mirror of
https://gitee.com/mateos/mateclaw.git
synced 2026-09-13 11:13:43 +08:00
1affbd7b82
- goal: continue (not skip) on max-iterations and evidence-insufficient turns.
A max-iterations turn grants a fresh iteration budget ("hard continuation"),
bounded per run and sized into the graph recursion ceiling, so a task too big
for one budget keeps going instead of stalling until the next user message.
- plan-execute: re-plan the remaining work on a step exception, and on a
signature-based stall (repeated failures / identical results / no usable
result) instead of advancing dependent steps with junk; bounded by a per-run
re-plan cap, with a graduated change-strategy nudge before the hard stop.
- plan-execute: auto-derive a goal from a genuine multi-step plan, seeding the
acceptance criteria from the plan steps, so the goal subsystem engages without
the model calling setGoal; broadcast goal_created so the UI hydrates.
- react: refund the iteration for setup-only rounds (load_skill / enable_tool)
so a tight budget is not eaten by the load-then-use two-step.
- ui: re-fetch the active goal when a turn finishes so a goal created or mutated
mid-conversation surfaces without depending on an SSE event.
- streaming: make retry backoff / total-time budget instance fields with a
test-only seam; clarify that the wall-clock budget (not max-retries) bounds a
sustained SERVER_ERROR loop to ~8 attempts, fixing the slow/flaky retry test.
|
||
|---|---|---|
| .. | ||
| acp | ||
| activity | ||
| agent | ||
| approval | ||
| audit | ||
| auth | ||
| channel | ||
| common | ||
| config | ||
| cron | ||
| dashboard | ||
| datasource | ||
| doc | ||
| exception | ||
| goal | ||
| hook | ||
| i18n | ||
| llm | ||
| memory | ||
| notification | ||
| planning | ||
| plugin | ||
| skill | ||
| stt | ||
| system | ||
| task | ||
| tool | ||
| trigger | ||
| tts | ||
| wiki | ||
| workflow | ||
| workspace | ||
| MateClawApplication.java | ||