Add experimental Auggie engine support#42314
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
🔍 PR Triage — §28395315609
Score breakdown: impact 25 + urgency 5 + quality 10
|
|
I ran the external Auggie smoke test in a temporary public repo. Repo: https://github.com/carlosflorencio/gh-aw-auggie Result: failure in What passed:
Failure:
This looks like the intended PR behavior is not wired through yet: exclude |
|
Hey This looks ready for maintainer review — tests are present, the description covers all the moving parts, and the diff is focused entirely on Auggie support. The
|
🤖 PR Triage — Run §28413530597
Notes: Draft (7.1h). Very large experimental feature: 288 files, +3213/-558. No CI yet. Defer until promoted from draft with CI results. Labels confirmed correct.
|
This adds Augment Code's Auggie CLI as a new experimental engine so workflows can use
engine: auggiealongside the existing agentic engines. It wires Auggie through compilation, runtime metadata, docs, schema validation, and smoke coverage usingAUGMENT_SESSION_AUTHfor authentication.Engine registration and defaults
auggieengine ID, default version pin (0.29.0), model env vars, engine option metadata, and built-in engine definition.Runtime implementation
AuggieEnginewith experimental metadata and Auggie-specific capabilities:.augment/@augmentcode/auggie, validateAUGMENT_SESSION_AUTH, render standard JSON MCP config, and emit Auggie execution steps with:--print --quiet--model--mcp-configFirewall and domain handling
AUGMENT_SESSION_AUTHfrom forwarded firewall env while still making it available to the agent process.Schema, docs, and UX
auggie.Smoke workflow and generated artifacts
smoke-auggie.mdand compile it to a lockfile..augment/manifest protection and engine catalog state are reflected consistently.Example workflow:
At execution time this compiles down to an Auggie invocation shaped like: