ai-consultants 3.4.0 → 3.5.0

package/.env.example

@@ -122,6 +122,8 @@ GEMINI_TIMEOUT=180
 GEMINI_CMD=agy
 # API-mode model ID (only used when GEMINI_USE_API=true)
 GEMINI_API_MODEL=gemini-3.1-pro-preview
+# Authenticated opt-ins: use Gemini 3.7 Flash (High/Low) for GEMINI_MODEL or
+# gemini-3.7-flash for GEMINI_API_MODEL.
 # Reasoning effort for the agy CLI. Passed as --effort <value>. Accepts only
 # low|medium|high; anything else is rejected by the provider and surfaces as a
 # diagnosed error (provider owns the enum — same stance as QWEN3_REASONING_EFFORT).
@@ -137,22 +139,30 @@ CODEX_CMD=codex
 # CODEX_REASONING_EFFORT=
 
 # Mistral Vibe - The Devil's Advocate
+# API model ID. Vibe uses the separate CLI alias below. Mistral Medium 3.5,
+# Large 3, and Small 4 API IDs are documented opt-ins until an API smoke passes.
 MISTRAL_MODEL=mistral-large-3
+MISTRAL_CLI_MODEL=mistral-medium-3.5
+# Official API opt-ins: use mistral-medium-3-5, mistral-large-2512, or
+# mistral-small-2603 for MISTRAL_MODEL after an authenticated API smoke.
 MISTRAL_TIMEOUT=180
 MISTRAL_CMD=vibe
 
 # Cursor - The Integrator
 CURSOR_MODEL=composer-2.5
 CURSOR_TIMEOUT=180
-CURSOR_CMD=agent
+CURSOR_CMD=cursor-agent
 
 # Kimi - The Eastern Sage (K3 via Kimi Code CLI)
 KIMI_MODEL=kimi-code/k3
+# max_quality selects the inventory-probed kimi-code/k3-256k target.
 KIMI_TIMEOUT=180
 KIMI_CMD=kimi
 
 # Claude - The Synthesizer
 CLAUDE_MODEL=claude-opus-5 # ai-consultants:default
+# Fable 5 is catalogued and priced but remains an explicit CLAUDE_MODEL opt-in
+# after its local smoke timed out.
 CLAUDE_TIMEOUT=240
 CLAUDE_CMD=claude
 CLAUDE_API_MAX_TOKENS=16384
@@ -184,13 +194,13 @@ QWEN3_CMD=qwen
 # =============================================================================
 
 # GLM - The Methodologist
-GLM_MODEL=glm-5.2
+GLM_MODEL=glm-5.3
 GLM_TIMEOUT=180
 GLM_API_URL=https://api.z.ai/api/coding/paas/v4/chat/completions
 
 # Grok Build CLI + xAI API fallback - The Provocateur
 GROK_CMD=grok
-GROK_MODEL=grok-4.5
+GROK_MODEL=grok-4.6
 GROK_TIMEOUT=180
 GROK_API_URL=https://api.x.ai/v1/chat/completions
 
@@ -202,6 +212,7 @@ DEEPSEEK_API_URL=https://api.deepseek.com/v1/chat/completions
 # MiniMax - The Pragmatic Optimizer (CLI via mmx by default, v2.21; API opt-in)
 MINIMAX_CMD=mmx
 MINIMAX_MODEL=MiniMax-M2.7
+# max_quality selects the smoke-tested MiniMax-M3 target.
 MINIMAX_TIMEOUT=180
 MINIMAX_API_URL=https://api.minimax.io/v1/chat/completions
 

package/CLAUDE.md

@@ -6,7 +6,7 @@ AI Consultants is a multi-model coverage system that queries up to 11 AI consult
 
 **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**: 3.4.0
+**Version**: 3.5.0
 
 ## Distribution
 
@@ -180,7 +180,7 @@ Functions in `lib/common.sh`:
 ### Configuration Presets
 ```bash
 # Quality Tier Presets (v2.5)
-./scripts/consult_all.sh --preset max_quality "question"  # 8 of 11 consultants + premium models + peer review
+./scripts/consult_all.sh --preset max_quality "question"  # 8 of 11 consultants + maximum tier + peer review
 ./scripts/consult_all.sh --preset medium "question"       # 4 consultants + standard models
 ./scripts/consult_all.sh --preset fast "question"         # 2 consultants + economy models
 
@@ -364,11 +364,12 @@ The `doctor.sh` script now shows CLI/API mode status:
 ## v2.5 Features
 
 ### Model Quality Tiers
-Three tiers of models are available for each consultant, configurable via `apply_model_tier()`:
+Three normal tiers plus a `maximum` tier are configurable via `apply_model_tier()`:
 
 | Tier | Description | Example Models |
 |------|-------------|----------------|
 | **premium** | Latest flagship models | claude-opus-5, Gemini 3.1 Pro (High), gpt-5.6-sol |
+| **maximum** | Smoke-tested separate-plan targets used by max_quality | K3-256k, Qwen3.8-Max, MiniMax M3 |
 | **standard** | Good quality at reasonable cost | claude-sonnet-5, Gemini 3.6 Flash (High), gpt-5.6-terra |
 | **economy** | Optimized for speed and low cost | claude-haiku-4-5, Gemini 3.6 Flash (Low), gpt-5.6-luna |
 
@@ -378,6 +379,7 @@ Three tiers of models are available for each consultant, configurable via `apply
 # Programmatic usage
 source scripts/config.sh
 apply_model_tier "premium"   # Set all consultants to premium models
+apply_model_tier "maximum"   # max_quality-only / separate-plan models
 apply_model_tier "standard"  # Set all consultants to standard models
 apply_model_tier "economy"   # Set all consultants to economy models
 
@@ -390,7 +392,7 @@ get_model_for_tier "claude" "economy"   # → claude-haiku-4-5
 Three new presets leverage the model tiers:
 
 ```bash
-# Maximum quality - all premium models + debate + peer review
+# Maximum quality - maximum tier + debate + peer review
 ./scripts/consult_all.sh --preset max_quality "critical architecture decision"
 
 # Balanced quality - standard models, 4 consultants, light debate
@@ -408,11 +410,11 @@ All consultants now use premium models by default:
 | Claude | claude-opus-5 |
 | Gemini | Gemini 3.1 Pro (High) (via agy CLI) |
 | Codex | gpt-5.6-sol |
-| Mistral | mistral-large-3 |
+| Mistral | CLI: mistral-medium-3.5; API: mistral-large-3 |
 | Cursor | composer-2.5 |
 | DeepSeek | deepseek-v4-pro |
-| GLM | glm-5.2 |
-| Grok | grok-4.5 |
+| GLM | glm-5.3 |
+| Grok | grok-4.6 |
 | Qwen3 | qwen3.7-max |
 | Kimi | kimi-code/k3 |
 | MiniMax | MiniMax-M2.7 |
@@ -420,7 +422,7 @@ 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
+`grok-4.6` 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
@@ -619,6 +621,7 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 | `GEMINI_API_MODEL` | gemini-3.1-pro-preview | Gemini API-mode model ID (v2.15) |
 | `CODEX_MODEL` | gpt-5.6-sol | Codex model (v2.5) |
 | `MISTRAL_MODEL` | mistral-large-3 | Mistral model (v2.5) |
+| `MISTRAL_CLI_MODEL` | mistral-medium-3.5 | Vibe CLI model alias |
 | `SYNTHESIS_STRATEGY` | coverage | Synthesis strategy (coverage=union of distinct points) |
 | `ENABLE_SEMANTIC_CACHE` | true | Semantic response caching (v2.3) |
 | `CACHE_TTL_HOURS` | 24 | Cache expiration in hours (v2.3) |
@@ -643,7 +646,7 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 - `agy` CLI - Antigravity CLI (Gemini consultant; successor to the deprecated Gemini CLI, v2.15)
 - `codex` CLI - OpenAI Codex
 - `vibe` CLI - Mistral Vibe
-- `agent` CLI - Cursor
+- `cursor-agent` CLI - Cursor (validated by capability, read-only ask mode)
 - `kimi` CLI - Kimi Code (v2.9)
 - `claude` CLI - Claude (v2.2, also used for synthesis)
 - `qwen` CLI - Qwen via qwen-code (v2.7, optional)
@@ -787,6 +790,18 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v3.5.0
+
+- **The catalog now distinguishes an advisory panel's normal premium tier from subscription-only maximum targets.** `get_model_for_tier()` accepts an explicit transport, while `apply_model_tier maximum` selects K3-256k and MiniMax M3 and promotes Qwen3.8-Max only when `QWEN3_USE_API=true`, the wire is OpenAI-compatible, the endpoint is a Token Plan `/chat/completions` URL, and a key is present (`scripts/config.sh:581-737`). The Qwen effort is marked tier-managed, cleared when leaving maximum, and never overwrites a user pin. Gemini 3.7, Fable 5, and the new Mistral API IDs remain catalogued opt-ins after their exact transports failed authentication or timed out; normal runs do not inherit delegation-kit's routing gates.
+- **Mistral CLI and API names are no longer conflated.** `MISTRAL_CLI_MODEL=mistral-medium-3.5` reaches Vibe through `VIBE_ACTIVE_MODEL`; `MISTRAL_MODEL` remains API-only. Vibe verifies its bounded read-only interface, runs `plan` for one turn in a mode-700 temporary workspace, and treats empty or post-launch failures as failures (`scripts/query_mistral.sh:47-143`). The current machine passed the exact Vibe smoke; no Mistral API key was available, so the new API IDs were not promoted.
+- **Cursor now means Cursor.** The old `CURSOR_CMD=agent` resolved to Grok on this machine. Runtime, configure, and doctor now default to `cursor-agent`, validate the Cursor help surface, bound model-inventory calls, require Composer 2.5, and invoke `--mode ask --trust` only against an ephemeral workspace (`scripts/query_cursor.sh:33-132`, `scripts/configure.sh:322-363`). The local Cursor account is not logged in, so runtime authentication remains a user gate rather than something this release works around.
+- **Model identity evidence is additive and honest.** Every envelope carries the requested ID and one of `provider-reported`, `capability-probed`, or `requested-only`; API model strings are syntax-validated before adoption (`scripts/lib/common.sh:935-1068`, `scripts/lib/api_query.sh:162-194`). `modelUsage` remains billing participation, not content identity. The shared billing resolver prefers a known effective ID, then the explicit requested ID, and uses consultant fallback only for legacy responses that lack the new metadata (`scripts/lib/costs.sh:311-430`).
+- **The reliability boundary is finite.** Cursor/Gemini/Mistral capability probes and Cursor configure/doctor probes have explicit time limits. An HTTP 200 with an empty body increments the retry counter, including at the shipped `MAX_RETRIES=2`, instead of spinning indefinitely (`scripts/lib/api.sh`, `scripts/test_api_transport.sh`). Google `thinkingConfig` is emitted only for Gemini 3.7; the proven 3.1 API body remains byte-compatible.
+- **Managed migrations are exact and pins survive.** `configure` upgrades only the historical managed Cursor command, GLM 5.2, and Grok 4.5 values. Environment/`--set` model values and any `# ai-consultants:pin` entry remain user-owned. The new catalog-parity gate checks all 44 consultant/tier cells and all 16 Gemini/Mistral transport cells against `docs/cost_rates.json`, requiring every automatic target to be priced or explicitly unpriced.
+- **Promotion evidence is recorded without overstating it.** Exact ai-consultants smokes passed for Mistral Vibe Medium 3.5, GLM 5.3, Grok 4.6, K3-256k, Qwen3.8-Max Token Plan, and MiniMax M3. Gemini 3.7 lacked agy/API auth, Mistral API lacked a key, Fable 5 timed out, and Cursor lacked login; those stay opt-in/unverified. Cross-family Opus 5/max review first returned `NO-SHIP` with four blockers, then `SHIP` after the hermeticity, trust, probe, thinking, billing, retry, and parity findings were fixed. Final gate: 22/22 suites, 443/443 core checks, ShellCheck and npm tarball green.
+
+  Deliberate residuals: Cursor and Vibe isolate the workspace but retain ambient HOME for their authenticated CLI state; unpriced credit/subscription models are disclosed but cannot be enforced by a dollar budget; provider/requested model substitutions are available in raw JSON but not yet summarized in the human report.
+
 ### v3.4.0
 - **Gemini was unreachable from an SSH session, and no amount of re-authenticating helped.** `agy` picks its credential store from the environment: seeing `SSH_CLIENT`, `SSH_CONNECTION`, or `SSH_TTY` it switches to a file-based token store and never consults the macOS Keychain. A user who signed in locally therefore lost Gemini entirely over SSH, and signing in again landed the new credential in the Keychain the CLI had already decided to ignore. Reproduced live before fixing (`agy models` → "Please sign in"; the same command under `env -u SSH_CLIENT -u SSH_CONNECTION -u SSH_TTY` → full inventory), and confirmed again end to end after. Found by reading delegation-kit's 0.13.1 fix and checking whether the same failure applied here — it did, in the very session doing the work.
 - **The fix ships in two shapes on purpose** (`lib/common.sh:163-164`). `AGY_ENV_PREFIX` is an array of `env -u …` for anything that reaches `agy` through `run_with_timeout`, because GNU `timeout` execs a binary and **cannot invoke a shell function**; `agy_env` is the same-shell wrapper, defined *from* that array so the two cannot drift. Applied at every executing call site — `query_gemini.sh`, `doctor.sh`, `update_clis.sh`, and `build_synthesis_args` (which is executed directly by `synthesize.sh:304`, not through timeout, so either shape would work there — it uses the array for consistency). The remaining `${GEMINI_CMD:-agy}` hits are `command -v` probes and config-dump strings, which execute nothing.

package/README.md

@@ -1,8 +1,8 @@
-# AI Consultants v3.4.0
+# AI Consultants v3.5.0
 
 > **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-3.4.0-blue.svg)](https://github.com/matteoscurati/ai-consultants)
+[![Version](https://img.shields.io/badge/version-3.5.0-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)
@@ -375,20 +375,22 @@ INVOKING_AGENT=codex ./scripts/consult_all.sh "Question"    # Codex excluded
 | **Google Gemini** | `agy` | The Architect | Design patterns, scalability, enterprise |
 | **OpenAI Codex** | `codex` | The Pragmatist | Simplicity, quick wins, proven solutions |
 | **Mistral Vibe** | `vibe` | The Devil's Advocate | Problems, edge cases, vulnerabilities |
-| **Cursor** | `agent` | The Integrator | Full-stack perspective |
+| **Cursor** | `cursor-agent` | The Integrator | Full-stack perspective |
 | **Kimi K3** | `kimi` | The Eastern Sage | Holistic, balanced perspectives |
 | **Claude** | `claude` | The Synthesizer | Big picture, synthesis, connecting ideas |
 | **Qwen3** | `qwen` | The Analyst | Data-driven analysis |
 | **Grok** | `grok` | The Provocateur | Challenge conventions |
 | **MiniMax** | `mmx` | The Pragmatic Optimizer | Performance, efficiency, pragmatism |
 
-Grok uses Grok Build with `grok-4.5` in an isolated, tool-free sandbox. Prompts
+Grok uses Grok Build with `grok-4.6` in an isolated, tool-free sandbox. Prompts
 are passed through a private file rather than process arguments. It falls back
 to the xAI API only when the CLI is missing, cannot launch, or has no usable
 authentication and `GROK_API_KEY` is configured; post-launch request failures
 are surfaced without a silent API charge. Qwen3 and MiniMax can also switch
 from their CLI to API transport. Gemini, Codex, Claude, and Mistral are
-CLI/API switchable. Grok and Kimi compatibility is capability-probed before
+CLI/API switchable. Gemini, Cursor, Grok, and Kimi verify the requested model
+against the CLI inventory before dispatch when that inventory exists. Grok and
+Kimi compatibility is capability-probed before
 dispatch: the requested model, headless arguments, and structured-output
 surface must be available. Any CLI version is accepted when those checks pass;
 the observed version is response provenance only.
@@ -397,7 +399,7 @@ the observed version is response provenance only.
 
 | Consultant | Default Model | Persona | Focus |
 |------------|---------------|---------|-------|
-| **GLM** | glm-5.2 | The Methodologist | Structured approaches |
+| **GLM** | glm-5.3 | The Methodologist | Structured approaches |
 | **DeepSeek** | deepseek-v4-pro | The Code Specialist | Algorithms, code generation |
 
 ### Installing Consultant CLIs
@@ -413,7 +415,7 @@ curl https://cursor.com/install -fsS | bash  # Cursor
 # Optional CLI-based consultants
 curl -L code.kimi.com/install.sh | bash            # Kimi K3
 npm install -g @qwen-code/qwen-code@latest  # Qwen (alternative to API)
-curl -fsSL https://x.ai/cli/install.sh | bash # Grok Build (grok-4.5)
+curl -fsSL https://x.ai/cli/install.sh | bash # Grok Build (grok-4.6)
 npm install -g mmx-cli                       # MiniMax
 
 ```
@@ -436,7 +438,7 @@ Choose the right balance of quality, speed, and cost with model quality tiers.
 
 | Preset | Tier | Agents | Use Case |
 |--------|------|--------|----------|
-| `max_quality` | Premium | 8 of 11 | Critical decisions |
+| `max_quality` | Maximum | 8 of 11 | Critical decisions |
 | `medium` | Standard | 4 | General questions |
 | `fast` | Economy | 2 | Quick checks |
 
@@ -445,19 +447,31 @@ parallel and returns the coverage union.
 
 ### Models by Tier
 
-| Consultant | Premium | Standard | Economy |
-|------------|---------|----------|---------|
-| Claude | claude-opus-5 | claude-sonnet-5 | claude-haiku-4-5 |
-| Gemini | Gemini 3.1 Pro (High) | Gemini 3.6 Flash (High) | Gemini 3.6 Flash (Low) |
-| Codex | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna |
-| Mistral | mistral-large-3 | mistral-medium-latest | devstral-small-2 |
-| Cursor | composer-2.5 | composer-2 | gemini-3-flash |
-| DeepSeek | deepseek-v4-pro | deepseek-v4-flash | deepseek-v4-flash |
-| GLM | glm-5.2 | glm-5.2 | glm-4-flash |
-| Grok | grok-4.5 | grok-4.1-fast | grok-4.1-fast |
-| Qwen3 | qwen3.7-max | qwen3.6-35b-a3b | qwen3-32b |
-| Kimi | kimi-code/k3 | kimi-code/k3 | kimi-code/k3 |
-| MiniMax | MiniMax-M2.7 | MiniMax-M2.7 | MiniMax-M2.5 |
+| Consultant | `max_quality` | Premium | Standard | Economy |
+|------------|---------------|---------|----------|---------|
+| Claude | claude-opus-5 | claude-opus-5 | claude-sonnet-5 | claude-haiku-4-5 |
+| Gemini | Gemini 3.1 Pro (High) | Gemini 3.1 Pro (High) | Gemini 3.6 Flash (High) | Gemini 3.6 Flash (Low) |
+| Codex | gpt-5.6-sol | gpt-5.6-sol | gpt-5.6-terra | gpt-5.6-luna |
+| Mistral CLI | mistral-medium-3.5 | mistral-medium-3.5 | mistral-medium-3.5 | devstral-small-2 |
+| Mistral API | mistral-large-3 | mistral-large-3 | mistral-large-3 | mistral-large-3 |
+| Cursor | composer-2.5 | composer-2.5 | composer-2.5 | composer-2.5 |
+| DeepSeek | deepseek-v4-pro | deepseek-v4-pro | deepseek-v4-flash | deepseek-v4-flash |
+| GLM | glm-5.3 | glm-5.3 | glm-5.3 | glm-4-flash |
+| Grok | grok-4.6 | grok-4.6 | grok-4.5 | grok-4.5 |
+| Qwen3 | qwen3.8-max when Token Plan is configured; otherwise qwen3.7-max | qwen3.7-max | qwen3.6-35b-a3b | qwen3-32b |
+| Kimi | kimi-code/k3-256k | kimi-code/k3 | kimi-code/k3 | kimi-code/k3 |
+| MiniMax | MiniMax-M3 | MiniMax-M2.7 | MiniMax-M2.7 | MiniMax-M2.5 |
+
+Promotion is transport-specific. Gemini 3.7 Flash, the new Mistral API IDs
+(`mistral-medium-3-5`, `mistral-large-2512`, `mistral-small-2603`), and Claude
+Fable 5 are catalogued opt-ins because this release could not complete an exact
+authenticated smoke for those transports. Select them explicitly only after
+your own `doctor --live`/adapter check. They are never promoted automatically;
+selecting a preset later intentionally reapplies that preset's tier and can
+replace an explicit model override for the run.
+Qwen3.8-Max is likewise selected by `max_quality` only when API mode already
+points at an authenticated OpenAI-compatible Token Plan `/chat/completions`
+endpoint; the preset never repoints a DashScope key or CLI installation.
 
 ### Usage
 
@@ -475,6 +489,7 @@ parallel and returns the coverage union.
 # Programmatic tier selection
 source scripts/config.sh
 apply_model_tier "premium"   # Set all to premium models
+apply_model_tier "maximum"   # max_quality-only / separate-plan models
 apply_model_tier "economy"   # Set all to economy models
 ```
 
@@ -488,7 +503,7 @@ Choose how many consultants to use:
 
 | Preset | Consultants | Tier | Use Case |
 |--------|-------------|------|----------|
-| `max_quality` | 8 of 11 | Premium | Critical decisions |
+| `max_quality` | 8 of 11 | Maximum | Critical decisions |
 | `medium` | 4 | Standard | General questions |
 | `fast` | 2 | Economy | Quick checks |
 | `minimal` | 2 (Gemini + Codex) | Default | Quick questions, low cost |
@@ -552,7 +567,8 @@ later run to adapt when a CLI or credential changes. Environment variables,
 `--set`, and unmarked values remain explicit user choices, except for the exact
 historical generated Claude default described below.
 Managed model defaults use `# ai-consultants:default`; `configure` upgrades the
-historical unmarked `CLAUDE_MODEL=claude-opus-4-8` default to Opus 5. To keep
+historical unmarked `CLAUDE_MODEL=claude-opus-4-8` default to Opus 5 and upgrades
+the exact managed Cursor, GLM, and Grok defaults. To keep
 4.8 intentionally, run
 `ai-consultants configure --set CLAUDE_MODEL=claude-opus-4-8`; explicit model
 overrides are stored with `# ai-consultants:pin`.
@@ -573,6 +589,7 @@ 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
 CLAUDE_API_MAX_TOKENS=16384  # Shared thinking + visible-output budget in API mode
+MISTRAL_CLI_MODEL=mistral-medium-3.5 # Vibe alias; MISTRAL_MODEL remains API-only
 ```
 
 Full reference: [`references/configuration.md`](references/configuration.md). Copy-paste workflows: [`docs/RECIPES.md`](docs/RECIPES.md). For category-aware preset suggestions: `ai-consultants doctor --suggest-preset --question "..."`.

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: 3.4.0
+  version: 3.5.0
 ---
 
-# AI Consultants v3.4.0 - AI Expert Panel
+# AI Consultants v3.5.0 - 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.
 
@@ -34,7 +34,7 @@ Configuration (presets, strategies, features, personas, API keys) can be managed
 | **Google Gemini** | `agy` | The Architect | Design patterns, scalability |
 | **OpenAI Codex** | `codex` | The Pragmatist | Simplicity, proven solutions |
 | **Mistral Vibe** | `vibe` | The Devil's Advocate | Edge cases, vulnerabilities |
-| **Cursor** | `agent` | The Integrator | Full-stack perspective |
+| **Cursor** | `cursor-agent` | The Integrator | Full-stack perspective |
 | **Kimi K3** | `kimi` | The Eastern Sage | Holistic, balanced perspectives |
 | **Claude** | `claude` | The Synthesizer | Big picture, synthesis |
 | **Qwen** | `qwen` | The Analyst | Data-driven, metrics |
@@ -43,13 +43,19 @@ Configuration (presets, strategies, features, personas, API keys) can be managed
 
 **API-only consultants**: GLM (The Methodologist), DeepSeek (The Code Specialist)
 
-**CLI/API Mode**: Gemini, Codex, Claude, Mistral, Qwen, Grok, and MiniMax can switch between CLI and API mode via `*_USE_API` environment variables. Grok is CLI-first on Grok Build with `grok-4.5` and falls back to the xAI API when the CLI cannot run. Gemini auto-selects API mode when `GEMINI_API_KEY` is set (no `agy` install needed) and the CLI otherwise.
+**CLI/API Mode**: Gemini, Codex, Claude, Mistral, Qwen, Grok, and MiniMax can switch between CLI and API mode via `*_USE_API` environment variables. Grok is CLI-first on Grok Build with `grok-4.6` and falls back to the xAI API when the CLI cannot run. Gemini auto-selects API mode when `GEMINI_API_KEY` is set (no `agy` install needed) and the CLI otherwise. Mistral keeps separate API (`MISTRAL_MODEL`) and Vibe (`MISTRAL_CLI_MODEL`) identifiers; Cursor uses `cursor-agent --mode ask` in an isolated workspace.
 
 Grok and Kimi are compatible by capability rather than by CLI version. Before
 dispatch, their adapters verify the required headless arguments, requested
 model, and structured-output surface. Compatible version changes are accepted;
 the observed version is recorded only as response provenance.
 
+The `max_quality` preset uses the separately smoke-tested K3-256k and MiniMax
+M3 targets, plus Qwen3.8-Max when an authenticated Token Plan transport is
+already configured. Gemini 3.7 Flash, Claude Fable 5, and the
+new Mistral API IDs remain explicit opt-ins until their exact local transports
+can authenticate and complete a smoke; no failed target is silently replaced.
+
 **Self-Exclusion**: The invoking agent is automatically excluded from the panel. When invoked from Claude Code, Claude is excluded; when invoked from Codex CLI, Codex is excluded, etc.
 
 ## Requirements

package/docs/COST_RATES.md

@@ -1,4 +1,4 @@
-# Cost Rates - AI Consultants v3.4.0
+# Cost Rates - AI Consultants v3.5.0
 
 This page documents the per-token rates used by the cost tracking system.
 
@@ -6,11 +6,14 @@ This page documents the per-token rates used by the cost tracking system.
 
 ## Model Quality Tiers (v2.5+)
 
-Since v2.5, models are organized into three tiers. Use `apply_model_tier()` or `get_model_for_tier()` to select models programmatically.
+Automatic selection has three normal tiers plus the `maximum` tier used by
+`max_quality`. Use `apply_model_tier()` or `get_model_for_tier()` to select
+models programmatically.
 
 | Tier | Description | Cost Level |
 |------|-------------|------------|
 | **Premium** | Latest flagship models (default) | Highest |
+| **Maximum** | Smoke-tested separate-plan or highest-cost targets | Varies / may be unpriced |
 | **Standard** | Good quality at reasonable cost | Medium |
 | **Economy** | Optimized for speed and low cost | Lowest |
 
@@ -23,30 +26,37 @@ Since v2.5, models are organized into three tiers. Use `apply_model_tier()` or `
 | Gemini 3.1 Pro (High) | Premium | $0.002 | Gemini (agy CLI) |
 | Gemini 3.6 Flash (High) | Standard | $0.0015 | Gemini (agy CLI) |
 | Gemini 3.6 Flash (Low) | Economy | $0.0015 | Gemini (agy CLI) |
+| Gemini 3.7 Flash (High/Low) | Opt-in | $0.00075 | Gemini (CLI/API; promotional through 2026-12-31) |
 | gpt-5.6-sol | Premium | $0.005 | Codex |
 | gpt-5.6-terra | Standard | $0.002 | Codex |
 | gpt-5.6-luna | Economy | $0.0002 | Codex |
 | claude-opus-5 | Premium | $0.005 | Claude |
+| claude-fable-5 | Opt-in | $0.010 | Claude |
 | claude-sonnet-5 | Standard | $0.003 | Claude |
 | claude-haiku-4-5 | Economy | $0.001 | Claude |
 | mistral-large-3 | Premium | $0.002 | Mistral |
-| mistral-medium-latest | Standard | $0.001 | Mistral |
+| mistral-medium-3.5 / mistral-medium-3-5 | Premium CLI / API opt-in | $0.0015 | Mistral |
+| mistral-large-2512 | API opt-in | $0.0005 | Mistral |
+| mistral-small-2603 | API opt-in | $0.00015 | Mistral |
 | devstral-small-2 | Economy | $0.00 | Mistral |
-| composer-2.5 | Premium | $0.0005 | Cursor |
-| composer-2 | Standard | $0.0005 | Cursor |
-| gemini-3-flash | Economy | $0.0005 | Cursor |
+| composer-2.5 | Maximum/Premium/Standard/Economy | $0.0005 | Cursor |
+| composer-2 | Legacy | $0.0005 | Cursor |
+| gemini-3-flash | Legacy | $0.0005 | Cursor |
 | deepseek-v4-pro | Premium | $0.000435 | DeepSeek |
 | deepseek-v4-flash | Standard/Economy | $0.00014 | DeepSeek |
-| glm-5.2 | Premium/Standard | $0.00098 | GLM |
+| glm-5.3 | Maximum/Premium/Standard | Unpriced | GLM coding-plan endpoint |
 | glm-4-flash | Economy | $0.001 | GLM |
-| grok-4.5 | Premium | $0.002 | Grok |
-| grok-4.1-fast | Standard/Economy | $0.0002 | Grok |
+| grok-4.6 | Maximum/Premium | $0.002 | Grok |
+| grok-4.5 | Standard/Economy | $0.002 | Grok |
 | qwen3.7-max | Premium | $0.0012 | Qwen3 |
 | qwen3.6-35b-a3b | Standard | $0.000163 | Qwen3 |
 | qwen3-32b | Economy | $0.0004 | Qwen3 |
-| MiniMax-M2.7 | Premium/Standard | $0.00025 | MiniMax |
-| MiniMax-M2.5 | Economy | $0.000255 | MiniMax |
+| qwen3.8-max | Maximum | Unpriced | Qwen3 Token Plan |
+| MiniMax-M3 | Maximum | $0.0003 | MiniMax (≤512k standard input) |
+| MiniMax-M2.7 | Premium/Standard | $0.0003 | MiniMax |
+| MiniMax-M2.5 | Economy | $0.0003 | MiniMax |
 | kimi-code/k3 | Premium/Standard/Economy | $0.0005 | Kimi |
+| kimi-code/k3-256k | Maximum | Unpriced | Kimi subscription |
 | default | - | $0.005 | Fallback |
 
 ### Output Tokens
@@ -56,30 +66,37 @@ Since v2.5, models are organized into three tiers. Use `apply_model_tier()` or `
 | Gemini 3.1 Pro (High) | Premium | $0.012 | Gemini (agy CLI) |
 | Gemini 3.6 Flash (High) | Standard | $0.0075 | Gemini (agy CLI) |
 | Gemini 3.6 Flash (Low) | Economy | $0.0075 | Gemini (agy CLI) |
+| Gemini 3.7 Flash (High/Low) | Opt-in | $0.00375 | Gemini (CLI/API; promotional through 2026-12-31) |
 | gpt-5.6-sol | Premium | $0.030 | Codex |
 | gpt-5.6-terra | Standard | $0.012 | Codex |
 | gpt-5.6-luna | Economy | $0.0012 | Codex |
 | claude-opus-5 | Premium | $0.025 | Claude |
+| claude-fable-5 | Opt-in | $0.050 | Claude |
 | claude-sonnet-5 | Standard | $0.015 | Claude |
 | claude-haiku-4-5 | Economy | $0.005 | Claude |
 | mistral-large-3 | Premium | $0.006 | Mistral |
-| mistral-medium-latest | Standard | $0.003 | Mistral |
+| mistral-medium-3.5 / mistral-medium-3-5 | Premium CLI / API opt-in | $0.0075 | Mistral |
+| mistral-large-2512 | API opt-in | $0.0015 | Mistral |
+| mistral-small-2603 | API opt-in | $0.0006 | Mistral |
 | devstral-small-2 | Economy | $0.00 | Mistral |
-| composer-2.5 | Premium | $0.0025 | Cursor |
-| composer-2 | Standard | $0.0025 | Cursor |
-| gemini-3-flash | Economy | $0.003 | Cursor |
+| composer-2.5 | Maximum/Premium/Standard/Economy | $0.0025 | Cursor |
+| composer-2 | Legacy | $0.0025 | Cursor |
+| gemini-3-flash | Legacy | $0.003 | Cursor |
 | deepseek-v4-pro | Premium | $0.00087 | DeepSeek |
 | deepseek-v4-flash | Standard/Economy | $0.00028 | DeepSeek |
-| glm-5.2 | Premium/Standard | $0.00308 | GLM |
+| glm-5.3 | Maximum/Premium/Standard | Unpriced | GLM coding-plan endpoint |
 | glm-4-flash | Economy | $0.003 | GLM |
-| grok-4.5 | Premium | $0.006 | Grok |
-| grok-4.1-fast | Standard/Economy | $0.0005 | Grok |
+| grok-4.6 | Maximum/Premium | $0.006 | Grok |
+| grok-4.5 | Standard/Economy | $0.006 | Grok |
 | qwen3.7-max | Premium | $0.006 | Qwen3 |
 | qwen3.6-35b-a3b | Standard | $0.0009 | Qwen3 |
 | qwen3-32b | Economy | $0.0016 | Qwen3 |
-| MiniMax-M2.7 | Premium/Standard | $0.001 | MiniMax |
-| MiniMax-M2.5 | Economy | $0.001 | MiniMax |
+| qwen3.8-max | Maximum | Unpriced | Qwen3 Token Plan |
+| MiniMax-M3 | Maximum | $0.0012 | MiniMax (≤512k standard input) |
+| MiniMax-M2.7 | Premium/Standard | $0.0012 | MiniMax |
+| MiniMax-M2.5 | Economy | $0.0012 | MiniMax |
 | kimi-code/k3 | Premium/Standard/Economy | $0.002 | Kimi |
+| kimi-code/k3-256k | Maximum | Unpriced | Kimi subscription |
 | default | - | $0.015 | Fallback |
 
 ## Cost Estimation per Session
@@ -155,7 +172,18 @@ This is a conservative estimate. Actual costs may vary.
 
 ### Data Source
 
-Rates are defined in `scripts/lib/costs.sh` and are periodically updated to reflect official provider pricing.
+Rates are defined in `docs/cost_rates.json` and are periodically updated from
+the providers' official pricing pages: [Anthropic](https://platform.claude.com/docs/en/about-claude/models/choosing-a-model),
+[Google](https://ai.google.dev/gemini-api/docs/pricing),
+[Mistral](https://docs.mistral.ai/getting-started/models/models_overview/),
+[xAI](https://docs.x.ai/developers/models), and
+[MiniMax](https://platform.minimax.io/docs/guides/pricing-paygo). Gemini 3.7's
+listed rate is the promotion effective through December 31, 2026.
+
+`glm-5.3`, `qwen3.8-max`, and `kimi-code/k3-256k` are explicitly unpriced on
+the transports used here. Their zero catalog entries prevent the estimator from
+inventing a dollar figure; session reports disclose their exclusion rather than
+presenting them as free.
 
 ### Dependencies
 

package/docs/JSON_SCHEMA.md

@@ -37,6 +37,8 @@ The schema is defined in `scripts/lib/schema.json` following JSON Schema Draft-0
     "tokens_output": 300,
     "latency_ms": 2345,
     "model_version": "gemini-3.1-pro-preview",
+    "requested_model": "gemini-3.1-pro-preview",
+    "model_identity_source": "provider-reported",
     "cli_version": "0.27.0",
     "cli_compatibility": "capability-probed",
     "timestamp": "2024-01-14T12:34:56Z"
@@ -198,6 +200,8 @@ Present only if Multi-Agent Debate is enabled (round >= 2):
     "tokens_output": 300,
     "latency_ms": 2345,
     "model_version": "gemini-3.1-pro-preview",
+    "requested_model": "gemini-3.1-pro-preview",
+    "model_identity_source": "provider-reported",
     "timestamp": "2024-01-14T12:34:56Z"
   }
 }
@@ -210,7 +214,9 @@ Present only if Multi-Agent Debate is enabled (round >= 2):
 | `tokens_input` | integer | Prompt tokens, when the provider reported them (API mode only) |
 | `tokens_output` | integer | Completion tokens, when the provider reported them (API mode only) |
 | `latency_ms` | integer | Response time in ms |
-| `model_version` | string | Exact model version |
+| `model_version` | string | Best effective model identifier available to the transport |
+| `requested_model` | string | Model identifier requested before provider resolution |
+| `model_identity_source` | string | `provider-reported` \| `capability-probed` \| `requested-only` |
 | `cli_version` | string | Observed CLI version for provenance; never a compatibility gate |
 | `cli_compatibility` | string | Capability-probe result: `capability-probed` or `incompatible` |
 | `timestamp` | string | ISO 8601 timestamp |
@@ -335,6 +341,8 @@ jq 'has("consultant") and has("response") and has("confidence")' output.json
     "tokens_source": "estimated",
     "latency_ms": 1850,
     "model_version": "gemini-3.1-pro-preview",
+    "requested_model": "gemini-3.1-pro-preview",
+    "model_identity_source": "requested-only",
     "timestamp": "2024-01-14T12:34:56Z"
   }
 }

package/docs/RECIPES.md

@@ -155,7 +155,7 @@ QWEN3_API_KEY=your-dashscope-key
 ENABLE_GROK=true
 GROK_USE_API=false
 GROK_API_KEY=your-xai-key
-GROK_MODEL=grok-4.5
+GROK_MODEL=grok-4.6
 
 ENABLE_GLM=false
 ENABLE_DEEPSEEK=false
@@ -195,7 +195,8 @@ source of truth is [`scripts/config.sh`](../scripts/config.sh).
 `qwen3.8-max` is **not** served by DashScope/ModelStudio. It is reachable
 only through a Qwen Cloud **Token Plan** subscription, which has its own base URL
 and its own API key. This is opt-in: nothing below is a default, and the panel's
-premium Qwen model remains `qwen3.7-max`.
+premium Qwen model remains `qwen3.7-max`; `max_quality` selects the separately
+smoke-tested `qwen3.8-max` Token Plan target.
 
 Understand the tradeoffs before enabling it:
 

package/docs/SETUP.md

@@ -294,6 +294,7 @@ Get API key: [Mistral Console](https://console.mistral.ai/api-keys/)
 curl https://cursor.com/install -fsS | bash
 
 # Uses Cursor subscription - no additional key needed
+cursor-agent status
 ```
 
 ### Claude CLI (The Synthesizer) - v2.2
@@ -339,6 +340,9 @@ export KIMI_MODEL=kimi-code/k3
 ./scripts/query_kimi.sh "Review this API boundary"
 ```
 
+`max_quality` selects `kimi-code/k3-256k`, whose availability is verified from
+the Kimi provider inventory before the request.
+
 ### MiniMax (CLI via mmx) - v2.21
 
 MiniMax runs via the `mmx` CLI by default (CLI-first, OAuth). Install and sign in: