converse-mcp-server 4.2.1 → 4.4.0

package/.env.example

@@ -91,11 +91,11 @@ TYPESAFE_API_KEY=your_typesafe_api_key_here
 # The model a bare provider name ("codex", "openai", ...) and "auto" use.
 # Each must be a model ID or alias from that provider's catalog; startup fails
 # with "did you mean" suggestions otherwise. Per request, use "provider:model".
-# CODEX_DEFAULT_MODEL=gpt-6-astra     # 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)
+# 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
-# COPILOT_DEFAULT_MODEL=gpt-6-sol     # COPILOT_MODEL is the legacy name
-# OPENAI_DEFAULT_MODEL=gpt-6-sol
+# 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
 # XAI_DEFAULT_MODEL=grok-4.5
 # ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5

package/README.md

@@ -230,7 +230,8 @@ SUMMARIZATION_MODEL=gpt-5-nano        # Default: gpt-5-nano
 
 ### OpenAI Models
 
-- **gpt-6-sol** (default; aliases: `gpt-6`, `gpt-5`, `sol`): Default GPT-6 (1M context, 128K output) - Complex coding and agentic workflows; effort `none`–`max`
+- **gpt-6.1-sol** (default; aliases: `gpt-6`, `gpt-6.1`, `gpt-5`, `sol`): GPT-6.1 Sol (1M context, 128K output) - Near-Astra coding, computer use, and professional work at a fifth of the Astra price; effort `low`–`max`
+- **gpt-6-sol**: Previous GPT-6 Sol (1M context, 128K output), reachable by versioned name only; effort `none`–`max`
 - **gpt-6-luna** (alias: `luna`): Most efficient GPT-6 (1M context, 128K output) - Focused, high-volume tasks; effort `none`–`max`
 - **gpt-6-astra** (alias: `astra`): Frontier GPT-6 flagship (1M context, 128K output) - Hardest end-to-end work; effort `low`–`max` (EXPENSIVE: 5x Sol)
 - **gpt-5.6-sol** (alias: `gpt-5.6`): Previous flagship GPT-5.6 (1M context, 128K output)
@@ -274,7 +275,8 @@ SUMMARIZATION_MODEL=gpt-5-nano        # Default: gpt-5-nano
 - **claude-opus-5** (alias: `opus-5`): Previous Opus generation (1M context, 128K output)
 - **claude-opus-4-8** / **claude-opus-4-7** / **claude-opus-4-6**: Earlier Opus generations with adaptive thinking (200K context, 1M via beta, 128K output)
 - **claude-opus-4-5** / **claude-opus-4-1**: Legacy Opus models with extended thinking (64K / 32K output)
-- **claude-sonnet-4-6** (alias: `sonnet`): Best combination of speed and intelligence with adaptive thinking (64K output)
+- **claude-sonnet-5-5** (aliases: `sonnet`, `sonnet-5.5`): Current Sonnet with adaptive thinking and effort (1M context, 128K output)
+- **claude-sonnet-4-6** (alias: `sonnet-4.6`): Previous Sonnet generation with adaptive thinking (64K output)
 - **claude-haiku-4-5** (alias: `haiku`): Fast and intelligent for simple queries (64K output)
 
 ### Mistral Models
@@ -306,9 +308,9 @@ Any other model works via its full `provider/model` slug or the `openrouter:` na
 
 OpenAI Codex agentic coding assistant. `codex` uses its default model (GPT-6 Astra, or `CODEX_DEFAULT_MODEL`); `codex:<model>` picks one (e.g. `codex:luna`, `codex:astra`, `codex:gpt-5.6-terra`):
 
-- **gpt-6-sol** (default; aliases: `sol`, `gpt-6`), **gpt-6-luna** (`luna`), **gpt-6-astra** (`astra`)
+- **gpt-6.1-sol** (`sol`, `gpt-6`), **gpt-6-sol**, **gpt-6-luna** (`luna`), **gpt-6-astra** (`astra`)
 - **gpt-5.6-sol** (`gpt-5.6`), **gpt-5.6-terra** (`terra`), **gpt-5.6-luna**, **gpt-5.5**, **gpt-5.3-codex-spark** (`spark`)
-  - `reasoning_effort` maps onto the tiers the chosen backend accepts (Sol/Luna: `none` through `max`; GPT-6 Astra: `low` through `max`, no `none`)
+  - `reasoning_effort` maps onto the tiers the chosen backend accepts (versioned GPT-6 Sol, Luna, and GPT-5.6: `none` through `max`; GPT-6.1 Sol and GPT-6 Astra: `low` through `max`, no `none`)
   - Thread-based sessions with persistent context
   - Direct filesystem access from working directory
   - Typical response time: 6-20 seconds (longer for complex tasks)
@@ -321,15 +323,16 @@ Claude via the Claude Agent SDK. `claude` uses its default model (Opus 5.5, or `
 
 - **claude-opus-5-5** (default; aliases: `opus`, `claude-opus`, `opus-5.5`), **claude-opus-5** (`opus-5`)
 - **claude-fable-5-1** (aliases: `fable`, `claude-fable`, `fable-5.1`), **claude-fable-5** (`fable-5`)
+- **claude-sonnet-5-5** (aliases: `sonnet`, `claude-sonnet`, `sonnet-5.5`)
 - Uses Claude Code CLI authentication (`claude login`) - no API key needed
 - Direct filesystem access from working directory
 
 ### GitHub Copilot SDK Models
 
-Reach these only with the `copilot:` namespace (e.g. `copilot:gpt-6-sol`) — Copilot never serves bare model names. `copilot` alone uses GPT-6 Sol, or `COPILOT_DEFAULT_MODEL`. Uses your GitHub Copilot subscription (`gh auth login`) - no API key needed:
+Reach these only with the `copilot:` namespace (e.g. `copilot:gpt-6.1-sol`) — Copilot never serves bare model names. `copilot` alone uses GPT-6.1 Sol, or `COPILOT_DEFAULT_MODEL`. Uses your GitHub Copilot subscription (`gh auth login`) - no API key needed:
 
-- **OpenAI**: `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `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` (alias: `fable`), `claude-sonnet-5` (alias: `sonnet`), `claude-opus-5`, `claude-opus-4.8`
+- **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` (alias: `fable`), `claude-sonnet-5.5` (alias: `sonnet`), `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`)
 
 ## 📚 Help & Documentation
@@ -391,8 +394,8 @@ CODEX_APPROVAL_POLICY=never                  # never (default), untrusted, on-fa
 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)
-COPILOT_DEFAULT_MODEL=gpt-6-sol              # COPILOT_MODEL still works as a fallback
-OPENAI_DEFAULT_MODEL=gpt-6-sol
+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
 XAI_DEFAULT_MODEL=grok-4.5
 ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5
@@ -462,14 +465,14 @@ Every entry in `models` takes one of four forms:
 "codex"; // -> Codex (GPT-6 Astra)
 "claude"; // -> Claude Agent SDK (Claude Opus 5.5)
 "gemini"; // -> Antigravity CLI (Gemini 3.8 Flash); `agy` works too
-"openai"; // -> OpenAI API (GPT-6 Sol)
+"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)
 "google:gemini-3.1-pro-preview"; // -> Google API
-"copilot:sonnet"; // -> GitHub Copilot (Claude Sonnet 5)
+"copilot:sonnet"; // -> GitHub Copilot (Claude Sonnet 5.5)
 "openrouter:z-ai/glm-5.2:online"; // -> OpenRouter with web search opt-in
 
 // A bare model ID or alias — the first configured provider that offers it
@@ -495,8 +498,8 @@ Provider priority order (subscription-based local providers first, then API-key
 1. Codex (`codex` → GPT-6 Astra)
 2. Gemini via Antigravity CLI (`gemini` / `agy` → Gemini 3.8 Flash)
 3. Claude Agent SDK (`claude` → Claude Opus 5.5)
-4. Copilot (`copilot` → GPT-6 Sol; `auto` only, never bare names)
-5. OpenAI (`openai` → GPT-6 Sol)
+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)
 7. XAI (`xai` → Grok 4.5)
 8. Anthropic (`anthropic` → Claude Opus 5.5)

package/docs/API.md

@@ -480,7 +480,8 @@ Provide models as plain name strings in the `models` array. Each entry is `auto`
 
 | Model | Aliases | Context | Output | Notes |
 |-------|---------|---------|--------|-------|
-| `gpt-6-sol` | `gpt-6`, `gpt-5`, `sol` | 1M | 128K | Default OpenAI model; effort `none`–`max` |
+| `gpt-6.1-sol` | `gpt-6`, `gpt-6.1`, `gpt-5`, `sol` | 1M | 128K | Default OpenAI model; near-Astra coding, computer use, and professional work at a fifth of the Astra price; effort `low`–`max` |
+| `gpt-6-sol` | — | 1M | 128K | Previous GPT-6 Sol; reachable by versioned name only; effort `none`–`max` |
 | `gpt-6-luna` | `luna` | 1M | 128K | Most efficient GPT-6; effort `none`–`max` |
 | `gpt-6-astra` | `astra` | 1M | 128K | Frontier flagship (expensive); effort `low`–`max`, no `none` |
 | `gpt-5.6-sol` | `gpt-5.6` | 1M | 128K | Previous flagship |
@@ -524,10 +525,11 @@ Provide models as plain name strings in the `models` array. Each entry is `auto`
 | `claude-opus-5` | `opus-5` | 1M | 128K | Previous Opus, adaptive thinking + effort, compaction |
 | `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6` | `opus-4.8`, `opus-4.7`, `opus-4.6` | 200K (1M beta) | 128K | Previous Opus generations |
 | `claude-opus-4-5-20251101`, `claude-opus-4-1-20250805` | `opus-4.5`, `opus-4.1` | 200K | 64K / 32K | Earlier Opus tiers |
-| `claude-sonnet-4-6` | `sonnet`, `sonnet-4.6` | 200K (1M beta) | 64K | Best speed/intelligence balance, adaptive thinking |
+| `claude-sonnet-5-5` | `sonnet`, `sonnet-5.5`, `claude-sonnet` | 1M | 128K | Current Sonnet, adaptive thinking + effort, compaction |
+| `claude-sonnet-4-6` | `sonnet-4.6` | 200K (1M beta) | 64K | Previous Sonnet, adaptive thinking |
 | `claude-haiku-4-5-20251001` | `haiku`, `haiku-4.5` | 200K | 64K | Fast and intelligent |
 
-Models with adaptive thinking control depth via `reasoning_effort`, which is passed by name to Anthropic's `effort` parameter and clamped to what each model accepts: Opus 5.5, Fable 5, Opus 5, Opus 4.8, and Opus 4.7 take `low`–`max`; Opus 4.6 and Sonnet 4.6 lack `xhigh` (it becomes `max`); Opus 4.5 tops out at `high`. `none` and `minimal` become `low` everywhere. System prompts are automatically cached for 1 hour; cache stats appear in response metadata as `cache_creation_input_tokens` / `cache_read_input_tokens`.
+Models with adaptive thinking control depth via `reasoning_effort`, which is passed by name to Anthropic's `effort` parameter and clamped to what each model accepts: Opus 5.5, Sonnet 5.5, Fable 5, Opus 5, Opus 4.8, and Opus 4.7 take `low`–`max`; Opus 4.6 and Sonnet 4.6 lack `xhigh` (it becomes `max`); Opus 4.5 tops out at `high`. `none` and `minimal` become `low` everywhere. System prompts are automatically cached for 1 hour; cache stats appear in response metadata as `cache_creation_input_tokens` / `cache_read_input_tokens`.
 
 ### Mistral Models
 
@@ -567,20 +569,20 @@ Any other model works via its full `provider/model` slug (e.g. `anthropic/claude
 **Codex** is an agentic coding assistant with direct filesystem access:
 
 - **Model**: `codex` (underlying model: GPT-6 Astra by default, or `CODEX_DEFAULT_MODEL`)
-- **Backend selection**: `codex:<model>` per request (e.g. `codex:luna`, `codex:astra`, `codex:gpt-5.6-terra`) from the Codex catalog: `gpt-6-sol` (`sol`, `gpt-6`), `gpt-6-luna` (`luna`), `gpt-6-astra` (`astra`), `gpt-5.6-sol` (`gpt-5.6`), `gpt-5.6-terra` (`terra`), `gpt-5.6-luna`, `gpt-5.5`, `gpt-5.3-codex-spark` (`spark`). Other names are rejected with suggestions. Bare IDs from this list (e.g. `gpt-6-astra`) go to Codex first, then the OpenAI API.
+- **Backend selection**: `codex:<model>` per request (e.g. `codex:luna`, `codex:astra`, `codex:gpt-5.6-terra`) from the Codex catalog: `gpt-6.1-sol` (`sol`, `gpt-6`), `gpt-6-sol`, `gpt-6-luna` (`luna`), `gpt-6-astra` (`astra`), `gpt-5.6-sol` (`gpt-5.6`), `gpt-5.6-terra` (`terra`), `gpt-5.6-luna`, `gpt-5.5`, `gpt-5.3-codex-spark` (`spark`). Other names are rejected with suggestions. Bare IDs from this list (e.g. `gpt-6-astra`) go to Codex first, then the OpenAI API.
 - **Availability**: the Codex SDK is installed and `~/.codex/auth.json` exists (`$CODEX_HOME/auth.json` when set) or `CODEX_API_KEY` is set
 - **Thread-based sessions**: persistent conversation history via `continuation_id` in `chat` mode
 - **Direct file access**: reads files from the working directory (paths relative to `CLIENT_CWD`)
 - **Response times**: 6-20 seconds typical (complex tasks may take minutes)
 - **Authentication**: ChatGPT login OR `CODEX_API_KEY` (NOT `OPENAI_API_KEY`)
-- `reasoning_effort` is clamped onto the tiers the chosen backend accepts (GPT-6 Sol/Luna and GPT-5.6: `none`–`max`; GPT-6 Astra: `low`–`max`, no `none`); web search is not applicable — Codex manages its own execution
+- `reasoning_effort` is clamped onto the tiers the chosen backend accepts (GPT-6 Sol/Luna and GPT-5.6: `none`–`max`; GPT-6 Astra and GPT-6.1 Sol: `low`–`max`, no `none`); web search is not applicable — Codex manages its own execution
 
 ### Claude Agent SDK (subscription)
 
 **Claude** is available through the Claude Agent SDK, using Claude Code CLI authentication instead of an API key:
 
 - **Model**: `claude` (namespaces: `claude`, `claude-code`, `claude-sdk`) — defaults to Claude Opus 5.5 (`claude-opus-5-5`), or `CLAUDE_DEFAULT_MODEL`
-- **Model selection**: `claude-opus-5-5` (`opus`, `claude-opus`, `opus-5.5`), `claude-opus-5` (`opus-5`), `claude-fable-5-1` (`fable`, `claude-fable`, `fable-5.1`), `claude-fable-5` (`fable-5`), e.g. `claude:opus`, `claude:fable`. Other names are rejected with suggestions.
+- **Model selection**: `claude-opus-5-5` (`opus`, `claude-opus`, `opus-5.5`), `claude-opus-5` (`opus-5`), `claude-fable-5-1` (`fable`, `claude-fable`, `fable-5.1`), `claude-fable-5` (`fable-5`), `claude-sonnet-5-5` (`sonnet`, `claude-sonnet`, `sonnet-5.5`), e.g. `claude:opus`, `claude:fable`, `claude:sonnet`. Other names are rejected with suggestions.
 - **Authentication**: `claude login` — no `ANTHROPIC_API_KEY` needed
 - **Availability**: the Claude Agent SDK is installed and `~/.claude/.credentials.json` exists (`$CLAUDE_CONFIG_DIR` when set), or `CLAUDE_CODE_OAUTH_TOKEN`/`ANTHROPIC_API_KEY` is in the environment; on macOS the Keychain login is assumed. An expired login is caught at call time and bare-name/`auto` routing fails over.
 - **Permissions**: runs with `bypassPermissions`
@@ -618,10 +620,10 @@ agy
 
 ### GitHub Copilot SDK (subscription)
 
-Reach these only with the `copilot:` namespace (also `github-copilot:`, `copilot-sdk:`; e.g. `copilot:gpt-6-sol`) — Copilot never serves bare model names. `copilot` alone uses GPT-6 Sol, or `COPILOT_DEFAULT_MODEL`. Available when the Copilot SDK is installed; uses your GitHub Copilot subscription (`gh auth login`) — no API key needed:
+Reach these only with the `copilot:` namespace (also `github-copilot:`, `copilot-sdk:`; e.g. `copilot:gpt-6.1-sol`) — Copilot never serves bare model names. `copilot` alone uses GPT-6.1 Sol, or `COPILOT_DEFAULT_MODEL`. Available when the Copilot SDK is installed; uses your GitHub Copilot subscription (`gh auth login`) — no API key needed:
 
-- **OpenAI**: `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `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` (alias: `fable`), `claude-sonnet-5` (alias: `sonnet`), `claude-opus-5`, `claude-opus-4.8`
+- **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` (alias: `fable`), `claude-sonnet-5.5` (alias: `sonnet`), `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`)
 - Any other `copilot:<id>` is rejected with suggestions
 
@@ -638,7 +640,7 @@ Every entry in `models` takes one of four forms:
 
 ```text
 "auto"                     // First available provider (chat); first 3 (consensus)
-"gpt-6"                    // Codex (-> gpt-6-sol), else OpenAI API
+"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
@@ -655,7 +657,7 @@ Every entry in `models` takes one of four forms:
 "claude:fable"             // Claude Agent SDK (Claude Fable 5.1)
 "codex:luna"               // Codex (GPT-6 Luna)
 "gemini"                   // Antigravity CLI (Gemini 3.8 Flash)
-"copilot:gpt-6-sol"        // GitHub Copilot SDK
+"copilot:gpt-6.1-sol"      // GitHub Copilot SDK
 ```
 
 **Local agent permissions:** bare names and `auto` reach the local agent providers whenever they are set up. The Antigravity CLI auto-approves every tool request and the Claude Agent SDK runs with `bypassPermissions`, so a read-only prompt is not an enforced boundary there. Name the API provider (`google:pro`, `anthropic:opus`, `openai:gpt-6-astra`) to keep a request on a plain API.
@@ -704,8 +706,8 @@ Each provider's default model (used for its bare provider name and for `auto`) c
 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)
-COPILOT_DEFAULT_MODEL=gpt-6-sol              # COPILOT_MODEL is honored as a legacy fallback
-OPENAI_DEFAULT_MODEL=gpt-6-sol
+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
 XAI_DEFAULT_MODEL=grok-4.5
 ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5

package/docs/PROVIDERS.md

@@ -9,7 +9,8 @@ This guide documents all supported AI providers in the Converse MCP Server and t
 - **Get Key**: [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
 - **Environment Variable**: `OPENAI_API_KEY`
 - **Supported Models**:
-  - `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `sol`) - Default GPT-6 and the default OpenAI model (1M context, 128K output; effort `none`–`max`)
+  - `gpt-6.1-sol` (aliases: `gpt-6`, `gpt-6.1`, `gpt-5`, `sol`) - Default OpenAI model (1M context, 128K output); near-Astra coding, computer use, and professional work at a fifth of the Astra price; effort `low`–`max`
+  - `gpt-6-sol` - Previous GPT-6 Sol (1M context, 128K output), reachable by versioned name only; effort `none`–`max`
   - `gpt-6-luna` (alias: `luna`) - Most efficient GPT-6 for focused, high-volume tasks (1M context, 128K output; effort `none`–`max`)
   - `gpt-6-astra` (alias: `astra`) - Frontier GPT-6 flagship, 5x the Sol price (1M context, 128K output; effort `low`–`max`)
   - `gpt-5.6-sol` (alias: `gpt-5.6`) - Previous flagship GPT-5.6
@@ -53,7 +54,8 @@ This guide documents all supported AI providers in the Converse MCP Server and t
   - `claude-opus-5` (alias `opus-5`) - Previous Opus generation (1M context, 128K output)
   - `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6` - Earlier Opus generations with adaptive thinking (128K output)
   - `claude-opus-4-5-20251101`, `claude-opus-4-1-20250805` - Legacy Opus models (64K / 32K output)
-  - `claude-sonnet-4-6` (alias `sonnet`) - Best combination of speed and intelligence with adaptive thinking (64K output)
+  - `claude-sonnet-5-5` (aliases `sonnet`, `sonnet-5.5`, `claude-sonnet`) - Current Sonnet: speed and capability for everyday coding and agentic work; adaptive thinking, effort `low`–`max` (1M context, 128K output)
+  - `claude-sonnet-4-6` (alias `sonnet-4.6`) - Previous Sonnet generation with adaptive thinking (64K output)
   - `claude-sonnet-4-5-20250929` - Legacy Sonnet (64K output)
   - `claude-haiku-4-5-20251001` (alias `haiku`) - Fast and intelligent with extended thinking (64K output)
 
@@ -110,11 +112,11 @@ This guide documents all supported AI providers in the Converse MCP Server and t
 - **Supported Models**:
   - `codex` - OpenAI Codex agentic coding assistant (GPT-6 Astra by default)
   - `codex:<model>` - Same, with an explicit backend from the Codex catalog:
-    - `gpt-6-sol` (aliases: `sol`, `gpt-6`), `gpt-6-luna` (`luna`), `gpt-6-astra` (`astra`)
+    - `gpt-6.1-sol` (`sol`, `gpt-6`), `gpt-6-sol`, `gpt-6-luna` (`luna`), `gpt-6-astra` (`astra`)
     - `gpt-5.6-sol` (`gpt-5.6`), `gpt-5.6-terra` (`terra`), `gpt-5.6-luna`, `gpt-5.5`, `gpt-5.3-codex-spark` (`spark`)
   - Names outside this catalog are rejected with suggestions
   - These IDs are also bare names: `gpt-6-astra`, `luna` or `terra` alone go to Codex first and fail over to the OpenAI API (see [Model Routing Logic](#model-routing-logic))
-  - `reasoning_effort` is clamped onto what the backend accepts (Sol/Luna: `none`–`max`; GPT-6 Astra: `low`–`max`, no `none`)
+  - `reasoning_effort` is clamped onto what the backend accepts (versioned GPT-6 Sol, Luna, and GPT-5.6: `none`–`max`; GPT-6.1 Sol and GPT-6 Astra: `low`–`max`, no `none`)
   - Thread-based sessions with persistent context
   - Direct filesystem access from working directory
   - Typical response time: 6-20 seconds (longer for complex tasks)
@@ -215,7 +217,8 @@ agy
   - `claude-opus-5` (alias: `opus-5`) - Claude Opus 5
   - `claude-fable-5-1` (aliases: `fable`, `claude-fable`, `fable-5.1`) - Claude Fable 5.1 (`claude:fable`)
   - `claude-fable-5` (alias: `fable-5`) - Claude Fable 5.0
-  - Names outside this catalog are rejected with suggestions (e.g. `claude:sonnet` suggests `copilot:sonnet` and `anthropic:sonnet`)
+  - `claude-sonnet-5-5` (aliases: `sonnet`, `claude-sonnet`, `sonnet-5.5`) - Claude Sonnet 5.5 (`claude:sonnet`)
+  - Names outside this catalog are rejected with suggestions (e.g. `claude:haiku` suggests `anthropic:haiku`)
 
 **Key Features:**
 - **Subscription Access**: Uses your Claude subscription instead of API credits
@@ -228,7 +231,7 @@ agy
 **Differences from Anthropic API Provider:**
 - **Authentication**: Claude Code login vs `ANTHROPIC_API_KEY`
 - **Billing**: Claude subscription vs pay-per-use API
-- **Model Routing**: `claude` and `claude:<model>` → SDK provider; `anthropic:<model>` → API provider; bare names both serve as the same model (`opus`, `claude-opus-5-5`, `claude-opus-5`, `claude-fable-5`) → SDK first, then the API on authentication/availability failure; bare names only the API serves (e.g., `sonnet`, `haiku`) → API provider. Bare `fable` is Fable 5.1 on the SDK but Fable 5 on the API, so it does not fail over between them.
+- **Model Routing**: `claude` and `claude:<model>` → SDK provider; `anthropic:<model>` → API provider; bare names both serve as the same model (`opus`, `sonnet`, `claude-opus-5-5`, `claude-opus-5`, `claude-sonnet-5-5`, `claude-fable-5`) → SDK first, then the API on authentication/availability failure; bare names only the API serves (e.g., `haiku`, `sonnet-4.6`) → API provider. Bare `fable` is Fable 5.1 on the SDK but Fable 5 on the API, so it does not fail over between them.
 - **Permissions**: The SDK runs with `bypassPermissions`, and bare names and `auto` reach it whenever it is available. Use `anthropic:<model>` to keep a request on the plain API.
 
 ### GitHub Copilot SDK
@@ -236,11 +239,11 @@ agy
 - **Setup Required**: Authenticate the GitHub CLI and ensure your account has an active Copilot subscription
 - **Availability**: The Copilot SDK (`@github/copilot-sdk`) is installed
 - **Environment Variables**:
-  - `COPILOT_DEFAULT_MODEL` - Model used for bare `copilot` and `auto` (default: `gpt-6-sol`). The legacy name `COPILOT_MODEL` is honored when `COPILOT_DEFAULT_MODEL` is unset.
-- **Supported Models** (namespace-only: reach them with `copilot:`, `github-copilot:` or `copilot-sdk:`, e.g. `copilot:gpt-6-sol`; Copilot never serves bare model names):
-  - `copilot` - GPT-6 Sol, or `COPILOT_DEFAULT_MODEL`
-  - OpenAI: `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `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` (alias: `fable`), `claude-sonnet-5` (alias: `sonnet`), `claude-opus-5`, `claude-opus-4.8`
+  - `COPILOT_DEFAULT_MODEL` - Model used for bare `copilot` and `auto` (default: `gpt-6.1-sol`). The legacy name `COPILOT_MODEL` is honored when `COPILOT_DEFAULT_MODEL` is unset.
+- **Supported Models** (namespace-only: reach them with `copilot:`, `github-copilot:` or `copilot-sdk:`, e.g. `copilot:gpt-6.1-sol`; Copilot never serves bare model names):
+  - `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` (alias: `fable`), `claude-sonnet-5.5` (alias: `sonnet`), `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`)
 - **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.
@@ -281,8 +284,8 @@ Each provider has a `<PROVIDER>_DEFAULT_MODEL` variable that sets the model used
 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)
-COPILOT_DEFAULT_MODEL=gpt-6-sol              # COPILOT_MODEL is honored as a legacy fallback
-OPENAI_DEFAULT_MODEL=gpt-6-sol
+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
 XAI_DEFAULT_MODEL=grok-4.5
 ANTHROPIC_DEFAULT_MODEL=claude-opus-5-5
@@ -333,7 +336,7 @@ All providers support streaming responses for real-time output.
 - **Google**:
   - Gemini 3.0 Pro: Thinking levels (low/high) via `reasoning_effort` - always enabled
   - Gemini 2.5 Pro/Flash: Thinking budget (token-based) via `reasoning_effort`
-- **Anthropic**: Claude Fable 5, Opus 4.6+, and Sonnet 4.6 use adaptive thinking (depth controlled by `reasoning_effort` via Anthropic's `effort` parameter); older Claude 4 models use budget-based extended thinking
+- **Anthropic**: Claude Fable 5, Opus 4.6+, and Sonnet 4.6+ use adaptive thinking (depth controlled by `reasoning_effort` via Anthropic's `effort` parameter); older Claude 4 models use budget-based extended thinking
 - **X.AI**: Grok 4.5 maps `reasoning_effort` to `low`/`medium`/`high` and always reasons (cannot be disabled)
 - **Mistral**: `mistral-medium-3-5` and `mistral-small-2603` map `reasoning_effort` to `high` (enabled) or `none` (disabled); `mistral-large-2512` has no adjustable reasoning
 - **DeepSeek**: V4 models use thinking mode via `reasoning_effort` (`none` disables; enabled levels use `high`, `max` uses `max`)
@@ -379,12 +382,12 @@ Routing is derived entirely from each provider's model list (canonical IDs plus
 Examples:
 
 ```text
-"gpt-6"                    // Codex (gpt-6-sol), else OpenAI API
+"gpt-6"                    // Codex (gpt-6.1-sol), else OpenAI API
 "openai:gpt-6"             // OpenAI API only
 "fable"                    // Claude Agent SDK (claude-fable-5-1) when set up, otherwise Anthropic API (claude-fable-5)
 "opus"                     // Claude Agent SDK (claude-opus-5-5), else Anthropic API
 "anthropic:opus"           // Anthropic API only
-"sonnet"                   // Anthropic API (claude-sonnet-4-6)
+"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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "converse-mcp-server",
-  "version": "4.2.1",
+  "version": "4.4.0",
   "description": "Converse MCP Server - Converse with other LLMs with chat and consensus tools",
   "type": "module",
   "main": "src/index.js",
@@ -93,16 +93,16 @@
     ".env.example"
   ],
   "dependencies": {
-    "@anthropic-ai/claude-agent-sdk": "^0.3.282",
-    "@anthropic-ai/sdk": "^0.128.0",
-    "@github/copilot-sdk": "^1.0.14",
+    "@anthropic-ai/claude-agent-sdk": "^0.3.284",
+    "@anthropic-ai/sdk": "^0.129.0",
+    "@github/copilot-sdk": "^1.0.15",
     "@google/genai": "^2.24.0",
     "@lydell/node-pty": "1.2.0-beta.15",
     "@mistralai/mistralai": "^2.7.0",
-    "@modelcontextprotocol/sdk": "^1.30.1",
-    "@openai/codex-sdk": "^0.157.0",
+    "@modelcontextprotocol/sdk": "^1.31.0",
+    "@openai/codex-sdk": "^0.159.0",
     "cors": "^2.8.6",
-    "dotenv": "^18.0.3",
+    "dotenv": "^18.0.4",
     "express": "^5.2.1",
     "lru-cache": "^11.5.3",
     "nanoid": "^6.0.1",
@@ -111,10 +111,10 @@
     "vite": "^8.3.1"
   },
   "devDependencies": {
-    "@vitest/coverage-v8": "^5.0.1",
+    "@vitest/coverage-v8": "^5.0.2",
     "cross-env": "^10.1.0",
     "eslint": "^10.11.0",
     "rimraf": "^6.1.3",
-    "vitest": "^5.0.1"
+    "vitest": "^5.0.2"
   }
 }

package/src/providers/anthropic.js

@@ -37,6 +37,7 @@ const SUPPORTED_MODELS = {
     effortTiers: EFFORT_TIERS_FULL,
     // Absent from Anthropic's compaction compatibility list, unlike Opus 5
     supportsCompaction: false,
+    supportsDefaultFallback: true,
     description:
       'Claude Opus 5.5 - Flagship Opus for complex agentic coding and deep reasoning; matches Fable 5.1 on most work at Opus pricing',
     aliases: [
@@ -93,6 +94,7 @@ const SUPPORTED_MODELS = {
     effortGA: true,
     effortTiers: EFFORT_TIERS_FULL,
     supportsCompaction: true,
+    supportsDefaultFallback: true,
     description:
       'Claude Opus 5 - Previous Opus generation for complex agentic coding and deep reasoning',
     aliases: [
@@ -103,6 +105,37 @@ const SUPPORTED_MODELS = {
       'claude-opus-5.0',
     ],
   },
+  'claude-sonnet-5-5': {
+    modelName: 'claude-sonnet-5-5',
+    friendlyName: 'Claude Sonnet 5.5',
+    contextWindow: 1000000, // 1M context by default - no beta header required
+    maxOutputTokens: 128000,
+    supportsStreaming: true,
+    supportsImages: true,
+    supportsWebSearch: false,
+    supportsThinking: true,
+    supportsAdaptiveThinking: true, // {type: "disabled"} is rejected; adaptive is the only on-mode
+    timeout: 1800000,
+    supportsEffort: true,
+    effortGA: true,
+    effortTiers: EFFORT_TIERS_FULL,
+    supportsCompaction: true,
+    supportsDefaultFallback: true,
+    description:
+      'Claude Sonnet 5.5 - Current Sonnet: speed and capability for everyday coding and agentic work',
+    aliases: [
+      'claude-sonnet-5-5',
+      'claude-sonnet-5.5',
+      'claude-5.5-sonnet',
+      'claude-5-5-sonnet',
+      'sonnet-5.5',
+      'sonnet-5-5',
+      'sonnet5.5',
+      'sonnet5-5',
+      'sonnet',
+      'claude-sonnet',
+    ],
+  },
   'claude-opus-4-8': {
     modelName: 'claude-opus-4-8',
     friendlyName: 'Claude Opus 4.8',
@@ -270,7 +303,7 @@ const SUPPORTED_MODELS = {
     supports1MContext: true, // Beta 1M context support
     supportsCompaction: true, // Beta server-side context compaction
     description:
-      'Claude Sonnet 4.6 - Best combination of speed and intelligence with adaptive thinking',
+      'Claude Sonnet 4.6 - Previous Sonnet generation with adaptive thinking',
     aliases: [
       'claude-sonnet-4-6',
       'claude-4.6-sonnet',
@@ -280,8 +313,6 @@ const SUPPORTED_MODELS = {
       'sonnet4.6',
       'sonnet4-6',
       'claude-sonnet-4.6',
-      'sonnet',
-      'claude-sonnet',
     ],
   },
   'claude-sonnet-4-5-20250929': {
@@ -369,6 +400,24 @@ class AnthropicProviderError extends ProviderError {
   }
 }
 
+/**
+ * A refusal arrives as a successful response whose text is empty or cut off
+ * mid-answer, so it must not be passed on as a (partial) answer. The category
+ * tells the caller whether rephrasing or another model is the way forward.
+ */
+function refusalError(stopDetails) {
+  const category = stopDetails?.category
+    ? ` (category: ${stopDetails.category})`
+    : '';
+  const explanation = stopDetails?.explanation
+    ? `: ${stopDetails.explanation}`
+    : '';
+  return new AnthropicProviderError(
+    `Anthropic declined the request${category}${explanation}`,
+    ErrorCodes.REFUSED,
+  );
+}
+
 /**
  * Resolve model name to canonical form, including aliases
  */
@@ -661,6 +710,13 @@ export const anthropicProvider = {
       );
     }
 
+    // A safety-classifier decline is retried server-side on the model Anthropic
+    // recommends for that refusal category; only a decline by the whole chain
+    // comes back as a refusal.
+    if (modelConfig.supportsDefaultFallback) {
+      betas.push('server-side-fallback-2026-07-01');
+    }
+
     // Add effort beta feature for models that need it (not GA yet)
     if (modelConfig.supportsEffort && reasoning_effort && !modelConfig.effortGA) {
       betas.push('effort-2025-11-24');
@@ -690,6 +746,10 @@ export const anthropicProvider = {
       requestPayload.system = systemPrompt;
     }
 
+    if (modelConfig.supportsDefaultFallback) {
+      requestPayload.fallbacks = 'default';
+    }
+
     // Set max tokens - API requires this field
     if (maxTokens) {
       requestPayload.max_tokens = Math.min(
@@ -823,6 +883,10 @@ export const anthropicProvider = {
       const responseTime = Date.now() - startTime;
       debugLog(`[Anthropic] Response received in ${responseTime}ms`);
 
+      if (response.stop_reason === 'refusal') {
+        throw refusalError(response.stop_details);
+      }
+
       // Extract response content
       let content = '';
 
@@ -965,6 +1029,7 @@ export const anthropicProvider = {
     let thinkingContent = '';
     let lastUsage = null;
     let finishReason = null;
+    let stopDetails = null;
 
     try {
       // Yield start event
@@ -1040,6 +1105,7 @@ export const anthropicProvider = {
             // Message-level updates (usage, stop_reason)
             if (event.delta?.stop_reason) {
               finishReason = event.delta.stop_reason;
+              stopDetails = event.delta.stop_details ?? null;
             }
             if (event.usage) {
               lastUsage = event.usage;
@@ -1083,6 +1149,10 @@ export const anthropicProvider = {
         }
       }
 
+      if (finishReason === 'refusal') {
+        throw refusalError(stopDetails);
+      }
+
       const responseTime = Date.now() - startTime;
       debugLog(`[Anthropic] Streaming completed in ${responseTime}ms`);
 

package/src/providers/claude.js

@@ -93,6 +93,25 @@ const SUPPORTED_MODELS = {
       'Claude Fable 5 via Agent SDK - requires claude login authentication',
     aliases: ['fable-5', 'fable5'],
   },
+  'claude-sonnet-5-5': {
+    modelName: 'claude-sonnet-5-5',
+    friendlyName: 'Claude Sonnet 5.5 (via Agent SDK)',
+    contextWindow: 1000000,
+    maxOutputTokens: 128000,
+    supportsStreaming: true,
+    supportsImages: true,
+    supportsWebSearch: false,
+    timeout: 1800000,
+    description:
+      'Claude Sonnet 5.5 via Agent SDK - requires claude login authentication',
+    aliases: [
+      'sonnet',
+      'claude-sonnet',
+      'claude-sonnet-5.5',
+      'sonnet-5-5',
+      'sonnet-5.5',
+    ],
+  },
 };
 
 /**

package/src/providers/codex.js

@@ -29,14 +29,14 @@ import {
 /**
  * Models Codex can run, keyed by the slug passed to the CLI as --model. The
  * catalog key is the canonical model ID the router resolves to. The reasoning tiers are the ones each model's API accepts, verified
- * against the API's own rejection messages (gpt-6-astra: "Supported values
- * are: 'low', 'medium', 'high', 'xhigh', and 'max'"; the Sol/Luna tiers of
- * both generations accept 'none' as well). The SDK's ModelReasoningEffort
- * type is the union across models, so the backend is the authority and
- * requests are clamped per model.
+ * against the API's own rejection messages (gpt-6-astra and gpt-6.1-sol:
+ * "Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'"; the
+ * GPT-6 and GPT-5.6 Sol/Luna tiers accept 'none' as well). The SDK's
+ * ModelReasoningEffort type is the union across models, so the backend is the
+ * authority and requests are clamped per model.
  *
  * Bare tier names (sol, luna) and the bare generation (gpt-6) point at the
- * current generation; the GPT-5.6 tiers stay reachable by full slug.
+ * current release of each tier; older releases stay reachable by full slug.
  *
  * Codex also exposes 'ultra' above 'max', but that tier turns on automatic
  * sub-agent delegation — a change in how the run executes, not just how deep
@@ -44,6 +44,7 @@ import {
  * and nothing at the tool level can select it.
  */
 const ALL_EFFORTS = ['none', 'low', 'medium', 'high', 'xhigh', 'max'];
+const NO_NONE_EFFORTS = ['low', 'medium', 'high', 'xhigh', 'max'];
 
 function codexModel(slug, friendlyName, { aliases, contextWindow = 272000, supportedEfforts = ALL_EFFORTS }) {
   return {
@@ -62,15 +63,19 @@ function codexModel(slug, friendlyName, { aliases, contextWindow = 272000, suppo
 }
 
 const SUPPORTED_MODELS = {
+  'gpt-6.1-sol': codexModel('gpt-6.1-sol', 'GPT-6.1 Sol', {
+    aliases: ['sol', 'gpt-6', 'gpt6', 'gpt-6.1', 'gpt6.1', 'gpt6.1-sol', 'gpt-6-codex'],
+    supportedEfforts: NO_NONE_EFFORTS,
+  }),
   'gpt-6-sol': codexModel('gpt-6-sol', 'GPT-6 Sol', {
-    aliases: ['sol', 'gpt-6', 'gpt6', 'gpt6-sol', 'gpt-6-codex'],
+    aliases: ['gpt6-sol'],
   }),
   'gpt-6-luna': codexModel('gpt-6-luna', 'GPT-6 Luna', {
     aliases: ['luna', 'gpt6-luna'],
   }),
   'gpt-6-astra': codexModel('gpt-6-astra', 'GPT-6 Astra', {
     aliases: ['astra', 'gpt6-astra'],
-    supportedEfforts: ['low', 'medium', 'high', 'xhigh', 'max'],
+    supportedEfforts: NO_NONE_EFFORTS,
   }),
   'gpt-5.6-sol': codexModel('gpt-5.6-sol', 'GPT-5.6 Sol', {
     aliases: ['gpt-5.6', 'gpt5.6', 'gpt5.6-sol', 'gpt-5.6-codex'],

package/src/providers/copilot.js

@@ -21,16 +21,30 @@ import { clampReasoningEffort } from '../utils/reasoningEffort.js';
 import { findCatalogEntry, findCatalogId } from '../utils/modelCatalog.js';
 import { isPackageResolvable } from '../utils/localProviderAuth.js';
 
-const DEFAULT_MODEL = 'gpt-6-sol';
+const DEFAULT_MODEL = 'gpt-6.1-sol';
 
 // Keyed by the SDK model ID, which is also the canonical ID the router
 // resolves to. Every name here is reached only through the `copilot:`
 // namespace — Copilot never serves bare model names.
 const SUPPORTED_MODELS = {
   // OpenAI models
-  // `gpt-6` / `gpt-5.6` point at that generation's Sol, matching Copilot's own
-  // bare-alias behavior; `sol`/`luna` and the legacy `gpt-5` shortcut follow
-  // the current generation. `codex` and `gpt` point at the latest GPT tier.
+  // `gpt-6` / `gpt-5.6` point at that generation's latest Sol, matching
+  // Copilot's own bare-alias behavior; `sol`/`luna` and the legacy `gpt-5`
+  // shortcut follow the current release of each tier. `codex` and `gpt` point
+  // at the latest GPT tier.
+  'gpt-6.1-sol': {
+    modelName: 'gpt-6.1-sol',
+    friendlyName: 'GPT-6.1 Sol (via Copilot)',
+    contextWindow: 1050000,
+    maxOutputTokens: 32768,
+    supportsStreaming: true,
+    supportsImages: false,
+    supportsWebSearch: false,
+    supportsReasoningEffort: true,
+    timeout: 1800000,
+    description: 'OpenAI GPT-6.1 Sol via Copilot subscription',
+    aliases: ['gpt-6', 'gpt-6.1', 'gpt-5', 'gpt', 'codex', 'sol'],
+  },
   'gpt-6-sol': {
     modelName: 'gpt-6-sol',
     friendlyName: 'GPT-6 Sol (via Copilot)',
@@ -42,7 +56,7 @@ const SUPPORTED_MODELS = {
     supportsReasoningEffort: true,
     timeout: 1800000,
     description: 'OpenAI GPT-6 Sol via Copilot subscription',
-    aliases: ['gpt-6', 'gpt-5', 'gpt', 'codex', 'sol'],
+    aliases: [],
   },
   'gpt-6-luna': {
     modelName: 'gpt-6-luna',
@@ -123,6 +137,18 @@ const SUPPORTED_MODELS = {
     description: 'Anthropic Claude Fable 5 via Copilot subscription',
     aliases: ['fable'],
   },
+  'claude-sonnet-5.5': {
+    modelName: 'claude-sonnet-5.5',
+    friendlyName: 'Claude Sonnet 5.5 (via Copilot)',
+    contextWindow: 200000,
+    maxOutputTokens: 32768,
+    supportsStreaming: true,
+    supportsImages: false,
+    supportsWebSearch: false,
+    timeout: 1800000,
+    description: 'Anthropic Claude Sonnet 5.5 via Copilot subscription',
+    aliases: ['sonnet', 'claude-sonnet-5-5'],
+  },
   'claude-sonnet-5': {
     modelName: 'claude-sonnet-5',
     friendlyName: 'Claude Sonnet 5 (via Copilot)',
@@ -133,7 +159,7 @@ const SUPPORTED_MODELS = {
     supportsWebSearch: false,
     timeout: 1800000,
     description: 'Anthropic Claude Sonnet 5 via Copilot subscription',
-    aliases: ['sonnet'],
+    aliases: [],
   },
   'claude-opus-5': {
     modelName: 'claude-opus-5',

package/src/providers/interface.js

@@ -168,6 +168,7 @@ export const ErrorCodes = {
   // Response errors
   NO_RESPONSE_CONTENT: 'NO_RESPONSE_CONTENT',
   NO_RESPONSE_CHOICE: 'NO_RESPONSE_CHOICE',
+  REFUSED: 'REFUSED',
 
   // Rate limiting and quota
   RATE_LIMIT_EXCEEDED: 'RATE_LIMIT_EXCEEDED',

package/src/providers/openai.js

@@ -11,14 +11,14 @@ import { clampReasoningEffort } from '../utils/reasoningEffort.js';
 
 // Values each family accepts for reasoning effort, per the model pages at
 // developers.openai.com/api/docs/models. The GPT-6 Sol/Luna tiers and the
-// GPT-5.6 family take the whole ladder; GPT-6 Astra has no 'none'; the
-// GPT-5.4 tier stops at 'xhigh'; the original GPT-5 minis kept 'minimal' but
-// never gained 'xhigh'; the o-series predates both ends of the ladder;
-// GPT-5.4 Pro starts at 'medium'. Models without a list are passed the
+// GPT-5.6 family take the whole ladder; GPT-6 Astra and GPT-6.1 Sol have no
+// 'none'; the GPT-5.4 tier stops at 'xhigh'; the original GPT-5 minis kept
+// 'minimal' but never gained 'xhigh'; the o-series predates both ends of the
+// ladder; GPT-5.4 Pro starts at 'medium'. Models without a list are passed the
 // requested value unchanged, except uncatalogued GPT-5 Pro snapshots, which
 // are only known to accept 'high'.
 const FULL_EFFORT_TIERS = ['none', 'low', 'medium', 'high', 'xhigh', 'max'];
-const GPT_6_ASTRA_EFFORT_TIERS = ['low', 'medium', 'high', 'xhigh', 'max'];
+const NO_NONE_EFFORT_TIERS = ['low', 'medium', 'high', 'xhigh', 'max'];
 const GPT_54_EFFORT_TIERS = ['none', 'low', 'medium', 'high', 'xhigh'];
 const GPT_54_PRO_EFFORT_TIERS = ['medium', 'high', 'xhigh'];
 const GPT_5_EFFORT_TIERS = ['minimal', 'low', 'medium', 'high'];
@@ -27,35 +27,53 @@ const PRO_PASSTHROUGH_EFFORT_TIERS = ['high'];
 
 // Define supported models with their capabilities.
 // Bare tier names (sol, luna) and the bare generation (gpt-6, and the legacy
-// gpt-5 shortcut) follow the current generation; older tiers stay reachable by
-// their versioned names.
+// gpt-5 shortcut) follow the current release of each tier; older tiers stay
+// reachable by their versioned names.
 const SUPPORTED_MODELS = {
-  'gpt-6-sol': {
-    modelName: 'gpt-6-sol',
-    friendlyName: 'OpenAI (GPT-6 Sol)',
+  'gpt-6.1-sol': {
+    modelName: 'gpt-6.1-sol',
+    friendlyName: 'OpenAI (GPT-6.1 Sol)',
     contextWindow: 1050000,
     maxOutputTokens: 128000,
     supportsStreaming: true,
     supportsImages: true,
     supportsWebSearch: true,
     supportsResponsesAPI: true,
-    supportedEfforts: FULL_EFFORT_TIERS,
+    supportedEfforts: NO_NONE_EFFORT_TIERS,
     timeout: 10800000, // 3 hours
     description:
-      'Default GPT-6 model (1M context, 128K output) - Complex coding and agentic workflows at a fifth of the Astra price',
+      'Default GPT-6 model (1M context, 128K output) - Near-Astra coding, computer use and professional work at a fifth of the Astra price',
     aliases: [
       'gpt-6',
       'gpt6',
       'gpt 6',
+      'gpt-6.1',
+      'gpt6.1',
+      'gpt 6.1',
       'gpt-5',
       'gpt5',
       'gpt 5',
       'sol',
-      'gpt6-sol',
-      'gpt-6sol',
-      'gpt 6 sol',
+      'gpt6.1-sol',
+      'gpt-6.1sol',
+      'gpt 6.1 sol',
     ],
   },
+  'gpt-6-sol': {
+    modelName: 'gpt-6-sol',
+    friendlyName: 'OpenAI (GPT-6 Sol)',
+    contextWindow: 1050000,
+    maxOutputTokens: 128000,
+    supportsStreaming: true,
+    supportsImages: true,
+    supportsWebSearch: true,
+    supportsResponsesAPI: true,
+    supportedEfforts: FULL_EFFORT_TIERS,
+    timeout: 10800000, // 3 hours
+    description:
+      'Previous GPT-6 Sol (1M context, 128K output) - Complex coding and agentic workflows; the only Sol that accepts none effort',
+    aliases: ['gpt6-sol', 'gpt-6sol', 'gpt 6 sol'],
+  },
   'gpt-6-luna': {
     modelName: 'gpt-6-luna',
     friendlyName: 'OpenAI (GPT-6 Luna)',
@@ -80,7 +98,7 @@ const SUPPORTED_MODELS = {
     supportsImages: true,
     supportsWebSearch: true,
     supportsResponsesAPI: true,
-    supportedEfforts: GPT_6_ASTRA_EFFORT_TIERS,
+    supportedEfforts: NO_NONE_EFFORT_TIERS,
     timeout: 10800000, // 3 hours
     description:
       'Frontier GPT-6 flagship (1M context, 128K output) - Maximum intelligence for the hardest end-to-end work (EXPENSIVE: 5x Sol)',
@@ -410,7 +428,7 @@ function acceptsReasoningEffort(resolvedModel, modelConfig) {
 /**
  * Resolve the reasoning effort actually sent to the API. Catalogued models
  * clamp onto their declared tiers. Pass-through IDs are matched by family
- * where the tiers are known (GPT-5 Pro snapshots, GPT-6 Sol/Luna and GPT-5.6
+ * where the tiers are known (GPT-5 Pro snapshots, GPT-6.x and GPT-5.6
  * snapshots) and otherwise keep the requested value.
  */
 function resolveReasoningEffort(resolvedModel, modelConfig, reasoningEffort) {
@@ -420,8 +438,11 @@ function resolveReasoningEffort(resolvedModel, modelConfig, reasoningEffort) {
   if (resolvedModel.endsWith('-pro') && resolvedModel.startsWith('gpt-5')) {
     return clampReasoningEffort(reasoningEffort, PRO_PASSTHROUGH_EFFORT_TIERS);
   }
-  if (resolvedModel.startsWith('gpt-6-astra')) {
-    return clampReasoningEffort(reasoningEffort, GPT_6_ASTRA_EFFORT_TIERS);
+  if (
+    resolvedModel.startsWith('gpt-6-astra') ||
+    resolvedModel.startsWith('gpt-6.1-sol')
+  ) {
+    return clampReasoningEffort(reasoningEffort, NO_NONE_EFFORT_TIERS);
   }
   if (
     resolvedModel.startsWith('gpt-6-sol') ||
@@ -547,7 +568,7 @@ function convertMessages(messages, useResponsesAPI = false) {
 /**
  * Main OpenAI provider implementation
  */
-const DEFAULT_MODEL = 'gpt-6-sol';
+const DEFAULT_MODEL = 'gpt-6.1-sol';
 
 export const openaiProvider = {
   defaultModel: DEFAULT_MODEL,