BYOK gpt-5.5 --effort xhigh falls back to medium for individual plan

## Summary

When using Copilot CLI with a BYOK/custom provider for `gpt-5.5`, `--effort xhigh` falls back to `medium` if the user is signed in with an individual Copilot plan.

With the same BYOK provider, the same `gpt-5.5` model, and the same command, `xhigh` works as expected when `COPILOT_OFFLINE=true` is set.

## Environment

- Copilot CLI: 1.0.40
- Platform: macOS arm64
- Provider mode: BYOK/custom provider
- Provider wire API: responses
- Model: `gpt-5.5` through a custom provider
- GitHub Copilot plan: individual

Relevant environment variables:

```text
COPILOT_MODEL=gpt-5.5
COPILOT_PROVIDER_BASE_URL=
COPILOT_PROVIDER_API_KEY=
COPILOT_PROVIDER_WIRE_API=responses
```

## Reproduction steps

1. Configure a BYOK/custom provider:

```bash
export COPILOT_MODEL=gpt-5.5
export COPILOT_PROVIDER_BASE_URL=
export COPILOT_PROVIDER_API_KEY=
export COPILOT_PROVIDER_WIRE_API=responses
```

2. Run:

```bash
copilot --effort xhigh --log-level debug --prompt "Reply with exactly: OK" --silent --allow-all-tools
```

3. Check the debug log.

## Actual behavior

Copilot CLI uses the custom provider, but the effective reasoning effort becomes `medium`:

```text
Using custom provider: type=openai, wireApi=responses
"defaultReasoningEffort": "medium"
"reasoning_effort": "medium"
```

The debug log also shows that the GitHub plan context is `individual`:

```text
github_copilotcli_copilotplan=individual
```

## Expected behavior

When `COPILOT_PROVIDER_BASE_URL` is set and inference is routed to a custom provider, `--effort xhigh` should be preserved if the selected provider/model supports it. It should not be downgraded based on the GitHub Copilot account plan.

Expected debug output:

```text
"defaultReasoningEffort": "xhigh"
"reasoning_effort": "xhigh"
```

## Control test

With the same BYOK provider, the same `gpt-5.5` model, and the same command, adding `COPILOT_OFFLINE=true` makes `xhigh` work:

```bash
COPILOT_OFFLINE=true copilot --effort xhigh --log-level debug --prompt "Reply with exactly: OK" --silent --allow-all-tools
```

Debug log:

```text
Running in offline mode. GitHub features are unavailable.
Using custom provider: type=openai, wireApi=responses
"defaultReasoningEffort": "xhigh"
```

## Additional check

With the same BYOK provider, `--effort high` works correctly:

```text
"defaultReasoningEffort": "high"
"reasoning_effort": "high"
```

Reproduce the issue with the listed COPILOT_* variables and the copilot --effort xhigh command, then compare debug output with and without COPILOT_OFFLINE=true. Trace where the individual plan context changes the effective reasoning effort for a custom provider. Done means xhigh remains xhigh for the BYOK gpt-5.5 setup while the existing high-effort behavior still works.

Scritto dal modello di indicizzazione a partire dal testo della issue.