fix(adapters): pass through cache tokens in the remaining 8 adapters

Live testing proved both sensenova and zen DO return cache fields:
- zen laguna-s-2.1-free: usage.prompt_tokens_details.cached_tokens = 32
  (real hit), plus cache_write_tokens/audio_tokens
- sensenova glm-5.2: prompt_tokens_details.cached_tokens present (0 on
  short prompts)

The previous round only patched deepseek/openai/anthropic/gemini.lua;
sensenova/opencode (localzen!) and the other adapters still dropped them.

- sensenova/opencode/groq/mistral/github/kimicode: stream + response
  cache passthrough (same pattern as openai.lua)
- agentrouter: response passthrough + NEW stream usage forwarding (it
  previously dropped the terminal usage-only chunk entirely)
- ollama skipped intentionally: its native API has no cache fields

Verified end-to-end through the gateway: localzen/laguna-s-2.1-free now
returns prompt_tokens_details.cached_tokens=32 to clients, and the request
record carries cache_hit_tokens (both chat and stream paths).

internal/lua/adapters/agentrouter.lua

@@ -52,6 +52,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
 
     if type(resp.choices) == "table" and #resp.choices > 0 then
@@ -86,7 +98,30 @@ function adapter.transform_stream_chunk(raw_chunk)
     local ok, chunk = pcall(json.decode, raw_chunk)
     if not ok then return "" end
 
-    if not chunk.choices or #chunk.choices == 0 then return "" end
+    -- usage-only terminal chunk (empty choices + usage): forward it so the
+    -- gateway emits exact token counts (and cache fields when present).
+    local uses = nil
+    if type(chunk.usage) == "table" then
+        uses = {
+            prompt = chunk.usage.prompt_tokens or chunk.usage.prompt or 0,
+            completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
+            total = chunk.usage.total_tokens or chunk.usage.total or 0,
+        }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
+    end
+
+    if not chunk.choices or #chunk.choices == 0 then
+        if uses ~= nil then
+            return json.encode({ usage = uses, done = false })
+        end
+        return ""
+    end
     local delta = chunk.choices[1].delta or {}
     local fr = chunk.choices[1].finish_reason
 
@@ -105,6 +140,9 @@ function adapter.transform_stream_chunk(raw_chunk)
     if delta.tool_calls then
         unified.tool_calls = delta.tool_calls
     end
+    if uses ~= nil then
+        unified.usage = uses
+    end
     return json.encode(unified)
 end
 

internal/lua/adapters/github.lua

@@ -33,6 +33,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
 
     if type(resp.choices) == "table" and #resp.choices > 0 then
@@ -74,6 +86,13 @@ function adapter.transform_stream_chunk(raw_chunk)
             completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
             total = chunk.usage.total_tokens or chunk.usage.total or 0,
         }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
     end
 
     if not chunk.choices or #chunk.choices == 0 then

internal/lua/adapters/groq.lua

@@ -32,6 +32,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
 
     if type(resp.choices) == "table" and #resp.choices > 0 then
@@ -73,6 +85,13 @@ function adapter.transform_stream_chunk(raw_chunk)
             completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
             total = chunk.usage.total_tokens or chunk.usage.total or 0,
         }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
     end
 
     if not chunk.choices or #chunk.choices == 0 then

internal/lua/adapters/kimicode.lua

@@ -64,6 +64,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
     if type(resp.choices) == "table" and #resp.choices > 0 then
         local ch = resp.choices[1]
@@ -106,6 +118,13 @@ function adapter.transform_stream_chunk(raw_chunk)
             completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
             total = chunk.usage.total_tokens or chunk.usage.total or 0,
         }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
     end
 
     if not chunk.choices or #chunk.choices == 0 then

internal/lua/adapters/mistral.lua

@@ -32,6 +32,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
 
     if type(resp.choices) == "table" and #resp.choices > 0 then
@@ -73,6 +85,13 @@ function adapter.transform_stream_chunk(raw_chunk)
             completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
             total = chunk.usage.total_tokens or chunk.usage.total or 0,
         }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
     end
 
     if not chunk.choices or #chunk.choices == 0 then

internal/lua/adapters/opencode.lua

@@ -100,6 +100,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
 
     if type(resp.choices) == "table" and #resp.choices > 0 then
@@ -146,6 +158,13 @@ function adapter.transform_stream_chunk(raw_chunk)
             completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
             total = chunk.usage.total_tokens or chunk.usage.total or 0,
         }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
     end
 
     if not chunk.choices or #chunk.choices == 0 then

internal/lua/adapters/sensenova.lua

@@ -37,6 +37,18 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.prompt_tokens or 0
         unified.token_usage.completion = resp.usage.completion_tokens or 0
         unified.token_usage.total = resp.usage.total_tokens or 0
+        local hit = 0
+        if type(resp.usage.prompt_tokens_details) == "table" and (resp.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            hit = resp.usage.prompt_tokens_details.cached_tokens
+            unified.token_usage.prompt_tokens_details = { cached_tokens = hit }
+        end
+        if (resp.usage.prompt_cache_hit_tokens or 0) > 0 then
+            unified.token_usage.prompt_cache_hit_tokens = resp.usage.prompt_cache_hit_tokens
+            unified.token_usage.prompt_cache_miss_tokens = resp.usage.prompt_cache_miss_tokens or 0
+            if hit == 0 then
+                unified.token_usage.prompt_tokens_details = { cached_tokens = resp.usage.prompt_cache_hit_tokens }
+            end
+        end
     end
 
     if type(resp.choices) == "table" and #resp.choices > 0 then
@@ -67,6 +79,13 @@ function adapter.transform_stream_chunk(raw_chunk)
             completion = chunk.usage.completion_tokens or chunk.usage.completion or 0,
             total = chunk.usage.total_tokens or chunk.usage.total or 0,
         }
+        if type(chunk.usage.prompt_tokens_details) == "table" and (chunk.usage.prompt_tokens_details.cached_tokens or 0) > 0 then
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_tokens_details.cached_tokens }
+        elseif (chunk.usage.prompt_cache_hit_tokens or 0) > 0 then
+            uses.prompt_cache_hit_tokens = chunk.usage.prompt_cache_hit_tokens
+            uses.prompt_cache_miss_tokens = chunk.usage.prompt_cache_miss_tokens or 0
+            uses.prompt_tokens_details = { cached_tokens = chunk.usage.prompt_cache_hit_tokens }
+        end
     end
 
     if not chunk.choices or #chunk.choices == 0 then