9router/open-sse/translator/concerns
whale bbae990b92 fix(volcengine-ark): clamp GLM-5 max_tokens to model output ceiling (#2428)
Ark rejects max_tokens above 128000 for GLM-5.2. Add a config-driven STRIP_RULES entry that clamps max_tokens, max_completion_tokens and max_output_tokens down to the model maxOutput before the upstream call.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-07 11:57:04 +07:00
..
chunk.js refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup 2026-06-14 18:49:38 +07:00
finishReason.js refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup 2026-06-14 18:49:38 +07:00
image.js fix(image): pin DNS-resolved IP to prevent SSRF via DNS rebinding (GHSA-cmhj-wh2f-9cgx) 2026-06-17 11:02:04 +07:00
json.js refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup 2026-06-14 18:49:38 +07:00
message.js refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup 2026-06-14 18:49:38 +07:00
modality.js Refactor 2026-06-15 18:18:04 +07:00
paramSupport.js fix(volcengine-ark): clamp GLM-5 max_tokens to model output ceiling (#2428) 2026-07-07 11:57:04 +07:00
prefetch.js Refactor 2026-06-15 18:18:04 +07:00
reasoning.js Refactor 2026-06-15 18:18:04 +07:00
thinking.js Refactor 2026-06-15 18:18:04 +07:00
thinkingUnified.js fix(kimi): normalize reasoning_effort to backend enum (#2427) 2026-07-07 11:56:39 +07:00
toolCall.js refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup 2026-06-14 18:49:38 +07:00
usage.js feat(usage): track cached tokens + correct input/output/cache cost (#2209) 2026-07-03 15:18:27 +07:00