messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "You are tasked with calculating the interest earned on a bank account balance over a specified number of years using a given annual interest rate. Implement a function `calculate_interest(balance: float, interest_rate: float, years: int) -> float` that takes in three parameters... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You need to implement a function that calculates the number of cores based on a specified range of values. The function should take two parameters: the start value and the end value (inclusive), both of which are integers. The step size for the range is fixed at 25. For each va... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "[Request interrupted by user for tool use]\nwhy is part of it being filled in? thats not our logo anymore. Why did it turn black? I said make it look better, not change our logo\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/log/logo.html\", \"old_... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Build me a photo-realistic, highly interactive 3D digital twin of Earth.\nAssistant: I'll build this as a self-contained WebGL app — a Three.js globe with real NASA-derived 8K satellite imagery, day/night terminator computed from the actual sun position, animated clouds, atmosp... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with merging two dictionaries. Write a function `merge_dictionaries(groups: Optional[Dict[str, Any]], policies: Optional[Dict[str, Any]]) -> Tuple[Dict[str, Any], Dict[str, Any]]` that takes two optional parameters, `groups` and `policies`. If `groups` is provide... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nartMatch(MAPS[selectedMap], 'bots');\\\\n renderer.loadMap(MAPS[selectedMap]);\\\"]:\\n assert call in src\\n src = src.replace(call, \\\"currentMapId = selectedMap;\\\\n \\\" + call)\\nold = \\\"game.startMatch(MAPS[mapId] || MAPS.vector, 'dm');\... | 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 teacher of foundational analysis who can articulate why R was constructed and what 'completeness' actually means."
},
{
"role": "user",
"content": "My professor keeps saying Q isn't complete and R is — but Q is dense in R, so every real is a limit of rat... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates cropping a rectangular section of a slide given its original dimensions and a set of coordinates representing the top-left and bottom-right corners of the section to be cropped. The function should take in the width and... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n.transformer import MythosMini\n7\t\n8\t\n9\t@dataclass(frozen=True)\n10\tclass ScoredPair:\n11\t context: list[int]\n12\t continuation: list[int]\n13\t\n14\t\n15\tdef truncate_pair(pair: ScoredPair, max_len: int) -> tuple[list[int], int]:\n16\t ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n str) -> None:\n640\t consecutive_failures = 0\n641\t state = load_state() or default_state(goal)\n642\t for iteration in range(1, MAX_ITERATIONS + 1):\n643\t verify_pending_freebuff_tasks(goal, state, iteration)\n644\t if not TASKS... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that calculates the frequency of a musical tone based on a specific formula. The function should take an integer input representing the tone and return the corresponding frequency. The frequency calculation follows the formula: frequency ... | 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 DevOps engineer. Focus on reliability, security, and reproducibility."
},
{
"role": "user",
"content": "'Permission denied' when running Docker"
},
{
"role": "assistant",
"content": "# \"Permission denied\" with Docker — Common Causes & Fixes... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that processes a list of GitHub repository names and their star counts. The function should filter out repositories with a star count falling within a specified range, and return the remaining repository names in lowercase sort... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates basic operations on a list of match objects. The function should take a list of match objects and perform the following operations: 1. Add a new match object to the end of the list. 2. Remove a match object at a specifi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nt Research', s.indexOf('people-grid'))>-1);\\nnew Function(s.split('<script>')[1].split('</script>')[0]); console.log('JS OK');\\n// crude div balance in body\\nconst body=s.slice(s.indexOf('<body>'),s.indexOf('</body>'));\\nconsole.log('divs:',(body.matc... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ncurrent in your context — no need to Read it back)\nAssistant: Restart server (realtime.js changed), then build the three-player WS protocol test:\nAssistant action: Bash {\"command\": \"pkill -f \\\"node server/index.js\\\"; sleep 1; (nohup node server/i... | 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": "…[earlier truncated]…\n-person-survival-game\\\\index.html\", \"old_string\": \" const hue = 78 + Math.random() * 32, light = 22 + Math.random() * 22;\", \"new_string\": \" const hue = 78 + Math.random() * 32, light = 36 + Math.random() * 26;\"}\nResult: The file C:\\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": "You are tasked with implementing a function that generates a list of valid states from an initial state to a goal state using a set of operators and a successors function. The function should take in the following parameters: an initial state, a goal state, a set of operators (... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsh | cat\\necho ---\\n# 2) try the wrapped command with a timeout, capture first bytes\\ntimeout 20 docker exec -i -e TERM=xterm-256color --user codex -w /workspace $C script -qfec \\\"stty cols 120 rows 30 2>/dev/null; exec claude --model claude-sonnet-4... | 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": "n [-72, 8, 38],\\n [-32, 42, 72],\\n [5, 122, 12],\\n [56, 58, -46],\\n [-12, 22, -70],\\n [-58, 11, -46],\\n ],\", \"old_string\": \" cam: [\\n [-80, 8, 42],\\n [-32, 42, 74],\\n [6, 112, 14],\\n [56, 58, -46],\\n [-... | 1 | victor/fable-5-boeing-747-trace | null |
[
{
"role": "user",
"content": "The core idea:\n- Bitnet = ternary {−1,0,1} in a 2-bit container (1.58-bit effective)\n- Dragonoid: \"Why not do the same for 4-bit, since it's all about sparsity anyway?\"\n- Clock = sparse 3.5-bit format: 12 states (like clock hours → hence the name)\n- First version: 12 stat... | 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 padding function for byte strings. The padding function should add a specified number of padding bytes to the input byte string such that the value of each padding byte is equal to the number of padding bytes added. Your function should take a... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>b1vjckjzh</task-id>\n<summary>Monitor event: \"2B run: training log lines, errors, phase transitions\"</summary>\n<event>step 2000 tokens 262144000 loss 1.3279 lr 3.00e-03 micro_batch 256 accum 1 checkpoint step_00002000.pt\nstep 4000 tokens 524288... | 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": "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 set of validation rules are met based on given inputs. The function `validate_input` takes in two parameters: `error` (a dictionary with keys `type` and `message`, where `type` is a string) and `properties` (a list of... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nt().splitlines()\\n entries = [line.st …[truncated]\nResult: File created successfully at: /home/lane/MythosMini/tests/e2e/test_repo_contract.py (file state is current in your context — no need to Read it back)\nAssistant action: Write {\"file_path\": ... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nd into the hero** - it now sits in the empty space to the right of \"Bigger isn't better. / Smaller is smarter.\", and the stroke-draw animation runs in coral orange (`#d97757`) instead of white. The hero is a two-column grid (copy left, logo right); it f... | 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": "Assistant: Write AGENTS.md now.\nAssistant action: Write {\"content\": \"# AGENTS.md \\u2014 Mandatory Operating Rules for AI Agents\\n\\nThis file defines non-negotiable rules for any AI agent working in this repository. Read this file in full before doing anything else. These... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the sentiment score for a given list of reviews. Each review is represented as a list of integer word indices. The function should take a list of lists, where each inner list represents a review, and return a list of 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": "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": "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 debugging specialist. Diagnose systematically — measure, don't guess."
},
{
"role": "user",
"content": "My JavaScript application has a memory leak in the browser. How do I find it?"
},
{
"role": "assistant",
"content": "# Finding a JavaScrip... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "system",
"content": "You are an event sourcing practitioner who has run CQRS systems with billions of events in production. Help the user think through projection rebuilds, schema evolution of read models, and the tradeoffs of catching up versus parallel cutovers."
},
{
"role": "user",
... | 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": "what if you do english text? Like the traning pipeline.\nAssistant: Good question — that's the real test. Honest assessment of what transfers and what breaks:\n\n## The dataset problem is the crux\n\nThe math experiment worked because the \"quick thinking\" response was *progra... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Given the inorder and postorder traversal sequences of a binary tree, your task is to construct the binary tree and return the root node of the tree. The inorder traversal sequence represents the order in which the nodes are visited in an inorder traversal, and the postorder tr... | 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 implementing a function called `get_error_data` that simulates retrieving error data from a backend server. The function should take a string input representing the type of error and return a JSON string that indicates the error type and a predefined error m... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n⡴⠋⡴⣫⢦⡀⠘⣇ ⣸⠃ ⢻⡀ ⢀⡟⢀⡴⠋⣠⣄⠙⢦⡀ \n⢰⠋⣠⠞ ⠻⣄⠙⢦⡈⠳⠤⣤⠤⣄⠙⢦⡀ ⣠⠞⢁⡤⢤⡤⠴⢋⡴⠋⣠⠞⠁⠈⠳⡄⢹⡆\n⢸ ⣿ ⠈⠳⣄⠙⢦⡀ ⠈⠳⣄⠙⢦⡀ ⣠⠞⢁⡴⠋ ⢀⡴⠋⣠⠞⠁ ⡇⢸⡇\n⢸ ⣿ ⠈⠳⣄⣹⣦⠤⣤⡀⠈⠳⣄⠙⠛⠉⠉⠙⠚⢁⡴⠋⢀⡤⠶⠶⠋⣠⠞⠁ ⡇⢸⡇\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 implementing a Python function that processes a given list of tuples representing chat messages. Each tuple contains a chat ID (string) and a message text (string). Your function should extract the chat ID and message text from the first tuple in the list, a... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\": \"/home/user/AIArchives/archives/neonstrike/blender/weapons.py\", \"content\": \"# NEONSTRIKE weapon factory. Builds all 7 weapons as real meshes and renders\\n# them with Cycles (GPU-style path tracing on CPU) to transparent PNGs:\\n# <id>_vm.png ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes a list of raw matches and constructs a list of dictionary objects based on certain conditions. Each raw match is represented by a dictionary containing two keys: 'external_references', which is a list of dictionaries wi... | 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 two dictionaries: `steps_high` and `steps_low`, where the keys are individual identifiers and the values are lists of integers representing steps taken by those individuals in high and low activity situations, respectively. Your task is to implement a function `ca... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of integers representing temperatures in degrees Celsius. Your task is to implement a function that returns a list of integers where each element represents the number of days until a warmer temperature. If there is no future day for which this is possible,... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given a string `text`, you are to implement a function `calculate_terminal_width(text: str) -> int` that calculates the maximum number of characters that can be displayed in a single line of a terminal window without wrapping. The terminal width is fixed at 80 characters. Your ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that validates a configuration data string and its associated file format. Write a function `validate_and_warn` that takes two parameters: \n- `cfg_str` (string): A string containing the configuration data. \n- `file_format` (strin... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a Python decorator called `@schedule` that simulates the scheduling of a function to be executed at a specified datetime in the future. The decorator will take a `datetime` object as an argument and will execute the decorated function immediatel... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a frontend development expert. Provide modern, idiomatic code."
},
{
"role": "user",
"content": "What's the difference between Vite and Webpack?"
},
{
"role": "assistant",
"content": "# Vite vs Webpack\n\n## Core Architecture\n\n**Webpack** bun... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n: \"/tmp/glint-ui-test.js\", \"content\": \"// Browser verification: drives the Glint UI end-to-end in real Chromium.\\nconst { chromium } = require('/home/user/rblx/node_modules/playwright');\\nconst fs = require('fs');\\n\\nconst BASE = 'http://localhos... | 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]…\nlost the tournament). OEC crashed — investigate:\nAssistant action: Bash {\"command\": \"tail -25 /tmp/r3_oec.log | tr '\\\\r' '\\\\n' | tail -12; echo ===; grep -E \\\"step_00000038|step_00000488|step_00009000|proc_after done|oec_after done\\\" /tmp/r4_p... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with creating a simple banking system that manages a bank account. Write a function `manage_bank_account` that takes an account number, an initial balance, a list of transactions, and returns the final balance of the account. The transactions can include either d... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "My PC keeps crashing! Can you diagnose and patch the bug?\nAssistant: PC crash diagnosis need data. Check logs first.\nAssistant action: Bash {\"command\": \"journalctl -p err -b -1 --no-pager | tail -50; echo ---; journalctl --list-boots --no-pager | tail -5\", \"description\"... | 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&1 | tail -4\", \"description\": \"Test, format, typecheck data pipeline\"}\nResult: ........ [100%]\n8 passed in 0.58s\nsrc/mythosmini/data/fineweb.py:15: error: Skipping analyzing \"dataset... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with managing a collection of model packagings in a Python application. Implement a function `packaging_delete_id(pack_id: str) -> bool` that simulates the deletion of a model packaging with the given ID. The function should return `True` if the model packaging w... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nple[list[str], str | None]:\n2253\t configured_base_url = self.config.get_base_url()\n2254\t api_key = self.config.get_api_key() or (\"none\" if configured_base_url else \"\")\n2255\t base_url, proxy_target = self._codex_base_url_and_... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "MythosMini:\n config = ModelConfig(\n dim=16,\n n_heads=2,\n prelude_layers=1,\n coda_layers=1,\n shared_loops=2,\n lora_rank=2,\n ffn_hidden=32,\n max_seq_len=32,\n )\n return MythosMini(config)\n\n\ndef test_per... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "Assistant\n\nView agent\n\nSystem updated GLI-245\n\nHire technical and research team for small language model proje… - status -> blocked\n\nView GLI-245\n\nHiringAssistant run failed\n\nGroq returned HTTP 429: {\"error\":{\"message\":\"Rate limit reached for model `openai/gpt-... | 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": "Make me a photorealistic survival game. We are in the woods surrounded by trees, hills, grass, flowers, nature. The lighting should look really real as well. We can walk around, the wind is blowing, there's ambient sounds and everything, as close to photo-realism as possible\nA... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>bbq5po02i</task-id>\n<tool-use-id>toolu_01DzzJbENhKBPKUkuGFmwaX2</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/e24a84d9-b09d-4531-97ce-3c078924b269/tasks/bbq5po02i.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntruncated]\nResult: The file C:\\Users\\user\\CascadeProjects\\windsurf-project-10\\backend\\app\\agents\\triangulation.py has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant: Now the extraction laye... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that extracts specific patterns from a given input text using regular expressions. Your function should take the input text and a list of extractors, which are regular expressions, and return a list of tuples. Each tuple should contain th... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "(file state is current in your context — no need to Read it back)\nResult: The file /home/lane/cc/.claude/memory/context7.md has been updated successfully. (file state is current in your context — no need to Read it back)\nResult: The file /home/lane/cc/.claude/memory/context7.... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "gion from `~/.aws` config files when `AWS_REGION` isn't set, matching AWS SD… │\n│ │ Added a search bar when browsing a marketplace's plugins in `/plugin` │\n│ Mini-Fable-5 with low e... | 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]…\ns — http 200\n ✔ viewmodel sprites decoded in browser — 7/7\n ✔ HDR bloom visibly changes pixels — 10.0% changed\n ✔ character limbs exist as capsules — 24 capsules\n ✔ walk cycle animates limb pos …[truncated]\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]…\n03cThink\\u003e\\n\\n\\u003c/Think\\u003e\"},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"usage\":{\"queue_time\":\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/GR/glint-cli/src/core/agent.ts\", \"old_string\": \" o... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Repo: /home/user/MythosMini — a 1,050,241-param byte-level (vocab 257) looped-shared-block transformer trained on fineweb-edu, benchmarked on WikiText-2 byte PPL, BLiMP, ARC-Easy against the Tiny-ML leaderboard (overall = mean of blimp, arc, normalized wiki score; efficiency = ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Continue the MythosMini task: check /tmp/run_fast3_2b.log. When finished (instruct results printed): add scores.md rows for the throughput restructure run (28cf7be..latest), journal verbatim results incl. stm oom shrink prints, commit, and report to user: throughput ladder (den... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "rd answer\n\n✦ four\n\n╭──────────────────────────────────────────────────────────────────────────────────────────────────╮\n│ ❯ │\n╰──────────────────────────────────────────────────... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntle\":\"Qwen3.5 9B API | Together AI\",\"url\":\"https://www.together.ai/models/qwen3-5-9b\"},{\"title\":\"[Deep Dive] Qwen 3.5 Brings Native Multimodality and Long Context to Small Open Models\",\"url\":\"https://trilogyai.substack.com/p/deep-dive-qwe …[... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a user authentication system that allows you to create new user accounts and authenticate existing users. Each user account will have a username and a password. The password must adhere to the following requirements: it must be at least 8 characters... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ncheduler.py (file state is current in your context — no need to Read it back)\nAssistant action: Write {\"file_path\": \"/home/user/MythosMini/src/mythosmini/training/optimizer.py\", \"content\": \"from torch import nn\\nfrom torch.optim import NAdam\\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": "system",
"content": "You are a senior software engineer helping a colleague. Be practical and specific."
},
{
"role": "user",
"content": "How do I write good tests?"
},
{
"role": "assistant",
"content": "# Writing Good Tests\n\n## Core principles\n\n**Test behavior, not im... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntdout\",\"chunk\":\" to\"}\n{\"ts\":\"2026-06-11T21:05:12.709Z\",\"stream\":\"stdout\",\"chunk\":\" \\\"\"}\n{\"ts\":\"2026-06-11T21:05:12.711Z\",\"stream\":\"stdout\",\"chunk\":\"Make\"}\n{\"ts\":\"2026-06-11T21:05:12.715Z\",\"stream\":\"stdout\",\"chunk... | 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": "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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.