rohitg00/ai-engineering-from-scratch · error · ValueError

review_goal must be accepted with a string goal

Error message

review_goal must be accepted with a string goal

What it means

The elicitation step only satisfies the server when the user accepted the form (action == 'accept') AND content.goal is a string. Declines, cancels, or a missing/non-string goal raise this — the server treats an unaccepted goal as an invalid response rather than a retryable input.

Source

Thrown at certifications/claude/lessons/11-mcp-server-design-and-integration/code/main.py:422

        workspace_scope = responses["workspace_scope"]
        review_sample = responses["review_sample"]
        elicitation = responses["review_goal"]
        if not all(
            isinstance(response, dict)
            for response in (workspace_scope, review_sample, elicitation)
        ):
            raise ValueError("inputResponses entries must be objects")
        elicitation_content = elicitation.get("content", {})
        if not isinstance(elicitation_content, dict):
            raise ValueError("review_goal.content must be an object")
        roots = workspace_scope.get("roots")
        sample_content = review_sample.get("content", {})
        goal = elicitation_content.get("goal")
        if not isinstance(roots, list) or not isinstance(sample_content, dict):
            raise ValueError("inputResponses contain invalid roots or sampling results")
        if elicitation.get("action") != "accept" or not isinstance(goal, str):
            raise ValueError("review_goal must be accepted with a string goal")
        sample = sample_content.get("text")
        if not isinstance(sample, str):
            raise ValueError("review_sample must contain text")
        summary = {
            "goal": goal,
            "rootCount": len(roots),
            "sample": sample,
            "topic": arguments["topic"],
        }
        return self._complete(
            content=[{"type": "text", "text": json.dumps(summary, sort_keys=True)}],
            isError=False,
        )

    @staticmethod
    def _progress(token: str | int, progress: int, total: int, message: str) -> dict[str, Any]:
        return {
            "jsonrpc": "2.0",

View on GitHub (pinned to 39ea8a1c6d)

Solutions

1. Only resume the call after the user accepts the form with a non-empty goal string
2. Handle decline/cancel as a user-abort path before resuming tools/call, not as a response payload
3. Verify action == 'accept' and isinstance(goal, str) client-side before sending inputResponses

Example fix

# before
review_goal = {"action": "decline", "content": {}}

# after
review_goal = {"action": "accept", "content": {"goal": "tighten auth review"}}

goal_response = responses["review_goal"]
if goal_response.get("action") != "accept":
    raise UserAborted("elicitation not accepted")
if not isinstance(goal_response.get("content", {}).get("goal"), str):
    raise ValueError("accepted elicitation must carry a string goal")

def is_accepted_goal(response: object) -> bool:
    return (
        isinstance(response, dict)
        and response.get("action") == "accept"
        and isinstance(response.get("content", {}).get("goal"), str)
    )

try:
    result = server.exchange("tools/call", params, metadata=meta)
except ValueError as exc:
    if "review_goal" in str(exc):
        rerun_elicitation()
    raise

When it happens

Trigger: review_goal of {"action": "decline"}, {"action": "cancel"}, or {"action": "accept", "content": {}} where goal is absent or not a string.

Common situations: User cancels the elicitation dialog; the UI sends the goal under a different key ('value', 'text'); a form validation gap lets an empty or null goal through.

Related errors

• inputResponses entries must be objects
• review_goal.content must be an object
• -32600
• -32603
• _meta.{PROTOCOL_VERSION_KEY} is required

AI-assisted analysis of rohitg00/ai-engineering-from-scratch@39ea8a1c6d (2026-08-26). Data as JSON: /api/errors/2887e87aead83444. Report an issue: GitHub.