# =============================================================================
# AI Consultants - Environment Variables
# =============================================================================
# Copy this file to .env and customize as needed.
# All variables have sensible defaults - only override what you need.
#
# IMPORTANT: At least 2 consultants must be enabled for the system to work.
#
# Export variables before running, or source this file:
#   source .env && ./scripts/consult_all.sh "Your question"
#
# For detailed setup instructions, see: docs/SETUP.md

# =============================================================================
# API KEYS & AUTHENTICATION
# =============================================================================
# Each CLI tool requires its own authentication. Set the appropriate API keys
# or use the CLI's built-in auth flow.

# Google Gemini API key (only needed for API mode; the agy CLI uses OAuth)
# Get yours at: https://makersuite.google.com/app/apikey
# CLI mode uses the Antigravity CLI (agy); sign in by running `agy` once.
# GEMINI_API_KEY=your-google-api-key

# OpenAI API Key (required for Codex)
# Get yours at: https://platform.openai.com/api-keys
# OPENAI_API_KEY=sk-your-openai-api-key

# Mistral API Key
# Get yours at: https://console.mistral.ai/api-keys/
# MISTRAL_API_KEY=your-mistral-api-key

# Anthropic API Key (for Claude API mode or synthesis)
# Get yours at: https://console.anthropic.com/settings/keys
# ANTHROPIC_API_KEY=sk-ant-your-anthropic-api-key


# =============================================================================
# API-BASED CONSULTANT KEYS
# =============================================================================
# These are required for API transports and API-only consultants.

# Qwen3 (Alibaba DashScope) - The Analyst
# Get yours at: https://dashscope.console.aliyun.com/
# QWEN3_API_KEY=your_dashscope_api_key

# GLM (Zhipu AI) - The Methodologist
# Get yours at: https://open.z.ai/
# GLM_API_KEY=your_zhipu_api_key

# Grok API fallback (the Grok Build CLI normally uses its own login)
# Official docs call this XAI_API_KEY; GROK_API_KEY remains the project setting.
# Get yours at: https://console.x.ai/
# GROK_API_KEY=your_xai_api_key

# DeepSeek - The Code Specialist
# Get yours at: https://platform.deepseek.com/
# DEEPSEEK_API_KEY=your_deepseek_api_key

# MiniMax - The Pragmatic Optimizer (v2.10)
# Get yours at: https://platform.minimax.io/user-center/basic-information/interface-key
# MINIMAX_API_KEY=your_minimax_api_key

# =============================================================================
# ENABLED CONSULTANTS
# =============================================================================
# Set to "false" to disable a consultant you haven't configured.
# MINIMUM 2 consultants must be enabled for a useful coverage panel.

# CLI-based consultants (default: enabled)
ENABLE_GEMINI=true
ENABLE_CODEX=true
ENABLE_MISTRAL=true
ENABLE_KIMI=true
ENABLE_QWEN3=true
ENABLE_GROK=true
ENABLE_MINIMAX=true
ENABLE_CLAUDE=true

# API-only consultants (default: disabled - require API keys)
ENABLE_GLM=false
ENABLE_DEEPSEEK=false

# =============================================================================
# CLI/API MODE SWITCHING (v2.6+)
# =============================================================================
# 7 agents support switching: Gemini, Codex, Claude, Mistral, Qwen3, Grok, MiniMax
# When API mode is enabled, CLI mode is automatically disabled.

# GEMINI_USE_API is auto-resolved when left UNSET (v2.15.1): API mode if
# GEMINI_API_KEY is present (no CLI install / OAuth needed — best for npm/npx),
# else the agy CLI. Leave it commented to keep auto-resolution; uncomment only
# to force a specific mode (an explicit value disables auto-detection).
# GEMINI_USE_API=false       # Force Google AI API (true) or agy CLI (false)
# Leave the following commented to keep CLI-first auto-resolution (CLI wins
# when installed; API is the fallback for a key with no CLI). Uncomment only
# to force a specific transport for that agent.
# CODEX_USE_API=false          # Use OpenAI API instead of codex CLI
# CLAUDE_USE_API=false         # Use Anthropic API instead of claude CLI
# MISTRAL_USE_API=false        # Use Mistral API instead of vibe CLI
# QWEN3_USE_API=false          # Use qwen CLI (default) or DashScope API (v2.7)
# MINIMAX_USE_API=false      # Unset = API for legacy key users, otherwise mmx CLI

# API endpoints (override if using custom endpoints)
# GEMINI_API_URL=https://generativelanguage.googleapis.com/v1beta/models
# CODEX_API_URL=https://api.openai.com/v1/chat/completions
# CLAUDE_API_URL=https://api.anthropic.com/v1/messages
# MISTRAL_API_URL=https://api.mistral.ai/v1/chat/completions
# QWEN3_API_URL=https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation
#   Token Plan alternative (OpenAI-compatible, needs QWEN3_FORMAT=openai and a
#   Token Plan key in QWEN3_API_KEY; pass the FULL path, it is used verbatim):
#   https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions

# =============================================================================
# MODEL CONFIGURATION (August 2026 premium defaults)
# =============================================================================

# Gemini - The Architect (CLI mode via Antigravity CLI: agy)
GEMINI_MODEL="Gemini 3.7 Flash (High)"
GEMINI_TIMEOUT=180
GEMINI_CMD=agy
# API-mode model ID (only used when GEMINI_USE_API=true)
GEMINI_API_MODEL=gemini-3.1-pro-preview
# Gemini 3.1 Pro and 3.6 Flash remain valid CLI pins. API mode stays on the
# separately verified 3.1 Pro ID; gemini-3.7-flash is an API-only opt-in until
# that transport completes its own authenticated smoke.
# Reasoning effort for the agy CLI. Passed as --effort <value>. Accepts only
# low|medium|high; anything else is rejected by the provider and surfaces as a
# diagnosed error (provider owns the enum — same stance as QWEN3_REASONING_EFFORT).
# GEMINI_REASONING_EFFORT=

# Codex - The Pragmatist
CODEX_MODEL=gpt-6-astra
CODEX_API_MAX_TOKENS=16384
CODEX_TIMEOUT=180
CODEX_CMD=codex
# Reasoning effort for the codex CLI (and API mode). Passed as
# -c model_reasoning_effort=<value>. The provider owns the accepted enum;
# an unsupported value is rejected rather than silently ignored.
# CODEX_REASONING_EFFORT=

# Mistral Vibe - The Devil's Advocate
# API model ID. Vibe uses the separate CLI alias below. Mistral Medium 3.5,
# Large 3, and Small 4 API IDs are documented opt-ins until an API smoke passes.
MISTRAL_MODEL=mistral-large-3
MISTRAL_CLI_MODEL=mistral-medium-3.5
MISTRAL_API_MAX_TOKENS=4096
# Official API opt-ins: use mistral-medium-3-5, mistral-large-2512, or
# mistral-small-2603 for MISTRAL_MODEL after an authenticated API smoke.
MISTRAL_TIMEOUT=180
MISTRAL_CMD=vibe
MISTRAL_MAX_TURNS=4

# Kimi - The Eastern Sage (K3 via Kimi Code CLI)
KIMI_MODEL=kimi-code/k3
# max_quality selects the inventory-probed kimi-code/k3-256k target.
KIMI_TIMEOUT=180
KIMI_CMD=kimi

# Claude - The Synthesizer
CLAUDE_MODEL=claude-fable-5-1 # ai-consultants:default
# For the lower-cost standard/medium Claude tier, set CLAUDE_MODEL to
# claude-opus-5 (or apply_model_tier standard for a single run).
CLAUDE_TIMEOUT=240
CLAUDE_CMD=claude
CLAUDE_API_MAX_TOKENS=16384
# Reasoning effort for the claude CLI (and API mode). Passed as --effort <value>.
# The provider owns the accepted enum; an unsupported value is rejected rather
# than silently ignored.
# CLAUDE_REASONING_EFFORT=

# Qwen3 - The Analyst (CLI/API switchable v2.7)
QWEN3_MODEL=qwen3.7-max
QWEN3_TIMEOUT=180
QWEN3_MAX_QUALITY_TIMEOUT=600
QWEN3_API_MAX_TOKENS=16384
QWEN3_CMD=qwen
# Reasoning effort. API mode ONLY - the qwen CLI has no effort flag, so in CLI
# mode this is ignored (with a warning); set model.reasoningEffort in
# ~/.qwen/settings.json instead. Accepted: none|minimal|low|medium|high|xhigh|max
# (the provider's own enum). The valid subset depends on the model:
# qwen3.8-max takes all of them EXCEPT 'none' - thinking cannot be
# disabled on it - and defaults to xhigh. An unsupported combination is
# rejected by the provider with a 400, not silently ignored.
# QWEN3_REASONING_EFFORT=

# GROK_USE_API is auto-resolved CLI-first: Grok Build is used whenever `grok`
# is installed; the xAI API is selected when the CLI is unavailable and a key
# exists. A failed CLI launch also falls back to the API at runtime.
# GROK_USE_API=false
# Grok OAuth concurrency: shared keeps one runner-owned credential generation
# so parallel consultants can safely reuse refresh rotation. serialized holds
# the adapter lock for the full CLI call and is intended for diagnostics.
# GROK_OAUTH_MODE=shared

# =============================================================================
# API-ONLY AND FALLBACK CONFIGURATION
# =============================================================================

# GLM - The Methodologist
GLM_MODEL=glm-5.3-flash
GLM_TIMEOUT=180
GLM_API_MAX_TOKENS=16384
GLM_API_URL=https://api.z.ai/api/coding/paas/v4/chat/completions
# GLM_REASONING_EFFORT=  # max_quality sets max

# Grok Build CLI + xAI API fallback - The Provocateur
GROK_CMD=grok
GROK_MODEL=grok-4.6
GROK_TIMEOUT=180
GROK_MAX_TURNS=4
GROK_OAUTH_MODE=shared
GROK_API_MAX_TOKENS=4096
GROK_API_URL=https://api.x.ai/v1/chat/completions
# GROK_REASONING_EFFORT= # max_quality sets xhigh (Grok Build maximum)

# DeepSeek - The Code Specialist
DEEPSEEK_MODEL=deepseek-flash
DEEPSEEK_TIMEOUT=180
DEEPSEEK_MAX_QUALITY_TIMEOUT=600
DEEPSEEK_API_MAX_TOKENS=16384
DEEPSEEK_API_URL=https://api.deepseek.com/v1/chat/completions
# DEEPSEEK_REASONING_EFFORT= # max_quality sets max

# MiniMax - The Pragmatic Optimizer (CLI via mmx by default, v2.21; API opt-in)
MINIMAX_CMD=mmx
MINIMAX_MODEL=MiniMax-M2.7
# max_quality selects the smoke-tested MiniMax-M3 target.
MINIMAX_TIMEOUT=180
MINIMAX_API_MAX_TOKENS=4096
MINIMAX_MAX_TOKENS=4096
MINIMAX_MAX_QUALITY_TOKENS=16384
MAX_QUALITY_API_MAX_TOKENS=16384
MINIMAX_API_URL=https://api.minimax.io/v1/chat/completions

# Wire format for a consultant's API mode. Honored since v2.25 (previously
# declared but never read). Values: google_ai|anthropic|qwen|openai; an
# unrecognized value falls back to the consultant's default with a warning.
# Change this only to reach an endpoint that speaks a different protocol than
# the provider's own - e.g. QWEN3_FORMAT=openai for Qwen Cloud Token Plan,
# which is OpenAI-compatible while DashScope is not. See docs/RECIPES.md.
QWEN3_FORMAT=qwen
GLM_FORMAT=openai
GROK_FORMAT=openai
DEEPSEEK_FORMAT=openai
MINIMAX_FORMAT=openai

# =============================================================================
# FEATURES v2.8
# =============================================================================

# Defaults used when --preset / --strategy are omitted
# DEFAULT_PRESET=balanced
DEFAULT_STRATEGY=coverage

# The invoking integration normally sets this per run for self-exclusion.
INVOKING_AGENT=unknown

# Personas: specialized roles for each consultant
ENABLE_PERSONA=true

# Auto-synthesis: automatic synthesis of all responses
ENABLE_SYNTHESIS=true
SYNTHESIS_CMD=claude
# Optional synthesis-specific model. Empty delegates model selection to the CLI.
SYNTHESIS_MODEL=
SYNTHESIS_EXTRACT_FIELDS=true
SYNTH_MAX=10
SYNTH_DETAIL_MAX_CHARS=4000
SYNTHESIS_TIMEOUT=240
SYNTHESIS_TOTAL_TIMEOUT=480

# Health gate and quorum: validate the live panel before spending on a full run
ENABLE_HEALTH_GATE=false       # Adds one small ping per selected consultant
HEALTH_GATE_TIMEOUT=30
QUORUM_MIN=2
QUORUM_ACTION=warn             # warn or stop

# =============================================================================
# SEMANTIC CACHING (v2.3)
# =============================================================================

ENABLE_SEMANTIC_CACHE=true
CACHE_TTL_HOURS=24
# CACHE_DIR=/custom/cache/path

# API retry and rate-limit controls
API_BASE_BACKOFF=2
API_MAX_BACKOFF=60
API_RATE_LIMIT=30

# Optional response limits by question category
ENABLE_RESPONSE_LIMITS=false
MAX_RESPONSE_TOKENS_BY_CATEGORY=QUICK_SYNTAX:200,CODE_REVIEW:800,BUG_DEBUG:800,ARCHITECTURE:1000,SECURITY:1000,DATABASE:600,GENERAL:500

# =============================================================================
# BUDGET ENFORCEMENT (v2.4, opt-in)
# =============================================================================

ENABLE_BUDGET_LIMIT=false
BUDGET_ACTION=warn           # warn or stop
MAX_SESSION_COST=1.00

# =============================================================================
# SMART ROUTING
# =============================================================================

# Question classification (required for smart routing)
ENABLE_CLASSIFICATION=true
CLASSIFICATION_MODE=pattern  # pattern (fast) or llm (accurate)

# Smart routing: select consultants based on question category
ENABLE_SMART_ROUTING=false
MIN_AFFINITY=7               # Minimum affinity score (1-10) to include

# Cost-aware routing (v2.3)
ENABLE_COST_AWARE_ROUTING=false
USE_ECONOMIC_MODELS_FOR_SIMPLE=true
COMPLEXITY_THRESHOLD_SIMPLE=3
COMPLEXITY_THRESHOLD_MEDIUM=6
FALLBACK_CONFIDENCE_THRESHOLD=7

# =============================================================================
# COST MANAGEMENT
# =============================================================================

ENABLE_COST_TRACKING=true
WARN_AT_COST=0.50            # Warning threshold (USD)
ENABLE_RELIABILITY_TRACKING=true
# COST_TRACKING_FILE=/custom/data/costs.json
# RELIABILITY_FILE=/custom/data/reliability.json
# COST_RATES_FILE=/custom/config/cost_rates.json

# =============================================================================
# SESSION MANAGEMENT
# =============================================================================

SESSION_CLEANUP_DAYS=7       # Deprecated no-op; retained for v4.x compatibility
# SESSION_DIR=/custom/state/sessions

# Deprecated no-ops; retained for v4.x compatibility
ENABLE_PROGRESS_BARS=true
ENABLE_EARLY_TERMINATION=true

# =============================================================================
# PRE-FLIGHT CHECKS
# =============================================================================

ENABLE_PREFLIGHT=false       # Run health check before each consultation
PREFLIGHT_QUICK=true         # Quick mode: CLI check only, skip API test

# =============================================================================
# RETRY & TIMEOUT
# =============================================================================

MAX_RETRIES=2                # Max retry attempts on failure
RETRY_DELAY_SECONDS=5        # Pause between retries
LAUNCH_STAGGER_MAX_SECONDS=2

# Output directory base
# DEFAULT_OUTPUT_DIR_BASE=/custom/cache/consultations

# Live doctor probe timeout
DOCTOR_LIVE_TIMEOUT=45

# =============================================================================
# CONTEXT HANDOFF & TOKEN OPTIMIZATION
# =============================================================================

TOKEN_OPTIMIZATION_MODE=ast
MAX_CONTEXT_FILE_BYTES=8000
ENABLE_AST_EXTRACTION=true
ENABLE_SYMBOL_COMPRESSION=false
ENABLE_SEMANTIC_CHUNKING=true
CHUNK_MAX_TOKENS=500
CHUNK_OVERLAP_LINES=5
CHUNK_PRIORITY_KEYWORDS=main,export,public,api,handler,controller
INCLUDE_DOCSTRINGS=true
INCLUDE_CRITICAL_COMMENTS=true
MAX_BODY_SUMMARY_LINES=3
MIN_IDENTIFIER_LENGTH=8
PRESERVE_EXPORTS=true
USE_COMPACT_PROMPTS=true      # Deprecated no-op; retained for v4.x compatibility
FORCE_PROJECT_TREE=false
ENABLE_SELECTIVE_CONTEXT=false # Deprecated no-op; retained for v4.x compatibility
MAX_FILES_PER_CONSULTANT=5     # Deprecated no-op; retained for v4.x compatibility

# =============================================================================
# REPORTING & STORAGE
# =============================================================================

ENABLE_COMPACT_REPORT=true
REPORT_MAX_JSON_LINES=50
# RATE_LIMIT_DIR=/custom/cache/ratelimit
# CHUNK_TEMP_DIR=/custom/cache/chunks

# =============================================================================
# CUSTOM ROUTING & PERSONAS
# =============================================================================

# AFFINITY_FILE=/path/to/affinity.json

# Each consultant supports _PERSONA_ID (1-21), _PERSONA (custom prompt), and
# _PERSONA_NAME (custom display name). Uncomment only the overrides you need.
# GEMINI_PERSONA_ID=1
# CODEX_PERSONA_ID=2
# MISTRAL_PERSONA_ID=3
# KIMI_PERSONA_ID=20
# CLAUDE_PERSONA_ID=18
# QWEN3_PERSONA_ID=6
# GLM_PERSONA_ID=7
# GROK_PERSONA_ID=8
# DEEPSEEK_PERSONA_ID=17
# MINIMAX_PERSONA_ID=21
# GEMINI_PERSONA=Custom persona instructions
# GEMINI_PERSONA_NAME=Custom persona name
# CODEX_PERSONA=Custom persona instructions
# CODEX_PERSONA_NAME=Custom persona name
# MISTRAL_PERSONA=Custom persona instructions
# MISTRAL_PERSONA_NAME=Custom persona name
# KIMI_PERSONA=Custom persona instructions
# KIMI_PERSONA_NAME=Custom persona name
# CLAUDE_PERSONA=Custom persona instructions
# CLAUDE_PERSONA_NAME=Custom persona name
# QWEN3_PERSONA=Custom persona instructions
# QWEN3_PERSONA_NAME=Custom persona name
# GLM_PERSONA=Custom persona instructions
# GLM_PERSONA_NAME=Custom persona name
# GROK_PERSONA=Custom persona instructions
# GROK_PERSONA_NAME=Custom persona name
# DEEPSEEK_PERSONA=Custom persona instructions
# DEEPSEEK_PERSONA_NAME=Custom persona name
# MINIMAX_PERSONA=Custom persona instructions
# MINIMAX_PERSONA_NAME=Custom persona name

# Calibration judge commands
TASTE_JUDGE_CMD=
JUDGE_CLI=claude

# =============================================================================
# LOGGING
# =============================================================================

LOG_LEVEL=INFO               # DEBUG, INFO, WARN, ERROR