langchain-ai/deepagents · error · TypeError

workspace context is required

Error message

workspace context is required

What it means

`require_thread_workspace` validates the workspace context payload carried with each run. This TypeError is raised when the payload is not a non-empty dict, meaning the run did not carry the workspace context required to verify the thread's binding.

Source

Thrown at libs/code/deepagents_code/workspace.py:341

async def require_thread_workspace(
    thread_id: str,
    payload: object,
    workspace_config: object | None = None,
    *,
    config_fingerprint: str | None = None,
) -> WorkspaceBinding:
    """Validate run context against the durable workspace binding.

    Returns:
        The server-authoritative binding and persisted resource policy.

    Raises:
        TypeError: If workspace context is not an object.
        WorkspaceConflictError: If the context, policy, or workspace has changed.
    """
    if not isinstance(payload, dict) or not payload:
        msg = "workspace context is required"
        raise TypeError(msg)
    data = cast("dict[str, Any]", payload)
    claimed_fingerprint = config_fingerprint
    if workspace_config is not None:
        _, claimed_fingerprint = canonical_workspace_config(workspace_config)

    def _require() -> WorkspaceBinding:
        with sqlite3.connect(_database_path(), timeout=5) as conn:
            conn.row_factory = sqlite3.Row
            conn.execute("BEGIN IMMEDIATE")
            _initialize(conn)
            row = conn.execute(
                "SELECT * FROM dcode_thread_workspaces WHERE thread_id = ?",
                (thread_id,),
            ).fetchone()
            if row is None:
                msg = f"thread {thread_id} has no workspace binding"
                raise WorkspaceConflictError(msg)
            existing = _row_binding(row)

View on GitHub (pinned to a1af029e6e)

Solutions

1. Pass the workspace context payload obtained from the thread's binding (e.g. via `workspace`/`resolve_workspace`) as a non-empty dict
2. Re-bind the thread to regenerate a context for old sessions
3. Check the code path that builds run payloads so it always includes the workspace context

Example fix

// before
require_thread_workspace(thread_id, payload=None)
// after
require_thread_workspace(thread_id, payload=binding.to_payload())

if not isinstance(payload, dict) or not payload:
    raise TypeError("run payload must include a non-empty workspace context")

def has_workspace_context(v: object) -> TypeGuard[dict[str, Any]]:
    return isinstance(v, dict) and len(v) > 0

try:
    await require_thread_workspace(tid, payload=ctx)
except TypeError:
    binding = await bind_thread_workspace(tid, cwd)
    await require_thread_workspace(tid, payload=binding.to_payload())

When it happens

Trigger: Calling `require_thread_workspace` with `payload=None`, an empty dict `{}`, or a non-dict (list/string); a caller (e.g. `_execute_offload` or `make_graph`) invoking runs without attaching the workspace context produced at bind time.

Common situations: Older checkpoints/sessions created before workspace context was introduced; hand-constructed run payloads omitting the context; context dropped when forwarding run metadata through custom middleware.

Related errors

• context.{key} must be a string or null, got {type(value).__n
• context.{key} must be an object, got {type(value).__name__}.
• workspace_config must be an object
• interpreter_ptc must be False, 'safe', 'all', or a list of t
• Workspace policy and fingerprint must be configured together

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/59fa43021b165759. Report an issue: GitHub.