busya/ss-tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
791 Commits 3 Branches 0 Tags
ce368429f7e31f2f7ac75dbb3ef5811e202d4fe3
Commit Graph

8 Commits

Author SHA1 Message Date
busya
082d6af3ab test(agent-chat): audit guardrail and error handling 2026-07-06 01:20:12 +03:00
busya
ec9bc76a37 cleanup: убрать мёртвые env-переменные, консолидировать чтение в agent/_config.py 
Удалены из кода:
- JWT_SECRET — мёртвая (decode_token использует AUTH_SECRET_KEY)
- SESSION_SECRET_KEY — заменён на прямой AUTH_SECRET_KEY
- POSTGRES_URL — deprecated fallback, удалён из database.py и reencrypt.py

Консолидировано чтение env-переменных agent-модуля:
- Создан agent/_config.py — единый модуль для FASTAPI_URL,
  SERVICE_JWT, GRADIO_*, STORAGE_ROOT, AGENT_* (9 констант)
- Все agent/*.py импортируют из _config вместо разрозненных os.getenv

Удалены or-дефолты (безопасность):
- agent/langgraph_setup.py — удалён hardcoded DB URL postgres:postgres
- agent/langgraph_setup.py — удалены fallback API URL и model name
- scripts/reencrypt.py — удалён hardcoded DB URL postgres:postgres
- plugins/llm_analysis/service.py — удалены or-дефолты URL/app name

.env.example — минимализация:
- backend/.env.example: только 4 обязательные переменные
- root/.env.example: обязательные + docker + SSO/админ

Обновлены тесты (139 passed)
 2026-07-04 14:58:43 +03:00
busya
2f238dee13 fix(agent): seed trace_id for agent process lifecycle 
Agent logs had trace_id='no-trace' because the Gradio process
never called seed_trace_id(). The CotJsonFormatter reads trace_id
from ContextVar — without seeding, it defaults to empty string
displayed as 'no-trace'.

Fix:
- app.py: seed_trace_id() on every agent_handler invocation
- run.py: seed_trace_id() on agent startup (for LLM config fetch)

Each Gradio submit gets a fresh trace_id, making agent logs
correlatable with downstream FastAPI calls.
 2026-06-30 17:33:21 +03:00
busya
a0619ca049 fix(agent): unify logging API + add molecular-cot coverage to agent module 
Phase 1 — API unification:
- Replace direct log() from cot_logger with canonical logger.reason/reflect/explore
  across _confirmation.py, _persistence.py, _tool_resolver.py, app.py

Phase 2 — Gap filling:
- tools.py: add REASON/REFLECT/EXPLORE to 17 C3 tool functions (was 0 logs)
- app.py agent_handler (C4): add lifecycle REASON on entry, REFLECT on exit,
  EXPLORE on OutputParserException + general exception
- langgraph_setup.py create_agent (C4): add REASON with model/config_source,
  EXPLORE on env-var/InMemorySaver fallback, REFLECT on graph compilation
- _tool_resolver.py infer_tool_from_text (C3, 13 branches): REASON on inference
- _persistence.py: REFLECT on save_conversation success, EXPLORE on prefetch

Phase 3 — Plain log migration:
- middleware.py: plain logger.info() -> logger.reason()
- run.py: 7 plain logger.info/warning/error -> molecular REASON/EXPLORE

Phase 4 — Cleanup:
- cot_logger.py: deprecate MarkerLogger (@DEPRECATED + @REPLACED_BY)
- molecular-cot-logging SKILL.md: remove cot_span Section IV (never implemented),
  renumber sections V-VII -> IV-VI, add cot_span rejection rationale

Verification: pytest 27/27, axiom rebuild 5844/2993/0 warnings
 2026-06-30 15:48:46 +03:00
busya
3b4ac807a5 feat(agent+ui): fullstack agent module refactoring + UI/UX improvements 
## Backend: agent module GRACE-Poly compliance
- Split app.py (749→~280 lines) into _tool_resolver, _confirmation, _persistence
- All 18 naked functions wrapped in #region/#endregion contracts
- Fixed @DEFGROUP→@defgroup typos; added @DATA_CONTRACT, @SIDE_EFFECT, CoT logs
- Conversation list API: added last_role, has_tool_calls, has_error, risk_level fields
- Message state detection: Russian/English error patterns (недоступен, unavailable)
- State field preserved in save_conversation messages
- HITL titles: descriptive tool names instead of generic "HITL resume"

## Backend: conversation title generation (two-layer)
- Layer 1: clean_title() — rule-based, strips file markers, pre-fetch blocks, JSON/CSV,
  URLs, code; truncates at 80 chars word boundary (25 unit tests, all edge cases)
- Layer 2: generate_llm_title() — async best-effort LLM titling via /v1/chat/completions
  with per-conversation lock, graceful degradation on failure

## Frontend: conversation list indicators (orthogonal system)
- Status dot (green/yellow/red/blue) per conversation state
- Icon column: tool activity, errors, waiting, completed
- Risk stripe (left border accent) + message count badge + relative time
- Fixed group labels: "Сегодня"/"Вчера" instead of "3 ч"/"5 ч"
- Hide "Окружение: —" when env is empty

## Frontend: guardrails card verification + fixes
- Confirmed all interaction modes: Enter/click confirm, Escape/click deny
- Auto-populate envId from environmentContextStore in DashboardDetailModel
- Better error message: missing_context_hint with recovery guidance

## Design system: semantic tokens
- Added category-* gradient tokens to tailwind.config.js
- Sidebar + Breadcrumbs use semantic tokens (10 categories)
- Raw Tailwind reduced from ~50 to 6 occurrences
- Added skip-to-content link in root layout (+layout.svelte)
- Added aria-label on DashboardDataGrid row checkboxes

## Protocol: INV_7 pragmatic exception
- Modules may exceed 400 lines when contract-dense (every function has #region)
- Recorded in semantics-core SKILL.md with rationale

Total: 5841+ contracts, 2993+ edges, backend 41/41, frontend 2501/2501
 2026-06-30 15:21:05 +03:00
busya
12678c637b fix(agent-chat): streaming state leak, document parser magic bytes, HITL flow 
### Bugfixes — Agent Chat 'Думаю' State Leak
- fix(agent-chat): loadHistory() now resets streamingState/idle + cancels stale
  submission — prevents 'Думаю' state leak across conversation switches
- fix(agent-chat): onDisconnected/onDisconnectedPermanent cascade to
  streamingState — prevents permanent hang on connection loss during stream
- fix(agent-chat):  guard on isLoadingHistory — prevents false commit
  of 'agent unavailable' fallback when switching conversations
- fix(agent-chat): remove race in _sendNow empty-response check vs Svelte
   microtask (duplicate logic removed,  handles correctly)
- fix(stream-processor): confirm_resolved now appends msg.text to partialText
  instead of dropping it

### Bugfixes — Backend PDF Upload
- fix(document-parser): _detect_format_by_magic() — reads file header magic
  bytes as fallback when Gradio loses filename
- fix(document-parser): improved name extraction — tries orig_name, path stem
- fix(document-parser): @RELATION AgentChatTypes -> AgentChat.Types

### HITL Flow & Agent Chat Improvements
- feat(agent): HITL resume confirm/deny with userId/userJwt/envId propagation
- feat(agent): confirm_required metadata fallback via aget_state() after
  'Event loop is closed' error during interrupt
- feat(agent): interrupt_before re-enabled via AGENT_CONFIRM_TOOLS env var
- feat(frontend): debug panel with connection/stream state monitoring
- feat(frontend): AgentChatModel constructor options + onBeforeSend callback
- feat(frontend): crypto.randomUUID() for local conversation ID on first send

### Backend Agent Refactoring
- refactor(agent): langgraph_setup — monkey-patch for PydanticSerializationError
- refactor(agent): tools.py — dual identity headers, expanded tool set
- refactor(agent): run.py — _find_free_port, Gradio server port fallback
- refactor(agent): app.py — file size validation, message truncation, HITL path

### Frontend
- feat(dashboard-hub): DashboardHubModel with filters, pagination, git actions
- feat(ui): DateRangeFilter component
- feat(i18n): new dashboard keys; cache tooltips fix
- fix(i18n): full run tooltips — cache is NOT ignored

### Semantic Protocol
- chore(agents): update all agents with canonical format
- chore(skills): sync semantics-core, semantics-contracts, molecular-cot-logging

### Housekeeping
- chore: remove stale semantic reports (10 files, Jan 2026)
- chore: update 033-gradio-agent-chat specs, contracts, UX, tasks, tests
- chore: add .agents/ directory (mirrors .opencode/ agent layouts)
- chore: update run.sh with DEV_MODE, port management
 2026-06-29 17:15:25 +03:00
busya
1fd5e55db7 fix(agent): auto-fallback to free port on GRADIO_SERVER_PORT conflict 
The Gradio agent (run.py) crashed with OSError when port 7860 was
already occupied by a previous instance. Added _find_free_port() that
scans up to 100 ports from the configured GRADIO_SERVER_PORT and picks
the first available one, logging a warning on fallback.

Contract updates:
- AgentChat.Run: [C:3] [TYPE Module] (was C2/Function), added
  @RATIONALE, @REJECTED, @SIDE_EFFECT for port-finding logic
- AgentChat.GradioApp: added @RATIONALE, @REJECTED
- AgentChat.LangGraph.Setup: added @REJECTED, deduplicated @RELATION
- AgentChat.Tools: added @RATIONALE
 2026-06-10 16:37:02 +03:00
busya
f87ebf5d4b feat(agent): Gradio-powered LangGraph agent chat with streaming, tool calls, file upload, conversation persistence 
- Gradio 5.50.0 ChatInterface with type='messages' streaming
- LangGraph create_react_agent with InMemorySaver checkpointer
- 4 @tool functions: search_dashboards, get_health_summary, list_environments, get_task_status
- Structured ChatMessage metadata (7 discriminator types: stream_token, tool_start/end/error, confirm_required, confirm_resolved, error)
- HITL resume via second submit() with interrupt_before/Command
- Dual-identity RBAC: service JWT + user JWT for tool calls
- File upload (10 MB limit, pdfplumber/xlsx/JSON parser)
- Conversation persistence via POST /api/agent/conversations/save
- REST API: list, history, archive conversations; multi-tab gate; LLM config
- LLM provider selection via Admin -> LLM Settings (assistant_planner_provider)
- Svelte 5 AgentChatModel with stream event queue, dedup, stream_status watcher
- MarkdownRenderer using svelte-markdown with semantic Tailwind tokens
- ToolCallCard (3 states: executing/completed/failed)
- ConversationList with search, date grouping, infinite scroll
- ConnectionIndicator with Gradio health status
- /agent route with two-column layout
- Vite proxy /api/agent/gradio -> Gradio SSE
- Fixed: not_() SQLAlchemy operator, route collision with _admin_routes
- Fixed: conversation_id -> id normalization, .pyc cache staleness
- Fixed: event.data array parsing (Gradio returns [jsonStr, null])
- Requirements pinned: gradio==5.50.0, pydantic>=2.7,<=2.12.3
 2026-06-10 10:27:19 +03:00