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": "able 5) on general coding tasks through harness/loop architecture alone โ NO new model, NO new API keys.\n\nFirst, ground yourself: read /home/lane/GR/glint-cli/src/core/agent.ts (the runTurn loop, the nudge guards, reviewGoal, runSubagent), src/core/config.ts (the EFFORT_LEVEL... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\n\\nimport threading\"}\nResult: The file C:\\Users\\user\\Documents\\github\\teich\\src\\teich\\studio\\interactive.py has been updated successfully. (file state is current in your context โ no need to Read it back)\nAssistant action: Edit {\"replace_all\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that generates a formatted string representation of an HTTP response. The function should take in the following parameters: a list of addresses, a boolean indicating if the response is fatal, an integer representing the number of retr... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "ches ALL `step_*.pt`. With 2000-step interval over 2B tokens = many. SLERP only needs top diverse seeds. Pre-filter by cheap proxy (last-N or every-other) before full 3-dataset bench.\n\n**6. `total` loss tensor accumulates on device.** `accumulate_gradients:70` keeps running G... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with validating and processing user data for a web service. Write a function `store_user_data(client_id, content)` that takes in two parameters: `client_id` and `content`. The function should perform the following checks: \n1. Validate that `client_id` is a non-e... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "ionMove,\\n onSuggestionComplete,\\n onSuggestionAccept,\\n}: InputProps): React.ReactElement {\", \"replace_all\": false}\nResult: The file /home/lane/GR/glint-cli/src/components/Input.tsx has been updated successfully. (file state is current in your context โ no need to Rea... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "I'm in need of a 3D video game that I can play online with my friends. Something like an online skate park where we can go and do tricks and stuff\nAssistant: I'll build you a 3D multiplayer skate park game โ Three.js for the graphics, a Node.js WebSocket server so you and your... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that processes a list of IDs and returns a new list containing only the IDs that meet specific criteria. The IDs are represented as strings and must adhere to the following conditions: 1. The length of each ID must be at least 5 ch... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\nfrom your prompt. A goal reviewer reads the transcript when the agent stops and re-prompts it until the goal is actually met, not just claimed.</p></div>\\n <div class=\\\"card\\\"><h3><sp โฆ[truncated]\nResult: The file /home/lane/GR/site/index.html ... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are given a string containing only the characters '(' and ')'. Your task is to implement a function `count_invalid_parenthesis(string)` that takes this string as input and returns the minimum number of invalid parentheses that need to be removed to make the sequence valid. ... | 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 debugger helping trace through complex logic, for a blog post, I need to produce a 4,500-word essay on fairness in machine learning. I'm a tech lead reviewing code who's excited but uncertain about definitions, impossibilities, and engineering. The essay needs to cover: im... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\n:\"2026-06-11T17:15:49.889Z\",\"requiresRestart\":true}\nAssistant action: Bash {\"command\": \"AID=d027bfa7-6d38-412b-94a7-1766519a20da; R=$(curl -s -m15 -X POST \\\"http://localhost:3100/api/agents/$AID/wakeup\\\" -H \\\"Content-Type: application/json\\... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\n: 130}\nResult: 826\t </footer>\n827\t</div>\n828\t</div>\n829\t<script>\n830\tconst models = [\n831\t {\n832\t name: 'MicroSupra-1k',\n833\t org: 'supralabs',\n834\t params: '1K',\n835\t blimp: 58.61,\n836\t arc: 26.39,\n837\t wiki: 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": "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": "โฆ[earlier truncated]โฆ\ner({ server, path: '/ws' });\\n wss.on('error', () => {}); // http server owns error handling (port retry)\\n apiRouter.presence = () => presence;\"}\nResult: The file /home/user/rblx/server/realtime.js has been updated successfully. (file state is curr... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with processing output data from a simulation tool called CMPSim. The output data consists of sets of information related to warmup instructions and representative regions. Each entry in the output data can either represent only warmup instructions, only a repres... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "| assistant actions (CoT calls): 4665\nSKILL/TOOL COVERAGE taught:\n 960 Edit\n 866 ASSISTANT_MESSAGE\n 443 Read\n 311 Write\n 209 Bash:grep\n 136 PowerShell\n 121 Bash:cd\n 111 Bash:cat\n 83 Bash:python3\n 82 Bash:make\n 80 Bash... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are given a string representing a comma-separated values (CSV) data. Write a function that takes this CSV string as input and returns a list of lists, where each inner list represents a row of data from the CSV. Each row should contain the values as strings. Ensure that the... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\n\t-rw-r--r-- 1 aranr 197609 4565076 Jun 12 17:22 8k_earth_daymap.jpg\n7\t-rw-r--r-- 1 aranr 197609 3144468 Jun 12 17:22 8k_earth_nightmap.jpg\n8\t-rw-r--r-- 1 aranr 197609 1905513 Jun 12 17:22 8k_stars_milky_way.jpg\n9\t-rw-r--r-- 1 aranr 197609 3367... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"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": "You are tasked with implementing a function `select_coins(coins, target)` that selects a combination of coins to reach a target sum. The input `coins` is a list of dictionaries, where each dictionary represents a coin with a key `amount` indicating its value (an integer). The `... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\n return DeviceInfo(\n23\t device=\"cuda\",\n24\t name=properties.name,\n25\t total_memory_bytes=total_bytes,\n26\t free_memory_bytes=free_bytes,\n27\t supports_bf16=torch.cuda.is_bf16_supported(),\n... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Please summarize what is differnt about this arch than normal llama. and what slerp does at the end."
},
{
"role": "assistant",
"content": "<think>\nThe user wants a summary of differences between \"this arch\" and a normal LLaMA model, and also an explanation of wh... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with analyzing a list of build statuses and counting the number of failed builds and the number of failed builds triggered by pull requests (PRs). You need to implement a function called `count_failed_builds` that takes a list of build statuses as input and retur... | 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": "โฆ[earlier truncated]โฆ\nt(bob): /tmp/glint-shots/04-bob-sees-alice.png\n shot(alice): /tmp/glint-shots/05-alice-ingame.png\nโ
leave: both returned to game page\nโ
studio place: part count 3 (baseplate+spawn+kill brick)\n shot: /tmp/glint-shots/06-studio.png\nโ
studio select:... | 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": "Well, my opencode session limit has hit. See if it detects it properly. if not, fix it.\nAssistant: Run real opencode call to capture actual limit error.\nAssistant action: Bash {\"command\": \"timeout 120 opencode run --model opencode/deepseek-v4-flash-free \\\"reply with the ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\nctcjGfCJpQWhyGWGdyb3FY973wby4QtPHbqVi9zalN4vpe\"\n }\n },\n \"model\": \"groq/compound\",\n \"extraBody\": {\n \"compound_custom\": {\n \"tools\": {\n \"enabled_tools\": [\n ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "As a researcher documenting how experts solve problems, i'm a security researcher at work. I'm methodical and careful about the Needham-Schroeder protocol replay attack, specifically tracing the exact message sequence where the attacker wins. How do you form a hypothesis here? ... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "As a curious learner trying to understand, i'm excited but uncertain at work and trying to understand Hindley-Milner let-polymorphism and the escaping variable problem. I'm a devops engineer struggling with the actual semantic disaster of generalizing free variables. How do you... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a simple data structure to represent a blog post. Each blog post has a title, content, and an author. Your objective is to implement a function `serialize_blog_post` that takes in a dictionary representing a blog post with the keys 'title', 'content... | 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": "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": "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 version comparison function that compares two version strings and determines which one is greater. A version string is a series of numbers separated by periods, such as '1.2.3'. The comparison should follow the standard version comparison rules, w... | 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 implementing a function that simulates flipping tiles on a game board. The game board consists of a grid of tiles, each identified by its position. Initially, all tiles are in the 'off' state. The function should take a list of tile positions to flip and ret... | 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": "s://ec.\nAssistant: I have enough on the design-system fundamentals. Now let me get the animation library specifics via Context7 (GSAP, Motion/Framer) and search for View Transitions / CSS scroll-driven + Anthropic's artifact/Claude design guidance.\nAssistant action: mcp__cont... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "add animations. make it look super duper high quality. (slm_alliance.html). do nto make it look like AI.\nAssistant action: Read {\"file_path\": \"/home/user/MythosMini/slm_alliance.html\"}\nResult: File content (755KB) exceeds maximum allowed size (256KB). Use offset and limit... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of strings representing Python code snippets. Your task is to count the occurrences of specific keywords within these snippets. The keywords to be counted are provided in a separate list. Your function should return a dictionary where the keys are the keywo... | 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": "โฆ[earlier truncated]โฆ\nash input={\"command\": \"make fix >/dev/null 2>&1; make lint && make test 2>&1 | tail -2 && .venv/bin/python - << 'EOF'\\nimport ralph, time, types\\n\\ncalls = []\\nralph.ensure_freebuff = lambda: (calls.append(\\\"ensure\\\"), True)[1]\\nralph.subproce... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "Implement a function `circular_queue_operations(operations: List[Tuple[str, int]]) -> List[Union[bool, int]]` that simulates a circular queue based on a list of operations. The operations are provided as a list of tuples where each tuple consists of an operation name (a string)... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Build POV-Ray 2.2. Find and download the source archives, extract them to `/app/povray-2.2`, then compile and install to `/usr/local/bin/povray`.\n\n**Environment constraint:** The image already includes `build-essential`, `wget`, and `ncompress`. Do **not** use `apt-get instal... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "hand-drawn\"\n\nLinks: [{\"title\":\"Simulating Hand-Drawn Motion with SVG Filters - Camillo Visini\",\"url\":\"https://camillovisini.com/coding/simulating-hand-drawn-motion-with-svg-filters\"},{\"title\":\"Anthropic Ai Animations - Free Download in GIF, Lottie JSON\",\"url\":\... | 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": "You are tasked with implementing a Python function that calculates the average temperature for each month based on provided temperature data from a weather station. Your function should handle missing data by replacing it with a specified default value. You are given a dictiona... | 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": "โฆ[earlier truncated]โฆ\n (tool call) Bash input={\"command\": \"grep -rn \\\"authToken\\\" /home/user/paperclip/server/src --include='*.ts' -l | grep -v test | head; grep -rn \\\"authToken\\\" /home/user/paperclip/server/src/services/plugin-environment-driver.ts /home/user/paper... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a substitution cipher that can either encrypt or decrypt messages based on a provided cipher key. The cipher works by replacing each letter in the message with a corresponding letter from the key. The key is a string that contains all the letter... | 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": "user",
"content": "You are tasked with creating a program to determine the installation order of software packages based on their dependencies. Each package may have zero or more dependencies, and your goal is to return a list of packages in the order they should be installed to ensure all depend... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates capturing images at specified intervals from a virtual rendering environment. The function should take in a list of intervals (in milliseconds) and a filename, and it should return a list of filenames indicating the ima... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "th\": \"/home/lane/GR/glint-cli/src/core/tools.ts\", \"limit\": 20, \"offset\": 290}\nResult: 290\t const res = await chat(\n291\t [\n292\t {\n293\t role: \"user\",\n294\t content: `Search the web and answer concisely with source URLs:... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a simple grid navigation algorithm for an agent in a simulated environment. The environment is represented by a grid where the agent can move in four directions: up (0), down (1), left (2), and right (3). The agent starts at a given position 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": "You are tasked with simulating a simple robot controller. The robot starts at position (0, 0) and faces the positive y-axis initially. Implement a function `execute_commands` that takes a string of commands as input. The commands can be 'F' (move forward), 'B' (move backward), ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates loading torrent files. The function should accept three parameters: `path`, `scgi`, and `mount`. The `path` parameter is a string that represents the directory containing the torrent files (default should be '.' if not prov... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates a simple vending machine. The vending machine should be able to dispense items based on user input and maintain an inventory of available items. The items available for purchase will be predefined, and the vending machine 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": "user",
"content": "โฆ[earlier truncated]โฆ\nESULT: The file /home/user/MythosMini/tests/test_ralph_helpers.py has been updated successfully. (file state is current in your context โ no need to Read it back)\nAssistant action: Bash {\"command\": \"make fix >/dev/null 2>&1; make lint 2>&1 | grep -E \... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with writing a Python function that takes a string as input and returns a dictionary where the keys are the strings and the values are the number of backslashes present in each string. Your function should handle multiple strings provided in a list format. The in... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\nturn f\\\"{INCOMPLETE_SENTINEL}: verification hit a rate limit; verify everything yourself\\\"\"}\nResult: The file /home/user/MythosMini/ralph.py has been updated successfully. (file state is current in your context โ no need to Read it back)\nAssistant ... | 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": "Now, look at the most recent AI prompting guides (look at a minimum of 5) then summarize them. Then look at your agent.md. What should be improved so the agent actually listens and doesnt veer of track every five messages?\nAssistant: Load web tools, then research.\nAssistant a... | 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": "โฆ[earlier truncated]โฆ\ni.config import LEADERBOARD_URL\\nfrom src.mythosmini.leaderboard.entries import LeaderboardEntry, parse_leaderboard_html\\n\\nFETCH_TIMEOUT_SECONDS = 30.0\\n\\n\\ndef download_leaderboard_html(url: str = LEADERBOARD_URL) -> str:\\n request = urllib.re... | 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": "<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": "user",
"content": "You are tasked with implementing a function that validates file formats for a web application. The function should take a list of allowed file formats and a file format to validate as input. If the file format is not in the allowed list, the function should raise a `ValidationE... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with analyzing a given list of strings representing lines of source code to count the occurrences of specific license-related comments. License-related comments are defined as any comment line that contains the word \"License\" or \"licence\" (case-insensitive). ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\nenwise_divergence\\n\\ntorch.manual_seed(0)\\nfor dtype, atol in [(torch.float32, 1e-6), (torch.bfloat16, 1e-2)]:\\n s = torch.randn(57, 400, dtype=dtype, requires_grad=True)\\n t = torch.randn(57, 400, dtype=dtype)\\n\\n # reference: plain autog... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to calculate the win-loss-draw ratios for a set of AI agents based on the outcomes of duels between them. Each agent can have an outcome of 'win', 'loss', or 'draw' against another agent. You are given a list of agents and a list of p... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "unt_parameters,\ntests/test_model.py:26:def test_default_config_lands_near_one_million_parameters() -> None:\ntests/test_model.py:28: total = count_parameters(model)\ntests/test_model.py:87: optimizer = torch.optim.NAdam(model.parameters(), lr=3e-3, decoupled_weight_decay... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that extracts metadata from a given dictionary representing a Python package's setup configuration. The dictionary contains the following keys: 'long_description', 'classifiers', and 'install_requires', which represent the long des... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "โฆ[earlier truncated]โฆ\neep 2; done`). To wait for a command you started, use run_in_background: true. Do not chain shorter sleeps to work around this block.</tool_use_error>\nAssistant action: ToolSearch {\"query\": \"select:Monitor\", \"max_results\": 1}\nResult: \nAssistant a... | 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": " \nstep 3108 skipped: non-finite grad norm (inf) \nstep 3109 skipped: non-finite grad norm (inf) ... | 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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.