Weekly Tooling Brief — 2026-09-27

- Fixed repository, user and `--add-dir` skills, commands and skills-directory plugin manifests pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly`

Fixed a bug in image encoding that degraded image understanding in GPT-6 Sol and GPT-6 Luna. This update improves results on visual tasks in the API and Codex, including computer use. If your use cases involve image inputs, we recommend rerunning your evaluations and retrying workflows affected by the issue.

We've launched Claude Opus 5.5 (claude-opus-5-5), a model for long-running agentic coding and knowledge work. It has a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking, at $4 / $20 USD per MTok (Claude Opus 5 is $5 / $25).

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS generally available (GA): Released our next-generation text-to-speech (TTS) audio models and the Gemini API Voices endpoint (/v1beta/voices):

* **api:** add GCP external storage support ([#3943](https://github.com/openai/openai-python/issues/3943)) ([d12d60f](https://github.com/openai/openai-python/commit/d12d60fff9f5624f2dc50ade3d832028f4fecaa7)) * **api:** add GPT-Rosalind research model ([#3940](https://github.com/openai/openai-python/issues/3940)) ([d041d73](https://github.com/openai/openai-python/commit/d041d736f75f03f6c87aa77f932823011691bac5))

- Added Claude Opus 5.5 (`claude-opus-5-5`), now the default Opus model — 1M context, $4/$20 per Mtok with $0.20/Mtok cache reads

Added GPT-6 Sol and Luna, including Amazon Bedrock support and migration prompts for older models. (#47332, #47347)

* **api:** add GPT-6 Sol and Luna model identifiers ([#3935](https://github.com/openai/openai-python/issues/3935)) ([455ce1b](https://github.com/openai/openai-python/commit/455ce1b5da067e5d7631c86a571ca3b0d03b65cd))

- Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed - Added `deniedModels` managed setting to block specific models, even when `availableModels` allows them

* fix(core): prevent indirect prompt injection via build file modifications and untrusted flags by @villahernandez-coder in https://github.com/google-gemini/gemini-cli/pull/29250

- Fixed a recursive `rm` whose target is only command-substitution output, such as `rm -rf "$(pwd)"`, running unprompted in auto and `--dangerously-skip-permissions` mode; it now asks even with a Bash allow rule, unless run with `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT=1`

* **api:** add support for claude-opus-5-5, inline tool definitions and MCP tool-list pinning (beta) ([b5cc700](https://github.com/anthropics/anthropic-sdk-python/commit/b5cc70071a60def1d2e93f3634d1a595919007c8))

GPT-6 Sol and GPT-6 Luna are rolling out to Codex and ChatGPT Work at lower token prices than their GPT-5.6 predecessors. Use Sol for complex coding and agentic workflows, and Luna for focused, high-volume tasks.

Released GPT-6 Sol (gpt-6-sol) and GPT-6 Luna (gpt-6-luna). These reasoning models accept text and image inputs and generate text through the Responses and Chat Completions APIs. Standard pricing per 1M tokens for prompts with up to 272K input tokens: GPT-6 Sol: $2 input, $0.20 cached input, and $10 output. GPT-6 Luna: $0.10 input, $0.01 cached input, and $0.50 output.

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. Mid-stream refusals were already billed. Refusals billed under this change are charged like any other request, at the rates of the model that ran it. Refusals before any output in other categories are still not billed, and fallback credit is unchanged. This change applies on all platforms.

* **api:** add external storage configuration management ([#3909](https://github.com/openai/openai-python/issues/3909)) ([6332577](https://github.com/openai/openai-python/commit/6332577d3fb5f83f7f381a431460262f7192402d))

Cache diagnostics is out of beta on the Claude API and no longer requires the cache-diagnosis-2026-04-07 beta header. Include the diagnostics object on a Messages request to opt in; requests that still send the header work as before. Responses from POST /v1/messages now always include the diagnostics field, which is null when the request did not include the diagnostics object.

* Add Voices API resource to GAOS SDK ([c45b94e](https://github.com/googleapis/python-genai/commit/c45b94e7a0e0dcd5dcc2590f62f5d223f8c90e99))