Skip to content

Fix Prompt Optimization Ollama sandbox access #247

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Copilot wants to merge 4 commits into
base: main
Choose a base branch
from
+28 −6
Draft

Fix Prompt Optimization Ollama sandbox access #247

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3bc20c5
Initial plan
Copilot Sep 1, 2026
ca101bf
Fix prompt optimization Ollama sandbox access
Copilot Sep 1, 2026
8bc37ca
Restart Ollama with sandbox binding
Copilot Sep 1, 2026
787796a
Wait for Ollama daemon shutdown
Copilot Sep 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 13 additions & 2 deletions .github/workflows/prompt-optimization.lock.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

19 changes: 15 additions & 4 deletions .github/workflows/prompt-optimization.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,18 @@ steps:

- name: Start Ollama
run: |
ollama serve >"$RUNNER_TEMP/ollama.log" 2>&1 &
pkill -x ollama || true
for attempt in {1..30}; do
if ! curl --fail --silent http://127.0.0.1:11434/api/version >/dev/null; then
break
fi
if [ "$attempt" -eq 30 ]; then
echo "Ollama did not stop" >&2
exit 1
fi
sleep 1
done
OLLAMA_HOST=0.0.0.0:11434 ollama serve >"$RUNNER_TEMP/ollama.log" 2>&1 &
for attempt in {1..30}; do
if curl --fail --silent http://127.0.0.1:11434/api/version >/dev/null; then
exit 0
Expand Down Expand Up @@ -95,16 +106,16 @@ steps:
Improve the wizard's shipped scenario-assistant instructions with measured hill climbing. The
workflow has already restored the Ollama cache, downloaded GGUF proxies for both browser models
from Hugging Face, and started an OpenAI-compatible Ollama server on
`http://127.0.0.1:11434/v1`.
`http://host.docker.internal:11434/v1`.

Use the installed `optimize-scenario-prompt` skill and
`scripts/prompt-optimizer.mjs`. Use these options for every evaluation or score command:

```text
--all-models
--eval-url http://127.0.0.1:11434/v1
--eval-url http://host.docker.internal:11434/v1
--eval-model hf.co/bartowski/Qwen2.5-1.5B-Instruct-GGUF:Q4_K_M
--ios-eval-url http://127.0.0.1:11434/v1
--ios-eval-url http://host.docker.internal:11434/v1
--ios-eval-model hf.co/unsloth/SmolLM2-360M-Instruct-GGUF:Q4_K_M
```

Expand Down