Tuning Engines

Instructions

Implementation Reference

• src/client.ts:43-60 (handler)

  The actual API call to create a job.

  async createJob(params: {
    base_model?: string;
    output_name: string;
    repo_url?: string;
    branch?: string;
    github_token?: string;
    num_epochs?: number;
    max_examples?: number;
    base_user_model_id?: string;
    s3_output_bucket?: string;
    s3_access_key_id?: string;
    s3_secret_access_key?: string;
    s3_region?: string;
    agent?: string;
    quality_tier?: string;
  }): Promise<any> {
    return this.request("POST", "/api/v1/jobs", params);
  }

• src/mcp.ts:388-410 (registration)

  Tool handler in the MCP server for "create_job".

  case "create_job":
    if (!args?.base_model && !args?.base_user_model_id) {
      return {
        content: [{ type: "text", text: "Error: either base_model or base_user_model_id is required" }],
        isError: true,
      };
    }
    result = await client.createJob({
      base_model: args?.base_model as string | undefined,
      base_user_model_id: args?.base_user_model_id as string | undefined,
      output_name: args!.output_name as string,
      repo_url: args?.repo_url as string | undefined,
      branch: args?.branch as string | undefined,
      num_epochs: args?.num_epochs as number | undefined,
      max_examples: args?.max_examples as number | undefined,
      s3_output_bucket: args?.s3_output_bucket as string | undefined,
      s3_access_key_id: args?.s3_access_key_id as string | undefined,
      s3_secret_access_key: args?.s3_secret_access_key as string | undefined,
      s3_region: args?.s3_region as string | undefined,
      agent: args?.agent as string | undefined,
      quality_tier: args?.quality_tier as string | undefined,
    });
    break;

• src/mcp.ts:74-162 (schema)

  Tool registration and input schema for "create_job".

  name: "create_job",
  description:
    "Fine-tune an LLM on a GitHub repository using Tuning Engines. " +
    "This trains a custom model that learns from the code patterns, style, and conventions in the repo. " +
    "Choose an agent to control the training approach:\n\n" +
    "AVAILABLE AGENTS:\n" +
    "- agent='code_repo' (Cody) — LoRA-based code fine-tuning using QLoRA (4-bit quantized LoRA) via the Axolotl framework. " +
    "Trains on your repo's code patterns, naming conventions, and project structure to produce a fast, lightweight adapter. " +
    "Best for: code autocomplete, inline suggestions, tab-complete, code style matching.\n" +
    "- agent='sera_code_repo' (SIERA) — Bug-fix specialist using the Open Coding Agents approach from AllenAI. " +
    "Generates synthetic error-resolution training pairs from your repo, producing a model that understands your " +
    "codebase's failure patterns and fix conventions. Best for: debugging, error resolution, patch generation, root cause analysis. " +
    "Supports quality_tier='low' (faster) or quality_tier='high' (deeper analysis, more training data).\n\n" +
    "SUPPORTED BASE MODELS (by size):\n" +
    "- 3B: Qwen/Qwen2.5-Coder-3B-Instruct\n" +
    "- 7B: codellama/CodeLlama-7b-hf, deepseek-ai/deepseek-coder-7b-instruct-v1.5, Qwen/Qwen2.5-Coder-7B-Instruct\n" +
    "- 13-15B: codellama/CodeLlama-13b-Instruct-hf, bigcode/starcoder2-15b, Qwen/Qwen2.5-Coder-14B-Instruct\n" +
    "- 32-34B: deepseek-ai/deepseek-coder-33b-instruct, codellama/CodeLlama-34b-Instruct-hf, Qwen/Qwen2.5-Coder-32B-Instruct\n" +
    "- 70-72B: codellama/CodeLlama-70b-Instruct-hf, meta-llama/Llama-3.1-70B-Instruct, Qwen/Qwen2.5-72B-Instruct\n\n" +
    "TYPICAL WORKFLOW: estimate_job first to check cost, then create_job, then job_status to monitor progress.",
  inputSchema: {
    type: "object" as const,
    properties: {
      base_model: {
        type: "string",
        description:
          "HuggingFace model ID to fine-tune (e.g. 'Qwen/Qwen2.5-Coder-7B-Instruct'). Required unless base_user_model_id is provided. Use list_supported_models to see all options.",
      },
      base_user_model_id: {
        type: "string",
        description:
          "ID of a previously trained model to fine-tune further (iterative training). The base model is resolved automatically. Use list_models to find IDs.",
      },
      output_name: {
        type: "string",
        description:
          "Name for the resulting fine-tuned model (e.g. 'my-project-cody-7b')",
      },
      repo_url: {
        type: "string",
        description:
          "GitHub repository URL to train on (e.g. 'https://github.com/org/repo')",
      },
      branch: {
        type: "string",
        description: "Git branch to use (default: main)",
      },
      num_epochs: {
        type: "number",
        description: "Number of training epochs (more = better quality but higher cost)",
      },
      max_examples: {
        type: "number",
        description: "Maximum training examples to extract from the repo (minimum: 2)",
      },
      agent: {
        type: "string",
        enum: ["code_repo", "sera_code_repo"],
        description:
          "Training agent to use. 'code_repo' (Cody) = QLoRA-based fine-tuning for code autocomplete and inline suggestions. " +
          "'sera_code_repo' (SIERA) = bug-fix specialist using AllenAI's Open Coding Agents approach. " +
          "Default: 'code_repo'.",
      },
      quality_tier: {
        type: "string",
        enum: ["low", "high"],
        description:
          "Quality tier (SIERA agent only). 'low' = faster, fewer synthetic pairs. 'high' = deeper analysis, more training data, better results. Default: 'low'.",
      },
      s3_output_bucket: {
        type: "string",
        description:
          "S3 bucket to export the trained model to. If omitted, model is stored in Tuning Engines cloud storage.",
      },
      s3_access_key_id: {
        type: "string",
        description: "AWS access key ID for S3 export",
      },
      s3_secret_access_key: {
        type: "string",
        description: "AWS secret access key for S3 export",
      },
      s3_region: {
        type: "string",
        description: "AWS region for S3 export (e.g. us-east-1)",
      },
    },
    required: ["output_name", "repo_url"],
  },