[Bug]: max_completion_tokens error on OpenAI Responses compatible API

[sj0n]

Bug Description

ERROR: POST https://aihubmix.com/v1/responses

Caused by:
    400 Bad Request Reason: {"error":{"message":"Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

I saw there was already a merged fix for OpenAI-compatible API but is not sure if the fix is also applied for Responses API.

Steps to Reproduce

1. Setup api url on OpenAIResponsesCompatible.
2. Set the model to gpt-5.5-free or other gpt free models.

Expected Behavior

The API returns response from my prompt.

Actual Behavior

ERROR: POST https://aihubmix.com/v1/responses

Caused by:
    400 Bad Request Reason: {"error":{"message":"Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

Forge Version

2.12.16

Operating System & Version

WSL on Windows 11

AI Provider

Other

Model

gpt-5.5-free

Installation Method

curl -fsSL https://forgecode.dev/cli | sh

Configuration

"$schema" = "https://forgecode.dev/schema.json"

max_search_lines = 1000
max_search_result_bytes = 10240
max_fetch_chars = 50000
max_stdout_prefix_lines = 100
max_stdout_suffix_lines = 100
max_stdout_line_chars = 500
max_line_chars = 2000
max_read_lines = 2000
max_file_read_batch_size = 50
max_file_size_bytes = 104857600
max_image_size_bytes = 262144
tool_timeout_secs = 300
auto_open_dump = false
max_conversations = 100
max_sem_search_results = 100
sem_search_top_k = 10
services_url = "https://api.forgecode.dev/"
max_extensions = 15
max_parallel_file_reads = 64
model_cache_ttl_secs = 604800
use_forge_committer = true
max_commit_count = 20
top_p = 0.8
top_k = 30
max_tokens = 20480
max_tool_failure_per_turn = 3
max_requests_per_turn = 100
restricted = false
tool_supported = true
currency_symbol = "$"
currency_conversion_rate = 1.0
verify_todos = true
use_text_patch_fallback = false
research_subagent = false
subagents = true
merge_system_messages = false

[retry]
initial_backoff_ms = 200
min_delay_ms = 1000
backoff_factor = 2
max_attempts = 8
status_codes = [
    429,
    500,
    502,
    503,
    504,
    408,
    522,
    520,
    529,
]
suppress_errors = false

[http]
connect_timeout_secs = 30
read_timeout_secs = 900
pool_idle_timeout_secs = 90
pool_max_idle_per_host = 5
max_redirects = 10
hickory = false
tls_backend = "default"
adaptive_window = true
keep_alive_interval_secs = 60
keep_alive_timeout_secs = 10
keep_alive_while_idle = true
accept_invalid_certs = false

[session]
provider_id = "openai_responses_compatible"
model_id = "gpt-5.5-free"

[updates]
frequency = "daily"
auto_update = true

[compact]
retention_window = 6
eviction_window = 0.2
max_tokens = 2000
token_threshold = 100000
message_threshold = 200
on_turn_end = false

[reasoning]
effort = "none"
enabled = true