Skip to content

fix: add Gemini -latest aliases so a new API key can actually run the pipeline #379

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

Open
ayo0la wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: add Gemini -latest aliases so a new API key can actually run the pipeline #379

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 3 additions & 1 deletion .env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
# Default model to use (must exist in providers.json).
# Ollama examples: "gemma4:latest", "qwen3:4b", "mistral:7b"
# Gemini examples: "gemini-2.5-pro", "gemini-2.5-flash"
# Gemini examples: "gemini-flash-latest", "gemini-flash-lite-latest"
# (prefer the -latest aliases; dated pins such as gemini-2.5-flash are
# retired for new API keys and return a 404)
DEFAULT_MODEL=gemma4:latest

# API keys — only needed for providers whose api_key_env is set in providers.json.
Expand Down
5 changes: 3 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,7 +186,7 @@ $ cp .env.example .env

| Variable | Values | Description |
| ---------------- | ------------------------------------------- | ---------------------------------------------------------------------- |
| `DEFAULT_MODEL` | for example `gemma4:latest` or `gemini-2.5-pro` | Model to use; must exist in `providers.json` — the provider is inferred from which provider lists it. Defaults to `default_model` in `providers.json`. |
| `DEFAULT_MODEL` | for example `gemma4:latest` or `gemini-flash-latest` | Model to use; must exist in `providers.json` — the provider is inferred from which provider lists it. Defaults to `default_model` in `providers.json`. |
| `GEMINI_API_KEY` | string | Required when using a Gemini model. |
| `GITHUB_TOKEN` | optional | Inherits from your shell environment, improves GitHub API rate limits. |

Expand Down Expand Up @@ -340,7 +340,8 @@ role directory instead.

### Gemini

- Set `DEFAULT_MODEL` to a Gemini model listed in `providers.json`, for example `gemini-2.0-flash`
- Set `DEFAULT_MODEL` to a Gemini model listed in `providers.json`, for example `gemini-flash-latest`
- Prefer the `-latest` aliases over dated pins. Individual versions are retired over time, and a retired version returns `404 ... is no longer available to new users` on a newly created key
- Provide `GEMINI_API_KEY`
- The same `models.OpenAICompatibleProvider` wrapper is used, pointed at Gemini's OpenAI-compatible endpoint

Expand Down
4 changes: 3 additions & 1 deletion providers.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,9 @@
"gemini-2.0-flash-lite": { "temperature": 0.1, "top_p": 0.9 },
"gemini-2.5-flash": { "temperature": 0.1, "top_p": 0.9 },
"gemini-2.5-flash-lite": { "temperature": 0.1, "top_p": 0.9 },
"gemini-2.5-pro": { "temperature": 0.1, "top_p": 0.9 }
"gemini-2.5-pro": { "temperature": 0.1, "top_p": 0.9 },
"gemini-flash-latest": { "temperature": 0.1, "top_p": 0.9 },
"gemini-flash-lite-latest": { "temperature": 0.1, "top_p": 0.9 }
}
},
"anthropic": {
Expand Down