PyPI 1.0.8 is broken with current python-fastllm (ssage prints "Connecting..." then exits silently); fix #96 is on main but not released
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 48/100
Research direction
Start by inspecting commit 564d013 on main and the versioned package around shell_sage/core.py, then verify how the project publishes to PyPI. Done means a 1.0.9 package is available from PyPI and uv tool install shell-sage or pip install shell-sage produces a streamed answer with python-fastllm 0.0.40.
Written by the indexing model from the issue text.
Description
Bug
Installing shell-sage from PyPI (1.0.8) and running ssage produces no output — just a Connecting... spinner, then exit code 0.
To reproduce
uv tool install shell-sage # resolves to 1.0.8
ssage "Say hello"
Expected: a streamed answer. Actual: ⠋ Connecting... with nothing after it.
Error messages
None — the process exits with code 0 and empty stderr. The failure is silent, which makes it easy to miss.
Root cause
In 1.0.8, get_res in shell_sage/core.py only accumulates chunks that are dicts:
if isinstance(chunk, dict) and 'text' in chunk: _res += chunk['text']
Current python-fastllm (0.0.40) streams Text/Thinking objects instead of plain dicts, so no chunk is ever accumulated, nothing renders, and the process exits 0.
This is already fixed on main (commit 564d013, "fixes #96", using fastllm's StreamAccum) — but no release has been cut since. PyPI still serves 1.0.8 (released 2026-07-20), so everyone installing today gets the broken version. This affects both uv tool install and pip install shell-sage.
I searched the open issues before filing this — none report this bug. #96 (closed) only tracked the code fix itself, which is done; this issue is about that fix never being released.
Workaround
uv tool install --force --from git+https://github.com/AnswerDotAI/shell_sage shell-sage
Request
Please cut a 1.0.9 release so the StreamAccum fix ships to PyPI.
Environment
- macOS, zsh
- shell-sage 1.0.8 (PyPI)
- python-fastllm 0.0.40
- Dominant language
- Jupyter Notebook
- Stars
- 409
- Forks
- 45
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from AnswerDotAI/shell_sage
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
AnswerDotAI/shell_sage#97 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
AnswerDotAI/shell_sage#79 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
AnswerDotAI/shell_sage#103 ·
-
Difficulty 3/5 1-2 days Newbie friendliness 55/100
AnswerDotAI/shell_sage#94 ·
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
AnswerDotAI/shell_sage#77 · 1 comment ·
All issues in AnswerDotAI/shell_sage
Similar issues
-
Help-Wanted Needs-Triage Package-Request
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
microsoft/winget-pkgs#438680 ·
-
package-update
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
oSoWoSo/vOid_Community_repOsitory#148 · 1 comment ·
-
Difficulty 1/5 Under an hour Newbie friendliness 70/100
-
OS:Windows
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
Difficulty 1/5 Under an hour Newbie friendliness 68/100