Yeachan-Heo 00d0eb61d4 US-024: Add token limit metadata for kimi models ... Add ModelTokenLimit entries for kimi-k2.5 and kimi-k1.5 to enable preflight context window validation. Per Moonshot AI documentation: - Context window: 256,000 tokens - Max output: 16,384 tokens Includes 3 unit tests: - returns_context_window_metadata_for_kimi_models - kimi_alias_resolves_to_kimi_k25_token_limits - preflight_blocks_oversized_requests_for_kimi_models All tests pass, clippy clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-04-17 04:15:38 +00:00
..
api	US-024: Add token limit metadata for kimi models	2026-04-17 04:15:38 +00:00
commands	Keep poisoned test locks from cascading across unrelated regressions	2026-04-12 13:52:41 +00:00
compat-harness	feat: ultraclaw droid batch — ROADMAP #41 test isolation + #50 PowerShell permissions	2026-04-12 03:06:24 +09:00
mock-anthropic-service	feat(harness+usage): add auto_compact and token_cost parity scenarios	2026-04-03 22:41:42 +09:00
plugins	Keep poisoned test locks from cascading across unrelated regressions	2026-04-12 13:52:41 +00:00
runtime	Fix formatting in task_packet.rs for CI	2026-04-16 09:35:18 +00:00
rusty-claude-cli	Make ACP/Zed status obvious before users go source-diving	2026-04-16 03:13:50 +00:00
telemetry	feat: anthropic SDK header matching + request profile	2026-04-01 05:55:25 +00:00
tools	US-005: Typed task packet format with TaskScope enum	2026-04-16 09:28:42 +00:00