add tiny-agent

file-assistant/PROMPT.md

@@ -0,0 +1,84 @@
+# STRICT TOOL-CALLING PROMPT (Desktop Commander)
+
+You are a tool-using agent. Your #1 goal is correct tool calling.
+
+## A) NON-NEGOTIABLE RULE
+For file/folder location, the parameter key is ALWAYS exactly:
+"path"
+
+NEVER use: file_path, filename, source, filepath, or any other key.
+
+If you use the wrong key, you MUST immediately retry with "path".
+
+---
+
+## B) TOOL CALL MUST MATCH THESE TEMPLATES (COPY EXACTLY)
+When you need to call a tool, you MUST construct arguments by copying the template and only replacing the values.
+
+### read_file
+Template:
+{"path": "/ABSOLUTE/PATH/TO/FILE"}
+
+### write_file
+Template:
+{"path": "/ABSOLUTE/PATH/TO/FILE", "content": "..."}
+
+### list_directory
+Template:
+{"path": "/ABSOLUTE/PATH/TO/FOLDER"}
+
+### create_directory
+Template:
+{"path": "/ABSOLUTE/PATH/TO/FOLDER"}
+
+### move_file
+Template:
+{"path": "/ABSOLUTE/PATH/TO/SOURCE", "destination_path": "/ABSOLUTE/PATH/TO/DESTINATION"}
+
+### edit_block
+Template:
+{"path": "/ABSOLUTE/PATH/TO/FILE", "start_line": 1, "end_line": 1, "new_text": "..."}
+
+### start_search
+Template:
+{"query": "..."}
+
+---
+
+## C) PRE-FLIGHT CHECK (MANDATORY)
+Before sending ANY tool call, you MUST verify:
+1) The JSON contains a key named "path" if a path is needed.
+2) The JSON does NOT contain "file_path" / "filename" / "source".
+3) The path value starts with "/".
+
+If any check fails, rewrite the JSON until all checks pass.
+
+---
+
+## D) READING POLICY
+If user asks to "Read <path>":
+- DO NOT start_process
+- DO NOT interact_with_process
+- Call read_file with the template above.
+
+---
+
+## E) ERROR HANDLING (NO DISCUSSION)
+If tool returns error mentioning missing "path":
+- Immediately retry the same tool call with correct JSON:
+  {"path": "..."}.
+
+Do NOT ask the user to provide the path if the user already provided it.
+
+---
+
+## F) NO HALLUCINATION FOR ANALYSIS
+When analyzing text files (JD/resume):
+- Only use facts in the files you read.
+- Every fit statement must include a short quoted snippet from the file.
+- If not present, say: "Not stated in the file."
+
+---
+
+## G) OUTPUT STYLE
+Be concise. Use tools immediately.

file-assistant/agent.json

@@ -0,0 +1,10 @@
+{
+  "model": "Qwen/Qwen3-235B-A22B-Instruct-2507",
+  "servers": [
+    {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@wonderwhy-er/desktop-commander"]
+    }
+  ]
+}

file-assistant/candidates/john_resume.md

@@ -0,0 +1,58 @@
+# John Doe
+
+**Contact Information**
+- Email: email@example.com
+- Phone: (+1) 123-456-7890
+- Location: 1234 Abc Street, Example, EX 01234
+- GitHub: github.com/example
+- LinkedIn: linkedin.com/in/example
+- Website: example.com
+
+## Experience
+
+**Machine Learning Engineer Intern** | Slow Feet Technology | Jul 2021 - Present
+- Developed food-agnostic formulation for cross-ingredient meal cooking
+- Created competitive cream of mushroom soup recipe, published in NeurIPS 2099
+- Built specialized pan for meal cooking research
+
+**Research Intern** | Paddling University | Aug 2020 - Present
+- Designed efficient mapo tofu quality estimation method using thermometer
+- Proposed fast stir frying algorithm for tofu cooking, published in CVPR 2077
+- Outperformed SOTA methods with improved efficiency
+
+**Research Assistant** | Huangdu Institute of Technology | Mar 2020 - Jun 2020
+- Developed novel framework using spoon and chopsticks for eating mapo tofu
+- Designed tofu filtering strategy inspired by beans grinding method
+- Created evaluation criteria for eating plan novelty and diversity
+
+**Research Intern** | Paddling University | Jul 2018 - Aug 2018
+- Designed dual sandwiches using traditional burger ingredients
+- Utilized structure duality to boost cooking speed for shared ingredients
+- Outperformed baselines on QWE'15 and ASDF'14 datasets
+
+## Education
+
+**M.S. in Computer Science** | University of Charles River | Sep 2021 - Jan 2023
+- Location: Boston, MA
+
+**B.Eng. in Software Engineering** | Huangdu Institute of Technology | Sep 2016 - Jul 2020
+- Location: Shanghai, China
+
+## Skills
+
+**Programming Languages:** Python, JavaScript/TypeScript, HTML/CSS, Java
+**Tools and Frameworks:** Git, PyTorch, Keras, scikit-learn, Linux, Vue, React, Django, LaTeX
+**Languages:** English (proficient), Indonesia (native)
+
+## Awards and Honors
+
+- **Gold**, International Collegiate Catching Fish Contest (ICCFC) | 2018
+- **First Prize**, China National Scholarship for Outstanding Culinary Skills | 2017, 2018
+
+## Publications
+
+**Eating is All You Need** | NeurIPS 2099
+- Authors: Haha Ha, San Zhang
+
+**You Only Cook Once: Unified, Real-Time Mapo Tofu Recipe** | CVPR 2077 (Best Paper Honorable Mention)
+- Authors: Haha Ha, San Zhang, Si Li, Wu Wang

file-assistant/invitation.md

@@ -0,0 +1,14 @@
+# Interview Invitation
+
+Dear John Doe,
+
+We've reviewed your impressive background in food technology and machine learning, and we're excited to invite you for an interview for our Senior Food Technology Engineer position.
+
+Your innovative work at the intersection of culinary science and AI, including your publications in NeurIPS and CVPR, demonstrates exactly the kind of culinary innovation we're looking for.
+
+Please let us know your availability for an interview next week. We'd love to discuss how your expertise in algorithmic cooking optimization could contribute to our team.
+
+Best regards,
+
+Hiring Team
+Senior Food Technology Engineer Search Committee

file-assistant/job_description.md

@@ -0,0 +1,24 @@
+# Senior Food Technology Engineer
+
+## About the Role
+We're seeking a culinary innovator to transform cooking processes into precise algorithms and AI systems.
+
+## What You'll Do
+- Convert cooking instructions into measurable algorithms
+- Develop AI-powered kitchen tools
+- Create food quality assessment systems
+- Build recipe-following AI models
+
+## Requirements
+- MS in Computer Science (food-related thesis preferred)
+- Python and PyTorch expertise
+- Proven experience combining food science with ML
+- Strong communication skills using culinary metaphors
+
+## Perks
+- Access to experimental kitchen
+- Continuous taste-testing opportunities
+- Collaborative tech-foodie team environment
+
+*Note: Must attend conferences and publish on algorithmic cooking optimization.*
+

tiny-agent/agent.json

@@ -0,0 +1,13 @@
+{
+	"model": "Qwen/Qwen3-235B-A22B-Instruct-2507",
+	"servers": [
+		{
+			"type": "stdio",
+			"command": "npx",
+			"args": [
+				"mcp-remote", 
+				"https://cocolook-mcp-course-sentiment.hf.space/gradio_api/mcp/sse"
+			]
+		}
+	]
+}

tiny-agent/agent.py

@@ -0,0 +1,17 @@
+import os
+
+from huggingface_hub import Agent
+
+agent = Agent(
+    model="Qwen/Qwen2.5-72B-Instruct",
+    # provider="nebius",
+    servers=[
+        {
+            "command": "npx",
+            "args": [
+                "mcp-remote",
+                "https://cocolook-mcp-course-sentiment.hf.space/gradio_api/mcp/sse"  # Your Gradio MCP server
+            ]
+        }
+    ],
+)