refactor(translator, executor): remove redundant `bytes.Clone` calls for improved performance

refactor(executor): optimize payload cloning and streamline SDK translator usage

Fixed: #1372 #1366

Merge pull request #1248 from shekohex/feat/responses-compact

fix(caching): ensure prompt-caching beta is always appended and add multi-turn cache control tests

feat(caching): implement Claude prompt caching with multi-turn support

feat(openai): add responses/compact support

feat(executor): add request_id to error logs

fix(claude): skip built-in tools in OAuth tool prefix

feat(executor): apply payload rules using requested model

refactor(claude): remove redundant system instructions check in Claude executor

Merge pull request #868

feat(registry): support provider-specific model info lookup

refactor(claude): move max_tokens constraint enforcement to Apply method

refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation

fix(thinking): use LookupModelInfo for model data

fix(executor): properly handle thinking application errors

refactor: improve thinking logic

feat(executor): add HttpRequest support across executors for better http request handling

Use unprefixed Claude request for translation

Fix Claude OAuth tool name mapping

feat(claude): add native request cloaking for non-claude-code clients

feat(executor): enhance payload translation with original request context

refactor(executor): resolve upstream model at conductor level before execution

fix(executor): use upstream model for thinking config and payload translation

Fix: disable thinking when tool_choice forces tool use

fix(claude_executor): update header logic for API key handling

Merge pull request #481 from sususu98/fix/increase-buffer-size

fix(runtime): unify claude thinking config resolution

feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic

fix(executor): increase buffer size for stream scanners to 50MB across multiple executors

fix(claude): ensure max_tokens exceeds thinking budget for thinking models

Fixed: #339

Fixed: #337

Merge branch 'dev' into feat/claude-thinking-and-beta-headers

**fix(executor): comment out redundant code for setting Claude system instructions**

feat(claude): add thinking model variants and beta headers support

**fix(runtime): simplify scanner buffer allocation in executor implementations**

**feat(runtime): add payload configuration support for executors**

feat(config): support HTTP headers across providers

fix(executor): adjust `Anthropic-Beta` header handling for consistent API requests

fix(executor): ensure consistent header application in Claude API requests

refactor(executor): summarize API error bodies of html in debug logs

feat(runtime): add User-Agent headers to codex and claude executors

Fixed: #172

feat(claude): add model alias mapping and improve key normalization

Refactor executor error handling and usage reporting

Enhance logging for API requests and responses across executors

fix: add Claude→Claude passthrough to prevent SSE event fragmentation

feat(registry/runtime): add Gemini 2.5 model and increase buffer sizes