Files
orcs-code/src/utils/providerFlag.test.ts
KRATOS b4bd95b477 fix: normalize malformed Bash tool arguments from OpenAI-compatible providers (#385)
* fix: normalize malformed Bash tool arguments from OpenAI-compatible providers

* fix: keep invalid Bash tool args from becoming commands

* fix: preserve malformed Bash JSON literals

* test: stabilize rebased PR 385 checks

* test: isolate provider profile env assertions

* fix: extend tool argument normalization to all tools and harden edge cases

- Extend STRING_ARGUMENT_TOOL_FIELDS to normalize Read, Write, Edit,
  Glob, and Grep plain-string arguments (fixes "Invalid tool parameters"
  errors reported by VennDev)
- Normalize streaming Bash args regardless of finish_reason, not only
  when finish_reason is 'tool_calls'
- Broaden isLikelyStructuredObjectLiteral to catch malformed object-shaped
  strings like {command:"pwd"} and {'command':'pwd'} (fixes CR2 from
  Vasanthdev2004)
- Apply blank/object-literal guard to all tools, not just Bash
- Extract duplicated JSON repair suffix combinations into shared constant
- Add 32 isolated unit tests for toolArgumentNormalization

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: skip streaming normalization on finish_reason length

Truncated tool calls (finish_reason: 'length') now preserve the raw
buffer instead of normalizing into executable commands, preventing
incomplete commands from becoming runnable.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: comprehensive tool argument normalization hardening

- Remove all { raw: ... } returns that caused InputValidationError with
  z.strictObject schemas — return {} instead for clean Zod errors
- Extend normalizeAtStop buffering to all mapped tools (Read, Write,
  Edit, Glob, Grep) so streaming paths also get normalized
- Make repairPossiblyTruncatedObjectJson generic — repair any valid
  JSON object, not just ones with a command field
- Export hasToolFieldMapping for streaming normalizeAtStop decision
- Skip normalization on finish_reason: length to preserve raw truncated
  buffer
- Update all test expectations to match new behavior

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-06 22:08:45 +08:00

173 lines
5.3 KiB
TypeScript

import { afterEach, beforeEach, describe, expect, test } from 'bun:test'
import {
parseProviderFlag,
applyProviderFlag,
applyProviderFlagFromArgs,
VALID_PROVIDERS,
} from './providerFlag.js'
const originalEnv = { ...process.env }
const RESET_KEYS = [
'CLAUDE_CODE_USE_OPENAI',
'CLAUDE_CODE_USE_GEMINI',
'CLAUDE_CODE_USE_GITHUB',
'CLAUDE_CODE_USE_BEDROCK',
'CLAUDE_CODE_USE_VERTEX',
'OPENAI_BASE_URL',
'OPENAI_API_KEY',
'OPENAI_MODEL',
'GEMINI_MODEL',
] as const
beforeEach(() => {
for (const key of RESET_KEYS) {
delete process.env[key]
}
})
afterEach(() => {
for (const key of RESET_KEYS) {
if (originalEnv[key] === undefined) delete process.env[key]
else process.env[key] = originalEnv[key]
}
})
// --- parseProviderFlag ---
describe('parseProviderFlag', () => {
test('returns provider name when --provider flag present', () => {
expect(parseProviderFlag(['--provider', 'openai'])).toBe('openai')
})
test('returns provider name with --model alongside', () => {
expect(parseProviderFlag(['--provider', 'gemini', '--model', 'gemini-2.0-flash'])).toBe('gemini')
})
test('returns null when --provider flag absent', () => {
expect(parseProviderFlag(['--model', 'gpt-4o'])).toBeNull()
})
test('returns null for empty args', () => {
expect(parseProviderFlag([])).toBeNull()
})
test('returns null when --provider has no value', () => {
expect(parseProviderFlag(['--provider'])).toBeNull()
})
test('returns null when --provider value starts with --', () => {
expect(parseProviderFlag(['--provider', '--model'])).toBeNull()
})
})
// --- applyProviderFlag ---
describe('applyProviderFlag - anthropic', () => {
test('sets no env vars for anthropic (default)', () => {
const result = applyProviderFlag('anthropic', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_OPENAI).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_GEMINI).toBeUndefined()
})
})
describe('applyProviderFlag - openai', () => {
test('sets CLAUDE_CODE_USE_OPENAI=1', () => {
const result = applyProviderFlag('openai', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_OPENAI).toBe('1')
})
test('sets OPENAI_MODEL when --model is provided', () => {
applyProviderFlag('openai', ['--model', 'gpt-4o'])
expect(process.env.OPENAI_MODEL).toBe('gpt-4o')
})
})
describe('applyProviderFlag - gemini', () => {
test('sets CLAUDE_CODE_USE_GEMINI=1', () => {
const result = applyProviderFlag('gemini', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_GEMINI).toBe('1')
})
test('sets GEMINI_MODEL when --model is provided', () => {
applyProviderFlag('gemini', ['--model', 'gemini-2.0-flash'])
expect(process.env.GEMINI_MODEL).toBe('gemini-2.0-flash')
})
})
describe('applyProviderFlag - github', () => {
test('sets CLAUDE_CODE_USE_GITHUB=1', () => {
const result = applyProviderFlag('github', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_GITHUB).toBe('1')
})
})
describe('applyProviderFlag - bedrock', () => {
test('sets CLAUDE_CODE_USE_BEDROCK=1', () => {
const result = applyProviderFlag('bedrock', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_BEDROCK).toBe('1')
})
})
describe('applyProviderFlag - vertex', () => {
test('sets CLAUDE_CODE_USE_VERTEX=1', () => {
const result = applyProviderFlag('vertex', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_VERTEX).toBe('1')
})
})
describe('applyProviderFlag - ollama', () => {
test('sets CLAUDE_CODE_USE_OPENAI=1 with Ollama base URL', () => {
const result = applyProviderFlag('ollama', [])
expect(result.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_OPENAI).toBe('1')
expect(process.env.OPENAI_BASE_URL).toBe('http://localhost:11434/v1')
expect(process.env.OPENAI_API_KEY).toBe('ollama')
})
test('sets OPENAI_MODEL when --model is provided', () => {
applyProviderFlag('ollama', ['--model', 'llama3.2'])
expect(process.env.OPENAI_MODEL).toBe('llama3.2')
})
test('does not override existing OPENAI_BASE_URL when user set a custom one', () => {
process.env.OPENAI_BASE_URL = 'http://my-ollama:11434/v1'
applyProviderFlag('ollama', [])
expect(process.env.OPENAI_BASE_URL).toBe('http://my-ollama:11434/v1')
})
})
describe('applyProviderFlag - invalid provider', () => {
test('returns error for unknown provider', () => {
const result = applyProviderFlag('unknown-provider', [])
expect(result.error).toContain('unknown-provider')
expect(result.error).toContain(VALID_PROVIDERS.join(', '))
})
})
describe('applyProviderFlagFromArgs', () => {
test('applies ollama provider and model from argv in one step', () => {
const result = applyProviderFlagFromArgs([
'--provider',
'ollama',
'--model',
'qwen2.5:3b',
])
expect(result?.error).toBeUndefined()
expect(process.env.CLAUDE_CODE_USE_OPENAI).toBe('1')
expect(process.env.OPENAI_BASE_URL).toBe('http://localhost:11434/v1')
expect(process.env.OPENAI_MODEL).toBe('qwen2.5:3b')
})
test('returns undefined when --provider is absent', () => {
expect(applyProviderFlagFromArgs(['--model', 'gpt-4o'])).toBeUndefined()
})
})