mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-10 03:22:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8
7756 commits 1000 branches 12 tags 3.7 GiB
Commit graph

3 commits

Author SHA1 Message Date
Teknium
d0aad4b021 fix(computer-use): harden image-rejection fallback + AUTHOR_MAP 
Follow-up to #15328's vision-unsupported retry branch in run_agent.py.

_strip_images_from_messages() previously deleted any message whose content
was entirely images. That's fine for synthetic user messages injected for
attachment delivery, but it breaks providers for tool-role messages — the
paired tool_call_id on the preceding assistant message ends up unmatched,
which OpenAI-compatible APIs reject with HTTP 400.

Fix: tool-role messages whose content becomes empty are replaced with a
plaintext placeholder that preserves the tool_call_id linkage. Only
non-tool messages are dropped. Added 10 tests covering the role-alternation
invariants + image-type coverage.

Image-rejection detector: expanded phrase list (image content not
supported / multimodal input / vision input / model does not support
image) and gated on 4xx status so transient 5xx errors never get
misinterpreted as 'server said no to images'. Detection is documented as
best-effort English phrase matching.

AUTHOR_MAP: mapped 3820588+ddupont808@users.noreply.github.com to
ddupont808 so release notes attribute the salvage correctly.
 2026-05-08 11:07:38 -07:00
Teknium
e63364b8df
revert: computer-use cua-driver (PR #16919) (#16927) 
Reverts PR #16919 (commits dad10a78d, 413ee1a28, b4a8031b2, afb958829)
which was merged prematurely. Restoring the pre-merge state so #14817
and #15328 can be revisited as standing PRs.

Reverted commits:
- afb958829 fix(computer-use): harden image-rejection fallback + AUTHOR_MAP
- b4a8031b2 fix(computer-use): unwrap _multimodal tool results
- 413ee1a28 feat(computer-use): background focus-safe backend
- dad10a78d feat(computer-use): cua-driver backend, universal any-model schema

Co-authored-by: teknium1 <teknium@users.noreply.github.com>
 2026-04-28 01:57:21 -07:00
Teknium
afb9588298 fix(computer-use): harden image-rejection fallback + AUTHOR_MAP 
Follow-up to #15328's vision-unsupported retry branch in run_agent.py.

_strip_images_from_messages() previously deleted any message whose content
was entirely images. That's fine for synthetic user messages injected for
attachment delivery, but it breaks providers for tool-role messages — the
paired tool_call_id on the preceding assistant message ends up unmatched,
which OpenAI-compatible APIs reject with HTTP 400.

Fix: tool-role messages whose content becomes empty are replaced with a
plaintext placeholder that preserves the tool_call_id linkage. Only
non-tool messages are dropped. Added 10 tests covering the role-alternation
invariants + image-type coverage.

Image-rejection detector: expanded phrase list (image content not
supported / multimodal input / vision input / model does not support
image) and gated on 4xx status so transient 5xx errors never get
misinterpreted as 'server said no to images'. Detection is documented as
best-effort English phrase matching.

AUTHOR_MAP: mapped 3820588+ddupont808@users.noreply.github.com to
ddupont808 so release notes attribute the salvage correctly.
 2026-04-28 01:46:36 -07:00