jianf/ModelRouter
1
0
Fork 0
mirror of https://gitcode.com/JianFeeeee/ModelRouter.git synced 2026-09-20 00:48:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
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).
This commit is contained in:
dev
2026-08-25 09:52:55 +08:00
parent 24609289e8
commit ec89daad62
7 changed files with 153 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
internal/lua/adapters/kimicode.lua
View File

@ -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