go.chromium.org/luci@v0.0.0-20240309015107-7cdc2e660f33/swarming/internal/remoteworkers/bots.proto

syntax = "proto3";

package google.devtools.remoteworkers.v1test2;

import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/protobuf/any.proto";
import "google/protobuf/field_mask.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";

import "go.chromium.org/luci/swarming/internal/remoteworkers/worker.proto";

option csharp_namespace = "Google.DevTools.RemoteWorkers.V1Test2";
option go_package = "go.chromium.org/luci/swarming/internal/remoteworkers";
option java_multiple_files = true;
option java_outer_classname = "RemoteWorkersBots";
option java_package = "com.google.devtools.remoteworkers.v1test2";
option objc_class_prefix = "RW";

// Design doc: https://goo.gl/oojM5H
//
// Loosely speaking, the Bots interface monitors a collection of workers (think
// of them as "computers" for a moment). This collection is known as a "farm,"
// and its purpose is to perform work on behalf of a client.
//
// Each worker runs a small program known as a "bot" that allows it to be
// controlled by the server. This interface contains only methods that are
// called by the bots themselves; admin functionality is out of scope for this
// interface.
//
// More precisely, we use the term "worker" to refer to the physical "thing"
// running the bot. We use the term "worker," and not "machine" or "computer,"
// since a worker may consist of more than one machine - e.g., a computer with
// multiple attached devices, or even a cluster of computers, with only one of
// them running the bot. Conversely, a single machine may host several bots, in
// which case each bot has a "worker" corresponding to the slice of the machine
// being managed by that bot.
//
// The main resource in the Bots interface is not, surprisingly, a Bot - it is a
// BotSession, which represents a period of time in which a bot is in continuous
// contact with the server (see the BotSession message for more information).
// The parent of a bot session can be thought of as an instance of a farm. That
// is, one endpoint may be able to manage many farms for many users. For
// example, for a farm managed through GCP, the parent resource will typically
// take the form "projects/{project_id}". This is referred to below as "the farm
// resource."
service Bots {
  // CreateBotSession is called when the bot first joins the farm, and
  // establishes a session ID to ensure that multiple machines do not register
  // using the same name accidentally.
  rpc CreateBotSession(CreateBotSessionRequest) returns (BotSession) {
    option (google.api.method_signature) = "parent,bot_session";
    option (google.api.http) = {
      post: "/v1test2/{parent=**}/botSessions"
      body: "bot_session"
    };
    option (google.api.method_signature) = "parent,bot_session";
  }

  // UpdateBotSession must be called periodically by the bot (on a schedule
  // determined by the server) to let the server know about its status, and to
  // pick up new lease requests from the server.
  rpc UpdateBotSession(UpdateBotSessionRequest) returns (BotSession) {
    option (google.api.method_signature) = "name,bot_session,update_mask";
    option (google.api.http) = {
      patch: "/v1test2/{name=**/botSessions/*}"
      body: "bot_session"
    };
    option (google.api.method_signature) = "name,bot_session,update_mask";
  }
}

// A bot session represents the state of a bot while in continuous contact with
// the server for a period of time. The session includes information about the
// worker - that is, the *worker* (the physical or virtual hardware) is
// considered to be a property of the bot (the software agent running on that
// hardware), which is the reverse of real life, but more natural from the point
// of the view of this API, which communicates solely with the bot and not
// directly with the underlying worker.
message BotSession {
  option (google.api.resource) = {
    type: "remoteworkers.googleapis.com/BotSession",
    pattern: "{unknown_path}/botSessions/{bot_session}"
  };

  // The bot session name, as selected by the server. Output only during a call
  // to CreateBotSession.
  string name = 1;

  // A unique bot ID within the farm used to persistently identify this bot over
  // time (i.e., over multiple sessions). This ID must be unique within a
  // farm. Typically, the bot ID will be the same as the name of the primary
  // device in the worker (e.g., what you'd get from typing `uname -n` on *nix),
  // but this is not required since a single device may allow multiple bots to
  // run on it, each with access to different resources. What is important is
  // that this ID is meaningful to humans, who might need to hunt a physical
  // machine down to fix it.
  //
  // When CreateBotSession is successfully called with a bot_id, all prior
  // sessions with the same ID are invalidated. If a bot attempts to update an
  // invalid session, the server must reject that request, and may also
  // quarantine the other bot with the same bot IDs (ie, stop sending it new
  // leases and alert an admin).
  string bot_id = 2;

  // The status of the bot. This must be populated in every call to
  // UpdateBotSession.
  BotStatus status = 3;

  // A description of the worker hosting this bot. The Worker message is used
  // here in the Status context (see Worker for more information).  If multiple
  // bots are running on the worker, this field should only describe the
  // resources accessible from this bot.
  //
  // During the call to CreateBotSession, the server may make arbitrary changes
  // to the worker's `server_properties` field (see that field for more
  // information). Otherwise, this field is input-only.
  google.devtools.remoteworkers.v1test2.Worker worker = 4;

  // A list of all leases that are a part of this session. See the Lease message
  // for details.
  repeated Lease leases = 5;

  // The time at which this bot session will expire, unless the bot calls
  // UpdateBotSession again. Output only.
  google.protobuf.Timestamp expire_time = 6;

  // The version of the bot code currently running. The server may use this
  // information to issue an admin action to tell the bot to update itself.
  string version = 7;
}

// A Lease is a lease that the scheduler has assigned to this bot. If the bot
// notices (by UpdateBotSession) that it has any leases in the PENDING state, it
// should call UpdateBotSession to put the leases into the ACTIVE state and
// start executing their assignments.
//
// All fields in this message are output-only, *except* the `state` and `status`
// fields. Note that repeated fields can only be updated as a unit, so on every
// update the bot must provide an update for *all* the leases the server expects
// it to report on.
//
// The scheduler *should* ensure that all leases scheduled to a bot can actually
// be accepted, but race conditions may occur. In such cases, the bot should
// attempt to accept the leases in the order they are listed by the server, to
// allow the server to control priorities.
//
// The server will remove COMPLETED leases from time to time, after which the
// bot shouldn't report on them any more (the server will ignore superfluous
// COMPLETED records).
message Lease {
  // A short string uniquely identifing the lease within this bot session.
  string id = 7;

  // The actual work to be performed, if any. May be omitted by the server if
  // the lease is not in the `PENDING` state. The message must be meaningful to
  // the bot. Output only (must only be set by the server).
  google.protobuf.Any payload = 8;

  // Any result the bot wishes to provide about the lease. Must not be changed
  // after the first call with the lease in the `COMPLETED` or `CANCELLED`
  // state. Input only (must only be set by the bot, will not be echoed by the
  // server).
  google.protobuf.Any result = 9;

  // The state of the lease. See LeaseState for more information.
  LeaseState state = 2;

  // The final status of the lease (should be populated by the bot if the state
  // is completed). This is the status of the lease, not of any task represented
  // by the lease. For example, if the bot could not accept the lease because it
  // asked for some resource the bot didn't have, this status will be
  // FAILED_PRECONDITION. But if the assignment in the lease didn't execute
  // correctly, this field will be `OK` while the failure of the assignment must
  // communicated via the `result` field.
  google.rpc.Status status = 3;

  // The requirements that are being claimed by this lease. This field may be
  // omitted by the server if the lease is not pending.
  google.devtools.remoteworkers.v1test2.Worker requirements = 4;

  // The time at which this lease expires. The server *may* extend this over
  // time, but due to race conditions, the bot is not *required* to respect any
  // expiry date except the first one.
  google.protobuf.Timestamp expire_time = 5;

  // DEPRECATED. The assignment should be provided to the bot via the `payload`
  // field. Clients that wish to use a simple name (such as a queue of work
  // provided elsewhere) should define a custom message type and encode it into
  // `payload`.
  string assignment = 1 [deprecated = true];

  // DEPRECATED. Use `payload` instead.
  google.protobuf.Any inline_assignment = 6 [deprecated = true];
}

// A coarse description of the status of the bot that the server uses to
// determine whether to assign the bot new leases.
enum BotStatus {
  // Default value; do not use.
  BOT_STATUS_UNSPECIFIED = 0;

  // The bot is healthy, and will accept leases as normal.
  OK = 1;

  // The bot is unhealthy and will not accept new leases. For example, the bot
  // may have detected that available disk space is too low. This situation may
  // resolve itself, but will typically require human intervention.
  UNHEALTHY = 2;

  // The bot has been asked to reboot the host. The bot will not accept new
  // leases; once all leases are complete, this session will no longer be
  // updated but the bot will be expected to establish a new session after the
  // reboot completes.
  HOST_REBOOTING = 3;

  // The bot has been asked to shut down. As with HOST_REBOOTING, once all
  // leases are completed, the session will no longer be updated and the bot
  // will not be expected to establish a new session.
  //
  // Bots are typically only asked to shut down if its host computer will be
  // modified in some way, such as deleting a VM.
  BOT_TERMINATING = 4;

  // The bot is initializing and is not ready to accept leases.
  INITIALIZING = 5;

  // The bot is in maintenance status. In this state, the bot will continue to
  // be treated as online, but will not accept new leases.
  MAINTENANCE = 6;
}

// The state of the lease. All leases start in the PENDING state. A bot can
// change PENDING to ACTIVE or (in the case of an error) COMPLETED, or from
// ACTIVE to COMPLETED. The server can change PENDING or ACTIVE to CANCELLED if
// it wants the bot to release its resources - for example, if the bot needs to
// be quarantined (it's producing bad output) or a cell needs to be drained.
enum LeaseState {
  // Default value; do not use.
  LEASE_STATE_UNSPECIFIED = 0;

  // Pending: the server expects the bot to accept this lease. This may only be
  // set by the server.
  PENDING = 1;

  // Active: the bot has accepted this lease. This may only be set by the bot.
  ACTIVE = 2;

  // Completed: the bot is no longer leased. This may only be set by the bot,
  // and the status field must be populated iff the state is COMPLETED.
  COMPLETED = 4;

  // Cancelled: The bot should immediately release all resources associated with
  // the lease. This may only be set by the server.
  CANCELLED = 5;
}

// AdminTemp is a prelimiary set of administration tasks. It's called "Temp"
// because we do not yet know the best way to represent admin tasks; it's
// possible that this will be entirely replaced in later versions of this API.
// If this message proves to be sufficient, it will be renamed in the alpha or
// beta release of this API.
//
// This message (suitably marshalled into a protobuf.Any) can be used as the
// inline_assignment field in a lease; the lease assignment field should simply
// be `"admin"` in these cases.
//
// This message is heavily based on Swarming administration tasks from the LUCI
// project (http://github.com/luci/luci-py/appengine/swarming).
message AdminTemp {
  // Possible administration actions.
  enum Command {
    // Illegal value.
    UNSPECIFIED = 0;

    // Download and run a new version of the bot. `arg` will be a resource
    // accessible via `ByteStream.Read` to obtain the new bot code.
    BOT_UPDATE = 1;

    // Restart the bot without downloading a new version. `arg` will be a
    // message to log.
    BOT_RESTART = 2;

    // Shut down the bot. `arg` will be a task resource name (similar to those
    // in tasks.proto) that the bot can use to tell the server that it is
    // terminating.
    BOT_TERMINATE = 3;

    // Restart the host computer. `arg` will be a message to log.
    HOST_RESTART = 4;
  }
  // The admin action; see `Command` for legal values.
  Command command = 1;
  // The argument to the admin action; see `Command` for semantics.
  string arg = 2;
}

// Request message for CreateBotSession.
message CreateBotSessionRequest {
  // The farm resource.
  string parent = 1 [(google.api.field_behavior) = REQUIRED];

  // The bot session to create. Server-assigned fields like name must be unset.
  BotSession bot_session = 2 [(google.api.field_behavior) = REQUIRED];
}

// Request message for UpdateBotSession.
message UpdateBotSessionRequest {
  // The bot session name. Must match bot_session.name.
  string name = 1 [
    (google.api.field_behavior) = REQUIRED,
    (google.api.resource_reference).type =
        "remoteworkers.googleapis.com/BotSession"
  ];

  // The bot session resource to update.
  BotSession bot_session = 2 [(google.api.field_behavior) = REQUIRED];

  // The fields on the bot that should be updated. See the BotSession resource
  // for which fields are updatable by which caller.
  google.protobuf.FieldMask update_mask = 3
      [(google.api.field_behavior) = REQUIRED];
}