The Hackathon Organizer Node

Configuration Reference

Detailed configuration options for THON and Lemonade Server

Configuration Reference

thon.yaml (Unified Config)

The recommended way to configure THON is via a single thon.yaml file, created by python -m thon init. This file is the single source of truth for all settings — the CLI, API, and dashboard all read from it (or its .env export).

Full Example

# THON Configuration
# Generated by `python -m thon init` — edit freely or re-run the wizard.

# ── Network ───────────────────────────────────────────────────
# External IP for SSL cert SAN and URLs (auto-detected if empty)
external_ip: ""

# Demo mode (default workspace when no groups)
demo: false

# Logging level: DEBUG, INFO, WARNING, ERROR
log_level: "INFO"

# ── Groups & Users ────────────────────────────────────────────
# Each user gets their own VS Code sandbox with workspace at
# /workspace/{group}/{username}
groups:
  alpha:
    - alice
    - bob
    - carol
  beta:
    - dave
    - eve
  gamma:
    - frank

# ── Sandbox ───────────────────────────────────────────────────
sandbox:
  domain: "localhost:8080"
  api_key: ""
  image: "waterpistol/thon:latest"
  starting_port: 8443
  timeout_minutes: 0

# ── VS Code Instances ────────────────────────────────────────
vscode:
  secure: false
  settings_file: ""
  extensions_file: ""

# ── Nginx & SSL ──────────────────────────────────────────────
nginx:
  enabled: true
  ssl_dir: "/etc/nginx/ssl"
  domain: ""                   # Domain for server_name (enables Let's Encrypt)
  ssl_provider: "auto"         # auto, certbot, mkcert, openssl
  certbot_email: ""            # Email for Let's Encrypt registration

# ── Workspace ─────────────────────────────────────────────────
workspace:
  dir: ""                      # Host directory for bind mounts (empty = ephemeral)

# ── Lemonade Server (Local LLM Inference) ────────────────────
lemonade:
  enabled: false
  host: "0.0.0.0"
  port: 13305
  model: "unsloth/gemma-4-31B-it-GGUF:Q8_K_XL"
  model_name: "gemma-4-31b-it"
  mmproj: "mmproj-BF16.gguf"
  ctx_size_per_user: 262144
  embedding_model: "SuperPauly/harrier-oss-v1-0.6b-gguf:harrier-oss-v1-0.6B-BF16"
  embedding_model_name: "harrier-oss-v1-0.6b"
  embedding_ctx_size_per_user: 32768
  embedding_dimensions: 0
  llamacpp_backend: "auto"     # auto, vulkan, cpu
  prefer_system: true
  llamacpp_bin: "builtin"
  rocm_channel: "preview"
  generate_keys: true
  api_key: ""
  admin_api_key: ""
  llamacpp:                    # Inference tuning parameters
    ctk: "q8_0"
    ctv: "q8_0"
    batch_size: 8192
    ubatch_size: 8192
    split_mode: ""
    main_gpu: -1
    cpu_moe: false
    n_cpu_moe: 0
    min_p: 0.0
    presence_penalty: 0.0
  chat_models:                 # Additional models for selection
    - name: "gemma-4-31b-it"
      checkpoint: "unsloth/gemma-4-31B-it-GGUF:Q8_K_XL"
      context: 262144
      output: 4096
    - name: "qwen3.6-27b"
      checkpoint: "unsloth/Qwen3.6-27B-GGUF:Q8_K_XL"
      context: 262144
      output: 4096

# ── Kilo Code ─────────────────────────────────────────────────
kilo:
  config_file: ""              # Output path (default: ~/.thon/kilo.jsonc)
  skeleton_file: "config/kilo.jsonc.skeleton"
  chat_model: "lemonade/user.gemma-4-31b-it"
  small_model: ""

# ── AI Gateway (APISIX Rate Limiting) ────────────────────────
gateway:
  enabled: false
  mode: "per-user"             # per-user or per-group
  rate_limit_scope: "per-user" # per-user or per-model
  admin_key: ""
  redis_host: ""
  redis_port: 6379
  concurrency_limit: 1
  token_limit: 0               # 0 = unlimited
  token_window: 60
  model_concurrency:           # Per-model limits (when rate_limit_scope=per-model)
    - model: "gemma-4-31b-it"
      concurrency_limit: 1
      token_limit: 0
      token_window: 60
      priority: 0

# ── Langfuse Observability ────────────────────────────────────
langfuse:
  enabled: false
  public_key: ""
  secret_key: ""
  base_url: "https://cloud.langfuse.com"

# ── Dashboard ─────────────────────────────────────────────────
dashboard:
  host: "0.0.0.0"
  port: 8100
  debug: false

# ── Authentication (OIDC) ─────────────────────────────────────
auth:
  enabled: false
  session_secret: ""
  github:
    client_id: ""
    client_secret: ""
  gitlab:
    client_id: ""
    client_secret: ""
  linkedin:
    client_id: ""
    client_secret: ""

Config Sections

SectionDescription
external_ipExternal IP for SSL cert SAN and URLs
demoDemo mode (default workspace when no groups)
log_levelLogging level (DEBUG, INFO, WARNING, ERROR)
groupsGroup name → list of usernames mapping
sandboxSandbox server connection and instance settings
vscodeVS Code security and customization
nginxNginx reverse proxy, SSL, domain, and provider selection
workspacePersistent workspace bind-mounts
lemonadeLocal LLM inference server with llamacpp tuning
kiloKilo Code extension config injection with skeleton merging
gatewayAPISIX AI Gateway with rate limiting and per-model concurrency
langfuseLangfuse LLM observability integration
dashboardWeb dashboard settings
authOIDC authentication providers

Generating .env from thon.yaml

# Export config as .env file for the API and dashboard
python -m thon config env --output .env

The .env file maps thon.yaml fields to environment variables (e.g., lemonade.port → LEMONADE_PORT). Values already set in the environment are not overwritten.

groups.yaml

Defines users and groups for VS Code instance creation. Used by main.py --groups and can also be imported into the database via the dashboard.

Structure

groups:
  <group-name>:
    users:
      - <username>
      - <username>

Example

groups:
  alpha:
    users:
      - alice
      - bob
      - carol
  beta:
    users:
      - dave
      - eve
  gamma:
    users:
      - frank

Behavior

  • Each user gets a unique sandbox instance
  • Workspace path: /workspace/{group}/{username}
  • URL path: https://{ip}/{endpoint_port}/proxy/{code_server_port}/
  • Port assignment: Sequential from --port (default 8443)

nginx Configuration

SSL Providers

ProviderDescriptionBest For
auto (default)Tries mkcert → certbot → openssl in orderMost setups
certbotLet's Encrypt certificates (requires domain + port 80)Production with domain
mkcertCA-trusted certs, filename includes IP hashDevelopment
opensslSelf-signed certs with IP/domain in SANFallback

Select via nginx.ssl_provider in thon.yaml or THON_SSL_PROVIDER env var.

Domain Configuration

When nginx.domain is set:

  • nginx uses the domain as server_name
  • Let's Encrypt is preferred for CA-trusted certificates
  • InstanceInfo.domain_url is populated for domain-based URLs

Directory Structure

/etc/nginx/
├── sites-available/
│   ├── sandbox-thon-8443
│   ├── sandbox-thon-8444
│   └── ...
├── sites-enabled/
│   ├── sandbox-thon-8443 -> ../sites-available/sandbox-thon-8443
│   └── ...
└── ssl/
    ├── server-<ip-hash>.crt
    ├── server-<ip-hash>.key
    └── ca.crt (if mkcert)

Per-Port Server Block

Each VS Code instance gets its own nginx config:

server {
    listen 80;
    listen 443 ssl;
    server_name _;

    ssl_certificate /etc/nginx/ssl/server.crt;
    ssl_certificate_key /etc/nginx/ssl/server.key;
    ssl_protocols TLSv1.2 TLSv1.3;
    ssl_ciphers HIGH:!aNULL:!MD5;

    location / {
        proxy_pass http://127.0.0.1:52322/;

        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "upgrade";
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto https;
        proxy_redirect off;

        add_header Service-Worker-Allowed /;

        proxy_read_timeout 86400;
        proxy_send_timeout 86400;
        proxy_buffering off;
        proxy_request_buffering off;
    }

    location = /ca.crt {
        alias /path/to/mkcert/rootCA.pem;
    }
}

Key Configuration Points

SettingValueReason
proxy_passhttp://127.0.0.1:{port}/No upstream path (prevents doubling)
Service-Worker-Allowed/Fixes SW scope errors
proxy_read_timeout8640024h for long-lived WebSocket
proxy_bufferingoffReal-time terminal output

Lemonade Server Configuration

config.json

Location: /var/lib/lemonade/.cache/lemonade/config.json

{
  "config_version": 1,
  "port": 13305,
  "host": "0.0.0.0",
  "log_level": "info",
  "global_timeout": 300,
  "max_loaded_models": 2,
  "no_broadcast": false,
  "extra_models_dir": "",
  "models_dir": "auto",
  "ctx_size": 1572864,
  "offline": false,
  "disable_model_filtering": false,
  "enable_dgpu_gtt": false,
  "llamacpp": {
    "backend": "auto",
    "args": "",
    "prefer_system": true,
    "rocm_bin": "/usr/local/bin/llama-server",
    "vulkan_bin": "/usr/local/bin/llama-server",
    "cpu_bin": "/usr/local/bin/llama-server"
  },
  "whispercpp": {
    "backend": "auto",
    "args": "",
    "cpu_bin": "builtin",
    "npu_bin": "builtin"
  },
  "sdcpp": {
    "backend": "auto",
    "args": "",
    "steps": 20,
    "cfg_scale": 7.0,
    "width": 512,
    "height": 512,
    "cpu_bin": "builtin",
    "rocm_bin": "builtin",
    "vulkan_bin": "builtin"
  },
  "flm": { "args": "" },
  "ryzenai": { "server_bin": "builtin" },
  "kokoro": { "cpu_bin": "builtin" }
}

When embedding is enabled, max_loaded_models is automatically set to 2 (1 chat model + 1 embedding model).

Config Fields

FieldTypeDefaultDescription
portint13305HTTP server port
hoststringlocalhostBind address
log_levelstringinfotrace, debug, info, warning, error
global_timeoutint300Timeout in seconds
max_loaded_modelsint2Max models per type (-1 for unlimited); auto-set to 2 when embedding enabled
ctx_sizeint4096Default context size
offlineboolfalseSkip model downloads
llamacpp.backendstringautoauto, vulkan, cpu
llamacpp.prefer_systemboolfalsePrefer system llama.cpp
llamacpp.*_binstringbuiltinPath to binary or "builtin"

user_models.json

Location: /var/lib/lemonade/.cache/lemonade/user_models.json

{
  "gemma-4-31b-it": {
    "model_name": "gemma-4-31b-it",
    "checkpoint": "unsloth/gemma-4-31B-it-GGUF:Q8_K_XL",
    "recipe": "llamacpp",
    "suggested": true,
    "labels": ["custom", "vision"],
    "mmproj": "mmproj-BF16.gguf"
  },
  "harrier-oss-v1-0.6b": {
    "model_name": "harrier-oss-v1-0.6b",
    "checkpoint": "SuperPauly/harrier-oss-v1-0.6b-gguf:harrier-oss-v1-0.6B-BF16",
    "recipe": "llamacpp",
    "suggested": true,
    "labels": ["custom", "embedding"]
  }
}

Model Entry Fields

FieldRequiredDescription
model_nameNoDisplay name (matches key)
checkpointYesHuggingFace checkpoint (org/repo:variant)
recipeYesBackend engine (llamacpp, whispercpp, etc.)
suggestedNoShow as suggested model
labelsNoTags (custom, vision, embedding)
mmprojNoVision model mmproj filename
sizeNoModel size in GB (informational)

recipe_options.json

Location: /var/lib/lemonade/.cache/lemonade/recipe_options.json

{
  "user.gemma-4-31b-it": {
    "ctx_size": 1572864,
    "llamacpp_backend": "auto",
    "llamacpp_args": "-b 8192 -ub 8192 -to 3600 -ctk q8_0 -ctv q8_0 --temp 1.0 --top-k 64 --top-p 0.95 --min-p 0.0 --repeat-penalty 1.0 --no-webui --threads-http -1 --threads -1 -np 6"
  },
  "user.harrier-oss-v1-0.6b": {
    "ctx_size": 196608,
    "llamacpp_backend": "auto",
    "llamacpp_args": "-b 8192 -ub 8192 -to 3600 -ctk q8_0 -ctv q8_0 --no-webui --threads-http -1 --threads -1 -np 6"
  }
}

Embedding Model Scaling

When embedding is enabled, the embedding model gets its own entry in recipe_options.json with scaled parameters:

ParameterChat ModelEmbedding Model
ctx_size262144 per user32768 per user
-npnum_usersnum_users

Dynamic Rescaling

Adjust context size and parallel slots without restarting the server:

# Via CLI
python ./scripts/lemonade_server.py rescale --num-users 8

# Via API
curl -X POST http://localhost:8100/api/lemonade/rescale?num_users=8

This rewrites recipe_options.json and reloads models.

llamacpp Tuning Parameters

The lemonade.llamacpp section in thon.yaml controls inference tuning:

ParameterDefaultDescription
ctkq8_0Cache type K
ctvq8_0Cache type V
batch_size8192Batch size
ubatch_size8192Micro-batch size
split_mode""Multi-GPU split mode
main_gpu-1Primary GPU index
cpu_moefalseOffload MoE to CPU
n_cpu_moe0Number of CPU MoE experts
min_p0.0Minimum P sampling
presence_penalty0.0Presence penalty

Recipe Options Fields

FieldDescription
ctx_sizeTotal context size (for all parallel slots)
llamacpp_backendOverride backend for this model
llamacpp_argsCustom llama.cpp arguments

server_models.json

Location: /var/lib/lemonade/.cache/lemonade/server_models.json

Same structure as user_models.json. Used for server-suggested models that appear in the Lemonade desktop app.

kilo.jsonc (Kilo Code Config)

Skeleton Merging

The config/kilo.jsonc.skeleton file provides a base config. Dynamic fields (provider, apiKey, model, indexing) are deep-merged on top. Template variables are substituted per-user:

VariableReplacement
$THON_USERNAMEUser's username
$THON_USER_EMAILUser's email or {username}@thon.local
$WORKSPACEUser's workspace path

Deployment Modes

ModeConfig SourceKilo Points To
lemonade-direct--lemonade kilo.jsoncLemonade server directly
gateway-per-user--gatewayAPISIX gateway (per-user API key)
gateway-per-group--gateway --gateway-per-groupAPISIX gateway (shared group API key)

Location in Sandbox

/home/vscode/.config/kilo/config.json

Structure

{
  "provider": {
    "lemonade": {
      "models": {
        "user.gemma-4-31b-it": {
          "name": "unsloth/gemma-4-31B-it-GGUF:Q8_K_XL",
          "limit": {
            "context": 262144,
            "output": 4096
          }
        }
      },
      "options": {
        "apiKey": "your-api-key",
        "baseURL": "http://YOUR_IP:13305/v1"
      }
    }
  },
  "model": "lemonade/user.gemma-4-31b-it",
  "experimental": {
    "batch_tool": false,
    "codebase_search": true,
    "openTelemetry": false,
    "continue_loop_on_deny": true,
    "semantic_indexing": true,
    "agent_manager_tool": true
  },
  "indexing": {
    "enabled": true,
    "provider": "openai-compatible",
    "vectorStore": "lancedb",
    "openai-compatible": {
      "baseUrl": "http://YOUR_IP:13305/v1",
      "apiKey": "your-api-key",
      "model": "user.harrier-oss-v1-0.6b"
    }
  }
}

Fields

FieldDescription
provider.<name>.models.<id>.nameDisplay name (checkpoint)
provider.<name>.models.<id>.limit.contextMax context tokens
provider.<name>.models.<id>.limit.outputMax output tokens
provider.<name>.options.apiKeyAPI key for authentication
provider.<name>.options.baseURLOpenAI-compatible API endpoint
modelActive model (provider/model-id format)
experimental.batch_toolEnable batch tool calling
experimental.codebase_searchEnable codebase search
experimental.openTelemetryEnable OpenTelemetry tracing
experimental.continue_loop_on_denyContinue agent loop on tool deny
experimental.semantic_indexingEnable semantic code indexing
experimental.agent_manager_toolEnable agent manager tool
indexing.enabledEnable semantic indexing
indexing.providerIndexing provider (openai-compatible)
indexing.vectorStoreVector store type (lancedb)
indexing.openai-compatible.baseUrlEmbedding API base URL
indexing.openai-compatible.apiKeyEmbedding API key
indexing.openai-compatible.modelEmbedding model ID (e.g., user.harrier-oss-v1-0.6b)

Gateway-aware kilo.jsonc

When the AI Gateway is enabled, the kilo.jsonc points to the gateway instead of directly to Lemonade, and the indexing config uses the gateway URL for embedding requests:

{
  "providers": {
    "lemonade-gateway": {
      "baseUrl": "http://1.2.3.4:9080",
      "apiKey": "<consumer-api-key>"
    }
  },
  "models": {
    "gemma-4-31b-it": {
      "provider": "lemonade-gateway",
      "modelId": "user.gemma-4-31b-it"
    }
  },
  "experimental": {
    "batch_tool": false,
    "codebase_search": true,
    "openTelemetry": false,
    "continue_loop_on_deny": true,
    "semantic_indexing": true,
    "agent_manager_tool": true
  },
  "indexing": {
    "enabled": true,
    "provider": "openai-compatible",
    "vectorStore": "lancedb",
    "openai-compatible": {
      "baseUrl": "http://1.2.3.4:9080/v1",
      "apiKey": "<consumer-api-key>",
      "model": "user.harrier-oss-v1-0.6b"
    }
  }
}

VS Code Settings

vscode-settings.jsonc

Injected into each sandbox at /home/vscode/.local/share/code-server/User/settings.json.

Key settings for Lemonade integration:

{
  "kilo-code.new.showTaskTimeline": true,
  "kilo-code.new.browserAutomation.enabled": true,
  "telemetry.telemetryLevel": "off"
}

Config File Storage

VS Code settings can also be stored in the database (via the Settings page in the dashboard or the /api/config-files REST API). When main.py runs without --vscode-settings, it reads the stored config from the database.

DB KeyLabelDescription
config_vscode_settingsVS Code SettingsCode-server settings JSON
config_kilo_jsonKilo Code ConfigKilo Code provider config
config_groups_yamlGroups YAMLGroups and users definition

Priority: CLI flag (e.g., --vscode-settings) > database > none.

Authentication

THON supports two authentication mechanisms that operate independently:

Streamlit Dashboard: Local Password

A single shared password that gates access to the Streamlit dashboard.

VariableDefaultDescription
AUTH_LOCAL_PASSWORD(none)Set a password to require login; unset = no auth

When set, visitors see a login form before any dashboard content renders. Suitable for internal or hackathon use. Not a replacement for OIDC in production.

FastAPI REST API: OIDC/OAuth2

Full OIDC/OAuth2 authentication via GitHub, GitLab, or LinkedIn.

VariableDefaultDescription
AUTH_ENABLEDfalseEnable OIDC authentication on the REST API
AUTH_SESSION_SECRET(none)HMAC secret for signing session tokens (required when enabled)
AUTH_GITHUB_CLIENT_ID(none)GitHub OAuth App client ID
AUTH_GITHUB_CLIENT_SECRET(none)GitHub OAuth App client secret
AUTH_GITLAB_CLIENT_ID(none)GitLab OAuth App client ID
AUTH_GITLAB_CLIENT_SECRET(none)GitLab OAuth App client secret
AUTH_LINKEDIN_CLIENT_ID(none)LinkedIn OIDC client ID
AUTH_LINKEDIN_CLIENT_SECRET(none)LinkedIn OIDC client secret

When AUTH_ENABLED=true, unauthenticated requests to /api/* return 401. The OAuth flow uses PKCE (S256) for security. Sessions are HMAC-signed tokens stored as HttpOnly cookies with 24-hour expiry.

See Dashboard → Authentication for the full OAuth flow diagram, session details, and provider setup instructions.

Systemd Override

Location

/etc/systemd/system/lemonade-server.service.d/override.conf

Structure

[Service]
Environment="LEMONADE_API_KEY=your-api-key"
Environment="LEMONADE_ADMIN_API_KEY=your-admin-key"

Apply Changes

sudo systemctl daemon-reload
sudo systemctl restart lemonade-server

PVC Workspace Volumes

When users are created via the dashboard or imported from YAML, each user is assigned a Docker named volume (PVC) for persistent workspace storage.

Volume Naming

  • Workspace: thon-workspace-{group}-{username}
  • Storage: thon-storage-{group}-{username}

Behavior

  • Volumes are created automatically via docker volume create before sandbox creation
  • When a sandbox is recreated (via the dashboard or --from-db), the same PVC volume is reattached so files persist across instance lifecycles
  • PVC volumes take precedence over --workspace-dir bind mounts

From main.py

# When using --from-db, PVC volumes from the database are used automatically
python ./scripts/main.py --from-db --external-ip 1.2.3.4

Dashboard Configuration

The Streamlit dashboard reads the same environment variables as the backend services. No separate configuration file is needed — or use python -m thon config env to generate the .env file from thon.yaml.

Environment Variables

VariableDefaultDescription
SANDBOX_DOMAINlocalhost:8080Sandbox server address
SANDBOX_API_KEY(none)Sandbox API key
SANDBOX_IMAGEwaterpistol/thon:latestDocker image for sandboxes
LEMONADE_HOST0.0.0.0Lemonade server bind address
LEMONADE_PORT13305Lemonade server port
LEMONADE_API_KEY(none)Lemonade API key
LEMONADE_ADMIN_API_KEY(none)Lemonade admin API key
THON_DB_PATH~/.thon/thon.dbSQLite database path
THON_WORKSPACE_DIR~/.thon/workspaceWorkspace directory for groups
THON_DOMAIN(none)Domain name for nginx and Let's Encrypt
THON_SSL_PROVIDERautoSSL provider: auto, certbot, mkcert, openssl
THON_CERTBOT_EMAIL(none)Email for Let's Encrypt registration
THON_KILO_CONFIG(none)Path to kilo.jsonc
THON_VSCODE_SETTINGS(none)Path to VS Code settings file
THON_LOG_LEVELINFOLogging level
DASHBOARD_HOST0.0.0.0FastAPI bind address
DASHBOARD_PORT8100FastAPI port
DASHBOARD_DEBUGfalseEnable FastAPI debug/reload mode

AI Gateway Configuration

VariableDefaultDescription
GATEWAY_ENABLEDfalseEnable APISIX AI Gateway
GATEWAY_ADMIN_URLhttp://127.0.0.1:9180APISIX Admin API URL
GATEWAY_ADMIN_KEY(auto-detected)APISIX Admin API key
GATEWAY_PROXY_PORT9080APISIX proxy port
GATEWAY_REDIS_HOST(none)Redis host for shared rate limiting
GATEWAY_REDIS_PORT6379Redis port
GATEWAY_REDIS_PASSWORD(none)Redis password
GATEWAY_RATE_LIMIT_TOKENS500Token limit per consumer per time window
GATEWAY_RATE_LIMIT_WINDOW60Rate limit time window in seconds
GATEWAY_MODEper-userConsumer mode: per-user or per-group
GATEWAY_RATE_LIMIT_SCOPEper-userRate limit scope: per-user or per-model
GATEWAY_CONCURRENCY_LIMIT1Concurrency limit per consumer

Langfuse Configuration

VariableDefaultDescription
LANGFUSE_ENABLEDfalseEnable Langfuse observability
LANGFUSE_PUBLIC_KEY(none)Langfuse public key
LANGFUSE_SECRET_KEY(none)Langfuse secret key
LANGFUSE_BASEURLhttps://cloud.langfuse.comLangfuse API base URL

Running

# Streamlit dashboard (port 8501)
streamlit run dashboard/streamlit_app.py --server.port 8501

# FastAPI REST API (port 8100, optional)
python -m thon run

See Dashboard for full documentation including pages and implementation details.

CLI Reference

Complete command-line reference for THON and Lemonade Server

Dashboard

Streamlit dashboard for managing VS Code instances, groups, and Lemonade Server

On this page

Configuration Referencethon.yaml (Unified Config)Full ExampleConfig SectionsGenerating .env from thon.yamlgroups.yamlStructureExampleBehaviornginx ConfigurationSSL ProvidersDomain ConfigurationDirectory StructurePer-Port Server BlockKey Configuration PointsLemonade Server Configurationconfig.jsonConfig Fieldsuser_models.jsonModel Entry Fieldsrecipe_options.jsonEmbedding Model ScalingDynamic Rescalingllamacpp Tuning ParametersRecipe Options Fieldsserver_models.jsonkilo.jsonc (Kilo Code Config)Skeleton MergingDeployment ModesLocation in SandboxStructureFieldsGateway-aware kilo.jsoncVS Code Settingsvscode-settings.jsoncConfig File StorageAuthenticationStreamlit Dashboard: Local PasswordFastAPI REST API: OIDC/OAuth2Systemd OverrideLocationStructureApply ChangesPVC Workspace VolumesVolume NamingBehaviorFrom main.pyDashboard ConfigurationEnvironment VariablesAI Gateway ConfigurationLangfuse ConfigurationRunning