opencode: Add support for OpenCode Go (#53651)

**TL;DR**: add support for OpenCode Go (flat-rate monthly subscription)
along the already-implemented OpenCode Zed (pay-as-you-go billing).

> [!WARNING]
> This code was written by LLMs, under the supervision of a so-called
developer that never wrote Rust profesionally and that spends more time
in Pages&Keynote than in an IDE.

Self-Review Checklist:

- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable

## Background

OpenCode offers a few different ways to access models:
- **free access to 3 models**, with feedback and data used to improve
the model. These models use the OpenCode Zen API endpoints, but have
different usage limits (200 requests per 5 hours) and have a different
privacy policy. Some people disable or block the free models, some
people are super-excited to have access to LLMs for free, and some
people like using the free models to test new LLMs (at launch MiMo-V2
had 2 free weeks of usage, for example).
- **pay-as-you-go access to 30 models** as part of the [OpenCode
Zen](https://opencode.ai/zen) subscription. These models use the same
OpenCode Zen API endpoints.
- **flat-rate monthly access to 7 models** as part of the [OpenCode
Go](https://opencode.ai/go) subscription. These models use the OpenCode
Zen API endpoints with an extra `/go` appended to the path. There are
5-hour, weekly, and monthly usage limits and, additionally, users can
toggle a switch in the OpenCode Console to use Zen models with their
pay-as-you-go billing after the Go limits are hit.

There's also a currently-paused [OpenCode
Black](https://opencode.ai/black) flat-rate subscription with way higher
usage limits and with access to more models, with $100 and $200 monthly
plans.

The whole thing is a bit messy, but it's great value and highly reliable
LLM access!

<br>

https://github.com/zed-industries/zed/pull/49589 added support for
OpenCode Zen by implementing a new `opencode` provider. OpenCode Go
[could be used by overriding the API
URL](https://github.com/zed-industries/zed/pull/49589#issuecomment-4130300454),
but that is a terrible user experience: some models have to be manually
added, the model list always shows the 30-something OpenCode Zen models,
and free models cannot be used at all.

I was annoyed by the experience of using OpenCode Go with Zed and this
past week I had to test a bunch of LLMs and providers and harnesses, so
I took this on as a test case 🙂

## Implementation

This PR makes the OpenCode provider more general (not just for Zen) and
adds an `OpenCodeModelSubscription` concept which is then used to
implement support for OpenCode Go. The free models are also broken out
into their own subscription for a prettier model list.

For a better user experience, the different subscriptions can be enabled
or disabled, both in the settings file and in the UX:
<img width="434" height="176" alt="Screenshot showing the OpenCode
provider configuration, with the newly added toggles"
src="https://github.com/user-attachments/assets/3520e114-00c8-4794-84bf-35cd72d9c57e"
/>


The code was written by LLMs, but I do understand it and I did a bunch
of "manual" iterations and "manual" tweaks. Still, my Rust experience is
non-existent so **I won't feel offended if y'all reject this PR**! I did
consider alternatives (adding a new `opencode-go` provider and renaming
this to `opencode-zen`, for example, or adding support for custom API
URLs in OpenCode custom models which would've been the smallest code
change but a terrible user experience, and so on) but all alternatives
would have been, in my opinion, a worse user experience.

**Tests I did**:
- confirmed OpenCode Go models work as expected
- confirmed OpenCode Zen Free models work as expected
- confirmed I get an error when trying to use OpenCode Zen models since
I don't have that subscription
- confirmed the subcription toggles work as expected (model are
shown/hidden, settings file is updated)

**Notes**:
- this PR is best reviewed commit-by-commit. I did not create a separate
PR for the model updates to minimize delays
- my exeprience with Rust is roughly zero, but I tried to strike a
balance between idiomatic Rust and easy-to-read code
- users of the OpenCode provider might have to do some re-configuration
after this PR is merged since the model identifiers now include the
subscription, eg `claude-haiku-4-5` is now `zen/claude-haiku-4-5`. Since
this is a relatively new provider and the impact is small, I preffered
that rather than adding complex migration/mapping logic.
- does changing the provider name from "OpenCode Zen" to "OpenCode"
break anything for y'all at Zed?
- does changing the telemetry id from `"opencode/<model-id>"` to
`"opencode/<subscription>/<model-id>"` break anything for y'all at Zed?

---

Release Notes:
- OpenCode provider: add support for OpenCode Go

---------

Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>

crates/opencode/src/opencode.rs

@@ -17,6 +17,40 @@ pub enum ApiProtocol {
     Google,
 }
 
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Serialize, Deserialize)]
+#[cfg_attr(feature = "schemars", derive(schemars::JsonSchema))]
+#[serde(rename_all = "snake_case")]
+pub enum OpenCodeSubscription {
+    Zen,
+    Go,
+    Free,
+}
+
+impl OpenCodeSubscription {
+    pub fn display_name(&self) -> &'static str {
+        match self {
+            Self::Zen => "Zen",
+            Self::Go => "Go",
+            Self::Free => "Free",
+        }
+    }
+
+    pub fn id_prefix(&self) -> &'static str {
+        match self {
+            Self::Zen => "zen",
+            Self::Go => "go",
+            Self::Free => "free",
+        }
+    }
+
+    pub fn api_path_suffix(&self) -> &'static str {
+        match self {
+            Self::Zen | Self::Free => "",
+            Self::Go => "/go",
+        }
+    }
+}
+
 #[cfg_attr(feature = "schemars", derive(schemars::JsonSchema))]
 #[derive(Clone, Debug, Default, Serialize, Deserialize, PartialEq, EnumIter)]
 pub enum Model {
@@ -86,20 +120,26 @@ pub enum Model {
     MiniMaxM2_5Free,
     #[serde(rename = "glm-5")]
     Glm5,
+    #[serde(rename = "glm-5.1")]
+    Glm5_1,
     #[serde(rename = "kimi-k2.5")]
     KimiK2_5,
-    #[serde(rename = "mimo-v2-pro-free")]
-    MimoV2ProFree,
-    #[serde(rename = "mimo-v2-omni-free")]
-    MimoV2OmniFree,
-    #[serde(rename = "mimo-v2-flash-free")]
-    MimoV2FlashFree,
-    #[serde(rename = "trinity-large-preview-free")]
-    TrinityLargePreviewFree,
+    #[serde(rename = "kimi-k2.6")]
+    KimiK2_6,
+    #[serde(rename = "minimax-m2.7")]
+    MiniMaxM2_7,
+    #[serde(rename = "mimo-v2-pro")]
+    MimoV2Pro,
+    #[serde(rename = "mimo-v2-omni")]
+    MimoV2Omni,
     #[serde(rename = "big-pickle")]
     BigPickle,
     #[serde(rename = "nemotron-3-super-free")]
     Nemotron3SuperFree,
+    #[serde(rename = "qwen3.5-plus")]
+    Qwen3_5Plus,
+    #[serde(rename = "qwen3.6-plus")]
+    Qwen3_6Plus,
 
     // -- Custom model --
     #[serde(rename = "custom")]
@@ -109,6 +149,7 @@ pub enum Model {
         max_tokens: u64,
         max_output_tokens: Option<u64>,
         protocol: ApiProtocol,
+        custom_model_api_url: Option<String>,
     },
 }
 
@@ -117,6 +158,49 @@ impl Model {
         Self::ClaudeHaiku4_5
     }
 
+    pub fn default_go() -> Self {
+        Self::KimiK2_5
+    }
+
+    pub fn default_go_fast() -> Self {
+        Self::MiniMaxM2_5
+    }
+
+    pub fn default_free() -> Self {
+        Self::BigPickle
+    }
+
+    pub fn default_free_fast() -> Self {
+        Self::MiniMaxM2_5Free
+    }
+
+    pub fn available_subscriptions(&self) -> &'static [OpenCodeSubscription] {
+        match self {
+            // Models available in both Zen and Go
+            Self::Glm5
+            | Self::Glm5_1
+            | Self::KimiK2_6
+            | Self::KimiK2_5
+            | Self::MiniMaxM2_5
+            | Self::Qwen3_5Plus
+            | Self::Qwen3_6Plus => &[OpenCodeSubscription::Zen, OpenCodeSubscription::Go],
+
+            // Go-only models
+            Self::MiniMaxM2_7 | Self::MimoV2Pro | Self::MimoV2Omni => &[OpenCodeSubscription::Go],
+
+            // Free models
+            Self::MiniMaxM2_5Free | Self::Nemotron3SuperFree | Self::BigPickle => {
+                &[OpenCodeSubscription::Free]
+            }
+
+            // Custom models get their subscription from settings, not from here
+            Self::Custom { .. } => &[],
+
+            // All other built-in models are Zen-only
+            _ => &[OpenCodeSubscription::Zen],
+        }
+    }
+
     pub fn id(&self) -> &str {
         match self {
             Self::ClaudeOpus4_7 => "claude-opus-4-7",
@@ -151,11 +235,14 @@ impl Model {
             Self::MiniMaxM2_5 => "minimax-m2.5",
             Self::MiniMaxM2_5Free => "minimax-m2.5-free",
             Self::Glm5 => "glm-5",
+            Self::Glm5_1 => "glm-5.1",
             Self::KimiK2_5 => "kimi-k2.5",
-            Self::MimoV2ProFree => "mimo-v2-pro-free",
-            Self::MimoV2OmniFree => "mimo-v2-omni-free",
-            Self::MimoV2FlashFree => "mimo-v2-flash-free",
-            Self::TrinityLargePreviewFree => "trinity-large-preview-free",
+            Self::KimiK2_6 => "kimi-k2.6",
+            Self::MiniMaxM2_7 => "minimax-m2.7",
+            Self::MimoV2Pro => "mimo-v2-pro",
+            Self::MimoV2Omni => "mimo-v2-omni",
+            Self::Qwen3_5Plus => "qwen3.5-plus",
+            Self::Qwen3_6Plus => "qwen3.6-plus",
             Self::BigPickle => "big-pickle",
             Self::Nemotron3SuperFree => "nemotron-3-super-free",
 
@@ -197,11 +284,14 @@ impl Model {
             Self::MiniMaxM2_5 => "MiniMax M2.5",
             Self::MiniMaxM2_5Free => "MiniMax M2.5 Free",
             Self::Glm5 => "GLM 5",
+            Self::Glm5_1 => "GLM 5.1",
             Self::KimiK2_5 => "Kimi K2.5",
-            Self::MimoV2ProFree => "MiMo V2 Pro Free",
-            Self::MimoV2OmniFree => "MiMo V2 Omni Free",
-            Self::MimoV2FlashFree => "MiMo V2 Flash Free",
-            Self::TrinityLargePreviewFree => "Trinity Large Preview Free",
+            Self::KimiK2_6 => "Kimi K2.6",
+            Self::MiniMaxM2_7 => "MiniMax M2.7",
+            Self::MimoV2Pro => "MiMo V2 Pro",
+            Self::MimoV2Omni => "MiMo V2 Omni",
+            Self::Qwen3_5Plus => "Qwen3.5 Plus",
+            Self::Qwen3_6Plus => "Qwen3.6 Plus",
             Self::BigPickle => "Big Pickle",
             Self::Nemotron3SuperFree => "Nemotron 3 Super Free",
 
@@ -211,8 +301,18 @@ impl Model {
         }
     }
 
-    pub fn protocol(&self) -> ApiProtocol {
+    pub fn protocol(&self, subscription: OpenCodeSubscription) -> ApiProtocol {
         match self {
+            // Models offered by OpenCode have the same configuration across subscriptions
+            //  with one outlier: non-free MiniMax models
+            Self::MiniMaxM2_7 | Self::MiniMaxM2_5 => {
+                if subscription == OpenCodeSubscription::Zen {
+                    ApiProtocol::OpenAiChat
+                } else {
+                    ApiProtocol::Anthropic
+                }
+            }
+
             Self::ClaudeOpus4_7
             | Self::ClaudeOpus4_6
             | Self::ClaudeOpus4_5
@@ -241,14 +341,15 @@ impl Model {
 
             Self::Gemini3_1Pro | Self::Gemini3Flash => ApiProtocol::Google,
 
-            Self::MiniMaxM2_5
-            | Self::MiniMaxM2_5Free
+            Self::MiniMaxM2_5Free
             | Self::Glm5
+            | Self::Glm5_1
             | Self::KimiK2_5
-            | Self::MimoV2ProFree
-            | Self::MimoV2OmniFree
-            | Self::MimoV2FlashFree
-            | Self::TrinityLargePreviewFree
+            | Self::KimiK2_6
+            | Self::MimoV2Pro
+            | Self::MimoV2Omni
+            | Self::Qwen3_5Plus
+            | Self::Qwen3_6Plus
             | Self::BigPickle
             | Self::Nemotron3SuperFree => ApiProtocol::OpenAiChat,
 
@@ -259,10 +360,12 @@ impl Model {
     pub fn max_token_count(&self) -> u64 {
         match self {
             // Anthropic models
-            Self::ClaudeOpus4_7 | Self::ClaudeOpus4_6 | Self::ClaudeSonnet4_6 => 1_000_000,
-            Self::ClaudeOpus4_5 | Self::ClaudeSonnet4_5 | Self::ClaudeSonnet4 => 200_000,
+            Self::ClaudeOpus4_7 => 1_000_000,
+            Self::ClaudeOpus4_6 | Self::ClaudeSonnet4_6 => 1_000_000,
+            Self::ClaudeSonnet4_5 => 1_000_000,
+            Self::ClaudeOpus4_5 | Self::ClaudeHaiku4_5 => 200_000,
             Self::ClaudeOpus4_1 => 200_000,
-            Self::ClaudeHaiku4_5 => 200_000,
+            Self::ClaudeSonnet4 => 1_000_000,
             Self::Claude3_5Haiku => 200_000,
 
             // OpenAI models
@@ -281,14 +384,15 @@ impl Model {
             Self::Gemini3Flash => 1_048_576,
 
             // OpenAI-compatible models
-            Self::MiniMaxM2_5 | Self::MiniMaxM2_5Free => 196_608,
-            Self::Glm5 => 200_000,
-            Self::KimiK2_5 => 262_144,
-            Self::MimoV2ProFree => 1_048_576,
-            Self::MimoV2OmniFree | Self::MimoV2FlashFree => 262_144,
-            Self::TrinityLargePreviewFree => 131_072,
+            Self::MiniMaxM2_7 => 204_800,
+            Self::MiniMaxM2_5 | Self::MiniMaxM2_5Free => 204_800,
+            Self::Glm5 | Self::Glm5_1 => 204_800,
+            Self::KimiK2_6 | Self::KimiK2_5 => 262_144,
+            Self::MimoV2Pro => 1_048_576,
+            Self::MimoV2Omni => 262_144,
+            Self::Qwen3_5Plus | Self::Qwen3_6Plus => 262_144,
             Self::BigPickle => 200_000,
-            Self::Nemotron3SuperFree => 262_144,
+            Self::Nemotron3SuperFree => 204_800,
 
             Self::Custom { max_tokens, .. } => *max_tokens,
         }
@@ -298,12 +402,12 @@ impl Model {
         match self {
             // Anthropic models
             Self::ClaudeOpus4_7 | Self::ClaudeOpus4_6 => Some(128_000),
-            Self::ClaudeSonnet4_6 => Some(64_000),
             Self::ClaudeOpus4_5
-            | Self::ClaudeOpus4_1
+            | Self::ClaudeSonnet4_6
             | Self::ClaudeSonnet4_5
-            | Self::ClaudeSonnet4
-            | Self::ClaudeHaiku4_5 => Some(64_000),
+            | Self::ClaudeHaiku4_5
+            | Self::ClaudeSonnet4 => Some(64_000),
+            Self::ClaudeOpus4_1 => Some(32_000),
             Self::Claude3_5Haiku => Some(8_192),
 
             // OpenAI models
@@ -327,12 +431,14 @@ impl Model {
             Self::Gemini3_1Pro | Self::Gemini3Flash => Some(65_536),
 
             // OpenAI-compatible models
-            Self::MiniMaxM2_5 | Self::MiniMaxM2_5Free => Some(65_536),
-            Self::Glm5 | Self::BigPickle => Some(128_000),
-            Self::KimiK2_5 => Some(65_536),
-            Self::MimoV2ProFree => Some(131_072),
-            Self::MimoV2OmniFree | Self::MimoV2FlashFree => Some(65_536),
-            Self::TrinityLargePreviewFree | Self::Nemotron3SuperFree => Some(16_384),
+            Self::MiniMaxM2_7 => Some(131_072),
+            Self::MiniMaxM2_5 | Self::MiniMaxM2_5Free => Some(131_072),
+            Self::Glm5 | Self::Glm5_1 => Some(131_072),
+            Self::BigPickle => Some(128_000),
+            Self::KimiK2_6 | Self::KimiK2_5 => Some(65_536),
+            Self::Qwen3_5Plus | Self::Qwen3_6Plus => Some(65_536),
+            Self::Nemotron3SuperFree => Some(128_000),
+            Self::MimoV2Pro | Self::MimoV2Omni => Some(64_000),
 
             Self::Custom {
                 max_output_tokens, ..
@@ -377,15 +483,20 @@ impl Model {
             // Google models support images
             Self::Gemini3_1Pro | Self::Gemini3Flash => true,
 
-            // OpenAI-compatible models — conservative default
+            // OpenAI-compatible models with image support
+            Self::KimiK2_6
+            | Self::KimiK2_5
+            | Self::MimoV2Omni
+            | Self::Qwen3_5Plus
+            | Self::Qwen3_6Plus => true,
+
+            // OpenAI-compatible models without image support
             Self::MiniMaxM2_5
             | Self::MiniMaxM2_5Free
             | Self::Glm5
-            | Self::KimiK2_5
-            | Self::MimoV2ProFree
-            | Self::MimoV2OmniFree
-            | Self::MimoV2FlashFree
-            | Self::TrinityLargePreviewFree
+            | Self::Glm5_1
+            | Self::MiniMaxM2_7
+            | Self::MimoV2Pro
             | Self::BigPickle
             | Self::Nemotron3SuperFree => false,
 
@@ -400,12 +511,12 @@ impl Model {
     }
 }
 
-/// Stream generate content for Google models via OpenCode Zen.
+/// Stream generate content for Google models via OpenCode.
 ///
 /// Unlike `google_ai::stream_generate_content()`, this uses:
 /// - `/v1/models/{model}` path (not `/v1beta/models/{model}`)
 /// - `Authorization: Bearer` header (not `key=` query param)
-pub async fn stream_generate_content_zen(
+pub async fn stream_generate_content(
     client: &dyn HttpClient,
     api_url: &str,
     api_key: &str,
@@ -451,7 +562,7 @@ pub async fn stream_generate_content_zen(
         let mut text = String::new();
         response.body_mut().read_to_string(&mut text).await?;
         Err(anyhow!(
-            "error during streamGenerateContent via OpenCode Zen, status code: {:?}, body: {}",
+            "error during streamGenerateContent via OpenCode, status code: {:?}, body: {}",
             response.status(),
             text
         ))