vrr/kimi-code
2
0
Fork 0
mirror of https://github.com/MoonshotAI/kimi-code.git synced 2026-08-27 01:24:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
kimi-code/packages/agent-core/test/agent
History
Exact
Kai 84d8d5b063
feat(agent-core): make compaction notes capture a forward plan, not just the next step (#1342) 
Compaction runs at the point of maximum context for the task, and the next
turn resumes with less. So the handoff note now records the plan for the
remaining work — upcoming steps, settled decisions, and foreseeable obstacles,
plus any work that can be pre-committed — instead of only the immediate next
command. Update the affected compaction snapshots and one hardcoded
input-token assertion (the instruction is ~163 tokens longer).
2026-07-03 13:38:09 +08:00
..
background fix(agent-core): cap foreground shell output to prevent OOM crash (#1285) 2026-07-02 13:42:39 +08:00
compaction feat(agent-core): make compaction notes capture a forward plan, not just the next step (#1342) 2026-07-03 13:38:09 +08:00
config feat: add model alias overrides (#1262) 2026-07-01 19:57:13 +08:00
context fix(agent-core): recover sessions bricked by orphan tool results (#1308) 2026-07-02 19:29:05 +08:00
cron feat(cron): render scheduled reminders in TUI and expose fired events (#204) 2026-06-01 11:34:35 +08:00
harness refactor!: overhaul thinking config and effort resolution (#1132) 2026-06-30 22:34:13 +08:00
injection feat(agent-core): rework compaction to keep only user prompts and summary (#1214) 2026-07-01 01:17:30 +08:00
permission feat(goal): support guided goal authoring (#839) 2026-06-18 18:48:23 +08:00
records feat(agent-core): rework compaction to keep only user prompts and summary (#1214) 2026-07-01 01:17:30 +08:00
turn feat(agent-core): detect and escalate repeated tool calls to prevent infinite loops (#364) 2026-06-03 14:16:14 +08:00
basic.test.ts chore(agent-core): remove experimental micro compaction (#1317) 2026-07-02 19:50:51 +08:00
bg-idle-notification-repro.test.ts fix: preserve long tool output (#1062) 2026-06-24 14:42:11 +08:00
config-state.test.ts feat: add KIMI_MODEL_THINKING_EFFORT to force a thinking effort (#1275) 2026-07-01 21:20:27 +08:00
config.test.ts refactor!: overhaul thinking config and effort resolution (#1132) 2026-06-30 22:34:13 +08:00
context.test.ts chore(telemetry): track conversation undo, shell mode, and effort changes (#1271) 2026-07-01 20:04:31 +08:00
goal-outcome.test.ts fix: polish goal lifecycle messaging (#555) 2026-06-09 11:47:00 +08:00
goal.test.ts fix: polish goal lifecycle messaging (#555) 2026-06-09 11:47:00 +08:00
kosong-llm.test.ts feat(timing): split TTFT into api-server and client portions (#1228) 2026-06-30 19:15:02 +08:00
permission.test.ts feat(agent-core): rework compaction to keep only user prompts and summary (#1214) 2026-07-01 01:17:30 +08:00
plan.test.ts feat: Harden the default system prompt and built-in tool descriptions (#1102) 2026-06-26 16:56:40 +08:00
question.test.ts feat(agent-core): ModelProvider interface and SingleModelProvider (#167) 2026-05-28 22:27:09 +08:00
resume.test.ts fix(agent-core): recover sessions bricked by orphan tool results (#1308) 2026-07-02 19:29:05 +08:00
skill-prompt.test.ts fix: surface skill directory in the loaded-skill context block (#785) 2026-06-15 22:29:00 +08:00
skill-tool-manager.test.ts fix: surface skill directory in the loaded-skill context block (#785) 2026-06-15 22:29:00 +08:00
tool.test.ts ci: run unit tests on windows (#1037) 2026-06-26 11:56:41 +08:00
turn.test.ts refactor!: overhaul thinking config and effort resolution (#1132) 2026-06-30 22:34:13 +08:00
usage.test.ts Kimi For Coding 2026-05-22 15:54:50 +08:00