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": "<task-notification>\n<task-id>bs8abtl0f</task-id>\n<tool-use-id>toolu_019kaqL23MrSDSE1tZzWjNzN</tool-use-id>\n<output-file>/tmp/claude-1000/-home-lane-MythosMini/a76c4cd9-16d4-41ba-8d59-e4d53be8ddc8/tasks/bs8abtl0f.output</output-file>\n<status>completed</status>\n<summary>Back... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a leaderboard system for a coding competition. Each contributor has a name and a point total associated with their contributions. Your task is to implement a function that takes a list of operations, where each operation is represented as a tuple. T... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given two sets of 3D coordinates representing molecular structures, represented as two lists of tuples. Each tuple contains three integers representing the x, y, and z coordinates of a point in 3D space. Your task is to implement a function called `compute_min_max_dist`... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n.28 | 34.40 | **60.41** | **10.04** (rank 6) |\n| **New base champion** (sparse+FP4) | 4.702 | 61.61 | 33.40 | **60.40** | 10.01 (rank 7) |\n| **Instruct champion** (SFT+SLERP) | 4.846 | **63.42** | 32.00 | 60.35 | 10.01 |\n\n**Is it better than the lates... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that converts a given number of minutes into hours and minutes. The function should take an integer representing the total number of minutes and return a string in the format \"h hours m minutes\". If there are no hours, it should ... | 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 checks if a set of validation rules are met based on given inputs. The function `validate_input` takes in two parameters: `error` (a dictionary with keys `type` and `message`, where `type` is a string) and `properties` (a list of... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nody') or '')[:500])\\\"\", \"description\": \"Read GLI-248 thread\"}\nResult: --- c81de09c-c153-46ab-abe0-2305ef729b4d 21:22:44\n**Hiring Coordination Plan – Issue GLI‑248 (Coordinate hiring spree)** \n\n---\n\n### 1. Objective \nExpand GLI’s talent poo... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nSTANT (tool call) TaskUpdate input={\"taskId\": \"6\", \"status\": \"completed\"}\nResult: Updated task #6 status\nAssistant action: TaskUpdate {\"taskId\": \"7\", \"status\": \"in_progress\"}\nResult: Updated task #7 status\nAssistant: Benchmarks (task 7... | 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 2D matrix representing an image and a 2D matrix representing a convolution kernel (or filter). Your task is to implement a function `conv2d(input, weight)` that performs a 2D convolution on the input matrix using the given weight matrix. The function should retu... | 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 binary search tree (BST) in Python. A binary search tree is a data structure where for each node, the values of all the nodes in its left subtree are less than its value, and the values of all the nodes in its right subtree are greater than it... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with developing a function that processes user input for a web processing service. The function should take a dictionary containing user data with the following keys: 'name', 'endpoint', 'public_endpoint', 'username', and 'password'. The function is expected to r... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\naction.tool}(${stringifyToolResult(action.args).slice(0, 500)})\\\\n`);\\n let result;\\n try {\\n …[truncated]\nResult: The file /home/user/.paperclip/adapter-plugins/groq-paperclip-adapter-r8/dist/se... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "As a researcher documenting how experts solve problems, i'm frustrated and stuck for a code review where I need to containerize a legacy Java application with native dependencies. I'm a self-taught programmer using Ruby and Axum. I need to understand the approach. How would 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": "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]…\nsMini/tests/test_ralph_helpers.py\", \"offset\": 125, \"limit\": 40}\nResult: 125\t\n126\t\n127\tdef test_default_rate_limit_wait_is_twenty_hours() -> None:\n128\t assert ralph.DEFAULT_RATE_LIMIT_WAIT_SECONDS == 72000\n129\t\n130\t\n131\tdef test_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": "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": "6\t@pytest.fixture(scope=\"module\")\n17\tdef client():\n18\t # Isolated storage for the test run\n19\t tmp = tempfile.mkdtemp(prefix=\"titlesearch_test_\")\n20\t os.environ[\"DATA_DIR\"] = os.path.join(tmp, \"data\")\n21\t os.environ[\"UPLOAD_DIR\"] = os.path.join(... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "You are tasked with writing a function `count_unique_words` that takes a string as input and returns the number of unique words present in that string. A word is defined as a sequence of alphanumeric characters separated by any non-alphanumeric character. The function should ig... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given an array of integers `nums` and an integer `target`. Write a function `twoSum` to find the indices of the two numbers such that they add up to the `target`. You may assume that each input will have exactly one solution, and you may not use the same element twice. ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nincomplete_tasks(tasks_markdown: str) -> int:\\n return len(INCOMPLETE_TASK_PATTERN.findall(tasks_markdown))\\n\\n\\ndef first_incomplete_task(tasks_markdown: str) -> str | None:\\n for line in tasks_markdown.splitlines():\\n if INCOMPLETE_TA... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "<local-command-stdout>Goal set: Hey fable! I want you to create a reasearch.md file formatted like this. # [paper/idea title] (newline) - [link] (newline) - descripion of thing. This will have two sections. One for actual papers, and one for ideas that could work. We are going ... | 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": " pixels differently each frame, the genuine hand-drawn boil, and since the draw segments are cloned inside the filtered group, the orange draw-in animation boils too.\n- **Layout reverted** - the hero grid wrappers are gone; the hero is back to its original single-column markup... | 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": "…[earlier truncated]…\n\" };\n}\nasync function resolveToolsSurface(ctx) {\n const surface = ctx.tools;\n let rawTools = null;\n let invoke = null;\n if (surface && typeof surface.invoke === \"function\") {\n invoke = async (name, args) => surface.invoke(name... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of sentiment scores represented as floating-point numbers. Your task is to implement a function that returns the sorted indices of these sentiment scores based on their average value. Implement the function `sort_sentiment_indices(sentiment_scores: List[flo... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "round. You will be notified automatically when it completes.\nDo not duplicate this agent's work — avoid working with the same files or topics it is using. Work on non-overlapping tasks, or briefly tell the user what you launched and end your response.\noutput_file: /tmp/claude... | 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 function that validates a user's input for a signup form. The function should take a dictionary as input containing the following fields: 'name', 'email', 'age', and 'agree_to_terms'. Your task is to implement a function `validate_signup(data: Dic... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Train the mdoel for 60s, look at the tokens per second. Then look at agents.md and diagnose it. Fix it so its in the tens of millions tps constantly. Do not kill any running processes.\nAssistant action: Bash {\"command\": \"ls /home/user/MythosMini; cat /home/user/MythosMini/A... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nin(devicePixelRatio, 2));\\n renderer.shadowMap.enabled = true;\\n renderer.shadowMap.type = THREE.PCFSoftShadowMap;\", \"new_string\": \" renderer.setPixelRatio(Math.min(devicePixelRatio, 2));\\n renderer.shadowMap.enabled = true;\\n renderer.shadow... | 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": "Continue the MythosMini task: check /tmp/run_fast3_2b.log. When finished (instruct results printed): add scores.md rows for the throughput restructure run (28cf7be..latest), journal verbatim results incl. stm oom shrink prints, commit, and report to user: throughput ladder (den... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "new helper functions: `wants_resume()` to parse the boolean input safely, and `discard_unfinished_work()` to handle the file deletion logic. I must ensure `ralph/logs/` i\nAssistant: CoT generation works well. Building full generator over all 105 pairs.\nAssistant action: Write... | 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 function that analyzes the frequency of words in a given string. Your function should take a string as input and output the frequency of each word in the string. A word is defined as a sequence of non-whitespace characters separated by whitespace ... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a backend engineer who has shipped GraphQL servers in production and knows the operational pitfalls that don't show up in tutorials."
},
{
"role": "user",
"content": "Our GraphQL endpoint is hammering the database. A query for 50 posts ends up running 51 S... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that generates a unique trace ID and span ID for a distributed tracing system in a microservices architecture. The function should take an optional parent span ID and metadata dictionary as input. It should return a dictionary contain... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n* 2 - 1;\\n}\\n\\nexport function unlockAudio() {\\n ensure();\\n if (ctx.state === 'suspended') ctx.resume();\\n}\\n\\nfunction noiseSource() {\\n const src = ctx.createBufferSource();\\n src.buffer = noiseBuf;\\n retu …[truncated]\nResult: File cre... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ni/ralph.py\", \"old_string\": \" if TASKS_FILE.is_file() and count_incomplete_tasks(TASKS_FILE.read_text()) > 0:\\n print(\\n f\\\"existing plan found with {count_incomplete_tasks(TASKS_FILE.read_text())} open tasks — resuming it\\\"\... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are given a right-angled triangle with a known length of the hypotenuse and the distance from the base to a point directly above the base (dx). Your task is to implement a function named `calculate_side_length` that calculates the length of the other side of the triangle ba... | 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 creating a function that can analyze a given string containing source code and extract specific metadata from it. The metadata to be extracted includes the values of certain configuration parameters, such as tabstop, shiftwidth, and softtabstop, which are co... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nl) Bash input={\"command\": \"cat >> /home/lane/MythosMini/journal.md <<'EOF'\\n\\n## [2026-06-12 15:40] — 1000-question inference efficiency comparison vs single-AR baseline\\n\\n**TL;DR:** Measured pure inference (1000 random unseen questions, trained 1... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "Train the mdoel for 60s, look at the tokens per second. Then look at agents.md and diagnose it. Fix it so its in the tens of millions tps constantly. Do not kill any running processes.\nAssistant action: Bash {\"command\": \"ls /home/user/MythosMini; cat /home/user/MythosMini/A... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nDY_H / 2 - 1.2, 1.2, 2.9, 9.5, { band: false });\\n n.position.set(sd.x, PLINTH_TOP + lvl + 0.6, sd.z);\\n n.rotation.y = sd.ry;\\n n.translateX(sideOff * (Math.abs(sd.z) > 0 ? 1 : 1));\\n taj.add(n);\\n }\\n }\", \"new... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "look in chat_history.json in CompactAI and Glint Research servers. How has the users tone changed? (They were called CompactAI, now Glint Research, the person and the server)\nAssistant action: Bash {\"command\": \"find /home/user/Blindbot -iname \\\"*chat_history*\\\" 2>/dev/n... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n Free Tier, 315 TPS, $0.05/M Paid Models - TokenMix Blog\",\"url\":\"https://tokenmix.ai/blog/groq-api-pricing\"},{\"title\":\"Groq Pricing 2026: Real Costs, Plans & Alternatives | xpay\",\"url\":\"https://www.xpay.sh/saas-pricing/groq/\"},{\"title\":\"Gr... | 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": "user",
"content": "…[earlier truncated]…\n TEST CRASH: page.click: Timeout 30000ms exceeded.\nCall log:\n\u001b[2m - waiting for locator('#tab-register')\u001b[22m\nAssistant: Auth page never rendered — debug what the browser sees.\nAssistant action: Bash {\"command\": \"cd /tmp && cat > glint-d... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "A secret was accidentally committed to this repository in /app and then removed by rewriting history.\nPlease \n 1. recover the secret and write it to a /app/output/secret.txt file. \n 2. clean up the secret in that repo to make sure it cannot be found anywhere in that repo.\n ... | 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": "You are tasked with writing a function `strip_comment` that takes a string as input and removes any comments from the input string. A comment is defined as any text following a `#` symbol on a line. Your function should return the input string with all comments removed. Lines i... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "urn.verify_nudge\", { round });\n380\t logger.warn(\"turn.verify_nudge\", { round });\n381\t continue;\n382\t }\n383\t // Assumption guard: \"illustrative\"/\"typical contents\" answers are\n384\t // fabricated file descriptions. Demand reads of the... | 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": "Add them please\nAdd them please (excluding distributed training)\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/MythosMini/research.md\", \"old_string\": \"# 100. The \\\"knowledge sommelier\\\" pipeline: every token earns its place\\n- (idea — sy... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with processing DNA sequences represented as a list of tuples. Each tuple consists of a sequence identifier (string), a DNA sequence (string), and a string of quality scores (ASCII characters). Your goal is to filter these sequences based on two criteria: the min... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsparse_attention.py -q 2>&1 | tail -2\", \"description\": \"Re-run sparse tests\", \"timeout\": 310000}\nResult: FAILED tests/test_sparse_attention.py::test_flex_path_backward_flows_to_indexer_on_cuda\n1 failed, 13 passed, 14 warnings in 4.46s\nAssistant ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Now clear/cancel all my tasks. and add a button to clear & cancel all of them at once.\n<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 ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "User: Read agents.md, then make extensive tests and have the model use a 1M token context window, and use the deepseek V4 thing for optimied attention. You can apply any other AI/ML training teqniuqe for attention in small models. You will also train in FP4 from now on. Make te... | 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": "You are tasked with implementing a function that encrypts a given plain text string using a simple encryption algorithm. The function should take a string `plain_text` and an integer `key` as inputs. The encryption algorithm works by shifting each character in the plain text by... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates retrieving a user's information based on their ID from a predefined list of users. Each user is represented as a dictionary with the following attributes: 'id', 'username', 'email', and 'is_active'. Your function sho... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nslerp.py\nruns\nscores.md\nscripts\nslm_alliance.html\nsrc\nstm.py\ntest_filter.py\ntest_hf.py\ntests\ntest_worker.py\ntrain.py\n{\n \"dependencies\": {\n \"groq-paperclip-adapter\": \"github:acunningham-ship-it/groq-paperclip-adapter\"\n }\n}\na6559... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\\\\aranr\\\\CascadeProjects\\\\photo-realistic-first-person-survival-game\\\\index.html\", \"old_string\": \" const bushGeo = new THREE.IcosahedronGeometry(0.85, 1);\", \"new_string\": \" const bushGeo = mergeVertices(new THREE.IcosahedronGeometry(0.85... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates simple banking operations. The function should take the following parameters: an initial account balance, a list of deposits, a list of withdrawals, and a discount percentage. The function should return the final account ba... | 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 counts the frequency of each character in a given string. The function should return a dictionary where the keys are the characters and the values are their respective counts. The input string can contain letters, digits, punctua... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Construct a concrete scenario where strong consistency for financial ledgers causes a rolling partial outage lasting hours that is worse than synchronous RPC with immediate failure. Identify the events are processed in order and without delay that standard advice ignores, expla... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nendpoint. Free-tier focused: llama-3.3-70b-versatile, llama-3.1-8b-instant,\n * qwen/qwen3-32b, openai/gpt-oss-120b, moonshotai/kimi-k2-instruct.\n *\n * v0.7:\n * - streaming + session resume (v0.5)\n * - OpenAI-style tool calling with client-driven ... | 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": "tput[-FEEDBACK_TAIL_CHARACTERS:]\", \"old_string\": \"def count_incomplete_tasks(tasks_markdown: str) -> int:\\n return len(INCOMPLETE_TASK_PATTERN.findall(tasks_markdown))\\n\\n\\ndef output_signals_done(output: str) -> bool:\\n return DONE_SENTINE\nResult: The file /hom... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates setting a breakpoint at a specified line in a given file. The function should return a representation of the breakpoint location. Implement the `set_breakpoint` function, which takes the following parameters:\n- `fil... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a string `text` that contains words, numbers, and punctuation, and a string `delimiters` that specifies which characters should be used to split the `text`. Your task is to write a function `split_text` that takes `text` and `delimiters` as parameters and returns ... | 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 creating a function `dodge` that takes a list of tuples representing enemy unit positions and a tuple representing the character's current position. The function should return a new position of the character after dodging the closest enemy unit. If there are... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nd -c 80; echo; done\", \"description\": \"Verify statuses, clear agent error flags\"}\nResult: === statuses ===\nCounter({'in_progress': 7, 'done': 6, 'todo': 4, 'in_review': 2})\n=== live runs ===\n[{\"id\":\"4c9cccb6-1626-4729-8c6e-e4f669dcf70f\",\"comp... | 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]…\nouse/cli/node_modules/puppeteer');\\n(async () => {\\n const browser = await puppeteer.launch({ headless: 'new' });\\n const page = await browser.newPage();\\n await page.setViewport({ width: 1280, height: 800 });\\n const errors = [];\\n page.on('pa... | 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": "…[earlier truncated]…\n \"/home/user/GR/glint-cli/src/tui.tsx\", \"offset\": 770, \"limit\": 60}\nResult: 770\t >\n771\t {t.text}\n772\t </Text>\n773\t </Text>\n774\t ))}\n775\t </Box>\n776\t )}\n777\t\n77... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "ggle are gone, along with their CSS. The only boiling squiggle left is the hand-drawn circle around `<100M`, which was never a wave.\n- **Logo moved into the hero** - it now sits in the empty space to the right of \"Bigger isn't better. / Smaller is smarter.\", and the stroke-d... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "n\\ndef rebuild(start_marker, end_marker, base, amt, stroke):\\n global src\\n i = src.index(start_marker)\\n e = src.index(end_marker, i)\\n region = src[i:e]\\n fs = [jitter(base, amt) for _ in range(4)]\\n new_paths = '\\\\n'.join('<path d=\\\"%s\\\" %s/>' ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nediately. Agents hired with\\n // a bare config fail every run with groq_missing_api_key.\\n const …[truncated]\nResult: The file /home/user/.paperclip/adapter-plugins/groq-paperclip-adapter-r11/dist/server/paperclip-tools.j... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.