mirror of
https://github.com/coder/coder.git
synced 2026-09-24 15:04:27 +08:00
feat: structured disconnect attribution for agent logs (#25191)
Implements [PLAT-60](https://linear.app/codercom/issue/PLAT-60/enhance-disconnect-logs-with-structured-reason-attribution): adds structured disconnect attribution to disconnect logs throughout the agent and tailnet packages. Every disconnect log site now carries structured slog fields. All existing logs remain; existing messages are preserved with the fields added alongside. New fields on disconnect log lines: - `connect_type` — which layer disconnected: `server_to_agent`, `agent_to_client`, or `client_to_server` - `disconnect_reason` — categorical reason: `graceful`, `network_error`, `server_shutdown`, etc. - `disconnect_expected` — whether the disconnect is normal operation (`true`) or should be investigated (`false`) - `disconnect_initiator` — who started it: `client`, `agent`, `server`, or `network` (control-plane sites only) - `disconnect_detail` — free-form supplemental info (where useful) ## What's covered **Control plane (`server_to_agent`):** coordination RPC, DERP map subscriber, agent runLoop, agent Close, `BasicCoordination.Close`, `Controller.run`. **Data plane (`agent_to_client`):** SSH sessions, reconnecting PTY, JetBrains port-forwarding. <details> <summary>Control-plane sites</summary> | Site | Reason | Initiator | |---|---|---| | `agent/agent.go` `runLoop` EOF | `network_error` | `network` | | `agent/agent.go` `runCoordinator` deferred exit | `server_shutdown` / `graceful` / `network_error` | `agent` / `server` / `network` | | `agent/agent.go` `runDERPMapSubscriber` deferred exit | same (shared `classifyCoordinatorRPCExit`) | same | | `agent/agent.go` `Close` shutdown timeout | `server_shutdown` + detail | `agent` | | `agent/agent.go` `Close` clean coord disconnect | `server_shutdown` | `agent` | | `tailnet/controllers.go` `BasicCoordination.Close` | `graceful` or `network_error` | `c.initiator` | | `tailnet/controllers.go` `Controller.run` `net.ErrClosed` | `network_error` | `network` | </details> <details> <summary>Data-plane sites</summary> | Site | Reason | Notes | |---|---|---| | `agent/agentssh/agentssh.go` SSH session closed | free-form (`graceful`, `process exited with error status: N`, etc.) | Also sets `closeCause("normal exit")` for clean exits so coderd's `connection_log.DisconnectReason` is no longer empty | | `agent/reconnectingpty/server.go` PTY closed | `server_shutdown`, error string, or `graceful` | | | `agent/agentssh/jetbrainstrack.go` channel closed | `normal close` or error string | Previously passed empty reason | </details> <details> <summary>Bug fix</summary> The deferred `disconnected from coordination RPC` log no longer fires when the initial `Coordinate()` RPC call fails before any connection is established. </details> Refs PLAT-60. --- _This PR was prepared by Coder Agents on behalf of @Emyrk._ **Manually QA'd a lot of common disconnects** --------- Co-authored-by: Coder Agents <noreply@coder.com>
This commit is contained in:
co-authored by
Coder Agents
parent
c9c933a300
commit
1afc6d4fd0
@@ -1,17 +1,20 @@
|
||||
package agent
|
||||
|
||||
import (
|
||||
"context"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"testing"
|
||||
|
||||
"github.com/google/uuid"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/xerrors"
|
||||
|
||||
"cdr.dev/slog/v3"
|
||||
"cdr.dev/slog/v3/sloggers/slogtest"
|
||||
"github.com/coder/coder/v2/agent/agentcontextconfig"
|
||||
"github.com/coder/coder/v2/agent/proto"
|
||||
"github.com/coder/coder/v2/codersdk"
|
||||
agentsdk "github.com/coder/coder/v2/codersdk/agentsdk"
|
||||
"github.com/coder/coder/v2/testutil"
|
||||
)
|
||||
@@ -86,3 +89,56 @@ func TestContextConfigAPI_InitOnce(t *testing.T) {
|
||||
require.NotEmpty(t, mcpFiles2)
|
||||
require.Contains(t, mcpFiles2[0], dir2)
|
||||
}
|
||||
|
||||
func TestClassifyCoordinatorRPCExit(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
canceled, cancel := context.WithCancel(context.Background())
|
||||
cancel()
|
||||
|
||||
cases := []struct {
|
||||
name string
|
||||
ctx context.Context
|
||||
retErr error
|
||||
reason codersdk.DisconnectReason
|
||||
initiator codersdk.DisconnectInitiator
|
||||
}{
|
||||
{
|
||||
name: "local shutdown, no error",
|
||||
ctx: canceled,
|
||||
retErr: nil,
|
||||
reason: codersdk.DisconnectReasonServerShutdown,
|
||||
initiator: codersdk.DisconnectInitiatorAgent,
|
||||
},
|
||||
{
|
||||
name: "local shutdown, with cleanup error",
|
||||
ctx: canceled,
|
||||
retErr: xerrors.New("close timed out"),
|
||||
reason: codersdk.DisconnectReasonServerShutdown,
|
||||
initiator: codersdk.DisconnectInitiatorAgent,
|
||||
},
|
||||
{
|
||||
name: "remote graceful, no error",
|
||||
ctx: context.Background(),
|
||||
retErr: nil,
|
||||
reason: codersdk.DisconnectReasonGraceful,
|
||||
initiator: codersdk.DisconnectInitiatorServer,
|
||||
},
|
||||
{
|
||||
name: "stream broke unexpectedly",
|
||||
ctx: context.Background(),
|
||||
retErr: xerrors.New("read: connection reset"),
|
||||
reason: codersdk.DisconnectReasonNetworkError,
|
||||
initiator: codersdk.DisconnectInitiatorNetwork,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range cases {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
reason, initiator := classifyCoordinatorRPCExit(tc.ctx, tc.retErr)
|
||||
require.Equal(t, tc.reason, reason)
|
||||
require.Equal(t, tc.initiator, initiator)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user