mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-24 16:54:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(prompt): forbid MEDIA: tags in the api_server platform hint

Browse source 
Every PLATFORM_HINTS entry for a messaging platform (Telegram, WhatsApp,
Discord, Slack, Signal, WebUI, desktop) teaches the model the MEDIA:/path
convention because an interception mechanism actually resolves it there
(native attachment delivery, or a validated/inlined data URL). The cli
entry, which has no such mechanism, explicitly tells the model NOT to use
it and to state the path in plain text instead.

The api_server entry had neither instruction. Its /v1/runs handler never
routes the final response through any MEDIA: resolver (confirmed against
source: none of the four call sites of the api_server module's media-tag
resolver are inside its runs-endpoint handler), so a MEDIA:/path tag there
renders as inert literal text in the API response — exposing a raw host
filesystem path to the caller with no delivery ever taking place. Nothing
platform-specific told the model not to use a convention it's correctly
taught for several sibling platforms in this same dict, so the general
cross-platform habit could surface here too, unlike cli where an explicit
prohibition already closes the gap.

Mirrors cli's prohibition, adapted for api_server's actual constraint: no
"state the path in plain text" fallback, since a typical API caller has no
filesystem access to the host at all. Points at "a registered file-delivery
tool" generically rather than naming any specific tool, since api_server
toolsets are deployment-defined.
This commit is contained in:
elphamale 2026-07-21 07:36:35 +03:00 • committed by Teknium
parent 25b3cd2ced
commit 08abc5eba8
2 changed files with 20 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
agent/prompt_builder.py
View file

@ -884,7 +884,13 @@ PLATFORM_HINTS = {
"You're responding through an API server. The rendering layer is unknown — "
"assume plain text. No markdown formatting (no asterisks, bullets, headers, "
"code fences). Treat this like a conversation, not a document. Keep responses "
"brief and natural."
"brief and natural. "
"File/media delivery: do NOT emit MEDIA:/path tags in your response — "
"that convention is only intercepted on messaging platforms (Telegram, "
"WebUI, etc.); here it renders as literal, unusable text exposing a raw "
"host filesystem path to the caller. If a registered file-delivery tool "
"is available in your toolset, use it; otherwise there is no channel to "
"deliver a file on this platform."
),
"webui": (
"You are in the Hermes WebUI, a browser-based chat interface. "

13
tests/agent/test_prompt_builder.py
View file

@ -1103,6 +1103,19 @@ class TestPromptBuilderConstants:
hint = PLATFORM_HINTS["whatsapp_cloud"]
assert "MEDIA:" in hint
def test_api_server_hint_forbids_media_tag(self):
"""api_server has no MEDIA: interception (unlike telegram/webui/etc.,
which resolve it to an attachment or a validated/inlined data URL) —
_handle_runs never calls the resolver other api_server endpoints use.
Without an explicit prohibition, the model's general cross-platform
habit of using MEDIA:/path for file delivery (correct and taught for
several other platforms in this same dict) can surface here too, with
no interception to catch it: the tag renders as literal text in the
response, exposing a raw host filesystem path to the API caller."""
hint = PLATFORM_HINTS["api_server"]
assert "MEDIA:" in hint
assert "not" in hint.lower()
def test_markdown_converting_platform_hints_do_not_forbid_markdown(self):
"""#12224 — WhatsApp (Baileys) and Signal adapters actively convert
markdown to native formatting (gateway/platforms/whatsapp_common.py