[Bug]: GPT5 Doesn't Support max_token, instead use max_completion_tokens instead

[zakriyaalisabir]

trafficstars

Opencommit Version

3.2.10

Node Version

v22.14.0

NPM Version

9.8.1

What OS are you seeing the problem on?

Mac

What happened?

Got this error when trying to use model = gpt-5-nano of provider = openai

400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

Expected Behavior

Should work fine.

Current Behavior

open-commit │ ◇ 1 staged files: openapi_config_dev.tf │ ◇ ✖ Failed to generate the commit message BadRequestError3: 400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead. at _APIError.generate (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:63105:14) at OpenAI.makeStatusError (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:62641:22) at OpenAI.makeRequest (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:62684:24) at process.processTicksAndRejections (node:internal/process/task_queues:105:5) at async OpenAiEngine.generateCommitMessage (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:66539:28) at async generateCommitMessageByDiff (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:67373:27) at async generateCommitMessageFromGitDiff (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:67595:25) at async trytm (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:67563:18) at async commit (/Users/zakriyaalisabir/.nvm/versions/node/v22.14.0/lib/node_modules/opencommit/out/cli.cjs:67768:35) { status: 400, headers: { 'access-control-expose-headers': 'X-Request-ID', 'alt-svc': 'h3=":443"; ma=86400', 'cf-cache-status': 'DYNAMIC', 'cf-ray': '96bd9448efb899a6-BKK', connection: 'keep-alive', 'content-length': '245', 'content-type': 'application/json', date: 'Fri, 08 Aug 2025 08:17:46 GMT', 'openai-organization': 'personal-jtddxj', 'openai-processing-ms': '30', 'openai-project': 'proj_eCY4aMVNwQMbxmgQAIUjP8px', 'openai-version': '2020-10-01', server: 'cloudflare', 'set-cookie': '__cf_bm=RRjE3GkDUk5Jies9AZ3oJJCJ5SGHLA1WrIEG19ntHiE-1754641066-1.0.1.1-wJXjZMtnCAbobQxcjTahng_mKK6hiZ1NMxmAJFLM3q7F9WYCUtZPMclstOHoVFKsf1zNTfcXpZ5Rd3dZiKULdrZ.9UP9AbZ16DpRFJPgGjA; path=/; expires=Fri, 08-Aug-25 08:47:46 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None, _cfuvid=dFVNKvQUJJljvr2GLkrs.OQm5lNDFjvXUoDyvP5Tpjg-1754641066665-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None', 'strict-transport-security': 'max-age=31536000; includeSubDomains; preload', 'x-content-type-options': 'nosniff', 'x-envoy-upstream-service-time': '54', 'x-ratelimit-limit-requests': '500', 'x-ratelimit-limit-tokens': '200000', 'x-ratelimit-remaining-requests': '499', 'x-ratelimit-remaining-tokens': '198928', 'x-ratelimit-reset-requests': '120ms', 'x-ratelimit-reset-tokens': '321ms', 'x-request-id': 'req_8e2c19296b32418382b4154d90fdc647' }, request_id: 'req_8e2c19296b32418382b4154d90fdc647', error: { message: "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.", type: 'invalid_request_error', param: 'max_tokens', code: 'unsupported_parameter' }, code: 'unsupported_parameter', param: 'max_tokens', type: 'invalid_request_error' } │ └ ✖ 400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

Possible Solution

No response

Steps to Reproduce

No response

Relevant log output