DocsConfigurationConfiguration Reference
Back to Docs
Configuration

Configuration Reference

A user-focused guide to YeePilot's main settings: AI behavior, safety, sandboxing, files, vault, updates, and TUI controls.

Last updated: May 15, 2026

Where The Config Lives

YeePilot writes its main config to:

text
~/.yeepilot/config.yml

Legacy note:

  • old installs may still have ~/.yeepilot/config.yaml
  • YeePilot can still read that legacy file
  • new saves use config.yml

Reset and regenerate the config through the setup flow:

bash
yeepilot setup --reset

A Good Starting Example

yaml
ai:
  provider: openrouter
  model: openai/gpt-oss-120b:free
  autonomy_profile: guarded
  vibe_coding: true
  token_mode: normal
  think_mode: medium
 
security:
  mode: strict
  require_confirmation: true
 
sandbox:
  enabled: true
  use_namespaces: true
  network_access: true
 
tui:
  theme: auto
  live_stream_panel_enabled: true
 
vault:
  enabled: false
  auto_lock_duration: 15m
 
update:
  auto_check: true
  channel: public

ai: Provider, Model, And Runtime Behavior

These are the settings most users will actually touch:

KeyWhat it does
ai.providerChooses openrouter, openai, or anthropic
ai.modelSets the default model
ai.api_keyStores the provider credential if you are not using env vars or keyring storage
ai.base_urlOverrides the API endpoint
ai.max_tokensCaps response size
ai.token_modenormal or saver
ai.conversation_max_historyLimits how much recent conversation is kept verbatim
ai.output_truncate_lengthLimits how much command output is fed back into the model
ai.max_response_lengthSets a hard response-size cap
ai.engineUsually keep v2
ai.autonomy_profilehigh, guarded, strict_review, or ultra
ai.vibe_codingLocal on/off switch for coding-agent capability when your plan allows it
ai.think_modeoff, auto, best, low, medium, or high

Provider defaults

If you set only ai.provider, YeePilot fills in the default model and base URL automatically:

  • OpenRouter: openai/gpt-oss-120b:free
  • OpenAI: gpt-4o
  • Anthropic: claude-sonnet-4-20250514

ai.codeintel: Better Local Context For Repos

These settings improve how YeePilot understands local projects:

yaml
ai:
  codeintel:
    enabled: true
    index_backend: sqlite
    ast_enabled: true
    embeddings_enabled: true
    embeddings_provider: provider
    max_indexed_files: 10000
    max_file_size_bytes: 524288
    rebuild_on_startup: false

Most end users should leave these defaults alone unless indexing needs to be smaller or faster.

ai.verification, ai.recovery, And ai.agentic

These sections control how carefully YeePilot verifies work and how much automatic repair it attempts.

Verification

yaml
ai:
  verification:
    require_post_mutation_verify: true
    max_verify_retries: 1

Recovery

yaml
ai:
  recovery:
    enabled: true
    global_max_cycles: 4
    auto_fix_cycles_max: 4
    stop_on_repeated_signature: true
    require_verify_after_auto_fix: true
    missing_dependency_policy: smart

missing_dependency_policy values:

  • smart
  • fallback_only
  • auto_install

For most end users, smart is the safest balance.

Agentic behavior

yaml
ai:
  agentic:
    preedit_auto_context_enabled: true
    recovery_auto_context_enabled: true
    auto_verify_rerun_enabled: true
    auto_checklist_rerun_enabled: true
    auto_patch_synthesis_enabled: true
    auto_patch_max_candidates: 2
    auto_patch_apply_strategy: patch_first
    auto_patch_confidence_threshold: 0.70
    max_auto_repair_passes: 3

These are advanced controls. End users normally leave them at their defaults.

ai.knowledge And ai.context7

These settings influence freshness and external knowledge retrieval:

yaml
ai:
  knowledge:
    enabled: true
    freshness_policy: auto_live
    offline_behavior: graceful_fallback
    source_policy: official_first
    max_sources: 4
    cache_ttl: 6h
 
  context7:
    enabled: true
    base_url: https://context7.com
    max_chars: 8000

Recommended for normal end-user use:

  • keep knowledge.enabled: true
  • keep offline_behavior: graceful_fallback
  • keep source_policy: official_first

ai.failover

If you want fallback providers:

yaml
ai:
  failover:
    enabled: true
    chain:
      - provider: openai
        model: gpt-4o
      - provider: openrouter
        model: openai/gpt-oss-120b:free

This is optional, but useful if provider uptime matters to you.

security

yaml
security:
  mode: strict
  require_confirmation: true
  blocked_patterns:
    - "shutdown"
  audit_log_path: ~/.yeepilot/audit.log
  audit_max_size_mb: 10
  audit_max_archives: 50

Key end-user advice:

  • use strict on production or important machines
  • keep require_confirmation: true
  • use blocked_patterns for your own environment-specific no-go commands

sandbox

yaml
sandbox:
  enabled: true
  use_namespaces: true
  network_access: true
  max_cpu_seconds: 300
  max_memory_mb: 512
  max_filesize_mb: 100
  max_processes: 64
  denied_paths:
    - /etc/shadow
    - /etc/gshadow
    - /root

This is the main execution isolation section. Most users should leave it enabled and only tune network access or limits when a task clearly needs it.

tui

These are the main user-facing interface settings:

yaml
tui:
  theme: auto
  sidecar_emoji_mode: off
  stats_panel: true
  sidecar_module: sysmon
  code_line_numbers: false
  live_stream_panel_enabled: true
  live_stream_panel_height: 12
  live_stream_panel_scope: all_mutating_tools
  live_stream_panel_animation: true
  live_stream_panel_redact_sensitive: true

Useful values:

  • theme: auto, dark, light, neon
  • sidecar_module: sysmon, vault, tasks, notes, explorer
  • live_stream_panel_scope: all_mutating_tools, file_tools_only, off

About HUD and keybind config

You may also see:

  • tui.hud.*
  • tui.keybinds.actions

These are real settings, but most end users should manage them through the Neural HUD instead of editing them manually.

files

yaml
files:
  max_entries: 20
  max_file_size: 102400
  max_total: 524288
  upload_dir: ~/.yeepilot/uploads
  clipboard_paste_mode: auto

clipboard_paste_mode values:

  • auto
  • on
  • off

vault

yaml
vault:
  enabled: false
  start_locked: true
  auto_lock_duration: 15m
  bruteforce_protection_enabled: true
  wipe_on_bruteforce_enabled: false
  wipe_after_failures: 15

Important note:

  • wipe_on_bruteforce_enabled is intentionally high risk
  • only enable it if you fully understand the recovery consequences

personality

yaml
personality:
  tone: casual
  language: auto
  use_emoji: false
  verbosity: normal

Useful values:

  • tone: casual, professional, minimal
  • language: auto, en, de
  • verbosity: normal, brief, detailed

platform

yaml
platform:
  server_url: https://yee.to

This is the base URL for platform auth, heartbeats, diagnostics, and entitlement-aware client calls.

update

yaml
update:
  auto_check: true
  check_interval_hours: 1
  channel: public
  channel_token: ""

Useful values:

  • channel: public or canary
  • channel_token: required for protected canary usage

Best End-User Editing Strategy

Use these three methods in this order:

  1. the setup wizard for provider and auth changes
  2. the Neural HUD Settings tab for day-to-day adjustments
  3. direct editing of config.yml for advanced or bulk changes

That keeps the configuration understandable and avoids accidental low-level changes.