feat: add claude-code/opus reviewer + max-thinking spec support (#5)

Adds claude-code/opus to gadfly's dogfood swarm (both sonnet and opus run
end-to-end), bumps the image pin to :sha-80d8f53 so the clean-lens
telemetry fix is live, and adds engine support for a
"claude-code/<model>:max" extended-thinking spec (MAX_THINKING_TOKENS,
best-effort). Validated: only 13 findings on this clean PR vs 43 on the
comparable #4 — the telemetry fix works.

Folded in the swarm's two real findings: a runPass env-injection test and
keeping MAX_THINKING_TOKENS in claudeEnv. Follow-up enables
claude-code/opus:max once this image builds.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Steve Dudenhoeffer <steve@stevedudenhoeffer.com>
Co-committed-by: Steve Dudenhoeffer <steve@stevedudenhoeffer.com>

.gitea/workflows/adversarial-review.yml

@@ -45,7 +45,7 @@ jobs:
     # with the 3-lens suite. All cloud now, so runs are fast.
     timeout-minutes: 90
     steps:
-      - uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-86f12c1
+      - uses: docker://gitea.stevedudenhoeffer.com/steve/gadfly:sha-80d8f53
         env:
           GITEA_API: ${{ github.server_url }}/api/v1/repos/${{ github.repository }}
           GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
@@ -54,14 +54,14 @@ jobs:
           # below): Pro/Max subscription token. Dogfoods the Phase-1 engine on
           # gadfly's own PRs as a competitor alongside the Ollama models.
           CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
-          # Fleet: 6 cloud (3 at a time) + Claude Code (sonnet) — one consolidated
-          # comment each, all cloud now. The local Macs (m1/m5) and the weaker
-          # cloud models (gemma4, gpt-oss:120b, kimi-k2.7-code) were dropped as
-          # low-signal for gadfly's own PRs. claude-code/sonnet runs the Phase-1
-          # engine as a competitor in its own lane (needs CLAUDE_CODE_OAUTH_TOKEN).
-          GADFLY_MODELS: "minimax-m3:cloud,glm-5.2:cloud,glm-5.1:cloud,deepseek-v4-pro:cloud,nemotron-3-super:cloud,qwen3-coder:480b-cloud,claude-code/sonnet"
-          # cloud runs 3 at once; claude-code one at a time; both lanes parallel.
-          GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3,claude-code=1"
+          # Fleet: 6 cloud (3 at a time) + Claude Code (sonnet + opus) — one
+          # consolidated comment each, all cloud now. The local Macs (m1/m5) and
+          # the weaker cloud models (gemma4, gpt-oss:120b, kimi-k2.7-code) were
+          # dropped as low-signal. The claude-code/* entries run the Phase-1
+          # engine as competitors in their own lane (need CLAUDE_CODE_OAUTH_TOKEN).
+          GADFLY_MODELS: "minimax-m3:cloud,glm-5.2:cloud,glm-5.1:cloud,deepseek-v4-pro:cloud,nemotron-3-super:cloud,qwen3-coder:480b-cloud,claude-code/sonnet,claude-code/opus"
+          # cloud runs 3 at once; claude-code 2 at a time; both lanes parallel.
+          GADFLY_PROVIDER_CONCURRENCY: "ollama-cloud=3,claude-code=2"
           # 3 cloud models x 3 lenses = 9 concurrent ollama-cloud queries (under the 10 budget).
           GADFLY_PROVIDER_LENS_CONCURRENCY: "ollama-cloud=3"
           # Default => the 3-lens suite (security, correctness, error-handling).