Initial SQL-only 1C adapter baseline

2026-07-22 03:03:47 +03:00
commit e2503b77e7
545 changed files with 184711 additions and 0 deletions
@@ -0,0 +1,15 @@
+# Core
+
+Общее ядро LLM-платформы.
+
+`core` отвечает за переиспользуемые возможности:
+
+- реестр моделей;
+- инференс;
+- обучение и дообучение;
+- eval-тесты;
+- GPU deployment;
+- хранение;
+- мониторинг.
+
+Прикладная логика задач должна находиться в `plugins`.
@@ -0,0 +1 @@
+"""Shared core platform modules."""
@@ -0,0 +1,45 @@
+# Core Deploy
+
+Общие правила развертывания.
+
+GPU workload target: `docker-gpu.cin.su`.
+
+Infrastructure/lightweight proxy target: `docker.cin.su`.
+
+В репозитории храним только воспроизводимую конфигурацию и документацию. Секреты, токены и пароли не коммитим.
+
+Локальные модели и RAG-артефакты проверяются отдельно перед переносом или
+Docker-запуском: `docs/runbooks/artifact-portability.md`.
+
+Локальная консоль управления запускается командой:
+
+```powershell
+powershell -NoProfile -ExecutionPolicy Bypass -File scripts/run_management_console.ps1
+```
+
+Runbook: `docs/runbooks/management-console.md`.
+
+1C MCP proxy:
+
+```text
+docs/runbooks/adapter-1c-mcp.md
+core/deploy/docker/adapter-1c-mcp/compose.yaml
+```
+
+1C REST adapter on GPU host:
+
+```text
+core/deploy/docker-gpu/adapter-1c/compose.yaml
+```
+
+1C agent service (подпроект):
+
+```text
+core/deploy/docker/1c-agent/compose.yaml
+docs/runbooks/1c-agent.md
+```
+
+The current container is read-first and route-index backed. It serves
+`http://docker-gpu.cin.su:8011`, keeps the route index in the
+`adapter-1c_adapter-1c-data` Docker volume, and is used by
+`adapter-1c-mcp` through `ONEC_ADAPTER_URL`.
@@ -0,0 +1,7 @@
+# Docker GPU Deployment
+
+Целевой хост для GPU-развертываний: `docker-gpu.cin.su`.
+
+Здесь будут находиться compose-файлы, env-шаблоны и инструкции для запуска GPU-сервисов.
+
+Секреты должны передаваться через окружение, секрет-хранилище или настройки хоста, но не через git.
@@ -0,0 +1,11 @@
+ADAPTER_1C_IMAGE=adapter-1c-rest:latest
+ADAPTER_1C_CONTAINER_NAME=adapter-1c-rest
+ADAPTER_1C_HOST_PORT=8011
+
+# Live SQL connections. Keep real credentials outside git.
+# Example:
+# ONEC_SQL_BASES_JSON={"upo_test":{"server":"sql-host","database":"upo_test","user":"configured_login","password_env":"ONEC_SQL_PASSWORD_UPO_TEST"}}
+# ONEC_SQL_PASSWORD_UPO_TEST=put-this-only-in-a-real-non-committed-env-file
+ONEC_SQL_BASES_JSON=
+# Optional path inside the container to a JSON file with the same shape as ONEC_SQL_BASES_JSON.
+ONEC_SQL_BASES_JSON_FILE=/data/onec-sql-bases.json
@@ -0,0 +1,32 @@
+name: adapter-1c
+
+services:
+  adapter-1c-rest:
+    build:
+      context: ../../../../plugins/1c
+      dockerfile: connector/Dockerfile
+    image: ${ADAPTER_1C_IMAGE:-adapter-1c-rest:latest}
+    container_name: ${ADAPTER_1C_CONTAINER_NAME:-adapter-1c-rest}
+    restart: unless-stopped
+    ports:
+      - "${ADAPTER_1C_HOST_PORT:-8011}:8011"
+    volumes:
+      - adapter-1c-data:/data
+    environment:
+      ONEC_ADAPTER_HOST: 0.0.0.0
+      ONEC_ADAPTER_PORT: 8011
+      ONEC_ADAPTER_SERVICE_TOKEN: ${ONEC_ADAPTER_SERVICE_TOKEN:-}
+      ONEC_ADAPTER_ALLOW_UNAUTHENTICATED_ADMIN: ${ONEC_ADAPTER_ALLOW_UNAUTHENTICATED_ADMIN:-true}
+      ONEC_SQL_BASES_JSON: ${ONEC_SQL_BASES_JSON:-}
+      ONEC_SQL_BASES_JSON_FILE: ${ONEC_SQL_BASES_JSON_FILE:-/data/onec-sql-bases.json}
+      ONEC_INFOBASE_USER_ADMIN_BASES_JSON: ${ONEC_INFOBASE_USER_ADMIN_BASES_JSON:-}
+      ONEC_INFOBASE_USER_ADMIN_BASES_JSON_FILE: ${ONEC_INFOBASE_USER_ADMIN_BASES_JSON_FILE:-/data/onec-infobase-user-admin.json}
+      ONEC_INFOBASE_USER_ADMIN_TOKEN_UPO_TEST: ${ONEC_INFOBASE_USER_ADMIN_TOKEN_UPO_TEST:-}
+      ONEC_INFOBASE_USER_ADMIN_ALLOW_UNAUTHENTICATED: ${ONEC_INFOBASE_USER_ADMIN_ALLOW_UNAUTHENTICATED:-false}
+      ONEC_REPOSITORY_RUNNER_TOKEN: ${ONEC_REPOSITORY_RUNNER_TOKEN:-}
+      ONEC_ADAPTER_ENABLE_EXTERNAL_1C: ${ONEC_ADAPTER_ENABLE_EXTERNAL_1C:-false}
+      ONEC_REPOSITORY_REQUEST_TTL_SECONDS: ${ONEC_REPOSITORY_REQUEST_TTL_SECONDS:-86400}
+      ONEC_REPOSITORY_CONFIRMATION_TTL_SECONDS: ${ONEC_REPOSITORY_CONFIRMATION_TTL_SECONDS:-7200}
+
+volumes:
+  adapter-1c-data:
@@ -0,0 +1,17 @@
+# Copy to .env on the deployment host and adjust values there.
+# Do not commit real tokens, private paths, or credentials.
+
+LLAMA_CONTAINER_NAME=llm-llama-devstral-1c
+LLAMA_IMAGE=ghcr.io/ggml-org/llama.cpp:server-cuda
+LLAMA_HOST_PORT=8080
+LLAMA_MODEL_PATH=/models/gguf/1c/devstral-small-2-24b-instruct-2512-q4_k_m/mistralai_Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf
+LLAMA_SERVED_MODEL_NAME=devstral-1c-q4
+LLAMA_CTX_SIZE=32768
+LLAMA_GPU_LAYERS=999
+LLAMA_THREADS=8
+LLAMA_PARALLEL=1
+LLAMA_FIT=off
+LLAMA_REASONING=off
+LLAMA_REASONING_FORMAT=none
+LLAMA_CHAT_TEMPLATE=mistral-v7-tekken
+HOST_MODELS_DIR=/models
@@ -0,0 +1,43 @@
+services:
+  llama-cpp:
+    image: ${LLAMA_IMAGE:-ghcr.io/ggml-org/llama.cpp:server-cuda}
+    container_name: ${LLAMA_CONTAINER_NAME:-llm-llama-devstral-1c}
+    restart: unless-stopped
+    ports:
+      - "${LLAMA_HOST_PORT:-8080}:8080"
+    volumes:
+      - ${HOST_MODELS_DIR:-/models}:/models
+    command:
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8080"
+      - --model
+      - ${LLAMA_MODEL_PATH}
+      - --alias
+      - ${LLAMA_SERVED_MODEL_NAME:-devstral-1c-q4}
+      - --ctx-size
+      - ${LLAMA_CTX_SIZE:-32768}
+      - --n-gpu-layers
+      - ${LLAMA_GPU_LAYERS:-999}
+      - --threads
+      - ${LLAMA_THREADS:-8}
+      - --parallel
+      - ${LLAMA_PARALLEL:-1}
+      - --fit
+      - ${LLAMA_FIT:-off}
+      - --reasoning
+      - ${LLAMA_REASONING:-off}
+      - --reasoning-format
+      - ${LLAMA_REASONING_FORMAT:-none}
+      - --chat-template
+      - ${LLAMA_CHAT_TEMPLATE:-mistral-v7-tekken}
+      - --skip-chat-parsing
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,19 @@
+# Qwen3-Coder Q6 GPU llama.cpp settings for docker-gpu.cin.su.
+# This model is too large to keep online together with SDXL/vLLM on a 24 GiB RTX 4090.
+
+LLAMA_CONTAINER_NAME=llm-llama-qwen3-coder-q6-test
+LLAMA_IMAGE=ghcr.io/ggml-org/llama.cpp:server-cuda
+LLAMA_HOST_PORT=8081
+LLAMA_MODEL_PATH=/models/gguf/1c/qwen3-coder-30b-a3b-instruct-q6_k/Qwen3-Coder-30B-A3B-Instruct-Q6_K.gguf
+LLAMA_SERVED_MODEL_NAME=qwen3-coder-1c-q6
+LLAMA_CTX_SIZE=8192
+LLAMA_GPU_LAYERS=auto
+LLAMA_THREADS=12
+LLAMA_PARALLEL=1
+LLAMA_FIT=on
+LLAMA_REASONING=auto
+LLAMA_REASONING_FORMAT=none
+LLAMA_CHAT_TEMPLATE=chatml
+# Optional future LoRA path after converting the trained adapter to GGUF for llama.cpp:
+# LLAMA_LORA_PATH=/models/adapters/1c/qwen3-coder-30b-a3b-1c-lora-v1.gguf
+HOST_MODELS_DIR=Z:/LLM/models
@@ -0,0 +1,24 @@
+services:
+  model-chat-ui:
+    image: ${MODEL_CHAT_IMAGE:-vllm/vllm-openai:v0.10.2}
+    container_name: ${MODEL_CHAT_CONTAINER_NAME:-llm-model-chat-ui}
+    restart: unless-stopped
+    ports:
+      - "${MODEL_CHAT_HOST_PORT:-8765}:8765"
+    volumes:
+      - ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
+      - ${HOST_MODELS_DIR:-Z:/LLM/models}:/models:ro
+      - ${HOST_REPORTS_DIR:-Z:/LLM/reports}:/reports
+    environment:
+      MODEL_CHAT_REPORT_ROOT: /reports
+    working_dir: /app
+    entrypoint:
+      - python3
+    command:
+      - scripts/model_chat_server.py
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8765"
+      - --static-dir
+      - /app
@@ -0,0 +1,25 @@
+services:
+  train-1c-lora:
+    image: ${TRAINING_IMAGE:-pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime}
+    container_name: llm-train-1c-lora
+    working_dir: /workspace
+    shm_size: 16gb
+    volumes:
+      - ${HOST_WORKSPACE_DIR:-/workspace/LLM}:/workspace
+      - ${HOST_MODELS_DIR:-/models}:/models
+    command:
+      - bash
+      - -lc
+      - |
+        pip install -r requirements-training.txt &&
+        python scripts/preflight_1c_training.py --config ${TRAINING_CONFIG:-/workspace/plugins/1c/training/configs/qwen3-coder-30b-a3b-lora.yaml} &&
+        if [ "${PREFLIGHT_ONLY:-0}" = "1" ]; then exit 0; fi &&
+        python scripts/train_1c_lora.py --config ${TRAINING_CONFIG:-/workspace/plugins/1c/training/configs/qwen3-coder-30b-a3b-lora.yaml}
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,4 @@
+TRAINING_IMAGE=pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime
+HOST_WORKSPACE_DIR=Z:/LLM/model-chat-app
+HOST_MODELS_DIR=Z:/LLM/models
+TRAINING_CONFIG=/workspace/plugins/1c/training/configs/qwen3-coder-30b-a3b-lora.yaml
@@ -0,0 +1,38 @@
+name: llm-transformers-audio
+
+services:
+  audio-api:
+    image: ${TRANSFORMERS_IMAGE:-vllm/vllm-openai:v0.10.2}
+    container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-audio}
+    restart: unless-stopped
+    ipc: host
+    ports:
+      - "${TRANSFORMERS_HOST_PORT:-8020}:8020"
+    environment:
+      HF_HOME: /root/.cache/huggingface
+      MODEL_PATH: ${MODEL_PATH:-/models/audio/whisper-large-v3-turbo}
+      SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-whisper-large-v3-turbo}
+      PORT: "8020"
+      LOAD_ON_START: ${LOAD_ON_START:-0}
+    volumes:
+      - ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
+      - ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
+      - ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
+    working_dir: /app
+    entrypoint: python3
+    command:
+      - scripts/transformers_plugin_server.py
+      - --plugin
+      - audio
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8020"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,9 @@
+HOST_APP_DIR=Z:/LLM/model-chat-app
+HOST_MODELS_DIR=Z:/LLM/models
+HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
+TRANSFORMERS_IMAGE=vllm/vllm-openai:v0.10.2
+TRANSFORMERS_CONTAINER_NAME=llm-transformers-audio
+TRANSFORMERS_HOST_PORT=8020
+MODEL_PATH=/models/audio/whisper-large-v3-turbo
+SERVED_MODEL_NAME=whisper-large-v3-turbo
+LOAD_ON_START=0
@@ -0,0 +1,10 @@
+FROM vllm/vllm-openai:v0.10.2
+
+RUN python3 -m pip install --no-cache-dir \
+    "diffusers>=0.35.0" \
+    "transformers>=4.51.0" \
+    "accelerate>=1.0.0" \
+    safetensors \
+    pillow
+
+WORKDIR /app
@@ -0,0 +1,42 @@
+name: llm-transformers-image
+
+services:
+  image-api:
+    image: ${TRANSFORMERS_IMAGE:-llm-transformers-image:latest}
+    build:
+      context: ../../../../
+      dockerfile: core/deploy/docker-gpu/transformers/image.Dockerfile
+    container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-image}
+    restart: unless-stopped
+    ipc: host
+    ports:
+      - "${TRANSFORMERS_HOST_PORT:-8040}:8040"
+    environment:
+      HF_HOME: /root/.cache/huggingface
+      MODEL_PATH: ${MODEL_PATH:-/models/image/sdxl-base-1.0}
+      EDIT_MODEL_PATH: ${EDIT_MODEL_PATH:-/models/image/sdxl-inpainting-1.0}
+      SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-sdxl-image}
+      PORT: "8040"
+      LOAD_ON_START: ${LOAD_ON_START:-1}
+      BACKGROUND_LOAD_ON_START: ${BACKGROUND_LOAD_ON_START:-1}
+    volumes:
+      - ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
+      - ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
+      - ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
+    working_dir: /app
+    entrypoint: /bin/sh
+    command:
+      - -lc
+      - >
+        exec python3 scripts/transformers_plugin_server.py
+        --plugin image
+        --host 0.0.0.0
+        --port 8040
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,11 @@
+HOST_APP_DIR=Z:/LLM/model-chat-app
+HOST_MODELS_DIR=Z:/LLM/models
+HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
+TRANSFORMERS_IMAGE=llm-transformers-image:latest
+TRANSFORMERS_CONTAINER_NAME=llm-transformers-image
+TRANSFORMERS_HOST_PORT=8040
+MODEL_PATH=/models/image/sdxl-base-1.0
+EDIT_MODEL_PATH=/models/image/sdxl-inpainting-1.0
+SERVED_MODEL_NAME=sdxl-image
+LOAD_ON_START=1
+BACKGROUND_LOAD_ON_START=1
@@ -0,0 +1,11 @@
+HOST_APP_DIR=Z:/LLM/model-chat-app
+HOST_MODELS_DIR=Z:/LLM/models
+HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
+TRANSFORMERS_IMAGE=llm-transformers-image:latest
+TRANSFORMERS_CONTAINER_NAME=llm-transformers-image
+TRANSFORMERS_HOST_PORT=8040
+MODEL_PATH=/models/image/qwen-image-edit
+EDIT_MODEL_PATH=/models/image/qwen-image-edit
+SERVED_MODEL_NAME=qwen-image-edit
+LOAD_ON_START=0
+BACKGROUND_LOAD_ON_START=0
@@ -0,0 +1,38 @@
+name: llm-transformers-translation
+
+services:
+  translation-api:
+    image: ${TRANSFORMERS_IMAGE:-vllm/vllm-openai:v0.10.2}
+    container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-translation}
+    restart: unless-stopped
+    ipc: host
+    ports:
+      - "${TRANSFORMERS_HOST_PORT:-8010}:8010"
+    environment:
+      HF_HOME: /root/.cache/huggingface
+      MODEL_PATH: ${MODEL_PATH:-/models/translation/lmt-60-4b}
+      SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-lmt-60-4b}
+      PORT: "8010"
+      LOAD_ON_START: ${LOAD_ON_START:-0}
+    volumes:
+      - ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
+      - ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
+      - ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
+    working_dir: /app
+    entrypoint: python3
+    command:
+      - scripts/transformers_plugin_server.py
+      - --plugin
+      - translation
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8010"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,9 @@
+HOST_APP_DIR=Z:/LLM/model-chat-app
+HOST_MODELS_DIR=Z:/LLM/models
+HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
+TRANSFORMERS_IMAGE=vllm/vllm-openai:v0.10.2
+TRANSFORMERS_CONTAINER_NAME=llm-transformers-translation
+TRANSFORMERS_HOST_PORT=8010
+MODEL_PATH=/models/translation/lmt-60-4b
+SERVED_MODEL_NAME=lmt-60-4b
+LOAD_ON_START=0
@@ -0,0 +1,38 @@
+name: llm-transformers-video
+
+services:
+  video-api:
+    image: ${TRANSFORMERS_IMAGE:-vllm/vllm-openai:v0.10.2}
+    container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-video}
+    restart: unless-stopped
+    ipc: host
+    ports:
+      - "${TRANSFORMERS_HOST_PORT:-8030}:8030"
+    environment:
+      HF_HOME: /root/.cache/huggingface
+      MODEL_PATH: ${MODEL_PATH:-/models/video/qwen2.5-vl-7b-instruct}
+      SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-qwen2.5-vl-7b-instruct}
+      PORT: "8030"
+      LOAD_ON_START: ${LOAD_ON_START:-0}
+    volumes:
+      - ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
+      - ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
+      - ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
+    working_dir: /app
+    entrypoint: python3
+    command:
+      - scripts/transformers_plugin_server.py
+      - --plugin
+      - video
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8030"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,9 @@
+HOST_APP_DIR=Z:/LLM/model-chat-app
+HOST_MODELS_DIR=Z:/LLM/models
+HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
+TRANSFORMERS_IMAGE=vllm/vllm-openai:v0.10.2
+TRANSFORMERS_CONTAINER_NAME=llm-transformers-video
+TRANSFORMERS_HOST_PORT=8030
+MODEL_PATH=/models/video/qwen2.5-vl-7b-instruct
+SERVED_MODEL_NAME=qwen2.5-vl-7b-instruct
+LOAD_ON_START=0
@@ -0,0 +1,20 @@
+# Copy to .env on the deployment host and adjust values there.
+# Do not commit real tokens, private paths, or credentials.
+
+VLLM_CONTAINER_NAME=llm-vllm-text
+VLLM_IMAGE=vllm/vllm-openai:latest
+VLLM_MODEL_ID=Qwen/Qwen3-4B-Instruct-2507
+VLLM_SERVED_MODEL_NAME=qwen3-4b-instruct
+VLLM_LORA_MODULES=qwen3-4b-1c=/models/adapters/1c/qwen3-4b-1c-lora-v1
+VLLM_MAX_LORAS=1
+VLLM_HOST_PORT=8000
+VLLM_GPU_MEMORY_UTILIZATION=0.90
+VLLM_MAX_MODEL_LEN=32768
+VLLM_DTYPE=auto
+
+# Local model/cache paths on docker-gpu.cin.su.
+HOST_MODELS_DIR=/models
+HOST_HF_CACHE_DIR=/models/cache/huggingface
+
+# Set on the host only if the model source requires it.
+HF_TOKEN=
@@ -0,0 +1,42 @@
+services:
+  vllm:
+    image: ${VLLM_IMAGE:-vllm/vllm-openai:latest}
+    container_name: ${VLLM_CONTAINER_NAME:-llm-vllm-text}
+    restart: unless-stopped
+    ipc: host
+    ports:
+      - "${VLLM_HOST_PORT:-8000}:8000"
+    environment:
+      HF_HOME: /root/.cache/huggingface
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN:-}
+    volumes:
+      - ${HOST_MODELS_DIR:-/models}:/models
+      - ${HOST_HF_CACHE_DIR:-/models/cache/huggingface}:/root/.cache/huggingface
+    command:
+      - --model
+      - ${VLLM_MODEL_ID:-Qwen/Qwen3-4B-Instruct-2507}
+      - --served-model-name
+      - ${VLLM_SERVED_MODEL_NAME:-qwen3-4b-instruct}
+      - --enable-lora
+      - --max-loras
+      - ${VLLM_MAX_LORAS:-1}
+      - --lora-modules
+      - ${VLLM_LORA_MODULES:-qwen3-4b-1c=/models/adapters/1c/qwen3-4b-1c-lora-v1}
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8000"
+      - --gpu-memory-utilization
+      - ${VLLM_GPU_MEMORY_UTILIZATION:-0.90}
+      - --max-model-len
+      - ${VLLM_MAX_MODEL_LEN:-32768}
+      - --dtype
+      - ${VLLM_DTYPE:-auto}
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities:
+                - gpu
@@ -0,0 +1,24 @@
+ONEC_AGENT_IMAGE=onec-agent:latest
+ONEC_AGENT_CONTAINER_NAME=onec-agent
+ONEC_AGENT_HOST_PORT=8090
+ONEC_AGENT_DEFAULT_BASE_URL=http://docker-gpu.cin.su:8000
+ONEC_AGENT_DEFAULT_MODEL=qwen3-4b-instruct-2507
+ONEC_ADAPTER_URL=http://docker-gpu.cin.su:8011
+
+# Для интеграции с несколькими ИИ провайдерскими конечными точками
+# Формат JSON:
+# {
+#   "default": {
+#     "type": "openai-compatible",
+#     "base_url": "http://docker-gpu.cin.su:8000",
+#     "model": "qwen3-4b-instruct-2507"
+#   },
+#   "openrouter": {
+#     "type": "openai-compatible",
+#     "base_url": "https://openrouter.ai/api/v1",
+#     "model": "some-openai-compatible-id",
+#     "api_key_env": "OPENROUTER_API_KEY"
+#   }
+# }
+ONEC_AGENT_PROVIDERS=
+OPENROUTER_API_KEY=
@@ -0,0 +1,26 @@
+name: onec-agent
+
+services:
+  onec-agent:
+    build:
+      context: ../../../../
+      dockerfile: plugins/1c/agent/Dockerfile
+    image: ${ONEC_AGENT_IMAGE:-onec-agent:latest}
+    container_name: ${ONEC_AGENT_CONTAINER_NAME:-onec-agent}
+    restart: unless-stopped
+    ports:
+      - "${ONEC_AGENT_HOST_PORT:-8090}:8090"
+    volumes:
+      - onec-agent-data:/app/data
+    environment:
+      ONEC_AGENT_HOST: 0.0.0.0
+      ONEC_AGENT_PORT: 8090
+      ONEC_AGENT_DB_PATH: /app/data/onec-agent.db
+      ONEC_AGENT_DEFAULT_BASE_URL: ${ONEC_AGENT_DEFAULT_BASE_URL:-http://docker-gpu.cin.su:8000}
+      ONEC_AGENT_DEFAULT_MODEL: ${ONEC_AGENT_DEFAULT_MODEL:-qwen3-4b-instruct-2507}
+      ONEC_ADAPTER_URL: ${ONEC_ADAPTER_URL:-http://docker-gpu.cin.su:8011}
+      ONEC_ADAPTER_TOKEN: ${ONEC_ADAPTER_TOKEN:-}
+      ONEC_AGENT_PROVIDERS: ${ONEC_AGENT_PROVIDERS:-}
+
+volumes:
+  onec-agent-data:
@@ -0,0 +1,11 @@
+ADAPTER_1C_MCP_IMAGE=adapter-1c-mcp:latest
+ADAPTER_1C_MCP_CONTAINER_NAME=adapter-1c-mcp
+ADAPTER_1C_MCP_HOST_PORT=8021
+
+# REST 1C adapter endpoint. The MCP proxy forwards onec_request(method,payload)
+# to this service. Change it when the real adapter container is deployed.
+ONEC_ADAPTER_URL=http://docker-gpu.cin.su:8011
+ONEC_ADAPTER_TIMEOUT_SECONDS=120
+
+# Optional bearer token for the REST adapter. Do not commit real secrets.
+ONEC_ADAPTER_TOKEN=
@@ -0,0 +1,17 @@
+name: adapter-1c-mcp
+
+services:
+  adapter-1c-mcp:
+    build:
+      context: ../../../../plugins/1c/mcp
+      dockerfile: Dockerfile
+    image: ${ADAPTER_1C_MCP_IMAGE:-adapter-1c-mcp:latest}
+    container_name: ${ADAPTER_1C_MCP_CONTAINER_NAME:-adapter-1c-mcp}
+    restart: unless-stopped
+    ports:
+      - "${ADAPTER_1C_MCP_HOST_PORT:-8021}:8021"
+    environment:
+      PORT: "8021"
+      ONEC_ADAPTER_URL: ${ONEC_ADAPTER_URL:-http://docker-gpu.cin.su:8011}
+      ONEC_ADAPTER_TOKEN: ${ONEC_ADAPTER_TOKEN:-}
+      ONEC_ADAPTER_TIMEOUT_SECONDS: ${ONEC_ADAPTER_TIMEOUT_SECONDS:-240}
@@ -0,0 +1,12 @@
+# Core Evals
+
+Общие правила оценки качества моделей.
+
+Eval-наборы должны позволять сравнить:
+
+- базовую модель;
+- модель с RAG;
+- модель с адаптером;
+- разные версии адаптеров.
+
+Для каждого плагина могут быть собственные eval-наборы.
@@ -0,0 +1,12 @@
+# Core Inference
+
+Общий слой инференса.
+
+Цель: дать единый интерфейс для запуска моделей разных типов.
+
+Планируемые режимы:
+
+- OpenAI-compatible API для текстовых моделей;
+- batch inference;
+- локальный inference для eval-тестов;
+- подключение LoRA/adapters поверх базовых моделей.
@@ -0,0 +1,10 @@
+# Core Monitoring
+
+Мониторинг должен покрывать:
+
+- использование GPU и VRAM;
+- время ответа;
+- ошибки инференса;
+- количество запросов;
+- версии используемых моделей;
+- результаты eval-прогонов.
@@ -0,0 +1,14 @@
+"""Shared observability helpers for services and plugins."""
+
+from .redaction import sanitize_for_logging
+from .store import JsonlAuditStore, resolve_audit_root
+from .trace import next_trace_id, resolve_request_id, resolve_trace_id
+
+__all__ = [
+    "JsonlAuditStore",
+    "next_trace_id",
+    "resolve_audit_root",
+    "resolve_request_id",
+    "resolve_trace_id",
+    "sanitize_for_logging",
+]
@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import re
+from typing import Any
+
+
+REDACTED = "[REDACTED]"
+SENSITIVE_KEY_PARTS = (
+    "authorization",
+    "api_key",
+    "apikey",
+    "access_token",
+    "refresh_token",
+    "token",
+    "password",
+    "secret",
+    "cookie",
+    "set-cookie",
+)
+BEARER_RE = re.compile(r"(?i)\bBearer\s+[A-Za-z0-9._~+/=-]+")
+
+
+def _looks_sensitive_key(key: str) -> bool:
+    lowered = key.strip().lower()
+    return any(part in lowered for part in SENSITIVE_KEY_PARTS)
+
+
+def _sanitize_string(value: str) -> str:
+    return BEARER_RE.sub("Bearer " + REDACTED, value)
+
+
+def sanitize_for_logging(value: Any) -> Any:
+    if isinstance(value, dict):
+        cleaned: dict[str, Any] = {}
+        for key, item in value.items():
+            key_text = str(key)
+            if _looks_sensitive_key(key_text):
+                cleaned[key_text] = REDACTED
+            else:
+                cleaned[key_text] = sanitize_for_logging(item)
+        return cleaned
+    if isinstance(value, list):
+        return [sanitize_for_logging(item) for item in value]
+    if isinstance(value, tuple):
+        return [sanitize_for_logging(item) for item in value]
+    if isinstance(value, str):
+        return _sanitize_string(value)
+    return value
@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+import json
+import threading
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+
+def utc_now_iso() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def resolve_audit_root(root: Path, *, service: str, env_var: str | None = None) -> Path:
+    import os
+
+    configured = os.environ.get(env_var or "", "").strip() if env_var else ""
+    if configured:
+        return Path(configured)
+    return root / "reports" / "observability" / service
+
+
+class JsonlAuditStore:
+    def __init__(self, root: Path, *, service: str) -> None:
+        self.root = root
+        self.service = service
+        self.root.mkdir(parents=True, exist_ok=True)
+        self._lock = threading.Lock()
+
+    def _path_for(self, event_type: str) -> Path:
+        stamp = datetime.now(timezone.utc).strftime("%Y%m%d")
+        return self.root / event_type / f"{stamp}.jsonl"
+
+    def write_event(self, event_type: str, payload: dict[str, Any]) -> dict[str, Any]:
+        record = {
+            "event_type": event_type,
+            "service": self.service,
+            "logged_at": utc_now_iso(),
+            **payload,
+        }
+        path = self._path_for(event_type)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        line = json.dumps(record, ensure_ascii=False, separators=(",", ":")) + "\n"
+        with self._lock:
+            with path.open("a", encoding="utf-8") as handle:
+                handle.write(line)
+        return record
@@ -0,0 +1,26 @@
+from __future__ import annotations
+
+import uuid
+from typing import Mapping
+
+
+def next_trace_id() -> str:
+    return uuid.uuid4().hex
+
+
+def _header_value(headers: Mapping[str, str], *names: str) -> str:
+    for name in names:
+        value = headers.get(name)
+        if value:
+            return str(value).strip()
+    return ""
+
+
+def resolve_trace_id(headers: Mapping[str, str]) -> str:
+    trace_id = _header_value(headers, "x-trace-id", "X-Trace-Id", "x-request-id", "X-Request-Id")
+    return trace_id or next_trace_id()
+
+
+def resolve_request_id(headers: Mapping[str, str], *, fallback_trace_id: str) -> str:
+    request_id = _header_value(headers, "x-request-id", "X-Request-Id")
+    return request_id or fallback_trace_id
@@ -0,0 +1,10 @@
+# Core Registry
+
+Общий слой работы с реестром моделей.
+
+Планируемые функции:
+
+- проверка `model-card.yaml`;
+- поиск моделей по задаче, языку и требованиям VRAM;
+- учет базовых моделей и адаптеров;
+- контроль статусов `draft`, `staging`, `production`, `archived`.
@@ -0,0 +1,24 @@
+# Core Storage
+
+Правила хранения моделей, датасетов и артефактов.
+
+Рекомендуемая внешняя структура:
+
+```text
+/models
+  /base
+  /adapters
+  /embeddings
+  /audio
+  /video
+  /translation
+
+/datasets
+  /raw
+  /prepared
+
+/evals
+/artifacts
+```
+
+В git храним только метаданные и инструкции.
@@ -0,0 +1,7 @@
+# Core Training
+
+Общие пайплайны подготовки данных и дообучения.
+
+Основной подход для доменных моделей: adapter-based fine-tuning, например LoRA/QLoRA.
+
+Полное дообучение базовых моделей не используем как первый вариант из-за стоимости, сложности хранения и риска ухудшения общего качества.