fix(executor): add logging and prompt cache key handling for OpenAI responses

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

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

Fixed: #140 #133 #80

docs: add GPT-5 Codex guidelines for internal usage

Refactor executor error handling and usage reporting

Fixed: #148

Enhance logging for API requests and responses across executors

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

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

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

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

rebuild branch

remove all

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

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

refactor(executor): centralize header application logic for executors

chore(executor): add debug logging for API request errors

feat(auth): standardize `last_refresh` metadata handling across executors

chore(logging): add debug logs for executor `Refresh` methods

feat: implement token refresh support for executors

refactor: standardize constant naming and improve file-based auth handling

v6 version first commit