a0d657ee18
* feat(zai): add Z.AI GLM Coding Plan provider preset Add dedicated Z.AI provider support for the GLM Coding Plan, enabling use of GLM-5.1, GLM-5-Turbo, GLM-4.7, and GLM-4.5-Air models through the OpenAI-compatible shim with proper thinking mode (reasoning_content), max_tokens handling, and context window sizing. * fix(zai): unify GLM max output token limits across casing variants glm-5/glm-4.7 had conservative 16K max output while GLM-5/GLM-4.7 had 131K. Use consistent Z.AI coding plan limits for all GLM variants. * fix(zai): restore DashScope GLM limits, enable GLM thinking support - Restore lowercase glm-5/glm-4.7 to 16_384 max output (DashScope limits) while keeping Z.AI coding plan high limits on uppercase GLM-* keys only - Add GLM model support to modelSupportsThinking() so reasoning_content is enabled when using GLM-5.x/GLM-4.7 models on Z.AI * fix(zai): tighten GLM regexes, fix misleading context window comment - Use precise regex in thinking.ts: exact GLM model matches only, no false positives on glm-50/glm-4, includes glm-4.5-air - Use uppercase-only match in StartupScreen rawModel fallback so DashScope lowercase glm-* models aren't mislabeled as Z.AI - Clarify context window comment: lowercase glm-5.1/glm-5-turbo/ glm-4.5-air are Z.AI-specific aliases, not DashScope * fix(zai): scope GLM detection to Z.AI * improve readability of max_completion_tokens check Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
64 lines
1.9 KiB
TypeScript
64 lines
1.9 KiB
TypeScript
import { afterEach, beforeEach, describe, expect, test } from 'bun:test'
|
|
import { modelSupportsThinking } from './thinking.js'
|
|
|
|
const ENV_KEYS = [
|
|
'CLAUDE_CODE_USE_OPENAI',
|
|
'CLAUDE_CODE_USE_GEMINI',
|
|
'CLAUDE_CODE_USE_GITHUB',
|
|
'CLAUDE_CODE_USE_MISTRAL',
|
|
'CLAUDE_CODE_USE_BEDROCK',
|
|
'CLAUDE_CODE_USE_VERTEX',
|
|
'CLAUDE_CODE_USE_FOUNDRY',
|
|
'OPENAI_BASE_URL',
|
|
'OPENAI_API_BASE',
|
|
'OPENAI_MODEL',
|
|
'NVIDIA_NIM',
|
|
'MINIMAX_API_KEY',
|
|
'USER_TYPE',
|
|
]
|
|
|
|
const originalEnv: Record<string, string | undefined> = {}
|
|
|
|
beforeEach(() => {
|
|
for (const key of ENV_KEYS) {
|
|
originalEnv[key] = process.env[key]
|
|
delete process.env[key]
|
|
}
|
|
})
|
|
|
|
afterEach(() => {
|
|
for (const key of ENV_KEYS) {
|
|
if (originalEnv[key] === undefined) {
|
|
delete process.env[key]
|
|
} else {
|
|
process.env[key] = originalEnv[key]
|
|
}
|
|
}
|
|
})
|
|
|
|
describe('modelSupportsThinking — Z.AI GLM', () => {
|
|
test('enables thinking for exact GLM models on api.z.ai', () => {
|
|
process.env.CLAUDE_CODE_USE_OPENAI = '1'
|
|
process.env.OPENAI_BASE_URL = 'https://api.z.ai/api/coding/paas/v4'
|
|
|
|
expect(modelSupportsThinking('GLM-5.1')).toBe(true)
|
|
expect(modelSupportsThinking('GLM-5-Turbo')).toBe(true)
|
|
expect(modelSupportsThinking('GLM-4.7')).toBe(true)
|
|
expect(modelSupportsThinking('GLM-4.5-Air')).toBe(true)
|
|
})
|
|
|
|
test('does not enable GLM thinking on non-Z.AI OpenAI-compatible endpoints', () => {
|
|
process.env.CLAUDE_CODE_USE_OPENAI = '1'
|
|
process.env.OPENAI_BASE_URL = 'https://dashscope.aliyuncs.com/compatible-mode/v1'
|
|
|
|
expect(modelSupportsThinking('glm-5.1')).toBe(false)
|
|
expect(modelSupportsThinking('GLM-5.1')).toBe(false)
|
|
})
|
|
|
|
test('does not match unrelated GLM-looking model names', () => {
|
|
process.env.CLAUDE_CODE_USE_OPENAI = '1'
|
|
process.env.OPENAI_BASE_URL = 'https://api.z.ai/api/coding/paas/v4'
|
|
|
|
expect(modelSupportsThinking('glm-50')).toBe(false)
|
|
})
|
|
}) |