docs: add GPT-5 Codex guidelines for internal usage

Refactor executor error handling and usage reporting

Fixed: #148

feat(iflow): add masked token logs; increase refresh lead to 24h

feat(logging): centralize sensitive header masking

Enhance logging for API requests and responses across executors

Feature: #103

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

feat(usage): add support for tracking request source in usage records

refactor(provider): remove Gemini Web cookie-based provider

feat(registry, executor, util): add support for `gemini-2.5-flash-image-preview` and improve aspect ratio handling

feat(registry, executor): add support for `glm-4.6` model and enhance Gemini CLI token handling

feat(registry, executor): add support for `gemini-2.5-flash-image` model

feat(gemini-web): Enable config hot-reload and fix Gem selection

fix(gemini): Disable thinking config for incompatible models

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

feat(iflow): Add User-Agent header to API requests

feat: Add support for iFlow provider

feat(auth): improve OpenAI compatibility normalization and API key handling

feat(runtime): remove `previous_response_id` from Codex executor request body

feat(gemini-web): Add support for custom auth labels

feat(gemini-web): Add conversation affinity selector

refactor(proxy): improve SOCKS5 proxy authentication handling

feat(runtime): introduce `newProxyAwareHTTPClient` for enhanced proxy handling

refactor(runtime): move `Anthropic-Beta` header setting to `applyClaudeHeaders` for better header management

feat(provider/gemini-web): Prioritize explicit label for account identification

refactor(config): migrate to `SDKConfig` and streamline proxy handling

refactor(executor): remove redundant handling of "reasoning.effort" in gpt-5 and gpt-5-codex models

feat(gemini-web): Introduce stable account label for identification

rebuild branch

remove all

chore(docs): add and refine package-level comments across modules

fix(gemini): handle "[DONE]" chunk, trim "data:" prefix, and remove session_id from requests

Removed the cookie snapshot feature.

refactor(gemini-web): Move provider logic to its own package

refactor(executor): remove ClientAdapter and legacy fallback logic

fix(codex): Remove reasoning.effort for default gpt-5-codex model

feat(translators): add token counting support for Claude and Gemini responses

feat(usage): implement usage tracking infrastructure across executors

feat(translators): improve system instruction extraction and input handling for OpenAI and Claude responses

feat(translators): improve system instruction extraction and input handling for OpenAI and Claude responses

fix(gemini): trim "data:" prefix in raw JSON and resolve variable shadowing in stream translation

fix(gemini-web): Correct stream translation and reduce auth refresh lead

Merge pull request #58 from router-for-me/v6-test

refactor(gemini-web): Remove auto-refresh, auto-close, and caching

feat(claude-executor): add ZSTD decoding support for Claude executor responses

feat(gemini-web): Inject fallback text for image-only flash model responses

feat(gemini-executor): implement `CountTokens` method with request translation and API integration

feat(executor): add `CountTokens` support across all executors

refactor(headers): centralize header logic using `EnsureHeader` utility