ai-consultants 3.3.0 → 3.5.0

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
@@ -190,28 +190,39 @@ For every available variable and its default, see
 [`references/configuration.md`](../references/configuration.md). The executable
 source of truth is [`scripts/config.sh`](../scripts/config.sh).
 
-## Qwen via Qwen Cloud Token Plan (opt-in, preview)
+## Qwen via Qwen Cloud Token Plan (opt-in)
 
-`qwen3.8-max-preview` is **not** served by DashScope/ModelStudio. It is reachable
+`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:
 
-- **Preview, not GA.** Alibaba describes it as continuously evolving. No open
-  weights, no published benchmarks, no stable per-token price.
+- **Token Plan only.** No open weights, no published benchmarks, no stable
+  per-token price.
 - **Billed in prepaid credits**, not per token — and credit consumption varies
   with reasoning depth. Cost reports therefore exclude it and say so explicitly
   rather than estimating a figure.
 
+Both `qwen3.8-max` and `qwen3.8-max-preview` are served by Token Plan and are
+**separate deployments**, not an alias or rename: each completion reports its
+own requested id back in `.model`. Verified against the live endpoint on
+2026-08-05. Prefer `qwen3.8-max`; `qwen3.8-max-preview` is the older
+deployment and the natural candidate for eventual retirement. An existing
+`qwen3.8-max-preview` pin keeps working and stays correctly catalogued — both
+ids are listed in `unpriced_models`, so the session report continues to
+disclose them as credit-billed and excluded from the total rather than falling
+through to `default_rate`.
+
 ### API mode (the effort knob works here)
 
 ```bash
 QWEN3_USE_API=true
 QWEN3_FORMAT=openai      # Token Plan is OpenAI-compatible; DashScope is not
 QWEN3_API_URL=https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
-QWEN3_MODEL=qwen3.8-max-preview
+QWEN3_MODEL=qwen3.8-max
 QWEN3_API_KEY=<your Token Plan key>
 QWEN3_REASONING_EFFORT=high    # none|minimal|low|medium|high|xhigh|max; default xhigh
 ```
@@ -240,8 +251,8 @@ ai-consultants cannot deliver it per call and warns if you set
   "modelProviders": {
     "openai": [
       {
-        "id": "qwen3.8-max-preview",
-        "name": "[Token Plan] qwen3.8-max-preview",
+        "id": "qwen3.8-max",
+        "name": "[Token Plan] qwen3.8-max",
         "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
         "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
         "generationConfig": { "reasoning": { "effort": "high" } }

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:

package/docs/cost_rates.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.3.0",
+  "version": "3.5.0",
   "updated": "2026-07-25",
   "models": {
     "_comment_units": "All rates are USD per 1,000 tokens (per-1K). lib/costs.sh computes cost as (token_count / 1000) * rate, so every value here MUST be a per-1K rate = (provider $/1M price) / 1000. Do NOT paste $/MTok figures directly.",
@@ -8,6 +8,10 @@
       "input": 0.005,
       "output": 0.025
     },
+    "claude-fable-5": {
+      "input": 0.01,
+      "output": 0.05
+    },
     "gemini-3.1-pro-preview": {
       "input": 0.00125,
       "output": 0.005
@@ -17,22 +21,58 @@
       "input": 0.002,
       "output": 0.012
     },
-    "Gemini 3.5 Flash (High)": {
+    "Gemini 3.6 Flash (High)": {
       "input": 0.0015,
-      "output": 0.009
+      "output": 0.0075
     },
-    "Gemini 3.5 Flash (Low)": {
+    "Gemini 3.6 Flash (Low)": {
       "input": 0.0015,
-      "output": 0.009
+      "output": 0.0075
     },
-    "gpt-5.5": {
+    "gemini-3.7-flash": {
+      "input": 0.00075,
+      "output": 0.00375
+    },
+    "Gemini 3.7 Flash (High)": {
+      "input": 0.00075,
+      "output": 0.00375
+    },
+    "Gemini 3.7 Flash (Low)": {
+      "input": 0.00075,
+      "output": 0.00375
+    },
+    "gpt-5.6-sol": {
       "input": 0.005,
       "output": 0.030
     },
+    "gpt-5.6-terra": {
+      "input": 0.002,
+      "output": 0.012
+    },
+    "gpt-5.6-luna": {
+      "input": 0.0002,
+      "output": 0.0012
+    },
     "mistral-large-3": {
       "input": 0.002,
       "output": 0.006
     },
+    "mistral-medium-3-5": {
+      "input": 0.0015,
+      "output": 0.0075
+    },
+    "mistral-medium-3.5": {
+      "input": 0.0015,
+      "output": 0.0075
+    },
+    "mistral-large-2512": {
+      "input": 0.0005,
+      "output": 0.0015
+    },
+    "mistral-small-2603": {
+      "input": 0.00015,
+      "output": 0.0006
+    },
     "deepseek-v4-pro": {
       "input": 0.000435,
       "output": 0.00087
@@ -45,6 +85,10 @@
       "input": 0.002,
       "output": 0.006
     },
+    "grok-4.6": {
+      "input": 0.002,
+      "output": 0.006
+    },
     "qwen3.6-plus": {
       "input": 0.000325,
       "output": 0.00195
@@ -58,8 +102,12 @@
       "output": 0.0025
     },
     "minimax-m2.7": {
-      "input": 0.00025,
-      "output": 0.001
+      "input": 0.0003,
+      "output": 0.0012
+    },
+    "minimax-m3": {
+      "input": 0.0003,
+      "output": 0.0012
     },
     "kimi-code/k3": {
       "input": 0.0005,
@@ -75,7 +123,7 @@
       "output": 0.00
     },
     "_comment_standard": "Standard tier models",
-    "claude-sonnet-4-6": {
+    "claude-sonnet-5": {
       "input": 0.003,
       "output": 0.015
     },
@@ -133,10 +181,34 @@
       "output": 0.0016
     },
     "minimax-m2.5": {
-      "input": 0.000255,
-      "output": 0.001
+      "input": 0.0003,
+      "output": 0.0012
     },
     "_comment_legacy": "Legacy models for backwards compatibility",
+    "Gemini 3.5 Flash (High)": {
+      "input": 0.0015,
+      "output": 0.009
+    },
+    "Gemini 3.5 Flash (Low)": {
+      "input": 0.0015,
+      "output": 0.009
+    },
+    "gpt-5.5": {
+      "input": 0.005,
+      "output": 0.030
+    },
+    "gpt-5.4": {
+      "input": 0.0025,
+      "output": 0.015
+    },
+    "gpt-5.4-nano": {
+      "input": 0.0002,
+      "output": 0.00125
+    },
+    "claude-sonnet-4-6": {
+      "input": 0.003,
+      "output": 0.015
+    },
     "claude-opus-4-8": {
       "input": 0.005,
       "output": 0.025
@@ -289,14 +361,6 @@
       "input": 0.0003,
       "output": 0.0015
     },
-    "gpt-5.4": {
-      "input": 0.0025,
-      "output": 0.015
-    },
-    "gpt-5.4-nano": {
-      "input": 0.0002,
-      "output": 0.00125
-    },
     "composer-2.5": {
       "input": 0.0005,
       "output": 0.0025
@@ -326,23 +390,38 @@
       "output": 0.0025
     },
     "_comment_unpriced": "Credit-billed models: drawn from a prepaid subscription pool, with no published per-token price. Rated 0 so the estimator does not fabricate a figure - an absent model would otherwise fall through to default_rate (0.005/0.015) and be reported as a confident, wrong number. Every entry here must also be listed in unpriced_models, which is what makes the session report disclose the exclusion instead of implying the model was free.",
+    "qwen3.8-max": {
+      "input": 0,
+      "output": 0
+    },
     "qwen3.8-max-preview": {
       "input": 0,
       "output": 0
+    },
+    "glm-5.3": {
+      "input": 0,
+      "output": 0
+    },
+    "kimi-code/k3-256k": {
+      "input": 0,
+      "output": 0
     }
   },
   "unpriced_models": [
-    "qwen3.8-max-preview"
+    "qwen3.8-max",
+    "qwen3.8-max-preview",
+    "glm-5.3",
+    "kimi-code/k3-256k"
   ],
   "consultant_fallbacks": {
-    "_comment": "Premium defaults - Updated Jul 2026",
+    "_comment": "Premium defaults - Updated Aug 2026",
     "claude": "claude-opus-5",
     "gemini": "Gemini 3.1 Pro (High)",
-    "codex": "gpt-5.5",
+    "codex": "gpt-5.6-sol",
     "mistral": "mistral-large-3",
     "deepseek": "deepseek-v4-pro",
-    "glm": "glm-5.2",
-    "grok": "grok-4.5",
+    "glm": "glm-5.3",
+    "grok": "grok-4.6",
     "qwen3": "qwen3.7-max",
     "cursor": "composer-2.5",
     "kimi": "kimi-code/k3",
@@ -350,46 +429,79 @@
   },
   "model_tiers": {
     "_comment": "Model tiers for apply_model_tier() function",
+    "maximum": {
+      "claude": "claude-opus-5",
+      "gemini": "Gemini 3.1 Pro (High)",
+      "codex": "gpt-5.6-sol",
+      "mistral": "mistral-medium-3.5",
+      "deepseek": "deepseek-v4-pro",
+      "glm": "glm-5.3",
+      "grok": "grok-4.6",
+      "qwen3": "qwen3.8-max",
+      "cursor": "composer-2.5",
+      "kimi": "kimi-code/k3-256k",
+      "minimax": "MiniMax-M3"
+    },
     "premium": {
       "claude": "claude-opus-5",
       "gemini": "Gemini 3.1 Pro (High)",
-      "codex": "gpt-5.5",
-      "mistral": "mistral-large-3",
+      "codex": "gpt-5.6-sol",
+      "mistral": "mistral-medium-3.5",
       "deepseek": "deepseek-v4-pro",
-      "glm": "glm-5.2",
-      "grok": "grok-4.5",
+      "glm": "glm-5.3",
+      "grok": "grok-4.6",
       "qwen3": "qwen3.7-max",
       "cursor": "composer-2.5",
       "kimi": "kimi-code/k3",
-      "minimax": "minimax-m2.7"
+      "minimax": "MiniMax-M2.7"
     },
     "standard": {
-      "claude": "claude-sonnet-4-6",
-      "gemini": "Gemini 3.5 Flash (High)",
-      "codex": "gpt-5.4",
-      "mistral": "mistral-medium-latest",
+      "claude": "claude-sonnet-5",
+      "gemini": "Gemini 3.6 Flash (High)",
+      "codex": "gpt-5.6-terra",
+      "mistral": "mistral-medium-3.5",
       "deepseek": "deepseek-v4-flash",
-      "glm": "glm-5.2",
-      "grok": "grok-4.1-fast",
+      "glm": "glm-5.3",
+      "grok": "grok-4.5",
       "qwen3": "qwen3.6-35b-a3b",
-      "cursor": "composer-2",
+      "cursor": "composer-2.5",
       "kimi": "kimi-code/k3",
-      "minimax": "minimax-m2.7"
+      "minimax": "MiniMax-M2.7"
     },
     "economy": {
       "claude": "claude-haiku-4-5",
-      "gemini": "Gemini 3.5 Flash (Low)",
-      "codex": "gpt-5.4-nano",
+      "gemini": "Gemini 3.6 Flash (Low)",
+      "codex": "gpt-5.6-luna",
       "mistral": "devstral-small-2",
       "deepseek": "deepseek-v4-flash",
       "glm": "glm-4-flash",
-      "grok": "grok-4.1-fast",
+      "grok": "grok-4.5",
       "qwen3": "qwen3-32b",
-      "cursor": "gemini-3-flash",
+      "cursor": "composer-2.5",
       "kimi": "kimi-code/k3",
-      "minimax": "minimax-m2.5"
+      "minimax": "MiniMax-M2.5"
     }
   },
+  "transport_model_tiers": {
+    "_comment": "Transport-specific namespaces used by Gemini and Mistral; the legacy model_tiers table reflects their CLI values.",
+    "gemini": {
+      "maximum": {"cli": "Gemini 3.1 Pro (High)", "api": "gemini-3.1-pro-preview"},
+      "premium": {"cli": "Gemini 3.1 Pro (High)", "api": "gemini-3.1-pro-preview"},
+      "standard": {"cli": "Gemini 3.6 Flash (High)", "api": "gemini-3.1-pro-preview"},
+      "economy": {"cli": "Gemini 3.6 Flash (Low)", "api": "gemini-3.1-pro-preview"}
+    },
+    "mistral": {
+      "maximum": {"cli": "mistral-medium-3.5", "api": "mistral-large-3"},
+      "premium": {"cli": "mistral-medium-3.5", "api": "mistral-large-3"},
+      "standard": {"cli": "mistral-medium-3.5", "api": "mistral-large-3"},
+      "economy": {"cli": "devstral-small-2", "api": "mistral-large-3"}
+    }
+  },
+  "opt_in_targets": {
+    "gemini": ["gemini-3.7-flash", "Gemini 3.7 Flash (High)", "Gemini 3.7 Flash (Low)"],
+    "mistral_api": ["mistral-medium-3-5", "mistral-large-2512", "mistral-small-2603"],
+    "claude": ["claude-fable-5"]
+  },
   "default_rate": {
     "input": 0.005,
     "output": 0.015

package/docs/releases/v3.4.0.md

@@ -0,0 +1,102 @@
+# Release v3.4.0
+
+**Date:** 2026-08-05
+**Type:** Minor — Gemini works over SSH again, the Codex consultant is isolated, and the model catalog moves to the current generation
+**Previous:** v3.3.0
+
+## Highlights
+
+- **Gemini consultations from an SSH session were failing authentication, and re-signing-in could not fix it.** Now fixed at every `agy` call site.
+- **The Codex consultant no longer inherits your local Codex environment** — no `config.toml`, no `AGENTS.md`, no hooks, no MCP servers, and a read-only sandbox.
+- **Model catalog refreshed** to `gpt-5.6-sol/terra/luna`, `claude-sonnet-5`, and Gemini 3.6 Flash, every id verified against the installed CLIs rather than documentation.
+- **`*_REASONING_EFFORT` actually works now.** It was honored in API mode only, which meant it did nothing in the default CLI-first configuration.
+- **Existing installations receive the new Codex model.** Without the migration added here, they would have kept querying `gpt-5.5` indefinitely while every doc claimed otherwise.
+
+## What's New
+
+### Gemini authentication over SSH
+
+The Antigravity CLI picks its credential store from the environment. When it sees any of `SSH_CLIENT`, `SSH_CONNECTION`, or `SSH_TTY`, it switches to a file-based token store and never consults the macOS Keychain. If you signed in locally — as almost everyone does — the credential lives in the Keychain, so every Gemini consultation over SSH failed to authenticate. Signing in again did not help: the new login also landed in the store the CLI had already decided to ignore.
+
+Those three markers are now stripped for every `agy` invocation: consultations, `doctor`, `update-clis`, and synthesis. On a local session they are already unset, so this changes nothing there. It grants no additional tools and no filesystem access — only which credential store the CLI consults.
+
+If you drive ai-consultants over SSH, this is the release that makes Gemini work.
+
+### The Codex consultant runs isolated
+
+Previously the Codex adapter ran `codex exec` in your ambient environment. That meant your `~/.codex/config.toml`, the repository's `AGENTS.md`, your hooks, your MCP servers, and your execpolicy rules all shaped what is supposed to be an independent second opinion — and the sandbox was unpinned.
+
+CLI mode now runs under an ephemeral HOME and working directory with `--ephemeral`, `--ignore-user-config`, `--ignore-rules`, and `-s read-only`. **Authentication is unaffected**: `CODEX_HOME` still resolves to your real Codex auth store.
+
+Two side effects worth knowing:
+
+- **Large contexts no longer break it.** The prompt is delivered on stdin rather than argv, which removes both the `ARG_MAX` ceiling and the exposure of your prompt in the process list.
+- **Failures are reported as failures.** A timeout, authentication error, or exhausted retry is never rewritten into a success, even when a partial answer reached disk.
+
+### Reasoning effort works in CLI mode
+
+`*_REASONING_EFFORT` was documented as API-mode only. Since CLI-first transport became mandatory in v2.21, that meant the setting did nothing at all in the default configuration — while three consultant CLIs did expose the control.
+
+| Consultant | Variable | Passed as |
+|---|---|---|
+| Codex | `CODEX_REASONING_EFFORT` | `-c model_reasoning_effort=<value>` |
+| Claude | `CLAUDE_REASONING_EFFORT` | `--effort <value>` |
+| Gemini | `GEMINI_REASONING_EFFORT` | `--effort <value>` |
+
+There is deliberately no local allowlist of accepted values. The enum belongs to the provider — `agy`, for instance, accepts only `low|medium|high` — and an unsupported value comes back as a diagnosed error rather than being silently pre-empted. Consultants whose CLI has no such flag still warn, as before.
+
+All three are optional. Leave them unset and each CLI keeps its own default.
+
+### Model catalog
+
+Every replacement id was verified live against the installed CLIs:
+
+| Consultant | Premium | Standard | Economy |
+|---|---|---|---|
+| Codex | `gpt-5.6-sol` | `gpt-5.6-terra` | `gpt-5.6-luna` |
+| Claude | `claude-opus-5` *(unchanged)* | `claude-sonnet-5` | `claude-haiku-4-5` *(unchanged)* |
+| Gemini | `Gemini 3.1 Pro (High)` *(unchanged)* | `Gemini 3.6 Flash (High)` | `Gemini 3.6 Flash (Low)` |
+
+Gemini's premium tier stays on 3.1 Pro because the live model inventory has no 3.6 Pro. Cost rates ship alongside the new ids — a model missing from the catalog would otherwise be billed at the fallback rate and reported as a confident, wrong figure. Superseded ids remain catalogued so pinned configurations and historical responses still resolve.
+
+The opt-in Qwen Token Plan model is referenced as `qwen3.8-max`. Both it and `qwen3.8-max-preview` are still served by Token Plan, and they are separate deployments rather than aliases — each reports its own id back. Both stay catalogued, so an existing `-preview` pin keeps working and keeps its credit-billed cost disclosure. The shipped premium Qwen model remains `qwen3.7-max`.
+
+### Existing installations get the new Codex model
+
+`init` copies `.env.example` verbatim, so the then-current Codex default was written into your config as an ordinary value — and `configure` reads any unmarked value as a deliberate pin. A catalog refresh alone would therefore never have reached you: your panel would have kept querying `gpt-5.5` while the docs, tier tables, and cost catalog all said `gpt-5.6-sol`.
+
+`configure` now migrates that one exact historical value and marks it as managed, so future refreshes can reach it too. **An explicit pin is preserved** — if you deliberately want `gpt-5.5`, record it with `--set CODEX_MODEL=gpt-5.5` and it will survive.
+
+## Breaking Changes
+
+None. All new parameters are additive, existing configurations migrate, and no consultant is added or removed.
+
+Two behavior changes are worth noting even though nothing breaks:
+
+- **Codex answers may differ**, because it no longer sees your local Codex configuration. That is the intent — an advisory consultation shaped by your own hooks and project instructions is not an independent opinion.
+- **Codex and Gemini tier models changed.** Pin `CODEX_MODEL` / `GEMINI_MODEL` explicitly if you need the previous ones.
+
+## Upgrade Guide
+
+```bash
+# If installed via npx, nothing to do — npx resolves the published version
+npx ai-consultants "your question"
+
+# If installed via git clone
+cd ~/.claude/skills/ai-consultants && git pull
+
+# If installed via curl | bash
+curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash
+```
+
+Then, to pick up the new Codex default in an existing configuration:
+
+```bash
+ai-consultants configure
+```
+
+No other configuration changes are required. Run `ai-consultants doctor --live` afterwards to confirm each consultant actually answers — the static check only verifies that CLIs are installed and keys are present.
+
+## Contributors
+
+- @matteoscurati

package/docs/releases/v3.5.0.md

@@ -0,0 +1,129 @@
+# Release v3.5.0
+
+**Date:** 2026-08-21  
+**Type:** Minor — transport-aware model catalog and honest model identity  
+**Previous:** v3.4.0
+
+## Highlights
+
+- Normal premium runs remain cost-balanced; `max_quality` gains a separate maximum tier for exact-transport-smoked subscription targets.
+- Mistral Vibe uses `mistral-medium-3.5` through a dedicated CLI setting, while API IDs remain separate and opt-in until verified.
+- Cursor now invokes and validates `cursor-agent`, never the unrelated `agent` binary, and runs in read-only ask mode inside an ephemeral workspace.
+- Responses distinguish requested models from provider-reported or capability-probed effective identity.
+- GLM 5.3 and Grok 4.6 become the promoted defaults; new prices, unpriced disclosures, migrations, and 22-suite regression coverage ship with them.
+
+## What's New
+
+### A maximum tier that fails closed
+
+`max_quality` no longer means simply “the normal premium tier with more consultants.” It selects the strongest targets that completed a smoke through ai-consultants' own adapter and output contract:
+
+| Consultant | Normal premium | `max_quality` maximum | Promotion evidence |
+|---|---|---|---|
+| Kimi | `kimi-code/k3` | `kimi-code/k3-256k` | CLI inventory + live response |
+| Qwen3 | `qwen3.7-max` | `qwen3.8-max` only on an already-configured Token Plan transport | Provider-reported API model |
+| MiniMax | `MiniMax-M2.7` | `MiniMax-M3` | Explicit CLI model + live response |
+| Claude | `claude-opus-5` | `claude-opus-5` | Fable 5 timed out, so it remains opt-in |
+
+Qwen is never silently redirected from DashScope or CLI mode to a different paid endpoint. Without the exact Token Plan configuration, maximum keeps Qwen on `qwen3.7-max`.
+
+### Transport-aware Gemini and Mistral configuration
+
+Gemini and Mistral no longer pretend that one model string works on both transports:
+
+- Gemini keeps separate `GEMINI_MODEL` and `GEMINI_API_MODEL` values. Gemini 3.7 Flash is priced and documented but remains opt-in because neither local transport could authenticate for its smoke.
+- Mistral API continues to use `MISTRAL_MODEL`; Vibe uses the new `MISTRAL_CLI_MODEL`, defaulting to `mistral-medium-3.5` through `VIBE_ACTIVE_MODEL`.
+- The official Mistral API IDs `mistral-medium-3-5`, `mistral-large-2512`, and `mistral-small-2603` remain opt-in because no Mistral API key was available for exact transport verification.
+
+### Bounded advisory CLIs
+
+Cursor and Mistral now run in temporary workspaces with read-only modes and bounded capability probes:
+
+- Cursor defaults to `cursor-agent`, verifies the Cursor interface and requested Composer 2.5 inventory, and uses `--mode ask --trust` only for the newly-created workspace. `-f`/force mode is never used.
+- Mistral verifies prompt/output/agent/workdir/max-turn capabilities and the built-in plan agent before dispatch.
+- A failed or timed-out probe stops before a model request. A timeout, empty reply, or other failure after launch never triggers a silent alternate model or transport.
+
+### Requested versus effective model identity
+
+Response metadata adds:
+
+```json
+{
+  "requested_model": "glm-5.3",
+  "model_identity_source": "provider-reported"
+}
+```
+
+`model_identity_source` is one of:
+
+- `provider-reported` — the API explicitly named the effective model;
+- `capability-probed` — the requested CLI model was present in an authenticated inventory;
+- `requested-only` — the transport accepted the request but exposed no stronger content-model evidence.
+
+The top-level `model` remains the best effective identifier available. Provider billing participants such as Claude CLI `modelUsage` are not misrepresented as content identity.
+
+### Prices, unpriced targets, and migrations
+
+The catalog now includes current entries for Fable 5, Gemini 3.7 Flash, Mistral Medium 3.5/Large 3/Small 4, Grok 4.6, and MiniMax M3/M2.7/M2.5. GLM 5.3 on the coding-plan endpoint, Qwen3.8-Max Token Plan, and K3-256k remain explicitly unpriced: reports disclose their exclusion instead of inventing a dollar rate or calling them free.
+
+`ai-consultants configure` migrates only these exact historical managed values:
+
+- `CURSOR_CMD=agent` → `cursor-agent`
+- `GLM_MODEL=glm-5.2` → `glm-5.3`
+- `GROK_MODEL=grok-4.5` → `grok-4.6`
+
+Values carrying `# ai-consultants:pin` remain unchanged.
+
+## Verification and Provider Status
+
+- Full gate: 22/22 suites
+- Core gate: 443/443 checks
+- ShellCheck, Bash syntax, JSON validation, and npm tarball: passed
+- Cross-family material review: Claude Opus 5 at max effort; initial `NO-SHIP`, final `SHIP` after findings were resolved
+- PR CI: full GitHub Actions job executed and passed
+
+Not verified locally in this release:
+
+- Gemini 3.7 Flash — agy/API authentication unavailable
+- Mistral new API IDs — no API key available
+- Claude Fable 5 — max-effort adapter and direct probes timed out
+- Cursor response — CLI installed, account not logged in
+
+These targets are not presented as verified defaults.
+
+## Breaking Changes
+
+None — this release is backwards-compatible. New metadata and configuration fields are additive. Managed migrations are limited to exact historical defaults and preserve explicit pins.
+
+`max_quality` can select subscription/credit-billed targets that have no reliable per-token USD price. They are disclosed in the cost caveat, but a dollar budget cannot cap consumption the estimator cannot price.
+
+## Upgrade Guide
+
+```bash
+# npx (no install)
+npx ai-consultants "question"
+
+# git clone install
+cd ~/.claude/skills/ai-consultants && git pull
+
+# curl | bash install
+curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash
+```
+
+Run the configurator once to migrate managed Cursor, GLM, and Grok defaults:
+
+```bash
+ai-consultants configure
+ai-consultants doctor --live
+```
+
+No credential or authentication state is modified automatically.
+
+## Commits
+
+- `97f537c` feat: refresh consultant model catalog and transport contracts
+- `3614949` Merge pull request #12 from `agent/model-catalog-3.5.0`
+
+## Contributors
+
+- @matteoscurati

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-consultants",
-  "version": "3.3.0",
+  "version": "3.5.0",
   "description": "A harness for every question - a panel of up to 11 AI models that picks its own deliberation strategy per question (convergence, adversarial verification, tournament) and checks its work before answering",
   "bin": {
     "ai-consultants": "bin/ai-consultants"