feat(providers): add Standard Compute as a bundled descriptor row

Adds Standard Compute on the existing compatible-host descriptor path:
Chat Completions at https://api.stdcmpt.com/v1, STANDARDCOMPUTE_API_KEY,
and the `standardcompute` router id as the bootstrap model. Live
GET /v1/models stays the model authority. Billing is recorded as
Unknown in the pricing omission ledger; no provider enum or price row.

Signed-off-by: Henrik Bakke Dukefoss <[email protected]>
Co-Authored-By: Claude Opus 5.5 <[email protected]>

crates/config/assets/provider_descriptors.json

@@ -2227,6 +2227,21 @@
         "meituan-sensenova-cn"
       ]
     },
+    {
+      "id": "standardcompute",
+      "label": "Standard Compute",
+      "wire": "openai-compatible",
+      "base_url": "https://api.stdcmpt.com/v1",
+      "api_key_env": "STANDARDCOMPUTE_API_KEY",
+      "default_model": "standardcompute",
+      "discovery": "models_endpoint",
+      "docs_url": "https://docs.standardcompute.com/quickstart",
+      "credential_url": "https://standardcompute.com/dashboard/api-keys",
+      "guidance": "OpenAI-compatible host (Chat Completions + GET /v1/models). The standardcompute model id routes each request across models and providers; vendor-prefixed ids such as deepseek/deepseek-v4-pro pin one model. Live /v1/models is the model authority. Store STANDARDCOMPUTE_API_KEY, not a raw key.",
+      "aliases": [
+        "standard-compute"
+      ]
+    },
     {
       "id": "tsubasa",
       "label": "Tsubasa",

crates/config/src/descriptors.rs

@@ -312,6 +312,20 @@ mod tests {
         );
     }
 
+    #[test]
+    fn standard_compute_is_a_descriptor_row() {
+        let row = provider_descriptor("standard-compute").expect("standardcompute");
+        assert_eq!(row.id, "standardcompute");
+        assert_eq!(row.wire, DescriptorWire::OpenaiCompatible);
+        assert_eq!(row.base_url, "https://api.stdcmpt.com/v1");
+        assert_eq!(row.api_key_env, "STANDARDCOMPUTE_API_KEY");
+        assert_eq!(row.default_model, "standardcompute");
+        assert_eq!(
+            provider_descriptor("standard_compute").map(|row| row.id.as_str()),
+            Some("standardcompute")
+        );
+    }
+
     #[test]
     fn descriptors_do_not_embed_model_rosters() {
         let raw = DESCRIPTORS_JSON;
@@ -404,6 +418,6 @@ mod tests {
         // reusing its name; compatible-host lookup remains separately scoped.
         assert!(provider_descriptor("openai").is_none());
         assert!(provider_descriptor("deepseek").is_none());
-        assert_eq!(bundled_provider_descriptors().len(), 10);
+        assert_eq!(bundled_provider_descriptors().len(), 11);
     }
 }

crates/tui/src/pricing/default_coverage_tests.rs

@@ -149,7 +149,7 @@ fn shipped_default_routes_have_reviewed_pricing_coverage() {
     assert_eq!(built_in_count, 51, "review changed shipped-default breadth");
     assert_eq!(
         defaults.len() - built_in_count,
-        10,
+        11,
         "review compatible-default breadth"
     );
     let recorded_at = Utc.with_ymd_and_hms(2026, 9, 8, 12, 0, 0).unwrap();

crates/tui/src/pricing/default_coverage_unpriced.json

@@ -36,7 +36,7 @@
   },
   {
     "reason": "unknown_billing_basis",
-    "review": "No mode/credential product is supplied. Both MiniMax dialects share a PAYG/plan endpoint that cannot prove product (route_billing.rs:253,402; pricing.rs:534); Ollama Cloud is unclassified possible spend, not local/free (pricing.rs:411). Generic Custom and nine non-Baseten compatible defaults are transport descriptors without a reviewed product; production envelope refuses Unknown at cost_status.rs:239. AICraft is the sixth compatible default: dc170add3 restored its row from the closed PR #6171 with endpoint, credential env and bootstrap model only, and no billing product or pricing row was reviewed for it. Its default is claude-4.6-sonnet, which has no bundled/hand row either; that omission is recorded here on the shape of the descriptor, and a real source review of AICraft's billing basis is still owed. Tsubasa (#6695) is the seventh: endpoint, credential env and bootstrap model tsubasa-pro only; its public site lists prepaid-credit per-token rates, but no pricing row was reviewed or frozen for it, so it stays Unknown here too. Yolo-Auto is the eighth: its row carries endpoint, credential env and bootstrap model (qwen3.8-flash, the vendor's recommended start model on free and paid plans) only, the gateway sells flat-rate subscription tiers with no published per-token catalog to review, and the URL proves no plan product, so the route stays Unknown rather than being guessed into subscription or local-no-bill; a source review of Yolo-Auto's billing basis is owed. Cheaper Inference is the ninth non-Baseten compatible default: its gpt-5.4-mini bootstrap model and API endpoint do not establish a billing product or reviewed price, so it also remains Unknown. ChatGPT source review: the official API endpoint alone does not prove a ChatGPT plan product. route_billing.rs capture_product requires the Config's owned official registration for Subscription; the offline default inventory has none and remains Unknown. The retired backend endpoint supplies no transport or billing authority.",
+    "review": "No mode/credential product is supplied. Both MiniMax dialects share a PAYG/plan endpoint that cannot prove product (route_billing.rs:253,402; pricing.rs:534); Ollama Cloud is unclassified possible spend, not local/free (pricing.rs:411). Generic Custom and ten non-Baseten compatible defaults are transport descriptors without a reviewed product; production envelope refuses Unknown at cost_status.rs:239. AICraft is the sixth compatible default: dc170add3 restored its row from the closed PR #6171 with endpoint, credential env and bootstrap model only, and no billing product or pricing row was reviewed for it. Its default is claude-4.6-sonnet, which has no bundled/hand row either; that omission is recorded here on the shape of the descriptor, and a real source review of AICraft's billing basis is still owed. Tsubasa (#6695) is the seventh: endpoint, credential env and bootstrap model tsubasa-pro only; its public site lists prepaid-credit per-token rates, but no pricing row was reviewed or frozen for it, so it stays Unknown here too. Yolo-Auto is the eighth: its row carries endpoint, credential env and bootstrap model (qwen3.8-flash, the vendor's recommended start model on free and paid plans) only, the gateway sells flat-rate subscription tiers with no published per-token catalog to review, and the URL proves no plan product, so the route stays Unknown rather than being guessed into subscription or local-no-bill; a source review of Yolo-Auto's billing basis is owed. Cheaper Inference is the ninth non-Baseten compatible default: its gpt-5.4-mini bootstrap model and API endpoint do not establish a billing product or reviewed price, so it also remains Unknown. Standard Compute is the tenth: its row carries endpoint, credential env and the standardcompute router id only; the gateway sells flat monthly plans with a per-plan compute budget, and neither the URL nor the router id proves a plan product or per-request price, so the route stays Unknown. ChatGPT source review: the official API endpoint alone does not prove a ChatGPT plan product. route_billing.rs capture_product requires the Config's owned official registration for Subscription; the offline default inventory has none and remains Unknown. The retired backend endpoint supplies no transport or billing authority.",
     "routes": [
       ["aicraft", "claude-4.6-sonnet", "https://aicraftapi.com/v1", "chat_completions", "unknown"],
       ["cerebras", "llama-3.3-70b", "https://api.cerebras.ai/v1", "chat_completions", "unknown"],
@@ -50,6 +50,7 @@
       ["ollama-cloud", "gpt-oss:120b", "https://ollama.com/v1", "chat_completions", "unknown"],
       ["openai-codex", "gpt-5.6", "https://api.openai.com/v1", "responses", "unknown"],
       ["sensenova", "deepseek-v4-flash", "https://token.sensenova.cn/v1", "chat_completions", "unknown"],
+      ["standardcompute", "standardcompute", "https://api.stdcmpt.com/v1", "chat_completions", "unknown"],
       ["tsubasa", "tsubasa-pro", "https://api.tsubasa.sh/v1", "chat_completions", "unknown"],
       ["yolo-auto", "qwen3.8-flash", "https://yolo-auto.com/v1", "chat_completions", "unknown"]
     ]

docs/PROVIDERS.md

@@ -49,6 +49,7 @@ against the vendor's own docs before trusting any value here:
 | Tsubasa | `https://api.tsubasa.sh/v1` | `tsubasa-pro`, `tsubasa-fast` (32,768-token context) | `TSUBASA_API_KEY` |
 | Cheaper Inference | `https://api.cheaperinference.com/v1` | `gpt-5.4-mini`, `claude-sonnet-5`, `gemini-3.1-pro` | `CHEAPER_INFERENCE_API_KEY` |
 | Yolo-Auto | `https://yolo-auto.com/v1` | `qwen3.8-flash`; `yolo` / `yolo-small` | `YOLO_AUTO_API_KEY` |
+| Standard Compute | `https://api.stdcmpt.com/v1` | `standardcompute` (router); `deepseek/deepseek-v4-pro`, `anthropic/claude-sonnet-5.5` | `STANDARDCOMPUTE_API_KEY` |
 
 AICraft's roster spans DeepSeek, Anthropic Claude, Google Gemini, Qwen, GLM,
 MiniMax and Doubao ids on its OpenAI-compatible endpoint. The authority is
@@ -65,6 +66,13 @@ Pricing varies by model and route; consult the provider’s current catalog.
 The authority is `GET https://api.cheaperinference.com/v1/models` with your key.
 Docs: <https://cheaperinference.com/docs>.
 
+Standard Compute is an OpenAI-compatible gateway billed as a flat monthly plan
+with a compute budget; requests return HTTP 402 once the plan's budget is used.
+The `standardcompute` model id routes each request across models and providers;
+vendor-prefixed ids such as `deepseek/deepseek-v4-pro` pin one model. The
+authority is `GET https://api.stdcmpt.com/v1/models`.
+Docs: <https://docs.standardcompute.com/quickstart>.
+
 OpenCode Zen and OpenCode Go are first-class provider routes, configured like
 any other provider below; they are not part of this table. In `/provider`,
 type to filter the list (letters not bound to a row action); `Ctrl+T` probes the

docs/zh_hans/PROVIDERS.md

@@ -25,11 +25,13 @@ DeepSeek 仍是默认提供商，但 `ProviderKind::ALL` 中的每个条目都
 | Tsubasa | `https://api.tsubasa.sh/v1` | `tsubasa-pro`, `tsubasa-fast`（32,768 token 上下文） | `TSUBASA_API_KEY` |
 | Yolo-Auto | `https://yolo-auto.com/v1` | `qwen3.8-flash`；`yolo` / `yolo-small` | `YOLO_AUTO_API_KEY` |
 | Cheaper Inference | `https://api.cheaperinference.com/v1` | `gpt-5.4-mini`、`claude-sonnet-5`、`gemini-3.1-pro` | `CHEAPER_INFERENCE_API_KEY` |
+| Standard Compute | `https://api.stdcmpt.com/v1` | `standardcompute`（路由）；`deepseek/deepseek-v4-pro`、`anthropic/claude-sonnet-5.5` | `STANDARDCOMPUTE_API_KEY` |
 
 AICraft 的 OpenAI 兼容端点提供 DeepSeek、Anthropic Claude、Google Gemini、Qwen、GLM、MiniMax 和 Doubao 的模型 ID。权威来源是带上你的密钥请求 `GET https://aicraftapi.com/v1/models` 的结果：请从该列表中选择模型，而不是从上表中选。
 Tsubasa 只实现了 `GET /v1/models` 和 Chat Completions。它的两个公开模型 ID 共用 32,768 token 的上下文，小于 Codewhale 对未知模型假定的 128,000 token，因此保存后请在该路由上设置：
 `codewhale config set providers.tsubasa.context_window 32768`。
 Cheaper Inference 是 OpenAI 兼容网关，模型 ID 不带前缀（例如 `gpt-5.4-mini`、`claude-sonnet-5`），以带密钥请求 `GET https://api.cheaperinference.com/v1/models` 的结果为准；价格随模型和路由而变，请以提供商的实时目录为准。
+Standard Compute 是 OpenAI 兼容网关，按月固定套餐计费并附带算力预算，预算用尽后请求返回 HTTP 402。模型 ID `standardcompute` 会在多个模型和提供商之间路由每个请求；带厂商前缀的 ID（例如 `deepseek/deepseek-v4-pro`）则固定使用单个模型，以 `GET https://api.stdcmpt.com/v1/models` 的结果为准。
 OpenCode Zen 和 OpenCode Go 是一等提供商路由，配置方式与下文其他提供商相同；它们不在上表之列。在 `/provider` 中，直接输入即可筛选列表（未绑定行操作的字母）；`Ctrl+T` 探测所选行的 `/models`，只记录可达性（2xx 并不代表模型可用）。
 
 需要保持同步的来源：

web/data/agent-docs.generated.json

@@ -48,8 +48,8 @@
     "sources": [
       {
         "path": "docs/PROVIDERS.md",
-        "sha256": "6d578f231ebdb823023bf233f1163026a72ed636e2c377385e1e83e77efc28c6",
-        "content": "# Provider Registry\n\n> 阅读简体中文版：[zh_hans/PROVIDERS.md](zh_hans/PROVIDERS.md)\n\nSpeech recognition, synthesis, translation and video have separate execution\npaths. See [media models](MEDIA_MODELS.md) for current support and reviewed\nupstream candidates; a chat catalogue row alone does not add a media backend.\n\nThis registry describes provider behavior that is wired into the current\nCodewhale codebase. It is intentionally conservative: shipped entries are\nlimited to provider IDs, config keys, auth paths, base URLs, model resolution,\nand capability metadata that the code already knows about.\n\nDeepSeek remains the default provider, but every entry in `ProviderKind::ALL`\nis a first-class selectable provider route. `ALL` is the catalog/picker\nsurface — one identity per vendor. Dual-wire dialect kinds (`*Anthropic`, e.g.\n`deepseek-anthropic`) and the Model Studio plan variants stay on the enum for\nserde and `provider_for_kind` but are deliberately **not** catalog rows:\na plan is `mode`/`base_url` and a dialect is `wire = openai|anthropic` on the\nprimary provider config (`crates/config/src/provider_kind.rs:221-226`). Hosted\nroutes, generic OpenAI-compatible endpoints, the OpenAI Codex/ChatGPT route,\nnative Anthropic, and local runtimes all run the same terminal harness against\nthe selected provider/model/base URL.\n\nA host reached over plain Chat Completions is an ordinary named provider,\nnot a `ProviderKind`: enum variants are reserved for distinct *wires*\n(Anthropic Messages, Codex Responses, Google thought signatures). Any such\nhost is a `[providers.<name>]` table with a base URL, a model, and a key env\n(`docs/CONFIGURATION.md`); `/provider` and `/setup` keep a \"paste a Base URL\nand a key\" path for exactly this. Offerings come from live `GET /v1/models`\nplus the Codewhale catalog rather than a compiled roster (#5350, #6289).\n\nKnown-good hosts. These ship as bundled descriptor rows in\n`crates/config/assets/provider_descriptors.json` (compiled in by\n`crates/config/src/descriptors.rs`): each row says how to reach the host — wire,\nbase URL, key env, aliases — while model ids stay live from `GET /v1/models`\nand the Codewhale catalog; the example model is only a bootstrap hint. Verify\nagainst the vendor's own docs before trusting any value here:\n\n| Host | Base URL | Example models | API key env |\n| --- | --- | --- | --- |\n| SenseNova | `https://token.sensenova.cn/v1` | `deepseek-v4-flash` | `SENSENOVA_API_KEY` |\n| Baseten | `https://inference.baseten.co/v1` | `deepseek-ai/DeepSeek-V4-Pro` | `BASETEN_API_KEY` |\n| Groq | `https://api.groq.com/openai/v1` | `llama-3.3-70b-versatile` | `GROQ_API_KEY` |\n| Cerebras | `https://api.cerebras.ai/v1` | `llama-3.3-70b` | `CEREBRAS_API_KEY` |\n| Command Code | `https://api.commandcode.ai/provider/v1` | `deepseek/deepseek-v4-flash` | `COMMAND_CODE_API_KEY` |\n| Alibaba Model Studio (DashScope) | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1` | `qwen3.8-flash` | `DASHSCOPE_API_KEY` |\n| AICraft | `https://aicraftapi.com/v1` | `claude-4.6-sonnet`; DeepSeek / Claude / Gemini / Qwen / GLM / MiniMax / Doubao families | `AICRAFT_API_KEY` |\n| Tsubasa | `https://api.tsubasa.sh/v1` | `tsubasa-pro`, `tsubasa-fast` (32,768-token context) | `TSUBASA_API_KEY` |\n| Cheaper Inference | `https://api.cheaperinference.com/v1` | `gpt-5.4-mini`, `claude-sonnet-5`, `gemini-3.1-pro` | `CHEAPER_INFERENCE_API_KEY` |\n| Yolo-Auto | `https://yolo-auto.com/v1` | `qwen3.8-flash`; `yolo` / `yolo-small` | `YOLO_AUTO_API_KEY` |\n\nAICraft's roster spans DeepSeek, Anthropic Claude, Google Gemini, Qwen, GLM,\nMiniMax and Doubao ids on its OpenAI-compatible endpoint. The authority is\n`GET https://aicraftapi.com/v1/models` with your key — pick a model from that\nlist, not from this table.\nTsubasa implements only `GET /v1/models` and Chat Completions. Its two public\nmodel ids share a 32,768-token context, smaller than the 128,000 tokens Codewhale assumes\nfor an unknown model, so set it on the route after saving:\n`codewhale config set providers.tsubasa.context_window 32768`.\n\nCheaper Inference is an OpenAI-compatible gateway with one key for models from\nseveral labs. Model ids are bare, such as `gpt-5.4-mini` or `claude-sonnet-5`.\nPricing varies by model and route; consult the provider’s current catalog.\nThe authority is `GET https://api.cheaperinference.com/v1/models` with your key.\nDocs: <https://cheaperinference.com/docs>.\n\nOpenCode Zen and OpenCode Go are first-class provider routes, configured like\nany other provider below; they are not part of this table. In `/provider`,\ntype to filter the list (letters not bound to a row action); `Ctrl+T` probes the\nselected row's `/models` and records reachability only (a 2xx is not\nmodel-ready).\n\nSources to keep in sync:\n\n- `crates/config/assets/provider_descriptors.json` - built-in and compatible-host\n  labels, defaults, aliases, key-env lists, config/secLine truncated
+        "sha256": "15e5f540066793db088a7df33cf269e3843e66437f15311132c6ab5e3bb65112",
+        "content": "# Provider Registry\n\n> 阅读简体中文版：[zh_hans/PROVIDERS.md](zh_hans/PROVIDERS.md)\n\nSpeech recognition, synthesis, translation and video have separate execution\npaths. See [media models](MEDIA_MODELS.md) for current support and reviewed\nupstream candidates; a chat catalogue row alone does not add a media backend.\n\nThis registry describes provider behavior that is wired into the current\nCodewhale codebase. It is intentionally conservative: shipped entries are\nlimited to provider IDs, config keys, auth paths, base URLs, model resolution,\nand capability metadata that the code already knows about.\n\nDeepSeek remains the default provider, but every entry in `ProviderKind::ALL`\nis a first-class selectable provider route. `ALL` is the catalog/picker\nsurface — one identity per vendor. Dual-wire dialect kinds (`*Anthropic`, e.g.\n`deepseek-anthropic`) and the Model Studio plan variants stay on the enum for\nserde and `provider_for_kind` but are deliberately **not** catalog rows:\na plan is `mode`/`base_url` and a dialect is `wire = openai|anthropic` on the\nprimary provider config (`crates/config/src/provider_kind.rs:221-226`). Hosted\nroutes, generic OpenAI-compatible endpoints, the OpenAI Codex/ChatGPT route,\nnative Anthropic, and local runtimes all run the same terminal harness against\nthe selected provider/model/base URL.\n\nA host reached over plain Chat Completions is an ordinary named provider,\nnot a `ProviderKind`: enum variants are reserved for distinct *wires*\n(Anthropic Messages, Codex Responses, Google thought signatures). Any such\nhost is a `[providers.<name>]` table with a base URL, a model, and a key env\n(`docs/CONFIGURATION.md`); `/provider` and `/setup` keep a \"paste a Base URL\nand a key\" path for exactly this. Offerings come from live `GET /v1/models`\nplus the Codewhale catalog rather than a compiled roster (#5350, #6289).\n\nKnown-good hosts. These ship as bundled descriptor rows in\n`crates/config/assets/provider_descriptors.json` (compiled in by\n`crates/config/src/descriptors.rs`): each row says how to reach the host — wire,\nbase URL, key env, aliases — while model ids stay live from `GET /v1/models`\nand the Codewhale catalog; the example model is only a bootstrap hint. Verify\nagainst the vendor's own docs before trusting any value here:\n\n| Host | Base URL | Example models | API key env |\n| --- | --- | --- | --- |\n| SenseNova | `https://token.sensenova.cn/v1` | `deepseek-v4-flash` | `SENSENOVA_API_KEY` |\n| Baseten | `https://inference.baseten.co/v1` | `deepseek-ai/DeepSeek-V4-Pro` | `BASETEN_API_KEY` |\n| Groq | `https://api.groq.com/openai/v1` | `llama-3.3-70b-versatile` | `GROQ_API_KEY` |\n| Cerebras | `https://api.cerebras.ai/v1` | `llama-3.3-70b` | `CEREBRAS_API_KEY` |\n| Command Code | `https://api.commandcode.ai/provider/v1` | `deepseek/deepseek-v4-flash` | `COMMAND_CODE_API_KEY` |\n| Alibaba Model Studio (DashScope) | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1` | `qwen3.8-flash` | `DASHSCOPE_API_KEY` |\n| AICraft | `https://aicraftapi.com/v1` | `claude-4.6-sonnet`; DeepSeek / Claude / Gemini / Qwen / GLM / MiniMax / Doubao families | `AICRAFT_API_KEY` |\n| Tsubasa | `https://api.tsubasa.sh/v1` | `tsubasa-pro`, `tsubasa-fast` (32,768-token context) | `TSUBASA_API_KEY` |\n| Cheaper Inference | `https://api.cheaperinference.com/v1` | `gpt-5.4-mini`, `claude-sonnet-5`, `gemini-3.1-pro` | `CHEAPER_INFERENCE_API_KEY` |\n| Yolo-Auto | `https://yolo-auto.com/v1` | `qwen3.8-flash`; `yolo` / `yolo-small` | `YOLO_AUTO_API_KEY` |\n| Standard Compute | `https://api.stdcmpt.com/v1` | `standardcompute` (router); `deepseek/deepseek-v4-pro`, `anthropic/claude-sonnet-5.5` | `STANDARDCOMPUTE_API_KEY` |\n\nAICraft's roster spans DeepSeek, Anthropic Claude, Google Gemini, Qwen, GLM,\nMiniMax and Doubao ids on its OpenAI-compatible endpoint. The authority is\n`GET https://aicraftapi.com/v1/models` with your key — pick a model from that\nlist, not from this table.\nTsubasa implements only `GET /v1/models` and Chat Completions. Its two public\nmodel ids share a 32,768-token context, smaller than the 128,000 tokens Codewhale assumes\nfor an unknown model, so set it on the route after saving:\n`codewhale config set providers.tsubasa.context_window 32768`.\n\nCheaper Inference is an OpenAI-compatible gateway with one key for models from\nseveral labs. Model ids are bare, such as `gpt-5.4-mini` or `claude-sonnet-5`.\nPricing varies by model and route; consult the provider’s current catalog.\nThe authority is `GET https://api.cheaperinference.com/v1/models` with your key.\nDocs: <https://cheaperinference.com/docs>.\n\nStandard Compute is an OpenAI-compatible gateway billed as a flat monthly plan\nwith a compute budget; requests return HTTP 402 once the plan's budget is used.\nThe `standardcompute` model id routes each request across models and providers;\nvendor-prefixed ids such as `deepseek/deepseek-v4-pro` pin one model. The\nautLine truncated
       },
       {
         "path": "docs/MODEL_LAB.md",