refactor: split opencode runtime and tests

docs/architecture.md

@@ -14,8 +14,10 @@ webhook_server ── trusted base config ──► review_config
 review_pr facade/orchestrator
    ├── entrypoints/gitea  fetch diff, reviews, config; publish review
    ├── diff_compress      reduce prompt context
-   ├── opencode_review     isolated checkout + agent execution
-   │       └── model / repo factory (.opencode)
+   ├── opencode             review orchestration seam
+   │   ├── opencode_workspace  archive, sanitization, brief, factory
+   │   ├── opencode_lens_config reviewer configuration and selection
+   │   └── opencode_synthesis  normalization, deduplication, summaries
    ├── review parsing      normalize findings + validate anchors
    ├── feedback            persist reactions and derive scores
    └── langfuse_trace      usage, cost, evaluation telemetry
@@ -37,8 +39,10 @@ The internal seams are deliberately narrower:
 - `entrypoints/gitea.request()` and `GiteaClient` own HTTP authentication, JSON
   request encoding, timeout, and Gitea URL construction.
 - `model_client.complete()` owns the legacy Anthropic-compatible request shape.
-  `opencode_review` is the preferred agent adapter and keeps Gitea I/O out of
-  the autonomous process.
+  `opencode` is the preferred agent adapter and keeps Gitea I/O out of the
+  autonomous process. Its sibling modules provide internal seams for workspace
+  preparation, lens policy, and synthesis without expanding the caller-facing
+  interface.
 - `review/analysis`, `review/output`, `review/configuration`, and
   `review/adapters` keep prompt construction, finding parsing, config filtering,
   rendering, and publishing in focused modules.