kimi-code/packages/agent-core
haozhe.yang f7c7a6be35 fix(agent-core): tune tool-dedup thresholds and preserve isError state
- Lower repeat-reminder thresholds to 3, 5, 8 and force-stop to 12\n- Force-stop no longer overrides successful tool results to isError\n- Move stopTurn field into ExecutableToolSuccessResult for explicit loop-control without requiring isError
2026-06-03 13:25:19 +08:00
..
src fix(agent-core): tune tool-dedup thresholds and preserve isError state 2026-06-03 13:25:19 +08:00
test fix(agent-core): tune tool-dedup thresholds and preserve isError state 2026-06-03 13:25:19 +08:00
CHANGELOG.md ci: release packages (#237) 2026-06-02 10:22:31 +08:00
package.json ci: release packages (#237) 2026-06-02 10:22:31 +08:00
README.md Kimi For Coding 2026-05-22 15:54:50 +08:00
tsconfig.json Kimi For Coding 2026-05-22 15:54:50 +08:00
tsdown.config.ts Kimi For Coding 2026-05-22 15:54:50 +08:00
vitest.config.ts Kimi For Coding 2026-05-22 15:54:50 +08:00

@moonshot-ai/agent-core

The unified agent engine for Kimi Code.

Part of the Kimi Code monorepo.

See the main repository for documentation, issues, and contribution guidelines.

License

MIT