Hemilt0n f38facd430 fix(proxy): use max_completion_tokens for o1/o3 series models (#1451) ...

* fix(proxy): use max_completion_tokens for o1/o3 series models

When converting Anthropic requests to OpenAI format for o1/o3 series
models (like o1-mini, o3-mini), use max_completion_tokens instead of
max_tokens to avoid unsupported_parameter errors.

Fixes #1448

* fix: revert incorrect o-series max_completion_tokens in Responses API path

Responses API uses max_output_tokens for all models including o-series.
The o-series max_completion_tokens fix should only apply to Chat Completions API.

---------

Co-authored-by: Hajen Teowideo <hajen.teowideo@example.com>
Co-authored-by: Jason Young <44939412+farion1231@users.noreply.github.com>
Co-authored-by: Jason <farion1231@gmail.com>

2026-03-15 20:39:17 +08:00

..

providers

fix(proxy): use max_completion_tokens for o1/o3 series models (#1451)

2026-03-15 20:39:17 +08:00

usage

style: format Rust code with cargo fmt

2026-03-08 22:27:53 +08:00

body_filter.rs

chore(proxy): remove unused body filter helper

2026-01-04 23:00:13 +08:00

cache_injector.rs

feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) (#1301)

2026-03-07 18:57:21 +08:00

circuit_breaker.rs

feat(proxy): add thinking signature rectifier for Claude API (#595)

2026-01-14 00:12:13 +08:00

error_mapper.rs

Feat/usage improvements (#508)

2025-12-31 22:57:00 +08:00

error.rs

Refactor/simplify proxy logs (#585)

2026-01-11 20:50:54 +08:00

failover_switch.rs

Refactor/simplify proxy logs (#585)

2026-01-11 20:50:54 +08:00

forwarder.rs

Fix proxy forwarder failure logs

2026-03-08 19:42:18 +08:00

handler_config.rs

Feat/usage improvements (#508)

2025-12-31 22:57:00 +08:00

handler_context.rs

feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) (#1301)

2026-03-07 18:57:21 +08:00

handlers.rs

feat: add OpenAI Responses API format conversion (api_format = "openai_responses")

2026-03-08 19:41:29 +08:00

health.rs

Feat/proxy server (#355)

2025-12-05 11:26:41 +08:00

http_client.rs

fix(codex): fix 404 errors and connection timeout with custom base_url (#760)

2026-01-29 09:10:17 +08:00

log_codes.rs

Fix proxy forwarder failure logs

2026-03-08 19:42:18 +08:00

mod.rs

feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) (#1301)

2026-03-07 18:57:21 +08:00

model_mapper.rs

feat(proxy): fix thinking rectifiers and resolve clippy warnings (#1005)

2026-02-12 22:28:05 +08:00

provider_router.rs

fix(failover): switch to P1 immediately when enabling auto failover

2026-01-21 11:27:44 +08:00

response_handler.rs

Feat/proxy server (#355)

2025-12-05 11:26:41 +08:00

response_processor.rs

feat: add usage daily rollups, incremental auto-vacuum, and sync-aware backup

2026-03-08 19:42:18 +08:00

server.rs

fix: support codex /responses/compact route (#1194)

2026-03-04 23:47:38 +08:00

session.rs

Feat/usage improvements (#508)

2025-12-31 22:57:00 +08:00

thinking_budget_rectifier.rs

feat(proxy): fix thinking rectifiers and resolve clippy warnings (#1005)

2026-02-12 22:28:05 +08:00

thinking_optimizer.rs

feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) (#1301)

2026-03-07 18:57:21 +08:00

thinking_rectifier.rs

feat(proxy): fix thinking rectifiers and resolve clippy warnings (#1005)

2026-02-12 22:28:05 +08:00

types.rs

feat: add Bedrock request optimizer (PRE-SEND thinking + cache injection) (#1301)

2026-03-07 18:57:21 +08:00