messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"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 card.innerHTML = `<span class=\\\"buy-name\\\">${def.name}</span>\\n <span class=\\\"buy-stats\\\">DMG ${def.dmg}${def.pellets ? '×' + def.pellets : ''} · RPM ${def.rpm}</span>\\n <span class=\\\"buy-price\\\">${def.price === 0 ? 'FREE' : '$'... | 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 implementing a function to determine the latest supported Bazel version based on the given current Bazel version and a list of other Bazel versions. The Bazel versions follow the semantic versioning format (major.minor.patch). Implement the function `latest_... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nload(sys.stdin)\\nprint(d['title'],'|',d['status'],'| assignee',d.get('assigneeAgentId'))\\nprint('desc:',(d.get('description') or '')[:200])\\\"; curl -s http://127.0.0.1:3100/api/issues/GLI-247/comments | python3 -c \\\"\\nimport json,sys\\ncs=json.load... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with verifying the correctness of a server's response based on two input strings, `s1` and `s2`, and an encrypted response from the server. Each input string contains key-value pairs separated by a specific separator. Your goal is to determine if the server's res... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n:0;padding:0;}\\n html{scroll-behavior:smooth;}\\n body{background:var(--bg); …[truncated]\nResult: File created successfully at: /home/user/GR/site/index.html (file state is current in your context — no need to Read it back)\nAssistant: Website done. C... | 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": "…[earlier truncated]…\ntruncated]\nResult: File created successfully at: /home/user/rblx/public/js/api.js (file state is current in your context — no need to Read it back)\nAssistant action: Write {\"file_path\": \"/home/user/rblx/public/js/avatar2d.js\", \"content\": \"// Proc... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a sentiment analysis program to evaluate a series of text snippets and determine if they indicate signs of depression. Your function should take in two parameters: a list of dictionaries, where each dictionary contains a sentiment score for a text s... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "remove the dots.\nAssistant: Dots = round line caps rendering as points before each segment grows. Switch caps to butt:\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/log/logo.html\", \"old_string\": \" stroke-linecap:round!important;\", \"new... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": ". DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>\nUser: <command-name>/login</command-name>\n <command-message>login</command-message>\n <command-args></command-ar... | 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": "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]…\ntail -2 && ./dist/glint --version\", \"description\": \"Bundle devtools dependency and recompile binary\"}\nResult: 3 packages installed [229.00ms]\n [20ms] bundle 558 modules\n [31ms] compile dist/glint\nglint 1.0.0\nAssistant action: Bash {\"comman... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a data processing algorithm that extracts complete lines of data from a given string. A complete line of data is defined as a string terminated by a newline character ('\\n'). Your function should return a list of complete lines of data. If ther... | 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": "Take a look at this project. It needs to be 100% hardened and foolproof. I can't have AI making bad decision and causing a massive failure that ends up costing my company a lot of money because we didn't do our job of title search and approval properly.\nAssistant: I'll take a ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n) || global.FIGHTERS;\\nconst M = require('./public/maps.js') || global.MAPRENDER;\\nconst fighters = require('./public/characters.js');\\nconst maps = require('./public/maps.js');\\nconst chars = Object.keys(SHARED.CHARACTERS);\\nconst anims = ['idle','r... | 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": "Sick, now apply the combination that gives the best results to the default training pipeline.\nAssistant: Best combination: **3-round recursive STM after training, before benchmark/SLERP**. Wiring it into `train.py`. Per AGENTS.md training-change rules this needs a full 2B veri... | 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": "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": "any way to optimize it so it isnt so laggy/choppy? I want a lot more fps and i dont think it's optimized well for that\nAssistant: The choppiness has three big causes: every frame draws ~2.7M grass vertices with culling disabled, ~10k double-sided leaf cards get re-rendered *tw... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that processes a list of strings and returns a dictionary containing the frequency of each unique word in the list. The function should ignore case sensitivity and consider only alphanumeric characters within the words. Additionall... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "http://127.0.0.1:3100/GLI/issues/GLI-247 It didnt do shit\nAssistant action: Bash {\"command\": \"curl -s http://127.0.0.1:3100/api/issues/GLI-247 | python3 -c \\\"\\nimport json,sys;d=json.load(sys.stdin)\\nprint(d['title'],'|',d['status'],'| assignee',d.get('assigneeAgentId')... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Now, research what a ralph loop is. Then add one (opencode) it should use minimax m3 on opencode correcytly, it should be like this. python3 ralph.py then it asks for a goal you want done. example: verify tests work. Then it would take that, call opencode with the model, and as... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a simple feature flag management system. A feature flag is a way to control the visibility of a feature in an application. Your goal is to implement a function `manage_feature_flags` that takes a list of feature names and returns a list of uniqu... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n | groq_local | groq/compound\nCoder | groq_local | groq/compound\nHR Assistant | groq_local | None\nCTO | groq_local | groq/compound\nAssistant action: Read {\"file_path\": \"/home/user/.paperclip/adapter-plugins/groq-paperclip-adapter-r10/dist/server/ex... | 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 implementing a custom event handling system in Python. Your goal is to create a mechanism for registering and dispatching events within a program. An event can be any action or occurrence that needs to be observed and handled by other parts of the program. I... | 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": "(-90%) skewX(-16deg);\\n animation:aiLogoSweep202606 .8s cubic-bezier(.4,0,.2,1) var(--sweep-delay,1.55s) both;\\n }\\n @keyframes aiLogoDrawSegment202606{to{stroke-dasharray:var(--segment-length) var(--path-length);}}\\n @keyframes aiLogoSegmentIn202606{from{opac... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "Given three integers `n`, `min_val`, and `max_val`, write a function `count_values_in_range(n, min_val, max_val)` that calculates how many integers raised to the power of `n` lie within the inclusive range from `min_val` to `max_val`. The function should return an integer repre... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function to evaluate a specific polynomial at a given value (abscissa) and polynomial order. The polynomial is defined by the following recurrence relation: \\[ P_n(x) = \\begin{cases} 1 & \\text{if } n = 0 \\\\ x & \\text{if } n = 1 \\\\ 2xP_... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that counts the frequency of each character in a given string. The function should return a dictionary where the keys are the characters and the values are their respective counts. The input string can contain letters, digits, punctua... | 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": "…[earlier truncated]…\ny agent working here. Read it fully, then read `journal.md` before starting any task. Detailed procedures live in `docs/rules/` — read the relevant one before doing that kind of work; they are part of this contract, not optional extras.\n4\t\n5\t## Comman... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates a simple text-based game. The game involves a player navigating through a grid-based world, collecting treasures, and avoiding obstacles. The player's goal is to reach the end of the grid while collecting as many tre... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ners aggregate\n407\t * tokens + …[truncated]\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/lane/paperclip/ui/src/components/IssuesList.tsx\", \"old_string\": \" onLoadMoreIssues?: () => void;\\n onSearchChange?: (search: str... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ncall) Edit input={\"replace_all\": false, \"file_path\": \"/home/user/MythosMini/docs/functions.md\", \"old_string\": \"**Purpose:** Bridges an opencode rate-limit window with freebuff: announces when opencode resumes (clock time), ensures freebuff is rea... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Implement a function `custom_tanh(x: List[float], scale: float) -> List[float]` that takes two parameters: a list of floats `x` representing the input values and a float `scale` representing the scaling factor to be applied to the hyperbolic tangent function. The function shoul... | 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 professional technical writer. Be clear, direct, and well-structured."
},
{
"role": "user",
"content": "Write release notes for a security patch."
},
{
"role": "assistant",
"content": "# Release Notes — Security Patch v2.4.1\n\n**Release Date... | 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": "<task-notification>\n<task-id>bwlrrkyn3</task-id>\n<tool-use-id>toolu_01Q9khJj7UY4stHK8HDJohMf</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane/22bb18a2-14fc-4d00-b566-037d9c98da2f/tasks/bwlrrkyn3.output</output-file>\n<status>completed</status>\n<summary>Background comm... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with calculating the linear and angular velocities of a differential drive robot based on the angular velocities of its two wheels and its current angular position. You are given the following parameters: the radius of the robot's wheels (in meters), the distance... | 1 | v3-rft-acecode | true |
[
{
"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": "…[earlier truncated]…\nSULT: The file C:\\Users\\user\\CascadeProjects\\3d-render\\index.html has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: ToolSearch {\"query\": \"select:mcp__Claude_Preview__preview_start,m... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Build pMARS (http://www.koth.org/pmars/) from source with no X server. \n\nSince koth.org is unreliable, get the source from Debian packages instead. After downloading, the unpacked Debian source tree must live under **`/app/src/`** (e.g. `/app/src/pmars-<version>/`), not as a ... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to calculate the Spearman rank correlation coefficient between two sets of ranks. The Spearman rank correlation is a non-parametric measure of statistical dependence between two variables. Your function should take in two lists of num... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nith the active turn.\\n if (running) {\\n queueRef.current.push(text);\\n push({ kind: \\\"notice\\\", text: `queued — sends when this turn finishes: ${text.slice(0, 80)}` });\\n return;\\n }\"}\nResult: The file /home/user/... | 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": "User: Make the training scripts for self distillation fine-tuning. I will be using traces like the one found on huggingface armand0e/qwen3.7-max-pi-traces as the base data. but we need to do on-policy SDFT instead of destructive SFT"
},
{
"role": "assistant",
"conte... | 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": "You are tasked with analyzing sales data represented as a list of dictionaries in Python. Each dictionary represents a sales record and contains the keys 'product', 'price', and 'quantity'. Your goal is to implement a function that calculates the total revenue generated from th... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function to manage a directed graph. The function should support the addition of nodes and directed edges, as well as the ability to retrieve all outgoing edges from a given node. The graph must enforce unique edges, meaning that adding a dupl... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nroving tests\"}\nResult: ........... [100%]\n11 passed in 0.60s\nAssistant action: Bash {\"command\": \".venv/bin/ruff format src/ tests/ >/dev/null; .venv/bin/ruff check --fix src/ tests/ >/dev... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsting slash command + live agent turn with approval.\nAssistant action: Bash {\"command\": \"tmux send-keys -t glint '/help' Enter && sleep 1 && tmux capture-pane -t glint -p | tail -32\", \"description\": \"Test /help command in TUI\"}\nResult: ✦ glint v... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with generating a list of file paths based on a given list of file names and their types. The file names may contain special characters and spaces, which need to be normalized. Your function should take a list of tuples as input, where each tuple contains a filen... | 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 mathematics educator. Build intuition before formalism."
},
{
"role": "user",
"content": "I can do induction proofs by following the template — prove base case, assume P(k), prove P(k+1) — but I don't actually understand *why* it works. It feels like cir... | 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": "user",
"content": "You are tasked with implementing a function to decode a string that has been encoded using a simple rotation cipher known as ROT-13. In ROT-13, each letter in the input string is shifted 13 places down or up the alphabet. For example, 'a' becomes 'n', 'b' becomes 'o', 'c' becom... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n more about it in the\r\n [FastAPI docs for Lifespan Events](https://fastapi.tiangolo.com/advanced/events/).\r\n \r\n return self.router.on_event(event_type) # ty: ignore[deprecated]\r\n\r\n-- Docs: https://docs.pytest. …[truncated]\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with analyzing sales data represented as a list of dictionaries in Python. Each dictionary represents a sales record and contains the keys 'product', 'price', and 'quantity'. Your goal is to implement a function that calculates the total revenue generated from th... | 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]…\nrain.py ralph.py | grep -v \"__init__.py\" && { echo \"error: comments found in source files\" >&2; exit 1; } || true\n\nfix:\n\t$(VENV)/bin/ruff format src/ tests/ ralph.py train.py\n\t$(VENV)/bin/ruff check --fix src/ tests/ ralph.py train.py\n\nrun:\n\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes an input string by modifying its uppercase alphabetic characters based on a given integer value. Specifically, your function should iterate through each character in the input string. For each character, if it is an upp... | 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": "You are tasked with comparing two lists of NMR data points to identify any differences between them. Each list contains tuples representing data points, where each tuple consists of three elements: (x, y, intensity). Your job is to implement a function that compares these two l... | 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": "You are tasked with implementing a function that converts an object into a dictionary format suitable for a specific API. The function `to_api_dict` should take an object as input and create a dictionary from its attributes. Specifically, the function should check if the input ... | 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": "You are given a 2D grid filled with non-negative integers representing the cost of moving through each cell. Your task is to find the minimum sum of a path from the top-left cell to the bottom-right cell, moving only right or down. Implement a function `minPathSum(grid)` that t... | 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": "You are tasked with implementing a function that processes a list of strings (nodes) and renders them in a specific way. The function should perform the following tasks: 1. Strip any leading or trailing whitespace from each string. 2. Replace multiple consecutive line breaks ('... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "EL, \"temperature\": 0.7, \"reasoning_effort\": \"low\",\n156\t \"max_tokens\": MAX_OUT_TOKENS,\n157\t \"messages\": [\n158\t {\"role\": \"system\", \"content\": SYS_PROMPT},\n159\t {\"role\": \"user\", \"content\":\n160\t \"CO... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nround\": true}\nResult: Command running in background with ID: bxnu01lec. Output is being written to: /tmp/claude-1000/-home-lane-MythosMini/189f0549-c2fc-4fc7-b50d-37cd255eabf2/tasks/bxnu01lec.output. You will be notified when it completes. To check inte... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "ning-channel thinking is left alone.\n\n## Verified flawless (independent filesystem checks, not self-report)\n\n- **Conversational**: Hi / what can you do / what was my last message / thanks — zero file exploration, answers \"last message\" correctly from context.\n- **Python ... | 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]…\n.061,1.668] x∈[0.061,5.330] NaN=0\nt= 14.0s maxSpeed= 1.05 m/s KE/m= 0.071 y∈[0.061,1.571] x∈[0.061,5.330] NaN=0\nt= 16.0s maxSpeed= 0.64 m/s KE/m= 0.040 y∈[0.061,1.602] x∈[0.061,5.330] NaN=0\nt= 18.0s maxSpeed= 0.55 m/s KE/m= 0.029 y... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nloat) -> Tensor:\\n if a.shape != b.shape:\\n raise ValueError(f\\\"shape mismatch: {tuple(a.shape)} vs {tuple(b.shape)}\\\")\\n a32 = a.float().flatten()\\n b32 = b.float().flatten()\\n dot = float(torch.dot(a32, b32).item())\\n if ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nNSECUTIVE_FAILURE_LIMIT = 3\", \"new_string\": \"CONSECUTIVE_FAILURE_LIMIT = 3\\nDEFAULT_RATE_LIMIT_WAIT_SECONDS = 72000\"}\nResult: The file /home/user/MythosMini/ralph.py has been updated successfully. (file state is current in your context — no need to... | 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": "<task-notification>\n<task-id>btf58zd0z</task-id>\n<tool-use-id>toolu_01RbEnx8qxuKozmtx4tPU2Wq</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/5eeb7e10-99a4-4d7d-a505-3ef47dcab480/tasks/btf58zd0z.output</output-file>\n<status>completed</status>\n<summary>Back... | 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": "…[earlier truncated]…\n everything yourself\\\"\\n return verification_feedback(output)\"}\nResult: The file /home/user/MythosMini/ralph.py has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Bash {\"command\": ... | 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": "…[earlier truncated]…\n [100%]\n8 passed in 0.58s\nsrc/mythosmini/data/fineweb.py:15: error: Skipping analyzing \"datasets\": module is installed, but missing library stubs or py.typed marker [import-untyped]\nsrc/mythosmini... | 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": "…[earlier truncated]…\nr ray tracer. No rasterized geometry: every pixel\\n// casts a primary ray against the analytic scene (AABBs + spheres), then\\n// shadow rays, AO rays, and reflection bounces per settings.\\n\\nimport { BOXES, LIGHTS, SUN_DIR, SUN_COLOR, SUN_INTENSITY } ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that calculates the nth digit in a sequence of square numbers. The sequence is generated by concatenating the squares of consecutive integers starting from 1. For example, the first few terms of the sequence are 149162536496481100121144..... | 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.