Files
Codeman/test/custom-model-injection.test.ts
T
DevvynandClaude Sonnet 5 e2034177c5 fix(custom-model): root-cause and fix DeepSeek's HTTP_404 (missing /v1)
DeepSeek Harness's own bundled provider module
(@deepseek-ai/dsh-llm-deepseek) builds its request URL as
`${DEEPSEEK_BASE_URL}/chat/completions` with no `/v1` insertion of its
own (its real public API, https://api.deepseek.com, expects the
caller's base URL to already carry any needed prefix), while
llama-swap/llama.cpp only ever serves the OpenAI-conventional
`/v1/chat/completions`.

Confirmed two ways:
- Installed the real @deepseek-ai/dsh package (all its actual
  published dependencies) into a scratch dir purely to read
  dsh-llm-deepseek's source: `fetch(`${connection.baseURL}/chat/
  completions`, ...)`, baseURL read straight from DEEPSEEK_BASE_URL —
  the same grep-the-real-source bar pi/grok's fixes were held to.
- Live against the test-picker's llama-swap: `POST <baseUrl>/chat/
  completions` -> 404, `POST <baseUrl>/v1/chat/completions` -> 200,
  same endpoint. dsh's own error template ("DeepSeek API error (HTTP
  ${status})") reproduces the originally-reported
  "dsh: HTTP_404: DeepSeek API error (HTTP 404)" exactly.

- New registry field `appendV1Suffix` (env kind only, deepseek's entry
  alone — claude/gemini must NOT get it, since claude was already
  confirmed working against the unmodified baseUrl). When set,
  buildCustomModelInjection runs endpoint.baseUrl through the same
  withV1Suffix() helper configDir-kind CLIs (pi/grok/codex) already
  use, instead of writing it verbatim.

Not yet re-run end-to-end through a real dsh binary — no install
available in this environment (not in PATH, and the test-picker
container doesn't bundle it) — so this is source-confirmed and
live-verified at the HTTP level, not yet promoted to "verified"
alongside claude/opencode/pi/grok/omp. Docs (custom-model-endpoints.md,
the plan doc's confidence table, the wiki page, CLAUDE.md) all updated
to reflect this precisely rather than leaving the old "root cause not
identified" claim in place.

2 new/updated tests for the /v1 suffix (including idempotency against
a baseUrl that already ends in /v1) plus a corrected mock-server
contract test. Typecheck/lint clean; full suite shows no new
regressions.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
2026-09-17 13:41:19 +08:00

242 lines
12 KiB
TypeScript

/**
* @fileoverview Tests for the Custom Model Endpoint Profiles pure builder.
* Uses the real CLI registry entries (getCli) rather than hand-rolled
* fixtures, so a change to a real entry's customModelInjection declaration
* is exercised here automatically instead of silently diverging.
*
* Port: N/A (no server needed)
*/
import { describe, it, expect } from 'vitest';
import { getCli } from '../src/config/cli-registry/index.js';
import {
buildCustomModelInjection,
withV1Suffix,
GROK_CUSTOM_MODEL_NAME,
type CustomModelEndpoint,
} from '../src/custom-model-injection.js';
const endpoint: CustomModelEndpoint = {
id: 'ep1',
label: 'llama.cpp box',
baseUrl: 'http://192.168.1.50:8080',
apiKey: 'my-key',
};
function entryOrThrow(id: string) {
const entry = getCli(id);
if (!entry) throw new Error(`missing CLI registry entry: ${id}`);
return entry;
}
describe('withV1Suffix', () => {
it('appends /v1 when missing', () => {
expect(withV1Suffix('http://host:8080')).toBe('http://host:8080/v1');
});
it('is idempotent when already present', () => {
expect(withV1Suffix('http://host:8080/v1')).toBe('http://host:8080/v1');
expect(withV1Suffix('http://host:8080/v1/')).toBe('http://host:8080/v1');
});
it('strips a trailing slash with no /v1', () => {
expect(withV1Suffix('http://host:8080/')).toBe('http://host:8080/v1');
});
});
describe('buildCustomModelInjection', () => {
it('claude: env kind sets base URL, api key, and all three tier model vars', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), endpoint, 'qwen3');
expect(result.kind).toBe('env');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides).toEqual({
ANTHROPIC_BASE_URL: 'http://192.168.1.50:8080',
ANTHROPIC_API_KEY: 'my-key',
ANTHROPIC_DEFAULT_SONNET_MODEL: 'qwen3',
ANTHROPIC_DEFAULT_HAIKU_MODEL: 'qwen3',
ANTHROPIC_DEFAULT_OPUS_MODEL: 'qwen3',
});
});
it('claude: also declares configDirVar (CLAUDE_CONFIG_DIR isolation) on the env-kind result', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.configDirVar).toBe('CLAUDE_CONFIG_DIR');
});
it('claude: injects CLAUDE_CODE_MAX_CONTEXT_TOKENS when a context length is known', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), endpoint, 'qwen3', 16384);
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides.CLAUDE_CODE_MAX_CONTEXT_TOKENS).toBe('16384');
});
it('claude: omits CLAUDE_CODE_MAX_CONTEXT_TOKENS when the context length is unknown', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides.CLAUDE_CODE_MAX_CONTEXT_TOKENS).toBeUndefined();
});
it('claude: also declares apiKeyTrustFile, carrying the literal apiKey used', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.apiKeyTrustFile).toEqual({ relPath: '.claude.json', shape: 'claude-api-key-responses' });
expect(result.apiKey).toBe('my-key');
});
it('claude: also declares skipFirstRunPrompts on the env-kind result', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.skipFirstRunPrompts).toBe(true);
});
it('opencode: has no skipFirstRunPrompts (no apiKeyTrustFile/configDirVar concept for it either)', () => {
const result = buildCustomModelInjection(entryOrThrow('opencode'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.skipFirstRunPrompts).toBeUndefined();
});
it('claude: falls back to a dummy key when the endpoint has none', () => {
const result = buildCustomModelInjection(entryOrThrow('claude'), { ...endpoint, apiKey: undefined }, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides.ANTHROPIC_API_KEY).toBe('local-dummy-key');
});
it('opencode: configContentEnv carries a JSON blob in OPENCODE_CONFIG_CONTENT', () => {
const result = buildCustomModelInjection(entryOrThrow('opencode'), endpoint, 'qwen3');
expect(result.kind).toBe('env');
if (result.kind !== 'env') throw new Error('unreachable');
const parsed = JSON.parse(result.envOverrides.OPENCODE_CONFIG_CONTENT);
expect(parsed.model).toBe('custom/qwen3');
expect(parsed.provider.custom.options.baseURL).toBe('http://192.168.1.50:8080/v1');
expect(parsed.provider.custom.options.apiKey).toBe('my-key');
expect(parsed.provider.custom.models.qwen3).toEqual({});
});
it('codex: configDir writes an isolated config.toml with model/base_url, and the key rides as extraEnv (never a literal TOML field)', () => {
const result = buildCustomModelInjection(entryOrThrow('codex'), endpoint, 'qwen3');
expect(result.kind).toBe('configDir');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.dirEnvVar).toBe('CODEX_HOME');
expect(result.files).toHaveLength(1);
expect(result.files[0].relPath).toBe('config.toml');
expect(result.files[0].content).toContain('model = "qwen3"');
expect(result.files[0].content).toContain('base_url = "http://192.168.1.50:8080/v1"');
expect(result.files[0].content).toContain('wire_api = "responses"');
expect(result.files[0].content).not.toContain('api_key ='); // never a literal TOML field
expect(result.files[0].content).toContain('env_key = "CODEMAN_CUSTOM_MODEL_API_KEY"');
expect(result.extraEnv).toEqual({ CODEMAN_CUSTOM_MODEL_API_KEY: 'my-key' });
});
it('codex: escapes a quote in the model id so it cannot break out of the TOML string', () => {
const result = buildCustomModelInjection(entryOrThrow('codex'), endpoint, 'weird"model');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.files[0].content).toContain('model = "weird\\"model"');
});
it('pi: configDir writes .pi/agent/models.json, redirected via HOME (verified live — PI_CONFIG_DIR does nothing for pi)', () => {
const result = buildCustomModelInjection(entryOrThrow('pi'), endpoint, 'qwen3');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.dirEnvVar).toBe('HOME');
expect(result.files[0].relPath).toBe('.pi/agent/models.json');
const parsed = JSON.parse(result.files[0].content);
expect(parsed.providers.custom.baseUrl).toBe('http://192.168.1.50:8080/v1');
expect(parsed.providers.custom.authHeader).toBe(true);
expect(parsed.providers.custom.models).toEqual([{ id: 'qwen3' }]); // array, NOT keyed by id
});
it('omp: configDir writes .omp/agent/models.yml, redirected via HOME (verified live end-to-end)', () => {
const result = buildCustomModelInjection(entryOrThrow('omp'), endpoint, 'qwen3');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.dirEnvVar).toBe('HOME');
expect(result.files[0].relPath).toBe('.omp/agent/models.yml');
expect(result.files[0].content).toContain('baseUrl: "http://192.168.1.50:8080/v1"');
expect(result.files[0].content).toContain('authHeader: true');
expect(result.files[0].content).toContain('- id: "qwen3"');
});
it('gemini: env kind sets GOOGLE_GEMINI_BASE_URL/GEMINI_API_KEY/GEMINI_MODEL', () => {
const result = buildCustomModelInjection(entryOrThrow('gemini'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides).toEqual({
GOOGLE_GEMINI_BASE_URL: 'http://192.168.1.50:8080',
GEMINI_API_KEY: 'my-key',
GEMINI_MODEL: 'qwen3',
});
});
it('grok: configDir writes a config.toml [model.<name>] block, key rides as extraEnv (XAI_API_KEY)', () => {
const result = buildCustomModelInjection(entryOrThrow('grok'), endpoint, 'qwen3');
expect(result.kind).toBe('configDir');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.dirEnvVar).toBe('GROK_HOME');
expect(result.files).toHaveLength(1);
expect(result.files[0].relPath).toBe('config.toml');
expect(result.files[0].content).toContain('model = "qwen3"');
expect(result.files[0].content).toContain('base_url = "http://192.168.1.50:8080/v1"');
expect(result.files[0].content).toContain('api_backend = "chat_completions"');
expect(result.files[0].content).toContain('env_key = "XAI_API_KEY"');
expect(result.files[0].content).not.toContain('api_key ='); // never a literal TOML field
expect(result.extraEnv).toEqual({ XAI_API_KEY: 'my-key' });
});
it('deepseek: env kind sets base URL (with a /v1 suffix appended) and key, no model var', () => {
// appendV1Suffix is REQUIRED here, not cosmetic: confirmed by reading dsh's own
// bundled source (@deepseek-ai/dsh-llm-deepseek) that it builds the request URL as
// `${DEEPSEEK_BASE_URL}/chat/completions` with no "/v1" of its own, while
// llama-swap/llama.cpp only serves "/v1/chat/completions" — without this, every
// request 404s (confirmed live; this is the fix for the originally-reported
// "dsh: HTTP_404: DeepSeek API error (HTTP 404)").
const result = buildCustomModelInjection(entryOrThrow('deepseek'), endpoint, 'qwen3');
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides).toEqual({
DEEPSEEK_BASE_URL: 'http://192.168.1.50:8080/v1',
DEEPSEEK_API_KEY: 'my-key',
});
});
it('deepseek: appending the /v1 suffix is idempotent against a baseUrl that already ends in /v1', () => {
const result = buildCustomModelInjection(
entryOrThrow('deepseek'),
{ ...endpoint, baseUrl: 'http://192.168.1.50:8080/v1' },
'qwen3'
);
if (result.kind !== 'env') throw new Error('unreachable');
expect(result.envOverrides.DEEPSEEK_BASE_URL).toBe('http://192.168.1.50:8080/v1');
});
it('antigravity: unsupported', () => {
const result = buildCustomModelInjection(entryOrThrow('antigravity'), endpoint, 'qwen3');
expect(result).toEqual({ kind: 'unsupported' });
});
it('shell: unsupported', () => {
const result = buildCustomModelInjection(entryOrThrow('shell'), endpoint, 'qwen3');
expect(result).toEqual({ kind: 'unsupported' });
});
});
describe('launchModel (the model launch param that selects the injected provider)', () => {
it('pi and omp get --model custom/<modelId>: the config file alone leaves them on their default provider', () => {
for (const id of ['pi', 'omp']) {
const result = buildCustomModelInjection(entryOrThrow(id), endpoint, 'qwen3.5-0.8b');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.launchModel, id).toBe('custom/qwen3.5-0.8b');
}
});
it('grok gets the [model.<name>] block name, pinned to the constant the config template writes', () => {
const result = buildCustomModelInjection(entryOrThrow('grok'), endpoint, 'qwen3');
if (result.kind !== 'configDir') throw new Error('unreachable');
expect(result.launchModel).toBe(GROK_CUSTOM_MODEL_NAME);
expect(result.files[0].content).toContain(`[model.${GROK_CUSTOM_MODEL_NAME}]`);
});
it('CLIs whose config selects the model on its own declare none', () => {
for (const id of ['claude', 'opencode', 'codex', 'gemini', 'deepseek']) {
const result = buildCustomModelInjection(entryOrThrow(id), endpoint, 'qwen3');
if (result.kind === 'unsupported') throw new Error('unreachable');
expect(result.launchModel, id).toBeUndefined();
}
});
});