Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: unify agent and session identity

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-14 01:59:21 +08:00
parent 7a33ee94be
commit 709cc7200e
105 changed files with 899 additions and 948 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/guard/repeat-tool-guard/README.md
View File

@@ -24,8 +24,8 @@ 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 `AgentId` to key on.
- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so chains are keyed by `AgentId`; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain; agent disposal drops its state.
- **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.
- **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

19
packages/guard/repeat-tool-guard/src/index.ts
View File

@@ -22,7 +22,7 @@
* exclude: [todo_write] # tool-name patterns transparent to the chain
* ```
*
* Chain state is keyed per {@link AgentId} — the tool registry is a
* Chain state is keyed by the live agent object — the tool registry is a
* context-level singleton whose waterfalls interleave every agent's calls, so
* a shared counter would let one agent's repetition trip another's reminder.
* State is in-memory only: a session resumed from persistence starts with a
@@ -37,7 +37,7 @@
import type { Context } from 'cordis'
import z from 'schemastery'
import type { AgentId, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
import type { Agent, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
import type { MessageSource } from '@deepseek-ai/dsh-llm'
import type { PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools'
@@ -202,9 +202,7 @@ export function apply(ctx: Context, config: Config): void {
throw new Error(`repeat-tool-guard: invalid argumentsPreviewChars ${argumentsPreviewChars} — must be an integer >= 1`)
}
// TODO(agent-keyed-repeat-chain): key a WeakMap by the Agent itself; that
// removes the disposal-only status listener and cannot collide on id reuse.
const chains = new Map<AgentId, Chain>()
const chains = new WeakMap<Agent, Chain>()
/** Whether a tool participates in the chain (untracked calls are transparent: they neither count nor reset). */
function tracked(toolName: string): boolean {
@@ -227,9 +225,9 @@ export function apply(ctx: Context, config: Config): void {
if (!tracked(exec.name)) return undefined
const canonical = canonicalize(exec.arguments)
const key = JSON.stringify([exec.name, canonical])
const chain = chains.get(exec.agent.id)
const chain = chains.get(exec.agent)
const count = chain !== undefined && chain.key === key ? chain.count + 1 : 1
chains.set(exec.agent.id, { key, count })
chains.set(exec.agent, { key, count })
if (!thresholdSet.has(count)) return undefined
const text = count === thresholds[0]
? GENTLE_REMINDER
@@ -259,12 +257,7 @@ export function apply(ctx: Context, config: Config): void {
// loop. Pure reset hook: always delegates (attaching nothing, vetoing
// nothing).
ctx.on('agent/prompt-submit', (agent, _content, _source, next): Promise<PromptDecision> => {
chains.delete(agent.id)
chains.delete(agent)
return next()
})
// Drop state when an agent goes away, bounding the map over harness lifetime.
ctx.on('agent/status', (agent, status) => {
if (status === 'disposed') chains.delete(agent.id)
})
}

39
packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts
View File

@@ -1,10 +1,11 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService, { CallId } from '@deepseek-ai/dsh-llm'
import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard'
import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard'
@@ -57,7 +58,7 @@ describe('threshold escalation', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -78,7 +79,7 @@ describe('threshold escalation', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -100,7 +101,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -124,7 +125,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -142,7 +143,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -163,7 +164,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -179,7 +180,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -195,7 +196,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -215,8 +216,8 @@ describe('chain semantics', () => {
toolCallResponse('b3', 'probe', { q: 1 }),
textResponse('done'),
]))
const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' })
const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' })
const agentA = ctx.agentLoop.create(SessionId('a'), { model: 'mock-a' })
const agentB = ctx.agentLoop.create(SessionId('b'), { model: 'mock-b' })
agentA.send([{ type: 'text', text: 'go' }])
agentB.send([{ type: 'text', text: 'go' }])
await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)])
@@ -235,7 +236,7 @@ describe('chain semantics', () => {
textResponse('turn two done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
agent.send([{ type: 'text', text: 'again' }])
@@ -256,14 +257,14 @@ describe('chain semantics', () => {
// (the loop.spec pattern): a child plugin fiber owns `first`.
let first!: ReactLoopAgent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' })
first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' })
}, { inject: ['agentLoop'] }))
first.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, first)
await fiber.dispose()
await first.done
const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' })
const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' })
second.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, second)
@@ -279,7 +280,7 @@ describe('chain semantics', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -295,7 +296,7 @@ describe('chain semantics', () => {
toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2
textResponse('done'),
]))
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -317,7 +318,7 @@ describe('fold onto the downstream decision', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -348,7 +349,7 @@ describe('fold onto the downstream decision', () => {
textResponse('done'),
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)