feat: migrate Bedrock provider to AI SDK (#11243)

* feat: migrate Bedrock provider to AI SDK

Replace the raw AWS SDK (@aws-sdk/client-bedrock-runtime) Bedrock handler
with the Vercel AI SDK (@ai-sdk/amazon-bedrock). Reduces provider from
1,633 lines to 575 lines (65% reduction).

Key changes:
- Use streamText()/generateText() instead of ConverseStreamCommand/ConverseCommand
- Use createAmazonBedrock() with native auth (access key, secret, session,
  profile via credentialProvider, API key, VPC endpoint as baseURL)
- Reasoning config via providerOptions.bedrock.reasoningConfig
- Anthropic beta headers via providerOptions.bedrock.anthropicBeta
- Thinking signature captured from providerMetadata.bedrock.signature
  on reasoning-delta stream events
- Thinking signature round-tripped via providerOptions.bedrock.signature
  on reasoning parts in convertToAiSdkMessages()
- Redacted thinking captured from providerMetadata.bedrock.redactedData
- isAiSdkProvider() returns true for reasoning block preservation
- Keep: getModel, ARN parsing, cross-region inference, cost calculation,
  service tier pricing, 1M context beta

Tests: 83 tests skipped (mock old AWS SDK internals, need rewrite for
AI SDK mocking). 106 tests pass. 0 tests fail.

* fix: address review feedback for Bedrock AI SDK migration

- Wire usePromptCache into AI SDK via providerOptions.bedrock.cachePoint
  on system prompt and last two user messages
- Remove debug logger.info that fires on every stream event with
  providerMetadata
- Tighten isThrottlingError to match 'rate limit' instead of broad
  'rate'/'limit' substrings that false-positive on context length errors
- Use shared handleAiSdkError utility for consistent error handling
  with status code preservation for retry logic

* fix: bedrock AI SDK migration - fix usage metrics, rewrite tests, remove dead code

- Fix reasoningTokens always 0 (usage.details?.reasoningTokens → usage.reasoningTokens)
- Fix cacheReadInputTokens always 0 (read from usage.inputTokenDetails instead of providerMetadata)
- Fix invokedModelId not extracted for prompt router cost calculation
- Rewrite all 6 skipped bedrock test suites for AI SDK mocking pattern (140 tests pass)
- Remove dead code: bedrock-converse-format.ts, cache-strategy/ (6 files, ~2700 lines)

* chore: remove dead @anthropic-ai/bedrock-sdk dep and stale AWS SDK mocks

* chore: update pnpm-lock.yaml after removing @anthropic-ai/bedrock-sdk

* fix: compute cache point indices from original Anthropic messages before AI SDK conversion

The previous approach naively targeted the last 2 user messages in the
post-conversion AI SDK array, but convertToAiSdkMessages() splits user
messages containing tool_results into separate tool + user messages,
causing cache points to land on the wrong messages (tiny text fragments
instead of the intended meaty user turns).

Now we identify the last 2 user messages in the original Anthropic
message array (matching the Anthropic provider's caching strategy) and
build a parallel-walk mapping to apply cachePoint to the correct
corresponding AI SDK message.

* perf: optimize prompt caching with 3-point message strategy + anchor for 20-block window

Previous approach only cached the last 2 user messages (using 2 of 4
available cache checkpoints for messages). This left significant cache
savings on the table for longer conversations.

New strategy uses up to 3 message cache points (+ 1 system = 4 total):
- Last user message: write to cache for next request
- Second-to-last user message: read from cache for current request
- Anchor message at ~1/3 position: ensures the 20-block lookback window
  from the second-to-last breakpoint hits a stable cache entry, covering
  all assistant/tool messages in the middle of the conversation

Also extracted the parallel-walk mapping logic into a reusable
applyCachePointsToAiSdkMessages() helper method.

Industry benchmarks show 70-95% token cache rates are achievable;
this change should significantly improve our 39% baseline for longer
multi-turn conversations.

* chore: remove stale bedrock-sdk external, fix arnInfo property name, remove unused exports

---------

Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>

Author: hannesrudolph

apps/cli/tsup.config.ts

@@ -16,7 +16,6 @@ export default defineConfig({
 	external: [
 		// Keep native modules external
 		"@anthropic-ai/sdk",
-		"@anthropic-ai/bedrock-sdk",
 		"@anthropic-ai/vertex-sdk",
 		// Keep @vscode/ripgrep external - we bundle the binary separately
 		"@vscode/ripgrep",

pnpm-lock.yaml

@@ -22,38 +22,6 @@ vitest.mock("../../../utils/logging", () => ({
 	},
 }))
 
-// Mock AWS SDK
-vitest.mock("@aws-sdk/client-bedrock-runtime", () => {
-	const mockModule = {
-		lastCommandInput: null as Record<string, any> | null,
-		mockSend: vitest.fn().mockImplementation(async function () {
-			return {
-				output: new TextEncoder().encode(JSON.stringify({ content: "Test response" })),
-			}
-		}),
-		mockConverseCommand: vitest.fn(function (input) {
-			mockModule.lastCommandInput = input
-			return { input }
-		}),
-		MockBedrockRuntimeClient: class {
-			public config: any
-			public send: any
-
-			constructor(config: { region?: string }) {
-				this.config = config
-				this.send = mockModule.mockSend
-			}
-		},
-	}
-
-	return {
-		BedrockRuntimeClient: mockModule.MockBedrockRuntimeClient,
-		ConverseCommand: mockModule.mockConverseCommand,
-		ConverseStreamCommand: vitest.fn(),
-		__mock: mockModule, // Expose mock internals for testing
-	}
-})
-
 describe("Bedrock ARN Handling", () => {
 	// Helper function to create a handler with specific options
 	const createHandler = (options: Partial<ApiHandlerOptions> = {}) => {
@@ -224,8 +192,8 @@ describe("Bedrock ARN Handling", () => {
 					"arn:aws:bedrock:eu-west-1:123456789012:inference-profile/anthropic.claude-3-sonnet-20240229-v1:0",
 			})
 
-			// Verify the client was created with the ARN region, not the provided region
-			expect((handler as any).client.config.region).toBe("eu-west-1")
+			// Verify the handler's options were updated with the ARN region
+			expect((handler as any).options.awsRegion).toBe("eu-west-1")
 		})
 
 		it("should log region mismatch warning when ARN region differs from provided region", () => {