refactor codex websocket request normalization

refactor(stream): harden forwarding and hook composition

ein

fix(responses): reject invalid SSE data JSON

fix(openai): emit valid responses stream error chunks

test(handlers): add tests for passthrough headers behavior in WriteErrorResponse

feat: add passthrough headers configuration

fix: ensure connection-scoped headers are filtered in upstream requests

Merge PR #1626 into codex/pr-1626

Merge pull request #1618 from alexey-yanchenko/fix/completions-usage

feat(logging, executor): add request logging tests and WebSocket-based Codex executor

feat: passthrough upstream response headers to clients

Add usage to /v1/completions

refactor(all): replace manual pointer assignments with `new` to enhance code readability and maintainability

feat: add Kimi authentication support and streamline device ID handling

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

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

refactor(util, executor): optimize payload handling and schema processing

Merge pull request #1174 from lieyan666/fix/issue-1082-change-error-status-code

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

fix(logging): capture streaming TTFB on first chunk and make timestamps required

fix(logging): add API response timestamp and fix request timestamp timing

feat(handlers): add test to verify no retries after partial stream response

refactor: consolidate channel send logic with context-safe handlers

fix(openai): drop stream for responses/compact

feat(openai): add responses/compact support

Merge pull request #1132 from XYenon/fix/gemini-models-displayname-override

fix(api): enhance ClaudeModels response to align with api.anthropic.com

fix: change HTTP status code from 400 to 502 when no provider available

feat(executor): apply payload rules using requested model

fix(gemini): preserve displayName and description in models list

feat(cliproxy, gemini): improve ID matching logic and enrich normalized model output

refactor(gemini): replace static model handling with dynamic model registry lookup

refactor: improve thinking logic

refactor(config): replace `nonstream-keepalive` with `nonstream-keepalive-interval`

feat(api): add non-streaming keep-alive support for idle timeout prevention

fix(test): implement missing HttpRequest method in stream bootstrap mock

feat(management): add `PostOAuthCallback` handler to token requester interface

feat(api): add `GetAuthStatus` method to `ManagementTokenRequester` interface

Merge pull request #761 from router-for-me/log

feat(api): add ManagementTokenRequester interface for management token request endpoints

fix(handlers): preserve upstream response logs before duplicate detection

fix(handlers): match raw error text before JSON body for duplicate detection

fix(logging): improve request/response capture

fix(config): make streaming keepalive and retries ints

fix(test): remove extra argument from ExecuteStreamWithAuthManager call

feat(logging): implement request ID tracking and propagation

refactor(handlers): streamline error and data channel handling in streaming logic

fix: keep streaming defaults legacy-safe

fix: stop streaming loop on context cancel