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": "You are tasked with writing a function that simulates the loading of logging configurations from a YAML file. The function should accept the path of the YAML file as a string and return a dictionary containing the logging settings. If the file cannot be opened or read, the func... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a custom exception handling mechanism for a simple banking application. In this application, you have to create a custom exception class called `WithdrawalError` that inherits from the base `Exception` class. The `WithdrawalError` class should h... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>\n<command-name>/login</command-n... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nh input={\"command\": \"cp /tmp/lb_index.html /home/user/MythosMini/tests/fixtures/leaderboard_index.html && grep -c \\\"name:\\\" /home/user/MythosMini/tests/fixtures/leaderboard_index.html\", \"description\": \"Commit real leaderboard html as test fixtu... | 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 teach generating functions by demystifying the algebra — show students that the formal series is just bookkeeping for a recurrence."
},
{
"role": "user",
"content": "Generating functions feel like magic — you write down x/(1-x-x²) and Fibonacci numbers fall ou... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with creating a function to manage a list of unique site names. Implement a function `add_site` that takes a list of existing site names and a new site name to add. The function should check if the new site name is already in the list. If the name is not unique, ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of RGB color values and need to identify which colors fall within a specified range of red colors defined in the HSV color space. Write a function `highlight_color_range(rgb_colors: List[Tuple[int, int, int]]) -> List[Tuple[int, int, int]]` that takes a lis... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of line segments, where each line segment is defined by two points in a 2D plane. Your task is to implement a function that counts the occurrences of each point across all line segments and returns a dictionary where the keys are the points and the values a... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nAR_TO_ID = {ch: 3 + i for i, ch in enumerate(CHAR_TOKENS)}\\nID_TO_CHAR = {v: k for k, v in CHAR_TO_ID.items()}\\nVOCAB_SIZE = 3 + len(CHAR_TOKENS)\\nPROMPT_LEN = 8\\nTHINK_LEN = 7\\nANSWER_LEN = 4\\n\\n\\n@dataclass\\nclass ExperimentConfig:\\n digits... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "lled. Falling back to torch implementation. To install follow https://github.com/fla-org/flash-linear-attention#installation and https://github.com/Dao-AILab/causal-conv1d\n\rLoading weights: 0%| | 0/426 [00:00<?, ?it/s]\rLoading weights: 100%|██████████| 426/426 [00... | 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": "Implement the provided `BaseTerminal` interface. It provides a simple python interface to send keys to a headless terminal.\n\n**Interface variant:** The abstract API uses **`relay_chars(payload, idle_seconds=...)`** instead of `send_keystrokes`. The semantics are the same: inj... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "As a curious learner trying to understand, i'm hands-on and experimental for a hackathon and I have an image of Scala code snippet from a blog post with heavy syntax highlighting. I'm a team lead trying to understand to transcribe what's visible and check for an obvious bug. Ho... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "ng and the script crashed mid-execution, I need to manually inspect the environment first. Confirming these files exist is critical before attempting to read their content or proceed with the goal of creating `test.py`, ensuring I'm not building on missing context.\n\n--- THINK... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a computer science tutor. Explain concepts clearly with examples."
},
{
"role": "user",
"content": "Explain Gödel's incompleteness theorems — what they actually prove, the self-referential construction, implications for mathematics and AI, and common misin... | 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": "…[earlier truncated]…\nth\": \"/home/user/MythosMini/ralph.py\", \"old_string\": \" if TASKS_FILE.is_file() and ensure_freebuff():\\n if shutil.which(\\\"tmux\\\") is not None:\\n print(\\\"switching to freebuff (minimax m3, standard) for the wait\\\", flus... | 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]…\nt={\"command\": \"~/tools/blender-4.2.5-linux-x64/blender -b -P blender/weapons.py -- \\\"$(pwd)/app/public/assets/weapons\\\" 2>&1 | grep -E \\\"DONE|Error\\\" | tail -2\", \"description\": \"Final weapon re-render with origin fix\", \"timeout\": 600000,... | 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": "You are tasked with finding the longest common substring between two given text strings. Implement a function `find_match(text1: str, text2: str) -> Tuple[int, int]` that takes in two strings `text1` and `text2`, and returns a tuple of two integers representing the starting and... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a simple configuration management system for a web application. Your system should allow registering configuration parameters with various flags that control their behavior. Each parameter can have different flags, such as `FLAG_REQUIRED`, `FLAG... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a transaction validation system for a digital artifact management platform. Your goal is to validate user actions with respect to artifacts. You need to implement a function `validate_transaction` that takes two parameters: `action` (string) and... | 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]…\nrHome],\\n [/^#\\\\/discover/, renderDiscover],\\n [/^#\\\\/game\\\\/([\\\\w-]+)/, renderGamePage],\\n [/^#\\\\/play\\\\/([\\\\w-]+)/, renderPlay],\\n [/^#\\\\/studio\\\\/([\\\\w-]+)/, renderStudio],\\n [/^#\\\\/studio/, renderStudioList],\\n [/^#\\... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n1]))\n )), TensorBox(StorageBox(\n InputBuffer(name='primals_7', layout=FixedLayout('cuda:0', torch.float32, size=[], stride=[]))\n )))\n args[13]: ()\nAssistant: Found it: flex backward can't handle the grad-requiring scalar `gate` captured in scor... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are given a grid world of size n x n, where an agent starts at the top-left corner (0, 0) and can move in four directions: up, down, left, and right. The goal of the agent is to reach the bottom-right corner (n-1, n-1). Implement a function `move_agent` that takes in a grid... | 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": "User: make me an online multiplayer game i can play with my friends. I want it to be like super smash bros. a 2D platform fighter. generate all the assets, make realistic fighting animations for each character and everything. on the start screen we wait for everyone to join, th... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "p: 0.05, default: 0.75 },\n12\t fov: { label: 'Field of View', type: 'range', min: 60, max: 120, step: 1, default: 95 },\n13\t rayBounces: { label: 'RT Reflection Bounces', type: 'range', min: 0, max: 3, step: 1, default: 1 },\n14\t shadows: { label: 'RT Shadows'... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with writing a function called `calculate_air_quality_index` that takes three parameters: `pm25`, `pm10`, and `aqi`. The function should return a string that represents the air quality status based on the given values. The air quality status is determined as foll... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that retrieves the version of a library given its module name as a string input. Implement a function called `get_library_version(library_name: str) -> str` that takes the name of a library and returns its version. The version should be r... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\naved is not None:\\n log_progress(deps, state, lr, saved)\", \"new_string\": \" torch.nn.utils.clip_grad_norm_(deps.model.parameters(), config.grad_clip)\\n optimizer.step()\\n state.step += 1\\n step_tokens = state.... | 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]…\nceDataURL } from './avatar2d.js';\", \"new_string\": \"import { avatarSVG, faceDataURL } from './avatar2d.js';\\nimport { hatThumb } from './hatthumb.js';\"}\nResult: The file /home/user/rblx/public/js/app.js has been updated successfully. (file state is ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that validates a list of RPM (Revolutions Per Minute) values. The validation should ensure that each RPM value in the list is a positive integer. If any value is invalid, your function should raise a ValueError with a message indicating w... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>\n<command-name>/model</command-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 evaluating the performance of a character-level prediction model. Given two lists of labels, one representing the actual labels and the other representing the predicted labels, your goal is to calculate the accuracy of the model's predictions. The accuracy 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": "user",
"content": "You are tasked with implementing a function that simulates a grid layout for a graphical user interface (GUI) application. The function should support adding widgets to the grid and generating the layout configuration as a string. Implement the function `generate_grid_layout(ro... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "1,1.668] 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∈[0.061,1.562] x∈[0.061,5... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "[Request interrupted by user for tool use]\ndoes ollama support diffusion?\nAssistant action: ToolSearch {\"query\": \"select:WebSearch\", \"max_results\": 1}\nResult: \nAssistant action: WebSearch {\"query\": \"ollama llama.cpp support diffusiongemma block diffusion text model... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n'networkidle0' });\\nawait page.waitForFunction('window.GAME && window.GAME.ready');\\nawait page.evaluate(() => {\\n GAME.test.setSetting('graphics.preset', 'balanced');\\ …[truncated]\nResult: {\n \"spheres\": 12,\n \"caps\": 24,\n \"sample\": {\n \"a... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "<task-notification>\n<task-id>b2btb0hd1</task-id>\n<tool-use-id>toolu_01NWpjo8yaEQWPnbk4w84UiZ</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/602033e7-dc55-4b7f-909f-1c67135d8f4b/tasks/b2btb0hd1.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsformer import MythosMini\n4\tfrom src.mythosmini.training.fp4 import (\n5\t FP4_BLOCK,\n6\t FP4_LEVELS,\n7\t Fp4Linear,\n8\t fp4_weight,\n9\t quantize_fp4,\n10\t)\n11\t\n12\t\n13\tdef test_quantize_fp4_outputs_only_e2m1_grid_values() -> No... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n for block in self.prelude:\\n x = block(x, cos, sin, None, frozen)\\n for loop_index in range(loop_count):\\n clamped = min(loop_index, self.max_loops - 1)\\n …[truncated]\nResult: The file /home/user/Mytho... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nrd placement: overall 59.62 (rank 16/36), efficiency 9.90 (rank 10/36)\nstep_00007630: wiki_ppl 5.139 blimp 57.55 arc 31.00\nstep_00007630: overall 57.70 (rank 17/36), efficiency 9.58 (rank 12/36)\nstep_00008230: wiki_ppl 4.669 blimp 59.00 arc 31.00\nstep... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nnt.py:16:class MergeCandidate:\nsrc/mythosmini/merging/tournament.py:26:def improves_any_category(child: BenchmarkScores, best: BenchmarkScores) -> bool:\nsrc/mythosmini/merging/tournament.py:30:def category_best(candidates: list[MergeCandidate]) -> Bench... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a computer science tutor. Explain concepts clearly with examples."
},
{
"role": "user",
"content": "Our GraphQL API is hammering the database. A query for 20 posts with their authors fires 21 SQL queries — the classic N+1 problem. I know DataLoader is the ... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a secure password verification system. Your goal is to create a function `verify_password` that checks if the given password matches the provided hashed password. The password and hashed password are represented as strings. The hashed password i... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that processes HTTP response codes and extracts data from a JSON response. Your function should take a dictionary simulating an HTTP response object as input, which contains the following keys: 'status_code', 'headers', and 'json_d... | 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 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": "user",
"content": "User: Create a functonal clone of the popular site Roblox, you should include all assets required. It must have the following: 1. default pre-made games 2. a game maker\n with full colaberation with other users. 3. multiplayer lobbies with REAL players/connections 4. game conf... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simple text comparison tool. The function should take two strings, `original_text` and `other_text`, as input and identify the differences between them. For each line in the `original_text`, if the line is not present... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nSULT: written\npyaot: check passed (0 warning(s))\npyaot: compiled -> /tmp/sem2\nSINGLE-FILE-OK\nAssistant action: Bash {\"command\": \"python -m pytest tests -q 2>&1 | tail -2; python -c \\\"import ast; ast.parse(open('pyaot.py').read())\\\" && echo PARS... | 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]…\nricing.ts\\\";\\nimport { visiblePrefix } from \\\"./core/protocol.ts\\\";\\nimport { loadSession, saveSession } from \\\"./core/session.ts\\\";\\nimport { expandSkill, listSkills, loadSkill } from \\\"./core/skil …[truncated]\nResult: The file /home/user... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that can parse a simple string representation of sensor measurements. The input string will contain the base sensor information followed by several measurements. The base information will be formatted as 'base_name:base_time:base_unit:bas... | 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": "As a study buddy helping prepare for technical interviews, for a personal learning goal, I came across mechanical gear assembly blueprint with tolerances. I'm a junior developer who's curious and exploratory about whether the tolerances are manufacturable and what would bind fi... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nue: each squiggle is 3 slightly different hand-drawn SVG paths flipbooked at ~13fps (`steps(1)`, 0.72s cycle), so lines constantly wobble like pencil frames:\n - Coral squiggly underline under \"Smaller is smarter.\" in the hero\n - Wobbling sage hand-d... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ntate and nudge history\"}\nResult: def add(a, b):\n return a + b\n\ndef multiply(a, b):\n result = 0\n for _ in range(b):\n result += a\n return result\n\ndef average(nums):\n return sum(nums) / len(nums)\n---\n{\"ts\":\"2026-06-12T2... | 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": "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": "user",
"content": "You are tasked with implementing a Python function that validates an authentication token for a hypothetical data management platform. The function `validate_token` should check if the provided token is valid. If the token is `None`, the function should raise a ValueError with ... | 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": "You are tasked with writing a function that extracts and returns a list of operations performed on a quantum circuit from a given code snippet. The code snippet consists of operations represented as lines of code. Each operation could be modifying the position of a handler, add... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nt\", \"timeout\": 90000, \"run_in_background\": true}\nResult: Command running in background with ID: b01o94n7g. Output is being written to: /tmp/claude-1000/-home-lane-MythosMini/471accf0-3df7-4e2e-a567-a094f8f8d585/tasks/b01o94n7g.output. You will be no... | 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 analyzing the performance of a machine learning model by generating a confusion matrix from its predicted and actual categories. The confusion matrix is a 2D array that visualizes how often the model's predictions match the actual categories. Your function 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": "<command-name>/model</command-name>\n <command-message>model</command-message>\n <command-args></command-args>"
},
{
"role": "user",
"content": "<local-command-stdout>Set model to \u001b[1mFable 5\u001b[22m and saved as your default for new ses... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that will recursively search for a specific file within a given directory structure and return the full path of the file if it is found. The directory structure is represented as a nested dictionary where each key is a director... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nE[path.extn …[truncated]\nResult: The file D:\\project-5\\tools\\smoke.mjs has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: PowerShell {\"command\": \"node D:\\\\project-5\\\\tools\\\\smok... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n this._flash(`🏁 You reached the goal! +${msg.reward || 5} ◈`);\\n } else {\\n this._flash(`🏁 ${esc(msg.username)} reached the goal!`);\\n }\\n break;\\n }\\n case 'tag': {\\n this.itId = msg.itId;\\n ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that validates client information. The function should take a dictionary as input and check if it contains the required keys: 'name' and 'email'. If both keys are present, the function should return 'Client added successfully'. If eit... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a configuration management system for a software application that allows toggling configuration parameters. Implement a function `toggle_boolean_parameter(configurations: dict, key: str) -> bool` that takes in a dictionary of configurations and a ke... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given a 2D grid of integers, implement a function `calculate_neighborhood_sum(grid, row, col)` that calculates and returns the sum of the values in the neighborhood cells surrounding a specified cell `(row, col)`. The neighborhood cells are defined as the cells in a 3x3 grid pa... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a senior engineer helping debug an intermittent test failure. Focus on reproduction strategy, bisection, and distinguishing race conditions from timing-dependent tests and shared-state pollution."
},
{
"role": "user",
"content": "test_order_processor_handl... | 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": "_len: 3436 content_len: 4007\n=== reasoning_effort=low ===\ncompletion_tokens: 1292 total: 1411\nreasoning_len: 64 content_len: 5315\nAssistant: `reasoning_effort=low` is a clean win:\n- Discarded reasoning: 3436 → **64 chars** (was ~860 wasted tokens/call).\n- Answer CoT: **lo... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "ction: ToolSearch {\"max_results\": 1, \"query\": \"select:Monitor\"}\nResult: \nAssistant: Sweep + full CPU test suite still running in background. Will report when both finish.\nUser: <task-notification>\n<task-id>bw7jwz5xn</task-id>\n<tool-use-id>toolu_01Pt2v1cULPKDxrkHs6pgz... | 1 | 1EYE4ALL/Fable-5-traces | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.