Skip to content

[Bug]: Antigravity 1.5 transient mid-turn HTTP 404 (NOT_FOUND) falls through to generic "Provider error" without retry #39864

Closed

Description

@heartwerktech

Before submitting

Area

apps/server

Steps to reproduce

  1. Start a multi-step Antigravity thread on Gemini 4 Neon (High) (MODEL_PLACEHOLDER_M532) using Antigravity ACP runtime 1.5.13.
  2. Run a long agentic turn with multiple tool calls.
  3. Intermittently (mid-turn, after 10+ successful streamGenerateContent calls on the same session), Google's daily-cloudcode-pa ESF edge returns a transient HTTP 404 Not Found (NOT_FOUND: Requested entity was not found.).

Expected behavior

  1. AntigravityTurnOutcome.ts should parse Antigravity 1.5's STATUS (code NNN): message error step shape (similar to fix(server): Antigravity 1.5 quota errors resume at the reset #39196) instead of falling through to the generic "Antigravity stopped this turn because of an error." message.
  2. When a 404 NOT_FOUND happens mid-turn (i.e. after prior steps in the session already succeeded on this model, distinguishing it from permanent unentitled/invalid-model 404s like [Bug]: Antigravity provider exposes Unavailable models (Neon/Orchestrator), causing false quota crashes #39438), T3 Code should ideally treat it as retryable / perform a bounded auto-resume (similar to fix(server): Antigravity resumes a turn after an empty model reply #39123) rather than aborting the turn — since agy itself does not retry HTTP 404 ([Bug]: shouldReplaceUserErrorMessage & (*ACPServer).sendTurnStepUpdates mask 4xx/502 errors as generic '⚠ Agent execution terminated due to error.' and skip retry on transient 404 google-antigravity/antigravity-cli#1485).

Actual behavior

The assistant message emits:

⚠ NOT_FOUND (code 404): Requested entity was not found.

and T3 Code terminates the turn with:

Provider error
Antigravity stopped this turn because of an error.

In apps/server/src/provider/acp/AntigravityTurnOutcome.ts:

  • API_ERROR (/Error (\d{3}), Message: (.+?), Status: ([A-Z_]+)/s) does not match Antigravity 1.5's NOT_FOUND (code 404): Requested entity was not found. payload, so apiError is null and it falls through to the generic non-retryable provider_error.
  • Even with fix(server): Antigravity 1.5 quota errors resume at the reset #39196's STATUS_ERROR parser, retryable: rateLimited || Number(httpStatus) >= 500 would still leave transient mid-turn 404s non-retryable.

Sending continue immediately resumes the exact same session and succeeds for dozens more steps.

Impact

Major degradation or frequent failure

Version or commit

0.1.12-nightly.20261120.4994 (Antigravity ACP runtime 1.5.13)

Environment

macOS 26.3 (arm64), T3 Code Nightly desktop app, Antigravity provider (gemini-4-neon, High)

Additional context (from local conversations/<id>.db, step_type = 17)

Occurred twice in one thread (idx = 18 at 2026-11-20T19:27:40Z and idx = 70 at 2026-11-20T19:30:29Z), both after 10+ successful calls in the same turn:

short_error: NOT_FOUND (code 404): Requested entity was not found.
full_error:
  HTTP 404 Not Found
  TraceID: 0x5613be76c0af1656 (and 0x7e32de96a1cd3f0c)
  Headers: {"Content-Length":["114"],"Content-Type":["text/event-stream"],"Server":["ESF"],...}
  {"error":{"code":404,"message":"Requested entity was not found.","status":"NOT_FOUND"}}
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