ai-consultants 2.25.1 → 3.0.0

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

@@ -42,34 +42,29 @@ Query multiple AI models for expert opinions on a coding question.
    - Read `<output_dir>/synthesis.json` using the **Read** tool (may not exist if synthesis was skipped or failed)
    - If neither exists, use the **Glob** tool with pattern `<output_dir>/*.json` to discover individual consultant response files, then read each one
 
-5. **Present the results** using this template:
+5. **Present the results** using this template. The panel's value is *coverage* — the
+   union of distinct points across diverse models, including what only one raised — not a
+   single voted winner:
 
-   ### Consensus
-   - **Score**: <consensus_percentage>% (<consensus_level: strong/medium/low/none>)
-   - **Category**: <question_category>
+   ### Category
+   - <question_category>
 
    ### Consultant Summary
    | Consultant | Confidence | Approach | Key Insight |
    |------------|-----------|----------|-------------|
    | <name> | <score>/10 | <approach> | <one-line from summary> |
 
-   ### Synthesized Recommendation
-   - **Recommended approach**: <approach>
-   - **Summary**: <synthesized summary>
+   ### Coverage (the union of distinct considerations)
+   - <every distinct point, recommendation, risk, and edge case raised by ANY consultant,
+     deduplicated but preserving points only one model raised; note who raised each>
 
-   ### Key Agreements
-   - <points most consultants agree on>
-
-   ### Key Disagreements
-   - <points where consultants diverge>
-
-   ### Risk Assessment
-   - <caveats and uncertainty factors raised>
+   ### Risks & Caveats
+   - <distinct caveats and uncertainty factors raised across the panel>
 
    ### Suggested Next Steps
-   - <actionable items based on the recommendation>
+   - <actionable items drawn from the coverage above>
 
-   If `synthesis.json` is missing, build the summary table and recommendation directly from the individual consultant JSON files in the output directory.
+   If `synthesis.json` is missing, build the summary table and coverage directly from the individual consultant JSON files in the output directory (take the union of their distinct points).
 
 6. **Error recovery**:
    - **Exit code 1** (general failure): Tell the user and suggest running diagnostics:
@@ -84,9 +79,8 @@ Query multiple AI models for expert opinions on a coding question.
 
 | Variable | Effect |
 |----------|--------|
-| `ENABLE_DEBATE=true` | Enable multi-round debate for deeper analysis |
 | `ENABLE_SMART_ROUTING=true` | Auto-select best consultants for the question type |
-| `DEBATE_ROUNDS=2` | Number of debate rounds (1-3) |
+| `SYNTHESIS_STRATEGY=compare_only` | Present each consultant side-by-side instead of the coverage union |
 | `FORCE_PROJECT_TREE=true` | Include the project tree even for pointed categories (SECURITY, QUICK_SYNTAX, etc.) |
 
 ## Follow-up

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

@@ -12,8 +12,6 @@ All skill details (consultants, personas, presets, strategies, features, configu
 | Command | Description |
 |---------|-------------|
 | `/ai-consultants:consult` | Main consultation — ask AI consultants a coding question |
-| `/ai-consultants:debate` | Run consultation with multi-round debate |
-| `/ai-consultants:roster-audit` | Audit which consultants add distinct value vs echo the panel |
 | `/ai-consultants:help` | Show this help |
 
 ## Quick Examples

package/.env.example

@@ -203,7 +203,7 @@ MINIMAX_FORMAT=openai
 
 # Defaults used when --preset / --strategy are omitted
 DEFAULT_PRESET=balanced
-DEFAULT_STRATEGY=majority
+DEFAULT_STRATEGY=coverage
 
 # The invoking integration normally sets this per run for self-exclusion.
 INVOKING_AGENT=unknown
@@ -219,34 +219,6 @@ 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
-
-# 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
@@ -297,23 +269,6 @@ 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
 # =============================================================================

package/CLAUDE.md

@@ -6,7 +6,7 @@ AI Consultants is a multi-model AI deliberation system that queries up to 11 AI
 
 **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**: 2.25.1
+**Version**: 3.0.0
 
 ## Distribution
 
@@ -39,27 +39,18 @@ ai-consultants/
 │   ├── config.sh               # Centralized configuration
 │   ├── doctor.sh               # Diagnostic and auto-fix tool (v2.2)
 │   ├── update_clis.sh          # Check/update installed consultant CLIs (v2.21)
-│   ├── peer_review.sh          # Anonymous peer review (v2.2)
-│   ├── roster_audit.sh         # Roster uncorrelated-value audit (v2.20)
-│   ├── roster_calibrate.sh     # Measured capability calibration, Tier A (v2.20)
-│   ├── run_calibration.sh      # Calibration data-collection harness (v2.20)
-│   ├── taste_elo.sh            # Pairwise-judge taste Elo, Tier B (v2.20)
 │   ├── install.sh              # One-liner installer (v2.2)
 │   ├── query_*.sh              # Wrapper for each consultant
 │   ├── query_claude.sh         # Claude consultant (v2.2)
-│   ├── synthesize.sh           # Auto-synthesis of responses
-│   ├── debate_round.sh         # Multi-Agent Debate
+│   ├── synthesize.sh           # Coverage-union synthesis of responses
 │   ├── classify_question.sh    # Question classifier
 │   ├── followup.sh             # Follow-up queries
 │   ├── preflight_check.sh      # DEPRECATED v2.10.9 (thin wrapper -> doctor.sh)
 │   └── lib/
-│       ├── common.sh           # Shared utilities (logging, panic mode)
+│       ├── common.sh           # Shared utilities (logging, quorum grading)
 │       ├── personas.sh         # Consultant persona definitions
 │       ├── schema.json         # JSON output schema
-│       ├── voting.sh           # Voting/consensus + confidence intervals
-│       ├── routing.sh          # Smart routing + cost-aware routing
-│       ├── orchestration.sh    # Dynamic orchestration planner + shapes (v2.16)
-│       ├── stance.sh           # Stance-based semantic consensus (v2.21, opt-in)
+│       ├── routing.sh          # Smart routing (category affinity) + cost-aware routing
 │       ├── session.sh          # Session management
 │       ├── costs.sh            # Cost tracking + response limits
 │       ├── cache.sh            # Semantic caching (v2.3)
@@ -158,17 +149,13 @@ Each consultant must produce JSON with this minimum structure:
 ## Main Flow
 
 1. `consult_all.sh` receives query, optional files, and flags (`--preset`, `--strategy`)
-2. Applies preset if specified (`apply_preset()` in config.sh)
+2. Applies preset if specified (`apply_preset()` in config.sh) — sets the consultant set + model tier
 3. Classifies the question (`classify_question.sh`)
-4. Plans orchestration: complexity + intent → shape (`select_orchestration_shape()` in `lib/orchestration.sh`); `ORCHESTRATION_MODE=fixed` bypasses to the legacy path
-5. Selects consultants (smart routing or all)
-6. Launches parallel queries (`query_*.sh`)
-7. Deliberates per the chosen shape: convergence loop / adversarial gate / tournament / exhaustive sweep (`run_orchestration()`), or fixed debate rounds in `fixed` mode
-8. Calculates voting/consensus with confidence intervals (`lib/voting.sh`)
-9. Checks for panic mode triggers (`lib/common.sh`)
-10. Generates synthesis with selected strategy (`synthesize.sh`)
-11. Optionally runs peer review (`peer_review.sh`)
-12. Produces final report
+4. Selects consultants (smart routing by category affinity, or all)
+5. Launches parallel queries (`query_*.sh`) — one shot per consultant, no serial rounds
+6. Grades quorum (`grade_quorum()` in `lib/common.sh`) — surfaces a degraded panel
+7. Generates synthesis with the selected strategy (`synthesize.sh`); the default `coverage` produces the deduplicated UNION of every distinct point across the panel
+8. Produces final report
 
 ## v2.2 Features
 
@@ -613,32 +600,21 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 |----------|---------|-------------|
 | `INVOKING_AGENT` | unknown | Agent invoking the skill (for self-exclusion) |
 | `ENABLE_CLAUDE` | true | Enable Claude consultant (auto-excluded under Claude Code) |
-| `ENABLE_DEBATE` | false | Enable Multi-Agent Debate |
-| `DEBATE_ROUNDS` | 1 | Number of debate rounds |
-| `ENABLE_SYNTHESIS` | true | Auto-synthesis of responses |
-| `ENABLE_SMART_ROUTING` | false | Intelligent routing |
+| `ENABLE_SYNTHESIS` | true | Coverage-union synthesis of responses |
+| `ENABLE_SMART_ROUTING` | false | Intelligent routing by category |
 | `ENABLE_COST_TRACKING` | true | Track costs |
 | `MAX_SESSION_COST` | 1.00 | Max budget ($) |
-| `ENABLE_PANIC_MODE` | auto | Panic mode trigger (v2.2) |
-| `PANIC_CONFIDENCE_THRESHOLD` | 5 | Panic threshold (v2.2) |
 | `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) |
 | `CODEX_MODEL` | gpt-5.5 | Codex model (v2.5) |
 | `MISTRAL_MODEL` | mistral-large-3 | Mistral model (v2.5) |
-| `SYNTHESIS_STRATEGY` | majority | Synthesis strategy (v2.2) |
+| `SYNTHESIS_STRATEGY` | coverage | Synthesis strategy (coverage=union of distinct points) |
 | `ENABLE_SEMANTIC_CACHE` | true | Semantic response caching (v2.3) |
 | `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` | 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) |
-| `CAPABILITY_WEIGHT_STRENGTH` | 10 | Vote-weight modulation: conf*(S+cap)/S (v2.20) |
-| `CAPABILITY_DEFAULT` | 5 | Fallback capability for a missing consultant/axis (v2.20) |
-| `ENABLE_STANCE_CONSENSUS` | false | Enumerated-stance exact-match consensus (v2.21, opt-in; +1 LLM call/run) |
-| `STANCE_MAX_OPTIONS` | 5 | Max stance options generated per question (v2.21) |
 | `ENABLE_BUDGET_LIMIT` | false | Budget enforcement (v2.4, opt-in) |
 | `BUDGET_ACTION` | warn | Action on budget exceeded: warn/stop (v2.4) |
 | `QWEN3_USE_API` | false | Use DashScope API instead of qwen CLI (v2.7) |
@@ -801,6 +777,18 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v3.0.0
+- **Phase 2 of the panel-premise investigation: the deliberation/consensus machinery is removed and the default is now the coverage union.** Two independent reviews (Codex `gpt-5.6-sol`, then Fable-5) had judged the panel premise weak — voting/consensus measure *agreement*, not correctness, and no held-out comparison against one strong model existed. A held-out A/W/C coverage experiment (maintainer instrumentation on the `experiment/coverage-metric` branch, not shipped) resolved it: **task-dependent.** On convergent single-answer defect-finding a single strong model (Gemini 3.1 Pro) caught **19/19** hard bugs (repo-internal + external CVEs/concurrency incl. the Rust `Arc` bug found by RustBelt formal verification) → the panel has no coverage headroom. On **breadth/enumeration** (deep 60-point rubrics across JWT/webhook/cache), rubric coverage was **A 51% · self-consistency C 70% · panel W 93%, W>C>A on every item** → diversity, not volume, and specifically the raw **union** (deliberation OFF). The durable value is the diverse fan-out + union; the averaging machinery adds nothing measurable. Directional (n=3 breadth, hand-validated; n=19 defect).
+- **Removed end to end** (six test-green commits on `refactor/remove-deliberation`, merged via PR #6): `lib/voting.sh` (voted recommendation, 1-10 score, consensus score, dissenters), `lib/orchestration.sh` (shape planner + convergence loop) + `debate_round.sh`, `lib/stance.sh`, `peer_review.sh`, and the capability-calibration cluster `roster_audit.sh`/`roster_calibrate.sh`/`run_calibration.sh`/`taste_elo.sh` + `references/calibration_benchmark.json` + the `capabilities`/`category_axis` blocks in `affinity.json`. Panic functions cut from `common.sh`; capability functions (`get_capability`/`get_category_axis`) and the `ENABLE_CAPABILITY_ROUTING` branch cut from `routing.sh`. Config: `ENABLE_DEBATE`/`DEBATE_ROUNDS`, `ORCHESTRATION_MODE`/`CONVERGENCE_*`, `ENABLE_DEBATE_OPTIMIZATION`/`DEBATE_*`, `ENABLE_PANIC_MODE`/`PANIC_*`, `ENABLE_ADVERSARIAL_VERIFY`, `ENABLE_PEER_REVIEW`/`PEER_REVIEW_MIN`, `ENABLE_CAPABILITY_*`/`CAPABILITY_*`, `ENABLE_STANCE_CONSENSUS`/`STANCE_*`. Presets no longer force debate/peer-review. The `debate` and `roster-audit` slash commands are gone (installers prune them). 19 files deleted, ~-4600 lines. 6 test suites removed.
+- **`consult_all.sh` pipeline** is now classify → route → parallel fan-out → synthesis (the orchestration-planning, panic, Round-2+ deliberation, and voting/consensus blocks are gone; `optimization_metrics.json` and the report no longer emit consensus/orchestration/capability fields). `QUERY_COMPLEXITY` is retained (from `costs.sh`) for opt-in cost-aware routing. `KNOWN_FEATURE_FLAGS` synced (27 → 19).
+- **`synthesize.sh`** default strategy is now `coverage` (alias `union`): the deduplicated union of every distinct point, crediting what only one model raised; it does NOT collapse to a winner. `majority` reworded (no consensus language); `compare_only`/`risk_averse`/`security_first`/`cost_capped` kept. `DEFAULT_STRATEGY` default `majority` → `coverage`. `doctor --suggest-preset` now recommends `coverage`.
+- **`npm test` = 15 suites** (was 22), hermetic (`AI_CONSULTANTS_CONFIG_DIR=<empty>`). **Release-gate note (recurring):** `scripts/release.sh` runs `npm test` against the maintainer's real `~/.config` (it sources `config.sh` → `load_user_config` first), and under the real config `test_context_optimization.sh` hung the gate; the tree is green under the documented hermetic condition (`AI_CONSULTANTS_CONFIG_DIR=<empty> npm test </dev/null`). Same hermeticity class as the v2.23.0/v2.25.1 gate incidents.
+- **Docs swept** (README/SKILL/CLAUDE.md/consult.md/references/docs) to the coverage-first framing; the reference-doc sweep was delegated and verified. CLAUDE.md's historical `## v2.X Features` sections are left as archive — this entry recontextualizes them. **Not statistically binding**: breadth is n=3; a binding claim needs n≥15–20 deep-rubric items (the harness exists on `experiment/coverage-metric`).
+
+### v2.25.2
+- **`doctor`'s static ✓ was a false all-clear.** `check_cli_consultant` verifies `command -v` (installed) or key-present; neither confirms the consultant answers. So `✓ All systems healthy!` and JSON `status: "healthy"` were printed on installation state alone — a consultant with an expired key or spent quota passes every static check and fails the first real query. Surfaced concretely: static doctor called all 11 healthy; `doctor --live` showed 8/11 (Cursor usage limit, Qwen3 401, Grok bad xAI key returned as HTTP 400). Fix gates the word "healthy" on `LIVE_MODE`: a static-only clean run now prints "Static checks passed: CLIs installed, keys present … verify with doctor --live", and JSON reports `status: "static_ok"` + a new `verified: live|static` field; "healthy" now implies a live check backed it. `test_doctor.sh` asserts the invariant directly (a static-only run must never report `healthy`) rather than pinning a specific status, so it holds regardless of the test host's own consultant health. v2.18.0 added `--live` but left the default over-claiming; this closes that. `npm test` = 22 suites.
+- **Note (not shipped, local only)**: the 3 down consultants were all credentials, not code — Grok/Qwen3 keys refreshed and Cursor disabled in the maintainer's own `~/.config`, taking the local live panel to 10/10 (Cursor off by choice). Qwen locally points at Token Plan `qwen3.8-max-preview`; the shipped default stays `qwen3.7-max`.
+
 ### v2.25.1
 - **Six defects found by an independent review of the released v2.25.0** (Codex `gpt-5.6-sol`, effort high, read-only via the `sol-reviewer` profile). Five were reproduced locally by executing the shipped functions before accepting them; the bash 3.2 crash was verified by the reviewer against `/bin/bash 3.2.57`.
 - **`calculate_final_score` scored every consultant as a dissenter.** `calculate_weighted_recommendation` emitted `_map_sanitize_key`'s output (spaces and punctuation stripped) as the winner, while `calculate_final_score` compared the raw `.response.approach` against it. Unanimous multiword panels scored 2/10, single-word panels 10/10. Voting now keeps original strings in bash 3.2-compatible indexed arrays. **The shipped voting tests used single-word approaches, which is exactly why this survived every prior review** — when writing a voting fixture, use a realistic multiword approach.

package/README.md

@@ -1,8 +1,8 @@
-# AI Consultants v2.25.1
+# AI Consultants v3.0.0
 
-> **A harness for every question.** A panel of up to 11 frontier models that writes its own playbook per question — fan out, debate to convergence, cross-examine under adversarial review, or run a tournament — and checks its work before it reaches you.
+> **Coverage, not a single guess.** A panel of up to 11 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-2.25.1-blue.svg)](https://github.com/matteoscurati/ai-consultants)
+[![Version](https://img.shields.io/badge/version-3.0.0-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)
@@ -35,15 +35,13 @@
 
 ## Why AI Consultants?
 
-A single model gives you a single guess. AI Consultants gives you a **panel that deliberates — and adapts how it deliberates to the question in front of it.**
+A single model gives you a single guess — and it misses whatever falls in its blind spots. AI Consultants fans your question out to a **panel of models from different vendors** and returns the **union of their distinct answers**: the point one model raised and the others didn't is exactly the value.
 
-Instead of running a fixed script, it classifies your question, picks an orchestration **shape**, and iterates until the answers hold up — the way a workflow builds a harness for the task at hand:
-
-- **Dynamic orchestration** — the engine chooses the strategy per question: a quick read, a convergence loop, an adversarial refutation gate, a tournament of approaches, or an exhaustive sweep
-- **Convergence, not fixed rounds** — debate iterates until the panel actually agrees (or provably won't), instead of a hardcoded count
-- **Self-checking** — security answers are stress-tested by consultants trying to refute them before anything reaches you
-- **11 supported consultants** with distinct personas (Architect, Pragmatist, Devil's Advocate, …)
-- **Confidence-weighted synthesis** — one recommendation, with the dissent and the path it took surfaced so you know how much to trust it
+- **Cross-vendor diversity → coverage** — different model families have different blind spots, so the union covers what any one misses. On open-ended questions ("what could go wrong with this design?", "enumerate the risks") a diverse panel covers materially more of the answer space than one strong model — or than sampling one model repeatedly.
+- **Parallel fan-out** — every consultant runs at once; no serial deliberation rounds.
+- **Coverage synthesis** — the default synthesis is the deduplicated *union* of every distinct point, not a single voted winner (use `--strategy compare_only` for a side-by-side, or `majority` for a blended recommendation).
+- **11 supported consultants** with distinct personas (Architect, Pragmatist, Devil's Advocate, …) — the personas deliberately decorrelate the panel.
+- **Best for breadth** — threat-modeling, design review, "what am I missing?", exhaustive enumeration. For a single-answer factual or defect-finding question, one strong model is usually enough.
 
 ---
 
@@ -216,7 +214,6 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 | Command | Description |
 |---------|-------------|
 | `/ai-consultants:consult` | Main consultation - ask AI consultants a coding question |
-| `/ai-consultants:debate` | Run consultation with multi-round debate |
 | `/ai-consultants:help` | Show all commands and usage |
 
 Configuration (presets, strategies, features, personas, API keys) can be managed via natural language — just ask.
@@ -342,8 +339,8 @@ cd ai-consultants
 # With preset
 ./scripts/consult_all.sh --preset balanced "Redis or Memcached?"
 
-# With debate
-ENABLE_DEBATE=true DEBATE_ROUNDS=2 ./scripts/consult_all.sh "Microservices vs monolith?"
+# Side-by-side instead of the coverage union
+./scripts/consult_all.sh --strategy compare_only "Microservices vs monolith?"
 
 # With smart routing
 ENABLE_SMART_ROUTING=true ./scripts/consult_all.sh "Bug in auth code"
@@ -434,13 +431,8 @@ Choose the right balance of quality, speed, and cost with model quality tiers.
 | `medium` | Standard | 4 | General questions |
 | `fast` | Economy | 2 | Quick checks |
 
-**Deliberation depth is not fixed by the preset.** Under the default
-`ORCHESTRATION_MODE=auto` the planner picks the shape per question, so the
-`DEBATE_ROUNDS` a preset pins applies only under `ORCHESTRATION_MODE=fixed`,
-and a `SECURITY`-classified question runs the adversarial shape — including a
-peer-review round — whatever preset you chose. `max_quality` additionally
-enables peer review outright; `medium` and `fast` do not *clear* it, so an
-enabled peer review carries into them.
+A preset only chooses the **consultant set and model tier** — every run then fans out in
+parallel and returns the coverage union.
 
 ### Models by Tier
 
@@ -487,14 +479,14 @@ Choose how many consultants to use:
 
 | Preset | Consultants | Tier | Use Case |
 |--------|-------------|------|----------|
-| `max_quality` | 8 of 11 (+ peer review) | Premium | Critical decisions |
+| `max_quality` | 8 of 11 | Premium | Critical decisions |
 | `medium` | 4 | Standard | General questions |
 | `fast` | 2 | Economy | Quick checks |
 | `minimal` | 2 (Gemini + Codex) | Default | Quick questions, low cost |
 | `balanced` | 4 (+ Mistral + Cursor) | Default | Standard consultations |
 | `thorough` | 4 | Default | Comprehensive analysis |
-| `high-stakes` | Expanded panel + debate | Default | Critical decisions |
-| `security` | Security-focused + debate | Default | Security reviews |
+| `high-stakes` | Expanded panel (5 of 11) | Default | Critical decisions |
+| `security` | Security-focused (4) | Default | Security reviews |
 | `cost-capped` | Budget-conscious | Default | Minimal API costs |
 
 **Bash:**
@@ -533,8 +525,8 @@ ai-consultants configure --interactive
 # Set any persistent parameter without opening an editor
 ai-consultants configure \
   --set DEFAULT_PRESET=balanced \
-  --set ENABLE_DEBATE=true \
-  --set ORCHESTRATION_MODE=converge
+  --set DEFAULT_STRATEGY=coverage \
+  --set ENABLE_SMART_ROUTING=true
 
 # Inspect the complete machine-readable parameter surface
 ai-consultants configure --show-parameters
@@ -561,8 +553,8 @@ For ad-hoc overrides without persisting, the most common knobs:
 
 ```bash
 DEFAULT_PRESET=balanced      # minimal | balanced | thorough | high-stakes | fast | security
-DEFAULT_STRATEGY=majority    # majority | risk_averse | security_first | cost_capped | compare_only
-ENABLE_DEBATE=true           # Multi-agent debate (auto-skipped when consensus is high since v2.13)
+DEFAULT_STRATEGY=coverage    # coverage | compare_only | majority | risk_averse | security_first | cost_capped
+ENABLE_SMART_ROUTING=true    # Auto-select consultants by question category
 MAX_SESSION_COST=1.00        # USD budget cap (paired with ENABLE_BUDGET_LIMIT=true to enforce)
 KIMI_MODEL=kimi-code/k3      # Pin the Kimi consultant to K3
 ```
@@ -571,35 +563,25 @@ Full reference: [`references/configuration.md`](references/configuration.md). Co
 
 ### Configuration Recipes
 
-**Dynamic debate until convergence:**
+**Breadth review — the coverage union (default):**
 
 ```bash
-ENABLE_DEBATE=true \
-ORCHESTRATION_MODE=converge \
-CONVERGENCE_MAX_ROUNDS=4 \
-CONVERGENCE_TARGET_CONSENSUS=75 \
-ai-consultants --strategy risk_averse \
-  "Event log or mutable relational state for this service?"
+ai-consultants --preset high-stakes \
+  "What could go wrong with this webhook-delivery design?" src/webhooks.ts@PRIMARY
 ```
 
-**Repeatable two-round review:**
+**Security review, security-first framing:**
 
 ```bash
-ENABLE_DEBATE=true \
-ORCHESTRATION_MODE=fixed \
-DEBATE_ROUNDS=2 \
-ENABLE_DEBATE_OPTIMIZATION=false \
-ai-consultants "Review this migration plan" docs/migration.md@PRIMARY
+ai-consultants --preset security --strategy security_first \
+  "Find authentication bypasses" src/auth.ts@PRIMARY
 ```
 
-**Security review with adversarial verification:**
+**Side-by-side comparison (no synthesized union):**
 
 ```bash
-ENABLE_DEBATE=true \
-ORCHESTRATION_MODE=adversarial \
-ENABLE_PEER_REVIEW=true \
-ai-consultants --preset security --strategy security_first \
-  "Find authentication bypasses" src/auth.ts@PRIMARY
+ai-consultants --strategy compare_only \
+  "Event log or mutable relational state for this service?"
 ```
 
 **Live health gate plus hard quorum:**
@@ -611,9 +593,8 @@ QUORUM_ACTION=stop \
 ai-consultants "Make a release recommendation"
 ```
 
-See [13 complete recipes](docs/RECIPES.md) for fast, high-stakes, tournament,
-exhaustive audit, budget-capped, CLI-only, hybrid API, semantic-consensus, and
-large-context workflows.
+See the [recipes](docs/RECIPES.md) for balanced, fast, security, compare-only,
+budget-capped, CLI-only, hybrid API, and large-context workflows.
 
 ### Doctor Command
 
@@ -637,35 +618,18 @@ ai-consultants update-clis --dry-run                           # Preview: each C
 ## How It Works
 
 ```
-Classify -> Plan shape -> Fan out -> Deliberate & converge -> Synthesize
-   |            |             |               |
- category   orchestration  Gemini (8)    convergence loop /
- complexity    shape       Codex (7)     adversarial gate /
- intent                    Mistral (6)   tournament / exhaustive
-                           Cursor (9)
+Classify -> Route -> Fan out (parallel) -> Coverage synthesis
+   |          |            |                      |
+ category  smart       Gemini (8)          union of every
+          routing      Codex (7)           distinct point,
+                       Mistral (6)         deduplicated
+                       Cursor (9)
 ```
 
-The **shape** is chosen per question (or pinned via `ORCHESTRATION_MODE`):
-
-| Shape | When | What happens |
-|-------|------|--------------|
-| `quick` | simple questions | one fan-out, no debate |
-| `converge` | most questions | debate rounds until consensus is reached (not a fixed count) |
-| `adversarial` | security | a forced critique round + peer-review refutation gate |
-| `tournament` | "compare X vs Y" | converge, then declare a single winning approach |
-| `exhaustive` | "find all / audit" | loop until a round surfaces no new angle |
-
-Set `ORCHESTRATION_MODE=fixed` for the classic fixed-round pipeline.
-
-Consensus is measured lexically by default; set `ENABLE_STANCE_CONSENSUS=true`
-(opt-in, v2.21) to have the panel pick from a shared set of enumerated stance
-options and score agreement by exact match instead — see
-[references/configuration.md](references/configuration.md#semantic-consensus-v221-opt-in).
-
-With peer review:
-```
-Responses -> Anonymize -> Peer Ranking -> De-anonymize -> Peer Scores
-```
+1. **Classify** the question into a category.
+2. **Route** (optional, `ENABLE_SMART_ROUTING`) to the consultants with the best category affinity (`references/affinity.json`).
+3. **Fan out** to every selected consultant in parallel — one shot each, no serial rounds.
+4. **Synthesize** the **coverage union**: the deduplicated set of every distinct point, recommendation, risk, and edge case raised by any consultant. Override with `--strategy compare_only` (side-by-side) or `majority` (a single blended recommendation).
 
 ### Output
 
@@ -677,31 +641,34 @@ Each consultation generates:
 ├── codex.json           #   with confidence scores
 ├── mistral.json
 ├── cursor.json
-├── voting.json          # Consensus calculation
-├── synthesis.json       # Weighted recommendation
-├── report.md            # Human-readable report
-└── round_2/             # (if debate enabled)
+├── synthesis.json       # Coverage union
+└── report.md            # Human-readable report
 ```
 
 ---
 
 ## Best Practices
 
-### When to Use High-Stakes Mode
+### When the Panel Helps Most
+
+The panel's edge is **coverage** — surfacing what a single model misses. It pays off on
+open-ended, breadth questions:
 
-- Architectural decisions affecting system design
-- Security-critical code changes
-- Performance-critical optimizations
+- Threat-modeling and design review ("what could go wrong with this?")
+- Enumerating risks, edge cases, or failure modes
+- "What am I missing?" / exhaustive audits
 - Decisions that are difficult to reverse
 
+For a single-answer factual or defect-finding question, a single strong model is usually
+enough — the panel adds little.
+
 ### Interpreting Results
 
 | Scenario | Recommendation |
 |----------|----------------|
-| High confidence + High consensus | Proceed with confidence |
-| Low confidence OR Low consensus | Consider more options |
-| Mistral (Devil's Advocate) disagrees | Investigate the risks |
-| Panic mode triggered | Add more consultants or debate rounds |
+| A point only one consultant raised | Weigh it — the diversity is the point |
+| Mistral (Devil's Advocate) flags a risk | Investigate it |
+| Consultants diverge on approach | Use `--strategy compare_only` to see each side-by-side |
 
 ### Security
 

package/SKILL.md

@@ -5,12 +5,12 @@ license: MIT
 compatibility: Requires bash, jq, and at least 2 AI CLI tools (agy, codex, vibe, etc.). macOS and Linux.
 metadata:
   author: matteoscurati
-  version: 2.25.1
+  version: 3.0.0
 ---
 
-# AI Consultants v2.25.1 - AI Expert Panel
+# AI Consultants v3.0.0 - AI Expert Panel
 
-**A harness for every question.** Convene a panel of AI "consultants" for coding questions — and let the engine pick *how* they deliberate: a quick read, a convergence loop, an adversarial refutation gate, a tournament, or an exhaustive sweep. Each consultant has a **configurable persona** that shapes its analysis.
+**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.
 
 ## Quick Start
 
@@ -23,7 +23,6 @@ metadata:
 | Command | Description |
 |---------|-------------|
 | `/ai-consultants:consult` | Main consultation - ask AI consultants a coding question |
-| `/ai-consultants:debate` | Run consultation with multi-round debate |
 | `/ai-consultants:help` | Show all commands and usage |
 
 Configuration (presets, strategies, features, personas, API keys) can be managed via natural language — just ask.
@@ -71,29 +70,24 @@ For detailed CLI installation instructions, see [Setup Guide](docs/SETUP.md).
 ```
 /ai-consultants:consult "How to optimize this SQL query?"
 /ai-consultants:consult "Review this authentication flow" src/auth.ts
-/ai-consultants:debate "Microservices or monolith for our new service?"
+/ai-consultants:consult "What could go wrong with this design?" src/service.ts
 ```
 
-Presets: `minimal`, `balanced`, `thorough`, `high-stakes`, `local`, `security`, `cost-capped`. Strategies: `majority`, `risk_averse`, `security_first`, `cost_capped`, `compare_only`. See [Reference Details](references/details.md) for full tables, bash usage, and best practices.
+Presets: `minimal`, `balanced`, `thorough`, `high-stakes`, `security`, `cost-capped`, `max_quality`, `medium`, `fast`. Strategies: `coverage` (default; union of distinct points), `compare_only`, `majority`, `risk_averse`, `security_first`, `cost_capped`. See [Reference Details](references/details.md) for full tables, bash usage, and best practices.
 
 ## Workflow
 
-Query is classified, then sent to consultants in parallel. Responses are scored, voted on, and synthesized into a recommendation.
-
-**Dynamic orchestration (v2.16+):** a planner picks an orchestration *shape* per question — `quick` (simple), `converge` (debate until consensus, not a fixed round count), `adversarial` (SECURITY: forced critique + peer-review refutation gate), `tournament` (compare approaches → pick a winner), `exhaustive` (find-all: loop until no new angle). Set `ORCHESTRATION_MODE=fixed` for the legacy pipeline. See [configuration reference](references/configuration.md#dynamic-orchestration-v216).
+The query is classified, optionally routed by category, then sent to all consultants in parallel. Their responses are synthesized into the **coverage union** — the deduplicated set of every distinct point, recommendation, and risk raised across the panel (not a single voted winner). Use `--strategy compare_only` for a side-by-side, or `majority` for a blended recommendation.
 
 ## Features
 
 | Feature | Description | Toggle |
 |---------|-------------|--------|
-| **Personas** | Each consultant has a role that shapes responses | `ENABLE_PERSONA` |
-| **Synthesis** | Auto-combine responses into recommendation | `ENABLE_SYNTHESIS` |
-| **Debate** | Consultants critique each other's answers | `ENABLE_DEBATE` |
-| **Peer Review** | Consultants anonymously rank each other | `ENABLE_PEER_REVIEW` |
-| **Smart Routing** | Auto-select best consultants per question type | `ENABLE_SMART_ROUTING` |
+| **Personas** | Each consultant has a role that decorrelates responses | `ENABLE_PERSONA` |
+| **Coverage synthesis** | Union of every distinct point across the panel (default) | `ENABLE_SYNTHESIS` |
+| **Smart Routing** | Auto-select best consultants per question category | `ENABLE_SMART_ROUTING` |
 | **Cost Tracking** | Track API usage costs | `ENABLE_COST_TRACKING` |
-| **Panic Mode** | Auto-add rigor when uncertainty detected | `ENABLE_PANIC_MODE` |
-| **Stance Consensus** | Panel picks from enumerated stances; agreement by exact match (opt-in, v2.21) | `ENABLE_STANCE_CONSENSUS` |
+| **Health Gate** | Ping and prune dead consultants before the run (opt-in) | `ENABLE_HEALTH_GATE` |
 
 ## Configuration
 
@@ -101,9 +95,8 @@ All settings use environment variables. Key toggles:
 
 ```bash
 ai-consultants configure     # Auto-detect CLIs/API keys and persist all settings
-ENABLE_DEBATE=true           # Multi-agent debate
-ENABLE_SYNTHESIS=true        # Automatic synthesis
-ENABLE_PANIC_MODE=auto       # Auto-rigor for uncertainty
+ENABLE_SYNTHESIS=true        # Coverage-union synthesis
+ENABLE_SMART_ROUTING=true    # Route by question category
 ENABLE_BUDGET_LIMIT=false    # Budget enforcement (v2.4)
 ```
 
@@ -121,8 +114,7 @@ See [Full Configuration Reference](references/configuration.md) for all variable
 /tmp/ai_consultations/TIMESTAMP/
 ├── gemini.json        # Individual responses
 ├── codex.json
-├── voting.json        # Consensus
-├── synthesis.json     # Recommendation
+├── synthesis.json     # Coverage union
 └── report.md          # Human-readable
 ```
 
@@ -147,10 +139,9 @@ When a consultant fails during a consultation, the run prints the captured reaso
 
 | Scenario | Recommendation |
 |----------|----------------|
-| High confidence + High consensus | Proceed confidently |
-| Low confidence OR Low consensus | Consider more options |
-| Mistral disagrees | Investigate risks |
-| Panic mode triggered | Add debate rounds |
+| A point only one consultant raised | Weigh it — the diversity is the point |
+| Mistral (Devil's Advocate) flags a risk | Investigate it |
+| Consultants diverge on approach | Use `--strategy compare_only` to see each side-by-side |
 
 ## Troubleshooting
 
@@ -160,7 +151,7 @@ Run `./scripts/doctor.sh` to diagnose issues, or `./scripts/doctor.sh --fix` to
 
 - [Reference Details](references/details.md) - Presets, strategies, best practices, limitations
 - [Full Configuration](references/configuration.md) - All environment variables, models, tiers, timeouts
-- [Configuration Recipes](docs/RECIPES.md) - Copy-paste workflows for debate, routing, budgets, and transport
+- [Configuration Recipes](docs/RECIPES.md) - Copy-paste workflows for routing, budgets, and transport
 - [Setup Guide](docs/SETUP.md) - Installation, authentication
 - [Cost Rates](docs/COST_RATES.md) - Model pricing
 - [Smart Routing](docs/SMART_ROUTING.md) - Category routing