Calling GitHub Copilot with `gpt-5.*` / `o*` models (e.g.
`github_copilot/gpt-5.4`, `github_copilot/gpt-5.4-mini`) failed with a
chain of misleading errors:
1. `Unsupported parameter: 'max_tokens' is not supported with this
model. Use 'max_completion_tokens' instead.`
2. `model "gpt-5.4-mini" is not accessible via the /chat/completions
endpoint` (`unsupported_api_for_model`).
3. `The requested model is not supported.` (`model_not_supported`)
even after routing to /responses.
Root causes (each one masked the next):
* The `github_copilot` ProviderSpec did not opt into
`supports_max_completion_tokens`, so `_build_kwargs` always sent the
legacy `max_tokens` parameter that GPT-5/o-series reject.
* `_should_use_responses_api` was hard-gated to
`spec.name == "openai"` plus a direct-OpenAI base URL, so the
GitHub Copilot backend always went through /chat/completions even
for models the Copilot gateway exposes only via /responses
(e.g. `gpt-5.4-mini`).
* When /responses did fail on github_copilot, the existing
"compatibility marker" heuristic silently fell back to
/chat/completions — which can never succeed for these models — so
the real upstream error was hidden.
* `_build_responses_body` did not honour `spec.strip_model_prefix`,
so the request body sent `model="github_copilot/gpt-5.4-mini"`
(with the routing prefix), which the Copilot gateway rejects with
`model_not_supported`. (`_build_kwargs` already stripped it; this
branch was missed.)
Fix:
* registry.py: set `supports_max_completion_tokens=True` on the
`github_copilot` spec so requests use `max_completion_tokens`.
* openai_compat_provider.py:
- `_should_use_responses_api` now also allows the
`github_copilot` spec, and skips the direct-OpenAI base check
for it (the Copilot gateway is its own base URL).
- `_build_responses_body` now strips the model routing prefix
when `spec.strip_model_prefix` is set, matching `_build_kwargs`.
- `chat` / `chat_stream` no longer fall back from /responses to
/chat/completions on the `github_copilot` spec: the fallback
cannot succeed for GPT-5/o-series and would mask the real
gateway error.
Tests:
* tests/cli/test_commands.py: switched the
`test_github_copilot_provider_refreshes_client_api_key_before_chat`
fixture model from `gpt-5.1` to `gpt-4` so it continues to exercise
the /chat/completions code path it was designed for (gpt-5.1 now
correctly routes to /responses on github_copilot).
* `pytest tests/providers/ tests/cli/test_commands.py` — 314 passed.
* Verified end-to-end against the live Copilot gateway with both
`github_copilot/gpt-5.4` and `github_copilot/gpt-5.4-mini`.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Replace platform-specific shell=True logic with shutil.which('npm') to
resolve the full path to the npm executable. This is cleaner because:
- No shell=True needed (safer, no shell injection risk)
- No platform-specific branching (sys.platform checks removed)
- Works identically on Windows, macOS, and Linux
- shutil.which() resolves npm.cmd on Windows automatically
The npm path check that already existed in _get_bridge_dir() is now
reused as the resolved path for subprocess calls. The same pattern is
applied to channels_login().
On Windows, npm is installed as npm.cmd (a batch script), not a direct
executable. When subprocess.run() is called with a list like
['npm', 'install'] without shell=True, Python's CreateProcess cannot
locate npm.cmd, resulting in:
FileNotFoundError: [WinError 2] The system cannot find the file specified
This fix adds a sys.platform == 'win32' check before each npm subprocess
call. On Windows, it uses shell=True with a string command so the shell
can resolve npm.cmd. On other platforms, the original list-based call is
preserved unchanged.
Affected locations:
- _get_bridge_dir(): npm install, npm run build
- channels_login(): npm start
No behavioral change on Linux/macOS.
GitHub Copilot's API returns tool_calls split across multiple choices:
- choices[0]: content only (tool_calls=null)
- choices[1]: tool_calls only (content=null)
The existing _parse_response only inspected choices[0], so tool_calls
were silently lost, causing the agent to never execute tools when using
github_copilot/ models.
This fix scans all choices and merges tool_calls + content, so
providers that return multi-choice responses work correctly.
Single-choice providers (OpenAI, Anthropic, etc.) are unaffected since
the loop over one choice is equivalent to the original code.
Peixian GongandCopilot
