Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
2 changes: 1 addition & 1 deletion .changeset/patch-add-engine-bare-frontmatter-field.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-add-gemini-yolo-flag.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-bump-cli-defaults-2026-02-28.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-bump-cli-versions-2026-04-10.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-bump-gemini-cli-0-37-2.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-bump-gemini-cli-0-39-1.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-drop-cache-name.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-fix-gemini-mcp-config.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-05.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-06.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-07.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-11.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-16.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-17.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-model-inventory-2026-05-21.md

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

2 changes: 1 addition & 1 deletion .changeset/patch-upload-firewall-audit-logs-artifact.md

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

2 changes: 1 addition & 1 deletion .github/aw/github-agentic-workflows.md

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

6 changes: 3 additions & 3 deletions .github/aw/llms.md
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ curl -sf http://api-proxy:10000/reflect | jq '.endpoints[] | select(.configured)
| `openai` / `codex` | 10000 | `http://api-proxy:10000/v1` | `OPENAI_API_KEY` |
| `anthropic` | 10001 | `http://api-proxy:10001/v1` (or no `/v1` for native SDK) | `ANTHROPIC_API_KEY` |
| `copilot` | 10002 | `http://api-proxy:10002/v1` | `COPILOT_GITHUB_TOKEN` |
| `gemini` | 10003 | `http://api-proxy:10003/v1` | `GEMINI_API_KEY` |
| `antigravity` | 10003 | `http://api-proxy:10003/v1` | `ANTIGRAVITY_API_KEY` |

All ports use the OpenAI-compatible API format. The api-proxy injects auth headers automatically — **do not pass raw API keys** to these URLs.

Expand All @@ -34,7 +34,7 @@ All ports use the OpenAI-compatible API format. The api-proxy injects auth heade
{ "provider": "openai", "port": 10000, "configured": true, "models": ["gpt-4o", "o1-mini"], "models_url": "http://api-proxy:10000/v1/models" },
{ "provider": "anthropic", "port": 10001, "configured": true, "models": ["claude-sonnet-4-5"], "models_url": "http://api-proxy:10001/v1/models" },
{ "provider": "copilot", "port": 10002, "configured": true, "models": null, "models_url": "http://api-proxy:10002/models" },
{ "provider": "gemini", "port": 10003, "configured": false, "models": null, "models_url": null }
{ "provider": "antigravity", "port": 10003, "configured": false, "models": null, "models_url": null }
],
"models_fetch_complete": true
}
Expand Down Expand Up @@ -76,7 +76,7 @@ curl -sf http://api-proxy:10000/reflect \
| jq -r '.endpoints[] | select(.provider == "openai" and .configured) | .models_url' \
| xargs curl -sf | jq '[.data[].id]'

# Gemini format → { models: [{name: "models/gemini-..."}] }
# Antigravity format → { models: [{name: "models/antigravity-..."}] }
curl -sf http://api-proxy:10003/v1/models | jq '[.models[].name | ltrimstr("models/")]'
```

Expand Down
6 changes: 3 additions & 3 deletions .github/aw/subagents.md
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,8 @@ Only two fields are supported inside a sub-agent frontmatter block:

| Alias | Resolves to | When to use |
|---|---|---|
| `small` | `mini` → haiku, gpt-5-mini, gpt-5-nano, gemini-flash | Cheap, fast tasks: extraction, classification, formatting |
| `large` | sonnet, gpt-5-pro, gpt-5, gemini-pro | Complex reasoning or synthesis tasks |
| `small` | `mini` → haiku, gpt-5-mini, gpt-5-nano, antigravity-flash | Cheap, fast tasks: extraction, classification, formatting |
| `large` | sonnet, gpt-5-pro, gpt-5, antigravity-pro | Complex reasoning or synthesis tasks |
| `inherited` | Parent workflow model | Default — use when the sub-agent needs the same capability as the parent |

All other fields (`engine`, `tools`, `network`, etc.) are stripped at runtime with a warning. Sub-agents inherit the parent's engine, tool access, and network configuration.
Expand All @@ -79,7 +79,7 @@ Sub-agent files are written to the directory and with the extension each engine
| Copilot (default) | `.agents/agents/` | `.agent.md` |
| Claude | `.claude/agents/` | `.md` |
| Codex | `.codex/agents/` | `.md` |
| Gemini | `.gemini/agents/` | `.md` |
| Antigravity | `.antigravity/agents/` | `.md` |

The engine is detected at compile time from the `engine:` field and injected as `GH_AW_ENGINE_ID` into the interpolation step's environment.

Expand Down
8 changes: 4 additions & 4 deletions .github/aw/syntax.md
Original file line number Diff line number Diff line change
Expand Up @@ -395,12 +395,12 @@ The YAML frontmatter supports these fields:
```

- **`engine:`** - AI processor configuration
- String format: `"copilot"` (default, recommended), `"claude"`, `"codex"`, `"gemini"`, or `"opencode"` (experimental)
- String format: `"copilot"` (default, recommended), `"claude"`, `"codex"`, `"antigravity"`, or `"opencode"` (experimental)
- Object format for extended configuration:

```yaml
engine:
id: copilot # Required: coding agent identifier (copilot, claude, codex, gemini, or opencode)
id: copilot # Required: coding agent identifier (copilot, claude, codex, antigravity, or opencode)
version: beta # Optional: version of the action (has sensible default); also accepts GitHub Actions expressions: ${{ inputs.engine-version }}
model: gpt-5 # Optional: LLM model to use (has sensible default)
agent: technical-doc-writer # Optional: custom agent file (Copilot only, references .github/agents/{agent}.agent.md)
Expand All @@ -412,7 +412,7 @@ The YAML frontmatter supports these fields:
args: ["--verbose"] # Optional: custom CLI arguments injected before prompt (array)
api-target: api.acme.ghe.com # Optional: custom API endpoint hostname for GHEC/GHES (hostname only, no protocol/path)
command: /usr/local/bin/copilot # Optional: override default engine executable (skips installation)
bare: true # Optional: disable automatic context loading (copilot: --no-custom-instructions; claude: --bare; codex: --no-system-prompt; gemini: GEMINI_SYSTEM_MD=/dev/null). Default: false
bare: true # Optional: disable automatic context loading (copilot: --no-custom-instructions; claude: --bare; codex: unsupported; antigravity: unsupported). Default: false
user-agent: "myapp/1.0" # Optional: custom user agent string (codex engine only)
config: | # Optional: additional TOML config appended to config.toml (codex engine only)
[extra]
Expand All @@ -426,7 +426,7 @@ The YAML frontmatter supports these fields:
```

- **Note**: The `version`, `model`, and `max-turns` fields have sensible defaults and can typically be omitted unless you need specific customization.
- **`gemini` engine**: Google Gemini CLI. Requires `GEMINI_API_KEY` secret. Does not support `max-turns`, `web-fetch`, or `web-search`. Supports AWF firewall and LLM gateway.
- **`antigravity` engine**: Antigravity CLI. Requires `ANTIGRAVITY_API_KEY` secret. Does not support `max-turns`, `web-fetch`, or `web-search`. Supports AWF firewall and LLM gateway.
- **`opencode` engine** (experimental): Provider-agnostic, open-source AI coding agent (BYOK). Defaults to Copilot routing via `COPILOT_GITHUB_TOKEN` (or `${{ github.token }}` with `copilot-requests` feature). Supports 75+ models via `provider/model` format. Supports AWF firewall and LLM gateway.

- **`network:`** - Network access control for AI engines (top-level field)
Expand Down
Loading