-agents forbidden in this project
- DAMAGE_REPORT.md + SCHEMA_DRIFTS.md: Complete damage assessment
- scripts/schema_drift_check.py: Schema drift checker tool

Tests: 24/24 Phase J + 12/12 Phase K = 36/36 passed
tsc: 0 errors
Frontend build: successful
 2026-08-21 10:02:50 +02:00
Agent Zero 62793a001c feat: I-WORK-HANDOFF + I-WORK-PROACTIVE — approval requests posted to communication with approval_request block, proactive suggestions posted to communication with action_card block
Check Cross-Plugin Imports / check (push) Has been cancelled
Details
2026-08-21 00:05:13 +02:00
Agent Zero 4ab91284c9 feat: Phase I.1 — I-AW (start_workflow + check_workflow_status agent tools) + I-AK (ask_knowledge + search_knowledge agent tools), registered in automation/plugin.py on_activate
Check Cross-Plugin Imports / check (push) Has been cancelled
Details
2026-08-20 23:35:34 +02:00
Agent Zero 8ee88d9b41 fix: connect 10 unconnected backend modules to real code paths (context_builder→agent_runner, agent_permissions→agent_runner, agent_tools→agent_runner, data_policy→agent_runner, oversight→agent_runner+migration 0128, transparency→agent_runner, agent_stream→agent_routes SSE endpoint, agent_memory AI-module deleted, decision_guard→engine, require_approval→agent_runner), 11 integration tests passing
Check Cross-Plugin Imports / check (push) Has been cancelled
Details
2026-08-19 16:25:20 +02:00
Agent Zero f3fbb5d1e8 fix: remove broken agent_workstream import from agent_loop.py (was deleted in cleanup) 2026-08-19 09:53:12 +02:00
Agent Zero 7d86592e54 cleanup: remove all unconnected Phase I+J scaffold code and unconnected Phase F+H modules (workstream_contract, proactive_feed, dashboard, dsgvo_export, onboarding, mcp_exposure, integration_tools, self_improvement, agent_workstream, workflows/workstream, knowledge_sources, knowledge_extraction, knowledge_lifecycle, platform.py routes, 13 frontend files, 2 test files), restore Dashboard.tsx, tsc clean, backend OK 2026-08-19 09:47:20 +02:00
Agent Zero 3854a19705 feat(J): J-SIGNAL/J-PATTERN/J-PROP/J-DRAFT/J-EVAL/J-APPROVAL/J-ACTIVATE/J-MEASURE — controlled self-improvement backend (signals, patterns, proposals, drafts, evaluation, approval, activation, rollback, impact measurement), 26 tests passing 2026-08-19 01:58:18 +02:00
Agent Zero 92ac6229d2 feat(I): I-ONB — onboarding backend (setup wizard status, guide, progress tracking), 46 tests passing 2026-08-19 01:27:13 +02:00
Agent Zero 534adc9aaa feat(I): I-DSGVO/I-DSAR/I-COMP-EXPORT — DSGVO data subject access export, DSAR workflow, compliance evidence export (audit, oversight, approval records, technical policies), 43 tests passing 2026-08-19 01:25:18 +02:00
Agent Zero 94c61a439d feat(I): I-DASH/I-COST/I-USE — platform dashboard, cost tracking, usage analytics (agent/workflow/search/knowledge metrics, cost per agent, budget alerts, success rates), 38 tests passing 2026-08-19 01:20:12 +02:00
Agent Zero df261b1b2c feat(I): I-WORK-PROACTIVE — proactive workstream feed (suggestions, cooldown, dedupe, user settings, priority filtering), 34 tests passing 2026-08-19 01:09:08 +02:00
Agent Zero 6feca2ba98 feat(I): I-WORK-BASE/I-WORK-ACTOR/I-WORK-HANDOFF — workstream contract (typed blocks, unified posting path, human-agent handoff with task creation), 25 tests passing 2026-08-19 00:30:30 +02:00
Agent Zero e8060f6259 feat(I): I-MCP — MCP exposure layer (6 tools: search, ask_knowledge, start_workflow, check_workflow_status, list_agents, create_task), permission-checked, 16 tests passing 2026-08-19 00:26:37 +02:00
Agent Zero dc1321c78b feat(I): I-APPR-LOOP — agent loop human-in-the-loop approval integration (require_approval + approval_tools params, ApprovalRequest creation, workstream notification, pause loop), 8 tests passing 2026-08-19 00:20:36 +02:00
Agent Zero 610af39f75 feat(I): I-AW/I-AK — agent integration tools (start_workflow, check_workflow_status, ask_knowledge, search_knowledge), 6 tests passing 2026-08-19 00:18:07 +02:00
Agent Zero a6e593dc40 feat(H): H-EVT/H-DATA-LIFE/H-RET/H-ASK/H-REV — knowledge lifecycle (event-driven extraction, derived-data propagation, retention policy, ask-knowledge with evidence, review queue), 42 tests passing 2026-08-18 23:17:33 +02:00
Agent Zero 70bbfe93e6 feat(H): H-EXT/H-ENT/H-AUTO/H-CONF — LLM knowledge extraction (entities, relationships, auto-create in GraphRAG, confidence scoring with review queue), 31 tests passing 2026-08-18 12:02:33 +02:00
Agent Zero e09e33e225 feat(H): H-SRC/H-CITE — knowledge source adapter (wiki/dms/mail/communication), evidence references with deep-links and workstream blocks, 23 tests passing 2026-08-18 11:59:39 +02:00
Agent Zero 8ed6d27885 feat(F): F-WORK agent_workstream + F-EMAIL/CONTACT/FOLLOW/REPORT prebuilt agents
Check Cross-Plugin Imports / check (push) Has been cancelled
Details 
- 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
Agent Zero 158feec374 feat(F): F-MEM agent_memory + frontend agent overview components
Check Cross-Plugin Imports / check (push) Has been cancelled
Details 
- 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
Agent Zero 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
Details 
- 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
Agent Zero 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
Details 
- 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
Agent Zero c760b5961c feat(F-LOOP): true ReAct loop with structured Thought/Action/Observation step tracking
Check Cross-Plugin Imports / check (push) Has been cancelled
Details 
- 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
Agent Zero 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
Agent Zero b5546ea7bd feat(B.13-B.17+B.16): Error-Handling-Infra, Observability, Graceful Shutdown, Cost-Cap, API Versioning 
B.13 Error-Handling-Infrastruktur:
- ErrorCategory Enum (TRANSIENT/PERMANENT/PARTIAL), ApiError erweitert
- Einheitliches Error-Response-Format: {code, detail, field, trace_id, retryable, category}
- 3 FastAPI Exception-Handler (ApiError, HTTPException, unhandled)
- classify_exception() Helper, 6 neue Error-Codes
- 28 Tests in test_error_handling.py

B.14 Observability & trace_id-Korrelation:
- trace_id pro Request (UUID4 short) in structlog contextvars
- X-Trace-Id Response-Header
- Sensitive Fields structlog processor
- llm_complete()/llm_embed() akzeptieren trace_id kwarg
- 12 Tests in test_observability.py

B.15 Graceful Shutdown & Connection Draining:
- _shutdown_event + _inflight_requests Tracking in main.py
- drain_all_connections() in ws_helpers.py
- Worker on_shutdown pausiert WorkflowInstances (status=paused)
- 8 Tests in test_graceful_shutdown.py

B.16 API Versioning Strategie:
- Plugin-Dev-Guide Kapitel 30: URL-basiertes Versioning, Breaking Change Prozess

B.17 Cost Overrun Protection:
- llm_monthly_budget_usd + llm_hard_cutoff Settings
- _check_tenant_budget() vor jedem LLM-Call
- _track_tenant_cost() in Redis (INCRBYFLOAT)
- _check_cost_alerts() bei 50%/80%/100% -> post_system_message()
- 20 Tests in test_cost_protection.py

Total: 68 neue Tests, alle grün. Keine Regressionen.
 2026-08-13 21:33:14 +02:00
Agent Zero b231c2d0d3 feat(B-SENS): Sensitive Data Boundary + AI/Data Exposure Policy + AIProvider Compliance
Check Cross-Plugin Imports / check (push) Has been cancelled
Details 
B-SENS: app/core/sensitive_data.py (NEU) — zentrale Sensitive-Field-Verwaltung
- SENSITIVE_FIELDS dict für contact/user/mail_account/system_settings
- is_sensitive(), sanitize_dict(), register_sensitive_fields()
- Integration: errors.py (Log-Redaction), audit.py (Audit-Masking), export_service.py (Export-Filter), embedding.py (Index-Filter)

B-DATA-POL: AI/Data Exposure Policy
- DATA_EXPOSURE_POLICY: pro Entity+Field welche Systeme erlaubt (llm_context/search/embeddings/rag/agent_memory/export)
- filter_for_llm_context/search/embeddings/export/rag/agent_memory()

B-AIPROV-COMP: AIProvider Compliance Metadata
- Migration 0119: 7 neue Spalten an ai_providers (region, hosting_type, dpa_status, retention_policy, training_on_customer_data, transfer_notice, allowed_data_classes)
- llm_client.py: get_provider_compliance() + check_data_class_allowed()

B-PRIV-TEST: 76 Tests in test_sensitive_data.py — alle grün
- Sensitive Fields, Exposure Policy, Provider Compliance, Secrets-always-blocked
- Keine Regression: 39 LLM-Client Tests grün
 2026-08-13 20:39:32 +02:00
Agent Zero e3ca3b3d28 feat(B-LLM): Zentraler LLM Client — llm_complete() + llm_embed() + Migration + Tests + Doku
Check Cross-Plugin Imports / check (push) Has been cancelled
Details 
B-LLM: llm_client.py um generische llm_complete() und llm_embed() erweitert
- Provider-Auswahl, API-Key-Auflösung, Error-Handling, Cost-Tracking
- Retry mit Exponential-Backoff für transient errors
- Timeout konfigurierbar
- Helper: get_api_credentials(), build_model(), _classify_error()

B-LLM-MIG: Alle 8 direkten litellm.acompletion() Calls auf llm_complete() umgestellt
- agent_runner.py, query_understanding.py (2x), ai_proactive (3x), ai_assistant (2x)
- 0 verbleibende direkte litellm.acompletion() Calls außerhalb llm_client.py

B-LLM-TEST: 39 Tests in test_llm_client.py — alle grün
- Mock mode, error handling, embed, helpers, backward compat

B-LLM-DOC: Plugin-Dev-Guide Kapitel 7 (LLM Integration) hinzugefügt
 2026-08-13 16:22:05 +02:00
Agent Zero 879106c4eb Phase 1C: Frontend unified contact UI 2026-07-23 17:17:32 +02:00
Agent Zero ec81940178 Phase 0 Complete: Tasks 0.7-0.20 
- 0.7: UI-Design-Richtlinien (docs/ui-design-guidelines.md, 535 lines)
- 0.8: Theme-Customization Backend (4 theme fields, migration 0023)
- 0.9: Theme-Customization Frontend (SettingsTheme.tsx, themeStore.ts, live preview)
- 0.10: RBAC-Audit (4 plugins secured, 53 routes with require_permission)
- 0.11: LiteLLM-Cleanup (llm_client.py migrated from httpx to litellm)
- 0.12: KI-Agent-Framework docs (plugin-development-guide.md, agent_capabilities field)
- 0.13: Heartbeat configurable (ProactiveSettings, migration 0024, frontend UI)
- 0.14: Unified Search Field-Level RBAC (resolve_permissions + filter_fields_by_permission)
- 0.15: Undo/History-System (EntityHistory model, service, routes, migration 0025, HistoryViewer)
- 0.16: Storage Backend (LocalStorage + S3Storage, DMS/attachments/mail updated)
- 0.17: Import/Export unified Contact fields (firstname, surname, email_1, phone_1)
- 0.18: .gitignore & Config-Cleanup (webui→frontend, python-jose removed, .env untracked)
- 0.19: Mail-Salt Security-Fix (per-account random salt, migration 0026)
- 0.20: AGPL replaced (PyMuPDF→pypdf, OnlyOffice→Collabora, LICENSE + THIRD_PARTY_LICENSES.md)
 2026-07-23 08:42:26 +02:00
leocrm-bot a2452cc04b chore: fix all ruff lint errors + format — 0 errors, 306 tests pass 2026-06-29 17:43:56 +02:00
leocrm-bot 851e7999ba T09: KI-Copilot API + Hybrid Workflow Engine + LLM client + event-triggered workflows 
- KI-Copilot: NL query → proposed actions, execute with RBAC, history, audit logging
- LLM client: mock mode (no API key) + OpenAI-compatible mode (AI_MODEL/AI_API_KEY)
- Action mapper: NL intent → API calls (create/update/delete/search company/contact)
- Workflow engine: step types (action/approval/notification/condition), JSONB steps
- Workflow lifecycle: pending → in_progress → completed/rejected/cancelled
- Event-triggered workflows: event bus → auto-start instances
- Code-engine workflows: onboarding on user.created event
- Approval timeout: auto-reject after configured hours
- 5 new tenant-scoped tables with RLS: ai_conversations, ai_messages, workflows, workflow_instances, workflow_step_history
- Migration 0004: all tables + RLS policies + tenant_id + indexes
- 238 tests pass (30 AC + 105 coverage + 103 existing), 84.12% T09 module coverage
- MissingGreenlet fix: safe accessor helpers for async ORM attribute access
 2026-06-29 08:02:15 +02:00