[Bug]: Antigravity turn ends on a dropped ACP stream: raw proxy error shown, no reconnect after a clean WebSocket close (1000)

Before submitting

• I searched existing issues and did not find a duplicate.
• I included enough detail to reproduce or investigate the problem.

Area

apps/server (Antigravity / ACP provider, session lifecycle and error handling)

Steps to reproduce

1. T3 Code (Alpha) 0.0.40, also seen on 0.0.41-nightly.20260913.1675, on macOS. Antigravity provider, Gemini 3.8 Flash.
2. Run a normal multi-minute turn with several tool calls.
3. Partway through, the local Antigravity proxy (agy_acp_server at http://127.0.0.1:<port>) drops the streaming request to the model.
4. After the turn fails, send the prompt again ("try again" or "continue").

Expected behavior

• A dropped upstream stream (streamGenerateContent returning EOF) should be retried with backoff.
• A clean WebSocket close (code 1000 OK) from the ACP process should reconnect, not end the turn.
• Any error shown to the user should be readable, not a raw Go transport string.

Actual behavior

Two problems, both in T3's handling of the drop:

1. The raw error reaches the user. When the proxy returns EOF, the adapter forwards the message unchanged and ends the turn: Agent execution error: model unreachable: doRequest: error sending request: Post "…streamGenerateContent…": EOF.
2. A clean close is treated as fatal. On the next prompt, the session cannot recover: Failed to rebuild agent: received 1000 (OK); then sent 1000 (OK). Code 1000 is a normal close, but the rebuild path fails on it. The user has to start the turn over.

Seen in four real sessions across two builds, three on 0.0.40 (2026-09-10) and one on 0.0.41-nightly.20260913 (2026-09-14), so it survives across releases:

Likely code areas

References are pinned to commit c07575f573dd3a1af4f734297d17f7c951c95f10 (main), so the line numbers stay valid as the file changes. Neither error string exists in the source, so both come from the agy_acp_server binary and pass through unclassified. The handling gaps are:

• AcpAdapterSupport.ts L30-L43 (mapAcpToAdapterError): sets detail: error.message with no branch for transient or network errors, so the raw proxy string reaches the chat.
• AcpSessionRuntime.ts L363-L374 (ensureConnected): does not reconnect. It only re-throws a stored termination error. recordTermination L376-L392 latches the first failure, and retireRuntime L912-L917 kills the child process, so the runtime cannot recover on its own.
• AntigravityAdapter.ts: no retry, backoff, or reconnect around the prompt. The prompt is dispatched once.
• The only recovery path is a full instance rebuild in ProviderInstanceRegistry.ts, which re-runs the ACP handshake. A clean WebSocket close during that handshake is what surfaces as Failed to rebuild agent: received 1000 (OK).

Impact

A recoverable disconnect ends the turn and makes the user re-send the prompt. The message says model unreachable, so users assume the model or network is down, when it is the local proxy dropping the stream.

Version or commit

T3 Code (Alpha) 0.0.40, still reproducing on 0.0.41-nightly.20260913.1675.

Environment

• macOS 26.5.2 (Build 25F84, arm64)
• Antigravity provider via the local agy_acp_server proxy at http://127.0.0.1:<port>
• Model: gemini-3.8-flash-high

Logs or stack traces

Assistant-surfaced errors, with the GCP project id and the ephemeral port masked:

Agent execution error: model unreachable: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF

Agent connection was lost and could not be re-established: Failed to rebuild agent: received 1000 (OK); then sent 1000 (OK)

Full provider event logs are available on request at ~/.t3/userdata/logs/provider/events.<thread>.log for the four sessions above. Scrub <project-id> before sharing.

Workaround

Send the prompt again. This usually starts a fresh agent. There is no automatic retry or reconnect.

[2026-09-10 08:53:07Z] Agent execution error: model unreachable: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF
[2026-09-10 09:03:54Z] Agent connection was lost and could not be re-established: Failed to rebuild agent: received 1000 (OK); then sent 1000 (OK)

doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF

[2026-09-10 12:41:33Z] Agent execution error: model unreachable: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF
[2026-09-10 12:44:25Z] Agent connection was lost and could not be re-established: Failed to rebuild agent: received 1000 (OK); then sent 1000 (OK)

doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF

[2026-09-10 12:41:35Z] Agent execution error: model unreachable: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF
[2026-09-10 12:44:16Z] Agent connection was lost and could not be re-established: Failed to rebuild agent: received 1000 (OK); then sent 1000 (OK)

doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF

[2026-09-14 01:24:37Z] Agent execution error: model unreachable: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF: doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF
[2026-09-14 01:55:05Z] Agent connection was lost and could not be re-established: Failed to rebuild agent: received 1000 (OK); then sent 1000 (OK)

doRequest: error sending request: Post "http://127.0.0.1:<port>/v1beta1/projects/<project-id>/locations/us/publishers/google/models/gemini-3.8-flash-high:streamGenerateContent?alt=sse": EOF

Start with apps/server/src/provider/acp/AcpAdapterSupport.ts and inspect mapAcpToAdapterError, then trace session recovery through AcpSessionRuntime.ts, AntigravityAdapter.ts, and ProviderInstanceRegistry.ts. Reproduce or inspect the dropped stream and clean WebSocket-close paths. Done means transient failures produce readable errors, dropped streams can retry with backoff, and a normal close can recover without requiring the user to restart the turn.