fix(gateway): pass through upstream token usage in streams for all adapters

The prior usage-passthrough fix only covered openai/opencode; the same
empty-choices+usage drop bug remained in the 5 sibling OpenAI-compatible
adapters, and non-OpenAI providers (anthropic/gemini/ollama) never surfaced
streaming usage at all.

- deepseek/github/groq/kimicode/mistral: preserve usage on empty-choices
  chunks and attach it to normal chunks (same pattern as openai.lua)
- anthropic: emit usage from message_start (prompt) and message_delta
  (completion); gateway merges split usage additively
- gemini: read usageMetadata in the stream path
- ollama: fix non-streaming key (usage -> token_usage, matches
  UnifiedResponse json tag) and read prompt_eval_count/eval_count;
  surface counts from the done stream chunk
- gateway: mergeUsage combines usage across chunks (non-zero fields win,
  total recomputed from prompt+completion) so split usage doesn't lose
  the prompt half; single-chunk case (OpenAI) preserved exactly
- usage-only chunks: done=false (no redundant terminal stop), matching
  the Go fallback standardSSEChunk

internal/lua/adapters/openai.lua

@@ -81,7 +81,9 @@ function adapter.transform_stream_chunk(raw_chunk)
 
     if not chunk.choices or #chunk.choices == 0 then
         if uses ~= nil then
-            return json.encode({ usage = uses, done = (chunk.usage ~= nil) })
+            -- usage-only chunk is not a content/finish signal; the gateway
+            -- emits its own terminal stop chunk and merges this usage.
+            return json.encode({ usage = uses, done = false })
         end
         return ""
     end