messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "…[earlier truncated]…\ned = (blocks / scales).abs()\\n levels = torch.tensor(FP4_LEVELS)\\n distances = (normalized.unsqueeze(-1) - levels).abs().amin(dim=-1)\\n assert float(distances.max()) < 1e-5\\n\\n\\ndef test_quanti …[truncated]\nResult: File created successfull... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a queue that supports standard enqueue and dequeue operations, as well as a method to retrieve the minimum element currently in the queue in constant time, O(1). You need to implement a function `min_queue_operations(operations: List[Tuple[str, ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of strings. Your task is to implement a function that calculates the total number of characters present in all the strings combined. The function should take a list of strings as input and return an integer representing the total character count. Note that ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": " 's');\\n root.style.setProperty('--sweep-delay', (maxEndTime + 0.15).toFixed(3) + 's');\", \"old_string\": \" // Light sweep fires right as the draw finishes, whatever the settings.\\n root.style.setProperty('--sweep-delay', Math.max(0, maxEndTime - 0.1).t... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a metadata validation function for a monitoring agent. The function should validate metadata values based on a regular expression pattern. Implement the function `validate_metadata` that takes the following parameters: \n- `metadata`: a dictiona... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "ne sentence each\\\" && tmux send-keys -t glint C-m\\nsleep 8\\nfor i in 1 2 3 4; do tmux send-keys -t glint PageUp; sleep 0.3; done\\necho \\\"### during-run scrolled up?\\\"; tmux capture-pane -t glint -p | grep -c -i \\\"scrolled up\\\"; echo \\\"top:\\\"; tmux capture-pane ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntillation from an ensemble of teachers trained on a small dataset with no performance penalty\",\"url\":\"https://arxiv.org/abs/2308.02019\"},{\"title\":\"[2308.02019v2] Baby Llama: knowledge distillation from an ensemble of teachers trained on a small da... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n;\\n const [stream, setStream] = useState(\\\"\\\");\\n const [activeTool, setActiveTool] = useState<{ tool: string; hint: string } | null>(null);\", \"new_string\": \" const [running, setRunning] = useState(false);\\n const [activeTool, setActiveTool... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "continue\nAssistant action: Write {\"file_path\": \"D:\\\\fps\\\\src\\\\enemy.js\", \"content\": \"import * as THREE from 'three';\\nimport { buildSoldier } from './soldier.js';\\n\\nexport const BOT_STATE = { PATROL: 0, ALERT: 1, COMBAT: 2, HUNT: 3, DEAD: 4 };\\n\\nconst _ray ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "ethod, headers: {} };\\n if (body !== undefined) {\\n options.headers[\\\"Content-Type\\\"] = \\\"application/json\\\";\\n options.body = JSON.stringify(body);\\n }\\n const response = await fetch(url, options);\\n let payload = null;\\n try { payload = await respons... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "As a senior engineer mentoring someone, i'm skeptical and critical for a blog post because writing a philosophy essay on autonomous weapons ethics. I'm a team lead trying to figure out the strongest version of the pro-autonomy argument and where it breaks. Where's the line wher... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": " (PgUp/PgDn, shift+↑/↓) again.\n2. **Memory realigned** to your intent — `remember` now stores only **how-to procedures for this environment** (build/test/deploy commands, env vars), explicitly *not* conversation facts or trivia. Three stores clarified in the prompt: `create_sk... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "now ensure smooth gameplay and all features work properly, assume three players which you will create \nAssistant: Three-player verification plan: fix two gameplay issues I already know about (all players spawn on the exact same point and stack inside each other; leavers stay o... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "how much compute would this take for like a 9B model with high context? ideally we use Qwen3.5-9B and retain it's multimodal capabilities.\nAssistant: Let me verify what Qwen3.5-9B actually is (size class, context, whether it's natively multimodal) before doing the math — it's ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that processes user data represented as a list of dictionaries. Each dictionary contains user details such as name, email, and age. Your function should return a list of unique email addresses from the input user data. If there are duplic... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of integers `nums` and a specific integer `k`. Your task is to implement a function `process_list(nums, k)` that processes the list and prints 'Skipping: ' followed by the value of `k` for each occurrence of `k` in the list. If `k` is not present in the lis... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsfully and its contents have been verified.\n\n- **Action taken:** Used `write_file` to create `hello.txt` with the exact text `glint was here`.\n- **Verification:** Read the file back with `read_file`, which returned:\n\n```\n1| glint was here\n```\n\nTh... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given an array of integers. Your task is to implement a function that sorts the array using the bubble sort algorithm and returns the number of swaps performed and the first element of the sorted array. The bubble sort algorithm works by repeatedly stepping through the ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": " \\\"[verification check] You modified a file but haven't confirmed the result. Confirm it the way that fits \nResult: The file /home/lane/GR/glint-cli/src/core/agent.ts has been updated successfully. (file state is current in your context — no need to Read it back)\nAssi... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "As a helpful assistant, i'm an embedded systems engineer here, for a blog post. I'm paranoid about edge cases about the halting problem and why undecidability doesn't stop static analysis — how practical tools get around the theoretical limit. What are we actually sacrificing w... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "As a technical writer helping draft educational content, for a blog post, I'm dealing with writing a blog post about facial recognition in public spaces. I'm a tech lead reviewing code who wants the technical pipeline at a high level and what privacy-critical steps are. What wo... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that validates a list of user inputs for a command-line application. The function should check if a list of required arguments is provided by the user. If any required argument is missing, the function should raise a `ValueError` with a s... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "ter(([, t]) => !t.needsApproval))\\n : tools;\", \"old_string\": \" // A pure greeting gets a friendly reply and NO tools at all \\u2014 not even\\n // read-only ones, so the model can't go \\\"investigate\\\" the project on \\\"hi\\\".\\n const casual = isCasualChat(us... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that takes the name of a machine learning execution and its creation time, and returns a dictionary that represents the serialized execution data. The dictionary should contain the following keys and their corresponding values: 'name'... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a senior software engineer helping a colleague. Be practical and specific."
},
{
"role": "user",
"content": "I need to add real-time notifications to our web app. What are my options?"
},
{
"role": "assistant",
"content": "Here are your main op... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Please add more recent and useful papers, those are all pretty old and basic\nAssistant: More fresh papers. Hunt 2025–2026 work.\nAssistant action: WebSearch {\"query\": \"arxiv 2026 small language model training recipe state of the art efficient\"}\nAssistant action: WebSearch... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "User: Hai"
},
{
"role": "assistant",
"content": "There's an issue with the selected model (claude-fable-5). It may not exist or you may not have access to it. Run /model to pick a different model."
}
] | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to manage the title of an HTML document. Write a function `set_html_title` that takes a single parameter `title`. The function should set the title of the HTML document to the provided string if it is valid. If the title is not a stri... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that formats a title string for a blogging platform. Your function should accept a string as input and return a formatted version of the title. If the title exceeds 20 characters, return the first 20 characters followed by an ellipsis ('.... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a metadata validation function for a monitoring agent. The function should validate metadata values based on a regular expression pattern. Implement the function `validate_metadata` that takes the following parameters: \n- `metadata`: a dictiona... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a 2D grid representing a game board. The grid is a list of lists, where each inner list contains two integers representing the x and y coordinates of a ghost's position on the board. Additionally, you are given the player's position as a list of two integers repre... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "rue,\\\"responseHeaders\\\":{\\\"retry-after\\\":\\\"9995\\\"},'\\n '\\\"message\\\":\\\"Rate limit exceeded. Please try again later.\\\"}}'\\n)\\n\\n\\ndef test_looks_rate_limited_matches_common_phrasings() -> None:\\n assert ralph.looks_rate_limited(\\\"Error: 429 Too M... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that constructs a URL based on a given application name and URL name. Additionally, you need to compare this constructed URL with a specified changelist URL, which is derived from an admin site name, application label, and model name.... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with finding all starting indices of anagrams of a given pattern in a string. An anagram is formed by rearranging the letters of a word or phrase. Your function should take in two parameters: a string `str1` and a string `pattern`. It should return a list of inte... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nX procedural. Verified by a 78-check automated playtest including two real networked clients.\\\"\\nd['description'] = \\\"NEONSTRIKE is a fully ray-traced first-person shooter in the spirit of Counter-Strike. No rasterized geometry: a WebGL2 fragment sha... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that checks if a user has permission to access a specific keyword. The function should take two parameters: a boolean representing whether the user is logged in (`is_logged_in`) and a list of permissions that the user has (`user_permi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n13\t)\n14\tfrom app.agents.title_extraction import empty_extraction, normalize_extraction\n15\t\n16\t\n17\tdef _wrap(v, c=0.9):\n18\t return {\"value\": v, \"confidence\": c}\n19\t\n20\t\n21\tdef _doc_ext(**kwargs):\n22\t ext = empty_extraction()\n2... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "alright, please add any missing svg icons and improve detail of all 3d objects \nAssistant: All original icon designs and geometry. Two parts: an SVG icon set (replacing every emoji), and a 3D detail pass — stud-top block textures, edge outlines, animated water/speed/teleporter... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\n10\tfrom src.mythosmini.checkpointing.saver import BackgroundSaver\n11\tfrom src.mythosmini.config import (\n12\t CHECKPOINT_INTERVAL_STEPS,\n13\t LOG_INTERVAL_STEPS,\n14\t ModelConfig,\n15\t TrainConfig,\n16\t)\n17\tfrom src.mythosmini.data... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with calculating the link probability between multiple points on a map based on a given upper triangular matrix A and a distance matrix D. The link probability is defined as the product of the exponential of the negative distances and the corresponding entries in... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nindbot/chat_history.json'))\\nk=list(d)[0]\\nprint(json.dumps(d[k],indent=1)[:1500])\\n\\\"\", \"description\": \"Look at one channel entry\"}\nResult: {\n \"name\": \"announcements\",\n \"guild_id\": \"1493402605504823357\",\n \"messages\": [\n {\n \"... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with calculating the y-coordinate of the center of mass of a processed image represented as a 2D list of integers. Each non-zero integer represents a pixel, while zero represents an empty pixel. The center of mass is defined as the average y-coordinate of all non... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "I'm paranoid about edge cases for a technical documentation and trying to understand Bloom filters and the trade-off between false positives and memory. I'm a startup founder struggling with why counting Bloom filters aren't used more often. What would you worry about first? Th... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "Given an array of integers `nums` and an integer `target`, write a function `twoSum` that finds the indices of the two distinct numbers in `nums` that add up to the `target`. You may assume that each input has exactly one solution, and you may not use the same element twice. Th... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given a string `word`, implement a function `analyze_word` that analyzes the word and returns a tuple. The first element of the tuple should be the total number of characters in the word. The second element should be a dictionary that counts the occurrences of each vowel (a, e,... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Please look at how you could improve this python AOT compiler to be ready for real-world use."
},
{
"role": "assistant",
"content": "<think>\nThe user wants me to look at how to improve a Python AOT (Ahead‑Of‑Time) compiler so it can be ready for real‑world use. To ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ns').catch(e=>{console.error('import fail (expected if deps heavy):', e.message); process.exit(0)});\\nEOF\\nnode test-parse.mjs; echo ---; node -e \\\"\\n// re-test parser logic standalone by extracting function via regex\\nconst fs=require('fs');\\nconst... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nessage): Now surface skipped page renders from `pdf_to_images` and wire them through the pipeline:\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"C:\\\\Users\\\\aranr\\\\CascadeProjects\\\\windsurf-project-10\\\\backend\\\\app\\\\servic... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of strings representing motions and postulates in a parliamentary setting. Each string consists of a combination of words and may contain uppercase letters, lowercase letters, and punctuation marks. Your task is to write a function to analyze the given list... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a DNA sequence as a string `seq` and a substring `pattern`. Your task is to write a function that finds the starting positions of all the occurrences of the specified pattern within the DNA sequence. The function should return a list of starting positions (0-index... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntool call) Bash input={\"command\": \"make fix >/dev/null 2>&1; make lint 2>&1 | grep -vE \\\"^grep|^\\\\.venv|^ruff|formatted|passed\\\" | tail -4\", \"description\": \"Lint before relaunch\", \"timeout\": 120000}\nResult: |\n\nFound 2 errors.\nmake: ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "im only getting around 11fps any way to optimize it?\nAssistant: 11 fps means either the fragment shader is too heavy for your GPU (most likely — the composite shader evaluates the entire procedural sky, with multiple multi-octave noise calls, **3 times per pixel** at full reso... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a sentiment analysis algorithm using bigram models. A bigram model is a type of probabilistic language model that predicts the next word in a sequence based on the previous word. In this problem, you will implement a function that calculates the... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a string `msg` containing a message. Your task is to write a function `reverse_words` to reverse the order of words in the message while maintaining the order of characters within each word. A word is defined as a sequence of non-space characters. For example, if ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "using the discord bot token in .env, look at the Glint Research server and properly configure the Muted role\nAssistant action: Bash {\"command\": \"grep -i token /home/user/Blindbot/.env | sed 's/=.*/=<present>/'\", \"description\": \"Check token var name in .env\"}\nResult: #... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nile with no markdown headers, covering: release date (June 9, 2026), Mythos-class designation, undisclosed parameter count, safety classifier with Opus 4.8 fallback, agentic long-horizon capabilities, scientific reasoning, SOTA vision, long-context perfor... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with writing a function `count_unique_words` that takes a string as input and returns the number of unique words present in that string. A word is defined as a sequence of alphanumeric characters separated by any non-alphanumeric character. The function should ig... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "I'm methodical and careful for a code review and I have an image of mobile banking transfer flow designed by a friend. I'm a full-stack developer trying to understand the obvious friction points and which screen to redesign first. How do you prioritize what to check first? how ... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a custom learning rate scheduler for a deep learning model. The learning rate scheduler will adjust the learning rate during training according to a polynomial decay schedule. The polynomial decay schedule is defined by the following equation: \... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given the dimensions of a rectangular box represented by its width (W), height (H), and length (L), along with an integer N. Your task is to write a function that determines the maximum number of smaller cubes with dimensions LxLxL that can fit into the larger box, or r... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "ence-gated version and measure what % of questions exit at the fast path?\nUser: do that please\nAssistant: Building the confidence-gated adaptive pipeline: thinker diffuses scratchpad+answer jointly; high-confidence rows exit with the diffusion answer (no AR); low-confidence r... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates a simple library management system for student records. Implement a function `manage_students(operations)` that takes a list of operations and returns a list of results based on the operations. The operations can be of thre... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "e is current in your context — no need to Read it back)\nAssistant action: Edit {\"file_path\": \"D:\\\\physics\\\\sdft\\\\scripts\\\\train_sdft.py\", \"new_string\": \" from peft import LoraConfig, get_peft_model\\n\\n # A string is treated by peft as a regex ove... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n(file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/MythosMini/tests/double_decoder.py\", \"old_string\": \" thinks = torch.where(reveal, sampled, thinks)\\n... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "5.0\\\" \\\\\\n -d '{\\\"model\\\":\\\"openai/gpt-oss-120b\\\",\\\"messages\\\":[{\\\"role\\\":\\\"user\\\",\\\"content\\\":\\\"hi\\\"}],\\\"max_tokens\\\":5}' \\\\\\n | grep -i \\\"x-ratelimit\\\\|retry-after\\\\|^HTTP\\\"\", \"description\": \"Inspect Groq rate limit header... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function to validate a configuration dictionary that describes multiple instances. Write a function called `validate_instance_config` that takes a dictionary as an argument and performs the following checks: 1. Ensure that the number of ins... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\none = None,\n3822\t ) -> Path:\n3823\t if session_id is None:\n3824\t session_id = str(uuid.uuid4())\n3825\t workspace_root, workspace = self._prepare_workspace(session_id, prompt_input, self.container_kind)\n3826\t home... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "rf-project-10\\backend\\app\\services\\pipeline.py has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"file_path\": \"C:\\\\Users\\\\user1\\\\CascadeProjects\\\\windsurf-project-10\\\\backend\\\\app\\\\serv... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that validates a list of user inputs for a command-line application. The function should check if a list of required arguments is provided by the user. If any required argument is missing, the function should raise a `ValueError` with a s... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with designing a function that simulates the alteration of a project management application's `supervisors` field in a `Project` model. The `supervisors` field is a list of user IDs representing the users who supervise a project. Your function should take a list ... | 1 | v3-rft-acecode | true |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.