Merge remote-tracking branch 'origin/worktree/context-source-cards' into worktree/context-forms-remaining
# Conflicts: # apps/web/tests/snapshots/queue-actions/layout.expected.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/goal.i18n.yaml # docs/core-data-structures/goal.md # docs/core-data-structures/goal.zh.md # docs/event-producer-consumer.md # examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl # examples/acp-agent/tests/goal-snapshots/goal-wrapup/session.expected.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/acp-agent/tests/snapshots/bash-spill/session.jsonl # examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/cancel/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl # examples/acp-agent/tests/snapshots/error-finish/session.jsonl # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/fs-edit/session.jsonl # examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl # examples/acp-agent/tests/snapshots/fs-read/session.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl # examples/acp-agent/tests/snapshots/fs-write/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl # examples/acp-agent/tests/snapshots/missing-sandbox-runner/session.jsonl # examples/acp-agent/tests/snapshots/multi-turn/session.jsonl # examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/partial-landlock-child-failure/session.jsonl # examples/acp-agent/tests/snapshots/pty-tools/session.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl # examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl # examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl # examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/subagent-continuable/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-continuable/session.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl # examples/acp-agent/tests/snapshots/subagent-list-agents/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-list-agents/session.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl # examples/acp-agent/tests/snapshots/subagent-published-run-failure/session.jsonl # examples/acp-agent/tests/snapshots/subagent-report/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-report/session.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/acp-agent/tests/snapshots/todo-write/session.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl # examples/acp-agent/tests/snapshots/web-fetch/session.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl # examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/pty-tools/session.jsonl # examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl # packages/bash/tool-bash/tests/integration.spec.ts # packages/context/time-context/src/index.ts # packages/context/tmux-context/src/index.ts # packages/core/agent-loop/src/agent.ts # packages/core/system-prompt/src/index.ts # packages/goal/goal/src/domain.ts # packages/goal/goal/src/index.ts # packages/goal/goal/src/render.ts # packages/plan/plan-mode/src/index.ts
This commit is contained in:
creatixchu
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/guard/README.md
|
||||
README.md: b7375fd2bb12ae0cec94b13e6a1012c6f143bdad
|
||||
README.zh.md: 7092f50b05516a2fb358c5d6f496b967ebdc6819
|
||||
README.md: 8da2f2ddcc1432e7963e600b35549f5e26121af2
|
||||
README.zh.md: aa8b5bd1f7d10d90d1dc84d07a7aad81bfb4259c
|
||||
|
||||
@@ -2,10 +2,8 @@
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
Behavioral guard plugins that watch the agent loop for unproductive patterns and nudge the model back on course. A single **product** package — there is no interface/implementation seam here, because a guard is a self-contained consumer of existing core seams (`tools/post-execute`, `agent/prompt-submit`, `agent/status`), not a swappable capability.
|
||||
Behavioral guard plugins watch the agent loop for unproductive patterns and nudge the model back on course. A guard is a self-contained consumer of core seams, not a swappable capability.
|
||||
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| `repeat-tool-guard/` | Advisory reminders when an agent loops on identical tool calls | (listens on `ctx.tools`' waterfalls) |
|
||||
|
||||
Reminders travel as `additionalContexts` on the `tools/post-execute` decision; the agent loop appends them as logged plugin-sourced `user/message` events after the step's tool results (see [the tools package](../core/tools)), so everything a guard says to the model is reconstructable from the session log.
|
||||
| [`repeat-tool-guard/`](repeat-tool-guard/README.md) | Advisory reminders for repeated tool calls | listens on tool and agent events |
|
||||
|
||||
@@ -1,11 +1,9 @@
|
||||
# guard/：循环健康 guard 家族
|
||||
# guard/ — 循环卫生 guard 家族
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
这组行为 guard 插件会监视 agent loop（智能体循环）中的低效模式，并提醒模型调整方向。这里只有一个**产品**包，不设接口／实现 seam：guard 是现有核心 seam（`tools/post-execute`、`agent/prompt-submit`、`agent/status`）的自包含消费方，并非可替换能力。
|
||||
行为 guard 插件监视 agent loop（智能体循环）中的无效模式，并推动模型回到正轨。guard 是 core seam 的自包含消费方，而非可替换能力。
|
||||
|
||||
| 包 | 职责 | ctx 键 |
|
||||
| 包 | 职责 | ctx key |
|
||||
|---|---|---|
|
||||
| `repeat-tool-guard/` | 当 agent 对完全相同的工具调用反复循环时给出提示 | （监听 `ctx.tools` 的 waterfall，即瀑布式事件） |
|
||||
|
||||
提示以 `additionalContexts` 形式附在 `tools/post-execute` 决策中传递；agent loop 会在该步骤的工具结果之后，将其追加为有日志记录、来源为插件的 `user/message` 事件（参见[工具包](../core/tools)）。因此，guard 告诉模型的所有内容都能从会话日志中重建。
|
||||
| [`repeat-tool-guard/`](repeat-tool-guard/README.md) | 针对重复工具调用的建议性提醒 | 监听工具和 agent 事件 |
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/guard/repeat-tool-guard/README.md
|
||||
README.md: 226dba10239031e8e79bd5698e77c213688ce579
|
||||
README.zh.md: 004c463d8b3b6d3ed6f215e86e59b02fec27cf3f
|
||||
README.md: 4d7b24b1188d021a82ed87b0c721fa539a4e5f0b
|
||||
README.zh.md: b332d579d10af1a55d0bf75207452ae7d15bb7c9
|
||||
|
||||
@@ -27,17 +27,13 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de
|
||||
- **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful: bookkeeping tools interleaved into a loop must not launder it.
|
||||
- **Denied calls count.** Detection sits on `tools/post-execute`, which also runs for calls a `tools/pre-execute` listener denied — a model hammering a denied call is exactly the loop worth breaking.
|
||||
- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no live agent object to key on.
|
||||
- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so a `WeakMap<Agent, Chain>` keys each chain by the live agent object; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain, and object lifetime bounds the weak entry without a disposal listener.
|
||||
- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so a `WeakMap<Agent, Chain>` keys each chain by the live agent object; one agent's repetition never trips another's reminder. A user prompt (`agent/pre-step`) resets the submitting agent's chain, and object lifetime bounds the weak entry without a disposal listener.
|
||||
- **In-memory only.** A session resumed from persistence starts with a fresh chain — the guard is a heuristic nudge, not a logged invariant, later reminders are the accepted cost.
|
||||
|
||||
## Reminder delivery
|
||||
|
||||
Reminders ride the post-execute decision's `additionalContexts` (source `{kind: 'plugin', plugin: 'repeat-tool-guard'}`), never a `content` replacement: the `tool/result` event stays the tool's own output for audit. The loop buffers the context and appends it as an injected `user/message` after the step's tool results, which the session renders as a plain synthetic user message — so the reminder is model-visible, source-attributed, and reconstructable from the session log with no new session event. The guard always delegates via `next()` and prepends its reminder to the downstream decision's context array (both variants — a blocked call still gets the nudge); every entry retains its own source and metadata.
|
||||
|
||||
## Testing
|
||||
|
||||
Unit suites drive a real agent loop against a mock adapter (no network) and cover the chain semantics above to per-file 100%. The snapshot tier owns the transcript surface: a scripted-replay scenario repeats a call five times and pins both reminder tiers (gentle at 3, detailed at 5) as injected `user/message`s in the ACP transcript.
|
||||
|
||||
## Model Experience
|
||||
|
||||
### First-threshold context message
|
||||
|
||||
@@ -27,17 +27,13 @@
|
||||
- **不受跟踪的调用对链透明。** 被 `include`／`exclude` 排除的调用既不递增计数器，也不重置计数器；因此，`grep X → todo_write → grep X` 仍算作连续两次 `grep X`，即使 `todo_write` 已被排除。这正是排除机制的价值：循环中穿插的记录类工具不能掩盖循环。
|
||||
- **被拒绝的调用也计数。** 检测位于 `tools/post-execute`；即便调用被 `tools/pre-execute` 监听器拒绝，该事件也会运行。模型反复尝试被拒绝的调用，恰恰是需要打断的循环。
|
||||
- **忽略没有 agent 的调用。** 直接调用 `ctx.tools.execute()` 的调用方没有需要提醒的模型，也没有可作为键的活跃 agent 对象。
|
||||
- **按 agent 分键。** 工具注册表位于上下文层级，subagent 会交错通过同一个 waterfall（瀑布式事件），因此每条链使用 `WeakMap<Agent, Chain>`，以活跃 agent 对象为键。一个 agent 的重复调用绝不会触发另一个 agent 的提醒。用户提示词（`agent/prompt-submit`）会重置提交该提示词的 agent 链；对象生命周期会自然限制弱引用条目的寿命，无需 dispose（资源释放）监听器。
|
||||
- **按 agent 分键。** 工具注册表位于上下文层级，subagent 会交错通过同一个 waterfall（瀑布式事件），因此每条链使用 `WeakMap<Agent, Chain>`，以活跃 agent 对象为键。一个 agent 的重复调用绝不会触发另一个 agent 的提醒。用户提示词（`agent/pre-step`）会重置提交该提示词的 agent 链；对象生命周期会自然限制弱引用条目的寿命，无需 dispose（资源释放）监听器。
|
||||
- **仅驻留内存。** 从持久化恢复的会话会从一条全新的链开始：guard 是启发式提醒，并非有日志记录的不变量；提醒会延后，这是可接受的代价。
|
||||
|
||||
## 提醒传递
|
||||
|
||||
提醒通过 post-execute 决策中的 `additionalContexts`（来源为 `{kind: 'plugin', plugin: 'repeat-tool-guard'}`）传递，绝不替换 `content`；用于审计的 `tool/result` 事件仍保留工具自己的输出。循环会缓冲这段上下文，并在该步骤的工具结果之后将其作为注入的 `user/message` 追加；会话会将它渲染为普通的合成用户消息。因此，提醒对模型可见、带有来源归属，并且无需增加会话事件即可从会话日志重建。guard 始终通过 `next()` 委派，并将自己的提醒放在下游决策的上下文数组之前（两种结果都适用：被阻止的调用也会收到提醒）；每个条目保留自己的来源和元数据。
|
||||
|
||||
## 测试
|
||||
|
||||
单元测试使用 mock 适配器（无网络）驱动真实 agent loop，并对上述链语义实现逐文件 100% 覆盖率。快照层负责 transcript（文本记录）接口：脚本化回放场景会将同一调用重复 5 次，并在 ACP（Agent Client Protocol）的 transcript 中固定两个提醒层级，即第 3 次的温和提醒和第 5 次的详细提醒；二者均为注入的 `user/message`。
|
||||
|
||||
## 模型体验
|
||||
|
||||
### 首个阈值的上下文消息
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import type { Agent, PromptDecision } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent, PreStepDecision } from '@deepseek-ai/dsh-agent'
|
||||
import { createUserMessage } from '@deepseek-ai/dsh-llm'
|
||||
import type { MessageSource } from '@deepseek-ai/dsh-llm'
|
||||
import type { UserMessage } from '@deepseek-ai/dsh-session'
|
||||
@@ -226,8 +226,8 @@ export function apply(ctx: Context, config: Config): void {
|
||||
// A user interjection changes the context; repetition across it is not a
|
||||
// loop. Pure reset hook: always delegates (attaching nothing, vetoing
|
||||
// nothing).
|
||||
ctx.on('agent/prompt-submit', (agent, _message, _signal, next): Promise<PromptDecision> => {
|
||||
chains.delete(agent)
|
||||
ctx.on('agent/pre-step', (agent, messages, _context, next): Promise<PreStepDecision> => {
|
||||
if (messages.some(message => message.source.kind === 'user')) chains.delete(agent)
|
||||
return next()
|
||||
})
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user