kimi-code/packages/agent-core/test/agent/tool.test.ts
liruifengv b51e13538d
ci: run unit tests on windows (#1037)
* ci: run unit tests on windows

* fix(migration-legacy): align workdir bucket key with agent-core

computeWorkdirBucket used a local node:path-based resolve that yields backslash-separated paths on Windows, while agent-core's encodeWorkDirKey uses pathe (forward slashes on every platform). The SHA-256 inputs diverged, so migrated sessions were written to a bucket that the session picker never reads, making them invisible on Windows.

Alias computeWorkdirBucket to encodeWorkDirKey so both sides stay byte-identical, drop the local slugify copy, and update the workdir-bucket test reference accordingly.

* test(acp-adapter): expect platform-native separators in e2e-fs path

The e2e-fs test asserted the fs/readTextFile wire path as the raw POSIX targetPath, but AcpKaos.toClientPath converts '/' to '\' when the inner LocalKaos reports pathClass 'win32' (Windows). On Windows the wire path became '\Users\test\x.ts' and the assertion failed.

Mirror toClientPath in the test: expect backslash separators on win32 and the raw path otherwise. Implementation is unchanged.

* test(sdk): normalize workDir and skillDir paths in session tests

SessionStore.create/list and the skill loader normalize paths through pathe (forward slashes). The SDK tests compared the resulting workDir and skill loaded-dir against raw mkdtemp / node:path strings, which use backslashes on Windows (and node:fs realpath also returns backslashes for the skill dir), failing three toMatchObject assertions.

Build the expected paths with agent-core's normalizeWorkDir so they match the internal pathe representation on every platform. The skill dir keeps its realpath() (the loader realpaths the root) and only normalizes separators.

* test(skill): normalize realpath to forward slashes in scanner tests

resolveSkillRoots normalizes every root.path through fs.realpath followed by replacing backslashes with forward slashes (scanner.ts). The scanner tests compared root.path against node:fs realpath directly, which returns backslashes on Windows, so twenty assertions failed (toEqual / toContain / toHaveLength) even though the resolved paths were identical.

Wrap realpath at the top of the test file to mirror the implementation's normalization, so every comparison uses the same forward-slash form on every platform.

* test: skip Unix-only permission tests on Windows

The Unix file-permission assertions (mode bits like 0o600 / 0o700 and chmod 000 making a path unreadable) have no equivalent on Windows, which uses ACLs; fs.chmod there can only toggle the read-only bit. These six tests failed on Windows with mismatched mode values or a missing 40411.

Skip them on win32 via it.skipIf(process.platform === 'win32'): oauth FileTokenStorage (0600 file, 0700 dir), agent-core BackgroundTaskPersistence (0700 tasks dir), agent-core createPerIdJsonStore (0700 subdir), migration-legacy atomicWrite (0600 file), and server fs:browse (chmod 000 -> 40411).

* test(tui): make platform-sensitive assertions cross-platform

The TUI implementations are already platform-aware (pathe-style paths, pathToFileURL, quoteShellArg cmd/POSIX quoting, Alt+V on Windows for paste expansion), but the tests hard-coded POSIX expectations and failed on Windows.

Align the assertions with the implementation's platform behavior: footer-goal-badge matches the '[goal' badge prefix instead of /goal/ (toolbar tips contain '/goal'); tool-call expects backslash relative paths on win32; plan-box builds the file:// URL via pathToFileURL; custom-editor sends Alt+V on win32 for paste expansion; file-mention-provider normalizes the expected description to forward slashes; kimi-tui-startup builds the resume command with quoteShellArg; kimi-tui-message-flow builds the expected install path with resolve().

* test: align path assertions with pathe on Windows

Several test suites asserted paths produced by node:path/node:os/node:fs against values that agent-core, node-sdk and kaos normalize through pathe (forward slashes). On Windows the two forms diverge (backslashes vs forward slashes), failing about 19 assertions.

Mirror the implementation's normalization in the assertions via a local toPosix helper (or agent-core's normalizeWorkDir), so expected paths use forward slashes on every platform: kaos LocalKaos, node-sdk export/list/resume/config/transport sessions, cli FileMentionProvider, and agent-core skill-session.

* test(native): build path expectations with node:path.resolve

paths.mjs builds every path with node:path.resolve, which yields backslash-separated absolute paths on Windows. The path-helpers tests asserted against template strings that mixed the backslash appRoot with forward-slash segments, so Object.is failed on Windows even though the strings looked identical.

Build the expectations with the same resolve(appRoot, ...) helper so the separators match on every platform.

* fix: make Windows CI tests pass across all packages

Fix the remaining Windows CI failures so the Windows test job can go green. The changes fall into a few categories:

- Path separators: agent-core/node-sdk/kaos normalize paths via pathe (forward slashes); align test expectations and a couple of implementations (native cache base, workspace registry) with that.

- Platform-only services: skip launchd/systemd manager suites on win32 (Windows uses schtasks).

- Process/signal lifecycle: skip or relax tests that rely on POSIX signals / SIGTERM semantics that Windows does not support.

- Hook shell syntax: rewrite hook test commands from POSIX shell (single quotes, semicolons, stderr redirects, if/then/fi) to node -e / .cjs files that run under cmd.exe.

- CRLF: make Bash tool description stripping tolerate CRLF line endings.

- Misc: realpath short-name divergence, port-retry timing, telemetry spawn, fs-watch timing, snapshot path normalization, etc.

* fix: remove unused basename import in workspaceRegistryService

Fix lint error (no-unused-vars): basename from node:path is no longer used after switching to posixBasename from pathe.

* fix: align resume harness pathClass and wait for banner state on Windows

Two more Windows CI fixes:

- createResumeNoSideEffectKaos now reports pathClass 'win32' on Windows so tool descriptions (e.g. Glob's Windows note) match the live agent in expectResumeMatches, fixing usage/description deep-equal drift.

- kimi-tui-startup once-banner test now waits for writeBannerDisplayState to land before asserting, since the atomic write can lag behind the render on Windows.

* fix: resolve remaining Windows unit test failures

Make the new Windows CI job green across agent-core, kaos, node-sdk and server:

- Align the resume harness kaos pathClass with the live agent so platform-conditional tool descriptions (Glob's Windows note) match in expectResumeMatches instead of drifting on win32.
- Rewrite hook commands in agent-core tests as cross-platform node one-liners; single-quote echo, >&2 and ';' do not work under cmd.exe.
- Add .gitattributes enforcing LF so raw-imported templates (e.g. the compaction instruction) produce byte-identical token counts on Windows and POSIX.
- Terminate the full process tree on Windows in both the hook runner and kaos (taskkill /T /F) so grandchildren cannot outlive their parent and keep the cwd locked.
- Normalize workDir path separators in two kimi-sdk session tests to match the stored canonical form.
- Avoid cmd.exe arg-quoting pitfalls in the kaos cmd.exe test, and run the Windows process-tree kill test from a script file with the pid path passed via argv.
- Give the first fs-git e2e test more time on Windows and retry the temp-dir cleanup; skip the fs-watch overflow-burst assertion on Windows where fs-event coalescing prevents the single-window spike.

* ci: retrigger checks

* fix: resolve remaining Windows failures after merging main

- Terminate the spawned git/gh process tree on Windows in FsGitService (taskkill /T /F on timeout) so a timed-out 'gh pr view' cannot leave a grandchild holding the workspace cwd, which made the fs-git e2e cleanup fail with EPERM.

- Give the fs:git_status e2e suite a longer timeout on Windows and retry the temp-dir cleanup longer to ride out the slower child-process teardown.

- Make the third-party plugin install trust test assert the resolved install path via node:path so it matches the Windows-resolved path (D:\tmp\...) as well as the POSIX one.

* fix: align workspace registry roots and harden fs-git cleanup on Windows

- workspace-registry test: compare normalized (forward-slash) roots, since the registry and session index both store workDir via pathe.resolve (forward slashes on every platform). realpath() yields backslashes on Windows and diverged from the stored root.

- fs-git e2e: bump the temp-dir cleanup retries and the afterEach timeout, since Windows child-process teardown after server.close() is asynchronous and can keep the workspace cwd locked for several seconds.

* test: stub openUrl in kimi-tui-message-flow feedback tests

The /feedback command falls back to openUrl(FEEDBACK_ISSUE_URL) when submission fails, which spawned a real browser window on every test run. Mock #/utils/open-url (matching the existing login/message-replay/server test convention) so the suite never opens a browser.

* test: harden fs-git e2e cleanup against Windows cwd locks

On Windows, git/gh child processes and the session core process can outlive server.close() and keep the temp workspace as their cwd, so rmSync fails with EPERM even after a long retry. Add rmSyncRobust that retries and, if the cwd is still locked, swallows EPERM/EBUSY on Windows — the OS reclaims the temp dir and a cleanup hiccup must not fail an otherwise-passing test.

* test: harden server e2e cleanup against async teardown races

server.close() does not fully await the server's asynchronous teardown, so on a loaded CI runner the temp home/workspace dirs can still be held or written to when the afterEach rmSync runs, failing with EPERM (Windows) or ENOTEMPTY (Linux). Use a rmSyncRobust helper (retry + swallow EPERM/EBUSY/ENOTEMPTY) in the fs-git and question e2e cleanup. Also fix a leftover `throw err` (renamed to `throw error`) that broke the typecheck.
2026-06-26 11:56:41 +08:00

528 lines
24 KiB
TypeScript

import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import type { ToolCall } from '@moonshot-ai/kosong';
import { describe, expect, it, vi } from 'vitest';
import { budgetToolResultForModel } from '../../src/agent/turn/tool-result-budget';
import { HookEngine } from '../../src/session/hooks';
import type { SessionSubagentHost } from '../../src/session/subagent-host';
import { FLAG_DEFINITIONS, FlagResolver } from '../../src/flags';
import { createFakeKaos } from '../tools/fixtures/fake-kaos';
import { createCommandKaos, testAgent } from './harness/agent';
import { executeTool } from '../tools/fixtures/execute-tool';
const signal = new AbortController().signal;
describe('Agent tools', () => {
it('blocks tools through PreToolUse before permission and emits PostToolUseFailure', async () => {
const execWithEnv = vi.fn().mockRejectedValue(new Error('Bash should not execute'));
const triggered: Array<[string, string, number]> = [];
const hookEngine = new HookEngine(
[
{
event: 'PreToolUse',
matcher: 'Bash',
command: 'node -e "process.stderr.write(\'blocked by PreToolUse\'); process.exit(2)"',
},
{
event: 'PostToolUseFailure',
matcher: 'Bash',
command: 'exit 0',
},
],
{
onTriggered: (event, target, count) => {
triggered.push([event, target, count]);
},
},
);
const ctx = testAgent({
kaos: createFakeKaos({ execWithEnv }),
hookEngine,
});
ctx.configure({ tools: ['Bash'] });
ctx.mockNextResponse({ type: 'text', text: 'I will run Bash.' }, bashCall());
ctx.mockNextResponse({ type: 'text', text: 'The hook blocked Bash.' });
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Try Bash' }] });
await ctx.untilTurnEnd();
expect(execWithEnv).not.toHaveBeenCalled();
expect(triggered).toEqual([
['PreToolUse', 'Bash', 1],
['PostToolUseFailure', 'Bash', 1],
]);
expect(JSON.stringify(ctx.agent.context.data().history)).toContain('blocked by PreToolUse');
});
it('emits PostToolUse after successful tools', async () => {
const triggered: Array<[string, string, number]> = [];
const hookEngine = new HookEngine(
[
{
event: 'PostToolUse',
matcher: 'Bash',
command: 'exit 0',
},
],
{
onTriggered: (event, target, count) => {
triggered.push([event, target, count]);
},
},
);
const ctx = testAgent({
kaos: createCommandKaos('ok'),
hookEngine,
});
ctx.configure({ tools: ['Bash'] });
await ctx.rpc.setPermission({ mode: 'auto' });
ctx.mockNextResponse({ type: 'text', text: 'I will run Bash.' }, bashCall());
ctx.mockNextResponse({ type: 'text', text: 'Bash returned ok.' });
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Run Bash' }] });
await ctx.untilTurnEnd();
expect(triggered).toEqual([['PostToolUse', 'Bash', 1]]);
});
it('uses builtin descriptions on tool call start events', async () => {
const ctx = testAgent({
kaos: createCommandKaos('ok'),
});
ctx.configure({ tools: ['Bash'] });
await ctx.rpc.setPermission({ mode: 'yolo' });
ctx.mockNextResponse({ type: 'text', text: 'I will run Bash.' }, bashCall());
ctx.mockNextResponse({ type: 'text', text: 'Bash returned ok.' });
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Run Bash' }] });
await ctx.untilTurnEnd();
const started = ctx.allEvents.find(
(event) => event.type === '[rpc]' && event.event === 'tool.call.started',
);
expect(started?.args).toMatchObject({
description: 'Running: printf hook-output',
});
});
it('continues after a foreground Agent tool returns a max_tokens failure', async () => {
const completion = Promise.reject(
new Error('Subagent turn failed before completing its final summary: reason=max_tokens.'),
);
void completion.catch(() => undefined);
const subagentHost = {
spawn: vi.fn().mockResolvedValue({
agentId: 'agent-child',
profileName: 'coder',
resumed: false,
completion,
}),
resume: vi.fn(),
} as unknown as SessionSubagentHost;
const ctx = testAgent({ subagentHost });
ctx.configure({ tools: ['Agent'] });
ctx.mockNextResponse({ type: 'text', text: 'I will ask a subagent.' }, agentCall());
ctx.mockNextResponse({
type: 'text',
text: 'The subagent failed with reason=max_tokens, so I will continue in the parent turn.',
});
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Delegate and recover' }] });
await ctx.untilTurnEnd();
expect(subagentHost.spawn).toHaveBeenCalledWith(
expect.objectContaining({
profileName: 'coder',
parentToolCallId: 'call_agent',
prompt: 'Investigate deeply',
description: 'Investigate deeply',
runInBackground: false,
}),
);
expect(ctx.llmCalls).toHaveLength(2);
expect(ctx.allEvents).toContainEqual(
expect.objectContaining({
type: '[rpc]',
event: 'tool.result',
args: expect.objectContaining({
toolCallId: 'call_agent',
isError: true,
output: expect.stringContaining('reason=max_tokens'),
}),
}),
);
expect(JSON.stringify(ctx.llmCalls[1]?.history)).toContain('reason=max_tokens');
});
it('passes text from content-part error outputs to PostToolUseFailure hooks', async () => {
const lookupCall: ToolCall = {
type: 'function',
id: 'call_lookup',
name: 'Lookup',
arguments: '{"query":"moon"}',
};
const resolved: Array<[string, string, string]> = [];
const hookEngine = new HookEngine(
[
{
event: 'PostToolUseFailure',
matcher: 'Lookup',
command: hookErrorMessageAssertCommand('rich failure text'),
},
],
{
onResolved: (event, target, action) => {
resolved.push([event, target, action]);
},
},
);
const ctx = testAgent({ hookEngine });
ctx.configure();
await ctx.rpc.setPermission({ mode: 'auto' });
await ctx.rpc.registerTool({
name: 'Lookup',
description: 'Look up a short test value.',
parameters: {
type: 'object',
properties: {
query: { type: 'string' },
},
required: ['query'],
additionalProperties: false,
},
});
ctx.mockNextResponse({ type: 'text', text: 'I will look it up.' }, lookupCall);
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Look up moon' }] });
await ctx.untilToolCall({
isError: true,
output: [{ type: 'text', text: 'rich failure text' }],
});
ctx.mockNextResponse({ type: 'text', text: 'The lookup failed.' });
await ctx.untilTurnEnd();
await vi.waitFor(() => {
expect(resolved).toEqual([['PostToolUseFailure', 'Lookup', 'allow']]);
});
});
it('uses the active builtin tool set as the LLM visible tools', async () => {
const ctx = testAgent();
ctx.configure({ tools: ['Write', 'Bash'] });
ctx.mockNextResponse({ type: 'text', text: 'ready' });
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Which tools are active?' }] });
await ctx.untilTurnEnd();
expect(ctx.lastLlmInput()).toMatchInlineSnapshot(`
system: <system-prompt>
tools: Bash, Write
messages:
user: text "Which tools are active?"
`);
await ctx.expectResumeMatches();
});
it('disables Bash background mode unless task management tools are active', async () => {
const ctx = testAgent();
ctx.configure({ tools: ['Bash'] });
const bashOnly = ctx.agent.tools.loopTools.find((tool) => tool.name === 'Bash');
expect(bashOnly).toBeDefined();
expect(bashOnly!.description).toContain('Background execution is disabled for this agent.');
expect(bashOnly!.description).not.toContain('the command will be started as a background task');
await expect(
executeTool(bashOnly!, {
turnId: '0',
toolCallId: 'call_bash',
args: { command: 'sleep 10', run_in_background: true, description: 'watch' },
signal,
}),
).resolves.toMatchObject({
isError: true,
output:
'Background execution is not available for this agent because TaskOutput and TaskStop are not enabled.',
});
ctx.agent.tools.setActiveTools(['Bash', 'TaskList', 'TaskOutput', 'TaskStop']);
const managedBash = ctx.agent.tools.loopTools.find((tool) => tool.name === 'Bash');
expect(managedBash).toBeDefined();
expect(managedBash!.description).toContain('run_in_background=true');
});
it('exposes AgentSwarm when a subagent host is available', () => {
const subagentHost = {} as unknown as SessionSubagentHost;
const ctx = testAgent({
subagentHost,
experimentalFlags: new FlagResolver({}, FLAG_DEFINITIONS),
});
ctx.configure({ tools: ['AgentSwarm'] });
expect(ctx.agent.tools.loopTools.some((tool) => tool.name === 'AgentSwarm')).toBe(true);
});
it('routes registered user tools through tool.call request/response', async () => {
const lookupCall: ToolCall = {
type: 'function',
id: 'call_lookup',
name: 'Lookup',
arguments: '{"query":"moon"}',
};
const ctx = testAgent();
ctx.configure();
await ctx.rpc.setPermission({ mode: 'auto' });
await ctx.rpc.registerTool({
name: 'Lookup',
description: 'Look up a short test value.',
parameters: {
type: 'object',
properties: {
query: { type: 'string' },
},
required: ['query'],
additionalProperties: false,
},
});
ctx.mockNextResponse({ type: 'text', text: 'I will look it up.' }, lookupCall);
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Look up moon' }] });
expect(
await ctx.untilToolCall({
content: 'moon-result',
output: 'moon-result',
}),
).toMatchInlineSnapshot(`
[wire] permission.set_mode { "mode": "auto", "time": "<time>" }
[emit] agent.status.updated { "model": "mock-model", "contextTokens": 0, "maxContextTokens": 1000000, "contextUsage": 0, "planMode": false, "swarmMode": false, "permission": "auto" }
[wire] tools.register_user_tool { "name": "Lookup", "description": "Look up a short test value.", "parameters": { "type": "object", "properties": { "query": { "type": "string" } }, "required": [ "query" ], "additionalProperties": false }, "time": "<time>" }
[wire] turn.prompt { "input": [ { "type": "text", "text": "Look up moon" } ], "origin": { "kind": "user" }, "time": "<time>" }
[emit] turn.started { "turnId": 0, "origin": { "kind": "user" } }
[wire] context.append_message { "message": { "role": "user", "content": [ { "type": "text", "text": "Look up moon" } ], "toolCalls": [], "origin": { "kind": "user" } }, "time": "<time>" }
[wire] context.append_message { "message": { "role": "user", "content": [ { "type": "text", "text": "<auto-mode-enter-reminder>" } ], "toolCalls": [], "origin": { "kind": "injection", "variant": "permission_mode" } }, "time": "<time>" }
[wire] context.append_loop_event { "event": { "type": "step.begin", "uuid": "<uuid-1>", "turnId": "0", "step": 1 }, "time": "<time>" }
[emit] turn.step.started { "turnId": 0, "step": 1, "stepId": "<uuid-1>" }
[emit] assistant.delta { "turnId": 0, "delta": "I will look it up." }
[emit] tool.call.delta { "turnId": 0, "toolCallId": "call_lookup", "name": "Lookup", "argumentsPart": "{\\"query\\":\\"moon\\"}" }
[wire] context.append_loop_event { "event": { "type": "content.part", "uuid": "<uuid-2>", "turnId": "0", "step": 1, "stepUuid": "<uuid-1>", "part": { "type": "text", "text": "I will look it up." } }, "time": "<time>" }
[wire] context.append_loop_event { "event": { "type": "tool.call", "uuid": "call_lookup", "turnId": "0", "step": 1, "stepUuid": "<uuid-1>", "toolCallId": "call_lookup", "name": "Lookup", "args": { "query": "moon" } }, "time": "<time>" }
[emit] tool.call.started { "turnId": 0, "toolCallId": "call_lookup", "name": "Lookup", "args": { "query": "moon" } }
[emit] toolCall { "turnId": 0, "toolCallId": "call_lookup", "args": { "query": "moon" } }
`);
expect(ctx.lastLlmInput()).toMatchInlineSnapshot(`
system: <system-prompt>
tools: Lookup
messages:
user: text "Look up moon"
user: text <auto-mode-enter-reminder>
`);
ctx.mockNextResponse({ type: 'text', text: 'The lookup result is moon-result.' });
expect(await ctx.untilTurnEnd()).toMatchInlineSnapshot(`
[wire] context.append_loop_event { "event": { "type": "tool.result", "parentUuid": "call_lookup", "toolCallId": "call_lookup", "result": { "output": "moon-result" } }, "time": "<time>" }
[emit] tool.result { "turnId": 0, "toolCallId": "call_lookup", "output": "moon-result" }
[wire] context.append_loop_event { "event": { "type": "step.end", "uuid": "<uuid-1>", "turnId": "0", "step": 1, "usage": { "inputOther": 88, "output": 16, "inputCacheRead": 0, "inputCacheCreation": 0 }, "finishReason": "tool_use" }, "time": "<time>" }
[emit] turn.step.completed { "turnId": 0, "step": 1, "stepId": "<uuid-1>", "usage": { "inputOther": 88, "output": 16, "inputCacheRead": 0, "inputCacheCreation": 0 }, "finishReason": "tool_use" }
[wire] usage.record { "model": "mock-model", "usage": { "inputOther": 88, "output": 16, "inputCacheRead": 0, "inputCacheCreation": 0 }, "usageScope": "turn", "time": "<time>" }
[emit] agent.status.updated { "model": "mock-model", "contextTokens": 104, "maxContextTokens": 1000000, "contextUsage": 0.000104, "planMode": false, "swarmMode": false, "permission": "auto", "usage": { "byModel": { "mock-model": { "inputOther": 88, "output": 16, "inputCacheRead": 0, "inputCacheCreation": 0 } }, "total": { "inputOther": 88, "output": 16, "inputCacheRead": 0, "inputCacheCreation": 0 }, "currentTurn": { "inputOther": 88, "output": 16, "inputCacheRead": 0, "inputCacheCreation": 0 } } }
[wire] context.append_loop_event { "event": { "type": "step.begin", "uuid": "<uuid-3>", "turnId": "0", "step": 2 }, "time": "<time>" }
[emit] turn.step.started { "turnId": 0, "step": 2, "stepId": "<uuid-3>" }
[emit] assistant.delta { "turnId": 0, "delta": "The lookup result is moon-result." }
[wire] context.append_loop_event { "event": { "type": "content.part", "uuid": "<uuid-4>", "turnId": "0", "step": 2, "stepUuid": "<uuid-3>", "part": { "type": "text", "text": "The lookup result is moon-result." } }, "time": "<time>" }
[wire] context.append_loop_event { "event": { "type": "step.end", "uuid": "<uuid-3>", "turnId": "0", "step": 2, "usage": { "inputOther": 108, "output": 12, "inputCacheRead": 0, "inputCacheCreation": 0 }, "finishReason": "end_turn" }, "time": "<time>" }
[emit] turn.step.completed { "turnId": 0, "step": 2, "stepId": "<uuid-3>", "usage": { "inputOther": 108, "output": 12, "inputCacheRead": 0, "inputCacheCreation": 0 }, "finishReason": "end_turn" }
[wire] usage.record { "model": "mock-model", "usage": { "inputOther": 108, "output": 12, "inputCacheRead": 0, "inputCacheCreation": 0 }, "usageScope": "turn", "time": "<time>" }
[emit] agent.status.updated { "model": "mock-model", "contextTokens": 120, "maxContextTokens": 1000000, "contextUsage": 0.00012, "planMode": false, "swarmMode": false, "permission": "auto", "usage": { "byModel": { "mock-model": { "inputOther": 196, "output": 28, "inputCacheRead": 0, "inputCacheCreation": 0 } }, "total": { "inputOther": 196, "output": 28, "inputCacheRead": 0, "inputCacheCreation": 0 }, "currentTurn": { "inputOther": 196, "output": 28, "inputCacheRead": 0, "inputCacheCreation": 0 } } }
[emit] turn.ended { "turnId": 0, "reason": "completed" }
`);
expect(ctx.lastLlmInput()).toMatchInlineSnapshot(`
messages:
<last>
assistant: text "I will look it up." calls call_lookup:Lookup { "query": "moon" }
tool[call_lookup]: text "moon-result"
`);
await ctx.rpc.unregisterTool({ name: 'Lookup' });
ctx.mockNextResponse({ type: 'text', text: 'No lookup tool is available.' });
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Can you still use Lookup?' }] });
expect(await ctx.untilTurnEnd()).toMatchInlineSnapshot(`
[wire] tools.unregister_user_tool { "name": "Lookup", "time": "<time>" }
[wire] turn.prompt { "input": [ { "type": "text", "text": "Can you still use Lookup?" } ], "origin": { "kind": "user" }, "time": "<time>" }
[emit] turn.started { "turnId": 1, "origin": { "kind": "user" } }
[wire] context.append_message { "message": { "role": "user", "content": [ { "type": "text", "text": "Can you still use Lookup?" } ], "toolCalls": [], "origin": { "kind": "user" } }, "time": "<time>" }
[wire] context.append_loop_event { "event": { "type": "step.begin", "uuid": "<uuid-5>", "turnId": "1", "step": 1 }, "time": "<time>" }
[emit] turn.step.started { "turnId": 1, "step": 1, "stepId": "<uuid-5>" }
[emit] assistant.delta { "turnId": 1, "delta": "No lookup tool is available." }
[wire] context.append_loop_event { "event": { "type": "content.part", "uuid": "<uuid-6>", "turnId": "1", "step": 1, "stepUuid": "<uuid-5>", "part": { "type": "text", "text": "No lookup tool is available." } }, "time": "<time>" }
[wire] context.append_loop_event { "event": { "type": "step.end", "uuid": "<uuid-5>", "turnId": "1", "step": 1, "usage": { "inputOther": 128, "output": 10, "inputCacheRead": 0, "inputCacheCreation": 0 }, "finishReason": "end_turn" }, "time": "<time>" }
[emit] turn.step.completed { "turnId": 1, "step": 1, "stepId": "<uuid-5>", "usage": { "inputOther": 128, "output": 10, "inputCacheRead": 0, "inputCacheCreation": 0 }, "finishReason": "end_turn" }
[wire] usage.record { "model": "mock-model", "usage": { "inputOther": 128, "output": 10, "inputCacheRead": 0, "inputCacheCreation": 0 }, "usageScope": "turn", "time": "<time>" }
[emit] agent.status.updated { "model": "mock-model", "contextTokens": 138, "maxContextTokens": 1000000, "contextUsage": 0.000138, "planMode": false, "swarmMode": false, "permission": "auto", "usage": { "byModel": { "mock-model": { "inputOther": 324, "output": 38, "inputCacheRead": 0, "inputCacheCreation": 0 } }, "total": { "inputOther": 324, "output": 38, "inputCacheRead": 0, "inputCacheCreation": 0 }, "currentTurn": { "inputOther": 128, "output": 10, "inputCacheRead": 0, "inputCacheCreation": 0 } } }
[emit] turn.ended { "turnId": 1, "reason": "completed" }
`);
expect(ctx.lastLlmInput()).toMatchInlineSnapshot(`
tools: []
messages:
<last>
assistant: text "The lookup result is moon-result."
user: text "Can you still use Lookup?"
`);
await ctx.expectResumeMatches();
});
it('persists oversized registered tool results before adding them to model context', async () => {
const sessionDir = mkdtempSync(join(tmpdir(), 'tool-result-overflow-'));
try {
const lookupCall: ToolCall = {
type: 'function',
id: 'call_lookup',
name: 'Lookup',
arguments: '{"query":"moon"}',
};
const largeOutput = `${'x'.repeat(60_000)}tail survives`;
const ctx = testAgent({ homedir: sessionDir });
ctx.configure();
await ctx.rpc.setPermission({ mode: 'auto' });
await ctx.rpc.registerTool({
name: 'Lookup',
description: 'Look up a short test value.',
parameters: { type: 'object', properties: {} },
});
ctx.mockNextResponse({ type: 'text', text: 'I will look it up.' }, lookupCall);
await ctx.rpc.prompt({ input: [{ type: 'text', text: 'Look up moon' }] });
await ctx.untilToolCall({ output: largeOutput });
ctx.mockNextResponse({ type: 'text', text: 'done' });
await ctx.untilTurnEnd();
const toolText = ctx.compactHistory().find((message) => message.role === 'tool')?.text ?? '';
const outputPath = /^output_path: (.+)$/m.exec(toolText)?.[1];
expect(toolText).toContain('Tool output exceeded 50000 characters');
expect(toolText).not.toContain('tail survives');
expect(outputPath).toBeTruthy();
expect(readFileSync(outputPath!, 'utf8')).toBe(largeOutput);
} finally {
rmSync(sessionDir, { recursive: true, force: true });
}
});
it('does not overwrite saved oversized tool results with repeated call IDs', async () => {
const sessionDir = mkdtempSync(join(tmpdir(), 'tool-result-overflow-'));
try {
const firstOutput = `${'a'.repeat(60_000)}first tail`;
const secondOutput = `${'b'.repeat(60_000)}second tail`;
const first = await budgetToolResultForModel({
homedir: sessionDir,
toolName: 'Lookup',
toolCallId: 'call_lookup',
result: { output: firstOutput },
});
const second = await budgetToolResultForModel({
homedir: sessionDir,
toolName: 'Lookup',
toolCallId: 'call_lookup',
result: { output: secondOutput },
});
const firstPath = savedOutputPath(first.output);
const secondPath = savedOutputPath(second.output);
expect(firstPath).not.toBe(secondPath);
expect(readFileSync(firstPath, 'utf8')).toBe(firstOutput);
expect(readFileSync(secondPath, 'utf8')).toBe(secondOutput);
} finally {
rmSync(sessionDir, { recursive: true, force: true });
}
});
it('keeps oversized tool results intact when no session directory is available', async () => {
const largeOutput = `${'x'.repeat(60_000)}tail survives`;
const result = { output: largeOutput };
const budgeted = await budgetToolResultForModel({
toolName: 'Lookup',
toolCallId: 'call_lookup',
result,
});
expect(budgeted).toBe(result);
expect(budgeted.output).toBe(largeOutput);
});
it('does not save already-truncated tool result previews as full output', async () => {
const sessionDir = mkdtempSync(join(tmpdir(), 'tool-result-overflow-'));
try {
const largeOutput = `${'x'.repeat(60_000)}[...truncated]`;
const result = {
output: largeOutput,
truncated: true,
};
const budgeted = await budgetToolResultForModel({
homedir: sessionDir,
toolName: 'Lookup',
toolCallId: 'call_lookup',
result,
});
expect(budgeted).toBe(result);
expect(budgeted.output).toBe(largeOutput);
expect(budgeted.output).not.toContain('output_path:');
expect(existsSync(join(sessionDir, 'tool-results'))).toBe(false);
} finally {
rmSync(sessionDir, { recursive: true, force: true });
}
});
});
function bashCall(): ToolCall {
return {
type: 'function',
id: 'call_bash',
name: 'Bash',
arguments: '{"command":"printf hook-output","timeout":60}',
};
}
function agentCall(): ToolCall {
return {
type: 'function',
id: 'call_agent',
name: 'Agent',
arguments: JSON.stringify({
prompt: 'Investigate deeply',
description: 'Investigate deeply',
subagent_type: 'coder',
}),
};
}
function savedOutputPath(output: unknown): string {
expect(typeof output).toBe('string');
const outputPath = /^output_path: (.+)$/m.exec(output as string)?.[1];
expect(outputPath).toBeTruthy();
return outputPath!;
}
function hookErrorMessageAssertCommand(expected: string): string {
const script = [
"let input = '';",
"process.stdin.on('data', (chunk) => { input += chunk; });",
"process.stdin.on('end', () => {",
' const payload = JSON.parse(input);',
` if (payload.error?.message === ${JSON.stringify(expected)}) process.exit(0);`,
" console.error(payload.error?.message ?? '<missing>');",
' process.exit(2);',
'});',
].join('');
return `node -e ${JSON.stringify(script)}`;
}