mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(prompt): add Google model operational guidance for Gemini and Gemma (#4641)

Browse source 
Adapted from OpenCode's gemini.txt. Gemini and Gemma models now get
structured operational directives alongside tool-use enforcement:
absolute paths, verify-before-edit, dependency checks, conciseness,
parallel tool calls, non-interactive flags, autonomous execution.

Based on PR #4026, extended to cover Gemma models.
This commit is contained in:
Teknium 2026-04-02 11:52:34 -07:00 • committed by GitHub
parent 3186668799
commit d89cc7fec1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 29 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

24
agent/prompt_builder.py
View file

@ -187,7 +187,29 @@ TOOL_USE_ENFORCEMENT_GUIDANCE = (
# Model name substrings that trigger tool-use enforcement guidance.
# Add new patterns here when a model family needs explicit steering.
TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex")
TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma")
# Gemini/Gemma-specific operational guidance, adapted from OpenCode's gemini.txt.
# Injected alongside TOOL_USE_ENFORCEMENT_GUIDANCE when the model is Gemini or Gemma.
GOOGLE_MODEL_OPERATIONAL_GUIDANCE = (
"# Google model operational directives\n"
"Follow these operational rules strictly:\n"
"- **Absolute paths:** Always construct and use absolute file paths for all "
"file system operations. Combine the project root with relative paths.\n"
"- **Verify first:** Use read_file/search_files to check file contents and "
"project structure before making changes. Never guess at file contents.\n"
"- **Dependency checks:** Never assume a library is available. Check "
"package.json, requirements.txt, Cargo.toml, etc. before importing.\n"
"- **Conciseness:** Keep explanatory text brief — a few sentences, not "
"paragraphs. Focus on actions and results over narration.\n"
"- **Parallel tool calls:** When you need to perform multiple independent "
"operations (e.g. reading several files), make all the tool calls in a "
"single response rather than sequentially.\n"
"- **Non-interactive commands:** Use flags like -y, --yes, --non-interactive "
"to prevent CLI tools from hanging on prompts.\n"
"- **Keep going:** Work autonomously until the task is fully resolved. "
"Don't stop with a plan — execute it.\n"
)
# Model name substrings that should use the 'developer' role instead of
# 'system' for the system prompt. OpenAI's newer models (GPT-5, Codex)