fix(cli): stop setting exit code when run cancels a form

Co-authored-by: Alireza Haghdoost <haghdoost@uber.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>

.github/workflows/publish.yml

@@ -24,6 +24,10 @@ on:
         description: "Override version (optional)"
         required: false
         type: string
+      release_notes:
+        description: "Reviewed V2 release notes for the Discord announcement (optional)"
+        required: false
+        type: string
 
 concurrency: ${{ github.workflow }}-${{ github.ref }}-${{ (github.ref_name == 'v2' && (inputs.version || inputs.bump) && 'release') || inputs.version || inputs.bump }}
 
@@ -653,3 +657,19 @@ jobs:
           OPENCODE_DESKTOP_DIST: /tmp/desktop
           CLOUDFLARE_ACCOUNT_ID: 15d29c8639fd3733b1b5486a2acfd968
           CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+
+  notify-discord-v2:
+    needs:
+      - version
+      - publish
+    if: github.repository == 'anomalyco/opencode' && github.ref_name == 'v2' && needs.version.outputs.release && needs.publish.result == 'success'
+    runs-on: blacksmith-4vcpu-ubuntu-2404
+    steps:
+      # Unlike dev, V2 publishes a tag rather than a GitHub Release event.
+      - name: Announce V2 release in Discord
+        uses: SethCohen/github-releases-to-discord@24d166886aee4646d448c8a389ff9e1ebcab3682 # v1.20.0
+        with:
+          webhook_url: ${{ secrets.DISCORD_WEBHOOK }}
+          release_name: OpenCode V2 ${{ needs.version.outputs.tag }}
+          release_body: ${{ inputs.release_notes }}
+          release_html_url: https://github.com/${{ github.repository }}/tree/${{ needs.version.outputs.tag }}

packages/ai/README.md

@@ -129,8 +129,9 @@ VercelAIGateway.configure().experimental.evaluation("typesafe-ai/jev")
 
 OpenRouter reads `OPENROUTER_API_KEY`. Vercel reads `AI_GATEWAY_API_KEY`, then `VERCEL_OIDC_TOKEN`.
 The common API uses `boolean`; System One routes lower it to native `noul`.
-Choice and score confidence plus score legends remain available in provider metadata, and the
-provider's rounded probabilities are returned unchanged.
+Choice and score answers include `confidence` when the provider returns it, such as
+`response.answers.department.confidence`. Score legends remain available in provider metadata, and
+the provider's rounded probabilities are returned unchanged.
 
 ## Alibaba Cloud Model Studio
 

packages/ai/src/experimental/evaluation.ts

@@ -63,6 +63,7 @@ export const ChoiceAnswer = Schema.Struct({
   type: Schema.Literal("choice"),
   choice: Schema.String,
   probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ChoiceAnswer = Schema.Schema.Type<typeof ChoiceAnswer>
 
@@ -70,6 +71,7 @@ export const ScoreAnswer = Schema.Struct({
   type: Schema.Literal("score"),
   score: Schema.Number,
   probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ScoreAnswer = Schema.Schema.Type<typeof ScoreAnswer>
 
@@ -92,6 +94,7 @@ export type AnswerFor<Question extends EvaluationQuestion> = Question extends {
       readonly type: "choice"
       readonly choice: Extract<keyof Criteria, string>
       readonly probabilities?: Readonly<Record<Extract<keyof Criteria, string>, number>>
+      readonly confidence?: number
     }
   : Question extends { readonly type: "score" }
     ? ScoreAnswer

packages/ai/src/experimental/system-one.ts

@@ -142,32 +142,37 @@ export const model = <Options extends EvaluationOptions = EvaluationOptions>(cfg
             Effect.mapError((cause) => fail("System One returned an invalid response", cause, text)),
           )
 
-          const confidence: Record<string, number> = {}
           const legend: Record<string, Record<string, Schema.Json>> = {}
           const answers = Object.fromEntries(
             Object.entries(data.answers).map(([id, answer]): [string, EvaluationAnswer] => {
               if (answer.type === "noul") return [id, { type: "boolean", probability: answer.noul }]
               if (answer.type === "choice") {
-                if (answer.confidence !== undefined) confidence[id] = answer.confidence
                 return [
                   id,
                   {
                     type: "choice",
                     choice: answer.choice,
                     probabilities: answer.probabilities,
+                    ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
                   },
                 ]
               }
-              if (answer.confidence !== undefined) confidence[id] = answer.confidence
               if (answer.legend !== undefined) legend[id] = answer.legend
-              return [id, { type: "score", score: answer.score, probabilities: answer.probabilities }]
+              return [
+                id,
+                {
+                  type: "score",
+                  score: answer.score,
+                  probabilities: answer.probabilities,
+                  ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
+                },
+              ]
             }),
           )
           const meta = {
             ...(data.id === undefined ? {} : { responseId: data.id }),
             ...(data.provider === undefined ? {} : { provider: data.provider }),
             ...data.provider_metadata?.[cfg.providerMetadataKey],
-            ...(Object.keys(confidence).length === 0 ? {} : { confidence }),
             ...(Object.keys(legend).length === 0 ? {} : { legend }),
           }
           return new EvaluationResponse({

packages/ai/src/protocols/openai-chat.ts

@@ -64,6 +64,14 @@ const OpenAIChatTool = Schema.Struct({
 })
 type OpenAIChatTool = Schema.Schema.Type<typeof OpenAIChatTool>
 
+// Gemini's OpenAI-compatible surface carries thought signatures in tool call
+// `extra_content` and rejects replayed parallel calls without them:
+// https://ai.google.dev/gemini-api/docs/thinking#signatures
+const ExtraContent = Schema.Struct({
+  google: Schema.Struct({ thought_signature: Schema.String }),
+})
+const decodeExtraContent = (value: unknown) => Option.getOrUndefined(Schema.decodeUnknownOption(ExtraContent)(value))
+
 const OpenAIChatAssistantToolCall = Schema.Struct({
   id: Schema.String,
   type: Schema.tag("function"),
@@ -71,6 +79,7 @@ const OpenAIChatAssistantToolCall = Schema.Struct({
     name: Schema.String,
     arguments: Schema.String,
   }),
+  extra_content: Schema.optional(ExtraContent),
 })
 type OpenAIChatAssistantToolCall = Schema.Schema.Type<typeof OpenAIChatAssistantToolCall>
 
@@ -112,12 +121,6 @@ const decodeReasoningDetail = Schema.decodeUnknownOption(ReasoningDetail)
 const knownReasoningDetails = (details: ReadonlyArray<unknown>) =>
   details.flatMap((detail) => Option.toArray(decodeReasoningDetail(detail)))
 
-// Intentionally omit Gemini's provider-specific `extra_content.google.thought_signature`
-// extension until direct Google OpenAI-compatible routing is supported here:
-// https://github.com/vercel/ai/issues/11590
-// https://github.com/vercel/ai/pull/11745
-// https://ai.google.dev/gemini-api/docs/thought-signatures#openai
-
 const OpenAIChatUserContent = Schema.Union([
   Schema.Struct({
     type: Schema.Literal("text"),
@@ -242,6 +245,7 @@ const OpenAIChatToolCallDelta = Schema.Struct({
   index: optionalNull(Schema.Number),
   id: optionalNull(Schema.String),
   function: optionalNull(OpenAIChatToolCallDeltaFunction),
+  extra_content: optionalNull(Schema.Unknown),
 })
 type OpenAIChatToolCallDelta = Schema.Schema.Type<typeof OpenAIChatToolCallDelta>
 
@@ -294,6 +298,7 @@ interface PendingToolDelta {
   readonly id?: string
   readonly name?: string
   readonly input: string
+  readonly extraContent?: Schema.Schema.Type<typeof ExtraContent>
 }
 
 export interface ParserState {
@@ -347,13 +352,17 @@ const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
     tool: (name) => ({ type: "function" as const, function: { name } }),
   })
 
-const lowerToolCall = (part: ToolCallPart, options: LoweringOptions): OpenAIChatAssistantToolCall => ({
+const lowerToolCall = (
+  part: ToolCallPart,
+  options: LoweringOptions & { readonly providerMetadataKey: string },
+): OpenAIChatAssistantToolCall => ({
   id: options.toolCallID?.(part.id) ?? part.id,
   type: "function",
   function: {
     name: part.name,
     arguments: ProviderShared.encodeJson(part.input === undefined ? {} : part.input),
   },
+  extra_content: decodeExtraContent(part.providerMetadata?.[options.providerMetadataKey]?.extraContent),
 })
 
 const lowerMedia = Effect.fn("OpenAIChat.lowerMedia")(function* (part: MediaPart) {
@@ -721,7 +730,9 @@ const detectSupportsStore = (provider: string, baseURL: string | undefined): boo
     p === "vercel-ai-gateway" || url.includes("ai-gateway.vercel.sh") || url.includes("vercel.sh")
   const isAntLing = p === "ant-ling" || url.includes("api.ant-ling.com")
   const isOpencode = p === "opencode" || url.includes("opencode.ai")
+  const isGemini = url.includes("generativelanguage.googleapis.com")
   const isNonStandard =
+    isGemini ||
     isNvidia ||
     isCerebras ||
     isXai ||
@@ -1114,12 +1125,13 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
       const id = current?.id ?? pending?.id ?? (tool.id || undefined)
       const name = current?.name ?? pending?.name ?? (tool.function?.name || undefined)
       const text = `${pending?.input ?? ""}${tool.function?.arguments ?? ""}`
+      const extraContent = pending?.extraContent ?? decodeExtraContent(tool.extra_content)
       latestToolIndex = index
       nextToolIndex = Math.max(nextToolIndex, index + 1)
       if (!current && (!id || !name)) {
         pendingTools = {
           ...pendingTools,
-          [index]: { id: id || undefined, name: name || undefined, input: text },
+          [index]: { id: id || undefined, name: name || undefined, input: text, extraContent },
         }
         continue
       }
@@ -1131,7 +1143,12 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
         ADAPTER,
         tools,
         index,
-        { id: id || undefined, name: name || undefined, text },
+        {
+          id: id || undefined,
+          name: name || undefined,
+          text,
+          providerMetadata: extraContent && { [state.providerMetadataKey]: { extraContent } },
+        },
         "OpenAI Chat tool call delta is missing id or name",
       )
       if (ToolStream.isError(result))

packages/ai/src/protocols/utils/tool-stream.ts

@@ -147,7 +147,12 @@ export const appendOrStart = <K extends StreamKey>(
   route: string,
   tools: State<K>,
   key: K,
-  delta: { readonly id?: string; readonly name?: string; readonly text: string },
+  delta: {
+    readonly id?: string
+    readonly name?: string
+    readonly text: string
+    readonly providerMetadata?: ProviderMetadata
+  },
   missingToolMessage: string,
 ): AppendOutcome<K> | AIError => {
   const current = tools[key]
@@ -161,7 +166,7 @@ export const appendOrStart = <K extends StreamKey>(
     namespace: current?.namespace,
     input: `${current?.input ?? ""}${delta.text}`,
     providerExecuted: current?.providerExecuted,
-    providerMetadata: current?.providerMetadata,
+    providerMetadata: current?.providerMetadata ?? delta.providerMetadata,
   }
   if (current && delta.text.length === 0 && current.id === id && current.name === name)
     return { tools, tool: current, events: [] }

packages/ai/test/evaluation.test.ts

@@ -39,17 +39,18 @@ describe("experimental Evaluation", () => {
         type: "choice",
         choice: "billing",
         probabilities: { billing: 0.9, technical: 0.1 },
+        confidence: 0.8,
       })
       expect(response.answers.urgency).toEqual({
         type: "score",
         score: 1.2,
         probabilities: { "0": 0, "1": 0.8, "2": 0.2 },
+        confidence: 0.6,
       })
       expect(response.answers.refund).toEqual({ type: "boolean", probability: 0.97 })
       expect(response.usage?.totalTokens).toBe(36)
       expect(response.providerMetadata).toEqual({
         typesafe: {
-          confidence: { department: 0.8, urgency: 0.6 },
           legend: { urgency: { "0": "Can wait", "1": "Needs attention", "2": "Blocking" } },
         },
       })

packages/ai/test/evaluation.types.ts

@@ -26,8 +26,10 @@ const request = Evaluation.request({
 const result = EvaluationClient.evaluate(request)
 type Result = Success<typeof result>
 type Choice = Assert<Equal<Result["answers"]["topic"]["choice"], "billing" | "support">>
+type Confidence = Assert<Equal<Result["answers"]["topic"]["confidence"], number | undefined>>
 type ClientRequirements = Assert<Equal<Requirements<typeof result>, Service>>
 void (true satisfies Choice)
+void (true satisfies Confidence)
 void (true satisfies ClientRequirements)
 
 Effect.gen(function* () {

packages/ai/test/fixtures/recordings/openai-compatible-chat/gemini-parallel-tool-signatures.json

@@ -0,0 +1,54 @@
+{
+  "version": 1,
+  "metadata": {
+    "model": "gemini-3.8-flash",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:google",
+      "protocol:openai-chat",
+      "tool",
+      "tool-loop",
+      "continuation"
+    ],
+    "name": "gemini-parallel-tool-signatures",
+    "recordedAt": "2026-09-28T03:12:05.083Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}},\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723181\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":16,\"prompt_tokens\":74,\"total_tokens\":132}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723184\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565124,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: [DONE]\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_723181\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}}},{\"id\":\"call_723184\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_723181\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"},{\"role\":\"tool\",\"tool_call_id\":\"call_723184\",\"content\":\"{\\\"temperature\\\":0,\\\"condition\\\":\\\"unknown\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"content\":\"It is currently sunny and 22°C in Paris,\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":13,\"prompt_tokens\":150,\"total_tokens\":226}}\n\ndata: {\"choices\":[{\"delta\":{\"content\":\" while Tokyo is 0°C.\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":150,\"total_tokens\":234}}\n\ndata: {\"choices\":[{\"delta\":{\"extra_content\":{\"google\":{\"thought_signature\":\"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\"}},\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":192,\"total_tokens\":276}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/provider/evaluation.recorded.test.ts

@@ -92,5 +92,6 @@ const assertEvaluation = <Options extends EvaluationOptions>(
     expect(response.answers.refund.probability).toBeGreaterThan(0.5)
     expect(response.usage?.inputTokens).toBeGreaterThan(0)
     expect(response.usage?.outputTokens).toBeGreaterThan(0)
-    expect(response.providerMetadata?.[metadataKey]?.confidence).toBeDefined()
+    expect(response.answers.department.confidence).toBeGreaterThan(0)
+    expect(response.answers.urgency.confidence).toBeGreaterThan(0)
   })

packages/ai/test/provider/gemini-openai-chat.recorded.test.ts

@@ -0,0 +1,68 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, LLMEvent, LLMRequest, Message, ToolRuntime, toDefinitions } from "../../src/index.js"
+import * as OpenAICompatible from "../../src/providers/openai-compatible.js"
+import { LLMClient } from "../../src/route.js"
+import { compileRequest } from "../../src/route/client.js"
+import { recordedTests } from "../recorded-test.js"
+import { weatherRuntimeTool, weatherToolName } from "../recorded-scenarios.js"
+
+const model = OpenAICompatible.configure({
+  provider: "google",
+  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai",
+  apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY ?? "fixture",
+}).model("gemini-3.8-flash")
+
+const recorded = recordedTests({
+  prefix: "openai-compatible-chat",
+  provider: "google",
+  protocol: "openai-chat",
+  requires: ["GOOGLE_GENERATIVE_AI_API_KEY"],
+  tags: ["tool", "tool-loop", "continuation"],
+  metadata: { model: model.id },
+})
+
+describe("Gemini OpenAI-compatible Chat recorded", () => {
+  recorded.effect.with(
+    "replays thought signatures through a parallel tool loop",
+    { cassette: "openai-compatible-chat/gemini-parallel-tool-signatures" },
+    () =>
+      Effect.gen(function* () {
+        const tools = { [weatherToolName]: weatherRuntimeTool }
+        const request = LLM.request({
+          model,
+          system: "Call get_weather for every requested city in parallel, then answer in one short sentence.",
+          prompt: "What is the weather in Paris and in Tokyo?",
+          tools: toDefinitions(tools),
+          cache: "none",
+        })
+        const first = yield* LLMClient.generate(request)
+        const calls = first.events.filter(LLMEvent.is.toolCall)
+        expect(calls.map((call) => call.input)).toEqual([{ city: "Paris" }, { city: "Tokyo" }])
+        const extraContent = calls[0]?.providerMetadata?.google?.extraContent
+        expect(extraContent).toEqual({ google: { thought_signature: expect.any(String) } })
+
+        const results = yield* Effect.forEach(calls, (call) => ToolRuntime.dispatch(tools, call))
+        const continuation = LLMRequest.update(request, {
+          messages: [
+            ...request.messages,
+            first.message,
+            ...calls.map((call, index) =>
+              Message.tool({ id: call.id, name: call.name, result: results[index]!.result }),
+            ),
+          ],
+        })
+        const prepared = yield* compileRequest(continuation)
+        const assistant = prepared.body.messages.find((message) => message.role === "assistant")
+        expect(assistant?.role === "assistant" ? assistant.tool_calls?.[0]?.extra_content : undefined).toEqual(
+          extraContent,
+        )
+
+        const second = yield* LLMClient.generate(continuation)
+        expect(second.events.filter(LLMEvent.is.toolCall)).toHaveLength(0)
+        expect(second.text).toMatch(/Paris/)
+        expect(second.text).toMatch(/Tokyo/)
+      }),
+    60_000,
+  )
+})

packages/ai/test/provider/openai-chat.test.ts

@@ -472,6 +472,45 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("replays Gemini thought signatures as tool call extra content", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Weather in Paris and Tokyo?"),
+            Message.assistant([
+              ToolCallPart.make({
+                id: "call_1",
+                name: "lookup",
+                input: { city: "Paris" },
+                providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+              }),
+              ToolCallPart.make({ id: "call_2", name: "lookup", input: { city: "Tokyo" } }),
+            ]),
+            Message.tool({ id: "call_1", name: "lookup", result: "Sunny" }),
+            Message.tool({ id: "call_2", name: "lookup", result: "Rainy" }),
+          ],
+        }),
+      )
+
+      const assistant = prepared.body.messages[1]
+      expect(assistant?.role === "assistant" ? assistant.tool_calls : undefined).toEqual([
+        {
+          id: "call_1",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Paris" }) },
+          extra_content: { google: { thought_signature: "sig_1" } },
+        },
+        {
+          id: "call_2",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Tokyo" }) },
+        },
+      ])
+    }),
+  )
+
   it.effect("limits OpenAI and Azure Chat tool call IDs to 40 characters", () =>
     Effect.gen(function* () {
       const id = `call_${"a".repeat(48)}`
@@ -1805,6 +1844,78 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("preserves Gemini thought signatures on streamed parallel tool calls", () =>
+    Effect.gen(function* () {
+      // Gemini's OpenAI-compatible endpoint omits `index`, streams each call whole,
+      // and signs only the first call of a parallel batch.
+      const body = sseEvents(
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [
+            {
+              extra_content: { google: { thought_signature: "sig_1" } },
+              id: "call_1",
+              type: "function",
+              function: { name: "lookup", arguments: '{"city":"Paris"}' },
+            },
+          ],
+        }),
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [{ id: "call_2", type: "function", function: { name: "lookup", arguments: '{"city":"Tokyo"}' } }],
+        }),
+        deltaChunk({}, "stop"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall)).toEqual([
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { city: "Paris" },
+          providerExecuted: undefined,
+          providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+        },
+        {
+          type: "tool-call",
+          id: "call_2",
+          name: "lookup",
+          input: { city: "Tokyo" },
+          providerExecuted: undefined,
+          providerMetadata: undefined,
+        },
+      ])
+    }),
+  )
+
+  it.effect("keeps extra content that arrives before the tool identity", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({
+          tool_calls: [
+            { index: 0, extra_content: { google: { thought_signature: "sig_1" } }, function: { arguments: "{" } },
+          ],
+        }),
+        deltaChunk({ tool_calls: [{ index: 0, id: "call_1", function: { name: "lookup", arguments: "}" } }] }),
+        deltaChunk({}, "tool_calls"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall).map((event) => event.providerMetadata)).toEqual([
+        { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+      ])
+    }),
+  )
+
   it.effect("does not finalize streamed tool calls when content is filtered", () =>
     Effect.gen(function* () {
       const body = sseEvents(

packages/cli/src/commands/commands.ts

@@ -51,7 +51,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
     ),
     session: Flag.string("session").pipe(
       Flag.withAlias("s"),
-      Flag.withDescription("Session ID to continue"),
+      Flag.withDescription("Session ID to continue, or to create if it does not exist"),
       Flag.optional,
     ),
     prompt: Flag.string("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
@@ -328,7 +328,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         ),
         session: Flag.string("session").pipe(
           Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
           Flag.optional,
         ),
         fork: Flag.boolean("fork").pipe(
@@ -368,7 +368,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         ),
         session: Flag.string("session").pipe(
           Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
           Flag.optional,
         ),
         fork: Flag.boolean("fork").pipe(

packages/cli/src/commands/handlers/default.ts

@@ -11,6 +11,10 @@ import { UpdatePreflight } from "../../services/update-preflight"
 import { Npm } from "@opencode/util/npm"
 import { OPENCODE_ARTIFACT, OPENCODE_CHANNEL, OPENCODE_VERSION } from "../../version"
 import { Env } from "../../env"
+import { Service } from "@opencode/client/effect/service"
+import { OpenCode } from "@opencode/client/promise"
+import { findSession } from "../../session-target"
+import { errorMessage } from "../../util/error"
 
 export default Runtime.handler(Commands, (input) =>
   Effect.gen(function* () {
@@ -46,6 +50,15 @@ export default Runtime.handler(Commands, (input) =>
         Effect.promise(() => preflight.fail("OpenCode update could not start the new background service")),
       ),
     )
+    const session = Option.getOrUndefined(input.session)
+    // A missing --session ID becomes the ID of the session the first prompt creates.
+    const sessionExists =
+      session !== undefined &&
+      (yield* Effect.tryPromise({
+        try: () =>
+          findSession(OpenCode.make({ baseUrl: server.endpoint.url, headers: Service.headers(server.endpoint) }), session),
+        catch: (cause) => new Error(errorMessage(cause)),
+      })) !== undefined
     const updater = yield* Updater.Service
     let installing: string | undefined
     const updateListeners = new Set<(version: string) => void>()
@@ -81,7 +94,8 @@ export default Runtime.handler(Commands, (input) =>
       },
       args: {
         continue: input.continue,
-        sessionID: Option.getOrUndefined(input.session),
+        sessionID: sessionExists ? session : undefined,
+        newSessionID: sessionExists ? undefined : session,
         prompt: Option.getOrUndefined(input.prompt),
         auto: input.auto || input.yolo || input.dangerouslySkipPermissions,
       },

packages/cli/src/run/noninteractive.ts

@@ -135,6 +135,7 @@ export async function runNonInteractivePrompt(input: Input) {
   const replyPermission = async (request: { id: string; action: string; resources: ReadonlyArray<string> }) => {
     if (!input.auto) {
       permissionRejected = true
+      if (input.compatibility !== "v1") process.exitCode = 1
       UI.println(
         UI.Style.TEXT_WARNING_BOLD + "!",
         UI.Style.TEXT_NORMAL +
@@ -493,7 +494,8 @@ export async function runNonInteractivePrompt(input: Input) {
       if (event.type === "session.execution.interrupted") {
         if (input.compatibility === "v1" && (permissionRejected || formCancelled)) return
         if (event.data.reason === "user" && interrupted) process.exitCode = 130
-        if (event.data.reason !== "user" && !emittedError) {
+        // A declined tool call ends the step with an interruption; it was already reported above.
+        if (event.data.reason !== "user" && !emittedError && !permissionRejected && !formCancelled) {
           emittedError = true
           process.exitCode = 1
           const error = { type: "aborted" as const, message: `Session interrupted: ${event.data.reason}` }
@@ -620,7 +622,9 @@ export async function runNonInteractivePrompt(input: Input) {
         UI.error(item.state.error.message)
       }
 
-      if (message.error && !emittedError) {
+      // A declined tool call ends its step with an interrupted-step error that is
+      // only a consequence of our own rejection; it was already reported above.
+      if (message.error && !emittedError && !permissionRejected && !formCancelled) {
         emittedError = true
         process.exitCode = 1
         if (!emit("error", timestamp, { error: message.error })) UI.error(message.error.message)

packages/cli/src/session-target.ts

@@ -63,6 +63,7 @@ export async function resolveSessionTarget(input: {
     (await input.client.session
       .create(
         {
+          id: input.session,
           agent: prepared.agent,
           model: prepared.model,
           location: { directory: location.directory },
@@ -101,14 +102,11 @@ async function selectSession(input: {
   fork?: boolean
   signal?: AbortSignal
 }) {
-  const explicit = input.session
-    ? await input.client.session.get({ sessionID: input.session }, ...requestOptions(input.signal)).catch((error) => {
-        if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError")
-          return undefined
-        throw error
-      })
-    : undefined
-  if (input.session && !explicit) throw new Error("Session not found")
+  const explicit = input.session ? await findSession(input.client, input.session, input.signal) : undefined
+  if (input.session && !explicit) {
+    if (input.fork) throw new Error("Session not found")
+    return { session: undefined }
+  }
   if (explicit)
     return {
       session: input.fork
@@ -133,6 +131,13 @@ async function selectSession(input: {
   }
 }
 
+export function findSession(client: OpenCodeClient, sessionID: string, signal?: AbortSignal) {
+  return client.session.get({ sessionID }, ...requestOptions(signal)).catch((error) => {
+    if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError") return undefined
+    throw error
+  })
+}
+
 async function latestSession(
   client: OpenCodeClient,
   location: LocationGetOutput,

packages/cli/test/session-target.test.ts

@@ -42,6 +42,28 @@ describe("session target resolver", () => {
     })
   })
 
+  test("creates a missing explicit Session with its ID", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.session, "get").mockRejectedValue({ _tag: "SessionNotFoundError" })
+    spyOn(client.location, "get").mockResolvedValue(location("/project"))
+    const create = spyOn(client.session, "create").mockResolvedValue(session("ses_chosen", "/project"))
+
+    const target = await resolveSessionTarget({ client, session: "ses_chosen", prepare })
+    expect(create).toHaveBeenCalledWith(expect.objectContaining({ id: "ses_chosen" }))
+    expect(target).toMatchObject({ session: { id: "ses_chosen" }, resume: false })
+  })
+
+  test("does not create a missing explicit Session to fork", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.session, "get").mockRejectedValue({ _tag: "SessionNotFoundError" })
+    const create = spyOn(client.session, "create")
+
+    await expect(resolveSessionTarget({ client, session: "ses_chosen", fork: true, prepare })).rejects.toThrow(
+      "Session not found",
+    )
+    expect(create).not.toHaveBeenCalled()
+  })
+
   test("paginates to continue the exact directory", async () => {
     const client = OpenCode.make({ baseUrl: "https://opencode.test" })
     spyOn(client.location, "get").mockResolvedValue(location("/project"))

packages/core/src/generate.ts

@@ -1,6 +1,7 @@
 export * as Generate from "./generate.js"
 
 import { LLM, LLMClient, AIError } from "@opencode/ai"
+import { SessionID } from "@opencode/schema/session-id"
 import { Context, Effect, Layer, Schema } from "effect"
 import { makeLocationNode } from "@opencode/util/effect/app-node"
 import { llmClient } from "./effect/app-node-platform.js"
@@ -60,15 +61,24 @@ export const layer = Layer.effect(
             ? `Model unavailable: ${input.model.providerID}/${input.model.id}`
             : "No model specified and no supported model is available",
         })
-      const response = yield* llm.generate(LLM.request({ model: resolved.model, prompt: input.prompt })).pipe(
-        Effect.mapError(
-          (error: AIError) =>
-            new UnavailableError({
-              message: error.message,
-              service: resolved.ref.providerID,
-            }),
-        ),
-      )
+      const response = yield* llm
+        .generate(
+          LLM.request({
+            model: resolved.model,
+            prompt: input.prompt,
+            // Gateways require session attribution even for a stateless call; no Session is stored.
+            http: { headers: { "x-opencode-session": SessionID.create() } },
+          }),
+        )
+        .pipe(
+          Effect.mapError(
+            (error: AIError) =>
+              new UnavailableError({
+                message: error.message,
+                service: resolved.ref.providerID,
+              }),
+          ),
+        )
       return response.text
     })
 

packages/core/src/repository.ts

@@ -145,8 +145,9 @@ function parts(input: string) {
     .filter(Boolean)
 }
 
+// cachePath makes each `:`-separated host part a directory.
 function safeHost(input: string) {
-  return Boolean(input) && !input.startsWith("-") && !/[\s/\\]/.test(input)
+  return Boolean(input) && !input.startsWith("-") && input.split(":").every(safeSegment)
 }
 
 function safeSegment(input: string) {

packages/core/src/session/model-request.ts

@@ -273,12 +273,12 @@ export const layer = Layer.effect(
         model: model.model,
         http: {
           headers: {
-            "x-session-affinity": session.id,
-            "X-Session-Id": session.id,
+            "x-session-affinity": affinity,
+            "X-Session-Id": affinity,
             ...(session.parentID ? { "x-parent-session-id": session.parentID } : {}),
             "User-Agent": App.useragent(app),
             "x-opencode-project": session.projectID,
-            "x-opencode-session": session.id,
+            "x-opencode-session": affinity,
             "x-opencode-client": app.name,
           },
         },

packages/core/test/generate.test.ts

@@ -1,5 +1,6 @@
 import { expect } from "bun:test"
-import { LanguageModel } from "@opencode/ai"
+import { LanguageModel, LLMClient } from "@opencode/ai"
+import { RequestExecutor } from "@opencode/ai/route"
 import { OpenAIChat } from "@opencode/ai/protocols"
 import { TestLLM } from "@opencode/ai/testing"
 import { AISDK } from "@opencode/core/aisdk"
@@ -10,6 +11,7 @@ import { ID, Info, Model, Ref } from "@opencode/core/model"
 import { Provider } from "@opencode/core/provider"
 import { Npm } from "@opencode/util/npm"
 import { Effect, Layer } from "effect"
+import { HttpClient, HttpClientResponse } from "effect/unstable/http"
 import { testEffect } from "./lib/effect"
 
 const selected = Info.make({
@@ -89,3 +91,56 @@ resolverIt.effect("resolves dynamic models with their catalog metadata", () =>
     })
   }),
 )
+
+testEffect(Layer.empty).effect("attributes each stateless completion without creating a stored session", () =>
+  Effect.gen(function* () {
+    const sessions: string[] = []
+    const http = Layer.succeed(
+      HttpClient.HttpClient,
+      HttpClient.make((request) =>
+        Effect.sync(() => {
+          const session = request.headers["x-opencode-session"]
+          if (!session)
+            return HttpClientResponse.fromWeb(
+              request,
+              Response.json(
+                {
+                  error: { type: "MissingSessionID", message: "Session ID is required" },
+                },
+                { status: 400 },
+              ),
+            )
+          sessions.push(session)
+          return HttpClientResponse.fromWeb(
+            request,
+            new Response(
+              `data: ${JSON.stringify({
+                id: "completion",
+                object: "chat.completion.chunk",
+                created: 1,
+                model: "gemini",
+                choices: [{ index: 0, delta: { content: "OK" }, finish_reason: "stop" }],
+              })}\n\ndata: [DONE]\n\n`,
+              { headers: { "content-type": "text/event-stream" } },
+            ),
+          )
+        }),
+      ),
+    )
+    const native = LLMClient.layer.pipe(Layer.provide(RequestExecutor.layer.pipe(Layer.provide(http))))
+    yield* Effect.gen(function* () {
+      const generate = yield* Generate.Service
+      for (let index = 0; index < 2; index++) {
+        expect(
+          yield* generate.text({
+            prompt: "Return exactly OK",
+            model: Ref.make({ providerID: selected.providerID, id: selected.id }),
+          }),
+        ).toBe("OK")
+      }
+    }).pipe(Effect.provide(Generate.layer.pipe(Layer.provide(Layer.merge(resolver, native)))))
+    expect(sessions).toHaveLength(2)
+    expect(sessions[0]).toStartWith("ses_")
+    expect(sessions[1]).not.toBe(sessions[0])
+  }),
+)

packages/core/test/repository.test.ts

@@ -41,6 +41,12 @@ describe("Repository", () => {
     })
   })
 
+  test("caches a host with a port under a directory per host part", () => {
+    expect(Repository.cachePath("/cache", Repository.parseRemote("ssh://git@example.com:2222/owner/repo"))).toBe(
+      path.join("/cache", "example.com", "2222", "owner", "repo"),
+    )
+  })
+
   test("keeps local file repositories distinct from remote repositories", () => {
     const localPath = path.resolve("repo.git")
     const reference = Repository.parse(pathToFileURL(localPath).href)
@@ -62,6 +68,18 @@ describe("Repository", () => {
     expect(() => Repository.validateBranch("bad branch")).toThrow(Repository.InvalidBranchError)
   })
 
+  test.each([
+    "..:repo",
+    "git@..:repo",
+    "../owner/repo",
+    "ssh://../repo",
+    "ssh://..:22/repo",
+    "https://%2e%2e/owner/repo",
+    ".:repo",
+  ])("rejects %s because its host contains a relative path segment", (input) => {
+    expect(() => Repository.parseRemote(input)).toThrow(Repository.InvalidReferenceError)
+  })
+
   test("compares cache identity independent of input spelling", () => {
     const shorthand = Repository.parseRemote("owner/repo")
 

packages/core/test/session-compaction.test.ts

@@ -445,12 +445,12 @@ it.effect("manual compaction summarizes short context instead of no-op", () =>
     expect(requests).toHaveLength(1)
     expect(requests[0]?.promptCacheKey).toBe(parentID)
     expect(requests[0]?.http?.headers).toEqual({
-      "x-session-affinity": sessionID,
-      "X-Session-Id": sessionID,
+      "x-session-affinity": parentID,
+      "X-Session-Id": parentID,
       "x-parent-session-id": parentID,
       "User-Agent": App.useragent(App.make()),
       "x-opencode-project": Project.ID.global,
-      "x-opencode-session": sessionID,
+      "x-opencode-session": parentID,
       "x-opencode-client": "opencode",
     })
     expect(requests[0]?.generation).toEqual(GenerationOptions.make({ maxTokens: 20_000 }))

packages/core/test/session-runner.test.ts

@@ -4693,7 +4693,12 @@ describe("SessionRunnerLLM", () => {
       .pipe(Effect.orDie)
     yield* s.runPrompt("Run child request")
 
-    expect(s.requests[0]?.http?.headers?.["x-parent-session-id"]).toBe(parentID)
+    expect(s.requests[0]?.http?.headers).toMatchObject({
+      "x-session-affinity": parentID,
+      "X-Session-Id": parentID,
+      "x-parent-session-id": parentID,
+      "x-opencode-session": parentID,
+    })
     expect(s.requests[0]?.promptCacheKey).toBe(parentID)
   })
 

packages/tui/src/component/dialog-open.tsx

@@ -208,6 +208,8 @@ export function DialogOpen(props: { sessions: SessionInfo[]; onLoad: (sessions:
     const projectOptions = data.project
       .list()
       .filter((project) => project.canonical !== "/")
+      // Historical project identities can share a checkout. The list is newest-active first.
+      .filter((project, index, projects) => projects.findIndex((item) => item.canonical === project.canonical) === index)
       .map((project) => ({ directory: project.canonical, project }))
       .map((item) => {
         const title =

packages/tui/src/component/prompt/index.tsx

@@ -53,6 +53,7 @@ import { usePromptMove } from "./move"
 import { resolvePastedAttachments } from "./local-attachment"
 import { locationKey, useData } from "../../context/data"
 import { useLocation } from "../../context/location"
+import { useArgs } from "../../context/args"
 import { Keymap, type KeymapCommand } from "../../context/keymap"
 import { useInteractivity } from "../../context/interactivity"
 import { abbreviateHome } from "../../runtime"
@@ -206,6 +207,7 @@ export function Prompt(props: PromptProps) {
   const directoryRecents = useDirectoryRecents()
   const keymapCommands = Keymap.useCommands()
   const currentLocation = useLocation()
+  const args = useArgs()
   const config = useConfig().data
   const dialog = useDialog()
   const toast = useToast()
@@ -1229,7 +1231,9 @@ export function Prompt(props: PromptProps) {
       // a local session record synchronously, so the navigation below happens
       // immediately — enter feels sent even while the create round-trip is in
       // flight. Sends against the new session gate on the request.
+      const newSessionID = args.takeNewSessionID()
       const created = data.session.create({
+        id: newSessionID,
         location: directory ? { directory } : location,
         agent: agent.id,
         model: {
@@ -1238,6 +1242,7 @@ export function Prompt(props: PromptProps) {
           variant,
         },
       })
+      if (newSessionID !== undefined) created.request.catch(() => args.restoreNewSessionID(newSessionID))
       sessionID = created.id
       session = data.session.get(created.id)
       newSession = {

packages/tui/src/context/args.tsx

@@ -1,3 +1,4 @@
+import { mergeProps } from "solid-js"
 import { createSimpleContext } from "./helper"
 
 export interface Args {
@@ -6,11 +7,25 @@ export interface Args {
   prompt?: string
   continue?: boolean
   sessionID?: string
+  newSessionID?: string
   fork?: boolean
   auto?: boolean
 }
 
 export const { use: useArgs, provider: ArgsProvider } = createSimpleContext({
   name: "Args",
-  init: (props: Args) => props,
+  init: (props: Args) => {
+    // The first new session created from home takes this ID; later ones mint their own.
+    let pending = props.newSessionID
+    return mergeProps(props, {
+      takeNewSessionID() {
+        const id = pending
+        pending = undefined
+        return id
+      },
+      restoreNewSessionID(id: string) {
+        pending ??= id
+      },
+    })
+  },
 })

packages/tui/src/routes/home.tsx

@@ -65,12 +65,13 @@ export function Home() {
     untrack(() => composer.set(prompt))
   })
 
-  // Wait for the model store to be ready before auto-submitting --prompt.
+  // Wait for everything submit needs before auto-submitting --prompt; it runs once.
   createEffect(() => {
     const r = ref()
     if (sent) return
     if (!r) return
-    if (!local.model.ready) return
+    if (!local.model.ready || !local.model.catalogReady) return
+    if (!local.agent.current() || !local.model.current()) return
     if (!args.prompt) return
     if (r.current.text !== args.prompt) return
     sent = true

packages/tui/src/routes/session/index.tsx

@@ -2808,7 +2808,7 @@ function Shell(props: ToolProps) {
       command={stringValue(props.input.command)}
       workdir={stringValue(props.input.workdir)}
       status={props.part.state.status}
-      background={Boolean(stringValue(props.metadata.shellID)) && props.part.state.status !== "running"}
+      background={props.part.state.status === "completed" && props.metadata.status === "running"}
       output={stringValue(props.metadata.shellID) ? undefined : props.output}
     />
   )

packages/tui/test/app-lifecycle.test.tsx

@@ -876,6 +876,61 @@ test("session startup prompt is submitted exactly once", async () => {
   }
 })
 
+test("home startup prompt is submitted exactly once", async () => {
+  await using state = await tmpdir()
+  const cwd = process.cwd()
+  const location = { directory: cwd, project: { id: "project", directory: cwd, canonical: cwd } }
+  const bodies: unknown[] = []
+  const submitted = Promise.withResolvers<void>()
+  let session: unknown
+  await using setup = await createAppFixture({
+    state: state.path,
+    args: { prompt: "HOME_READY" },
+    config: { animations: false, tabs: { mode: "off" } },
+    fetch: async (url, request) => {
+      if (url.pathname === "/api/location") return json(location)
+      if (url.pathname === "/api/fs/list") return json({ location, data: [] })
+      if (url.pathname === "/api/agent")
+        return json({ location, data: [{ id: "build", mode: "primary", hidden: false, permissions: [] }] })
+      if (url.pathname === "/api/model")
+        return json({ location, data: [{ id: "model", providerID: "provider", name: "Model", variants: [] }] })
+      if (url.pathname === "/api/provider") return json({ location, data: [{ id: "provider", name: "Provider" }] })
+      if (url.pathname === "/api/session" && request.method === "POST") {
+        const input: unknown = await request.json()
+        if (typeof input !== "object" || input === null) throw new Error("Expected a session input")
+        session = {
+          ...input,
+          projectID: "project",
+          cost: 0,
+          tokens: { input: 0, output: 0, reasoning: 0, cache: { read: 0, write: 0 } },
+          time: { created: 0, updated: 0 },
+        }
+        return json({ data: session })
+      }
+      if (/^\/api\/session\/[^/]+\/prompt$/.test(url.pathname)) {
+        bodies.push(await request.json())
+        submitted.resolve()
+        return json({ data: {} })
+      }
+      if (/^\/api\/session\/[^/]+\/(message|inbox|permission)$/.test(url.pathname))
+        return json({ data: [], cursor: {} })
+      if (session && /^\/api\/session\/[^/]+$/.test(url.pathname)) return json({ data: session })
+      return undefined
+    },
+  })
+
+  await setup.ready
+  await Promise.race([
+    submitted.promise,
+    Bun.sleep(2000).then(() => {
+      throw new Error("startup prompt was not submitted")
+    }),
+  ])
+  await Bun.sleep(20)
+  expect(bodies).toHaveLength(1)
+  expect(bodies[0]).toMatchObject({ text: "HOME_READY" })
+})
+
 test.each([false, true])("uses the resolved launch directory for new prompts (fallback: %s)", async (fallback) => {
   await using state = await tmpdir()
   const target = fallback ? directory : process.cwd()

packages/tui/test/new-session-id.test.tsx

@@ -0,0 +1,100 @@
+import { expect, test } from "bun:test"
+import { createAppFixture } from "./fixture/app"
+import { json } from "./fixture/tui-client"
+
+type SessionInput = { id?: string; location?: { directory: string } }
+
+const location = {
+  directory: "/tmp/opencode/packages/tui",
+  project: { id: "project", directory: "/tmp/opencode", canonical: "/tmp/opencode" },
+}
+
+function sessionInfo(record: SessionInput) {
+  return {
+    ...record,
+    location: record.location ?? { directory: location.directory },
+    projectID: "project",
+    cost: 0,
+    tokens: { input: 0, output: 0, reasoning: 0, cache: { read: 0, write: 0 } },
+    time: { created: 0, updated: 0 },
+  }
+}
+
+async function launch(options: { failCreates?: number } = {}) {
+  const attempts: (string | undefined)[] = []
+  const created: SessionInput[] = []
+  const prompts: string[] = []
+  let failures = options.failCreates ?? 0
+  const setup = await createAppFixture({
+    args: { newSessionID: "ses_chosen" },
+    config: { animations: false, keybinds: { "session.new": "f6" } },
+    fetch: async (url, request) => {
+      if (url.pathname === "/api/agent")
+        return json({ location, data: [{ id: "build", mode: "primary", hidden: false, permissions: [] }] })
+      if (url.pathname === "/api/provider") return json({ location, data: [{ id: "demo", name: "Demo" }] })
+      if (url.pathname === "/api/model")
+        return json({ location, data: [{ id: "model", providerID: "demo", name: "Demo Model", variants: [] }] })
+      if (url.pathname === "/api/session" && request.method === "POST") {
+        const record: SessionInput = await request.json()
+        attempts.push(record.id)
+        if (failures > 0) {
+          failures--
+          return json({ message: "create failed" }, { status: 500 })
+        }
+        created.push(record)
+        return json({ data: sessionInfo(record) })
+      }
+      if (/^\/api\/session\/[^/]+\/prompt$/.test(url.pathname)) {
+        prompts.push(url.pathname.split("/")[3] ?? "")
+        return json({ data: {} })
+      }
+      if (/^\/api\/session\/[^/]+\/(message|inbox|permission)$/.test(url.pathname))
+        return json({ data: [], cursor: {} })
+      if (/^\/api\/session\/[^/]+\/(agent|model)$/.test(url.pathname)) return new Response(null, { status: 204 })
+      if (/^\/api\/session\/[^/]+$/.test(url.pathname)) {
+        const record = created.find((item) => item.id === url.pathname.split("/")[3])
+        if (!record) return json({ message: "not found" }, { status: 404 })
+        return json({ data: sessionInfo(record) })
+      }
+      return undefined
+    },
+  })
+  return { setup, attempts, created, prompts }
+}
+
+test("the first new session uses the launch session ID and later ones mint their own", async () => {
+  const run = await launch()
+  await using setup = run.setup
+
+  await setup.ready
+  await setup.waitForFrame((frame) => frame.includes("Demo Model"))
+  await setup.mockInput.typeText("hello")
+  setup.mockInput.pressEnter()
+  await setup.waitForFrame(() => run.prompts.length === 1)
+  expect(run.prompts[0]).toBe("ses_chosen")
+  expect(run.created.map((item) => item.id)).toEqual(["ses_chosen"])
+
+  setup.mockInput.pressKey("F6")
+  await setup.renderOnce()
+  await setup.mockInput.typeText("again")
+  setup.mockInput.pressEnter()
+  await setup.waitForFrame(() => run.created.length === 2)
+  expect(run.created[1]?.id).toMatch(/^ses/)
+  expect(run.created[1]?.id).not.toBe("ses_chosen")
+})
+
+test("a failed first create keeps the launch session ID for the retry", async () => {
+  const run = await launch({ failCreates: 1 })
+  await using setup = run.setup
+
+  await setup.ready
+  await setup.waitForFrame((frame) => frame.includes("Demo Model"))
+  await setup.mockInput.typeText("hello")
+  setup.mockInput.pressEnter()
+  await setup.waitForFrame((frame) => frame.includes("Creating a session failed") && frame.includes("hello"))
+  expect(run.attempts).toEqual(["ses_chosen"])
+
+  setup.mockInput.pressEnter()
+  await setup.waitForFrame(() => run.created.length === 1)
+  expect(run.attempts).toEqual(["ses_chosen", "ses_chosen"])
+})

script/release.ts

@@ -61,7 +61,9 @@ if ((await editor.exited) !== 0) {
 const document = await Bun.file(review).text()
 const notes = document.match(/<!-- changelog:start -->\s*([\s\S]*?)\s*<!-- changelog:end -->/)
 if (!notes) throw new Error("Release review is missing its changelog markers")
-await Bun.write(changelog, `${notes[1].trim()}\n`)
+const releaseNotes = notes[1].trim()
+if (!releaseNotes) throw new Error("Release review has no changelog")
+await Bun.write(changelog, `${releaseNotes}\n`)
 
 const answer = prompt(`Trigger the ${version} release? [y/N]`)
 if (answer?.trim().toLowerCase() !== "y" && answer?.trim().toLowerCase() !== "yes") {
@@ -69,7 +71,7 @@ if (answer?.trim().toLowerCase() !== "y" && answer?.trim().toLowerCase() !== "ye
   process.exit(0)
 }
 
-await $`gh workflow run publish.yml --ref v2 ${input}`
+await $`gh workflow run publish.yml --ref v2 ${input} -f release_notes=${releaseNotes}`
 console.log(`Triggered the ${version} release`)
 
 async function generateReview(base: string) {

services/www/src/docs/components/DocsPage.astro

@@ -5,6 +5,7 @@ import Card from "./Card.astro"
 import CardGroup from "./CardGroup.astro"
 import CodeBlock from "./CodeBlock.astro"
 import CodeTabs from "./CodeTabs.astro"
+import PlanTabs from "./PlanTabs.astro"
 import DocsLayout from "../layouts/DocsLayout.astro"
 
 interface Props {
@@ -22,5 +23,5 @@ const rendered = await render(entry)
   headings={rendered.headings}
   showTableOfContents={entry.data.tableOfContents !== false}
 >
-  <rendered.Content components={{ Callout, Card, CardGroup, CodeBlock, CodeTabs }} />
+  <rendered.Content components={{ Callout, Card, CardGroup, CodeBlock, CodeTabs, PlanTabs }} />
 </DocsLayout>

services/www/src/docs/components/PlanTabs.astro

@@ -0,0 +1,103 @@
+---
+interface Props {
+  id: string
+  label: string
+  syncKey: string
+}
+
+const plans = [
+  { id: "go", label: "Go" },
+  { id: "go-plus", label: "Go Plus" },
+] as const
+---
+
+<div class="docs-plan-tabs" data-plan-tabs data-sync-key={Astro.props.syncKey}>
+  <div class="docs-plan-tabs-list" role="tablist" aria-label={Astro.props.label}>
+    {
+      plans.map((plan, index) => (
+        <button
+          type="button"
+          role="tab"
+          id={`${Astro.props.id}-tab-${plan.id}`}
+          aria-controls={`${Astro.props.id}-panel-${plan.id}`}
+          aria-selected={index === 0 ? "true" : "false"}
+          tabindex={index === 0 ? 0 : -1}
+          data-plan-tab={plan.id}
+        >
+          {plan.label}
+        </button>
+      ))
+    }
+  </div>
+  {
+    plans.map((plan, index) => (
+      <div
+        role="tabpanel"
+        id={`${Astro.props.id}-panel-${plan.id}`}
+        aria-labelledby={`${Astro.props.id}-tab-${plan.id}`}
+        hidden={index !== 0}
+        data-plan-panel={plan.id}
+      >
+        <slot name={plan.id} />
+      </div>
+    ))
+  }
+</div>
+
+<script>
+  const selectPlan = (tabs: HTMLElement, plan: string) => {
+    tabs.querySelectorAll<HTMLButtonElement>("[data-plan-tab]").forEach((button) => {
+      const selected = button.dataset.planTab === plan
+      button.setAttribute("aria-selected", String(selected))
+      button.tabIndex = selected ? 0 : -1
+    })
+    tabs.querySelectorAll<HTMLElement>("[data-plan-panel]").forEach((panel) => {
+      panel.hidden = panel.dataset.planPanel !== plan
+    })
+  }
+
+  const selectSyncedPlan = (source: HTMLElement, plan: string) => {
+    const syncKey = source.dataset.syncKey
+    if (!syncKey) return
+    document.querySelectorAll<HTMLElement>("[data-plan-tabs]").forEach((tabs) => {
+      if (tabs.dataset.syncKey === syncKey) selectPlan(tabs, plan)
+    })
+    localStorage.setItem(`docs-plan-tabs:${syncKey}`, plan)
+  }
+
+  document.querySelectorAll<HTMLElement>("[data-plan-tabs]").forEach((tabs) => {
+    const syncKey = tabs.dataset.syncKey
+    const plan = syncKey ? localStorage.getItem(`docs-plan-tabs:${syncKey}`) : undefined
+    if (plan) selectPlan(tabs, plan)
+  })
+
+  document.addEventListener("click", (event) => {
+    if (!(event.target instanceof Element)) return
+    const button = event.target.closest<HTMLButtonElement>("[data-plan-tab]")
+    const tabs = button?.closest<HTMLElement>("[data-plan-tabs]")
+    if (!button || !tabs || !button.dataset.planTab) return
+    selectSyncedPlan(tabs, button.dataset.planTab)
+  })
+
+  document.addEventListener("keydown", (event) => {
+    if (!(event.target instanceof HTMLButtonElement) || !event.target.matches("[data-plan-tab]")) return
+    const tabs = event.target.closest<HTMLElement>("[data-plan-tabs]")
+    if (!tabs) return
+    const buttons = [...tabs.querySelectorAll<HTMLButtonElement>("[data-plan-tab]")]
+    const selected = buttons.indexOf(event.target)
+    const next =
+      event.key === "Home"
+        ? buttons[0]
+        : event.key === "End"
+          ? buttons.at(-1)
+          : event.key === "ArrowRight"
+            ? buttons[(selected + 1) % buttons.length]
+            : event.key === "ArrowLeft"
+              ? buttons[(selected - 1 + buttons.length) % buttons.length]
+              : undefined
+    if (!next?.dataset.planTab) return
+    event.preventDefault()
+    selectSyncedPlan(tabs, next.dataset.planTab)
+    next.focus()
+  })
+</script>

services/www/src/docs/content/console/go.mdx

@@ -1,17 +1,22 @@
 ---
 title: "Go"
-description: "Low cost subscription for open coding models."
+description: "Reliable access to open coding models with two usage tiers."
 ---
 
-OpenCode Go is a low cost **$10/month subscription** that gives you reliable access to popular open coding models.
+OpenCode Go gives you reliable access to popular open coding models, with two monthly plans:
+
+| Plan | Price | Included usage |
+| ---- | ----- | -------------- |
+| **Go** | **$10/month** | Lower-cost access to the models below |
+| **Go Plus** | **$40/month** | Higher usage limits across the models below |
 
 Go works like any other provider in OpenCode. You subscribe to OpenCode Go and get your API key. It's **completely optional** and you don't need it to use OpenCode.
 
-It is designed primarily for international users and provides stable global access.
+The service is designed primarily for international users and provides stable global access.
 
 ## How it works
 
-1. Sign in to the [OpenCode console](https://opencode.ai/console), subscribe to Go, add your billing details, and copy your API key.
+1. Sign in to the [OpenCode Console](https://opencode.ai/console), subscribe to Go or Go Plus, add your billing details, and copy your API key.
 2. Run `/connect` in the TUI, select **OpenCode Go**, and paste your API key.
 
    ```text
@@ -24,7 +29,7 @@ It is designed primarily for international users and provides stable global acce
    /models
    ```
 
-<Callout>Only one member per workspace can subscribe to OpenCode Go.</Callout>
+<Callout>Only one member per workspace can subscribe to OpenCode Go or Go Plus.</Callout>
 
 The current list of models includes:
 
@@ -33,13 +38,13 @@ The current list of models includes:
 - **GLM-5.3-Flash**
 - **GLM-5.3**
 - **GLM-5.2**
-- **GLM-5.1**
 - **GPT 6 Luna**
 - **GPT 5.6 Luna**
 - **Kimi K3**
 - **Kimi K2.7 Code**
 - **Kimi K2.6**
 - **LongCat-2.0**
+- **LongCat 2.5 Preview Free** (limited time)
 - **MiMo-V2.6-Flash**
 - **MiMo-V2.6-Pro**
 - **MiMo-V2.5**
@@ -50,9 +55,7 @@ The current list of models includes:
 - **Muse Spark 1.2 Contributor** ([limited regions](https://ai.developer.meta.com/legal/geographic-use-policy))
 - **Qwen3.8 Max**
 - **Qwen3.8 Flash**
-- **Qwen3.7 Max**
 - **Qwen3.7 Plus**
-- **Qwen3.6 Plus**
 - **DeepSeek V4.1 Flash**
 - **DeepSeek V4 Pro**
 - **DeepSeek V4 Flash**
@@ -60,7 +63,6 @@ The current list of models includes:
 - **Hy4 preview**
 - **Hy3**
 - **Space Bunny Free** (limited time)
-- **LongCat 2.5 Preview Free** (limited time)
 
 The list of models may change as we test and add new ones.
 
@@ -109,127 +111,202 @@ investigated. The linked reports track fixes and workarounds.
 ## Usage limits
 
 Usage limits are defined as monthly dollar amounts. The table below shows the
-monthly limit and token costs for each model.
+monthly limit for each plan and the token costs for each model. Token pricing is
+the same for Go and Go Plus.
 
 Each model has the following usage limits: 5-hour — 20% of the monthly limit;
 weekly — 50%; and monthly — 100%.
 
-For example, if a model has a $60 monthly limit, you can spend up to:
-
-- **5-hour limit** — $12 of usage
-- **Weekly limit** — $30 of usage
-- **Monthly limit** — $60 of usage
+Each model's monthly limit below determines how its usage counts toward those allowances.
 
 Token prices are per 1M tokens.
 
-<div class="docs-table-scroll" role="region" aria-label="Go model pricing" tabIndex={0}>
+<PlanTabs id="go-pricing" label="Go plan" syncKey="go-plan">
+  <div slot="go">
 
-| Model                                   | Input  | Output | Cached Read | Cached Write | Monthly limit                                        |
-| --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------------- |
-| GLM-5.3-Flash                           | $0.15  | $0.50  | $0.03       | -            | **$60**                                              |
-| GLM-5.3                                 | $1.40  | $4.40  | $0.26       | -            | **$15**                                              |
-| GLM-5.2                                 | $1.40  | $4.40  | $0.26       | -            | **$60**                                              |
-| GLM-5.1                                 | $1.40  | $4.40  | $0.26       | -            | **$60**                                              |
-| Kimi K3                                 | $3.00  | $15.00 | $0.30       | -            | **$15**                                              |
-| Kimi K2.7 Code                          | $0.95  | $4.00  | $0.19       | -            | **$60**                                              |
-| Kimi K2.6                               | $0.95  | $4.00  | $0.16       | -            | **$60**                                              |
-| LongCat-2.0                             | $0.30  | $1.20  | $0.006      | -            | **$60**                                              |
-| MiMo-V2.6-Flash                         | $0.14  | $0.28  | $0.0028     | -            | **$60**                                              |
-| MiMo-V2.6-Pro                           | $0.435 | $0.87  | $0.003625   | -            | **$15**                                              |
-| MiMo-V2.5                               | $0.14  | $0.28  | $0.0028     | -            | **$60**                                              |
-| MiMo-V2.5-Pro                           | $0.435 | $0.87  | $0.003625   | -            | **$15**                                              |
-| MiniMax M3                              | $0.30  | $1.20  | $0.06       | -            | **$60**                                              |
-| MiniMax M2.7                            | $0.30  | $1.20  | $0.06       | $0.375       | **$60**                                              |
-| MiniMax M2.5                            | $0.30  | $1.20  | $0.06       | $0.375       | **$60**                                              |
-| Muse Spark 1.3 Contributor              | $0.10  | $0.20  | $0.002      | -            | **$60**                                              |
-| Muse Spark 1.2 Contributor              | $0.10  | $0.20  | $0.002      | -            | **$60**                                              |
-| Qwen3.8 Max                             | $2.00  | $6.00  | $0.25       | $2.50        | **$15**                                              |
-| Qwen3.8 Flash                           | $0.15  | $0.47  | $0.016      | $0.20        | **$30**                                              |
-| Qwen3.7 Max                             | $2.50  | $7.50  | $0.50       | $3.125       | **$30**                                              |
-| Qwen3.7 Plus (≤ 256K tokens)            | $0.40  | $1.60  | $0.04       | $0.50        | **$60**                                              |
-| Qwen3.7 Plus (> 256K tokens)            | $1.20  | $4.80  | $0.12       | $1.50        | **$60**                                              |
-| Qwen3.6 Plus (≤ 256K tokens)            | $0.50  | $3.00  | $0.05       | $0.625       | **$60**                                              |
-| Qwen3.6 Plus (> 256K tokens)            | $2.00  | $6.00  | $0.20       | $2.50        | **$60**                                              |
-| DeepSeek V4.1 Flash (Off-Peak)          | $0.15  | $0.60  | $0.003      | -            | **$60**                                              |
-| DeepSeek V4.1 Flash (Peak)              | $0.30  | $1.20  | $0.006      | -            | **$60**                                              |
-| DeepSeek V4 Pro (Off-Peak)              | $0.66  | $1.98  | $0.022      | -            | **$15**                                              |
-| DeepSeek V4 Pro (Peak)                  | $1.32  | $3.96  | $0.044      | -            | **$15**                                              |
-| DeepSeek V4 Flash (Off-Peak)            | $0.15  | $0.60  | $0.003      | -            | **$30**                                              |
-| DeepSeek V4 Flash (Peak)                | $0.30  | $1.20  | $0.006      | -            | **$30**                                              |
-| DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15  | $0.60  | $0.003      | -            | **$15**                                              |
-| DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                              |
-| Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                              |
-| Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                              |
-| Space Bunny Free                        | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small>       |
-| LongCat 2.5 Preview Free                | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small>       |
-| Grok 4.7 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                              |
-| Grok 4.7 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                              |
-| Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                              |
-| Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                              |
-| GPT 6 Luna (≤ 272K tokens)              | $0.10  | $0.50  | $0.01       | $0.125       | **$15**                                              |
-| GPT 6 Luna (> 272K tokens)              | $0.20  | $0.75  | $0.02       | $0.25        | **$15**                                              |
-| GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                              |
-| GPT 5.6 Luna (> 272K tokens)            | $0.40  | $1.80  | $0.04       | $0.50        | **$15**                                              |
+    | Model                                   | Input  | Output | Cached Read | Cached Write | Monthly limit                                  |
+    | --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
+    | GLM-5.3-Flash                           | $0.15  | $0.50  | $0.03       | -            | **$60**                                        |
+    | GLM-5.3                                 | $1.40  | $4.40  | $0.26       | -            | **$15**                                        |
+    | GLM-5.2                                 | $1.40  | $4.40  | $0.26       | -            | **$60**                                        |
+    | Kimi K3                                 | $3.00  | $15.00 | $0.30       | -            | **$15**                                        |
+    | Kimi K2.7 Code                          | $0.95  | $4.00  | $0.19       | -            | **$60**                                        |
+    | Kimi K2.6                               | $0.95  | $4.00  | $0.16       | -            | **$60**                                        |
+    | LongCat-2.0                             | $0.30  | $1.20  | $0.006      | -            | **$60**                                        |
+    | LongCat 2.5 Preview Free                | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small> |
+    | MiMo-V2.6-Flash                         | $0.14  | $0.28  | $0.0028     | -            | **$60**                                        |
+    | MiMo-V2.6-Pro                           | $0.435 | $0.87  | $0.003625   | -            | **$15**                                        |
+    | MiMo-V2.5                               | $0.14  | $0.28  | $0.0028     | -            | **$60**                                        |
+    | MiMo-V2.5-Pro                           | $0.435 | $0.87  | $0.003625   | -            | **$15**                                        |
+    | MiniMax M3                              | $0.30  | $1.20  | $0.06       | -            | **$60**                                        |
+    | MiniMax M2.7                            | $0.30  | $1.20  | $0.06       | $0.375       | **$60**                                        |
+    | Muse Spark 1.3 Contributor              | $0.10  | $0.20  | $0.002      | -            | **$60**                                        |
+    | Muse Spark 1.2 Contributor              | $0.10  | $0.20  | $0.002      | -            | **$60**                                        |
+    | Qwen3.8 Max                             | $2.00  | $6.00  | $0.25       | $2.50        | **$15**                                        |
+    | Qwen3.8 Flash                           | $0.15  | $0.47  | $0.016      | $0.20        | **$30**                                        |
+    | Qwen3.7 Plus (≤ 256K tokens)            | $0.40  | $1.60  | $0.04       | $0.50        | **$60**                                        |
+    | Qwen3.7 Plus (> 256K tokens)            | $1.20  | $4.80  | $0.12       | $1.50        | **$60**                                        |
+    | DeepSeek V4.1 Flash (Off-Peak)          | $0.15  | $0.60  | $0.003      | -            | **$60**                                        |
+    | DeepSeek V4.1 Flash (Peak)              | $0.30  | $1.20  | $0.006      | -            | **$60**                                        |
+    | DeepSeek V4 Pro (Off-Peak)              | $0.66  | $1.98  | $0.022      | -            | **$15**                                        |
+    | DeepSeek V4 Pro (Peak)                  | $1.32  | $3.96  | $0.044      | -            | **$15**                                        |
+    | DeepSeek V4 Flash (Off-Peak)            | $0.15  | $0.60  | $0.003      | -            | **$30**                                        |
+    | DeepSeek V4 Flash (Peak)                | $0.30  | $1.20  | $0.006      | -            | **$30**                                        |
+    | DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15  | $0.60  | $0.003      | -            | **$15**                                        |
+    | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$15**                                        |
+    | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$30**                                        |
+    | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$60**                                        |
+    | Space Bunny Free                        | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small> |
+    | Grok 4.7 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                        |
+    | Grok 4.7 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                        |
+    | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$15**                                        |
+    | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$15**                                        |
+    | GPT 6 Luna (≤ 272K tokens)              | $0.10  | $0.50  | $0.01       | $0.125       | **$15**                                        |
+    | GPT 6 Luna (> 272K tokens)              | $0.20  | $0.75  | $0.02       | $0.25        | **$15**                                        |
+    | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$15**                                        |
+    | GPT 5.6 Luna (> 272K tokens)            | $0.40  | $1.80  | $0.04       | $0.50        | **$15**                                        |
 
-</div>
+  </div>
+  <div slot="go-plus">
+
+    | Model                                   | Input  | Output | Cached Read | Cached Write | Monthly limit                                  |
+    | --------------------------------------- | ------ | ------ | ----------- | ------------ | ---------------------------------------------- |
+    | GLM-5.3-Flash                           | $0.15  | $0.50  | $0.03       | -            | **$180**                                       |
+    | GLM-5.3                                 | $1.40  | $4.40  | $0.26       | -            | **$120**                                       |
+    | GLM-5.2                                 | $1.40  | $4.40  | $0.26       | -            | **$180**                                       |
+    | Kimi K3                                 | $3.00  | $15.00 | $0.30       | -            | **$60**                                        |
+    | Kimi K2.7 Code                          | $0.95  | $4.00  | $0.19       | -            | **$180**                                       |
+    | Kimi K2.6                               | $0.95  | $4.00  | $0.16       | -            | **$240**                                       |
+    | LongCat-2.0                             | $0.30  | $1.20  | $0.006      | -            | **$240**                                       |
+    | LongCat 2.5 Preview Free                | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small> |
+    | MiMo-V2.6-Flash                         | $0.14  | $0.28  | $0.0028     | -            | **$120**                                       |
+    | MiMo-V2.6-Pro                           | $0.435 | $0.87  | $0.003625   | -            | **$60**                                        |
+    | MiMo-V2.5                               | $0.14  | $0.28  | $0.0028     | -            | **$120**                                       |
+    | MiMo-V2.5-Pro                           | $0.435 | $0.87  | $0.003625   | -            | **$60**                                        |
+    | MiniMax M3                              | $0.30  | $1.20  | $0.06       | -            | **$180**                                       |
+    | MiniMax M2.7                            | $0.30  | $1.20  | $0.06       | $0.375       | **$240**                                       |
+    | Muse Spark 1.3 Contributor              | $0.10  | $0.20  | $0.002      | -            | **$120**                                       |
+    | Muse Spark 1.2 Contributor              | $0.10  | $0.20  | $0.002      | -            | **$120**                                       |
+    | Qwen3.8 Max                             | $2.00  | $6.00  | $0.25       | $2.50        | **$60**                                        |
+    | Qwen3.8 Flash                           | $0.15  | $0.47  | $0.016      | $0.20        | **$90**                                        |
+    | Qwen3.7 Plus (≤ 256K tokens)            | $0.40  | $1.60  | $0.04       | $0.50        | **$180**                                       |
+    | Qwen3.7 Plus (> 256K tokens)            | $1.20  | $4.80  | $0.12       | $1.50        | **$180**                                       |
+    | DeepSeek V4.1 Flash (Off-Peak)          | $0.15  | $0.60  | $0.003      | -            | **$120**                                       |
+    | DeepSeek V4.1 Flash (Peak)              | $0.30  | $1.20  | $0.006      | -            | **$120**                                       |
+    | DeepSeek V4 Pro (Off-Peak)              | $0.66  | $1.98  | $0.022      | -            | **$60**                                        |
+    | DeepSeek V4 Pro (Peak)                  | $1.32  | $3.96  | $0.044      | -            | **$60**                                        |
+    | DeepSeek V4 Flash (Off-Peak)            | $0.15  | $0.60  | $0.003      | -            | **$120**                                       |
+    | DeepSeek V4 Flash (Peak)                | $0.30  | $1.20  | $0.006      | -            | **$120**                                       |
+    | DeepSeek V4 Flash Vision Exp (Off-Peak) | $0.15  | $0.60  | $0.003      | -            | **$60**                                        |
+    | DeepSeek V4 Flash Vision Exp (Peak)     | $0.30  | $1.20  | $0.006      | -            | **$60**                                        |
+    | Hy4 preview                             | $0.834 | $2.501 | $0.042      | -            | **$120**                                       |
+    | Hy3                                     | $0.14  | $0.58  | $0.035      | -            | **$240**                                       |
+    | Space Bunny Free                        | Free   | Free   | Free        | -            | **Unlimited**<br /><small>limited time</small> |
+    | Grok 4.7 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$60**                                        |
+    | Grok 4.7 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$60**                                        |
+    | Grok 4.6 (≤ 200K tokens)                | $2.00  | $6.00  | $0.50       | -            | **$60**                                        |
+    | Grok 4.6 (> 200K tokens)                | $4.00  | $12.00 | $1.00       | -            | **$60**                                        |
+    | GPT 6 Luna (≤ 272K tokens)              | $0.10  | $0.50  | $0.01       | $0.125       | **$60**                                        |
+    | GPT 6 Luna (> 272K tokens)              | $0.20  | $0.75  | $0.02       | $0.25        | **$60**                                        |
+    | GPT 5.6 Luna (≤ 272K tokens)            | $0.20  | $1.20  | $0.02       | $0.25        | **$60**                                        |
+    | GPT 5.6 Luna (> 272K tokens)            | $0.40  | $1.80  | $0.04       | $0.50        | **$60**                                        |
+
+  </div>
+</PlanTabs>
 
 **Space Bunny Free:** Free for a limited time.
 
 **LongCat 2.5 Preview Free:** Free for a limited time.
 
-**DeepSeek V4.1 Flash / V4 Pro / V4 Flash Vision Exp:** Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday through Friday; all other hours, including weekends, are Off-Peak. [Learn more](https://api-docs.deepseek.com/quick_start/pricing/).
+**DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp:** Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday through Friday; all other hours, including weekends, are Off-Peak. [Learn more](https://api-docs.deepseek.com/quick_start/pricing/).
 
 **DeepSeek V4 Flash Vision Exp:** Images are converted into tokens based on their dimensions and billed as input tokens alongside text tokens. [Learn more](https://api-docs.deepseek.com/quick_start/pricing/).
 
 ### Estimated requests
 
-The table below provides an estimated request count based on typical Go usage patterns:
+The tables below estimate request counts based on typical Go usage patterns. Go
+Plus estimates scale with each model's higher usage limit.
 
-<div class="docs-table-scroll" role="region" aria-label="Go estimated requests" tabIndex={0}>
+<PlanTabs id="go-requests" label="Go plan" syncKey="go-plan">
+  <div slot="go">
 
-| Model                                                    | requests per 5 hour       | requests per week          | requests per month          |
-| -------------------------------------------------------- | ------------------------- | -------------------------- | --------------------------- |
-| GLM-5.3-Flash                                            | 6,320                     | 15,790                     | 31,580                      |
-| GLM-5.3                                                  | 220                       | 540                        | 1,080                       |
-| GLM-5.2                                                  | 880                       | 2,150                      | 4,300                       |
-| GLM-5.1                                                  | 880                       | 2,150                      | 4,300                       |
-| Kimi K3                                                  | 110                       | 250                        | 490                         |
-| Kimi K2.7 Code                                           | 1,350                     | 3,380                      | 6,750                       |
-| Kimi K2.6                                                | 1,150                     | 2,880                      | 5,750                       |
-| LongCat-2.0                                              | 11,400                    | 28,600                     | 57,200                      |
-| MiMo-V2.6-Flash                                          | 30,100                    | 75,200                     | 150,400                     |
-| MiMo-V2.6-Pro                                            | 3,250                     | 8,150                      | 16,300                      |
-| MiMo-V2.5                                                | 30,100                    | 75,200                     | 150,400                     |
-| MiMo-V2.5-Pro                                            | 3,250                     | 8,150                      | 16,300                      |
-| MiniMax M3                                               | 3,200                     | 8,000                      | 16,000                      |
-| MiniMax M2.7                                             | 3,400                     | 8,500                      | 17,000                      |
-| Muse Spark 1.3 Contributor                               | 45,300                    | 113,300                    | 226,600                     |
-| Muse Spark 1.2 Contributor                               | 45,300                    | 113,300                    | 226,600                     |
-| Qwen3.8 Max                                              | 160                       | 400                        | 810                         |
-| Qwen3.8 Flash                                            | 5,400                     | 13,500                     | 27,000                      |
-| Qwen3.7 Max                                              | 170                       | 420                        | 840                         |
-| Qwen3.7 Plus                                             | 4,300                     | 10,800                     | 21,600                      |
-| Qwen3.6 Plus                                             | 3,300                     | 8,200                      | 16,300                      |
-| DeepSeek V4.1 Flash                                    | 26,000                   | 65,000                   | 130,000                   |
-| DeepSeek V4 Pro                                          | 1,050                     | 2,600                      | 5,200                       |
-| DeepSeek V4 Flash                                        | 13,000                    | 32,500                     | 65,000                      |
-| DeepSeek V4 Flash Vision Exp                             | 6,500                     | 16,250                     | 32,500                      |
-| Hy4 preview                                              | 1,350                     | 3,380                      | 6,770                       |
-| Hy3                                                      | 4,300                     | 10,750                     | 21,500                      |
-| Space Bunny Free                                         | Unlimited                 | Unlimited                  | Unlimited                   |
-| LongCat 2.5 Preview Free                                 | Unlimited                 | Unlimited                  | Unlimited                   |
-| Grok 4.7                                                 | 169                       | 423                        | 845                         |
-| Grok 4.6                                                 | 169                       | 423                        | 845                         |
-| GPT 6 Luna                                               | 4,230                     | 10,560                     | 21,130                      |
-| GPT 5.6 Luna                                             | 2,050                     | 5,100                      | 10,250                      |
+    | Model                        | Requests per 5 hours | Requests per week | Requests per month |
+    | ---------------------------- | -------------------- | ----------------- | ------------------ |
+    | GLM-5.3-Flash                | 6,320                | 15,790            | 31,580             |
+    | GLM-5.3                      | 220                  | 540               | 1,080              |
+    | GLM-5.2                      | 880                  | 2,150             | 4,300              |
+    | Kimi K3                      | 110                  | 250               | 490                |
+    | Kimi K2.7 Code               | 1,350                | 3,380             | 6,750              |
+    | Kimi K2.6                    | 1,150                | 2,880             | 5,750              |
+    | LongCat-2.0                  | 11,400               | 28,600            | 57,200             |
+    | LongCat 2.5 Preview Free     | Unlimited            | Unlimited         | Unlimited          |
+    | MiMo-V2.6-Flash              | 30,100               | 75,200            | 150,400            |
+    | MiMo-V2.6-Pro                | 3,250                | 8,150             | 16,300             |
+    | MiMo-V2.5                    | 30,100               | 75,200            | 150,400            |
+    | MiMo-V2.5-Pro                | 3,250                | 8,150             | 16,300             |
+    | MiniMax M3                   | 3,200                | 8,000             | 16,000             |
+    | MiniMax M2.7                 | 3,400                | 8,500             | 17,000             |
+    | Muse Spark 1.3 Contributor   | 45,300               | 113,300           | 226,600            |
+    | Muse Spark 1.2 Contributor   | 45,300               | 113,300           | 226,600            |
+    | Qwen3.8 Max                  | 160                  | 400               | 810                |
+    | Qwen3.8 Flash                | 5,400                | 13,500            | 27,000             |
+    | Qwen3.7 Plus                 | 4,300                | 10,800            | 21,600             |
+    | DeepSeek V4.1 Flash          | 26,000               | 65,000            | 130,000            |
+    | DeepSeek V4 Pro              | 1,050                | 2,600             | 5,200              |
+    | DeepSeek V4 Flash            | 13,000               | 32,500            | 65,000             |
+    | DeepSeek V4 Flash Vision Exp | 6,500                | 16,250            | 32,500             |
+    | Hy4 preview                  | 1,350                | 3,380             | 6,770              |
+    | Hy3                          | 4,300                | 10,750            | 21,500             |
+    | Space Bunny Free             | Unlimited            | Unlimited         | Unlimited          |
+    | Grok 4.7                     | 169                  | 423               | 845                |
+    | Grok 4.6                     | 169                  | 423               | 845                |
+    | GPT 6 Luna                   | 4,230                | 10,560            | 21,130             |
+    | GPT 5.6 Luna                 | 2,050                | 5,100             | 10,250             |
 
-</div>
+  </div>
+  <div slot="go-plus">
+
+    | Model                        | Requests per 5 hours | Requests per week | Requests per month |
+    | ---------------------------- | -------------------- | ----------------- | ------------------ |
+    | GLM-5.3-Flash                | 18,960               | 47,370            | 94,740             |
+    | GLM-5.3                      | 1,760                | 4,320             | 8,640              |
+    | GLM-5.2                      | 2,640                | 6,450             | 12,900             |
+    | Kimi K3                      | 440                  | 1,000             | 1,960              |
+    | Kimi K2.7 Code               | 4,050                | 10,140            | 20,250             |
+    | Kimi K2.6                    | 4,600                | 11,520            | 23,000             |
+    | LongCat-2.0                  | 45,600               | 114,400           | 228,800            |
+    | LongCat 2.5 Preview Free     | Unlimited            | Unlimited         | Unlimited          |
+    | MiMo-V2.6-Flash              | 60,200               | 150,400           | 300,800            |
+    | MiMo-V2.6-Pro                | 13,000               | 32,600            | 65,200             |
+    | MiMo-V2.5                    | 60,200               | 150,400           | 300,800            |
+    | MiMo-V2.5-Pro                | 13,000               | 32,600            | 65,200             |
+    | MiniMax M3                   | 9,600                | 24,000            | 48,000             |
+    | MiniMax M2.7                 | 13,600               | 34,000            | 68,000             |
+    | Muse Spark 1.3 Contributor   | 90,600               | 226,600           | 453,200            |
+    | Muse Spark 1.2 Contributor   | 90,600               | 226,600           | 453,200            |
+    | Qwen3.8 Max                  | 640                  | 1,600             | 3,240              |
+    | Qwen3.8 Flash                | 16,200               | 40,500            | 81,000             |
+    | Qwen3.7 Plus                 | 12,900               | 32,400            | 64,800             |
+    | DeepSeek V4.1 Flash          | 52,000               | 130,000           | 260,000            |
+    | DeepSeek V4 Pro              | 4,200                | 10,400            | 20,800             |
+    | DeepSeek V4 Flash            | 52,000               | 130,000           | 260,000            |
+    | DeepSeek V4 Flash Vision Exp | 26,000               | 65,000            | 130,000            |
+    | Hy4 preview                  | 5,400                | 13,520            | 27,080             |
+    | Hy3                          | 17,200               | 43,000            | 86,000             |
+    | Space Bunny Free             | Unlimited            | Unlimited         | Unlimited          |
+    | Grok 4.7                     | 676                  | 1,692             | 3,380              |
+    | Grok 4.6                     | 676                  | 1,692             | 3,380              |
+    | GPT 6 Luna                   | 16,920               | 42,240            | 84,520             |
+    | GPT 5.6 Luna                 | 8,200                | 20,400            | 41,000             |
+
+  </div>
+</PlanTabs>
 
 The estimates use the following token counts per request; actual usage varies.
 
 - Grok 4.7/4.6 — 390 input, 32,500 cached, 120 output tokens per request
 - GLM-5.3-Flash — 1,000 input, 55,000 cached, 200 output tokens per request
-- GLM-5.3/5.2/5.1 — 700 input, 52,000 cached, 150 output tokens per request
+- GLM-5.3/5.2 — 700 input, 52,000 cached, 150 output tokens per request
 - GPT 6 Luna — 1,000 input, 50,000 cached, 220 output tokens per request
 - GPT 5.6 Luna — 1,000 input, 50,000 cached, 220 output tokens per request
 - Kimi K3 — 1,050 input, 76,500 cached, 300 output tokens per request
@@ -249,9 +326,7 @@ The estimates use the following token counts per request; actual usage varies.
 - MiMo-V2.5-Pro — 790 input, 86,000 cached, 305 output tokens per request
 - Qwen3.8 Max — 420 input, 66,000 cached, 200 output tokens per request
 - Qwen3.8 Flash — 600 input, 58,000 cached, 200 output tokens per request
-- Qwen3.7 Max — 420 input, 66,000 cached, 200 output tokens per request
 - Qwen3.7 Plus — 500 input, 57,000 cached, 190 output tokens per request
-- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
 - Hy4 preview — 830 input, 71,500 cached, 295 output tokens per request
 - Hy3 — 830 input, 71,500 cached, 295 output tokens per request
 
@@ -261,6 +336,7 @@ You can track your current usage in the [console](https://opencode.ai/console).
 
 Usage limits may change as we learn from early usage and feedback.
 
+---
 
 ### Usage beyond limits
 
@@ -271,7 +347,7 @@ after you've reached your usage limits instead of blocking requests.
 
 ### Why some models have lower usage
 
-With Go, you pay $10/month, and the included monthly usage varies by model.
+With Go, the included monthly usage varies by model.
 
 For most models, we make this work through bulk discounts and reserved GPU capacity. We then pass those savings on to you as higher monthly usage.
 
@@ -294,7 +370,6 @@ You can also access Go models through the following API endpoints.
 | GLM-5.3-Flash                | glm-5.3-flash                | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | GLM-5.3                      | glm-5.3                      | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | GLM-5.2                      | glm-5.2                      | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
-| GLM-5.1                      | glm-5.1                      | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Kimi K3                      | kimi-k3                      | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Kimi K2.7 Code               | kimi-k2.7-code               | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Kimi K2.6                    | kimi-k2.6                    | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -309,14 +384,11 @@ You can also access Go models through the following API endpoints.
 | MiMo-V2.5-Pro                | mimo-v2.5-pro                | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | MiniMax M3                   | minimax-m3                   | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | MiniMax M2.7                 | minimax-m2.7                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
-| MiniMax M2.5                 | minimax-m2.5                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Muse Spark 1.3 Contributor   | muse-spark-1.3-contributor   | `https://opencode.ai/zen/go/v1/responses`        | `@ai-sdk/openai`            |
 | Muse Spark 1.2 Contributor   | muse-spark-1.2-contributor   | `https://opencode.ai/zen/go/v1/responses`        | `@ai-sdk/openai`            |
 | Qwen3.8 Max                  | qwen3.8-max                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Qwen3.8 Flash                | qwen3.8-flash                | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
-| Qwen3.7 Max                  | qwen3.7-max                  | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Qwen3.7 Plus                 | qwen3.7-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
-| Qwen3.6 Plus                 | qwen3.6-plus                 | `https://opencode.ai/zen/go/v1/messages`         | `@ai-sdk/anthropic`         |
 | Hy4 preview                  | hy4-preview                  | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Hy3                          | hy3                          | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
 | Space Bunny Free             | space-bunny-free             | `https://opencode.ai/zen/go/v1/chat/completions` | `@ai-sdk/openai-compatible` |
@@ -353,7 +425,6 @@ curl https://opencode.ai/zen/go/v1/models
 | GLM-5.3-Flash                | Not used       | 0 days         |
 | GLM-5.3                      | Not used       | 0 days         |
 | GLM-5.2                      | Not used       | 0 days         |
-| GLM-5.1                      | Not used       | 0 days         |
 | Kimi K3                      | Not used       | 0 days         |
 | Kimi K2.7 Code               | Not used       | 0 days         |
 | Kimi K2.6                    | Not used       | 0 days         |
@@ -364,9 +435,7 @@ curl https://opencode.ai/zen/go/v1/models
 | MiMo-V2.5                    | Not used       | 0 days         |
 | Qwen3.8 Max                  | Not used       | 0 days         |
 | Qwen3.8 Flash                | Not used       | 0 days         |
-| Qwen3.7 Max                  | Not used       | 0 days         |
 | Qwen3.7 Plus                 | Not used       | 0 days         |
-| Qwen3.6 Plus                 | Not used       | 0 days         |
 | MiniMax M3                   | Not used       | 0 days         |
 | MiniMax M2.7                 | Not used       | 0 days         |
 | Muse Spark 1.3 Contributor   | Yes            | Not ZDR        |
@@ -384,7 +453,7 @@ curl https://opencode.ai/zen/go/v1/models
 - **GPT 6 Luna / GPT 5.6 Luna:** Abuse monitoring logs are generated for all API feature usage and retained for up to 30 days. [Learn more](https://developers.openai.com/api/docs/guides/your-data#data-retention-controls-for-abuse-monitoring).
 - **Muse Spark 1.3 Contributor:** Heavily discounted token pricing in exchange for permission to use your prompts and completions to train future Meta models. Availability is limited to regions permitted by Meta's [Geographic Use Policy](https://ai.developer.meta.com/legal/geographic-use-policy). [Learn more](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
 - **Muse Spark 1.2 Contributor:** Heavily discounted token pricing in exchange for permission to use your prompts and completions to train future Meta models. Availability is limited to regions permitted by Meta's [Geographic Use Policy](https://ai.developer.meta.com/legal/geographic-use-policy). [Learn more](https://dev.meta.ai/docs/pricing-rate-limits#contributor-tier).
-- **DeepSeek:** ZDR agreement is renewed monthly. The current agreement is valid through September 30, 2026.
+- **DeepSeek:** ZDR agreement is renewed monthly. The current agreement is valid through October 31, 2026.
 
 ## Background
 
@@ -400,7 +469,7 @@ To fix this, we did a couple of things:
 2. We worked with a few providers to make sure these were being served correctly.
 3. We benchmarked the combination of the model/provider and came up with a list that we feel good recommending.
 
-OpenCode Go gives you access to these models for **$10/month**.
+Both Go and Go Plus provide access to these models; choose the plan that fits how much you use them.
 
 ## Goals
 

services/www/src/docs/styles/global.css

@@ -912,6 +912,48 @@ main {
   overflow-x: auto;
 }
 
+.docs-plan-tabs {
+  margin-bottom: 1.5rem;
+}
+
+.docs-plan-tabs-list {
+  display: flex;
+  gap: 0;
+  margin-bottom: 1rem;
+  border-bottom: 1px solid var(--border);
+}
+
+.docs-plan-tabs-list button {
+  margin-bottom: -1px;
+  padding: 0.5rem 1rem;
+  border: 0;
+  border-bottom: 2px solid transparent;
+  background: transparent;
+  color: var(--muted);
+  font: inherit;
+  font-weight: 600;
+  cursor: pointer;
+}
+
+.docs-plan-tabs-list button[aria-selected="true"] {
+  border-bottom-color: var(--foreground);
+  color: var(--foreground);
+}
+
+.docs-plan-tabs-list button:focus-visible {
+  outline: 2px solid var(--link);
+  outline-offset: 2px;
+}
+
+.docs-plan-tabs [role="tabpanel"] {
+  overflow-x: auto;
+}
+
+.docs-plan-tabs [role="tabpanel"] > :last-child,
+.docs-plan-tabs [role="tabpanel"] > :last-child > :last-child {
+  margin-bottom: 0;
+}
+
 .prose table {
   width: 100%;
   margin-bottom: 1.5rem;