mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification
# Conflicts: # .agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml # .agents/notes/implemented/architecture/2026-07-31-goal-owned-durable-events.i18n.yaml # .agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml # .agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.i18n.yaml # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # 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/code-mode-workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/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-fork/session.1.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-multi/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl # examples/acp-agent/tests/snapshots/workspace-context/session.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/headless-agent/tests/snapshots/pty-tools/session.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl # packages/acp/acp/README.i18n.yaml # packages/acp/acp/src/index.ts # packages/client/connection/src/client/index.ts # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/runtime/src/client/sessions/session.ts # packages/client/runtime/tests/queue-store.spec.ts # packages/client/ui-conversation/src/client/input/contract.ts # packages/client/ui-goal/README.i18n.yaml # packages/compact/compact-basic/src/index.ts # packages/context/time-context/tests/time-context.spec.ts # packages/context/tmux-context/tests/tmux-context.spec.ts # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/README.md # packages/core/agent-loop/README.zh.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent/README.i18n.yaml # packages/core/agent/README.md # packages/core/agent/README.zh.md # packages/core/agent/src/types.ts # packages/core/session/README.i18n.yaml # packages/core/session/README.md # packages/core/session/README.zh.md # packages/goal/command-goal/tests/command-goal.spec.ts # packages/goal/goal/tests/goal.spec.ts # packages/goal/tool-goal/README.i18n.yaml # packages/goal/tool-goal/README.md # packages/goal/tool-goal/README.zh.md # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/events.schema.ts # packages/host/apiproxy/src/api/events.ts # packages/host/apiproxy/src/api/rpc.ts # packages/host/apiproxy/tests/api-proxy-commands.spec.ts # packages/host/apiproxy/tests/api-proxy-projections.spec.ts # packages/host/apiproxy/tests/rpc-schemas.spec.ts # packages/pty/pty-local/tests/index.spec.ts # packages/pty/pty-local/tests/local.spec.ts # packages/pty/tool-pty/tests/loader-composition.spec.ts # packages/pty/tool-pty/tests/tools.spec.ts # packages/session-persistence/session-checkpoint-policy/src/index.ts # packages/session-persistence/session-persistence/tests/coordinator-contract.ts # packages/skill/tool-skill/tests/tool-skill.spec.ts # packages/subagent/subagent-inprocess/README.i18n.yaml # packages/subagent/subagent-inprocess/README.md # packages/subagent/subagent-inprocess/README.zh.md # packages/subagent/subagent-inprocess/src/index.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/support/acp-snapshot/src/harness.ts # packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
_Kerman
@@ -8,7 +8,7 @@ import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import { GoalId } from '@deepseek-ai/dsh-goal'
|
||||
import type { GoalRef, GoalView } from '@deepseek-ai/dsh-goal'
|
||||
import { HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import { createUserMessage, HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { GenericCallView } from '@deepseek-ai/dsh-tools'
|
||||
import type {} from '@deepseek-ai/dsh-system-prompt'
|
||||
@@ -17,6 +17,7 @@ import {
|
||||
goalToolExecution,
|
||||
requireDirectHuman,
|
||||
} from './authority.ts'
|
||||
import { renderWrapupContext } from './wrapup.ts'
|
||||
|
||||
export const name = 'tool-goal'
|
||||
export const inject = ['agents', 'goals', 'tools', 'systemPrompt']
|
||||
@@ -309,7 +310,14 @@ export function apply(ctx: Context, config: Config): void {
|
||||
code: 'model-reported',
|
||||
message: args.blocked_reason as string,
|
||||
})
|
||||
if (authority.kind === 'goal-round') exec.concludeTurn()
|
||||
if (authority.kind === 'goal-round') {
|
||||
exec.deferContext(createUserMessage({
|
||||
content: args.action === 'complete'
|
||||
? renderWrapupContext(goal.objective)
|
||||
: renderWrapupContext(goal.objective, args.blocked_reason as string),
|
||||
source: { kind: 'plugin', plugin: 'tool-goal' },
|
||||
}))
|
||||
}
|
||||
return Promise.resolve(goalValue(goal))
|
||||
},
|
||||
presentCall: args => present(
|
||||
|
||||
41
packages/goal/tool-goal/src/wrapup.ts
Normal file
41
packages/goal/tool-goal/src/wrapup.ts
Normal file
@@ -0,0 +1,41 @@
|
||||
/** Model-visible wrap-up instruction for a terminal autonomous goal update. */
|
||||
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
|
||||
const GROUNDING =
|
||||
'Report only what earlier rounds and tool results in this session actually establish; '
|
||||
+ 'when a detail is not in the session, say so instead of inventing it. '
|
||||
|
||||
/**
|
||||
* Render the closing-message instruction injected after an autonomous goal
|
||||
* round reports `complete` or `blocked`, replacing the former hard turn stop
|
||||
* so the model still addresses the user once before the turn ends.
|
||||
* @param objective - the terminal goal's objective, echoed for grounding.
|
||||
* @param blockedReason - the validated report for `blocked`; omitted for `complete`.
|
||||
* @returns a fresh one-block context for `ToolRunContext.deferContext()`.
|
||||
*/
|
||||
export function renderWrapupContext(objective: string, blockedReason?: string): ContentBlock[] {
|
||||
const heading = `Objective: ${JSON.stringify(objective)}\n`
|
||||
const text = blockedReason === undefined
|
||||
? '<goal_complete>\n'
|
||||
+ heading
|
||||
+ 'The goal is marked complete and this autonomous run is ending. Write the closing '
|
||||
+ 'message to the user now: state the outcome, summarize what was done and how it was '
|
||||
+ 'verified, and point to the concrete results (files, commits, or other artifacts). '
|
||||
+ GROUNDING
|
||||
+ 'Note anything the user should review or do next. Address the user directly. Do not '
|
||||
+ "call any more tools in this run; further work waits for the user's next instruction.\n"
|
||||
+ '</goal_complete>'
|
||||
: '<goal_blocked>\n'
|
||||
+ heading
|
||||
+ `Blocked: ${JSON.stringify(blockedReason)}\n`
|
||||
+ 'The goal is marked blocked and this autonomous run is ending. Write the closing '
|
||||
+ 'message to the user now: state what has been completed so far, describe the concrete '
|
||||
+ 'blocking condition and what you tried, and say exactly what you need from the user to '
|
||||
+ 'continue. '
|
||||
+ GROUNDING
|
||||
+ 'Address the user directly. Do not call any more tools in this run; further work '
|
||||
+ "waits for the user's next instruction.\n"
|
||||
+ '</goal_blocked>'
|
||||
return [{ type: 'text', text }]
|
||||
}
|
||||
@@ -34,7 +34,7 @@ function stubAgent(rawId: string, supplied?: Session): StubAgent {
|
||||
ctx: new Context(),
|
||||
send: () => {},
|
||||
followup: () => {},
|
||||
steer: () => {},
|
||||
steer: () => ({ outcome: Promise.resolve({ status: 'rejected' as const }) }),
|
||||
inject(input) {
|
||||
this.inbox.append('next-step', input)
|
||||
},
|
||||
@@ -351,7 +351,7 @@ describe('goal tool state transitions', () => {
|
||||
expect(goal).toMatchObject({ phase: 'active', revision: 4 })
|
||||
})
|
||||
|
||||
it('terminal-stops an autonomous completion but leaves a human pause interactive', async () => {
|
||||
it('injects one wrap-up instruction for an autonomous completion but leaves a human pause interactive', async () => {
|
||||
const { ctx, root } = await harness()
|
||||
const humanTurn = openTurn(root, { kind: 'user' })
|
||||
const created = ctx.goals.create(root.agent, { objective: 'pause cleanly' })
|
||||
@@ -360,6 +360,7 @@ describe('goal tool state transitions', () => {
|
||||
}, root.agent)
|
||||
expect(resultGoal(paused)).toMatchObject({ phase: 'paused' })
|
||||
expect(paused.concludesTurn).toBeUndefined()
|
||||
expect(paused.additionalContexts).toBeUndefined()
|
||||
const resumed = resultGoal(await execute(ctx, 'update_goal', {
|
||||
goal_id: created.id, revision: 2, action: 'resume',
|
||||
}, root.agent))
|
||||
@@ -372,7 +373,27 @@ describe('goal tool state transitions', () => {
|
||||
goal_id: created.id, revision: resumed['revision'], action: 'complete',
|
||||
}, root.agent)
|
||||
expect(resultGoal(complete)).toMatchObject({ phase: 'complete' })
|
||||
expect(complete.concludesTurn).toBe(true)
|
||||
expect(complete.concludesTurn).toBeUndefined()
|
||||
const contexts = complete.additionalContexts ?? []
|
||||
expect(contexts).toHaveLength(1)
|
||||
expect(contexts[0]?.source).toEqual({ kind: 'plugin', plugin: 'tool-goal' })
|
||||
const block = contexts[0]?.content[0]
|
||||
if (block?.type !== 'text') throw new Error('expected one text wrap-up block')
|
||||
expect(block.text).toContain('<goal_complete>')
|
||||
expect(block.text).toContain('"pause cleanly"')
|
||||
expect(block.text).toContain("Do not call any more tools in this run; further work waits for the user's next instruction.")
|
||||
})
|
||||
|
||||
it('completes without a wrap-up instruction under direct human authority', async () => {
|
||||
const { ctx, root } = await harness()
|
||||
openTurn(root, { kind: 'user' })
|
||||
const created = ctx.goals.create(root.agent, { objective: 'finish now' })
|
||||
const complete = await execute(ctx, 'update_goal', {
|
||||
goal_id: created.id, revision: created.revision, action: 'complete',
|
||||
}, root.agent)
|
||||
expect(resultGoal(complete)).toMatchObject({ phase: 'complete' })
|
||||
expect(complete.concludesTurn).toBeUndefined()
|
||||
expect(complete.additionalContexts).toBeUndefined()
|
||||
})
|
||||
|
||||
it('rearms a restored active goal only after a new direct human prompt', async () => {
|
||||
@@ -554,6 +575,14 @@ describe('goal tool state transitions', () => {
|
||||
blockedReason: { code: 'model-reported', message: 'The required credential is still unavailable.' },
|
||||
roundsStarted: 3,
|
||||
})
|
||||
expect(blocked.concludesTurn).toBeUndefined()
|
||||
const contexts = blocked.additionalContexts ?? []
|
||||
expect(contexts).toHaveLength(1)
|
||||
const block = contexts[0]?.content[0]
|
||||
if (block?.type !== 'text') throw new Error('expected one text wrap-up block')
|
||||
expect(block.text).toContain('<goal_blocked>')
|
||||
expect(block.text).toContain('The required credential is still unavailable.')
|
||||
expect(block.text).toContain("Do not call any more tools in this run; further work waits for the user's next instruction.")
|
||||
})
|
||||
|
||||
it('lets direct human authority block before the model threshold', async () => {
|
||||
@@ -574,5 +603,7 @@ describe('goal tool state transitions', () => {
|
||||
},
|
||||
roundsStarted: 0,
|
||||
})
|
||||
expect(blocked.concludesTurn).toBeUndefined()
|
||||
expect(blocked.additionalContexts).toBeUndefined()
|
||||
})
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user