shell_gpt · Issues· 121 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #801
gpt-5.6 models: every request 400s when functions are enabled (function tools rejected on /v1/chat/completions)
Updated Sep 1, 2026 - #799
docs: hosted API_BASE_URL example (not Ollama / not LiteLLM)
Updated Aug 28, 2026 - #793
Function-calling feature executes LLM-proposed shell commands with no confirmation, unlike the tool's own --shell mode
Updated Aug 5, 2026 - #578
lmstudio ?
Updated Jul 10, 2026 - #776
Multiple tool_calls Aggregation Produces Corrupted Output
Updated Jun 11, 2026 - #769
Integration Proposal: CAJAL — Local Scientific Paper Model for ShellGPT
Updated Jun 4, 2026 - #767
`environment variable` wanted in `.sgptrc`
Updated Apr 24, 2026 - #748
Since update, Issu with function calling
Updated Apr 6, 2026 - #754
feat request: Document secure runtime injection for OPENAI_API_KEY via password manager CLI
Updated Mar 18, 2026 - #741
<think> tag will lead to "IndexError: list index out of range"
Updated Mar 11, 2026 - #751
Suggestion: support `.config/shell_gpt/sgptrc`
Updated Feb 1, 2026 - #682
Add MCP server support
enhancementUpdated Jan 28, 2026 - #651
rebrand OPENAI_API_KEY to something generic if using litellm models
Updated Jan 12, 2026 - #611
Error Messages with local Ollama Models
Updated Dec 25, 2025 - #727
Execute command problem in local models
Updated Oct 11, 2025