converse-mcp-server 4.6.2 → 4.7.0

package/.env.example

@@ -103,10 +103,10 @@ CLOUDFLARE_API_TOKEN=your_cloudflare_api_token_here
 # with "did you mean" suggestions otherwise. Per request, use "provider:model".
 # CODEX_DEFAULT_MODEL=gpt-6-astra     # gpt-6.1-sol, gpt-6-sol, gpt-6-luna, gpt-6-astra, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.3-codex-spark (CODEX_MODEL is the legacy name)
 # CLAUDE_DEFAULT_MODEL=claude-opus-5-5
-# AGY_DEFAULT_MODEL=gemini-3.8-flash  # Antigravity CLI: gemini-3.8-flash, gemini-3.1-pro-preview
+# AGY_DEFAULT_MODEL=gemini-3.8-flash  # Antigravity CLI: gemini-4-argon (default, requires Google AI Ultra), gemini-3.8-flash
 # COPILOT_DEFAULT_MODEL=gpt-6.1-sol   # COPILOT_MODEL is the legacy name
 # OPENAI_DEFAULT_MODEL=gpt-6.1-sol
-# GOOGLE_DEFAULT_MODEL=gemini-3.1-pro-preview
+# GOOGLE_DEFAULT_MODEL=gemini-4-argon
 # XAI_DEFAULT_MODEL=grok-4.5
 # ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5
 # MISTRAL_DEFAULT_MODEL=mistral-medium-3-5

package/README.md

@@ -258,14 +258,15 @@ SUMMARIZATION_MODEL=gpt-5-nano        # Default: gpt-5-nano
 
 **Supported Models**:
 
-- **gemini-3.1-pro-preview** (aliases: `pro`, `gemini-pro`): Most advanced reasoning with expanded thinking levels (1M context, 64K output)
+- **gemini-4-argon** (default; aliases: `argon`, `pro`, `gemini-pro`): Flagship reasoning model for complex software engineering and agentic work; paid API tier only (1M context, 65K output)
+- **gemini-3.1-pro-preview** (aliases: `gemini-3.1-pro`, `gemini-3`): Gemini 3.1 Pro reasoning with expanded thinking levels (1M context, 64K output)
 - **gemini-3.5-flash** (aliases: `gemini-3.5`, `flash-3.5`): Frontier-level agentic and coding performance at Flash speed (1M context, 65K output)
 - **gemini-3.8-flash** (aliases: `gemini-3.8`, `flash-3.8`): Current-generation Flash with stronger long-horizon agentic performance (1M context, 65K output; thinking levels low/medium/high — no minimal)
 - **gemini-2.5-pro** (alias: `pro 2.5`): Deep reasoning with thinking budget (1M context, 65K output)
 - **gemini-2.5-flash** (alias: `flash`): Ultra-fast (1M context, 65K output)
 - **gemini-2.5-flash-lite** (alias: `flash-lite`): Lightweight fast model (1M context, 65K output)
 
-**Note**: The Antigravity CLI provider serves `gemini-3.8-flash` and `gemini-3.1-pro-preview` under the same names and aliases, so bare `pro`, `gemini-pro`, `flash` and those IDs go to Antigravity first when it is installed (see [Model Selection](#model-selection)). Use `google:<model>` to always use the Google API.
+**Note**: The Antigravity CLI provider serves `gemini-4-argon` and `gemini-3.8-flash`. Bare `pro` and `gemini-pro` resolve to Gemini 4 Argon on Antigravity first, then the Google API as failover; bare `gemini-3.1-pro-preview` routes to the Google API only. Bare `flash` and `gemini-3.8-flash` route to Antigravity first when it is installed (see [Model Selection](#model-selection)). Use `google:<model>` to always use the Google API.
 
 ### X.AI/Grok Models
 
@@ -348,7 +349,7 @@ Reach these only with the `copilot:` namespace (e.g. `copilot:gpt-6.1-sol`) —
 
 - **OpenAI**: `gpt-6.1-sol` (aliases: `gpt-6`, `gpt-6.1`, `gpt-5`, `sol`), `gpt-6-sol`, `gpt-6-luna` (alias: `luna`), `gpt-5.6-sol` (alias: `gpt-5.6`), `gpt-5.6-terra`, `gpt-5.6-luna` (all support `reasoning_effort`)
 - **Anthropic**: `claude-opus-5.5` (aliases: `opus`, `claude`), `claude-fable-5.1` (alias: `fable`), `claude-fable-5`, `claude-sonnet-5.5` (alias: `sonnet`), `claude-haiku-5.5` (alias: `haiku`), `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4.8`
-- **Google**: `gemini-3.1-pro-preview` (aliases: `gemini`, `gemini-3.1-pro`), `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`), `gemini-3.5-flash` (alias: `gemini-flash`)
+- **Google**: `gemini-4-argon` (aliases: `gemini`, `argon`, `gemini-4`), `gemini-3.8-flash` (alias: `gemini-flash`)
 
 ## 📚 Help & Documentation
 
@@ -409,10 +410,10 @@ CODEX_APPROVAL_POLICY=never                  # never (default), untrusted, on-fa
 # list; startup fails with suggestions otherwise.
 CODEX_DEFAULT_MODEL=gpt-6-astra              # CODEX_MODEL still works as a fallback
 CLAUDE_DEFAULT_MODEL=claude-opus-5-5
-AGY_DEFAULT_MODEL=gemini-3.8-flash           # Antigravity CLI (gemini)
+AGY_DEFAULT_MODEL=gemini-4-argon             # Requires Google AI Ultra; other plans can use gemini:flash or set AGY_DEFAULT_MODEL=gemini-3.8-flash
 COPILOT_DEFAULT_MODEL=gpt-6.1-sol            # COPILOT_MODEL still works as a fallback
 OPENAI_DEFAULT_MODEL=gpt-6.1-sol
-GOOGLE_DEFAULT_MODEL=gemini-3.1-pro-preview
+GOOGLE_DEFAULT_MODEL=gemini-4-argon
 XAI_DEFAULT_MODEL=grok-4.5
 ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5
 MISTRAL_DEFAULT_MODEL=mistral-medium-3-5
@@ -481,13 +482,13 @@ Every entry in `models` takes one of four forms:
 // A provider: its default model (hardcoded, or <PROVIDER>_DEFAULT_MODEL)
 "codex"; // -> Codex (GPT-6 Astra)
 "claude"; // -> Claude Agent SDK (Claude Opus 5.5)
-"gemini"; // -> Antigravity CLI (Gemini 3.8 Flash); `agy` works too
+"gemini"; // -> Antigravity CLI (Gemini 4 Argon)
 "openai"; // -> OpenAI API (GPT-6.1 Sol)
 
 // provider:model — that model on that provider only
 "codex:astra"; // -> Codex (GPT-6 Astra)
 "openai:gpt-6-astra"; // -> OpenAI API, even when Codex is available
-"gemini:pro"; // -> Antigravity CLI (Gemini 3.1 Pro)
+"gemini:pro"; // -> Antigravity CLI (Gemini 4 Argon)
 "google:gemini-3.1-pro-preview"; // -> Google API
 "copilot:sonnet"; // -> GitHub Copilot (Claude Sonnet 5.5)
 "openrouter:z-ai/glm-5.2:online"; // -> OpenRouter with web search opt-in
@@ -495,7 +496,7 @@ Every entry in `models` takes one of four forms:
 // A bare model ID or alias — the first configured provider that offers it
 "gpt-6-astra"; // -> Codex, else OpenAI API
 "opus"; // -> Claude Agent SDK, else Anthropic API
-"pro"; // -> Antigravity CLI, else Google API
+"pro"; // -> Antigravity CLI (gemini-4-argon), else Google API
 "grok"; // -> grok-4.5 (XAI)
 "z-ai/glm-5.2"; // -> OpenRouter (any vendor/model slug)
 ```
@@ -513,11 +514,11 @@ Every entry in `models` takes one of four forms:
 Provider priority order (subscription-based local providers first, then API-key providers), used by both `auto` and bare model names:
 
 1. Codex (`codex` → GPT-6 Astra)
-2. Gemini via Antigravity CLI (`gemini` / `agy` → Gemini 3.8 Flash)
+2. Gemini via Antigravity CLI (`gemini` / `agy` → Gemini 4 Argon)
 3. Claude Agent SDK (`claude` → Claude Opus 5.5)
 4. Copilot (`copilot` → GPT-6.1 Sol; `auto` only, never bare names)
 5. OpenAI (`openai` → GPT-6.1 Sol)
-6. Google (`google` → Gemini 3.1 Pro)
+6. Google (`google` → Gemini 4 Argon)
 7. XAI (`xai` → Grok 4.5)
 8. Anthropic (`anthropic` → Claude Opus 5.5)
 9. Mistral (`mistral` → Mistral Medium 3.5)

package/docs/API.md

@@ -520,14 +520,15 @@ Provide models as plain name strings in the `models` array. Each entry is `auto`
 
 | Model | Aliases | Context | Output | Notes |
 |-------|---------|---------|--------|-------|
-| `gemini-3.1-pro-preview` | `pro`, `gemini-pro` | 1M | 64K | Most advanced reasoning, expanded thinking levels |
+| `gemini-4-argon` | `argon`, `pro`, `gemini-pro` | 1M | 65K | Default; flagship reasoning for complex software engineering and agentic work; paid API tier only |
+| `gemini-3.1-pro-preview` | `gemini-3.1-pro`, `gemini-3` | 1M | 64K | Gemini 3.1 Pro reasoning, expanded thinking levels |
 | `gemini-3.5-flash` | `gemini-3.5`, `flash-3.5` | 1M | 65K | Frontier agentic/coding at Flash speed |
 | `gemini-3.8-flash` | `gemini-3.8`, `flash-3.8` | 1M | 65K | Current-generation Flash; thinking low/medium/high only |
 | `gemini-2.5-pro` | `pro 2.5` | 1M | 65K | Deep reasoning with thinking budget |
 | `gemini-2.5-flash` | `flash` | 1M | 65K | Ultra-fast |
 | `gemini-2.5-flash-lite` | `flash-lite` | 1M | 65K | Lightweight fast model |
 
-**Note:** The **Antigravity CLI** provider (`agy`, OAuth-based) serves `gemini-3.8-flash` and `gemini-3.1-pro-preview` under the same IDs and aliases, so bare `pro`, `gemini-pro`, `flash` and those IDs go to Antigravity first when `agy` is installed; the bare name `gemini` is the Antigravity namespace. Use `google:<model>` (e.g. `google:pro`) to always use the Google API.
+**Note:** The **Antigravity CLI** provider (`agy`, OAuth-based) serves `gemini-4-argon` and `gemini-3.8-flash`. Bare `pro` and `gemini-pro` resolve to Gemini 4 Argon on Antigravity first, then the Google API as failover; bare `gemini-3.1-pro-preview` routes to the Google API only. Bare `flash` and `gemini-3.8-flash` route to Antigravity first when `agy` is installed; the bare name `gemini` is the Antigravity namespace. Use `google:<model>` (e.g. `google:pro`) to always use the Google API.
 
 ### X.AI / Grok Models
 
@@ -627,14 +628,14 @@ All three are uncensored ("abliterated") reasoning models using Abliteration's O
 
 The **Antigravity CLI** (`agy`) provides subscription-based access to Gemini models through Google OAuth:
 
-- **Models** (text-only): `gemini-3.8-flash` (`flash`, `gemini-3.8`, `flash-3.8`, ...; default, `gemini` = `gemini:flash`), `gemini-3.1-pro-preview` (`pro`, `gemini-pro`, `gemini-3.1-pro`, ...; `gemini:pro`). Default override: `AGY_DEFAULT_MODEL`.
+- **Models** (text-only): `gemini-4-argon` (default; `argon`, `pro`, `gemini-pro`, ...; `gemini:pro`), `gemini-3.8-flash` (`flash`, `gemini-3.8`, `flash-3.8`, ...; `gemini:flash`). Gemini 4 Argon requires Google AI Ultra; other plans can use `gemini:flash` or set `AGY_DEFAULT_MODEL=gemini-3.8-flash`. Default override: `AGY_DEFAULT_MODEL`.
 - **Namespaces**: `gemini`, `agy`, `antigravity`, `gemini-cli`
 - **Availability**: the `agy` binary is found on PATH or at the platform install location
 - **Permissions**: `agy` runs with `--dangerously-skip-permissions`, so every tool request is auto-approved
 - **Authentication**: Google OAuth via `agy` (one-time interactive login)
 - **Setup**: install the Antigravity CLI and run `agy` once to log in
 - **Billing**: uses your Antigravity subscription/compute allowance instead of API credits
-- **Reasoning effort**: `low`/`medium`/`high`/`max` select the model variant
+- **Reasoning effort**: Every model has Low, Medium, and High variants selected by `reasoning_effort`
 - **Context**: 1M tokens
 - One-shot responses (no token-level streaming); ~7s minimum per call
 
@@ -656,7 +657,7 @@ Reach these only with the `copilot:` namespace (also `github-copilot:`, `copilot
 
 - **OpenAI**: `gpt-6.1-sol` (aliases: `gpt-6`, `gpt-6.1`, `gpt-5`, `sol`), `gpt-6-sol`, `gpt-6-luna` (alias: `luna`), `gpt-5.6-sol` (alias: `gpt-5.6`), `gpt-5.6-terra`, `gpt-5.6-luna` (all accept `reasoning_effort`)
 - **Anthropic**: `claude-opus-5.5` (aliases: `opus`, `claude`), `claude-fable-5.1` (alias: `fable`), `claude-fable-5`, `claude-sonnet-5.5` (alias: `sonnet`), `claude-haiku-5.5` (alias: `haiku`), `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4.8`
-- **Google**: `gemini-3.1-pro-preview` (aliases: `gemini`, `gemini-3.1-pro`), `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`), `gemini-3.5-flash` (alias: `gemini-flash`)
+- **Google**: `gemini-4-argon` (aliases: `gemini`, `argon`, `gemini-4`), `gemini-3.8-flash` (alias: `gemini-flash`)
 - Any other `copilot:<id>` is rejected with suggestions
 
 ### Model Selection
@@ -675,7 +676,7 @@ Every entry in `models` takes one of four forms:
 "gpt-6"                    // Codex (-> gpt-6.1-sol), else OpenAI API
 "openai:gpt-6"             // OpenAI API only
 "gemini-2.5-flash"         // Google API
-"pro"                      // Antigravity CLI (-> gemini-3.1-pro-preview), else Google API
+"pro"                      // Antigravity CLI (-> gemini-4-argon), else Google API
 "google:pro"               // Google API only
 "grok-4.5"                 // X.AI
 "deepseek"                 // DeepSeek (-> deepseek-v4-pro)
@@ -689,7 +690,7 @@ Every entry in `models` takes one of four forms:
 "claude"                   // Claude Agent SDK (-> Claude Opus 5.5)
 "claude:fable"             // Claude Agent SDK (Claude Fable 5.1)
 "codex:luna"               // Codex (GPT-6 Luna)
-"gemini"                   // Antigravity CLI (Gemini 3.8 Flash)
+"gemini"                   // Antigravity CLI (Gemini 4 Argon)
 "copilot:gpt-6.1-sol"      // GitHub Copilot SDK
 ```
 
@@ -738,10 +739,10 @@ Each provider's default model (used for its bare provider name and for `auto`) c
 ```bash
 CODEX_DEFAULT_MODEL=gpt-6-astra              # CODEX_MODEL is honored as a legacy fallback
 CLAUDE_DEFAULT_MODEL=claude-opus-5-5
-AGY_DEFAULT_MODEL=gemini-3.8-flash           # Antigravity CLI (gemini)
+AGY_DEFAULT_MODEL=gemini-4-argon             # Antigravity CLI (gemini)
 COPILOT_DEFAULT_MODEL=gpt-6.1-sol            # COPILOT_MODEL is honored as a legacy fallback
 OPENAI_DEFAULT_MODEL=gpt-6.1-sol
-GOOGLE_DEFAULT_MODEL=gemini-3.1-pro-preview
+GOOGLE_DEFAULT_MODEL=gemini-4-argon
 XAI_DEFAULT_MODEL=grok-4.5
 ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5
 MISTRAL_DEFAULT_MODEL=mistral-medium-3-5

package/docs/ARCHITECTURE.md

@@ -299,7 +299,7 @@ export const config = {
   models: {
     aliases: {
       'flash': 'gemini-2.5-flash',
-      'pro': 'gemini-3.1-pro-preview',
+      'pro': 'gemini-4-argon',
       'grok': 'grok-4.5'
     }
   }

package/docs/PROVIDERS.md

@@ -26,13 +26,14 @@ This guide documents all supported AI providers in the Converse MCP Server and t
 - **Get Key**: [makersuite.google.com/app/apikey](https://makersuite.google.com/app/apikey)
 - **Environment Variable**: `GOOGLE_API_KEY`
 - **Supported Models**:
-  - `gemini-3.1-pro-preview` (aliases: `pro`, `gemini-pro`) - Most advanced reasoning with expanded thinking levels (1M context, 64K output)
+  - `gemini-4-argon` (default; aliases: `argon`, `pro`, `gemini-pro`) - Flagship reasoning model for complex software engineering and agentic work; paid API tier only (1M context, 65K output)
+  - `gemini-3.1-pro-preview` (aliases: `gemini-3.1-pro`, `gemini-3`) - Gemini 3.1 Pro reasoning with expanded thinking levels (1M context, 64K output)
   - `gemini-3.5-flash` (aliases: `gemini-3.5`, `flash-3.5`) - Frontier-level agentic and coding performance at Flash speed (1M context, 65K output)
   - `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`) - Current-generation Flash with stronger long-horizon agentic performance (1M context, 65K output; thinking levels low/medium/high — no minimal)
   - `gemini-2.5-pro` (alias: `pro 2.5`) - Deep reasoning with thinking budget (1M context, 65K output)
   - `gemini-2.5-flash` (alias: `flash`) - Ultra-fast model with thinking budget (1M context, 65K output)
   - `gemini-2.5-flash-lite` (alias: `flash-lite`) - Lightweight fast model (1M context, 65K output)
-- **Note**: The **Antigravity CLI** provider (`agy`, OAuth-based access) serves `gemini-3.8-flash` and `gemini-3.1-pro-preview` under the same IDs and aliases, and it comes before the Google API in bare-name order. When `agy` is installed, bare `pro`, `gemini-pro`, `flash`, `gemini-3.1-pro-preview` and `gemini-3.8-flash` go to Antigravity first; the bare name `gemini` is the Antigravity namespace. Use `google:<model>` (e.g. `google:pro`, `google:gemini-2.5-flash`) to always use the Google API. Names only the Google API serves (e.g. `gemini-2.5-pro`, `gemini-3.5-flash`) route there directly.
+- **Note**: The **Antigravity CLI** provider (`agy`, OAuth-based access) serves `gemini-4-argon` and `gemini-3.8-flash`, and it comes before the Google API in bare-name order. When `agy` is installed, bare `pro` and `gemini-pro` resolve to Gemini 4 Argon on Antigravity first, with the Google API as failover; bare `gemini-3.1-pro-preview` routes to the Google API only. The bare name `gemini` is the Antigravity namespace. Use `google:<model>` (e.g. `google:pro`, `google:gemini-2.5-flash`) to always use the Google API. Names only the Google API serves (e.g. `gemini-2.5-pro`, `gemini-3.5-flash`) route there directly.
 
 ### X.AI (Grok)
 - **API Key Format**: `xai-...` (starts with `xai-`)
@@ -155,12 +156,12 @@ This guide documents all supported AI providers in the Converse MCP Server and t
   2. Authenticate: run `agy` once interactively and complete the Google OAuth login. This also establishes workspace trust for your home directory (the provider spawns each call in a per-call subdirectory under `~/.converse/agy-runs`).
 - **Availability**: The `agy` binary is found on PATH or at the platform install location
 - **Environment Variables**:
-  - `AGY_DEFAULT_MODEL` - Model used for bare `gemini` and `auto` (default: `gemini-3.8-flash`)
+  - `AGY_DEFAULT_MODEL` - Model used for bare `gemini` and `auto` (default: `gemini-4-argon`, requires Google AI Ultra; other plans can use `gemini:flash` or set `AGY_DEFAULT_MODEL=gemini-3.8-flash`)
 - **Namespaces**: `gemini`, `agy`, `antigravity`, `gemini-cli` (all equivalent, e.g. `agy:pro`)
 - **Supported Models** (text-only — print mode has no image input channel):
-  - `gemini-3.8-flash` (aliases: `flash`, `gemini-3.8`, `flash-3.8`, ...) - Gemini 3.8 Flash (default; `gemini` alone = `gemini:flash`)
-  - `gemini-3.1-pro-preview` (aliases: `pro`, `gemini-pro`, `gemini-3.1-pro`, `gemini-3`, ...) - Gemini 3.1 Pro (`gemini:pro`)
-  - `reasoning_effort` selects the variant: `low` → (Low), `medium` → (Medium) for Flash / (High) for Pro, `high`/`max` → (High); unset defaults to (High)
+  - `gemini-4-argon` (aliases: `argon`, `pro`, `gemini-pro`, ...) - Gemini 4 Argon (default; `gemini` alone = `gemini:gemini-4-argon`; `gemini:pro`)
+  - `gemini-3.8-flash` (aliases: `flash`, `gemini-3.8`, `flash-3.8`, ...) - Gemini 3.8 Flash (`gemini:flash`)
+  - Every model has Low, Medium, and High variants selected by `reasoning_effort`.
 
 **Key Features:**
 - **OAuth Authentication**: Uses your Antigravity Google login instead of API keys
@@ -213,7 +214,7 @@ agy
 **Differences from Google API Provider:**
 - **Authentication**: Google OAuth via `agy` vs API Key (Google API)
 - **Billing**: Antigravity subscription/compute allowance vs pay-per-use API
-- **Model Routing**: `gemini` / `gemini:<model>` / `agy:<model>` → Antigravity CLI provider; `google:<model>` → Google API provider; bare names both serve (`pro`, `gemini-pro`, `gemini-3.1-pro-preview`, `gemini-3.8-flash`) → Antigravity first, then the Google API on authentication/availability failure; bare names only the Google API serves (e.g., `gemini-2.5-pro`) → Google API provider. Bare `flash` is Gemini 3.8 Flash on Antigravity but Gemini 2.5 Flash on the Google API, so it does not fail over between them.
+- **Model Routing**: `gemini` / `gemini:<model>` / `agy:<model>` → Antigravity CLI provider; `google:<model>` → Google API provider; bare `pro` and `gemini-pro` resolve to Gemini 4 Argon on Antigravity first, then the Google API on authentication/availability failure. Bare `gemini-3.1-pro-preview` routes to the Google API only. Bare `gemini-3.8-flash` is served by both providers and tries Antigravity first; bare `flash` is Gemini 3.8 Flash on Antigravity but Gemini 2.5 Flash on the Google API, so it does not fail over between them.
 - **Images**: Not supported (text-only) vs full multimodal on the Google API provider
 - **Permissions**: `agy` runs with `--dangerously-skip-permissions` (headless calls cannot prompt), so every tool request, including shell commands and file writes, is auto-approved. Bare names and `auto` reach it whenever `agy` is installed; use `google:<model>` to keep a request on the plain API.
 
@@ -257,7 +258,7 @@ agy
   - `copilot` - GPT-6.1 Sol, or `COPILOT_DEFAULT_MODEL`
   - OpenAI: `gpt-6.1-sol` (aliases: `gpt-6`, `gpt-6.1`, `gpt-5`, `sol`), `gpt-6-sol`, `gpt-6-luna` (alias: `luna`), `gpt-5.6-sol` (alias: `gpt-5.6`), `gpt-5.6-terra`, `gpt-5.6-luna`
   - Anthropic: `claude-opus-5.5` (aliases: `opus`, `claude`; Copilot Pro+/Max/Business/Enterprise), `claude-fable-5.1` (alias: `fable`), `claude-fable-5`, `claude-sonnet-5.5` (alias: `sonnet`), `claude-haiku-5.5` (alias: `haiku`), `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4.8`
-  - Google: `gemini-3.1-pro-preview` (aliases: `gemini`, `gemini-3.1-pro`), `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`), `gemini-3.5-flash` (alias: `gemini-flash`)
+  - Google: `gemini-4-argon` (aliases: `gemini`, `argon`, `gemini-4`), `gemini-3.8-flash` (alias: `gemini-flash`)
 - **Reasoning**: The GPT-6 and GPT-5.6 tiers accept `reasoning_effort` (clamped onto Copilot's `low`–`xhigh`).
 - **Unknown IDs**: Any other `copilot:<id>` is rejected with suggestions; only the IDs and aliases above are accepted.
 
@@ -297,10 +298,10 @@ Each provider has a `<PROVIDER>_DEFAULT_MODEL` variable that sets the model used
 ```bash
 CODEX_DEFAULT_MODEL=gpt-6-astra              # CODEX_MODEL is honored as a legacy fallback
 CLAUDE_DEFAULT_MODEL=claude-opus-5-5
-AGY_DEFAULT_MODEL=gemini-3.8-flash           # Antigravity CLI (gemini)
+AGY_DEFAULT_MODEL=gemini-4-argon             # Antigravity CLI (gemini)
 COPILOT_DEFAULT_MODEL=gpt-6.1-sol            # COPILOT_MODEL is honored as a legacy fallback
 OPENAI_DEFAULT_MODEL=gpt-6.1-sol
-GOOGLE_DEFAULT_MODEL=gemini-3.1-pro-preview
+GOOGLE_DEFAULT_MODEL=gemini-4-argon
 XAI_DEFAULT_MODEL=grok-4.5
 ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5
 MISTRAL_DEFAULT_MODEL=mistral-medium-3-5
@@ -408,7 +409,7 @@ Examples:
 "sonnet"                   // Claude Agent SDK (claude-sonnet-5-5), else Anthropic API
 "claude"                   // Claude Agent SDK (defaults to Claude Opus 5.5)
 "claude:fable"             // Claude Agent SDK (Claude Fable 5.1)
-"pro"                      // Antigravity CLI (gemini-3.1-pro-preview), else Google API
+"pro"                      // Antigravity CLI (gemini-4-argon), else Google API
 "google:pro"               // Google API only
 "gemini-2.5-pro"           // Google API
 "grok-4.5"                 // X.AI

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "converse-mcp-server",
-  "version": "4.6.2",
+  "version": "4.7.0",
   "description": "Converse MCP Server - Converse with other LLMs with chat and consensus tools",
   "type": "module",
   "main": "src/index.js",

package/src/providers/copilot.js

@@ -211,29 +211,28 @@ const SUPPORTED_MODELS = {
   },
 
   // Google models
-  // GA `gemini-3.1-pro` does not exist upstream — keep the -preview suffix.
-  'gemini-3.1-pro-preview': {
-    modelName: 'gemini-3.1-pro-preview',
-    friendlyName: 'Gemini 3.1 Pro Preview (via Copilot)',
+  'gemini-4-argon': {
+    modelName: 'gemini-4-argon',
+    friendlyName: 'Gemini 4 Argon (via Copilot)',
     contextWindow: 1048576,
     maxOutputTokens: 65536,
     supportsStreaming: true,
     supportsImages: false,
     supportsWebSearch: false,
     timeout: 1800000,
-    description: 'Google Gemini 3.1 Pro Preview via Copilot subscription',
-    aliases: ['gemini', 'gemini-3.1-pro'],
+    description: 'Google Gemini 4 Argon via Copilot subscription',
+    aliases: ['gemini', 'argon', 'gemini-4'],
   },
-  'gemini-3.5-flash': {
-    modelName: 'gemini-3.5-flash',
-    friendlyName: 'Gemini 3.5 Flash (via Copilot)',
+  'gemini-3.8-flash': {
+    modelName: 'gemini-3.8-flash',
+    friendlyName: 'Gemini 3.8 Flash (via Copilot)',
     contextWindow: 1048576,
     maxOutputTokens: 65536,
     supportsStreaming: true,
     supportsImages: false,
     supportsWebSearch: false,
     timeout: 1800000,
-    description: 'Google Gemini 3.5 Flash via Copilot subscription',
+    description: 'Google Gemini 3.8 Flash via Copilot subscription',
     aliases: ['gemini-flash'],
   },
 };

package/src/providers/gemini-cli.js

@@ -19,9 +19,9 @@
  *   establishes workspace trust for the user's home directory.
  *
  * The provider registry key remains 'gemini-cli'; its namespaces are `gemini:`
- * and `agy:`. Flash is the default: Gemini 3.8 Flash is the current-generation
- * model agy lists first, while 3.1 Pro remains the only Pro tier Antigravity
- * offers.
+ * and `agy:`. Gemini 4 Argon is the default; Antigravity serves it only on
+ * Google AI Ultra plans, so other plans select `gemini:flash` (or set
+ * AGY_DEFAULT_MODEL). Antigravity no longer offers Gemini 3.1 Pro.
  */
 
 import { existsSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';
@@ -60,6 +60,33 @@ const PTY_COLS = 1000;
  * channel).
  */
 const SUPPORTED_MODELS = {
+  'gemini-4-argon': {
+    modelName: 'gemini-4-argon',
+    friendlyName: 'Gemini 4 Argon (via Antigravity CLI)',
+    contextWindow: 1048576,
+    maxOutputTokens: 65536,
+    supportsStreaming: true,
+    supportsImages: false,
+    supportsWebSearch: false,
+    supportsThinking: true,
+    timeout: DEFAULT_TIMEOUT_MS,
+    description:
+      'Gemini 4 Argon via Antigravity CLI (agy, default) - requires Antigravity Google OAuth login on a Google AI Ultra plan',
+    aliases: [
+      'argon',
+      'gemini-argon',
+      'gemini argon',
+      'gemini-4',
+      'gemini4',
+      'gemini 4 argon',
+      '4-argon',
+      'pro',
+      'gemini-pro',
+      'gemini pro',
+    ],
+    // agy display-name base; reasoning_effort selects the parenthesized variant
+    agyModelBase: 'Gemini 4 Argon',
+  },
   'gemini-3.8-flash': {
     modelName: 'gemini-3.8-flash',
     friendlyName: 'Gemini 3.8 Flash (via Antigravity CLI)',
@@ -71,7 +98,7 @@ const SUPPORTED_MODELS = {
     supportsThinking: true,
     timeout: DEFAULT_TIMEOUT_MS,
     description:
-      'Gemini 3.8 Flash via Antigravity CLI (agy, default) - requires Antigravity Google OAuth login',
+      'Gemini 3.8 Flash via Antigravity CLI (agy) - requires Antigravity Google OAuth login',
     aliases: [
       'flash',
       'gemini-3.8',
@@ -83,40 +110,11 @@ const SUPPORTED_MODELS = {
       'gemini flash 3.8',
       '3.8-flash',
     ],
-    // agy display-name base; reasoning_effort selects the parenthesized variant
     agyModelBase: 'Gemini 3.8 Flash',
   },
-  'gemini-3.1-pro-preview': {
-    modelName: 'gemini-3.1-pro-preview',
-    friendlyName: 'Gemini 3.1 Pro (via Antigravity CLI)',
-    contextWindow: 1048576,
-    maxOutputTokens: 65536,
-    supportsStreaming: true,
-    supportsImages: false,
-    supportsWebSearch: false,
-    supportsThinking: true,
-    timeout: DEFAULT_TIMEOUT_MS,
-    description:
-      'Gemini 3.1 Pro via Antigravity CLI (agy) - requires Antigravity Google OAuth login',
-    aliases: [
-      'pro',
-      'gemini-pro',
-      'gemini pro',
-      'gemini-3.1-pro',
-      'gemini-3.1',
-      'gemini3.1',
-      '3.1-pro',
-      'gemini-3',
-      'gemini3',
-      'gemini-3-pro',
-      'gemini-3-pro-preview',
-      '3-pro',
-    ],
-    agyModelBase: 'Gemini 3.1 Pro',
-  },
 };
 
-const DEFAULT_MODEL = 'gemini-3.8-flash';
+const DEFAULT_MODEL = 'gemini-4-argon';
 
 /**
  * Custom error class for Gemini CLI (agy) provider errors
@@ -187,24 +185,21 @@ export function findAgyBinary() {
   return _cachedAgyPath;
 }
 
-// agy variant tiers per model base. Flash offers Low/Medium/High; Pro has no
-// Medium variant.
-const FLASH_EFFORT_TIERS = ['low', 'medium', 'high'];
-const PRO_EFFORT_TIERS = ['low', 'high'];
+// agy variant tiers shared by every catalog model: each is listed as
+// '<base> (Low)', '(Medium)' and '(High)'.
+const EFFORT_TIERS = ['low', 'medium', 'high'];
 
 /**
  * Map a reasoning_effort value to the agy parenthesized variant suffix.
  * Unset effort selects High, agy's own default.
- * @param {string} base - agy model base ('Gemini 3.8 Flash' / 'Gemini 3.1 Pro')
  * @param {string} [reasoningEffort]
  * @returns {string} e.g. '(Low)', '(Medium)', '(High)'
  */
-function effortSuffix(base, reasoningEffort) {
+function effortSuffix(reasoningEffort) {
   if (!reasoningEffort) {
     return '(High)';
   }
-  const tiers = /pro/i.test(base) ? PRO_EFFORT_TIERS : FLASH_EFFORT_TIERS;
-  const tier = clampReasoningEffort(reasoningEffort.toLowerCase(), tiers);
+  const tier = clampReasoningEffort(reasoningEffort.toLowerCase(), EFFORT_TIERS);
   return `(${tier[0].toUpperCase()}${tier.slice(1)})`;
 }
 
@@ -226,8 +221,7 @@ export function resolveAgyModel(model, reasoningEffort) {
       ErrorCodes.MODEL_NOT_FOUND,
     );
   }
-  const base = entry.agyModelBase;
-  return `${base} ${effortSuffix(base, reasoningEffort)}`;
+  return `${entry.agyModelBase} ${effortSuffix(reasoningEffort)}`;
 }
 
 /**
@@ -662,6 +656,14 @@ async function executeAgy(messages, options) {
   const cleaned = cleanAgyOutput(output);
 
   if (exitCode !== 0) {
+    // agy's model list is per-plan (Gemini 4 Argon is Ultra-only), so a
+    // catalog model can still be missing for the signed-in account.
+    if (/not recognized as a known model/i.test(cleaned)) {
+      throw new GeminiCliProviderError(
+        `Antigravity CLI (agy) does not offer "${agyModel}" to the signed-in account (Gemini 4 Argon requires a Google AI Ultra plan). Use gemini:flash, or set AGY_DEFAULT_MODEL to change the default. agy output: ${cleaned.slice(0, 800)}`,
+        ErrorCodes.MODEL_NOT_FOUND,
+      );
+    }
     const tail = cleaned.slice(-500);
     throw new GeminiCliProviderError(
       `Antigravity CLI (agy) exited with code ${exitCode}. ${tail ? `Output tail: ${tail}` : 'No output.'} If this persists, run \`agy\` interactively once to authenticate (Antigravity Google OAuth).`,

package/src/providers/google.js

@@ -98,6 +98,30 @@ const SUPPORTED_MODELS = {
       'gemini3.1',
       'gemini-3.1-pro',
       '3.1-pro',
+    ],
+  },
+  'gemini-4-argon': {
+    modelName: 'gemini-4-argon',
+    friendlyName: 'Gemini (4 Argon)',
+    contextWindow: 1048576, // 1M tokens
+    maxOutputTokens: 65536,
+    supportsStreaming: true,
+    supportsImages: true,
+    supportsThinking: true,
+    supportsWebSearch: true,
+    thinkingMode: 'level',
+    thinkingLevels: ['low', 'medium', 'high'],
+    timeout: 900000,
+    description:
+      'Gemini 4 Argon - Flagship reasoning model for complex software engineering and agentic work (1M context)',
+    aliases: [
+      'argon',
+      'gemini-argon',
+      'gemini argon',
+      'gemini-4',
+      'gemini4',
+      'gemini 4 argon',
+      '4-argon',
       'gemini pro',
       'gemini-pro',
       'pro',
@@ -434,7 +458,7 @@ async function retryWithBackoff(fn, maxRetries = 4) {
 /**
  * Main Google provider implementation
  */
-const DEFAULT_MODEL = 'gemini-3.1-pro-preview';
+const DEFAULT_MODEL = 'gemini-4-argon';
 
 export const googleProvider = {
   defaultModel: DEFAULT_MODEL,