diff --git a/docs/models.md b/docs/models.md
index d1144a222..5ca430d03 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -419,7 +419,7 @@ So a model can exist in registry but not be selectable until auth is available.
 - exact model id (provider inferred)
 - fuzzy/substring matching
 - glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)
-- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)
+- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh|max`)
 
 `--provider` is legacy; `--model` is preferred.
 
@@ -582,7 +582,7 @@ Reasoning / thinking:
 
 - `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok, Z.ai/Zhipu, and Xiaomi MiMo).
 - `supportsReasoningParams` — whether request shaping may send reasoning params at all. Default: auto (off for GitHub Copilot chat-completions).
-- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> "max"`).
+- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh|max`) to provider-specific strings (e.g. Fireworks GLM maps `minimal -> "none"`).
 - `thinkingFormat` — request shape for thinking: `"openai"` (`reasoning_effort`), `"openrouter"` (`reasoning: { effort }`), `"zai"` (`thinking: { type: "enabled" }`), `"qwen"` (top-level `enable_thinking`), or `"qwen-chat-template"` (`chat_template_kwargs.enable_thinking`). Default: `"openai"`.
 - `reasoningContentField` — assistant field carrying chain-of-thought: `"reasoning_content"`, `"reasoning"`, or `"reasoning_text"`. Default: auto.
 - `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.
diff --git a/docs/rpc.md b/docs/rpc.md
index 6e23cf86b..973b80e1b 100644
--- a/docs/rpc.md
+++ b/docs/rpc.md
@@ -192,7 +192,7 @@ Local-only slash commands may emit `command_output` frames before completing via
 ```json
 {
   "model": { "provider": "...", "id": "..." },
-  "thinkingLevel": "off|minimal|low|medium|high|xhigh",
+  "thinkingLevel": "off|minimal|low|medium|high|xhigh|max",
   "isStreaming": false,
   "isCompacting": false,
   "steeringMode": "all|one-at-a-time",
diff --git a/docs/settings.md b/docs/settings.md
index 7961c7a1b..5db977693 100644
--- a/docs/settings.md
+++ b/docs/settings.md
@@ -282,7 +282,7 @@ Every key below is defined in the settings schema; `omp config list` shows the f
 
 ### Models
 
-`modelRoles`, `modelTags`, and `cycleOrder` work together to define the models you can switch between. Role values may carry a thinking suffix (`:minimal`, `:low`, `:medium`, `:high`, `:xhigh`).
+`modelRoles`, `modelTags`, and `cycleOrder` work together to define the models you can switch between. Role values may carry a thinking suffix (`:minimal`, `:low`, `:medium`, `:high`, `:xhigh`, `:max`).
 
 ```yaml
 modelRoles:
@@ -342,17 +342,19 @@ thinkingBudgets:
   medium: 8192
   high: 16384
   xhigh: 32768
+  max: 32768
 ```
 
 | Key | Type | Default | Values |
 |---|---|---|---|
-| `defaultThinkingLevel` | enum | `high` | `minimal`, `low`, `medium`, `high`, `xhigh`, `auto`. Override per run with `--thinking`. |
+| `defaultThinkingLevel` | enum | `high` | `minimal`, `low`, `medium`, `high`, `xhigh`, `max`, `auto`. Override per run with `--thinking`. |
 | `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output. `--hide-thinking` sets it for the run (display only). |
 | `thinkingBudgets.minimal` | number | `1024` | Token budget for the `minimal` level. |
 | `thinkingBudgets.low` | number | `2048` | Token budget for `low`. |
 | `thinkingBudgets.medium` | number | `8192` | Token budget for `medium`. |
 | `thinkingBudgets.high` | number | `16384` | Token budget for `high`. |
 | `thinkingBudgets.xhigh` | number | `32768` | Token budget for `xhigh`. |
+| `thinkingBudgets.max` | number | `32768` | Token budget for `max`. |
 
 ### Sampling
 
diff --git a/packages/agent/CHANGELOG.md b/packages/agent/CHANGELOG.md
index 109f6905a..c8702a17d 100644
--- a/packages/agent/CHANGELOG.md
+++ b/packages/agent/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Added
+
+- Added `ThinkingLevel.Max` ("max") above `xhigh`, mapping to the catalog `Effort.Max` tier.
+
 ### Fixed
 
 - Fixed remote compaction for Codex Responses Lite models (GPT-5.6 family): both the V1 `/responses/compact` request and the V2 `compaction_trigger` stream now apply the lite rewrite (instructions as an input item, no top-level `instructions`/`tools`, `all_turns` reasoning replay on V2) and send the `x-openai-internal-codex-responses-lite` header, matching codex-rs routing compaction through `build_responses_request`.
diff --git a/packages/agent/README.md b/packages/agent/README.md
index 87c3b2435..148b7182f 100644
--- a/packages/agent/README.md
+++ b/packages/agent/README.md
@@ -134,7 +134,7 @@ const agent = new Agent({
   initialState: {
     systemPrompt: string[],
     model: Model,
-    thinkingLevel: "off" | "minimal" | "low" | "medium" | "high" | "xhigh",
+    thinkingLevel: "off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max",
     tools: AgentTool<any>[],
     messages: AgentMessage[],
   },
diff --git a/packages/agent/src/compaction/compaction.ts b/packages/agent/src/compaction/compaction.ts
index 772f0b232..8acf7ffb8 100644
--- a/packages/agent/src/compaction/compaction.ts
+++ b/packages/agent/src/compaction/compaction.ts
@@ -659,6 +659,8 @@ function effortFromThinkingLevel(level: ThinkingLevel): Effort {
 			return Effort.High;
 		case ThinkingLevel.XHigh:
 			return Effort.XHigh;
+		case ThinkingLevel.Max:
+			return Effort.Max;
 		case ThinkingLevel.Off:
 		case ThinkingLevel.Inherit:
 			throw new Error(`effortFromThinkingLevel: ${level} must be handled by caller`);
diff --git a/packages/agent/src/thinking.ts b/packages/agent/src/thinking.ts
index e89c1e834..3dcd6611f 100644
--- a/packages/agent/src/thinking.ts
+++ b/packages/agent/src/thinking.ts
@@ -13,6 +13,7 @@ export const ThinkingLevel = {
 	Medium: Effort.Medium,
 	High: Effort.High,
 	XHigh: Effort.XHigh,
+	Max: Effort.Max,
 } as const;
 
 export type ThinkingLevel = (typeof ThinkingLevel)[keyof typeof ThinkingLevel];
diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index 7f0c5dc5f..b2c3669e1 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -4,10 +4,14 @@
 
 ### Added
 
+- Added `max` as a first-class reasoning effort option across providers and wire schemas
+- Updated `max` reasoning budget to 32768 tokens across all provider budget tables
+
 - Added model-driven Codex Responses Lite: `responsesLite` now defaults to the catalog `useResponsesLite` flag (codex-rs `use_responses_lite`, set on the GPT-5.6 family), so lite requests are sent without per-call opt-in.
 - Added the full Responses Lite wire contract: lite requests move tools into a leading `{type: "additional_tools", role: "developer"}` input item and the base instructions into a developer message, omit top-level `instructions`/`tools`, and force `parallel_tool_calls: false`, mirroring codex-rs `build_responses_request`.
 - Added concurrent reasoning summaries on Codex Responses: requests with a reasoning summary send `stream_options: { reasoning_summary_delivery: "sequential_cutoff" }`, and the stream decoder consumes the matching atomic `response.reasoning_summary_text.done` events (resolved by `item_id`/`output_index`, stale dones dropped, incremental `.delta`/`.part.*` events ignored under the cutoff contract). The cutoff gate reads the post-`onPayload` wire body on both transports, and `response.reasoning_summary_text.done` now counts as websocket watchdog progress.
 - Added Novita API-key login with authenticated key validation and `NOVITA_API_KEY` discovery ([#4917](https://github.com/can1357/oh-my-pi/pull/4917) by [@jason-wu-ai](https://github.com/jason-wu-ai)).
+- Added `"max"` as a first-class reasoning effort across provider options, wire types (`reasoning_effort`/`reasoning.effort`), server intake guards, and the Codex request transformer; user `max` now serializes 1:1 to the provider `max` tier instead of being reachable only through the retired shifted effort maps. Inbound Anthropic gateway requests now map `output_config.effort` onto `options.reasoning`.
 
 ### Changed
 
@@ -16,6 +20,7 @@
 - Standardized Responses Lite activation via model-level catalog flags
 - Recognized Pro Lite as a paid plan tier for OpenAI Codex models
 - Changed Responses Lite image handling to match current codex-rs: a lite request containing input images now stays on the lite transport with image `detail` stripped, instead of silently falling back to the full Responses shape.
+- Changed effort budget tables (`ANTHROPIC_THINKING`, `GOOGLE_THINKING`, `BEDROCK_CLAUDE_THINKING`, Bedrock `defaultBudgets`) to carry a `max` row (32768), and `getGoogleBudget` to resolve `max` to the largest bucket explicitly.
 
 ### Fixed
 
diff --git a/packages/ai/src/providers/amazon-bedrock.ts b/packages/ai/src/providers/amazon-bedrock.ts
index f361692bc..b30d8a9aa 100644
--- a/packages/ai/src/providers/amazon-bedrock.ts
+++ b/packages/ai/src/providers/amazon-bedrock.ts
@@ -997,6 +997,7 @@ function buildAdditionalModelRequestFields(
 		medium: 8192,
 		high: 16384,
 		xhigh: 32768,
+		max: 32768,
 	};
 	const budget = options.thinkingBudgets?.[level] ?? defaultBudgets[level];
 
diff --git a/packages/ai/src/providers/anthropic-messages-server.ts b/packages/ai/src/providers/anthropic-messages-server.ts
index 480d00931..63616473a 100644
--- a/packages/ai/src/providers/anthropic-messages-server.ts
+++ b/packages/ai/src/providers/anthropic-messages-server.ts
@@ -1,3 +1,4 @@
+import { Effort } from "@oh-my-pi/pi-catalog/effort";
 import { logger } from "@oh-my-pi/pi-utils";
 import { type } from "arktype";
 import { captureRequestHeaders, resolvePromptCacheKey } from "../auth-gateway/http";
@@ -291,6 +292,19 @@ function deriveCacheRetention(data: {
 	return strongest;
 }
 
+/**
+ * Inbound `output_config.effort` wire literal → catalog `Effort` (1:1).
+ * Values outside this table (none exist in the schema today) are ignored
+ * rather than guessed at.
+ */
+const REASONING_EFFORT_BY_WIRE: Partial<Record<string, Effort>> = {
+	low: Effort.Low,
+	medium: Effort.Medium,
+	high: Effort.High,
+	xhigh: Effort.XHigh,
+	max: Effort.Max,
+};
+
 export function parseRequest(body: unknown, headers?: Headers): ParsedRequest {
 	const data = anthropicMessagesRequestSchema(body);
 	if (data instanceof type.errors) {
@@ -351,6 +365,10 @@ export function parseRequest(body: unknown, headers?: Headers): ParsedRequest {
 	if (data.output_config?.task_budget) {
 		options.taskBudget = data.output_config.task_budget;
 	}
+	if (data.output_config?.effort) {
+		const mapped = REASONING_EFFORT_BY_WIRE[data.output_config.effort];
+		if (mapped !== undefined) options.reasoning = mapped;
+	}
 	const cacheRetention = deriveCacheRetention(data);
 	if (cacheRetention !== undefined) options.cacheRetention = cacheRetention;
 	// Anthropic clients commonly send `metadata: { user_id }`; forward verbatim
diff --git a/packages/ai/src/providers/azure-openai-responses.ts b/packages/ai/src/providers/azure-openai-responses.ts
index 31090702c..2c8e73430 100644
--- a/packages/ai/src/providers/azure-openai-responses.ts
+++ b/packages/ai/src/providers/azure-openai-responses.ts
@@ -56,7 +56,7 @@ function resolveDeploymentName(model: Model<"azure-openai-responses">, options?:
 
 // Azure OpenAI Responses-specific options
 export interface AzureOpenAIResponsesOptions extends StreamOptions {
-	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh";
+	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 	reasoningSummary?: "auto" | "detailed" | "concise" | null;
 	azureApiVersion?: string;
 	azureResourceName?: string;
diff --git a/packages/ai/src/providers/ollama.ts b/packages/ai/src/providers/ollama.ts
index a0fb862a4..bfcdb65e0 100644
--- a/packages/ai/src/providers/ollama.ts
+++ b/packages/ai/src/providers/ollama.ts
@@ -35,7 +35,7 @@ import { transformMessages } from "./transform-messages";
 import { joinTextWithImagePlaceholder, partitionVisionContent } from "./vision-guard";
 
 export interface OllamaChatOptions extends StreamOptions {
-	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh";
+	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 	disableReasoning?: boolean;
 	toolChoice?: ToolChoice;
 }
diff --git a/packages/ai/src/providers/openai-chat-server-schema.ts b/packages/ai/src/providers/openai-chat-server-schema.ts
index bdb1835e8..2490eec53 100644
--- a/packages/ai/src/providers/openai-chat-server-schema.ts
+++ b/packages/ai/src/providers/openai-chat-server-schema.ts
@@ -209,7 +209,7 @@ export const openaiChatRequestSchema = type({
 	"frequency_penalty?": "number",
 	"logit_bias?": type({ "[string]": "number" }),
 	"user?": "string",
-	"reasoning_effort?": "'minimal' | 'low' | 'medium' | 'high' | 'xhigh'",
+	"reasoning_effort?": "'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max'",
 	"parallel_tool_calls?": "boolean",
 	"service_tier?": "'auto' | 'default' | 'flex' | 'scale' | 'priority'",
 	"metadata?": type({ "[string]": "unknown" }),
diff --git a/packages/ai/src/providers/openai-chat-server.ts b/packages/ai/src/providers/openai-chat-server.ts
index 441138ea9..d2f8e0bbc 100644
--- a/packages/ai/src/providers/openai-chat-server.ts
+++ b/packages/ai/src/providers/openai-chat-server.ts
@@ -35,7 +35,14 @@ export type { ParsedRequest };
 type ReasoningEffort = NonNullable<ParsedRequest["options"]["reasoning"]>;
 
 function isReasoningEffort(value: unknown): value is ReasoningEffort {
-	return value === "minimal" || value === "low" || value === "medium" || value === "high" || value === "xhigh";
+	return (
+		value === "minimal" ||
+		value === "low" ||
+		value === "medium" ||
+		value === "high" ||
+		value === "xhigh" ||
+		value === "max"
+	);
 }
 
 function isServiceTier(value: unknown): value is ServiceTier {
diff --git a/packages/ai/src/providers/openai-chat-wire.ts b/packages/ai/src/providers/openai-chat-wire.ts
index b2e5f22a0..0ff7f4a9c 100644
--- a/packages/ai/src/providers/openai-chat-wire.ts
+++ b/packages/ai/src/providers/openai-chat-wire.ts
@@ -116,7 +116,7 @@ export type Metadata = {
 };
 
 /** Constrains effort on reasoning for reasoning models. */
-export type ReasoningEffort = "none" | "minimal" | "low" | "medium" | "high" | "xhigh" | null;
+export type ReasoningEffort = "none" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max" | null;
 
 /** JSON object response format (older JSON mode). */
 export interface ResponseFormatJSONObject {
diff --git a/packages/ai/src/providers/openai-codex-responses.ts b/packages/ai/src/providers/openai-codex-responses.ts
index 609a570fb..a96d5b2a9 100644
--- a/packages/ai/src/providers/openai-codex-responses.ts
+++ b/packages/ai/src/providers/openai-codex-responses.ts
@@ -110,7 +110,7 @@ import {
 import { transformMessages } from "./transform-messages";
 
 export interface OpenAICodexResponsesOptions extends StreamOptions {
-	reasoning?: "none" | "minimal" | "low" | "medium" | "high" | "xhigh";
+	reasoning?: "none" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 	reasoningSummary?: "auto" | "concise" | "detailed" | null;
 	/** `reasoning.context` replay scope; defaults to `all_turns` when unset. The `all_turns` value is gated to gpt-5.4+ Codex models — older ids reject it, so it is suppressed and `context` omitted. */
 	reasoningContext?: CodexReasoningContext;
diff --git a/packages/ai/src/providers/openai-codex/request-transformer.ts b/packages/ai/src/providers/openai-codex/request-transformer.ts
index 8c095137f..a25d5b665 100644
--- a/packages/ai/src/providers/openai-codex/request-transformer.ts
+++ b/packages/ai/src/providers/openai-codex/request-transformer.ts
@@ -8,7 +8,7 @@ import { mapOpenAIReasoningEffort } from "../openai-shared";
 export type CodexReasoningContext = "auto" | "current_turn" | "all_turns";
 
 /** User-facing effort levels accepted by Codex request options. */
-type CodexCallerEffort = "minimal" | "low" | "medium" | "high" | "xhigh";
+type CodexCallerEffort = "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 
 /** Caller literal → catalog `Effort` bridge (the enum is nominal). */
 const EFFORT_BY_NAME: Record<CodexCallerEffort, Effort> = {
@@ -17,6 +17,7 @@ const EFFORT_BY_NAME: Record<CodexCallerEffort, Effort> = {
 	medium: Effort.Medium,
 	high: Effort.High,
 	xhigh: Effort.XHigh,
+	max: Effort.Max,
 };
 
 export interface ReasoningConfig {
@@ -28,7 +29,7 @@ export interface ReasoningConfig {
 }
 
 export interface CodexRequestOptions {
-	/** User-facing effort; the wire-only `max` tier is reached via the model's effort map. */
+	/** User-facing effort; maps 1:1 onto the wire tier of the same name. */
 	reasoningEffort?: CodexCallerEffort | "none";
 	reasoningSummary?: ReasoningConfig["summary"] | null;
 	/** Explicit `reasoning.context` override; defaults to `all_turns` when unset. The `all_turns` value is gated to gpt-5.4+ Codex models — older ids reject it, so it is suppressed and `context` omitted. */
@@ -99,7 +100,8 @@ export function resolveCodexResponsesLite(
 
 /**
  * Clamp a user-facing effort to the model's ladder, then remap to the wire
- * tier (e.g. GPT-5.6's shifted five-tier scale sends `max` for user `xhigh`).
+ * tier. User efforts map 1:1 onto wire tiers; the effort map only covers
+ * host quirks where a wire tier genuinely does not exist (e.g. `minimal→none`).
  * A mapped value outside the Codex wire vocabulary is a broken compat/model
  * effort map — fail loudly rather than silently sending a different tier.
  */
diff --git a/packages/ai/src/providers/openai-completions.ts b/packages/ai/src/providers/openai-completions.ts
index f200c268c..83cc11666 100644
--- a/packages/ai/src/providers/openai-completions.ts
+++ b/packages/ai/src/providers/openai-completions.ts
@@ -459,7 +459,7 @@ export function isOpenAICompletionsProgressChunk(chunk: unknown): boolean {
 
 export interface OpenAICompletionsOptions extends StreamOptions {
 	toolChoice?: ToolChoice;
-	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh";
+	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 	/** Force-disable reasoning where supported, or request the lowest effort on generic effort endpoints. */
 	disableReasoning?: boolean;
 	serviceTier?: ServiceTier;
diff --git a/packages/ai/src/providers/openai-responses-server.ts b/packages/ai/src/providers/openai-responses-server.ts
index 6a4d947d8..e2dd73389 100644
--- a/packages/ai/src/providers/openai-responses-server.ts
+++ b/packages/ai/src/providers/openai-responses-server.ts
@@ -40,7 +40,14 @@ export type { ParsedRequest };
 // ─── narrow guards ──────────────────────────────────────────────────────────
 
 function isReasoningEffort(value: unknown): value is NonNullable<ParsedRequest["options"]["reasoning"]> {
-	return value === "minimal" || value === "low" || value === "medium" || value === "high" || value === "xhigh";
+	return (
+		value === "minimal" ||
+		value === "low" ||
+		value === "medium" ||
+		value === "high" ||
+		value === "xhigh" ||
+		value === "max"
+	);
 }
 
 function isServiceTier(value: unknown): value is NonNullable<ParsedRequest["options"]["serviceTier"]> {
diff --git a/packages/ai/src/providers/openai-responses-wire.ts b/packages/ai/src/providers/openai-responses-wire.ts
index 7992ec319..e194a4c3f 100644
--- a/packages/ai/src/providers/openai-responses-wire.ts
+++ b/packages/ai/src/providers/openai-responses-wire.ts
@@ -6305,9 +6305,9 @@ export interface Reasoning {
 	/**
 	 * Constrains effort on reasoning for
 	 * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-	 * supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
-	 * Reducing reasoning effort can result in faster responses and fewer tokens used
-	 * on reasoning in a response.
+	 * supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and
+	 * `max`. Reducing reasoning effort can result in faster responses and fewer
+	 * tokens used on reasoning in a response.
 	 *
 	 * - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
 	 *   reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -6316,6 +6316,7 @@ export interface Reasoning {
 	 *   support `none`.
 	 * - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
 	 * - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
+	 * - `max` is supported for `gpt-5.6` and later models.
 	 */
 	effort?: ReasoningEffort | null;
 	/**
@@ -6346,9 +6347,9 @@ export interface Reasoning {
 /**
  * Constrains effort on reasoning for
  * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
- * supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
- * Reducing reasoning effort can result in faster responses and fewer tokens used
- * on reasoning in a response.
+ * supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and
+ * `max`. Reducing reasoning effort can result in faster responses and fewer tokens
+ * used on reasoning in a response.
  *
  * - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
  *   reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -6357,8 +6358,9 @@ export interface Reasoning {
  *   support `none`.
  * - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
  * - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
+ * - `max` is supported for `gpt-5.6` and later models.
  */
-export type ReasoningEffort = "none" | "minimal" | "low" | "medium" | "high" | "xhigh" | null;
+export type ReasoningEffort = "none" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max" | null;
 /**
  * JSON object response format. An older method of generating JSON responses. Using
  * `json_schema` is recommended for models that support it. Note that the model
diff --git a/packages/ai/src/providers/openai-responses.ts b/packages/ai/src/providers/openai-responses.ts
index 937cbe87a..2be20dd81 100644
--- a/packages/ai/src/providers/openai-responses.ts
+++ b/packages/ai/src/providers/openai-responses.ts
@@ -95,7 +95,7 @@ import {
 
 // OpenAI Responses-specific options
 export interface OpenAIResponsesOptions extends StreamOptions {
-	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh";
+	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 	reasoningSummary?: "auto" | "detailed" | "concise" | null;
 	serviceTier?: ServiceTier;
 	textVerbosity?: "low" | "medium" | "high";
diff --git a/packages/ai/src/providers/openai-shared.ts b/packages/ai/src/providers/openai-shared.ts
index 789f31213..47a803349 100644
--- a/packages/ai/src/providers/openai-shared.ts
+++ b/packages/ai/src/providers/openai-shared.ts
@@ -643,7 +643,7 @@ export type OpenAICompletionsParams = Omit<ChatCompletionCreateParamsStreaming,
 
 /** Reasoning-relevant slice of caller options the Chat Completions dialect dispatch reads. */
 export interface ChatCompletionsReasoningOptions {
-	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh";
+	reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 	disableReasoning?: boolean;
 }
 
diff --git a/packages/ai/src/stream.ts b/packages/ai/src/stream.ts
index de922d926..7c66e6c9f 100644
--- a/packages/ai/src/stream.ts
+++ b/packages/ai/src/stream.ts
@@ -1244,6 +1244,7 @@ export const ANTHROPIC_THINKING: Record<Effort, number> = {
 	medium: 8192,
 	high: 16384,
 	xhigh: 32768,
+	max: 32768,
 };
 
 const GOOGLE_THINKING: Record<Effort, number> = {
@@ -1252,6 +1253,7 @@ const GOOGLE_THINKING: Record<Effort, number> = {
 	medium: 8192,
 	high: 16384,
 	xhigh: 24575,
+	max: 32768,
 };
 
 const BEDROCK_CLAUDE_THINKING: Record<Effort, number> = {
@@ -1260,6 +1262,7 @@ const BEDROCK_CLAUDE_THINKING: Record<Effort, number> = {
 	medium: 8192,
 	high: 16384,
 	xhigh: 16384,
+	max: 32768,
 };
 
 function resolveBedrockThinkingBudget(
@@ -1842,7 +1845,9 @@ function getGoogleBudget(
 				return 2048;
 			case "medium":
 				return 8192;
-			default:
+			case "high":
+			case "xhigh":
+			case "max":
 				return model.id.includes("2.5-flash") ? 24576 : 32768;
 		}
 	}
diff --git a/packages/ai/test/anthropic-alignment.test.ts b/packages/ai/test/anthropic-alignment.test.ts
index d3e7b42f5..837bf7b21 100644
--- a/packages/ai/test/anthropic-alignment.test.ts
+++ b/packages/ai/test/anthropic-alignment.test.ts
@@ -1939,16 +1939,17 @@ describe("Anthropic request fingerprint alignment", () => {
 	});
 
 	it("drops sampling params and keeps summarized adaptive thinking for OAuth Opus 4.7+", async () => {
+		const opus47 = buildModel({
+			...ANTHROPIC_MODEL_SPEC,
+			id: "claude-opus-4-7",
+			name: "Claude Opus 4.7",
+			thinking: {
+				mode: "anthropic-adaptive",
+				efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
+			},
+		});
 		const payload = (await captureAnthropicPayload(
-			buildModel({
-				...ANTHROPIC_MODEL_SPEC,
-				id: "claude-opus-4-7",
-				name: "Claude Opus 4.7",
-				thinking: {
-					mode: "anthropic-adaptive",
-					efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-				},
-			}),
+			opus47,
 			{
 				systemPrompt: ["Stay concise."],
 				messages: [{ role: "user", content: "Hi", timestamp: Date.now() }],
@@ -1976,18 +1977,10 @@ describe("Anthropic request fingerprint alignment", () => {
 		expect(payload.context_management).toEqual({
 			edits: [{ type: "clear_thinking_20251015", keep: "all" }],
 		});
-		expect(payload.output_config).toEqual({ effort: "xhigh" });
+		expect(payload.output_config).toEqual({ effort: "high" });
 
-		const maxPayload = (await captureAnthropicPayload(
-			buildModel({
-				...ANTHROPIC_MODEL_SPEC,
-				id: "claude-opus-4-7",
-				name: "Claude Opus 4.7",
-				thinking: {
-					mode: "anthropic-adaptive",
-					efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-				},
-			}),
+		const xhighPayload = (await captureAnthropicPayload(
+			opus47,
 			{
 				systemPrompt: ["Stay concise."],
 				messages: [{ role: "user", content: "Hi", timestamp: Date.now() }],
@@ -2000,6 +1993,23 @@ describe("Anthropic request fingerprint alignment", () => {
 			thinking?: { type?: string; display?: string };
 			output_config?: { effort?: string };
 		};
+		expect(xhighPayload.thinking).toEqual({ type: "adaptive", display: "summarized" });
+		expect(xhighPayload.output_config).toEqual({ effort: "xhigh" });
+
+		const maxPayload = (await captureAnthropicPayload(
+			opus47,
+			{
+				systemPrompt: ["Stay concise."],
+				messages: [{ role: "user", content: "Hi", timestamp: Date.now() }],
+			},
+			{
+				thinkingEnabled: true,
+				reasoning: Effort.Max,
+			},
+		)) as {
+			thinking?: { type?: string; display?: string };
+			output_config?: { effort?: string };
+		};
 		expect(maxPayload.thinking).toEqual({ type: "adaptive", display: "summarized" });
 		expect(maxPayload.output_config).toEqual({ effort: "max" });
 	});
@@ -2014,15 +2024,14 @@ describe("Anthropic request fingerprint alignment", () => {
 				baseUrl: "https://api.code.umans.ai",
 				thinking: {
 					mode: "anthropic-budget-effort",
-					efforts: [Effort.High, Effort.XHigh],
-					effortMap: { [Effort.XHigh]: "max" },
+					efforts: [Effort.High, Effort.Max],
 				},
 			}),
 			{
 				systemPrompt: ["Stay concise."],
 				messages: [{ role: "user", content: "Hi", timestamp: Date.now() }],
 			},
-			Effort.XHigh,
+			Effort.Max,
 		)) as {
 			thinking?: { type?: string; budget_tokens?: number };
 			output_config?: { effort?: string };
@@ -2098,7 +2107,7 @@ describe("Anthropic request fingerprint alignment", () => {
 				name: "Claude Opus 4.7",
 				thinking: {
 					mode: "anthropic-adaptive",
-					efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+					efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 				},
 			}),
 			{
@@ -2120,7 +2129,7 @@ describe("Anthropic request fingerprint alignment", () => {
 		expect(payload.context_management).toEqual({
 			edits: [{ type: "clear_thinking_20251015", keep: "all" }],
 		});
-		expect(payload.output_config).toEqual({ effort: "xhigh" });
+		expect(payload.output_config).toEqual({ effort: "high" });
 	});
 
 	it("sends task budgets through Anthropic output_config without dropping adaptive effort", async () => {
@@ -2131,7 +2140,7 @@ describe("Anthropic request fingerprint alignment", () => {
 				name: "Claude Opus 4.7",
 				thinking: {
 					mode: "anthropic-adaptive",
-					efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+					efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 				},
 			}),
 			{
@@ -2151,7 +2160,7 @@ describe("Anthropic request fingerprint alignment", () => {
 		};
 
 		expect(payload.output_config).toEqual({
-			effort: "xhigh",
+			effort: "high",
 			task_budget: { type: "tokens", total: 64_000, remaining: 48_000 },
 		});
 	});
@@ -2164,7 +2173,7 @@ describe("Anthropic request fingerprint alignment", () => {
 				name: "Claude Opus 4.7",
 				thinking: {
 					mode: "anthropic-adaptive",
-					efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+					efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 				},
 			}),
 			{
@@ -2209,7 +2218,7 @@ describe("Anthropic request fingerprint alignment", () => {
 					maxTokens: 128_000,
 					thinking: {
 						mode: "anthropic-adaptive",
-						efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+						efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 					},
 				}),
 				{
@@ -2236,7 +2245,7 @@ describe("Anthropic request fingerprint alignment", () => {
 
 			expect(payload.tool_choice).toEqual({ type: "auto" });
 			expect(payload.thinking).toEqual({ type: "adaptive", display: "summarized" });
-			expect(payload.output_config).toEqual({ effort: "xhigh" });
+			expect(payload.output_config).toEqual({ effort: "high" });
 		}
 	});
 
diff --git a/packages/ai/test/auth-gateway-anthropic-messages.test.ts b/packages/ai/test/auth-gateway-anthropic-messages.test.ts
index dce464548..1df22f39e 100644
--- a/packages/ai/test/auth-gateway-anthropic-messages.test.ts
+++ b/packages/ai/test/auth-gateway-anthropic-messages.test.ts
@@ -2,6 +2,7 @@ import { describe, expect, it } from "bun:test";
 import { encodeResponse, encodeStream, parseRequest } from "@oh-my-pi/pi-ai/providers/anthropic-messages-server";
 import type { AssistantMessage, AssistantMessageEvent, ToolResultMessage } from "@oh-my-pi/pi-ai/types";
 import { AssistantMessageEventStream } from "@oh-my-pi/pi-ai/utils/event-stream";
+import { Effort } from "@oh-my-pi/pi-catalog/effort";
 
 function emptyUsage(): AssistantMessage["usage"] {
 	return {
@@ -220,6 +221,32 @@ describe("anthropic-messages parseRequest", () => {
 		expect(parsed.context.messages[1]!.role).toBe("toolResult");
 	});
 
+	it("maps inbound output_config.effort onto options.reasoning 1:1", () => {
+		const cases = [
+			["low", Effort.Low],
+			["medium", Effort.Medium],
+			["high", Effort.High],
+			["xhigh", Effort.XHigh],
+			["max", Effort.Max],
+		] as const;
+		for (const [wire, effort] of cases) {
+			const parsed = parseRequest({
+				model: "m",
+				max_tokens: 8,
+				output_config: { effort: wire },
+				messages: [{ role: "user", content: "hi" }],
+			});
+			expect(parsed.options.reasoning).toBe(effort);
+		}
+
+		const absent = parseRequest({
+			model: "m",
+			max_tokens: 8,
+			messages: [{ role: "user", content: "hi" }],
+		});
+		expect(absent.options.reasoning).toBeUndefined();
+	});
+
 	it("rejects missing required fields and unsupported request controls", () => {
 		expect(() => parseRequest({})).toThrow(/model/);
 		expect(() => parseRequest({ model: "m", messages: [] })).toThrow(/max_tokens/);
diff --git a/packages/ai/test/deepseek-reasoning-content.test.ts b/packages/ai/test/deepseek-reasoning-content.test.ts
index 3cbdfd349..f651f5714 100644
--- a/packages/ai/test/deepseek-reasoning-content.test.ts
+++ b/packages/ai/test/deepseek-reasoning-content.test.ts
@@ -3,6 +3,7 @@ import { renderDemotedThinking } from "@oh-my-pi/pi-ai/dialect";
 import { convertMessages } from "@oh-my-pi/pi-ai/providers/openai-completions";
 import type { AssistantMessage, Model, ModelSpec, ThinkingContent, ToolCall } from "@oh-my-pi/pi-ai/types";
 import { buildModel } from "@oh-my-pi/pi-catalog/build";
+import { Effort } from "@oh-my-pi/pi-catalog/effort";
 import { getBundledModel } from "@oh-my-pi/pi-catalog/models";
 
 interface OpenAICompletionAssistantWireMessage {
@@ -66,52 +67,37 @@ function assistantToolCall(
 
 describe("DeepSeek reasoning_content tool-call replay", () => {
 	// ----------------------------------------------------------------
-	// Fix 1: effortMap for DeepSeek-family on any provider
+	// Fix 1: honest [high, max] ladder for DeepSeek-family on any provider
 	// ----------------------------------------------------------------
-	describe("thinking effortMap (Fix 1)", () => {
-		it("maps unsupported lower DeepSeek efforts to high on opencode-go", () => {
+	describe("thinking ladder (Fix 1)", () => {
+		it("bakes the honest [high, max] ladder with no effortMap on opencode-go", () => {
 			const model = deepseekModel({
 				provider: "opencode-go",
 				baseUrl: "https://opencode.ai/zen/go/v1",
 				id: "deepseek-v4-flash",
 			});
-			expect(model.thinking?.effortMap).toMatchObject({
-				minimal: "high",
-				low: "high",
-				medium: "high",
-				high: "high",
-				xhigh: "max",
-			});
+			expect(model.thinking?.efforts).toEqual([Effort.High, Effort.Max]);
+			expect(model.thinking?.effortMap).toBeUndefined();
 		});
 
-		it("maps unsupported lower DeepSeek efforts to high on NVIDIA", () => {
+		it("bakes the honest [high, max] ladder with no effortMap on NVIDIA", () => {
 			const model = deepseekModel({
 				provider: "nvidia",
 				baseUrl: "https://integrate.api.nvidia.com/v1",
 				id: "deepseek-ai/deepseek-v4-flash",
 			});
-			expect(model.thinking?.effortMap).toMatchObject({
-				minimal: "high",
-				low: "high",
-				medium: "high",
-				high: "high",
-				xhigh: "max",
-			});
+			expect(model.thinking?.efforts).toEqual([Effort.High, Effort.Max]);
+			expect(model.thinking?.effortMap).toBeUndefined();
 		});
 
-		it("maps unsupported lower DeepSeek efforts to high on the official endpoint", () => {
+		it("bakes the honest [high, max] ladder with no effortMap on the official endpoint", () => {
 			const model = deepseekModel({
 				provider: "deepseek",
 				baseUrl: "https://api.deepseek.com/v1",
 				id: "deepseek-v4-pro",
 			});
-			expect(model.thinking?.effortMap).toMatchObject({
-				minimal: "high",
-				low: "high",
-				medium: "high",
-				high: "high",
-				xhigh: "max",
-			});
+			expect(model.thinking?.efforts).toEqual([Effort.High, Effort.Max]);
+			expect(model.thinking?.effortMap).toBeUndefined();
 		});
 
 		it("does NOT map xhigh for non-DeepSeek models", () => {
diff --git a/packages/ai/test/glm-5.2-reasoning-effort.test.ts b/packages/ai/test/glm-5.2-reasoning-effort.test.ts
index 969e4291f..1cb4246f0 100644
--- a/packages/ai/test/glm-5.2-reasoning-effort.test.ts
+++ b/packages/ai/test/glm-5.2-reasoning-effort.test.ts
@@ -6,11 +6,12 @@ import { buildModel } from "@oh-my-pi/pi-catalog/build";
 import { Effort } from "@oh-my-pi/pi-catalog/effort";
 
 // GLM-5.2 reasoning-effort dialects diverge per host (verified against live
-// endpoints): a direct GLM host (Fireworks) wants the top UI tier on the wire
-// as `max` while keeping its distinct lower tiers, whereas OpenRouter rejects
-// `max` (HTTP 400) and treats `xhigh` as its own max tier. The catalog bakes
-// the right `thinking.effortMap`; these tests pin the resulting wire value so a
-// future map change can't silently 400 either host.
+// endpoints): a direct GLM host (Fireworks) exposes a real `max` top tier and
+// keeps its distinct lower tiers (with the `minimal -> none` host quirk),
+// whereas OpenRouter rejects `max` (HTTP 400) and treats `xhigh` as its own
+// max tier. The catalog bakes the right ladder/`thinking.effortMap`; these
+// tests pin the resulting wire value so a future change can't silently 400
+// either host.
 const context: Context = { messages: [{ role: "user", content: "hi", timestamp: 0 }] };
 
 function chatSse(): Response {
@@ -105,8 +106,8 @@ const openRouter = buildModel({
 describe("GLM-5.2 reasoning effort wire mapping", () => {
 	afterEach(() => vi.restoreAllMocks());
 
-	it("maps the top tier to reasoning_effort:max on a direct GLM host (Fireworks), lower tiers literal", async () => {
-		expect(await captureChatEffort(fireworks, Effort.XHigh)).toBe("max");
+	it("sends reasoning_effort:max for the real max tier on a direct GLM host (Fireworks), lower tiers literal", async () => {
+		expect(await captureChatEffort(fireworks, Effort.Max)).toBe("max");
 		expect(await captureChatEffort(fireworks, Effort.High)).toBe("high");
 		expect(await captureChatEffort(fireworks, Effort.Medium)).toBe("medium");
 		// Fireworks rejects literal `minimal`; the host quirk merge keeps `minimal -> none`.
diff --git a/packages/ai/test/max-effort-wire.test.ts b/packages/ai/test/max-effort-wire.test.ts
new file mode 100644
index 000000000..d716fe221
--- /dev/null
+++ b/packages/ai/test/max-effort-wire.test.ts
@@ -0,0 +1,158 @@
+import { describe, expect, it, vi } from "bun:test";
+import { streamAnthropic } from "@oh-my-pi/pi-ai/providers/anthropic";
+import { transformRequestBody } from "@oh-my-pi/pi-ai/providers/openai-codex/request-transformer";
+import { streamOpenAICompletions } from "@oh-my-pi/pi-ai/providers/openai-completions";
+import { streamOpenAIResponses } from "@oh-my-pi/pi-ai/providers/openai-responses";
+import type { Context, FetchImpl, Model } from "@oh-my-pi/pi-ai/types";
+import { buildModel } from "@oh-my-pi/pi-catalog/build";
+import { Effort } from "@oh-my-pi/pi-catalog/effort";
+import { createCodexModel } from "./helpers";
+
+// End-to-end guard for the first-class `max` reasoning tier: a user-requested
+// `reasoning: "max"` on a model whose ladder natively includes `Effort.Max`
+// must reach every wire surface verbatim — no aliasing, no clamping. Fixtures
+// use explicit thinking ladders and neutral ids so catalog detection cannot
+// interfere.
+
+const context: Context = { messages: [{ role: "user", content: "hi", timestamp: 0 }] };
+
+const MAX_LADDER = [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max] as const;
+
+function chatSse(): Response {
+	const chunk = (delta: unknown, finish: string | null) =>
+		JSON.stringify({
+			id: "x",
+			object: "chat.completion.chunk",
+			created: 0,
+			choices: [{ index: 0, delta, finish_reason: finish }],
+		});
+	return new Response(`data: ${chunk({ content: "ok" }, null)}\n\ndata: ${chunk({}, "stop")}\n\ndata: [DONE]\n\n`, {
+		status: 200,
+		headers: { "content-type": "text/event-stream" },
+	});
+}
+
+function responsesSse(): Response {
+	return new Response(
+		`data: ${JSON.stringify({
+			type: "response.completed",
+			response: {
+				status: "completed",
+				usage: { input_tokens: 1, output_tokens: 1, total_tokens: 2, input_tokens_details: { cached_tokens: 0 } },
+			},
+		})}\n\n`,
+		{ status: 200, headers: { "content-type": "text/event-stream" } },
+	);
+}
+
+describe("first-class max reasoning tier wire coverage", () => {
+	it("sends reasoning_effort:max on Chat Completions", async () => {
+		const model: Model<"openai-completions"> = buildModel({
+			id: "max-wire-chat",
+			name: "Max Wire Chat",
+			api: "openai-completions",
+			provider: "custom",
+			baseUrl: "https://chat.example.test/v1",
+			reasoning: true,
+			compat: {
+				thinkingFormat: "openai",
+				supportsReasoningParams: true,
+				supportsReasoningEffort: true,
+			},
+			thinking: { mode: "effort", efforts: MAX_LADDER },
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 128_000,
+			maxTokens: 16_384,
+		});
+
+		let body: Record<string, unknown> | undefined;
+		const fetchMock: FetchImpl = vi.fn(async (_input: string | URL | Request, init?: RequestInit) => {
+			body = JSON.parse(typeof init?.body === "string" ? init.body : "{}") as Record<string, unknown>;
+			return chatSse();
+		});
+		for await (const event of streamOpenAICompletions(model, context, {
+			apiKey: "k",
+			fetch: fetchMock,
+			reasoning: "max",
+		})) {
+			if (event.type === "done" || event.type === "error") break;
+		}
+		expect(body?.reasoning_effort).toBe("max");
+	});
+
+	it("sends reasoning.effort:max on the Responses surface", async () => {
+		const model: Model<"openai-responses"> = buildModel({
+			id: "max-wire-responses",
+			name: "Max Wire Responses",
+			api: "openai-responses",
+			provider: "custom-responses",
+			baseUrl: "https://responses.example.test/v1",
+			reasoning: true,
+			compat: {
+				supportsReasoningParams: true,
+				supportsReasoningEffort: true,
+			},
+			thinking: { mode: "effort", efforts: MAX_LADDER },
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 128_000,
+			maxTokens: 16_384,
+		});
+
+		let body: Record<string, unknown> | undefined;
+		const fetchMock: FetchImpl = vi.fn(async (_input: string | URL | Request, init?: RequestInit) => {
+			body = JSON.parse(typeof init?.body === "string" ? init.body : "{}") as Record<string, unknown>;
+			return responsesSse();
+		});
+		for await (const event of streamOpenAIResponses(model, context, {
+			apiKey: "k",
+			fetch: fetchMock,
+			reasoning: "max",
+		})) {
+			if (event.type === "done" || event.type === "error") break;
+		}
+		const reasoningParam = body?.reasoning as { effort?: string } | undefined;
+		expect(reasoningParam?.effort).toBe("max");
+	});
+
+	it("sends reasoning.effort:max through the Codex request transformer", async () => {
+		const model = createCodexModel("codex-max-wire", {
+			thinking: { mode: "effort", efforts: MAX_LADDER },
+		});
+		const transformed = await transformRequestBody({ model: model.id, input: [] }, model, {
+			reasoningEffort: "max",
+		});
+		expect(transformed.reasoning?.effort).toBe("max");
+	});
+
+	it("sends output_config.effort:max on Anthropic adaptive thinking", async () => {
+		const model = buildModel({
+			id: "adaptive-max-wire",
+			name: "Adaptive Max Wire",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: true,
+			thinking: { mode: "anthropic-adaptive", efforts: MAX_LADDER },
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 200_000,
+			maxTokens: 8_192,
+		});
+
+		const { promise, resolve } = Promise.withResolvers<unknown>();
+		const controller = new AbortController();
+		controller.abort();
+		streamAnthropic(model, context, {
+			apiKey: "sk-ant-test",
+			isOAuth: false,
+			signal: controller.signal,
+			thinkingEnabled: true,
+			reasoning: Effort.Max,
+			onPayload: payload => resolve(payload),
+		});
+		const payload = (await promise) as { output_config?: { effort?: string } };
+		expect(payload.output_config).toEqual({ effort: "max" });
+	});
+});
diff --git a/packages/ai/test/ollama-reasoning-effort-backfill.test.ts b/packages/ai/test/ollama-reasoning-effort-backfill.test.ts
index 8cafe1f2a..04d0ea2af 100644
--- a/packages/ai/test/ollama-reasoning-effort-backfill.test.ts
+++ b/packages/ai/test/ollama-reasoning-effort-backfill.test.ts
@@ -3,6 +3,7 @@ import { streamOpenAIResponses } from "@oh-my-pi/pi-ai/providers/openai-response
 import type { Context } from "@oh-my-pi/pi-ai/types";
 import { buildModel } from "@oh-my-pi/pi-catalog/build";
 import { Effort } from "@oh-my-pi/pi-catalog/effort";
+import { clampThinkingLevelForModel, getSupportedEfforts } from "@oh-my-pi/pi-catalog/model-thinking";
 
 const testContext: Context = {
 	messages: [{ role: "user", content: "hi", timestamp: 0 }],
@@ -14,11 +15,13 @@ function abortedSignal(): AbortSignal {
 	return controller.signal;
 }
 
-describe("ollama reasoning effort backfill reaches the Responses wire", () => {
-	it("sends low instead of minimal for a stale ollama spec carrying no effort map", async () => {
-		// Reproduces the HTTP 400 `invalid reasoning value: "minimal"` path: a
-		// reasoning-capable Ollama model whose cached/custom spec predates the
-		// remap. buildModel must backfill the effort map so the wire sends `low`.
+describe("ollama effort ladder normalization reaches the Responses wire", () => {
+	it("normalizes a stale ollama spec and sends native max on the wire", async () => {
+		// A cached/custom spec from before the wire-exact ladder existed:
+		// reasoning-capable with `minimal` offered. buildModel must normalize
+		// the ladder to Ollama's low/medium/high/max vocabulary so requests at
+		// the top tier serialize `max` verbatim (HTTP 400 `invalid reasoning
+		// value: "minimal"` was the historical failure of the stale surface).
 		const model = buildModel({
 			id: "gemma4:e4b",
 			name: "gemma4:e4b",
@@ -33,16 +36,20 @@ describe("ollama reasoning effort backfill reaches the Responses wire", () => {
 			thinking: { mode: "effort", efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High] },
 		});
 
+		// The stale `minimal` tier is gone; selecting it clamps to the floor.
+		expect(getSupportedEfforts(model)).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.Max]);
+		expect(clampThinkingLevelForModel(model, Effort.Minimal)).toBe(Effort.Low);
+
 		const { promise, resolve } = Promise.withResolvers<Record<string, unknown>>();
 		streamOpenAIResponses(model, testContext, {
 			apiKey: "test-key",
 			signal: abortedSignal(),
-			reasoning: "minimal",
+			reasoning: "max",
 			reasoningSummary: "auto",
 			onPayload: payload => resolve(payload as Record<string, unknown>),
 		});
 
 		const payload = await promise;
-		expect(payload.reasoning).toEqual({ effort: "low", summary: "auto" });
+		expect(payload.reasoning).toEqual({ effort: "max", summary: "auto" });
 	});
 });
diff --git a/packages/ai/test/openai-codex.test.ts b/packages/ai/test/openai-codex.test.ts
index 1c7492afc..d174d7071 100644
--- a/packages/ai/test/openai-codex.test.ts
+++ b/packages/ai/test/openai-codex.test.ts
@@ -312,28 +312,29 @@ describe("openai-codex reasoning effort validation", () => {
 			transformRequestBody({ ...body }, createCodexModel(body.model), { reasoningEffort: "xhigh" }),
 		).rejects.toThrow(/Supported efforts: medium, high/);
 	});
+
+	it("rejects gpt-5.6 minimal now that the wire floor is low", async () => {
+		const body: RequestBody = { model: "gpt-5.6-sol", input: [] };
+		await expect(
+			transformRequestBody(body, createCodexModel(body.model), { reasoningEffort: "minimal" }),
+		).rejects.toThrow(/Supported efforts: low, medium, high, xhigh, max/);
+	});
 });
 
 describe("openai-codex reasoning effort wire mapping", () => {
-	it("shifts gpt-5.6 user efforts one wire tier up via the baked effort map", async () => {
+	it("maps gpt-5.6 user efforts 1:1 onto wire tiers", async () => {
 		const model = createCodexModel("gpt-5.6-sol");
-		const shifted = [
-			["minimal", "low"],
-			["low", "medium"],
-			["medium", "high"],
-			["high", "xhigh"],
-			["xhigh", "max"],
-		] as const;
+		const efforts = ["low", "medium", "high", "xhigh", "max"] as const;
 
-		for (const [requested, wire] of shifted) {
+		for (const effort of efforts) {
 			const transformed = await transformRequestBody({ model: model.id }, model, {
-				reasoningEffort: requested,
+				reasoningEffort: effort,
 			});
-			expect(transformed.reasoning?.effort).toBe(wire);
+			expect(transformed.reasoning?.effort).toBe(effort);
 		}
 	});
 
-	it("keeps pre-5.6 efforts unshifted and passes none through unmapped", async () => {
+	it("keeps pre-5.6 efforts 1:1 and passes none through unmapped", async () => {
 		const gpt55 = createCodexModel("gpt-5.5");
 		const unshifted = await transformRequestBody({ model: gpt55.id }, gpt55, { reasoningEffort: "xhigh" });
 		expect(unshifted.reasoning?.effort).toBe("xhigh");
diff --git a/packages/ai/test/openai-completions-compat.test.ts b/packages/ai/test/openai-completions-compat.test.ts
index 728124025..4c9d8ff0e 100644
--- a/packages/ai/test/openai-completions-compat.test.ts
+++ b/packages/ai/test/openai-completions-compat.test.ts
@@ -115,7 +115,7 @@ function kimiZaiModel(): Model<"openai-completions"> {
 async function captureOpenAICompletionsPayload(
 	model: Model<"openai-completions">,
 	context: Context = baseContext(),
-	options?: { reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" },
+	options?: { reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max" },
 ): Promise<unknown> {
 	const { promise, resolve } = Promise.withResolvers<unknown>();
 	const fetchMock = createMockFetch(["[DONE]"]);
@@ -810,7 +810,7 @@ describe("openai-completions compatibility", () => {
 		expect(getNestedBoolean(chatTemplateArgs, "enable_thinking")).toBe(true);
 	});
 
-	it("maps GLM-5.2 xhigh to Z.AI max and enables tool streaming", async () => {
+	it("sends reasoning_effort:max for the real Z.AI max tier and enables tool streaming", async () => {
 		const model = zaiGlm52Model();
 		const readTool: Tool = {
 			name: "read",
@@ -828,7 +828,7 @@ describe("openai-completions compatibility", () => {
 			{ ...baseContext(), tools: [readTool] },
 			{
 				apiKey: "test-key",
-				reasoning: "xhigh",
+				reasoning: "max",
 				signal: createAbortedSignal(),
 				onPayload: payload => resolve(payload),
 				maxTokens: 65_536,
@@ -879,21 +879,10 @@ describe("openai-completions compatibility", () => {
 		expect(payloadObject?.tool_stream).toBeUndefined();
 	});
 
-	it("maps GLM-5.2 minimal reasoning to disabled Z.AI thinking", async () => {
+	it("bakes the honest [high, max] Z.AI GLM-5.2 ladder with no effortMap", () => {
 		const model = zaiGlm52Model();
-
-		const { promise, resolve } = Promise.withResolvers<unknown>();
-		streamOpenAICompletions(model, baseContext(), {
-			apiKey: "test-key",
-			reasoning: "minimal",
-			signal: createAbortedSignal(),
-			onPayload: payload => resolve(payload),
-		});
-		const payload = await promise;
-		const thinking = getNestedObject(payload, "thinking");
-
-		expect(thinking?.type).toBe("disabled");
-		expect(toObject(payload)?.reasoning_effort).toBeUndefined();
+		expect(model.thinking?.efforts).toEqual([Effort.High, Effort.Max]);
+		expect(model.thinking?.effortMap).toBeUndefined();
 	});
 
 	it("treats finish_reason end as stop", async () => {
@@ -1217,7 +1206,7 @@ describe("kimi model detection via detectCompat", () => {
 		expect(openRouterKimi.compat.thinkingFormat).toBe("openrouter");
 	});
 
-	it("maps OpenRouter Anthropic adaptive reasoning efforts to the Anthropic scale", async () => {
+	it("sends OpenRouter Anthropic adaptive reasoning efforts 1:1 on the wire", async () => {
 		const model: Model<"openai-completions"> = buildModel({
 			...gpt4oMiniSpec,
 			api: "openai-completions",
@@ -1229,9 +1218,11 @@ describe("kimi model detection via detectCompat", () => {
 
 		const highPayload = await captureOpenAICompletionsPayload(model, baseContext(), { reasoning: "high" });
 		const xhighPayload = await captureOpenAICompletionsPayload(model, baseContext(), { reasoning: "xhigh" });
+		const maxPayload = await captureOpenAICompletionsPayload(model, baseContext(), { reasoning: "max" });
 
-		expect(getNestedObject(highPayload, "reasoning")).toEqual({ effort: "xhigh" });
-		expect(getNestedObject(xhighPayload, "reasoning")).toEqual({ effort: "max" });
+		expect(getNestedObject(highPayload, "reasoning")).toEqual({ effort: "high" });
+		expect(getNestedObject(xhighPayload, "reasoning")).toEqual({ effort: "xhigh" });
+		expect(getNestedObject(maxPayload, "reasoning")).toEqual({ effort: "max" });
 	});
 
 	// Regression for #1071: OpenCode-Go/Zen handle reasoning content server-side
diff --git a/packages/ai/test/openai-reasoning-effort-fallback.test.ts b/packages/ai/test/openai-reasoning-effort-fallback.test.ts
index 1676e29ff..991be7df8 100644
--- a/packages/ai/test/openai-reasoning-effort-fallback.test.ts
+++ b/packages/ai/test/openai-reasoning-effort-fallback.test.ts
@@ -171,10 +171,10 @@ function createResponsesModel(): Model<"openai-responses"> {
 		maxTokens: 16_384,
 	});
 }
-function createMappedResponsesModel(): Model<"openai-responses"> {
+function createMaxLadderResponsesModel(): Model<"openai-responses"> {
 	return buildModel({
-		id: "mapped-responses-reasoner",
-		name: "Mapped Responses Reasoner",
+		id: "max-ladder-responses-reasoner",
+		name: "Max Ladder Responses Reasoner",
 		api: "openai-responses",
 		provider: "custom-responses",
 		baseUrl: "https://responses.example.test/v1",
@@ -185,8 +185,7 @@ function createMappedResponsesModel(): Model<"openai-responses"> {
 		},
 		thinking: {
 			mode: "effort",
-			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-			effortMap: { [Effort.XHigh]: "max" },
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 		},
 		input: ["text"],
 		cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
@@ -285,10 +284,10 @@ describe("OpenAI reasoning effort fallback retry", () => {
 			{ preconnect: fetch.preconnect },
 		);
 
-		const result = await streamOpenAIResponses(createMappedResponsesModel(), testContext, {
+		const result = await streamOpenAIResponses(createMaxLadderResponsesModel(), testContext, {
 			apiKey: "test-key",
 			fetch: fetchMock,
-			reasoning: "xhigh",
+			reasoning: "max",
 		}).result();
 
 		expect(result.stopReason).toBe("stop");
diff --git a/packages/ai/test/stream.test.ts b/packages/ai/test/stream.test.ts
index ce1769430..c48f90d83 100644
--- a/packages/ai/test/stream.test.ts
+++ b/packages/ai/test/stream.test.ts
@@ -1765,7 +1765,7 @@ describe("Generate E2E Tests", () => {
 						tools: [calculatorTool],
 					},
 					{
-						reasoning: Effort.XHigh,
+						reasoning: Effort.Max,
 						interleavedThinking: true,
 						onPayload: payload => {
 							capturedPayload = payload;
diff --git a/packages/catalog/CHANGELOG.md b/packages/catalog/CHANGELOG.md
index 1df563b14..02e7eee1e 100644
--- a/packages/catalog/CHANGELOG.md
+++ b/packages/catalog/CHANGELOG.md
@@ -10,10 +10,17 @@
 - Added Zenmux variants for GPT-5.6 (Luna, Sol, and Terra)
 - Added Novita as a model provider with authoritative public catalog discovery and generated pricing, limits, modality, reasoning, and tool metadata ([#4917](https://github.com/can1357/oh-my-pi/pull/4917) by [@jason-wu-ai](https://github.com/jason-wu-ai)).
 - Added `useResponsesLite` to `Model`/`ModelSpec` and Codex discovery parsing of the upstream `use_responses_lite` flag; regenerated `models.json` marks the GPT-5.6 family (`sol`/`terra`/`luna` and their pro aliases) for the Responses Lite transport. Added the `x-openai-internal-codex-responses-lite` marker to `OPENAI_HEADERS`.
+- Added `Effort.Max` ("max") as a first-class user-facing thinking level above `xhigh`.
 
 ### Changed
 
+- Standardized reasoning effort levels to use a wire-exact `max` tier across all model providers
+- Refactored Devin model routing to support 1:1 mapping for the `max` effort tier
+- Normalized stale Ollama model configurations to the new wire-exact effort ladder
+
 - Updated costs and context windows for various models in the catalog
+- **Breaking**: Effort ladders are now wire-exact and the shifted five-tier effort mapping is gone. Models expose exactly the effort tiers their wire accepts, mapped 1:1: GPT-5.6+ and Anthropic adaptive models with a real xhigh tier (Opus 4.7+, Sonnet 5+, Fable/Mythos 5) expose `low..max`; legacy adaptive models (Opus 4.6 and all Bedrock adaptive) expose `low/medium/high/max`; Sonnet/Haiku 4.6 expose `low/medium/high`; GLM-5.2 on Z.ai/Zhipu/Umans/Ollama Cloud/Baseten and Sakana Fugu and DeepSeek expose `high/max`; local Ollama reasoning models expose `low/medium/high/max`; Fire Pass Kimi exposes `low..max` with distinct `xhigh` and `max` budgets. Removed `SHIFTED_FIVE_TIER_EFFORT_MAP`, `ANTHROPIC_ADAPTIVE_EFFORT_MAP_4_TIER`, and the per-host `xhigh -> "max"` alias maps; selecting a tier a model lacks clamps down via `clampThinkingLevelForModel`. Devin effort routing is now 1:1 onto per-tier siblings (`max -> -max`; families without a `-max` sibling top out at `xhigh`; the fake `minimal -> -low` fallback is gone). Regenerated `models.json`.
+- Changed `fillThinkingWireDefaults` to re-derive the effort map whenever the model-defined ladder disagrees with cached metadata, so stale cached surfaces from the shifted-map era normalize to the new wire-exact shape on every `buildModel`.
 
 ## [16.3.15] - 2026-07-09
 
diff --git a/packages/catalog/src/compat/openai.ts b/packages/catalog/src/compat/openai.ts
index dcfcd3df9..a01430b33 100644
--- a/packages/catalog/src/compat/openai.ts
+++ b/packages/catalog/src/compat/openai.ts
@@ -71,31 +71,11 @@ const DSML_HEALING_PROVIDERS = new Set([
 	"openrouter",
 ]);
 
-/**
- * Ollama's OpenAI-compatible `reasoning.effort` only accepts
- * `high|medium|low|max|none`; OMP's `minimal`/`xhigh` levels make the server
- * reject the turn with HTTP 400 `invalid reasoning value`. Map the two
- * unsupported levels onto the closest accepted ones. Stamped in the compat
- * builder (not only at discovery) so stale-cached and custom `ollama`-provider
- * specs are backfilled on every `buildModel`, not just on a fresh
- * `omp models refresh`. Custom OpenAI-compatible providers pointed at a local
- * Ollama port under a different provider id are not covered — they must set
- * `compat.reasoningEffortMap` themselves.
- */
-const OLLAMA_REASONING_EFFORT_MAP: ResolvedOpenAISharedCompat["reasoningEffortMap"] = { minimal: "low", xhigh: "max" };
-
-/**
- * Merge the Ollama default effort map under any explicit overrides (overrides
- * win). No-op off the local `ollama` provider or for non-reasoning models.
- */
-function mergeOllamaReasoningEffortMap(
-	compat: ResolvedOpenAISharedCompat,
-	provider: string,
-	reasoning: boolean | undefined,
-): void {
-	if (provider !== "ollama" || !reasoning) return;
-	compat.reasoningEffortMap = { ...OLLAMA_REASONING_EFFORT_MAP, ...compat.reasoningEffortMap };
-}
+// Ollama's OpenAI-compatible `reasoning.effort` accepts `high|medium|low|max|none`;
+// `ollama`-provider reasoning models carry the wire-exact `low..max` effort
+// ladder (see getModelDefinedEfforts), so no compat-level remapping is needed.
+// Custom OpenAI-compatible providers pointed at a local Ollama port under a
+// different provider id must set `compat.reasoningEffortMap` themselves.
 
 function resolveReasoningDisableMode(
 	thinkingFormat: ResolvedOpenAISharedCompat["thinkingFormat"],
@@ -554,7 +534,6 @@ export function buildOpenAICompat(spec: ModelSpec<"openai-completions">): Resolv
 	if (spec.compat?.omitReasoningEffort === undefined && !compat.supportsReasoningEffort) {
 		compat.omitReasoningEffort = true;
 	}
-	mergeOllamaReasoningEffortMap(compat, provider, spec.reasoning);
 	mergeMimoReasoningEffortMap(compat, isMimoReasoningEffortModel);
 
 	const whenThinkingPolicy =
@@ -568,7 +547,6 @@ export function buildOpenAICompat(spec: ModelSpec<"openai-completions">): Resolv
 		if (whenThinkingPolicy.omitReasoningEffort === undefined && !variant.supportsReasoningEffort) {
 			variant.omitReasoningEffort = true;
 		}
-		mergeOllamaReasoningEffortMap(variant, provider, spec.reasoning);
 		mergeMimoReasoningEffortMap(variant, isMimoReasoningEffortModel);
 		compat.whenThinking = variant;
 	}
@@ -678,7 +656,6 @@ export function buildOpenAIResponsesCompat(spec: OpenAIResponsesSpecLike): Resol
 	if (spec.compat?.omitReasoningEffort === undefined && !compat.supportsReasoningEffort) {
 		compat.omitReasoningEffort = true;
 	}
-	mergeOllamaReasoningEffortMap(compat, spec.provider, spec.reasoning);
 	return compat;
 }
 
diff --git a/packages/catalog/src/effort.ts b/packages/catalog/src/effort.ts
index 831a13ede..e3491c2a9 100644
--- a/packages/catalog/src/effort.ts
+++ b/packages/catalog/src/effort.ts
@@ -5,6 +5,7 @@ export const enum Effort {
 	Medium = "medium",
 	High = "high",
 	XHigh = "xhigh",
+	Max = "max",
 }
 
 export const THINKING_EFFORTS: readonly Effort[] = [
@@ -13,4 +14,5 @@ export const THINKING_EFFORTS: readonly Effort[] = [
 	Effort.Medium,
 	Effort.High,
 	Effort.XHigh,
+	Effort.Max,
 ];
diff --git a/packages/catalog/src/model-thinking.ts b/packages/catalog/src/model-thinking.ts
index 611eb1f60..f2842e4d5 100644
--- a/packages/catalog/src/model-thinking.ts
+++ b/packages/catalog/src/model-thinking.ts
@@ -61,12 +61,34 @@ const GEMINI_3_FLASH_EFFORTS: readonly Effort[] = [Effort.Minimal, Effort.Low, E
 const GPT_5_2_PLUS_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh];
 const GPT_5_1_CODEX_MINI_EFFORTS: readonly Effort[] = [Effort.Medium, Effort.High];
 const LOW_MEDIUM_HIGH_REASONING_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High];
-const GLM_52_HIGH_MAX_REASONING_EFFORTS: readonly Effort[] = [Effort.High, Effort.XHigh];
-
-const FUGU_REASONING_EFFORTS: readonly Effort[] = [Effort.High, Effort.XHigh];
-const FUGU_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
-	[Effort.XHigh]: "max",
-};
+/** Wire-exact two-tier scale (`high`/`max`): GLM-5.2 on Z.ai/Umans/Ollama Cloud/Baseten, Sakana Fugu, DeepSeek. */
+const HIGH_MAX_REASONING_EFFORTS: readonly Effort[] = [Effort.High, Effort.Max];
+/** OpenRouter's DeepSeek route accepts only `high`. */
+const HIGH_ONLY_REASONING_EFFORTS: readonly Effort[] = [Effort.High];
+/**
+ * Five wire tiers with a `low` floor: GPT-5.6+, Anthropic adaptive models
+ * with the real xhigh tier (Opus 4.7+, Sonnet 5+, Fable/Mythos 5), and the
+ * Fire Pass Kimi router (distinct xhigh and max budgets).
+ */
+const FIVE_TIER_EFFORTS_LOW_TO_MAX: readonly Effort[] = [
+	Effort.Low,
+	Effort.Medium,
+	Effort.High,
+	Effort.XHigh,
+	Effort.Max,
+];
+/** Legacy adaptive scale (Opus/Sonnet 4.6, every Bedrock adaptive model): four wire tiers, no xhigh. */
+const FOUR_TIER_EFFORTS_LOW_TO_MAX: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.Max];
+/** GLM-5.2 resellers that pass the default lower tiers verbatim and expose the genuine `max` top tier. */
+const DEFAULT_REASONING_EFFORTS_WITH_MAX: readonly Effort[] = [
+	Effort.Minimal,
+	Effort.Low,
+	Effort.Medium,
+	Effort.High,
+	Effort.Max,
+];
+/** Local Ollama wire vocabulary (`low`/`medium`/`high`/`max`; `none` is thinking-off). */
+const OLLAMA_REASONING_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.Max];
 type EffortMap = Partial<Record<Effort, string>>;
 
 const GROQ_QWEN3_32B_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
@@ -76,57 +98,14 @@ const GROQ_QWEN3_32B_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
 	[Effort.High]: "default",
 	[Effort.XHigh]: "default",
 };
-const DEEPSEEK_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
-	[Effort.Minimal]: "high",
-	[Effort.Low]: "high",
-	[Effort.Medium]: "high",
-	[Effort.High]: "high",
-	[Effort.XHigh]: "max",
-};
 const FIREWORKS_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
 	[Effort.Minimal]: "none",
 };
-const ZAI_GLM_52_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
-	[Effort.Minimal]: "none",
-	[Effort.Low]: "high",
-	[Effort.Medium]: "high",
-	[Effort.High]: "high",
-	[Effort.XHigh]: "max",
-};
-const GLM_52_XHIGH_MAX_EFFORT_MAP: Readonly<EffortMap> = {
-	[Effort.XHigh]: "max",
-};
 const MIMO_REASONING_EFFORT_MAP: Readonly<EffortMap> = {
 	[Effort.Minimal]: "low",
 	[Effort.XHigh]: "high",
 };
 
-/**
- * Effort → wire-value map for a shifted five-tier scale (`low..max`):
- * user-facing efforts shift up one notch so the top tier reaches the genuine
- * "max" and "high" lands on the recommended "xhigh" coding/agentic default.
- * Used by Anthropic adaptive models with a real xhigh tier (Opus 4.7+ and
- * Fable/Mythos 5 on the Messages API) and by GPT-5.6+ wire-effort models,
- * which expose the same genuine `max` tier above `xhigh`.
- */
-export const SHIFTED_FIVE_TIER_EFFORT_MAP: Readonly<Partial<Record<Effort, string>>> = {
-	[Effort.Minimal]: "low",
-	[Effort.Low]: "medium",
-	[Effort.Medium]: "high",
-	[Effort.High]: "xhigh",
-	[Effort.XHigh]: "max",
-};
-
-/**
- * Effort → wire-value map for the legacy 4-tier adaptive scale (Opus 4.6,
- * Sonnet 4.6+, and every adaptive model on Bedrock Converse). `low..high` pass
- * through verbatim; there is no real "xhigh", so it aliases the top "max" tier.
- */
-export const ANTHROPIC_ADAPTIVE_EFFORT_MAP_4_TIER: Readonly<Partial<Record<Effort, string>>> = {
-	[Effort.Minimal]: "low",
-	[Effort.XHigh]: "max",
-};
-
 const MINIMAX_ANTHROPIC_ADAPTIVE_EFFORT_MAP: Readonly<EffortMap> = {
 	[Effort.Low]: "adaptive",
 	[Effort.Medium]: "adaptive",
@@ -172,8 +151,10 @@ export function resolveModelThinking<TApi extends Api>(
 /**
  * Backfill identity-derived wire facts onto explicit thinking metadata.
  * Explicit `effortMap` / `supportsDisplay` (including `false`) win, except
- * model-defined effort restrictions still normalize stale cached capability
- * surfaces before request-time code can observe them.
+ * when the model-defined effort ladder disagrees with the cached surface:
+ * then both the ladder AND the wire map are re-derived from identity, so
+ * stale cached metadata from before a wire-truth change (e.g. the retired
+ * shifted five-tier maps) cannot survive normalization.
  */
 function fillThinkingWireDefaults<TApi extends Api>(
 	spec: ModelSpec<TApi>,
@@ -184,11 +165,9 @@ function fillThinkingWireDefaults<TApi extends Api>(
 	const normalizedEfforts = getModelDefinedEfforts(spec, compat) ?? thinking.efforts;
 	const effortsChanged = !sameEffortList(normalizedEfforts, thinking.efforts);
 	const effortMap =
-		thinking.effortMap === undefined
-			? inferEffortMap(spec, compat, parsed, thinking.mode, normalizedEfforts)
-			: effortsChanged
-				? filterEffortMapToSupportedEfforts(thinking.effortMap, normalizedEfforts)
-				: undefined;
+		thinking.effortMap === undefined || effortsChanged
+			? inferEffortMap(spec, compat, thinking.mode, normalizedEfforts)
+			: undefined;
 	const shouldReplaceEffortMap = thinking.effortMap === undefined ? effortMap !== undefined : effortsChanged;
 	const needsDisplay =
 		thinking.supportsDisplay === undefined &&
@@ -229,7 +208,7 @@ export function deriveThinking<TApi extends Api>(spec: ModelSpec<TApi>, compat:
 		mode: inferThinkingControlMode(spec, parsed),
 		efforts,
 	};
-	const effortMap = inferEffortMap(spec, compat, parsed, config.mode, config.efforts);
+	const effortMap = inferEffortMap(spec, compat, config.mode, config.efforts);
 	if (effortMap !== undefined) {
 		config.effortMap = effortMap;
 	}
@@ -264,11 +243,10 @@ function omitsWireReasoningEffort(api: Api, compat: CompatOf<Api>): boolean {
 function inferEffortMap<TApi extends Api>(
 	spec: ModelSpec<TApi>,
 	compat: CompatOf<TApi>,
-	parsedModel: ParsedModel,
 	mode: ThinkingConfig["mode"],
 	efforts: readonly Effort[],
 ): EffortMap | undefined {
-	const detected = inferDetectedEffortMap(spec, compat, parsedModel, mode);
+	const detected = inferDetectedEffortMap(spec, compat, mode);
 	const configured = readCompatEffortMap(compat);
 	const merged =
 		detected === undefined ? configured : configured === undefined ? detected : { ...detected, ...configured };
@@ -300,9 +278,9 @@ function isOpenAICompatReasoningApi(api: Api): boolean {
 
 /**
  * GPT-5.6+ addressed through a wire `reasoning.effort`/`reasoning_effort`
- * field, where the shifted five-tier map applies. Devin (`devin-agent`)
- * selects effort by routing to per-tier sibling model ids instead and must
- * stay unmapped.
+ * field, where the five-tier `low..max` wire scale applies. Devin
+ * (`devin-agent`) selects effort by routing to per-tier sibling model ids
+ * instead and must stay unmapped.
  */
 function isGpt56PlusWireEffortModel<TApi extends Api>(spec: ModelSpec<TApi>): boolean {
 	switch (spec.api) {
@@ -324,24 +302,64 @@ function getModelDefinedEfforts<TApi extends Api>(
 	compat: CompatOf<TApi>,
 ): readonly Effort[] | undefined {
 	if (isGlm52ReasoningEffortModelId(spec.id)) {
-		// Z.ai/Zhipu and OpenRouter both surface GLM-5.2's full effort ladder,
-		// including the top `xhigh` (= "max") tier; Umans and Ollama Cloud
-		// expose only high/max.
-		if (isZaiThinkingFormat(compat) || isOpenRouterThinkingFormat(compat)) {
+		// GLM-5.2's reasoning_effort dialect is host-specific (verified against
+		// live endpoints):
+		//   - Z.ai/Zhipu ("zai" dialect) expose only high/max ("none" is the
+		//     thinking-off state, not a user tier).
+		//   - Umans, Ollama Cloud, and Baseten serve the same two-tier
+		//     high/max scale on their GLM-5.2 routes.
+		//   - OpenRouter rejects `max` — `xhigh` IS its top tier.
+		//   - Other openai-compat hosts (Fireworks, resellers) pass the
+		//     default lower tiers through verbatim and expose the genuine
+		//     `max` above `high` (host quirks like Fireworks' minimal→none
+		//     stay in the host maps).
+		if (isOpenRouterThinkingFormat(compat)) {
 			return DEFAULT_REASONING_EFFORTS_WITH_XHIGH;
 		}
-		if (isUmansGlm52ReasoningEffortModel(spec) || isOllamaCloudGlm52ReasoningEffortModel(spec)) {
-			return GLM_52_HIGH_MAX_REASONING_EFFORTS;
+		if (
+			isZaiThinkingFormat(compat) ||
+			isUmansGlm52ReasoningEffortModel(spec) ||
+			isOllamaCloudGlm52ReasoningEffortModel(spec) ||
+			spec.provider === "baseten"
+		) {
+			return HIGH_MAX_REASONING_EFFORTS;
+		}
+		if (isOpenAICompatReasoningApi(spec.api)) {
+			return DEFAULT_REASONING_EFFORTS_WITH_MAX;
 		}
 	}
 	if (isSakanaFuguReasoningModel(spec)) {
-		return FUGU_REASONING_EFFORTS;
+		return HIGH_MAX_REASONING_EFFORTS;
 	}
 	if (isGpt56PlusWireEffortModel(spec)) {
-		// Normalize stale baked/discovered `low..xhigh` surfaces to the full
-		// five-tier ladder so the shifted map keeps the native `low` tier
-		// reachable (user `minimal`).
-		return DEFAULT_REASONING_EFFORTS_WITH_XHIGH;
+		// Normalize stale baked/discovered `low..xhigh` surfaces to the
+		// wire-exact five-tier `low..max` ladder.
+		return FIVE_TIER_EFFORTS_LOW_TO_MAX;
+	}
+	const anthropicAdaptive = getAnthropicAdaptiveEfforts(spec);
+	if (anthropicAdaptive !== undefined) {
+		return anthropicAdaptive;
+	}
+	// Fire Pass's Kimi router accepts low..max with distinct xhigh and max
+	// budgets; user minimal has no wire tier there.
+	if (spec.provider === "firepass") {
+		return FIVE_TIER_EFFORTS_LOW_TO_MAX;
+	}
+	// Local Ollama's effort vocabulary is low/medium/high/max regardless of
+	// model. Custom OpenAI-compatible providers pointed at an Ollama port
+	// under a different provider id must set `compat.reasoningEffortMap`
+	// themselves.
+	if (spec.provider === "ollama") {
+		return OLLAMA_REASONING_EFFORTS;
+	}
+	if (isOpenAICompatReasoningApi(spec.api) && isDeepseekReasoningModel(spec)) {
+		// DeepSeek's reasoning_effort accepts only high/max; OpenRouter's
+		// DeepSeek route tops out at high.
+		return isOpenRouterThinkingFormat(compat) ? HIGH_ONLY_REASONING_EFFORTS : HIGH_MAX_REASONING_EFFORTS;
+	}
+	if (spec.provider === "baseten" && isOpenAIGptOssModelId(spec.id)) {
+		// Baseten's gpt-oss router mirrors its GLM route: high/max only.
+		return HIGH_MAX_REASONING_EFFORTS;
 	}
 	return isOpenAICompatReasoningApi(spec.api) &&
 		(isMinimaxM2FamilyModelId(spec.id) ||
@@ -351,6 +369,27 @@ function getModelDefinedEfforts<TApi extends Api>(
 		: undefined;
 }
 
+/**
+ * Wire-exact effort ladders for Anthropic adaptive models (4.6+). Model-defined
+ * so stale cached surfaces normalize on every build: Messages-API models with
+ * the real xhigh tier (4.7+) expose the full five-tier `low..max` scale;
+ * Opus/Sonnet 4.6 and every Bedrock adaptive model stay on the four-tier
+ * `low/medium/high/max` scale.
+ */
+function getAnthropicAdaptiveEfforts<TApi extends Api>(spec: ModelSpec<TApi>): readonly Effort[] | undefined {
+	const parsed = parseAnthropicModel(bareModelId(spec.id));
+	if (!parsed || !isAnthropicAdaptiveGenAtLeast(parsed, "4.6")) return undefined;
+	if (spec.api === "anthropic-messages" || spec.api === "bedrock-converse-stream") {
+		return anthropicModelHasRealXHighEffort(spec, parsed)
+			? FIVE_TIER_EFFORTS_LOW_TO_MAX
+			: FOUR_TIER_EFFORTS_LOW_TO_MAX;
+	}
+	if (isOpenRouterAnthropicAdaptiveReasoningModel(parsed, spec)) {
+		return isAnthropicAdaptiveGenAtLeast(parsed, "4.7") ? FIVE_TIER_EFFORTS_LOW_TO_MAX : FOUR_TIER_EFFORTS_LOW_TO_MAX;
+	}
+	return undefined;
+}
+
 function isOllamaCloudGlm52ReasoningEffortModel<TApi extends Api>(spec: ModelSpec<TApi>): boolean {
 	return spec.api === "ollama-chat" && spec.provider === "ollama-cloud" && isGlm52ReasoningEffortModelId(spec.id);
 }
@@ -395,62 +434,31 @@ function isZaiThinkingFormat(compat: CompatOf<Api>): boolean {
 function inferDetectedEffortMap<TApi extends Api>(
 	spec: ModelSpec<TApi>,
 	compat: CompatOf<TApi>,
-	parsedModel: ParsedModel,
 	mode: ThinkingConfig["mode"],
 ): EffortMap | undefined {
 	if (mode === "anthropic-adaptive") {
 		if (isMinimaxReasoningModelOnAnthropicEndpoint(spec)) {
 			return MINIMAX_ANTHROPIC_ADAPTIVE_EFFORT_MAP;
 		}
-		return anthropicModelHasRealXHighEffort(spec, parsedModel)
-			? SHIFTED_FIVE_TIER_EFFORT_MAP
-			: ANTHROPIC_ADAPTIVE_EFFORT_MAP_4_TIER;
-	}
-	// GLM-5.2 coding SKUs accept `reasoning_effort`, but the effort dialect is
-	// host-specific (verified against live endpoints):
-	//   - Z.ai/Zhipu ("zai" dialect): the model exposes only none/high/max, so
-	//     `xhigh` 400s — collapse minimal->none, low/medium/high->high, xhigh->max.
-	//   - OpenRouter: `max` 400s and `xhigh` IS its max tier, so it passes `xhigh`
-	//     through literally (no map; the tier is exposed via getModelDefinedEfforts).
-	//   - Umans and Ollama Cloud expose only high/max on their GLM-5.2 routes.
-	//   - Other openai-compat hosts (Fireworks, resellers) keep their distinct
-	//     lower tiers and host quirks (e.g. Fireworks rejects `minimal`, so
-	//     `minimal->none` stays) and only remap the top `xhigh` UI tier onto the
-	//     genuine `max` budget. Filtered to supported efforts later.
-	const isGlm52 = isGlm52ReasoningEffortModelId(spec.id);
-	if (isGlm52 && isZaiThinkingFormat(compat)) {
-		return ZAI_GLM_52_REASONING_EFFORT_MAP;
-	}
-	if (isUmansGlm52ReasoningEffortModel(spec) || isOllamaCloudGlm52ReasoningEffortModel(spec)) {
-		return GLM_52_XHIGH_MAX_EFFORT_MAP;
-	}
-	if (isSakanaFuguReasoningModel(spec)) {
-		return FUGU_REASONING_EFFORT_MAP;
-	}
-	if (isGpt56PlusWireEffortModel(spec)) {
-		return SHIFTED_FIVE_TIER_EFFORT_MAP;
+		// Adaptive effort ladders are wire-exact (see
+		// getAnthropicAdaptiveEfforts) — no mapping needed.
+		return undefined;
 	}
 	if (!isOpenAICompatReasoningApi(spec.api)) {
 		return undefined;
 	}
-	let map: EffortMap | undefined;
 	if (spec.provider === "groq" && spec.id === "qwen/qwen3-32b") {
-		map = GROQ_QWEN3_32B_REASONING_EFFORT_MAP;
-	} else if (isDeepseekReasoningModel(spec)) {
-		map = DEEPSEEK_REASONING_EFFORT_MAP;
-	} else if (isOpenAICompatMimoReasoningEffortModel(spec, compat)) {
-		map = MIMO_REASONING_EFFORT_MAP;
-	} else if (modelMatchesHost(spec, "openrouter")) {
-		map = getOpenRouterAnthropicReasoningEffortMap(spec.id);
-	} else if (modelMatchesHost(spec, "fireworks")) {
-		map = FIREWORKS_REASONING_EFFORT_MAP;
+		return GROQ_QWEN3_32B_REASONING_EFFORT_MAP;
 	}
-	// Overlay GLM-5.2's top-tier `xhigh -> max` on the host base map, except on
-	// OpenRouter (xhigh IS its max tier; `max` 400s there).
-	if (isGlm52 && !isOpenRouterThinkingFormat(compat)) {
-		map = { ...map, ...GLM_52_XHIGH_MAX_EFFORT_MAP };
+	if (isOpenAICompatMimoReasoningEffortModel(spec, compat)) {
+		return MIMO_REASONING_EFFORT_MAP;
 	}
-	return map;
+	// Host quirk: Fireworks rejects `minimal` (maps to `none`) on ladders
+	// that genuinely include it. Filtered to supported efforts later.
+	if (modelMatchesHost(spec, "fireworks")) {
+		return FIREWORKS_REASONING_EFFORT_MAP;
+	}
+	return undefined;
 }
 
 function isSakanaFuguReasoningModel<TApi extends Api>(spec: ModelSpec<TApi>): boolean {
@@ -471,17 +479,6 @@ function isDeepseekReasoningModel<TApi extends Api>(spec: ModelSpec<TApi>): bool
 	);
 }
 
-function getOpenRouterAnthropicReasoningEffortMap(modelId: string): EffortMap | undefined {
-	const parsed = parseAnthropicModel(bareModelId(modelId));
-	if (!parsed) return undefined;
-	// Adaptive efforts on OpenRouter's completions front: Fable/Mythos, Sonnet 5+,
-	// and Opus 4.6+ only — older Sonnet versions stay on the plain effort vocabulary there.
-	if (!isAnthropicAdaptiveGenAtLeast(parsed, "4.6")) return undefined;
-
-	const hasRealXHigh = isAnthropicAdaptiveGenAtLeast(parsed, "4.7");
-	return hasRealXHigh ? SHIFTED_FIVE_TIER_EFFORT_MAP : ANTHROPIC_ADAPTIVE_EFFORT_MAP_4_TIER;
-}
-
 function inferSupportedEfforts<TApi extends Api>(
 	parsedModel: ParsedModel,
 	spec: ModelSpec<TApi>,
@@ -507,10 +504,9 @@ function inferOpenAISupportedEfforts(model: OpenAIModel): readonly Effort[] {
 	if (model.variant === "codex-mini" && semverEqual(model.version, "5.1")) {
 		return GPT_5_1_CODEX_MINI_EFFORTS;
 	}
-	// 5.6+ exposes the full five-tier ladder: the shifted wire map spans
-	// low..max, with user `minimal` reaching the native `low` tier.
+	// 5.6+ exposes the wire-exact five-tier ladder low..max.
 	if (semverGte(model.version, "5.6")) {
-		return DEFAULT_REASONING_EFFORTS_WITH_XHIGH;
+		return FIVE_TIER_EFFORTS_LOW_TO_MAX;
 	}
 	if (semverGte(model.version, "5.2")) {
 		return GPT_5_2_PLUS_EFFORTS;
@@ -554,16 +550,18 @@ function inferAnthropicSupportedEfforts<TApi extends Api>(
 	spec: ModelSpec<TApi>,
 	compat: CompatOf<TApi>,
 ): readonly Effort[] {
-	if (
-		(spec.api === "anthropic-messages" || spec.api === "bedrock-converse-stream") &&
-		semverGte(parsedModel.version, "4.6")
-	) {
-		return isAnthropicAdaptiveGenAtLeast(parsedModel, "4.6")
-			? DEFAULT_REASONING_EFFORTS_WITH_XHIGH
-			: DEFAULT_REASONING_EFFORTS;
+	// Ladders for adaptive-generation models (Opus 4.6+, Sonnet 5+,
+	// Fable/Mythos) are model-defined and already resolved by
+	// getAnthropicAdaptiveEfforts. Every other 4.6+ model on the Messages
+	// API (Sonnet/Haiku 4.6) still runs adaptive mode with the three-tier
+	// low/medium/high wire scale — no minimal, no max.
+	if (spec.api === "anthropic-messages" && semverGte(parsedModel.version, "4.6")) {
+		return LOW_MEDIUM_HIGH_REASONING_EFFORTS;
 	}
-	if (isOpenRouterAnthropicAdaptiveReasoningModel(parsedModel, spec)) {
-		return DEFAULT_REASONING_EFFORTS_WITH_XHIGH;
+	// Non-adaptive 4.6 models on Bedrock stay budget-mode, where minimal is
+	// a legitimate synthetic budget tier.
+	if (spec.api === "bedrock-converse-stream" && semverGte(parsedModel.version, "4.6")) {
+		return DEFAULT_REASONING_EFFORTS;
 	}
 	return inferFallbackEfforts(spec, compat);
 }
@@ -752,6 +750,7 @@ export function mapEffortToGoogleThinkingLevel(effort: Effort): "MINIMAL" | "LOW
 			return "MEDIUM";
 		case Effort.High:
 		case Effort.XHigh:
+		case Effort.Max:
 			return "HIGH";
 	}
 }
diff --git a/packages/catalog/src/models.json b/packages/catalog/src/models.json
index b19a10fd5..474e62114 100644
--- a/packages/catalog/src/models.json
+++ b/packages/catalog/src/models.json
@@ -1573,8 +1573,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 123000,
+			"maxTokens": 16000
 		},
 		"baidu/ernie-5-0-thinking-latest": {
 			"id": "baidu/ernie-5-0-thinking-latest",
@@ -2409,19 +2409,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-pro": {
@@ -2445,19 +2435,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-chat-v3-0324": {
@@ -2500,19 +2480,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1": {
@@ -2536,19 +2506,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"elevenlabs/eleven_multilingual_v2": {
@@ -7738,16 +7698,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"anthropic.claude-opus-4-7": {
@@ -7772,16 +7727,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -7807,16 +7757,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -7842,16 +7787,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -7906,16 +7846,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"au.anthropic.claude-opus-4-8": {
@@ -7940,16 +7875,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8033,16 +7963,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8330,16 +8255,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8481,16 +8401,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"eu.anthropic.claude-opus-4-7": {
@@ -8515,16 +8430,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8550,16 +8460,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8672,16 +8577,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8736,16 +8636,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8829,16 +8724,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"global.anthropic.claude-opus-4-7": {
@@ -8863,16 +8753,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -8898,16 +8783,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -9020,16 +8900,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -9124,16 +8999,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -9159,16 +9029,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -9252,16 +9117,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -10256,16 +10116,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -10407,16 +10262,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"us.anthropic.claude-opus-4-7": {
@@ -10441,16 +10291,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -10476,16 +10321,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -10598,16 +10438,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -11141,19 +10976,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -11239,19 +11067,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -11447,16 +11268,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"claude-opus-4-7": {
@@ -11481,19 +11297,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -11519,19 +11328,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -11667,14 +11469,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"claude-sonnet-5": {
@@ -11699,19 +11497,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		}
@@ -12679,19 +12470,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"moonshotai/Kimi-K2.5": {
@@ -12863,9 +12644,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"low",
-					"medium",
-					"high"
+					"high",
+					"max"
 				]
 			}
 		},
@@ -13293,19 +13073,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -13451,16 +13224,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4-7": {
@@ -13485,19 +13253,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -13523,19 +13284,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -13621,14 +13375,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"anthropic/claude-sonnet-5": {
@@ -13653,19 +13403,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -14296,19 +14039,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V4-Pro": {
@@ -14332,19 +14065,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"google/gemma-4-31B-it": {
@@ -16059,19 +15782,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-pro": {
@@ -16109,19 +15822,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		}
 	},
@@ -16328,19 +16031,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "claude-opus-4-7-low",
-					"low": "claude-opus-4-7-medium",
-					"medium": "claude-opus-4-7-high",
-					"high": "claude-opus-4-7-xhigh",
-					"xhigh": "claude-opus-4-7-max"
+					"low": "claude-opus-4-7-low",
+					"medium": "claude-opus-4-7-medium",
+					"high": "claude-opus-4-7-high",
+					"xhigh": "claude-opus-4-7-xhigh",
+					"max": "claude-opus-4-7-max"
 				}
 			},
 			"requestModelId": "claude-opus-4-7-low"
@@ -16368,19 +16071,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "claude-opus-4-7-low-fast",
-					"low": "claude-opus-4-7-medium-fast",
-					"medium": "claude-opus-4-7-high-fast",
-					"high": "claude-opus-4-7-xhigh-fast",
-					"xhigh": "claude-opus-4-7-max-fast"
+					"low": "claude-opus-4-7-low-fast",
+					"medium": "claude-opus-4-7-medium-fast",
+					"high": "claude-opus-4-7-high-fast",
+					"xhigh": "claude-opus-4-7-xhigh-fast",
+					"max": "claude-opus-4-7-max-fast"
 				}
 			},
 			"requestModelId": "claude-opus-4-7-low-fast"
@@ -16408,19 +16111,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "claude-opus-4-8-low",
-					"low": "claude-opus-4-8-medium",
-					"medium": "claude-opus-4-8-high",
-					"high": "claude-opus-4-8-xhigh",
-					"xhigh": "claude-opus-4-8-max"
+					"low": "claude-opus-4-8-low",
+					"medium": "claude-opus-4-8-medium",
+					"high": "claude-opus-4-8-high",
+					"xhigh": "claude-opus-4-8-xhigh",
+					"max": "claude-opus-4-8-max"
 				}
 			},
 			"requestModelId": "claude-opus-4-8-low"
@@ -16448,19 +16151,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "claude-opus-4-8-low-fast",
-					"low": "claude-opus-4-8-medium-fast",
-					"medium": "claude-opus-4-8-high-fast",
-					"high": "claude-opus-4-8-xhigh-fast",
-					"xhigh": "claude-opus-4-8-max-fast"
+					"low": "claude-opus-4-8-low-fast",
+					"medium": "claude-opus-4-8-medium-fast",
+					"high": "claude-opus-4-8-high-fast",
+					"xhigh": "claude-opus-4-8-xhigh-fast",
+					"max": "claude-opus-4-8-max-fast"
 				}
 			},
 			"requestModelId": "claude-opus-4-8-low-fast"
@@ -16917,7 +16620,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -16925,7 +16627,6 @@
 				],
 				"effortRouting": {
 					"off": "MODEL_GPT_5_2_NONE",
-					"minimal": "MODEL_GPT_5_2_LOW",
 					"low": "MODEL_GPT_5_2_LOW",
 					"medium": "MODEL_GPT_5_2_MEDIUM",
 					"high": "MODEL_GPT_5_2_HIGH",
@@ -16957,7 +16658,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -16965,7 +16665,6 @@
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "gpt-5-3-codex-low",
 					"low": "gpt-5-3-codex-low",
 					"medium": "gpt-5-3-codex-medium",
 					"high": "gpt-5-3-codex-high",
@@ -16997,7 +16696,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17005,7 +16703,6 @@
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "gpt-5-3-codex-low-priority",
 					"low": "gpt-5-3-codex-low-priority",
 					"medium": "gpt-5-3-codex-medium-priority",
 					"high": "gpt-5-3-codex-high-priority",
@@ -17037,7 +16734,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17045,7 +16741,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-4-none",
-					"minimal": "gpt-5-4-low",
 					"low": "gpt-5-4-low",
 					"medium": "gpt-5-4-medium",
 					"high": "gpt-5-4-high",
@@ -17077,7 +16772,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17085,7 +16779,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-4-none-priority",
-					"minimal": "gpt-5-4-low-priority",
 					"low": "gpt-5-4-low-priority",
 					"medium": "gpt-5-4-medium-priority",
 					"high": "gpt-5-4-high-priority",
@@ -17117,7 +16810,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17125,7 +16817,6 @@
 				],
 				"requiresEffort": true,
 				"effortRouting": {
-					"minimal": "gpt-5-4-mini-low",
 					"low": "gpt-5-4-mini-low",
 					"medium": "gpt-5-4-mini-medium",
 					"high": "gpt-5-4-mini-high",
@@ -17157,7 +16848,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17165,7 +16855,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-5-none",
-					"minimal": "gpt-5-5-low",
 					"low": "gpt-5-5-low",
 					"medium": "gpt-5-5-medium",
 					"high": "gpt-5-5-high",
@@ -17197,7 +16886,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17205,7 +16893,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-5-none-priority",
-					"minimal": "gpt-5-5-low-priority",
 					"low": "gpt-5-5-low-priority",
 					"medium": "gpt-5-5-medium-priority",
 					"high": "gpt-5-5-high-priority",
@@ -17237,19 +16924,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"effortRouting": {
 					"off": "gpt-5-6-luna-none",
-					"minimal": "gpt-5-6-luna-low",
-					"low": "gpt-5-6-luna-medium",
-					"medium": "gpt-5-6-luna-high",
-					"high": "gpt-5-6-luna-xhigh",
-					"xhigh": "gpt-5-6-luna-max"
+					"low": "gpt-5-6-luna-low",
+					"medium": "gpt-5-6-luna-medium",
+					"high": "gpt-5-6-luna-high",
+					"xhigh": "gpt-5-6-luna-xhigh",
+					"max": "gpt-5-6-luna-max"
 				}
 			},
 			"requestModelId": "gpt-5-6-luna-none"
@@ -17277,7 +16964,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17285,7 +16971,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-6-luna-none-priority",
-					"minimal": "gpt-5-6-luna-low-priority",
 					"low": "gpt-5-6-luna-low-priority",
 					"medium": "gpt-5-6-luna-medium-priority",
 					"high": "gpt-5-6-luna-high-priority",
@@ -17317,19 +17002,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"effortRouting": {
 					"off": "gpt-5-6-sol-none",
-					"minimal": "gpt-5-6-sol-low",
-					"low": "gpt-5-6-sol-medium",
-					"medium": "gpt-5-6-sol-high",
-					"high": "gpt-5-6-sol-xhigh",
-					"xhigh": "gpt-5-6-sol-max"
+					"low": "gpt-5-6-sol-low",
+					"medium": "gpt-5-6-sol-medium",
+					"high": "gpt-5-6-sol-high",
+					"xhigh": "gpt-5-6-sol-xhigh",
+					"max": "gpt-5-6-sol-max"
 				}
 			},
 			"requestModelId": "gpt-5-6-sol-none"
@@ -17357,7 +17042,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17365,7 +17049,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-6-sol-none-priority",
-					"minimal": "gpt-5-6-sol-low-priority",
 					"low": "gpt-5-6-sol-low-priority",
 					"medium": "gpt-5-6-sol-medium-priority",
 					"high": "gpt-5-6-sol-high-priority",
@@ -17397,19 +17080,19 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
 				"effortRouting": {
 					"off": "gpt-5-6-terra-none",
-					"minimal": "gpt-5-6-terra-low",
-					"low": "gpt-5-6-terra-medium",
-					"medium": "gpt-5-6-terra-high",
-					"high": "gpt-5-6-terra-xhigh",
-					"xhigh": "gpt-5-6-terra-max"
+					"low": "gpt-5-6-terra-low",
+					"medium": "gpt-5-6-terra-medium",
+					"high": "gpt-5-6-terra-high",
+					"xhigh": "gpt-5-6-terra-xhigh",
+					"max": "gpt-5-6-terra-max"
 				}
 			},
 			"requestModelId": "gpt-5-6-terra-none"
@@ -17437,7 +17120,6 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
@@ -17445,7 +17127,6 @@
 				],
 				"effortRouting": {
 					"off": "gpt-5-6-terra-none-priority",
-					"minimal": "gpt-5-6-terra-low-priority",
 					"low": "gpt-5-6-terra-low-priority",
 					"medium": "gpt-5-6-terra-medium-priority",
 					"high": "gpt-5-6-terra-high-priority",
@@ -17812,15 +17493,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "none"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		}
 	},
@@ -17846,19 +17524,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			},
 			"compat": {
 				"supportsToolChoice": false,
@@ -17886,19 +17554,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			},
 			"compat": {
 				"supportsToolChoice": false,
@@ -18059,11 +17717,10 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
 				"effortMap": {
-					"minimal": "none",
-					"xhigh": "max"
+					"minimal": "none"
 				}
 			}
 		},
@@ -18563,19 +18220,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -18675,16 +18325,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"claude-opus-4.7": {
@@ -18713,19 +18358,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -18755,19 +18393,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -18865,14 +18496,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"claude-sonnet-5": {
@@ -18901,19 +18528,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -21962,16 +21582,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"claude-opus-4-7@default": {
@@ -21996,19 +21611,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -22034,19 +21642,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -22102,14 +21703,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"claude-sonnet-5@default": {
@@ -22134,19 +21731,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -22171,19 +21761,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/deepseek-v3.2-maas": {
@@ -22207,19 +21787,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"gemini-2.5-flash": {
@@ -22746,19 +22316,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"gemma2-9b-it": {
@@ -23177,19 +22737,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-R1-0528": {
@@ -23213,19 +22763,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V3.1": {
@@ -23268,19 +22808,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V4-Flash": {
@@ -23304,19 +22834,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V4-Pro": {
@@ -23340,19 +22860,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"google/gemma-4-26B-A4B-it": {
@@ -26130,8 +25640,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 123000,
+			"maxTokens": 16000
 		},
 		"baidu/qianfan-ocr-fast": {
 			"id": "baidu/qianfan-ocr-fast",
@@ -26540,19 +26050,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1": {
@@ -26576,19 +26076,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1-0528": {
@@ -26612,19 +26102,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1-distill-llama-70b": {
@@ -26686,19 +26166,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.1-terminus:exacto": {
@@ -26741,19 +26211,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2-exp": {
@@ -26777,19 +26237,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2-speciale": {
@@ -26832,19 +26282,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash:discounted": {
@@ -26906,19 +26346,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro:discounted": {
@@ -28554,8 +27984,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 32768,
+			"maxTokens": 32000
 		},
 		"meta-llama/llama-3.3-70b-instruct": {
 			"id": "meta-llama/llama-3.3-70b-instruct",
@@ -28746,8 +28176,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 65535,
+			"maxTokens": 8000
 		},
 		"minimax/minimax-01": {
 			"id": "minimax/minimax-01",
@@ -34446,7 +33876,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": null
+			"maxTokens": 262144
 		},
 		"tencent/hy3-preview": {
 			"id": "tencent/hy3-preview",
@@ -34513,7 +33943,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": null
+			"maxTokens": 262144
 		},
 		"thedrummer/cydonia-24b-v4.1": {
 			"id": "thedrummer/cydonia-24b-v4.1",
@@ -35579,11 +35009,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"z-ai/glm-5v-turbo": {
@@ -40546,19 +39973,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V3.1": {
@@ -40639,19 +40056,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				},
 				"effortRouting": {
 					"off": "deepseek-ai/deepseek-v3.2-exp",
 					"minimal": "deepseek-ai/deepseek-v3.2-exp-thinking",
@@ -40840,19 +40247,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-prover-v2-671b": {
@@ -40933,19 +40330,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash": {
@@ -40969,19 +40356,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash:thinking": {
@@ -41005,19 +40382,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro": {
@@ -41041,19 +40408,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro-cheaper": {
@@ -41077,19 +40434,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro-cheaper:thinking": {
@@ -41113,19 +40460,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro:thinking": {
@@ -41149,19 +40486,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"dmind/dmind-1": {
@@ -45719,8 +45046,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 32768,
+			"maxTokens": 32000
 		},
 		"meta-llama/llama-3.3-70b-instruct": {
 			"id": "meta-llama/llama-3.3-70b-instruct",
@@ -45835,8 +45162,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 65535,
+			"maxTokens": 8000
 		},
 		"MiniMax-M1": {
 			"id": "MiniMax-M1",
@@ -46134,8 +45461,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 1000000,
+			"maxTokens": 40000
 		},
 		"miromind-ai/mirothinker-v1.5-235b": {
 			"id": "miromind-ai/mirothinker-v1.5-235b",
@@ -48640,19 +47967,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-luna-pro": {
@@ -48696,19 +48016,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-sol-pro": {
@@ -48752,19 +48065,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-terra-pro": {
@@ -51265,8 +50571,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 8192,
+			"maxTokens": 32000
 		},
 		"Sao10K/L3.1-70B-Euryale-v2.2": {
 			"id": "Sao10K/L3.1-70B-Euryale-v2.2",
@@ -51994,19 +51300,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"TEE/deepseek-v4-pro:thinking": {
@@ -52030,19 +51326,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"TEE/gemma-3-27b-it": {
@@ -52317,11 +51603,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"TEE/gpt-oss-120b": {
@@ -52768,7 +52051,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": null
+			"maxTokens": 262144
 		},
 		"tencent/hy3-preview": {
 			"id": "tencent/hy3-preview",
@@ -53024,8 +52307,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 32000,
+			"maxTokens": 32000
 		},
 		"THUDM/GLM-4-9B-0414": {
 			"id": "THUDM/GLM-4-9B-0414",
@@ -54774,11 +54057,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"zai-org/glm-latest": {
@@ -55017,19 +54297,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1-0528": {
@@ -55054,19 +54324,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1-0528-qwen3-8b": {
@@ -55111,19 +54371,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1-turbo": {
@@ -55148,19 +54398,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1/community": {
@@ -55185,19 +54425,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3-0324": {
@@ -55262,19 +54492,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.1-terminus": {
@@ -55299,19 +54519,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2": {
@@ -55336,19 +54546,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2-exp": {
@@ -55373,19 +54573,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3/community": {
@@ -55430,19 +54620,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro": {
@@ -55467,19 +54647,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"dev/glm46": {
@@ -57615,11 +56785,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"zai-org/glm-5v-turbo": {
@@ -57885,19 +57052,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/deepseek-v3.1": {
@@ -57921,19 +57078,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/deepseek-v3.1-terminus": {
@@ -57957,19 +57104,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/deepseek-v3.2": {
@@ -57993,19 +57130,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/deepseek-v4-flash": {
@@ -58029,19 +57156,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/deepseek-v4-pro": {
@@ -58065,19 +57182,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"google/codegemma-1.1-7b": {
@@ -58568,8 +57675,8 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
-			"contextWindow": null,
-			"maxTokens": null
+			"contextWindow": 32768,
+			"maxTokens": 32000
 		},
 		"meta/llama-3.2-90b-vision-instruct": {
 			"id": "meta/llama-3.2-90b-vision-instruct",
@@ -61082,11 +60189,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"z-ai/glm4.7": {
@@ -61619,11 +60723,8 @@
 				"mode": "effort",
 				"efforts": [
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"gpt-oss:120b": {
@@ -63271,19 +62372,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-luna": {
@@ -63309,19 +62403,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-luna-pro": {
@@ -63343,26 +62430,19 @@
 			},
 			"contextWindow": 1050000,
 			"maxTokens": 128000,
+			"requestModelId": "gpt-5.6-luna",
+			"reasoningMode": "pro",
 			"applyPatchToolType": "freeform",
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
-			},
-			"requestModelId": "gpt-5.6-luna",
-			"reasoningMode": "pro"
+					"xhigh",
+					"max"
+				]
+			}
 		},
 		"gpt-5.6-sol": {
 			"id": "gpt-5.6-sol",
@@ -63387,19 +62467,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-sol-pro": {
@@ -63421,26 +62494,19 @@
 			},
 			"contextWindow": 1050000,
 			"maxTokens": 128000,
+			"requestModelId": "gpt-5.6-sol",
+			"reasoningMode": "pro",
 			"applyPatchToolType": "freeform",
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
-			},
-			"requestModelId": "gpt-5.6-sol",
-			"reasoningMode": "pro"
+					"xhigh",
+					"max"
+				]
+			}
 		},
 		"gpt-5.6-terra": {
 			"id": "gpt-5.6-terra",
@@ -63465,19 +62531,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-terra-pro": {
@@ -63499,26 +62558,19 @@
 			},
 			"contextWindow": 1050000,
 			"maxTokens": 128000,
+			"requestModelId": "gpt-5.6-terra",
+			"reasoningMode": "pro",
 			"applyPatchToolType": "freeform",
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
-			},
-			"requestModelId": "gpt-5.6-terra",
-			"reasoningMode": "pro"
+					"xhigh",
+					"max"
+				]
+			}
 		},
 		"o1": {
 			"id": "o1",
@@ -64330,19 +63382,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-luna-pro": {
@@ -64372,26 +63417,19 @@
 			"preferWebsockets": true,
 			"useResponsesLite": true,
 			"priority": 3,
+			"requestModelId": "gpt-5.6-luna",
+			"reasoningMode": "pro",
 			"applyPatchToolType": "freeform",
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
-			},
-			"requestModelId": "gpt-5.6-luna",
-			"reasoningMode": "pro"
+					"xhigh",
+					"max"
+				]
+			}
 		},
 		"gpt-5.6-sol": {
 			"id": "gpt-5.6-sol",
@@ -64424,19 +63462,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-sol-pro": {
@@ -64466,26 +63497,19 @@
 			"preferWebsockets": true,
 			"useResponsesLite": true,
 			"priority": 1,
+			"requestModelId": "gpt-5.6-sol",
+			"reasoningMode": "pro",
 			"applyPatchToolType": "freeform",
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
-			},
-			"requestModelId": "gpt-5.6-sol",
-			"reasoningMode": "pro"
+					"xhigh",
+					"max"
+				]
+			}
 		},
 		"gpt-5.6-terra": {
 			"id": "gpt-5.6-terra",
@@ -64518,19 +63542,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"gpt-5.6-terra-pro": {
@@ -64560,26 +63577,19 @@
 			"preferWebsockets": true,
 			"useResponsesLite": true,
 			"priority": 2,
+			"requestModelId": "gpt-5.6-terra",
+			"reasoningMode": "pro",
 			"applyPatchToolType": "freeform",
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
-			},
-			"requestModelId": "gpt-5.6-terra",
-			"reasoningMode": "pro"
+					"xhigh",
+					"max"
+				]
+			}
 		}
 	},
 	"opencode": {
@@ -64757,19 +63767,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-pro": {
@@ -64799,19 +63799,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"glm-5": {
@@ -64897,11 +63887,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"kimi-k2.5": {
@@ -65350,19 +64337,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"claude-3-5-haiku": {
@@ -65407,19 +64384,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -65535,16 +64505,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"claude-opus-4-7": {
@@ -65569,19 +64534,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -65607,19 +64565,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -65705,14 +64656,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"claude-sonnet-5": {
@@ -65737,19 +64684,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -65774,19 +64714,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-flash-free": {
@@ -65810,19 +64740,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-pro": {
@@ -65846,19 +64766,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"gemini-3-flash": {
@@ -66118,11 +65028,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"gpt-5": {
@@ -68094,19 +67001,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-haiku-4.5": {
@@ -68247,16 +67147,11 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.6-fast": {
@@ -68281,16 +67176,11 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.7": {
@@ -68315,19 +67205,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.7-fast": {
@@ -68352,19 +67235,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.8": {
@@ -68389,19 +67265,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.8-fast": {
@@ -68426,19 +67295,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-sonnet-4": {
@@ -68550,19 +67412,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"arcee-ai/trinity-large-preview": {
@@ -69091,17 +67946,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-r1": {
@@ -69125,17 +67971,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-r1-0528": {
@@ -69159,17 +67996,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v3.1-terminus": {
@@ -69193,17 +68021,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v3.1-terminus:exacto": {
@@ -69227,17 +68046,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2": {
@@ -69261,17 +68071,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2-exp": {
@@ -69295,17 +68096,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash": {
@@ -69329,17 +68121,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash:free": {
@@ -69363,17 +68146,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro": {
@@ -69397,17 +68171,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"essentialai/rnj-1-instruct": {
@@ -73011,19 +71776,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-luna-pro": {
@@ -73048,19 +71806,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-sol": {
@@ -73085,19 +71836,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-sol-pro": {
@@ -73122,19 +71866,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-terra": {
@@ -73159,19 +71896,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-terra-pro": {
@@ -73196,19 +71926,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-audio": {
@@ -75714,7 +74437,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": null,
+			"maxTokens": 262144,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -75868,17 +74591,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high"
-				}
+				]
 			}
 		},
 		"tngtech/tng-r1t-chimera": {
@@ -76815,13 +75529,13 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.84,
-				"output": 2.64,
-				"cacheRead": 0.156,
+				"input": 0.77,
+				"output": 2.42,
+				"cacheRead": 0.143,
 				"cacheWrite": 0
 			},
 			"contextWindow": 1048576,
-			"maxTokens": 128000,
+			"maxTokens": 131072,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -76876,19 +75590,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		}
 	},
@@ -76956,11 +75660,8 @@
 				"mode": "effort",
 				"efforts": [
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			},
 			"compat": {
 				"includeEncryptedReasoning": false,
@@ -76989,11 +75690,8 @@
 				"mode": "effort",
 				"efforts": [
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			},
 			"compat": {
 				"includeEncryptedReasoning": false,
@@ -77022,11 +75720,8 @@
 				"mode": "effort",
 				"efforts": [
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			},
 			"compat": {
 				"includeEncryptedReasoning": false,
@@ -77337,19 +76032,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V3": {
@@ -77392,19 +76077,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-ai/DeepSeek-V3.1": {
@@ -77447,19 +76122,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"essentialai/Rnj-1-Instruct": {
@@ -78224,11 +76889,8 @@
 				"mode": "anthropic-budget-effort",
 				"efforts": [
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			},
 			"input": [
 				"text"
@@ -78863,19 +77525,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-flash": {
@@ -78899,19 +77551,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-pro": {
@@ -78935,19 +77577,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"e2ee-deepseek-v4-flash": {
@@ -82488,19 +81120,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -82646,16 +81271,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.7": {
@@ -82680,19 +81300,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -82718,19 +81331,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -82816,14 +81422,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"anthropic/claude-sonnet-5": {
@@ -82848,19 +81450,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -85843,11 +84438,11 @@
 			"thinking": {
 				"mode": "budget",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				]
 			}
 		},
@@ -85873,11 +84468,11 @@
 			"thinking": {
 				"mode": "budget",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				]
 			}
 		},
@@ -85903,11 +84498,11 @@
 			"thinking": {
 				"mode": "budget",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				]
 			}
 		},
@@ -87470,19 +86065,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek-v4-pro": {
@@ -87506,19 +86091,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"GLM-5.1": {
@@ -88636,14 +87211,6 @@
 			},
 			"contextWindow": 2000000,
 			"maxTokens": 2000000,
-			"compat": {
-				"reasoningEffortMap": {
-					"minimal": "low"
-				},
-				"includeEncryptedReasoning": false,
-				"filterReasoningHistory": true,
-				"omitReasoningEffort": false
-			},
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -88656,6 +87223,14 @@
 				"effortMap": {
 					"minimal": "low"
 				}
+			},
+			"compat": {
+				"reasoningEffortMap": {
+					"minimal": "low"
+				},
+				"includeEncryptedReasoning": false,
+				"filterReasoningHistory": true,
+				"omitReasoningEffort": false
 			}
 		},
 		"grok-4.3": {
@@ -88677,14 +87252,6 @@
 			},
 			"contextWindow": 1000000,
 			"maxTokens": 1000000,
-			"compat": {
-				"reasoningEffortMap": {
-					"minimal": "low"
-				},
-				"includeEncryptedReasoning": false,
-				"filterReasoningHistory": true,
-				"omitReasoningEffort": false
-			},
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -88697,6 +87264,14 @@
 				"effortMap": {
 					"minimal": "low"
 				}
+			},
+			"compat": {
+				"reasoningEffortMap": {
+					"minimal": "low"
+				},
+				"includeEncryptedReasoning": false,
+				"filterReasoningHistory": true,
+				"omitReasoningEffort": false
 			}
 		},
 		"grok-4.5": {
@@ -88737,20 +87312,7 @@
 				},
 				"includeEncryptedReasoning": false,
 				"filterReasoningHistory": true,
-				"omitReasoningEffort": false
-			},
-			"thinking": {
-				"mode": "effort",
-				"efforts": [
-					"minimal",
-					"low",
-					"medium",
-					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				"omitReasoningEffort": true
 			}
 		},
 		"grok-build": {
@@ -89905,19 +88467,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -89943,19 +88498,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -90091,16 +88639,11 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"anthropic/claude-opus-4.7": {
@@ -90125,19 +88668,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -90163,19 +88699,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -90261,14 +88790,10 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high"
-				],
-				"effortMap": {
-					"minimal": "low"
-				}
+				]
 			}
 		},
 		"anthropic/claude-sonnet-5": {
@@ -90293,19 +88818,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -90331,19 +88849,12 @@
 			"thinking": {
 				"mode": "anthropic-adaptive",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"xhigh",
+					"max"
 				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				},
 				"supportsDisplay": true
 			}
 		},
@@ -90776,19 +89287,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-r1-0528": {
@@ -90812,19 +89313,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-reasoner": {
@@ -90848,19 +89339,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
+					"max"
 				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				},
 				"requiresEffort": true
 			}
 		},
@@ -90885,19 +89366,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v3.2-exp": {
@@ -90921,19 +89392,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash": {
@@ -90957,19 +89418,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-flash-free": {
@@ -90993,19 +89444,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro": {
@@ -91029,19 +89470,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"deepseek/deepseek-v4-pro-free": {
@@ -91065,19 +89496,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "high",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"google/gemini-2.0-flash": {
@@ -93131,19 +91552,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-sol": {
@@ -93168,19 +91582,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-5.6-terra": {
@@ -93205,19 +91612,12 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "low",
-					"low": "medium",
-					"medium": "high",
-					"high": "xhigh",
-					"xhigh": "max"
-				}
+					"xhigh",
+					"max"
+				]
 			}
 		},
 		"openai/gpt-image-1.5": {
@@ -94060,7 +92460,7 @@
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
-			"maxTokens": null,
+			"maxTokens": 262144,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -95169,11 +93569,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"z-ai/glm-5.2-free": {
@@ -95201,11 +93598,8 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"z-ai/glm-5v-turbo": {
@@ -95516,19 +93910,9 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
-				],
-				"effortMap": {
-					"minimal": "none",
-					"low": "high",
-					"medium": "high",
-					"high": "high",
-					"xhigh": "max"
-				}
+					"max"
+				]
 			}
 		},
 		"glm-5v-turbo": {
@@ -95566,4 +93950,4 @@
 			}
 		}
 	}
-}
+}
\ No newline at end of file
diff --git a/packages/catalog/src/provider-models/ollama.ts b/packages/catalog/src/provider-models/ollama.ts
index 3708a8f0f..b9248903e 100644
--- a/packages/catalog/src/provider-models/ollama.ts
+++ b/packages/catalog/src/provider-models/ollama.ts
@@ -25,8 +25,7 @@ type OllamaShowResponse = {
 const OLLAMA_RETRY_DELAYS_MS = [2_000, 5_000, 10_000];
 const OLLAMA_CLOUD_GLM_52_THINKING: ThinkingConfig = {
 	mode: "effort",
-	efforts: [Effort.High, Effort.XHigh],
-	effortMap: { [Effort.XHigh]: "max" },
+	efforts: [Effort.High, Effort.Max],
 };
 
 function trimTrailingSlash(value: string): string {
diff --git a/packages/catalog/src/provider-models/openai-compat.ts b/packages/catalog/src/provider-models/openai-compat.ts
index 0b785b6ca..421a6a404 100644
--- a/packages/catalog/src/provider-models/openai-compat.ts
+++ b/packages/catalog/src/provider-models/openai-compat.ts
@@ -622,9 +622,8 @@ const UMANS_REASONING_EFFORT_BY_LEVEL: Record<string, Effort> = {
 	medium: Effort.Medium,
 	high: Effort.High,
 	xhigh: Effort.XHigh,
-	max: Effort.XHigh,
+	max: Effort.Max,
 };
-const UMANS_MAX_REASONING_EFFORT_MAP = { [Effort.XHigh]: "max" } as const;
 const UMANS_DEFAULT_REASONING_EFFORTS = [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh] as const;
 const UMANS_VIA_HANDOFF_MODEL_IDS = ["umans-glm-5.1", "umans-glm-5.2"] as const;
 
@@ -689,9 +688,6 @@ function mapUmansThinkingConfig(value: unknown): ThinkingConfig | undefined {
 		mode: umansHasMaxReasoningLevel(value) ? "anthropic-budget-effort" : "budget",
 		efforts,
 	};
-	if (thinking.mode === "anthropic-budget-effort") {
-		thinking.effortMap = UMANS_MAX_REASONING_EFFORT_MAP;
-	}
 	if (isRecord(value)) {
 		if (value.can_disable === false) {
 			thinking.requiresEffort = true;
@@ -2802,18 +2798,13 @@ export function basetenModelManagerOptions(
 
 						const baseModel = mapWithBundledReference(entry, defaults, reference);
 
+						// Baseten's reasoning router accepts only the high/max
+						// effort tiers for its GLM-5.2 and gpt-oss routes.
 						const isEffortReasoning = defaults.id === "openai/gpt-oss-120b" || defaults.id === "zai-org/GLM-5.2";
 						const thinking = isEffortReasoning
 							? {
 									mode: "effort" as const,
-									efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-									effortMap: {
-										minimal: "high",
-										low: "high",
-										medium: "high",
-										high: "high",
-										xhigh: "max",
-									},
+									efforts: [Effort.High, Effort.Max],
 								}
 							: undefined;
 
@@ -2936,8 +2927,7 @@ const SAKANA_FUGU_ULTRA_COST = { input: 5, output: 30, cacheRead: 0.5, cacheWrit
 const SAKANA_FUGU_ULTRA_CONTEXT_WINDOW = 1_000_000;
 const SAKANA_FUGU_THINKING: ThinkingConfig = {
 	mode: "effort",
-	efforts: [Effort.High, Effort.XHigh],
-	effortMap: { [Effort.XHigh]: "max" },
+	efforts: [Effort.High, Effort.Max],
 };
 const SAKANA_RESPONSES_COMPAT: ModelSpec<"openai-responses">["compat"] = {
 	includeEncryptedReasoning: false,
diff --git a/packages/catalog/src/variant-collapse.ts b/packages/catalog/src/variant-collapse.ts
index 46d1f9d52..770d7610d 100644
--- a/packages/catalog/src/variant-collapse.ts
+++ b/packages/catalog/src/variant-collapse.ts
@@ -111,15 +111,12 @@ function thinkingPair(baseId: string, name: string): EffortVariantFamily {
 	};
 }
 
-type DevinTierRoutes = Partial<Record<"off" | "minimal" | "low" | "medium" | "high" | "xhigh", string>>;
+type DevinTierRoutes = Partial<Record<"off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max", string>>;
 
-const DEVIN_FIVE_TIER_EFFORTS: readonly Effort[] = [
-	Effort.Minimal,
-	Effort.Low,
-	Effort.Medium,
-	Effort.High,
-	Effort.XHigh,
-];
+/** Devin families with a `-max` sibling: five wire tiers, `low` floor. */
+const DEVIN_FIVE_TIER_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max];
+/** Devin families topping out at `-xhigh` (pre-5.6 GPT, 5.6 fast lanes). */
+const DEVIN_FOUR_TIER_EFFORTS: readonly Effort[] = [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh];
 
 function devinTierFamily(
 	id: string,
@@ -132,11 +129,7 @@ function devinTierFamily(
 	for (const effort of efforts) {
 		switch (effort) {
 			case Effort.Minimal:
-				if (routes.minimal) {
-					routing[effort] = routes.minimal;
-				} else if (routes.low) {
-					routing[effort] = routes.low;
-				}
+				if (routes.minimal) routing[effort] = routes.minimal;
 				break;
 			case Effort.Low:
 				if (routes.low) routing[effort] = routes.low;
@@ -150,11 +143,20 @@ function devinTierFamily(
 			case Effort.XHigh:
 				if (routes.xhigh) routing[effort] = routes.xhigh;
 				break;
+			case Effort.Max:
+				if (routes.max) routing[effort] = routes.max;
+				break;
 		}
 	}
-	const members = [routes.off, routes.minimal, routes.low, routes.medium, routes.high, routes.xhigh].filter(
-		(member, index, items): member is string => typeof member === "string" && items.indexOf(member) === index,
-	);
+	const members = [
+		routes.off,
+		routes.minimal,
+		routes.low,
+		routes.medium,
+		routes.high,
+		routes.xhigh,
+		routes.max,
+	].filter((member, index, items): member is string => typeof member === "string" && items.indexOf(member) === index);
 	return {
 		id,
 		name,
@@ -169,11 +171,9 @@ function devinTierFamily(
 }
 
 /**
- * GPT-5.6 (Luna/Sol/Terra) adds a genuine `max` tier above `xhigh`, so the
- * standard family shifts every user effort up one notch (`minimal` → `-low`
- * … `xhigh` → `-max`), mirroring the Opus 4.7+ five-tier mapping. Devin
- * serves no `-max-priority` sibling, so the fast family keeps the direct
- * `low..xhigh` `-priority` scale.
+ * GPT-5.6 (Luna/Sol/Terra) serves per-tier siblings for the full five-tier
+ * `low..max` wire scale; user efforts route 1:1 onto them. Devin serves no
+ * `-max-priority` sibling, so the fast family tops out at `xhigh`.
  */
 function devinGpt56Families(variant: "luna" | "sol" | "terra", name: string): readonly EffortVariantFamily[] {
 	const base = `gpt-5-6-${variant}`;
@@ -183,11 +183,11 @@ function devinGpt56Families(variant: "luna" | "sol" | "terra", name: string): re
 			name,
 			{
 				off: `${base}-none`,
-				minimal: `${base}-low`,
-				low: `${base}-medium`,
-				medium: `${base}-high`,
-				high: `${base}-xhigh`,
-				xhigh: `${base}-max`,
+				low: `${base}-low`,
+				medium: `${base}-medium`,
+				high: `${base}-high`,
+				xhigh: `${base}-xhigh`,
+				max: `${base}-max`,
 			},
 			DEVIN_FIVE_TIER_EFFORTS,
 		),
@@ -201,7 +201,7 @@ function devinGpt56Families(variant: "luna" | "sol" | "terra", name: string): re
 				high: `${base}-high-priority`,
 				xhigh: `${base}-xhigh-priority`,
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 	];
 }
@@ -357,98 +357,54 @@ export const GEMINI_CLI_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 };
 export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 	families: [
-		{
-			id: "claude-opus-4-7",
-			name: "Claude Opus 4.7",
-			members: [
-				"claude-opus-4-7-low",
-				"claude-opus-4-7-medium",
-				"claude-opus-4-7-high",
-				"claude-opus-4-7-xhigh",
-				"claude-opus-4-7-max",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-7-low",
-				[Effort.Low]: "claude-opus-4-7-medium",
-				[Effort.Medium]: "claude-opus-4-7-high",
-				[Effort.High]: "claude-opus-4-7-xhigh",
-				[Effort.XHigh]: "claude-opus-4-7-max",
+		devinTierFamily(
+			"claude-opus-4-7",
+			"Claude Opus 4.7",
+			{
+				low: "claude-opus-4-7-low",
+				medium: "claude-opus-4-7-medium",
+				high: "claude-opus-4-7-high",
+				xhigh: "claude-opus-4-7-xhigh",
+				max: "claude-opus-4-7-max",
 			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
+		devinTierFamily(
+			"claude-opus-4-7-fast",
+			"Claude Opus 4.7 Fast",
+			{
+				low: "claude-opus-4-7-low-fast",
+				medium: "claude-opus-4-7-medium-fast",
+				high: "claude-opus-4-7-high-fast",
+				xhigh: "claude-opus-4-7-xhigh-fast",
+				max: "claude-opus-4-7-max-fast",
 			},
-		},
-		{
-			id: "claude-opus-4-7-fast",
-			name: "Claude Opus 4.7 Fast",
-			members: [
-				"claude-opus-4-7-low-fast",
-				"claude-opus-4-7-medium-fast",
-				"claude-opus-4-7-high-fast",
-				"claude-opus-4-7-xhigh-fast",
-				"claude-opus-4-7-max-fast",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-7-low-fast",
-				[Effort.Low]: "claude-opus-4-7-medium-fast",
-				[Effort.Medium]: "claude-opus-4-7-high-fast",
-				[Effort.High]: "claude-opus-4-7-xhigh-fast",
-				[Effort.XHigh]: "claude-opus-4-7-max-fast",
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
+		devinTierFamily(
+			"claude-opus-4-8",
+			"Claude Opus 4.8",
+			{
+				low: "claude-opus-4-8-low",
+				medium: "claude-opus-4-8-medium",
+				high: "claude-opus-4-8-high",
+				xhigh: "claude-opus-4-8-xhigh",
+				max: "claude-opus-4-8-max",
 			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
+		devinTierFamily(
+			"claude-opus-4-8-fast",
+			"Claude Opus 4.8 Fast",
+			{
+				low: "claude-opus-4-8-low-fast",
+				medium: "claude-opus-4-8-medium-fast",
+				high: "claude-opus-4-8-high-fast",
+				xhigh: "claude-opus-4-8-xhigh-fast",
+				max: "claude-opus-4-8-max-fast",
 			},
-		},
-		{
-			id: "claude-opus-4-8",
-			name: "Claude Opus 4.8",
-			members: [
-				"claude-opus-4-8-low",
-				"claude-opus-4-8-medium",
-				"claude-opus-4-8-high",
-				"claude-opus-4-8-xhigh",
-				"claude-opus-4-8-max",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-8-low",
-				[Effort.Low]: "claude-opus-4-8-medium",
-				[Effort.Medium]: "claude-opus-4-8-high",
-				[Effort.High]: "claude-opus-4-8-xhigh",
-				[Effort.XHigh]: "claude-opus-4-8-max",
-			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
-			},
-		},
-		{
-			id: "claude-opus-4-8-fast",
-			name: "Claude Opus 4.8 Fast",
-			members: [
-				"claude-opus-4-8-low-fast",
-				"claude-opus-4-8-medium-fast",
-				"claude-opus-4-8-high-fast",
-				"claude-opus-4-8-xhigh-fast",
-				"claude-opus-4-8-max-fast",
-			],
-			routing: {
-				[Effort.Minimal]: "claude-opus-4-8-low-fast",
-				[Effort.Low]: "claude-opus-4-8-medium-fast",
-				[Effort.Medium]: "claude-opus-4-8-high-fast",
-				[Effort.High]: "claude-opus-4-8-xhigh-fast",
-				[Effort.XHigh]: "claude-opus-4-8-max-fast",
-			},
-			thinking: {
-				mode: "effort",
-				efforts: DEVIN_FIVE_TIER_EFFORTS,
-				requiresEffort: true,
-			},
-		},
+			DEVIN_FIVE_TIER_EFFORTS,
+		),
 		devinTierFamily(
 			"gpt-5-2",
 			"GPT-5.2",
@@ -459,7 +415,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "MODEL_GPT_5_2_HIGH",
 				xhigh: "MODEL_GPT_5_2_XHIGH",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-3-codex",
@@ -470,7 +426,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-3-codex-high",
 				xhigh: "gpt-5-3-codex-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-3-codex-fast",
@@ -481,7 +437,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-3-codex-high-priority",
 				xhigh: "gpt-5-3-codex-xhigh-priority",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-4",
@@ -493,7 +449,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-4-high",
 				xhigh: "gpt-5-4-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-4-fast",
@@ -505,7 +461,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-4-high-priority",
 				xhigh: "gpt-5-4-xhigh-priority",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-4-mini",
@@ -516,7 +472,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-4-mini-high",
 				xhigh: "gpt-5-4-mini-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-5",
@@ -528,7 +484,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-5-high",
 				xhigh: "gpt-5-5-xhigh",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		devinTierFamily(
 			"gpt-5-5-fast",
@@ -540,7 +496,7 @@ export const DEVIN_VARIANT_COLLAPSE_TABLE: VariantCollapseTable = {
 				high: "gpt-5-5-high-priority",
 				xhigh: "gpt-5-5-xhigh-priority",
 			},
-			DEVIN_FIVE_TIER_EFFORTS,
+			DEVIN_FOUR_TIER_EFFORTS,
 		),
 		...devinGpt56Families("luna", "GPT-5.6 Luna"),
 		...devinGpt56Families("sol", "GPT-5.6 Sol"),
diff --git a/packages/catalog/test/generated-policies.test.ts b/packages/catalog/test/generated-policies.test.ts
index bd32f2f43..2c6da8a51 100644
--- a/packages/catalog/test/generated-policies.test.ts
+++ b/packages/catalog/test/generated-policies.test.ts
@@ -76,8 +76,7 @@ describe("generated model policies", () => {
 		expect(models[0]?.cost.cacheWrite).toBe(6.25);
 		expect(models[1]?.thinking).toEqual({
 			mode: "anthropic-adaptive",
-			efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-			effortMap: { minimal: "low", xhigh: "max" },
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.Max],
 		});
 		expect(models[1]?.cost.cacheRead).toBe(0.5);
 		expect(models[1]?.cost.cacheWrite).toBe(6.25);
@@ -103,8 +102,7 @@ describe("generated model policies", () => {
 		expect(models[0]?.cost).toEqual({ input: 10, output: 50, cacheRead: 1, cacheWrite: 12.5 });
 		expect(models[0]?.thinking).toEqual({
 			mode: "anthropic-adaptive",
-			efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-			effortMap: { minimal: "low", low: "medium", medium: "high", high: "xhigh", xhigh: "max" },
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 			supportsDisplay: true,
 		});
 	});
diff --git a/packages/catalog/test/litellm-provider.test.ts b/packages/catalog/test/litellm-provider.test.ts
index c353ac16f..48ded780f 100644
--- a/packages/catalog/test/litellm-provider.test.ts
+++ b/packages/catalog/test/litellm-provider.test.ts
@@ -277,10 +277,9 @@ describe("LiteLLM provider discovery", () => {
 			reasoning: true,
 			thinking: {
 				mode: "effort",
-				efforts: ["minimal", "low", "medium", "high", "xhigh"],
+				efforts: ["minimal", "low", "medium", "high", "max"],
 				effortMap: {
 					minimal: "none",
-					xhigh: "max",
 				},
 			},
 		});
@@ -709,10 +708,9 @@ describe("LiteLLM provider discovery", () => {
 			reasoning: true,
 			thinking: {
 				mode: "effort",
-				efforts: ["minimal", "low", "medium", "high", "xhigh"],
+				efforts: ["minimal", "low", "medium", "high", "max"],
 				effortMap: {
 					minimal: "none",
-					xhigh: "max",
 				},
 			},
 		});
diff --git a/packages/catalog/test/model-thinking.test.ts b/packages/catalog/test/model-thinking.test.ts
index a21a323fc..ed08575f1 100644
--- a/packages/catalog/test/model-thinking.test.ts
+++ b/packages/catalog/test/model-thinking.test.ts
@@ -196,7 +196,7 @@ describe("model thinking derivation", () => {
 			api: "openai-completions",
 			provider: "deepseek",
 			baseUrl: "https://api.deepseek.com/v1",
-			compat: { reasoningEffortMap: { xhigh: "max-plus" } },
+			compat: { reasoningEffortMap: { max: "max-plus" } },
 		});
 		const openRouterAnthropic = createModel({
 			id: "anthropic/claude-opus-4.7",
@@ -212,20 +212,20 @@ describe("model thinking derivation", () => {
 			medium: "default",
 			high: "default",
 		});
-		expect(deepseek.thinking?.effortMap).toMatchObject({
-			minimal: "high",
-			low: "high",
-			medium: "high",
-			high: "high",
-			xhigh: "max-plus",
-		});
-		expect(openRouterAnthropic.thinking?.effortMap).toEqual({
-			minimal: "low",
-			low: "medium",
-			medium: "high",
-			high: "xhigh",
-			xhigh: "max",
-		});
+		// DeepSeek's ladder is the wire-exact high/max pair; explicit compat
+		// overrides still win over the identity wire values.
+		expect(getSupportedEfforts(deepseek)).toEqual([Effort.High, Effort.Max]);
+		expect(deepseek.thinking?.effortMap).toEqual({ max: "max-plus" });
+		// OpenRouter-hosted Anthropic adaptive models carry the wire-exact
+		// five-tier ladder with no remapping.
+		expect(getSupportedEfforts(openRouterAnthropic)).toEqual([
+			Effort.Low,
+			Effort.Medium,
+			Effort.High,
+			Effort.XHigh,
+			Effort.Max,
+		]);
+		expect(openRouterAnthropic.thinking?.effortMap).toBeUndefined();
 	});
 
 	it("maps GLM-5.2 reasoning effort per host dialect", () => {
@@ -248,19 +248,20 @@ describe("model thinking derivation", () => {
 			baseUrl: "https://openrouter.ai/api/v1",
 		});
 
-		// Z.ai dialect: the model only does none/high/max, so the lower tiers
-		// collapse and the top `xhigh` tier reaches `max`.
-		expect(zai.thinking?.effortMap).toEqual({
-			minimal: "none",
-			low: "high",
-			medium: "high",
-			high: "high",
-			xhigh: "max",
-		});
-		// Fireworks keeps its distinct lower tiers and the `minimal -> none` quirk;
-		// only the top `xhigh` UI tier remaps onto the genuine `max` budget.
-		expect(getSupportedEfforts(fireworks)).toContain(Effort.XHigh);
-		expect(fireworks.thinking?.effortMap).toEqual({ minimal: "none", xhigh: "max" });
+		// Z.ai dialect: the model only does none/high/max on the wire, so the
+		// ladder is the honest high/max pair (none = thinking off).
+		expect(getSupportedEfforts(zai)).toEqual([Effort.High, Effort.Max]);
+		expect(zai.thinking?.effortMap).toBeUndefined();
+		// Fireworks keeps its distinct lower tiers and the `minimal -> none`
+		// quirk; the genuine `max` tier sits above `high`.
+		expect(getSupportedEfforts(fireworks)).toEqual([
+			Effort.Minimal,
+			Effort.Low,
+			Effort.Medium,
+			Effort.High,
+			Effort.Max,
+		]);
+		expect(fireworks.thinking?.effortMap).toEqual({ minimal: "none" });
 		// OpenRouter rejects `max` and treats `xhigh` as its max tier: expose the
 		// `xhigh` tier and pass it through unmapped.
 		expect(getSupportedEfforts(openRouter)).toContain(Effort.XHigh);
@@ -428,30 +429,34 @@ describe("model thinking derivation", () => {
 			},
 		});
 		expect(mapEffortToAnthropicAdaptiveEffort(minimaxM3, Effort.High)).toBe("adaptive");
-		// Opus 4.6 has no real xhigh level — the baked 4-tier map aliases XHigh to "max".
-		expect(opus46.thinking?.effortMap).toEqual({ minimal: "low", xhigh: "max" });
-		expect(mapEffortToAnthropicAdaptiveEffort(opus46, Effort.XHigh)).toBe("max");
-		// Opus 4.7+ on the Messages API exposes the full five-tier scale: the baked
-		// map shifts each user-facing effort up one notch so the top tier reaches "max".
-		expect(opus47.thinking?.effortMap).toEqual({
-			minimal: "low",
-			low: "medium",
-			medium: "high",
-			high: "xhigh",
-			xhigh: "max",
-		});
-		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.Minimal)).toBe("low");
-		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.High)).toBe("xhigh");
-		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.XHigh)).toBe("max");
-		expect(mapEffortToAnthropicAdaptiveEffort(mythos, Effort.High)).toBe("xhigh");
-		expect(mapEffortToAnthropicAdaptiveEffort(mythosBedrock, Effort.XHigh)).toBe("max");
-		expect(mapEffortToAnthropicAdaptiveEffort(sonnet5, Effort.High)).toBe("xhigh");
-		expect(mapEffortToAnthropicAdaptiveEffort(sonnet5Bedrock, Effort.XHigh)).toBe("max");
-		// Bedrock Converse keeps the four-tier legacy mapping; xhigh aliases to "max".
-		expect(opus47Bedrock.thinking?.effortMap).toEqual({ minimal: "low", xhigh: "max" });
+		// Opus 4.6 has no real xhigh tier — the honest ladder is the four-tier
+		// low/medium/high/max wire scale, mapped 1:1.
+		expect(getSupportedEfforts(opus46)).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.Max]);
+		expect(opus46.thinking?.effortMap).toBeUndefined();
+		expect(mapEffortToAnthropicAdaptiveEffort(opus46, Effort.Max)).toBe("max");
+		expect(() => mapEffortToAnthropicAdaptiveEffort(opus46, Effort.XHigh)).toThrow(/not supported/);
+		// Opus 4.7+ on the Messages API exposes the full five-tier wire scale
+		// low..max with no remapping.
+		expect(getSupportedEfforts(opus47)).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max]);
+		expect(opus47.thinking?.effortMap).toBeUndefined();
+		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.Low)).toBe("low");
+		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.High)).toBe("high");
+		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.XHigh)).toBe("xhigh");
+		expect(mapEffortToAnthropicAdaptiveEffort(opus47, Effort.Max)).toBe("max");
+		expect(() => mapEffortToAnthropicAdaptiveEffort(opus47, Effort.Minimal)).toThrow(/not supported/);
+		expect(mapEffortToAnthropicAdaptiveEffort(mythos, Effort.XHigh)).toBe("xhigh");
+		expect(mapEffortToAnthropicAdaptiveEffort(sonnet5, Effort.Max)).toBe("max");
+		// Bedrock Converse stays on the four-tier scale regardless of version.
+		expect(getSupportedEfforts(opus47Bedrock)).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.Max]);
+		expect(opus47Bedrock.thinking?.effortMap).toBeUndefined();
 		expect(mapEffortToAnthropicAdaptiveEffort(opus47Bedrock, Effort.High)).toBe("high");
-		expect(mapEffortToAnthropicAdaptiveEffort(sonnet5Bedrock, Effort.High)).toBe("high");
+		expect(mapEffortToAnthropicAdaptiveEffort(opus47Bedrock, Effort.Max)).toBe("max");
+		expect(mapEffortToAnthropicAdaptiveEffort(sonnet5Bedrock, Effort.Max)).toBe("max");
+		expect(() => mapEffortToAnthropicAdaptiveEffort(sonnet5Bedrock, Effort.XHigh)).toThrow(/not supported/);
+		// Sonnet 4.6 runs adaptive mode on the three-tier low/medium/high scale.
+		expect(getSupportedEfforts(sonnet46)).toEqual([Effort.Low, Effort.Medium, Effort.High]);
 		expect(() => mapEffortToAnthropicAdaptiveEffort(sonnet46, Effort.XHigh)).toThrow(/not supported/);
+		expect(() => mapEffortToAnthropicAdaptiveEffort(sonnet46, Effort.Max)).toThrow(/not supported/);
 	});
 
 	it("bakes adaptive display support for Opus 4.7+, Sonnet 5+, and Fable/Mythos 5", () => {
@@ -488,8 +493,9 @@ describe("model thinking derivation", () => {
 	});
 
 	it("backfills wire facts onto explicit thinking, explicit values winning", () => {
-		// Authored capability surface (mode/efforts) keeps identity-derived wire
-		// facts: configs never need to know Anthropic's tier tables.
+		// Authored partial ladders on wire-exact models normalize to the
+		// model-defined ladder, and the wire map is re-derived alongside:
+		// stale cached surfaces cannot pin retired wire facts.
 		const filled = createModel({
 			id: "claude-opus-4-8",
 			api: "anthropic-messages",
@@ -498,24 +504,24 @@ describe("model thinking derivation", () => {
 		});
 		expect(filled.thinking).toEqual({
 			mode: "anthropic-adaptive",
-			efforts: [Effort.Low, Effort.High],
-			effortMap: { low: "medium", high: "xhigh" },
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 			supportsDisplay: true,
 		});
 
-		// Explicit wire facts are authoritative — including `false`.
+		// Explicit wire facts are authoritative — including `false` — when the
+		// authored ladder matches the wire truth.
 		const pinned = createModel({
 			id: "claude-opus-4-8",
 			api: "anthropic-messages",
 			provider: "anthropic",
 			thinking: {
 				mode: "anthropic-adaptive",
-				efforts: [Effort.Low, Effort.High],
-				effortMap: { xhigh: "max" },
+				efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
+				effortMap: { max: "ultra" },
 				supportsDisplay: false,
 			},
 		});
-		expect(pinned.thinking?.effortMap).toEqual({ xhigh: "max" });
+		expect(pinned.thinking?.effortMap).toEqual({ max: "ultra" });
 		expect(pinned.thinking?.supportsDisplay).toBe(false);
 	});
 
@@ -568,7 +574,7 @@ describe("model thinking derivation", () => {
 		expect(clampThinkingLevelForModel(model, Effort.High)).toBeUndefined();
 	});
 
-	it("bakes the GPT-5.6 shifted five-tier effort map on wire-effort APIs", () => {
+	it("bakes the wire-exact five-tier low..max ladder on GPT-5.6 wire-effort APIs", () => {
 		const codex = createModel({
 			id: "gpt-5.6-sol",
 			api: "openai-codex-responses",
@@ -577,19 +583,12 @@ describe("model thinking derivation", () => {
 
 		expect(codex.thinking).toEqual({
 			mode: "effort",
-			efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-			effortMap: {
-				minimal: "low",
-				low: "medium",
-				medium: "high",
-				high: "xhigh",
-				xhigh: "max",
-			},
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 		});
 
-		// Stale baked four-tier metadata (caches/discovery) normalizes back to
-		// the five-tier ladder with the map attached — the wire-defaults
-		// backfill path — and namespaced OpenRouter ids parse.
+		// Stale baked metadata (caches/discovery) — including shifted-era maps —
+		// normalizes to the wire-exact ladder with the map re-derived away, and
+		// namespaced OpenRouter ids parse.
 		const staleOpenRouter = createModel({
 			id: "openai/gpt-5.6-terra",
 			api: "openrouter",
@@ -597,24 +596,24 @@ describe("model thinking derivation", () => {
 			baseUrl: "https://openrouter.ai/api/v1",
 			thinking: {
 				mode: "effort",
-				efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+				efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+				effortMap: {
+					minimal: "low",
+					low: "medium",
+					medium: "high",
+					high: "xhigh",
+					xhigh: "max",
+				},
 			},
 		});
 
 		expect(staleOpenRouter.thinking).toEqual({
 			mode: "effort",
-			efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-			effortMap: {
-				minimal: "low",
-				low: "medium",
-				medium: "high",
-				high: "xhigh",
-				xhigh: "max",
-			},
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 		});
 	});
 
-	it("keeps pre-5.6 and Devin-routed GPT models off the shifted effort map", () => {
+	it("keeps pre-5.6 and Devin-routed GPT models on their own effort surfaces", () => {
 		const gpt55 = createModel({
 			id: "gpt-5.5",
 			api: "openai-responses",
@@ -628,7 +627,7 @@ describe("model thinking derivation", () => {
 		expect(gpt55.thinking?.effortMap).toBeUndefined();
 
 		// Devin selects effort by routing to per-tier sibling model ids, never
-		// via a wire reasoning.effort field — the shifted map must not attach.
+		// via a wire reasoning.effort field — no effort map may attach.
 		const devin = createModel({
 			id: "gpt-5-6-sol",
 			api: "devin-agent",
@@ -636,20 +635,20 @@ describe("model thinking derivation", () => {
 			baseUrl: "https://server.codeium.com",
 			thinking: {
 				mode: "effort",
-				efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+				efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
 				effortRouting: {
 					off: "gpt-5-6-sol-none",
-					minimal: "gpt-5-6-sol-low",
-					low: "gpt-5-6-sol-medium",
-					medium: "gpt-5-6-sol-high",
-					high: "gpt-5-6-sol-xhigh",
-					xhigh: "gpt-5-6-sol-max",
+					low: "gpt-5-6-sol-low",
+					medium: "gpt-5-6-sol-medium",
+					high: "gpt-5-6-sol-high",
+					xhigh: "gpt-5-6-sol-xhigh",
+					max: "gpt-5-6-sol-max",
 				},
 			},
 		});
 
 		expect(devin.thinking?.effortMap).toBeUndefined();
-		expect(devin.thinking?.efforts).toEqual([Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh]);
+		expect(devin.thinking?.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max]);
 	});
 });
 
@@ -712,7 +711,7 @@ describe("model thinking runtime helpers", () => {
 		);
 	});
 
-	it("maps GLM-5.2 xhigh to Z.AI provider-native max", () => {
+	it("exposes the Z.AI GLM-5.2 high/max wire pair directly", () => {
 		const model = createModel({
 			id: "glm-5.2",
 			api: "openai-completions",
@@ -723,19 +722,15 @@ describe("model thinking runtime helpers", () => {
 
 		expect(model.thinking).toEqual({
 			mode: "effort",
-			efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
-			effortMap: {
-				minimal: "none",
-				low: "high",
-				medium: "high",
-				high: "high",
-				xhigh: "max",
-			},
+			efforts: [Effort.High, Effort.Max],
 		});
-		expect(requireSupportedEffort(model, Effort.XHigh)).toBe(Effort.XHigh);
+		expect(requireSupportedEffort(model, Effort.Max)).toBe(Effort.Max);
+		expect(() => requireSupportedEffort(model, Effort.XHigh)).toThrow(/Supported efforts: high, max/);
+		// Selecting a retired tier clamps down instead of erroring in UI flows.
+		expect(clampThinkingLevelForModel(model, Effort.XHigh)).toBe(Effort.High);
 	});
 
-	it("maps Ollama Cloud GLM-5.2 xhigh to max and hides unsupported lower efforts", () => {
+	it("exposes Ollama Cloud GLM-5.2 high/max and hides unsupported lower efforts", () => {
 		const model = createModel({
 			id: "glm-5.2",
 			api: "ollama-chat",
@@ -745,14 +740,11 @@ describe("model thinking runtime helpers", () => {
 
 		expect(model.thinking).toEqual({
 			mode: "effort",
-			efforts: [Effort.High, Effort.XHigh],
-			effortMap: {
-				xhigh: "max",
-			},
+			efforts: [Effort.High, Effort.Max],
 		});
 		expect(requireSupportedEffort(model, Effort.High)).toBe(Effort.High);
-		expect(requireSupportedEffort(model, Effort.XHigh)).toBe(Effort.XHigh);
-		expect(() => requireSupportedEffort(model, Effort.Medium)).toThrow(/Supported efforts: high, xhigh/);
+		expect(requireSupportedEffort(model, Effort.Max)).toBe(Effort.Max);
+		expect(() => requireSupportedEffort(model, Effort.Medium)).toThrow(/Supported efforts: high, max/);
 	});
 
 	it("derives binary-thinking fallback from resolved compat when catalog compat is partial", () => {
@@ -774,7 +766,7 @@ describe("model thinking runtime helpers", () => {
 		);
 	});
 
-	it("exposes xhigh for OpenRouter-hosted Anthropic adaptive models", () => {
+	it("exposes wire-exact adaptive ladders for OpenRouter-hosted Anthropic models", () => {
 		const fable = createModel({
 			id: "anthropic/claude-fable-5",
 			api: "openai-completions",
@@ -795,12 +787,13 @@ describe("model thinking runtime helpers", () => {
 			api: "openai-completions",
 			provider: "openrouter",
 		});
-		expect(fable.thinking?.efforts.at(-1)).toBe(Effort.XHigh);
-		expect(opus46.thinking?.efforts.at(-1)).toBe(Effort.XHigh);
+		expect(fable.thinking?.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max]);
+		expect(opus46.thinking?.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.Max]);
 		expect(sonnet46.thinking?.efforts.at(-1)).toBe(Effort.High);
-		expect(sonnet5.thinking?.efforts.at(-1)).toBe(Effort.XHigh);
-		expect(requireSupportedEffort(fable, Effort.XHigh)).toBe(Effort.XHigh);
+		expect(sonnet5.thinking?.efforts.at(-1)).toBe(Effort.Max);
+		expect(requireSupportedEffort(fable, Effort.Max)).toBe(Effort.Max);
 		expect(requireSupportedEffort(sonnet5, Effort.XHigh)).toBe(Effort.XHigh);
+		expect(() => requireSupportedEffort(opus46, Effort.XHigh)).toThrow(/not supported/);
 	});
 
 	it("enables xhigh for openai-responses and openai-codex-responses APIs", () => {
diff --git a/packages/catalog/test/ollama-cloud-provider.test.ts b/packages/catalog/test/ollama-cloud-provider.test.ts
index 4f640c145..4f85dac46 100644
--- a/packages/catalog/test/ollama-cloud-provider.test.ts
+++ b/packages/catalog/test/ollama-cloud-provider.test.ts
@@ -141,8 +141,7 @@ describe("ollama-cloud provider support", () => {
 		expect(model?.reasoning).toBe(true);
 		expect(built?.thinking).toEqual({
 			mode: "effort",
-			efforts: [Effort.High, Effort.XHigh],
-			effortMap: { xhigh: "max" },
+			efforts: [Effort.High, Effort.Max],
 		});
 	});
 
@@ -286,7 +285,7 @@ describe("ollama-cloud provider support", () => {
 		expect(result.errorMessage).toContain("prompt filled the context window");
 	});
 
-	test("sends max for GLM-5.2 xhigh reasoning on Ollama Cloud", async () => {
+	test("sends native max for GLM-5.2 max reasoning on Ollama Cloud", async () => {
 		let requestBody: Record<string, unknown> | undefined;
 		const fetchMock: FetchImpl = vi.fn(async (_input, init) => {
 			requestBody = JSON.parse(String(init?.body ?? "{}")) as Record<string, unknown>;
@@ -302,7 +301,7 @@ describe("ollama-cloud provider support", () => {
 			provider: "ollama-cloud",
 			baseUrl: "https://ollama.com",
 			reasoning: true,
-			thinking: { mode: "effort", efforts: [Effort.High, Effort.XHigh], effortMap: { [Effort.XHigh]: "max" } },
+			thinking: { mode: "effort", efforts: [Effort.High, Effort.Max] },
 			input: ["text"],
 			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
 			contextWindow: 1_000_000,
@@ -315,7 +314,7 @@ describe("ollama-cloud provider support", () => {
 			{
 				apiKey: "cloud-test-key",
 				fetch: fetchMock,
-				reasoning: Effort.XHigh,
+				reasoning: Effort.Max,
 			},
 		).result();
 
diff --git a/packages/catalog/test/ollama-provider.test.ts b/packages/catalog/test/ollama-provider.test.ts
index acbf10fb3..aebd75789 100644
--- a/packages/catalog/test/ollama-provider.test.ts
+++ b/packages/catalog/test/ollama-provider.test.ts
@@ -3,6 +3,7 @@ import { streamOllama } from "@oh-my-pi/pi-ai/providers/ollama";
 import type { Context, Tool } from "@oh-my-pi/pi-ai/types";
 import { buildModel } from "@oh-my-pi/pi-catalog/build";
 import { Effort } from "@oh-my-pi/pi-catalog/effort";
+import { clampThinkingLevelForModel } from "@oh-my-pi/pi-catalog/model-thinking";
 import { ollamaModelManagerOptions } from "@oh-my-pi/pi-catalog/provider-models/openai-compat";
 import type { FetchImpl, ModelSpec } from "@oh-my-pi/pi-catalog/types";
 
@@ -87,10 +88,14 @@ describe("ollama local provider discovery", () => {
 		const builtReasoningModel = reasoningModel ? buildModel(reasoningModel) : undefined;
 		const builtPlainModel = plainModel ? buildModel(plainModel) : undefined;
 
-		// Ollama's OpenAI-compatible endpoint rejects "minimal" with HTTP 400;
-		// reasoning models must bake a thinking effort map to an accepted level (low).
+		// Ollama's OpenAI-compatible endpoint accepts low/medium/high/max;
+		// reasoning models carry that wire-exact ladder with no remapping
+		// (minimal/xhigh never reach the wire because they are not offered).
 		expect(reasoningModel?.reasoning).toBe(true);
-		expect(builtReasoningModel?.thinking?.effortMap).toMatchObject({ minimal: "low" });
+		expect(builtReasoningModel?.thinking).toEqual({
+			mode: "effort",
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.Max],
+		});
 		// Non-reasoning models never send an effort, so they carry no thinking metadata.
 		expect(plainModel?.reasoning).toBe(false);
 		expect(builtPlainModel?.thinking).toBeUndefined();
@@ -150,7 +155,7 @@ describe("ollama tool forcing", () => {
 	});
 });
 
-describe("ollama reasoning effort backfill (buildModel)", () => {
+describe("ollama reasoning effort normalization (buildModel)", () => {
 	const staleOllamaSpec = <TApi extends "openai-responses" | "openai-completions">(
 		api: TApi,
 		compat?: ModelSpec<TApi>["compat"],
@@ -170,38 +175,32 @@ describe("ollama reasoning effort backfill (buildModel)", () => {
 			compat,
 		}) as ModelSpec<TApi>;
 
-	test("stamps the effort map on a stale ollama responses spec lacking compat", () => {
-		// A cache row or hand-written config written before the remap existed:
-		// reasoning-capable, `minimal` offered, but no reasoningEffortMap. The
-		// builder must backfill it so the wire never sends raw `minimal`/`xhigh`.
+	test("normalizes a stale ollama responses spec to the wire-exact ladder", () => {
+		// A cache row or hand-written config from the remap era: reasoning-capable
+		// with `minimal` offered. The builder must normalize the ladder so the
+		// wire never sends raw `minimal`/`xhigh`.
 		const model = buildModel(staleOllamaSpec("openai-responses"));
-		expect(model.compat.reasoningEffortMap).toMatchObject({ minimal: "low", xhigh: "max" });
-		// xhigh drops out of thinking.effortMap — it is not an offered effort.
-		expect(model.thinking?.effortMap).toEqual({ minimal: "low" });
+		expect(model.thinking?.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.Max]);
+		expect(model.thinking?.effortMap).toBeUndefined();
+		// Retired tiers clamp instead of erroring.
+		expect(clampThinkingLevelForModel(model, Effort.Minimal)).toBe(Effort.Low);
+		expect(clampThinkingLevelForModel(model, Effort.XHigh)).toBe(Effort.High);
 	});
 
-	test("backfills openai-completions ollama specs too", () => {
+	test("normalizes openai-completions ollama specs too", () => {
 		const model = buildModel(staleOllamaSpec("openai-completions"));
-		expect(model.compat.reasoningEffortMap).toMatchObject({ minimal: "low", xhigh: "max" });
+		expect(model.thinking?.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.Max]);
 	});
 
-	test("explicit overrides win while missing ollama defaults stay", () => {
-		const model = buildModel(staleOllamaSpec("openai-responses", { reasoningEffortMap: { minimal: "medium" } }));
-		expect(model.compat.reasoningEffortMap).toEqual({ minimal: "medium", xhigh: "max" });
+	test("explicit compat overrides survive for live tiers", () => {
+		const model = buildModel(staleOllamaSpec("openai-responses", { reasoningEffortMap: { high: "medium" } }));
+		expect(model.compat.reasoningEffortMap).toEqual({ high: "medium" });
+		expect(model.thinking?.effortMap).toEqual({ high: "medium" });
 	});
 
 	test("leaves non-ollama providers untouched", () => {
 		const model = buildModel({ ...staleOllamaSpec("openai-responses"), provider: "custom" });
 		expect(model.compat.reasoningEffortMap).toEqual({});
-	});
-
-	test("merges the ollama defaults into the whenThinking variant", () => {
-		const model = buildModel(
-			staleOllamaSpec("openai-completions", { whenThinking: { reasoningEffortMap: { minimal: "medium" } } }),
-		);
-		// The thinking-engaged variant must keep the xhigh default; otherwise a
-		// partial whenThinking override would re-leak raw `minimal`/`xhigh`.
-		expect(model.compat.whenThinking?.reasoningEffortMap).toEqual({ minimal: "medium", xhigh: "max" });
-		expect(model.compat.reasoningEffortMap).toEqual({ minimal: "low", xhigh: "max" });
+		expect(model.thinking?.efforts).toEqual([Effort.Minimal, Effort.Low, Effort.Medium, Effort.High]);
 	});
 });
diff --git a/packages/catalog/test/sakana-provider.test.ts b/packages/catalog/test/sakana-provider.test.ts
index f7b9d3ac2..0456be443 100644
--- a/packages/catalog/test/sakana-provider.test.ts
+++ b/packages/catalog/test/sakana-provider.test.ts
@@ -60,8 +60,8 @@ describe("Sakana AI provider support", () => {
 		expect(bundled.find(model => model.id === "fugu-ultra-20260615")?.contextWindow).toBe(1_000_000);
 		for (const model of bundled) {
 			expect(model.api).toBe("openai-responses");
-			expect(model.thinking?.efforts).toEqual([Effort.High, Effort.XHigh]);
-			expect(model.thinking?.effortMap?.[Effort.XHigh]).toBe("max");
+			expect(model.thinking?.efforts).toEqual([Effort.High, Effort.Max]);
+			expect(model.thinking?.effortMap).toBeUndefined();
 			expect((model.compat as ResolvedOpenAIResponsesCompat).includeEncryptedReasoning).toBe(false);
 			expect((model.compat as ResolvedOpenAIResponsesCompat).streamIdleTimeoutMs).toBe(0);
 		}
@@ -95,8 +95,8 @@ describe("Sakana AI provider support", () => {
 		expect(models?.map(model => model.id)).toEqual(["fugu", "fugu-next", "fugu-ultra"]);
 		const fuguNext = models?.find(model => model.id === "fugu-next");
 		expect(fuguNext?.reasoning).toBe(true);
-		expect(fuguNext?.thinking?.efforts).toEqual([Effort.High, Effort.XHigh]);
-		expect(fuguNext?.thinking?.effortMap?.[Effort.XHigh]).toBe("max");
+		expect(fuguNext?.thinking?.efforts).toEqual([Effort.High, Effort.Max]);
+		expect(fuguNext?.thinking?.effortMap).toBeUndefined();
 		expect(fuguNext?.compat?.includeEncryptedReasoning).toBe(false);
 	});
 
diff --git a/packages/catalog/test/umans-provider.test.ts b/packages/catalog/test/umans-provider.test.ts
index a128d59f8..a641e6ec9 100644
--- a/packages/catalog/test/umans-provider.test.ts
+++ b/packages/catalog/test/umans-provider.test.ts
@@ -118,12 +118,11 @@ describe("umans provider catalog", () => {
 			thinking: {
 				mode: "anthropic-budget-effort",
 				defaultLevel: "high",
-				efforts: ["high", "xhigh"],
-				effortMap: { xhigh: "max" },
+				efforts: ["high", "max"],
 			},
 		});
 		if (!glm52) throw new Error("Umans GLM 5.2 was not discovered");
-		expect(glm52.thinking?.effortMap).toEqual({ [Effort.XHigh]: "max" });
+		expect(glm52.thinking?.effortMap).toBeUndefined();
 		expect(glm52.thinking?.defaultLevel).toBe(Effort.High);
 	});
 
@@ -307,15 +306,15 @@ describe("umans provider catalog", () => {
 		});
 	});
 
-	it("bundles Umans GLM 5.2 high/max reasoning metadata with the max wire effort", () => {
+	it("bundles Umans GLM 5.2 with the wire-exact high/max ladder", () => {
 		const providers = modelsJson as Record<string, Record<string, BundledModel>>;
 		const model = providers.umans?.["umans-glm-5.2"];
 
 		expect(model).toBeDefined();
 		expect(model.thinking).toMatchObject({
 			mode: "anthropic-budget-effort",
-			efforts: ["high", "xhigh"],
-			effortMap: { xhigh: "max" },
+			efforts: ["high", "max"],
 		});
+		expect(model.thinking?.effortMap).toBeUndefined();
 	});
 });
diff --git a/packages/catalog/test/variant-collapse.test.ts b/packages/catalog/test/variant-collapse.test.ts
index ae373b6bf..cbfc93781 100644
--- a/packages/catalog/test/variant-collapse.test.ts
+++ b/packages/catalog/test/variant-collapse.test.ts
@@ -17,6 +17,7 @@ import {
 	ANTIGRAVITY_VARIANT_COLLAPSE_TABLE,
 	collapseEffortVariants,
 	collapseEffortVariantsAcrossProviders,
+	DEVIN_VARIANT_COLLAPSE_TABLE,
 	deriveThinkingPairFamilies,
 	GEMINI_CLI_VARIANT_COLLAPSE_TABLE,
 	getVariantAliasSources,
@@ -526,6 +527,45 @@ describe("collapseEffortVariantsAcrossProviders", () => {
 	});
 });
 
+describe("Devin tier routing", () => {
+	const family = (id: string) => {
+		const found = DEVIN_VARIANT_COLLAPSE_TABLE.families.find(f => f.id === id);
+		if (!found) throw new Error(`Devin family ${id} missing`);
+		return found;
+	};
+
+	it("routes user efforts 1:1 onto per-tier siblings including max", () => {
+		const opus = family("claude-opus-4-8");
+		expect(opus.routing).toEqual({
+			[Effort.Low]: "claude-opus-4-8-low",
+			[Effort.Medium]: "claude-opus-4-8-medium",
+			[Effort.High]: "claude-opus-4-8-high",
+			[Effort.XHigh]: "claude-opus-4-8-xhigh",
+			[Effort.Max]: "claude-opus-4-8-max",
+		});
+		expect(opus.thinking.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max]);
+		expect(opus.thinking.requiresEffort).toBe(true);
+
+		const sol = family("gpt-5-6-sol");
+		expect(sol.routing[Effort.Max]).toBe("gpt-5-6-sol-max");
+		expect(sol.routing[Effort.Low]).toBe("gpt-5-6-sol-low");
+		expect(sol.routing.off).toBe("gpt-5-6-sol-none");
+		expect(sol.routing[Effort.Minimal]).toBeUndefined();
+	});
+
+	it("keeps families without a -max sibling on the xhigh ceiling", () => {
+		const solFast = family("gpt-5-6-sol-fast");
+		expect(solFast.thinking.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.XHigh]);
+		expect(solFast.routing[Effort.Max]).toBeUndefined();
+		expect(solFast.routing[Effort.XHigh]).toBe("gpt-5-6-sol-xhigh-priority");
+
+		const gpt55 = family("gpt-5-5");
+		expect(gpt55.thinking.efforts).toEqual([Effort.Low, Effort.Medium, Effort.High, Effort.XHigh]);
+		expect(gpt55.routing[Effort.Minimal]).toBeUndefined();
+		expect(gpt55.routing[Effort.Max]).toBeUndefined();
+	});
+});
+
 describe("variant aliases", () => {
 	it("resolves members and recycled ids per provider", () => {
 		expect(resolveVariantAlias("google-antigravity", "gemini-3.5-flash-low")).toBe("gemini-3.5-flash");
diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 658e3a904..214127a96 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -6,10 +6,18 @@
 
 - Renamed the bundled agent `explore` to `scout` (including renaming its configuration keys, prompt files, and task definitions). Any configurations, allowlists, or invocations referencing `explore` must now use `scout`.
 
+### Added
+
+- Added `max` as a native, first-class thinking tier for supported models
+- Added `thinkingBudgets.max` configuration setting
+- Updated terminal theme to support optional `thinkingMax` border color and icons
+
+- Added a real `max` thinking level above `xhigh` with an optional `thinkingMax` theme border color (falls back to `thinkingXhigh`). `max` owns the top status-line icons (`◉` unicode, fire nerd-font, `[max]` ascii); the nerd-font preset uses an empty-to-full battery ramp for `minimal` through `xhigh` and shuffle while automatic effort is unresolved. `max` appears in cycling, selectors, `--thinking`, `:max` model suffixes, role scopes, settings, and completions on models that genuinely support it; on other models it clamps down like any unsupported tier.
+
 ### Changed
 
 - Renamed the bundled agent `explore` to `scout` (including all internal references, prompt definitions, and task tool configurations). Any custom configurations or task invocations referencing `explore` must now use `scout`.
-
+- Changed `max` from a parse-time alias of `xhigh` to a distinct level everywhere (CLI flag, `:max` suffix, `defaultThinkingLevel`, ACP/RPC): the effort a model receives is now exactly the tier its wire supports, with no shifted remapping. Ultrathink now requests `max` (clamped per model); automatic thinking still tops out at `xhigh`. Added `thinkingBudgets.max` (default 32768).
 - Fixed collapsed compacted session transcript rebuilds reattaching snapcompact archive image frames to the live TUI, avoiding large retained JSC heaps on resume and transcript refresh. ([#4979](https://github.com/can1357/oh-my-pi/issues/4979))
 
 ### Fixed
diff --git a/packages/coding-agent/src/config/model-registry.ts b/packages/coding-agent/src/config/model-registry.ts
index 82c4e0545..7fb1491b6 100644
--- a/packages/coding-agent/src/config/model-registry.ts
+++ b/packages/coding-agent/src/config/model-registry.ts
@@ -690,7 +690,7 @@ function normalizeSuppressedSelector(
 	const trimmed = selector.trim();
 	if (!trimmed) return trimmed;
 	const parsed = parseModelString(trimmed, {
-		allowMaxAlias: true,
+		allowMaxSuffix: true,
 		allowAutoAlias: true,
 		isLiteralModelId: (provider, id) => hasLiveModel?.(provider, id) === true,
 	});
diff --git a/packages/coding-agent/src/config/model-resolver.ts b/packages/coding-agent/src/config/model-resolver.ts
index f09310b51..32ed6116f 100644
--- a/packages/coding-agent/src/config/model-resolver.ts
+++ b/packages/coding-agent/src/config/model-resolver.ts
@@ -79,23 +79,24 @@ export interface ScopedModel {
 }
 
 interface ThinkingSuffixOptions {
-	allowMaxAlias?: boolean;
+	allowMaxSuffix?: boolean;
 	allowAutoAlias?: boolean;
 }
 
 interface ModelStringParseOptions extends ThinkingSuffixOptions {
 	isLiteralModelId?: (provider: string, id: string) => boolean;
 }
-// Alias-suffix recognition for the model-pattern parser: `:max` maps to xhigh
-// and `:auto` maps to the auto sentinel. Both are gated behind the alias flags
-// (and the literal-id / exact-match guards on the callers) so a real model id
-// ending in `:max` / `:auto` isn't silently reinterpreted as a thinking suffix.
-const MAX_THINKING_SUFFIX_OPTIONS: ThinkingSuffixOptions = { allowMaxAlias: true, allowAutoAlias: true };
+// Suffix recognition for the model-pattern parser: `:max` is a real thinking
+// level and `:auto` maps to the auto sentinel. Both are gated behind flags
+// (and the literal-id / exact-match guards on the callers) because real model
+// ids end in `:max` (e.g. `glm-4.7:max`) — an ungated split would silently
+// reinterpret them as a thinking suffix.
+const MAX_THINKING_SUFFIX_OPTIONS: ThinkingSuffixOptions = { allowMaxSuffix: true, allowAutoAlias: true };
 
 function parseThinkingSuffix(value: string, options?: ThinkingSuffixOptions): ConfiguredThinkingLevel | undefined {
 	const level = parseThinkingLevel(value);
+	if (level === ThinkingLevel.Max) return options?.allowMaxSuffix === true ? level : undefined;
 	if (level !== undefined) return level;
-	if (options?.allowMaxAlias === true && value === "max") return ThinkingLevel.XHigh;
 	if (options?.allowAutoAlias === true && value === AUTO_THINKING) return AUTO_THINKING;
 	return undefined;
 }
@@ -104,8 +105,9 @@ function parseThinkingSuffix(value: string, options?: ThinkingSuffixOptions): Co
  * Split a trailing `:<level>` thinking selector off a model pattern.
  *
  * `level` is set when the suffix parses as a concrete thinking level (or, when
- * the caller opts in via `allowMaxAlias`/`allowAutoAlias`, the `:max` / `:auto`
- * aliases); `base` then has the suffix stripped. Otherwise `base` is the input.
+ * the caller opts in via `allowMaxSuffix`/`allowAutoAlias`, the guarded `:max`
+ * level / `:auto` sentinel); `base` then has the suffix stripped. Otherwise
+ * `base` is the input.
  * `minColonIndex` requires the colon to appear strictly after that index —
  * role-alias callers pass `PREFIX_MODEL_ROLE.length` so the base is at least
  * as long as the `pi/` prefix.
@@ -183,7 +185,7 @@ export function parseModelString(
 	// Strip strict thinking level suffixes first (e.g. "claude-sonnet-4-6:high" -> id "claude-sonnet-4-6", thinkingLevel "high").
 	const strict = splitThinkingSuffix(id);
 	if (strict.level) return { provider, id: strict.base, thinkingLevel: strict.level };
-	// `max` is a provider-facing alias for xhigh, but real model IDs can end in
+	// `max` is a real thinking level, but real model IDs can also end in
 	// `:max`. Context-aware callers pass a literal lookup so those models win.
 	const maxAlias = splitThinkingSuffix(id, -1, options);
 	if (maxAlias.level) {
@@ -239,7 +241,7 @@ function getOpenRouterRouteSuffix(modelId: string): { baseId: string; suffix: st
 	}
 
 	const suffix = modelId.slice(colonIdx + 1).trim();
-	// `max` is a thinking-level alias (xhigh), never an OpenRouter route suffix, so
+	// `max` is a thinking-level suffix, never an OpenRouter route suffix, so
 	// `openrouter/<id>:max` falls through to the max-aware selector split instead of
 	// being cloned into a literal `<id>:max` model id with the reasoning level lost.
 	if (!suffix || parseThinkingSuffix(suffix, MAX_THINKING_SUFFIX_OPTIONS)) {
@@ -766,7 +768,7 @@ function parseModelPatternWithContext(
 
 	// No match - try stripping a valid thinking suffix and recursing.
 	// `max` is accepted only after the full pattern failed, so literal model IDs
-	// ending in `:max` keep winning over the alias.
+	// ending in `:max` keep winning over the thinking suffix.
 	const { base, level } = splitThinkingSuffix(pattern, -1, MAX_THINKING_SUFFIX_OPTIONS);
 	if (level) {
 		const result = parseModelPatternWithContext(base, availableModels, context, options);
diff --git a/packages/coding-agent/src/config/models-config-schema.ts b/packages/coding-agent/src/config/models-config-schema.ts
index 7d886bff5..1309ad8de 100644
--- a/packages/coding-agent/src/config/models-config-schema.ts
+++ b/packages/coding-agent/src/config/models-config-schema.ts
@@ -23,6 +23,7 @@ const ReasoningEffortMapSchema = type({
 	"medium?": "string",
 	"high?": "string",
 	"xhigh?": "string",
+	"max?": "string",
 });
 
 const OpenAICompatFields = {
@@ -74,13 +75,13 @@ const ApiSchema = type(
 	'"openai-completions" | "openai-responses" | "openai-codex-responses" | "azure-openai-responses" | "anthropic-messages" | "google-generative-ai" | "google-gemini-cli" | "google-vertex"',
 );
 
-const EffortSchema = type('"minimal" | "low" | "medium" | "high" | "xhigh"');
+const EffortSchema = type('"minimal" | "low" | "medium" | "high" | "xhigh" | "max"');
 
 const ThinkingControlModeSchema = type(
 	'"effort" | "budget" | "google-level" | "anthropic-adaptive" | "anthropic-budget-effort"',
 );
 
-const EFFORT_ORDER = ["minimal", "low", "medium", "high", "xhigh"] as const;
+const EFFORT_ORDER = ["minimal", "low", "medium", "high", "xhigh", "max"] as const;
 
 /**
  * Accepts the canonical `efforts` vocabulary plus the legacy
diff --git a/packages/coding-agent/src/config/settings-schema.ts b/packages/coding-agent/src/config/settings-schema.ts
index 5ee3269d1..81f4ef7dd 100644
--- a/packages/coding-agent/src/config/settings-schema.ts
+++ b/packages/coding-agent/src/config/settings-schema.ts
@@ -936,7 +936,7 @@ export const SETTINGS_SCHEMA = {
 	// Reasoning and prompts
 	defaultThinkingLevel: {
 		type: "enum",
-		values: [...THINKING_EFFORTS, AUTO_THINKING, "max"],
+		values: [...THINKING_EFFORTS, AUTO_THINKING],
 		default: "high",
 		ui: {
 			tab: "model",
@@ -4964,6 +4964,8 @@ export const SETTINGS_SCHEMA = {
 	"thinkingBudgets.high": { type: "number", default: 16384 },
 
 	"thinkingBudgets.xhigh": { type: "number", default: 32768 },
+
+	"thinkingBudgets.max": { type: "number", default: 32768 },
 } as const;
 
 // ═══════════════════════════════════════════════════════════════════════════
@@ -5180,6 +5182,7 @@ export interface ThinkingBudgetsSettings {
 	medium: number;
 	high: number;
 	xhigh: number;
+	max: number;
 }
 
 export interface SttSettings {
diff --git a/packages/coding-agent/src/modes/theme/defaults/dark-poimandres.json b/packages/coding-agent/src/modes/theme/defaults/dark-poimandres.json
index 69c56126c..80aa3e6cf 100644
--- a/packages/coding-agent/src/modes/theme/defaults/dark-poimandres.json
+++ b/packages/coding-agent/src/modes/theme/defaults/dark-poimandres.json
@@ -122,11 +122,12 @@
       "status.pending": "◌",
       "nav.cursor": "▸",
       "nav.selected": "▴",
-      "thinking.minimal": "◌",
-      "thinking.low": "◍",
-      "thinking.medium": "◎",
-      "thinking.high": "◉",
-      "thinking.xhigh": "●",
+      "thinking.minimal": "∘",
+      "thinking.low": "◌",
+      "thinking.medium": "◍",
+      "thinking.high": "◎",
+      "thinking.xhigh": "◉",
+      "thinking.max": "●",
       "icon.model": "◇",
       "icon.plan": "◈",
       "icon.goal": "⊙",
diff --git a/packages/coding-agent/src/modes/theme/defaults/light-poimandres.json b/packages/coding-agent/src/modes/theme/defaults/light-poimandres.json
index 8b00ca22e..a6da984a9 100644
--- a/packages/coding-agent/src/modes/theme/defaults/light-poimandres.json
+++ b/packages/coding-agent/src/modes/theme/defaults/light-poimandres.json
@@ -122,11 +122,12 @@
       "status.pending": "◌",
       "nav.cursor": "▸",
       "nav.selected": "▴",
-      "thinking.minimal": "◌",
-      "thinking.low": "◍",
-      "thinking.medium": "◎",
-      "thinking.high": "◉",
-      "thinking.xhigh": "●",
+      "thinking.minimal": "∘",
+      "thinking.low": "◌",
+      "thinking.medium": "◍",
+      "thinking.high": "◎",
+      "thinking.xhigh": "◉",
+      "thinking.max": "●",
       "icon.model": "◇",
       "icon.plan": "◈",
       "icon.goal": "⊙",
diff --git a/packages/coding-agent/src/modes/theme/theme-schema.json b/packages/coding-agent/src/modes/theme/theme-schema.json
index 3fd9972b4..8dd7eb41c 100644
--- a/packages/coding-agent/src/modes/theme/theme-schema.json
+++ b/packages/coding-agent/src/modes/theme/theme-schema.json
@@ -33,7 +33,7 @@
 		},
 		"colors": {
 			"type": "object",
-			"description": "Theme color definitions (all required)",
+			"description": "Theme color definitions (all required except thinkingMax)",
 			"required": [
 				"accent",
 				"border",
@@ -301,7 +301,11 @@
 				},
 				"thinkingXhigh": {
 					"$ref": "#/$defs/colorValue",
-					"description": "Thinking level border: xhigh (OpenAI codex-max only)"
+					"description": "Thinking level border: xhigh"
+				},
+				"thinkingMax": {
+					"$ref": "#/$defs/colorValue",
+					"description": "Thinking level border: max (optional; falls back to thinkingXhigh when omitted)"
 				},
 				"bashMode": {
 					"$ref": "#/$defs/colorValue",
diff --git a/packages/coding-agent/src/modes/theme/theme.ts b/packages/coding-agent/src/modes/theme/theme.ts
index 77140221b..ca0a6397f 100644
--- a/packages/coding-agent/src/modes/theme/theme.ts
+++ b/packages/coding-agent/src/modes/theme/theme.ts
@@ -142,6 +142,7 @@ export type SymbolKey =
 	| "thinking.medium"
 	| "thinking.high"
 	| "thinking.xhigh"
+	| "thinking.max"
 	| "thinking.autoPending"
 	// Checkboxes
 	| "checkbox.checked"
@@ -344,11 +345,12 @@ const UNICODE_SYMBOLS: SymbolMap = {
 	// Compaction divider
 	"icon.camera": "📷",
 	// Thinking levels
-	"thinking.minimal": "◔ min",
-	"thinking.low": "◑ low",
-	"thinking.medium": "◒ med",
-	"thinking.high": "◕ high",
-	"thinking.xhigh": "◉ xhigh",
+	"thinking.minimal": "○ min",
+	"thinking.low": "◔ low",
+	"thinking.medium": "◑ med",
+	"thinking.high": "◒ high",
+	"thinking.xhigh": "◕ xhigh",
+	"thinking.max": "◉ max",
 	"thinking.autoPending": "⟳",
 	// Checkboxes
 	"checkbox.checked": "☑",
@@ -639,19 +641,15 @@ const NERD_SYMBOLS: SymbolMap = {
 	"icon.mic": "\uf130",
 	// Compaction divider - fa-camera-retro
 	"icon.camera": "\uf083",
-	// Thinking Levels - emoji labels
-	// pick: 🤨 min | alt:  min  min
-	"thinking.minimal": "\u{F0E7} min",
-	// pick: 🤔 low | alt:  low  low
-	"thinking.low": "\u{F10C} low",
-	// pick: 🤓 med | alt:  med  med
-	"thinking.medium": "\u{F192} med",
-	// pick: 🤯 high | alt:  high  high
-	"thinking.high": "\u{F111} high",
-	// pick: 🧠 xhi | alt:  xhi  xhi
-	"thinking.xhigh": "\u{F06D} xhi",
-	// pick:  (fa-circle-o-notch) | alt: 󰂼 (nf-md-cached) ⟳
-	"thinking.autoPending": "\uf1ce",
+	// Thinking levels — empty-to-full battery ramp, then fire.
+	"thinking.minimal": "\u{F244} min",
+	"thinking.low": "\u{F243} low",
+	"thinking.medium": "\u{F242} med",
+	"thinking.high": "\u{F241} high",
+	"thinking.xhigh": "\u{F240} xhi",
+	"thinking.max": "\u{F06D} max",
+	// Auto mode uses shuffle until the model resolves its thinking level.
+	"thinking.autoPending": "\u{F074}",
 	// Checkboxes
 	// pick:  | alt:  
 	"checkbox.checked": "\uf14a",
@@ -868,6 +866,7 @@ const ASCII_SYMBOLS: SymbolMap = {
 	"thinking.medium": "[med]",
 	"thinking.high": "[high]",
 	"thinking.xhigh": "[xhi]",
+	"thinking.max": "[max]",
 	"thinking.autoPending": "[~]",
 	// Checkboxes
 	"checkbox.checked": "[x]",
@@ -1059,6 +1058,7 @@ const themeColorsSchema = type({
 	thinkingMedium: "string | number",
 	thinkingHigh: "string | number",
 	thinkingXhigh: "string | number",
+	"thinkingMax?": "string | number",
 	bashMode: "string | number",
 	pythonMode: "string | number",
 	statusLineBg: "string | number",
@@ -1163,6 +1163,7 @@ export type ThemeColor =
 	| "thinkingMedium"
 	| "thinkingHigh"
 	| "thinkingXhigh"
+	| "thinkingMax"
 	| "bashMode"
 	| "pythonMode"
 	| "statusLineSep"
@@ -1225,6 +1226,7 @@ const THEME_COLOR_RECORD = {
 	thinkingMedium: true,
 	thinkingHigh: true,
 	thinkingXhigh: true,
+	thinkingMax: true,
 	bashMode: true,
 	pythonMode: true,
 	statusLineSep: true,
@@ -1675,6 +1677,9 @@ export class Theme {
 				return (str: string) => this.fg("thinkingHigh", str);
 			case "xhigh":
 				return (str: string) => this.fg("thinkingXhigh", str);
+			case "max":
+				// thinkingMax is optional; themes without it resolve to the xhigh color.
+				return (str: string) => this.fg(this.#fgColors.thinkingMax ? "thinkingMax" : "thinkingXhigh", str);
 			default:
 				return (str: string) => this.fg("thinkingOff", str);
 		}
@@ -1861,6 +1866,7 @@ export class Theme {
 			medium: this.#symbols["thinking.medium"],
 			high: this.#symbols["thinking.high"],
 			xhigh: this.#symbols["thinking.xhigh"],
+			max: this.#symbols["thinking.max"],
 			autoPending: this.#symbols["thinking.autoPending"],
 		};
 	}
diff --git a/packages/coding-agent/src/sdk.ts b/packages/coding-agent/src/sdk.ts
index 16a066675..8afd72517 100644
--- a/packages/coding-agent/src/sdk.ts
+++ b/packages/coding-agent/src/sdk.ts
@@ -1309,7 +1309,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 			for (let i = 0; i < sessionModelStrings.length; i++) {
 				const sessionModelStr = sessionModelStrings[i];
 				const parsedModel = parseModelString(sessionModelStr, {
-					allowMaxAlias: true,
+					allowMaxSuffix: true,
 					allowAutoAlias: true,
 					isLiteralModelId: (provider, id) => modelRegistry.find(provider, id) !== undefined,
 				});
@@ -1953,7 +1953,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 			for (let i = 0; i < sessionRetryLimit; i++) {
 				const sessionModelStr = sessionModelStrings[i];
 				const parsedModel = parseModelString(sessionModelStr, {
-					allowMaxAlias: true,
+					allowMaxSuffix: true,
 					allowAutoAlias: true,
 					isLiteralModelId: (provider, id) => modelRegistry.find(provider, id) !== undefined,
 				});
diff --git a/packages/coding-agent/src/session/agent-session.ts b/packages/coding-agent/src/session/agent-session.ts
index a98f48521..e6702ad36 100644
--- a/packages/coding-agent/src/session/agent-session.ts
+++ b/packages/coding-agent/src/session/agent-session.ts
@@ -1081,7 +1081,7 @@ function parseRetryFallbackSelector(
 	const trimmed = selector.trim();
 	if (!trimmed) return undefined;
 	const parsed = parseModelString(trimmed, {
-		allowMaxAlias: true,
+		allowMaxSuffix: true,
 		allowAutoAlias: true,
 		isLiteralModelId: (provider, id) => modelLookup?.find(provider, id) !== undefined,
 	});
@@ -9260,7 +9260,7 @@ export class AgentSession {
 	}
 
 	/**
-	 * Cycle to next thinking level: off → auto → minimal..xhigh → off.
+	 * Cycle to next thinking level: off → auto → minimal..max → off.
 	 * @returns New selector, or undefined if model doesn't support thinking
 	 */
 	cycleThinkingLevel(): ConfiguredThinkingLevel | undefined {
@@ -9302,8 +9302,9 @@ export class AgentSession {
 		let resolved: Effort | undefined;
 		if (this.#magicKeywordEnabled("ultrathink") && containsUltrathink(promptText)) {
 			// The user explicitly asked for maximum thinking; bypass the classifier
-			// and jump straight to the highest auto-supported level for this model.
-			resolved = clampAutoThinkingEffort(model, Effort.XHigh);
+			// (and its xhigh auto ceiling) and jump straight to the highest
+			// supported level for this model.
+			resolved = clampAutoThinkingEffort(model, Effort.Max);
 		} else {
 			const controller = new AbortController();
 			const timer = setTimeout(() => controller.abort(), AgentSession.#AUTO_THINKING_TIMEOUT_MS);
@@ -11967,7 +11968,7 @@ export class AgentSession {
 		if (!trimmedTarget) return undefined;
 
 		const parsed = parseModelString(trimmedTarget, {
-			allowMaxAlias: true,
+			allowMaxSuffix: true,
 			allowAutoAlias: true,
 			isLiteralModelId: (provider, id) =>
 				availableModels.some(model => model.provider === provider && model.id === id),
diff --git a/packages/coding-agent/src/system-prompt.test.ts b/packages/coding-agent/src/system-prompt.test.ts
index 673085068..2f93dbbc4 100644
--- a/packages/coding-agent/src/system-prompt.test.ts
+++ b/packages/coding-agent/src/system-prompt.test.ts
@@ -123,29 +123,36 @@ describe.skipIf(process.platform !== "linux")("system prompt GPU probe", () => {
 	}, 15_000);
 
 	it("kills the GPU probe at the prep deadline", async () => {
-		const result = await runProbeScenario({ runs: 1, sleepSeconds: 7, holdStdoutOpen: true });
+		const result = await runProbeScenario({ runs: 1, sleepSeconds: 12, holdStdoutOpen: true });
 
 		expect(result.cached).toEqual({ gpu: null });
+		// Probe is SIGKILLed at ~4.5s and the drain wait is bounded, so in-child
+		// time sits near the deadline; waiting on the descendant would push it
+		// past the 12s sleep.
 		expect(result.elapsedMs).toBeLessThan(6500);
-		// Codex#3838: the child process MUST exit shortly after the deadline,
-		// not linger until a descendant holding stdout (sleep 7) exits on its own.
-		expect(result.childElapsedMs).toBeLessThan(6500);
-	}, 15_000);
+		// Codex#3838: the child process MUST exit shortly after the deadline, not
+		// linger until a descendant holding stdout (sleep 12) exits on its own.
+		// The bound over in-child time budgets bun spawn/startup on loaded runners
+		// while staying far below the descendant's 12s exit.
+		expect(result.childElapsedMs).toBeLessThan(9000);
+	}, 20_000);
 
 	it("does not wait on stdout held by a descendant after a successful probe", async () => {
-		const result = await runProbeScenario({ runs: 1, sleepSeconds: 3, descendantHoldsStdout: true });
+		const result = await runProbeScenario({ runs: 1, sleepSeconds: 8, descendantHoldsStdout: true });
 
 		expect(result.cached).toEqual({ gpu: null });
 		// Probe exits 0 immediately but leaves a backgrounded sleep holding the stdout
 		// pipe. The success path MUST bound the drain wait, not block until sleep exits.
 		expect(result.elapsedMs).toBeLessThan(2000);
-		expect(result.childElapsedMs).toBeLessThan(2000);
-	}, 15_000);
+		// Budgets bun spawn/startup overhead; blocking on the descendant would
+		// take at least the 8s sleep.
+		expect(result.childElapsedMs).toBeLessThan(5000);
+	}, 20_000);
 
 	it("keeps probe output captured before a descendant delays EOF", async () => {
 		const result = await runProbeScenario({
 			runs: 1,
-			sleepSeconds: 3,
+			sleepSeconds: 8,
 			descendantHoldsStdout: true,
 			validOutput: "00:02.0 VGA compatible controller: NVIDIA TestGPU",
 		});
@@ -154,8 +161,10 @@ describe.skipIf(process.platform !== "linux")("system prompt GPU probe", () => {
 		// Captured stdout MUST be cached, not discarded as if the probe failed.
 		expect(result.cached).toEqual({ gpu: "02.0 VGA compatible controller: NVIDIA TestGPU" });
 		expect(result.elapsedMs).toBeLessThan(2000);
-		expect(result.childElapsedMs).toBeLessThan(2000);
-	}, 15_000);
+		// Budgets bun spawn/startup overhead; blocking on the descendant would
+		// take at least the 8s sleep.
+		expect(result.childElapsedMs).toBeLessThan(5000);
+	}, 20_000);
 });
 
 describe.skipIf(process.platform !== "linux")("system prompt CPU model", () => {
diff --git a/packages/coding-agent/src/thinking.ts b/packages/coding-agent/src/thinking.ts
index 7a6e83a8b..0bf10760c 100644
--- a/packages/coding-agent/src/thinking.ts
+++ b/packages/coding-agent/src/thinking.ts
@@ -33,7 +33,12 @@ const THINKING_LEVEL_METADATA: Record<ThinkingLevel, ThinkingLevelMetadata> = {
 	[ThinkingLevel.XHigh]: {
 		value: ThinkingLevel.XHigh,
 		label: "xhigh",
-		description: "Maximum reasoning (~32k tokens)",
+		description: "Extended reasoning (~32k tokens)",
+	},
+	[ThinkingLevel.Max]: {
+		value: ThinkingLevel.Max,
+		label: "max",
+		description: "Maximum reasoning the model supports",
 	},
 };
 
@@ -43,7 +48,7 @@ const EFFORT_BY_SELECTOR: Readonly<Record<string, Effort>> = {
 	[Effort.Medium]: Effort.Medium,
 	[Effort.High]: Effort.High,
 	[Effort.XHigh]: Effort.XHigh,
-	max: Effort.XHigh,
+	[Effort.Max]: Effort.Max,
 };
 const THINKING_LEVEL_BY_SELECTOR: Readonly<Record<string, ThinkingLevel>> = {
 	[ThinkingLevel.Inherit]: ThinkingLevel.Inherit,
@@ -53,6 +58,7 @@ const THINKING_LEVEL_BY_SELECTOR: Readonly<Record<string, ThinkingLevel>> = {
 	[ThinkingLevel.Medium]: ThinkingLevel.Medium,
 	[ThinkingLevel.High]: ThinkingLevel.High,
 	[ThinkingLevel.XHigh]: ThinkingLevel.XHigh,
+	[ThinkingLevel.Max]: ThinkingLevel.Max,
 };
 
 function getOwnSelector<T>(selectors: Readonly<Record<string, T>>, value: string | null | undefined): T | undefined {
@@ -149,7 +155,6 @@ const AUTO_THINKING_METADATA: ConfiguredThinkingLevelMetadata = {
  */
 export function parseConfiguredThinkingLevel(value: string | null | undefined): ConfiguredThinkingLevel | undefined {
 	if (value === AUTO_THINKING) return AUTO_THINKING;
-	if (value === "max") return ThinkingLevel.XHigh;
 	return parseThinkingLevel(value);
 }
 
@@ -160,7 +165,7 @@ export function getConfiguredThinkingLevelMetadata(level: ConfiguredThinkingLeve
 
 /**
  * Thinking selectors accepted by the `--thinking` CLI flag, in display order:
- * `off`, every concrete effort (`minimal`..`xhigh`), then `auto`. Single source
+ * `off`, every concrete effort (`minimal`..`max`), then `auto`. Single source
  * for the flag's `options` list, shell completions, and the "invalid level"
  * warning so all three stay in sync.
  */
@@ -168,7 +173,7 @@ export const CLI_THINKING_LEVELS: readonly string[] = [ThinkingLevel.Off, ...THI
 
 /**
  * Parses a `--thinking` CLI value. Accepts every {@link parseConfiguredThinkingLevel}
- * selector (`off`, `auto`, `minimal`..`xhigh`, plus the `max` alias) but rejects
+ * selector (`off`, `auto`, `minimal`..`max`) but rejects
  * `inherit`: an explicit `inherit` on the command line would suppress the
  * settings/scoped-model fallback during startup resolution only to resolve back
  * to the provider default, which is never what the user means.
@@ -211,9 +216,13 @@ export function clampAutoThinkingEffort(model: Model | undefined, effort: Effort
 /**
  * The provisional concrete level shown while `auto` is configured but before a
  * turn has been classified. Prefers the model's `defaultLevel`, otherwise High,
- * clamped into the auto range. Returns `undefined` for non-reasoning models.
+ * clamped into the auto range. Auto never provisions {@link Effort.Max} (the
+ * classifier ceiling is XHigh; only an explicit user request reaches Max), so a
+ * `defaultLevel` of `max` is capped at XHigh before clamping. Returns
+ * `undefined` for non-reasoning models.
  */
 export function resolveProvisionalAutoLevel(model: Model | undefined): Effort | undefined {
 	if (!model?.reasoning) return undefined;
-	return clampAutoThinkingEffort(model, model.thinking?.defaultLevel ?? Effort.High);
+	const preferred = model.thinking?.defaultLevel ?? Effort.High;
+	return clampAutoThinkingEffort(model, preferred === Effort.Max ? Effort.XHigh : preferred);
 }
diff --git a/packages/coding-agent/test/agent-session-retry-fallback.test.ts b/packages/coding-agent/test/agent-session-retry-fallback.test.ts
index 345d42df3..25c8c6791 100644
--- a/packages/coding-agent/test/agent-session-retry-fallback.test.ts
+++ b/packages/coding-agent/test/agent-session-retry-fallback.test.ts
@@ -8,7 +8,7 @@ import { buildModel } from "@oh-my-pi/pi-catalog/build";
 import { writeModelCache } from "@oh-my-pi/pi-catalog/model-cache";
 import { getBundledModel } from "@oh-my-pi/pi-catalog/models";
 import { ModelRegistry } from "@oh-my-pi/pi-coding-agent/config/model-registry";
-import { parseModelPattern } from "@oh-my-pi/pi-coding-agent/config/model-resolver";
+import { parseModelPattern, parseModelString } from "@oh-my-pi/pi-coding-agent/config/model-resolver";
 import { Settings } from "@oh-my-pi/pi-coding-agent/config/settings";
 import type { ExtensionRunner } from "@oh-my-pi/pi-coding-agent/extensibility/extensions";
 import { AgentSession, type AgentSessionEvent } from "@oh-my-pi/pi-coding-agent/session/agent-session";
@@ -1602,6 +1602,12 @@ describe("AgentSession retry fallback", () => {
 		expect(modelRegistry.isSelectorSuppressed("openai/gpt-4o")).toBe(true);
 		expect(modelRegistry.isSelectorSuppressed("openai/gpt-4o:low")).toBe(true);
 
+		// `:max` is a real thinking level now, not an xhigh alias — the two parse
+		// to distinct selectors...
+		expect(parseModelString("openai/gpt-4o:max", { allowMaxSuffix: true })?.thinkingLevel).toBe(Effort.Max);
+		expect(parseModelString("openai/gpt-4o:xhigh")?.thinkingLevel).toBe(Effort.XHigh);
+		// ...but suppression normalizes every thinking suffix to the base selector,
+		// so suppressing either still covers both.
 		modelRegistry.suppressSelector("openai/gpt-4o:max", future);
 		expect(modelRegistry.isSelectorSuppressed("openai/gpt-4o:xhigh")).toBe(true);
 		expect(modelRegistry.isSelectorSuppressed("openai/gpt-4o:max")).toBe(true);
diff --git a/packages/coding-agent/test/agent-session-role-thinking.test.ts b/packages/coding-agent/test/agent-session-role-thinking.test.ts
index a489a02b6..910908325 100644
--- a/packages/coding-agent/test/agent-session-role-thinking.test.ts
+++ b/packages/coding-agent/test/agent-session-role-thinking.test.ts
@@ -147,14 +147,16 @@ describe("AgentSession role model thinking behavior", () => {
 		expect(toSlow?.thinkingLevel).toBe(Effort.High);
 		expect(session.thinkingLevel).toBe(Effort.High);
 
-		session.setThinkingLevel(Effort.Minimal);
-		expect(session.thinkingLevel).toBe(Effort.Minimal);
+		// `medium` is supported on both ladders (4-6 dropped `minimal`), so the
+		// selection survives the role switch unclamped.
+		session.setThinkingLevel(Effort.Medium);
+		expect(session.thinkingLevel).toBe(Effort.Medium);
 
 		const toDefault = await session.cycleRoleModels(["default", "slow"]);
 		expect(toDefault?.role).toBe("default");
 		expect(toDefault?.model.id).toBe(defaultModel.id);
-		expect(toDefault?.thinkingLevel).toBe(Effort.Minimal);
-		expect(session.thinkingLevel).toBe(Effort.Minimal);
+		expect(toDefault?.thinkingLevel).toBe(Effort.Medium);
+		expect(session.thinkingLevel).toBe(Effort.Medium);
 	});
 
 	it("applies slow role thinking even when plan shares the same model", async () => {
@@ -231,6 +233,36 @@ describe("AgentSession role model thinking behavior", () => {
 		expect(session.getAvailableThinkingLevels()).not.toContain("xhigh");
 	});
 
+	it("clamps max selections down to the ladder ceiling on models without a max tier", async () => {
+		// Budget-mode sonnet-4-5 tops out at xhigh; a max request must clamp down.
+		const model = getAnthropicModelOrThrow("claude-sonnet-4-5");
+		const agent = new Agent({
+			initialState: {
+				model,
+				systemPrompt: ["Test"],
+				tools: [],
+				messages: [],
+				thinkingLevel: undefined,
+			},
+		});
+		const authStorage = await AuthStorage.create(path.join(tempDir.path(), "testauth-max-clamp.db"));
+		authStorages.push(authStorage);
+		authStorage.setRuntimeApiKey("anthropic", "test-key");
+		const modelRegistry = new ModelRegistry(authStorage, path.join(tempDir.path(), "models-max-clamp.yml"));
+
+		sessionSettings = Settings.isolated();
+		session = new AgentSession({
+			agent,
+			sessionManager: SessionManager.inMemory(),
+			settings: sessionSettings,
+			modelRegistry,
+		});
+
+		session.setThinkingLevel(Effort.Max);
+		expect(session.thinkingLevel).toBe(Effort.XHigh);
+		expect(session.getAvailableThinkingLevels()).not.toContain("max");
+	});
+
 	it("cycles through off and auto before returning to effort levels", async () => {
 		const model = getAnthropicModelOrThrow("claude-sonnet-4-5");
 
@@ -267,6 +299,40 @@ describe("AgentSession role model thinking behavior", () => {
 		expect(session.thinkingLevel).toBe(Effort.Minimal);
 	});
 
+	it("cycles through max as the final tier on a max-capable model", async () => {
+		const model = getAnthropicModelOrThrow("claude-opus-4-7");
+		const agent = new Agent({
+			initialState: {
+				model,
+				systemPrompt: ["Test"],
+				tools: [],
+				messages: [],
+				thinkingLevel: Effort.XHigh,
+			},
+		});
+		const authStorage = await AuthStorage.create(path.join(tempDir.path(), "testauth-cycle-max.db"));
+		authStorages.push(authStorage);
+		authStorage.setRuntimeApiKey("anthropic", "test-key");
+		const modelRegistry = new ModelRegistry(authStorage, path.join(tempDir.path(), "models-cycle-max.yml"));
+
+		sessionSettings = Settings.isolated();
+		session = new AgentSession({
+			agent,
+			sessionManager: SessionManager.inMemory(),
+			settings: sessionSettings,
+			modelRegistry,
+		});
+
+		const available = session.getAvailableThinkingLevels();
+		expect(available.at(-1)).toBe(Effort.Max);
+
+		session.setThinkingLevel(Effort.XHigh);
+		expect(session.cycleThinkingLevel()).toBe(Effort.Max);
+		expect(session.thinkingLevel).toBe(Effort.Max);
+		// max is the last tier: the wheel wraps back to off.
+		expect(session.cycleThinkingLevel()).toBe("off");
+	});
+
 	it("keeps auto configured while applying the classifier result as the effective level", async () => {
 		const model = getAnthropicModelOrThrow("claude-sonnet-4-5");
 		await createSession({
@@ -472,7 +538,7 @@ describe("AgentSession role model thinking behavior", () => {
 		expect(session.autoResolvedThinkingLevel()).toBeUndefined();
 	});
 
-	it("maps ultrathink prompts directly to the highest auto-supported level", async () => {
+	it("maps ultrathink prompts to the model's highest supported level, clamped below max", async () => {
 		const model = getAnthropicModelOrThrow("claude-sonnet-4-5");
 		await createSession({
 			initialModelId: model.id,
@@ -483,7 +549,9 @@ describe("AgentSession role model thinking behavior", () => {
 		const classifierSpy = vi.spyOn(autoThinkingClassifier, "classifyDifficulty").mockResolvedValue(Effort.Low);
 
 		session.setThinkingLevel(AUTO_THINKING);
-		const expected = clampAutoThinkingEffort(model, Effort.XHigh);
+		// sonnet-4-5 has no max tier, so the ultrathink jump clamps to xhigh.
+		const expected = clampAutoThinkingEffort(model, Effort.Max);
+		expect(expected).toBe(Effort.XHigh);
 		await session.prompt("ultrathink through the unsafe refactor");
 
 		expect(classifierSpy).not.toHaveBeenCalled();
@@ -491,6 +559,24 @@ describe("AgentSession role model thinking behavior", () => {
 		expect(session.autoResolvedThinkingLevel()).toBe(expected);
 	});
 
+	it("resolves ultrathink to max on max-capable models", async () => {
+		const model = getAnthropicModelOrThrow("claude-opus-4-7");
+		await createSession({
+			initialModelId: model.id,
+			initialThinkingLevel: Effort.High,
+			modelRoles: { default: `${model.provider}/${model.id}` },
+		});
+		vi.spyOn(session.agent, "prompt").mockResolvedValue(undefined);
+		const classifierSpy = vi.spyOn(autoThinkingClassifier, "classifyDifficulty").mockResolvedValue(Effort.Low);
+
+		session.setThinkingLevel(AUTO_THINKING);
+		await session.prompt("ultrathink through the unsafe refactor");
+
+		expect(classifierSpy).not.toHaveBeenCalled();
+		expect(session.thinkingLevel).toBe(Effort.Max);
+		expect(session.autoResolvedThinkingLevel()).toBe(Effort.Max);
+	});
+
 	it("keeps auto effectively off for non-reasoning models", async () => {
 		const model = getBundledModel("openai", "gpt-4o-mini");
 		if (!model) throw new Error("Expected bundled gpt-4o-mini model");
diff --git a/packages/coding-agent/test/auto-thinking-classifier.test.ts b/packages/coding-agent/test/auto-thinking-classifier.test.ts
index 912b1e6d8..29f67b392 100644
--- a/packages/coding-agent/test/auto-thinking-classifier.test.ts
+++ b/packages/coding-agent/test/auto-thinking-classifier.test.ts
@@ -3,6 +3,7 @@ import * as path from "node:path";
 import { ThinkingLevel } from "@oh-my-pi/pi-agent-core";
 import * as ai from "@oh-my-pi/pi-ai";
 import { Effort, type Model } from "@oh-my-pi/pi-ai";
+import { buildModel } from "@oh-my-pi/pi-catalog/build";
 import { getBundledModel } from "@oh-my-pi/pi-catalog/models";
 import {
 	classifyDifficulty,
@@ -71,7 +72,7 @@ describe("auto thinking classifier helpers", () => {
 	it("parses CLI --thinking selectors while rejecting inherit", () => {
 		expect(parseCliThinkingLevel(ThinkingLevel.Off)).toBe(ThinkingLevel.Off);
 		expect(parseCliThinkingLevel(AUTO_THINKING)).toBe(AUTO_THINKING);
-		expect(parseCliThinkingLevel("max")).toBe(ThinkingLevel.XHigh);
+		expect(parseCliThinkingLevel("max")).toBe(ThinkingLevel.Max);
 		expect(parseCliThinkingLevel(ThinkingLevel.Inherit)).toBeUndefined();
 		expect(parseCliThinkingLevel("bogus")).toBeUndefined();
 	});
@@ -182,6 +183,24 @@ describe("auto thinking classifier helpers", () => {
 		expect(clampAutoThinkingEffort(model, Effort.Minimal)).toBe(Effort.Low);
 	});
 
+	it("clamps max down to the ladder ceiling on models without a max tier", () => {
+		const xhighCeilingModel = buildModel({
+			id: "mock-xhigh-ceiling",
+			name: "Mock XHigh Ceiling",
+			api: "openai-completions",
+			provider: "mock",
+			baseUrl: "https://example.com",
+			reasoning: true,
+			thinking: { mode: "effort", efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh] },
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 128_000,
+			maxTokens: 4096,
+		});
+
+		expect(clampAutoThinkingEffort(xhighCeilingModel, Effort.Max)).toBe(Effort.XHigh);
+	});
+
 	it("returns undefined for reasoning models without controllable efforts (devin-agent shape)", () => {
 		// Repro for https://github.com/can1357/oh-my-pi/issues/3356 — Devin
 		// models report `reasoning: true` but expose no `thinking.efforts` (Cascade
@@ -202,13 +221,14 @@ describe("auto thinking classifier helpers", () => {
 
 		expect(clampAutoThinkingEffort(devinModel, Effort.Low)).toBeUndefined();
 		expect(clampAutoThinkingEffort(devinModel, Effort.XHigh)).toBeUndefined();
+		expect(clampAutoThinkingEffort(devinModel, Effort.Max)).toBeUndefined();
 		expect(resolveProvisionalAutoLevel(devinModel)).toBeUndefined();
 	});
 
-	it("accepts max as the top configured thinking alias", () => {
-		expect(parseEffort("max")).toBe(Effort.XHigh);
-		expect(parseThinkingLevel("max")).toBeUndefined();
-		expect(parseConfiguredThinkingLevel("max")).toBe(ThinkingLevel.XHigh);
+	it("parses max as a real thinking level", () => {
+		expect(parseEffort("max")).toBe(Effort.Max);
+		expect(parseThinkingLevel("max")).toBe(ThinkingLevel.Max);
+		expect(parseConfiguredThinkingLevel("max")).toBe(ThinkingLevel.Max);
 	});
 
 	it("rejects inherited object keys as thinking selectors", () => {
diff --git a/packages/coding-agent/test/cli-hide-thinking-flag.test.ts b/packages/coding-agent/test/cli-hide-thinking-flag.test.ts
index 40c4d548b..807acd653 100644
--- a/packages/coding-agent/test/cli-hide-thinking-flag.test.ts
+++ b/packages/coding-agent/test/cli-hide-thinking-flag.test.ts
@@ -52,10 +52,10 @@ describe("parseArgs — --thinking flag", () => {
 		expect(parseArgs(["--thinking=off"]).thinking).toBe(ThinkingLevel.Off);
 	});
 
-	it("accepts auto, concrete efforts, and the max alias", () => {
+	it("accepts auto and every concrete effort including max", () => {
 		expect(parseArgs(["--thinking", "auto"]).thinking).toBe(AUTO_THINKING);
 		expect(parseArgs(["--thinking", "medium"]).thinking).toBe(Effort.Medium);
-		expect(parseArgs(["--thinking", "max"]).thinking).toBe(ThinkingLevel.XHigh);
+		expect(parseArgs(["--thinking", "max"]).thinking).toBe(ThinkingLevel.Max);
 	});
 
 	it("ignores invalid levels and the internal inherit selector", () => {
diff --git a/packages/coding-agent/test/cli/completions.test.ts b/packages/coding-agent/test/cli/completions.test.ts
index 4da7f19ef..3dd8dd9a6 100644
--- a/packages/coding-agent/test/cli/completions.test.ts
+++ b/packages/coding-agent/test/cli/completions.test.ts
@@ -211,7 +211,7 @@ describe("omp completions (integration / drift)", () => {
 		}
 		expect(stdout).toContain("{-r,--resume}");
 		// Real enum option sets flow through unchanged.
-		expect(stdout).toContain(":value:(off minimal low medium high xhigh auto)");
+		expect(stdout).toContain(":value:(off minimal low medium high xhigh max auto)");
 		expect(stdout).toContain(":value:(always-ask write yolo)");
 		// Real subcommands present; dynamic callbacks wired.
 		expect(stdout).toContain("_omp_cmd_commit");
diff --git a/packages/coding-agent/test/model-resolver.test.ts b/packages/coding-agent/test/model-resolver.test.ts
index e3e36fd96..4e2e5d4fc 100644
--- a/packages/coding-agent/test/model-resolver.test.ts
+++ b/packages/coding-agent/test/model-resolver.test.ts
@@ -219,6 +219,25 @@ const mockCodexOverlapModels: Model<"anthropic-messages">[] = [
 	}),
 ];
 
+const mockMaxCapableModels: Model<"anthropic-messages">[] = [
+	buildModel({
+		id: "claude-opus-4-7",
+		name: "Claude Opus 4.7",
+		api: "anthropic-messages",
+		provider: "anthropic",
+		baseUrl: "https://api.anthropic.com",
+		reasoning: true,
+		thinking: {
+			mode: "anthropic-adaptive",
+			efforts: [Effort.Low, Effort.Medium, Effort.High, Effort.XHigh, Effort.Max],
+		},
+		input: ["text", "image"],
+		cost: { input: 15, output: 75, cacheRead: 1.5, cacheWrite: 18.75 },
+		contextWindow: 200000,
+		maxTokens: 32000,
+	}),
+];
+
 const openaiGpt55Models: Model<Api>[] = [
 	buildModel({
 		id: "gpt-5.5",
@@ -410,7 +429,15 @@ describe("parseModelPattern", () => {
 		});
 
 		test("all valid thinking levels work", () => {
-			const levels = ["off", Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh] as const;
+			const levels = [
+				"off",
+				Effort.Minimal,
+				Effort.Low,
+				Effort.Medium,
+				Effort.High,
+				Effort.XHigh,
+				Effort.Max,
+			] as const;
 			for (const level of levels) {
 				const result = parseModelPattern(`sonnet:${level}`, allModels);
 				expect(result.model?.id).toBe("claude-sonnet-4-5");
@@ -418,15 +445,15 @@ describe("parseModelPattern", () => {
 				expect(result.warning).toBeUndefined();
 			}
 		});
-		test("max aliases the highest thinking level after the literal pattern misses", () => {
+		test("max parses as a real thinking level after the literal pattern misses", () => {
 			const result = parseModelPattern("gpt-5.3-codex:max", allModels);
 			expect(result.model?.id).toBe("gpt-5.3-codex");
-			expect(result.thinkingLevel).toBe(Effort.XHigh);
+			expect(result.thinkingLevel).toBe(Effort.Max);
 			expect(result.explicitThinkingLevel).toBe(true);
 			expect(result.warning).toBeUndefined();
 		});
 
-		test("literal model ids ending in max win over the thinking alias", () => {
+		test("literal model ids ending in max win over the thinking suffix", () => {
 			const result = parseModelPattern("nanogpt/coding-router:max", mockMaxSuffixModels);
 			expect(result.model?.id).toBe("coding-router:max");
 			expect(result.thinkingLevel).toBeUndefined();
@@ -523,13 +550,13 @@ describe("parseModelPattern", () => {
 			expect(result.warning).toBeUndefined();
 		});
 
-		test("openrouter/<id>:max applies xhigh through the exact-selector path, not an OpenRouter route", () => {
-			// `max` is a thinking alias, never an OpenRouter route suffix: the request must
-			// resolve the base model and carry xhigh, not clone a literal `z-ai/glm-4.7:max`.
+		test("openrouter/<id>:max applies max through the exact-selector path, not an OpenRouter route", () => {
+			// `max` is a thinking-level suffix, never an OpenRouter route suffix: the request
+			// must resolve the base model and carry max, not clone a literal `z-ai/glm-4.7:max`.
 			const result = parseModelPattern("openrouter/z-ai/glm-4.7:max", allModels);
 			expect(result.model?.provider).toBe("openrouter");
 			expect(result.model?.id).toBe("z-ai/glm-4.7");
-			expect(result.thinkingLevel).toBe(Effort.XHigh);
+			expect(result.thinkingLevel).toBe(Effort.Max);
 			expect(result.explicitThinkingLevel).toBe(true);
 		});
 	});
@@ -618,6 +645,7 @@ describe("resolveModelRoleValue", () => {
 
 		expect(result.model?.provider).toBe("openai-codex");
 		expect(result.model?.id).toBe("gpt-5.3-codex");
+		// Role-value resolution clamps: gpt-5.3-codex's ladder tops out at xhigh.
 		expect(result.thinkingLevel).toBe(Effort.XHigh);
 		expect(result.explicitThinkingLevel).toBe(true);
 	});
@@ -679,6 +707,15 @@ describe("resolveModelRoleValue", () => {
 		expect(result.explicitThinkingLevel).toBe(true);
 	});
 
+	test("passes max through unclamped when the model ladder includes it", () => {
+		const result = resolveModelRoleValue("anthropic/claude-opus-4-7:max", mockMaxCapableModels);
+
+		expect(result.model?.provider).toBe("anthropic");
+		expect(result.model?.id).toBe("claude-opus-4-7");
+		expect(result.thinkingLevel).toBe(Effort.Max);
+		expect(result.explicitThinkingLevel).toBe(true);
+	});
+
 	test("preserves an explicit :auto suffix as an explicit thinking selector", () => {
 		const result = resolveModelRoleValue("anthropic/claude-sonnet-4-5:auto", allModels);
 
@@ -1071,7 +1108,7 @@ describe("resolveModelScope", () => {
 		expect(scoped[0].model.id).toBe("gpt-5.5");
 	});
 
-	test("applies max thinking aliases to glob scopes when no literal max ids match", async () => {
+	test("applies max thinking selectors to glob scopes when no literal max ids match", async () => {
 		const registry = {
 			getAvailable: () => mockCodexOverlapModels,
 		};
@@ -1079,10 +1116,23 @@ describe("resolveModelScope", () => {
 		const scoped = await resolveModelScope(["openai-codex/*:max"], registry);
 
 		expect(scoped).toHaveLength(2);
+		// Scoped levels clamp per model: max on an xhigh-ceiling ladder resolves to xhigh.
 		expect(scoped.map(entry => entry.thinkingLevel)).toEqual([Effort.XHigh, Effort.XHigh]);
 		expect(scoped.every(entry => entry.explicitThinkingLevel)).toBe(true);
 	});
 
+	test("keeps max on glob scopes when the model ladder includes it", async () => {
+		const registry = {
+			getAvailable: () => mockMaxCapableModels,
+		};
+
+		const scoped = await resolveModelScope(["anthropic/*:max"], registry);
+
+		expect(scoped).toHaveLength(1);
+		expect(scoped[0].thinkingLevel).toBe(Effort.Max);
+		expect(scoped[0].explicitThinkingLevel).toBe(true);
+	});
+
 	test("preserves literal :max in scoped-model globs", async () => {
 		const registry = {
 			getAvailable: () => mockMaxSuffixModels,
@@ -1144,18 +1194,25 @@ describe("parseModelString", () => {
 		});
 
 		test("extracts max when explicitly enabled for provider id selectors", () => {
-			const result = parseModelString("deepseek/deepseek-v4-pro:max", { allowMaxAlias: true });
-			expect(result).toEqual({ provider: "deepseek", id: "deepseek-v4-pro", thinkingLevel: Effort.XHigh });
+			const result = parseModelString("deepseek/deepseek-v4-pro:max", { allowMaxSuffix: true });
+			expect(result).toEqual({ provider: "deepseek", id: "deepseek-v4-pro", thinkingLevel: Effort.Max });
 		});
 
 		test("preserves literal max model ids when the caller can prove they exist", () => {
 			const result = parseModelString("nanogpt/coding-router:max", {
-				allowMaxAlias: true,
+				allowMaxSuffix: true,
 				isLiteralModelId: (provider, id) => provider === "nanogpt" && id === "coding-router:max",
 			});
 			expect(result).toEqual({ provider: "nanogpt", id: "coding-router:max" });
 		});
 
+		test("leaves :max attached to the model id unless the caller opts in via allowMaxSuffix", () => {
+			// Without allowMaxSuffix, the strict suffix parser must not silently
+			// reinterpret a literal `:max` id as a thinking suffix.
+			const result = parseModelString("anthropic/claude-sonnet-4-5:max");
+			expect(result).toEqual({ provider: "anthropic", id: "claude-sonnet-4-5:max" });
+		});
+
 		test("leaves :auto attached to the model id unless the caller opts in via allowAutoAlias", () => {
 			// Without allowAutoAlias, the strict suffix parser must not silently
 			// reinterpret a literal `:auto` id as an auto-thinking selector.
@@ -1242,7 +1299,7 @@ describe("extractExplicitThinkingSelector", () => {
 		const result = extractExplicitThinkingSelector("nanogpt/coding-router:max", undefined, {
 			isLiteralModelId: () => false,
 		});
-		expect(result).toBe(Effort.XHigh);
+		expect(result).toBe(Effort.Max);
 	});
 
 	test("treats max on pi role aliases as an explicit selector before expansion", () => {
@@ -1251,7 +1308,7 @@ describe("extractExplicitThinkingSelector", () => {
 		const result = extractExplicitThinkingSelector("pi/smol:max", settings, {
 			isLiteralModelId: (provider, id) => provider === "nanogpt" && id === "coding-router:max",
 		});
-		expect(result).toBe(Effort.XHigh);
+		expect(result).toBe(Effort.Max);
 	});
 
 	test("does not carry auto from literal role model ids", () => {
diff --git a/packages/coding-agent/test/model-selector-role-badge-thinking.test.ts b/packages/coding-agent/test/model-selector-role-badge-thinking.test.ts
index 50db05d61..0b9da2aec 100644
--- a/packages/coding-agent/test/model-selector-role-badge-thinking.test.ts
+++ b/packages/coding-agent/test/model-selector-role-badge-thinking.test.ts
@@ -171,7 +171,7 @@ describe("ModelSelector role badge thinking display", () => {
 		expect(menuRendered).toContain("Set as SMOL (Quick)");
 	});
 
-	test("renders xhigh effort for OpenAI GPT-5.5 thinking options", async () => {
+	test("renders the xhigh-ceiling ladder without a speculative max tier (GPT-5.5)", async () => {
 		installTestTheme();
 		const model = getBundledModel("openai", "gpt-5.5");
 		if (!model) throw new Error("Expected bundled model openai/gpt-5.5");
@@ -186,7 +186,25 @@ describe("ModelSelector role badge thinking display", () => {
 		const rendered = normalizeRenderedText(selector.render(220).join("\n"));
 		expect(rendered).toContain("Thinking for: Default (gpt-5.5)");
 		expect(rendered).toContain("low medium high xhigh");
-		expect(rendered).not.toContain("low medium high max");
+		// gpt-5.5's wire has no max tier; the selector must not invent one.
+		expect(rendered).not.toContain("max");
+	});
+
+	test("renders max as a real final tier on max-capable models (GPT-5.6)", async () => {
+		installTestTheme();
+		const model = getBundledModel("openai", "gpt-5.6");
+		if (!model) throw new Error("Expected bundled model openai/gpt-5.6");
+
+		const selector = createSelector(model, Settings.isolated({}));
+		await Bun.sleep(0);
+		installTestTheme();
+
+		selector.handleInput("\n");
+		selector.handleInput("\n");
+
+		const rendered = normalizeRenderedText(selector.render(220).join("\n"));
+		expect(rendered).toContain("Thinking for: Default (gpt-5.6)");
+		expect(rendered).toContain("low medium high xhigh max");
 	});
 
 	test("reloads DEFAULT(auto) from defaultThinkingLevel", async () => {
diff --git a/packages/coding-agent/test/sdk-model-selection.test.ts b/packages/coding-agent/test/sdk-model-selection.test.ts
index ab3c0396c..e2706d95e 100644
--- a/packages/coding-agent/test/sdk-model-selection.test.ts
+++ b/packages/coding-agent/test/sdk-model-selection.test.ts
@@ -277,7 +277,7 @@ describe("createAgentSession deferred model pattern resolution", () => {
 		expect(session.thinkingLevel).toBe("off");
 	});
 
-	test("normalizes max default thinking level from settings", async () => {
+	test("clamps a max default thinking level to the model's ladder ceiling", async () => {
 		const settings = Settings.isolated({ defaultThinkingLevel: "max" });
 
 		const { session } = await createAgentSession({
@@ -287,6 +287,8 @@ describe("createAgentSession deferred model pattern resolution", () => {
 
 		expect(session.model?.provider).toBe("runtime-provider");
 		expect(session.model?.id).toBe("runtime-reasoning-model");
+		// The extension model has no explicit ladder; the inferred fallback tops
+		// out at xhigh, so the real max level clamps down.
 		expect(session.thinkingLevel).toBe(Effort.XHigh);
 	});
 
diff --git a/packages/terminal-bench/README.md b/packages/terminal-bench/README.md
index 1c5786942..4dd12f551 100644
--- a/packages/terminal-bench/README.md
+++ b/packages/terminal-bench/README.md
@@ -65,7 +65,7 @@ bun src/runner.ts [options] [-- <extra harbor args>]
 | `-n, --concurrency <N>` | `4` | Concurrent trials |
 | `-k, --attempts <N>` | `1` | Attempts per task (pass@k) |
 | `-i/-x, --include/--exclude <glob>` | — | Task filters (repeatable) |
-| `--thinking <level>` | — | `off…xhigh` |
+| `--thinking <level>` | — | `off…max` |
 | `--advisor-model <p/m>` | — | Second model reviewing the primary; spend summed in |
 | `--agent <name>` | `omp` | `oracle`/`nop`/any harbor agent (bypasses omp) |
 | `--install <local\|published>` | `local` | `published` = npm `@oh-my-pi/pi-coding-agent` |
diff --git a/packages/terminal-bench/src/runner.ts b/packages/terminal-bench/src/runner.ts
index 33b24c52e..2aa0ee02c 100755
--- a/packages/terminal-bench/src/runner.ts
+++ b/packages/terminal-bench/src/runner.ts
@@ -113,7 +113,7 @@ Model / agent:
       --agent <name>             omp (default) | oracle | nop | any harbor agent
       --install <local|published> omp source. local = pack /work/pi (default)
       --version <v>              omp version for published install (default: latest)
-      --thinking <level>         off|minimal|low|medium|high|xhigh
+      --thinking <level>         off|minimal|low|medium|high|xhigh|max
       --advisor-model <p/m>      Second model reviewing the primary (spend summed in)
       --advisor-sync <off|1|3|5> Advisor catch-up backlog (default 1 = accurate spend; off = faster)
       --tarball <path>           Reuse a prebuilt omp tarball (implies --no-build)
diff --git a/packages/typescript-edit-benchmark/src/index.ts b/packages/typescript-edit-benchmark/src/index.ts
index fcb0035da..aebfa8e0a 100755
--- a/packages/typescript-edit-benchmark/src/index.ts
+++ b/packages/typescript-edit-benchmark/src/index.ts
@@ -116,7 +116,7 @@ Usage:
 Options:
   --model <id>              Provider/model ID, e.g. anthropic/claude-sonnet-4-20250514 (default)
   --provider <id>           Override provider (auto-detected from model prefix if omitted)
-  --thinking <level>        Thinking level: off, minimal, low, medium, high, xhigh
+  --thinking <level>        Thinking level: off, minimal, low, medium, high, xhigh, max
   --runs <n>                Runs per task (default: 1)
   --timeout <ms>            Timeout per run in ms (default: 120000)
   --connection-timeout <ms>  Timeout for first event before fast-retry (default: 30000)
diff --git a/python/omp-rpc/src/omp_rpc/protocol.py b/python/omp-rpc/src/omp_rpc/protocol.py
index a761e4d34..ccd94cee7 100644
--- a/python/omp-rpc/src/omp_rpc/protocol.py
+++ b/python/omp-rpc/src/omp_rpc/protocol.py
@@ -11,8 +11,10 @@ JsonValue: TypeAlias = JsonPrimitive | list["JsonValue"] | dict[str, "JsonValue"
 JsonObject: TypeAlias = dict[str, JsonValue]
 
 Attribution: TypeAlias = Literal["user", "agent"]
-Effort: TypeAlias = Literal["minimal", "low", "medium", "high", "xhigh"]
-ThinkingLevel: TypeAlias = Literal["off", "minimal", "low", "medium", "high", "xhigh"]
+Effort: TypeAlias = Literal["minimal", "low", "medium", "high", "xhigh", "max"]
+ThinkingLevel: TypeAlias = Literal[
+    "off", "minimal", "low", "medium", "high", "xhigh", "max"
+]
 StreamingBehavior: TypeAlias = Literal["steer", "followUp"]
 SteeringMode: TypeAlias = Literal["all", "one-at-a-time"]
 InterruptMode: TypeAlias = Literal["immediate", "wait"]
@@ -50,7 +52,7 @@ VALUE_EXTENSION_UI_METHODS: Final[frozenset[ValueExtensionUiMethod]] = frozenset
     {"select", "input", "editor"}
 )
 _EFFORT_VALUES: Final[frozenset[str]] = frozenset(
-    {"minimal", "low", "medium", "high", "xhigh"}
+    {"minimal", "low", "medium", "high", "xhigh", "max"}
 )
 _THINKING_LEVEL_VALUES: Final[frozenset[str]] = _EFFORT_VALUES | frozenset({"off"})
 _STEERING_MODE_VALUES: Final[frozenset[str]] = frozenset({"all", "one-at-a-time"})
diff --git a/python/omp-rpc/uv.lock b/python/omp-rpc/uv.lock
new file mode 100644
index 000000000..3966be0f4
--- /dev/null
+++ b/python/omp-rpc/uv.lock
@@ -0,0 +1,8 @@
+version = 1
+revision = 3
+requires-python = ">=3.11"
+
+[[package]]
+name = "omp-rpc"
+version = "0.1.0"
+source = { editable = "." }
diff --git a/python/robomp/src/config.py b/python/robomp/src/config.py
index 6b645f90c..af6abc285 100644
--- a/python/robomp/src/config.py
+++ b/python/robomp/src/config.py
@@ -10,7 +10,7 @@ from typing import Literal
 from pydantic import Field, SecretStr, field_validator, model_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
-ThinkingLevel = Literal["off", "low", "medium", "high", "xhigh"]
+ThinkingLevel = Literal["off", "low", "medium", "high", "xhigh", "max"]
 
 
 class Settings(BaseSettings):
diff --git a/python/robomp/src/pragmas.py b/python/robomp/src/pragmas.py
index 1f5a9cd92..4f4114aa7 100644
--- a/python/robomp/src/pragmas.py
+++ b/python/robomp/src/pragmas.py
@@ -33,7 +33,7 @@ Supported keys (today):
   contains `<alias>` (case-insensitive). Falls back to the normal random
   pool selection if no member matches.
 - `/thinking <level>` — override `ROBOMP_THINKING` for this run. Accepts
-  `off|none|no`, `lo|low`, `med|medium`, `hi|high`, `xhi|xhigh`
+  `off|none|no`, `lo|low`, `med|medium`, `hi|high`, `xhi|xhigh`, `max`
   (case-insensitive); anything else is ignored.
 
 Parser semantics:
@@ -49,7 +49,7 @@ from __future__ import annotations
 import re
 from typing import Literal
 
-ThinkingLevel = Literal["off", "low", "medium", "high", "xhigh"]
+ThinkingLevel = Literal["off", "low", "medium", "high", "xhigh", "max"]
 
 # Key = ascii lowercase / digit / dash / underscore, must start with a letter.
 # The value (when using `/key=value` form) runs to end-of-token.
@@ -164,6 +164,7 @@ _THINKING_ALIASES: dict[str, ThinkingLevel] = {
     "high": "high",
     "xhi": "xhigh",
     "xhigh": "xhigh",
+    "max": "max",
 }
 
 
diff --git a/scripts/edit_benchmark_common.py b/scripts/edit_benchmark_common.py
index 2b7c37859..3280fc1a8 100644
--- a/scripts/edit_benchmark_common.py
+++ b/scripts/edit_benchmark_common.py
@@ -654,7 +654,7 @@ def install_verbose_logging(
         with _PRINT_LOCK:
             sys.stderr.write(
                 f"[{model.removeprefix('openrouter/')}] verbose> "
-                "no thinking level requested; pass --thinking low|medium|high|xhigh if the provider exposes reasoning.\n"
+                "no thinking level requested; pass --thinking low|medium|high|xhigh|max if the provider exposes reasoning.\n"
             )
             sys.stderr.flush()
 
@@ -914,7 +914,7 @@ def parse_args(description: str) -> argparse.Namespace:
     )
     parser.add_argument(
         "--thinking",
-        choices=["off", "minimal", "low", "medium", "high", "xhigh"],
+        choices=["off", "minimal", "low", "medium", "high", "xhigh", "max"],
         default="medium",
         help="Request a specific thinking level for models that support reasoning (default: medium).",
     )