ai-consultants 2.25.2 → 3.1.1

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

@@ -38,7 +38,7 @@
 # =============================================================================
 # API-BASED CONSULTANT KEYS
 # =============================================================================
-# These are required for the API-based consultants (Qwen3, GLM, Grok, DeepSeek)
+# These are required for API transports and API-only consultants.
 
 # Qwen3 (Alibaba DashScope) - The Analyst
 # Get yours at: https://dashscope.console.aliyun.com/
@@ -48,7 +48,8 @@
 # Get yours at: https://open.z.ai/
 # GLM_API_KEY=your_zhipu_api_key
 
-# Grok (xAI) - The Provocateur
+# Grok API fallback (the Grok Build CLI normally uses its own login)
+# Official docs call this XAI_API_KEY; GROK_API_KEY remains the project setting.
 # Get yours at: https://console.x.ai/
 # GROK_API_KEY=your_xai_api_key
 
@@ -73,18 +74,18 @@ ENABLE_MISTRAL=true
 ENABLE_CURSOR=true
 ENABLE_KIMI=true
 ENABLE_QWEN3=true
+ENABLE_GROK=true
 ENABLE_MINIMAX=true
 ENABLE_CLAUDE=true
 
 # API-only consultants (default: disabled - require API keys)
 ENABLE_GLM=false
-ENABLE_GROK=false
 ENABLE_DEEPSEEK=false
 
 # =============================================================================
 # CLI/API MODE SWITCHING (v2.6+)
 # =============================================================================
-# 6 agents support switching: Gemini, Codex, Claude, Mistral, Qwen3, MiniMax
+# 7 agents support switching: Gemini, Codex, Claude, Mistral, Qwen3, Grok, MiniMax
 # When API mode is enabled, CLI mode is automatically disabled.
 
 # GEMINI_USE_API is auto-resolved when left UNSET (v2.15.1): API mode if
@@ -160,8 +161,13 @@ QWEN3_CMD=qwen
 # rejected by the provider with a 400, not silently ignored.
 # QWEN3_REASONING_EFFORT=
 
+# GROK_USE_API is auto-resolved CLI-first: Grok Build is used whenever `grok`
+# is installed; the xAI API is selected when the CLI is unavailable and a key
+# exists. A failed CLI launch also falls back to the API at runtime.
+# GROK_USE_API=false
+
 # =============================================================================
-# API-BASED CONSULTANT CONFIGURATION
+# API-ONLY AND FALLBACK CONFIGURATION
 # =============================================================================
 
 # GLM - The Methodologist
@@ -169,7 +175,8 @@ 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 Build CLI + xAI API fallback - The Provocateur
+GROK_CMD=grok
 GROK_MODEL=grok-4.5
 GROK_TIMEOUT=180
 GROK_API_URL=https://api.x.ai/v1/chat/completions
@@ -203,7 +210,7 @@ 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 +226,6 @@ 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 +276,6 @@ 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

@@ -2,11 +2,11 @@
 
 ## Project Overview
 
-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.
+AI Consultants is a multi-model coverage 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**: 2.25.2
+**Version**: 3.1.1
 
 ## 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
 
@@ -432,6 +419,15 @@ All consultants now use premium models by default:
 
 Override with environment variables: `CLAUDE_MODEL`, `GEMINI_MODEL`, `CODEX_MODEL`, `KIMI_MODEL`, etc.
 
+Grok is CLI-first through the official Grok Build `grok` command, with
+`grok-4.5` passed explicitly in headless mode. The prompt is delivered with
+`--prompt-file`; HOME and CWD are isolated, built-in/MCP tools are denied, and
+the strict sandbox prevents user or project extensions from joining the
+consultation. The xAI Chat Completions path is retained only when the CLI is
+missing, cannot launch, or lacks usable authentication and `GROK_API_KEY` is
+available. A timeout, model error, empty response, or other post-launch failure
+is surfaced and never silently rerouted to the API.
+
 ## v2.4 Features
 
 ### Budget Enforcement (Opt-in)
@@ -613,32 +609,21 @@ 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 +786,24 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v3.1.1
+- **`doctor` no longer aborts at the first missing enabled consultant.** The v3.1.0 tag workflow exposed the pre-existing `set -e` interaction when Grok became CLI-first and the clean Ubuntu runner had no `grok` binary: the main JSON diagnostic exited before emitting output. Missing CLI/API configuration checks now add their issue and continue to the final summary, which still exits unhealthy. `test_doctor.sh` stubs the complete CLI roster, rejects empty JSON output, and includes a dedicated missing-Grok regression. Full gate: 16/16 suites; shellcheck green.
+
+### v3.1.0
+- **Grok is now a first-class CLI/API-switchable consultant on `grok-4.5`.** `scripts/query_grok.sh` uses the official Grok Build headless interface, `scripts/config.sh` resolves CLI-first while preserving API-only installations, and configure/doctor/update-clis/docs all classify Grok with the other switchable consultants. `XAI_API_KEY` is accepted as the official alias for the historical `GROK_API_KEY` contract. The route that actually answered is recorded as `metadata.transport = cli|api|api_fallback`.
+- **The CLI boundary is enforced rather than documented.** The first implementation disabled plan/subagents/memory/web but still inherited the current checkout and the maintainer's Grok environment; `grok inspect --json` showed 1 MCP server, 13 plugins, 11 hooks, 79 skills, and 3 project instructions available to an advisory consultation. Each run now creates an ephemeral mode-700 HOME/CWD, copies only a regular non-symlink `auth.json` at mode 600, supplies `--tools ""`, `--permission-mode dontAsk`, `--sandbox strict`, and explicit deny rules, then validates the temp-prefix before recursive cleanup. A live Grok 4.5 smoke succeeded through this isolated path.
+- **Prompts use `--prompt-file`, not argv.** `FULL_QUERY` includes context files; passing it through `-p "$FULL_QUERY"` exposed the prompt in the process list and failed before Grok launched once the combined context crossed `ARG_MAX`. Reproduced locally with a 1.1 MiB context (`timeout: Argument list too long`). The private prompt file removes both failure modes, and the regression suite drives the same 1.1 MiB case.
+- **API fallback means transport unavailable, not "any non-zero".** The initial adapter sent every CLI error to the API when a key existed — including timeouts, model errors, empty responses, and a generic tested `exit 42` — which hid CLI regressions and could add an unexpected API charge. `grok_cli_is_unavailable` now recognizes missing/unexecutable binaries and authentication/startup failures only; post-launch failures remain `transport=cli` and surface as errors. Missing-command and authentication fallback paths are tested separately.
+- **Regression and release coverage.** New `test_query_grok.sh` carries 26 assertions across headless flags/model pinning, HOME/CWD/auth isolation, tool denial, transport metadata, API fallback boundaries, and large contexts. The master runner discovers it automatically, taking `npm test` to 16 suites; the v3.1.0 release gate and shellcheck pass. README, SKILL, setup/recipes/configuration references, changelog, and the showcase roster are synchronized.
+
+### 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`.