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

inputResponses contain invalid roots or sampling results

Error message

inputResponses contain invalid roots or sampling results

What it means

After the object checks, the server requires workspace_scope.roots to be a list (a roots/list result body) and review_sample.content to be an object (a createMessage result body). A missing 'roots' key yields None, and a bare string/array content fails the dict check.

Source

Thrown at certifications/claude/lessons/11-mcp-server-design-and-integration/code/main.py:420

                inputRequests=missing_responses, requestState=state
            )

        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]:

View on GitHub (pinned to 39ea8a1c6d)

Solutions

1. Supply roots as a list — an empty list [] is acceptable for an empty workspace
2. Return the sampling result with content as an object, e.g. {"content": {"type": "text", "text": ...}}
3. Mirror the MCP roots/list and sampling/createMessage response shapes exactly

Example fix

# before
workspace_scope = {}
review_sample = {"content": "draft text"}

# after
workspace_scope = {"roots": []}
review_sample = {"content": {"type": "text", "text": "draft text"}}

roots = responses["workspace_scope"].get("roots")
sample_content = responses["review_sample"].get("content", {})
if not isinstance(roots, list):
    responses["workspace_scope"]["roots"] = []
if not isinstance(sample_content, dict):
    raise ValueError("sampling content must be an object")

def valid_roots_and_sample(scope: object, sample: object) -> bool:
    return (
        isinstance(scope, dict) and isinstance(scope.get("roots"), list)
        and isinstance(sample, dict) and isinstance(sample.get("content", {}), dict)
    )

When it happens

Trigger: workspace_scope without a 'roots' key or with roots as an object/None, or a review_sample whose content is raw text or a list instead of an object.

Common situations: Client forwards an empty no-roots response as null; a sampling shim returns content as a bare string; fixtures written against an older response shape.

Understand the failure class

Background: Schema validation failed / invalid input schema: payload rejected because its shape doesn't match the expected schema — this error's family across 28 libraries.

Related errors

• review_sample must contain text
• -32600
• -32603
• _meta.{PROTOCOL_VERSION_KEY} is required
• _meta.{CLIENT_CAPABILITIES_KEY} is required

AI-assisted analysis of rohitg00/ai-engineering-from-scratch@39ea8a1c6d (2026-08-26). Data as JSON: /api/errors/55b9b80a4f387963. Report an issue: GitHub.