b437597286
- NEW tools/observer-self-assessment-api.mjs
buildSelfAssessmentPrompt({ prompt, recommendedNode, actualNode, chainExecuted })
pure, handles nulls/undefined, returns { system, user } strings
callSelfAssessmentApi(opts) async, fail-quiet — returns string|null
AbortController + timeout race (works even when fetchImpl ignores signal)
guards: !apiKey -> return null immediately (no fetch call)
guards: !response.ok, fetch throw, JSON parse error -> return null
passes x-api-key + authorization headers per ProxyAPI two-header pattern
readRuntimeFlag(name, { homedir, fsImpl }) reads ~/.claude/runtime/<name>.json
returns value field string or 'off' on missing/malformed
- NEW tools/observer-self-assessment-api.test.mjs: 14 tests, 0 failed
1. buildSelfAssessmentPrompt all 4 fields interpolated
2. buildSelfAssessmentPrompt null/undefined inputs (2 tests)
3. callSelfAssessmentApi returns null when apiKey falsy (2 tests)
4. returns content[0].text on 200 ok (fake fetchImpl)
5. returns null on non-2xx (response.ok=false)
6. returns null on fetch throw
7. returns null on timeout (never-resolving fake fetchImpl, timeoutMs=30ms)
8. sends correct headers+body shape (spy fetchImpl)
9. readRuntimeFlag reads {"value":"on"}, returns 'off' on missing/malformed (4 tests)
- EDIT tools/observer-stop-hook.mjs
import { callSelfAssessmentApi, readRuntimeFlag } added
stdin 'end' handler made async
step 3.5 inserted between buildEpisodeFromContext and appendEpisode:
reads self-assessment-mode runtime flag; if 'on' and ROUTER_LLM_KEY set,
calls callSelfAssessmentApi and attaches ep.self_assessment via buildSelfAssessment()
fail-quiet: on any error apiResult=null -> self_assessment_pending: true
Regression: 628/628 tests passed (35 test files), 0 failed
gitleaks: 0 leaks on all 3 files
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
261 lines
9.5 KiB
JavaScript
261 lines
9.5 KiB
JavaScript
/**
|
|
* Tests for tools/observer-self-assessment-api.mjs
|
|
* Phase 3 deferred follow-up #5: real LLM self-assessment API call.
|
|
* TDD — these tests are written BEFORE the implementation exists.
|
|
*/
|
|
|
|
import { describe, it, expect } from 'vitest';
|
|
import {
|
|
buildSelfAssessmentPrompt,
|
|
callSelfAssessmentApi,
|
|
readRuntimeFlag,
|
|
} from './observer-self-assessment-api.mjs';
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 1. buildSelfAssessmentPrompt — all 4 fields interpolated
|
|
// ---------------------------------------------------------------------------
|
|
describe('buildSelfAssessmentPrompt — all fields interpolated', () => {
|
|
it('returns system+user strings with all 4 fields present in user string', () => {
|
|
const { system, user } = buildSelfAssessmentPrompt({
|
|
prompt: 'напиши тест для биллинга',
|
|
recommendedNode: '#62',
|
|
actualNode: '#19',
|
|
chainExecuted: ['#19', '#62'],
|
|
});
|
|
expect(typeof system).toBe('string');
|
|
expect(system.length).toBeGreaterThan(0);
|
|
expect(typeof user).toBe('string');
|
|
expect(user).toContain('напиши тест для биллинга');
|
|
expect(user).toContain('#62');
|
|
expect(user).toContain('#19');
|
|
expect(user).toContain('#62'); // part of chainExecuted serialisation
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 2. buildSelfAssessmentPrompt — handles missing/null inputs gracefully
|
|
// ---------------------------------------------------------------------------
|
|
describe('buildSelfAssessmentPrompt — null/undefined inputs', () => {
|
|
it('returns valid strings when all inputs are undefined/null', () => {
|
|
const { system, user } = buildSelfAssessmentPrompt({});
|
|
expect(typeof system).toBe('string');
|
|
expect(typeof user).toBe('string');
|
|
// Should contain fallback placeholders, not throw
|
|
expect(user).not.toContain('undefined');
|
|
expect(user).not.toContain('[object Object]');
|
|
});
|
|
|
|
it('handles null recommendedNode and empty chainExecuted', () => {
|
|
const { user } = buildSelfAssessmentPrompt({
|
|
prompt: 'test',
|
|
recommendedNode: null,
|
|
actualNode: 'direct',
|
|
chainExecuted: [],
|
|
});
|
|
expect(user).toContain('test');
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 3. callSelfAssessmentApi — returns null when apiKey is missing/empty
|
|
// ---------------------------------------------------------------------------
|
|
describe('callSelfAssessmentApi — missing apiKey', () => {
|
|
it('returns null immediately when apiKey is falsy (no fetch call)', async () => {
|
|
let fetchCalled = false;
|
|
const fakeFetch = async () => { fetchCalled = true; };
|
|
|
|
const result = await callSelfAssessmentApi({
|
|
prompt: 'x', recommendedNode: '#1', actualNode: '#1', chainExecuted: [],
|
|
apiKey: '',
|
|
fetchImpl: fakeFetch,
|
|
});
|
|
|
|
expect(result).toBeNull();
|
|
expect(fetchCalled).toBe(false);
|
|
});
|
|
|
|
it('returns null when apiKey is undefined', async () => {
|
|
const result = await callSelfAssessmentApi({
|
|
prompt: 'x', recommendedNode: '#1', actualNode: '#1', chainExecuted: [],
|
|
apiKey: undefined,
|
|
});
|
|
expect(result).toBeNull();
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 4. callSelfAssessmentApi — returns text on 200 + content[0].text
|
|
// ---------------------------------------------------------------------------
|
|
describe('callSelfAssessmentApi — successful 200 response', () => {
|
|
it('returns content[0].text on ok response', async () => {
|
|
const responseText = '{"summary":"chose correctly","confidence_in_choice":0.9,"what_could_be_better":null,"lesson_learned":null}';
|
|
const fakeFetch = async () => ({
|
|
ok: true,
|
|
json: async () => ({
|
|
content: [{ type: 'text', text: responseText }],
|
|
}),
|
|
});
|
|
|
|
const result = await callSelfAssessmentApi({
|
|
prompt: 'do something',
|
|
recommendedNode: '#19',
|
|
actualNode: '#19',
|
|
chainExecuted: ['#19'],
|
|
apiKey: 'test-key',
|
|
baseUrl: 'https://api.example.com/anthropic',
|
|
model: 'claude-sonnet-4-6',
|
|
fetchImpl: fakeFetch,
|
|
timeoutMs: 5000,
|
|
});
|
|
|
|
expect(result).toBe(responseText);
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 5. callSelfAssessmentApi — returns null on non-2xx (r.ok=false)
|
|
// ---------------------------------------------------------------------------
|
|
describe('callSelfAssessmentApi — non-2xx response', () => {
|
|
it('returns null when response.ok is false', async () => {
|
|
const fakeFetch = async () => ({
|
|
ok: false,
|
|
status: 429,
|
|
json: async () => ({ error: { message: 'rate limited' } }),
|
|
});
|
|
|
|
const result = await callSelfAssessmentApi({
|
|
prompt: 'x', recommendedNode: '#1', actualNode: '#1', chainExecuted: [],
|
|
apiKey: 'test-key',
|
|
fetchImpl: fakeFetch,
|
|
timeoutMs: 5000,
|
|
});
|
|
|
|
expect(result).toBeNull();
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 6. callSelfAssessmentApi — returns null on fetch throw
|
|
// ---------------------------------------------------------------------------
|
|
describe('callSelfAssessmentApi — fetch throws', () => {
|
|
it('returns null (fail-quiet) when fetch throws a network error', async () => {
|
|
const fakeFetch = async () => { throw new Error('network error'); };
|
|
|
|
const result = await callSelfAssessmentApi({
|
|
prompt: 'x', recommendedNode: '#1', actualNode: '#1', chainExecuted: [],
|
|
apiKey: 'test-key',
|
|
fetchImpl: fakeFetch,
|
|
timeoutMs: 5000,
|
|
});
|
|
|
|
expect(result).toBeNull();
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 7. callSelfAssessmentApi — returns null on timeout
|
|
// ---------------------------------------------------------------------------
|
|
describe('callSelfAssessmentApi — timeout', () => {
|
|
it('returns null when fetch never resolves within timeoutMs', async () => {
|
|
// fakeFetch returns a promise that never resolves
|
|
const fakeFetch = async (_url, _opts) => new Promise(() => { /* never */ });
|
|
|
|
const start = Date.now();
|
|
const result = await callSelfAssessmentApi({
|
|
prompt: 'x', recommendedNode: '#1', actualNode: '#1', chainExecuted: [],
|
|
apiKey: 'test-key',
|
|
fetchImpl: fakeFetch,
|
|
timeoutMs: 30, // 30 ms timeout — very fast for test
|
|
});
|
|
const elapsed = Date.now() - start;
|
|
|
|
expect(result).toBeNull();
|
|
// Should resolve around the timeout, not hang indefinitely
|
|
expect(elapsed).toBeLessThan(500);
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 8. callSelfAssessmentApi — sends correct headers and body
|
|
// ---------------------------------------------------------------------------
|
|
describe('callSelfAssessmentApi — request format', () => {
|
|
it('sends correct headers and body shape (spy fetchImpl)', async () => {
|
|
let capturedUrl, capturedOpts;
|
|
const fakeFetch = async (url, opts) => {
|
|
capturedUrl = url;
|
|
capturedOpts = opts;
|
|
return {
|
|
ok: true,
|
|
json: async () => ({ content: [{ type: 'text', text: 'ok' }] }),
|
|
};
|
|
};
|
|
|
|
await callSelfAssessmentApi({
|
|
prompt: 'test prompt',
|
|
recommendedNode: '#62',
|
|
actualNode: '#62',
|
|
chainExecuted: ['#62'],
|
|
apiKey: 'my-secret-key',
|
|
baseUrl: 'https://api.proxyapi.ru/anthropic',
|
|
model: 'claude-sonnet-4-6',
|
|
fetchImpl: fakeFetch,
|
|
timeoutMs: 5000,
|
|
});
|
|
|
|
expect(capturedUrl).toContain('/v1/messages');
|
|
const headers = capturedOpts.headers;
|
|
expect(headers['authorization'] || headers['x-api-key']).toBeTruthy();
|
|
const body = JSON.parse(capturedOpts.body);
|
|
expect(body.model).toBe('claude-sonnet-4-6');
|
|
expect(Array.isArray(body.messages)).toBe(true);
|
|
expect(body.messages[0].role).toBe('user');
|
|
expect(body.max_tokens).toBeGreaterThan(0);
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// 9. readRuntimeFlag — reads value from file; returns 'off' on missing/malformed
|
|
// ---------------------------------------------------------------------------
|
|
describe('readRuntimeFlag', () => {
|
|
it('returns the value from {"value":"on"} when file exists', () => {
|
|
const fakeHomedir = '/fake/home';
|
|
const fakeFsImpl = {
|
|
existsSync: (p) => p.endsWith('self-assessment-mode.json'),
|
|
readFileSync: (_p, _enc) => '{"value":"on"}',
|
|
};
|
|
|
|
const result = readRuntimeFlag('self-assessment-mode', { homedir: fakeHomedir, fsImpl: fakeFsImpl });
|
|
expect(result).toBe('on');
|
|
});
|
|
|
|
it('returns "off" when file does not exist', () => {
|
|
const fakeFsImpl = {
|
|
existsSync: () => false,
|
|
readFileSync: () => { throw new Error('no file'); },
|
|
};
|
|
|
|
const result = readRuntimeFlag('self-assessment-mode', { homedir: '/fake', fsImpl: fakeFsImpl });
|
|
expect(result).toBe('off');
|
|
});
|
|
|
|
it('returns "off" on malformed JSON', () => {
|
|
const fakeFsImpl = {
|
|
existsSync: () => true,
|
|
readFileSync: () => 'NOT JSON',
|
|
};
|
|
|
|
const result = readRuntimeFlag('self-assessment-mode', { homedir: '/fake', fsImpl: fakeFsImpl });
|
|
expect(result).toBe('off');
|
|
});
|
|
|
|
it('returns "off" when value field is missing', () => {
|
|
const fakeFsImpl = {
|
|
existsSync: () => true,
|
|
readFileSync: () => '{"mode":"on"}', // no "value" key
|
|
};
|
|
|
|
const result = readRuntimeFlag('self-assessment-mode', { homedir: '/fake', fsImpl: fakeFsImpl });
|
|
expect(result).toBe('off');
|
|
});
|
|
});
|