ai-consultants 4.0.3 → 4.0.4

package/.env.example

@@ -335,15 +335,12 @@ ENABLE_RELIABILITY_TRACKING=true
 # SESSION MANAGEMENT
 # =============================================================================
 
-SESSION_CLEANUP_DAYS=7       # Auto-cleanup sessions older than N days
+SESSION_CLEANUP_DAYS=7       # Deprecated no-op; retained for v4.x compatibility
 # 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
+# Deprecated no-ops; retained for v4.x compatibility
+ENABLE_PROGRESS_BARS=true
+ENABLE_EARLY_TERMINATION=true
 
 # =============================================================================
 # PRE-FLIGHT CHECKS
@@ -383,10 +380,10 @@ INCLUDE_CRITICAL_COMMENTS=true
 MAX_BODY_SUMMARY_LINES=3
 MIN_IDENTIFIER_LENGTH=8
 PRESERVE_EXPORTS=true
-USE_COMPACT_PROMPTS=true
+USE_COMPACT_PROMPTS=true      # Deprecated no-op; retained for v4.x compatibility
 FORCE_PROJECT_TREE=false
-ENABLE_SELECTIVE_CONTEXT=false
-MAX_FILES_PER_CONSULTANT=5
+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

package/CLAUDE.md

@@ -6,7 +6,7 @@ AI Consultants is a multi-model coverage system that queries up to 10 AI consult
 
 **Self-Exclusion**: The invoking agent is automatically excluded from both the panel and synthesis. Claude Code won't query or synthesize with Claude, Codex CLI won't query or synthesize with Codex, etc.
 
-**Version**: 4.0.3
+**Version**: 4.0.4
 
 ## Distribution
 
@@ -760,6 +760,13 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v4.0.4
+
+- **Housekeeping now removes dead implementation without removing public compatibility.** The cleanup deletes uncalled API, cache, optimizer, common, cost, persona, reliability, routing-summary, and session-display helpers, plus the stale README changelog and redundant npm ignore file. The documented `get_routing_mode`, `get_recommended_count`, and `get_category_timeout` helpers stay available and are regression-tested. Six historic config keys that had no runtime reader remain accepted as explicitly deprecated no-ops through v4.x: `SESSION_CLEANUP_DAYS`, `ENABLE_PROGRESS_BARS`, `ENABLE_EARLY_TERMINATION`, `USE_COMPACT_PROMPTS`, `ENABLE_SELECTIVE_CONTEXT`, and `MAX_FILES_PER_CONSULTANT`.
+- **All Bash test suites now share one assertion framework.** `scripts/lib/test_helpers.sh` owns counters, pass/fail/skip rendering, regex/string/numeric/JSON/exit assertions, section rendering, and both concise and detailed summaries. `test_suite.sh` retains compatibility adapters for its established assertion call sites while delegating all mechanics; its summary fails on zero assertions or any failure. The previously excluded `test_functions.sh` is replaced by auto-discovered `test_common.sh`, which keeps regression coverage for diagnosed failures, quorum, health probes, feature-flag recognition, Kimi stream extraction, fenced/bare JSON normalization, confidence preservation, and both detailed-summary failure gates.
+- **The package and active guidance are smaller and truthful.** `package.json#files` is the sole npm allowlist; the package excludes the GitHub release-note archive, tests, fixtures, and maintainer release tooling while retaining active docs. The manifest moves 107 → 61 files, packed bytes 340,662 → 268,831, and unpacked bytes 1,145,406 → 929,330. Setup/CI instructions use `doctor` and `configure`, examples use XDG consultation paths, and routing documentation describes real affinity selection rather than an inert routing-mode/timeout path.
+- **Verification is wholly offline for this patch.** No consultant adapter, model, host transport, roster, cost rate, or synthesis behavior changed, so no billable live smoke was needed. Hermetic `npm test` passed 24/24 suites; core 447 assertions, configure 94 checks, installer/package 51 checks, common-helper 38 checks, Bash 3.2 syntax, ShellCheck, `npm ci --dry-run`, markdown links, and two rounds of cross-family cleanup review are green. PR #16 merged with its merge commit and all final CI checks passed.
+
 ### v4.0.3
 
 - **GLM's active catalog target moves from `glm-5.3` to `glm-5.3-flash` without changing transport or tier semantics.** `scripts/config.sh:189` changes the clean-install default, and the maximum/premium/standard branches at `scripts/config.sh:626-656` select the same exact provider ID. `max_quality` still supplies `GLM_REASONING_EFFORT=max`; economy deliberately remains `glm-4-flash`.

package/README.md

@@ -1,8 +1,8 @@
-# AI Consultants v4.0.3
+# AI Consultants v4.0.4
 
 > **Coverage, not a single guess.** A panel of up to 10 frontier models from different vendors fans out on your question in parallel and hands you the *union* of what they collectively see — the risks, edge cases, and approaches a single model misses.
 
-[![Version](https://img.shields.io/badge/version-4.0.3-blue.svg)](https://github.com/matteoscurati/ai-consultants)
+[![Version](https://img.shields.io/badge/version-4.0.4-blue.svg)](https://github.com/matteoscurati/ai-consultants)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-orange.svg)](https://docs.anthropic.com/en/docs/claude-code/skills)
 [![GitHub stars](https://img.shields.io/github/stars/matteoscurati/ai-consultants?style=social)](https://github.com/matteoscurati/ai-consultants)
@@ -331,7 +331,7 @@ skillport status ai-consultants
 git clone https://github.com/matteoscurati/ai-consultants.git
 cd ai-consultants
 ./scripts/doctor.sh --fix
-./scripts/setup_wizard.sh
+./bin/ai-consultants configure
 ```
 
 **Commands:**
@@ -698,15 +698,19 @@ Classify -> Route -> Fan out (parallel) -> Coverage synthesis
 Each consultation generates:
 
 ```
-/tmp/ai_consultations/TIMESTAMP/
+${XDG_CACHE_HOME:-$HOME/.cache}/ai-consultants/consultations/TIMESTAMP/
+├── context.md            # Built consultation context
 ├── gemini.json          # Individual responses
 ├── codex.json           #   with confidence scores
 ├── mistral.json
 ├── grok.json
 ├── synthesis.json       # Coverage union
+├── optimization_metrics.json
 └── report.md            # Human-readable report
 ```
 
+The command prints the exact output directory as its final stdout line.
+
 ---
 
 ## Best Practices
@@ -736,7 +740,8 @@ enough — the panel adds little.
 
 - **Never** include credentials or API keys in queries
 - Review and redact sensitive code before sending it to any external consultant
-- Files in `/tmp` are automatically cleaned up
+- Private query and context-staging files are removed automatically; generated
+  reports remain in the XDG cache directory until you remove them
 
 ---
 
@@ -748,121 +753,11 @@ enough — the panel adds little.
 - [Smart Routing](docs/SMART_ROUTING.md) - Category-based routing
 - [JSON Schema](docs/JSON_SCHEMA.md) - Output format specification
 - [Reference Details](references/details.md) - Presets, strategies, best practices
+- [Changelog](https://github.com/matteoscurati/ai-consultants/blob/main/CHANGELOG.md) - Complete version history
 - [Contributing](CONTRIBUTING.md) - How to contribute
 
 ---
 
-## Changelog
-
-### v2.23.0
-
-- **`ENABLE_REFLECTION` and `REFLECTION_CYCLES` removed.** The self-reflection module they controlled was never called by anything, so the settings had never affected a consultation — v2.16's `converge` and `adversarial` shapes already run critique-refine off measured consensus. **If you set either key**, remove it: `configure --set ENABLE_REFLECTION=...` now exits non-zero, and both keys are dropped when an existing `.env` is rewritten.
-- **The release gate works again.** Two test suites failed deterministically against any real user configuration, so no release since 2.22.0 could pass its own `npm test`.
-- **`npm test` no longer swallows failures.** A failing assertion followed by a passing one inside the same test function was counted as a pass, across 8 of 13 test functions.
-- **Feature flags can no longer be enrolled as consultants.** A registry that told feature flags apart from custom API agents was 18 entries out of date; it is now complete and pinned by a test.
-- **Preset tables corrected** — they described a debate and peer-review depth the code has not enforced since v2.16, and called `high-stakes`/`max_quality` "all consultants" when they enable 5 and 8 of 11. See the [v2.23.0 release note](docs/releases/v2.23.0.md).
-
-### v2.22.0
-
-- **`ai-consultants configure`**: a public automatic configurator. It detects your installed CLIs and API keys, picks CLI-first transports, and writes a private XDG config while preserving your existing settings and secrets. Drive it with repeatable `--set KEY=VALUE`, review it with `--interactive` / `--advanced`, or preview it with `--dry-run`. See the [v2.22.0 release note](docs/releases/v2.22.0.md).
-
-### v2.21.1
-
-- **Kimi K3**: Kimi now defaults to `kimi-code/k3`, and the adapter passes the model explicitly with `--model`.
-- **Focused 11-consultant roster**: Kilo, Aider, Amp, and Ollama were removed end-to-end, including their adapters and configuration variables. See the [v2.21.1 release note](docs/releases/v2.21.1.md) for migration guidance.
-
-### v2.15.1
-
-- **Gemini fixes (Antigravity CLI)**: the default model (`Gemini 3.1 Pro (High)`) wraps its JSON in a ```` ```json ```` fence; v2.15.0 didn't strip it, so every Gemini reply degraded to a generic fallback. Now de-fenced on all paths (response processing, self-reflection, synthesis).
-- **Works out-of-the-box for `npx`**: Gemini auto-selects API mode when `GEMINI_API_KEY` is set (the `agy` CLI can't be npm-installed and is OAuth-only), so a key-only environment no longer silently drops Gemini.
-- **Synthesis no longer hangs** when `agy` is the synthesizer (it was launched interactively instead of in print mode).
-
-### v2.10.0
-
-- **MiniMax M2.5 support**: New API-based consultant with "The Pragmatic Optimizer" persona
-- **15 consultants total**: Gemini, Codex, Mistral, Kilo, Cursor, Aider, Amp, Kimi, Claude, Qwen3, GLM, Grok, DeepSeek, MiniMax, Ollama
-- **npx distribution**: `npx ai-consultants "question"` - run directly without install
-- **npm packaging**: `package.json` with zero dependencies, `.npmignore` for clean publishing
-
-### v2.8.1
-
-- **Bug fixes**: Fixed `((count++))` abort under `set -e`, missing Amp in consultant map, hardcoded `claude` in synthesize.sh
-- **Security**: Variable name validation before `export` in escalation and cost-aware routing
-- **DRY refactoring**: Rewrote `query_kilo.sh` and `query_cursor.sh` using shared `process_consultant_response()`; added `get_model_for_tier()` as single source of truth
-
-### v2.8.0
-
-- **Amp CLI support**: New consultant with "The Systems Thinker" persona
-- **13 consultants total**: Gemini, Codex, Mistral, Kilo, Cursor, Aider, Amp, Claude, Qwen3, GLM, Grok, DeepSeek, Ollama
-- **Installation**: `curl -fsSL https://ampcode.com/install.sh | bash`
-
-### v2.7.0
-
-- **Qwen CLI support**: CLI/API mode switching for Qwen3 via qwen-code
-- **5 switchable agents**: Gemini, Codex, Claude, Mistral, and now Qwen3 support CLI/API mode
-- **CLI default**: `QWEN3_USE_API` defaults to `false` (CLI mode via qwen-code)
-
-### v2.6.0
-
-- **CLI/API mode switching**: Gemini, Codex, Claude, and Mistral can switch between CLI and API mode
-- **New environment variables**: `*_USE_API` and `*_API_URL` for each switchable agent
-- **Unified API query module**: `lib/api_query.sh` for consistent API handling
-
-### v2.5.0
-
-- **Model quality tiers**: Premium, standard, and economy tiers for all consultants
-- **New presets**: `max_quality`, `medium`, `fast` for quick tier selection
-- **Premium defaults**: All consultants now use premium models by default (March 2026)
-- **`apply_model_tier()` function**: Programmatically switch all models to a tier
-- **Updated models**: opus-4.6, gemini-3.1-pro-preview, gpt-5.3-codex, mistral-large-3, etc.
-
-### v2.4.0
-
-- **Budget enforcement**: Optional budget limits with configurable actions (warn/stop)
-- **Budget checks**: 4 enforcement points (before/after consultation, debate, synthesis)
-- **Budget configuration**: Configurable via natural language or environment variables
-
-### v2.3.0
-
-- **Semantic caching**: Cache responses to avoid redundant API calls (15-25% savings)
-- **Cost-aware routing**: Route simple queries to cheaper models (30-50% savings)
-- **Fallback escalation**: Auto-escalate to premium model if confidence < 7
-- **Debate optimization**: Skip debate if all consultants agree (opt-in)
-- **Category exceptions**: SECURITY/ARCHITECTURE always trigger debate
-- **Quality monitoring**: `optimization_metrics.json` tracks optimization impact
-- **Compact reports**: Shorter reports by default (summaries only)
-- **Response limits**: Per-category token limits (opt-in)
-
-### v2.2.0
-
-- **Claude consultant**: New consultant with "The Synthesizer" persona
-- **Self-exclusion**: Invoking agent automatically excluded from panel
-- **Presets**: Quick configuration with `--preset minimal/balanced/high-stakes/security`
-- **Doctor command**: Diagnostic and auto-fix tool
-- **Synthesis strategies**: `--strategy majority/risk_averse/security_first/compare_only`
-- **Confidence intervals**: Statistical confidence ranges (e.g., "8 +/- 1.2")
-- **Anonymous peer review**: Unbiased evaluation of responses
-- **Ollama support**: Local model inference for privacy
-- **Panic mode**: Automatic rigor when uncertainty detected
-- **One-liner install**: `curl | bash` installation
-
-### v2.1.0
-
-- New consultants: Aider, DeepSeek
-- 17 configurable personas
-- Token optimization with AST extraction
-
-### v2.0.0
-
-- Persona system with 15 predefined roles
-- Confidence scoring (1-10) on every response
-- Auto-synthesis with weighted recommendations
-- Multi-Agent Debate (MAD)
-- Smart routing by question category
-- Session management and cost tracking
-
----
-
 ## License
 
 MIT License - see [LICENSE](LICENSE) for details.

package/SKILL.md

@@ -5,10 +5,10 @@ license: MIT
 compatibility: Requires bash, jq, and at least 2 AI CLI tools (agy, codex, vibe, etc.). macOS and Linux.
 metadata:
   author: matteoscurati
-  version: 4.0.3
+  version: 4.0.4
 ---
 
-# AI Consultants v4.0.3 - AI Expert Panel
+# AI Consultants v4.0.4 - AI Expert Panel
 
 **Coverage, not a single guess.** Convene a panel of AI "consultants" from different vendors for coding questions: they fan out in parallel and you get the *union* of what they collectively see — the risks, edge cases, and approaches a single model misses. Each consultant has a **configurable persona** that decorrelates its analysis.
 
@@ -185,13 +185,17 @@ See [Full Configuration Reference](references/configuration.md) for all variable
 ## Output
 
 ```
-/tmp/ai_consultations/TIMESTAMP/
+${XDG_CACHE_HOME:-$HOME/.cache}/ai-consultants/consultations/TIMESTAMP/
+├── context.md          # Built consultation context
 ├── gemini.json        # Individual responses
 ├── codex.json
 ├── synthesis.json     # Coverage union
+├── optimization_metrics.json
 └── report.md          # Human-readable
 ```
 
+The command prints the exact output directory as its final stdout line.
+
 ## Doctor Command
 
 Diagnose and fix issues:

package/docs/COST_RATES.md

@@ -1,4 +1,4 @@
-# Cost Rates - AI Consultants v4.0.3
+# Cost Rates - AI Consultants v4.0.4
 
 This page documents the per-token rates used by the cost tracking system.
 

package/docs/JSON_SCHEMA.md

@@ -1,4 +1,4 @@
-# JSON Schema - AI Consultants v3.5
+# AI Consultants JSON Schema
 
 This document describes the JSON schema used for consultant responses.
 

package/docs/SETUP.md

@@ -1,4 +1,4 @@
-# Setup Guide - AI Consultants v2.21.1
+# AI Consultants Setup Guide
 
 This guide walks you through installing and configuring AI Consultants for various AI coding agents.
 
@@ -688,33 +688,18 @@ Checks:
 ./scripts/doctor.sh --fix
 ```
 
-### Preflight Check
-
-```bash
-./scripts/preflight_check.sh
-```
-
-Expected output:
-```
-[OK] jq installed
-[OK] Gemini CLI installed and authenticated
-[OK] Codex CLI installed and authenticated
-Status: Ready
-```
-
-### Setup Wizard (Bash)
+### Configuration
 
-Interactive configuration:
+Auto-detect the available CLI and API transports:
 
 ```bash
-./scripts/setup_wizard.sh
+./bin/ai-consultants configure
 ```
 
-The wizard will:
-1. Check installed CLIs
-2. Test authentication
-3. Suggest configuration
-4. Generate `.env` file
+Use `--interactive` for a guided review, `--advanced` for every supported
+parameter, or `--dry-run` to preview the generated configuration without
+writing it. The deprecated `setup_wizard.sh` and `preflight_check.sh` entry
+points remain compatibility forwarders but are not the maintained interface.
 
 ---
 
@@ -805,10 +790,10 @@ After setup:
 **Bash:**
 ```bash
 # Test your configuration
-./scripts/consult_all.sh --preset minimal "How do I optimize a SQL query?"
+output_dir=$(./scripts/consult_all.sh --preset minimal "How do I optimize a SQL query?")
 
 # View the report
-cat /tmp/ai_consultations/*/report.md
+less "$output_dir/report.md"
 ```
 
 See [README.md](../README.md) for usage examples and full documentation.

package/docs/SMART_ROUTING.md

@@ -1,4 +1,4 @@
-# Smart Routing - AI Consultants v2.11
+# AI Consultants Smart Routing
 
 The Smart Routing system automatically selects the most suitable consultants based on the question category.
 
@@ -85,30 +85,11 @@ This is useful for:
 The matrix is loaded once per shell and cached in memory — no jq overhead
 on subsequent calls.
 
-## Routing Modes
-
-The system automatically determines how many consultants to involve:
-
-| Mode | Consultants | Categories | Rationale |
-|------|-------------|------------|-----------|
-| **full** | All enabled | SECURITY, GENERAL | All for complete perspectives |
-| **selective** | Top 5 by affinity | CODE_REVIEW, BUG_DEBUG, ARCHITECTURE, ALGORITHM, DATABASE, API_DESIGN, TESTING | Best matches for the category |
-| **single** | 1 | QUICK_SYNTAX | Only the best for quick answers |
-
-### Selection Logic
-
-```
-SECURITY      → full (all)     # Too important to exclude anyone
-QUICK_SYNTAX  → single (1)    # A quick answer is sufficient
-CODE_REVIEW   → selective (5) # Top 5 by affinity
-BUG_DEBUG     → selective (5)
-ARCHITECTURE  → selective (5)
-*             → full (all)    # Default: all enabled
-```
-
 ## Cost-Aware Routing (v2.3+)
 
-When `ENABLE_COST_AWARE_ROUTING=true`, the system routes queries to cheaper models based on complexity:
+When `ENABLE_COST_AWARE_ROUTING=true`, selected consultants use economy models
+for simple questions and can retry low-confidence responses with their premium
+model. Consultant selection itself continues to use the affinity matrix above.
 
 ```bash
 ENABLE_COST_AWARE_ROUTING=true
@@ -119,23 +100,6 @@ COMPLEXITY_THRESHOLD_MEDIUM=6    # Score 4-6 = use standard models
 
 See [COST_RATES.md](COST_RATES.md) for model pricing by tier.
 
-## Timeout per Category
-
-Timeouts optimized based on category complexity:
-
-| Category | Timeout | Rationale |
-|----------|---------|-----------|
-| QUICK_SYNTAX | 60s | Short answers |
-| DATABASE | 120s | Medium-complexity queries |
-| TESTING | 120s | Test case generation |
-| CODE_REVIEW | 180s | Detailed analysis |
-| BUG_DEBUG | 180s | Investigation |
-| ALGORITHM | 180s | Reasoning |
-| API_DESIGN | 180s | Detailed design |
-| GENERAL | 180s | Default |
-| ARCHITECTURE | 240s | Complex design |
-| SECURITY | 240s | In-depth analysis |
-
 ## Supported Categories
 
 ### CODE_REVIEW
@@ -235,8 +199,8 @@ ENABLE_SMART_ROUTING=true \
 
 # Output:
 # [INFO] Category: SECURITY
-# [INFO] Routing mode: full (all enabled consultants)
-# [INFO] Timeout: 240s
+# [INFO] Smart routing for category SECURITY...
+# [INFO] Selected consultants: Mistral Codex ...
 ```
 
 ## API Functions
@@ -255,12 +219,6 @@ select_consultants "SECURITY" 7    # → All enabled consultants
 # Check recommendation
 is_recommended "SECURITY" "Claude" 7 && echo "Recommended"
 
-# Get timeout
-get_category_timeout "ARCHITECTURE"  # → 240
-
-# Get routing mode
-get_routing_mode "QUICK_SYNTAX"      # → single
-
-# Cost-aware selection (v2.3)
-select_consultants_cost_aware "QUICK_SYNTAX" 7  # → Economy model selection
+# Cost-aware model selection (v2.3)
+get_cost_aware_model "codex" 2  # → Economy model when enabled
 ```

package/docs/cost_rates.json

@@ -1,5 +1,5 @@
 {
-  "version": "4.0.3",
+  "version": "4.0.4",
   "updated": "2026-08-23",
   "models": {
     "_comment_units": "All rates are USD per 1,000 tokens (per-1K). lib/costs.sh computes cost as (token_count / 1000) * rate, so every value here MUST be a per-1K rate = (provider $/1M price) / 1000. Do NOT paste $/MTok figures directly.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-consultants",
-  "version": "4.0.3",
+  "version": "4.0.4",
   "description": "A cross-vendor panel of up to 10 AI models that returns the coverage union of their distinct perspectives",
   "bin": {
     "ai-consultants": "bin/ai-consultants"
@@ -19,6 +19,7 @@
     "SKILL.md",
     "CLAUDE.md",
     "docs/",
+    "!docs/releases/",
     "references/"
   ],
   "keywords": [

package/scripts/config.sh

@@ -304,12 +304,6 @@ CLAUDE_CMD="${CLAUDE_CMD:-claude}"
 # All available consultants (ordered by typical usage)
 ALL_CONSULTANTS=("Gemini" "Codex" "Mistral" "Kimi" "Claude" "Qwen3" "GLM" "Grok" "DeepSeek" "MiniMax")
 
-# CLI-based consultants (use CLI tools, some support CLI/API switching)
-CLI_CONSULTANTS=("Gemini" "Codex" "Mistral" "Kimi" "Claude" "Qwen3" "Grok" "MiniMax")
-
-# API-only consultants (use HTTP API directly, no CLI available)
-API_CONSULTANTS=("GLM" "DeepSeek")
-
 # =============================================================================
 # ENABLED CONSULTANTS
 # =============================================================================
@@ -435,17 +429,11 @@ BUDGET_ACTION="${BUDGET_ACTION:-warn}"
 # (persistent across reboots; sessions enable follow-up queries).
 SESSION_DIR="${SESSION_DIR:-${_AI_CONSULTANTS_XDG_STATE}/sessions}"
 
-# Days after which to clean old sessions
+# Deprecated no-op; retained through v4.x for configuration compatibility.
 SESSION_CLEANUP_DAYS="${SESSION_CLEANUP_DAYS:-7}"
 
-# =============================================================================
-# INTERACTIVE MODE (v2.0)
-# =============================================================================
-
-# Enable interactive progress bars
+# Deprecated no-ops; retained through v4.x for configuration compatibility.
 ENABLE_PROGRESS_BARS="${ENABLE_PROGRESS_BARS:-true}"
-
-# Enable early termination (Ctrl+C to stop with partial responses)
 ENABLE_EARLY_TERMINATION="${ENABLE_EARLY_TERMINATION:-true}"
 
 # =============================================================================
@@ -485,7 +473,7 @@ ENABLE_SEMANTIC_CHUNKING="${ENABLE_SEMANTIC_CHUNKING:-true}"
 # Maximum tokens per chunk (for chunking mode)
 CHUNK_MAX_TOKENS="${CHUNK_MAX_TOKENS:-500}"
 
-# Use compact prompts (shorter personas and output format)
+# Deprecated no-op; retained through v4.x for configuration compatibility.
 USE_COMPACT_PROMPTS="${USE_COMPACT_PROMPTS:-true}"
 
 # Extract only essential fields for synthesis (instead of full JSON)
@@ -525,8 +513,7 @@ USE_ECONOMIC_MODELS_FOR_SIMPLE="${USE_ECONOMIC_MODELS_FOR_SIMPLE:-true}"
 COMPLEXITY_THRESHOLD_SIMPLE="${COMPLEXITY_THRESHOLD_SIMPLE:-3}"
 COMPLEXITY_THRESHOLD_MEDIUM="${COMPLEXITY_THRESHOLD_MEDIUM:-6}"
 
-# --- Selective Context ---
-# Send only relevant files to each consultant
+# Deprecated no-ops; retained through v4.x for configuration compatibility.
 ENABLE_SELECTIVE_CONTEXT="${ENABLE_SELECTIVE_CONTEXT:-false}"
 MAX_FILES_PER_CONSULTANT="${MAX_FILES_PER_CONSULTANT:-5}"
 
@@ -1011,4 +998,4 @@ EOF
 # VERSION
 # =============================================================================
 
-AI_CONSULTANTS_VERSION="4.0.3"
+AI_CONSULTANTS_VERSION="4.0.4"

package/scripts/consult_all.sh

@@ -489,12 +489,12 @@ if [[ ${#SELECTED_CONSULTANTS[@]} -eq 0 ]]; then
     exit 1
 fi
 
-# Minimum 2 consultants required for meaningful comparison
+# Minimum 2 consultants required for a coverage panel
 if [[ ${#SELECTED_CONSULTANTS[@]} -lt 2 ]]; then
-    log_error "At least 2 consultants required for meaningful comparison."
+    log_error "At least 2 consultants are required for a coverage panel."
     log_error "Currently enabled: ${#SELECTED_CONSULTANTS[@]} (${SELECTED_CONSULTANTS[*]})"
     echo "" >&2
-    log_info "Run ./scripts/setup_wizard.sh to configure additional consultants"
+    log_info "Run \"$SCRIPT_DIR/../bin/ai-consultants\" configure to configure additional consultants"
     log_info "Or manually enable more:"
     log_info "  ENABLE_GEMINI=true ENABLE_CODEX=true ./scripts/consult_all.sh \"query\""
     exit 1

package/scripts/doctor.sh

@@ -413,11 +413,11 @@ check_configuration() {
         check_pass
     elif [[ $enabled_count -eq 1 ]]; then
         _print "  ✗ Enabled consultants: $enabled_count (need at least 2)"
-        add_issue "config" "Only 1 consultant enabled, need at least 2" "Run: ./scripts/setup_wizard.sh"
+        add_issue "config" "Only 1 consultant enabled, need at least 2" "Run: \"$SCRIPT_DIR/../bin/ai-consultants\" configure"
         check_fail
     else
         _print "  ✗ Enabled consultants: 0 (need at least 2)"
-        add_issue "config" "No consultants enabled" "Run: ./scripts/setup_wizard.sh"
+        add_issue "config" "No consultants enabled" "Run: \"$SCRIPT_DIR/../bin/ai-consultants\" configure"
         check_fail
     fi
 
@@ -825,8 +825,8 @@ suggest_configuration() {
     if (( available_count < 2 )); then
         echo ""
         echo "# WARNING: Less than 2 consultants available."
-        echo "# AI Consultants requires at least 2 to deliberate."
-        echo "# Install more CLIs or run ./scripts/setup_wizard.sh"
+        echo "# AI Consultants requires at least 2 for a coverage panel."
+        echo "# Install more CLIs or run \"$SCRIPT_DIR/../bin/ai-consultants\" configure"
     fi
 }
 

package/scripts/install.sh

@@ -348,8 +348,8 @@ echo "━━━━━━━━━━━━━━━━━━━━━━━━
 echo ""
 log_info "Option B: Configure via Bash"
 echo ""
-echo "  1. Run the setup wizard:"
-echo "     $INSTALL_DIR/scripts/setup_wizard.sh"
+echo "  1. Configure available consultants:"
+echo "     $INSTALL_DIR/bin/ai-consultants configure"
 echo ""
 echo "  2. Run a consultation:"
 echo "     $INSTALL_DIR/scripts/consult_all.sh \"Your question\""

package/scripts/lib/api.sh

@@ -38,46 +38,6 @@ sanitize_error_message() {
         -e 's/([a-zA-Z0-9_-]{32,})/[POSSIBLE_KEY]/g'
 }
 
-# =============================================================================
-# API KEY VALIDATION
-# =============================================================================
-
-# Check if an API key environment variable is set
-# Usage: check_api_key "QWEN3_API_KEY" "Qwen3"
-check_api_key() {
-    local key_var_name="$1"
-    local consultant_name="$2"
-
-    # Get the value of the environment variable by name
-    local key_value="${!key_var_name:-}"
-
-    if [[ -z "$key_value" ]]; then
-        log_error "[$consultant_name] API key not set: $key_var_name"
-        log_info "Set the $key_var_name environment variable to use $consultant_name"
-        return 1
-    fi
-
-    # Basic validation: key should be non-empty and not contain obvious placeholders
-    if [[ "$key_value" == *"your_"* ]] || [[ "$key_value" == *"YOUR_"* ]] || [[ "$key_value" == "xxx"* ]]; then
-        log_error "[$consultant_name] API key appears to be a placeholder: $key_var_name"
-        return 1
-    fi
-
-    # Validate key format (minimum length, no whitespace)
-    if [[ ${#key_value} -lt 10 ]]; then
-        log_error "[$consultant_name] API key too short: $key_var_name"
-        return 1
-    fi
-
-    if [[ "$key_value" =~ [[:space:]] ]]; then
-        log_error "[$consultant_name] API key contains whitespace: $key_var_name"
-        return 1
-    fi
-
-    log_debug "[$consultant_name] API key validated"
-    return 0
-}
-
 # =============================================================================
 # HTTP ERROR HANDLING
 # =============================================================================
@@ -724,18 +684,3 @@ check_rate_limit() {
 
     return 0
 }
-
-# Clear rate limit state for a consultant (useful for testing)
-# Usage: clear_rate_limit <consultant_name>
-clear_rate_limit() {
-    local consultant_name="$1"
-    local safe_name=$(echo "$consultant_name" | tr '[:upper:]' '[:lower:]' | tr -cs '[:alnum:]' '_')
-    local state_file="${RATE_LIMIT_DIR}/${safe_name}_ratelimit"
-
-    rm -f "$state_file" 2>/dev/null || true
-}
-
-# Clear all rate limit state
-clear_all_rate_limits() {
-    rm -rf "$RATE_LIMIT_DIR" 2>/dev/null || true
-}