shishantbiswas/coder
1
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-06-02 20:48:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(coderd/x/chatd): skip stale notification flakes (#25177)

Browse Source 
Skip the chatd tests that currently flake because the control
notification flow cannot distinguish stale wake/status NOTIFY payloads
from real interrupt requests. Each skipped test includes a TODO to
re-enable it after the chatd notification flow refactor handles stale
notifications correctly.

Supersedes #25133, #25134, #25135, and #25139.

Refs [CODAGT-353](https://linear.app/coder/issue/CODAGT-353),
[CODAGT-356](https://linear.app/coder/issue/CODAGT-356),
[CODAGT-360](https://linear.app/coder/issue/CODAGT-360), and
[CODAGT-361](https://linear.app/coder/issue/CODAGT-361).

> Mux working on behalf of Mike.
This commit is contained in:
Michael Suchacz
2026-05-12 14:50:30 +02:00
committed by GitHub
parent 4e08543ace
commit f847ff3731
2 changed files with 30 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
coderd/x/chatd/chatd_test.go
+6
View File
@@ -2623,6 +2623,12 @@ func TestPromoteQueuedMessageReloadsChatWhenModelConfigChangesDuringPending(t *t
func TestAutoPromoteQueuedMessagesPreservesPerTurnModelOrder(t *testing.T) {
t.Parallel()
// TODO(CODAGT-353): Re-enable this test after the chatd notification flow
// refactor gives workers enough causal information to distinguish stale
// control NOTIFY messages from real interrupts. The current design reuses
// the same status notification shape for wake-only and interrupt intents,
// so a stale NOTIFY can cancel a new processChat run.
t.Skip("skipped until chatd notification flow refactor handles stale control notifications")
db, ps := dbtestutil.NewDB(t)
ctx := testutil.Context(t, testutil.WaitSuperLong)
coderd/x/chatd/integration_responses_test.go
+24
View File
@@ -25,6 +25,12 @@ import (
func TestOpenAIResponsesNoStaleWebSearchReplay(t *testing.T) {
t.Parallel()
// TODO(CODAGT-353): Re-enable this test after the chatd notification flow
// refactor gives workers enough causal information to distinguish stale
// control NOTIFY messages from real interrupts. The current design reuses
// the same status notification shape for wake-only and interrupt intents,
// so a stale NOTIFY can cancel a new processChat run.
t.Skip("skipped until chatd notification flow refactor handles stale control notifications")
db, ps := dbtestutil.NewDB(t)
ctx := testutil.Context(t, testutil.WaitLong)
@@ -108,6 +114,12 @@ func TestOpenAIResponsesNoStaleWebSearchReplay(t *testing.T) {
func TestOpenAIResponsesFullReplayPairsReasoningAndWebSearch(t *testing.T) {
t.Parallel()
// TODO(CODAGT-353): Re-enable this test after the chatd notification flow
// refactor gives workers enough causal information to distinguish stale
// control NOTIFY messages from real interrupts. The current design reuses
// the same status notification shape for wake-only and interrupt intents,
// so a stale NOTIFY can cancel a new processChat run.
t.Skip("skipped until chatd notification flow refactor handles stale control notifications")
db, ps := dbtestutil.NewDB(t)
ctx := testutil.Context(t, testutil.WaitLong)
@@ -190,6 +202,12 @@ func TestOpenAIResponsesFullReplayPairsReasoningAndWebSearch(t *testing.T) {
func TestOpenAIResponsesChainModeSkipsWhenLocalCallPending(t *testing.T) {
t.Parallel()
// TODO(CODAGT-353): Re-enable this test after the chatd notification flow
// refactor gives workers enough causal information to distinguish stale
// control NOTIFY messages from real interrupts. The current design reuses
// the same status notification shape for wake-only and interrupt intents,
// so a stale NOTIFY can cancel a new processChat run.
t.Skip("skipped until chatd notification flow refactor handles stale control notifications")
db, ps := dbtestutil.NewDB(t)
ctx := testutil.Context(t, testutil.WaitLong)
@@ -257,6 +275,12 @@ func TestOpenAIResponsesChainModeSkipsWhenLocalCallPending(t *testing.T) {
func TestOpenAIResponsesChainModeStillFiresForProviderExecutedOnly(t *testing.T) {
t.Parallel()
// TODO(CODAGT-353): Re-enable this test after the chatd notification flow
// refactor gives workers enough causal information to distinguish stale
// control NOTIFY messages from real interrupts. The current design reuses
// the same status notification shape for wake-only and interrupt intents,
// so a stale NOTIFY can cancel a new processChat run.
t.Skip("skipped until chatd notification flow refactor handles stale control notifications")
db, ps := dbtestutil.NewDB(t)
ctx := testutil.Context(t, testutil.WaitLong)