shareAI-lab/learn-claude-code · error · GoalError

Install dependencies first: pip install -r requirements.txt

Error message

Install dependencies first: pip install -r requirements.txt

What it means

make_live_session failed to import the optional third-party packages 'anthropic' and/or 'dotenv' (s17_goal_loop/code.py:815). The live path is optional, so these dependencies are not installed with the base code; ImportError is caught and re-raised as GoalError telling you to install requirements.txt.

Source

Thrown at s17_goal_loop/code.py:815

            return f"Edited {path.relative_to(self.workdir)}"

        if name == "glob":
            matches = [
                match
                for match in glob.glob(str(arguments["pattern"]), root_dir=self.workdir)
                if (self.workdir / match).resolve().is_relative_to(self.workdir)
            ]
            return "\n".join(matches[:200]) if matches else "(no matches)"

        raise GoalError(f"unknown tool '{name}'")


def make_live_session(workdir: Path) -> AgentSession:
    try:
        from anthropic import Anthropic
        from dotenv import load_dotenv
    except ImportError as error:
        raise GoalError(
            "Install dependencies first: pip install -r requirements.txt"
        ) from error

    load_dotenv(override=True)
    model = os.getenv("MODEL_ID")
    if not model:
        raise GoalError("MODEL_ID is required in the environment or .env")
    evaluator_model = (
        os.getenv("GOAL_EVALUATOR_MODEL_ID")
        or os.getenv("ANTHROPIC_DEFAULT_HAIKU_MODEL")
        or model
    )
    if os.getenv("ANTHROPIC_BASE_URL"):
        os.environ.pop("ANTHROPIC_AUTH_TOKEN", None)
    client = Anthropic(base_url=os.getenv("ANTHROPIC_BASE_URL"))
    evaluator = PromptGoalEvaluator(client=client, model=evaluator_model)
    block_cap = int(
        os.getenv(

View on GitHub (pinned to 985456f4ad)

Solutions

1. Run pip install -r requirements.txt inside the venv/interpreter you will execute with
2. Verify with 'python -c "import anthropic, dotenv"' using the same interpreter
3. If using uv/poetry, run through 'uv run python ...' / 'poetry run python ...' so the project env is used

Example fix

# before
$ python -m s17_goal_loop.code
error: Install dependencies first: pip install -r requirements.txt

# after
$ python -m venv .venv && source .venv/bin/activate
$ pip install -r requirements.txt
$ python -m s17_goal_loop.code

import importlib.util
missing = [m for m in ("anthropic", "dotenv") if importlib.util.find_spec(m) is None]
if missing:
    raise SystemExit(f"install deps first: {', '.join(missing)} (pip install -r requirements.txt)")
session = make_live_session(workdir)

When it happens

Trigger: Calling make_live_session(path) in an environment where 'pip install -r requirements.txt' (which provides anthropic and python-dotenv) has not been run, or where a different virtualenv/interpreter is active than the one the packages were installed into.

Common situations: Fresh clone, no venv set up; running under a different python (system vs venv vs poetry/uv env); IDE launching with a stale interpreter; installing with --user into a Python other than the one runs the script.

Related errors

• MODEL_ID is required in the environment or .env
• Not in a git repository. worktree tools require git.
• Memory directory escapes the workspace
• Dependency not found: {dependency}
• Dependency not found: {dependency}

AI-assisted analysis of shareAI-lab/learn-claude-code@985456f4ad (2026-08-14). Data as JSON: /api/errors/667a774809310891. Report an issue: GitHub.