feat: preserve bounded model requests and complete task history

This commit is contained in:
Agent Workbench Dev
2026-10-29 21:09:50 +08:00
parent 19b738b468
commit 8f32dec6cc
58 changed files with 1269 additions and 108 deletions
+7 -7
View File
@@ -115,7 +115,7 @@ test('tool result artifacts and event cursors retain project ownership across re
runtime.start(f.session.id, 'Read the fixture'); await runtime.active.get(f.session.id).promise;
const snapshot = f.store.executionSnapshot(f.session);
assert.equal(snapshot.run.usage.requests, 2); assert.equal(snapshot.run.usage.totalTokens, 28);
const artifact = snapshot.artifacts[0]; assert.equal(artifact.projectId, f.project.id);
const artifact = snapshot.artifacts.find(value => value.kind === 'tool-result'); assert.equal(artifact.projectId, f.project.id);
assert.match(JSON.parse(f.store.artifactStore.read(artifact)).content, /Fixture project/);
const other = f.store.createSession(f.project.id);
assert.throws(() => f.store.owned('artifact', artifact.id, other.id), { status: 404 });
@@ -133,22 +133,22 @@ test('tool result artifacts and event cursors retain project ownership across re
test('token budgets pause before tools execute and continuation keeps original task and accumulated usage', async t => {
const f = fixture(t), provider = new Provider(); let round = 0;
f.store.saveConfig({ maxRunTokens: 25 });
f.store.saveConfig({ maxRunTokens: 12000 });
provider.complete = async () => ({ message: { role: 'assistant', content: '', tool_calls: [call('budget-' + round++, 'run_command', { command: 'node --version', reason: 'must not execute over budget' })] },
usage: { prompt_tokens: 20, completion_tokens: 10 } });
usage: { prompt_tokens: 12020, completion_tokens: 10 } });
const runtime = new Runtime(f.store, provider); f.onCleanup(() => runtime.stopAll());
runtime.start(f.session.id, 'Original goal'); await runtime.active.get(f.session.id).promise;
assert.equal(f.session.status, 'paused'); assert.equal(f.session.approvals.length, 0);
const originalTaskId = f.session.taskId;
assert.equal(f.store.core.run.get(f.session.runId).stopReason, 'token_limit');
assert.equal(f.store.core.task.get(originalTaskId).usage.totalTokens, 30); assertToolPairs(f.session.providerMessages);
f.store.saveConfig({ maxRunTokens: 1000 });
assert.equal(f.store.core.task.get(originalTaskId).usage.totalTokens, 12030); assertToolPairs(f.session.providerMessages);
f.store.saveConfig({ maxRunTokens: 16000 });
provider.complete = async () => ({ message: { role: 'assistant', content: 'Finished.' }, usage: { prompt_tokens: 5, completion_tokens: 5 } });
runtime.start(f.session.id, 'Also preserve the public API.'); await runtime.active.get(f.session.id).promise;
assert.equal(f.session.taskId, originalTaskId); assert.equal(f.store.core.task.get(originalTaskId).goal, 'Original goal');
assert.equal(f.store.core.task.get(originalTaskId).instructions[0].content, 'Also preserve the public API.');
assert.equal(f.store.core.task.get(originalTaskId).usage.totalTokens, 40);
assert.equal(f.store.core.run.get(f.session.runId).budget.maxTokens, 1000);
assert.equal(f.store.core.task.get(originalTaskId).usage.totalTokens, 12040);
assert.equal(f.store.core.run.get(f.session.runId).budget.maxTokens, 16000);
});
test('a time budget interrupts an unresponsive model and persists a resumable run', async t => {