feat(responses): provider-opted visible thinking summaries via showThinkingSummary

docs-site/src/content/docs/reference/configuration/providers.md

@@ -208,6 +208,7 @@ Providers can expose a built-in shorthand, such as `agy` for `google-antigravity
 | `preserveReasoningContentModels?` | `string[]` | Models requiring prior assistant `reasoning_content` in chat history. |
 | `reasoningDetailsModels?` | `string[]` | Models whose endpoint returns thinking as a structured `reasoning_details` array (MiniMax M-series with `reasoning_split`); stream deltas are cumulative snapshots that are prefix-diffed, and preserved reasoning replays as a `reasoning_details` array instead of a `reasoning_content` string. |
 | `requiresReasoningPlaceholderModels?` | `string[]` | Models whose upstream rejects a tool_call continuation missing `reasoning_content` (DeepSeek thinking mode); a minimal placeholder is injected when the replay cache misses. Defaults to `preserveReasoningContentModels`; set `[]` to opt out. |
+| `showThinkingSummary?` | `boolean` | Opt-in: surface upstream thinking as visible reasoning even when the client omits `reasoning.summary` (the Codex default, which otherwise keeps thinking in hidden replay envelopes). An explicit client `reasoning.summary: "none"` still wins, and `false` opts a seeded preset back out. Which channel carries the visible text is the bridge's decision, not this flag's. `google-antigravity` is an OAuth-only `google` provider using the Cloud Code Assist wire and is seeded `true`. On that wire the opt-in also sets `generationConfig.thinkingConfig.includeThoughts` for Gemini models — Cloud Code Assist reports `thoughtsTokenCount` either way but sends no `thought` text without it (Gemini only; Claude is never asked and `gpt-oss` rejects the field with `INVALID_ARGUMENT`). |
 | `thinkingToggleModels?` | `string[]` | Chat models using `thinking.enabled` rather than an effort ladder. |
 | `thinkingBudgetModels?` | `string[]` | Chat models using integer `thinking_budget`; effort maps to a budget fraction. |
 | `noVisionModels?` | `string[]` | Text-only models sent through the vision sidecar; matching tolerates an Ollama `:size` tag. |

scripts/test-layout/layout.json

@@ -1101,6 +1101,7 @@
     "responses-routed-web-search-fields.test.ts": "responses",
     "responses-self-named-namespace-scrub.test.ts": "responses",
     "responses-shadow-intercept.test.ts": "responses",
+    "responses-show-thinking-summary.test.ts": "responses",
     "responses-snapshot-repair-server.test.ts": "responses",
     "responses-snapshot-repair.test.ts": "responses",
     "responses-state-write-amplification.test.ts": "responses",

src/adapters/google-wire-compiler.ts

@@ -130,12 +130,20 @@ function compileGenerationConfig(value: unknown): JsonObject | undefined {
     ))].slice(0, 5);
     if (stopSequences.length > 0) out.stopSequences = stopSequences;
   }
-  if (isObject(value.thinkingConfig) && typeof value.thinkingConfig.thinkingLevel === "string") {
-    const raw = value.thinkingConfig.thinkingLevel.toLowerCase();
-    const thinkingLevel = GOOGLE_THINKING_LEVELS.has(raw)
-      ? raw
-      : (["xhigh", "max", "ultra"].includes(raw) ? "high" : undefined);
-    if (thinkingLevel) out.thinkingConfig = { thinkingLevel };
+  if (isObject(value.thinkingConfig)) {
+    const thinking: JsonObject = {};
+    if (typeof value.thinkingConfig.thinkingLevel === "string") {
+      const raw = value.thinkingConfig.thinkingLevel.toLowerCase();
+      const thinkingLevel = GOOGLE_THINKING_LEVELS.has(raw)
+        ? raw
+        : (["xhigh", "max", "ultra"].includes(raw) ? "high" : undefined);
+      if (thinkingLevel) thinking.thinkingLevel = thinkingLevel;
+    }
+    // The one key that makes Google return `thought: true` text. Cloud Code Assist serves
+    // thinking either way (thoughtsTokenCount stays non-zero) but withholds the text unless the
+    // request opts in, so dropping it here silently reinstates the missing-thinking behavior.
+    if (value.thinkingConfig.includeThoughts === true) thinking.includeThoughts = true;
+    if (Object.keys(thinking).length > 0) out.thinkingConfig = thinking;
   }
   if (Array.isArray(value.responseModalities)) {
     const valid = value.responseModalities.filter((m): m is string => typeof m === "string" && ["TEXT", "IMAGE", "AUDIO"].includes(m));

src/adapters/google.ts

@@ -866,11 +866,27 @@ export function createGoogleAdapter(provider: OcxProviderConfig): ProviderAdapte
         );
         antigravityModel = wireModelId;
         antigravitySession = sessionId;
+        // Gemini returns no chain-of-thought TEXT unless the request opts in. Probed against CCA
+        // 2026-09-12: `gemini-3.8-flash-high` answered with thoughtsTokenCount=321 and zero
+        // `thought` parts, then 358-652 chars of genuine reasoning once includeThoughts was set.
+        // Scoped to Gemini wire ids — Claude-on-CCA accepts the flag but never returns thought
+        // parts, and gpt-oss rejects it outright (400 INVALID_ARGUMENT, which would break every
+        // gpt-oss turn). Gated on the provider's visible-thinking opt-in so a user who wants
+        // thinking hidden does not pay conversation-history tokens for text nobody renders;
+        // `hideThinkingSummary !== true` is the same per-request gate the response path uses, so
+        // a client that explicitly asked for hidden thinking is not billed for the text either.
+        const includeThoughts = provider.showThinkingSummary === true
+          && parsed.options.hideThinkingSummary !== true
+          && /^gemini-/.test(wireModelId)
+          && !isImageCapableModel(parsed.modelId);
         // Effort → thinkingConfig for CCA (CLIProxyAPI proven: request.generationConfig.thinkingConfig).
         // Suffix/compat IDs return thinkingLevel=undefined — the suffix IS the effort, no contradiction.
-        if (thinkingLevel) {
+        if (thinkingLevel || includeThoughts) {
           const gc = (body.generationConfig ?? {}) as Record<string, unknown>;
-          gc.thinkingConfig = { thinkingLevel };
+          gc.thinkingConfig = {
+            ...(thinkingLevel ? { thinkingLevel } : {}),
+            ...(includeThoughts ? { includeThoughts: true } : {}),
+          };
           body.generationConfig = gc;
         }
         // Reasoning continuity: Gemini models re-inject cached thoughtSignatures; Claude-on-Antigravity

src/providers/derive.ts

@@ -44,6 +44,7 @@ export interface DerivedKeyLoginProvider {
   autoToolChoiceOnlyModels?: string[];
   preserveReasoningContentModels?: string[];
   requiresReasoningPlaceholderModels?: string[];
+  showThinkingSummary?: boolean;
   reasoningSplitModels?: string[];
   reasoningDetailsModels?: string[];
   thinkingToggleModels?: string[];
@@ -271,6 +272,7 @@ export function providerConfigSeed(entry: ProviderRegistryEntry): OcxProviderCon
     ...(entry.autoToolChoiceOnlyModels ? { autoToolChoiceOnlyModels: [...entry.autoToolChoiceOnlyModels] } : {}),
     ...(entry.preserveReasoningContentModels ? { preserveReasoningContentModels: [...entry.preserveReasoningContentModels] } : {}),
     ...(entry.requiresReasoningPlaceholderModels ? { requiresReasoningPlaceholderModels: [...entry.requiresReasoningPlaceholderModels] } : {}),
+    ...(entry.showThinkingSummary !== undefined ? { showThinkingSummary: entry.showThinkingSummary } : {}),
     ...(entry.reasoningSplitModels ? { reasoningSplitModels: [...entry.reasoningSplitModels] } : {}),
     ...(entry.reasoningDetailsModels ? { reasoningDetailsModels: [...entry.reasoningDetailsModels] } : {}),
     ...(entry.thinkingToggleModels ? { thinkingToggleModels: [...entry.thinkingToggleModels] } : {}),
@@ -320,6 +322,7 @@ export function deriveKeyLoginMap(): Record<string, DerivedKeyLoginProvider> {
       ...(entry.autoToolChoiceOnlyModels ? { autoToolChoiceOnlyModels: [...entry.autoToolChoiceOnlyModels] } : {}),
       ...(entry.preserveReasoningContentModels ? { preserveReasoningContentModels: [...entry.preserveReasoningContentModels] } : {}),
       ...(entry.requiresReasoningPlaceholderModels ? { requiresReasoningPlaceholderModels: [...entry.requiresReasoningPlaceholderModels] } : {}),
+      ...(entry.showThinkingSummary !== undefined ? { showThinkingSummary: entry.showThinkingSummary } : {}),
       ...(entry.reasoningSplitModels ? { reasoningSplitModels: [...entry.reasoningSplitModels] } : {}),
       ...(entry.reasoningDetailsModels ? { reasoningDetailsModels: [...entry.reasoningDetailsModels] } : {}),
       ...(entry.thinkingToggleModels ? { thinkingToggleModels: [...entry.thinkingToggleModels] } : {}),
@@ -574,6 +577,7 @@ export function enrichProviderFromRegistry(name: string, prov: OcxProviderConfig
   if (!prov.thinkingToggleModels && seed.thinkingToggleModels) prov.thinkingToggleModels = [...seed.thinkingToggleModels];
   if (!prov.thinkingBudgetModels && seed.thinkingBudgetModels) prov.thinkingBudgetModels = [...seed.thinkingBudgetModels];
   if (prov.escapeBuiltinToolNames === undefined && seed.escapeBuiltinToolNames !== undefined) prov.escapeBuiltinToolNames = seed.escapeBuiltinToolNames;
+  if (prov.showThinkingSummary === undefined && seed.showThinkingSummary !== undefined) prov.showThinkingSummary = seed.showThinkingSummary;
   if (prov.keyOptional === undefined && seed.keyOptional !== undefined) prov.keyOptional = seed.keyOptional;
   if (prov.freeTier === undefined && seed.freeTier !== undefined) prov.freeTier = seed.freeTier;
   if (prov.modelSuffixBracketStrip === undefined && seed.modelSuffixBracketStrip !== undefined) prov.modelSuffixBracketStrip = seed.modelSuffixBracketStrip;

src/providers/registry.ts

@@ -356,6 +356,10 @@ export interface ProviderRegistryEntry {
   autoToolChoiceOnlyModels?: string[];
   preserveReasoningContentModels?: string[];
   requiresReasoningPlaceholderModels?: string[];
+  /**
+   * Opt this provider into visible thinking (see OcxProviderConfig.showThinkingSummary).
+   */
+  showThinkingSummary?: boolean;
   reasoningSplitModels?: string[];
   reasoningDetailsModels?: string[];
   thinkingToggleModels?: string[];
@@ -380,7 +384,7 @@ export type ProviderConfigSeed = Pick<
   | "modelMaxInputTokens" | "defaultMaxOutputTokens" | "modelMaxOutputTokens"
   | "reasoningEfforts" | "modelReasoningEfforts" | "modelDefaultReasoningEfforts" | "reasoningEffortMap" | "modelReasoningEffortMap" | "reasoningWireFormat"
   | "noVisionModels" | "noReasoningModels" | "noTemperatureModels" | "noTopPModels" | "noPenaltyModels"
-  | "autoToolChoiceOnlyModels" | "preserveReasoningContentModels" | "requiresReasoningPlaceholderModels" | "reasoningSplitModels" | "reasoningDetailsModels" | "thinkingToggleModels" | "thinkingBudgetModels" | "escapeBuiltinToolNames" | "openaiChatEofTolerance"
+  | "autoToolChoiceOnlyModels" | "preserveReasoningContentModels" | "requiresReasoningPlaceholderModels" | "reasoningSplitModels" | "reasoningDetailsModels" | "thinkingToggleModels" | "thinkingBudgetModels" | "escapeBuiltinToolNames" | "openaiChatEofTolerance" | "showThinkingSummary"
   | "googleMode" | "project" | "location" | "headers"
 >;
 
@@ -2112,7 +2116,7 @@ export const PROVIDER_REGISTRY: readonly ProviderRegistryEntry[] = [
   // path must stay RELATIVE: this row sets `allowBaseUrlOverride`, and an absolute `url` would
   // retarget a user's custom base back to Google. A leading `./` is required because a bare
   // `v1internal:` reads as a URL scheme and `providerModelDiscoverySpecError` rejects it.
-  { id: "google-antigravity", alias: "agy", label: "Google Antigravity", adapter: "google", baseUrl: "https://daily-cloudcode-pa.googleapis.com", authKind: "oauth", allowBaseUrlOverride: true, dashboardUrl: "https://antigravity.google", models: ANTIGRAVITY_MODELS, liveModels: true, defaultModel: "gemini-3.8-flash", modelContextWindows: ANTIGRAVITY_MODEL_CONTEXT_WINDOWS, modelInputModalities: ANTIGRAVITY_MODEL_INPUT_MODALITIES, modelReasoningEfforts: ANTIGRAVITY_MODEL_EFFORTS, googleMode: "cloud-code-assist", jawcodeBundle: "google", extraMetadataAliases: ["antigravity", "gemini-antigravity"], modelDiscovery: { path: "./v1internal:fetchAvailableModels" } },
+  { id: "google-antigravity", alias: "agy", label: "Google Antigravity", adapter: "google", baseUrl: "https://daily-cloudcode-pa.googleapis.com", authKind: "oauth", allowBaseUrlOverride: true, dashboardUrl: "https://antigravity.google", models: ANTIGRAVITY_MODELS, liveModels: true, defaultModel: "gemini-3.8-flash", modelContextWindows: ANTIGRAVITY_MODEL_CONTEXT_WINDOWS, modelInputModalities: ANTIGRAVITY_MODEL_INPUT_MODALITIES, modelReasoningEfforts: ANTIGRAVITY_MODEL_EFFORTS, googleMode: "cloud-code-assist", showThinkingSummary: true, jawcodeBundle: "google", extraMetadataAliases: ["antigravity", "gemini-antigravity"], modelDiscovery: { path: "./v1internal:fetchAvailableModels" } },
   { id: "azure-openai", label: "Azure OpenAI", adapter: "azure-openai", baseUrl: "https://{resource}.openai.azure.com/openai", authKind: "key", featured: true, dashboardUrl: "https://portal.azure.com" },
   { id: "ollama", label: "Ollama (local)", adapter: "openai-chat", baseUrl: "http://localhost:11434/v1", authKind: "local", allowPrivateNetworkByDefault: true, allowBaseUrlOverride: true, featured: true, note: "Local — key usually blank" },
   { id: "vllm", label: "vLLM (local)", adapter: "openai-chat", baseUrl: "http://localhost:8000/v1", authKind: "local", allowPrivateNetworkByDefault: true, allowBaseUrlOverride: true, featured: true, note: "Local — key usually blank" },

src/router.ts

@@ -413,6 +413,13 @@ export function routedProviderConfig(providerName: string, provider: OcxProvider
     ...(provider.preserveResponsesReasoningContent === undefined && registryEntry.preserveResponsesReasoningContent !== undefined
       ? { preserveResponsesReasoningContent: registryEntry.preserveResponsesReasoningContent }
       : {}),
+    // The request path resolves through routedProviderConfig() and never calls
+    // enrichProviderFromRegistry(), so a saved provider row written before the
+    // registry learned this flag must be backfilled here or route.provider never
+    // carries it and the showThinkingSummary opt-in stays dead.
+    ...(provider.showThinkingSummary === undefined && registryEntry.showThinkingSummary !== undefined
+      ? { showThinkingSummary: registryEntry.showThinkingSummary }
+      : {}),
     // Registry-only client-facing repair policy (#938): fill only when the
     // saved provider has no explicit policy; clone so runtime never aliases
     // the registry constant.

src/server/auth-cors.ts

@@ -887,6 +887,7 @@ const PROVIDER_CONFIG_FIELD_POLICY = {
   autoToolChoiceOnlyModels: "editor",
   preserveReasoningContentModels: "editor",
   requiresReasoningPlaceholderModels: "editor",
+  showThinkingSummary: "editor",
   retryOn429: "editor",
   transientRetryOn5xx: "editor",
   reasoningSplitModels: "editor",

src/server/responses/core.ts

@@ -2473,6 +2473,20 @@ async function resolveSubagentFallbackModelEligibility(args: {
   };
 }
 
+/**
+ * Whether the client explicitly asked for hidden thinking (`reasoning.summary: "none"`).
+ *
+ * Pinned: parseRequest collapses "omitted" and "none" into one hideThinkingSummary
+ * flag, so the raw request body is the ONLY place that still distinguishes them.
+ * Provider opt-ins like showThinkingSummary must consult this — never the flag
+ * alone — or a future caller that copies only the flag would silently unlock an
+ * explicit opt-out.
+ */
+function clientExplicitlyHidThinking(parsed: OcxParsedRequest): boolean {
+  const rawReasoning = (parsed._rawBody as { reasoning?: { summary?: unknown } } | undefined)?.reasoning;
+  return typeof rawReasoning === "object" && rawReasoning !== null
+    && (rawReasoning as { summary?: unknown }).summary === "none";
+}
 /**
  * Apply every route-dependent request mutation against the final selected route.
  * Must run only after subagent fallback has settled the model/provider.
@@ -2514,6 +2528,16 @@ async function applyFinalRouteRequestNormalization(args: {
   // this request will actually use (#404).
   route.provider = resolveOpenCodeGoTransport(route.provider, getOrAllocateRequestSessionLane(req));
   route.provider = resolveWireProtocolOverride(route.providerName, route.modelId, route.provider, inboundWire);
+  // Provider-opted visible thinking (e.g. google-antigravity): parseRequest hides thinking
+  // whenever the client omits reasoning.summary, which is the Codex default. A provider that
+  // serves genuine user-facing reasoning opts back into visible reasoning here, so thought
+  // parts (Gemini thought, content-channel reasoning_text) reach the client instead of only
+  // the hidden replay envelopes. Which channel carries them is the bridge's decision, not
+  // this flag's. An explicit client reasoning.summary "none" still wins.
+  if (route.provider.showThinkingSummary === true && parsed.options.hideThinkingSummary === true
+    && !clientExplicitlyHidThinking(parsed)) {
+    parsed.options.hideThinkingSummary = false;
+  }
   if (preserveAnthropicResponseModel) parsed._responseModelId = responseModelId;
   logCtx.model = route.modelId;
   logCtx.provider = route.providerName;

src/types/provider.ts

@@ -773,6 +773,15 @@ export interface OcxProviderConfig {
    * out explicitly (e.g. MiniMax, where low effort disables thinking).
    */
   requiresReasoningPlaceholderModels?: string[];
+  /**
+   * Opt-in: surface upstream thinking as visible reasoning even when the client did not
+   * send `reasoning.summary`. parseRequest hides thinking by default (Codex omits the
+   * field), which strands genuine reasoning — e.g. Gemini `thought` parts on the
+   * google-antigravity (Cloud Code Assist) wire — in hidden replay envelopes. An explicit
+   * client `reasoning.summary: "none"` still wins. Which channel carries the visible text
+   * is the bridge's decision, not this flag's. Set `false` to opt a seeded preset back out.
+   */
+  showThinkingSummary?: boolean;
   /**
    * Opt-in same-target 429 retry policy. Codex itself never retries 429 (it retries 5xx only,
    * openai/codex#30471), and single-key pools have no failover, so the proxy waits and replays