YeonGyu-Kim eb044f0a02 fix(api): emit max_completion_tokens for gpt-5* on OpenAI-compat path — closes ROADMAP #35 ...

gpt-5.x models reject requests with max_tokens and require max_completion_tokens.
Detect wire model starting with 'gpt-5' and switch the JSON key accordingly.
Older models (gpt-4o etc.) continue to receive max_tokens unchanged.

Two regression tests added:
- gpt5_uses_max_completion_tokens_not_max_tokens
- non_gpt5_uses_max_tokens

140 api tests pass, cargo fmt clean.

2026-04-09 09:33:45 +09:00

..

api

fix(api): emit max_completion_tokens for gpt-5* on OpenAI-compat path — closes ROADMAP #35

2026-04-09 09:33:45 +09:00

commands

fix(commands): fix brittle /session help assertion after delete subcommand addition

2026-04-08 09:33:51 +09:00

compat-harness

wip: plugins progress

2026-04-01 07:09:06 +00:00

mock-anthropic-service

feat(harness+usage): add auto_compact and token_cost parity scenarios

2026-04-03 22:41:42 +09:00

plugins

fix(plugins): chmod +x generated hook scripts + tolerate BrokenPipe in stdin write — closes ROADMAP #25 hotfix lane

2026-04-08 15:48:20 +09:00

runtime

style: cargo fmt — fix CI formatting failures

2026-04-08 11:21:13 +09:00

rusty-claude-cli

feat(cli): populate Git SHA, target triple, and build date at compile time via build.rs

2026-04-08 18:11:46 +09:00

telemetry

feat: anthropic SDK header matching + request profile

2026-04-01 05:55:25 +00:00

tools

fix(tools): serialize web_search env-var tests with env_lock to prevent race

2026-04-08 18:34:06 +09:00