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

refactor: identify and freeze messages at creation

Browse Source
This commit is contained in:
_Kerman
2026-07-28 13:55:59 +08:00
parent c49c0ba497
commit fbf87e660c
345 changed files with 5220 additions and 2901 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
packages/guard/repeat-tool-guard/src/index.ts
View File

@@ -9,8 +9,9 @@
import type { Context } from 'cordis'
import z from 'schemastery'
import type { Agent, PromptDecision } from '@deepseek-ai/dsh-agent'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import type { MessageSource } from '@deepseek-ai/dsh-llm'
import type { UserMessageData } from '@deepseek-ai/dsh-session'
import type { UserMessage } from '@deepseek-ai/dsh-session'
import type { PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools'
export const name = 'repeat-tool-guard'
@@ -143,7 +144,7 @@ function validateThresholds(values: number[]): number[] {
* Prepend the guard's reminder while preserving every downstream context's
* source and metadata.
*/
function prependContext(ours: UserMessageData, theirs: UserMessageData[] | undefined): UserMessageData[] {
function prependContext(ours: UserMessage, theirs: UserMessage[] | undefined): UserMessage[] {
return [ours, ...theirs ?? []]
}
@@ -185,7 +186,7 @@ export function apply(ctx: Context, config: Config): void {
* same pipeline), and a model hammering a denied call is exactly the loop
* worth breaking.
*/
function observe(exec: ToolExecution): UserMessageData | undefined {
function observe(exec: ToolExecution): UserMessage | undefined {
// A direct `ctx.tools.execute()` caller has no model to remind and no id
// to key on; only agent-loop calls participate.
if (!exec.agent) return undefined
@@ -199,7 +200,7 @@ export function apply(ctx: Context, config: Config): void {
const text = count === thresholds[0]
? GENTLE_REMINDER
: detailedReminder(exec.name, count, previewArguments(canonical, argumentsPreviewChars))
return { content: [{ type: 'text', text }], source: PLUGIN_SOURCE }
return createUserMessage({ content: [{ type: 'text', text }], source: PLUGIN_SOURCE })
}
// Observe-and-enrich, never veto: count first (state advances regardless of
@@ -222,7 +223,7 @@ 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, _content, _source, _signal, next): Promise<PromptDecision> => {
ctx.on('agent/prompt-submit', (agent, _message, _signal, next): Promise<PromptDecision> => {
chains.delete(agent)
return next()
})

48
packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts
View File

@@ -1,6 +1,6 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import { createUserMessage, CallId } from '@deepseek-ai/dsh-llm'
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
@@ -56,7 +56,7 @@ describe('threshold escalation', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
@@ -77,7 +77,7 @@ describe('threshold escalation', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
@@ -99,7 +99,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
@@ -123,7 +123,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
expect(reminders(agent)).toHaveLength(1)
@@ -141,7 +141,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
@@ -162,7 +162,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
@@ -178,7 +178,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
expect(reminders(agent)).toHaveLength(1) // probe was NOT excluded
@@ -194,7 +194,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
expect(reminders(agent)).toHaveLength(1) // all three canonicalize identically
@@ -215,8 +215,8 @@ describe('chain semantics', () => {
]))
const agentA = ctx.agentLoop.create(SessionId('a'), { provider: 'mock-a', model: 'model-a' })
const agentB = ctx.agentLoop.create(SessionId('b'), { provider: 'mock-b', model: 'model-b' })
agentA.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agentB.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agentA.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
agentB.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)])
expect(reminders(agentA)).toHaveLength(0) // 2 repeats < 3, despite B's 3 in the same registry
@@ -234,9 +234,9 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
agent.followup({ content: [{ type: 'text', text: 'again' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'again' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
expect(reminders(agent)).toHaveLength(0)
@@ -256,13 +256,13 @@ describe('chain semantics', () => {
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
first = inner.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
first.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
first.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, first)
await fiber.dispose()
await first.whenIdle()
const second = ctx.agentLoop.create(SessionId('reused'), { provider: 'mock', model: 'mock' })
second.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
second.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, second)
expect(reminders(second)).toHaveLength(0)
@@ -278,7 +278,7 @@ describe('chain semantics', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
expect(reminders(agent)).toHaveLength(1)
@@ -294,7 +294,7 @@ describe('chain semantics', () => {
textResponse('done'),
]))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
expect(reminders(agent)).toHaveLength(0)
@@ -307,7 +307,9 @@ describe('fold onto the downstream decision', () => {
ctx.on('tools/post-execute', async () => ({
kind: 'block' as const,
feedback: [{ type: 'text' as const, text: 'nope' }],
additionalContexts: [{ content: [{ type: 'text' as const, text: 'downstream-ctx' }], source: { kind: 'plugin' as const, plugin: 'test' } }],
additionalContexts: [createUserMessage({
content: [{ type: 'text' as const, text: 'downstream-ctx' }], source: { kind: 'plugin' as const, plugin: 'test' },
})],
}))
const adapter = new MockAdapter([
toolCallResponse('c1', 'probe', { q: 1 }),
@@ -316,7 +318,7 @@ describe('fold onto the downstream decision', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
@@ -329,8 +331,8 @@ describe('fold onto the downstream decision', () => {
expect(found[2]).toEqual({ text: 'downstream-ctx', source: { kind: 'plugin', plugin: 'test' } })
// The block's feedback reached the tool result unchanged.
const results = [...agent.session.events].filter((e): e is SessionEvent<'tool/result'> => e.type === 'tool/result')
expect(results.every(r => r.data.isError)).toBe(true)
expect(results[1]!.data.content).toEqual([{ type: 'text', text: 'nope' }])
expect(results.every(r => r.data.message.content[0].isError)).toBe(true)
expect(results[1]!.data.message.content[0].content).toEqual([{ type: 'text', text: 'nope' }])
})
it('preserves a downstream canonical value replacement while folding', async () => {
@@ -346,14 +348,14 @@ describe('fold onto the downstream decision', () => {
])
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.followup({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const found = reminders(agent)
expect(found).toHaveLength(1)
expect(found[0]!.text).toContain('repeating the exact same tool call')
const results = [...agent.session.events].filter((e): e is SessionEvent<'tool/result'> => e.type === 'tool/result')
expect(results[1]!.data.content).toEqual([{ type: 'text', text: 'replaced' }])
expect(results[1]!.data.message.content[0].content).toEqual([{ type: 'text', text: 'replaced' }])
})
})