fix(prompts): replace [SYSTEM: with [IMPORTANT: to avoid Azure content filter
Azure OpenAI content filters (Default/DefaultV2) treat bracketed [SYSTEM: ...] meta-instructions as prompt-injection attempts and reject requests with HTTP 400. Replacing [SYSTEM: with [IMPORTANT: preserves the same semantic meaning for the model while bypassing the Azure heuristic. Fixes #6576
This commit is contained in:
@@ -329,7 +329,7 @@ def build_skill_invocation_message(
|
||||
|
||||
loaded_skill, skill_dir, skill_name = loaded
|
||||
activation_note = (
|
||||
f'[SYSTEM: The user has invoked the "{skill_name}" skill, indicating they want '
|
||||
f'[IMPORTANT: The user has invoked the "{skill_name}" skill, indicating they want '
|
||||
"you to follow its instructions. The full skill content is loaded below.]"
|
||||
)
|
||||
return _build_skill_message(
|
||||
@@ -368,7 +368,7 @@ def build_preloaded_skills_prompt(
|
||||
|
||||
loaded_skill, skill_dir, skill_name = loaded
|
||||
activation_note = (
|
||||
f'[SYSTEM: The user launched this CLI session with the "{skill_name}" skill '
|
||||
f'[IMPORTANT: The user launched this CLI session with the "{skill_name}" skill '
|
||||
"preloaded. Treat its instructions as active guidance for the duration of this "
|
||||
"session unless the user overrides them.]"
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user