test: switch opus defaults to sonnet/kimi for cheaper coverage

- opencode test default: claude-sonnet-4-6 → moonshotai/kimi-k2. claude-code
  default stays on sonnet (the agent-under-test for that path is Claude
  Code); the opencode path doesn't need an Anthropic model.
- byok-no-keys-fallback fixture: anthropic/claude-opus → moonshotai/kimi-k2.
  test verifies fallback to opencode/big-pickle, so the configured model
  is never invoked; picking a non-opus alias avoids burning credits if
  the fallback ever regresses.
- BEDROCK_MODEL_ID in both test workflows: us.anthropic.claude-opus-4-6-v1
  → us.anthropic.claude-sonnet-4-6. env var is required by the ci.test
  invariant that every provider's env vars are wired into the workflow.

.github/workflows/test.yml

@@ -62,7 +62,7 @@ jobs:
       OPENCODE_API_KEY: ${{ secrets.OPENCODE_API_KEY }}
       AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.AWS_BEARER_TOKEN_BEDROCK }}
       AWS_REGION: us-east-1
-      BEDROCK_MODEL_ID: us.anthropic.claude-opus-4-6-v1
+      BEDROCK_MODEL_ID: us.anthropic.claude-sonnet-4-6
       VERTEX_SERVICE_ACCOUNT_JSON: ${{ secrets.VERTEX_SERVICE_ACCOUNT_JSON }}
       GOOGLE_CLOUD_PROJECT: pullfrog
       VERTEX_LOCATION: global