The 11-model swarm (incl. the new claude-code/sonnet competitor)
reviewed PR #3. 52 findings graded via the MCP — almost all accurate
clean-verifications of a small, clean PR (telemetry over-extracts them).
Two were real and are folded in:
- model_test.go: add llamaswap with/without-token cases to
TestEndpointProvider. Caught by claude-code/sonnet itself, citing
CLAUDE.md's "add a test when you add logic" rule — the standout
finding and a strong validation of the Phase-1 engine.
- model.go: the default provider error messages omitted
"openai-compatible" though the switch accepts it. Caught by gpt-oss.
Added it to both messages.
gofmt clean, go vet quiet, go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase 2 of the gadfly-games build.
- Bump majordomo to the latest build and wire its new **llamaswap**
provider into gadfly's endpoint switches (GADFLY_PROVIDER=llamaswap +
GADFLY_BASE_URL, and GADFLY_ENDPOINT_<NAME>="llamaswap|url[|key]"),
mirroring the ollama provider. Wired but untested (no llama-swap here).
- Dogfood the Phase-1 claude-code engine: add `claude-code/sonnet` to
gadfly's own review swarm as a competitor alongside the 9 cloud models
+ M5, pin the workflow to :sha-86f12c1 (the image that bundles the
claude CLI), and map CLAUDE_CODE_OAUTH_TOKEN. Its own provider lane
(claude-code=1), parallel with the cloud and m5 lanes.
- Document the alternate Claude Code backends: Pro/Max (default), and —
EXAMPLE ONLY, not wired — running Ollama models THROUGH the CC harness
via ANTHROPIC_BASE_URL pointed at an Anthropic-compatible proxy
(claude-code-router / LiteLLM). The subprocess env already forwards
ANTHROPIC_*/CLAUDE_*, so no code change is needed for that path.
- README: llamaswap row in the providers table + a Claude Code
"alternate backends" note; examples/claude-code.yml shows the proxy env.
gofmt clean, go vet quiet, go build + go test -race green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
steve