feat(providers): add Fable 5 support across Anthropic providers (zoo …

ai_plans/2026-06-17_zoo-555-add-fable-5-support-across-anthropic-providers.md

@@ -0,0 +1,148 @@
+# Port plan — Zoo PR #555 → `feature/zoo-555-add-fable-5-support-across-anthropic-providers`
+
+> **For the executor (read first).** Do the steps in order. Do not improvise or
+> refactor beyond what is written (YAGNI). Every code block is already adapted to
+> this repo. This repo is **Tumble Code**: never introduce the strings "Roo" or
+> "Zoo" in user-facing text. The model id `claude-fable-5` is an **internal model
+> id**, not branding — keep it verbatim.
+
+---
+
+## 0. Context
+
+- **Upstream:** Zoo PR #555 — "Add Fable 5 support across Anthropic providers" (commit `cc2654521`).
+- **What it does:** Registers the `claude-fable-5` model across every Anthropic-family
+  provider path — direct Anthropic, Bedrock, Vertex, OpenRouter, Requesty, and the
+  Vercel AI Gateway — including model metadata, the adaptive-thinking guard, and the
+  `supportsTemperature: false` plumbing so temperature is omitted for this model.
+- **Model facts (mirror upstream, reviewed in PR #555):** context window `1_000_000`;
+  direct Anthropic `maxTokens` `128_000` (overridden to 8k when reasoning effort is
+  off); Bedrock/Vertex `maxTokens` `8192`; prices in=$10 / out=$50 / cacheWrite=$12.5 /
+  cacheRead=$1 per M; `supportsImages`, `supportsPromptCache`, `supportsReasoningBudget`,
+  `supportsReasoningBinary` all true; `supportsTemperature: false`. Uses the same
+  adaptive-thinking contract as Opus 4.7/4.8.
+- **Why we want it:** new top-tier Claude model; our providers have no `claude-fable-5`
+  entry yet (verified: `grep claude-fable-5` empty across `packages/types/src/providers/*`
+  and `src/api/providers/*`). Low risk, high value — matches our model-support cadence.
+- **Adaptations vs. the raw upstream diff (IMPORTANT):**
+  1. **Branding:** upstream edits a bedrock comment to say "Zoo Code UI"; our fork already
+     reads `// display: "summarized" surfaces thinking content in the UI.`
+     ([bedrock.ts:439](../src/api/providers/bedrock.ts#L439)). Keep "the UI" — do NOT
+     introduce "Zoo Code". The Fable-5 mentions in the doc comment are optional polish.
+  2. **model-params.ts:** upstream adds the `supportsTemperature === false` guard to the
+     generic **`else`** branch. Our `format === "anthropic"` branch already has that guard
+     ([model-params.ts:151](../src/api/transform/model-params.ts#L151)); the `else` branch
+     (our lines 179-187) does NOT. Apply the guard to the `else` branch only.
+  3. Dependencies `getAnthropicProviderReasoning` / `AnthropicProviderReasoningParams`
+     already exist in [reasoning.ts:61](../src/api/transform/reasoning.ts#L61) — the
+     requesty refactor applies cleanly.
+- **Original authors — credit them:**
+
+  ```text
+  Co-authored-by: T <taltas@users.noreply.github.com>
+  Co-authored-by: Elliott de Launay <edelauna@gmail.com>
+  ```
+
+## 1. Preconditions
+
+- [ ] Branch `feature/zoo-555-...` created off `main`.
+- [ ] No `claude-fable-5` entry exists yet in any provider type/handler.
+- [ ] `getAnthropicProviderReasoning` exported from `src/api/transform/reasoning.ts`.
+
+## 2. Source edits
+
+### Edit A — `packages/types/src/providers/anthropic.ts`
+Insert a `"claude-fable-5"` entry into `anthropicModels` (before `claude-opus-4-5-20251101`):
+maxTokens 128_000, contextWindow 1_000_000, images/cache true, in 10 / out 50 /
+cacheWrite 12.5 / cacheRead 1, supportsReasoningBudget/Binary true, supportsTemperature
+false, with the upstream description.
+
+### Edit B — `packages/types/src/providers/bedrock.ts`
+- Add `"anthropic.claude-fable-5"` to `bedrockModels` (maxTokens 8192, contextWindow 1M,
+  cache true + `minTokensPerCachePoint`/`maxCachePoints`/`cachableFields`, same prices,
+  reasoning flags, supportsTemperature false, description).
+- Append `"anthropic.claude-fable-5"` to `BEDROCK_GLOBAL_INFERENCE_MODEL_IDS` with the
+  cross-region comment line.
+
+### Edit C — `packages/types/src/providers/vertex.ts`
+Add `"claude-fable-5"` to `vertexModels` (maxTokens 8192, contextWindow 1M, etc.).
+
+### Edit D — `packages/types/src/providers/openrouter.ts`
+Add `"anthropic/claude-fable-5"` to both `OPEN_ROUTER_PROMPT_CACHING_MODELS` and
+`OPEN_ROUTER_REASONING_BUDGET_MODELS`.
+
+### Edit E — `packages/types/src/providers/vercel-ai-gateway.ts`
+Add `"anthropic/claude-fable-5"` to both `VERCEL_AI_GATEWAY_PROMPT_CACHING_MODELS` and
+`VERCEL_AI_GATEWAY_VISION_AND_TOOLS_MODELS`.
+
+### Edit F — `src/api/providers/anthropic.ts`
+Add `case "claude-fable-5":` to the two switch statements (after `claude-opus-4-8`).
+
+### Edit G — `src/api/providers/bedrock.ts`
+Add `baseModelId.includes("fable-5") ||` to the `isAdaptiveThinkingModel` guard. Optional:
+mention Fable 5 in the adjacent doc comments — but keep "the UI" wording (no "Zoo Code").
+
+### Edit H — `src/api/providers/requesty.ts`
+Swap import to `{ AnthropicProviderReasoningParams, getAnthropicProviderReasoning }`,
+change the two `thinking?: AnthropicReasoningParams` to `AnthropicProviderReasoningParams`,
+and in `getModel()` compute `reasoning = getAnthropicProviderReasoning({ model: info,
+reasoningBudget: params.reasoningBudget, settings: this.options })` and return
+`{ id, info, ...params, reasoning }`.
+
+### Edit I — `src/api/providers/vercel-ai-gateway.ts`
+Gate temperature on `info.supportsTemperature !== false && this.supportsTemperature(modelId)`
+in both `createMessage` and `completePrompt`.
+
+### Edit J — `src/api/providers/fetchers/openrouter.ts`
+Add the `anthropic/claude-fable-5` block setting maxTokens + reasoningBinary + temperature.
+
+### Edit K — `src/api/providers/fetchers/requesty.ts`
+Add the `anthropic/claude-fable-5` override block (reasoning flags + supportsTemperature false).
+
+### Edit L — `src/api/providers/fetchers/vercel-ai-gateway.ts`
+Add the `anthropic/claude-fable-5` → `supportsTemperature = false` block.
+
+### Edit M — `src/api/transform/model-params.ts`
+In the **`else`** branch only, prepend `if (model.supportsTemperature === false) {
+params.temperature = undefined }` and drop the stale 2-line OpenRouter TODO.
+
+### Edit N — `src/api/providers/anthropic-vertex.ts` (fork-specific; NOT in Zoo's diff)
+Zoo's PR did not touch this file because Zoo's Vertex handler already routed
+adaptive-binary models through `getAnthropicProviderReasoning` (from an earlier PR).
+**Our fork never got that change** — our `getModel()` returned `params.reasoning`
+from `getModelParams` (`getAnthropicReasoning`), which always emits
+`{ type: "enabled", budget_tokens }`. So Fable 5 (and Opus 4.7/4.8) on Vertex sent
+the wrong thinking config. Root cause proven via the new vertex adaptive test failing
+with `{ type: "enabled", budget_tokens: 8192 }` instead of `{ type: "adaptive" }`.
+Fix: import `getAnthropicProviderReasoning`; in `getModel()` compute
+`thinking = getAnthropicProviderReasoning({ model: info, reasoningBudget:
+params.reasoningBudget, reasoningEffort: params.reasoningEffort, settings: this.options })`
+and return `{ ...params, reasoning: thinking }`. Because `{ type: "adaptive" }` is not in
+the SDK's `ThinkingConfigParam` union, change the `createMessage`/`completePrompt` `params`
+declarations from a `: Anthropic.Messages.MessageCreateParams…` annotation to an
+`as Anthropic.Messages.MessageCreateParams…` cast (mirrors `AnthropicHandler`).
+
+## 3. Tests (port from upstream, adapt anchors)
+
+Add the Fable-5 cases to: `anthropic.spec.ts`, `anthropic-vertex.spec.ts`, `bedrock.spec.ts`,
+`requesty.spec.ts`, `vercel-ai-gateway.spec.ts`, `fetchers/__tests__/openrouter.spec.ts`,
+`fetchers/__tests__/vercel-ai-gateway.spec.ts`, `transform/__tests__/model-params.spec.ts`,
+`shared/__tests__/api.spec.ts`, and create new `fetchers/__tests__/requesty.spec.ts`.
+
+## 4. Out of scope
+- No "Zoo Code" branding. No TTS/router/cloud. Internal id `claude-fable-5` stays.
+
+## 5. Verify
+- `pnpm --filter @roo-code/types check-types` clean.
+- `cd src && npx vitest run api/providers/__tests__/anthropic.spec.ts api/providers/__tests__/bedrock.spec.ts api/providers/__tests__/anthropic-vertex.spec.ts api/providers/__tests__/requesty.spec.ts api/providers/__tests__/vercel-ai-gateway.spec.ts api/providers/fetchers/__tests__/openrouter.spec.ts api/providers/fetchers/__tests__/requesty.spec.ts api/providers/fetchers/__tests__/vercel-ai-gateway.spec.ts api/transform/__tests__/model-params.spec.ts shared/__tests__/api.spec.ts` all green.
+
+## 6. Acceptance
+- [ ] All new Fable-5 tests pass; touched suites green.
+- [ ] No "Roo"/"Zoo" user-facing strings introduced.
+
+## 7. Record
+```bash
+node .claude/skills/zoo-port/scripts/zoo-prs.mjs record --pr 555 --status ported \
+  --branch feature/zoo-555-add-fable-5-support-across-anthropic-providers \
+  --plan ai_plans/2026-06-17_zoo-555-add-fable-5-support-across-anthropic-providers.md
+```

packages/types/src/providers/anthropic.ts

@@ -126,6 +126,23 @@ export const anthropicModels = {
 		supportsReasoningBinary: true,
 		supportsTemperature: false,
 	},
+	"claude-fable-5": {
+		maxTokens: 128_000, // Overridden to 8k if `enableReasoningEffort` is false.
+		contextWindow: 1_000_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		inputPrice: 10.0, // $10 per million input tokens
+		outputPrice: 50.0, // $50 per million output tokens
+		cacheWritesPrice: 12.5, // $12.50 per million tokens
+		cacheReadsPrice: 1.0, // $1.00 per million tokens
+		// Fable 5 uses the same adaptive-thinking / binary-toggle convention as
+		// Opus 4.7+ on the direct Anthropic provider path.
+		supportsReasoningBudget: true,
+		supportsReasoningBinary: true,
+		supportsTemperature: false,
+		description:
+			"Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic work.",
+	},
 	"claude-opus-4-5-20251101": {
 		maxTokens: 32_000, // Overridden to 8k if `enableReasoningEffort` is false.
 		contextWindow: 200_000,

packages/types/src/providers/bedrock.ts

@@ -217,6 +217,24 @@ export const bedrockModels = {
 			},
 		],
 	},
+	"anthropic.claude-fable-5": {
+		maxTokens: 8192,
+		contextWindow: 1_000_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		supportsReasoningBudget: true,
+		supportsReasoningBinary: true,
+		supportsTemperature: false,
+		inputPrice: 10.0,
+		outputPrice: 50.0,
+		cacheWritesPrice: 12.5,
+		cacheReadsPrice: 1.0,
+		minTokensPerCachePoint: 1024,
+		maxCachePoints: 4,
+		cachableFields: ["system", "messages", "tools"],
+		description:
+			"Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic work.",
+	},
 	"anthropic.claude-opus-4-5-20251101-v1:0": {
 		maxTokens: 8192,
 		contextWindow: 200_000,
@@ -588,6 +606,7 @@ export const BEDROCK_1M_CONTEXT_MODEL_IDS = [
 // - Claude Opus 4.5
 // - Claude Opus 4.6
 // - Claude Opus 4.7
+// - Claude Fable 5 (cross-region inference only — can only be used through an inference profile)
 export const BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
 	"anthropic.claude-sonnet-4-20250514-v1:0",
 	"anthropic.claude-sonnet-4-5-20250929-v1:0",
@@ -597,6 +616,7 @@ export const BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
 	"anthropic.claude-opus-4-6-v1",
 	"anthropic.claude-opus-4-7",
 	"anthropic.claude-opus-4-8",
+	"anthropic.claude-fable-5",
 ] as const
 
 // Amazon Bedrock Service Tier types

packages/types/src/providers/openrouter.ts

@@ -43,6 +43,7 @@ export const OPEN_ROUTER_PROMPT_CACHING_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-haiku-4.5",
 	"google/gemini-2.5-flash-preview",
 	"google/gemini-2.5-flash-preview:thinking",
@@ -74,6 +75,7 @@ export const OPEN_ROUTER_REASONING_BUDGET_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-sonnet-4.5",
 	"anthropic/claude-sonnet-4.6",

packages/types/src/providers/vercel-ai-gateway.ts

@@ -13,6 +13,7 @@ export const VERCEL_AI_GATEWAY_PROMPT_CACHING_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-sonnet-4.6",
 	"openai/gpt-4.1",
@@ -55,6 +56,7 @@ export const VERCEL_AI_GATEWAY_VISION_AND_TOOLS_MODELS = new Set([
 	"anthropic/claude-opus-4.1",
 	"anthropic/claude-opus-4.5",
 	"anthropic/claude-opus-4.6",
+	"anthropic/claude-fable-5",
 	"anthropic/claude-sonnet-4",
 	"anthropic/claude-sonnet-4.6",
 	"google/gemini-1.5-flash",

packages/types/src/providers/vertex.ts

@@ -434,6 +434,21 @@ export const vertexModels = {
 			},
 		],
 	},
+	"claude-fable-5": {
+		maxTokens: 8192,
+		contextWindow: 1_000_000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		inputPrice: 10.0,
+		outputPrice: 50.0,
+		cacheWritesPrice: 12.5,
+		cacheReadsPrice: 1.0,
+		supportsReasoningBudget: true,
+		supportsReasoningBinary: true,
+		supportsTemperature: false,
+		description:
+			"Claude Fable 5 is Anthropic's most capable widely released model for the most demanding reasoning and long-horizon agentic work.",
+	},
 	"claude-opus-4-5@20251101": {
 		maxTokens: 8192,
 		contextWindow: 200_000,

src/api/providers/__tests__/anthropic-vertex.spec.ts

@@ -945,6 +945,23 @@ describe("VertexHandler", () => {
 			expect(model.betas).toContain("context-1m-2025-08-07")
 		})
 
+		it("should return Claude Fable 5 model info", () => {
+			const handler = new AnthropicVertexHandler({
+				apiModelId: "claude-fable-5",
+				vertexProjectId: "test-project",
+				vertexRegion: "us-central1",
+			})
+
+			const model = handler.getModel()
+			expect(model.id).toBe("claude-fable-5")
+			expect(model.info.maxTokens).toBe(8192)
+			expect(model.info.contextWindow).toBe(1_000_000)
+			expect(model.info.supportsReasoningBinary).toBe(true)
+			expect(model.info.supportsReasoningBudget).toBe(true)
+			expect(model.info.supportsPromptCache).toBe(true)
+			expect(model.info.supportsTemperature).toBe(false)
+		})
+
 		it("should not enable 1M context when flag is disabled", () => {
 			const handler = new AnthropicVertexHandler({
 				apiModelId: VERTEX_1M_CONTEXT_MODEL_IDS[0],
@@ -1161,6 +1178,35 @@ describe("VertexHandler", () => {
 				undefined,
 			)
 		})
+
+		it("should use adaptive thinking for Claude Fable 5", async () => {
+			const fableHandler = new AnthropicVertexHandler({
+				apiModelId: "claude-fable-5",
+				vertexProjectId: "test-project",
+				vertexRegion: "us-central1",
+				enableReasoningEffort: true,
+			})
+
+			const mockCreate = vitest.fn().mockImplementation(async () => ({
+				async *[Symbol.asyncIterator]() {
+					yield { type: "message_start", message: { usage: { input_tokens: 10, output_tokens: 5 } } }
+				},
+			}))
+			;(fableHandler["client"].messages as any).create = mockCreate
+
+			await fableHandler.createMessage("You are a helpful assistant", [{ role: "user", content: "Hello" }]).next()
+
+			expect(mockCreate).toHaveBeenCalledWith(
+				expect.objectContaining({
+					thinking: { type: "adaptive" },
+				}),
+				undefined,
+			)
+
+			const request = mockCreate.mock.calls[0][0]
+			expect(request.thinking).not.toHaveProperty("budget_tokens")
+			expect(request.temperature).toBeUndefined()
+		})
 	})
 
 	describe("native tool calling", () => {

src/api/providers/__tests__/anthropic.spec.ts

@@ -305,6 +305,33 @@ describe("AnthropicHandler", () => {
 			expect(requestBody?.max_tokens).toBe(32768)
 		})
 
+		it("should use adaptive thinking for Claude Fable 5 when reasoning is enabled", async () => {
+			const fableHandler = new AnthropicHandler({
+				apiKey: "test-api-key",
+				apiModelId: "claude-fable-5",
+				enableReasoningEffort: true,
+				modelMaxTokens: 32768,
+			})
+
+			const stream = fableHandler.createMessage(systemPrompt, [
+				{
+					role: "user",
+					content: [{ type: "text" as const, text: "Hello" }],
+				},
+			])
+
+			for await (const _chunk of stream) {
+				// Consume stream
+			}
+
+			const requestBody = mockCreate.mock.calls[mockCreate.mock.calls.length - 1]?.[0]
+			const requestOptions = mockCreate.mock.calls[mockCreate.mock.calls.length - 1]?.[1]
+			expect(requestBody?.thinking).toEqual({ type: "adaptive" })
+			expect(requestBody?.temperature).toBeUndefined()
+			expect(requestBody?.max_tokens).toBe(32768)
+			expect(requestOptions?.headers?.["anthropic-beta"]).toContain("prompt-caching-2024-07-31")
+		})
+
 		it("should not require the 1M context beta header for Claude Opus 4.8", async () => {
 			const opus48Handler = new AnthropicHandler({
 				apiKey: "test-api-key",
@@ -473,6 +500,23 @@ describe("AnthropicHandler", () => {
 			expect(model.reasoningBudget).toBeUndefined()
 		})
 
+		it("should handle Claude Fable 5 model correctly", () => {
+			const handler = new AnthropicHandler({
+				apiKey: "test-api-key",
+				apiModelId: "claude-fable-5",
+			})
+			const model = handler.getModel()
+			expect(model.id).toBe("claude-fable-5")
+			expect(model.info.maxTokens).toBe(128000)
+			expect(model.info.contextWindow).toBe(1000000)
+			expect(model.maxTokens).toBe(8192)
+			expect(model.info.supportsReasoningBinary).toBe(true)
+			expect(model.info.supportsReasoningBudget).toBe(true)
+			expect(model.info.supportsPromptCache).toBe(true)
+			expect(model.info.supportsTemperature).toBe(false)
+			expect(model.reasoningBudget).toBeUndefined()
+		})
+
 		it("should enable 1M context for Claude 4.5 Sonnet when beta flag is set", () => {
 			const handler = new AnthropicHandler({
 				apiKey: "test-api-key",