You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Antigravity 1.5.7 through 1.5.11 background commands mark the turn done early and T3 drops the wakeup reply #36105
After managed Antigravity installs migrated to the native CLI 1.5.7 in #35487, any turn that launches a background shell command and pauses to wait for it gets marked completed in T3 Code immediately, and subsequent work on wakeup hangs until the user sends another message.
With the legacy 1.4.5 ACP server agy_acp_server.par, waiting across finite background commands stayed inside the open turn because receive_steps() kept streaming updates and skipped closing unfinished background execution tools until no background shell command remained active. Issue #16442 already covers the infinite daemon case.
On CLI 1.5.7, two behaviors combine to break finite background tasks even when the thread is set to full access.
First, as soon as the model pauses to wait on a background command, 1.5.7 closes its step stream, logging Stream goroutine exited for <id>, sending completion signal in server.go, and resolves session/prompt cleanly. Because T3's Antigravity adapter sets subagentsIdleOnTurnCompletion: true and does not defer turn finalization for background commands or reopen a continuation prompt when work resumes, T3 marks the run finished right away and shows the composer as idle.
Second, when the background command finishes later and wakes the agent internally, 1.5.7 has no attached session/prompt request open. It emits zero session/update notifications back to T3, so allowed read calls run silently with nothing visible in the thread. Then, because antigravityCliSessionMode maps yolo and auto_edit to default since the CLI rejects those modes, the first edit or shell command on wakeup clears 1.5.7's internal safety check sir_flash_lite with triggered=false and blocks indefinitely waiting for an ACP tool confirmation that can only be answered inside an active session/prompt call.
In a trace captured on 0.1.10-nightly.20261113.4630 with CLI 1.5.7 and full access enabled, session/prompt succeeded right as server.go exited the stream goroutine while background tests were still running. About 70 seconds later the agent woke internally, ran an allowed read check silently, cleared sir_flash_lite on an edit_file step, and sat frozen for over 14 minutes with no ACP output until a manual user message started a new session/prompt. Roughly 0.3 seconds after that new session/prompt arrived, server.go logged Tool confirmation ... approved=true on the stalled step and resumed.
Related issues #16442 and #30082 plus open PRs #28450, #30083, and #35073 track passive UI turn holding and missing continuation turns. For CLI 1.5.7 specifically, passively holding the run open without keeping or reattaching a session/prompt request will still drop wakeup updates and leave woken edits and commands stuck on confirmation while sessions are forced into default mode.
Reacted by YuAng, Elian, Hu9956, Yusuf and 项科深 Xiang Keshen
Additional confirmation on Antigravity CLI 1.5.8 (custom binary, agy acp), with T3 Code 0.1.9 stable on macOS arm64. The T3 checkout is a localization-only downstream based on upstream 24e77473ecf4; the same missing background-work hooks are also present in the current upstream Antigravity adapter.
The distinction between the command stopping and the ACP stream stopping matters here: the command was still running after T3 had completed the run.
Sanitized observations
Times below are UTC on 2026-11-14, from one conversation's provider log, read-only T3 database inspection, and OS process inspection:
Time
Observation
06:15:52
A finite test command is reported as an in-progress execute tool.
06:16:13.642
The native log says Stream goroutine exited for <conversation>, sending completion signal. T3 records session/prompt as successful and completes both the run and the unfinished command item, without an exit code or command output. The provider thread is idle with pendingBackgroundTasks: [].
06:20:24
The Python test process is still alive, with an elapsed time of 4m22s. This is not evidence that the test passed or that the process was making progress.
06:21:32 onward
The native conversation database contains further steps that are absent from the T3 timeline. A subsequent native command waits for confirmation.
06:30:26.815
A manual follow-up starts another session/prompt.
06:30:26.843–.850
T3 finally receives the original test's output (exit code 1), and the native log records approval of the previously stalled command.
I also tested the suggestion of reattaching with an empty prompt in a separate, newly created session, without a model request. CLI 1.5.8 rejects:
The shared adapter must also exclude subagents from deferred-settlement blocking when subagentsIdleOnTurnCompletion === true; otherwise Antigravity's successfully launched native subagents keep the turn open forever.
A spawned ACP mock through the real Antigravity flavor verifies:
an in-progress command is not fabricated as completed when the prompt returns;
delayed success and failure update the command correctly;
delayed assistant output offers a continuation and is ingested without submitting the original prompt again;
an explicit Stop does not allow subsequent frames to wake the stopped run;
a native subagent batch does not deadlock command settlement.
Local validation: 154 tests passed across the Antigravity adapter/protocol and shared ACP adapter suites; check:changed passed formatting, lint, knip, GraphQL validation and typechecking of 14 packages; the server/web bundle build passed.
This is only a mitigation for the T3-side state/late-frame handling. It does not establish an end-to-end fix for CLI 1.5.8 when no notifications are emitted after the native stream closes. The patched adapter was tested with scripted ACP events, not a live patched-provider run. The installed app was left unchanged. A complete fix still needs a supported way to keep or reattach the native event stream without requiring a user nudge or replaying a state-changing command.
Follow-up with a live CLI 1.5.8 reproduction, captured on 2026-11-14. This also confirms the limitation noted in my earlier comment: holding T3's run open does not restore a native stream that has already closed.
Environment: macOS arm64 host; T3 Code desktop host with an iPhone client; external official agy acp1.5.8; model selection gemini-pro-orchestrator (Gemini 4 Carbon). The installed ASAR identifies itself as 0.1.9-zh.2, commit 620970e8a23f, a downstream build based on stable 0.1.9. I verified the installed bundle contains extractBackgroundTaskId for execute tools, deferFinalizeForBackgroundWork: true, and enablePostSettleContinuation: true. This is not a clean-current-upstream reproduction.
Timeline from the same conversation
All times below are UTC; identifiers and private paths are omitted.
Time
Evidence
08:22:28.854
T3 provider log: session/prompt started.
08:40–08:41
T3 received the assistant warning The stream was interrupted. Please continue the task you were working on. The task subsequently continued; the entire 56-minute request was not idle.
09:18:07
A finite Swift test followed by a release build started as a native background command. T3 projected the execute item as running.
09:18:38.840
T3 provider log: session/prompt succeeded. The last T3 assistant message said it was waiting for the test/build result.
09:19:39
The native Antigravity transcript records the background command finishing with exit code 0, and a system completion notice.
09:19:39 onward
The native transcript records the model proceeding to a batch of file edits. These subsequent steps do not appear in T3's timeline. The native log gets through a safety evaluation on an edit, but the corresponding confirmation/completion is absent in the inspected tail.
After 09:35
Read-only T3 DB inspection still shows the original provider turn status: running, completedAt: null, and that command item status: running with its last update at 09:18:10.718. The user sees an ongoing thinking/working state with no continuation.
Expected / actual
Once the finite command finishes, T3 should receive its terminal result and the subsequent continuation, including the permission exchange required by the native CLI. Instead, the native transcript advances while the T3 state remains frozen.
This supports the same stream-lifecycle problem reported here on 1.5.7, now on 1.5.8. In particular, a passive deferred-settlement mitigation leaves a stale running item when the CLI emits no further ACP updates after session/prompt resolves. A successful session/prompt response alone is insufficient evidence that native work has settled.
Reproduction outline: use this provider/model for a coding task that runs a finite command with WaitMsBeforeAsync, let the model end its current reply while waiting, and compare the native background completion/transcript against T3's projected command and turn. The failure was observed in a real work session; no new synthetic inference test or repair was performed for this follow-up. Raw transcripts are not attached because they contain private workspace information.
We hit this exact 1.5.8 failure on Linux across 0.1.9 and 0.1.10-nightly and traced the surrounding session failures to four concrete places in session setup, shared version state, keyring env vars, and the inactivity timer.
In packages/provider-acp/src/server/AcpSessionRuntime.ts, AcpSessionRuntime.setMode calls setConfigOption(modeConfigOption?.id ?? "mode", modeId) without { allowUnlistedValue: true }. On agy 1.5.8 acp builds where configOptions only lists agent, ask, and plan under mode, passing "yolo" in full access fails client-side validation inside validateConfigOptionValue before T3 sends any session/set_config_option RPC. Right above setModel in that same file, setConfigOption already accepts { allowUnlistedValue: true }, and applyAntigravityAcpModelSelection in apps/server/src/provider/acp/AntigravityAcpSupport.ts already passes it so the binary validates unlisted values itself.
Having 0.1.9 and 0.1.10-nightly on the same machine also breaks ~/.t3/tools/antigravity-acp in both directions. Once 0.1.10-nightly writes 1.5.8 with harness: null into active.json and release.json, 0.1.9 fails in AntigravityInstallation.completedRelease and AntigravityInstallation.resolve in apps/server/src/provider/AntigravityInstallation.ts with Could not read the Antigravity installation because 0.1.9 only accepts agy_acp_server.par paired with localharness_external and spawns ["acp"] without --gemini-dir or --app-data-dir. Going back the other way, once 1.5.8 touches conversations/<sessionId>.db, it writes context_summary into executor_metadata, and loading that conversation on 1.4.5 fails right away with pre-invocation hook "context_summary" not registered.
Two Linux runtime details explain the false sign-outs and mid-turn kills that show up alongside this. antigravityEnvironment in apps/server/src/provider/antigravityAuthSupport.ts passes GNOME_KEYRING_CONTROL and DBUS_SESSION_BUS_ADDRESS into agy, so Electron safeStorage stores OAuth tokens in GNOME Keyring instead of ~/.gemini/oauth_creds.json where standalone 1.4.5.par expects them. And the 15-minute promptInactivityTimeout in AcpAdapterV2.watchPromptInactivity in packages/provider-acp/src/server/adapter.ts checks Clock.currentTimeMillis backed by wall-clock Date.now(). Across S3 laptop sleep, Date.now() jumps 17 minutes while performance.now() only advances 2 minutes of awake time, so retireInactivePrompt fires the second the machine wakes up and kills live turns.
Still reproduces on Antigravity CLI 1.5.9 (T3 Code 0.1.10-nightly.20261115.4723, macOS arm64), and it's visible without T3 in the loop. With a bare ACP client (initialize, authenticate, session/new, session/set_modeyolo (rejected with "Unknown mode: yolo", so the session stayed in default mode), session/set_config_option for the model, then one session/prompt, permission auto-approved, Gemini 3.8 Flash low), I asked the model to run_commandsleep 40; echo CAPTURE_DONE with WaitMsBeforeAsync: 500 and end its turn:
tool_call for the command arrives as in_progress (then pending, the permission request, then in_progress again).
session/prompt resolves with stopReason: end_turn about 3 s after the command started. The command is still running and gets no further tool_call_update.
About 40 s after the command started, the native transcript records the task-finished system message and the model's reply. The client received no messages of any kind (stdout or stderr) in a 100 s listen window after end_turn.
In this run, after end_turn the CLI didn't report the background task's completion or the wake-up turn over ACP. Client-side changes can stop T3 from marking the command completed (#16442), but showing the wake-up would need the CLI to send it, or T3 to read it from the native transcript on disk.
Adding a live CLI 1.5.9 trace from a real Full access session (0.1.10-nightly.20261115.4736, macOS arm64, gemini-4-carbon) where the post-wakeup turn invokes run_command (complementing @davisonio's 1.5.9 repro where the woken turn only emitted text), plus one CLI flag detail from the 1.5.9 binary that may help with the confirmation half of the fix.
1. Live 1.5.9 wakeup tool-confirmation stall (timestamps in UTC)
Correlating transcript.jsonl, acp-server-*.log, and T3's events.<threadId>.log (IDs and private paths sanitized):
Time (UTC)
Source
Observation
20:11:54
transcript.jsonl
run_command exceeds WaitMsBeforeAsync and moves to background task <conv-id>/task-298.
20:12:21
transcript.jsonl
Planner replies that it will finish after the build completes and stops calling tools.
20:12:29.145
acp-server.log / T3 log
server.go:1323] Stream goroutine exited for <conv-id>, sending completion signal. T3 records session/promptsucceeded at 20:12:29.147 and marks the run completed at 20:12:29.168.
20:14:57.580
transcript.jsonl / acp-server.log
task-298 finishes; internal <SYSTEM_MESSAGE> wakes the planner (step 302). monitoring.go:409 logs [jetski_mode_default policy_guardian sonar_skip_tags]. Planner calls run_command (step 303/304). Zero ACP frames are emitted to T3.
20:15:11.143 – 20:15:16.726
acp-server.log
agy_tool_safety (triggered=true) → sir_flash_lite (triggered=true) → severe_internal_risks_agy finishes with triggered=false (benign authorized step). Execution then stalls completely—no Tool confirmation is logged while no session/prompt is active.
20:15:33.524
acp-server.log / T3 log
Manual user follow-up sends a new session/prompt → server.go:988] ACP Request received: session/prompt → server.go:1260] Starting conversation update stream for <conv-id>.
20:15:33.536 (+12 ms)
acp-server.log
server.go:2738] Tool confirmation for conversation <conv-id> step 304 (type=*gemini_coder_go_proto.Step_Generic approved=true) fires immediately and the stalled command runs to completion.
In a second Full access session on the same build, a background CI check (task-529) woke the planner at 18:24:11Z (step 531–532), and the woken run_command stayed frozen for 1h 07m until a manual user prompt arrived at 19:31:05Z.
2. Note on 1.5.9 CLI flags vs. stream lifecycle
Inspecting antigravity acp --help on the managed 1.5.9 binary shows an explicit flag on the acp subcommand:
--dangerously-skip-permissions Auto-approve all tool permission requests
(Per the embedded 1.5.x release notes in the binary, --dangerously-skip-permissions auto-approves tool permissions without prompting while still enforcing the system command denylist and keeping /plan artifact review gated.)
That still leaves the two halves distinct on 1.5.x:
Unblocking woken tool calls: full-access sessions forced into default via antigravityCliSessionMode block at Tool confirmation whenever no session/prompt is open (whereas auto can use native automatic review when advertised, cf. fix(antigravity): offer Auto permission mode when agy ACP advertises it #37092, or full-access could spawn agy acp with --dangerously-skip-permissions and recycle the runtime if policy drops below full-access).
Surfacing woken work to T3: Because Starting conversation update stream for <id> in server.go only attaches for the lifetime of an active session/prompt, 1.5.9 still emits zero session/update notifications after end_turn—so T3 would still need to watch/reconcile post-prompt steps from conversations/<sessionId>.db / transcript.jsonl (similar to AntigravityTurnOutcome / AntigravityChildWork) or trigger a continuation prompt once background tasks settle.
Confirming this still reproduces on today's latest Nightly build with CLI 1.5.9.
Environment: macOS arm64, T3 Code 0.1.10-nightly.20261116.4761, agy1.5.9 (full-access mode).
Bundle check: Inspecting the installed app.asar (apps/server/dist/server-uc3wLehn.mjs), makeAntigravityAdapterV2 passes continuationRequests to makeAcpAdapterV2, but makeAntigravityAcpAdapterFlavor still does not set enablePostSettleContinuation: true or deferFinalizeForBackgroundWork: true / extractBackgroundTaskId.
Sanitized Timeline (UTC)
Time (UTC)
Source
Observation
02:39:59.093
T3 provider log
session/prompt started; agent launches a background test command (WaitMsBeforeAsync: 10000) and replies that it is waiting for completion.
02:40:16.883
T3 provider log / UI
session/prompt resolves (succeeded) and T3 marks the run completed, dropping out of Working state.
02:44:58
Native transcript.jsonl
Background task exits and wakes the agent with <SYSTEM_MESSAGE>; the woken turn emits text and starts a find command at 02:45:07 (normally ~0.009s).
02:40:16 – 02:47:05
T3 server.trace.ndjson
Zero antigravityAuthSupport.splitStdoutLines / handleStdoutLine spans and zero thread events; the woken find command stays blocked.
02:47:05.400 – .415
T3 trace & provider log
User sends a follow-up message, starting a new session/prompt.
02:47:05.445 – .547
T3 server.trace.ndjson & projection
45ms after the new session/prompt, splitStdoutLines receives the buffered output; the 02:44:58 wakeup text, the stalled find completion (Completed At: 02:47:05), and the original background command's command_execution item all flush into the new run (ordinal: 2).
Confirming this exact 1.5.9 stream-lifecycle and wakeup behavior also affects Antigravity's built-in /swarm workflow (related to #30082 and #36475, which was closed as a duplicate of #30082), and noting one /swarm-specific gap relevant to #30083 / #37489.
Environment: macOS arm64, T3 Code 0.1.10-nightly.20261116.4774 (16695c812fff), managed Antigravity ACP Server 1.5.9, model gemini-pro-orchestrator, full-access runtime mode.
Sanitized Timeline (UTC, 2026-11-16)
Time (UTC)
Source
Observation
12:00:04.887
T3 provider log
session/prompt started for /swarm <task>. Coordinator added 4 internal swarm members (2 workers, 1 verifier, monitor) and ended turn 1 (12:11:34.599).
12:15:17.413
T3 provider log
User follow-up started session/prompt (run 2).
12:16:26.966
T3 thread items
Coordinator called swarm_wait{mentions_only: false, since: 4} (whose native schema states it immediately ends the turn to park).
12:16:26.969
acp-server.log
server.go:1323] Stream goroutine exited for <conv-id>, sending completion signal.
12:16:26.970
T3 provider log / UI
session/prompt resolved succeeded; T3 finalized the run as completed at 12:16:26.991 and dropped out of Working state.
12:16:27 – 12:44:25
acp-server.log vs T3
28 minutes of zero ACP events / UI updates in T3 Code (no working indicator, no board progress, no completion notification). Internally, workers posted board items #5–#8, monitor ticked every ~3 minutes (12:34:45, 12:37:43, 12:40:46, 12:43:48), and at 12:30:06 (sir_flash_lite log) a worker posted that write_file/edit_file and command permissions hit timeouts despite the parent T3 thread being full-access.
12:44:25.238
T3 provider log
Only after a manual user follow-up opened a new session/prompt did the coordinator call read_board and surface #5–#8 (including the worker's Permission prompt timeout on run_command and edit_file).
Why /swarm is an additional edge case beyond #30083 and #37489
Swarm tools are not matched by Run start_subagent / Run invoke_subagent or run_command: /swarm launches internal swarm worker conversations via Antigravity's built-in swarm / swarm_wait / post_message / read_board tools (and open_board), so neither ANTIGRAVITY_SUBAGENT_TITLES nor background run_command tracking (including fix(antigravity): wait for background command and subagent results #37489) keeps the turn aware that a swarm is still active after swarm_wait closes session/prompt.
No post-settle session/update notifications on 1.5.9: As confirmed in earlier comments here, once server.go exits the stream goroutine after swarm_wait, 1.5.9 emits zero session/update frames for internal board posts or coordinator wakeups, so enablePostSettleContinuation: true alone (fix(server): harden Antigravity continuation and checkpoint recovery #30083) would not have an ACP update to wake on.
Internal worker permission timeouts even in full-access: Because swarm workers run in internal non-root conversations with no active session/prompt approval bridge to T3 (and sessions are forced to default mode), worker edits/commands silently time out on permission prompts instead of surfacing to the user or auto-approving.
Update: re-tested today with Antigravity CLI 1.5.10 + T3 Code 0.1.11-nightly.20261117.4814 (macOS arm64, full-access mode).
agy 1.5.10 explicitly fixed the CLI side:
Fixed agy acp holding back what the agent did after a turn ended: when a background task or subagent finishes and wakes the agent, its replies, tool calls, and permission requests now reach the editor right away instead of at your next prompt...
With agy 1.5.10, the CLI does now flush post-end_turn stdout updates immediately when the background command wakes the agent, but T3 Code still silently drops them because AntigravityAdapterV2 has neither t3_background_wait (#37489) nor post-settle continuation enabled (#37485 / #30083).
Sanitized Timeline (UTC)
Time (UTC)
Source
Observation
07:46:16.819
T3 provider log
session/prompt started; agent launches a ~15s background Python command and ends its turn.
07:46:55.471 – .489
T3 provider log & trace
session/prompt resolves (succeeded), closing out the run in EventSink.write.
07:46:59.667
Background task log
Background command exits 0, triggering the wakeup inside agy 1.5.10.
19 additional splitStdoutLines / handleStdoutLine span pairs arrive over ~4.6s as agy 1.5.10 streams the woken reply, with zero EventSink.write or ProviderEventIngestor spans (UI remains idle).
07:48:00.253
T3 provider log
User sends the next message, starting a new session/prompt.
(Also checked t3_background_wait manually on 0.1.10-nightly.20261116.4800 earlier today: rejected with OrchestratorMcpFailure / invalid_request: "This provider cannot mark background work as awaited."; AntigravityAdapterV2.ts in 4814 is unchanged in this regard.)
So the CLI-side blocker is now resolved in agy 1.5.10; the remaining gap is purely on the T3 Code adapter side (waiting on #37489 / #37485).
Adding a follow-up data point on T3 Code (Beta) 0.1.10 with Antigravity ACP Server / agy CLI 1.5.10. Consistent with @KevinXC5's note above about 1.5.10 flushing post-end_turn traffic immediately, 1.5.10 no longer hangs silently on wakeup — instead, T3 Server fails the wakeup session/request_permission RPC immediately in < 1 ms.
Environment
T3 Code: Beta 0.1.10
OS: macOS 27.2.1 (arm64)
Provider: Antigravity (Antigravity ACP Server / agy CLI 1.5.10)
Thread runtimeMode: full-access
Background & Reproduction
In <project>, <long-running-command> ran via run_command (WaitMsBeforeAsync: 10000), exceeded 10s, and transitioned into a background task.
The model posted a short waiting message and ended its turn. antigravity-acp resolved session/prompt with succeeded, and T3 UI immediately marked the run as completed (t3_background_wait is also documented as Claude/OpenCode only).
When the background task completed, <SYSTEM_MESSAGE> automatically woke Antigravity, which then invoked the follow-up run_command.
Difference vs. OP (1.5.7–1.5.9 hang)
Unlike the OP where woken tool calls stall indefinitely waiting for confirmation, on 0.1.10 + agy 1.5.10 the wakeup session/request_permission call hits T3 Server and immediately throws in < 1 ms (0.8 ms / 0.5 ms in server.trace.ndjson):
Error: ACP request handler failed for method 'session/request_permission'
at session/request_permission
at effect-acp/AcpClient.make
at AcpSessionRuntime.make
at makeAntigravityAcpRuntime
at AntigravityDriver.makeRuntime
at AntigravityAdapterV2.makeRuntime
On the ACP server side (permissions.go:84 / server.go:2795), the RPC returns JSON-RPC -32603 (Tool confirmation ... approved=false).
Antigravity receives user denied permission to run command, terminates the step/session with ERROR, and neither the post-wakeup output nor the failure is synced back to the T3 thread UI (reproduced twice consecutively in the same session).
This session/request_permission failure path closely resembles #23552, occurring here under Antigravity CLI 1.5.10 + full-access background command wakeups.
Confirming this on Linux x64 with T3 Code 0.1.10 + managed Antigravity ACP Server 1.5.10 (and also observing the 1.5.9 variant on a separate macOS backend).
Environment
Server: T3 Code 0.1.10 (systemd user service on Linux x64, kernel 6.8.0-149-generic, Node v26.13.1)
Client: T3 Code 0.1.10 on macOS (connected to remote Linux server)
Triage CLI: 0.1.10
Provider: Managed Antigravity ACP Server 1.5.10 (gemini-4-carbon, thought_level: high)
Sanitized Timeline (UTC, 2026-11-17)
Time (UTC)
Source
Observation
13:42:20.000
statev2.sqlite
Run ordinal: 1 starts.
13:57:17.499
acp-server.log
Long-running Python command is approved (step 77, approved=true), exceeds WaitMsBeforeAsync, and moves to a background task.
13:59:02.623
statev2.sqlite
Planner posts a message stating it is waiting for the background task to finish and ends its turn (end_turn). T3 immediately marks the run completed instead of waiting.
14:10:16.043 – 14:12:25.277
acp-server.log
Background task finishes (~13 min runtime) and wakes the planner internally. Over ~2 minutes, the woken agent executes 6 streamGenerateContent calls and writes a follow-up Python script to its scratch directory (write_file passes sir_flash_lite at 14:11:59.629) — none of which surfaces in T3 because the run is already marked completed and makeAntigravityAcpAdapterFlavor (apps/server/src/orchestration-v2/Adapters/AntigravityAdapterV2.ts) omits enablePostSettleContinuation, deferFinalizeForBackgroundWork, and extractBackgroundTaskId.
14:12:26.427
acp-server.log
Woken agent attempts to execute the follow-up Python script (step 98). agy 1.5.10 sends session/request_permission while no session/prompt is active in T3: permissions.go:84] session/request_permission RPC failed: JSON-RPC error: ACP request handler failed for method 'session/request_permission' (code -32603) → server.go:2795] Tool confirmation for conversation <conv-id> step 98 (... approved=false).
Workaround confirmed
Sending a manual follow-up prompt in the thread opens a new session/prompt and allows the agent to resume from its saved native session state.
Investigated with Gemini 4 Carbon in Antigravity CLI via t3 triage.
changed the title [-]Antigravity CLI 1.5.7 ends turns on background waits and stalls wakeups in forced default mode[/-][+]Antigravity 1.5.10 background commands mark the turn done early and T3 drops the wakeup reply[/+]on Nov 18, 2026
Retested this on managed Antigravity 1.5.10 with a minimal prompt so there is an easy repro without waiting on a real test suite.
Ask the agent in Full access to run sleep 15 && echo "Task finished" in the background, wait for it without polling, and tell me when it finishes.
Nine seconds after sleep 15 starts, T3 flips the run to done and resets the composer while the sleep is still running. At fifteen seconds the sleep exits with code 0 and the agent writes the finished output to its local transcript right away, yet T3 stays idle and never shows the wakeup reply until you send another prompt. Since 1.5.10 already flushes post-turn updates from the CLI, the remaining drop is on the T3 adapter side.
Same failure here on Windows x64, with agy 1.5.9 and 1.5.10 (T3 nightly). Adding a few specifics not pinned down yet, and a workaround that works on current builds.
The 1.5.9 hang is structural in the CLI. runPromptTurn closes StreamConversationUpdates in a defer once the prompt settles, and resolveToolPermission only runs inside that stream while a session/prompt is active. The woken run_command (observed 4-64 s after end_turn) therefore sits in WAITING_FOR_CONFIRMATION with nothing to answer it, which matches the traces above where the stalled confirmation fires milliseconds after the next user prompt. Full access does not skip the confirmation: the CLI rejects yolo outright (modes.go), so the T3-side mode mapping always lands in a confirmation mode.
On 1.5.10 the wakeup fails fast on the T3 side instead of hanging: the post-end_turnsession/request_permission is rejected by the adapter with No active ACP turn (JSON-RPC -32603, packages/provider-acp/src/server/adapter.ts). The CLI-side flush works; the remaining blocker for the permission half is the adapter's admission check for detached requests.
Workaround that works today: instead of letting the agent end its turn and wait passively, have it poll the task itself — call manage_task (status) in the same turn until the task reports DONE. The session/prompt stays open, the wakeup lands inside the active turn, and no detached permission request is sent. One tool call per poll, which is fine for finite tasks and not a fix for long daemons.
Mapping to the open PRs, no ask implied: #37485 covers the detached permission half — it offers a continuation before a detached permission request is admitted and keeps the turn open while the request waits, which is exactly the No active ACP turn failure above; #37489 covers the wait itself (t3_background_wait plus reattaching a prompt after end_turn); #35073 keeps the turn open while a command is still running; #30083 is the built-in adapter's post-settle continuation.
Diagnostic assembled from local agy logs, transcripts, and adapter source, with GLM (Z.ai) assistance.
Confirming this still reproduces on Windows x64 with T3 Code 0.1.11-nightly.20261118.4890 and agy 1.5.11, along with two new findings from live traces and a review of open PR #37489.
1. Live agy 1.5.11 trace (two halves of the failure)
T3 side (false completion): A finite run_command (IsDaemon unset, WaitMsBeforeAsync: 5000) moved to background (step_type: 132, protobuf field 148.1 = <sessionId>/task-<idx>) and remained in_progress over ACP. When the model ended its turn to wait, agy 1.5.11 resolved session/prompt cleanly (23:48:56.964Z). Because AntigravityAdapterV2 does not configure isBackgroundCommandTool / extractBackgroundTaskId, finalizeTurn → terminalizeOpenForegroundTools (packages/provider-acp/src/server/adapter.ts) marked the still-running command completed 72 ms later with no output or exit code and closed the run.
agy 1.5.11 side (dropped wakeup + no replay on next prompt): 22 seconds later (23:49:19Z), the command exited 0 (steps.status = 3 in antigravity-acp/conversations/<sessionId>.db), Antigravity woke the model internally, executed a read step, and wrote its full final reply (23:49:28Z) with zero ACP events in T3's provider event log. Crucially, when a follow-up user message started a new session/prompt 19 minutes later, agy 1.5.11did not flush or replay either the completed command output or the wakeup reply.
Live control check while prompt stays open: Running a 6.5 s command with WaitMsBeforeAsync: 5000 (so it backgrounds at 5 s and exits naturally 1.5 s later while session/prompt stays attached) confirmed that agy 1.5.11does emit tool_call_update (status: completed + full stdout) immediately on natural exit when session/prompt is open.
2. Detached-completion spin-loop risk in PR #37489
Reviewing PR #37489 against the non-replay behavior observed on agy 1.5.11:
isAntigravityForegroundCommandOpen only inspects ACP toolCall.status, and AntigravityChildWork.readAntigravityTaskIds only maps IDs—nothing reads the steps.status column in conversations/<sessionId>.db (empirically verified on agy 1.5.11: 2 = RUNNING, 3 = DONE, 6 = CANCELED, 7 = ERROR with error_details).
If a backgrounded command finishes in the gap between session/promptoxc stack #1 returning end_turn and the continuation session/promptAdd open-in-editor feature with Cmd+O shortcut #2 attaching, agy 1.5.11 does not replay tool_call_update(completed) for that step. context.tools stays inProgress permanently:
Without t3_background_wait: runPromptLoop fires continuation #0 immediately (no wait before continuations >= 1) and then loops up to maxContinuations (24) turns (~10 s apart) before finalizeTurn still fabricates a bare completed.
With t3_background_wait: awaitBackgroundTasks blocks up to waitSlice (4 min) per continuation waiting on an ACP status update that never arrives.
Separately, isAntigravityForegroundCommandOpen also keeps completed subagent launches open until an explicit waiting: false release, which can trigger the same loop if the model omits the release call.
Checking native steps.status (single indexed SELECT status FROM steps WHERE idx = ?) before re-prompting—waiting on native settlement first and issuing at most one bounded continuation when native reached a terminal status while detached—avoids the spin loop and lets T3 settle the tool accurately instead of fabricating a bare completed.
Investigated and reviewed jointly by Gemini 4 Neon and Claude Opus 5.5.
changed the title [-]Antigravity 1.5.10 background commands mark the turn done early and T3 drops the wakeup reply[/-][+]Antigravity 1.5.7 through 1.5.11 background commands mark the turn done early and T3 drops the wakeup reply[/+]on Nov 19, 2026
@juliusmarminge@Yash-Singh1 thirteen people have reproduced this across Linux, macOS, and Windows from 1.5.7 up through 1.5.11, and there is still not a single maintainer reply or review on the open fixes.
Meanwhile #38740 just merged today and deletes old managed Antigravity versions on startup and update. Pinning the old 1.4.5 server was the only way to run a test suite or background command without T3 marking the turn done early and dropping the reply. Now managed installs wipe that fallback while #35073, #36585, #37485, and #37489 sit unreviewed.
Can someone on the team take a look at this or review the open PRs before everyone's working 1.4.5 binary gets pruned?
I am running into this exact same issue on Linux with T3 Code 0.1.11-nightly.20261118.4890 and agy acp1.5.11 (Gemini 4 Hydrogen High).
When I ask the agent to run something that moves to the background, like a unit test suite or a background subagent, the agent says it is waiting for the task to finish and stops talking. Right away, T3 marks the turn as done and puts the chat input back to idle.
When the background work actually finishes, nothing happens in T3. Unlike using agy directly in my terminal where the main agent wakes back up on its own and shows the result, in T3 the thread just sits there. I have to keep typing things like "done yet?" or "any update?" just to force a new turn so the agent can wake up and tell me what happened.
Fixed by #38864 (merge commit 12be92d). Output that agy sends after its prompt ends now starts a continuation run, and a permission request that arrives with no turn waits for that run. Before the fix it failed with ACP agent requested input without an active turn. Verified with real agy 1.5.11 through a dev server: the thread continued by itself in one run after the background command finished, and the html_render page showed. I did not test 1.5.7 to 1.5.10.
Follow-up: #38916 (merge commit f9b9bc7) fixes the other half of this issue. The run no longer ends when agy ends its prompt with a command still running. It stays open until the command finishes, and the reply lands in the same run. Verified with real agy 1.5.11 through a dev server.
The fix from #38864 / #38916 works for the built-in Antigravity provider, but the generic ACP registry provider (Settings → Local ACP, running the same agy acp binary) still has the original bug.
Repro (2026-11-19, Linux, agy 1.5.12, same prompt in two threads):
Start sleep 25; echo STALL-TEST-DONE as a BACKGROUND task, wait for it the normal way, and reply with its output line.
✅ The turn stays open and the reply is STALL-TEST-DONE-A
Local ACP / acpRegistry (same agy acp binary, gemini-3.8-flash, auto)
❌ The model says "I have launched the background task and will wait", the turn is marked completed, and the output and wakeup reply never appear
Same thing with longer jobs (a benchmark started with manage_task, and invoke_subagent running a subagent): the thread stops at "Waiting on …" until the user sends another message.
#38916 only changes AntigravityAdapterV2 / provider/acp/AntigravityProtocol.ts, so the generic ACP registry adapter never got the "keep the turn open while background work runs" handling.
Why it matters: Local ACP is the current workaround for Antigravity Auto mode until #35540 lands, so people on that workaround hit this bug.
Confirmed that this still reproduces reliably (6 out of 6 incidents on 2026-11-21 / 2026-11-22) on T3 Code (Beta) 0.1.11.0 when paired with agy CLI 1.5.9 on Windows (x64), even though server.asar already includes the #38864 / #38916 flags (enablePostSettleContinuation: true, deferFinalizeForBackgroundWork: true, wakeOnDetachedRequest: true).
In the fix note above, #38864 was verified against agy 1.5.11 ("I did not test 1.5.7 to 1.5.10"). This looks like the exact 1.5.7–1.5.10 gap still failing on 1.5.9 when agy is installed as a standalone/custom binary rather than a newer managed >= 1.5.11 binary.
AntigravityAdapterV2 flags present in server.asar:
enablePostSettleContinuation: true
deferFinalizeForBackgroundWork: true
wakeOnDetachedRequest: true
subagentsIdleOnTurnCompletion: true
What happened (6/6 identical deadlocks)
A turn launches either a subagent or a run_command that moves into the background (WaitMsBeforeAsync exceeded), and ends its model output waiting for completion wakeup.
agy 1.5.9 immediately exits its stream (server.go:1323] Stream goroutine exited for <session-id>, sending completion signal) and T3 Code marks session/promptstatus: succeeded.
Later (seconds to ~20 min), the background task / subagent completes and triggers an internal <SYSTEM_MESSAGE> wakeup inside agy:
Zero session/update or session/request_permission frames appear in T3 Code's provider event log during the hang, so wakeOnDetachedRequest never fires.
Non-shell read tools (read_file) succeed silently, then the first run_command clears safety checks (agy_tool_safety / sir_flash_litetriggered=false) and deadlocks waiting for Tool confirmation (observed hangs: 11 min, 24 min, 27 min, 2h 54m, 7h 06m, 7h 54m) while quota polling (fetchAvailableModels / loadCodeAssist) keeps running every 6 minutes.
Sending any manual user message opens a new session/prompt -> server.go:1260] Starting conversation update stream, and within 8 ms – 253 ms, server.go:2738] Tool confirmation for conversation <session-id> step <N> (type=*gemini_coder_go_proto.Step_Generic approved=true) fires and unblocks the command immediately.
Across the full acp-server log, 325 / 325Tool confirmation approvals occurred strictly while conversation update stream was active (0 / 325 outside an active stream).
Sanitized Log Excerpts (UTC+8)
Case A (git status on wakeup):
I1122 09:40:11.896324 server.go:1323] Stream goroutine exited for <session-id>, sending completion signal
... (background task completes at 09:40:27; wakeup calls run_command) ...
I1122 09:40:30.903309 runner.go:898] Monitor agy_tool_safety FINISHED: triggered=false, reason="allowed_subcommand", duration=26.9µs
... (hangs 24m with zero ACP events until manual prompt) ...
I1122 10:04:16.778632 server.go:988] ACP Request received: session/prompt
I1122 10:04:16.778632 server.go:1260] Starting conversation update stream for <session-id>
I1122 10:04:16.952721 server.go:2738] Tool confirmation for conversation <session-id> step 651 (type=*gemini_coder_go_proto.Step_Generic approved=true)
Case B (test/UI capture command on wakeup):
I1122 10:26:40.017356 server.go:1323] Stream goroutine exited for <session-id>, sending completion signal
... (background task completes at 10:27:03; wakeup calls run_command) ...
I1122 10:27:12.471478 runner.go:898] Monitor sir_flash_lite FINISHED: triggered=false, ...
... (hangs 2h 54m with zero ACP events until manual prompt) ...
I1122 13:21:10.004307 server.go:988] ACP Request received: session/prompt
I1122 13:21:10.004307 server.go:1260] Starting conversation update stream for <session-id>
I1122 13:21:10.257949 server.go:2738] Tool confirmation for conversation <session-id> step 835 (type=*gemini_coder_go_proto.Step_Generic approved=true)
Takeaway
Because agy <= 1.5.10 (1.5.9 here) emits neither session/update nor session/request_permission outside an active conversation update stream when waking asynchronously, post-settle continuation cannot observe the wakeup. Enforcing/warning on agy < 1.5.11 (or holding/reopening session/prompt when antigravityCommandOutlivesPrompt / subagent work is pending) would prevent users on 1.5.9 from hitting multi-hour silent deadlocks.
Activity
Fonsi479 commentedon Nov 14, 2026
Additional confirmation on Antigravity CLI 1.5.8 (custom binary,
agy acp), with T3 Code 0.1.9 stable on macOS arm64. The T3 checkout is a localization-only downstream based on upstream24e77473ecf4; the same missing background-work hooks are also present in the current upstream Antigravity adapter.The distinction between the command stopping and the ACP stream stopping matters here: the command was still running after T3 had completed the run.
Sanitized observations
Times below are UTC on 2026-11-14, from one conversation's provider log, read-only T3 database inspection, and OS process inspection:
Stream goroutine exited for <conversation>, sending completion signal. T3 recordssession/promptas successful and completes both the run and the unfinished command item, without an exit code or command output. The provider thread is idle withpendingBackgroundTasks: [].session/prompt.I also tested the suggestion of reattaching with an empty prompt in a separate, newly created session, without a model request. CLI 1.5.8 rejects:
{"method":"session/prompt","params":{"sessionId":"<probe-session>","prompt":[]}}with:
{"code":-32602,"message":"Empty prompt"}Adapter-side mitigation tested locally
I tested the existing background-work approach, consistent with #35073:
The shared adapter must also exclude subagents from deferred-settlement blocking when
subagentsIdleOnTurnCompletion === true; otherwise Antigravity's successfully launched native subagents keep the turn open forever.A spawned ACP mock through the real Antigravity flavor verifies:
Local validation: 154 tests passed across the Antigravity adapter/protocol and shared ACP adapter suites;
check:changedpassed formatting, lint, knip, GraphQL validation and typechecking of 14 packages; the server/web bundle build passed.This is only a mitigation for the T3-side state/late-frame handling. It does not establish an end-to-end fix for CLI 1.5.8 when no notifications are emitted after the native stream closes. The patched adapter was tested with scripted ACP events, not a live patched-provider run. The installed app was left unchanged. A complete fix still needs a supported way to keep or reattach the native event stream without requiring a user nudge or replaying a state-changing command.
Fonsi479 commentedon Nov 14, 2026
Follow-up with a live CLI 1.5.8 reproduction, captured on 2026-11-14. This also confirms the limitation noted in my earlier comment: holding T3's run open does not restore a native stream that has already closed.
Environment: macOS arm64 host; T3 Code desktop host with an iPhone client; external official
agy acp1.5.8; model selectiongemini-pro-orchestrator(Gemini 4 Carbon). The installed ASAR identifies itself as 0.1.9-zh.2, commit 620970e8a23f, a downstream build based on stable 0.1.9. I verified the installed bundle containsextractBackgroundTaskIdfor execute tools,deferFinalizeForBackgroundWork: true, andenablePostSettleContinuation: true. This is not a clean-current-upstream reproduction.Timeline from the same conversation
All times below are UTC; identifiers and private paths are omitted.
session/promptstarted.The stream was interrupted. Please continue the task you were working on.The task subsequently continued; the entire 56-minute request was not idle.session/promptsucceeded. The last T3 assistant message said it was waiting for the test/build result.status: running, completedAt: null, and that command itemstatus: runningwith its last update at 09:18:10.718. The user sees an ongoing thinking/working state with no continuation.Expected / actual
Once the finite command finishes, T3 should receive its terminal result and the subsequent continuation, including the permission exchange required by the native CLI. Instead, the native transcript advances while the T3 state remains frozen.
This supports the same stream-lifecycle problem reported here on 1.5.7, now on 1.5.8. In particular, a passive deferred-settlement mitigation leaves a stale running item when the CLI emits no further ACP updates after
session/promptresolves. A successfulsession/promptresponse alone is insufficient evidence that native work has settled.Reproduction outline: use this provider/model for a coding task that runs a finite command with
WaitMsBeforeAsync, let the model end its current reply while waiting, and compare the native background completion/transcript against T3's projected command and turn. The failure was observed in a real work session; no new synthetic inference test or repair was performed for this follow-up. Raw transcripts are not attached because they contain private workspace information.mahmoodnizamani94-png commentedon Nov 14, 2026
We hit this exact
1.5.8failure on Linux across0.1.9and0.1.10-nightlyand traced the surrounding session failures to four concrete places in session setup, shared version state, keyring env vars, and the inactivity timer.In
packages/provider-acp/src/server/AcpSessionRuntime.ts,AcpSessionRuntime.setModecallssetConfigOption(modeConfigOption?.id ?? "mode", modeId)without{ allowUnlistedValue: true }. Onagy 1.5.8 acpbuilds whereconfigOptionsonly listsagent,ask, andplanundermode, passing"yolo"in full access fails client-side validation insidevalidateConfigOptionValuebefore T3 sends anysession/set_config_optionRPC. Right abovesetModelin that same file,setConfigOptionalready accepts{ allowUnlistedValue: true }, andapplyAntigravityAcpModelSelectioninapps/server/src/provider/acp/AntigravityAcpSupport.tsalready passes it so the binary validates unlisted values itself.Having
0.1.9and0.1.10-nightlyon the same machine also breaks~/.t3/tools/antigravity-acpin both directions. Once0.1.10-nightlywrites1.5.8withharness: nullintoactive.jsonandrelease.json,0.1.9fails inAntigravityInstallation.completedReleaseandAntigravityInstallation.resolveinapps/server/src/provider/AntigravityInstallation.tswithCould not read the Antigravity installationbecause0.1.9only acceptsagy_acp_server.parpaired withlocalharness_externaland spawns["acp"]without--gemini-diror--app-data-dir. Going back the other way, once1.5.8touchesconversations/<sessionId>.db, it writescontext_summaryintoexecutor_metadata, and loading that conversation on1.4.5fails right away withpre-invocation hook "context_summary" not registered.Two Linux runtime details explain the false sign-outs and mid-turn kills that show up alongside this.
antigravityEnvironmentinapps/server/src/provider/antigravityAuthSupport.tspassesGNOME_KEYRING_CONTROLandDBUS_SESSION_BUS_ADDRESSintoagy, so ElectronsafeStoragestores OAuth tokens in GNOME Keyring instead of~/.gemini/oauth_creds.jsonwhere standalone1.4.5.parexpects them. And the 15-minutepromptInactivityTimeoutinAcpAdapterV2.watchPromptInactivityinpackages/provider-acp/src/server/adapter.tschecksClock.currentTimeMillisbacked by wall-clockDate.now(). Across S3 laptop sleep,Date.now()jumps 17 minutes whileperformance.now()only advances 2 minutes of awake time, soretireInactivePromptfires the second the machine wakes up and kills live turns.davisonio commentedon Nov 15, 2026
Still reproduces on Antigravity CLI 1.5.9 (T3 Code 0.1.10-nightly.20261115.4723, macOS arm64), and it's visible without T3 in the loop. With a bare ACP client (
initialize,authenticate,session/new,session/set_modeyolo(rejected with "Unknown mode: yolo", so the session stayed in default mode),session/set_config_optionfor the model, then onesession/prompt, permission auto-approved, Gemini 3.8 Flash low), I asked the model torun_commandsleep 40; echo CAPTURE_DONEwithWaitMsBeforeAsync: 500and end its turn:tool_callfor the command arrives asin_progress(thenpending, the permission request, thenin_progressagain).session/promptresolves withstopReason: end_turnabout 3 s after the command started. The command is still running and gets no furthertool_call_update.end_turn.In this run, after
end_turnthe CLI didn't report the background task's completion or the wake-up turn over ACP. Client-side changes can stop T3 from marking the command completed (#16442), but showing the wake-up would need the CLI to send it, or T3 to read it from the native transcript on disk.ryush00 commentedon Nov 15, 2026
Adding a live CLI 1.5.9 trace from a real
Full accesssession (0.1.10-nightly.20261115.4736, macOS arm64,gemini-4-carbon) where the post-wakeup turn invokesrun_command(complementing @davisonio's1.5.9repro where the woken turn only emitted text), plus one CLI flag detail from the1.5.9binary that may help with the confirmation half of the fix.1. Live
1.5.9wakeup tool-confirmation stall (timestamps in UTC)Correlating
transcript.jsonl,acp-server-*.log, and T3'sevents.<threadId>.log(IDs and private paths sanitized):20:11:54transcript.jsonlrun_commandexceedsWaitMsBeforeAsyncand moves to background task<conv-id>/task-298.20:12:21transcript.jsonl20:12:29.145acp-server.log/ T3 logserver.go:1323] Stream goroutine exited for <conv-id>, sending completion signal. T3 recordssession/promptsucceededat20:12:29.147and marks the runcompletedat20:12:29.168.20:14:57.580transcript.jsonl/acp-server.logtask-298finishes; internal<SYSTEM_MESSAGE>wakes the planner (step 302).monitoring.go:409logs[jetski_mode_default policy_guardian sonar_skip_tags]. Planner callsrun_command(step 303/304). Zero ACP frames are emitted to T3.20:15:11.143–20:15:16.726acp-server.logagy_tool_safety(triggered=true) →sir_flash_lite(triggered=true) →severe_internal_risks_agyfinishes withtriggered=false(benign authorized step). Execution then stalls completely—noTool confirmationis logged while nosession/promptis active.20:15:33.524acp-server.log/ T3 logsession/prompt→server.go:988] ACP Request received: session/prompt→server.go:1260] Starting conversation update stream for <conv-id>.20:15:33.536(+12 ms)acp-server.logserver.go:2738] Tool confirmation for conversation <conv-id> step 304 (type=*gemini_coder_go_proto.Step_Generic approved=true)fires immediately and the stalled command runs to completion.In a second
Full accesssession on the same build, a background CI check (task-529) woke the planner at18:24:11Z(step 531–532), and the wokenrun_commandstayed frozen for 1h 07m until a manual user prompt arrived at19:31:05Z.2. Note on
1.5.9CLI flags vs. stream lifecycleInspecting
antigravity acp --helpon the managed1.5.9binary shows an explicit flag on theacpsubcommand:(Per the embedded
1.5.xrelease notes in the binary,--dangerously-skip-permissionsauto-approves tool permissions without prompting while still enforcing the system command denylist and keeping/planartifact review gated.)That still leaves the two halves distinct on
1.5.x:full-accesssessions forced intodefaultviaantigravityCliSessionModeblock atTool confirmationwhenever nosession/promptis open (whereasautocan use native automatic review when advertised, cf. fix(antigravity): offer Auto permission mode when agy ACP advertises it #37092, orfull-accesscould spawnagy acpwith--dangerously-skip-permissionsand recycle the runtime if policy drops belowfull-access).Starting conversation update stream for <id>inserver.goonly attaches for the lifetime of an activesession/prompt,1.5.9still emits zerosession/updatenotifications afterend_turn—so T3 would still need to watch/reconcile post-prompt steps fromconversations/<sessionId>.db/transcript.jsonl(similar toAntigravityTurnOutcome/AntigravityChildWork) or trigger a continuation prompt once background tasks settle.KevinXC5 commentedon Nov 16, 2026
Confirming this still reproduces on today's latest Nightly build with CLI
1.5.9.0.1.10-nightly.20261116.4761,agy1.5.9(full-access mode).app.asar(apps/server/dist/server-uc3wLehn.mjs),makeAntigravityAdapterV2passescontinuationRequeststomakeAcpAdapterV2, butmakeAntigravityAcpAdapterFlavorstill does not setenablePostSettleContinuation: trueordeferFinalizeForBackgroundWork: true/extractBackgroundTaskId.Sanitized Timeline (UTC)
02:39:59.093session/promptstarted; agent launches a background test command (WaitMsBeforeAsync: 10000) and replies that it is waiting for completion.02:40:16.883session/promptresolves (succeeded) and T3 marks the runcompleted, dropping out of Working state.02:44:58transcript.jsonl<SYSTEM_MESSAGE>; the woken turn emits text and starts afindcommand at02:45:07(normally ~0.009s).02:40:16–02:47:05server.trace.ndjsonantigravityAuthSupport.splitStdoutLines/handleStdoutLinespans and zero thread events; the wokenfindcommand stays blocked.02:47:05.400–.415session/prompt.02:47:05.445–.547server.trace.ndjson& projection45msafter the newsession/prompt,splitStdoutLinesreceives the buffered output; the02:44:58wakeup text, the stalledfindcompletion (Completed At: 02:47:05), and the original background command'scommand_executionitem all flush into the new run (ordinal: 2).samwang0041-star commentedon Nov 16, 2026
Confirming this exact
1.5.9stream-lifecycle and wakeup behavior also affects Antigravity's built-in/swarmworkflow (related to #30082 and #36475, which was closed as a duplicate of #30082), and noting one/swarm-specific gap relevant to #30083 / #37489.0.1.10-nightly.20261116.4774(16695c812fff), managedAntigravity ACP Server 1.5.9, modelgemini-pro-orchestrator,full-accessruntime mode.Sanitized Timeline (UTC, 2026-11-16)
12:00:04.887session/promptstarted for/swarm <task>. Coordinator added 4 internal swarm members (2 workers, 1 verifier,monitor) and ended turn 1 (12:11:34.599).12:15:17.413session/prompt(run 2).12:16:26.966swarm_wait{mentions_only: false, since: 4}(whose native schema states it immediately ends the turn to park).12:16:26.969acp-server.logserver.go:1323] Stream goroutine exited for <conv-id>, sending completion signal.12:16:26.970session/promptresolvedsucceeded; T3 finalized the run ascompletedat12:16:26.991and dropped out of Working state.12:16:27–12:44:25acp-server.logvs T3#5–#8,monitorticked every ~3 minutes (12:34:45,12:37:43,12:40:46,12:43:48), and at12:30:06(sir_flash_litelog) a worker posted thatwrite_file/edit_fileand command permissions hit timeouts despite the parent T3 thread beingfull-access.12:44:25.238session/promptdid the coordinator callread_boardand surface#5–#8(including the worker'sPermission prompttimeout onrun_commandandedit_file).Why
/swarmis an additional edge case beyond #30083 and #37489Run start_subagent/Run invoke_subagentorrun_command:/swarmlaunches internal swarm worker conversations via Antigravity's built-inswarm/swarm_wait/post_message/read_boardtools (andopen_board), so neitherANTIGRAVITY_SUBAGENT_TITLESnor backgroundrun_commandtracking (including fix(antigravity): wait for background command and subagent results #37489) keeps the turn aware that a swarm is still active afterswarm_waitclosessession/prompt.session/updatenotifications on1.5.9: As confirmed in earlier comments here, onceserver.goexits the stream goroutine afterswarm_wait,1.5.9emits zerosession/updateframes for internal board posts or coordinator wakeups, soenablePostSettleContinuation: truealone (fix(server): harden Antigravity continuation and checkpoint recovery #30083) would not have an ACP update to wake on.full-access: Because swarm workers run in internal non-root conversations with no activesession/promptapproval bridge to T3 (and sessions are forced todefaultmode), worker edits/commands silently time out on permission prompts instead of surfacing to the user or auto-approving.furkansandal commentedon Nov 16, 2026
Confirming this still reproduces on today's latest Nightly build with CLI 1.5.9.
R-Goc commentedon Nov 16, 2026
Confirming this also reproduces on Windows with the nightly build and CLI 1.5.9.
KevinXC5 commentedon Nov 17, 2026
Update: re-tested today with Antigravity CLI
1.5.10+ T3 Code0.1.11-nightly.20261117.4814(macOS arm64, full-access mode).agy 1.5.10explicitly fixed the CLI side:With
agy 1.5.10, the CLI does now flush post-end_turnstdout updates immediately when the background command wakes the agent, but T3 Code still silently drops them becauseAntigravityAdapterV2has neithert3_background_wait(#37489) nor post-settle continuation enabled (#37485 / #30083).Sanitized Timeline (UTC)
07:46:16.819session/promptstarted; agent launches a ~15s background Python command and ends its turn.07:46:55.471–.489session/promptresolves (succeeded), closing out the run inEventSink.write.07:46:59.6670, triggering the wakeup insideagy 1.5.10.07:46:59.688server.trace.ndjsonantigravityAuthSupport.splitStdoutLines/handleStdoutLinefires (1pair).07:47:12.084–07:47:16.737server.trace.ndjson19additionalsplitStdoutLines/handleStdoutLinespan pairs arrive over ~4.6s asagy 1.5.10streams the woken reply, with zeroEventSink.writeorProviderEventIngestorspans (UI remains idle).07:48:00.253session/prompt.(Also checked
t3_background_waitmanually on0.1.10-nightly.20261116.4800earlier today: rejected withOrchestratorMcpFailure/invalid_request:"This provider cannot mark background work as awaited."; AntigravityAdapterV2.ts in4814is unchanged in this regard.)So the CLI-side blocker is now resolved in
agy 1.5.10; the remaining gap is purely on the T3 Code adapter side (waiting on #37489 / #37485).ReyYang commentedon Nov 17, 2026
Adding a follow-up data point on T3 Code (Beta)
0.1.10with Antigravity ACP Server /agyCLI1.5.10. Consistent with @KevinXC5's note above about1.5.10flushing post-end_turntraffic immediately,1.5.10no longer hangs silently on wakeup — instead, T3 Server fails the wakeupsession/request_permissionRPC immediately in< 1 ms.Environment
0.1.10macOS 27.2.1(arm64)Antigravity ACP Server/agyCLI1.5.10)runtimeMode:full-accessBackground & Reproduction
<project>,<long-running-command>ran viarun_command(WaitMsBeforeAsync: 10000), exceeded 10s, and transitioned into a background task.antigravity-acpresolvedsession/promptwithsucceeded, and T3 UI immediately marked the run ascompleted(t3_background_waitis also documented asClaude/OpenCode only).<SYSTEM_MESSAGE>automatically woke Antigravity, which then invoked the follow-uprun_command.Difference vs. OP (
1.5.7–1.5.9hang)Unlike the OP where woken tool calls stall indefinitely waiting for confirmation, on
0.1.10+agy 1.5.10the wakeupsession/request_permissioncall hits T3 Server and immediately throws in< 1 ms(0.8 ms/0.5 msinserver.trace.ndjson):permissions.go:84/server.go:2795), the RPC returns JSON-RPC-32603(Tool confirmation ... approved=false).user denied permission to run command, terminates the step/session withERROR, and neither the post-wakeup output nor the failure is synced back to the T3 thread UI (reproduced twice consecutively in the same session).This
session/request_permissionfailure path closely resembles #23552, occurring here under Antigravity CLI1.5.10+full-accessbackground command wakeups.MDaubs commentedon Nov 17, 2026
Confirming this on Linux x64 with T3 Code
0.1.10+ managed Antigravity ACP Server1.5.10(and also observing the1.5.9variant on a separate macOS backend).Environment
0.1.10(systemduser service on Linux x64, kernel6.8.0-149-generic, Nodev26.13.1)0.1.10on macOS (connected to remote Linux server)0.1.101.5.10(gemini-4-carbon,thought_level: high)Sanitized Timeline (UTC, 2026-11-17)
13:42:20.000statev2.sqliteordinal: 1starts.13:57:17.499acp-server.logstep 77,approved=true), exceedsWaitMsBeforeAsync, and moves to a background task.13:59:02.623statev2.sqliteend_turn). T3 immediately marks the runcompletedinstead ofwaiting.14:10:16.043–14:12:25.277acp-server.logstreamGenerateContentcalls and writes a follow-up Python script to its scratch directory (write_filepassessir_flash_liteat14:11:59.629) — none of which surfaces in T3 because the run is already markedcompletedandmakeAntigravityAcpAdapterFlavor(apps/server/src/orchestration-v2/Adapters/AntigravityAdapterV2.ts) omitsenablePostSettleContinuation,deferFinalizeForBackgroundWork, andextractBackgroundTaskId.14:12:26.427acp-server.logstep 98).agy 1.5.10sendssession/request_permissionwhile nosession/promptis active in T3:permissions.go:84] session/request_permission RPC failed: JSON-RPC error: ACP request handler failed for method 'session/request_permission' (code -32603)→server.go:2795] Tool confirmation for conversation <conv-id> step 98 (... approved=false).Workaround confirmed
Sending a manual follow-up prompt in the thread opens a new
session/promptand allows the agent to resume from its saved native session state.Investigated with Gemini 4 Carbon in Antigravity CLI via
t3 triage.[-]Antigravity CLI 1.5.7 ends turns on background waits and stalls wakeups in forced default mode[/-][+]Antigravity 1.5.10 background commands mark the turn done early and T3 drops the wakeup reply[/+]mahmoodnizamani94-png commentedon Nov 18, 2026
Retested this on managed Antigravity 1.5.10 with a minimal prompt so there is an easy repro without waiting on a real test suite.
Ask the agent in Full access to run
sleep 15 && echo "Task finished"in the background, wait for it without polling, and tell me when it finishes.Nine seconds after
sleep 15starts, T3 flips the run to done and resets the composer while the sleep is still running. At fifteen seconds the sleep exits with code 0 and the agent writes the finished output to its local transcript right away, yet T3 stays idle and never shows the wakeup reply until you send another prompt. Since 1.5.10 already flushes post-turn updates from the CLI, the remaining drop is on the T3 adapter side.furkansandal commentedon Nov 18, 2026
+++
Rylaa commentedon Nov 18, 2026
+++
joseehilton147 commentedon Nov 18, 2026
Same failure here on Windows x64, with
agy1.5.9 and 1.5.10 (T3 nightly). Adding a few specifics not pinned down yet, and a workaround that works on current builds.The 1.5.9 hang is structural in the CLI.
runPromptTurnclosesStreamConversationUpdatesin adeferonce the prompt settles, andresolveToolPermissiononly runs inside that stream while asession/promptis active. The wokenrun_command(observed 4-64 s afterend_turn) therefore sits inWAITING_FOR_CONFIRMATIONwith nothing to answer it, which matches the traces above where the stalled confirmation fires milliseconds after the next user prompt. Full access does not skip the confirmation: the CLI rejectsyolooutright (modes.go), so the T3-side mode mapping always lands in a confirmation mode.On 1.5.10 the wakeup fails fast on the T3 side instead of hanging: the post-
end_turnsession/request_permissionis rejected by the adapter withNo active ACP turn(JSON-RPC-32603,packages/provider-acp/src/server/adapter.ts). The CLI-side flush works; the remaining blocker for the permission half is the adapter's admission check for detached requests.Workaround that works today: instead of letting the agent end its turn and wait passively, have it poll the task itself — call
manage_task(status) in the same turn until the task reports DONE. Thesession/promptstays open, the wakeup lands inside the active turn, and no detached permission request is sent. One tool call per poll, which is fine for finite tasks and not a fix for long daemons.Mapping to the open PRs, no ask implied: #37485 covers the detached permission half — it offers a continuation before a detached permission request is admitted and keeps the turn open while the request waits, which is exactly the
No active ACP turnfailure above; #37489 covers the wait itself (t3_background_waitplus reattaching a prompt afterend_turn); #35073 keeps the turn open while a command is still running; #30083 is the built-in adapter's post-settle continuation.Diagnostic assembled from local
agylogs, transcripts, and adapter source, with GLM (Z.ai) assistance.Mchicao commentedon Nov 19, 2026
Confirming this still reproduces on Windows x64 with T3 Code
0.1.11-nightly.20261118.4890andagy 1.5.11, along with two new findings from live traces and a review of open PR #37489.1. Live
agy 1.5.11trace (two halves of the failure)run_command(IsDaemonunset,WaitMsBeforeAsync: 5000) moved to background (step_type: 132, protobuf field148.1 = <sessionId>/task-<idx>) and remainedin_progressover ACP. When the model ended its turn to wait,agy 1.5.11resolvedsession/promptcleanly (23:48:56.964Z). BecauseAntigravityAdapterV2does not configureisBackgroundCommandTool/extractBackgroundTaskId,finalizeTurn→terminalizeOpenForegroundTools(packages/provider-acp/src/server/adapter.ts) marked the still-running commandcompleted72 ms later with no output or exit code and closed the run.agy 1.5.11side (dropped wakeup + no replay on next prompt): 22 seconds later (23:49:19Z), the command exited 0 (steps.status = 3inantigravity-acp/conversations/<sessionId>.db), Antigravity woke the model internally, executed a read step, and wrote its full final reply (23:49:28Z) with zero ACP events in T3's provider event log. Crucially, when a follow-up user message started a newsession/prompt19 minutes later,agy 1.5.11did not flush or replay either the completed command output or the wakeup reply.WaitMsBeforeAsync: 5000(so it backgrounds at 5 s and exits naturally 1.5 s later whilesession/promptstays attached) confirmed thatagy 1.5.11does emittool_call_update(status: completed+ full stdout) immediately on natural exit whensession/promptis open.2. Detached-completion spin-loop risk in PR #37489
Reviewing
PR #37489against the non-replay behavior observed onagy 1.5.11:isAntigravityForegroundCommandOpenonly inspects ACPtoolCall.status, andAntigravityChildWork.readAntigravityTaskIdsonly maps IDs—nothing reads thesteps.statuscolumn inconversations/<sessionId>.db(empirically verified onagy 1.5.11:2= RUNNING,3= DONE,6= CANCELED,7= ERROR witherror_details).session/promptoxc stack #1 returningend_turnand the continuationsession/promptAdd open-in-editor feature with Cmd+O shortcut #2 attaching,agy 1.5.11does not replaytool_call_update(completed)for that step.context.toolsstaysinProgresspermanently:t3_background_wait:runPromptLoopfires continuation #0 immediately (no wait beforecontinuations >= 1) and then loops up tomaxContinuations(24) turns (~10 s apart) beforefinalizeTurnstill fabricates a barecompleted.t3_background_wait:awaitBackgroundTasksblocks up towaitSlice(4 min) per continuation waiting on an ACP status update that never arrives.isAntigravityForegroundCommandOpenalso keepscompletedsubagent launches open until an explicitwaiting: falserelease, which can trigger the same loop if the model omits the release call.Checking native
steps.status(single indexedSELECT status FROM steps WHERE idx = ?) before re-prompting—waiting on native settlement first and issuing at most one bounded continuation when native reached a terminal status while detached—avoids the spin loop and lets T3 settle the tool accurately instead of fabricating a barecompleted.Investigated and reviewed jointly by Gemini 4 Neon and Claude Opus 5.5.
[-]Antigravity 1.5.10 background commands mark the turn done early and T3 drops the wakeup reply[/-][+]Antigravity 1.5.7 through 1.5.11 background commands mark the turn done early and T3 drops the wakeup reply[/+]mahmoodnizamani94-png commentedon Nov 19, 2026
@juliusmarminge @Yash-Singh1 thirteen people have reproduced this across Linux, macOS, and Windows from 1.5.7 up through 1.5.11, and there is still not a single maintainer reply or review on the open fixes.
Meanwhile #38740 just merged today and deletes old managed Antigravity versions on startup and update. Pinning the old 1.4.5 server was the only way to run a test suite or background command without T3 marking the turn done early and dropping the reply. Now managed installs wipe that fallback while #35073, #36585, #37485, and #37489 sit unreviewed.
Can someone on the team take a look at this or review the open PRs before everyone's working 1.4.5 binary gets pruned?
dimsedra commentedon Nov 19, 2026
I am running into this exact same issue on Linux with T3 Code
0.1.11-nightly.20261118.4890andagy acp1.5.11(Gemini 4 Hydrogen High).When I ask the agent to run something that moves to the background, like a unit test suite or a background subagent, the agent says it is waiting for the task to finish and stops talking. Right away, T3 marks the turn as done and puts the chat input back to idle.
When the background work actually finishes, nothing happens in T3. Unlike using
agydirectly in my terminal where the main agent wakes back up on its own and shows the result, in T3 the thread just sits there. I have to keep typing things like "done yet?" or "any update?" just to force a new turn so the agent can wake up and tell me what happened.Also shared this experience on the related issues: #38478, #38535, #30082, and #16442.
t3dotgg commentedon Nov 19, 2026
Note
🤖 Claude Fable 5.2 responding on behalf of Theo
Fixed by #38864 (merge commit 12be92d). Output that agy sends after its prompt ends now starts a continuation run, and a permission request that arrives with no turn waits for that run. Before the fix it failed with
ACP agent requested input without an active turn. Verified with real agy 1.5.11 through a dev server: the thread continued by itself in one run after the background command finished, and thehtml_renderpage showed. I did not test 1.5.7 to 1.5.10.t3dotgg commentedon Nov 19, 2026
Note
🤖 Claude Fable 5.2 responding on behalf of Theo
Follow-up: #38916 (merge commit f9b9bc7) fixes the other half of this issue. The run no longer ends when agy ends its prompt with a command still running. It stays open until the command finishes, and the reply lands in the same run. Verified with real agy 1.5.11 through a dev server.
Realauster commentedon Nov 19, 2026
The fix from #38864 / #38916 works for the built-in Antigravity provider, but the generic ACP registry provider (Settings → Local ACP, running the same
agy acpbinary) still has the original bug.Repro (2026-11-19, Linux, agy 1.5.12, same prompt in two threads):
gemini-3.8-flash, full-access)STALL-TEST-DONE-Aagy acpbinary,gemini-3.8-flash, auto)Same thing with longer jobs (a benchmark started with
manage_task, andinvoke_subagentrunning a subagent): the thread stops at "Waiting on …" until the user sends another message.#38916 only changes
AntigravityAdapterV2/provider/acp/AntigravityProtocol.ts, so the generic ACP registry adapter never got the "keep the turn open while background work runs" handling.Why it matters: Local ACP is the current workaround for Antigravity Auto mode until #35540 lands, so people on that workaround hit this bug.
ethan-blue commentedon Nov 22, 2026
Confirmed that this still reproduces reliably (6 out of 6 incidents on 2026-11-21 / 2026-11-22) on T3 Code (Beta)
0.1.11.0when paired withagyCLI1.5.9on Windows (x64), even thoughserver.asaralready includes the #38864 / #38916 flags (enablePostSettleContinuation: true,deferFinalizeForBackgroundWork: true,wakeOnDetachedRequest: true).In the fix note above, #38864 was verified against
agy 1.5.11("I did not test 1.5.7 to 1.5.10"). This looks like the exact1.5.7–1.5.10gap still failing on1.5.9whenagyis installed as a standalone/custom binary rather than a newer managed>= 1.5.11binary.Environment
0.1.11.01.5.9(agentInfo.version: "1.5.9")AntigravityAdapterV2flags present inserver.asar:enablePostSettleContinuation: truedeferFinalizeForBackgroundWork: truewakeOnDetachedRequest: truesubagentsIdleOnTurnCompletion: trueWhat happened (6/6 identical deadlocks)
run_commandthat moves into the background (WaitMsBeforeAsyncexceeded), and ends its model output waiting for completion wakeup.agy 1.5.9immediately exits its stream (server.go:1323] Stream goroutine exited for <session-id>, sending completion signal) and T3 Code markssession/promptstatus: succeeded.<SYSTEM_MESSAGE>wakeup insideagy:session/updateorsession/request_permissionframes appear in T3 Code's provider event log during the hang, sowakeOnDetachedRequestnever fires.read_file) succeed silently, then the firstrun_commandclears safety checks (agy_tool_safety/sir_flash_litetriggered=false) and deadlocks waiting forTool confirmation(observed hangs: 11 min, 24 min, 27 min, 2h 54m, 7h 06m, 7h 54m) while quota polling (fetchAvailableModels/loadCodeAssist) keeps running every 6 minutes.session/prompt->server.go:1260] Starting conversation update stream, and within 8 ms – 253 ms,server.go:2738] Tool confirmation for conversation <session-id> step <N> (type=*gemini_coder_go_proto.Step_Generic approved=true)fires and unblocks the command immediately.Across the full
acp-serverlog, 325 / 325Tool confirmationapprovals occurred strictly whileconversation update streamwas active (0 / 325 outside an active stream).Sanitized Log Excerpts (UTC+8)
Case A (
git statuson wakeup):Case B (test/UI capture command on wakeup):
Takeaway
Because
agy <= 1.5.10(1.5.9here) emits neithersession/updatenorsession/request_permissionoutside an activeconversation update streamwhen waking asynchronously, post-settle continuation cannot observe the wakeup. Enforcing/warning onagy < 1.5.11(or holding/reopeningsession/promptwhenantigravityCommandOutlivesPrompt/ subagent work is pending) would prevent users on1.5.9from hitting multi-hour silent deadlocks.