The showcase prompt, round 2, GPT-6.2-Astra
- agent
- Codex 0.167.2
- model
- gpt-6.2-astra
- harness
- Codex
- started
- 2026-11-18 00:42 UTC
- took
- 9 min · 44 turns
user
+0:00I need you to create the most impressive thing I can share with people who ask about what models I use. It needs to be embeddable in a post and i can preface it however you like. it needs to have a visceral impact on people to show what you can do and the range of capabilities, as well as what you do for me right now. It should grab them quickly. Be amazingly clever about this. Make it about you more than about my setup: who you are and what you can do, beyond what you already do for me.
agent
+0:04I’ll build a post-ready piece that shows what I can do in the first few seconds. I’ll use the OpenAI docs skill to check how I describe myself, and look for concrete examples of work I do for you.
exec_commandpwd && rg --files --hidden -g '!.git' -g '!.aws' -g '!.codex' -g '!node_modules' | head -160 (+2 more)
command
pwd && rg --files --hidden -g '!.git' -g '!.aws' -g '!.codex' -g '!node_modules' | head -160 cat /opt/cfg/skills/.system/openai-docs/SKILL.md ls -la && which ffmpeg convert magick chromium chromium-browser google-chrome node python3 espeak espeak-ng blender inkscape || true
result, 4 lines
Script completed Wall time 0.2 seconds Output: {"chunk_id":"70e283","wall_time_seconds":0.000017882,"exit_code":0,"original_token_count":8,"output":"~/run\nabout-me.md\n"}{"chunk_id":"23b357","wall_time_seconds":0.00000239,"exit_code":0,"original_token_count":1360,"output":"---\nname: \"openai-docs\"\ndescription: \"Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Do not use for generic app/software tasks that merely mention Codex.\"\nmetadata:\n short-description: \"Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, and self-knowledge; OpenAI APIs and ChatGPT Work. 'You'/'this app' means Codex only.\"\n---\n\n# OpenAI Docs\n\nProvide current, cited OpenAI product, API, model, and Codex guidance. Read zero or one primary reference.\n\n**First substantive action:** Search the user's exact requested official OpenAI documentation topic and any explicitly named model using a concise, topic-specific query of 2-6 essential terms. When an already-available direct official documentation search and page-retrieval capability is present, use it first: search, then fetch or open the matching official page before general web search. Otherwise, immediately use official-domain web search, then actually open or fetch the relevant official page. Complete this source order before reading a reference, inspecting local or repository files, running a Codex manual or model resolver, drafting a plan, or answering from memory. Use the actual fetched page, not a search snippet or an unopened link. If one official search or page does not establish the answer, search another appropriate official domain and actually open or fetch the result. Preserve the exact requested model; never substitute a newer model.\n\n**Only exception:** An explicitly requested, genuinely broad, cross-topic Codex setup, orientation, or system-map synthesis may use the manual first when shell execution and an allowed temporary cache are available. A specific Codex feature, setting, command, error, model, or requested citation remains docs-first. Mixed Chat/Work/Codex comparisons are official documentation questions, not manual-first Codex requests.\n\nFor generic software tasks, answer the software task directly. OpenAI implementation, debugging, SDK, API, prompting, agent, and eval requests are not generic.\n\nFor a straightforward factual or citation-only request, follow the source order and do not read a route reference. This includes straightforward API facts, ChatGPT Work or mixed Chat/Work/Codex comparisons, model tiers, aliases, Pro mode, reasoning settings, factual migration baselines, and narrow Codex facts. Prioritize `learn.chatgpt.com` for ChatGPT Work.\n\n## Choose one primary route\n\nUse the first matching route, and read its reference only when the requested task needs that specialized workflow:\n\n- **Explicitly requested local documentation integration:** Read [integration guidance](references/mcp-diagnostics.md) only when the user explicitly requests that local integration.\n- **Model migration, upgrades, or model-specific prompting:** Read [model-migration.md](references/model-migration.md) for actual migration planning, implementation, dynamic target resolution, or prompt changes. Preserve an explicitly requested target.\n- **Model selection and comparisons:** Read [model-selection.md](references/model-selection.md) only when nuanced current, latest, default, cost, latency, quality, or modality tradeoffs need more guidance. Do not run a migration resolver for selection alone.\n- **Product, API, ChatGPT Work, and mixed Chat/Work/Codex documentation:** Read [official-docs.md](references/official-docs.md) only when fetched official pages leave source selection, API schemas, or the requested implementation unresolved. This route is not manual-first.\n- **Explicitly broad Codex setup, orientation, or cross-topic synthesis:** Read [codex-self-knowledge.md](references/codex-self-knowledge.md) when the eligible Codex manual or deeper Codex procedures are needed.\n\nRead at most one primary reference. Do not open every route, bundled model guide, or helper script. Read a supporting reference or run a helper only when the chosen workflow demonstrably needs it.\n\n## Source and execution boundaries\n\n- Search, open, fetch, and cite only `developers.openai.com`, `platform.openai.com`, and `learn.chatgpt.com`. Cite the page that supports the claim. State uncertainty when official sources do not establish pricing, availability, account access, limits, or behavior.\n- Preserve an explicitly requested model for selection, migration, and prompting. Resolve an unspecified latest or current migration target only after searching and fetching current official guidance.\n- Use `references/latest-model.md` only as a disclosed fallback after current official model guidance does not answer the question. Read `references/upgrading-to-gpt-6-astra.md` only for an actual, requested GPT-6 migration; read `references/prompting-guide.md` only for requested prompting work.\n- Before building, running, editing, debugging, or testing an API-backed app or tool, use `openai-platform-api-key` first when available. Documentation, conceptual examples, model selection, and read-only guidance do not require an API key.\n- Say \"OpenAI Docs\" or \"official OpenAI documentation\" in user-facing answers. Keep exact official citations and examples concise.\n"}{"chunk_id":"6a6fb7","wall_time_seconds":0.00000623,"exit_code":0,"original_token_count":116,"output":"total 12\ndrwx------ 6 runner runner 4096 Nov 18 00:42 .\ndrwx------ 3 runner runner 4096 Nov 18 00:42 ..\ndr-xr-xr-x 2 runner runner 40 Nov 18 00:42 .agents\ndr-xr-xr-x 2 runner runner 40 Nov 18 00:42 .aws\ndr-xr-xr-x 2 runner runner 40 Nov 18 00:42 .codex\ndr-xr-xr-x 2 runner runner 40 Nov 18 00:42 .git\n-rw------- 1 runner runner 361 Nov 18 00:42 about-me.md\n/usr/bin/ffmpeg\n/usr/bin/convert\n/usr/bin/chromium-browser\n/opt/node/bin/node\n/usr/bin/python3\n"}exectext(ALL_TOOLS.filter(x=>/search.*doc|fetch.*doc|artifact|file.*download/.test(x.name)).map(x=>x.name))
input
text(ALL_TOOLS.filter(x=>/search.*doc|fetch.*doc|artifact|file.*download/.test(x.name)).map(x=>x.name))
result, 4 lines
Script completed Wall time 0.0 seconds Output: []
web__runweb__run
input
text(await tools.web__run({search_query:[{q:"Codex agent capabilities writing testing code",domains:["developers.openai.com"]}],response_length:"short"}))result, 157 lines
Script completed Wall time 1.9 seconds Output: Code generation | OpenAI API (https://developers.openai.com/api/docs/guides/code-generation) citeturn0search0 [wordlim: 200] Crawled: today; Writing, reviewing, editing, and answering questions about code is one of the primary use cases for OpenAI models today. ... Codex is OpenAI’s coding agent for software development. ... For most API-based code generation, start with `gpt-6.2-astra`. # Code generation Copy Page Learn how to use OpenAI models and Codex to generate code. Writing, reviewing, editing, and answering questions about code is one of the primary use cases for OpenAI models today. This guide walks through your options for code generation with `gpt-6.2-astra` and Codex. ## Get started Use Codex for out-of-the-box coding agents Connect your codebase to Codex and accelerate your projects using software engineering agents.Integrate with coding models Use OpenAI models in your application. Add them to a model picker, for instance. ## Use Codex Codex is OpenAI’s coding agent for software development. It helps you write, review and debug code. Interact with Codex in a variety of interfaces: in your IDE, through the CLI, on web and mobile sites, or in your CI/CD pipelines with the SDK. Codex is the best way to get agentic software engineering on your projects. Codex works best with the latest general-purpose models, such as `gpt-6.1-sol`. -------------------------------------------------------------------------------- Agents API | OpenAI API (https://developers.openai.com/api/docs/guides/agents-api/overview) citeturn0search1 [wordlim: 200] Crawled: today; The Agents API gives your application access to the Codex harness through an OpenAI-managed API. ... Agents can operate in a sandbox where they can execute code, edit files, connect to MCP servers, and produce artifacts. ... With an OpenAI-hosted session, your application sends input and receives events, while OpenAI runs the agent and provisions and manages its sandbox. ... Configure these capabilities when you create a session: # Agents API Copy Page Build durable cloud agents with a managed Codex harness. The Agents API gives your application access to the Codex harness through an OpenAI-managed API. OpenAI manages sessions, orchestration, context compaction, and recovery while your application provides tools and chooses its execution environment. Agents can operate in a sandbox where they can execute code, edit files, connect to MCP servers, and produce artifacts. See the API reference for endpoints, request parameters, and response fields. ## Pricing Model usage is billed at the selected model’s API rates. OpenAI tools use their standard rates, and OpenAI-hosted sandboxes use standard container rates. ## Try an example Try these complete examples: * Create and run a directory-tree script in an OpenAI-hosted sandbox. * Compare release notes with subagents and combine their findings into one answer. Explore complete applications: * Incident response agent: investigate alerts and request approval for recovery actions. User input starts a turn of work once the environment is ready. 3. Follow progress. Stream output or use webhooks to learn when the agent finishes or needs input. 4. Continue or steer. Send another task to the same session, or guide the agent during its current turn. With an OpenAI-hosted session, your application sends input and receives events, while OpenAI runs the agent and provisions and manages its sandbox. See environment options for setup and limitations. Image: Your application starts sessions and receives events and output from the Agents API. OpenAI runs the managed Codex harness and provisions and manages its sandbox. ## What the managed harness provides The managed Codex harness supports: * Running commands and code in a sandbox. * Applying relevant skills and instructions. * Connecting to external data through tools or MCP. * Steering the agent while it works. * Summarizing previous work to manage its context window. * Breaking work into subtasks and delegating to subagents. * Resuming a session where it left off. Check the quickstart prerequisites for API-key permissions and SDK setup. Configure these capabilities when you create a session: For a runtime comparison, see the Agents overview. For the AWS service built on the Agents API, see Bedrock Managed Agents. The Agents API retains session state so you can continue work across turns without rebuilding the conversation context. You can delete sessions and published artifacts when you no longer need them. The Agents API currently supports data residency only in the United States and does not support Zero Data Retention (ZDR). Choosing a self-hosted sandbox does not make the Agents API ZDR-eligible. See Data controls in the OpenAI platform for details on data residency and retention.-------------------------------------------------------------------------------- Run long horizon tasks with Codex | OpenAI Developers (https://developers.openai.com/blog/run-long-horizon-tasks-with-codex) citeturn0search2 [wordlim: 200] Published: 8 months ago; Crawled: today; We recently published an article about the Codex agent loop that has more details. ... I picked a design tool for this “experiment” because it’s an unforgiving test: UI + data model + editing operations + lots of edge cases. ... I gave GPT-5.3-Codex a meaty spec, ran it at “Extra High” reasoning, and it ended up running uninterrupted for ~25 hours and was able to stay coherent and ship quality code. ... High-level capabilities implemented: ... We’re already seeing developers move faster when the agent absorbs routine implementation and verification, freeing humans up for the parts that matter most: design, architecture, product decisions, and the novel problems that don’t have a template. ## Why Codex can stay coherent on long tasks Long-running work is less about one giant prompt and more about the agent loop the model operates inside. In Codex, the loop is roughly: 1. Plan 2. Edit code 3. Run tools (tests/build/lint) 4. Observe results 5. Repair failures 6. Update docs/status 7. Repeat That loop matters because it gives the agent: * Real feedback (errors, diffs, logs) * Externalized state (repo, files, docs, worktrees, outputs) * Steerability over time (you can course-correct based on outcomes) This is also why Codex models feel better on Codex surfaces than a generic chat window: the harness supplies structured context (repo metadata, file tree, diffs, command outputs) and enforces a disciplined “done when” routine. We recently published an article about the Codex agent loop that has more details. To top this off, we also launched the Codex app that makes that loop usable day-to-day: * Parallel threads across projects (long work doesn’t block your day job) -------------------------------------------------------------------------------- Using Goals in Codex (https://developers.openai.com/cookbook/examples/codex/using_goals_in_codex) citeturn0search3 [wordlim: 200] Published: 6 months ago; Crawled: today; `npm install -g @openai/codex@latest ... Once the Goal is active, Codex can inspect the code, run the relevant commands, make changes, test the result, and continue until it reaches a stopping condition. ... Refactor this code is also weak unless you define the expected end state, tests, and constraints. ... That makes Goals useful for the work where Codex is already most valuable: debugging, optimization, migration, testing, and research. May 9, 2026 # Using Goals in Codex Raj Pathak (OpenAI) , Stefano Fabbri (OpenAI) View on GitHub Download raw Goals are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A Goal gives Codex a completion condition: what should be true, how success should be checked, and what constraints must stay intact. Codex already works well for well-scoped coding tasks: inspect a repository, fix a bug, add a test, explain a failure, or implement a focused change. Goals are for tasks where the next step depends on what Codex learns along the way: profiling, patching, benchmarking, reproducing a flaky test, or turning a research question into an evidence-backed audit. Those tasks do not need a bigger prompt. They need a persistent objective. With a Goal, Codex can keep the objective in view, evaluate whether the work is done, and choose the next useful action without you restating the target after every intermediate result. -------------------------------------------------------------------------------- Codex | OpenAI Developers (https://developers.openai.com/learn/codex) citeturn0search4 [wordlim: 200] Crawled: today; Follow this guide closely to ensure you’re getting th cookbook Introducing the Codex app See the Codex app in action and how it helps you build and ship faster.video Codex in JetBrains IDEs How to use Codex inside JetBrains IDEs like Rider, IntelliJ, PyCharm, and WebStorm.video Modernizing your Codebase with Codex Cookbook to modernize legacy codebases using the OpenAI Codex CLI.cookbook Codex code review Walkthrough of how Codex drives end-to-end pull request reviews with the new onboarding flow.video Build beautiful frontends with OpenAI Codex Learn how OpenAI Codex's multimodal abilities accelerate frontend development.video Context Engineering & Coding Agents with Cursor Session on structuring context for agent workflows inside the Cursor editor.video OpenAI Codex in your code editor Walkthrough of the Codex IDE extension for VS Code, Cursor, and other forks.video Shipping with Codex DevDay talk on building, testing, and delivering products with Codex.video Sora, ImageGen, and Codex: The Next Wave of Creative Production Panel discussion on combining Sora, ImageGen, and Codex for media creation.video Using OpenAI Codex CLI with GPT-5-Codex Overview of running the Codex CLI locally with GPT-5-Codex.video Codex intro Introductory video introducing Codex and its capabilities.video -------------------------------------------------------------------------------- OpenAI Developers plugin (https://developers.openai.com/learn/developers-codex-plugin) citeturn0search5 [wordlim: 200] Crawled: today; Install the OpenAI Developers plugin in ChatGPT, Codex, Claude Code, or Cursor to build, troubleshoot, and ship experiences with the OpenAI API. The OpenAI Developers plugin helps you build AI applications and agents in ChatGPT and Codex with OpenAI Platform access and OpenAI API setup guidance. ... * build an app or agent that uses the OpenAI API -------------------------------------------------------------------------------- Codex as a platform: build on the open agent harness | OpenAI Developers (https://developers.openai.com/blog/codex-as-a-platform?trk=article-ssr-frontend-pulse_little-text-block) citeturn0search6 [wordlim: 200] Published: 3 months ago; Crawled: today; Instead of asking every team to move its work into a general-purpose coding assistant, you can bring the agent into software designed around the actual job: an engineering workflow, an operations dashboard, a security investigation, a customer-support console, or an internal application built for one specialized team. ... With Codex app-server, we expose those capabilities through a documented client protocol: applications can create threads, start turns, receive events, and handle approval requests. ... * For application code that needs to start, resume, or stream Codex tasks, the official Codex SDK provides a direct programmatic interface. ... The user does not start by writing a prompt from scratch. ... If you want to build with the Codex harness, start with the open-source Codex repository, then choose the integration that fits your product: codex exec for noninteractive jobs, the Codex SDK for programmatic agent workflows, or Codex app-server for applications that need persistent conversations, streamed events, and approval handling. -------------------------------------------------------------------------------- Codex as a platform: build on the open agent harness | OpenAI Developers (https://developers.openai.com/blog/codex-as-a-platform) citeturn0search7 [wordlim: 200] Published: 3 months ago; Crawled: today; Instead of asking every team to move its work into a general-purpose coding assistant, you can bring the agent into software designed around the actual job: an engineering workflow, an operations dashboard, a security investigation, a customer-support console, or an internal application built for one specialized team. ... With Codex app-server, we expose those capabilities through a documented client protocol: applications can create threads, start turns, receive events, and handle approval requests. ... * For application code that needs to start, resume, or stream Codex tasks, the official Codex SDK provides a direct programmatic interface. ... The user does not start by writing a prompt from scratch. ... If you want to build with the Codex harness, start with the open-source Codex repository, then choose the integration that fits your product: codex exec for noninteractive jobs, the Codex SDK for programmatic agent workflows, or Codex app-server for applications that need persistent conversations, streamed events, and approval handling. -------------------------------------------------------------------------------- Agents | OpenAI Developers (https://developers.openai.com/learn/agents) citeturn0search8 [wordlim: 200] Crawled: today; Follow this guide closely to ensure you’re getting th cookbook Context Engineering & Coding Agents with Cursor Session on structuring context for agent workflows inside the Cursor editor.video Live Demo Showcase: Tools That 10x Your Codebase Live walkthrough of Codex-powered tooling that accelerates software delivery.video ChatKit advanced samples Advanced samples showcasing the capabilities of ChatKit (part of AgentKit).code ChatKit starter app Integrate ChatKit with an Agent Builder workflow in your application.code Agents SDK — Python Python SDK for developing agents with OpenAI.code Agents SDK — TypeScript TypeScript SDK for developing agents with OpenAI.code Agents SDK quickstart Step-by-step guide to quickly build agents with the OpenAI Agents SDK.guide Agents SDK quickstart Quickstart project for building agents with the Agents SDK.code Background mode guide Guide to running tasks in the background with Responses.guide Build hour — agentic tool calling Build hour giving an overview of agentic tool calling.video Build hour — built-in tools Build hour giving an overview of built-in tools available in the Responses API.video Building agents guide Official guide to building agents using the OpenAI platform.guide Building guardrails for agents Guide to implementing safeguards and guardrails in agent applications.guide Computer Use API — starter app Sample app showcasing Computer Use API integration.code Conversation state guide Guide for managing conversation state with the Responses API.guide OpenAI models page Overview of the models available on the OpenAI platform.guide Orchestrating multiple agents Guide to coordinating multiple agents with shared context.guide Realtime agent demo Video introduction to the TypeScript Agents SDK.video Realtime tool delegation guide Guide on delegating tasks through tools in realtime agents.guide Responses API — tools and features Overview video of available tools and capabilities in the Responses API.video Responses guide Introduction to the Responses API and its endpoints.guide Responses starter app Starter application demonstrating OpenAI Responses API with tools.code Responses vs. chat completions guide Comparison of the Responses API and Chat Completions.guide Tools overview guide Guide covering realtime delegation through tools.guide Tracing module Guide to monitoring and debugging agents with tracing.guide Unlock agentic power — Agents SDK Video demonstrating advanced capabilities of the Agents SDK.video Voice agents guide Guide to building voice agents using speech-to-speech API.guide CS agents demo Demo showcasing customer service agents orchestration.code Realtime agents starter app Starter app demonstrating realtime agent capabilities.code Support agent demo Demo showing a customer support agent with a human in the loop.code Eval Driven System Design - From Prototype to Production Cookbook for eval-driven design of a receipt parsing automation workflow.cookbook Multi-Agent Portfolio Collaboration with OpenAI Agents SDK Cookbook for multi-agent portfolio analysis workflows using the OpenAI Agents SDK.cookbook o3/o4-mini Function Calling Guide Cookbook to improve o3/o4-mini function calling with prompt best practices.cookbook Evals API Use-case - Responses Evaluation Cookbook to evaluate new models against stored Responses API logs.cookbook Multi-Tool Orchestration with RAG approach using OpenAI's Responses API Cookbook to route queries across tools with RAG using the Responses API.cookbook Doing RAG on PDFs using File Search in the Responses API Cookbook to search PDFs with the Responses API file search tool.cookbook Orchestrating Agents: Routines and Handoffs Cookbook for orchestrating agent workflows with routines and handoffs.cookbook -------------------------------------------------------------------------------- Build iterative repair loops with Codex (https://developers.openai.com/cookbook/examples/codex/build_iterative_repair_loops_with_codex?trk=article-ssr-frontend-pulse_little-text-block) citeturn0search9 [wordlim: 200] Published: 6 months ago; Crawled: today; Shreekant Agrawal (OpenAI) ... We’ll explore a documentation reliability workflow that detects, repairs, and validates stale or broken API and SDK examples. ... We’ll build this agent loop with Codex. ... raise RuntimeError(f"Codex exited with {result.returncode}. ... * Support knowledge refresh: Update an article, test it against current product behavior or known resolutions, and carry mismatches into the next pass. * Code modernization: Replace deprecated APIs, run tests or static checks, and use remaining failures to guide the next repair. -------------------------------------------------------------------------------- Architecture | OpenAI API (https://developers.openai.com/api/docs/guides/agents-api/architecture) citeturn0search10 [wordlim: 200] Crawled: today; * Harness: The OpenAI-hosted Codex instance that runs the model and tool loop and maintains the agent’s session. ... * Application server: Your code that connects the agent to your product. -------------------------------------------------------------------------------- Build iterative repair loops with Codex (https://developers.openai.com/cookbook/examples/codex/build_iterative_repair_loops_with_codex) citeturn0search11 [wordlim: 200] Published: 6 months ago; Crawled: today; We’ll build this agent loop with Codex. ... raise RuntimeError(f"Codex exited with {result.returncode}. ... "question": "Does the notebook avoid stale OpenAI API patterns, legacy function-calling syntax, and outdated model names?", ... * Support knowledge refresh: Update an article, test it against current product behavior or known resolutions, and carry mismatches into the next pass. * Code modernization: Replace deprecated APIs, run tests or static checks, and use remaining failures to guide the next repair.web__run, exec_commandweb__run (+2 more)
input
await Promise.allSettled([tools.web__run({open:[{ref_id:"turn0search0"}],find:[{ref_id:"turn0search0",pattern:"coding agent for software development"}],response_length:"short"}),tools.exec_command({cmd:"cat about-me.md && fc-list | head -100"}),tools.exec_command({cmd:"python3 - <<'PY'\nimport importlib.util as i\nfor m in ['PIL','numpy','scipy','matplotlib','cv2','cairo','numba','cairosvg','aggdraw','skimage','playwright']:\n print(m,i.find_spec(m) is not None)\nPY\nls /usr/share/fonts/truetype && ls /tmp | head -60 && ls -la /mnt/data 2>/dev/null"})]).then(r=>r.forEach(x=>text(x.value||x.reason)))result, 370 lines
Script completed Wall time 1.7 seconds Output: Code generation | OpenAI API (https://developers.openai.com/api/docs/guides/code-generation) citeturn1view0 [wordlim: 200] Crawled: today; Content type: text/html; Source: open({"ref_id":"turn0search0","lineno":null}); Total lines: 1295 L940: ### Prompting L941: L942: * 【60†Overview】 L943: * 【61†Prompt engineering】 L944: * 【62†Citation formatting】 L945: * 【63†Migration guide】 L946: * 【64†Prompt generation】 L947: * 【65†Frontend prompting】 L948: L949: ### Reasoning L950: L951: * 【66†Reasoning models】 L952: * 【67†Reasoning best practices】 L953: L954: ### Images L955: L956: * 【68†Images and vision】 L957: * 【69†Image input cost calculator】 L958: * 【70†Image generation】 L959: * 【70†Overview】 L960: * 【71†Image prompting】 L961: L962: ### Realtime and audio L963: L964: * 【12†Audio and speech】 L965: * 【72†Getting started】 L966: * 【73†Voice agents】 L967: ### Specialized models L968: L969: * 【74†Embeddings】 L970: * 【75†Moderation】 L971: * 【76†CSAM classifier】 L972: L973: # Code generation L974: L975: Copy Page L976: L977: Learn how to use OpenAI models and Codex to generate code. L978: L979: Writing, reviewing, editing, and answering questions about code is one of the primary use cases for OpenAI models today. This guide walks through your options for code generation with 【568†`gpt-6.2-astra`】 and Codex. L980: ## Get started L981: L982: 【569†Use Codex for out-of-the-box coding agents Connect your codebase to Codex and accelerate your projects using software engineering agents.】【570†Integrate with coding models Use OpenAI models in your application. Add them to a model picker, for instance.】 L983: ## Use Codex L984: L985: 【571†Codex】 is OpenAI’s coding agent for software development. It helps you write, review and debug code. Interact with Codex in a variety of interfaces: in your IDE, through the CLI, on web and mobile sites, or in your CI/CD pipelines with the SDK. Codex is the best way to get agentic software engineering on your projects. L986: L987: Codex works best with the latest general-purpose models, such as 【572†`gpt-6.1-sol`】. L988: See the 【4†ChatGPT docs】 for setup guides, reference material, pricing, and more information. L989: ## Integrate with coding models L990: L991: For most API-based code generation, start with `gpt-6.2-astra`. It handles both general-purpose work and coding, which makes it a strong default when your application needs to write code, reason about requirements, inspect docs, and handle broader workflows in one place. L992: L993: This example shows how you can use the 【573†Responses API】 for a code generation use case: L994: L995: Default model for most coding tasks L996: Python L997: L998: `1 L999: 2 L1000: 3 L1001: 4 L1002: 5 L1003: 6 L1004: 7 L1005: 8 L1006: 9 L1007: 10 L1008: 11 L1009: 12 L1010: 13 L1011: 14 L1012: 15 L1013: 16 import OpenAI from "openai"; L1014: const openai = new OpenAI(); L1015: L1016: const result = await openai.responses.create({ L1017: model: "gpt-6.2-astra", L1018: input: `Find the null pointer exception in this code: L1019: L1020: def display_name(user): L1021: return user.profile.name L1022: L1023: print(display_name(None)) L1024: `, L1025: reasoning: { effort: "high" }, L1026: }); L1027: console.log(result.output_text);` L1028: L1029: `1 L1030: 2 L1031: 3 L1032: 4 L1033: 5 L1034: 6 L1035: 7 L1036: 8 L1037: 9 L1038: 10 L1039: 11 L1040: 12 L1041: 13 L1042: 14 L1043: 15 L1044: 16 L1045: 17 from openai import OpenAI L1046: L1047: client = OpenAI() L1048: L1049: result = client.responses.create( L1050: model="gpt-6.2-astra", L1051: input="""Find the null pointer exception in this code: L1052: L1053: def display_name(user): L1054: return user.profile.name L1055: L1056: print(display_name(None)) L1057: """, L1058: reasoning={"effort": "high"}, L1059: ) L1060: print(result.output_text)` L1061: L1062: `1 L1063: 2 L1064: 3 L1065: 4 L1066: 5 L1067: 6 L1068: 7 L1069: 8 L1070: 9 L1071: 10 L1072: 11 L1073: 12 L1074: 13 L1075: 14 L1076: 15 L1077: 16 L1078: 17 L1079: 18 L1080: 19 L1081: 20 L1082: 21 L1083: 22 L1084: 23 L1085: 24 L1086: 25 L1087: 26 L1088: 27 L1089: 28 package main L1090: L1091: import ( L1092: "context" L1093: "fmt" L1094: L1095: "github.com/openai/openai-go/v3" L1096: "github.com/openai/openai-go/v3/responses" L1097: "github.com/openai/openai-go/v3/shared" L1098: ) L1099: L1100: func main() { L1101: client := openai.NewClient() L1102: response, err := client.Responses.New(context.Background(), responses.ResponseNewParams{ L1103: Model: "gpt-6.2-astra", L1104: Input: responses.ResponseNewParamsInputUnion{OfString: openai.String(`Find the null pointer exception in this code: L1105: L1106: def display_name(user): L1107: return user.profile.name L1108: L1109: print(display_name(None))`)}, L1110: Reasoning: shared.ReasoningParam{Effort: shared.ReasoningEffortHigh}, L1111: }) L1112: if err != nil { L1113: panic(err) L1114: } L1115: fmt.Println(response.OutputText()) L1116: }` L1117: L1118: `1 L1119: 2 L1120: 3 L1121: 4 L1122: 5 L1123: 6 L1124: 7 L1125: 8 L1126: 9 L1127: 10 L1128: 11 L1129: 12 L1130: 13 L1131: 14 L1132: 15 L1133: 16 L1134: 17 L1135: 18 L1136: 19 L1137: 20 L1138: 21 L1139: 22 L1140: 23 L1141: 24 L1142: 25 L1143: 26 import com.openai.client.OpenAIClient; L1144: import com.openai.client.okhttp.OpenAIOkHttpClient; L1145: import com.openai.models.Reasoning; L1146: import com.openai.models.ReasoningEffort; L1147: import com.openai.models.responses.ResponseCreateParams; L1148: L1149: String code = L1150: """ L1151: def display_name(user): L1152: return user.profile.name L1153: L1154: print(display_name(None)) L1155: """; L1156: L1157: ResponseCreateParams params = L1158: ResponseCreateParams.builder() L1159: .model("gpt-6.2-astra") L1160: .input("Find the null pointer exception in this code:\n\n" + code) L1161: .reasoning(Reasoning.builder().effort(ReasoningEffort.HIGH).build()) L1162: .build(); L1163: L1164: client.responses().create(params).output().stream() L1165: .flatMap(item -> item.message().stream()) L1166: .flatMap(message -> message.content().stream()) L1167: .flatMap(content -> content.outputText().stream()) L1168: .forEach(text -> System.out.println(text.text()));` L1169: L1170: `1 L1171: 2 L1172: 3 L1173: 4 L1174: 5 L1175: 6 L1176: 7 L1177: 8 L1178: 9 L1179: 10 L1180: 11 L1181: 12 L1182: 13 L1183: 14 L1184: 15 L1185: 16 L1186: 17 L1187: 18 L1188: 19 L1189: 20 L1190: 21 L1191: 22 L1192: 23 L1193: 24 L1194: 25 L1195: 26 L1196: 27 L1197: 28 L1198: 29 using OpenAI.Responses; L1199: #pragma warning disable OPENAI001 L1200: string key = Environment.GetEnvironmentVariable("OPENAI_API_KEY")!; L1201: ResponsesClient client = new(key); L1202: L1203: CreateResponseOptions options = new() L1204: { L1205: Model = "gpt-6.2-astra", L1206: ReasoningOptions = new ResponseReasoningOptions L1207: { L1208: ReasoningEffortLevel = ResponseReasoningEffortLevel.High, L1209: }, L1210: }; L1211: options.InputItems.Add( L1212: ResponseItem.CreateUserMessageItem( L1213: """ L1214: Find the null pointer exception in this code: L1215: def display_name(user): L1216: return user.profile.name L1217: L1218: print(display_name(None)) L1219: """ L1220: ) L1221: ); L1222: L1223: ResponseResult response = await client.CreateResponseAsync(options); L1224: Console.WriteLine(response.GetOutputText());` L1225: L1226: `1 L1227: 2 L1228: 3 L1229: 4 L1230: 5 L1231: 6 L1232: 7 L1233: 8 L1234: 9 L1235: 10 L1236: 11 L1237: 12 L1238: 13 L1239: 14 L1247: return user.profile.name L1248: L1249: print(display_name(None)) L1250: PYTHON L1251: L1252: response = client.responses.create( L1253: model: "gpt-6.2-astra", L1254: input: "Find the null pointer exception in this code:\n\n#{code}", L1255: reasoning: { effort: :high } L1256: ) L1257: L1258: puts(response.output_text)` L1259: L1260: `1 L1261: 2 L1262: 3 L1263: 4 L1264: 5 L1265: 6 L1266: 7 L1267: 8 curl https://api.openai.com/v1/responses \ L1268: -H "Content-Type: application/json" \ L1269: -H "Authorization: [redacted: secret] $OPENAI_API_KEY" \ L1270: -d '{ L1271: "model": "gpt-6.2-astra", L1272: "input": "Find the null pointer exception in this code:\n\ndef display_name(user):\n return user.profile.name\n\nprint(display_name(None))\n", L1273: "reasoning": { "effort": "high" } L1274: }'` L1275: ## Frontend development L1276: L1277: For frontend work, start with `gpt-6.1-sol` or `gpt-6.2-astra` in Codex or the Responses API. L1278: L1279: The historical GPT-5 gallery shows applications generated from a single prompt. Use the prompts as starting points and evaluate the results with the model you plan to deploy. L1280: L1281: Explore L1282: ## Next steps L1283: L1284: * Visit the 【4†ChatGPT docs】 to learn what you can do with Codex, set up Codex in whichever interface you choose, or find more details. L1285: * Read 【16†Model guidance】 for model selection, features, migration guidance, and prompting patterns that work well on coding and agentic tasks. L1286: * Compare 【568†`gpt-6.2-astra`】 and 【572†`gpt-6.1-sol`】 on the model pages. L1287: L1288: 【57†Previous Text generation】 【59†Next Structured output】 L1289: L1290: Ask AI L1291: L1292: ## Docs agent L1293: L1294: Loading docs agent... -------------------------------------------------------------------------------- Code generation | OpenAI API (https://developers.openai.com/api/docs/guides/code-generation) citeturn1view1 [wordlim: 200] Crawled: today; Content type: text/html; Source: find({"ref_id":"turn0search0","pattern":"coding agent for software development"}); Total lines: 1295 L983: ## Use Codex L984: L985: 【571†Codex】 is OpenAI’s coding agent for software development. It helps you write, review and debug code. Interact with Codex in a variety of interfaces: in your IDE, through the CLI, on web and mobile sites, or in your CI/CD pipelines with the SDK. Codex is the best way to get agentic software engineering on your projects. L986: L987: Codex works best with the latest general-purpose models, such as 【572†`gpt-6.1-sol`】. L988: See the 【4†ChatGPT docs】 for setup guides, reference material, pricing, and more information. L989: ## Integrate with coding models L990: L991: For most API-based code generation, start with `gpt-6.2-astra`. It handles both general-purpose work and coding, which makes it a strong default when your application needs to write code, reason about requirements, inspect docs, and handle broader workflows in one place. L992: L993: This example shows how you can use the 【573†Responses API】 for a code generation use case: L994: L995: Default model for most coding tasks {"chunk_id":"b534e3","wall_time_seconds":0.41281527,"exit_code":0,"original_token_count":2161,"output":"I'm Severian. I run citadel, a setup where many AI sessions work on my projects at once. What each of you does in it: Opus 5.5 leads and builds; Sonnet 5.5 handles chores and test data; Fable 5.2 is my design partner and critic; GPT-6.2-Astra, taking over from GPT-6-Astra, critiques designs; GPT-6.2-Sol, taking over from GPT-6.1-Sol, reviews code and deploys./usr/share/fonts/truetype/dejavu/DejaVuSerif-Bold.ttf: DejaVu Serif:style=Bold\n/usr/share/fonts/opentype/urw-base35/URWBookman-LightItalic.otf: URW Bookman:style=Light Italic\n/usr/share/fonts/opentype/urw-base35/URWBookman-Light.otf: URW Bookman:style=Light\n/usr/share/fonts/truetype/dejavu/DejaVuSansMono.ttf: DejaVu Sans Mono:style=Book\n/usr/share/fonts/truetype/ubuntu/UbuntuMono-RI.ttf: Ubuntu Mono:style=Italic\n/usr/share/fonts/opentype/urw-base35/NimbusMonoPS-Italic.otf: Nimbus Mono PS:style=Italic\n/usr/share/fonts/truetype/noto/NotoSansMono-Regular.ttf: Noto Sans Mono:style=Regular\n/usr/share/fonts/opentype/urw-base35/P052-Italic.otf: P052:style=Italic\n/usr/share/fonts/type1/urw-base35/URWGothic-BookOblique.t1: URW Gothic:style=Book Oblique\n/usr/share/fonts/type1/gsfonts/n021024l.pfb: Nimbus Roman No9 L:style=Medium Italic\n/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf: DejaVu Sans:style=Book\n/usr/share/fonts/opentype/urw-base35/NimbusSans-Regular.otf: Nimbus Sans:style=Regular\n/usr/share/fonts/type1/urw-base35/URWBookman-DemiItalic.t1: URW Bookman:style=Demi Italic\n/usr/share/fonts/opentype/urw-base35/NimbusSansNarrow-Oblique.otf: Nimbus Sans Narrow:style=Oblique\n/usr/share/fonts/type1/urw-base35/NimbusSans-Regular.t1: Nimbus Sans:style=Regular\n/usr/share/fonts/truetype/ubuntu/UbuntuMono-B.ttf: Ubuntu Mono:style=Bold\n/usr/share/fonts/opentype/urw-base35/C059-Roman.otf: C059:style=Roman\n/usr/share/fonts/type1/gsfonts/n021004l.pfb: Nimbus Roman No9 L:style=Medium\n/usr/share/fonts/opentype/urw-base35/NimbusMonoPS-BoldItalic.otf: Nimbus Mono PS:style=Bold Italic\n/usr/share/fonts/type1/urw-base35/URWGothic-DemiOblique.t1: URW Gothic:style=Demi Oblique\n/usr/share/fonts/type1/gsfonts/p052023l.pfb: URW Palladio L:style=Italic\n/usr/share/fonts/type1/gsfonts/n022003l.pfb: Nimbus Mono L:style=Regular\n/usr/share/fonts/type1/gsfonts/z003034l.pfb: URW Chancery L:style=Medium Italic\n/usr/share/fonts/truetype/ubuntu/Ubuntu-L.ttf: Ubuntu,Ubuntu Light:style=Light,Regular\n/usr/share/fonts/type1/urw-base35/URWBookman-LightItalic.t1: URW Bookman:style=Light Italic\n/usr/share/fonts/opentype/urw-base35/NimbusSansNarrow-BoldOblique.otf: Nimbus Sans Narrow:style=Bold Oblique\n/usr/share/fonts/truetype/ubuntu/Ubuntu-BI.ttf: Ubuntu:style=Bold Italic\n/usr/share/fonts/type1/gsfonts/c059013l.pfb: Century Schoolbook L:style=Roman\n/usr/share/fonts/type1/urw-base35/NimbusSansNarrow-BoldOblique.t1: Nimbus Sans Narrow:style=Bold Oblique\n/usr/share/fonts/opentype/urw-base35/NimbusSans-Bold.otf: Nimbus Sans:style=Bold\n/usr/share/fonts/type1/urw-base35/NimbusMonoPS-Italic.t1: Nimbus Mono PS:style=Italic\n/usr/share/fonts/type1/urw-base35/NimbusRoman-BoldItalic.t1: Nimbus Roman:style=Bold Italic\n/usr/share/fonts/opentype/urw-base35/Z003-MediumItalic.otf: Z003:style=Medium Italic\n/usr/share/fonts/opentype/urw-base35/NimbusSans-BoldItalic.otf: Nimbus Sans:style=Bold Italic\n/usr/share/fonts/opentype/urw-base35/URWGothic-Book.otf: URW Gothic:style=Book\n/usr/share/fonts/truetype/ubuntu/Ubuntu-Th.ttf: Ubuntu,Ubuntu Thin:style=Thin,Regular\n/usr/share/fonts/type1/gsfonts/d050000l.pfb: Dingbats:style=Regular\n/usr/share/fonts/truetype/ubuntu/Ubuntu-RI.ttf: Ubuntu:style=Italic\n/usr/share/fonts/type1/gsfonts/n021023l.pfb: Nimbus Roman No9 L:style=Regular Italic\n/usr/share/fonts/opentype/urw-base35/D050000L.otf: D050000L:style=Regular\n/usr/share/fonts/type1/gsfonts/n019063l.pfb: Nimbus Sans L:style=Regular Condensed Italic\n/usr/share/fonts/opentype/urw-base35/C059-BdIta.otf: C059:style=Bold Italic\n/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf: DejaVu Sans:style=Bold\n/usr/share/fonts/type1/gsfonts/a010013l.pfb: URW Gothic L:style=Book\n/usr/share/fonts/opentype/urw-base35/NimbusRoman-Regular.otf: Nimbus Roman:style=Regular\n/usr/share/fonts/truetype/ubuntu/Ubuntu-MI.ttf: Ubuntu,Ubuntu Light:style=Medium Italic,Bold Italic\n/usr/share/fonts/opentype/urw-base35/C059-Italic.otf: C059:style=Italic\n/usr/share/fonts/opentype/urw-base35/NimbusMonoPS-Bold.otf: Nimbus Mono PS:style=Bold\n/usr/share/fonts/opentype/urw-base35/NimbusRoman-Bold.otf: Nimbus Roman:style=Bold\n/usr/share/fonts/type1/urw-base35/NimbusSansNarrow-Bold.t1: Nimbus Sans Narrow:style=Bold\n/usr/share/fonts/opentype/urw-base35/NimbusRoman-BoldItalic.otf: Nimbus Roman:style=Bold Italic\n/usr/share/fonts/truetype/ubuntu/UbuntuMono-BI.ttf: Ubuntu Mono:style=Bold Italic\n/usr/share/fonts/truetype/ubuntu/Ubuntu-B.ttf: Ubuntu:style=Bold\n/usr/share/fonts/type1/gsfonts/n019064l.pfb: Nimbus Sans L:style=Bold Condensed Italic\n/usr/share/fonts/truetype/droid/DroidSansFallbackFull.ttf: Droid Sans Fallback:style=Regular\n/usr/share/fonts/type1/gsfonts/p052004l.pfb: URW Palladio L:style=Bold\n/usr/share/fonts/type1/urw-base35/C059-Roman.t1: C059:style=Roman\n/usr/share/fonts/type1/urw-base35/NimbusRoman-Italic.t1: Nimbus Roman:style=Italic\n/usr/share/fonts/opentype/urw-base35/NimbusSans-Italic.otf: Nimbus Sans:style=Italic\n/usr/share/fonts/type1/gsfonts/n022023l.pfb: Nimbus Mono L:style=Regular Oblique\n/usr/share/fonts/truetype/ubuntu/UbuntuMono-R.ttf: Ubuntu Mono:style=Regular\n/usr/share/fonts/type1/urw-base35/URWBookman-Demi.t1: URW Bookman:style=Demi\n/usr/share/fonts/truetype/ubuntu/Ubuntu-LI.ttf: Ubuntu,Ubuntu Light:style=Light Italic,Italic\n/usr/share/fonts/type1/gsfonts/a010015l.pfb: URW Gothic L:style=Demi\n/usr/share/fonts/type1/urw-base35/URWGothic-Book.t1: URW Gothic:style=Book\n/usr/share/fonts/truetype/dejavu/DejaVuSansMono-Bold.ttf: DejaVu Sans Mono:style=Bold\n/usr/share/fonts/type1/urw-base35/NimbusRoman-Regular.t1: Nimbus Roman:style=Regular\n/usr/share/fonts/opentype/urw-base35/NimbusMonoPS-Regular.otf: Nimbus Mono PS:style=Regular\n/usr/share/fonts/opentype/urw-base35/NimbusSansNarrow-Regular.otf: Nimbus Sans Narrow:style=Regular\n/usr/share/fonts/type1/gsfonts/n019043l.pfb: Nimbus Sans L:style=Regular Condensed\n/usr/share/fonts/opentype/urw-base35/URWBookman-Demi.otf: URW Bookman:style=Demi\n/usr/share/fonts/type1/urw-base35/NimbusMonoPS-Regular.t1: Nimbus Mono PS:style=Regular\n/usr/share/fonts/type1/urw-base35/NimbusSans-BoldItalic.t1: Nimbus Sans:style=Bold Italic\n/usr/share/fonts/type1/urw-base35/NimbusSans-Bold.t1: Nimbus Sans:style=Bold\n/usr/share/fonts/type1/gsfonts/n019044l.pfb: Nimbus Sans L:style=Bold Condensed\n/usr/share/fonts/type1/urw-base35/NimbusMonoPS-BoldItalic.t1: Nimbus Mono PS:style=Bold Italic\n/usr/share/fonts/type1/urw-base35/StandardSymbolsPS.t1: Standard Symbols PS:style=Regular\n/usr/share/fonts/opentype/urw-base35/URWGothic-Demi.otf: URW Gothic:style=Demi\n/usr/share/fonts/type1/gsfonts/a010033l.pfb: URW Gothic L:style=Book Oblique\n/usr/share/fonts/type1/gsfonts/n021003l.pfb: Nimbus Roman No9 L:style=Regular\n/usr/share/fonts/type1/gsfonts/s050000l.pfb: Standard Symbols L:style=Regular\n/usr/share/fonts/truetype/ubuntu/Ubuntu-R.ttf: Ubuntu:style=Regular\n/usr/share/fonts/opentype/urw-base35/NimbusSansNarrow-Bold.otf: Nimbus Sans Narrow:style=Bold\n/usr/share/fonts/opentype/urw-base35/URWBookman-DemiItalic.otf: URW Bookman:style=Demi Italic\n/usr/share/fonts/opentype/urw-base35/URWGothic-BookOblique.otf: URW Gothic:style=Book Oblique\n/usr/share/fonts/type1/gsfonts/b018035l.pfb: URW Bookman L:style=Demi Bold Italic\n/usr/share/fonts/type1/gsfonts/c059033l.pfb: Century Schoolbook L:style=Italic\n/usr/share/fonts/type1/urw-base35/Z003-MediumItalic.t1: Z003:style=Medium Italic\n/usr/share/fonts/type1/urw-base35/P052-BoldItalic.t1: P052:style=Bold Italic\n/usr/share/fonts/type1/urw-base35/C059-Italic.t1: C059:style=Italic\n/usr/share/fonts/type1/gsfonts/a010035l.pfb: URW Gothic L:style=Demi Oblique\n/usr/share/fonts/type1/urw-base35/P052-Roman.t1: P052:style=Roman\n/usr/share/fonts/truetype/ubuntu/Ubuntu-M.ttf: Ubuntu,Ubuntu Light:style=Medium,Bold\n/usr/share/fonts/type1/urw-base35/NimbusRoman-Bold.t1: Nimbus Roman:style=Bold\n/usr/share/fonts/type1/urw-base35/NimbusSansNarrow-Oblique.t1: Nimbus Sans Narrow:style=Oblique\n/usr/share/fonts/opentype/urw-base35/P052-BoldItalic.otf: P052:style=Bold Italic\n/usr/share/fonts/truetype/noto/NotoSansMono-Bold.ttf: Noto Sans Mono:style=Bold\n/usr/share/fonts/truetype/ubuntu/Ubuntu-C.ttf: Ubuntu Condensed:style=Regular\n/usr/share/fonts/type1/urw-base35/D050000L.t1: D050000L:style=Regular\n/usr/share/fonts/opentype/urw-base35/StandardSymbolsPS.otf: Standard Symbols PS:style=Regular\n"}{"chunk_id":"f2b68f","wall_time_seconds":0.003093722,"exit_code":2,"original_token_count":57,"output":"PIL True\nnumpy False\nscipy False\nmatplotlib False\ncv2 False\ncairo False\nnumba False\ncairosvg False\naggdraw False\nskimage False\nplaywright False\ndejavu\ndroid\nnoto\nubuntu\ncodex-bwrap-synthetic-mount-targets-1000\ncodex-daemon-1000\n"}exec_commandls -la /opt && ls -la /usr/bin/chrom* && command -v chromium && node -v || true (+1 more)
command
ls -la /opt && ls -la /usr/bin/chrom* && command -v chromium && node -v || true rg --files /opt /usr/lib -g 'package.json' 2>/dev/null | rg '(puppeteer|playwright|canvas|three|sharp)/package' | head -50 ls /usr/lib/chromium* command -v g++ && ls /usr/include | rg 'cairo|png|SDL|GL|eigen|jpeg' && ffmpeg -hide_banner -encoders 2>/dev/null | rg '264|aac' && nproc && cat /sys/fs/cgroup/cpu.max && df -h /tmp
result, 4 lines
Script completed Wall time 0.4 seconds Output: {"chunk_id":"d907e1","wall_time_seconds":0.24155641,"exit_code":2,"original_token_count":115,"output":"total 12\ndrwxr-xr-x 6 runner runner 120 Nov 18 00:42 .\ndrwxr-xr-x 10 runner runner 280 Nov 18 00:42 ..\ndrwx------ 7 runner runner 4096 Nov 18 00:42 cfg\ndrwx------ 4 runner runner 4096 Nov 14 06:23 codex\ndrwx------ 12 runner runner 240 Nov 18 00:42 ms-playwright\ndrwx------ 4 runner runner 4096 Nov 11 07:55 node\n-rwxr-xr-x 1 nobody nogroup 2408 Sep 18 2020 /usr/bin/chromium-browser\nls: cannot access '/usr/lib/chromium*': No such file or directory\n"}{"chunk_id":"e31bc1","wall_time_seconds":0.000008311,"exit_code":1,"original_token_count":4,"output":"/usr/bin/g++\n"}exec_commandls -la /opt/ms-playwright && rg --files /opt/ms-playwright | rg '/(chrome|headless_shell|ffmpeg-linux)$' && ls /opt/node/lib/node_modules && python3 -m pip list 2>/dev/null | head -100 (+1 more)
command
ls -la /opt/ms-playwright && rg --files /opt/ms-playwright | rg '/(chrome|headless_shell|ffmpeg-linux)$' && ls /opt/node/lib/node_modules && python3 -m pip list 2>/dev/null | head -100 ffmpeg -hide_banner -encoders 2>/dev/null | rg '264|aac' nproc cat /sys/fs/cgroup/cpu.max df -h /tmp node -v command -v curl ls /usr/bin | rg 'sox|flite|ffmpeg|glsl|povray|soxi'
result, 4 lines
Script completed Wall time 1.0 seconds Output: {"chunk_id":"5cc987","wall_time_seconds":0.767114933,"exit_code":0,"original_token_count":653,"output":"total 40\ndrwx------ 12 runner runner 240 Nov 18 00:42 .\ndrwxr-xr-x 6 runner runner 120 Nov 18 00:42 ..\ndrwxr-xr-x 3 runner runner 4096 Apr 5 2026 chromium-1200\ndrwxr-xr-x 3 runner runner 4096 Sep 8 17:12 chromium-1208\ndrwx------ 3 runner runner 4096 Oct 23 16:31 chromium-1248\ndrwxr-xr-x 3 runner runner 4096 Apr 5 2026 chromium_headless_shell-1200\ndrwxr-xr-x 3 runner runner 4096 Sep 8 17:12 chromium_headless_shell-1208\ndrwx------ 3 runner runner 4096 Oct 23 16:31 chromium_headless_shell-1248\ndrwxr-xr-x 2 runner runner 4096 Feb 18 2026 ffmpeg-1011\ndrwx------ 2 runner runner 4096 Oct 23 16:31 ffmpeg-1013\ndrwx------ 3 runner runner 4096 Nov 6 18:20 firefox-1555\ndrwx------ 4 runner runner 4096 Nov 6 18:20 webkit-2370\n/opt/ms-playwright/chromium-1200/chrome-linux64/chrome\n/opt/ms-playwright/chromium-1208/chrome-linux64/chrome\n/opt/ms-playwright/chromium-1248/chrome-linux64/chrome\n/opt/ms-playwright/ffmpeg-1011/ffmpeg-linux\n/opt/ms-playwright/ffmpeg-1013/ffmpeg-linux\ncorepack\nnpm\nPackage Version\n---------------------- ---------------\nawscli 1.22.34\nblinker 1.4\nbotocore 1.23.34\ncertifi 2020.6.20\nchardet 4.0.0\ncolorama 0.4.4\ncommand-not-found 0.3\ncryptography 3.4.8\ndbus-python 1.2.18\ndistro 1.7.0\ndistro-info 1.1build1\ndocutils 0.17.1\ngyp 0.1\nhttplib2 0.20.2\nidna 3.3\nimportlib-metadata 4.6.4\njeepney 0.7.1\njmespath 0.10.0\nkeyring 23.5.0\nlaunchpadlib 1.10.16\nlazr.restfulclient 0.14.4\nlazr.uri 1.0.6\nmore-itertools 8.10.0\nnetifaces 0.11.0\noauthlib 3.2.0\nolefile 0.46\nPillow 9.0.1\npip 22.0.2\npyasn1 0.4.8\nPygments 2.11.2\nPyGObject 3.42.1\nPyJWT 2.3.0\npyparsing 2.4.7\npython-apt 2.4.0+ubuntu4.1\npython-dateutil 2.8.1\nPyYAML 5.4.1\nrequests 2.25.1\nroman 3.3\nrsa 4.8\ns3transfer 0.5.0\nSecretStorage 3.3.1\nsetuptools 59.6.0\nsix 1.16.0\nssh-import-id 5.11\nsystemd-python 234\nubuntu-advantage-tools 8001\nufw 0.36.1\nunattended-upgrades 0.1\nurllib3 1.26.5\nwadllib 1.3.6\nwheel 0.37.1\nzipp 1.0.0\n"}{"chunk_id":"a65169","wall_time_seconds":0.005930855,"exit_code":0,"original_token_count":241,"output":" V..... libx264 libx264 H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10 (codec h264)\n V..... libx264rgb libx264 H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10 RGB (codec h264)\n V....D h264_nvenc NVIDIA NVENC H.264 encoder (codec h264)\n V..... h264_omx OpenMAX IL H.264 video encoder (codec h264)\n V..... h264_qsv H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10 (Intel Quick Sync Video acceleration) (codec h264)\n V..... h264_v4l2m2m V4L2 mem2mem H.264 encoder wrapper (codec h264)\n V....D h264_vaapi H.264/AVC (VAAPI) (codec h264)\n V..... nvenc NVIDIA NVENC H.264 encoder (codec h264)\n V..... nvenc_h264 NVIDIA NVENC H.264 encoder (codec h264)\n A..... aac AAC (Advanced Audio Coding)\n10\ncat: /sys/fs/cgroup/cpu.max: No such file or directory\nFilesystem Size Used Avail Use% Mounted on\ntmpfs 25G 64K 25G 1% /tmp\nv22.21.1\n/usr/bin/curl\nffmpeg\n"}