Daily Tooling Brief — 2026-10-30

Eligible ChatGPT Pro and Business subscribers can now claim up to $500 per month in free API credits as a subscription benefit.

Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways.

On Claude Opus 5.5, thinking can’t be disabled: thinking: {"type": "disabled"} and thinking: {"type": "enabled", ...} return a 400 error.

- Fixed Claude overwriting a very large CLAUDE.md, rules file or @-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place

The Usage and Cost API is now a legacy API, and so are the usage_report, cost_report, user_usage_report, and user_cost_report endpoints of the Claude Enterprise Analytics API. All of them remain supported.

- Closed a marketplace URL validation gap that could allow Git to connect to a different host than the one checked against allowed patterns. (#56263)

v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the temperature, top_p, and top_k parameters on Messages methods, and the tool runner’s client-side compaction_control.

Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it keep working.

A workflow is a program that runs many agents in phases and combines their results. The server runs it in the background as a workflow run.

- Fixed Claude Code retrying requests the API marked not to retry, which could hold a turn for minutes or, in unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`), indefinitely

New projects using the Generate Content API (generateContent, streamGenerateContent, and batchGenerateContent) on the paid tier now store requests by default (store=true), matching the Interactions API.

Released GPT-6.1 Terra, a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.

Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (budget_tokens), the sampling parameters temperature, top_p, and top_k, and assistant message prefill can each return a 400 error.

We’re resuming billing for refusals that arrive before any output when stop_details.category is "bio", "frontier_llm", or "reasoning_extraction", the categories where we measure low volumes of false positives.

- Added `codex doctor --network-only` for focused configuration, connectivity, and WebSocket diagnostics. (#57606)

Gemini API CLI (gemini-api) beta: Released the Gemini API CLI (gemini-api), a stateless, zero-dependency command-line client for AI coding agents, scripts, and CI pipelines.

We’ve launched OpenTelemetry export in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability platform.

We’ve raised the maximum request size for the Messages API and the Token Counting API from 32 MB to 128 MB on the first-party Claude API.

* **api:** add delegation controls and prompt cache lifetimes ([#4169](https://github.com/openai/openai-python/issues/4169)) ([43045fc](https://github.com/openai/openai-python/commit/43045fcaf91aec08571e54c57706597cefd32d45))

* **websocket:** recover queued binary frames after reconnect ([#4191](https://github.com/openai/openai-python/issues/4191)) ([f079868](https://github.com/openai/openai-python/commit/f0798682d36be3bb79293d40c260cd93dbabf939))