fix(chat): add WebUI surface context to agent turns

[AJV20]

Thinking Path

• Hermes WebUI runs browser-originated turns separately from Telegram and other messaging gateways.
• Messaging gateways can carry platform/channel context that browser sessions do not naturally expose.
• A small ephemeral WebUI surface note gives the agent the right execution context without persisting internal metadata into the visible transcript.
• This narrows the “WebUI feels like it has less context” gap while preserving current session/history storage behavior.

What Changed

• Adds a WebUI surface-context block to the agent ephemeral system prompt.
• Includes non-secret fields: source, session id, active profile, and workspace.
• Explicitly tells the agent that the browser chat is not the same live transcript as Telegram/Discord/Slack, and to use durable memory/sessions/tools for cross-surface recall.
• Adds regression coverage for the prompt content and empty-field handling.
• Updates CHANGELOG.md.

Why It Matters

WebUI chat turns now get the same kind of surface awareness that users expect from messaging-backed Hermes sessions, without assuming that Telegram transcript state is present in the browser session.

Verification

• python -m pytest tests/test_webui_surface_context.py -q -o 'addopts='
• python -m py_compile api/streaming.py
• git diff --check

Risks / Follow-ups

• This is intentionally metadata-only and ephemeral; it does not import messaging transcripts into WebUI.
• A larger follow-up could expose an explicit “search prior messaging sessions” affordance if maintainers want cross-surface recall to be user-visible.

Model Used

OpenAI gpt-5.5 via Hermes Agent, with repository tools and targeted pytest/py_compile verification.

[nesquena-hermes]

Phase 0 quick note — agent review queued, holding for cron tick

Thanks @AJV20 for the diagnostics/surface-context/dashboard-link burst. These three (#2523 + #2524 + #2533) are well-scoped and CI-eligible, but they're <6 hours old from a first-time contributor with several other in-flight PRs (#2527 + #2526 are getting maintainer-review treatment separately).

For this sweep I'm holding all three out of the batch and letting the agent-review cron pick them up on its next tick — that's a structured per-PR diff/test/integration read with a recap comment, after which the parallel reviewer typically follows. Once both have landed, they'll be eligible for the next batch.

Nothing wrong with the PRs themselves at a glance — the burst pattern just means "scrutiny stays per-PR, not 'batch everything because they're all small'". Will revisit on the next sweep.

[AJV20]

Superseded by #2547, which includes the WebUI surface-context fix on a fresh branch from current master along with related context-parity changes.