Files
OmniRoute/src/lib
Diego Rodrigues de Sa e Souza adb1fc5b27 fix(providers): honor max_token capability override in reasoning buffer clamp (#6524) (#6904)
getExplicitModelOutputCap() (the clamp ceiling used by
resolveReasoningBufferedMaxTokens) only ever read the unvalidated synced
limit_output / registry / static-spec chain — it ignored the operator-settable
max_token capability override that getResolvedModelCapabilities() already
consulted. When a provider's synced catalog row reports a wrong limit_output
(e.g. ollama-cloud/deepseek-v4-flash: limit_output=1048576, same as
limit_context, while the real upstream cap is 65536), the reasoning-buffer
clamp trusted the bad number and inflated max_tokens 64000 -> 96000, which
upstream rejected with "exceeds model's maximum output tokens (65536)".

The override table (model_capability_overrides, "max_token" key,
/api/model-capability-overrides) is the existing, already-shipped remediation
path for exactly this class of bad catalog data, but reasoningTokenBuffer.ts
had no way to benefit from it. Extracted the override lookup into a shared
getMaxTokenCapabilityOverride() helper and made getExplicitModelOutputCap()
consult it first, so both read paths now agree.
2026-07-11 11:22:15 -03:00
..
2026-07-06 02:25:17 -03:00
2026-06-19 06:49:01 -03:00
2026-06-29 08:40:06 -03:00
2026-07-07 13:14:06 -03:00
2026-06-30 06:54:29 -03:00
2026-07-02 10:47:13 -03:00
2026-06-30 06:54:29 -03:00
2026-06-29 16:51:03 -03:00
2026-07-06 02:25:17 -03:00
2026-07-04 13:00:30 -03:00
2026-06-20 07:09:43 -03:00
2026-06-27 09:07:12 -03:00
2026-06-29 16:51:03 -03:00
2026-06-30 06:54:29 -03:00
2026-05-24 18:05:58 -03:00
2026-07-04 13:00:30 -03:00
2026-06-25 13:17:40 -03:00
2026-07-04 13:00:30 -03:00
2026-07-02 10:47:13 -03:00
2026-06-29 16:51:03 -03:00
2026-06-30 06:54:29 -03:00
2026-07-07 13:14:06 -03:00
2026-07-02 10:47:13 -03:00
2026-06-19 06:49:01 -03:00
2026-07-06 02:25:17 -03:00
2026-07-02 10:47:13 -03:00
2026-07-02 10:47:13 -03:00
2026-06-17 19:26:32 -03:00
2026-06-30 06:54:29 -03:00
2026-06-20 14:55:24 -03:00
2026-06-30 06:54:29 -03:00
2026-06-20 07:09:43 -03:00
2026-07-06 02:25:17 -03:00
2026-07-02 10:47:13 -03:00
2026-06-20 14:55:24 -03:00
2026-05-26 23:51:47 -03:00
2026-07-02 10:47:13 -03:00
2026-07-02 10:47:13 -03:00
2026-07-02 10:47:13 -03:00
2026-06-29 16:51:03 -03:00
2026-05-29 12:44:29 -03:00
2026-06-17 02:43:21 -03:00
2026-06-30 06:54:29 -03:00
2026-06-29 08:40:06 -03:00
2026-05-29 12:44:29 -03:00
2026-05-29 12:44:29 -03:00
2026-05-26 23:51:47 -03:00
2026-06-26 02:51:06 -03:00
2026-06-29 08:40:06 -03:00
2026-06-29 08:40:06 -03:00
2026-06-26 02:51:06 -03:00
2026-07-06 02:25:17 -03:00
2026-05-26 23:51:47 -03:00
2026-06-29 16:51:03 -03:00
2026-07-07 13:14:06 -03:00
2026-07-02 10:47:13 -03:00
2026-04-30 01:27:03 -03:00
2026-06-12 23:49:22 -03:00
2026-06-29 08:40:06 -03:00
2026-06-29 16:51:03 -03:00
2026-06-29 16:51:03 -03:00
2026-05-24 18:05:58 -03:00
2026-06-13 17:27:40 -03:00
2026-06-20 14:55:24 -03:00
2026-07-02 10:47:13 -03:00
2026-07-02 10:47:13 -03:00
2026-06-09 15:56:24 -03:00
2026-06-17 19:26:32 -03:00