ai-consultants 2.21.0 → 2.22.0

package/.claude/commands/ai-consultants:consult.md

@@ -1,5 +1,5 @@
 ---
-description: Consult AI experts (Gemini, Codex, Mistral, Kilo, Cursor, Aider, Amp, Kimi, Qwen, GLM, Grok, DeepSeek, MiniMax, Ollama) for coding questions. Use when weighing trade-offs, comparing approaches, or wanting multiple expert perspectives on non-trivial decisions.
+description: Consult AI experts (Gemini, Codex, Mistral, Cursor, Kimi, Qwen, GLM, Grok, DeepSeek, MiniMax) for coding questions. Use when weighing trade-offs, comparing approaches, or wanting multiple expert perspectives on non-trivial decisions.
 argument-hint: <question> [file1] [file2] ...
 allowed-tools: Bash Read Glob Grep
 ---

package/.env.example

@@ -0,0 +1,432 @@
+# =============================================================================
+# 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 the API-based consultants (Qwen3, GLM, Grok, DeepSeek)
+
+# 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 (xAI) - The Provocateur
+# 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 comparison/voting to work.
+
+# CLI-based consultants (default: enabled)
+ENABLE_GEMINI=true
+ENABLE_CODEX=true
+ENABLE_MISTRAL=true
+ENABLE_CURSOR=true
+ENABLE_KIMI=true
+ENABLE_QWEN3=true
+ENABLE_MINIMAX=true
+ENABLE_CLAUDE=true
+
+# API-only consultants (default: disabled - require API keys)
+ENABLE_GLM=false
+ENABLE_GROK=false
+ENABLE_DEEPSEEK=false
+
+# =============================================================================
+# CLI/API MODE SWITCHING (v2.6+)
+# =============================================================================
+# 6 agents support switching: Gemini, Codex, Claude, Mistral, Qwen3, 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
+
+# =============================================================================
+# MODEL CONFIGURATION (June 2026 premium defaults)
+# =============================================================================
+
+# Gemini - The Architect (CLI mode via Antigravity CLI: agy)
+GEMINI_MODEL="Gemini 3.1 Pro (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
+
+# Codex - The Pragmatist
+CODEX_MODEL=gpt-5.5
+CODEX_TIMEOUT=180
+CODEX_CMD=codex
+
+# Mistral Vibe - The Devil's Advocate
+MISTRAL_MODEL=mistral-large-3
+MISTRAL_TIMEOUT=180
+MISTRAL_CMD=vibe
+
+# Cursor - The Integrator
+CURSOR_MODEL=composer-2.5
+CURSOR_TIMEOUT=180
+CURSOR_CMD=agent
+
+# Kimi - The Eastern Sage (K3 via Kimi Code CLI)
+KIMI_MODEL=kimi-code/k3
+KIMI_TIMEOUT=180
+KIMI_CMD=kimi
+
+# Claude - The Synthesizer
+CLAUDE_MODEL=claude-opus-4-8
+CLAUDE_TIMEOUT=240
+CLAUDE_CMD=claude
+
+# Qwen3 - The Analyst (CLI/API switchable v2.7)
+QWEN3_MODEL=qwen3.7-max
+QWEN3_TIMEOUT=180
+QWEN3_CMD=qwen
+
+# =============================================================================
+# API-BASED CONSULTANT CONFIGURATION
+# =============================================================================
+
+# GLM - The Methodologist
+GLM_MODEL=glm-5.2
+GLM_TIMEOUT=180
+GLM_API_URL=https://api.z.ai/api/coding/paas/v4/chat/completions
+
+# Grok - The Provocateur
+GROK_MODEL=grok-4.5
+GROK_TIMEOUT=180
+GROK_API_URL=https://api.x.ai/v1/chat/completions
+
+# DeepSeek - The Code Specialist
+DEEPSEEK_MODEL=deepseek-v4-pro
+DEEPSEEK_TIMEOUT=180
+DEEPSEEK_API_URL=https://api.deepseek.com/v1/chat/completions
+
+# MiniMax - The Pragmatic Optimizer (CLI via mmx by default, v2.21; API opt-in)
+MINIMAX_CMD=mmx
+MINIMAX_MODEL=MiniMax-M2.7
+MINIMAX_TIMEOUT=180
+MINIMAX_API_URL=https://api.minimax.io/v1/chat/completions
+
+# Response formats for API-based consultants
+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=majority
+
+# 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
+
+# Multi-Agent Debate (MAD): cross-critique rounds
+ENABLE_DEBATE=false
+DEBATE_ROUNDS=1              # 1 = no debate, 2-3 = with cross-critique
+
+# Self-Reflection (experimental): generate-critique-refine loop
+ENABLE_REFLECTION=false
+REFLECTION_CYCLES=1
+
+# Peer Review: anonymous evaluation
+ENABLE_PEER_REVIEW=false
+PEER_REVIEW_MIN_RESPONSES=3
+REVIEWS_PER_CONSULTANT=3
+
+# Panic Mode: auto-rigor when uncertainty detected
+ENABLE_PANIC_MODE=auto
+PANIC_CONFIDENCE_THRESHOLD=5
+PANIC_EXTRA_DEBATE_ROUNDS=1
+PANIC_KEYWORDS="uncertain|maybe|not sure|possibly|unclear|depends|hard to say|difficult to determine"
+
+# Dynamic orchestration: choose how the panel deliberates
+# auto | fixed | quick | converge | adversarial | tournament | exhaustive
+ORCHESTRATION_MODE=auto
+CONVERGENCE_MAX_ROUNDS=4
+CONVERGENCE_TARGET_CONSENSUS=75
+CONVERGENCE_STALL_EPSILON=5
+ENABLE_ADVERSARIAL_VERIFY=true
+
+# Debate optimization: avoid extra rounds when the panel already agrees
+ENABLE_DEBATE_OPTIMIZATION=true
+DEBATE_CONFIDENCE_SPREAD_THRESHOLD=2
+DEBATE_USE_SUMMARIES=true
+
+# 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
+
+# Capability-aware routing & voting (v2.20, opt-in): weight votes and rank the
+# panel by each consultant's capability on the quality axis a question stresses
+# (intelligence or taste, per references/affinity.json 'category_axis'). cost is
+# a composition/budget axis only, never a vote weight.
+ENABLE_CAPABILITY_WEIGHTING=false   # capability-weighted voting
+ENABLE_CAPABILITY_ROUTING=false     # capability-aware panel composition
+CAPABILITY_WEIGHT_STRENGTH=10       # higher = gentler nudge: weight = conf*(S+cap)/S
+CAPABILITY_DEFAULT=5                # fallback capability for a missing consultant/axis
+
+# Stance-based semantic consensus (v2.21, opt-in): the panel picks from a shared
+# enumerated stance set so agreement is scored by exact match instead of lexical
+# similarity. Adds ~1 LLM call per run; degrades to the lexical cluster on any
+# failure, so it is always safe to enable.
+ENABLE_STANCE_CONSENSUS=false
+STANCE_MAX_OPTIONS=5                # max stance options generated per question
+STANCE_TIMEOUT=60                  # seconds for the stance-generation call (guards a hang)
+
+# =============================================================================
+# 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       # Auto-cleanup sessions older than N days
+# SESSION_DIR=/custom/state/sessions
+
+# =============================================================================
+# INTERACTIVE MODE
+# =============================================================================
+
+ENABLE_PROGRESS_BARS=true    # Show progress bars during consultation
+ENABLE_EARLY_TERMINATION=true # Allow Ctrl+C to stop with partial results
+
+# =============================================================================
+# 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
+FORCE_PROJECT_TREE=false
+ENABLE_SELECTIVE_CONTEXT=false
+MAX_FILES_PER_CONSULTANT=5
+
+# =============================================================================
+# 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
+# CURSOR_PERSONA_ID=5
+# 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
+# CURSOR_PERSONA=Custom persona instructions
+# CURSOR_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

package/CLAUDE.md

@@ -2,11 +2,11 @@
 
 ## Project Overview
 
-AI Consultants is a multi-model AI deliberation system that queries up to 15 AI consultants (Gemini, Codex, Mistral, Kilo, Cursor, Aider, Amp, Kimi, Claude, Qwen3, GLM, Grok, DeepSeek, MiniMax, Ollama) to obtain diverse perspectives on coding problems.
+AI Consultants is a multi-model AI deliberation system that queries up to 11 AI consultants (Gemini, Codex, Mistral, Cursor, Kimi, Claude, Qwen3, GLM, Grok, DeepSeek, MiniMax) to obtain diverse perspectives on coding problems.
 
 **Self-Exclusion**: The invoking agent is automatically excluded from the panel to prevent self-consultation. Claude Code won't query Claude, Codex CLI won't query Codex, etc.
 
-**Version**: 2.21.0
+**Version**: 2.22.0
 
 ## Distribution
 
@@ -47,7 +47,6 @@ ai-consultants/
 │   ├── install.sh              # One-liner installer (v2.2)
 │   ├── query_*.sh              # Wrapper for each consultant
 │   ├── query_claude.sh         # Claude consultant (v2.2)
-│   ├── query_ollama.sh         # Local model support (v2.2)
 │   ├── synthesize.sh           # Auto-synthesis of responses
 │   ├── debate_round.sh         # Multi-Agent Debate
 │   ├── classify_question.sh    # Question classifier
@@ -73,6 +72,7 @@ ai-consultants/
 ├── docs/
 │   ├── releases/             # Release notes (one per version)
 │   ├── SETUP.md              # Installation guide
+│   ├── RECIPES.md            # Copy-paste workflow configurations
 │   ├── COST_RATES.md         # Model pricing
 │   ├── SMART_ROUTING.md      # Affinity matrix
 │   └── JSON_SCHEMA.md        # Output schema
@@ -200,9 +200,8 @@ Functions in `lib/common.sh`:
 
 # Use Case Presets
 ./scripts/consult_all.sh --preset minimal "question"    # Gemini + Codex
-./scripts/consult_all.sh --preset balanced "question"   # + Mistral + Kilo
+./scripts/consult_all.sh --preset balanced "question"   # + Mistral + Cursor
 ./scripts/consult_all.sh --preset high-stakes "question" # All + debate
-./scripts/consult_all.sh --preset local "question"      # Ollama only
 ```
 
 Presets are defined in `config.sh` via `apply_preset()` function.
@@ -225,17 +224,6 @@ Strategies are implemented in `synthesize.sh` via `get_strategy_instructions()`.
 ./scripts/doctor.sh --verbose    # Detailed output
 ```
 
-### Ollama Local Models
-```bash
-ENABLE_OLLAMA=true ./scripts/consult_all.sh "question"
-OLLAMA_MODEL=codellama ./scripts/consult_all.sh "question"
-```
-
-Configuration in `config.sh`:
-- `OLLAMA_MODEL` - Model to use (default: hf.co/prithivMLmods/VibeThinker-3B-GGUF)
-- `OLLAMA_HOST` - Server URL (default: http://localhost:11434)
-- `OLLAMA_TIMEOUT` - Timeout in seconds (default: 300)
-
 ### Panic Button Mode
 Automatically adds rigor when uncertainty detected:
 - Average confidence below `PANIC_CONFIDENCE_THRESHOLD` (default: 5)
@@ -270,30 +258,6 @@ Functions in `lib/reflection.sh`:
 - `heuristic_overconfidence_check()` - Fast fallback without LLM
 - `judge_all_responses()` - Batch evaluation
 
-## v2.8 Features
-
-### Amp CLI Support
-Amp Code is now supported as a CLI-based consultant with "The Systems Thinker" persona.
-
-```bash
-# Enable Amp consultant
-export ENABLE_AMP=true
-./scripts/consult_all.sh "question"
-```
-
-**CLI Installation:**
-```bash
-curl -fsSL https://ampcode.com/install.sh | bash
-```
-
-**Environment Variables:**
-- `ENABLE_AMP` - Enable Amp consultant (default: true)
-- `AMP_CMD` - CLI command (default: amp)
-- `AMP_TIMEOUT` - Timeout in seconds (default: 180)
-- `AMP_API_KEY` - API key for authentication
-
-**Persona:** The Systems Thinker - Focuses on holistic system design, component interactions, and emergent behaviors.
-
 ## v2.9 Features
 
 ### Kimi CLI Support
@@ -314,7 +278,7 @@ curl -L code.kimi.com/install.sh | bash
 - `ENABLE_KIMI` - Enable Kimi consultant (default: false)
 - `KIMI_CMD` - CLI command (default: kimi)
 - `KIMI_TIMEOUT` - Timeout in seconds (default: 180)
-- `KIMI_MODEL` - Model identifier (default: kimi-code/kimi-for-coding)
+- `KIMI_MODEL` - Kimi CLI model alias (default: kimi-code/k3; passed explicitly with `--model`)
 
 **Persona:** The Eastern Sage - Focuses on holistic understanding, balance of perspectives, and wisdom from diverse viewpoints.
 
@@ -468,13 +432,10 @@ All consultants now use premium models by default:
 | Cursor | composer-2.5 |
 | DeepSeek | deepseek-v4-pro |
 | GLM | glm-5.2 |
-| Grok | grok-4.3 |
+| Grok | grok-4.5 |
 | Qwen3 | qwen3.7-max |
-| Kimi | kimi-code/kimi-for-coding |
-| Aider | qwen3-coder:free |
+| Kimi | kimi-code/k3 |
 | MiniMax | MiniMax-M2.7 |
-| Kilo | auto |
-| Ollama | hf.co/prithivMLmods/VibeThinker-3B-GGUF |
 
 Override with environment variables: `CLAUDE_MODEL`, `GEMINI_MODEL`, `CODEX_MODEL`, `KIMI_MODEL`, etc.
 
@@ -628,6 +589,12 @@ REPORT_MAX_JSON_LINES=50         # Max JSON lines in full report
 ## Testing
 
 ```bash
+# Full regression suite (required before committing/releasing)
+npm test
+
+# ShellCheck lint
+npm run lint
+
 # Full diagnostic
 ./scripts/doctor.sh
 
@@ -661,8 +628,6 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 | `MAX_SESSION_COST` | 1.00 | Max budget ($) |
 | `ENABLE_PANIC_MODE` | auto | Panic mode trigger (v2.2) |
 | `PANIC_CONFIDENCE_THRESHOLD` | 5 | Panic threshold (v2.2) |
-| `ENABLE_OLLAMA` | false | Local model support (v2.2) |
-| `OLLAMA_MODEL` | hf.co/prithivMLmods/VibeThinker-3B-GGUF | Ollama model (v2.17 default) |
 | `CLAUDE_MODEL` | claude-opus-4-8 | Claude model (v2.5) |
 | `GEMINI_MODEL` | Gemini 3.1 Pro (High) | Gemini agy CLI model (v2.15) |
 | `GEMINI_API_MODEL` | gemini-3.1-pro-preview | Gemini API-mode model ID (v2.15) |
@@ -673,7 +638,7 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 | `CACHE_TTL_HOURS` | 24 | Cache expiration in hours (v2.3) |
 | `ENABLE_RESPONSE_LIMITS` | false | Response token limits (v2.3, opt-in) |
 | `ENABLE_COST_AWARE_ROUTING` | false | Cost-based model routing (v2.3) |
-| `ENABLE_DEBATE_OPTIMIZATION` | false | Skip debate if all agree (v2.3, opt-in) |
+| `ENABLE_DEBATE_OPTIMIZATION` | true | Skip debate if all agree; SECURITY and ARCHITECTURE remain mandatory (default since v2.13) |
 | `ENABLE_COMPACT_REPORT` | true | Compact report format (v2.3) |
 | `ENABLE_CAPABILITY_WEIGHTING` | false | Capability-weighted voting (v2.20, opt-in) |
 | `ENABLE_CAPABILITY_ROUTING` | false | Capability-aware panel composition (v2.20, opt-in) |
@@ -687,7 +652,7 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 | `QWEN3_CMD` | qwen | Qwen CLI command (v2.7) |
 | `ENABLE_KIMI` | true | Enable Kimi consultant (v2.9) |
 | `KIMI_CMD` | kimi | Kimi CLI command (v2.9) |
-| `KIMI_MODEL` | kimi-code/kimi-for-coding | Kimi model (v2.9) |
+| `KIMI_MODEL` | kimi-code/k3 | Kimi CLI model alias |
 | `ENABLE_MINIMAX` | true | Enable MiniMax consultant (v2.10; CLI via mmx v2.21) |
 | `MINIMAX_USE_API` | false | Use MiniMax API instead of the mmx CLI (v2.21) |
 | `MINIMAX_CMD` | mmx | MiniMax CLI command (v2.21) |
@@ -699,15 +664,11 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 - `agy` CLI - Antigravity CLI (Gemini consultant; successor to the deprecated Gemini CLI, v2.15)
 - `codex` CLI - OpenAI Codex
 - `vibe` CLI - Mistral Vibe
-- `kilocode` CLI - Kilo Code
 - `agent` CLI - Cursor
-- `aider` CLI - Aider
-- `amp` CLI - Amp Code (v2.8)
 - `kimi` CLI - Kimi Code (v2.9)
 - `claude` CLI - Claude (v2.2, also used for synthesis)
 - `qwen` CLI - Qwen via qwen-code (v2.7, optional)
 - `mmx` CLI - MiniMax via mmx-cli (v2.21, optional; `npm i -g mmx-cli`, auth `mmx auth login`)
-- `ollama` CLI - Local models (v2.2)
 - `jq` - JSON parsing
 
 ## Error Handling and Retry
@@ -727,13 +688,12 @@ RETRY_DELAY_SECONDS=10
 # Per-consultant timeout
 GEMINI_TIMEOUT=240
 CODEX_TIMEOUT=180
-OLLAMA_TIMEOUT=300  # Longer for local inference
 ```
 
 ## Extended Documentation
 
 For detailed information, see:
-- [docs/SETUP.md](docs/SETUP.md) - Installation, authentication, Ollama setup
+- [docs/SETUP.md](docs/SETUP.md) - Installation and authentication
 - [docs/COST_RATES.md](docs/COST_RATES.md) - Rates and budget management
 - [docs/SMART_ROUTING.md](docs/SMART_ROUTING.md) - Affinity matrix and routing
 - [docs/JSON_SCHEMA.md](docs/JSON_SCHEMA.md) - Complete output schema
@@ -741,8 +701,8 @@ For detailed information, see:
 ## Development Notes
 
 - Scripts in `lib/` are libraries, not standalone executables
-- Output goes to `/tmp/ai_consultations/TIMESTAMP/`
-- Session state in `/tmp/ai_consultants_sessions/`
+- Output goes to `$XDG_CACHE_HOME/ai-consultants/consultations/TIMESTAMP/` (normally `~/.cache/ai-consultants/consultations/`)
+- Session state lives in `$XDG_STATE_HOME/ai-consultants/sessions/` (normally `~/.local/state/ai-consultants/sessions/`)
 - All timeouts are configurable in `config.sh`
 - Consultants can be disabled individually (`ENABLE_GEMINI=false`, etc.)
 - Use `.env.example` as template for environment configuration
@@ -842,6 +802,24 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v2.22.0
+- Added the public `ai-consultants configure` / `config` subcommand. Automatic mode detects every current consultant, uses CLI-first transport selection with API fallback when credentials are available, persists to the XDG user config directory, preserves custom values and secrets while refreshing availability-derived `ENABLE_*` flags, backs up rewrites, and keeps files at mode 600.
+- Replaced the stale 1,092-line v2.0 configurator with a compact implementation whose accepted parameter surface is derived from `.env.example`. `--set KEY=VALUE` supports repeatable automation and participates in detection, `--interactive` reviews credentials/transports/panel selection, `--advanced` reviews every parameter, `--show-parameters` exposes the contract, and side-effect-free `--dry-run` redacts secrets.
+- Added `test_configure.sh` (60 assertions) covering public routing, runtime-wide template parity, full-roster detection, API fallback, override precedence/empty values, transport provenance, advanced defaults, export preservation, dry-run isolation/redaction, symlink refusal, backups/permissions, and rejection of removed settings. The npm-pack smoke path now includes `.env.example` and exercises both `init` and `configure` from the installed tarball.
+- **Three interactive/provenance bugs fixed before the subcommand ever shipped** (found in review; none reached a tagged release):
+  - **`--interactive` aborted on the first Enter.** `prompt_value` ended both branches with `[[ -n "$reply" ]] && set_value …`. An empty reply — the documented "press Enter to keep" path — made that `&&` list return 1, and since it was the function's last command, `prompt_value` returned 1; under `set -e` the plain call site in the `for` loop killed the script (exit 1, nothing written). Now an explicit `if` block, so an empty reply returns 0.
+  - **`--advanced` silently wrote garbage.** `done < <(list_parameters)` redirects fd 0 for the *whole loop body*, so `prompt_value`'s nested `read -r -p` consumed the parameter list instead of the terminal — each prompt took the *next parameter's name* as the user's answer (observed: `AFFINITY_FILE` ← `ANTHROPIC_API_KEY`). Fixed with the standard fd-separation idiom (`read … <&3` / `done 3< <(…)`).
+  - **`init` then `configure` disabled four consultants.** `init` copies `.env.example` verbatim, and the template carried uncommented `CODEX_USE_API=false` / `CLAUDE_USE_API` / `MISTRAL_USE_API` / `QWEN3_USE_API`. `has_explicit_value` reads any unmarked value as a user pin, so `configure_switchable` took the explicit-`false` branch: with no CLI and a valid API key the consultant was disabled outright instead of resolving to API. Fixed in the *template*, not the provenance logic — the four switches are now commented out, matching the convention `GEMINI_USE_API`/`MINIMAX_USE_API` already established (commented = auto-resolve, uncommented = force). CLI-first is unaffected: an installed CLI still wins over a present key.
+- **Backup names are now collision-proof.** `${OUTPUT_FILE}.backup.$(date +%Y%m%d_%H%M%S)` is only second-precise, so two runs inside one second resolved to the same path and the second `cp` clobbered the first backup — losing the user's *original* config while keeping a machine-generated one. Now `mktemp "…backup.<ts>.XXXXXX"`, which claims the name atomically (also making concurrent runs safe). Note the collision is unreachable from a sequential test — a real run takes ~1-8s, longer than the granularity — so the regression test stubs `date` on `PATH` to freeze the clock; the backup line is the only `date` caller in this path.
+- **`test_configure.sh` made hermetic against an ambient config environment — `scripts/release.sh` could not run its own gate.** `config.sh` auto-resolves `GEMINI_USE_API`/`MINIMAX_USE_API` and **exports** them; `configure.sh::has_explicit_value` treats any ambient value as a deliberate user pin. `release.sh` sources `lib/common.sh` (→ `config.sh`) *before* running `npm test`, so the gate inherited pinned transports: Tests 4 and 11 failed under `release.sh` while passing from a clean shell — a "flaky" result that was in fact deterministic per-environment. The suite now `unset`s the whole switchable `*_USE_API` set at the top (one place, covering all 10 configure invocations; only the two auto-resolved ones actually leak today, but the set is cleared so a future auto-resolution — as MiniMax gained in v2.21 — cannot silently reopen it). Same class as the v2.21.0 `test_user_config.sh` fix. Verified green both from a clean shell and under `source lib/common.sh; npm test`. Latent since `test_configure.sh` was introduced; it never affected the shipped runtime, only the release gate.
+- Deprecated `setup_wizard.sh` to a compatibility forwarder. Corrected `GOOGLE_API_KEY` to `GEMINI_API_KEY`, removed legacy `/tmp` overrides from the starter template, completed advanced settings/persona coverage, and fixed safe parsing of unquoted `.env` inline comments.
+
+### v2.21.1
+- **Kimi upgraded to K3.** `KIMI_MODEL` now defaults to `kimi-code/k3`; premium, standard, and economy tiers all resolve to the same K3 alias.
+- **Model selection is now real, not metadata-only.** `query_kimi.sh` passes `--model "$KIMI_MODEL"` to the CLI, overriding a stale user-level Kimi default. A dedicated offline regression test captures the CLI arguments and validates response metadata; a live K3 smoke test returned a structured response with confidence 10.
+- **Roster reduced from 15 to 11 supported consultants.** Kilo, Aider, Amp, and Ollama were removed end-to-end: canonical/default lists, presets, routing and personas, debate/synthesis/reflection, doctor/preflight, updater, configuration/wizard, schemas, tests, docs, and their four query adapters. `ENABLE_KILO`/`KILO_*`, `ENABLE_AIDER`/`AIDER_*`, `ENABLE_AMP`/`AMP_*`, `ENABLE_OLLAMA`/`OLLAMA_*`, and the Ollama-only `local` preset are obsolete and ignored.
+- **Documentation and release surfaces synced.** README, SKILL, `.env.example`, setup/configuration/recipes, cost catalog, changelog, release note, npm metadata, and the showcase site all identify Kimi K3. Version bumped to 2.21.1.
+
 ### v2.21.0
 - **CLI-first transport (principle).** Every `*_USE_API` defaults `false`; a consultant with a CLI always uses it, API is opt-in (CLI-less model or explicit choice). `ENABLE_AMP`/`ENABLE_CLAUDE` default true.
 - **MiniMax via `mmx` CLI** (was API-only). `query_minimax.sh` runs `mmx text chat --non-interactive …` in CLI mode; `config.sh` adds `MINIMAX_CMD` + auto-resolves `MINIMAX_USE_API` (API iff `MINIMAX_API_KEY` set — back-compat), drops MiniMax from `API_CONSULTANTS`; `doctor.sh` treats it as switchable.