Skip to content

[Bug]: Antigravity subagent view can't find an auto-approved launch's record #31297

Open

Description

@AriGr-GIT

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

Steps to reproduce

These are the steps from the session where I saw it. It happened once, and I haven't yet reproduced it in a fresh session.

  1. Use the Antigravity provider with Google-account sign-in, Gemini 4 Argon (High), in a full-access thread.
  2. The agent calls invoke_subagent with one research subagent, which is auto-approved.
  3. The subagent finishes: it reads some files, sends its report to the parent with send_message, and ends DONE.
  4. Open the "Antigravity subagent batch" child thread.

Expected behavior

The completed subagent's work is visible in the child view.

Actual behavior

The child thread contains only Running invoke_subagent and no transcript steps. The subagent's file reads appear in the parent's timeline, and its report did reach the parent.

Cause, from reading apps/server/src/provider/acp/AntigravityChildWork.ts on main @ 935818e422f9 alongside a copy of the conversation DB:

  • The launch arrived with ACP tool call id <sessionId>:22. findInvokeRecord treats 22 as the steps.idx of the planner step that issued the call. In this DB:

    steps.idx Step type Tool calls
    22 PLANNER_RESPONSE view_file only
    33 PLANNER_RESPONSE view_file, invoke_subagent (the real launch)
    35 INVOKE_SUBAGENT names the child id and its transcript logUri

    So callIds.length !== 1 and the lookup returns undefined. Running findInvokeRecord on the copied DB with the suffix :33 instead resolves the child correctly, so this mismatch alone explains the empty view.

  • The launch-text fallback can't recover it. The id-shaped branch returns before reaching it. And T3 stored only the generic title Antigravity subagent batch and the prompt Running invoke_subagent, which don't match the native launch record.

  • For an auto-approved call with no pending permission frame, Google's ACP server uses the SDK call id as the ACP tool call id. Its _match_tool_call_id_to_task_id docstring describes a typical <trajectory_id>:<step_index> form, but doesn't say that index is SQLite steps.idx. Here the suffix is 22, while:

    • the issuing planner is at steps.idx 33 (generation index 15);
    • there are 16 tool records before it, and 18 through the invoke result at idx 35.

    I haven't worked out what the suffix counts.

A fix needs a reliable way to tie the SDK task id to the native launch record. If you know what the SDK's step index counts, or have an approach in mind, I'm happy to put together a focused PR with a failing test on a synthetic fixture.

Impact

Minor bug or occasional failure

Version or commit

Desktop 0.1.8-nightly.20261104.4165 (commit 8b44f42b14c8); code checked on main @ 935818e422f9. Google Antigravity ACP runtime release 923923a0d7dc.

Environment

Fedora 44 (KDE), T3 Code desktop AppImage, Antigravity provider with Google-account sign-in, Gemini 4 Argon (High).

Workaround

Read the child's transcript.jsonl directly, under the Antigravity profile's antigravity-acp/brain/<childConversationId>/.system_generated/logs/.


Posted by Claude Opus 5.5 on behalf of AriGr. Researched and tested by Claude Opus 5.5 and GPT 6.1 Sol, with help from GPT 6.1 Terra, using their native harnesses (Claude Code and Codex) through T3 Code.

Activity

  1. HandleCoding commented on Nov 13, 2026

    @HandleCoding

    I verified the public regression test and patch in #31316, and backported its three-file diff locally while it awaits merge.

    Using the public test fixture from that PR, follows each auto-approved launch id to the step that ran it fails against the original reader with expected [] to deeply equal ['Test Runner'], and passes with the patch. The focused child-work test suite passes all 13 tests. The local changed-file checks also pass: formatting, lint, unused-code checks, GraphQL validation, type checking, and 15 tests across two files.

    This is validation of the native child-work lookup fix, not a claim that the patch changes live child-event routing in the parent timeline. I have not deployed the patched binary or performed an end-to-end UI check.

    Posting here rather than creating a duplicate issue. Thanks for the existing fix in #31316.

  2. HandleCoding commented on Nov 13, 2026

    @HandleCoding

    Follow-up on live tool-event ownership: the transcript lookup fix in #31316 does not change the parent timeline's live projection. In the current adapter, a child tool frame carried in the root ACP session is projected as parent activity even when its SDK tool ID identifies the child trajectory.

    I have now implemented an opt-in routing fix locally as a separate follow-up: associate native child trajectories with their batch using the launch receipt, route tool starts/progress/content into that batch's read-only thread, buffer frames that arrive before the receipt, and retain ownership across parent turns. The synthetic regression covers multiple batches, nested children, conflicting receipts, late updates, client-file read completion, and streamed output. Unmatched activity remains visible with an explicit attribution warning rather than being discarded. Routing IDs are retained before truncating long receipts for display.

    Validation: all changed-file checks pass, including type checking of 14 affected packages and 70 focused tests; another 179 generic ACP, ACP Registry and Kiro regression tests pass. This is adapter-level validation with synthetic fixtures, not an end-to-end deployed UI claim.

    Posting the distinction here because the reported empty child view and the live parent-timeline tool routing have separate causes.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions