Phillip Tarrant
16d79df421
- Detect empty LLM responses (no content, no tool calls) instead of silently treating them as task completion. Retries once without tools before warning the user. - Gate /no_think system message and chat_template_kwargs to Qwen/QwQ models only — sending /no_think to llama3.x caused empty responses. - Add model_profiles config section for per-model overrides (token budget, thinking, temperature, max_tokens) matched by name prefix. Applied at startup and on /model switch. - Update SessionManager on /model switch so session files record the correct model. - Add NDJSON fallback in SSE stream parser for Ollama compatibility. - Improve read_file error to suggest find_files on FileNotFoundError. - Add diagnostic logging for empty streams and empty results. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
108 lines
2.0 KiB
YAML
108 lines
2.0 KiB
YAML
# SneakyCode Configuration
|
|
|
|
llm:
|
|
model: "qwen3.5:latest"
|
|
endpoint: "http://localhost:11434"
|
|
api_path: "/v1/chat/completions"
|
|
temperature: 0.1
|
|
max_tokens: 4096
|
|
timeout: 120
|
|
max_retries: 3
|
|
retry_backoff_base: 1.0
|
|
retry_backoff_max: 30.0
|
|
thinking: false # Disable model thinking/reasoning mode (reduces reasoning-only loops)
|
|
# Extra parameters merged into the API request body (model-specific).
|
|
# Examples:
|
|
# OpenAI: reasoning_effort: "low"
|
|
extra_body: {}
|
|
|
|
agent:
|
|
max_iterations: 25
|
|
max_conversation_tokens: 32000 # Default token budget (overridden by model_profiles)
|
|
workspace_root: "."
|
|
truncation_keep_recent: 10
|
|
truncation_threshold: 0.85
|
|
|
|
# Per-model overrides — matched by longest model name prefix.
|
|
# Unset fields fall through to the defaults above.
|
|
model_profiles:
|
|
llama3:
|
|
max_conversation_tokens: 120000
|
|
thinking: false
|
|
qwen:
|
|
max_conversation_tokens: 32000
|
|
thinking: false
|
|
qwq:
|
|
max_conversation_tokens: 32000
|
|
thinking: true
|
|
|
|
permissions:
|
|
auto_approve:
|
|
- read_file
|
|
- list_dir
|
|
- grep_files
|
|
- find_files
|
|
- finish
|
|
prompt_user:
|
|
- write_file
|
|
- delete_file
|
|
- run_command
|
|
- str_replace
|
|
- patch_apply
|
|
- make_dir
|
|
deny: []
|
|
|
|
tools:
|
|
shell:
|
|
allowed_commands:
|
|
- git
|
|
- python
|
|
- pip
|
|
- pytest
|
|
- ruff
|
|
- ls
|
|
- head
|
|
- tail
|
|
- wc
|
|
- diff
|
|
- grep
|
|
- find
|
|
- echo
|
|
- which
|
|
- jq
|
|
- type
|
|
- file
|
|
denied_commands:
|
|
- rm -rf /
|
|
- sudo
|
|
- curl
|
|
- wget
|
|
max_output_bytes: 65536
|
|
filesystem:
|
|
max_file_size_bytes: 1048576 # 1 MB
|
|
binary_detection: true
|
|
cache:
|
|
enabled: true
|
|
max_entries: 128
|
|
|
|
session:
|
|
session_dir: ".sneakycode/sessions"
|
|
auto_save: true
|
|
max_session_age_hours: 72
|
|
offer_resume: true
|
|
|
|
display:
|
|
show_tool_calls: true
|
|
show_token_usage: true
|
|
stream_output: true
|
|
|
|
debug:
|
|
enabled: false
|
|
log_dir: ".sneakycode/logs"
|
|
max_files: 10
|
|
|
|
skills:
|
|
enabled: true
|
|
directories:
|
|
- ".sneakycode/skills"
|