AI Development & Programming: Build Apps with AI

You switched your Claude API calls to a newer model, and now you get AttributeError: 'ThinkingBlock' object has no attribute 'text', or the response text comes back empty. The cause is that Claude 5 and later models think when needed even if you don't set thinking, so the first block of the response becomes a thinking block. Claude 4 models didn't think unless you set it, so changing only the model name changes the shape of the response. With simple inputs the first block is still text, so tests that use light inputs pass. Based on Anthropic's documentation and my own tests of four models (November 1, 2026), this article covers the cause, how to fix it by finding text blocks by type (Python and TypeScript), what to do when max_tokens leaves you with no text, which models can and can't turn thinking off, and how not to miss it in testing.

"Codex won't go parallel unless you tell it to" is true, with conditions: the Codex app, CLI and IDE extension spawn subagents when you ask directly, or when AGENTS.md or a skill instructs delegation (Ultra in ChatGPT Work also delegates on its own judgment). Claude Code delegates on its own based on the request and each subagent's description. Using the official OpenAI and Anthropic documentation (checked October 26, 2026), this article compares what triggers parallel work, five things to put in your instructions, ready-to-use example prompts, [agents] in Codex's config.toml and the TOML files in .codex/agents/, Claude Code's .claude/agents/ and environment variables, commands such as /subagents, /tasks, /subtask, /batch and /worktree, tasks that suit parallel work and tasks that don't, and the impact on usage limits, and it also shares lessons this site learned from running subagents in parallel.

"Your credit balance is too low to access the Anthropic API" (shown as "Credit balance is too low" in Claude Code) means your Claude Console organization doesn't have enough prepaid credits. There are two causes: your balance really is too low, or you meant to use a plan such as Pro or Max but Claude Code is running on an API key from the ANTHROPIC_API_KEY environment variable and billing the API instead. You tell them apart with /status. Based on Anthropic's official documentation and Help Center (checked October 26, 2026), this article explains how the error appears, three questions to find the cause, how to buy credits under Billing in the Console and set up auto-reload, how to remove the API key on macOS, Linux and Windows and check it in VS Code, how this differs from the monthly API credits for Max and Team and from usage credits, and similar but different errors.

There are two ways to use Claude while staying on your Google Cloud bill: the Google-managed version, which Google runs as part of Agent Platform (formerly Vertex AI), and the Anthropic-managed version, which became generally available on October 22, 2026. Claude Code runs on the Google-managed version, configured with CLAUDE_CODE_USE_VERTEX and related settings (pinning the models is recommended if you roll it out to multiple people). If you need the Files API, Agent Skills, Managed Agents, fast mode and similar features, choose the Anthropic-managed version. On the Google-managed global endpoint, Opus 5.5, Sonnet 5.5 and Haiku 5.5 cost the same as the Claude API, while the us and eu multi-regions cost 1.1x. The Anthropic-managed version is metered in CCU, and no per-token price list appears in the official docs. Based on the official documentation (checked October 26, 2026), this article covers the differences and how to choose, pricing, regions, getting started, the SDKs, Claude Code setup, and how to handle quotas and 429 errors.

If the Claude API returns '`temperature` is deprecated for this model.', the cause is sending non-default values for temperature, top_p, or top_k to a Claude 4.7 or later model, and removing all three from the request fixes it. Claude 4.7 and later models already reject non-default values under API version 2023-06-01, and under the new API version 2026-10-21 they return a 400 error for any model, even with default values; newer SDKs such as Python anthropic 2.0.0 send 2026-10-21 automatically and no longer include the three arguments in their types, so code that still passes them will fail with an argument error or a 400 after an SDK upgrade. This article explains the two situations where the error appears, how to get consistent answers without these settings, how to find them in code, SDK versions, related changes such as how the API key is sent, and the fix for the similar 'anthropic-version: header is required' error, based on Anthropic's official documentation (checked October 26, 2026).

You don't need a high-end PC to run Claude Code or Codex. Both run their models on servers, so buying a new PC won't shorten the time the AI spends thinking and writing. Claude Code's CLI requires at least 4GB of RAM, an x64 or ARM64 CPU, and an internet connection, while Codex publishes no RAM or CPU figures. Your PC affects the time spent running commands locally, such as builds, tests, and searches. This article compares requirements, fast mode, per-OS sandbox conditions, and fixes for heavy workloads, and explains how to measure where your time goes and the three things to check before buying new hardware.

Claude Code's /goal lets you write down what counts as done. A separate small model checks the condition after each turn, and Claude keeps working until it is met. The article covers setup, checking, and clearing /goal from the official documentation, how the checker works and when it stops, how to write conditions, and how /goal differs from /loop and Codex's /goal. It also reports two runs aligning sentence-ending punctuation across this site's articles, including a 321-item run that finished in one turn, and notes that the checker cannot confirm finished quality that does not show up in the numbers.

This guide explains how to handle the Codex desktop app error "Organization settings could not be loaded" when it blocks you from continuing. The wording suggests a network or proxy problem, but GitHub bug reports show other causes too. It covers a case fixed by a single retry, four patterns reported by users, where to find the app logs, and what to avoid, such as signing out right away or deleting folders. It also explains what to report if the problem persists and how it differs from the similar "Couldn't load workspace settings" error.

The page was visible, but Codex could not control it. We distinguish a missing connection from a stale error page and explain what actually recovered.

DeepSeek V4.1 Flash 1017 (DeepSeek-V4.1-Flash-1017) is the revised V4.1 Flash that DeepSeek released on October 17, 2026, while keeping the same API name, deepseek-flash. This article checks DeepSeek's announcements, model card, and pricing page against third-party evaluations and national responses (confirmed October 19, 2026), and explains what changed, its specifications, benchmark results, pricing, safety status, and data storage. It also offers guidance on choosing between the API, Claude Code, and running the model locally.

Claude Code works with DeepSeek, GLM (Z.ai), and Kimi (Moonshot AI) models once you set ANTHROPIC_BASE_URL, each provider's API key, and the model name environment variables. The benefit is that you can swap only the model that answers while keeping the screen, tools, and settings, which helps when you want to cut costs or hit Claude's usage limits, though Anthropic does not support this use. The article draws on official documentation from each provider and Anthropic (checked October 19, 2026) to cover pros and cons, settings.json examples, per-million-token prices for nine models, estimated per-session costs, four factors that change billing, DeepSeek's search charges starting November 1, 2026 ($0.75 per 1,000 successful calls), comparisons with fixed-price plans such as GLM Coding Plan, and code privacy concerns such as DeepSeek's data storage in China.

Claude Haiku 5.5 (claude-haiku-5-5) is the lightweight model Anthropic released on October 7, 2026. For prompts up to 100,000 tokens it costs $0.10 input and $0.50 output per million tokens, one-tenth of Haiku 4.5. Above that it costs $0.50 input and $2.50 output, and tokens read from the cache count toward the length. It has a 1M-token context, 128K maximum output and a June 2026 knowledge cutoff, and it is the first Haiku that lets you choose the effort (medium by default). Based on official documentation and announcements checked against the originals on October 15, 2026, this article covers estimated costs for four models adjusted for the roughly 30% more tokens counted for the same text, how to read the benchmarks Anthropic published, how to choose between Sonnet 5.5 and Opus 5.5, how to set thinking and effort, request patterns that return a 400 error after moving from Haiku 4.5 and the changes that happen without an error, where haiku points in Claude Code (Haiku 5.5 on the Anthropic API from v2.1.293), and availability in the apps, GitHub Copilot and the cloud.