rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

Cross-cutting rename of the current llama.cpp endpoint on the RTX 3090
(port 7771) from frank-small to frank-secondary:

- Service trio: scripts/{frank-small.env,frank-small.service,
  serve-frank-small.sh,download-frank-small.sh} → frank-secondary.*
- Test: tests/frank_small_unit.bats → tests/frank_secondary_unit.bats
- Runbooks: serverAppConfigs-docs/LLM/frank-small-*.md →
  frank-secondary-*.md (9 files); the FreeToken runbook stays
  freetoken-frank-small.md (it documents the retired CUDA-era service)
- Identifiers: FRANK_SMALL→FRANK_SECONDARY, llm_small→llm_secondary,
  LLM_SMALL_*→LLM_SECONDARY_*, deploy_llm_small→deploy_llm_secondary
- Historical references to the OLD frank-small (FreeToken/CUDA on the
  3090, and the Dankserver service that became frank-medium) are
  preserved verbatim — they describe what the service was called
  at the time.

serverAppConfigs-docs/LLM/frank-large-flash-server-v2-swift15.md

@@ -112,7 +112,7 @@ instead of ~88 s cold — the big-TTFT win the 27B engine needed a manual
   outside `xhigh|medium|low` — the models.yml fold (high→xhigh) stays
   mandatory.
 - Vision: OpenAI `image_url` content parts only (the fleet's standard
-  contract; the legacy top-level `images` field is the frank-small trap).
+  contract; the legacy top-level `images` field is the frank-secondary trap).
   ≥256 px probe images or the model answers "video".
 - `HALOGEN_MAX_TOKENS_CAP` over-cap is a 400 naming the limit — never a
   truncation. `max_tokens` INCLUDES thinking.
@@ -181,7 +181,7 @@ the 27B engine ran on. Only revisit if the ledger shows SVM complaints.
 `maxTokens: 57344`, `input: [text, image]`,
 `reasoningContentField: "reasoning_content"`, the `high→xhigh` effort
 fold, `extraBody` temperature 1.0 / top_p 0.95. Compaction still rides
-frank-small (the `compactionModel` steering is unchanged).
+frank-secondary (the `compactionModel` steering is unchanged).
 
 ## Rollback