Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id
# Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
This commit is contained in:
@@ -81,10 +81,11 @@ function registerEcho(ctx: Context, name = 'echo'): unknown[] {
|
||||
}
|
||||
|
||||
/** A structural fake of the owning agent: captures session appends. */
|
||||
function fakeAgent(): { agent: Agent; events: { type: string; data: unknown }[] } {
|
||||
function fakeAgent(options: { cwd?: string } = { cwd: '/workspace' }): { agent: Agent; events: { type: string; data: unknown }[] } {
|
||||
const events: { type: string; data: unknown }[] = []
|
||||
const agent = {
|
||||
session: {
|
||||
header: options.cwd === undefined ? {} : { cwd: options.cwd },
|
||||
append: (type: string, data: unknown) => { events.push({ type, data }) },
|
||||
},
|
||||
} as unknown as Agent
|
||||
@@ -476,27 +477,71 @@ describe('the run_code dispatch bridge', () => {
|
||||
expect(dispatch.arguments).toEqual({ value: 'x', when: '1970-01-01T00:00:00.000Z' })
|
||||
})
|
||||
|
||||
it('suppresses sub-call additionalContext (deliberately; pinned)', async () => {
|
||||
it('defers sub-call additionalContexts onto the outer run_code result', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
registerEcho(ctx)
|
||||
ctx.on('tools/post-execute', (exec, _result, next): Promise<PostToolDecision> => {
|
||||
if (exec.name === 'echo') {
|
||||
return Promise.resolve({
|
||||
kind: 'accept' as const,
|
||||
additionalContext: { content: [{ type: 'text' as const, text: 'context for the next request' }], source: { kind: 'plugin' as const, plugin: 'test' } },
|
||||
additionalContexts: [{
|
||||
content: [{ type: 'text' as const, text: `context for ${exec.callId}` }],
|
||||
source: { kind: 'plugin' as const, plugin: 'test' },
|
||||
envelope: 'raw' as const,
|
||||
meta: { callId: exec.callId },
|
||||
}],
|
||||
})
|
||||
}
|
||||
return next()
|
||||
})
|
||||
runtime.behavior = async (request) => {
|
||||
await request.bindings[0]!.functions.echo!({ value: 'x' })
|
||||
await request.bindings[0]!.functions.echo!({ value: 'y' })
|
||||
return { logs: [], value: 'done' }
|
||||
}
|
||||
const result = await runCode(ctx, 'program')
|
||||
expect(result.isError).toBe(false)
|
||||
// The sub-call's context has no safe outlet mid-run; the parent result
|
||||
// must not carry it either.
|
||||
expect(result.additionalContext).toBeUndefined()
|
||||
expect(result.additionalContexts).toEqual([
|
||||
{
|
||||
content: [{ type: 'text', text: 'context for call-1:code:1' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
envelope: 'raw',
|
||||
meta: { callId: 'call-1:code:1' },
|
||||
},
|
||||
{
|
||||
content: [{ type: 'text', text: 'context for call-1:code:2' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
envelope: 'raw',
|
||||
meta: { callId: 'call-1:code:2' },
|
||||
},
|
||||
])
|
||||
})
|
||||
|
||||
it('keeps sub-call contexts when run_code fails after the nested dispatch', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'both' })
|
||||
registerEcho(ctx)
|
||||
ctx.on('tools/post-execute', (exec, _result, next): Promise<PostToolDecision> => {
|
||||
if (exec.name !== 'echo') return next()
|
||||
return Promise.resolve({
|
||||
kind: 'accept',
|
||||
additionalContexts: [{
|
||||
content: [{ type: 'text', text: 'nested context' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
}],
|
||||
})
|
||||
})
|
||||
runtime.behavior = async (request) => {
|
||||
await request.bindings[0]!.functions.echo!({ value: 'x' })
|
||||
return { logs: [], error: { kind: 'exception', message: 'program failed later' } }
|
||||
}
|
||||
|
||||
const result = await runCode(ctx, 'program')
|
||||
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.additionalContexts).toEqual([{
|
||||
content: [{ type: 'text', text: 'nested context' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
}])
|
||||
})
|
||||
|
||||
it('converts a failed run into a structured isError result carrying kind, message, and captured logs', async () => {
|
||||
@@ -670,6 +715,52 @@ describe('the run_code dispatch bridge', () => {
|
||||
expect(dispatch.resultSummary.endsWith('…')).toBe(true)
|
||||
})
|
||||
|
||||
it('normalizes the session workspace root before bounding durable result summaries', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'workspace_path',
|
||||
description: 'Return a path beneath the session workspace.',
|
||||
parameters: {},
|
||||
execute(_args, exec) {
|
||||
const cwd = exec.agent?.session.header.cwd ?? ''
|
||||
return Promise.resolve([{ type: 'text' as const, text: `<path>${cwd}/nested/task.txt</path>\n${'x'.repeat(240)}` }])
|
||||
},
|
||||
}))
|
||||
runtime.behavior = async request => ({
|
||||
logs: [],
|
||||
value: await request.bindings[0]!.functions.workspace_path!({}),
|
||||
})
|
||||
|
||||
const short = fakeAgent({ cwd: '/tmp/workspace' })
|
||||
const long = fakeAgent({ cwd: `/tmp/${'long-segment/'.repeat(30)}workspace` })
|
||||
const shortResult = await runCode(ctx, 'program', { agent: short.agent })
|
||||
const longResult = await runCode(ctx, 'program', { agent: long.agent })
|
||||
const shortDispatch = short.events[0]!.data as SessionEventMap['tool/code-dispatch']
|
||||
const longDispatch = long.events[0]!.data as SessionEventMap['tool/code-dispatch']
|
||||
|
||||
expect(shortResult.content).not.toEqual(longResult.content)
|
||||
expect(shortDispatch.resultSummary).toBe(longDispatch.resultSummary)
|
||||
expect(shortDispatch.resultSummary).toHaveLength(201)
|
||||
expect(shortDispatch.resultSummary).toMatch(/^<path>\.\/nested\/task\.txt<\/path>\n.+…$/)
|
||||
})
|
||||
|
||||
it('leaves result summaries unchanged when a session cwd is absent or is the filesystem root', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
registerEcho(ctx)
|
||||
runtime.behavior = async request => ({
|
||||
logs: [],
|
||||
value: await request.bindings[0]!.functions.echo!({ value: '/workspace/value' }),
|
||||
})
|
||||
|
||||
const absent = fakeAgent({})
|
||||
const root = fakeAgent({ cwd: '/' })
|
||||
await runCode(ctx, 'program', { agent: absent.agent })
|
||||
await runCode(ctx, 'program', { agent: root.agent })
|
||||
|
||||
expect((absent.events[0]!.data as SessionEventMap['tool/code-dispatch']).resultSummary).toBe('echo:/workspace/value')
|
||||
expect((root.events[0]!.data as SessionEventMap['tool/code-dispatch']).resultSummary).toBe('echo:/workspace/value')
|
||||
})
|
||||
|
||||
it('rejects undefined, JSON-throwing, and JSON-unrepresentable binding arguments BEFORE dispatch', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
const calls = registerEcho(ctx)
|
||||
|
||||
Reference in New Issue
Block a user