jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-10-24 07:42:21 +02:00
Code Issues Packages Projects Releases Wiki Activity
1,659 Commits 24 Branches 0 Tags
edd5ea36adad0f283e93c3bb2e84920094de379c
Commit Graph
13 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Dividesbyzer0 f5200ec45b fix(cookbook): treat local Windows as Windows for serve commands (#3975) 
* fix(cookbook): prefer native llama-server on local Windows

* fix(cookbook): harden local llama-server launch commands

* fix(cookbook): build serve commands for selected target
 2026-06-26 13:13:01 +01:00
Dividesbyzer0 2e16394b41 fix(agent): parse misfenced read_file calls (#4799) 2026-06-23 23:20:13 +02:00
Dividesbyzer0 2e9f641c2c fix(windows): detect installed CUDA toolkit on launch (#2639) 2026-06-15 20:26:07 +09:00
Dividesbyzer0 627a52ac44 fix(cookbook): shim Windows Store python3 alias (#2610) 2026-06-15 20:25:30 +09:00
Dividesbyzer0 b28aa1f2c4 fix(cookbook): allow local Windows Diffusers serving (#4077) 2026-06-15 15:21:01 +09:00
Dividesbyzer0 33c26bab88 fix(agent): parse raw json web search calls (#4088) 2026-06-15 15:19:38 +09:00
Dividesbyzer0 589fcd314a fix(image): patch realesrgan torchvision compatibility (#4110) 2026-06-15 15:16:41 +09:00
Dividesbyzer0 8cff1f87ee fix(cookbook): stop local Windows process trees 
Track the inner Bash runner PID for local Windows Cookbook tasks and stop the full child process tree during cleanup.
 2026-06-15 15:12:48 +09:00
Dividesbyzer0 ec4f91afdd fix(cookbook): normalize llama-cpp-python cache types 
Map llama-cpp-python --type_k/--type_v cache names to integer enum values after serve-command validation while preserving native llama-server flags.
 2026-06-15 15:12:18 +09:00
Dividesbyzer0 7f571c8f7e fix(agent): keep gpt-oss on text tool mode 
Treat gpt-oss local OpenAI-compatible models as text/fenced-tool models unless the endpoint explicitly declares native tool support.
 2026-06-15 15:11:52 +09:00
Dividesbyzer0 ece6cebc03 fix(cookbook): create bin dir before llama-server link 
Ensure ~/bin exists before the llama.cpp accelerated build script creates the llama-server link.
 2026-06-15 15:03:55 +09:00
Dividesbyzer0 a07fe35936 fix(agent): honor explicit web search requests 
Promote explicit web-search phrasing to tool use and keep web_search/web_fetch available for that turn even when the stale web toggle is false.
 2026-06-15 15:02:10 +09:00
Dividesbyzer0andClaude Opus 4.8 5dff35ba03 fix(cookbook): don't 500 the packages panel when an optional package crashes on import (#2618) 
list_packages() probes each optional package with importlib.import_module() but
only caught ImportError / PackageNotFoundError. A package that is installed yet
raises a different exception on import took down the whole panel with a 500,
surfaced in the UI as "Error loading packages: Unexpected token 'I', ...".

Concrete Windows case: a CUDA build of llama-cpp-python runs
os.add_dll_directory(r"...\CUDA\v12.3\bin") at import and raises FileNotFoundError
when that toolkit dir is absent. Catch any exception during the import probe and
report the package as not-installed instead of failing the entire request.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-07 18:14:43 +02:00