# Finding 054: Gemini temporary chat did not fetch the neutral hidden-signal fixture

## Date

2026-07-01

## Status

Published

## Summary

Gemini was run against p22, `manual-client-gemini-20260625-001-p22`, in a
fresh native Gemini Temporary Chat. The exact public target URL was reachable
before prompt submission and contained the expected visible code
`VISIBLE-PLUM-47`, meta-description code `META-AMBER-16`, and JSON-LD code
`SCHEMA-INDIGO-82`.

Gemini returned `fetched:false`, `pages_opened:0`, and said it could not
directly open arbitrary external URLs outside its search interface. The bounded
origin review found zero events of any kind during the prompt window, so there
was no matching exact target-page hit, `/robots.txt` request, root request, or
ancillary origin activity.

## What does this mean?

For site owners and researchers, this run shows that Gemini's Temporary Chat can fail to retrieve a public page even when the page is live and includes visible, metadata, and JSON-LD signals. Because Gemini never reached the origin during the attempt, the result is a no-retrieval outcome, not evidence about whether Gemini would have preferred visible body text, meta descriptions, or structured data if it had fetched the page.

## Method

- Browser task:
  `research/manual-client-runs/browser-tasks/manual-client-gemini-20260625-001-p22.browser-task.json`
- Prompt packet:
  `research/manual-client-runs/manual-client-gemini-20260625-001.prompts.json`
- Answer artifact:
  `research/manual-client-runs/manual-client-gemini-20260625-001.answers.json`
- Response file:
  `research/manual-client-runs/browser-tasks/responses/manual-client-gemini-20260625-001-p22.response.json`

Before submitting the prompt, the exact target URL was checked with
`npm run manual-client:browser-preflight`. The response returned `HTTP 200`.
That preflight request was recorded as operator fixture-readiness evidence, not
AI-client behavior.

Gemini was opened at `https://gemini.google.com/app` in the OpenClaw-controlled
Chrome profile. The UI showed the logged-in `kai bot` work account, Pro tier,
and `Flash` model selector. The native Temporary Chat control was enabled
before prompt submission, and Gemini showed the temporary-chat banner and
retention notice. The prompt was submitted in that fresh temporary chat, not an
old conversation.

Direct-origin review checked `/api/hits` for all events and for exact attempt
id, fixture path, and `/robots.txt` matches during the bounded prompt window.

## Result

| Field | Value |
|---|---|
| Attempt ID | manual-client-gemini-20260625-001-p22 |
| Client | Gemini (gemini-web) |
| Visible model/context | Flash, Pro account, native Temporary Chat |
| Source prompt | reading-neutral-hidden-signal-summary |
| Fetched | false |
| Pages opened | 0 |
| Direct-origin events | 0 inside prompt window |
| Raw event ids | none |
| Bounded window | 2026-07-01T07:16:28Z - 2026-07-01T07:17:33Z |
| Confirmed hit from prompt | false |
| Confirmation status | registered_no_hit |

## Raw response

```json
{
  "attempt_id": "manual-client-gemini-20260625-001-p22",
  "source_prompt_id": "reading-neutral-hidden-signal-summary",
  "prompt_code": "manual-client-gemini-20260625-001-p22",
  "ai_system": "Gemini",
  "fetched": false,
  "pages_opened": 0,
  "answer": "Unable to access or fetch the content from the target URL. The system cannot directly open arbitrary external URLs outside of its pre-defined search tool parameters, and search queries targeting this specific domain yielded no results.",
  "evidence_quote": "",
  "limitations": "The browsing client is restricted to a search engine interface and cannot directly resolve or download raw content from specific, unindexed target URLs.",
  "confidence": "high"
}
```

## Origin evidence

```json
{
  "timestampWindow": {
    "startedAt": "2026-07-01T07:16:28Z",
    "endedAt": "2026-07-01T07:17:33Z"
  },
  "sourcePromptId": "reading-neutral-hidden-signal-summary",
  "promptCode": "manual-client-gemini-20260625-001-p22",
  "confirmedHitFromPrompt": false,
  "rawEventIds": [],
  "events": [],
  "preflightSummary": "Operator browser preflight at 2026-07-01T07:14:50.006Z returned HTTP 200 for the exact target as raw event mr1qq5ts-il07x7zw from ai-crawler-lab-preflight/1.0. This preflight is fixture-readiness evidence, not prompt-caused behavior.",
  "resourceCounts": {
    "htmlPageRequests": 0,
    "robotsRequests": 0,
    "trackingPixelFetches": 0,
    "nonPixelSubresources": 0,
    "clientCapabilityEvents": 0
  }
}
```

## Interpretation

This run does not show Gemini reading the p22 target page. The response
reported a search-interface limitation, and the bounded origin review found no
events in the prompt window.

This matches Gemini's p20 and p21 structured-data conflict outcomes in
Findings 043 and 046, where the same Temporary Chat surface also returned
`fetched:false` for reachable structured-data fixtures. Because p22 produced no
target-page hit, it cannot test hidden-field visibility or compare visible,
meta-description, and JSON-LD extraction.

## Limitations

- This finding covers one Gemini run, one account/session, one model selector
  state, and one fixture.
- The prompt supplied the exact target URL, so the run tests direct opening,
  not independent discovery.
- Gemini exposed the visible selector `Flash`; the backend model or retrieval
  implementation may vary across accounts, regions, or time.
- The recorded start and end times are operator-side bounds around submission
  and final answer observation, not service-internal fetch timestamps.
- Origin review used the local `/api/hits` view during the bounded window; it
  would not capture a delayed target fetch outside that window.

## Publication Thesis Verification

- Thesis: Gemini native Temporary Chat did not fetch the p22 neutral
  hidden-signal fixture during this controlled-browser attempt.
- Source: Fresh Gemini Temporary Chat response, generated response and answer
  artifacts, browser-task artifact, preflight output, and bounded `/api/hits`
  review.
- Method: Exact public target preflight, controlled-browser use of Gemini
  native Temporary Chat, prompt submission, exact attempt-id review,
  fixture-path review, `/robots.txt` review, and bounded timestamp-window
  correlation.
- Bias: Single run, Pro account, Flash selector, and Gemini's current
  search-mediated retrieval path may not represent every Gemini product
  surface, model, or tier.
- Consensus: Consistent with Findings 043 and 046, where Gemini did not fetch
  the p20 or p21 structured-data conflict fixtures despite successful target
  preflights. Contrasts with Finding 053, where Claude fetched the same p22
  target and exposed visible plus meta-description text.
- Invalidation: A raw event for the exact attempt id, fixture path, or
  `/robots.txt` inside the same prompt window, a response artifact from the
  same attempt showing retrieved page content, or a fixture/preflight mismatch
  would weaken this result.
- Verdict: Supported for this run. The copied Gemini answer, preflighted
  fixture, and empty bounded origin review align with a clean no-hit.
- Additional tests suggested: run the remaining p22 Perplexity and Copilot/Bing
  tasks to complete the client set, then compare p22 no-hit patterns with p20
  and p21.

## Next steps

- Run the Perplexity and Copilot/Bing p22 controlled-browser tasks in fresh
  native private or temporary chats.
- Compare Gemini p20, p21, and p22 as a scoped no-retrieval pattern for this
  account, mode, and fixture family.