# Finding 056: Copilot Temporary chat did not fetch the neutral hidden-signal target

## Date

2026-07-01

## Status

Published

## Summary

Copilot/Bing was run against p22,
`manual-client-copilot-bing-20260626-001-p22`, in a fresh Copilot 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`.

Copilot returned `fetched:false`, `pages_opened:0`, and said the client could
not open or retrieve the target URL. The bounded origin review found no
matching direct-origin event for the exact attempt id, fixture path,
`/robots.txt`, or `/` during the prompt window, so this run is a bounded
clean no-hit.

## What does this mean?

For site owners and researchers, this run shows that Copilot can decline to retrieve a provided page even when the page is publicly reachable and the prompt asks for a neutral site-quality summary. In that case, the assistant answer is not evidence about which visible, metadata, or structured-data signals Copilot can read, because the site logs showed no prompt-window request for the page.

## Method

- Browser task:
  `research/manual-client-runs/browser-tasks/manual-client-copilot-bing-20260626-001-p22.browser-task.json`
- Prompt packet:
  `research/manual-client-runs/manual-client-copilot-bing-20260626-001.prompts.json`
- Answer artifact:
  `research/manual-client-runs/manual-client-copilot-bing-20260626-001.answers.json`
- Response file:
  `research/manual-client-runs/browser-tasks/responses/manual-client-copilot-bing-20260626-001-p22.response.json`

Before submitting the prompt, the exact target URL was checked with an
operator preflight request. The response returned `HTTP 200` and exposed
`VISIBLE-PLUM-47`, `META-AMBER-16`, and `SCHEMA-INDIGO-82`. That preflight is
fixture-readiness evidence, not AI-client behavior.

Copilot was opened from `https://www.bing.com/chat` in the OpenClaw-controlled
Chrome profile, which redirected to `https://copilot.microsoft.com/`. The UI
showed the logged-in `kai` account, Free Plan, native `Temporary` control, and
`Smart` response mode before prompt submission. The prompt was submitted in a
fresh Copilot chat at `/chats/BppmzioKp8APt1BC8LcRL`, not an old
conversation.

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

## Result

| Field | Value |
|---|---|
| Attempt ID | manual-client-copilot-bing-20260626-001-p22 |
| Client | Copilot/Bing (copilot-bing-web) |
| Visible model/context | kai Free Plan, Temporary chat, Smart response mode |
| Source prompt | reading-neutral-hidden-signal-summary |
| Fetched | false |
| Pages opened | 0 |
| Direct target-page events | 0 inside prompt window |
| Prompt-window Copilot/Bing origin events | 0 |
| Raw event ids | none |
| Bounded window | 2026-07-01T09:15:02Z - 2026-07-01T09:17:32Z |
| Confirmed target hit from prompt | false |
| Confirmation status | registered_no_hit |

## Raw response

```json
{
  "attempt_id": "manual-client-copilot-bing-20260626-001-p22",
  "source_prompt_id": "reading-neutral-hidden-signal-summary",
  "prompt_code": "manual-client-copilot-bing-20260626-001-p22",
  "ai_system": "Copilot/Bing",
  "model_id": "copilot-bing-manual",
  "fetched": false,
  "pages_opened": 0,
  "answer": "This client cannot open or retrieve the target URL.",
  "evidence_quote": "No page content accessible from this environment.",
  "limitations": "Browsing, retrieval, and URL opening are not supported in this client.",
  "confidence": "0.78"
}
```

## Origin evidence

```json
{
  "timestampWindow": {
    "startedAt": "2026-07-01T09:15:02Z",
    "endedAt": "2026-07-01T09:17:32Z"
  },
  "sourcePromptId": "reading-neutral-hidden-signal-summary",
  "promptCode": "manual-client-copilot-bing-20260626-001-p22",
  "confirmedHitFromPrompt": false,
  "rawEventIds": [],
  "events": [],
  "resourceCounts": {
    "targetPageRequests": 0,
    "robotsRequests": 0,
    "rootRequests": 0,
    "trackingPixelFetches": 0,
    "nonPixelSubresources": 0,
    "clientCapabilityEvents": 0
  }
}
```

## Interpretation

This run does not show Copilot reading the p22 target page. The response
reported no retrieval, and the bounded origin review found no exact attempt-id
request, fixture-path request, `/robots.txt` request, or root request during
the prompt window.

Because there was no target-page request, the result cannot say whether
Copilot would expose the visible code, meta-description code, or JSON-LD code
after a successful fetch. It only supports a no-retrieval conclusion for this
account, mode, prompt, and time window.

## Limitations

- This finding covers one Copilot run, one account/session, one Temporary chat,
  and one fixture.
- The prompt supplied the exact target URL, so the run tests direct opening,
  not independent discovery.
- The visible UI showed `Smart` response mode but not a precise underlying
  model version.
- 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: Copilot Temporary chat did not fetch the p22 neutral hidden-signal
  target page during this controlled-browser attempt.
- Source: Fresh Copilot 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 a fresh
  Copilot Temporary chat, prompt submission, exact attempt-id review,
  fixture-path review, `/robots.txt` review, root-path review, and bounded
  timestamp-window correlation.
- Bias: Single run, Free Plan account, Smart response mode, and Copilot's
  retrieval implementation may vary by account, region, product surface, or
  time.
- Consensus: Consistent with Findings 045 and 050, where Copilot also reported
  no successful target retrieval for structured-data conflict prompts. It also
  fits the broader p22 no-retrieval pattern for ChatGPT and Gemini, while
  contrasting with Finding 053 where Claude fetched the same target.
- Invalidation: A raw event for the exact attempt id or fixture path 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 Copilot answer and empty
  prompt-window origin review align with a bounded no-hit.
- Additional tests suggested: compare the complete p22 set with p20 and p21,
  separating confirmed-hit hidden-signal evidence from no-retrieval outcomes.

## Next steps

- Publish a scoped p22 comparison across ChatGPT, Claude, Gemini, Perplexity,
  and Copilot/Bing.
- Compare Copilot p20, p21, and p22 as a no-retrieval pattern for this
  account, mode, and fixture family.