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]…\nme/lane/GR/glint-cli/src/core/tools.ts has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/lane/GR/glint-cli/src/core/agent.ts\", \"old_st... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n limit to clear\nrate limit window over — switching back to opencode (it is faster)\nhandoff sequence: ['ensure', ('run', 'freebuff'), ('sleep', 5)]\nAssistant: Handoff sequence verified: freebuff session → sleep remaining timer → back to opencode. Update... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a simple message queue system for a messaging application. The message queue should support the following operations: 1. `send_message(message)`: Adds a new message to the end of the queue. 2. `receive_message()`: Removes and returns the message... | 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 that simulates the installation of different versions of a Bible. The function should take two parameters: a string representing the 'file_path' of the Bible, and a boolean 'replace' indicating whether to replace the currently install... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that processes a list of migration operations for a database schema. Each migration operation is represented as a tuple containing the migration type and the corresponding Python function to be executed. The migration types can... | 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]…\new_string\": \"RATE_LIMIT_PATTERN = re.compile(\\n r\\\"rate.?limit|RateLimitError|statusCode\\\\W+429|too many requests|quota|usage limit reached\\\",\\n re.IGNORECASE,\\n)\\nCLAUDE_LIMIT_PATTERN = re.compile(\\n r\\\"Claude usage limit reached\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n606.05988] Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation\",\"url\":\"https://arxiv.org/abs/2606.05988\"},{\"title\":\"Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation\",\"url\":\"https... | 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]…\ne view for the in-game viewmodel\\n# <id>_card.png 512x320 3/4 hero shot for the buy menu\\n# Run: blender -b -P weapons.py -- <out_dir>\\nimport bpy\\nimport math\\nimport sys\\n\\nOUT = sys.argv[sys.argv.index('--') + 1] if '--' in sys.argv else '/... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a security engineer. Prioritize defense-in-depth and concrete mitigations."
},
{
"role": "user",
"content": "What are the ethical implications of facial recognition technology?"
},
{
"role": "assistant",
"content": "# Ethical Implications of Fa... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n ENABLE_LLM_ADJUDICATION: bool = _env_bool(\\\"ENABLE_LLM_ADJUDICATION\\\", True)\\n RELEVANT_THRESHOLD: float = _env_float(\\\"RELEVANT_THRESHOLD\\\", 0.75)\\n NOT_RELEVANT_THRESHOLD: float = _env_float(\\\"NOT_RELEVANT_THRESHOLD\\\", 0.25)\", \... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that compares two lists of numerical values: the true values and the predicted values of a time series model. Write a function `compare_values(true_values, predicted_values)` that returns a dictionary containing the following keys ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the distance between two geodetic points given their coordinates and heights. A geodetic point is defined by its latitude, longitude, orthometric height, and ellipsoidal height. The distance can be calculated using the... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates a simple game of rock-paper-scissors. Write a Python function `rock_paper_scissors(player1, player2)` that takes two string arguments representing the choices of two players and returns the result of the game based o... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Look for uniqe archetectures now.\nAssistant: Hunt exotic architectures."
},
{
"role": "assistant",
"content": "<think>\nThe user just asked me to “Look for uniqe archetectures now.” They are clearly shifting focus from the collection of recent papers toward explori... | 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 generating a Look Up Table (LUT) for Absolute Humidity (AH) at 100% Relative Humidity (RH) based on a list of temperature values. The Absolute Humidity is calculated using a formula that incorporates constants. Your task is to implement a function `gen_ah_lu... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of integers representing the scores of a game. The game has a rule that a player can only score if the previous two scores are both even. If the player's score is even, it is added to the total score; otherwise, it is ignored. Write a function `calculate_to... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that validates the inputs for a command-line tool. The function should take three string arguments: `config_path`, `model_name`, and `task_name`. Your job is to ensure the following validations: 1. The `config_path` must not be an emp... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n/home/lane/MythosMini/train.py\", \"old_string\": \"if __name__ == \\\"__main__\\\":\\n raise SystemExit(main(sys.argv))\\n\\n\\ndef entry_point_exists() -> bool:\\n return True\", \"new_string\": \"if __name__ == \\\"__main__\\\":\\n raise Syste... | 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": "t len 376\nAssistant: Only 37 — thinking lives in separate assistant entries than text, and I reset user too early. Fix pairing: accumulate thinking across consecutive assistant blocks, keep user until next real user.\nAssistant action: Edit {\"file_path\": \"/home/lane/cc/scri... | 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": "<command-name>/login</command-name>\n <command-message>login</command-message>\n <command-args></command-args>\n<local-command-stdout>Login successful</local-command-stdout>\nContinue. (re-fan out)\nContinue. (re-fan out). but also prioritze research and m... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n~~~~~~~~~~~~~~~~~~~~^^^^^^\r\n File \"C:\\Users\\user\\AppData\\Roaming\\uv\\python\\cpython-3.13.3-windows-x86_64-none\\Lib\\asyncio\\base_events.py\", line 719, in run_until_complete\r\n return future.result()\r\n ~~~~~~~~~ …[truncated]\nA... | 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 given a string `frase` containing a sentence in Portuguese. Your task is to write a Python function that extracts the third character of each word in the sentence and returns a new string containing these characters in the order they appear in the original sentence. If ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n call) Bash input={\"command\": \"sed -n '380,520p' /home/user/MythosMini/docs/functions.md\", \"description\": \"Read docs entries for plan_tasks, rate_limit_handoff, freebuff functions\"}\nResult: **Callers/Callees:** Called by `main`, `ralph_loop` (via... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a simple system to manage contributors and the issues they are assigned to in a project. Define two classes, Contributor and Issue, each with specific attributes. The Contributor class should have the following attributes: 'name' (a string with a ma... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates a simple database management system. Your function should be able to perform the following operations: create a new database, retrieve the current database instance, and close the database. Implement a function `mana... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates the control of a messaging system based on given commands and options. The function should accept a list of command-line arguments that include options for controlling the messaging system and a command to execute. Your... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n+130ms service=llm providerID=opencode modelID=deepseek-v4-flash-free session.id=ses_151c45bb8ffeLm13vY3ttZ7l7E small=false agent=build mode=primary error={\"error\":{\"name\":\"AI_APICallError\",\"url\":\"https://opencode.ai/zen/v1/chat/completions\",\"r... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with writing a function that calculates the number of days since a given examination date. The function should take three parameters: a string representing the model name of the test result, a string representing the name of the test, and a date (in the format 'Y... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "make me a browser-based CAD editor\nAssistant: I'll build you a browser-based CAD editor. Let me first check what's already in this directory.\nAssistant action: PowerShell {\"command\": \"Get-ChildItem -Force D:\\\\physics\\\\cad | Select-Object Name, Length, Mode\", \"descrip... | 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]…\n664278030396 \nstep_00012000.pt 1.0998713970184326 \nstep_00014000.pt 1.1038994789123535 \nstep_00016000.pt 1.095629096031189 \nstep_00018000.pt 1.0993962287902832 \nstep_00020000.pt 1.0919594764709473 \nstep_00022000.pt 1.0710875988006592 \nstep_00024000... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "[Request interrupted by user]\nIts showing \"RECOVERY NEEDED\" when the agent is clearly still working. ALso, its INCREDIBLY STUPID. (live, still going I think). http://127.0.0.1:3100/GLI/issues/GLI-240\nAssistant action: Bash {\"command\": \"curl -s http://127.0.0.1:3100/api/i... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "iency 9.66 (rank 10/36)\ngen2_gen1_gen0_step_00006000+step_00007630@t0.66+step_00007630@t0.65+gen1_gen0_step_00007630+step_00006000@t0.20+gen0_step_00007630+step_00007630@t0.50@t0.35@t0.20: wiki_ppl 5.164 blimp 57.51 arc 31.40\ngen2_gen1_gen0_step_00006000+step_00007630@t0.66+s... | 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": "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": ": The file /home/lane/GR/glint-cli/src/core/agent.ts has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Bash {\"command\": \"tmux send-keys -t glint C-t && sleep 0.3 && tmux send-keys -t glint '/usage' && sleep 0.... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are working on a network packet processing system that involves handling various events related to packet transmission and reception. Your task is to implement a function `check_event_rules(events)` that takes a list of events and returns True if the events adhere to the fo... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "rc/commands.ts:4:import { memoryPath, readMemory } from \"./core/memory.ts\";\nsrc/commands.ts:31: { name: \"memory\", description: \"show persistent memory\" },\nsrc/commands.ts:142: case \"memory\": {\nsrc/commands.ts:143: const mem = readMemory();\nsrc/commands.ts:1... | 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": "his.save();\\n for (const fn of this.listeners) fn(path, val);\\n }\\n\\n onChange(fn) { this.listeners.push(fn); }\\n offChange(fn) {\\n const i = this.listeners.indexOf(fn);\\n if (i >= 0) this.listeners.splice(i, 1);\\n }\", \"old_string\": \" if (g === 'grap... | 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": "<task-notification>\n<task-id>b5ezyrm78</task-id>\n<summary>Monitor event: \"double-decoder iteration sweep results\"</summary>\n<event>{\"tag\": \"5d_1200\", \"seed\": 7, \"baseline\": 0.958, \"double\": 0.998, \"best_of_k\": 0.894, \"vote\": 0.998, \"oracle\": 1.0, \"dd_param... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of robots, where each robot can be assigned to specific targets. Each robot can only be assigned to one target, and each target can be assigned to at most one robot. Write a function that takes in a list of robots and their valid target IDs, and returns a v... | 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": "/code/boeing-fable/frontend.ts has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Bash {\"command\": \"cat > /tmp/dbg.ts <<'EOF'\\nimport puppeteer from \\\"puppeteer\\\";\\nconst browser = await puppeteer.launch(... | 1 | victor/fable-5-boeing-747-trace | 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 simulates basic banking operations for a single account. The function should take a list of operations as input, where each operation is represented as a tuple. The first element of the tuple indicates the operation type, which can be... | 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 Python dictionary `state_dict` containing information about the states in a country. Each key-value pair in the dictionary represents a state and its corresponding attributes. Your task is to write a function that extracts and returns the names of the states who... | 1 | v3-rft-acecode | true |
[
{
"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 position and the layout of the world are represented by a 2D grid... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with processing product data in an inventory system. Implement a function `process_product_data(tables, title, price, price_old, brand, link)` that processes the given product data and handles potential exceptions according to the following rules: \n\n1. If the p... | 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 creating a function that simulates basic banking operations. The function should accept three parameters: an initial balance, a list of deposit amounts, and a list of withdrawal amounts. The function should return the final balance after processing all depos... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a 2D list of rotation vectors, where each inner list represents a rotation vector in a batch. Your task is to calculate the average magnitude of these rotation vectors using the Euclidean norm. Write a function `average_magnitude(rot_vecs: List[List[float]]) -> fl... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a knowledgeable technology educator. Explain concepts at the right level for the question."
},
{
"role": "user",
"content": "What does HTTP status code 301 Moved Permanently mean?"
},
{
"role": "assistant",
"content": "# HTTP 301: Moved Permane... | 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": "n [-58, 11, -46],\\n ],\\n look: [\\n [0, 6.5, 0],\\n [0, 6.5, 0],\\n ],\\n fov: [37, 37],\\n ease: easeInOut,\\n },\\n];\", \"old_string\": \"export const SHOTS: Shot[] = [\\n {\\n // 1 \\u2014 The Face: low\nResult: <tool_use_error>String to... | 1 | victor/fable-5-boeing-747-trace | 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: Please summarize what is differnt about this arch than normal llama. and what slerp does at the end.\nAssistant action: Bash {\"command\": \"ls /home/lane/MythosMini && grep -n \\\"slerp\\\" -ri /home/lane/MythosMini --include=*.py | head\", \"description\": \"List repo a... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a database engineer with deep Postgres operational experience. Treat schema changes as production incidents waiting to happen."
},
{
"role": "user",
"content": "Review this migration. We're going to run it on a 200M-row table during a low-traffic window:\n... | 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": "<task-notification>\n<task-id>bzovuir82</task-id>\n<tool-use-id>toolu_01NrQJa83bNRPxvZEPW5PCjr</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane/22bb18a2-14fc-4d00-b566-037d9c98da2f/tasks/bzovuir82.output</output-file>\n<status>completed</status>\n<summary>Background comm... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": " ACPI EC detected.\n Race condition possible.\nJun 10 19:21:02 LaneAI kernel: hwmon hwmon6: Concurrent access to the ACPI EC detected.\n Race condition possible.\nJun 10 19:21:04 LaneAI kernel: hwmon hwmon6: Concurrent... | 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": "Look at paperclipai, then please refine how Groq models work. Multiple times has this happened. I send a simple request, it stalls at thionking, it updates to in progress, I now have two ghost agents and it warning me about \"This task still needs a next step.\". Please just r... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that converts a given volume in cubic meters to cubic feet. The conversion rate is that 1 cubic meter is equal to 35.3147 cubic feet. Your function should take a single parameter, volume_cubic_meters, which represents the volume in cubic ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that takes a string as input and returns a modified version of the string based on specific rules. The function should perform the following operations: 1. Convert the input string to lowercase. 2. Replace all occurrences of the le... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function to shuffle a given dataset to prevent using the result at time t to calculate the result at the same time t. This is crucial for time-series data analysis to avoid data leakage and ensure the model's predictive capability. Write a Pyt... | 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": "eY(-2px);\\n}\", \"replace_all\": false}\nResult: The file /home/lane/MythosMini/slm_alliance.html has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"file_path\": \"/home/lane/MythosMini/slm_alliance.html\... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "d(open(\\\"configs/tools.json\\\", encoding=\\\"utf-8\\\"))\\nlines = open(\\\"data/examples_sample.jsonl\\\", encoding=\\\"utf-8\\\").readlines()\\nkw = {\\\"enable_thinking\\\": False}\\n\\nfor n, line in enumerate(lines):\\n ex = json.loads(line)\\n p, tgt = expert_tar... | 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 given a list of integers representing a puzzle input. Your task is to calculate the sum of the products of adjacent pairs of integers in the list. If the last integer is reached, the \"next\" integer will be the first integer in the list. Write a function to compute thi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given an array `arr` containing integer values. Your task is to write a function `calculateEnvironmentalImpact` that calculates the environmental impact based on the given array. The environmental impact is calculated by multiplying the total amount of oxygen and carbon... | 1 | v3-rft-acecode | true |
[
{
"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": "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: using the discord bot token in .env, look at the Glint Research server and properly configure the Muted role\nAssistant action: Bash {\"command\": \"grep -i token /home/user1/Blindbot/.env | sed 's/=.*/=<present>/'\", \"description\": \"Check token var name in .env\"}\nRe... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the roots of a quadratic equation given its coefficients. The function should take three input parameters representing the coefficients of the quadratic equation (a, b, and c) and return the two roots (x_c and x_d) as ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nhitscan damages bot at close range — bot hp 100 -> 100\n ✔ bot AI navigates the map — 4/4 bots moved\n ✔ killing all bots ends round in player win — score 0 -> 1\n ✔ kill + win money awarded — $800 -> $5250\n ✔ next round enters buy phase — reached vi... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "\"command\": \"cd /home/lane/claude/fable_cot\\npython3 - <<'PY'\\nimport json\\nrecs=[json.loads(l) for l in open(\\\"fable5_cot_merged.jsonl\\\")]\\ndef endok(s):\\n s=(s or \\\"\\\").rstrip()\\n return bool(s) and s[-1] in \\\".!?\\\\\\\"')]}`\\\"\\n# show first few no... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "ated Websites in glint-cli\n\n## Recommended architecture\nAssistant: All 4 agents back. Synthesis:\n\n**Diagnosis (why output is \"stupid\"):** harness has heavy anti-fabrication guards but **zero design scaffolding**. Weak text-only model + no design knowledge → GitHub-cloned... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "As a helpful assistant, i'm skeptical and critical for an open source contribution because blood test results came back with hemoglobin 11.2, ferritin 15, B12 180. I'm a site reliability engineer trying to figure out what can I safely read into these before talking to my doctor... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "As a study buddy helping prepare for technical interviews, i'm a devops engineer here. building a home lab for electronics prototyping. I'm paranoid about edge cases about what safety equipment is actually necessary vs. overkill. But I also need to know: what voltage/current th... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that takes a list of items and returns a new list containing only the callable items from the original list. The input list may contain a mix of functions, integers, strings, and other objects. Your function should filter out any non-... | 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.