mateclaw/mateclaw-server/src/main/java/vip/mate/agent
matevip fcf5f3960b fix(agent): stop lossy-truncating retrieval tool results that must arrive whole
load_skill returns SKILL.md in full by design — it is the model's behavioral
contract, and pagination by default would let the model silently miss later
mandatory sections. read_file / readSkillFile / load_skill are therefore on
the spill-exclusion list so their output is never replaced by a disk pointer.

The exclusion only covered half the path. In spillRawOrTruncate, an excluded
tool's result came back from persistIfOversized unchanged (no spill), failed
the SPILL_MARKER_PREFIX check, and fell through to truncateToolResult(8000) —
so an 8261-char SKILL.md was hard-cut through the middle and stamped with a
'[TRUNCATED: ... middle omitted]' marker. Weaker models ignore the attached
fidelity note and fabricate the removed span, inventing tool calls against
endpoints the skill never described.

- spillRawOrTruncate now returns retrieval-excluded results raw; the per-turn
  aggregate budget stays the backstop.
- Outsized SKILL.md degrades to resumable pagination instead of an unbounded
  inline dump. Never a lossy middle-cut.
2026-07-28 05:06:24 -04:00
..
binding fix(mcp): cascade-delete agent-tool bindings when an MCP server is removed 2026-06-29 15:03:09 +08:00
context feat(skill): scope agent runtime skill resolution to the conversation workspace 2026-07-24 14:12:08 +08:00
controller feat(agent): one-sentence AI employee creation wizard 2026-06-17 17:38:42 +08:00
delegation feat(delegation): 本轮 token 总量页脚 + 子 Agent 用量向上滚加 2026-06-30 17:21:10 +08:00
event feat(agent,trigger): wire agent_lifecycle as a real event source 2026-05-08 15:07:18 +08:00
graph fix(agent): stop lossy-truncating retrieval tool results that must arrive whole 2026-07-28 05:06:24 -04:00
model feat(agent): add wiki_disabled opt-out flag for knowledge bases 2026-06-20 07:21:07 +08:00
progress docs(agent): fix stale ledger-guard comment and translate ActionNode javadoc 2026-07-06 11:53:00 +08:00
prompt refactor(prompt): clean up prompt corpus, fix summary_budget bug, route fallbacks through i18n 2026-04-19 09:02:37 +08:00
repository Initial commit: MateClaw — Java + Vue 3 AI Assistant System 2026-04-04 19:03:49 +08:00
runtime feat(agent): 注意力锚定与环境感知——MCP 工具溯源 + skill 约束固定 + 事件通知 (#490) 2026-07-06 11:50:41 +08:00
service feat(agent): one-sentence AI employee creation wizard 2026-06-17 17:38:42 +08:00
vo feat(agent): one-sentence AI employee creation wizard 2026-06-17 17:38:42 +08:00
AgentAuthoringTool.java feat(agent): digital-employee builder skill to auto-create agents and chain them into a workflow (#165) 2026-05-21 16:26:04 +08:00
AgentGraphBuilder.java feat(team): plan-execute leads orchestrate through the task board — hand-off bridge, resume gate and step dependencies 2026-07-25 22:22:38 +08:00
AgentService.java feat(team): team_tasks tool with role gating and team context injection into agent prompts 2026-07-24 17:38:02 +08:00
AgentState.java Initial commit: MateClaw — Java + Vue 3 AI Assistant System 2026-04-04 19:03:49 +08:00
AgentToolSet.java feat(tool,skill,ui): progressive tool/skill disclosure (load_skill + enable_tool + tier UI) 2026-05-23 09:07:45 +08:00
BaseAgent.java fix(workspace): harden chat-upload base-path containment + cleanup guard 2026-06-26 14:25:56 +08:00
GraphEventPublisher.java feat(agent): tool-call loop guard, post-mutation verify reminder, warning chips 2026-07-08 18:18:34 +08:00
StructuredStreamCapable.java Initial commit: MateClaw — Java + Vue 3 AI Assistant System 2026-04-04 19:03:49 +08:00