# NousResearch/hermes-agent · Multimodal content flattening in observed group contexts

## Open now

- 1 issue, 1 PR open on GitHub.
- #47415: \[Bug\]: Telegram group photos sent without an @mention are dropped (observed-context content stringified)
- PR #73661: fix(gateway): attach observed group images to the next addressed turn

A cluster of fixes addressing how multimodal and image content is handled when processing observed group messages, including flattening structured content to text, caching media, and attaching images to the correct turn. A related bug report covers dropped Telegram group photos in observed contexts.

## TL;DR

- 5 member(s): 1 open issue(s), 0 closed issue(s), 1 open PR(s), 0 merged PR(s), 3 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.40`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #47415: \[Bug\]: Telegram group photos sent without an @mention are dropped (observed-context content stringified)

## Prior & competing PRs

- **#47416: fix(gateway): flatten observed-group multimodal content to text**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#47427`, `#47584`
- **#47427: fix(gateway): flatten multimodal content to text in observed group context**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#47416`, `#47415`
- **#47584: fix(gateway): flatten multimodal content to text in observed group context**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#47416`
- **#73661: fix(gateway): attach observed group images to the next addressed turn**. open
  - maintainer direction: category `wontfix_bydesign`; implication `wontfix`; refs `9ceac1896`, `6b81590c5`, `fa3b06b03`
  - files: `gateway/observed_images.py`, `gateway/run.py`, `gateway/run_inbound.py`, `gateway/run_turn.py`, `plugins/platforms/telegram/adapter.py`, `plugins/platforms/telegram/telegram_observed_images.py`, `tests/gateway/test_observed_group_image_attachment.py`, `tests/gateway/test_queued_observed_image_attachment.py`, `tests/gateway/test_telegram_group_gating.py`

## Fix status

- No merged fix on record.
- Subsystem: `gateway`